feat: add real-time timing breakdown logging for consolidation

- Log timing breakdown after each batch (every 50 memories by default)
- Log timing breakdown in progress logs (every 10 memories)
- Shows recall, llm, embedding, db_write times incrementally
- Includes avg time per memory for quick diagnosis
- Helps diagnose performance issues in production without waiting for job completion

Example output (every 10 memories):
[CONSOLIDATION] bank=xyz progress: 10/39303 memories processed | recall=2.09s, llm=11.03s, embedding=0.48s, db_write=0.02s

Example output (per batch):
[CONSOLIDATION] bank=xyz batch 1/50 memories: recall=7.3s, llm=57.5s, embedding=2.0s, db_write=0.09s | avg=1.3s/memory

.env.example

@@ -2,10 +2,10 @@
 # Copy this file to .env and fill in your values
 
 # LLM Configuration (Required)
-# Supported providers: openai, groq, ollama, gemini, anthropic, lmstudio, vertexai, minimax
+# Supported providers: openai, groq, ollama, gemini, anthropic, lmstudio
 HINDSIGHT_API_LLM_PROVIDER=openai
 HINDSIGHT_API_LLM_API_KEY=your-api-key-here
-HINDSIGHT_API_LLM_MODEL=gpt-4o-mini
+HINDSIGHT_API_LLM_MODEL=o3-mini
 HINDSIGHT_API_LLM_BASE_URL=https://api.openai.com/v1
 
 # Example: Anthropic Claude configuration
@@ -13,18 +13,6 @@ HINDSIGHT_API_LLM_BASE_URL=https://api.openai.com/v1
 # HINDSIGHT_API_LLM_API_KEY=your-anthropic-api-key
 # HINDSIGHT_API_LLM_MODEL=claude-sonnet-4-20250514
 
-# Example: Google Vertex AI configuration
-# HINDSIGHT_API_LLM_PROVIDER=vertexai
-# HINDSIGHT_API_LLM_MODEL=google/gemini-2.0-flash-001
-# HINDSIGHT_API_LLM_VERTEXAI_PROJECT_ID=your-gcp-project-id
-# HINDSIGHT_API_LLM_VERTEXAI_REGION=us-central1
-# HINDSIGHT_API_LLM_VERTEXAI_SERVICE_ACCOUNT_KEY=/path/to/service-account-key.json  # Optional, uses ADC if not set
-
-# Example: MiniMax configuration (1M context window)
-# HINDSIGHT_API_LLM_PROVIDER=minimax
-# HINDSIGHT_API_LLM_API_KEY=your-minimax-api-key
-# HINDSIGHT_API_LLM_MODEL=MiniMax-M2.7
-
 # Example: LM Studio local configuration (Qwen 2.5 32B recommended)
 # HINDSIGHT_API_LLM_PROVIDER=lmstudio
 # HINDSIGHT_API_LLM_API_KEY=lmstudio
@@ -36,22 +24,10 @@ HINDSIGHT_API_HOST=0.0.0.0
 HINDSIGHT_API_PORT=8888
 HINDSIGHT_API_LOG_LEVEL=info
 
-# Base Path / Reverse Proxy Support (Optional)
-# Set these when deploying behind a reverse proxy with path-based routing
-# Example: To deploy at example.com/hindsight/, set both to "/hindsight"
-# HINDSIGHT_API_BASE_PATH=/hindsight
-# NEXT_PUBLIC_BASE_PATH=/hindsight
-
 # Database (Optional - uses embedded pg0 by default)
 # HINDSIGHT_API_DATABASE_URL=postgresql://user:pass@host:5432/db
 # HINDSIGHT_API_DATABASE_SCHEMA=public  # PostgreSQL schema name (default: public)
 
-# Vector Extension (Optional - uses pgvector by default)
-# Options: "pgvector" (default), "vchord", "pgvectorscale" (DiskANN)
-# HINDSIGHT_API_VECTOR_EXTENSION=pgvector
-# For Azure PostgreSQL with DiskANN:
-# HINDSIGHT_API_VECTOR_EXTENSION=pgvectorscale  # Auto-detects pg_diskann on Azure
-
 # Embeddings Configuration (Optional - uses local by default)
 # Provider: "local" (default) or "tei" (HuggingFace Text Embeddings Inference)
 # HINDSIGHT_API_EMBEDDINGS_PROVIDER=local
@@ -67,18 +43,3 @@ HINDSIGHT_API_LOG_LEVEL=info
 # HINDSIGHT_API_RERANKER_LOCAL_MODEL=cross-encoder/ms-marco-MiniLM-L-6-v2
 # For TEI provider:
 # HINDSIGHT_API_RERANKER_TEI_URL=http://localhost:8081
-
-# Observability & Tracing (Optional - disabled by default)
-# Enable OpenTelemetry tracing for LLM calls (GenAI semantic conventions)
-# HINDSIGHT_API_OTEL_TRACES_ENABLED=true
-#
-# Local development with Grafana LGTM stack (recommended - see scripts/dev/grafana/README.md)
-# HINDSIGHT_API_OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318
-#
-# Cloud backends (Grafana Cloud, Langfuse, DataDog, etc.)
-# HINDSIGHT_API_OTEL_EXPORTER_OTLP_ENDPOINT=https://your-backend-url
-# HINDSIGHT_API_OTEL_EXPORTER_OTLP_HEADERS="Authorization=Bearer your-token"
-#
-# Custom service name and environment (optional, defaults: hindsight-api, development)
-# HINDSIGHT_API_OTEL_SERVICE_NAME=hindsight-production
-# HINDSIGHT_API_OTEL_DEPLOYMENT_ENVIRONMENT=production

.github/dependabot.yml

@@ -1,6 +0,0 @@
-version: 2
-updates:
-  - package-ecosystem: "github-actions"
-    directory: "/"
-    schedule:
-      interval: "weekly"

.github/workflows/deploy-docs.yml

@@ -21,20 +21,17 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
-      - uses: actions/setup-node@v6
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
         with:
           node-version: 20
           cache: npm
           cache-dependency-path: package-lock.json
-      - uses: astral-sh/setup-uv@v7
+      - uses: astral-sh/setup-uv@v4
       - run: npm ci --workspace=hindsight-docs
       - run: uv run generate-llms-full
       - run: npm run build --workspace=hindsight-docs
-        env:
-          UMAMI_URL: https://analytics.hindsight.vectorize.io
-          UMAMI_WEBSITE_ID: ${{ secrets.UMAMI_WEBSITE_ID }}
-      - uses: actions/upload-pages-artifact@v4
+      - uses: actions/upload-pages-artifact@v3
         with:
           path: hindsight-docs/build
   deploy:

.github/workflows/release-integration.yml

@@ -1,99 +0,0 @@
-name: Release Integration
-
-on:
-  push:
-    tags:
-      - 'integrations/**'
-
-jobs:
-  publish:
-    runs-on: ubuntu-latest
-    permissions:
-      id-token: write  # for PyPI trusted publishing
-
-    steps:
-    - uses: actions/checkout@v6
-
-    - name: Extract integration info
-      id: info
-      run: |
-        # refs/tags/integrations/litellm/v0.1.0 → integration=litellm, version=0.1.0
-        TAG="${GITHUB_REF#refs/tags/}"
-        INTEGRATION=$(echo "$TAG" | cut -d'/' -f2)
-        VERSION=$(echo "$TAG" | cut -d'/' -f3 | sed 's/^v//')
-        echo "integration=$INTEGRATION" >> $GITHUB_OUTPUT
-        echo "version=$VERSION" >> $GITHUB_OUTPUT
-        echo "tag=$TAG" >> $GITHUB_OUTPUT
-        echo "Integration: $INTEGRATION, Version: $VERSION"
-
-    - name: Detect integration type
-      id: type
-      run: |
-        if [ -f "hindsight-integrations/${{ steps.info.outputs.integration }}/pyproject.toml" ]; then
-          echo "type=python" >> $GITHUB_OUTPUT
-        else
-          echo "type=typescript" >> $GITHUB_OUTPUT
-        fi
-
-    # ── Python integrations (litellm, pydantic-ai, crewai) ──────────────────
-
-    - name: Install uv
-      if: steps.type.outputs.type == 'python'
-      uses: astral-sh/setup-uv@v7
-      with:
-        enable-cache: true
-
-    - name: Set up Python
-      if: steps.type.outputs.type == 'python'
-      uses: actions/setup-python@v5
-      with:
-        python-version-file: ".python-version"
-
-    - name: Build Python package
-      if: steps.type.outputs.type == 'python'
-      working-directory: ./hindsight-integrations/${{ steps.info.outputs.integration }}
-      run: uv build --out-dir dist
-
-    - name: Publish Python package to PyPI
-      if: steps.type.outputs.type == 'python'
-      uses: pypa/gh-action-pypi-publish@release/v1
-      with:
-        packages-dir: ./hindsight-integrations/${{ steps.info.outputs.integration }}/dist
-        skip-existing: true
-
-    # ── TypeScript integrations (ai-sdk, chat, openclaw) ────────────────────
-
-    - name: Set up Node.js
-      if: steps.type.outputs.type == 'typescript'
-      uses: actions/setup-node@v6
-      with:
-        node-version: '22'
-        registry-url: 'https://registry.npmjs.org'
-
-    - name: Install dependencies
-      if: steps.type.outputs.type == 'typescript'
-      working-directory: ./hindsight-integrations/${{ steps.info.outputs.integration }}
-      run: npm ci
-
-    - name: Build TypeScript package
-      if: steps.type.outputs.type == 'typescript'
-      working-directory: ./hindsight-integrations/${{ steps.info.outputs.integration }}
-      run: npm run build
-
-    - name: Publish TypeScript package to npm
-      if: steps.type.outputs.type == 'typescript'
-      working-directory: ./hindsight-integrations/${{ steps.info.outputs.integration }}
-      run: |
-        set +e
-        OUTPUT=$(npm publish --access public 2>&1)
-        EXIT_CODE=$?
-        echo "$OUTPUT"
-        if [ $EXIT_CODE -ne 0 ]; then
-          if echo "$OUTPUT" | grep -q "cannot publish over"; then
-            echo "Package version already published, skipping..."
-            exit 0
-          fi
-          exit $EXIT_CODE
-        fi
-      env:
-        NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}

.github/workflows/release.yml

@@ -13,15 +13,15 @@ jobs:
       id-token: write
 
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
 
     - name: Install uv
-      uses: astral-sh/setup-uv@v7
+      uses: astral-sh/setup-uv@v5
       with:
         enable-cache: true
 
     - name: Set up Python
-      uses: actions/setup-python@v6
+      uses: actions/setup-python@v5
       with:
         python-version-file: ".python-version"
 
@@ -30,39 +30,29 @@ jobs:
       working-directory: ./hindsight-clients/python
       run: uv build --out-dir dist
 
-    - name: Build hindsight-api-slim
-      working-directory: ./hindsight-api-slim
-      run: uv build --out-dir dist
-
     - name: Build hindsight-api
       working-directory: ./hindsight-api
       run: uv build --out-dir dist
 
     - name: Build hindsight-all
-      working-directory: ./hindsight-all
+      working-directory: ./hindsight
       run: uv build --out-dir dist
 
-    - name: Build hindsight-all-slim
-      working-directory: ./hindsight-all-slim
+    - name: Build hindsight-litellm
+      working-directory: ./hindsight-integrations/litellm
       run: uv build --out-dir dist
 
     - name: Build hindsight-embed
       working-directory: ./hindsight-embed
       run: uv build --out-dir dist
 
-    # Publish in order (client and api-slim first, then api/all wrappers which depend on them)
+    # Publish in order (client and api first, then hindsight-all which depends on them)
     - name: Publish hindsight-client to PyPI
       uses: pypa/gh-action-pypi-publish@release/v1
       with:
         packages-dir: ./hindsight-clients/python/dist
         skip-existing: true
 
-    - name: Publish hindsight-api-slim to PyPI
-      uses: pypa/gh-action-pypi-publish@release/v1
-      with:
-        packages-dir: ./hindsight-api-slim/dist
-        skip-existing: true
-
     - name: Publish hindsight-api to PyPI
       uses: pypa/gh-action-pypi-publish@release/v1
       with:
@@ -72,13 +62,13 @@ jobs:
     - name: Publish hindsight-all to PyPI
       uses: pypa/gh-action-pypi-publish@release/v1
       with:
-        packages-dir: ./hindsight-all/dist
+        packages-dir: ./hindsight/dist
         skip-existing: true
 
-    - name: Publish hindsight-all-slim to PyPI
+    - name: Publish hindsight-litellm to PyPI
       uses: pypa/gh-action-pypi-publish@release/v1
       with:
-        packages-dir: ./hindsight-all-slim/dist
+        packages-dir: ./hindsight-integrations/litellm/dist
         skip-existing: true
 
     - name: Publish hindsight-embed to PyPI
@@ -89,15 +79,14 @@ jobs:
 
     # Upload artifacts for GitHub release
     - name: Upload artifacts
-      uses: actions/upload-artifact@v7
+      uses: actions/upload-artifact@v4
       with:
         name: python-packages
         path: |
           hindsight-clients/python/dist/*
-          hindsight-api-slim/dist/*
           hindsight-api/dist/*
-          hindsight-all/dist/*
-          hindsight-all-slim/dist/*
+          hindsight/dist/*
+          hindsight-integrations/litellm/dist/*
           hindsight-embed/dist/*
         retention-days: 1
 
@@ -106,10 +95,10 @@ jobs:
     environment: npm
 
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
 
     - name: Set up Node.js
-      uses: actions/setup-node@v6
+      uses: actions/setup-node@v4
       with:
         node-version: '20'
         registry-url: 'https://registry.npmjs.org'
@@ -144,7 +133,7 @@ jobs:
       run: npm pack
 
     - name: Upload artifacts
-      uses: actions/upload-artifact@v7
+      uses: actions/upload-artifact@v4
       with:
         name: typescript-client
         path: hindsight-clients/typescript/*.tgz
@@ -155,10 +144,10 @@ jobs:
     environment: npm
 
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
 
     - name: Set up Node.js
-      uses: actions/setup-node@v6
+      uses: actions/setup-node@v4
       with:
         node-version: '20'
         registry-url: 'https://registry.npmjs.org'
@@ -181,14 +170,11 @@ jobs:
     - name: Build
       run: npm run build --workspace=hindsight-control-plane
 
-    - name: Verify standalone build
-      run: test -f hindsight-control-plane/standalone/server.js || (echo 'standalone/server.js missing - build failed' && exit 1)
-
     - name: Publish to npm
       working-directory: ./hindsight-control-plane
       run: |
         set +e
-        OUTPUT=$(npm publish --access public --ignore-scripts 2>&1)
+        OUTPUT=$(npm publish --access public 2>&1)
         EXIT_CODE=$?
         echo "$OUTPUT"
         if [ $EXIT_CODE -ne 0 ]; then
@@ -206,7 +192,7 @@ jobs:
       run: npm pack
 
     - name: Upload artifacts
-      uses: actions/upload-artifact@v7
+      uses: actions/upload-artifact@v4
       with:
         name: control-plane
         path: hindsight-control-plane/*.tgz
@@ -229,13 +215,9 @@ jobs:
             target: aarch64-apple-darwin
             artifact_name: hindsight
             asset_name: hindsight-darwin-arm64
-          - os: ubuntu-24.04-arm
-            target: aarch64-unknown-linux-gnu
-            artifact_name: hindsight
-            asset_name: hindsight-linux-arm64
 
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
 
     - name: Install Rust
       uses: dtolnay/rust-toolchain@stable
@@ -253,14 +235,13 @@ jobs:
         chmod +x artifacts/${{ matrix.asset_name }}
 
     - name: Upload artifacts
-      uses: actions/upload-artifact@v7
+      uses: actions/upload-artifact@v4
       with:
         name: rust-cli-${{ matrix.asset_name }}
         path: artifacts/${{ matrix.asset_name }}
         retention-days: 1
 
   release-docker-images:
-    name: Release Docker (${{ matrix.image_name }}${{ matrix.tag_suffix }})
     runs-on: ubuntu-latest
     permissions:
       contents: read
@@ -270,31 +251,13 @@ jobs:
         include:
           - target: api-only
             image_name: hindsight-api
-            tag_suffix: ""
-            build_args: ""
-          - target: api-only
-            image_name: hindsight-api
-            tag_suffix: "-slim"
-            build_args: |
-              INCLUDE_LOCAL_MODELS=false
-              PRELOAD_ML_MODELS=false
           - target: cp-only
             image_name: hindsight-control-plane
-            tag_suffix: ""
-            build_args: ""
           - target: standalone
             image_name: hindsight
-            tag_suffix: ""
-            build_args: ""
-          - target: standalone
-            image_name: hindsight
-            tag_suffix: "-slim"
-            build_args: |
-              INCLUDE_LOCAL_MODELS=false
-              PRELOAD_ML_MODELS=false
 
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
 
     - name: Free Disk Space
       uses: jlumbroso/free-disk-space@main
@@ -308,13 +271,13 @@ jobs:
         swap-storage: true
 
     - name: Set up QEMU
-      uses: docker/setup-qemu-action@v4
+      uses: docker/setup-qemu-action@v3
 
     - name: Set up Docker Buildx
-      uses: docker/setup-buildx-action@v4
+      uses: docker/setup-buildx-action@v3
 
     - name: Log in to GitHub Container Registry
-      uses: docker/login-action@v4
+      uses: docker/login-action@v3
       with:
         registry: ghcr.io
         username: ${{ github.actor }}
@@ -326,12 +289,9 @@ jobs:
 
     - name: Extract metadata for release tags
       id: meta
-      uses: docker/metadata-action@v6
+      uses: docker/metadata-action@v5
       with:
         images: ghcr.io/${{ github.repository_owner }}/${{ matrix.image_name }}
-        flavor: |
-          latest=auto
-          suffix=${{ matrix.tag_suffix }}
         tags: |
           type=semver,pattern={{version}},value=${{ steps.get_version.outputs.VERSION }}
           type=semver,pattern={{major}}.{{minor}},value=${{ steps.get_version.outputs.VERSION }}
@@ -342,7 +302,7 @@ jobs:
     # # Step 1: Build for local testing (single platform, no push)
     # # This creates an identical image to what will be released, just for one platform
     # - name: Build image for testing
-    #   uses: docker/build-push-action@v7
+    #   uses: docker/build-push-action@v6
     #   with:
     #     context: .
     #     file: docker/standalone/Dockerfile
@@ -357,16 +317,15 @@ jobs:
     # - name: Smoke test - verify container starts
     #   env:
     #     GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-    #   run: ./docker/test-image.sh "${{ matrix.image_name }}:test" "${{ matrix.target }}"
+    #   run: ./scripts/docker-smoke-test.sh "${{ matrix.image_name }}:test" "${{ matrix.target }}"
 
     # Build multi-platform and push to release tags
     - name: Build and push release images
-      uses: docker/build-push-action@v7
+      uses: docker/build-push-action@v6
       with:
         context: .
         file: docker/standalone/Dockerfile
         target: ${{ matrix.target }}
-        build-args: ${{ matrix.build_args }}
         push: true
         platforms: linux/amd64,linux/arm64
         tags: ${{ steps.meta.outputs.tags }}
@@ -379,7 +338,7 @@ jobs:
       packages: write
 
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
 
     - name: Install Helm
       uses: azure/setup-helm@v4
@@ -399,7 +358,7 @@ jobs:
       run: helm push helm-packages/*.tgz oci://ghcr.io/${{ github.repository_owner }}/charts
 
     - name: Upload artifacts
-      uses: actions/upload-artifact@v7
+      uses: actions/upload-artifact@v4
       with:
         name: helm-chart
         path: helm-packages/*.tgz
@@ -412,50 +371,50 @@ jobs:
       contents: write
 
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
 
     - name: Extract version from tag
       id: get_version
       run: echo "VERSION=${GITHUB_REF#refs/tags/v}" >> $GITHUB_OUTPUT
 
     - name: Download Python packages
-      uses: actions/download-artifact@v8
+      uses: actions/download-artifact@v4
       with:
         name: python-packages
         path: ./artifacts/python-packages
 
     - name: Download TypeScript client
-      uses: actions/download-artifact@v8
+      uses: actions/download-artifact@v4
       with:
         name: typescript-client
         path: ./artifacts/typescript-client
 
     - name: Download Control Plane
-      uses: actions/download-artifact@v8
+      uses: actions/download-artifact@v4
       with:
         name: control-plane
         path: ./artifacts/control-plane
 
     - name: Download Rust CLI (Linux)
-      uses: actions/download-artifact@v8
+      uses: actions/download-artifact@v4
       with:
         name: rust-cli-hindsight-linux-amd64
         path: ./artifacts/rust-cli-linux
 
     - name: Download Rust CLI (macOS Intel)
-      uses: actions/download-artifact@v8
+      uses: actions/download-artifact@v4
       with:
         name: rust-cli-hindsight-darwin-amd64
         path: ./artifacts/rust-cli-darwin-amd64
 
     - name: Download Rust CLI (macOS ARM)
-      uses: actions/download-artifact@v8
+      uses: actions/download-artifact@v4
       with:
         name: rust-cli-hindsight-darwin-arm64
         path: ./artifacts/rust-cli-darwin-arm64
 
     - name: Download Helm chart
-      uses: actions/download-artifact@v8
+      uses: actions/download-artifact@v4
       with:
         name: helm-chart
         path: ./artifacts/helm-chart
@@ -465,10 +424,9 @@ jobs:
         mkdir -p release-assets
         # Python packages
         cp artifacts/python-packages/hindsight-clients/python/dist/* release-assets/ || true
-        cp artifacts/python-packages/hindsight-api-slim/dist/* release-assets/ || true
         cp artifacts/python-packages/hindsight-api/dist/* release-assets/ || true
-        cp artifacts/python-packages/hindsight-all/dist/* release-assets/ || true
-        cp artifacts/python-packages/hindsight-all-slim/dist/* release-assets/ || true
+        cp artifacts/python-packages/hindsight/dist/* release-assets/ || true
+        cp artifacts/python-packages/hindsight-integrations/litellm/dist/* release-assets/ || true
         cp artifacts/python-packages/hindsight-embed/dist/* release-assets/ || true
         # TypeScript client
         cp artifacts/typescript-client/*.tgz release-assets/ || true

.gitignore

@@ -46,7 +46,6 @@ hindsight-docs/static/llms-full.txt
 hindsight-dev/benchmarks/locomo/results/
 hindsight-dev/benchmarks/longmemeval/results/
 hindsight-dev/benchmarks/consolidation/results/
-hindsight-dev/benchmarks/perf/results/
 benchmarks/results/
 hindsight-cli/target
 hindsight-clients/rust/target
@@ -54,6 +53,4 @@ hindsight-clients/rust/target
 whats-next.md
 TASK.md
 # Changelog is now tracked in hindsight-docs/src/pages/changelog.md
-# CHANGELOG.md
-
-blog-post*
+# CHANGELOG.md

CLAUDE.md

@@ -17,20 +17,20 @@ Hindsight is an agent memory system that provides long-term memory for AI agents
 ./scripts/dev/start-api.sh
 
 # Run all tests (parallelized with pytest-xdist)
-cd hindsight-api-slim && uv run pytest tests/
+cd hindsight-api && uv run pytest tests/
 
 # Run specific test file
-cd hindsight-api-slim && uv run pytest tests/test_http_api_integration.py -v
+cd hindsight-api && uv run pytest tests/test_http_api_integration.py -v
 
 # Run single test function
-cd hindsight-api-slim && uv run pytest tests/test_retain.py::test_retain_simple -v
+cd hindsight-api && uv run pytest tests/test_retain.py::test_retain_simple -v
 
 # Lint and format
-cd hindsight-api-slim && uv run ruff check .
-cd hindsight-api-slim && uv run ruff format .
+cd hindsight-api && uv run ruff check .
+cd hindsight-api && uv run ruff format .
 
 # Type checking (uses ty - extremely fast type checker from Astral)
-cd hindsight-api-slim && uv run ty check hindsight_api/
+cd hindsight-api && uv run ty check hindsight_api/
 ```
 
 ### Control Plane (Next.js)
@@ -45,7 +45,6 @@ cd hindsight-control-plane && npm run dev
 ./scripts/dev/start-docs.sh
 ```
 
-
 ### Generating Clients/OpenAPI
 ```bash
 # Regenerate OpenAPI spec after API changes (REQUIRED after changing endpoints)
@@ -57,22 +56,15 @@ cd hindsight-control-plane && npm run dev
 
 ### Benchmarks
 ```bash
-# Accuracy benchmarks
 ./scripts/benchmarks/run-longmemeval.sh
 ./scripts/benchmarks/run-locomo.sh
-
-# Performance benchmarks
-./scripts/benchmarks/run-consolidation.sh
-./scripts/benchmarks/run-retain-perf.sh --document <path>  # Requires API server running
-
-# Results viewer
 ./scripts/benchmarks/start-visualizer.sh  # View results at localhost:8001
 ```
 
 ## Architecture
 
 ### Monorepo Structure
-- **hindsight-api-slim/**: Core FastAPI server with memory engine (Python, uv)
+- **hindsight-api/**: Core FastAPI server with memory engine (Python, uv)
 - **hindsight/**: Embedded Python bundle (hindsight-all package)
 - **hindsight-control-plane/**: Admin UI (Next.js, npm)
 - **hindsight-cli/**: CLI tool (Rust, cargo, uses progenitor for API client)
@@ -81,9 +73,9 @@ cd hindsight-control-plane && npm run dev
 - **hindsight-integrations/**: Framework integrations (LiteLLM, OpenAI)
 - **hindsight-dev/**: Development tools and benchmarks
 
-### Core Engine (hindsight-api-slim/hindsight_api/engine/)
+### Core Engine (hindsight-api/hindsight_api/engine/)
 - `memory_engine.py`: Main orchestrator (~170KB) for retain/recall/reflect operations
-- `llm_wrapper.py`: LLM abstraction supporting OpenAI, Anthropic, Gemini, Groq, MiniMax, Ollama, LM Studio
+- `llm_wrapper.py`: LLM abstraction supporting OpenAI, Anthropic, Gemini, Groq, Ollama, LM Studio
 - `embeddings.py`: Embedding generation (local sentence-transformers or TEI)
 - `cross_encoder.py`: Reranking (local or TEI)
 - `entity_resolver.py`: Entity extraction and normalization
@@ -101,7 +93,7 @@ cd hindsight-control-plane && npm run dev
 - `fusion.py`: Reciprocal rank fusion for combining results
 - `reranking.py`: Cross-encoder reranking
 
-### API Layer (hindsight-api-slim/hindsight_api/api/)
+### API Layer (hindsight-api/hindsight_api/api/)
 - `http.py`: FastAPI HTTP routers (~80KB) for all REST endpoints
 - `mcp.py`: Model Context Protocol server implementation
 
@@ -111,13 +103,13 @@ Main operations:
 - **Reflect**: Disposition-aware reasoning using memories and mental models.
 
 ### Database
-PostgreSQL with pgvector. Schema managed via Alembic migrations in `hindsight-api-slim/hindsight_api/alembic/`. Migrations run automatically on API startup.
+PostgreSQL with pgvector. Schema managed via Alembic migrations in `hindsight-api/hindsight_api/alembic/`. Migrations run automatically on API startup.
 
 Key tables: `banks`, `memory_units`, `documents`, `entities`, `entity_links`
 
 ### Adding Database Migrations
 
-1. **Create a new migration file** in `hindsight-api-slim/hindsight_api/alembic/versions/`:
+1. **Create a new migration file** in `hindsight-api/hindsight_api/alembic/versions/`:
    - File name format: `<revision_id>_<description>.py` (e.g., `f1a2b3c4d5e6_add_new_index.py`)
    - Use a unique hex revision ID (12 chars)
    - Set `down_revision` to the previous migration's revision ID
@@ -154,7 +146,7 @@ Key tables: `banks`, `memory_units`, `documents`, `entities`, `entity_links`
 
 3. **Run migrations locally**:
    ```bash
-   # Set database URL and run migrations for the base schema plus all tenants
+   # Set database URL and run migrations
    uv run hindsight-admin run-db-migration
 
    # Run on a specific tenant schema
@@ -245,61 +237,26 @@ def process(data: UserData) -> str:
 
 ### Adding New API Configuration Flags
 
-Configuration follows a hierarchical system: **Global (env vars) → Tenant (via extension) → Bank (database)**.
+When adding a new environment variable configuration:
 
-Fields must be categorized as either **hierarchical** (can be overridden per-tenant/bank) or **static** (server-level only).
-
-#### Adding a New Configuration Field
-
-1. **config.py** (`hindsight-api-slim/hindsight_api/config.py`):
-   - Add `ENV_*` constant for the environment variable name (e.g., `ENV_MY_SETTING = "HINDSIGHT_API_MY_SETTING"`)
+1. **config.py** (`hindsight-api/hindsight_api/config.py`):
+   - Add `ENV_*` constant for the environment variable name
    - Add `DEFAULT_*` constant for the default value
-   - Add field to `HindsightConfig` dataclass with type annotation
-   - **Mark as hierarchical or static** by adding to `_HIERARCHICAL_FIELDS` set (hierarchical) or leaving it out (static)
+   - Add field to `HindsightConfig` dataclass
    - Add initialization in `from_env()` method
 
-   ```python
-   # Hierarchical field (can be overridden per-bank)
-   _HIERARCHICAL_FIELDS = {
-       ...,
-       "my_setting",  # Add here for hierarchical
-   }
-
-   # Static field - just don't add to _HIERARCHICAL_FIELDS
-   ```
-
-2. **main.py** (`hindsight-api-slim/hindsight_api/main.py`):
+2. **main.py** (`hindsight-api/hindsight_api/main.py`):
    - Add field to the manual `HindsightConfig()` constructor call (search for "CLI override")
 
-3. **Use hierarchical config in MemoryEngine**:
-   ```python
-   # Config is resolved automatically per bank via ConfigResolver
-   config_dict = await self._config_resolver.get_bank_config(bank_id, context)
-   value = config_dict["my_setting"]
-   ```
-
-4. **Use static config** (non-hierarchical):
+3. **Use the config** in code:
    ```python
    from ...config import get_config
    config = get_config()
-   value = config.my_static_field
+   value = config.your_new_field
    ```
 
-5. **Documentation** (`hindsight-docs/docs/developer/configuration.md`):
+4. **Documentation** (`hindsight-docs/docs/developer/configuration.md`):
    - Add to appropriate section table with Variable, Description, Default
-   - Mark if it's hierarchical (can be overridden per-bank)
-
-#### Hierarchical vs Static Guidelines
-
-**Hierarchical** (per-bank overridable):
-- LLM settings (provider, model, API key, base URL)
-- Operation-specific settings (retain mode, chunk size, etc.)
-- Feature flags that vary by customer/bank
-
-**Static** (server-level only):
-- Infrastructure settings (database URL, port, host)
-- Global limits (max concurrent operations)
-- System-wide feature flags
 
 ## Environment Setup
 
@@ -308,19 +265,18 @@ cp .env.example .env
 # Edit .env with LLM API key
 
 # Python deps
-uv sync --directory hindsight-api-slim/
+uv sync --directory hindsight-api/
 
 # Node deps (uses npm workspaces)
 npm install
 ```
 
 Required env vars:
-- `HINDSIGHT_API_LLM_PROVIDER`: openai, anthropic, gemini, groq, minimax, ollama, lmstudio
+- `HINDSIGHT_API_LLM_PROVIDER`: openai, anthropic, gemini, groq, ollama, lmstudio
 - `HINDSIGHT_API_LLM_API_KEY`: Your API key
-- `HINDSIGHT_API_LLM_MODEL`: Model name (e.g., gpt-4o-mini, claude-sonnet-4-20250514)
+- `HINDSIGHT_API_LLM_MODEL`: Model name (e.g., o3-mini, claude-sonnet-4-20250514)
 
 Optional (uses local models by default):
 - `HINDSIGHT_API_EMBEDDINGS_PROVIDER`: local (default) or tei
 - `HINDSIGHT_API_RERANKER_PROVIDER`: local (default) or tei
 - `HINDSIGHT_API_DATABASE_URL`: External PostgreSQL (uses embedded pg0 by default)
-- `HINDSIGHT_API_ENABLE_BANK_CONFIG_API`: Enable per-bank config API (default: true)

CONTRIBUTING.md

@@ -93,34 +93,6 @@ uv run ty check hindsight_api  # Type check
 3. Run tests to ensure nothing breaks
 4. Submit a PR with a clear description of changes
 
-## Release Process
-
-The project uses `scripts/release.sh` for creating releases. This script automates the entire release workflow:
-
-1. Bumps version in all components (API, clients, CLI, control plane, Helm)
-2. **Regenerates OpenAPI spec and client SDKs** (Python, TypeScript, Rust)
-3. Updates documentation versioning
-4. Creates a commit and git tag
-5. Pushes to GitHub (triggers CI/CD to publish packages)
-
-### Usage
-
-```bash
-./scripts/release.sh <version>
-```
-
-**Example:**
-```bash
-./scripts/release.sh 0.5.0
-```
-
-### Important for Developers
-
-- During development, version bumps in `__init__.py` do NOT require client regeneration
-- Clients are only regenerated during releases
-- Do not manually run `./scripts/generate-clients.sh` unless testing generation changes
-- Client version comments will reflect the API version from the latest release
-
 ## Reporting Issues
 
 Open an issue on GitHub with:

README.md

@@ -2,16 +2,15 @@
 
 ![Hindsight Banner](./hindsight-docs/static/img/hindsight-github-banner.png)
 
-[Documentation](https://hindsight.vectorize.io) • [Paper](https://arxiv.org/abs/2512.12818) • [Cookbook](https://hindsight.vectorize.io/cookbook) • [Hindsight Cloud](https://ui.hindsight.vectorize.io/signup)
+[Documentation](https://hindsight.vectorize.io) • [Paper](https://arxiv.org/abs/2512.12818) • [Cookbook](https://hindsight.vectorize.io/cookbook) • [Hindsight Cloud](https://vectorize.io/hindsight/cloud)
 
 [![CI](https://github.com/vectorize-io/hindsight/actions/workflows/release.yml/badge.svg)](https://github.com/vectorize-io/hindsight/actions/workflows/release.yml)
 [![Slack Community](https://img.shields.io/badge/Slack-Join%20Community-4A154B?logo=slack)](https://join.slack.com/t/hindsight-space/shared_invite/zt-3nhbm4w29-LeSJ5Ixi6j8PdiYOCPlOgg)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 ![PyPI - Downloads](https://img.shields.io/pypi/dm/hindsight-api?label=PyPI)
 ![NPM Downloads](https://img.shields.io/npm/dm/%40vectorize-io%2Fhindsight-client?logoColor=orange&label=NPM&color=blue&link=https%3A%2F%2Fwww.npmjs.com%2Fpackage%2F%40vectorize-io%2Fhindsight-client)
-<br/>
 
-<a href="https://trendshift.io/repositories/15603" target="_blank"><img src="https://trendshift.io/api/badge/repositories/15603" alt="vectorize-io%2Fhindsight | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+
 </div>
 
 ---
@@ -37,57 +36,33 @@ Hindsight is being used in production at Fortune 500 enterprises and by a growin
 
 ## Adding Hindsight to Your AI Agents
 
-The easiest way to use Hindsight with an existing agent is with the LLM Wrapper. You can add memory to your agent with 2 lines of code. That will swap your current LLM client out with the Hindsight wrapper. After that, memories will be stored and retrieved automatically as you make LLM calls.
+The easiest way use Hindsight with an existing agent is with the LLM Wrapper. You can add memory to your agent with 2 lines of code. That will swap your current LLM client out with the Hindsight wrapper. After that, memories will be stored and retrieved automatically as you make LLM calls.
 
 If you need more control over how and when your agent stores and recalls memories, there's also a simple API you can integrate with using the SDKs or directly via HTTP.
 
 ![Hindsight Banner](./hindsight-docs/static/img/migration-code.png)
 
----
-
-> 🤖 **Using a coding agent?** Install the Hindsight documentation skill for instant access to docs while you code:
-> ```bash
-> npx skills add https://github.com/vectorize-io/hindsight --skill hindsight-docs
-> ```
-> Works with Claude Code, Cursor, and other AI coding assistants.
-
----
-
 
 ## Quick Start
 
 ### Docker (recommended)
 
 ```bash
-export OPENAI_API_KEY=sk-xxx
+export OPENAI_API_KEY=your-key
 
 docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
   -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
+  -e HINDSIGHT_API_LLM_MODEL=o3-mini \
   -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
   ghcr.io/vectorize-io/hindsight:latest
 ```
 
->API: http://localhost:8888
->UI: http://localhost:9999
+You can modify the LLM provider by setting `HINDSIGHT_API_LLM_PROVIDER`. Valid options are `openai`, `anthropic`, `gemini`, `groq`, `ollama`, and `lmstudio`. The documentation provides more details on [supported models](https://hindsight.vectorize.io/developer/models).
 
-You can modify the LLM provider by setting `HINDSIGHT_API_LLM_PROVIDER`. Valid options are `openai`, `anthropic`, `gemini`, `groq`, `ollama`, `lmstudio`, and `minimax`. The documentation provides more details on [supported models](https://hindsight.vectorize.io/developer/models).
+API: http://localhost:8888  
+UI: http://localhost:9999
 
-
-
-### Docker (external PostgreSQL)
-
-```bash
-export OPENAI_API_KEY=sk-xxx
-export HINDSIGHT_DB_PASSWORD=choose-a-password
-cd docker/docker-compose
-docker compose up 
-```
-
-
->API: http://localhost:8888
->UI: http://localhost:9999
-
-### Client
+Install client:
 
 ```bash
 pip install hindsight-client -U
@@ -95,7 +70,7 @@ pip install hindsight-client -U
 npm install @vectorize-io/hindsight-client
 ```
 
-#### Python
+Python example:
 
 ```python
 from hindsight_client import Hindsight
@@ -112,29 +87,7 @@ client.recall(bank_id="my-bank", query="What does Alice do?")
 client.reflect(bank_id="my-bank", query="Tell me about Alice")
 ```
 
-#### Node.js / TypeScript
-
-```bash
-npm install @vectorize-io/hindsight-client
-```
-
-```javascript
-const { HindsightClient } = require('@vectorize-io/hindsight-client');
-
-const main = async () => {
-  const client = new HindsightClient({ baseUrl: 'http://localhost:8888' });
-
-  await client.retain('my-bank', 'Alice loves hiking in Yosemite');
-
-  const results = await client.recall('my-bank', 'What does Alice like?');
-  console.log(results);
-}
-
-main();
-```
-
-
-### Python Embedded (no server required)
+### Python (embedded, no Docker)
 
 ```bash
 pip install hindsight-all -U
@@ -154,6 +107,20 @@ with HindsightServer(
     results = client.recall(bank_id="my-bank", query="Where does Alice work?")
 ```
 
+### Node.js / TypeScript
+
+```bash
+npm install @vectorize-io/hindsight-client
+```
+
+```javascript
+const { HindsightClient } = require('@vectorize-io/hindsight-client');
+
+const client = new HindsightClient({ baseUrl: 'http://localhost:8888' });
+
+await client.retain('my-bank', 'Alice loves hiking in Yosemite');
+await client.recall('my-bank', 'What does Alice like?');
+```
 
 ---
 
@@ -182,7 +149,7 @@ Satisfying these requirements in Hindsight is straightforward. When new user inp
 
 ![Overview](./hindsight-docs/static/img/hindsight-overview.webp)
 
-Most agent memory implementations rely on basic vector search or sometimes use a knowledge graph. Hindsight uses biomimetic data structures to organize agent memories in a way that is more like how human memory works:
+Most agent memory implementation rely on basic vector search or sometimes use a knowledge graph. Hindsight uses biomimetic data structures to organize agent memories in a way that is more like how human memory works:
 
 - **World:** Facts about the world ("The stove gets hot")
 - **Experiences:** Agent's own experiences ("I touched the stove and it really hurt")
@@ -308,5 +275,3 @@ MIT — see [LICENSE](./LICENSE)
 ---
 
 Built by [Vectorize.io](https://vectorize.io)
-
-<img src="https://umami-pixel.chris-latimer.workers.dev/?id=a8b043e6-6964-454d-80df-69b69d3f0d50&host=github.com&url=/vectorize-io/hindsight" width="1" height="1" alt="" />

deno.lock

@@ -1,139 +0,0 @@
-{
-  "version": "5",
-  "specifiers": {
-    "jsr:@std/assert@^1.0.17": "1.0.19",
-    "jsr:@std/assert@^1.0.19": "1.0.19",
-    "jsr:@std/expect@*": "1.0.18",
-    "jsr:@std/internal@^1.0.12": "1.0.12",
-    "jsr:@std/path@^1.1.4": "1.1.4",
-    "jsr:@std/testing@*": "1.0.17"
-  },
-  "jsr": {
-    "@std/[email protected]": {
-      "integrity": "eaada96ee120cb980bc47e040f82814d786fe8162ecc53c91d8df60b8755991e",
-      "dependencies": [
-        "jsr:@std/internal"
-      ]
-    },
-    "@std/[email protected]": {
-      "integrity": "8566eab35200466f8609eb7e7aed062ed0db314e9a258d5d201b1b8997ce801a",
-      "dependencies": [
-        "jsr:@std/assert@^1.0.19",
-        "jsr:@std/internal",
-        "jsr:@std/path"
-      ]
-    },
-    "@std/[email protected]": {
-      "integrity": "972a634fd5bc34b242024402972cd5143eac68d8dffaca5eaa4dba30ce17b027"
-    },
-    "@std/[email protected]": {
-      "integrity": "1d2d43f39efb1b42f0b1882a25486647cb851481862dc7313390b2bb044314b5",
-      "dependencies": [
-        "jsr:@std/internal"
-      ]
-    },
-    "@std/[email protected]": {
-      "integrity": "87bdc2700fa98249d48a17cd72413352d3d3680dcfbdb64947fd0982d6bbf681",
-      "dependencies": [
-        "jsr:@std/assert@^1.0.17",
-        "jsr:@std/internal"
-      ]
-    }
-  },
-  "workspace": {
-    "members": {
-      "hindsight-clients/typescript": {
-        "packageJson": {
-          "dependencies": [
-            "npm:@hey-api/[email protected]",
-            "npm:@types/jest@29",
-            "npm:@types/node@20",
-            "npm:jest@29",
-            "npm:ts-jest@29",
-            "npm:tsup@^8.5.1",
-            "npm:typescript@5"
-          ]
-        }
-      },
-      "hindsight-control-plane": {
-        "packageJson": {
-          "dependencies": [
-            "npm:@eslint/eslintrc@^3.3.3",
-            "npm:@eslint/js@^9.39.2",
-            "npm:@radix-ui/react-alert-dialog@^1.1.15",
-            "npm:@radix-ui/react-checkbox@^1.3.3",
-            "npm:@radix-ui/react-dialog@^1.1.15",
-            "npm:@radix-ui/react-dropdown-menu@^2.1.16",
-            "npm:@radix-ui/react-label@^2.1.8",
-            "npm:@radix-ui/react-popover@^1.1.15",
-            "npm:@radix-ui/react-radio-group@^1.3.8",
-            "npm:@radix-ui/react-select@^2.2.6",
-            "npm:@radix-ui/react-slider@^1.3.6",
-            "npm:@radix-ui/react-slot@^1.2.4",
-            "npm:@radix-ui/react-switch@^1.2.6",
-            "npm:@radix-ui/react-tabs@^1.1.13",
-            "npm:@radix-ui/react-tooltip@^1.2.8",
-            "npm:@tailwindcss/postcss@^4.1.17",
-            "npm:@tailwindcss/typography@~0.5.19",
-            "npm:@types/cytoscape@^3.21.9",
-            "npm:@types/node@^24.10.0",
-            "npm:@types/react-dom@^19.2.2",
-            "npm:@types/react@^19.2.2",
-            "npm:autoprefixer@^10.4.21",
-            "npm:class-variance-authority@~0.7.1",
-            "npm:clsx@^2.1.1",
-            "npm:cmdk@^1.1.1",
-            "npm:cytoscape-fcose@^2.2.0",
-            "npm:cytoscape@^3.33.1",
-            "npm:eslint-config-next@^16.0.1",
-            "npm:eslint-plugin-react-hooks@^7.0.1",
-            "npm:eslint-plugin-react@^7.37.5",
-            "npm:eslint@^9.39.1",
-            "npm:[email protected]",
-            "npm:next-themes@~0.4.6",
-            "npm:next@^16.1.6",
-            "npm:postcss@^8.5.6",
-            "npm:prettier@^3.7.4",
-            "npm:react-chrono@^2.9.1",
-            "npm:react-dom@^19.2.0",
-            "npm:react-markdown@^10.1.0",
-            "npm:react18-json-view@~0.2.9",
-            "npm:react@^19.2.0",
-            "npm:recharts@^3.5.1",
-            "npm:remark-gfm@^4.0.1",
-            "npm:sonner@^2.0.7",
-            "npm:tailwind-merge@^3.4.0",
-            "npm:tailwindcss-animate@^1.0.7",
-            "npm:tailwindcss@^4.1.17",
-            "npm:[email protected]",
-            "npm:typescript-eslint@^8.50.0",
-            "npm:typescript@^5.9.3"
-          ]
-        }
-      },
-      "hindsight-docs": {
-        "packageJson": {
-          "dependencies": [
-            "npm:@docusaurus/[email protected]",
-            "npm:@docusaurus/[email protected]",
-            "npm:@docusaurus/[email protected]",
-            "npm:@docusaurus/theme-common@^3.9.2",
-            "npm:@docusaurus/theme-mermaid@^3.9.2",
-            "npm:@docusaurus/[email protected]",
-            "npm:@docusaurus/[email protected]",
-            "npm:@easyops-cn/docusaurus-search-local@~0.52.2",
-            "npm:@mdx-js/react@3",
-            "npm:clsx@2",
-            "npm:prism-react-renderer@^2.3.0",
-            "npm:raw-loader@^4.0.2",
-            "npm:react-dom@19",
-            "npm:react-icons@^5.6.0",
-            "npm:react@19",
-            "npm:redocusaurus@^2.5.0",
-            "npm:typescript@~5.6.2"
-          ]
-        }
-      }
-    }
-  }
-}

docker/docker-compose/external-pg/docker-compose.yaml

@@ -1,54 +0,0 @@
-# Docker Compose file for Hindsight with PostgreSQL and pgvector
-#
-# Make sure to set the required environment variables before running:
-# - HINDSIGHT_DB_PASSWORD: Password for the PostgreSQL user
-# - Configure LLM provider variables as needed (see below in the hindsight service)
-#
-# Usage:
-# docker compose up -d
-#
-# Optional environment variables with defaults:
-# - HINDSIGHT_VERSION: Hindsight application version (default: latest)
-# - HINDSIGHT_DB_USER: PostgreSQL user (default: hindsight_user)
-# - HINDSIGHT_DB_NAME: PostgreSQL database name (default: hindsight_db)
-# - HINDSIGHT_DB_VERSION: PostgreSQL version (default: 18)
-
-services:
-  db:
-    # Use a PostgreSQL-Image with pgvector extension pre-installed
-    # see https://hub.docker.com/r/pgvector/pgvector 
-    image: pgvector/pgvector:pg${HINDSIGHT_DB_VERSION:-18}
-    container_name: hindsight-db
-    restart: always
-    # Expose PostgreSQL port
-    # ports:
-      # - "5432:5432"
-    environment:
-      POSTGRES_USER: ${HINDSIGHT_DB_USER:-hindsight_user}
-      POSTGRES_PASSWORD: ${HINDSIGHT_DB_PASSWORD:?Please set the HINDSIGHT_DB_PASSWORD env variable}
-      POSTGRES_DB: ${HINDSIGHT_DB_NAME:-hindsight_db}
-    volumes:
-      - pg_data:/var/lib/postgresql/${HINDSIGHT_DB_VERSION:-18}/docker
-    networks:
-      - hindsight-net
-
-  hindsight:
-    image: ghcr.io/vectorize-io/hindsight:${HINDSIGHT_VERSION:-latest}
-    container_name: hindsight-app
-    ports:
-      - "8888:8888"
-      - "9999:9999"
-    environment:
-      - HINDSIGHT_API_LLM_API_KEY=${OPENAI_API_KEY?Please set the OPENAI_API_KEY env variable}
-      - HINDSIGHT_API_DATABASE_URL=postgresql://${HINDSIGHT_DB_USER:-hindsight_user}:${HINDSIGHT_DB_PASSWORD:?Please set the HINDSIGHT_DB_PASSWORD env variable}@db:5432/${HINDSIGHT_DB_NAME:-hindsight_db}
-    depends_on:
-      - db
-    networks:
-      - hindsight-net
-
-networks:
-  hindsight-net:
-    driver: bridge
-
-volumes:
-  pg_data:

docker/docker-compose/nginx/README.md

@@ -1,96 +0,0 @@
-# Nginx Reverse Proxy with Custom Base Path
-
-Deploy Hindsight API under `/hindsight` (or any custom path) using Nginx reverse proxy.
-
-## Quick Start (Published Image - API Only)
-
-```bash
-docker-compose up
-```
-
-- **API:** http://localhost:8080/hindsight/docs
-- **Control Plane:** http://localhost:9999 (direct access, not proxied)
-
-## Full Stack with Custom Base Path (Requires Build)
-
-**Important:** You cannot rebuild from the published image with build args. You must build from source.
-
-### Build from Source with Custom Base Path
-
-1. **Clone the repository** (if you haven't):
-```bash
-git clone https://github.com/vectorize-io/hindsight.git
-cd hindsight
-```
-
-2. **Build with base path**:
-```bash
-docker build \
-  --build-arg NEXT_PUBLIC_BASE_PATH=/hindsight \
-  -f docker/standalone/Dockerfile \
-  -t hindsight:custom \
-  .
-```
-
-3. **Update docker-compose.yml** to use your built image:
-```yaml
-services:
-  hindsight:
-    image: hindsight:custom  # ← Change this
-    environment:
-      HINDSIGHT_API_BASE_PATH: /hindsight
-      NEXT_PUBLIC_BASE_PATH: /hindsight
-```
-
-4. **Update nginx.conf** to handle Control Plane routes (see below)
-
-5. **Run**:
-```bash
-docker-compose up
-```
-
-### Required nginx.conf for Full Stack
-
-Replace the current `nginx.conf` with this to proxy both API and Control Plane:
-
-```nginx
-events { worker_connections 1024; }
-
-http {
-    include /etc/nginx/mime.types;
-    default_type application/octet-stream;
-
-    upstream hindsight_api { server hindsight:8888; }
-    upstream hindsight_cp { server hindsight:9999; }
-
-    server {
-        listen 80;
-
-        # API
-        location ~ ^/hindsight/(docs|openapi\.json|health|metrics|v1|mcp) {
-            proxy_pass http://hindsight_api;
-            proxy_set_header Host $http_host;
-        }
-
-        # Control Plane static files
-        location ~ ^/hindsight/_next/ {
-            proxy_pass http://hindsight_cp;
-            proxy_set_header Host $http_host;
-        }
-
-        # Control Plane UI
-        location /hindsight {
-            proxy_pass http://hindsight_cp;
-            proxy_set_header Host $http_host;
-        }
-
-        location = / { return 301 /hindsight; }
-    }
-}
-```
-
-### Why Build is Required
-
-Next.js requires `basePath` at **build time**. The published image was built without a custom base path, so you must rebuild from source with the `NEXT_PUBLIC_BASE_PATH` build arg to deploy the Control Plane under a subpath.
-
-The API works without rebuild because `HINDSIGHT_API_BASE_PATH` is a runtime environment variable.

docker/docker-compose/nginx/docker-compose.yml

@@ -1,88 +0,0 @@
-# Hindsight API deployment with Nginx reverse proxy (API-only)
-#
-# This example deploys Hindsight API under the path /hindsight with:
-# - Hindsight standalone image (API + Control Plane + embedded pg0)
-# - Nginx reverse proxy (API only)
-#
-# Quick Start:
-#   docker-compose -f docker/docker-compose/nginx/docker-compose.yml up
-#
-# Access:
-#   API (via nginx):         http://localhost:8080/hindsight/docs
-#   Control Plane (direct):  http://localhost:9999
-#
-# For full stack deployment (API + Control Plane both under /hindsight):
-#   See README.md in this directory for instructions on building with basePath.
-#
-# Note: This configuration uses the published image (no build required).
-#       Control Plane is served directly because Next.js basePath requires
-#       build-time configuration. See README.md for the full stack option.
-
-services:
-  # Hindsight (API + Control Plane + embedded pg0)
-  hindsight:
-    image: ghcr.io/vectorize-io/hindsight:latest
-    ports:
-      - "9999:9999"  # Control Plane (direct access, not proxied)
-    environment:
-      # API base path for reverse proxy
-      HINDSIGHT_API_BASE_PATH: /hindsight
-
-      # LLM configuration
-      # Using mock provider for testing (no API key needed)
-      # For production, set OPENAI_API_KEY or ANTHROPIC_API_KEY and use a real provider
-      HINDSIGHT_API_LLM_PROVIDER: ${HINDSIGHT_API_LLM_PROVIDER:-mock}
-      HINDSIGHT_API_LLM_API_KEY: ${OPENAI_API_KEY:-not-needed-for-mock}
-      HINDSIGHT_API_LLM_MODEL: ${HINDSIGHT_API_LLM_MODEL:-mock-model}
-
-      # Production examples (uncomment and set appropriate API key):
-      # HINDSIGHT_API_LLM_PROVIDER: openai
-      # HINDSIGHT_API_LLM_API_KEY: ${OPENAI_API_KEY}
-      # HINDSIGHT_API_LLM_MODEL: gpt-4o-mini
-
-      # HINDSIGHT_API_LLM_PROVIDER: anthropic
-      # HINDSIGHT_API_LLM_API_KEY: ${ANTHROPIC_API_KEY}
-      # HINDSIGHT_API_LLM_MODEL: claude-sonnet-4-20250514
-
-      # Server config
-      HINDSIGHT_API_HOST: 0.0.0.0
-      HINDSIGHT_API_PORT: 8888
-      HINDSIGHT_API_LOG_LEVEL: info
-
-      # Control Plane config
-      HINDSIGHT_CP_DATAPLANE_API_URL: http://localhost:8888
-    volumes:
-      # Persist embedded pg0 database
-      - hindsight_data:/app/data
-    # Note: Ports not exposed - access via Nginx at localhost:8080/hindsight/
-    # To debug directly, uncomment these ports:
-    # ports:
-    #   - "8888:8888"  # API
-    #   - "9999:9999"  # Control Plane
-    healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8888/hindsight/health"]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-      start_period: 30s
-    networks:
-      - hindsight
-
-  # Nginx reverse proxy
-  nginx:
-    image: nginx:alpine
-    ports:
-      - "8080:80"
-    volumes:
-      - ./nginx.conf:/etc/nginx/nginx.conf:ro
-    depends_on:
-      hindsight:
-        condition: service_healthy
-    networks:
-      - hindsight
-
-volumes:
-  hindsight_data:
-
-networks:
-  hindsight:

docker/docker-compose/nginx/nginx.conf

@@ -1,40 +0,0 @@
-# Nginx configuration for API-only reverse proxy
-# Control Plane accessed directly (not through nginx)
-
-events {
-    worker_connections 1024;
-}
-
-http {
-    include /etc/nginx/mime.types;
-    default_type application/octet-stream;
-
-    # Logging
-    access_log /var/log/nginx/access.log;
-    error_log /var/log/nginx/error.log;
-
-    # Upstream - Hindsight API
-    upstream hindsight_api {
-        server hindsight:8888;
-    }
-
-    server {
-        listen 80;
-        server_name _;
-
-        # API endpoints - forward with /hindsight prefix
-        location /hindsight/ {
-            proxy_pass http://hindsight_api;
-
-            proxy_set_header Host $http_host;
-            proxy_set_header X-Real-IP $remote_addr;
-            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-            proxy_set_header X-Forwarded-Proto $scheme;
-        }
-
-        # Redirect root to API docs
-        location = / {
-            return 301 /hindsight/docs;
-        }
-    }
-}

docker/docker-compose/pg_textsearch/Dockerfile

@@ -1,32 +0,0 @@
-# PostgreSQL with pgvector and pg_textsearch extensions
-# Note: pg_textsearch requires PostgreSQL 17+
-FROM postgres:17
-
-# Install build dependencies
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    git \
-    postgresql-server-dev-17 \
-    libpq-dev \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install pgvector
-RUN cd /tmp && \
-    git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git && \
-    cd pgvector && \
-    make && \
-    make install
-
-# Install pg_textsearch
-RUN cd /tmp && \
-    git clone https://github.com/timescale/pg_textsearch.git && \
-    cd pg_textsearch && \
-    make && \
-    make install
-
-# Clean up source files and build dependencies
-RUN rm -rf /tmp/pgvector /tmp/pg_textsearch && \
-    apt-get purge -y --auto-remove build-essential git postgresql-server-dev-17
-
-# Ensure extensions are preloaded
-RUN echo "shared_preload_libraries = 'pg_textsearch'" >> /usr/share/postgresql/postgresql.conf.sample

docker/docker-compose/pg_textsearch/docker-compose.yaml

@@ -1,91 +0,0 @@
-name: hindsight
-# Docker Compose file for Hindsight with PostgreSQL and Timescale pg_textsearch
-# docker compose -f docker/docker-compose/pg_textsearch/docker-compose.yaml down && sleep 2 && docker compose -f docker/docker-compose/pg_textsearch/docker-compose.yaml up -d
-# Make sure to set the required environment variables before running:
-# - HINDSIGHT_DB_PASSWORD: Password for the PostgreSQL user
-# - Configure LLM provider variables as needed (see below in the hindsight service)
-#
-# Usage:
-# docker compose up -d
-#
-# Optional environment variables with defaults:
-# - HINDSIGHT_VERSION: Hindsight application version (default: latest)
-# - HINDSIGHT_DB_USER: PostgreSQL user (default: hindsight_user)
-# - HINDSIGHT_DB_NAME: PostgreSQL database name (default: hindsight_db)
-
-services:
-  db:
-    # Use custom PostgreSQL image with pgvector and pg_textsearch extensions
-    build:
-      context: .
-      dockerfile: Dockerfile
-    container_name: hindsight-db
-    restart: always
-    # Expose PostgreSQL port
-    ports:
-      - "5437:5432"
-    environment:
-      POSTGRES_USER: ${HINDSIGHT_DB_USER:-hindsight_user}
-      POSTGRES_PASSWORD: ${HINDSIGHT_DB_PASSWORD:-hindsight_password}
-      POSTGRES_DB: ${HINDSIGHT_DB_NAME:-hindsight_db}
-    volumes:
-      - pg_data:/var/lib/postgresql/data
-    networks:
-      - hindsight-net
-
-  pg-textsearch-init:
-    build:
-      context: .
-      dockerfile: Dockerfile
-    depends_on:
-      - db
-    environment:
-      - PGPASSWORD=${HINDSIGHT_DB_PASSWORD:-hindsight_password}
-    command: >
-      bash -c "
-        echo 'Waiting for PostgreSQL to be ready...';
-        until pg_isready -h hindsight-db -p 5432 -U hindsight_user; do
-          echo 'PostgreSQL is unavailable - sleeping';
-          sleep 2;
-        done;
-        echo 'PostgreSQL is ready - creating hindsight_db database';
-        psql -h hindsight-db -p 5432 -U hindsight_user -c 'CREATE DATABASE hindsight_db;' 2>/dev/null || echo 'Database already exists';
-        echo 'Creating extensions in hindsight_db database';
-        psql -h hindsight-db -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS vector CASCADE;';
-        psql -h hindsight-db -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS pg_textsearch CASCADE;';
-        echo 'Database and extensions created successfully';
-      "
-    restart: "no"
-    networks:
-      - hindsight-net
-
-  hindsight:
-    image: ghcr.io/vectorize-io/hindsight:${HINDSIGHT_VERSION:-latest}
-    container_name: hindsight-app
-    ports:
-      - "8888:8888"
-      - "9999:9999"
-    environment:
-      # LLM Configuration
-      HINDSIGHT_API_LLM_PROVIDER: ${HINDSIGHT_API_LLM_PROVIDER:-openai}
-      HINDSIGHT_API_LLM_API_KEY: ${OPENAI_API_KEY:-your-api-key}
-
-      # Database Configuration
-      HINDSIGHT_API_DATABASE_URL: postgresql://${HINDSIGHT_DB_USER:-hindsight_user}:${HINDSIGHT_DB_PASSWORD:-hindsight_password}@db:5432/${HINDSIGHT_DB_NAME:-hindsight_db}
-
-      # Vector and Text Search Extensions
-      HINDSIGHT_API_VECTOR_EXTENSION: pgvector
-      HINDSIGHT_API_TEXT_SEARCH_EXTENSION: pg_textsearch
-
-    depends_on:
-      - db
-    networks:
-      - hindsight-net
-
-
-networks:
-  hindsight-net:
-    driver: bridge
-
-volumes:
-  pg_data:

docker/docker-compose/s3-file-storage/docker-compose.yaml

@@ -1,83 +0,0 @@
-# Docker Compose file for Hindsight with S3 file storage (SeaweedFS)
-#
-# SeaweedFS (Apache 2.0) provides an S3-compatible object storage backend
-# for storing uploaded files instead of PostgreSQL BYTEA storage.
-#
-# Make sure to set the required environment variables before running:
-# - HINDSIGHT_DB_PASSWORD: Password for the PostgreSQL user
-# - Configure LLM provider variables as needed (see below in the hindsight service)
-#
-# Usage:
-# docker compose up -d
-#
-# Optional environment variables with defaults:
-# - HINDSIGHT_VERSION: Hindsight application version (default: latest)
-# - HINDSIGHT_DB_USER: PostgreSQL user (default: hindsight_user)
-# - HINDSIGHT_DB_NAME: PostgreSQL database name (default: hindsight_db)
-# - HINDSIGHT_DB_VERSION: PostgreSQL version (default: 18)
-# - SEAWEEDFS_S3_ACCESS_KEY: S3 access key (default: hindsight_s3_key)
-# - SEAWEEDFS_S3_SECRET_KEY: S3 secret key (default: hindsight_s3_secret)
-
-services:
-  db:
-    image: pgvector/pgvector:pg${HINDSIGHT_DB_VERSION:-18}
-    container_name: hindsight-db
-    restart: always
-    environment:
-      POSTGRES_USER: ${HINDSIGHT_DB_USER:-hindsight_user}
-      POSTGRES_PASSWORD: ${HINDSIGHT_DB_PASSWORD:?Please set the HINDSIGHT_DB_PASSWORD env variable}
-      POSTGRES_DB: ${HINDSIGHT_DB_NAME:-hindsight_db}
-    volumes:
-      - pg_data:/var/lib/postgresql/${HINDSIGHT_DB_VERSION:-18}/docker
-    networks:
-      - hindsight-net
-
-  seaweedfs:
-    image: chrislusf/seaweedfs:latest
-    container_name: hindsight-seaweedfs
-    restart: always
-    # Single-node mode: master + volume + filer + S3 gateway all in one process
-    command: >
-      server
-      -s3
-      -s3.port=8333
-      -s3.config=/etc/seaweedfs/s3.json
-      -ip.bind=0.0.0.0
-    volumes:
-      - seaweedfs_data:/data
-      - ./s3.json:/etc/seaweedfs/s3.json:ro
-    # Expose S3 API port (uncomment to access from host)
-    # ports:
-    #   - "8333:8333"
-    networks:
-      - hindsight-net
-
-  hindsight:
-    image: ghcr.io/vectorize-io/hindsight:${HINDSIGHT_VERSION:-latest}
-    container_name: hindsight-app
-    ports:
-      - "8888:8888"
-      - "9999:9999"
-    environment:
-      - HINDSIGHT_API_LLM_API_KEY=${OPENAI_API_KEY?Please set the OPENAI_API_KEY env variable}
-      - HINDSIGHT_API_DATABASE_URL=postgresql://${HINDSIGHT_DB_USER:-hindsight_user}:${HINDSIGHT_DB_PASSWORD:?Please set the HINDSIGHT_DB_PASSWORD env variable}@db:5432/${HINDSIGHT_DB_NAME:-hindsight_db}
-      # S3 file storage configuration (SeaweedFS)
-      - HINDSIGHT_API_FILE_STORAGE_TYPE=s3
-      - HINDSIGHT_API_FILE_STORAGE_S3_BUCKET=hindsight
-      - HINDSIGHT_API_FILE_STORAGE_S3_ENDPOINT=http://seaweedfs:8333
-      - HINDSIGHT_API_FILE_STORAGE_S3_REGION=us-east-1
-      - HINDSIGHT_API_FILE_STORAGE_S3_ACCESS_KEY_ID=${SEAWEEDFS_S3_ACCESS_KEY:-hindsight_s3_key}
-      - HINDSIGHT_API_FILE_STORAGE_S3_SECRET_ACCESS_KEY=${SEAWEEDFS_S3_SECRET_KEY:-hindsight_s3_secret}
-    depends_on:
-      - db
-      - seaweedfs
-    networks:
-      - hindsight-net
-
-networks:
-  hindsight-net:
-    driver: bridge
-
-volumes:
-  pg_data:
-  seaweedfs_data:

docker/docker-compose/s3-file-storage/s3.json

@@ -1,19 +0,0 @@
-{
-  "identities": [
-    {
-      "name": "hindsight",
-      "credentials": [
-        {
-          "accessKey": "hindsight_s3_key",
-          "secretKey": "hindsight_s3_secret"
-        }
-      ],
-      "actions": [
-        "Admin",
-        "Read",
-        "Write",
-        "List"
-      ]
-    }
-  ]
-}

docker/docker-compose/timescale/.dockerignore

@@ -1,16 +0,0 @@
-# Git
-.git
-.gitignore
-.gitattributes
-
-# Docker
-docker-compose.yaml
-.dockerignore
-
-# Documentation
-README.md
-*.md
-
-# Environment
-.env
-.env.example

docker/docker-compose/timescale/.env.example

@@ -1,25 +0,0 @@
-# PostgreSQL Configuration
-HINDSIGHT_DB_USER=hindsight_user
-HINDSIGHT_DB_PASSWORD=change-me-to-secure-password
-HINDSIGHT_DB_NAME=hindsight_db
-
-# Hindsight Version
-HINDSIGHT_VERSION=latest
-
-# LLM Configuration
-HINDSIGHT_API_LLM_PROVIDER=openai
-OPENAI_API_KEY=your-openai-api-key-here
-
-# Alternative LLM providers (uncomment and configure as needed):
-# HINDSIGHT_API_LLM_PROVIDER=anthropic
-# ANTHROPIC_API_KEY=your-anthropic-api-key
-
-# HINDSIGHT_API_LLM_PROVIDER=gemini
-# GEMINI_API_KEY=your-gemini-api-key
-
-# HINDSIGHT_API_LLM_PROVIDER=groq
-# GROQ_API_KEY=your-groq-api-key
-
-# Vector and Text Search (already configured in docker-compose.yaml)
-# HINDSIGHT_API_VECTOR_EXTENSION=pgvectorscale
-# HINDSIGHT_API_TEXT_SEARCH_EXTENSION=pg_textsearch

docker/docker-compose/timescale/Dockerfile

@@ -1,55 +0,0 @@
-# PostgreSQL with pgvector, pgvectorscale, and pg_textsearch extensions
-# All three extensions from Timescale/pgvector for high-performance vector and text search
-# Note: Requires PostgreSQL 16+
-FROM postgres:17
-
-# Install build dependencies and Rust toolchain
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    git \
-    postgresql-server-dev-17 \
-    libpq-dev \
-    cmake \
-    curl \
-    pkg-config \
-    libssl-dev \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install Rust toolchain (required for pgvectorscale)
-RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
-ENV PATH="/root/.cargo/bin:${PATH}"
-
-# Install pgvector (required by pgvectorscale)
-RUN cd /tmp && \
-    git clone --branch v0.8.0 https://github.com/pgvector/pgvector.git && \
-    cd pgvector && \
-    make && \
-    make install && \
-    rm -rf /tmp/pgvector
-
-# Install cargo-pgrx (PostgreSQL extension framework for Rust)
-RUN cargo install cargo-pgrx --version 0.12.5 --locked && \
-    cargo pgrx init --pg17 /usr/bin/pg_config
-
-# Install pgvectorscale (DiskANN index support)
-RUN cd /tmp && \
-    git clone --branch 0.5.1 https://github.com/timescale/pgvectorscale.git && \
-    cd pgvectorscale/pgvectorscale && \
-    cargo pgrx install --release && \
-    rm -rf /tmp/pgvectorscale
-
-# Install pg_textsearch (BM25 text search)
-RUN cd /tmp && \
-    git clone https://github.com/timescale/pg_textsearch.git && \
-    cd pg_textsearch && \
-    make && \
-    make install && \
-    rm -rf /tmp/pg_textsearch
-
-# Clean up build dependencies (keep runtime dependencies)
-RUN apt-get purge -y --auto-remove git cmake curl && \
-    rm -rf /root/.cargo/registry /root/.cargo/git
-
-# Ensure extensions are preloaded (pg_textsearch requires preloading)
-RUN echo "shared_preload_libraries = 'pg_textsearch'" >> /usr/share/postgresql/postgresql.conf.sample
-

docker/docker-compose/timescale/README.md

@@ -1,101 +0,0 @@
-# Hindsight with Timescale Extensions
-
-This Docker Compose setup provides a complete Hindsight deployment with **Timescale extensions**:
-- **pgvectorscale** - DiskANN algorithm for disk-based scalable vector search  
-- **pg_textsearch** - High-performance BM25 text search
-
-Both extensions are from [Timescale](https://github.com/timescale) and provide production-grade performance.
-
-## Prerequisites
-
-- Docker and Docker Compose installed
-- OpenAI API key (or another LLM provider)
-
-## Quick Start
-
-```bash
-# Set environment variables
-export HINDSIGHT_DB_PASSWORD="your-secure-password"
-export OPENAI_API_KEY="your-openai-api-key"
-
-# Build and start
-docker compose -f docker/docker-compose/timescale/docker-compose.yaml up -d --build
-
-# Check logs
-
-docker compose -f docker/docker-compose/timescale/docker-compose.yaml logs -f
-```
-
-**Access:**
-- API: http://localhost:8888
-- Control Plane: http://localhost:9999
-
-## Stop and Clean Up
-
-```bash
-# Stop services
-docker compose -f docker/docker-compose/timescale/docker-compose.yaml down
-
-# Remove volumes (deletes all data)
-docker compose -f docker/docker-compose/timescale/docker-compose.yaml down -v
-```
-
-## Configuration
-
-### Environment Variables
-
-| Variable | Description | Default |
-|----------|-------------|---------|
-| `HINDSIGHT_DB_PASSWORD` | PostgreSQL password | `hindsight_password` |
-| `HINDSIGHT_DB_USER` | PostgreSQL username | `hindsight_user` |
-| `HINDSIGHT_DB_NAME` | Database name | `hindsight_db` |
-| `HINDSIGHT_VERSION` | Hindsight Docker image version | `latest` |
-| `OPENAI_API_KEY` | OpenAI API key | (required) |
-| `HINDSIGHT_API_LLM_PROVIDER` | LLM provider | `openai` |
-
-### Why Timescale Extensions?
-
-**pgvectorscale (DiskANN):**
-- 28x lower p95 latency vs dedicated vector databases
-- 16x higher query throughput at 99% recall
-- 60-75% cost reduction (disk is cheaper than RAM)
-- Best for large datasets (10M+ vectors)
-
-**pg_textsearch (BM25):**
-- High-performance keyword retrieval
-- Native BM25 ranking algorithm
-- Optimized for full-text search
-
-## Troubleshooting
-
-### Extensions not installed
-
-Check if extensions are available:
-
-```bash
-docker exec -it hindsight-db-timescale psql -U hindsight_user -d hindsight_db -c "\dx"
-```
-
-You should see:
-- `vector` (pgvector)
-- `vectorscale` (pgvectorscale/DiskANN)
-- `pg_textsearch` (BM25 search)
-
-### Build fails
-
-If the Docker build fails during pgvectorscale compilation:
-
-1. Ensure you have sufficient memory (recommended: 4GB+)
-2. Check Docker build logs for Rust compilation errors
-3. Try building with more resources: `docker compose build --no-cache --memory 4g`
-
-### Port conflicts
-
-If port 5438 is already in use, modify the `ports` section in docker-compose.yaml.
-
-## Learn More
-
-- [pgvectorscale GitHub](https://github.com/timescale/pgvectorscale)
-- [pg_textsearch GitHub](https://github.com/timescale/pg_textsearch)
-- [HNSW vs DiskANN](https://www.tigerdata.com/learn/hnsw-vs-diskann)
-- [Hindsight Documentation](https://hindsight.dev)

docker/docker-compose/timescale/docker-compose.yaml

@@ -1,108 +0,0 @@
-name: hindsight
-# Docker Compose file for Hindsight with Timescale extensions
-# - pgvectorscale: DiskANN vector search (disk-based, scalable)
-# - pg_textsearch: BM25 text search (high-performance keyword retrieval)
-#
-# Quick start:
-# docker compose -f docker/docker-compose/timescale/docker-compose.yaml up -d --build
-#
-# Required environment variables:
-# - HINDSIGHT_DB_PASSWORD: Password for the PostgreSQL user
-# - OPENAI_API_KEY (or configure another LLM provider)
-#
-# Optional environment variables with defaults:
-# - HINDSIGHT_VERSION: Hindsight application version (default: latest)
-# - HINDSIGHT_DB_USER: PostgreSQL user (default: hindsight_user)
-# - HINDSIGHT_DB_NAME: PostgreSQL database name (default: hindsight_db)
-
-services:
-  db:
-    # Custom PostgreSQL image with Timescale extensions (pgvectorscale + pg_textsearch)
-    build:
-      context: .
-      dockerfile: Dockerfile
-    container_name: hindsight-db-timescale
-    restart: always
-    # Expose PostgreSQL port (using 5438 to avoid conflicts with other setups)
-    ports:
-      - "5438:5432"
-    environment:
-      POSTGRES_USER: ${HINDSIGHT_DB_USER:-hindsight_user}
-      POSTGRES_PASSWORD: ${HINDSIGHT_DB_PASSWORD:-hindsight_password}
-      POSTGRES_DB: ${HINDSIGHT_DB_NAME:-hindsight_db}
-    volumes:
-      - pg_data:/var/lib/postgresql/data
-    networks:
-      - hindsight-net
-    # Health check to ensure database is ready
-    healthcheck:
-      test: ["CMD-SHELL", "pg_isready -U hindsight_user"]
-      interval: 5s
-      timeout: 5s
-      retries: 5
-
-  timescale-init:
-    build:
-      context: .
-      dockerfile: Dockerfile
-    depends_on:
-      db:
-        condition: service_healthy
-    environment:
-      - PGPASSWORD=${HINDSIGHT_DB_PASSWORD:-hindsight_password}
-    command: >
-      bash -c "
-        echo 'PostgreSQL is ready - creating hindsight_db database';
-        psql -h hindsight-db-timescale -p 5432 -U hindsight_user -c 'CREATE DATABASE hindsight_db;' 2>/dev/null || echo 'Database already exists';
-        echo 'Installing Timescale extensions...';
-        echo '1/3: Installing pgvector (required by pgvectorscale)...';
-        psql -h hindsight-db-timescale -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS vector CASCADE;';
-        echo '2/3: Installing pgvectorscale (DiskANN vector search)...';
-        psql -h hindsight-db-timescale -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS vectorscale CASCADE;';
-        echo '3/3: Installing pg_textsearch (BM25 text search)...';
-        psql -h hindsight-db-timescale -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS pg_textsearch CASCADE;';
-        echo '';
-        echo '✅ Timescale extensions installed successfully';
-        echo '';
-        echo 'Installed extensions:';
-        psql -h hindsight-db-timescale -p 5432 -U hindsight_user -d hindsight_db -c \"\\dx\" | grep -E '(vector|vectorscale|pg_textsearch)';
-      "
-    restart: "no"
-    networks:
-      - hindsight-net
-
-  hindsight:
-    image: ghcr.io/vectorize-io/hindsight:${HINDSIGHT_VERSION:-latest}
-    container_name: hindsight-app-timescale
-    ports:
-      - "8888:8888"
-      - "9999:9999"
-    environment:
-      # LLM Configuration
-      HINDSIGHT_API_LLM_PROVIDER: ${HINDSIGHT_API_LLM_PROVIDER:-openai}
-      HINDSIGHT_API_LLM_API_KEY: ${OPENAI_API_KEY:-your-api-key}
-
-      # Database Configuration
-      HINDSIGHT_API_DATABASE_URL: postgresql://${HINDSIGHT_DB_USER:-hindsight_user}:${HINDSIGHT_DB_PASSWORD:-hindsight_password}@db:5432/${HINDSIGHT_DB_NAME:-hindsight_db}
-
-      # Timescale Extensions
-      # pgvectorscale: DiskANN algorithm for disk-based scalable vector search
-      HINDSIGHT_API_VECTOR_EXTENSION: pgvectorscale
-      # pg_textsearch: High-performance BM25 text search
-      HINDSIGHT_API_TEXT_SEARCH_EXTENSION: pg_textsearch
-
-    depends_on:
-      db:
-        condition: service_healthy
-      timescale-init:
-        condition: service_completed_successfully
-    networks:
-      - hindsight-net
-
-
-networks:
-  hindsight-net:
-    driver: bridge
-
-volumes:
-  pg_data:

docker/docker-compose/vchord/docker-compose.yaml

@@ -1,93 +0,0 @@
-name: hindsight
-# Docker Compose file for Hindsight with PostgreSQL and vectorchord
-# docker compose -f docker/docker-compose/docker-compose.yaml down && sleep 2 && docker compose -f docker/docker-compose/docker-compose.yaml up -d
-# Make sure to set the required environment variables before running:
-# - HINDSIGHT_DB_PASSWORD: Password for the PostgreSQL user
-# - Configure LLM provider variables as needed (see below in the hindsight service)
-#
-# Usage:
-# docker compose up -d
-#
-# Optional environment variables with defaults:
-# - HINDSIGHT_VERSION: Hindsight application version (default: latest)
-# - HINDSIGHT_DB_USER: PostgreSQL user (default: hindsight_user)
-# - HINDSIGHT_DB_NAME: PostgreSQL database name (default: hindsight_db)
-# - HINDSIGHT_DB_VERSION: PostgreSQL version (default: 18)
-
-services:
-  db:
-    # Use a PostgreSQL-Image with vectorchord extension pre-installed
-    image: tensorchord/vchord-suite:pg${HINDSIGHT_DB_VERSION:-18-latest}
-    container_name: hindsight-db
-    restart: always
-    # Expose PostgreSQL port
-    ports:
-      - "5436:5432"
-    environment:
-      POSTGRES_USER: ${HINDSIGHT_DB_USER:-hindsight_user}
-      POSTGRES_PASSWORD: ${HINDSIGHT_DB_PASSWORD:-hindsight_password}
-      POSTGRES_DB: ${HINDSIGHT_DB_NAME:-hindsight_db}
-    volumes:
-      - pg_data:/var/lib/postgresql/${HINDSIGHT_DB_VERSION:-18}/docker
-    networks:
-      - hindsight-net
-
-  vectorchord-init:
-    image: tensorchord/vchord-suite:pg18-latest
-    #container_name: vectorchord-init
-    depends_on:
-      - db
-    environment:
-      - PGPASSWORD=${HINDSIGHT_DB_PASSWORD:-hindsight_password}
-    command: >
-      bash -c "
-        echo 'Waiting for PostgreSQL to be ready...';
-        until pg_isready -h hindsight-db -p 5432 -U hindsight_user; do
-          echo 'PostgreSQL is unavailable - sleeping';
-          sleep 2;
-        done;
-        echo 'PostgreSQL is ready - creating hindsight_db database';
-        psql -h hindsight-db -p 5432 -U hindsight_user -c 'CREATE DATABASE hindsight_db;' 2>/dev/null || echo 'Database already exists';
-        echo 'Creating extensions in hindsight_db database';
-        psql -h hindsight-db -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS vchord CASCADE;';
-        psql -h hindsight-db -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS pg_tokenizer CASCADE;';
-        psql -h hindsight-db -p 5432 -U hindsight_user -d hindsight_db -c 'CREATE EXTENSION IF NOT EXISTS vchord_bm25 CASCADE;';
-        echo 'Creating llmlingua2 tokenizer';
-        psql -h hindsight-db -p 5432 -U hindsight_user -d hindsight_db -c \"SELECT create_tokenizer('llmlingua2', \\$\\$ model = \\\"llmlingua2\\\" \\$\\$);\" 2>/dev/null || echo 'Tokenizer already exists or creation skipped';
-        echo 'Database and extensions created successfully';
-      "
-    restart: "no"
-    networks:
-      - hindsight-net
-
-  hindsight:
-    image: ghcr.io/vectorize-io/hindsight:${HINDSIGHT_VERSION:-latest}
-    container_name: hindsight-app
-    ports:
-      - "8888:8888"
-      - "9999:9999"
-    environment:
-      # LLM Configuration (uses OpenAI for testing vchord)
-      # LLM configuration
-      HINDSIGHT_API_LLM_PROVIDER: ${HINDSIGHT_API_LLM_PROVIDER:-openai}
-      HINDSIGHT_API_LLM_API_KEY: ${OPENAI_API_KEY:-your-api-key}
-
-      # Database Configuration
-      HINDSIGHT_API_DATABASE_URL: postgresql://${HINDSIGHT_DB_USER:-hindsight_user}:${HINDSIGHT_DB_PASSWORD:-hindsight_password}@db:5432/${HINDSIGHT_DB_NAME:-hindsight_db}
-
-      # Vector and Text Search Extensions
-      HINDSIGHT_API_VECTOR_EXTENSION: vchord
-      HINDSIGHT_API_TEXT_SEARCH_EXTENSION: vchord
-
-    depends_on:
-      - db
-    networks:
-      - hindsight-net
-
-
-networks:
-  hindsight-net:
-    driver: bridge
-
-volumes:
-  pg_data:

docker/standalone/Dockerfile

@@ -8,7 +8,6 @@
 #                                     Set to false when using external providers (TEI, OpenAI, Cohere)
 #   PRELOAD_ML_MODELS=true/false   - Pre-download ML models during build (default: true)
 #                                     Only effective when INCLUDE_LOCAL_MODELS=true
-#                                     NOTE: tiktoken encodings are ALWAYS preloaded (required for air-gapped deployments)
 #
 # Examples:
 #   docker build -t hindsight .                                          # Both (standalone)
@@ -42,22 +41,25 @@ RUN apt-get update && apt-get install -y \
     && pip install --no-cache-dir uv
 
 # Copy dependency files and README (required by pyproject.toml)
-COPY hindsight-api-slim/pyproject.toml ./api/
-COPY hindsight-api-slim/README.md ./api/
+COPY hindsight-api/pyproject.toml ./api/
+COPY hindsight-api/README.md ./api/
 
 WORKDIR /app/api
 
-# Sync dependencies using appropriate extras based on INCLUDE_LOCAL_MODELS
-# local-ml: torch, sentence-transformers, transformers, einops, flashrank, mlx (optional)
-# embedded-db: pg0-embedded (always included for embedded PostgreSQL support)
-RUN if [ "$INCLUDE_LOCAL_MODELS" = "true" ]; then \
-        uv sync --extra local-ml --extra embedded-db; \
-    else \
-        uv sync --extra embedded-db; \
+# Remove local ML model dependencies if INCLUDE_LOCAL_MODELS=false
+# This creates a smaller image when using external providers (TEI, OpenAI, Cohere)
+RUN if [ "$INCLUDE_LOCAL_MODELS" != "true" ]; then \
+        echo "Removing local-models dependencies (sentence-transformers, torch, transformers)..." && \
+        sed -i '/"sentence-transformers/d' pyproject.toml && \
+        sed -i '/"transformers/d' pyproject.toml && \
+        sed -i '/"torch/d' pyproject.toml; \
     fi
 
+# Sync dependencies (will create lock file if needed)
+RUN uv sync
+
 # Copy source code (alembic migrations are inside hindsight_api/)
-COPY hindsight-api-slim/hindsight_api ./hindsight_api
+COPY hindsight-api/hindsight_api ./hindsight_api
 
 # Install the local package (uv sync only installed dependencies, not the package itself)
 RUN uv pip install -e .
@@ -109,10 +111,6 @@ RUN rm -f package-lock.json && sed -i '/"@vectorize-io\/hindsight-client":/d' pa
 # Copy built SDK directly into node_modules (more reliable than npm link in Docker)
 COPY --from=sdk-builder /app/hindsight-clients/typescript ./node_modules/@vectorize-io/hindsight-client
 
-# Accept base path as build argument for reverse proxy deployments
-# Usage: docker build --build-arg NEXT_PUBLIC_BASE_PATH=/hindsight ...
-ARG NEXT_PUBLIC_BASE_PATH=""
-
 # Build Control Plane - run next build first, then custom standalone copy
 # (The build:standalone script expects a specific path structure that differs in Docker)
 RUN npm exec -- next build
@@ -167,64 +165,20 @@ RUN chown -R hindsight:hindsight /app
 
 USER hindsight
 
-# Create pg0 data directory as hindsight user so that Docker seeds new named
-# volumes with correct ownership (UID 1000) on first use, avoiding the
-# "Permission denied" error when mounting a fresh root-owned volume.
-RUN mkdir -p /home/hindsight/.pg0
-
 ENV PATH="/app/api/.venv/bin:${PATH}"
 
-# Pre-download tiktoken encoding (ALWAYS - required for token counting even in air-gapped envs)
-# Tiktoken is a core runtime dependency, not an optional ML model
-RUN MAX_RETRIES=3; \
-    RETRY_DELAY=5; \
-    for i in $(seq 1 $MAX_RETRIES); do \
-      echo "Attempt $i/$MAX_RETRIES: Downloading tiktoken encoding..."; \
-      /app/api/.venv/bin/python -c "\
-import tiktoken; \
-print('Downloading cl100k_base encoding...'); \
-tiktoken.get_encoding('cl100k_base'); \
-print('Tiktoken encoding cached successfully')" && break; \
-      if [ $i -lt $MAX_RETRIES ]; then \
-        echo "Attempt $i failed, retrying in ${RETRY_DELAY}s..."; \
-        sleep $RETRY_DELAY; \
-        RETRY_DELAY=$((RETRY_DELAY * 2)); \
-      fi; \
-    done; \
-    if [ $i -eq $MAX_RETRIES ]; then \
-      echo "ERROR: Failed to download tiktoken encoding after $MAX_RETRIES attempts"; \
-      exit 1; \
-    fi
-
 # Pre-download ML models to avoid runtime download (conditional)
 # Only runs if both PRELOAD_ML_MODELS=true AND INCLUDE_LOCAL_MODELS=true
-# Includes retry logic with exponential backoff for transient network failures
 ARG PRELOAD_ML_MODELS
 ARG INCLUDE_LOCAL_MODELS
-ENV HF_HUB_DOWNLOAD_TIMEOUT=600
 RUN if [ "$PRELOAD_ML_MODELS" = "true" ] && [ "$INCLUDE_LOCAL_MODELS" = "true" ]; then \
-    MAX_RETRIES=3; \
-    RETRY_DELAY=10; \
-    for i in $(seq 1 $MAX_RETRIES); do \
-      echo "Attempt $i/$MAX_RETRIES: Downloading ML models..."; \
-      /app/api/.venv/bin/python -c "\
-import os; os.environ['HF_HUB_DOWNLOAD_TIMEOUT'] = '600'; \
+    /app/api/.venv/bin/python -c "\
 from sentence_transformers import SentenceTransformer, CrossEncoder; \
 print('Downloading embedding model...'); \
 SentenceTransformer('BAAI/bge-small-en-v1.5'); \
 print('Downloading cross-encoder model...'); \
 CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2'); \
-print('Models cached successfully')" && break; \
-      if [ $i -lt $MAX_RETRIES ]; then \
-        echo "Attempt $i failed, retrying in ${RETRY_DELAY}s..."; \
-        sleep $RETRY_DELAY; \
-        RETRY_DELAY=$((RETRY_DELAY * 2)); \
-      fi; \
-    done; \
-    if [ $i -eq $MAX_RETRIES ] && ! /app/api/.venv/bin/python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('BAAI/bge-small-en-v1.5')" 2>/dev/null; then \
-      echo "ERROR: Failed to download models after $MAX_RETRIES attempts"; \
-      exit 1; \
-    fi; \
+print('Models cached successfully')"; \
     elif [ "$INCLUDE_LOCAL_MODELS" != "true" ]; then echo "Skipping ML model preload (local-models not included)"; \
     else echo "Skipping ML model preload"; fi
 
@@ -236,10 +190,6 @@ ENV HINDSIGHT_API_LOG_LEVEL=info
 ENV HINDSIGHT_ENABLE_API=true
 ENV HINDSIGHT_ENABLE_CP=false
 ENV PYTHONUNBUFFERED=1
-# Suppress verbose transformers/HuggingFace model loading warnings
-ENV TRANSFORMERS_VERBOSITY=error
-ENV HF_HUB_VERBOSITY=error
-ENV TOKENIZERS_PARALLELISM=false
 
 CMD ["/app/start-all.sh"]
 
@@ -323,64 +273,20 @@ RUN chown -R hindsight:hindsight /app
 
 USER hindsight
 
-# Create pg0 data directory as hindsight user so that Docker seeds new named
-# volumes with correct ownership (UID 1000) on first use, avoiding the
-# "Permission denied" error when mounting a fresh root-owned volume.
-RUN mkdir -p /home/hindsight/.pg0
-
 ENV PATH="/app/api/.venv/bin:${PATH}"
 
-# Pre-download tiktoken encoding (ALWAYS - required for token counting even in air-gapped envs)
-# Tiktoken is a core runtime dependency, not an optional ML model
-RUN MAX_RETRIES=3; \
-    RETRY_DELAY=5; \
-    for i in $(seq 1 $MAX_RETRIES); do \
-      echo "Attempt $i/$MAX_RETRIES: Downloading tiktoken encoding..."; \
-      /app/api/.venv/bin/python -c "\
-import tiktoken; \
-print('Downloading cl100k_base encoding...'); \
-tiktoken.get_encoding('cl100k_base'); \
-print('Tiktoken encoding cached successfully')" && break; \
-      if [ $i -lt $MAX_RETRIES ]; then \
-        echo "Attempt $i failed, retrying in ${RETRY_DELAY}s..."; \
-        sleep $RETRY_DELAY; \
-        RETRY_DELAY=$((RETRY_DELAY * 2)); \
-      fi; \
-    done; \
-    if [ $i -eq $MAX_RETRIES ]; then \
-      echo "ERROR: Failed to download tiktoken encoding after $MAX_RETRIES attempts"; \
-      exit 1; \
-    fi
-
 # Pre-download ML models to avoid runtime download (conditional)
 # Only runs if both PRELOAD_ML_MODELS=true AND INCLUDE_LOCAL_MODELS=true
-# Includes retry logic with exponential backoff for transient network failures
 ARG PRELOAD_ML_MODELS
 ARG INCLUDE_LOCAL_MODELS
-ENV HF_HUB_DOWNLOAD_TIMEOUT=600
 RUN if [ "$PRELOAD_ML_MODELS" = "true" ] && [ "$INCLUDE_LOCAL_MODELS" = "true" ]; then \
-    MAX_RETRIES=3; \
-    RETRY_DELAY=10; \
-    for i in $(seq 1 $MAX_RETRIES); do \
-      echo "Attempt $i/$MAX_RETRIES: Downloading ML models..."; \
-      /app/api/.venv/bin/python -c "\
-import os; os.environ['HF_HUB_DOWNLOAD_TIMEOUT'] = '600'; \
+    /app/api/.venv/bin/python -c "\
 from sentence_transformers import SentenceTransformer, CrossEncoder; \
 print('Downloading embedding model...'); \
 SentenceTransformer('BAAI/bge-small-en-v1.5'); \
 print('Downloading cross-encoder model...'); \
 CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2'); \
-print('Models cached successfully')" && break; \
-      if [ $i -lt $MAX_RETRIES ]; then \
-        echo "Attempt $i failed, retrying in ${RETRY_DELAY}s..."; \
-        sleep $RETRY_DELAY; \
-        RETRY_DELAY=$((RETRY_DELAY * 2)); \
-      fi; \
-    done; \
-    if [ $i -eq $MAX_RETRIES ] && ! /app/api/.venv/bin/python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('BAAI/bge-small-en-v1.5')" 2>/dev/null; then \
-      echo "ERROR: Failed to download models after $MAX_RETRIES attempts"; \
-      exit 1; \
-    fi; \
+print('Models cached successfully')"; \
     elif [ "$INCLUDE_LOCAL_MODELS" != "true" ]; then echo "Skipping ML model preload (local-models not included)"; \
     else echo "Skipping ML model preload"; fi
 
@@ -394,10 +300,6 @@ ENV HINDSIGHT_CP_DATAPLANE_API_URL=http://localhost:8888
 ENV HINDSIGHT_ENABLE_API=true
 ENV HINDSIGHT_ENABLE_CP=true
 ENV PYTHONUNBUFFERED=1
-# Suppress verbose transformers/HuggingFace model loading warnings
-ENV TRANSFORMERS_VERBOSITY=error
-ENV HF_HUB_VERBOSITY=error
-ENV TOKENIZERS_PARALLELISM=false
 
 CMD ["/app/start-all.sh"]
 

docker/standalone/start-all.sh

@@ -77,32 +77,18 @@ PIDS=()
 # Start API if enabled
 if [ "$ENABLE_API" = "true" ]; then
     cd /app/api
-    API_HEALTH_URL="${HINDSIGHT_API_HEALTH_URL:-http://localhost:8888/health}"
-    API_STARTUP_WAIT_SECONDS="${HINDSIGHT_API_STARTUP_WAIT_SECONDS:-300}"
-
     # Run API directly - Python's PYTHONUNBUFFERED=1 handles output buffering
     hindsight-api &
     API_PID=$!
     PIDS+=($API_PID)
 
     # Wait for API to be ready
-    api_ready=false
-    for ((i=1; i<=API_STARTUP_WAIT_SECONDS; i++)); do
-        if ! kill -0 "$API_PID" 2>/dev/null; then
-            wait "$API_PID"
-            exit $?
-        fi
-        if curl -sf "$API_HEALTH_URL" &>/dev/null; then
-            api_ready=true
+    for i in {1..60}; do
+        if curl -sf http://localhost:8888/health &>/dev/null; then
             break
         fi
         sleep 1
     done
-
-    if [ "$api_ready" != "true" ]; then
-        echo "❌ API did not become healthy within ${API_STARTUP_WAIT_SECONDS}s"
-        exit 1
-    fi
 else
     echo "API disabled (HINDSIGHT_ENABLE_API=false)"
 fi
@@ -111,8 +97,7 @@ fi
 if [ "$ENABLE_CP" = "true" ]; then
     echo "🎛️  Starting Control Plane..."
     cd /app/control-plane
-    export HOSTNAME="${HINDSIGHT_CP_HOSTNAME:-0.0.0.0}"
-    PORT="${HINDSIGHT_CP_PORT:-9999}" node server.js &
+    PORT=9999 node server.js &
     CP_PID=$!
     PIDS+=($CP_PID)
 else
@@ -125,7 +110,7 @@ echo "✅ Hindsight is running!"
 echo ""
 echo "📍 Access:"
 if [ "$ENABLE_CP" = "true" ]; then
-    echo "   Control Plane: http://localhost:${HINDSIGHT_CP_PORT:-9999}"
+    echo "   Control Plane: http://localhost:9999"
 fi
 if [ "$ENABLE_API" = "true" ]; then
     echo "   API:           http://localhost:8888"

docker/test-image.sh

@@ -1,235 +0,0 @@
-#!/bin/bash
-#
-# Docker Smoke Test Script
-#
-# Tests that a Hindsight Docker image starts correctly and becomes healthy.
-# Can be run locally or in CI pipelines.
-#
-# Usage:
-#   ./docker/test-image.sh <image> [target]
-#
-# Arguments:
-#   image   - Docker image to test (e.g., hindsight-api:test, ghcr.io/vectorize-io/hindsight:latest)
-#   target  - Optional: 'cp-only' for control plane, otherwise assumes API image (default: api)
-#
-# Environment variables:
-#   HINDSIGHT_API_LLM_API_KEY                   - Required for API/standalone images (LLM verification)
-#   HINDSIGHT_API_LLM_PROVIDER                  - LLM provider (default: openai)
-#   HINDSIGHT_API_LLM_MODEL                     - LLM model (default: gpt-4o-mini)
-#   HINDSIGHT_API_EMBEDDINGS_PROVIDER           - Embeddings provider (optional, for slim images: openai, cohere, tei)
-#   HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY     - OpenAI API key for embeddings (optional)
-#   HINDSIGHT_API_RERANKER_PROVIDER             - Reranker provider (optional, for slim images: cohere, tei)
-#   HINDSIGHT_API_COHERE_API_KEY                - Cohere API key for reranking (optional)
-#   SMOKE_TEST_TIMEOUT                          - Timeout in seconds (default: 120)
-#   SMOKE_TEST_CONTAINER_NAME                   - Container name (default: hindsight-smoke-test)
-#
-# Examples:
-#   # Test a locally built full image
-#   ./docker/test-image.sh hindsight-api:test
-#
-#   # Test a released image
-#   ./docker/test-image.sh ghcr.io/vectorize-io/hindsight:latest
-#
-#   # Test control plane image
-#   ./docker/test-image.sh hindsight-control-plane:test cp-only
-#
-#   # Test slim image with external providers
-#   export HINDSIGHT_API_LLM_API_KEY=sk_xxx
-#   export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
-#   export HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=sk-xxx
-#   export HINDSIGHT_API_RERANKER_PROVIDER=cohere
-#   export HINDSIGHT_API_COHERE_API_KEY=xxx
-#   ./docker/test-image.sh hindsight-slim:test
-#
-# Exit codes:
-#   0 - Success (container healthy)
-#   1 - Failure (container not healthy within timeout)
-#   2 - Invalid arguments
-#
-
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-REPO_ROOT="$(dirname "$SCRIPT_DIR")"
-
-# Colors for output
-RED='\033[0;31m'
-GREEN='\033[0;32m'
-YELLOW='\033[0;33m'
-NC='\033[0m' # No Color
-
-# Configuration
-IMAGE="${1:-}"
-TARGET="${2:-api}"
-TIMEOUT="${SMOKE_TEST_TIMEOUT:-120}"
-CONTAINER_NAME="${SMOKE_TEST_CONTAINER_NAME:-hindsight-smoke-test}"
-LLM_PROVIDER="${HINDSIGHT_API_LLM_PROVIDER:-openai}"
-LLM_MODEL="${HINDSIGHT_API_LLM_MODEL:-gpt-4o-mini}"
-
-# Validate arguments
-if [ -z "$IMAGE" ]; then
-    echo -e "${RED}Error: Image argument is required${NC}"
-    echo ""
-    echo "Usage: $0 <image> [target]"
-    echo ""
-    echo "Examples:"
-    echo "  $0 hindsight-api:test"
-    echo "  $0 ghcr.io/vectorize-io/hindsight:latest"
-    echo "  $0 hindsight-control-plane:test cp-only"
-    exit 2
-fi
-
-# Determine health endpoint based on target
-if [ "$TARGET" = "cp-only" ]; then
-    HEALTH_PORT=9999
-    HEALTH_PATH="/api/health"
-    NEEDS_LLM=false
-else
-    HEALTH_PORT=8888
-    HEALTH_PATH="/health"
-    NEEDS_LLM=true
-fi
-
-# Check for required environment variables
-if [ "$NEEDS_LLM" = true ] && [ "$LLM_PROVIDER" != "vertexai" ] && [ -z "${HINDSIGHT_API_LLM_API_KEY:-}" ]; then
-    echo -e "${RED}Error: HINDSIGHT_API_LLM_API_KEY environment variable is required for API/standalone images${NC}"
-    echo "Set it with: export HINDSIGHT_API_LLM_API_KEY=your-api-key"
-    exit 2
-fi
-
-# Cleanup function
-cleanup() {
-    echo "Cleaning up..."
-    docker stop "$CONTAINER_NAME" 2>/dev/null || true
-    docker rm "$CONTAINER_NAME" 2>/dev/null || true
-}
-
-# Set trap to cleanup on exit
-trap cleanup EXIT
-
-echo -e "${YELLOW}Starting smoke test for: ${IMAGE}${NC}"
-echo "  Target: $TARGET"
-echo "  Health endpoint: http://localhost:${HEALTH_PORT}${HEALTH_PATH}"
-echo "  Timeout: ${TIMEOUT}s"
-echo ""
-
-# Remove any existing container with the same name
-docker rm -f "$CONTAINER_NAME" 2>/dev/null || true
-
-# Start container based on target type
-echo "Starting container..."
-if [ "$TARGET" = "cp-only" ]; then
-    docker run -d --name "$CONTAINER_NAME" \
-        -p "${HEALTH_PORT}:${HEALTH_PORT}" \
-        "$IMAGE"
-else
-    # Build docker run command with required and optional env vars
-    DOCKER_CMD="docker run -d --name $CONTAINER_NAME"
-    DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_PROVIDER=$LLM_PROVIDER"
-    if [ -n "${HINDSIGHT_API_LLM_API_KEY:-}" ]; then
-        DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_API_KEY=${HINDSIGHT_API_LLM_API_KEY}"
-    fi
-    DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_MODEL=$LLM_MODEL"
-
-    # Add Vertex AI config if provider is vertexai
-    if [ "$LLM_PROVIDER" = "vertexai" ]; then
-        if [ -n "${HINDSIGHT_API_LLM_VERTEXAI_SERVICE_ACCOUNT_KEY:-}" ]; then
-            DOCKER_CMD="$DOCKER_CMD -v ${HINDSIGHT_API_LLM_VERTEXAI_SERVICE_ACCOUNT_KEY}:/tmp/gcp-credentials.json:ro"
-            DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_VERTEXAI_SERVICE_ACCOUNT_KEY=/tmp/gcp-credentials.json"
-        fi
-        if [ -n "${HINDSIGHT_API_LLM_VERTEXAI_PROJECT_ID:-}" ]; then
-            DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_VERTEXAI_PROJECT_ID=${HINDSIGHT_API_LLM_VERTEXAI_PROJECT_ID}"
-        fi
-        if [ -n "${HINDSIGHT_API_LLM_VERTEXAI_REGION:-}" ]; then
-            DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_LLM_VERTEXAI_REGION=${HINDSIGHT_API_LLM_VERTEXAI_REGION}"
-        fi
-    fi
-
-    # Add optional embeddings provider config
-    if [ -n "${HINDSIGHT_API_EMBEDDINGS_PROVIDER:-}" ]; then
-        DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_EMBEDDINGS_PROVIDER=${HINDSIGHT_API_EMBEDDINGS_PROVIDER}"
-    fi
-    if [ -n "${HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY:-}" ]; then
-        DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=${HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY}"
-    fi
-
-    # Add optional reranker provider config
-    if [ -n "${HINDSIGHT_API_RERANKER_PROVIDER:-}" ]; then
-        DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_RERANKER_PROVIDER=${HINDSIGHT_API_RERANKER_PROVIDER}"
-    fi
-    if [ -n "${HINDSIGHT_API_COHERE_API_KEY:-}" ]; then
-        DOCKER_CMD="$DOCKER_CMD -e HINDSIGHT_API_COHERE_API_KEY=${HINDSIGHT_API_COHERE_API_KEY}"
-    fi
-
-    DOCKER_CMD="$DOCKER_CMD -p ${HEALTH_PORT}:${HEALTH_PORT}"
-    DOCKER_CMD="$DOCKER_CMD $IMAGE"
-
-    eval $DOCKER_CMD
-fi
-
-# Wait for health endpoint
-echo "Waiting for health endpoint at http://localhost:${HEALTH_PORT}${HEALTH_PATH}..."
-start_time=$(date +%s)
-
-for i in $(seq 1 "$TIMEOUT"); do
-    if curl -sf "http://localhost:${HEALTH_PORT}${HEALTH_PATH}" > /dev/null 2>&1; then
-        end_time=$(date +%s)
-        duration=$((end_time - start_time))
-        echo ""
-        echo -e "${GREEN}Container is healthy after ${duration}s${NC}"
-        echo ""
-        echo "=== Health Response ==="
-        curl -s "http://localhost:${HEALTH_PORT}${HEALTH_PATH}" | python3 -m json.tool 2>/dev/null || curl -s "http://localhost:${HEALTH_PORT}${HEALTH_PATH}"
-        echo ""
-
-        # Run retain/recall smoke test for API targets
-        if [ "$TARGET" != "cp-only" ]; then
-            echo ""
-            echo "=== Retain/Recall Smoke Test ==="
-            if ! "$REPO_ROOT/scripts/smoke-test-slim.sh" "http://localhost:${HEALTH_PORT}"; then
-                echo ""
-                echo "=== Container Logs (last 50 lines) ==="
-                docker logs "$CONTAINER_NAME" 2>&1 | tail -50
-                echo ""
-                echo -e "${RED}Smoke test FAILED${NC}"
-                exit 1
-            fi
-        fi
-
-        echo ""
-        echo "=== Container Logs (last 50 lines) ==="
-        docker logs "$CONTAINER_NAME" 2>&1 | tail -50
-        echo ""
-        echo -e "${GREEN}Smoke test PASSED${NC}"
-        exit 0
-    fi
-
-    # Show progress every 10 seconds
-    if [ $((i % 10)) -eq 0 ]; then
-        echo "  Still waiting... (${i}s)"
-    fi
-
-    # Check if container is still running
-    if ! docker ps -q -f "name=$CONTAINER_NAME" | grep -q .; then
-        echo ""
-        echo -e "${RED}Container exited unexpectedly!${NC}"
-        echo ""
-        echo "=== Container Logs ==="
-        docker logs "$CONTAINER_NAME" 2>&1
-        echo ""
-        echo -e "${RED}Smoke test FAILED${NC}"
-        exit 1
-    fi
-
-    sleep 1
-done
-
-# Timeout reached
-echo ""
-echo -e "${RED}Container failed to become healthy after ${TIMEOUT}s${NC}"
-echo ""
-echo "=== Container Logs ==="
-docker logs "$CONTAINER_NAME" 2>&1
-echo ""
-echo -e "${RED}Smoke test FAILED${NC}"
-exit 1

docker/test-slim-local.sh

@@ -1,47 +0,0 @@
-#!/bin/bash
-#
-# Local Test Script for Slim Docker Images
-#
-# This script makes it easy to test slim images locally with external providers.
-# It expects API keys to be set in environment variables.
-#
-# Usage:
-#   export OPENAI_API_KEY=sk-xxx
-#   export COHERE_API_KEY=xxx
-#   ./docker/test-slim-local.sh
-#
-# Or inline:
-#   OPENAI_API_KEY=sk_xxx COHERE_API_KEY=xxx ./docker/test-slim-local.sh
-#
-
-set -euo pipefail
-
-# Check for required API keys
-if [ -z "${OPENAI_API_KEY:-}" ]; then
-    echo "❌ Error: OPENAI_API_KEY environment variable is required"
-    echo "Set it with: export OPENAI_API_KEY=sk-xxx"
-    exit 1
-fi
-
-if [ -z "${COHERE_API_KEY:-}" ]; then
-    echo "❌ Error: COHERE_API_KEY environment variable is required"
-    echo "Set it with: export COHERE_API_KEY=xxx"
-    exit 1
-fi
-
-# Configuration
-IMAGE="${1:-hindsight-slim:test}"
-echo "Testing image: $IMAGE"
-echo ""
-
-# Set up LLM and external providers
-export HINDSIGHT_API_LLM_PROVIDER=openai
-export HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY
-export HINDSIGHT_API_LLM_MODEL=gpt-4o-mini
-export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
-export HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=$OPENAI_API_KEY
-export HINDSIGHT_API_RERANKER_PROVIDER=cohere
-export HINDSIGHT_API_COHERE_API_KEY=$COHERE_API_KEY
-
-# Run the test
-exec "$(dirname "$0")/test-image.sh" "$IMAGE" standalone

helm/hindsight/Chart.yaml

@@ -2,8 +2,8 @@ apiVersion: v2
 name: hindsight
 description: Hindsight helm chart
 type: application
-version: 0.4.19
-appVersion: "0.4.19"
+version: 0.4.1
+appVersion: "0.4.1"
 keywords:
   - ai
   - memory

helm/hindsight/templates/_helpers.tpl

@@ -127,38 +127,6 @@ API URL for control plane
 {{- printf "http://%s-api:%d" (include "hindsight.fullname" .) (.Values.api.service.port | int) }}
 {{- end }}
 
-{{/*
-TEI reranker labels
-*/}}
-{{- define "hindsight.tei.reranker.labels" -}}
-{{ include "hindsight.labels" . }}
-app.kubernetes.io/component: tei-reranker
-{{- end }}
-
-{{/*
-TEI reranker selector labels
-*/}}
-{{- define "hindsight.tei.reranker.selectorLabels" -}}
-{{ include "hindsight.selectorLabels" . }}
-app.kubernetes.io/component: tei-reranker
-{{- end }}
-
-{{/*
-TEI embedding labels
-*/}}
-{{- define "hindsight.tei.embedding.labels" -}}
-{{ include "hindsight.labels" . }}
-app.kubernetes.io/component: tei-embedding
-{{- end }}
-
-{{/*
-TEI embedding selector labels
-*/}}
-{{- define "hindsight.tei.embedding.selectorLabels" -}}
-{{ include "hindsight.selectorLabels" . }}
-app.kubernetes.io/component: tei-embedding
-{{- end }}
-
 {{/*
 Get the name of the secret to use
 */}}

helm/hindsight/templates/api-deployment.yaml

@@ -33,7 +33,7 @@ spec:
       - name: api
         securityContext:
           {{- toYaml .Values.securityContext | nindent 10 }}
-        image: "{{ .Values.api.image.repository }}:{{ .Values.api.image.tag | default .Values.version | default .Chart.AppVersion }}"
+        image: "{{ .Values.api.image.repository }}:{{ .Values.api.image.tag | default .Values.version }}"
         imagePullPolicy: {{ .Values.api.image.pullPolicy }}
         ports:
         - name: http
@@ -60,25 +60,10 @@ spec:
         - name: HINDSIGHT_API_WORKER_ENABLED
           value: "false"
         {{- end }}
-        {{- /* Explicitly set port to override K8s service discovery env var (HINDSIGHT_API_PORT) */}}
-        - name: HINDSIGHT_API_PORT
-          value: {{ .Values.api.service.targetPort | quote }}
         {{- range $key, $value := .Values.api.env }}
         - name: {{ $key }}
           value: {{ $value | quote }}
         {{- end }}
-        {{- if .Values.tei.reranker.enabled }}
-        - name: HINDSIGHT_API_RERANKER_PROVIDER
-          value: "tei"
-        - name: HINDSIGHT_API_RERANKER_TEI_URL
-          value: "http://{{ include "hindsight.fullname" . }}-tei-reranker:{{ .Values.tei.reranker.port }}"
-        {{- end }}
-        {{- if .Values.tei.embedding.enabled }}
-        - name: HINDSIGHT_API_EMBEDDINGS_PROVIDER
-          value: "tei"
-        - name: HINDSIGHT_API_EMBEDDINGS_TEI_URL
-          value: "http://{{ include "hindsight.fullname" . }}-tei-embedding:{{ .Values.tei.embedding.port }}"
-        {{- end }}
         {{- /* Only use api.secrets when not using existingSecret (for chart-managed secrets) */}}
         {{- if not .Values.existingSecret }}
         {{- range $key, $value := .Values.api.secrets }}
@@ -99,7 +84,7 @@ spec:
       nodeSelector:
         {{- toYaml . | nindent 8 }}
       {{- end }}
-      {{- with (.Values.api.affinity | default .Values.affinity) }}
+      {{- with .Values.affinity }}
       affinity:
         {{- toYaml . | nindent 8 }}
       {{- end }}

helm/hindsight/templates/controlplane-deployment.yaml

@@ -33,7 +33,7 @@ spec:
       - name: control-plane
         securityContext:
           {{- toYaml .Values.securityContext | nindent 10 }}
-        image: "{{ .Values.controlPlane.image.repository }}:{{ .Values.controlPlane.image.tag | default .Values.version | default .Chart.AppVersion }}"
+        image: "{{ .Values.controlPlane.image.repository }}:{{ .Values.controlPlane.image.tag | default .Values.version }}"
         imagePullPolicy: {{ .Values.controlPlane.image.pullPolicy }}
         ports:
         - name: http
@@ -71,7 +71,7 @@ spec:
       nodeSelector:
         {{- toYaml . | nindent 8 }}
       {{- end }}
-      {{- with (.Values.controlPlane.affinity | default .Values.affinity) }}
+      {{- with .Values.affinity }}
       affinity:
         {{- toYaml . | nindent 8 }}
       {{- end }}

helm/hindsight/templates/pdb.yaml

@@ -1,56 +0,0 @@
-{{- if and .Values.api.enabled .Values.api.podDisruptionBudget.enabled }}
-apiVersion: policy/v1
-kind: PodDisruptionBudget
-metadata:
-  name: {{ include "hindsight.fullname" . }}-api
-  labels:
-    {{- include "hindsight.api.labels" . | nindent 4 }}
-spec:
-  {{- if .Values.api.podDisruptionBudget.minAvailable }}
-  minAvailable: {{ .Values.api.podDisruptionBudget.minAvailable }}
-  {{- end }}
-  {{- if .Values.api.podDisruptionBudget.maxUnavailable }}
-  maxUnavailable: {{ .Values.api.podDisruptionBudget.maxUnavailable }}
-  {{- end }}
-  selector:
-    matchLabels:
-      {{- include "hindsight.api.selectorLabels" . | nindent 6 }}
-{{- end }}
----
-{{- if and .Values.controlPlane.enabled .Values.controlPlane.podDisruptionBudget.enabled }}
-apiVersion: policy/v1
-kind: PodDisruptionBudget
-metadata:
-  name: {{ include "hindsight.fullname" . }}-control-plane
-  labels:
-    {{- include "hindsight.controlPlane.labels" . | nindent 4 }}
-spec:
-  {{- if .Values.controlPlane.podDisruptionBudget.minAvailable }}
-  minAvailable: {{ .Values.controlPlane.podDisruptionBudget.minAvailable }}
-  {{- end }}
-  {{- if .Values.controlPlane.podDisruptionBudget.maxUnavailable }}
-  maxUnavailable: {{ .Values.controlPlane.podDisruptionBudget.maxUnavailable }}
-  {{- end }}
-  selector:
-    matchLabels:
-      {{- include "hindsight.controlPlane.selectorLabels" . | nindent 6 }}
-{{- end }}
----
-{{- if and .Values.worker.enabled .Values.worker.podDisruptionBudget.enabled }}
-apiVersion: policy/v1
-kind: PodDisruptionBudget
-metadata:
-  name: {{ include "hindsight.fullname" . }}-worker
-  labels:
-    {{- include "hindsight.worker.labels" . | nindent 4 }}
-spec:
-  {{- if .Values.worker.podDisruptionBudget.minAvailable }}
-  minAvailable: {{ .Values.worker.podDisruptionBudget.minAvailable }}
-  {{- end }}
-  {{- if .Values.worker.podDisruptionBudget.maxUnavailable }}
-  maxUnavailable: {{ .Values.worker.podDisruptionBudget.maxUnavailable }}
-  {{- end }}
-  selector:
-    matchLabels:
-      {{- include "hindsight.worker.selectorLabels" . | nindent 6 }}
-{{- end }}

helm/hindsight/templates/tei-embedding-deployment.yaml

@@ -1,76 +0,0 @@
-{{- if .Values.tei.embedding.enabled }}
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: {{ include "hindsight.fullname" . }}-tei-embedding
-  labels:
-    {{- include "hindsight.tei.embedding.labels" . | nindent 4 }}
-spec:
-  replicas: {{ .Values.tei.embedding.replicaCount }}
-  selector:
-    matchLabels:
-      {{- include "hindsight.tei.embedding.selectorLabels" . | nindent 6 }}
-  template:
-    metadata:
-      {{- with .Values.podAnnotations }}
-      annotations:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      labels:
-        {{- include "hindsight.tei.embedding.selectorLabels" . | nindent 8 }}
-    spec:
-      {{- if .Values.serviceAccount.create }}
-      serviceAccountName: {{ include "hindsight.serviceAccountName" . }}
-      {{- end }}
-      securityContext:
-        {{- toYaml .Values.podSecurityContext | nindent 8 }}
-      containers:
-      - name: tei-embedding
-        securityContext:
-          {{- toYaml .Values.securityContext | nindent 10 }}
-        image: "{{ .Values.tei.embedding.image.repository }}:{{ .Values.tei.embedding.image.tag }}"
-        imagePullPolicy: {{ .Values.tei.embedding.image.pullPolicy }}
-        args:
-          - "--model-id"
-          - {{ .Values.tei.embedding.model | quote }}
-          - "--hostname"
-          - "0.0.0.0"
-          {{- range .Values.tei.embedding.args }}
-          - {{ . | quote }}
-          {{- end }}
-        ports:
-        - name: http
-          containerPort: {{ .Values.tei.embedding.port }}
-          protocol: TCP
-        env:
-        - name: PORT
-          value: {{ .Values.tei.embedding.port | quote }}
-        {{- range $key, $value := .Values.tei.embedding.env }}
-        - name: {{ $key }}
-          value: {{ $value | quote }}
-        {{- end }}
-        livenessProbe:
-          {{- toYaml .Values.tei.embedding.livenessProbe | nindent 10 }}
-        readinessProbe:
-          {{- toYaml .Values.tei.embedding.readinessProbe | nindent 10 }}
-        resources:
-          {{- toYaml .Values.tei.embedding.resources | nindent 10 }}
-        volumeMounts:
-        - name: model-cache
-          mountPath: /data
-      volumes:
-      - name: model-cache
-        emptyDir: {}
-      {{- with .Values.nodeSelector }}
-      nodeSelector:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      {{- with .Values.affinity }}
-      affinity:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      {{- with .Values.tolerations }}
-      tolerations:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-{{- end }}

helm/hindsight/templates/tei-embedding-service.yaml

@@ -1,17 +0,0 @@
-{{- if .Values.tei.embedding.enabled }}
-apiVersion: v1
-kind: Service
-metadata:
-  name: {{ include "hindsight.fullname" . }}-tei-embedding
-  labels:
-    {{- include "hindsight.tei.embedding.labels" . | nindent 4 }}
-spec:
-  type: ClusterIP
-  ports:
-  - port: {{ .Values.tei.embedding.port }}
-    targetPort: http
-    protocol: TCP
-    name: http
-  selector:
-    {{- include "hindsight.tei.embedding.selectorLabels" . | nindent 4 }}
-{{- end }}

helm/hindsight/templates/tei-reranker-deployment.yaml

@@ -1,76 +0,0 @@
-{{- if .Values.tei.reranker.enabled }}
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: {{ include "hindsight.fullname" . }}-tei-reranker
-  labels:
-    {{- include "hindsight.tei.reranker.labels" . | nindent 4 }}
-spec:
-  replicas: {{ .Values.tei.reranker.replicaCount }}
-  selector:
-    matchLabels:
-      {{- include "hindsight.tei.reranker.selectorLabels" . | nindent 6 }}
-  template:
-    metadata:
-      {{- with .Values.podAnnotations }}
-      annotations:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      labels:
-        {{- include "hindsight.tei.reranker.selectorLabels" . | nindent 8 }}
-    spec:
-      {{- if .Values.serviceAccount.create }}
-      serviceAccountName: {{ include "hindsight.serviceAccountName" . }}
-      {{- end }}
-      securityContext:
-        {{- toYaml .Values.podSecurityContext | nindent 8 }}
-      containers:
-      - name: tei-reranker
-        securityContext:
-          {{- toYaml .Values.securityContext | nindent 10 }}
-        image: "{{ .Values.tei.reranker.image.repository }}:{{ .Values.tei.reranker.image.tag }}"
-        imagePullPolicy: {{ .Values.tei.reranker.image.pullPolicy }}
-        args:
-          - "--model-id"
-          - {{ .Values.tei.reranker.model | quote }}
-          - "--hostname"
-          - "0.0.0.0"
-          {{- range .Values.tei.reranker.args }}
-          - {{ . | quote }}
-          {{- end }}
-        ports:
-        - name: http
-          containerPort: {{ .Values.tei.reranker.port }}
-          protocol: TCP
-        env:
-        - name: PORT
-          value: {{ .Values.tei.reranker.port | quote }}
-        {{- range $key, $value := .Values.tei.reranker.env }}
-        - name: {{ $key }}
-          value: {{ $value | quote }}
-        {{- end }}
-        livenessProbe:
-          {{- toYaml .Values.tei.reranker.livenessProbe | nindent 10 }}
-        readinessProbe:
-          {{- toYaml .Values.tei.reranker.readinessProbe | nindent 10 }}
-        resources:
-          {{- toYaml .Values.tei.reranker.resources | nindent 10 }}
-        volumeMounts:
-        - name: model-cache
-          mountPath: /data
-      volumes:
-      - name: model-cache
-        emptyDir: {}
-      {{- with .Values.nodeSelector }}
-      nodeSelector:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      {{- with .Values.affinity }}
-      affinity:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      {{- with .Values.tolerations }}
-      tolerations:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-{{- end }}

helm/hindsight/templates/tei-reranker-service.yaml

@@ -1,17 +0,0 @@
-{{- if .Values.tei.reranker.enabled }}
-apiVersion: v1
-kind: Service
-metadata:
-  name: {{ include "hindsight.fullname" . }}-tei-reranker
-  labels:
-    {{- include "hindsight.tei.reranker.labels" . | nindent 4 }}
-spec:
-  type: ClusterIP
-  ports:
-  - port: {{ .Values.tei.reranker.port }}
-    targetPort: http
-    protocol: TCP
-    name: http
-  selector:
-    {{- include "hindsight.tei.reranker.selectorLabels" . | nindent 4 }}
-{{- end }}

helm/hindsight/templates/worker-statefulset.yaml

@@ -32,7 +32,7 @@ spec:
       - name: worker
         securityContext:
           {{- toYaml .Values.securityContext | nindent 10 }}
-        image: "{{ .Values.worker.image.repository }}:{{ .Values.worker.image.tag | default .Values.version | default .Chart.AppVersion }}"
+        image: "{{ .Values.worker.image.repository }}:{{ .Values.worker.image.tag | default .Values.version }}"
         imagePullPolicy: {{ .Values.worker.image.pullPolicy }}
         command: ["hindsight-worker"]
         ports:
@@ -99,7 +99,7 @@ spec:
       nodeSelector:
         {{- toYaml . | nindent 8 }}
       {{- end }}
-      {{- with (.Values.worker.affinity | default .Values.affinity) }}
+      {{- with .Values.affinity }}
       affinity:
         {{- toYaml . | nindent 8 }}
       {{- end }}

helm/hindsight/values.yaml

@@ -1,8 +1,7 @@
 # Default values for hindsight
 
-# Global version override - use this to set a consistent image tag across all components
-# If not set, defaults to Chart.appVersion from Chart.yaml
-# version: ""
+# Chart version - use this to set a consistent image tag across all components
+version: "0.1.1"
 
 # Use an existing secret instead of creating one from values
 # When set, all keys from this secret are injected as environment variables via envFrom
@@ -58,15 +57,6 @@ api:
     timeoutSeconds: 3
     failureThreshold: 3
 
-  # Pod disruption budget
-  podDisruptionBudget:
-    enabled: false
-    minAvailable: 1
-    # maxUnavailable: 1
-
-  # Pod affinity/anti-affinity (overrides global affinity for this component)
-  # affinity: {}
-
   # Environment variables
   env:
     #HINDSIGHT_API_LLM_PROVIDER: "groq"
@@ -85,7 +75,7 @@ worker:
   image:
     repository: ghcr.io/vectorize-io/hindsight-api
     pullPolicy: IfNotPresent
-    # tag: ""  # defaults to .Values.version, then Chart.appVersion if not specified
+    # tag defaults to .Values.version if not specified
 
   service:
     # Service for metrics scraping (headless for StatefulSet)
@@ -131,15 +121,6 @@ worker:
     # HTTP port for metrics/health (matches service.targetPort)
     HINDSIGHT_API_WORKER_HTTP_PORT: "8889"
 
-  # Pod disruption budget
-  podDisruptionBudget:
-    enabled: false
-    minAvailable: 1
-    # maxUnavailable: 1
-
-  # Pod affinity/anti-affinity (overrides global affinity for this component)
-  # affinity: {}
-
   # Secret environment variables (inherited from api.secrets if not specified)
   secrets: {}
 
@@ -183,15 +164,6 @@ controlPlane:
     timeoutSeconds: 3
     failureThreshold: 3
 
-  # Pod disruption budget
-  podDisruptionBudget:
-    enabled: false
-    minAvailable: 1
-    # maxUnavailable: 1
-
-  # Pod affinity/anti-affinity (overrides global affinity for this component)
-  # affinity: {}
-
   # Environment variables
   env:
     NODE_ENV: "production"
@@ -290,87 +262,9 @@ nodeSelector: {}
 # Tolerations
 tolerations: []
 
-# Affinity (applied to all components unless overridden per-component)
+# Affinity
 affinity: {}
 
-# TEI (Text Embeddings Inference) - optional standalone deployments
-# for reranking and/or embedding models
-tei:
-  reranker:
-    enabled: false
-    replicaCount: 1
-    image:
-      repository: ghcr.io/huggingface/text-embeddings-inference
-      tag: cpu-1.8.3
-      pullPolicy: IfNotPresent
-    model: "cross-encoder/ms-marco-MiniLM-L-6-v2"
-    port: 8090
-    args:
-      - "--auto-truncate"
-    env:
-      PAYLOAD_LIMIT: "10000000"
-      MAX_CLIENT_BATCH_SIZE: "256"
-    resources:
-      limits:
-        cpu: 2000m
-        memory: 2Gi
-      requests:
-        cpu: 500m
-        memory: 1Gi
-    livenessProbe:
-      httpGet:
-        path: /health
-        port: 8090
-      initialDelaySeconds: 30
-      periodSeconds: 10
-      timeoutSeconds: 5
-      failureThreshold: 6
-    readinessProbe:
-      httpGet:
-        path: /health
-        port: 8090
-      initialDelaySeconds: 15
-      periodSeconds: 5
-      timeoutSeconds: 3
-      failureThreshold: 3
-
-  embedding:
-    enabled: false
-    replicaCount: 1
-    image:
-      repository: ghcr.io/huggingface/text-embeddings-inference
-      tag: cpu-1.8.3
-      pullPolicy: IfNotPresent
-    model: "sentence-transformers/all-MiniLM-L6-v2"
-    port: 8091
-    args: []
-    env:
-      PAYLOAD_LIMIT: "10000000"
-      MAX_CLIENT_BATCH_SIZE: "256"
-    resources:
-      limits:
-        cpu: 2000m
-        memory: 2Gi
-      requests:
-        cpu: 500m
-        memory: 1Gi
-    livenessProbe:
-      httpGet:
-        path: /health
-        port: 8091
-      initialDelaySeconds: 30
-      periodSeconds: 10
-      timeoutSeconds: 5
-      failureThreshold: 6
-    readinessProbe:
-      httpGet:
-        path: /health
-        port: 8091
-      initialDelaySeconds: 15
-      periodSeconds: 5
-      timeoutSeconds: 3
-      failureThreshold: 3
-
 # Autoscaling
 autoscaling:
   enabled: false

hindsight-all-slim/pyproject.toml

@@ -1,33 +0,0 @@
-[build-system]
-requires = ["setuptools>=61"]
-build-backend = "setuptools.build_meta"
-
-[project]
-name = "hindsight-all-slim"
-version = "0.4.19"
-description = "Hindsight: Agent Memory That Works Like Human Memory - Slim All-in-One Bundle"
-readme = "README.md"
-requires-python = ">=3.11"
-dependencies = [
-    "hindsight-api-slim>=0.4.17",
-    "hindsight-client>=0.0.7",
-    "hindsight-embed>=0.1.0",
-]
-
-[tool.uv.sources]
-hindsight-api-slim = { workspace = true }
-hindsight-client = { workspace = true }
-hindsight-embed = { workspace = true }
-
-[project.optional-dependencies]
-test = [
-    "pytest>=7.0.0",
-    "pytest-asyncio>=0.21.0",
-]
-
-[tool.setuptools]
-packages = []
-
-[tool.pytest.ini_options]
-asyncio_mode = "auto"
-asyncio_default_fixture_loop_scope = "function"

hindsight-all/README.md

@@ -1,48 +0,0 @@
-# hindsight-all
-
-All-in-one package for Hindsight - Agent Memory That Works Like Human Memory
-
-## Quick Start
-
-```python
-from hindsight import start_server, HindsightClient
-
-# Start server with embedded PostgreSQL
-server = start_server(
-    llm_provider="groq",
-    llm_api_key="your-api-key",
-    llm_model="openai/gpt-oss-120b"
-)
-
-# Create client
-client = HindsightClient(base_url=server.url)
-
-# Store memories
-client.put(agent_id="assistant", content="User prefers Python for data analysis")
-
-# Search memories
-results = client.search(agent_id="assistant", query="programming preferences")
-
-# Generate contextual response
-response = client.think(agent_id="assistant", query="What languages should I recommend?")
-
-# Stop server when done
-server.stop()
-```
-
-## Using Context Manager
-
-```python
-from hindsight import HindsightServer, HindsightClient
-
-with HindsightServer(llm_provider="groq", llm_api_key="...") as server:
-    client = HindsightClient(base_url=server.url)
-    # ... use client ...
-# Server automatically stops
-```
-
-## Installation
-
-```bash
-pip install hindsight-all
-```

hindsight-all/hindsight/api_namespaces.py

@@ -1,193 +0,0 @@
-"""
-API namespace classes for organizing client methods.
-
-These classes provide organized access to different parts of the Hindsight API
-while ensuring the daemon is running before each call.
-"""
-
-from __future__ import annotations
-
-from typing import TYPE_CHECKING, Any
-
-if TYPE_CHECKING:
-    from .embedded import HindsightEmbedded
-
-
-class BanksAPI:
-    """Namespace for bank-related operations."""
-
-    def __init__(self, embedded: "HindsightEmbedded"):
-        self._embedded = embedded
-
-    def create(
-        self,
-        bank_id: str,
-        name: str | None = None,
-        mission: str | None = None,
-        disposition: dict[str, Any] | None = None,
-    ):
-        """Create a new bank."""
-        self._embedded._ensure_started()
-        return self._embedded._client.create_bank(
-            bank_id=bank_id,
-            name=name,
-            mission=mission,
-            disposition=disposition,
-        )
-
-    def delete(self, bank_id: str):
-        """Delete a bank."""
-        self._embedded._ensure_started()
-        return self._embedded._client.delete_bank(bank_id=bank_id)
-
-    def set_mission(self, bank_id: str, mission: str):
-        """Set or update the mission for a bank."""
-        self._embedded._ensure_started()
-        return self._embedded._client.set_mission(bank_id=bank_id, mission=mission)
-
-    def set_disposition(self, bank_id: str, disposition: dict[str, Any]):
-        """Set or update the disposition for a bank."""
-        self._embedded._ensure_started()
-        return self._embedded._client.set_disposition(bank_id=bank_id, disposition=disposition)
-
-
-class MentalModelsAPI:
-    """Namespace for mental model operations."""
-
-    def __init__(self, embedded: "HindsightEmbedded"):
-        self._embedded = embedded
-
-    def create(
-        self,
-        bank_id: str,
-        name: str,
-        content: str,
-        tags: list[str] | None = None,
-    ):
-        """Create a new mental model."""
-        self._embedded._ensure_started()
-        return self._embedded._client.create_mental_model(
-            bank_id=bank_id,
-            name=name,
-            content=content,
-            tags=tags,
-        )
-
-    def list(self, bank_id: str, tags: list[str] | None = None):
-        """List all mental models for a bank."""
-        self._embedded._ensure_started()
-        return self._embedded._client.list_mental_models(bank_id=bank_id, tags=tags)
-
-    def get(self, bank_id: str, mental_model_id: str):
-        """Get a specific mental model."""
-        self._embedded._ensure_started()
-        return self._embedded._client.get_mental_model(bank_id=bank_id, mental_model_id=mental_model_id)
-
-    def refresh(self, bank_id: str, mental_model_id: str):
-        """Refresh a mental model."""
-        self._embedded._ensure_started()
-        return self._embedded._client.refresh_mental_model(bank_id=bank_id, mental_model_id=mental_model_id)
-
-    def update(
-        self,
-        bank_id: str,
-        mental_model_id: str,
-        name: str | None = None,
-        content: str | None = None,
-        tags: list[str] | None = None,
-    ):
-        """Update a mental model."""
-        self._embedded._ensure_started()
-        return self._embedded._client.update_mental_model(
-            bank_id=bank_id,
-            mental_model_id=mental_model_id,
-            name=name,
-            content=content,
-            tags=tags,
-        )
-
-    def delete(self, bank_id: str, mental_model_id: str):
-        """Delete a mental model."""
-        self._embedded._ensure_started()
-        return self._embedded._client.delete_mental_model(bank_id=bank_id, mental_model_id=mental_model_id)
-
-
-class DirectivesAPI:
-    """Namespace for directive operations."""
-
-    def __init__(self, embedded: "HindsightEmbedded"):
-        self._embedded = embedded
-
-    def create(
-        self,
-        bank_id: str,
-        name: str,
-        content: str,
-        tags: list[str] | None = None,
-    ):
-        """Create a new directive."""
-        self._embedded._ensure_started()
-        return self._embedded._client.create_directive(
-            bank_id=bank_id,
-            name=name,
-            content=content,
-            tags=tags,
-        )
-
-    def list(self, bank_id: str, tags: list[str] | None = None):
-        """List all directives for a bank."""
-        self._embedded._ensure_started()
-        return self._embedded._client.list_directives(bank_id=bank_id, tags=tags)
-
-    def get(self, bank_id: str, directive_id: str):
-        """Get a specific directive."""
-        self._embedded._ensure_started()
-        return self._embedded._client.get_directive(bank_id=bank_id, directive_id=directive_id)
-
-    def update(
-        self,
-        bank_id: str,
-        directive_id: str,
-        name: str | None = None,
-        content: str | None = None,
-        tags: list[str] | None = None,
-    ):
-        """Update a directive."""
-        self._embedded._ensure_started()
-        return self._embedded._client.update_directive(
-            bank_id=bank_id,
-            directive_id=directive_id,
-            name=name,
-            content=content,
-            tags=tags,
-        )
-
-    def delete(self, bank_id: str, directive_id: str):
-        """Delete a directive."""
-        self._embedded._ensure_started()
-        return self._embedded._client.delete_directive(bank_id=bank_id, directive_id=directive_id)
-
-
-class MemoriesAPI:
-    """Namespace for memory operations."""
-
-    def __init__(self, embedded: "HindsightEmbedded"):
-        self._embedded = embedded
-
-    def list(
-        self,
-        bank_id: str,
-        type: str | None = None,
-        search_query: str | None = None,
-        limit: int = 100,
-        offset: int = 0,
-    ):
-        """List memories in a bank."""
-        self._embedded._ensure_started()
-        return self._embedded._client.list_memories(
-            bank_id=bank_id,
-            type=type,
-            search_query=search_query,
-            limit=limit,
-            offset=offset,
-        )

hindsight-all/hindsight/client_wrapper.py

@@ -1,423 +0,0 @@
-"""
-Wrapper for Hindsight client that adds API namespaces.
-
-Provides organized access to different parts of the Hindsight API through
-namespaces like .banks, .mental_models, etc.
-"""
-
-from __future__ import annotations
-
-from typing import Any
-
-from hindsight_client import Hindsight
-
-
-class BanksAPI:
-    """Namespace for bank-related operations.
-    
-    Provides methods to create, delete, and manage memory banks.
-    """
-
-    def __init__(self, client: Hindsight):
-        self._client = client
-
-    def create(
-        self,
-        bank_id: str,
-        name: str | None = None,
-        mission: str | None = None,
-        disposition: dict[str, Any] | None = None,
-    ) -> Any:
-        """Create a new bank.
-        
-        Args:
-            bank_id: Unique identifier for the bank.
-            name: Optional display name for the bank.
-            mission: Optional mission statement for the bank.
-            disposition: Optional disposition configuration dict.
-            
-        Returns:
-            Bank creation response from the API.
-        """
-        return self._client.create_bank(
-            bank_id=bank_id,
-            name=name,
-            mission=mission,
-            disposition=disposition,
-        )
-
-    def delete(self, bank_id: str) -> Any:
-        """Delete a bank.
-        
-        Args:
-            bank_id: The ID of the bank to delete.
-            
-        Returns:
-            Deletion response from the API.
-        """
-        return self._client.delete_bank(bank_id=bank_id)
-
-    def set_mission(self, bank_id: str, mission: str) -> Any:
-        """Set or update the mission for a bank.
-        
-        Args:
-            bank_id: The ID of the bank.
-            mission: The mission statement to set.
-            
-        Returns:
-            API response confirming the update.
-        """
-        return self._client.set_mission(bank_id=bank_id, mission=mission)
-
-    def set_disposition(self, bank_id: str, disposition: dict[str, Any]) -> Any:
-        """Set or update the disposition for a bank.
-        
-        Args:
-            bank_id: The ID of the bank.
-            disposition: The disposition configuration dict.
-            
-        Returns:
-            API response confirming the update.
-        """
-        return self._client.set_disposition(bank_id=bank_id, disposition=disposition)
-
-    def list(self) -> Any:
-        """List all banks.
-        
-        Returns:
-            List of banks from the API.
-        """
-        from hindsight_client.hindsight_client import _run_async
-
-        return _run_async(self._client._banks_api.list_banks())
-
-
-class MentalModelsAPI:
-    """Namespace for mental model operations.
-    
-    Mental models are reusable knowledge structures that guide agent behavior.
-    """
-
-    def __init__(self, client: Hindsight):
-        self._client = client
-
-    def create(
-        self,
-        bank_id: str,
-        name: str,
-        content: str,
-        tags: list[str] | None = None,
-    ) -> Any:
-        """Create a new mental model.
-        
-        Args:
-            bank_id: The ID of the bank to add the model to.
-            name: Name for the mental model.
-            content: The content/instructions for the mental model.
-            tags: Optional list of tags for categorization.
-            
-        Returns:
-            Creation response from the API.
-        """
-        return self._client.create_mental_model(
-            bank_id=bank_id,
-            name=name,
-            content=content,
-            tags=tags,
-        )
-
-    def list(self, bank_id: str, tags: list[str] | None = None) -> Any:
-        """List all mental models for a bank.
-        
-        Args:
-            bank_id: The ID of the bank.
-            tags: Optional filter by tags.
-            
-        Returns:
-            List of mental models.
-        """
-        return self._client.list_mental_models(bank_id=bank_id, tags=tags)
-
-    def get(self, bank_id: str, mental_model_id: str) -> Any:
-        """Get a specific mental model.
-        
-        Args:
-            bank_id: The ID of the bank.
-            mental_model_id: The ID of the mental model.
-            
-        Returns:
-            The mental model details.
-        """
-        return self._client.get_mental_model(bank_id=bank_id, mental_model_id=mental_model_id)
-
-    def refresh(self, bank_id: str, mental_model_id: str) -> Any:
-        """Refresh a mental model.
-        
-        Args:
-            bank_id: The ID of the bank.
-            mental_model_id: The ID of the mental model to refresh.
-            
-        Returns:
-            Refresh response from the API.
-        """
-        return self._client.refresh_mental_model(bank_id=bank_id, mental_model_id=mental_model_id)
-
-    def update(
-        self,
-        bank_id: str,
-        mental_model_id: str,
-        name: str | None = None,
-        content: str | None = None,
-        tags: list[str] | None = None,
-    ) -> Any:
-        """Update a mental model.
-        
-        Args:
-            bank_id: The ID of the bank.
-            mental_model_id: The ID of the mental model to update.
-            name: Optional new name.
-            content: Optional new content.
-            tags: Optional new tags list.
-            
-        Returns:
-            Update response from the API.
-        """
-        return self._client.update_mental_model(
-            bank_id=bank_id,
-            mental_model_id=mental_model_id,
-            name=name,
-            content=content,
-            tags=tags,
-        )
-
-    def delete(self, bank_id: str, mental_model_id: str) -> Any:
-        """Delete a mental model.
-        
-        Args:
-            bank_id: The ID of the bank.
-            mental_model_id: The ID of the mental model to delete.
-            
-        Returns:
-            Deletion response from the API.
-        """
-        return self._client.delete_mental_model(bank_id=bank_id, mental_model_id=mental_model_id)
-
-
-class DirectivesAPI:
-    """Namespace for directive operations.
-    
-    Directives are explicit instructions that guide agent behavior.
-    """
-
-    def __init__(self, client: Hindsight):
-        self._client = client
-
-    def create(
-        self,
-        bank_id: str,
-        name: str,
-        content: str,
-        tags: list[str] | None = None,
-    ) -> Any:
-        """Create a new directive.
-        
-        Args:
-            bank_id: The ID of the bank to add the directive to.
-            name: Name for the directive.
-            content: The directive content/instructions.
-            tags: Optional list of tags for categorization.
-            
-        Returns:
-            Creation response from the API.
-        """
-        return self._client.create_directive(
-            bank_id=bank_id,
-            name=name,
-            content=content,
-            tags=tags,
-        )
-
-    def list(self, bank_id: str, tags: list[str] | None = None) -> Any:
-        """List all directives for a bank.
-        
-        Args:
-            bank_id: The ID of the bank.
-            tags: Optional filter by tags.
-            
-        Returns:
-            List of directives.
-        """
-        return self._client.list_directives(bank_id=bank_id, tags=tags)
-
-    def get(self, bank_id: str, directive_id: str) -> Any:
-        """Get a specific directive.
-        
-        Args:
-            bank_id: The ID of the bank.
-            directive_id: The ID of the directive.
-            
-        Returns:
-            The directive details.
-        """
-        return self._client.get_directive(bank_id=bank_id, directive_id=directive_id)
-
-    def update(
-        self,
-        bank_id: str,
-        directive_id: str,
-        name: str | None = None,
-        content: str | None = None,
-        tags: list[str] | None = None,
-    ) -> Any:
-        """Update a directive.
-        
-        Args:
-            bank_id: The ID of the bank.
-            directive_id: The ID of the directive to update.
-            name: Optional new name.
-            content: Optional new content.
-            tags: Optional new tags list.
-            
-        Returns:
-            Update response from the API.
-        """
-        return self._client.update_directive(
-            bank_id=bank_id,
-            directive_id=directive_id,
-            name=name,
-            content=content,
-            tags=tags,
-        )
-
-    def delete(self, bank_id: str, directive_id: str) -> Any:
-        """Delete a directive.
-        
-        Args:
-            bank_id: The ID of the bank.
-            directive_id: The ID of the directive to delete.
-            
-        Returns:
-            Deletion response from the API.
-        """
-        return self._client.delete_directive(bank_id=bank_id, directive_id=directive_id)
-
-
-class MemoriesAPI:
-    """Namespace for memory operations.
-    
-    Provides methods to query and retrieve stored memories.
-    """
-
-    def __init__(self, client: Hindsight):
-        self._client = client
-
-    def list(
-        self,
-        bank_id: str,
-        type: str | None = None,
-        search_query: str | None = None,
-        limit: int = 100,
-        offset: int = 0,
-    ) -> Any:
-        """List memories in a bank.
-        
-        Args:
-            bank_id: The ID of the bank to query.
-            type: Optional filter by memory type.
-            search_query: Optional search query for filtering.
-            limit: Maximum number of results to return (default: 100).
-            offset: Number of results to skip for pagination (default: 0).
-            
-        Returns:
-            List of memories matching the criteria.
-        """
-        return self._client.list_memories(
-            bank_id=bank_id,
-            type=type,
-            search_query=search_query,
-            limit=limit,
-            offset=offset,
-        )
-
-
-class HindsightClient(Hindsight):
-    """
-    Enhanced Hindsight client with organized API namespaces.
-
-    This wrapper extends the auto-generated Hindsight client with organized
-    access to different parts of the API through namespaces.
-
-    Example:
-        ```python
-        from hindsight import HindsightClient
-
-        client = HindsightClient(base_url="http://localhost:8888")
-
-        # Core operations (inherited from Hindsight)
-        client.retain(bank_id="test", content="Hello")
-        results = client.recall(bank_id="test", query="Hello")
-
-        # Organized API access through namespaces
-        client.banks.create(bank_id="test", name="Test Bank")
-        models = client.mental_models.list(bank_id="test")
-        directives = client.directives.list(bank_id="test")
-        memories = client.memories.list(bank_id="test")
-        ```
-        
-    Attributes:
-        banks: Namespace for bank management operations.
-        mental_models: Namespace for mental model operations.
-        directives: Namespace for directive operations.
-        memories: Namespace for memory listing operations.
-    """
-
-    def __init__(self, *args: Any, **kwargs: Any) -> None:
-        super().__init__(*args, **kwargs)
-        self._banks_namespace: BanksAPI | None = None
-        self._mental_models_namespace: MentalModelsAPI | None = None
-        self._directives_namespace: DirectivesAPI | None = None
-        self._memories_namespace: MemoriesAPI | None = None
-
-    @property
-    def banks(self) -> BanksAPI:
-        """Access bank management operations.
-        
-        Returns:
-            BanksAPI instance for bank operations.
-        """
-        if self._banks_namespace is None:
-            self._banks_namespace = BanksAPI(self)
-        return self._banks_namespace
-
-    @property
-    def mental_models(self) -> MentalModelsAPI:
-        """Access mental model operations.
-        
-        Returns:
-            MentalModelsAPI instance for mental model operations.
-        """
-        if self._mental_models_namespace is None:
-            self._mental_models_namespace = MentalModelsAPI(self)
-        return self._mental_models_namespace
-
-    @property
-    def directives(self) -> DirectivesAPI:
-        """Access directive operations.
-        
-        Returns:
-            DirectivesAPI instance for directive operations.
-        """
-        if self._directives_namespace is None:
-            self._directives_namespace = DirectivesAPI(self)
-        return self._directives_namespace
-
-    @property
-    def memories(self) -> MemoriesAPI:
-        """Access memory listing operations.
-        
-        Returns:
-            MemoriesAPI instance for memory operations.
-        """
-        if self._memories_namespace is None:
-            self._memories_namespace = MemoriesAPI(self)
-        return self._memories_namespace

hindsight-all/hindsight/embedded.py

@@ -1,377 +0,0 @@
-"""
-Embedded Hindsight client with automatic daemon lifecycle management.
-
-This module provides HindsightEmbedded, a client that uses the same daemon
-management interface as hindsight-embed CLI, ensuring full compatibility.
-
-Example:
-    ```python
-    from hindsight import HindsightEmbedded
-
-    # Daemon starts automatically on first use
-    client = HindsightEmbedded(
-        profile="myapp",
-        llm_provider="groq",
-        llm_api_key="your-api-key",
-    )
-
-    # Use just like HindsightClient
-    client.retain(bank_id="alice", content="Alice loves AI")
-    results = client.recall(bank_id="alice", query="What does Alice like?")
-
-    # Optional cleanup
-    client.close()
-    ```
-
-Using context manager:
-    ```python
-    from hindsight import HindsightEmbedded
-
-    with HindsightEmbedded(profile="myapp") as client:
-        client.retain(bank_id="alice", content="Alice loves AI")
-        # Daemon managed automatically
-    ```
-"""
-
-import logging
-import os
-import threading
-from typing import Optional
-
-from hindsight_client import Hindsight
-from hindsight_embed import get_embed_manager
-
-from .api_namespaces import BanksAPI, DirectivesAPI, MemoriesAPI, MentalModelsAPI
-
-logger = logging.getLogger(__name__)
-
-
-class HindsightEmbedded:
-    """
-    Hindsight client with automatic daemon lifecycle management.
-
-    This client uses the same daemon management interface as hindsight-embed CLI,
-    ensuring full compatibility and shared profiles. The daemon is started automatically
-    on first use and manages profile-specific databases.
-
-    Profile data is stored in: ~/.pg0/instances/hindsight-embed-{profile}/
-
-    All methods from HindsightClient are available:
-    - retain(), retain_batch()
-    - recall()
-    - reflect()
-    - create_bank(), set_mission(), delete_bank()
-    - create_mental_model(), list_mental_models(), etc.
-    - create_directive(), list_directives(), etc.
-    - And all async variants (aretain, arecall, areflect, etc.)
-
-    Args:
-        profile: Profile name for data isolation (default: "default")
-        llm_provider: LLM provider ("groq", "openai", "ollama", "gemini", "anthropic", "lmstudio")
-        llm_api_key: API key for the LLM provider
-        llm_model: Model name to use
-        llm_base_url: Optional custom base URL for LLM API
-        database_url: Optional database URL override (default: profile-specific pg0)
-        idle_timeout: Seconds before daemon auto-exits when idle (default: 300)
-        log_level: Daemon log level (default: "info")
-    """
-
-    def __init__(
-        self,
-        profile: str = "default",
-        llm_provider: str = "groq",
-        llm_api_key: str = "",
-        llm_model: str = "openai/gpt-oss-120b",
-        llm_base_url: Optional[str] = None,
-        database_url: Optional[str] = None,
-        idle_timeout: int = 300,
-        log_level: str = "info",
-    ):
-        """
-        Initialize the embedded client (daemon starts on first use).
-
-        Args:
-            profile: Profile name for data isolation
-            llm_provider: LLM provider
-            llm_api_key: API key for the LLM provider
-            llm_model: Model name to use
-            llm_base_url: Optional custom base URL for LLM API
-            database_url: Optional database URL override
-            idle_timeout: Seconds before daemon auto-exits when idle
-            log_level: Daemon log level
-        """
-        self.profile = profile
-
-        # Build config dict for daemon (matches CLI format)
-        self.config = {
-            "HINDSIGHT_API_LLM_PROVIDER": llm_provider,
-            "HINDSIGHT_API_LLM_API_KEY": llm_api_key,
-            "HINDSIGHT_API_LLM_MODEL": llm_model,
-            "HINDSIGHT_API_LOG_LEVEL": log_level,
-            "HINDSIGHT_EMBED_DAEMON_IDLE_TIMEOUT": str(idle_timeout),
-        }
-
-        if llm_base_url:
-            self.config["HINDSIGHT_API_LLM_BASE_URL"] = llm_base_url
-
-        if database_url:
-            self.config["HINDSIGHT_EMBED_API_DATABASE_URL"] = database_url
-
-        self._client: Optional[Hindsight] = None
-        self._lock = threading.Lock()
-        self._started = False
-        self._closed = False
-        self._manager = get_embed_manager()
-
-        # API namespaces (initialized once, lazily)
-        self._banks_api: Optional[BanksAPI] = None
-        self._mental_models_api: Optional[MentalModelsAPI] = None
-        self._directives_api: Optional[DirectivesAPI] = None
-        self._memories_api: Optional[MemoriesAPI] = None
-
-    def _ensure_started(self):
-        """Ensure daemon is running (thread-safe)."""
-        if self._started and self._client is not None:
-            return
-
-        with self._lock:
-            # Double-check after acquiring lock
-            if self._started and self._client is not None:
-                return
-
-            if self._closed:
-                raise RuntimeError("Cannot use HindsightEmbedded after it has been closed")
-
-            # Use embed manager interface for daemon management
-            logger.info(f"Ensuring daemon is running for profile '{self.profile}'...")
-            success = self._manager.ensure_running(self.config, self.profile)
-            if not success:
-                raise RuntimeError(f"Failed to start daemon for profile '{self.profile}'")
-
-            # Get daemon URL and create client
-            daemon_url = self._manager.get_url(self.profile)
-            self._client = Hindsight(base_url=daemon_url)
-            self._started = True
-            logger.info(f"Connected to daemon at {daemon_url}")
-
-    def _cleanup(self, stop_daemon_on_close: bool = False):
-        """
-        Cleanup client resources (idempotent).
-
-        Args:
-            stop_daemon_on_close: If True, stops the daemon. Otherwise, daemon continues
-                running (it will auto-stop after idle timeout).
-        """
-        if self._closed:
-            return
-
-        with self._lock:
-            if self._closed:
-                return
-
-            if self._client is not None:
-                self._client.close()
-                self._client = None
-
-            # Optionally stop daemon (daemon has idle timeout, so not required)
-            if stop_daemon_on_close and self._started:
-                logger.info(f"Stopping daemon for profile '{self.profile}'...")
-                self._manager.stop(self.profile)
-
-            self._closed = True
-
-    def close(self, stop_daemon: bool = False):
-        """
-        Explicitly close the client.
-
-        Args:
-            stop_daemon: If True, stops the daemon. Otherwise, daemon continues running
-                and will auto-stop after idle timeout (default: False).
-
-        Note:
-            The daemon may be shared with other clients or the CLI, so stopping it
-            might affect other users. By default, we rely on the daemon's idle timeout.
-        """
-        self._cleanup(stop_daemon_on_close=stop_daemon)
-
-    def __getattr__(self, name: str):
-        """
-        Proxy all method calls to the underlying Hindsight client.
-
-        This allows HindsightEmbedded to expose all HindsightClient methods
-        without manually wrapping each one.
-        """
-        # Ensure server is started before proxying
-        self._ensure_started()
-
-        # Get the attribute from the underlying client
-        attr = getattr(self._client, name)
-
-        # If it's a callable, wrap it to ensure server is started
-        # (shouldn't be needed since _ensure_started already called, but defensive)
-        if callable(attr):
-
-            def wrapper(*args, **kwargs):
-                self._ensure_started()
-                return attr(*args, **kwargs)
-
-            return wrapper
-
-        return attr
-
-    def __enter__(self):
-        """Context manager entry - ensures server is started."""
-        self._ensure_started()
-        return self
-
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        """Context manager exit - stops the server."""
-        self.close()
-
-    def __del__(self):
-        """Cleanup on garbage collection."""
-        self._cleanup()
-
-    @property
-    def banks(self) -> BanksAPI:
-        """
-        Access bank management operations.
-
-        Each method call ensures the daemon is running before executing.
-
-        Example:
-            ```python
-            from hindsight import HindsightEmbedded
-
-            embedded = HindsightEmbedded(profile="myapp", ...)
-
-            # Create a bank
-            embedded.banks.create(bank_id="test", name="Test Bank")
-
-            # Set mission
-            embedded.banks.set_mission(bank_id="test", mission="Help users")
-            ```
-        """
-        if self._banks_api is None:
-            self._banks_api = BanksAPI(self)
-        return self._banks_api
-
-    @property
-    def mental_models(self) -> MentalModelsAPI:
-        """
-        Access mental model operations.
-
-        Each method call ensures the daemon is running before executing.
-
-        Example:
-            ```python
-            from hindsight import HindsightEmbedded
-
-            embedded = HindsightEmbedded(profile="myapp", ...)
-
-            # Create a mental model
-            embedded.mental_models.create(
-                bank_id="test",
-                name="User Preferences",
-                content="User prefers dark mode"
-            )
-
-            # List mental models
-            models = embedded.mental_models.list(bank_id="test")
-            ```
-        """
-        if self._mental_models_api is None:
-            self._mental_models_api = MentalModelsAPI(self)
-        return self._mental_models_api
-
-    @property
-    def directives(self) -> DirectivesAPI:
-        """
-        Access directive operations.
-
-        Each method call ensures the daemon is running before executing.
-
-        Example:
-            ```python
-            from hindsight import HindsightEmbedded
-
-            embedded = HindsightEmbedded(profile="myapp", ...)
-
-            # Create a directive
-            embedded.directives.create(
-                bank_id="test",
-                name="Response Style",
-                content="Always be concise and friendly"
-            )
-
-            # List directives
-            directives = embedded.directives.list(bank_id="test")
-            ```
-        """
-        if self._directives_api is None:
-            self._directives_api = DirectivesAPI(self)
-        return self._directives_api
-
-    @property
-    def memories(self) -> MemoriesAPI:
-        """
-        Access memory listing operations.
-
-        Each method call ensures the daemon is running before executing.
-
-        Example:
-            ```python
-            from hindsight import HindsightEmbedded
-
-            embedded = HindsightEmbedded(profile="myapp", ...)
-
-            # List memories
-            memories = embedded.memories.list(
-                bank_id="test",
-                type="world",
-                limit=50
-            )
-            ```
-        """
-        if self._memories_api is None:
-            self._memories_api = MemoriesAPI(self)
-        return self._memories_api
-
-    @property
-    def client(self) -> Hindsight:
-        """
-        Get the underlying Hindsight client for direct access.
-
-        WARNING: Using this property directly means daemon restarts won't be
-        handled automatically. Prefer using the API namespaces (banks, mental_models,
-        directives, memories) or direct method calls on HindsightEmbedded instead.
-
-        Ensures daemon is started before returning the client.
-
-        Returns:
-            Hindsight: The underlying client instance
-
-        Example:
-            ```python
-            from hindsight import HindsightEmbedded
-
-            embedded = HindsightEmbedded(profile="myapp", ...)
-
-            # Direct access (not recommended - daemon crashes won't be handled)
-            client = embedded.client
-            banks = client.list_banks()  # If daemon crashes, this will fail
-            ```
-        """
-        self._ensure_started()
-        return self._client
-
-    @property
-    def url(self) -> str:
-        """Get the daemon URL (starts daemon if needed)."""
-        self._ensure_started()
-        return self._manager.get_url(self.profile)
-
-    @property
-    def is_running(self) -> bool:
-        """Check if the client is initialized."""
-        return self._started and not self._closed and self._client is not None

hindsight-all/tests/test_embedded.py

@@ -1,338 +0,0 @@
-"""
-Integration tests for HindsightEmbedded client.
-
-Tests the embedded client with automatic server lifecycle management:
-1. Lazy server startup on first use
-2. Server reuse across multiple operations
-3. Context manager support
-4. Method proxying to underlying HindsightClient
-5. Proper cleanup
-
-Note: Each test uses random bank_ids to avoid conflicts and allow safe parallel execution.
-"""
-
-import os
-import uuid
-
-import pytest
-
-from hindsight import HindsightEmbedded
-
-
-@pytest.fixture(scope="session")
-def llm_config():
-    """Get LLM configuration from environment (session-scoped)."""
-    # Try both naming conventions
-    provider = os.getenv("HINDSIGHT_API_LLM_PROVIDER") or os.getenv("HINDSIGHT_LLM_PROVIDER", "groq")
-    api_key = os.getenv("HINDSIGHT_API_LLM_API_KEY") or os.getenv("HINDSIGHT_LLM_API_KEY", "")
-    model = os.getenv("HINDSIGHT_API_LLM_MODEL") or os.getenv("HINDSIGHT_LLM_MODEL", "openai/gpt-oss-120b")
-
-    if not api_key:
-        pytest.skip("LLM API key not configured. Set HINDSIGHT_API_LLM_API_KEY or HINDSIGHT_LLM_API_KEY.")
-
-    return {
-        "llm_provider": provider,
-        "llm_api_key": api_key,
-        "llm_model": model,
-    }
-
-
-def test_embedded_lazy_start(llm_config):
-    """
-    Test that HindsightEmbedded starts server lazily on first use.
-    """
-    profile = f"test_lazy_{uuid.uuid4().hex[:8]}"
-    bank_id = f"bank_{uuid.uuid4().hex[:8]}"
-
-    # Create client - should NOT start server yet
-    client = HindsightEmbedded(profile=profile, log_level="info", **llm_config)
-    assert not client.is_running, "Server should not be running after initialization"
-
-    # First call should start server
-    result = client.retain(bank_id=bank_id, content="Test content for lazy start")
-
-    # Verify server is now running
-    assert client.is_running, "Server should be running after first call"
-    assert result.success, "Retain should succeed"
-    assert result.items_count >= 1, "Should have stored at least 1 item"
-
-    # Cleanup
-    client.close()
-    assert not client.is_running, "Server should stop after close()"
-
-
-def test_embedded_context_manager(llm_config):
-    """
-    Test HindsightEmbedded with context manager.
-    """
-    profile = f"test_ctx_{uuid.uuid4().hex[:8]}"
-    bank_id = f"bank_{uuid.uuid4().hex[:8]}"
-
-    # Use context manager
-    with HindsightEmbedded(profile=profile, log_level="info", **llm_config) as client:
-        assert client.is_running, "Server should be running inside context"
-
-        # Store memory
-        result = client.retain(bank_id=bank_id, content="Testing context manager")
-        assert result.success, "Retain should succeed"
-
-        # Recall memory
-        recall_results = client.recall(bank_id=bank_id, query="context")
-        assert isinstance(recall_results.results, list), "Recall should return results list"
-
-    # Server should be stopped after context exit
-    # Note: We can't check client.is_running here as client is out of scope
-
-
-def test_embedded_complete_workflow(llm_config):
-    """
-    Test complete workflow with HindsightEmbedded.
-
-    This test:
-    1. Creates a client with lazy start
-    2. Creates a memory bank
-    3. Stores multiple memories
-    4. Recalls memories
-    5. Reflects on memories
-    6. Tests cleanup
-    """
-    profile = f"test_workflow_{uuid.uuid4().hex[:8]}"
-    bank_id = f"assistant_{uuid.uuid4().hex[:8]}"
-
-    client = HindsightEmbedded(profile=profile, log_level="info", **llm_config)
-
-    try:
-        # Step 1: Create a memory bank
-        print(f"\n1. Creating memory bank: {bank_id}")
-        bank_response = client.create_bank(
-            bank_id=bank_id, name="Test Assistant", mission="Help with programming tasks"
-        )
-        assert bank_response.bank_id == bank_id
-
-        # Step 2: Store memories (single)
-        print("\n2. Storing single memory...")
-        retain_response = client.retain(
-            bank_id=bank_id,
-            content="User prefers Python for data analysis.",
-            context="Programming preferences",
-        )
-        assert retain_response.success
-        assert retain_response.items_count >= 1
-
-        # Step 3: Store batch memories
-        print("\n3. Storing batch memories...")
-        batch_response = client.retain_batch(
-            bank_id=bank_id,
-            items=[
-                {"content": "User works with pandas and numpy."},
-                {"content": "User likes matplotlib for visualization."},
-                {"content": "User is interested in machine learning with scikit-learn."},
-            ],
-        )
-        assert batch_response.success
-        assert batch_response.items_count >= 3
-
-        # Step 4: Recall memories
-        print("\n4. Recalling memories...")
-        recall_response = client.recall(bank_id=bank_id, query="What tools does the user prefer?", max_tokens=2000)
-        assert isinstance(recall_response.results, list)
-        assert len(recall_response.results) > 0
-        print(f"   Found {len(recall_response.results)} relevant memories")
-
-        # Step 5: Reflect on memories
-        print("\n5. Reflecting on memories...")
-        reflect_response = client.reflect(
-            bank_id=bank_id,
-            query="What programming tools should I recommend?",
-            budget="low",
-        )
-        assert reflect_response.text
-        assert len(reflect_response.text) > 0
-        print(f"   Answer: {reflect_response.text[:150]}...")
-
-        # Verify answer mentions relevant tools
-        answer_lower = reflect_response.text.lower()
-        assert any(term in answer_lower for term in ["python", "pandas", "numpy", "data"])
-
-        # Step 6: List memories
-        print("\n6. Listing memories...")
-        list_response = client.list_memories(bank_id=bank_id, limit=10)
-        assert len(list_response.items) > 0
-        print(f"   Listed {len(list_response.items)} memories")
-
-    finally:
-        # Cleanup
-        client.close()
-
-
-def test_embedded_server_reuse(llm_config):
-    """
-    Test that the same server is reused across multiple calls.
-    """
-    profile = f"test_reuse_{uuid.uuid4().hex[:8]}"
-    bank_id = f"bank_{uuid.uuid4().hex[:8]}"
-
-    client = HindsightEmbedded(profile=profile, log_level="info", **llm_config)
-
-    try:
-        # First call starts server
-        result1 = client.retain(bank_id=bank_id, content="First message")
-        url1 = client.url
-        assert client.is_running
-
-        # Second call should reuse the same server
-        result2 = client.retain(bank_id=bank_id, content="Second message")
-        url2 = client.url
-
-        # URLs should be identical (same server)
-        assert url1 == url2, "Server URL should remain the same across calls"
-        assert result1.success and result2.success
-
-        # Third call should also reuse
-        recall_result = client.recall(bank_id=bank_id, query="message")
-        url3 = client.url
-        assert url3 == url1, "Server URL should remain the same for recall"
-        assert isinstance(recall_result.results, list)
-
-    finally:
-        client.close()
-
-
-def test_embedded_method_proxying(llm_config):
-    """
-    Test that all HindsightClient methods are properly proxied.
-
-    This ensures __getattr__ proxying works for various method types.
-    """
-    profile = f"test_proxy_{uuid.uuid4().hex[:8]}"
-    bank_id = f"bank_{uuid.uuid4().hex[:8]}"
-
-    client = HindsightEmbedded(profile=profile, log_level="info", **llm_config)
-
-    try:
-        # Test bank operations
-        bank = client.create_bank(bank_id=bank_id, name="Proxy Test")
-        assert bank.bank_id == bank_id
-
-        # Test mission setting
-        mission_response = client.set_mission(bank_id=bank_id, mission="Test mission for proxying")
-        assert mission_response.bank_id == bank_id
-
-        # Test retain
-        retain_result = client.retain(bank_id=bank_id, content="Test content")
-        assert retain_result.success
-
-        # Test retain_batch
-        batch_result = client.retain_batch(
-            bank_id=bank_id, items=[{"content": "Item 1"}, {"content": "Item 2"}]
-        )
-        assert batch_result.success
-        assert batch_result.items_count >= 2
-
-        # Test recall
-        recall_result = client.recall(bank_id=bank_id, query="test")
-        assert hasattr(recall_result, "results")
-
-        # Test reflect
-        reflect_result = client.reflect(bank_id=bank_id, query="What is stored?")
-        assert hasattr(reflect_result, "text")
-
-        # Test list_memories
-        list_result = client.list_memories(bank_id=bank_id, limit=5)
-        assert hasattr(list_result, "items")
-
-        print("✓ All methods successfully proxied")
-
-    finally:
-        client.close()
-
-
-def test_embedded_multiple_banks(llm_config):
-    """
-    Test that HindsightEmbedded can work with multiple banks.
-    """
-    profile = f"test_multibank_{uuid.uuid4().hex[:8]}"
-    bank1_id = f"bank1_{uuid.uuid4().hex[:8]}"
-    bank2_id = f"bank2_{uuid.uuid4().hex[:8]}"
-
-    client = HindsightEmbedded(profile=profile, log_level="info", **llm_config)
-
-    try:
-        # Create first bank and store data
-        client.create_bank(bank_id=bank1_id, name="Bank 1")
-        client.retain(bank_id=bank1_id, content="Alice prefers Python for data science")
-
-        # Create second bank and store data
-        client.create_bank(bank_id=bank2_id, name="Bank 2")
-        client.retain(bank_id=bank2_id, content="Bob uses JavaScript for web development")
-
-        # Recall from both banks
-        results1 = client.recall(bank_id=bank1_id, query="programming language")
-        results2 = client.recall(bank_id=bank2_id, query="programming language")
-
-        assert len(results1.results) > 0
-        assert len(results2.results) > 0
-
-        # Verify banks are isolated (each should only see their own content)
-        # This is a basic check - content isolation is tested more thoroughly in other tests
-        assert results1.results[0].text != results2.results[0].text or len(results1.results) != len(
-            results2.results
-        )
-
-    finally:
-        client.close()
-
-
-def test_embedded_profile_isolation(llm_config):
-    """
-    Test that different profiles create isolated data stores.
-    """
-    profile1 = f"test_iso1_{uuid.uuid4().hex[:8]}"
-    profile2 = f"test_iso2_{uuid.uuid4().hex[:8]}"
-    bank_id = "shared_bank_name"  # Same bank_id in both profiles
-
-    client1 = HindsightEmbedded(profile=profile1, log_level="info", **llm_config)
-    client2 = HindsightEmbedded(profile=profile2, log_level="info", **llm_config)
-
-    try:
-        # Store data in profile1
-        client1.retain(bank_id=bank_id, content="User likes TypeScript for frontend development")
-
-        # Store different data in profile2
-        client2.retain(bank_id=bank_id, content="User prefers Rust for systems programming")
-
-        # Each profile should only see its own data
-        results1 = client1.recall(bank_id=bank_id, query="programming preference")
-        results2 = client2.recall(bank_id=bank_id, query="programming preference")
-
-        # Both should have results
-        assert len(results1.results) > 0
-        assert len(results2.results) > 0
-
-        # Results should be different (basic isolation check)
-        # Note: This is a basic sanity check. Full isolation is ensured by pg0's data directory separation
-
-    finally:
-        client1.close()
-        client2.close()
-
-
-def test_embedded_error_after_close(llm_config):
-    """
-    Test that using HindsightEmbedded after close() raises an error.
-    """
-    profile = f"test_error_{uuid.uuid4().hex[:8]}"
-    bank_id = f"bank_{uuid.uuid4().hex[:8]}"
-
-    client = HindsightEmbedded(profile=profile, log_level="info", **llm_config)
-
-    # Use it once to start server
-    client.retain(bank_id=bank_id, content="Test")
-
-    # Close the client
-    client.close()
-    assert not client.is_running
-
-    # Trying to use it after close should raise an error
-    with pytest.raises(RuntimeError, match="Cannot use HindsightEmbedded after it has been closed"):
-        client.retain(bank_id=bank_id, content="This should fail")

hindsight-all/tests/test_embedded_namespaces.py

@@ -1,170 +0,0 @@
-"""Test that API namespaces ensure daemon is started before each call."""
-
-from unittest.mock import Mock, patch
-
-import pytest
-
-from hindsight import HindsightEmbedded
-
-
-@pytest.fixture
-def embedded_client():
-    """Create an embedded client for testing."""
-    return HindsightEmbedded(
-        profile="test",
-        llm_provider="openai",
-        llm_api_key="test-key",
-    )
-
-
-def test_banks_create_ensures_daemon_started(embedded_client):
-    """Test that banks.create() calls _ensure_started()."""
-    # Mock _ensure_started to track calls
-    with patch.object(embedded_client, "_ensure_started") as mock_ensure:
-        # Mock the underlying client to avoid actual API call
-        mock_client = Mock()
-        embedded_client._client = mock_client
-
-        # Call namespace method
-        try:
-            embedded_client.banks.create(bank_id="test", name="Test Bank")
-        except Exception:
-            pass  # We don't care if the actual call fails
-
-        # Verify _ensure_started was called
-        mock_ensure.assert_called_once()
-
-
-def test_mental_models_list_ensures_daemon_started(embedded_client):
-    """Test that mental_models.list() calls _ensure_started()."""
-    with patch.object(embedded_client, "_ensure_started") as mock_ensure:
-        mock_client = Mock()
-        embedded_client._client = mock_client
-
-        try:
-            embedded_client.mental_models.list(bank_id="test")
-        except Exception:
-            pass
-
-        mock_ensure.assert_called_once()
-
-
-def test_directives_list_ensures_daemon_started(embedded_client):
-    """Test that directives.list() calls _ensure_started()."""
-    with patch.object(embedded_client, "_ensure_started") as mock_ensure:
-        mock_client = Mock()
-        embedded_client._client = mock_client
-
-        try:
-            embedded_client.directives.list(bank_id="test")
-        except Exception:
-            pass
-
-        mock_ensure.assert_called_once()
-
-
-def test_memories_list_ensures_daemon_started(embedded_client):
-    """Test that memories.list() calls _ensure_started()."""
-    with patch.object(embedded_client, "_ensure_started") as mock_ensure:
-        mock_client = Mock()
-        embedded_client._client = mock_client
-
-        try:
-            embedded_client.memories.list(bank_id="test")
-        except Exception:
-            pass
-
-        mock_ensure.assert_called_once()
-
-
-def test_multiple_calls_ensure_daemon_each_time(embedded_client):
-    """Test that each namespace call ensures daemon is started."""
-    with patch.object(embedded_client, "_ensure_started") as mock_ensure:
-        mock_client = Mock()
-        embedded_client._client = mock_client
-
-        # Make multiple calls
-        try:
-            embedded_client.banks.create(bank_id="test", name="Test")
-        except Exception:
-            pass
-
-        try:
-            embedded_client.mental_models.list(bank_id="test")
-        except Exception:
-            pass
-
-        try:
-            embedded_client.directives.list(bank_id="test")
-        except Exception:
-            pass
-
-        # Should be called 3 times (once per namespace method call)
-        assert mock_ensure.call_count == 3
-
-
-def test_daemon_restart_handling(embedded_client):
-    """Test that namespace methods can recover from daemon crash."""
-    call_count = 0
-
-    def mock_ensure_started():
-        """Mock that simulates daemon restart."""
-        nonlocal call_count
-        call_count += 1
-        # Create a new mock client each time (simulating daemon restart)
-        embedded_client._client = Mock()
-        embedded_client._started = True
-
-    with patch.object(embedded_client, "_ensure_started", side_effect=mock_ensure_started):
-        # First call - daemon starts
-        embedded_client.banks.create(bank_id="test", name="Test")
-        assert call_count == 1
-
-        # Simulate daemon crash by clearing client
-        embedded_client._client = None
-        embedded_client._started = False
-
-        # Second call - daemon restarts
-        embedded_client.banks.create(bank_id="test", name="Test")
-        assert call_count == 2
-
-
-def test_ensure_started_calls_manager(embedded_client):
-    """Test that _ensure_started actually starts the daemon via manager."""
-    # Mock the manager
-    mock_manager = Mock()
-    mock_manager.ensure_running.return_value = True
-    mock_manager.get_url.return_value = "http://localhost:54321"
-
-    embedded_client._manager = mock_manager
-
-    # Mock Hindsight client constructor
-    with patch("hindsight.embedded.Hindsight") as mock_hindsight_class:
-        mock_client = Mock()
-        mock_hindsight_class.return_value = mock_client
-
-        # Call _ensure_started
-        embedded_client._ensure_started()
-
-        # Verify manager was called
-        mock_manager.ensure_running.assert_called_once_with(
-            embedded_client.config, embedded_client.profile
-        )
-        mock_manager.get_url.assert_called_once_with(embedded_client.profile)
-
-        # Verify Hindsight client was created
-        mock_hindsight_class.assert_called_once_with(base_url="http://localhost:54321")
-
-
-def test_namespace_singleton_behavior(embedded_client):
-    """Test that namespace properties return the same instance."""
-    banks1 = embedded_client.banks
-    banks2 = embedded_client.banks
-
-    # Should be the same instance
-    assert banks1 is banks2
-
-    # Same for other namespaces
-    assert embedded_client.mental_models is embedded_client.mental_models
-    assert embedded_client.directives is embedded_client.directives
-    assert embedded_client.memories is embedded_client.memories

hindsight-api-slim/README.md

@@ -1,137 +0,0 @@
-# Hindsight API
-
-**Memory System for AI Agents** — Temporal + Semantic + Entity Memory Architecture using PostgreSQL with pgvector.
-
-Hindsight gives AI agents persistent memory that works like human memory: it stores facts, tracks entities and relationships, handles temporal reasoning ("what happened last spring?"), and forms opinions based on configurable disposition traits.
-
-## Installation
-
-```bash
-pip install hindsight-api
-```
-
-## Quick Start
-
-### Run the Server
-
-```bash
-# Set your LLM provider
-export HINDSIGHT_API_LLM_PROVIDER=openai
-export HINDSIGHT_API_LLM_API_KEY=sk-xxxxxxxxxxxx
-
-# Start the server (uses embedded PostgreSQL by default)
-hindsight-api
-```
-
-The server starts at http://localhost:8888 with:
-- REST API for memory operations
-- MCP server at `/mcp` for tool-use integration
-
-### Use the Python API
-
-```python
-from hindsight_api import MemoryEngine
-
-# Create and initialize the memory engine
-memory = MemoryEngine()
-await memory.initialize()
-
-# Create a memory bank for your agent
-bank = await memory.create_memory_bank(
-    name="my-assistant",
-    background="A helpful coding assistant"
-)
-
-# Store a memory
-await memory.retain(
-    memory_bank_id=bank.id,
-    content="The user prefers Python for data science projects"
-)
-
-# Recall memories
-results = await memory.recall(
-    memory_bank_id=bank.id,
-    query="What programming language does the user prefer?"
-)
-
-# Reflect with reasoning
-response = await memory.reflect(
-    memory_bank_id=bank.id,
-    query="Should I recommend Python or R for this ML project?"
-)
-```
-
-## CLI Options
-
-```bash
-hindsight-api --help
-
-# Common options
-hindsight-api --port 9000          # Custom port (default: 8888)
-hindsight-api --host 127.0.0.1     # Bind to localhost only
-hindsight-api --workers 4          # Multiple worker processes
-hindsight-api --log-level debug    # Verbose logging
-```
-
-## Configuration
-
-Configure via environment variables:
-
-| Variable | Description | Default |
-|----------|-------------|---------|
-| `HINDSIGHT_API_DATABASE_URL` | PostgreSQL connection string | `pg0` (embedded) |
-| `HINDSIGHT_API_LLM_PROVIDER` | `openai`, `anthropic`, `gemini`, `groq`, `ollama`, `lmstudio` | `openai` |
-| `HINDSIGHT_API_LLM_API_KEY` | API key for LLM provider | - |
-| `HINDSIGHT_API_LLM_MODEL` | Model name | `gpt-4o-mini` |
-| `HINDSIGHT_API_HOST` | Server bind address | `0.0.0.0` |
-| `HINDSIGHT_API_PORT` | Server port | `8888` |
-
-### Example with External PostgreSQL
-
-```bash
-export HINDSIGHT_API_DATABASE_URL=postgresql://user:pass@localhost:5432/hindsight
-export HINDSIGHT_API_LLM_PROVIDER=groq
-export HINDSIGHT_API_LLM_API_KEY=gsk_xxxxxxxxxxxx
-
-hindsight-api
-```
-
-## Docker
-
-```bash
-docker run --rm -it -p 8888:8888 \
-  -e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
-  -v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
-  ghcr.io/vectorize-io/hindsight:latest
-```
-
-## MCP Server
-
-For local MCP integration without running the full API server:
-
-```bash
-hindsight-local-mcp
-```
-
-This runs a stdio-based MCP server that can be used directly with MCP-compatible clients.
-
-## Key Features
-
-- **Multi-Strategy Retrieval (TEMPR)** — Semantic, keyword, graph, and temporal search combined with RRF fusion
-- **Entity Graph** — Automatic entity extraction and relationship tracking
-- **Temporal Reasoning** — Native support for time-based queries
-- **Disposition Traits** — Configurable skepticism, literalism, and empathy influence opinion formation
-- **Three Memory Types** — World facts, bank actions, and formed opinions with confidence scores
-
-## Documentation
-
-Full documentation: [https://hindsight.vectorize.io](https://hindsight.vectorize.io)
-
-- [Installation Guide](https://hindsight.vectorize.io/developer/installation)
-- [Configuration Reference](https://hindsight.vectorize.io/developer/configuration)
-- [API Reference](https://hindsight.vectorize.io/api-reference)
-- [Python SDK](https://hindsight.vectorize.io/sdks/python)
-
-## License
-
-Apache 2.0

hindsight-api-slim/hindsight_api/alembic/versions/a1b2c3d4e5f6_add_file_storage_table.py

@@ -1,70 +0,0 @@
-"""Add file_storage table for BYTEA-based file storage
-
-Revision ID: a1b2c3d4e5f6
-Revises: y0t1u2v3w4x5
-Create Date: 2026-02-16
-
-Creates a dedicated table for storing uploaded files using BYTEA.
-This provides zero-config file storage that "just works" for development
-and small deployments. For production/scale, use S3-compatible storage.
-
-Files are stored in a separate table to avoid bloating the documents table.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "a1b2c3d4e5f6"
-down_revision: str | Sequence[str] | None = "y0t1u2v3w4x5"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    """Get schema prefix for table names (required for multi-tenant support)."""
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    """Create file_storage table for BYTEA storage."""
-    schema = _get_schema_prefix()
-
-    # Create file_storage table (minimal: just key + data)
-    op.execute(
-        f"""
-        CREATE TABLE IF NOT EXISTS {schema}file_storage (
-            storage_key TEXT PRIMARY KEY,
-            data BYTEA NOT NULL
-        )
-    """
-    )
-
-    # Add file tracking columns to documents table
-    op.execute(
-        f"""
-        ALTER TABLE {schema}documents
-        ADD COLUMN IF NOT EXISTS file_storage_key TEXT,
-        ADD COLUMN IF NOT EXISTS file_original_name TEXT,
-        ADD COLUMN IF NOT EXISTS file_content_type TEXT
-    """
-    )
-
-
-def downgrade() -> None:
-    """Remove file_storage table and related columns."""
-    schema = _get_schema_prefix()
-
-    # Drop columns from documents table
-    op.execute(
-        f"""
-        ALTER TABLE {schema}documents
-        DROP COLUMN IF EXISTS file_storage_key,
-        DROP COLUMN IF EXISTS file_original_name,
-        DROP COLUMN IF EXISTS file_content_type
-    """
-    )
-
-    # Drop file_storage table
-    op.execute(f"DROP TABLE IF EXISTS {schema}file_storage")

hindsight-api-slim/hindsight_api/alembic/versions/a2b3c4d5e6f7_add_text_signals_column.py

@@ -1,88 +0,0 @@
-"""Add text_signals column to memory_units for enriched BM25 indexing.
-
-text_signals stores a denormalized space-separated string of entity names
-(and future signals) to improve full-text search recall without polluting
-the stored fact text.
-
-- vchord: text_signals included in tokenize() at insert time
-- native: search_vector GENERATED column regenerated to include text_signals
-- pg_textsearch: no change (index only supports a single base column)
-
-Revision ID: a2b3c4d5e6f7
-Revises: z1u2v3w4x5y6
-Create Date: 2026-02-28
-"""
-
-import os
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "a2b3c4d5e6f7"
-down_revision: str | Sequence[str] | None = "aa2b3c4d5e6f"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def _detect_text_search_extension() -> str:
-    return os.getenv("HINDSIGHT_API_TEXT_SEARCH_EXTENSION", "native").lower()
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-    table = f"{schema}memory_units"
-    text_search_ext = _detect_text_search_extension()
-
-    # Add text_signals column (nullable TEXT, populated at retain time)
-    op.execute(f"ALTER TABLE {table} ADD COLUMN IF NOT EXISTS text_signals TEXT")
-
-    if text_search_ext == "native":
-        # Native PostgreSQL: drop and recreate the GENERATED tsvector column to include text_signals
-        op.execute(f"ALTER TABLE {table} DROP COLUMN IF EXISTS search_vector")
-        op.execute(f"""
-            ALTER TABLE {table}
-            ADD COLUMN search_vector tsvector
-            GENERATED ALWAYS AS (
-                to_tsvector('english',
-                    COALESCE(text, '') || ' ' ||
-                    COALESCE(context, '') || ' ' ||
-                    COALESCE(text_signals, '')
-                )
-            ) STORED
-        """)
-        # Recreate GIN index (was dropped with the column)
-        op.execute(f"""
-            CREATE INDEX IF NOT EXISTS idx_memory_units_text_search
-            ON {table} USING gin(search_vector)
-        """)
-
-    # vchord: tokenize() call in fact_storage.py is updated to include text_signals at insert time
-    # pg_textsearch: no change — index operates on the base `text` column only
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    table = f"{schema}memory_units"
-    text_search_ext = _detect_text_search_extension()
-
-    if text_search_ext == "native":
-        op.execute(f"DROP INDEX IF EXISTS {schema}idx_memory_units_text_search")
-        op.execute(f"ALTER TABLE {table} DROP COLUMN IF EXISTS search_vector")
-        op.execute(f"""
-            ALTER TABLE {table}
-            ADD COLUMN search_vector tsvector
-            GENERATED ALWAYS AS (
-                to_tsvector('english', COALESCE(text, '') || ' ' || COALESCE(context, ''))
-            ) STORED
-        """)
-        op.execute(f"""
-            CREATE INDEX idx_memory_units_text_search
-            ON {table} USING gin(search_vector)
-        """)
-
-    op.execute(f"ALTER TABLE {table} DROP COLUMN IF EXISTS text_signals")

hindsight-api-slim/hindsight_api/alembic/versions/a2b3c4d5e6f8_add_gin_index_source_memory_ids.py

@@ -1,54 +0,0 @@
-"""Add GIN index on source_memory_ids for observation lookup performance
-
-Without this index, queries using the array overlap operator (&&) or array
-containment (@>) on source_memory_ids require a full sequential scan over all
-observation memory_units. At ~77k observations this was measured at 45ms per
-query, becoming a bottleneck during consolidation recall (57-64s timeouts) and
-user recall (18-27s average).
-
-The GIN index reduces these queries to index scans: 45ms → 0.049ms (927x
-speedup). Recall dropped from 18-27s to ~6s, and consolidation recall
-stabilised from timeout to ~15s.
-
-Created with CONCURRENTLY so the migration does not block reads or writes.
-CONCURRENTLY requires running outside a transaction block, so the migration
-emits an explicit COMMIT before the statement and uses IF NOT EXISTS for
-idempotency.
-
-Revision ID: a2b3c4d5e6f8
-Revises: f7g8h9i0j1k2
-Create Date: 2026-03-04
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "a2b3c4d5e6f8"
-down_revision: str | Sequence[str] | None = "f7g8h9i0j1k2"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-
-    # CREATE INDEX CONCURRENTLY cannot run inside a transaction block.
-    # Commit the current Alembic transaction first.
-    op.execute("COMMIT")
-    op.execute(
-        f"CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_memory_units_source_memory_ids "
-        f"ON {schema}memory_units USING GIN (source_memory_ids) "
-        f"WHERE source_memory_ids IS NOT NULL"
-    )
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute("COMMIT")
-    op.execute(f"DROP INDEX CONCURRENTLY IF EXISTS {schema}idx_memory_units_source_memory_ids")

hindsight-api-slim/hindsight_api/alembic/versions/a3b4c5d6e7f8_add_consolidation_failed_at_to_memory_units.py

@@ -1,52 +0,0 @@
-"""Add consolidation_failed_at column to memory_units for tracking persistent LLM failures.
-
-When all LLM retries are exhausted on a single-memory batch, the memory is marked
-with consolidation_failed_at instead of consolidated_at, so it is not silently lost
-and can be retried later via the API.
-
-Revision ID: a3b4c5d6e7f8
-Revises: g7h8i9j0k1l2
-Create Date: 2026-03-17
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "a3b4c5d6e7f8"
-down_revision: str | Sequence[str] | None = "g7h8i9j0k1l2"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    """Get schema prefix for table names (required for multi-tenant support)."""
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-
-    op.execute(
-        f"""
-        ALTER TABLE {schema}memory_units
-        ADD COLUMN IF NOT EXISTS consolidation_failed_at TIMESTAMPTZ DEFAULT NULL
-        """
-    )
-
-    # Index to efficiently query memories that failed consolidation for a given bank
-    op.execute(
-        f"""
-        CREATE INDEX IF NOT EXISTS idx_memory_units_consolidation_failed
-        ON {schema}memory_units (bank_id, consolidation_failed_at)
-        WHERE consolidation_failed_at IS NOT NULL AND fact_type IN ('experience', 'world')
-        """
-    )
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_memory_units_consolidation_failed")
-    op.execute(f"ALTER TABLE {schema}memory_units DROP COLUMN IF EXISTS consolidation_failed_at")

hindsight-api-slim/hindsight_api/alembic/versions/aa2b3c4d5e6f_nullable_event_date.py

@@ -1,36 +0,0 @@
-"""Make event_date nullable in memory_units to support timestamp-free content
-
-Revision ID: aa2b3c4d5e6f
-Revises: z1u2v3w4x5y6
-Create Date: 2026-03-02
-
-When callers retain content without a timestamp (e.g. fictional documents, static text),
-the event_date column should be allowed to be NULL rather than defaulting to utcnow().
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "aa2b3c4d5e6f"
-down_revision: str | Sequence[str] | None = "z1u2v3w4x5y6"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    """Get schema prefix for table names (required for multi-tenant support)."""
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}memory_units ALTER COLUMN event_date DROP NOT NULL")
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    # Backfill NULLs with now() before restoring the NOT NULL constraint
-    op.execute(f"UPDATE {schema}memory_units SET event_date = now() WHERE event_date IS NULL")
-    op.execute(f"ALTER TABLE {schema}memory_units ALTER COLUMN event_date SET NOT NULL")

hindsight-api-slim/hindsight_api/alembic/versions/b3c4d5e6f7g8_add_temporal_date_indexes.py

@@ -1,68 +0,0 @@
-"""Add partial indexes on memory_units temporal date fields for fast temporal retrieval
-
-Revision ID: b3c4d5e6f7g8
-Revises: c1a2b3d4e5f6
-Create Date: 2026-03-02
-
-The temporal retrieval entry-point query filters memory_units by occurred_start,
-occurred_end, and mentioned_at using OR conditions. Without dedicated indexes the
-planner falls back to a sequential scan of all bank rows after applying the
-(bank_id, fact_type) index, then re-checks each date field.
-
-These three partial indexes give the planner bitmap-index scan options for the
-three most common date predicates, dramatically reducing the row set before any
-embedding computation is required.
-
-All indexes are created CONCURRENTLY so the migration does not block writes on
-memory_units during production deployments. CONCURRENTLY requires running outside
-a transaction block; see migrations.py for how this is handled safely.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "b3c4d5e6f7g8"
-down_revision: str | Sequence[str] | None = "c1a2b3d4e5f6"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-    # Partial index on occurred_start (covers "occurred_start BETWEEN $4 AND $5")
-    op.execute("COMMIT")
-    op.execute(
-        f"CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_memory_units_bank_occurred_start "
-        f"ON {schema}memory_units(bank_id, fact_type, occurred_start) "
-        f"WHERE occurred_start IS NOT NULL"
-    )
-    # Partial index on occurred_end (covers "occurred_end BETWEEN $4 AND $5")
-    op.execute("COMMIT")
-    op.execute(
-        f"CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_memory_units_bank_occurred_end "
-        f"ON {schema}memory_units(bank_id, fact_type, occurred_end) "
-        f"WHERE occurred_end IS NOT NULL"
-    )
-    # Partial index on mentioned_at (covers "mentioned_at BETWEEN $4 AND $5")
-    op.execute("COMMIT")
-    op.execute(
-        f"CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_memory_units_bank_mentioned_at "
-        f"ON {schema}memory_units(bank_id, fact_type, mentioned_at) "
-        f"WHERE mentioned_at IS NOT NULL"
-    )
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute("COMMIT")
-    op.execute(f"DROP INDEX CONCURRENTLY IF EXISTS {schema}idx_memory_units_bank_mentioned_at")
-    op.execute("COMMIT")
-    op.execute(f"DROP INDEX CONCURRENTLY IF EXISTS {schema}idx_memory_units_bank_occurred_end")
-    op.execute("COMMIT")
-    op.execute(f"DROP INDEX CONCURRENTLY IF EXISTS {schema}idx_memory_units_bank_occurred_start")

hindsight-api-slim/hindsight_api/alembic/versions/b4c5d6e7f8a9_backfill_observation_scopes.py

@@ -1,34 +0,0 @@
-"""Backfill observation_scopes column if missing.
-
-This migration ensures observation_scopes exists even on databases that had
-revision z1u2v3w4x5y6 applied when it referred to the old text_signals migration
-(before it was renamed to a2b3c4d5e6f7). The ADD COLUMN IF NOT EXISTS makes this
-a no-op on databases that already have the column.
-
-Revision ID: b4c5d6e7f8a9
-Revises: a2b3c4d5e6f7
-Create Date: 2026-03-02
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "b4c5d6e7f8a9"
-down_revision: str | Sequence[str] | None = "a2b3c4d5e6f7"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}memory_units ADD COLUMN IF NOT EXISTS observation_scopes JSONB")
-
-
-def downgrade() -> None:
-    pass  # intentionally no-op — safe to leave the column in place

hindsight-api-slim/hindsight_api/alembic/versions/c1a2b3d4e5f6_enable_pg_trgm_and_entities_trgm_index.py

@@ -1,46 +0,0 @@
-"""Enable pg_trgm extension and add GIN trigram index on entities.canonical_name
-
-Revision ID: c1a2b3d4e5f6
-Revises: b4c5d6e7f8a9
-Create Date: 2026-03-02
-
-Index is created CONCURRENTLY so the migration does not block writes on entities
-during production deployments. CONCURRENTLY requires running outside a transaction
-block; see migrations.py for how this is handled safely.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "c1a2b3d4e5f6"
-down_revision: str | Sequence[str] | None = "b4c5d6e7f8a9"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    # pg_trgm ships with every standard PostgreSQL installation as a contrib module.
-    # It enables fast similarity lookups via GIN indexes, used for entity name matching.
-    op.execute("CREATE EXTENSION IF NOT EXISTS pg_trgm")
-
-    schema = _get_schema_prefix()
-    # GIN index on canonical_name enables sub-millisecond trigram similarity queries
-    # (% operator, similarity()) instead of full-table scans across all bank entities.
-    op.execute("COMMIT")
-    op.execute(
-        f"CREATE INDEX CONCURRENTLY IF NOT EXISTS entities_canonical_name_trgm_idx "
-        f"ON {schema}entities USING GIN (canonical_name gin_trgm_ops)"
-    )
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute("COMMIT")
-    op.execute(f"DROP INDEX CONCURRENTLY IF EXISTS {schema}entities_canonical_name_trgm_idx")
-    # Note: not dropping pg_trgm extension as other indexes may depend on it

hindsight-api-slim/hindsight_api/alembic/versions/c3d4e5f6g7h8_add_history_to_mental_models.py

@@ -1,30 +0,0 @@
-"""Add history column to mental_models
-
-Revision ID: c3d4e5f6g7h8
-Revises: a2b3c4d5e6f7, a2b3c4d5e6f8
-Create Date: 2026-03-06
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "c3d4e5f6g7h8"
-down_revision: str | Sequence[str] | None = ("a2b3c4d5e6f7", "a2b3c4d5e6f8")
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}mental_models ADD COLUMN IF NOT EXISTS history JSONB DEFAULT '[]'::jsonb")
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}mental_models DROP COLUMN IF EXISTS history")

hindsight-api-slim/hindsight_api/alembic/versions/d2e3f4a5b6c7_add_memory_links_expansion_indexes.py

@@ -1,83 +0,0 @@
-"""Add covering and composite indexes to speed up link expansion graph retrieval.
-
-Two indexes target the two bottlenecks identified by EXPLAIN ANALYZE on a 17M-row
-memory_links table:
-
-1. idx_memory_links_to_type_weight  (to_unit_id, link_type, weight DESC)
-   The semantic incoming direction — finding facts that consider seeds as their
-   nearest neighbour — currently hits an expensive BitmapAnd of two separate
-   bitmap scans (to_unit_id bitmap ∩ link_type bitmap).  A composite index
-   on (to_unit_id, link_type) turns this into a single index scan and reduces
-   latency from ~36 ms to < 5 ms per query.
-
-2. idx_memory_links_entity_covering  (from_unit_id) INCLUDE (to_unit_id, entity_id)
-   WHERE link_type = 'entity'
-   The entity co-occurrence expansion uses COUNT(DISTINCT ml.entity_id) and
-   joins on ml.to_unit_id.  Without a covering index the planner must read
-   ~2 500 heap pages to fetch entity_id and to_unit_id after the bitmap index
-   scan, adding ~230 ms of random I/O.  INCLUDE adds those two columns to the
-   index leaf pages so the entire query can be served from the index (index-only
-   scan), eliminating the heap reads entirely.
-   Partial index (WHERE link_type = 'entity') keeps index size ~40 % smaller.
-
-Both indexes are created with CONCURRENTLY so the migration does not block
-concurrent reads or writes on memory_links.  CONCURRENTLY requires running
-outside a transaction block, so the migration emits an explicit COMMIT before
-each statement and uses IF NOT EXISTS for idempotency.
-
-Revision ID: d2e3f4a5b6c7
-Revises: b3c4d5e6f7g8
-Create Date: 2026-03-02
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "d2e3f4a5b6c7"
-down_revision: str | Sequence[str] | None = "b3c4d5e6f7g8"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-
-    # CREATE INDEX CONCURRENTLY cannot run inside a transaction block.
-    # Commit the current Alembic transaction, then issue each CONCURRENTLY
-    # statement in its own implicit autocommit transaction.
-    # IF NOT EXISTS makes each statement idempotent if the migration is retried.
-
-    # Index for the semantic *incoming* direction in link_expansion_retrieval.py.
-    # Replaces the BitmapAnd of idx_memory_links_to_unit ∩ idx_memory_links_link_type
-    # with a single composite index scan.
-    op.execute("COMMIT")
-    op.execute(
-        f"CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_memory_links_to_type_weight "
-        f"ON {schema}memory_links(to_unit_id, link_type, weight DESC)"
-    )
-
-    # Covering index for entity co-occurrence expansion.
-    # Enables an index-only scan: entity_id and to_unit_id are read from the
-    # index leaf pages instead of the heap, eliminating ~2 500 random heap-page
-    # reads per expansion query.
-    op.execute("COMMIT")
-    op.execute(
-        f"CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_memory_links_entity_covering "
-        f"ON {schema}memory_links(from_unit_id) "
-        f"INCLUDE (to_unit_id, entity_id) "
-        f"WHERE link_type = 'entity'"
-    )
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute("COMMIT")
-    op.execute(f"DROP INDEX CONCURRENTLY IF EXISTS {schema}idx_memory_links_entity_covering")
-    op.execute("COMMIT")
-    op.execute(f"DROP INDEX CONCURRENTLY IF EXISTS {schema}idx_memory_links_to_type_weight")

hindsight-api-slim/hindsight_api/alembic/versions/d4e5f6g7h8i9_gin_source_memory_ids_fastupdate_off.py

@@ -1,53 +0,0 @@
-"""Recreate idx_memory_units_source_memory_ids GIN index with fastupdate=off
-
-GIN indexes use a "fastupdate" pending list by default: small writes are
-buffered there and flushed to the main GIN tree in bulk. Flushing requires
-AccessExclusiveLock on the index. Under high insert concurrency (e.g. 8
-parallel pytest-xdist workers all calling retain_async) two transactions can
-each trigger a flush simultaneously and deadlock.
-
-Disabling fastupdate makes every insert write directly to the GIN tree
-(slightly slower per insert, but no pending-list lock cycles).
-
-Revision ID: d4e5f6g7h8i9
-Revises: d5e6f7a8b9c0
-Create Date: 2026-03-11
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "d4e5f6g7h8i9"
-down_revision: str | Sequence[str] | None = "d5e6f7a8b9c0"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-    # DROP + CREATE CONCURRENTLY must run outside a transaction block.
-    op.execute("COMMIT")
-    op.execute(f"DROP INDEX CONCURRENTLY IF EXISTS {schema}idx_memory_units_source_memory_ids")
-    op.execute(
-        f"CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_memory_units_source_memory_ids "
-        f"ON {schema}memory_units USING GIN (source_memory_ids) "
-        f"WITH (fastupdate=off) "
-        f"WHERE source_memory_ids IS NOT NULL"
-    )
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute("COMMIT")
-    op.execute(f"DROP INDEX CONCURRENTLY IF EXISTS {schema}idx_memory_units_source_memory_ids")
-    op.execute(
-        f"CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_memory_units_source_memory_ids "
-        f"ON {schema}memory_units USING GIN (source_memory_ids) "
-        f"WHERE source_memory_ids IS NOT NULL"
-    )

hindsight-api-slim/hindsight_api/alembic/versions/d5e6f7a8b9c0_add_bank_internal_id_and_per_bank_hnsw.py

@@ -1,131 +0,0 @@
-"""Add internal_id to banks and per-(bank, fact_type) partial HNSW indexes
-
-Revision ID: d5e6f7a8b9c0
-Revises: a3b4c5d6e7f8
-Create Date: 2026-03-11
-
-This migration:
-1. Adds internal_id UUID column to banks (stable identifier for index naming)
-2. Drops the global HNSW index (competes with per-bank partial indexes)
-3. Creates per-(bank_id, fact_type) partial HNSW indexes for all existing banks
-   (new banks get indexes created at bank-creation time via bank_utils.create_bank_hnsw_indexes)
-
-Why per-(bank, fact_type) indexes:
-- fact_type-only partial indexes are never chosen by the planner when bank_id is in the WHERE
-  clause, because the idx_memory_units_bank_id B-tree index always wins at planning time.
-- Per-(bank, fact_type) partial indexes have both predicates matching → planner selects them.
-- The global HNSW index competes for larger partitions (world, observation) and must be dropped.
-
-For large deployments, create indexes CONCURRENTLY before running this migration:
-    SELECT internal_id, bank_id FROM banks;
-    -- for each bank and each fact_type in (world, experience, observation):
-    CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_mu_emb_{ft}_{uid16}
-        ON memory_units USING hnsw (embedding vector_cosine_ops)
-        WHERE fact_type = '{ft}' AND bank_id = '{bank_id}';
-    DROP INDEX CONCURRENTLY IF EXISTS idx_memory_units_embedding;
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-from sqlalchemy import text
-
-revision: str = "d5e6f7a8b9c0"
-down_revision: str | Sequence[str] | None = "c3d4e5f6g7h8"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-_HNSW_FACT_TYPES: dict[str, str] = {
-    "world": "worl",
-    "experience": "expr",
-    "observation": "obsv",
-}
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-
-    # 1. Add internal_id column to banks
-    op.execute(
-        f"ALTER TABLE {schema}banks ADD COLUMN IF NOT EXISTS internal_id UUID DEFAULT gen_random_uuid() NOT NULL"
-    )
-    op.execute(f"ALTER TABLE {schema}banks ADD CONSTRAINT banks_internal_id_unique UNIQUE (internal_id)")
-
-    # 2. Drop any fact_type-only partial HNSW indexes that may exist from prior migrations
-    #    (bank_id B-tree always wins over them when bank_id is in the WHERE clause)
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_mu_emb_world")
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_mu_emb_observation")
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_mu_emb_experience")
-
-    # 4. Drop global HNSW index (competes with per-bank partial indexes)
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_memory_units_embedding")
-
-    # 5. Create per-(bank, fact_type) partial HNSW indexes for all existing banks
-    bind = op.get_bind()
-    schema_name = context.config.get_main_option("target_schema")
-    table_ref = f'"{schema_name}".memory_units' if schema_name else "memory_units"
-    banks_ref = f'"{schema_name}".banks' if schema_name else "banks"
-
-    rows = bind.execute(text(f"SELECT bank_id, internal_id FROM {banks_ref}")).fetchall()  # noqa: S608
-    for row in rows:
-        bank_id = row[0]
-        internal_id = str(row[1]).replace("-", "")[:16]
-        escaped_bank_id = bank_id.replace("'", "''")
-        for ft, ft_short in _HNSW_FACT_TYPES.items():
-            idx_name = f"idx_mu_emb_{ft_short}_{internal_id}"
-            # Index name is schema-unqualified (indexes live in the schema of their table)
-            bind.execute(
-                text(
-                    f"CREATE INDEX IF NOT EXISTS {idx_name} "
-                    f"ON {table_ref} USING hnsw (embedding vector_cosine_ops) "
-                    f"WHERE fact_type = '{ft}' AND bank_id = '{escaped_bank_id}'"
-                )
-            )
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-
-    # Drop per-bank HNSW indexes (iterate existing banks)
-    bind = op.get_bind()
-    schema_name = context.config.get_main_option("target_schema")
-    banks_ref = f'"{schema_name}".banks' if schema_name else "banks"
-
-    rows = bind.execute(text(f"SELECT internal_id FROM {banks_ref}")).fetchall()  # noqa: S608
-    for row in rows:
-        internal_id = str(row[0]).replace("-", "")[:16]
-        for ft_short in _HNSW_FACT_TYPES.values():
-            idx_name = f"idx_mu_emb_{ft_short}_{internal_id}"
-            bind.execute(text(f"DROP INDEX IF EXISTS {schema}{idx_name}"))
-
-    # Restore the global HNSW index
-    table_ref = f'"{schema_name}".memory_units' if schema_name else "memory_units"
-    op.execute(
-        f"CREATE INDEX IF NOT EXISTS idx_memory_units_embedding ON {table_ref} USING hnsw (embedding vector_cosine_ops)"
-    )
-
-    # Restore old fact_type-only partial indexes
-    op.execute(
-        f"CREATE INDEX IF NOT EXISTS idx_mu_emb_world "
-        f"ON {table_ref} USING hnsw (embedding vector_cosine_ops) "
-        f"WHERE fact_type = 'world'"
-    )
-    op.execute(
-        f"CREATE INDEX IF NOT EXISTS idx_mu_emb_observation "
-        f"ON {table_ref} USING hnsw (embedding vector_cosine_ops) "
-        f"WHERE fact_type = 'observation'"
-    )
-    op.execute(
-        f"CREATE INDEX IF NOT EXISTS idx_mu_emb_experience "
-        f"ON {table_ref} USING hnsw (embedding vector_cosine_ops) "
-        f"WHERE fact_type = 'experience'"
-    )
-
-    # Drop internal_id column
-    op.execute(f"ALTER TABLE {schema}banks DROP CONSTRAINT IF EXISTS banks_internal_id_unique")
-    op.execute(f"ALTER TABLE {schema}banks DROP COLUMN IF EXISTS internal_id")

hindsight-api-slim/hindsight_api/alembic/versions/e4f5a6b7c8d9_add_webhooks_tables.py

@@ -1,62 +0,0 @@
-"""Add webhooks table and next_retry_at to async_operations.
-
-Webhook deliveries are handled as async_operations tasks (operation_type='webhook_delivery')
-rather than a dedicated webhook_deliveries table.
-
-Revision ID: e4f5a6b7c8d9
-Revises: d2e3f4a5b6c7
-Create Date: 2026-03-04
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "e4f5a6b7c8d9"
-down_revision: str | Sequence[str] | None = "d2e3f4a5b6c7"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-
-    op.execute(
-        f"""
-        CREATE TABLE IF NOT EXISTS {schema}webhooks (
-            id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
-            bank_id TEXT,
-            url TEXT NOT NULL,
-            secret TEXT,
-            event_types TEXT[] NOT NULL DEFAULT '{{}}',
-            enabled BOOLEAN NOT NULL DEFAULT TRUE,
-            created_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
-            updated_at TIMESTAMPTZ NOT NULL DEFAULT NOW()
-        )
-        """
-    )
-
-    # Index for bank-scoped webhook lookup
-    op.execute(f"CREATE INDEX IF NOT EXISTS idx_webhooks_bank_id ON {schema}webhooks(bank_id)")
-
-    # Add next_retry_at to async_operations for task-owned retry scheduling
-    op.execute(f"ALTER TABLE {schema}async_operations ADD COLUMN IF NOT EXISTS next_retry_at TIMESTAMPTZ NULL")
-
-    # Index for polling: status + next_retry_at
-    op.execute(
-        f"CREATE INDEX IF NOT EXISTS idx_async_operations_status_retry "
-        f"ON {schema}async_operations(status, next_retry_at)"
-    )
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_async_operations_status_retry")
-    op.execute(f"ALTER TABLE {schema}async_operations DROP COLUMN IF EXISTS next_retry_at")
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_webhooks_bank_id")
-    op.execute(f"DROP TABLE IF EXISTS {schema}webhooks")

hindsight-api-slim/hindsight_api/alembic/versions/e5f6g7h8i9j0_cascade_delete_ops_on_bank_delete.py

@@ -1,73 +0,0 @@
-"""Add CASCADE DELETE FK from async_operations and webhooks to banks.
-
-When a bank is deleted, all its async_operations and webhooks rows are
-automatically deleted by the database. This ensures that any in-flight
-worker tasks detect the deletion via _check_op_alive() and abort early.
-
-Revision ID: e5f6g7h8i9j0
-Revises: d4e5f6g7h8i9
-Create Date: 2026-03-11
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "e5f6g7h8i9j0"
-down_revision: str | Sequence[str] | None = "d4e5f6g7h8i9"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-
-    # Remove orphaned async_operations rows whose bank no longer exists
-    # (can happen because there was no FK before this migration).
-    op.execute(
-        f"""
-        DELETE FROM {schema}async_operations
-        WHERE bank_id IS NOT NULL
-          AND bank_id NOT IN (SELECT bank_id FROM {schema}banks)
-        """
-    )
-
-    # Remove orphaned webhooks rows whose bank no longer exists.
-    op.execute(
-        f"""
-        DELETE FROM {schema}webhooks
-        WHERE bank_id IS NOT NULL
-          AND bank_id NOT IN (SELECT bank_id FROM {schema}banks)
-        """
-    )
-
-    # Add FK with ON DELETE CASCADE so that deleting a bank automatically
-    # cleans up all its pending/processing operations and webhook configs.
-    op.execute(
-        f"""
-        ALTER TABLE {schema}async_operations
-            ADD CONSTRAINT fk_async_operations_bank_id
-            FOREIGN KEY (bank_id) REFERENCES {schema}banks(bank_id)
-            ON DELETE CASCADE
-        """
-    )
-
-    op.execute(
-        f"""
-        ALTER TABLE {schema}webhooks
-            ADD CONSTRAINT fk_webhooks_bank_id
-            FOREIGN KEY (bank_id) REFERENCES {schema}banks(bank_id)
-            ON DELETE CASCADE
-        """
-    )
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}async_operations DROP CONSTRAINT IF EXISTS fk_async_operations_bank_id")
-    op.execute(f"ALTER TABLE {schema}webhooks DROP CONSTRAINT IF EXISTS fk_webhooks_bank_id")

hindsight-api-slim/hindsight_api/alembic/versions/f6g7h8i9j0k1_chunk_fk_cascade_delete.py

@@ -1,38 +0,0 @@
-"""chunk_fk_cascade_delete
-
-Revision ID: f6g7h8i9j0k1
-Revises: e5f6g7h8i9j0
-Create Date: 2026-03-16 00:00:00.000000
-
-"""
-
-from collections.abc import Sequence
-
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = "f6g7h8i9j0k1"
-down_revision: str | Sequence[str] | None = "e5f6g7h8i9j0"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def upgrade() -> None:
-    """Change memory_units.chunk_id FK from SET NULL to CASCADE.
-
-    When a document is deleted the CASCADE reaches chunks first; with SET NULL
-    the memory_units rows survived with chunk_id = NULL, leaving ghost records.
-    Switching to CASCADE ensures they are removed together with their chunk.
-    """
-    op.drop_constraint("memory_units_chunk_fkey", "memory_units", type_="foreignkey")
-    op.create_foreign_key(
-        "memory_units_chunk_fkey", "memory_units", "chunks", ["chunk_id"], ["chunk_id"], ondelete="CASCADE"
-    )
-
-
-def downgrade() -> None:
-    """Revert to SET NULL behaviour."""
-    op.drop_constraint("memory_units_chunk_fkey", "memory_units", type_="foreignkey")
-    op.create_foreign_key(
-        "memory_units_chunk_fkey", "memory_units", "chunks", ["chunk_id"], ["chunk_id"], ondelete="SET NULL"
-    )

hindsight-api-slim/hindsight_api/alembic/versions/f7g8h9i0j1k2_add_webhook_http_config.py

@@ -1,33 +0,0 @@
-"""Add http_config JSONB column to webhooks table.
-
-Stores HTTP delivery configuration (method, timeout, headers, params) as a
-single JSONB column rather than separate columns.
-
-Revision ID: f7g8h9i0j1k2
-Revises: e4f5a6b7c8d9
-Create Date: 2026-03-04
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "f7g8h9i0j1k2"
-down_revision: str | Sequence[str] | None = "e4f5a6b7c8d9"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}webhooks ADD COLUMN IF NOT EXISTS http_config JSONB NOT NULL DEFAULT '{{}}'")
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}webhooks DROP COLUMN IF EXISTS http_config")

hindsight-api-slim/hindsight_api/alembic/versions/g7h8i9j0k1l2_backsweep_orphan_observations.py

@@ -1,71 +0,0 @@
-"""backsweep_orphan_memory_units
-
-Two-pass cleanup of memory_units rows that were never removed by earlier bugs:
-
-Pass 1 — any fact_type, bank gone:
-  memory_units whose bank_id no longer exists in banks.  These accumulate when
-  a bank is deleted without a proper cascade (no FK from memory_units to banks
-  exists in the schema).
-
-Pass 2 — observations only, all sources gone:
-  observation rows whose bank still exists but every source_memory_id points
-  to a deleted memory unit.  These were left behind before PR #580 fixed the
-  chunk FK cascade and before delete_document() called
-  _delete_stale_observations_for_memories.
-
-Revision ID: g7h8i9j0k1l2
-Revises: f6g7h8i9j0k1
-Create Date: 2026-03-16
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "g7h8i9j0k1l2"
-down_revision: str | Sequence[str] | None = "f6g7h8i9j0k1"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-    mu = f"{schema}memory_units"
-    banks = f"{schema}banks"
-
-    # Pass 1: delete all memory_units (any fact_type) whose bank no longer exists.
-    # There is no FK from memory_units to banks, so these never cascade away.
-    op.execute(
-        f"""
-        DELETE FROM {mu}
-        WHERE NOT EXISTS (
-            SELECT 1 FROM {banks} b WHERE b.bank_id = {mu}.bank_id
-        )
-        """
-    )
-
-    # Pass 2: delete orphaned observations whose bank still exists but every
-    # source_memory_id refers to a now-deleted memory unit (or the array is
-    # empty).  Observations with at least one surviving source are left alone.
-    op.execute(
-        f"""
-        DELETE FROM {mu} orphan
-        WHERE orphan.fact_type = 'observation'
-          AND NOT EXISTS (
-              SELECT 1
-              FROM {mu} src
-              WHERE src.id = ANY(orphan.source_memory_ids)
-                AND src.bank_id = orphan.bank_id
-          )
-        """
-    )
-
-
-def downgrade() -> None:
-    # Deleted rows cannot be restored.
-    pass

hindsight-api-slim/hindsight_api/alembic/versions/n9i0j1k2l3m4_learnings_and_pinned_reflections.py

@@ -1,317 +0,0 @@
-"""learnings_and_pinned_reflections
-
-Revision ID: n9i0j1k2l3m4
-Revises: m8h9i0j1k2l3
-Create Date: 2026-01-21 00:00:00.000000
-
-This migration:
-1. Creates the 'learnings' table for automatic bottom-up consolidation
-2. Creates the 'pinned_reflections' table for user-curated living documents
-3. Adds consolidation tracking columns to the 'banks' table
-"""
-
-import os
-from collections.abc import Sequence
-
-from alembic import context, op
-from sqlalchemy import text
-
-# revision identifiers, used by Alembic.
-revision: str = "n9i0j1k2l3m4"
-down_revision: str | Sequence[str] | None = "m8h9i0j1k2l3"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    """Get schema prefix for table names (required for multi-tenant support)."""
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def _detect_vector_extension() -> str:
-    """
-    Detect or validate vector extension: 'pgvector', 'vchord', or 'pgvectorscale'.
-    Respects HINDSIGHT_API_VECTOR_EXTENSION env var if set.
-    """
-    conn = op.get_bind()
-    vector_extension = os.getenv("HINDSIGHT_API_VECTOR_EXTENSION", "pgvector").lower()
-
-    # Validate configured extension is installed
-    if vector_extension == "pgvectorscale":
-        # pgvectorscale/DiskANN requires pgvector
-        pgvector_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vector'")).scalar()
-        if not pgvector_check:
-            raise RuntimeError(
-                "DiskANN requires pgvector. Install with: CREATE EXTENSION vector; then vectorscale or pg_diskann CASCADE;"
-            )
-        # Check for either vectorscale (open source) or pg_diskann (Azure)
-        vectorscale_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vectorscale'")).scalar()
-        pg_diskann_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'pg_diskann'")).scalar()
-
-        if vectorscale_check:
-            return "pgvectorscale"
-        elif pg_diskann_check:
-            return "pg_diskann"
-        else:
-            raise RuntimeError(
-                "Configured vector extension 'pgvectorscale' not found. Install either:\n"
-                "  - pgvectorscale: CREATE EXTENSION vectorscale CASCADE;\n"
-                "  - pg_diskann (Azure): CREATE EXTENSION pg_diskann CASCADE;"
-            )
-    elif vector_extension == "vchord":
-        vchord_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vchord'")).scalar()
-        if not vchord_check:
-            raise RuntimeError(
-                "Configured vector extension 'vchord' not found. Install it with: CREATE EXTENSION vchord CASCADE;"
-            )
-        return "vchord"
-    elif vector_extension == "pgvector":
-        pgvector_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vector'")).scalar()
-        if not pgvector_check:
-            raise RuntimeError(
-                "Configured vector extension 'pgvector' not found. Install it with: CREATE EXTENSION vector;"
-            )
-        return "pgvector"
-    else:
-        raise ValueError(
-            f"Invalid HINDSIGHT_API_VECTOR_EXTENSION: {vector_extension}. Must be 'pgvector', 'vchord', or 'pgvectorscale'"
-        )
-
-
-def _detect_text_search_extension() -> str:
-    """
-    Detect or validate text search extension: 'native', 'vchord', or 'pg_textsearch'.
-    Respects HINDSIGHT_API_TEXT_SEARCH_EXTENSION env var.
-    Creates the extension if needed.
-    """
-    text_search_extension = os.getenv("HINDSIGHT_API_TEXT_SEARCH_EXTENSION", "native").lower()
-
-    if text_search_extension == "vchord":
-        # Create vchord_bm25 extension if not exists
-        try:
-            op.execute("CREATE EXTENSION IF NOT EXISTS vchord_bm25 CASCADE")
-        except Exception:
-            # Extension might already exist or user lacks permissions - verify it exists
-            conn = op.get_bind()
-            result = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vchord_bm25'")).fetchone()
-            if not result:
-                # Extension truly doesn't exist - re-raise the error
-                raise
-        return "vchord"
-    elif text_search_extension == "pg_textsearch":
-        # Create pg_textsearch extension if not exists
-        try:
-            op.execute("CREATE EXTENSION IF NOT EXISTS pg_textsearch CASCADE")
-        except Exception:
-            # Extension might already exist or user lacks permissions - verify it exists
-            conn = op.get_bind()
-            result = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'pg_textsearch'")).fetchone()
-            if not result:
-                # Extension truly doesn't exist - re-raise the error
-                raise
-        return "pg_textsearch"
-    elif text_search_extension == "native":
-        return "native"
-    else:
-        raise ValueError(
-            f"Invalid HINDSIGHT_API_TEXT_SEARCH_EXTENSION: {text_search_extension}. Must be 'native', 'vchord', or 'pg_textsearch'"
-        )
-
-
-def upgrade() -> None:
-    """Create learnings and pinned_reflections tables."""
-    schema = _get_schema_prefix()
-
-    # Detect which vector extension is available
-    vector_ext = _detect_vector_extension()
-
-    # Detect which text search extension to use
-    text_search_ext = _detect_text_search_extension()
-
-    # 1. Create learnings table
-    op.execute(f"""
-        CREATE TABLE {schema}learnings (
-            id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
-            bank_id VARCHAR(64) NOT NULL,
-            text TEXT NOT NULL,
-            proof_count INT NOT NULL DEFAULT 1,
-            history JSONB DEFAULT '[]'::jsonb,
-            mission_context VARCHAR(64),
-            pre_mission_change BOOLEAN DEFAULT FALSE,
-            embedding vector(384),
-            tags VARCHAR[] DEFAULT ARRAY[]::VARCHAR[],
-            created_at TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT now(),
-            updated_at TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT now()
-        )
-    """)
-
-    # Add foreign key constraint
-    op.execute(f"""
-        ALTER TABLE {schema}learnings
-        ADD CONSTRAINT fk_learnings_bank_id
-        FOREIGN KEY (bank_id) REFERENCES {schema}banks(bank_id) ON DELETE CASCADE
-    """)
-
-    # Indexes for learnings
-    op.execute(f"CREATE INDEX idx_learnings_bank_id ON {schema}learnings(bank_id)")
-
-    # Create vector index based on detected extension
-    if vector_ext == "pgvectorscale":
-        op.execute(f"""
-            CREATE INDEX idx_learnings_embedding ON {schema}learnings
-            USING diskann (embedding vector_cosine_ops)
-            WITH (num_neighbors = 50)
-        """)
-    elif vector_ext == "pg_diskann":
-        op.execute(f"""
-            CREATE INDEX idx_learnings_embedding ON {schema}learnings
-            USING diskann (embedding vector_cosine_ops)
-            WITH (max_neighbors = 50)
-        """)
-    elif vector_ext == "vchord":
-        op.execute(f"""
-            CREATE INDEX idx_learnings_embedding ON {schema}learnings
-            USING vchordrq (embedding vector_l2_ops)
-        """)
-    else:  # pgvector
-        op.execute(f"""
-            CREATE INDEX idx_learnings_embedding ON {schema}learnings
-            USING hnsw (embedding vector_cosine_ops)
-        """)
-
-    op.execute(f"CREATE INDEX idx_learnings_tags ON {schema}learnings USING GIN(tags)")
-
-    # Full-text search for learnings
-    if text_search_ext == "vchord":
-        # VectorChord BM25: bm25vector type (no GENERATED - tokenization happens on INSERT)
-        # Note: vchord_bm25 extension creates types in bm25_catalog schema
-        op.execute(f"""
-            ALTER TABLE {schema}learnings ADD COLUMN search_vector bm25_catalog.bm25vector
-        """)
-        op.execute(f"""
-            CREATE INDEX idx_learnings_text_search ON {schema}learnings
-            USING bm25 (search_vector bm25_catalog.bm25_ops)
-        """)
-    elif text_search_ext == "pg_textsearch":
-        # Timescale pg_textsearch: dummy TEXT column for consistency (indexes operate on base columns directly)
-        op.execute(f"""
-            ALTER TABLE {schema}learnings ADD COLUMN search_vector TEXT
-        """)
-        op.execute(f"""
-            CREATE INDEX idx_learnings_text_search ON {schema}learnings
-            USING bm25(text) WITH (text_config='english')
-        """)
-    else:  # native
-        # Native PostgreSQL: tsvector with automatic generation
-        op.execute(f"""
-            ALTER TABLE {schema}learnings ADD COLUMN search_vector tsvector
-            GENERATED ALWAYS AS (to_tsvector('english', text)) STORED
-        """)
-        op.execute(f"CREATE INDEX idx_learnings_text_search ON {schema}learnings USING gin(search_vector)")
-
-    # 2. Create pinned_reflections table
-    op.execute(f"""
-        CREATE TABLE {schema}pinned_reflections (
-            id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
-            bank_id VARCHAR(64) NOT NULL,
-            name VARCHAR(256) NOT NULL,
-            source_query TEXT NOT NULL,
-            content TEXT NOT NULL,
-            embedding vector(384),
-            tags VARCHAR[] DEFAULT ARRAY[]::VARCHAR[],
-            last_refreshed_at TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT now(),
-            created_at TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT now()
-        )
-    """)
-
-    # Add foreign key constraint
-    op.execute(f"""
-        ALTER TABLE {schema}pinned_reflections
-        ADD CONSTRAINT fk_pinned_reflections_bank_id
-        FOREIGN KEY (bank_id) REFERENCES {schema}banks(bank_id) ON DELETE CASCADE
-    """)
-
-    # Indexes for pinned_reflections
-    op.execute(f"CREATE INDEX idx_pinned_reflections_bank_id ON {schema}pinned_reflections(bank_id)")
-
-    # Create vector index based on detected extension
-    if vector_ext == "pgvectorscale":
-        op.execute(f"""
-            CREATE INDEX idx_pinned_reflections_embedding ON {schema}pinned_reflections
-            USING diskann (embedding vector_cosine_ops)
-            WITH (num_neighbors = 50)
-        """)
-    elif vector_ext == "pg_diskann":
-        op.execute(f"""
-            CREATE INDEX idx_pinned_reflections_embedding ON {schema}pinned_reflections
-            USING diskann (embedding vector_cosine_ops)
-            WITH (max_neighbors = 50)
-        """)
-    elif vector_ext == "vchord":
-        op.execute(f"""
-            CREATE INDEX idx_pinned_reflections_embedding ON {schema}pinned_reflections
-            USING vchordrq (embedding vector_l2_ops)
-        """)
-    else:  # pgvector
-        op.execute(f"""
-            CREATE INDEX idx_pinned_reflections_embedding ON {schema}pinned_reflections
-            USING hnsw (embedding vector_cosine_ops)
-        """)
-
-    op.execute(f"CREATE INDEX idx_pinned_reflections_tags ON {schema}pinned_reflections USING GIN(tags)")
-
-    # Full-text search for pinned_reflections
-    if text_search_ext == "vchord":
-        # VectorChord BM25: bm25vector type (no GENERATED - tokenization happens on INSERT/UPDATE)
-        # Note: vchord_bm25 extension creates types in bm25_catalog schema
-        op.execute(f"""
-            ALTER TABLE {schema}pinned_reflections ADD COLUMN search_vector bm25_catalog.bm25vector
-        """)
-        op.execute(f"""
-            CREATE INDEX idx_pinned_reflections_text_search ON {schema}pinned_reflections
-            USING bm25 (search_vector bm25_catalog.bm25_ops)
-        """)
-    elif text_search_ext == "pg_textsearch":
-        # Timescale pg_textsearch: dummy TEXT column for consistency (indexes operate on base columns directly)
-        op.execute(f"""
-            ALTER TABLE {schema}pinned_reflections ADD COLUMN search_vector TEXT
-        """)
-        op.execute(f"""
-            CREATE INDEX idx_pinned_reflections_text_search ON {schema}pinned_reflections
-            USING bm25(content)
-            WITH (text_config='english')
-        """)
-    else:  # native
-        # Native PostgreSQL: tsvector with automatic generation
-        op.execute(f"""
-            ALTER TABLE {schema}pinned_reflections ADD COLUMN search_vector tsvector
-            GENERATED ALWAYS AS (to_tsvector('english', COALESCE(name, '') || ' ' || content)) STORED
-        """)
-        op.execute(f"""
-            CREATE INDEX idx_pinned_reflections_text_search ON {schema}pinned_reflections
-            USING gin(search_vector)
-        """)
-
-    # 3. Add consolidation tracking columns to banks table
-    op.execute(f"""
-        ALTER TABLE {schema}banks
-        ADD COLUMN IF NOT EXISTS last_consolidated_at TIMESTAMP WITH TIME ZONE
-    """)
-    op.execute(f"""
-        ALTER TABLE {schema}banks
-        ADD COLUMN IF NOT EXISTS mission_changed_at TIMESTAMP WITH TIME ZONE
-    """)
-
-
-def downgrade() -> None:
-    """Drop learnings and pinned_reflections tables."""
-    schema = _get_schema_prefix()
-
-    # Drop tables
-    op.execute(f"DROP TABLE IF EXISTS {schema}learnings CASCADE")
-    op.execute(f"DROP TABLE IF EXISTS {schema}pinned_reflections CASCADE")
-
-    # Remove columns from banks
-    op.execute(f"ALTER TABLE {schema}banks DROP COLUMN IF EXISTS last_consolidated_at")
-    op.execute(f"ALTER TABLE {schema}banks DROP COLUMN IF EXISTS mission_changed_at")

hindsight-api-slim/hindsight_api/alembic/versions/w8r9s0t1u2v3_fix_mental_models_pk_isolation.py

@@ -1,60 +0,0 @@
-"""Fix mental_models primary key to be scoped per bank
-
-Revision ID: w8r9s0t1u2v3
-Revises: v7q8r9s0t1u2
-Create Date: 2026-02-05
-
-This migration fixes a critical bank isolation bug where mental_models.id was
-globally unique across all banks instead of being scoped per bank. This caused
-conflicts when different banks tried to use the same custom ID.
-
-CRITICAL FIX: Changes primary key from (id) to (bank_id, id) to ensure proper isolation.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "w8r9s0t1u2v3"
-down_revision: str | Sequence[str] | None = "v7q8r9s0t1u2"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    """Get schema prefix for table names (required for multi-tenant support)."""
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    """Change mental_models primary key from (id) to (bank_id, id) for proper bank isolation."""
-    schema = _get_schema_prefix()
-
-    # Drop the old primary key constraint (just id)
-    # Note: The constraint might be named differently on different DBs
-    # Try both old names (pinned_reflections_pkey from original, mental_models_pkey from rename)
-    op.execute(f"ALTER TABLE {schema}mental_models DROP CONSTRAINT IF EXISTS pinned_reflections_pkey")
-    op.execute(f"ALTER TABLE {schema}mental_models DROP CONSTRAINT IF EXISTS mental_models_pkey")
-
-    # Create the new composite primary key (bank_id, id)
-    # This ensures IDs are scoped per bank, not globally
-    op.execute(f"""
-        ALTER TABLE {schema}mental_models
-        ADD CONSTRAINT mental_models_pkey PRIMARY KEY (bank_id, id)
-    """)
-
-
-def downgrade() -> None:
-    """Revert mental_models primary key from (bank_id, id) to (id)."""
-    schema = _get_schema_prefix()
-
-    # Drop the composite primary key
-    op.execute(f"ALTER TABLE {schema}mental_models DROP CONSTRAINT IF EXISTS mental_models_pkey")
-
-    # Restore the old primary key (just id)
-    # WARNING: This downgrade will fail if there are duplicate IDs across banks
-    op.execute(f"""
-        ALTER TABLE {schema}mental_models
-        ADD CONSTRAINT mental_models_pkey PRIMARY KEY (id)
-    """)

hindsight-api-slim/hindsight_api/alembic/versions/x9s0t1u2v3w4_add_bank_config_column.py

@@ -1,64 +0,0 @@
-"""Add config JSONB column to banks table for hierarchical configuration
-
-Revision ID: x9s0t1u2v3w4
-Revises: w8r9s0t1u2v3
-Create Date: 2026-02-09
-
-This migration adds a `config` JSONB column to the banks table to support
-per-bank configuration overrides. This enables hierarchical configuration where:
-- Global config is loaded from environment variables
-- Tenant config is provided via TenantExtension
-- Bank config overrides are stored in banks.config JSONB column
-
-The config column stores overrides for hierarchical fields (LLM settings,
-retention parameters, retrieval settings, etc.) in Python field name format.
-"""
-
-from collections.abc import Sequence
-
-import sqlalchemy as sa
-from alembic import context, op
-from sqlalchemy.dialects.postgresql import JSONB
-
-revision: str = "x9s0t1u2v3w4"
-down_revision: str | Sequence[str] | None = "w8r9s0t1u2v3"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    """Get schema prefix for table names (required for multi-tenant support)."""
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    """Add config JSONB column to banks table with GIN index."""
-    schema = _get_schema_prefix()
-
-    # Add config column to banks table
-    op.execute(f"""
-        ALTER TABLE {schema}banks
-        ADD COLUMN config JSONB NOT NULL DEFAULT '{{}}'::jsonb
-    """)
-
-    # Add GIN index for efficient JSONB queries
-    op.execute(f"""
-        CREATE INDEX idx_banks_config
-        ON {schema}banks
-        USING gin(config)
-    """)
-
-
-def downgrade() -> None:
-    """Remove config column and index from banks table."""
-    schema = _get_schema_prefix()
-
-    # Drop index first
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_banks_config")
-
-    # Drop column
-    op.execute(f"""
-        ALTER TABLE {schema}banks
-        DROP COLUMN IF EXISTS config
-    """)

hindsight-api-slim/hindsight_api/alembic/versions/y0t1u2v3w4x5_add_result_metadata_gin_index.py

@@ -1,49 +0,0 @@
-"""Add GIN index on async_operations.result_metadata for parent_operation_id queries
-
-Revision ID: y0t1u2v3w4x5
-Revises: x9s0t1u2v3w4
-Create Date: 2026-02-13
-
-This migration adds a GIN index on the result_metadata JSONB column in the
-async_operations table to support efficient queries for child operations by
-parent_operation_id.
-
-The index enables fast lookups when querying for child operations:
-  SELECT * FROM async_operations
-  WHERE result_metadata::jsonb @> '{"parent_operation_id": "uuid"}'::jsonb
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "y0t1u2v3w4x5"
-down_revision: str | Sequence[str] | None = "x9s0t1u2v3w4"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    """Get schema prefix for table names (required for multi-tenant support)."""
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    """Add GIN index on result_metadata for efficient parent_operation_id queries."""
-    schema = _get_schema_prefix()
-
-    # Add GIN index for JSONB containment queries (@> operator)
-    op.execute(f"""
-        CREATE INDEX IF NOT EXISTS idx_async_operations_result_metadata
-        ON {schema}async_operations
-        USING gin(result_metadata)
-    """)
-
-
-def downgrade() -> None:
-    """Remove GIN index on result_metadata."""
-    schema = _get_schema_prefix()
-
-    # Drop index
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_async_operations_result_metadata")

hindsight-api-slim/hindsight_api/alembic/versions/z1u2v3w4x5y6_add_observation_tags_to_memory_units.py

@@ -1,35 +0,0 @@
-"""Add observation_scopes column to memory_units table
-
-Revision ID: z1u2v3w4x5y6
-Revises: a1b2c3d4e5f6
-Create Date: 2026-02-25
-
-Adds observation_scopes JSONB column to memory_units to control how observations
-are scoped during consolidation. Accepts "per_tag", "combined", or an explicit
-list of tag-set lists for custom multi-pass consolidation.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "z1u2v3w4x5y6"
-down_revision: str | Sequence[str] | None = "a1b2c3d4e5f6"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    """Get schema prefix for table names (required for multi-tenant support)."""
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def upgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}memory_units ADD COLUMN IF NOT EXISTS observation_scopes JSONB")
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}memory_units DROP COLUMN IF EXISTS observation_scopes")

hindsight-api-slim/hindsight_api/api/mcp.py

@@ -1,461 +0,0 @@
-"""Hindsight MCP Server implementation using FastMCP (HTTP transport)."""
-
-import json
-import logging
-import os
-from contextvars import ContextVar
-
-from fastmcp import FastMCP
-
-from hindsight_api import MemoryEngine
-from hindsight_api.config import _get_raw_config
-from hindsight_api.engine.memory_engine import _current_schema
-from hindsight_api.extensions import MCPExtension, load_extension
-from hindsight_api.extensions.tenant import AuthenticationError
-from hindsight_api.mcp_tools import MCPToolsConfig, register_mcp_tools
-from hindsight_api.models import RequestContext
-
-# All tools available in the system (explicit list — no wildcards)
-_ALL_TOOLS: frozenset[str] = frozenset(
-    {
-        "retain",
-        "recall",
-        "reflect",
-        "list_banks",
-        "create_bank",
-        "list_mental_models",
-        "get_mental_model",
-        "create_mental_model",
-        "update_mental_model",
-        "delete_mental_model",
-        "refresh_mental_model",
-        "list_directives",
-        "create_directive",
-        "delete_directive",
-        "list_memories",
-        "get_memory",
-        "delete_memory",
-        "list_documents",
-        "get_document",
-        "delete_document",
-        "list_operations",
-        "get_operation",
-        "cancel_operation",
-        "list_tags",
-        "get_bank",
-        "get_bank_stats",
-        "update_bank",
-        "delete_bank",
-        "clear_memories",
-    }
-)
-
-# Configure logging from HINDSIGHT_API_LOG_LEVEL environment variable
-_log_level_str = os.environ.get("HINDSIGHT_API_LOG_LEVEL", "info").lower()
-_log_level_map = {
-    "critical": logging.CRITICAL,
-    "error": logging.ERROR,
-    "warning": logging.WARNING,
-    "info": logging.INFO,
-    "debug": logging.DEBUG,
-    "trace": logging.DEBUG,
-}
-logging.basicConfig(
-    level=_log_level_map.get(_log_level_str, logging.INFO),
-    format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
-)
-logger = logging.getLogger(__name__)
-
-# Default bank_id from environment variable
-DEFAULT_BANK_ID = os.environ.get("HINDSIGHT_MCP_BANK_ID", "default")
-
-# Legacy MCP authentication token (for backwards compatibility)
-# If set, this token is checked first before TenantExtension auth
-MCP_AUTH_TOKEN = os.environ.get("HINDSIGHT_API_MCP_AUTH_TOKEN")
-
-# Context variable to hold the current bank_id
-_current_bank_id: ContextVar[str | None] = ContextVar("current_bank_id", default=None)
-
-# Context variable to hold the current API key (for tenant auth propagation)
-_current_api_key: ContextVar[str | None] = ContextVar("current_api_key", default=None)
-
-# Context variables for tenant_id and api_key_id (set by authenticate, used by usage metering)
-_current_tenant_id: ContextVar[str | None] = ContextVar("current_tenant_id", default=None)
-_current_api_key_id: ContextVar[str | None] = ContextVar("current_api_key_id", default=None)
-
-
-def get_current_bank_id() -> str | None:
-    """Get the current bank_id from context."""
-    return _current_bank_id.get()
-
-
-def get_current_api_key() -> str | None:
-    """Get the current API key from context."""
-    return _current_api_key.get()
-
-
-def get_current_tenant_id() -> str | None:
-    """Get the current tenant_id from context."""
-    return _current_tenant_id.get()
-
-
-def get_current_api_key_id() -> str | None:
-    """Get the current api_key_id from context."""
-    return _current_api_key_id.get()
-
-
-def create_mcp_server(memory: MemoryEngine, multi_bank: bool = True) -> FastMCP:
-    """
-    Create and configure the Hindsight MCP server.
-
-    Args:
-        memory: MemoryEngine instance (required)
-        multi_bank: If True, expose all tools with bank_id parameters (default).
-                   If False, only expose bank-scoped tools without bank_id parameters.
-
-    Returns:
-        Configured FastMCP server instance
-    """
-    mcp = FastMCP("hindsight-mcp-server")
-
-    global_config = _get_raw_config()
-
-    # Tools available for this mode (multi-bank exposes all tools; single-bank excludes bank-management tools)
-    _SINGLE_BANK_TOOLS: frozenset[str] = frozenset(
-        {
-            "retain",
-            "recall",
-            "reflect",
-            "list_mental_models",
-            "get_mental_model",
-            "create_mental_model",
-            "update_mental_model",
-            "delete_mental_model",
-            "refresh_mental_model",
-            "list_directives",
-            "create_directive",
-            "delete_directive",
-            "list_memories",
-            "get_memory",
-            "delete_memory",
-            "list_documents",
-            "get_document",
-            "delete_document",
-            "list_operations",
-            "get_operation",
-            "cancel_operation",
-            "list_tags",
-            "get_bank",
-            "update_bank",
-            "delete_bank",
-            "clear_memories",
-        }
-    )
-    base_tools: frozenset[str] | None = None if multi_bank else _SINGLE_BANK_TOOLS
-
-    # Apply global mcp_enabled_tools filter (env-level allowlist)
-    if global_config.mcp_enabled_tools is not None:
-        allowed = frozenset(global_config.mcp_enabled_tools)
-        base_tools = (base_tools if base_tools is not None else _ALL_TOOLS) & allowed
-
-    # Configure and register tools using shared module
-    config = MCPToolsConfig(
-        bank_id_resolver=get_current_bank_id,
-        api_key_resolver=get_current_api_key,  # Propagate API key for tenant auth
-        tenant_id_resolver=get_current_tenant_id,  # Propagate tenant_id for usage metering
-        api_key_id_resolver=get_current_api_key_id,  # Propagate api_key_id for usage metering
-        include_bank_id_param=multi_bank,
-        tools=base_tools,
-    )
-
-    register_mcp_tools(mcp, memory, config)
-
-    # Load and register additional tools from MCP extension if configured
-    mcp_extension = load_extension("MCP", MCPExtension)
-    if mcp_extension:
-        logger.info(f"Loading MCP extension: {mcp_extension.__class__.__name__}")
-        mcp_extension.register_tools(mcp, memory)
-
-    # Make all tools tolerant of extra arguments from LLMs (e.g., "explanation")
-    _make_tools_tolerant(mcp)
-
-    return mcp
-
-
-def _make_tools_tolerant(mcp: FastMCP) -> None:
-    """Wrap all tool run methods to strip unknown arguments before validation.
-
-    LLMs frequently add extra fields like "explanation" or "reasoning" to tool calls.
-    FastMCP's Pydantic TypeAdapter rejects these with "Unexpected keyword argument".
-    This wraps each tool's run() to filter arguments to only known parameters.
-    """
-    try:
-        for name, tool in mcp._tool_manager._tools.items():
-            if hasattr(tool, "parameters") and tool.parameters:
-                allowed = set(tool.parameters.get("properties", {}).keys())
-                original_run = tool.run
-
-                async def _tolerant_run(arguments, _allowed=allowed, _orig=original_run):
-                    extra_keys = set(arguments.keys()) - _allowed
-                    if extra_keys:
-                        logger.debug(f"Stripping unknown arguments from tool call: {extra_keys}")
-                        arguments = {k: v for k, v in arguments.items() if k in _allowed}
-                    return await _orig(arguments)
-
-                # FunctionTool is a Pydantic model with extra='forbid', so use
-                # object.__setattr__ to bypass Pydantic's setter validation.
-                object.__setattr__(tool, "run", _tolerant_run)
-    except (AttributeError, KeyError) as e:
-        logger.warning(f"Could not make tools tolerant of extra arguments: {e}")
-
-
-class MCPMiddleware:
-    """ASGI middleware that intercepts MCP requests and routes to appropriate MCP server.
-
-    This middleware wraps the main FastAPI app and intercepts requests matching the
-    configured prefix (default: /mcp). Non-MCP requests pass through to the inner app.
-
-    Authentication:
-        1. If HINDSIGHT_API_MCP_AUTH_TOKEN is set (legacy), validates against that token
-        2. Otherwise, uses TenantExtension.authenticate_mcp() from the MemoryEngine
-           - DefaultTenantExtension: no auth required (local dev)
-           - ApiKeyTenantExtension: validates against env var
-
-    Two modes based on URL structure:
-
-    1. Multi-bank mode (for /mcp/ root endpoint):
-       - Exposes all tools: retain, recall, reflect, list_banks, create_bank
-       - All tools include optional bank_id parameter for cross-bank operations
-       - Bank ID from: X-Bank-Id header or HINDSIGHT_MCP_BANK_ID env var
-
-    2. Single-bank mode (for /mcp/{bank_id}/ endpoints):
-       - Exposes bank-scoped tools only: retain, recall, reflect
-       - No bank_id parameter (comes from URL)
-       - No bank management tools (list_banks, create_bank)
-       - Recommended for agent isolation
-
-    Bank ID resolution priority:
-        1. URL path (e.g., /mcp/{bank_id}/) → single-bank mode
-        2. X-Bank-Id header → multi-bank mode
-        3. HINDSIGHT_MCP_BANK_ID env var → multi-bank mode (default: "default")
-
-    Examples:
-        # Single-bank mode (recommended for agent isolation)
-        claude mcp add --transport http my-agent http://localhost:8888/mcp/my-agent-bank/ \\
-            --header "Authorization: Bearer <token>"
-
-        # Multi-bank mode (for cross-bank operations)
-        claude mcp add --transport http hindsight http://localhost:8888/mcp \\
-            --header "X-Bank-Id: my-bank" --header "Authorization: Bearer <token>"
-    """
-
-    def __init__(
-        self,
-        app,
-        memory: MemoryEngine,
-        prefix: str = "/mcp",
-        multi_bank_app=None,
-        single_bank_app=None,
-        multi_bank_server=None,
-        single_bank_server=None,
-    ):
-        self.app = app
-        self.prefix = prefix
-        self.memory = memory
-        self.tenant_extension = memory._tenant_extension
-
-        if multi_bank_app and single_bank_app:
-            # Pre-created servers (used when called via add_middleware from create_app)
-            self.multi_bank_app = multi_bank_app
-            self.single_bank_app = single_bank_app
-            self.multi_bank_server = multi_bank_server
-            self.single_bank_server = single_bank_server
-        else:
-            # Create servers internally (for direct construction / tests)
-            self.multi_bank_server = create_mcp_server(memory, multi_bank=True)
-            self.multi_bank_app = self.multi_bank_server.http_app(path="/", stateless_http=True)
-            self.single_bank_server = create_mcp_server(memory, multi_bank=False)
-            self.single_bank_app = self.single_bank_server.http_app(path="/", stateless_http=True)
-
-    def _get_header(self, scope: dict, name: str) -> str | None:
-        """Extract a header value from ASGI scope."""
-        name_lower = name.lower().encode()
-        for header_name, header_value in scope.get("headers", []):
-            if header_name.lower() == name_lower:
-                return header_value.decode()
-        return None
-
-    async def __call__(self, scope, receive, send):
-        if scope["type"] != "http":
-            await self.app(scope, receive, send)
-            return
-
-        path = scope.get("path", "")
-
-        # Check if this is an MCP request (matches prefix)
-        if not (path == self.prefix or path.startswith(self.prefix + "/")):
-            # Not an MCP request — pass through to the inner app
-            await self.app(scope, receive, send)
-            return
-
-        # Strip prefix from path
-        path = path[len(self.prefix) :] or "/"
-
-        # Extract auth token from header (for tenant auth propagation)
-        auth_header = self._get_header(scope, "Authorization")
-        auth_token: str | None = None
-        if auth_header:
-            # Support both "Bearer <token>" and direct token
-            auth_token = auth_header[7:].strip() if auth_header.startswith("Bearer ") else auth_header.strip()
-
-        # Authenticate: check legacy MCP_AUTH_TOKEN first, then TenantExtension
-        tenant_context = None
-        auth_tenant_id: str | None = None
-        auth_api_key_id: str | None = None
-        if MCP_AUTH_TOKEN:
-            # Legacy authentication mode - validate against static token
-            if not auth_token:
-                await self._send_error(send, 401, "Authorization header required")
-                return
-            if auth_token != MCP_AUTH_TOKEN:
-                await self._send_error(send, 401, "Invalid authentication token")
-                return
-            # Legacy mode doesn't use tenant schemas
-            tenant_context = None
-        else:
-            # Use TenantExtension.authenticate_mcp() for auth
-            try:
-                auth_context = RequestContext(api_key=auth_token)
-                tenant_context = await self.tenant_extension.authenticate_mcp(auth_context)
-                # Capture tenant_id and api_key_id set by authenticate() for usage metering
-                auth_tenant_id = auth_context.tenant_id
-                auth_api_key_id = auth_context.api_key_id
-            except AuthenticationError as e:
-                await self._send_error(send, 401, str(e), extra_headers=e.headers)
-                return
-
-        # Set schema from tenant context so downstream DB queries use the correct schema
-        schema_token = (
-            _current_schema.set(tenant_context.schema_name) if tenant_context and tenant_context.schema_name else None
-        )
-
-        # Resolve bank_id: path takes priority over header.
-        # Path = user's explicit connection endpoint (e.g., /mcp/my-bank/).
-        # X-Bank-Id header = per-request override for multi-bank mode only.
-        bank_id = None
-        bank_id_from_path = False
-        new_path = path
-
-        # First, try to extract from path: /{bank_id}/...
-        if path.startswith("/") and len(path) > 1:
-            parts = path[1:].split("/", 1)
-            if parts[0]:
-                bank_id = parts[0]
-                bank_id_from_path = True
-                new_path = "/" + parts[1] if len(parts) > 1 else "/"
-
-        # If no path-based bank_id, try X-Bank-Id header (multi-bank mode)
-        if not bank_id:
-            bank_id = self._get_header(scope, "X-Bank-Id")
-
-        # Fall back to default bank_id
-        if not bank_id:
-            bank_id = DEFAULT_BANK_ID
-            logger.debug(f"Using default bank_id: {bank_id}")
-
-        # Select the appropriate MCP app based on how bank_id was provided:
-        # - Path-based bank_id → single-bank app (no bank_id param, scoped tools)
-        # - Header/env bank_id → multi-bank app (bank_id param, all tools)
-        target_app = self.single_bank_app if bank_id_from_path else self.multi_bank_app
-
-        # Set bank_id, api_key, tenant_id, and api_key_id context
-        bank_id_token = _current_bank_id.set(bank_id)
-        # Store the auth token for tenant extension to validate
-        api_key_token = _current_api_key.set(auth_token) if auth_token else None
-        # Store tenant_id and api_key_id from authentication for usage metering
-        tenant_id_token = _current_tenant_id.set(auth_tenant_id) if auth_tenant_id else None
-        api_key_id_token = _current_api_key_id.set(auth_api_key_id) if auth_api_key_id else None
-        try:
-            new_scope = scope.copy()
-            new_scope["path"] = new_path
-            # Clear root_path since we're passing directly to the app
-            new_scope["root_path"] = ""
-
-            # Ensure Accept header includes required MIME types for MCP SDK.
-            # Some clients (e.g., Claude Code) don't send Accept, causing
-            # the SDK to reject with 406 Not Acceptable.
-            accept_header = self._get_header(new_scope, "accept")
-            if not accept_header or "text/event-stream" not in accept_header:
-                headers = [(k, v) for k, v in new_scope.get("headers", []) if k.lower() != b"accept"]
-                headers.append((b"accept", b"application/json, text/event-stream"))
-                new_scope["headers"] = headers
-
-            # Wrap send to rewrite the SSE endpoint URL to include bank_id if using path-based routing.
-            # Only rewrite SSE (text/event-stream) responses to avoid corrupting tool results
-            # that might contain the literal string "data: /messages".
-            is_sse_response = False
-
-            async def send_wrapper(message):
-                nonlocal is_sse_response
-                if message["type"] == "http.response.start":
-                    for header_name, header_value in message.get("headers", []):
-                        if header_name == b"content-type" and b"text/event-stream" in header_value:
-                            is_sse_response = True
-                            break
-                if message["type"] == "http.response.body" and bank_id_from_path and is_sse_response:
-                    body = message.get("body", b"")
-                    if body and b"/messages" in body:
-                        # Rewrite /messages to /{bank_id}/messages in SSE endpoint event
-                        body = body.replace(b"data: /messages", f"data: /{bank_id}/messages".encode())
-                        message = {**message, "body": body}
-                await send(message)
-
-            await target_app(new_scope, receive, send_wrapper)
-        finally:
-            _current_bank_id.reset(bank_id_token)
-            if api_key_token is not None:
-                _current_api_key.reset(api_key_token)
-            if tenant_id_token is not None:
-                _current_tenant_id.reset(tenant_id_token)
-            if api_key_id_token is not None:
-                _current_api_key_id.reset(api_key_id_token)
-            if schema_token is not None:
-                _current_schema.reset(schema_token)
-
-    async def _send_error(self, send, status: int, message: str, extra_headers: dict[str, str] | None = None):
-        """Send an error response."""
-        body = json.dumps({"error": message}).encode()
-        headers = [(b"content-type", b"application/json")]
-        for key, value in (extra_headers or {}).items():
-            headers.append((key.encode(), value.encode()))
-        await send(
-            {
-                "type": "http.response.start",
-                "status": status,
-                "headers": headers,
-            }
-        )
-        await send(
-            {
-                "type": "http.response.body",
-                "body": body,
-            }
-        )
-
-
-def create_mcp_servers(memory: MemoryEngine):
-    """Create multi-bank and single-bank MCP servers and their Starlette apps.
-
-    Returns the servers and apps separately so lifespans can be chained before
-    the middleware wraps the main app.
-
-    Returns:
-        Tuple of (multi_bank_server, single_bank_server, multi_bank_app, single_bank_app)
-    """
-    multi_bank_server = create_mcp_server(memory, multi_bank=True)
-    multi_bank_app = multi_bank_server.http_app(path="/", stateless_http=True)
-
-    single_bank_server = create_mcp_server(memory, multi_bank=False)
-    single_bank_app = single_bank_server.http_app(path="/", stateless_http=True)
-
-    return multi_bank_server, single_bank_server, multi_bank_app, single_bank_app

hindsight-api-slim/hindsight_api/config_resolver.py

@@ -1,315 +0,0 @@
-"""
-Configuration resolution with hierarchical overrides.
-
-Resolves config values through the hierarchy:
-  Global (env vars) → Tenant config (via extension) → Bank config (database)
-
-Config values are resolved on every request to ensure consistency across
-multiple API servers.
-"""
-
-import json
-import logging
-from dataclasses import asdict, replace
-from typing import Any
-
-import asyncpg
-
-from hindsight_api.config import HindsightConfig, _get_raw_config, normalize_config_dict
-from hindsight_api.engine.memory_engine import fq_table
-from hindsight_api.extensions.tenant import TenantExtension
-from hindsight_api.models import RequestContext
-
-logger = logging.getLogger(__name__)
-
-
-class ConfigResolver:
-    """Resolves hierarchical configuration with tenant/bank overrides."""
-
-    def __init__(self, pool: asyncpg.Pool, tenant_extension: TenantExtension | None = None):
-        """
-        Initialize config resolver.
-
-        Args:
-            pool: Database connection pool
-            tenant_extension: Optional tenant extension for tenant-level config and permissions
-        """
-        self.pool = pool
-        self.tenant_extension = tenant_extension
-        self._global_config = _get_raw_config()
-        self._configurable_fields = HindsightConfig.get_configurable_fields()
-        self._credential_fields = HindsightConfig.get_credential_fields()
-
-    async def resolve_full_config(self, bank_id: str, context: RequestContext | None = None) -> HindsightConfig:
-        """
-        Resolve full HindsightConfig for a bank with hierarchical overrides applied.
-
-        This is for INTERNAL USE ONLY. Returns the complete config object with all fields
-        including credentials and static fields. Use get_bank_config() for API responses.
-
-        Resolution order:
-        1. Global config (from environment variables)
-        2. Tenant config overrides (from TenantExtension.get_tenant_config())
-        3. Bank config overrides (from banks.config JSONB)
-
-        Args:
-            bank_id: Bank identifier
-            context: Request context for tenant config resolution
-
-        Returns:
-            Complete HindsightConfig with hierarchical overrides applied
-        """
-        # Start with global config (all fields)
-        config_dict = asdict(self._global_config)
-
-        # Load tenant config overrides (if tenant extension available)
-        if self.tenant_extension and context:
-            try:
-                tenant_overrides = await self.tenant_extension.get_tenant_config(context)
-                if tenant_overrides:
-                    # Normalize keys and filter to configurable fields only
-                    normalized_tenant = normalize_config_dict(tenant_overrides)
-                    configurable_tenant = {k: v for k, v in normalized_tenant.items() if k in self._configurable_fields}
-                    config_dict.update(configurable_tenant)
-                    logger.debug(
-                        f"Applied tenant config overrides for bank {bank_id}: {list(configurable_tenant.keys())}"
-                    )
-            except Exception as e:
-                logger.warning(f"Failed to load tenant config for bank {bank_id}: {e}")
-
-        # Load bank config overrides
-        bank_overrides = await self._load_bank_config(bank_id)
-        if bank_overrides:
-            config_dict.update(bank_overrides)
-            logger.debug(f"Applied bank config overrides for bank {bank_id}: {list(bank_overrides.keys())}")
-
-        # Return full config object (dataclass doesn't have __init__ that accepts kwargs, so we update the object)
-        # Create a new config instance by copying the global config and updating fields
-        resolved_config = HindsightConfig(**config_dict)
-        return resolved_config
-
-    async def get_bank_config(self, bank_id: str, context: RequestContext | None = None) -> dict[str, Any]:
-        """
-        Get fully resolved config for a bank (filtered by permissions).
-
-        Resolution order:
-        1. Global config (from environment variables)
-        2. Tenant config overrides (from TenantExtension.get_tenant_config())
-        3. Bank config overrides (from banks.config JSONB)
-
-        Note: Config is resolved on every call (not cached) to ensure consistency
-        across multiple API servers.
-
-        SECURITY:
-        - Only returns configurable fields (excludes static/infrastructure fields)
-        - Filters out ALL credential fields (API keys, base URLs, etc.)
-        - Further filtered by tenant/bank permissions if extension provides them
-
-        Args:
-            bank_id: Bank identifier
-            context: Request context for tenant config resolution and permissions
-
-        Returns:
-            Dict of allowed configurable fields only (never includes credentials or static fields)
-        """
-        # Resolve full config with all hierarchical overrides
-        resolved_config = await self.resolve_full_config(bank_id, context)
-        config_dict = asdict(resolved_config)
-
-        # SECURITY: Filter to only configurable fields (exclude static/infrastructure)
-        filtered = {k: v for k, v in config_dict.items() if k in self._configurable_fields}
-
-        # SECURITY: Remove ALL credential fields (API keys, base URLs, etc.)
-        filtered = {k: v for k, v in filtered.items() if k not in self._credential_fields}
-
-        # PERMISSIONS: Further filter based on tenant/bank permissions
-        if self.tenant_extension and context:
-            try:
-                allowed_fields = await self.tenant_extension.get_allowed_config_fields(context, bank_id)
-                if allowed_fields is not None:  # None means "allow all"
-                    filtered = {k: v for k, v in filtered.items() if k in allowed_fields}
-                    logger.debug(
-                        f"Applied permission filter for bank {bank_id}: allowed={len(allowed_fields)} fields, "
-                        f"returned={len(filtered)} fields"
-                    )
-            except Exception as e:
-                logger.warning(f"Failed to load permissions for bank {bank_id}: {e}")
-
-        return filtered
-
-    async def _load_bank_config(self, bank_id: str) -> dict[str, Any]:
-        """
-        Load bank config overrides from banks.config JSONB column.
-
-        Args:
-            bank_id: Bank identifier
-
-        Returns:
-            Dict of config overrides (only configurable fields, normalized keys)
-        """
-        try:
-            async with self.pool.acquire() as conn:
-                row = await conn.fetchrow(
-                    f"""
-                    SELECT config FROM {fq_table("banks")} WHERE bank_id = $1
-                    """,
-                    bank_id,
-                )
-
-                if row and row["config"]:
-                    config_data = row["config"]
-
-                    # Handle case where JSONB is returned as JSON string
-                    if isinstance(config_data, str):
-                        config_data = json.loads(config_data)
-
-                    # Normalize keys (handle both env var format and Python field format)
-                    normalized = normalize_config_dict(config_data)
-
-                    # Only return overrides for configurable fields
-                    return {k: v for k, v in normalized.items() if k in self._configurable_fields}
-        except Exception as e:
-            logger.error(f"Failed to load bank config for {bank_id}: {e}")
-
-        return {}
-
-    async def update_bank_config(
-        self, bank_id: str, updates: dict[str, Any], context: RequestContext | None = None
-    ) -> None:
-        """
-        Update bank configuration overrides (with permission checking).
-
-        Args:
-            bank_id: Bank identifier
-            updates: Dict of config field names to new values.
-                    Keys can be in env var format (HINDSIGHT_API_LLM_PROVIDER)
-                    or Python field format (llm_provider).
-                    Only configurable fields are allowed.
-            context: Request context for permission checking
-
-        Raises:
-            ValueError: If attempting to override invalid/disallowed fields
-        """
-        # Normalize keys
-        normalized_updates = normalize_config_dict(updates)
-
-        # SECURITY: Reject credential fields explicitly
-        credential_attempts = set(normalized_updates.keys()) & self._credential_fields
-        if credential_attempts:
-            raise ValueError(
-                f"Cannot set credential fields via API: {sorted(credential_attempts)}. "
-                f"Credentials (API keys, base URLs) must be set at server level only."
-            )
-
-        # Validate all fields are configurable
-        invalid_fields = set(normalized_updates.keys()) - self._configurable_fields
-        if invalid_fields:
-            static_fields = HindsightConfig.get_static_fields()
-            invalid_static = invalid_fields & static_fields
-            if invalid_static:
-                raise ValueError(
-                    f"Cannot override static (server-level) fields: {sorted(invalid_static)}. "
-                    f"Only configurable fields can be overridden per-bank. "
-                    f"Configurable fields include: {sorted(list(self._configurable_fields)[:10])}... "
-                    f"(total: {len(self._configurable_fields)} fields)"
-                )
-            else:
-                raise ValueError(
-                    f"Unknown configuration fields: {sorted(invalid_fields)}. "
-                    f"Valid configurable fields: {sorted(list(self._configurable_fields)[:10])}..."
-                )
-
-        # PERMISSIONS: Check tenant/bank permissions
-        if self.tenant_extension and context:
-            try:
-                allowed_fields = await self.tenant_extension.get_allowed_config_fields(context, bank_id)
-                if allowed_fields is not None:  # None means "allow all"
-                    disallowed = set(normalized_updates.keys()) - allowed_fields
-                    if disallowed:
-                        raise ValueError(
-                            f"Not allowed to modify fields: {sorted(disallowed)}. "
-                            f"Your permissions allow: {sorted(list(allowed_fields)[:10])}..."
-                            if allowed_fields
-                            else "Not allowed to modify fields: {sorted(disallowed)}. "
-                            "Your permissions do not allow any config modifications."
-                        )
-            except ValueError:
-                raise  # Re-raise permission errors
-            except Exception as e:
-                logger.warning(f"Failed to check permissions for bank {bank_id}: {e}")
-                # Continue without permission check (fail open for backward compatibility)
-
-        # Validate retain_strategies: reject empty string keys
-        if "retain_strategies" in normalized_updates and normalized_updates["retain_strategies"]:
-            empty_keys = [k for k in normalized_updates["retain_strategies"] if not str(k).strip()]
-            if empty_keys:
-                raise ValueError(
-                    "Strategy names must not be empty strings. Remove entries with empty names before saving."
-                )
-
-        # Merge with existing config (JSONB || operator)
-        async with self.pool.acquire() as conn:
-            await conn.execute(
-                f"""
-                UPDATE {fq_table("banks")}
-                SET config = config || $1::jsonb,
-                    updated_at = now()
-                WHERE bank_id = $2
-                """,
-                json.dumps(normalized_updates),
-                bank_id,
-            )
-
-        logger.info(f"Updated bank config for {bank_id}: {list(normalized_updates.keys())}")
-
-    async def reset_bank_config(self, bank_id: str) -> None:
-        """
-        Reset bank configuration to defaults (remove all overrides).
-
-        Args:
-            bank_id: Bank identifier
-        """
-        async with self.pool.acquire() as conn:
-            await conn.execute(
-                f"""
-                UPDATE {fq_table("banks")}
-                SET config = '{{}}'::jsonb,
-                    updated_at = now()
-                WHERE bank_id = $1
-                """,
-                bank_id,
-            )
-
-        logger.info(f"Reset bank config for {bank_id} to defaults")
-
-
-def apply_strategy(config: HindsightConfig, strategy_name: str) -> HindsightConfig:
-    """
-    Apply a named retain strategy's overrides on top of a resolved config.
-
-    A strategy is a named set of hierarchical field overrides stored in
-    config.retain_strategies. Any field in _HIERARCHICAL_FIELDS can be
-    overridden, including retain_extraction_mode, retain_chunk_size,
-    entity_labels, entities_allow_free_form, etc.
-
-    Unknown strategy names log a warning and return config unchanged.
-    Unknown or non-hierarchical fields in the strategy are silently ignored.
-    """
-    strategies = config.retain_strategies or {}
-    if strategy_name not in strategies:
-        logger.warning(f"Unknown retain strategy '{strategy_name}', using resolved config as-is")
-        return config
-
-    overrides = strategies[strategy_name]
-    if not isinstance(overrides, dict):
-        logger.warning(f"Retain strategy '{strategy_name}' is not a dict, skipping")
-        return config
-
-    configurable = HindsightConfig.get_configurable_fields()
-    filtered = {k: v for k, v in overrides.items() if k in configurable}
-
-    if not filtered:
-        return config
-
-    logger.debug(f"Applying retain strategy '{strategy_name}': {list(filtered.keys())}")
-    return replace(config, **filtered)

hindsight-api-slim/hindsight_api/daemon.py

@@ -1,113 +0,0 @@
-"""
-Daemon mode support for Hindsight API.
-
-Provides idle timeout for running as a background daemon.
-"""
-
-import asyncio
-import logging
-import os
-import sys
-import time
-from pathlib import Path
-
-logger = logging.getLogger(__name__)
-
-# Default daemon configuration
-DEFAULT_DAEMON_PORT = 8888
-DEFAULT_IDLE_TIMEOUT = 0  # 0 = no auto-exit (hindsight-embed passes its own timeout)
-
-# Allow override via environment variable for profile-specific logs
-DAEMON_LOG_PATH = Path(os.getenv("HINDSIGHT_API_DAEMON_LOG", str(Path.home() / ".hindsight" / "daemon.log")))
-
-
-class IdleTimeoutMiddleware:
-    """ASGI middleware that tracks activity and exits after idle timeout."""
-
-    def __init__(self, app, idle_timeout: int = DEFAULT_IDLE_TIMEOUT):
-        self.app = app
-        self.idle_timeout = idle_timeout
-        self.last_activity = time.time()
-        self._checker_task = None
-
-    async def __call__(self, scope, receive, send):
-        # Update activity timestamp on each request
-        self.last_activity = time.time()
-        await self.app(scope, receive, send)
-
-    def start_idle_checker(self):
-        """Start the background task that checks for idle timeout."""
-        self._checker_task = asyncio.create_task(self._check_idle())
-
-    async def _check_idle(self):
-        """Background task that exits the process after idle timeout."""
-        # If idle_timeout is 0, don't auto-exit
-        if self.idle_timeout <= 0:
-            return
-
-        while True:
-            await asyncio.sleep(30)  # Check every 30 seconds
-            idle_time = time.time() - self.last_activity
-            if idle_time > self.idle_timeout:
-                logger.info(f"Idle timeout reached ({self.idle_timeout}s), shutting down daemon")
-                # Give a moment for any in-flight requests
-                await asyncio.sleep(1)
-                # Send SIGTERM to ourselves to trigger graceful shutdown
-                import signal
-
-                os.kill(os.getpid(), signal.SIGTERM)
-
-
-def daemonize():
-    """
-    Fork the current process into a background daemon.
-
-    Uses double-fork technique to properly detach from terminal.
-    """
-    # First fork - detach from parent
-    try:
-        pid = os.fork()
-        if pid > 0:
-            sys.exit(0)
-    except OSError as e:
-        sys.stderr.write(f"fork #1 failed: {e}\n")
-        sys.exit(1)
-
-    # Decouple from parent environment
-    os.chdir("/")
-    os.setsid()
-    os.umask(0)
-
-    # Second fork - prevent zombie
-    pid = os.fork()
-    if pid > 0:
-        sys.exit(0)
-
-    # Redirect standard file descriptors to log file
-    DAEMON_LOG_PATH.parent.mkdir(parents=True, exist_ok=True)
-
-    sys.stdout.flush()
-    sys.stderr.flush()
-
-    # Redirect stdin to /dev/null
-    with open("/dev/null", "r") as devnull:
-        os.dup2(devnull.fileno(), sys.stdin.fileno())
-
-    # Redirect stdout/stderr to log file
-    log_fd = open(DAEMON_LOG_PATH, "a")
-    os.dup2(log_fd.fileno(), sys.stdout.fileno())
-    os.dup2(log_fd.fileno(), sys.stderr.fileno())
-
-
-def check_daemon_running(port: int = DEFAULT_DAEMON_PORT) -> bool:
-    """Check if a daemon is running and responsive on the given port."""
-    import socket
-
-    try:
-        sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
-        sock.settimeout(1)
-        result = sock.connect_ex(("127.0.0.1", port))
-        sock.close()
-        return result == 0
-    except Exception:
-        return False

hindsight-api-slim/hindsight_api/engine/consolidation/prompts.py

@@ -1,83 +0,0 @@
-"""Prompts for the consolidation engine."""
-
-# Default mission when no bank-specific mission is set
-_DEFAULT_MISSION = "Track every detail: names, numbers, dates, places, and relationships. Prefer specifics over abstractions, never generalise."
-
-# Processing rules — always present regardless of mission
-_PROCESSING_RULES = """Processing rules (always apply):
-- REDUNDANT: same info worded differently → UPDATE the existing observation.
-- CONTRADICTION/UPDATE: capture both states with temporal markers ("used to X, now Y").
-- RESOLVE REFERENCES: when a new fact provides a concrete value resolving a vague placeholder in an existing observation (e.g. "home country", "hometown", "birthplace", "native language", "her ex", "that city"), UPDATE the observation to embed the resolved value explicitly. Example: new fact says "grandma in Sweden" + existing observation says "moved from her home country" → update to "home country is Sweden".
-- NEVER merge observations about different people or unrelated topics."""
-
-# Data section — format placeholders {facts_text} and {observations_text} are substituted at call time
-_BATCH_DATA_SECTION = """
-NEW FACTS:
-{facts_text}
-
-EXISTING OBSERVATIONS (JSON array, pooled from recalls across all facts above):
-{observations_text}
-
-Each observation includes:
-- id: unique identifier for updating
-- text: the observation content
-- proof_count: number of supporting memories
-- occurred_start/occurred_end: temporal range of source facts
-- source_memories: array of supporting facts with their text and dates
-
-Compare the facts against existing observations:
-- Same topic as an existing observation → UPDATE it (observation_id + source_fact_ids)
-- New topic with durable knowledge → CREATE a new observation (source_fact_ids)
-- Cross-reference facts within the batch: a later fact may resolve a vague reference in an earlier one
-- Purely ephemeral facts → omit them unless the MISSION above explicitly targets such data (e.g. timestamped events, session state, screen content)"""
-
-# Output format — JSON braces escaped as {{ }} so .format() leaves them literal
-_BATCH_OUTPUT_FORMAT = """
-Output a JSON object with three arrays.
-
-## EXAMPLE
-
-Input facts:
-[a1b2c3d4-e5f6-7890-abcd-ef1234567890] Alice mentioned she works long hours, often past midnight | Involving: Alice (occurred_start=2024-01-15, mentioned_at=2024-01-15)
-[b2c3d4e5-f6a7-8901-bcde-f12345678901] Alice said she's exhausted from the project deadlines | Involving: Alice (occurred_start=2024-01-20, mentioned_at=2024-01-20)
-
-Good observation text — clean prose, no metadata, each fact tracked distinctly:
-  "Alice works long hours, often past midnight."
-  "Alice feels exhausted from project deadlines."
-
-Bad observation text — NEVER do this (verbatim copy of fact text with metadata):
-  "Alice mentioned she works long hours, often past midnight | Involving: Alice (occurred_start=2024-01-15, mentioned_at=2024-01-15)"
-
-Observation text rules:
-- Write clean prose — NEVER copy raw fact lines or their metadata (temporal fields, "Involving:", "When:" labels, UUIDs).
-- Parenthesized metadata like (occurred_start=...) and pipe-separated labels like "| Involving: ..." are fact formatting — strip them entirely from observation text.
-- How many observations to create and how much to aggregate is driven by the MISSION above.
-
-{{"creates": [{{"text": "Alice works long hours, often past midnight.", "source_fact_ids": ["a1b2c3d4-e5f6-7890-abcd-ef1234567890"]}}, {{"text": "Alice feels exhausted from project deadlines.", "source_fact_ids": ["b2c3d4e5-f6a7-8901-bcde-f12345678901"]}}],
-  "updates": [{{"text": "Alice works at Acme Corp as a senior engineer", "observation_id": "c3d4e5f6-a7b8-9012-cdef-123456789012", "source_fact_ids": ["d4e5f6a7-b8c9-0123-defa-234567890123"]}}],
-  "deletes": [{{"observation_id": "e5f6a7b8-c9d0-1234-efab-345678901234"}}]}}
-
-Rules:
-- "source_fact_ids": copy the EXACT UUID strings shown in brackets [uuid] from NEW FACTS — never use integers or positions.
-- "observation_id": copy the EXACT "id" UUID string from EXISTING OBSERVATIONS.
-- One create/update may reference multiple facts when they jointly support the observation.
-- "deletes": only when an observation is directly superseded or contradicted by new facts.
-- Do NOT include "tags" — handled automatically.
-- Return {{"creates": [], "updates": [], "deletes": []}} if nothing durable is found."""
-
-
-def build_batch_consolidation_prompt(observations_mission: str | None = None) -> str:
-    """
-    Build the consolidation prompt for batch mode (multiple facts per LLM call).
-
-    The mission defines *what* to track (customisable per bank).
-    Processing rules and output format are always present regardless of mission.
-    """
-    mission = observations_mission or _DEFAULT_MISSION
-
-    return (
-        "You are a memory consolidation system. Synthesize facts into observations "
-        "and merge with existing observations when appropriate.\n\n"
-        f"## MISSION\n{mission}\n\n"
-        f"{_PROCESSING_RULES}" + _BATCH_DATA_SECTION + _BATCH_OUTPUT_FORMAT
-    )

hindsight-api-slim/hindsight_api/engine/jina_mlx_reranker.py

@@ -1,144 +0,0 @@
-"""
-MLX implementation of jina-reranker-v3 for Apple Silicon.
-
-This file is adapted from the official model repository:
-  https://huggingface.co/jinaai/jina-reranker-v3-mlx/blob/main/rerank.py
-
-License: CC BY-NC 4.0 (contact Jina AI for commercial usage)
-
-Changes from upstream:
-- Removed the __main__ example block
-- Type annotations added to public methods
-- top_n parameter added to rerank() (upstream only exposed it implicitly)
-"""
-
-import numpy as np
-
-
-class _MLPProjector:
-    def __init__(self):
-        import mlx.nn as nn
-
-        self.linear1 = nn.Linear(1024, 512, bias=False)
-        self.linear2 = nn.Linear(512, 512, bias=False)
-
-    def __call__(self, x):
-        import mlx.nn as nn
-
-        x = self.linear1(x)
-        x = nn.relu(x)
-        x = self.linear2(x)
-        return x
-
-
-def _load_projector(projector_path: str) -> _MLPProjector:
-    import mlx.core as mx
-    from safetensors import safe_open
-
-    projector = _MLPProjector()
-    with safe_open(projector_path, framework="numpy") as f:
-        projector.linear1.weight = mx.array(f.get_tensor("linear1.weight"))
-        projector.linear2.weight = mx.array(f.get_tensor("linear2.weight"))
-    return projector
-
-
-def _sanitize(text: str, special_tokens: dict[str, str]) -> str:
-    for token in special_tokens.values():
-        text = text.replace(token, "")
-    return text
-
-
-def _format_prompt(query: str, docs: list[str], special_tokens: dict[str, str]) -> str:
-    query = _sanitize(query, special_tokens)
-    docs = [_sanitize(d, special_tokens) for d in docs]
-
-    doc_token = special_tokens["doc_embed_token"]
-    query_token = special_tokens["query_embed_token"]
-
-    prefix = (
-        "<|im_start|>system\n"
-        "You are a search relevance expert who can determine a ranking of the passages based on how relevant they are to the query. "
-        "If the query is a question, how relevant a passage is depends on how well it answers the question. "
-        "If not, try to analyze the intent of the query and assess how well each passage satisfies the intent. "
-        "If an instruction is provided, you should follow the instruction when determining the ranking."
-        "<|im_end|>\n<|im_start|>user\n"
-    )
-    suffix = "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n"
-
-    body = (
-        f"I will provide you with {len(docs)} passages, each indicated by a numerical identifier. "
-        f"Rank the passages based on their relevance to query: {query}\n"
-    )
-    body += "\n".join(f'<passage id="{i}">\n{doc}{doc_token}\n</passage>' for i, doc in enumerate(docs))
-    body += f"\n<query>\n{query}{query_token}\n</query>"
-    return prefix + body + suffix
-
-
-class MLXReranker:
-    """
-    MLX-accelerated jina-reranker-v3 for Apple Silicon.
-
-    Loads the model from a local directory (use huggingface_hub.snapshot_download
-    to fetch jinaai/jina-reranker-v3-mlx if you don't have it already).
-    """
-
-    _SPECIAL_TOKENS = {
-        "query_embed_token": "<|rerank_token|>",
-        "doc_embed_token": "<|embed_token|>",
-    }
-    _DOC_TOKEN_ID = 151670
-    _QUERY_TOKEN_ID = 151671
-
-    def __init__(self, model_path: str, projector_path: str):
-        from mlx_lm import load
-
-        self.model, self.tokenizer = load(model_path)
-        self.model.eval()
-        self.projector = _load_projector(projector_path)
-
-    def rerank(self, query: str, documents: list[str], top_n: int | None = None) -> list[dict]:
-        """
-        Rank documents by relevance to a query.
-
-        Returns a list of dicts with keys: document, relevance_score, index.
-        Sorted by descending relevance_score.
-        """
-        import mlx.core as mx
-
-        prompt = _format_prompt(query, documents, self._SPECIAL_TOKENS)
-        input_ids = self.tokenizer.encode(prompt)
-        hidden_states = self.model.model([input_ids])[0]  # [seq_len, hidden_size]
-
-        input_ids_np = np.array(input_ids)
-        query_positions = np.where(input_ids_np == self._QUERY_TOKEN_ID)[0]
-        doc_positions = np.where(input_ids_np == self._DOC_TOKEN_ID)[0]
-
-        if len(query_positions) == 0:
-            raise ValueError("Query embed token not found in prompt")
-        if len(doc_positions) == 0:
-            raise ValueError("Document embed tokens not found in prompt")
-
-        query_hidden = mx.expand_dims(hidden_states[int(query_positions[0])], axis=0)
-        doc_hidden = mx.stack([hidden_states[int(p)] for p in doc_positions])
-
-        query_emb = self.projector(query_hidden)  # [1, 512]
-        doc_emb = self.projector(doc_hidden)  # [num_docs, 512]
-
-        query_exp = mx.broadcast_to(mx.expand_dims(query_emb, 0), (1, len(documents), 512))
-        doc_exp = mx.expand_dims(doc_emb, 0)
-
-        scores = mx.sum(doc_exp * query_exp, axis=-1) / (
-            mx.sqrt(mx.sum(doc_exp * doc_exp, axis=-1)) * mx.sqrt(mx.sum(query_exp * query_exp, axis=-1))
-        )  # [1, num_docs]
-        scores_np = np.array(scores[0])
-
-        order = np.argsort(scores_np)[::-1]
-        n = min(top_n, len(documents)) if top_n is not None else len(documents)
-        return [
-            {
-                "document": documents[order[i]],
-                "relevance_score": float(scores_np[order[i]]),
-                "index": int(order[i]),
-            }
-            for i in range(n)
-        ]

hindsight-api-slim/hindsight_api/engine/llm_interface.py

@@ -1,207 +0,0 @@
-"""
-Abstract interface for LLM providers.
-
-This module defines the interface that all LLM providers must implement,
-enabling support for multiple LLM backends (OpenAI, Anthropic, Gemini, Codex, etc.)
-"""
-
-from abc import ABC, abstractmethod
-from typing import Any
-
-from .response_models import LLMToolCallResult, TokenUsage
-
-
-class LLMInterface(ABC):
-    """
-    Abstract interface for LLM providers.
-
-    All LLM provider implementations must inherit from this class and implement
-    the required methods.
-    """
-
-    def __init__(
-        self,
-        provider: str,
-        api_key: str,
-        base_url: str,
-        model: str,
-        reasoning_effort: str = "low",
-        **kwargs: Any,
-    ):
-        """
-        Initialize LLM provider.
-
-        Args:
-            provider: Provider name (e.g., "openai", "codex", "anthropic", "gemini").
-            api_key: API key or authentication token.
-            base_url: Base URL for the API.
-            model: Model name.
-            reasoning_effort: Reasoning effort level for supported providers.
-            **kwargs: Additional provider-specific parameters.
-        """
-        self.provider = provider.lower()
-        self.api_key = api_key
-        self.base_url = base_url
-        self.model = model
-        self.reasoning_effort = reasoning_effort
-
-    @abstractmethod
-    async def verify_connection(self) -> None:
-        """
-        Verify that the LLM provider is configured correctly by making a simple test call.
-
-        Raises:
-            RuntimeError: If the connection test fails.
-        """
-        pass
-
-    @abstractmethod
-    async def call(
-        self,
-        messages: list[dict[str, str]],
-        response_format: Any | None = None,
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "memory",
-        max_retries: int = 10,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 60.0,
-        skip_validation: bool = False,
-        strict_schema: bool = False,
-        return_usage: bool = False,
-    ) -> Any:
-        """
-        Make an LLM API call with retry logic.
-
-        Args:
-            messages: List of message dicts with 'role' and 'content'.
-            response_format: Optional Pydantic model for structured output.
-            max_completion_tokens: Maximum tokens in response.
-            temperature: Sampling temperature (0.0-2.0).
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            skip_validation: Return raw JSON without Pydantic validation.
-            strict_schema: Use strict JSON schema enforcement (OpenAI only).
-            return_usage: If True, return tuple (result, TokenUsage) instead of just result.
-
-        Returns:
-            If return_usage=False: Parsed response if response_format is provided, otherwise text content.
-            If return_usage=True: Tuple of (result, TokenUsage) with token counts.
-
-        Raises:
-            OutputTooLongError: If output exceeds token limits.
-            Exception: Re-raises API errors after retries exhausted.
-        """
-        pass
-
-    @abstractmethod
-    async def call_with_tools(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "tools",
-        max_retries: int = 5,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 30.0,
-        tool_choice: str | dict[str, Any] = "auto",
-    ) -> LLMToolCallResult:
-        """
-        Make an LLM API call with tool/function calling support.
-
-        Args:
-            messages: List of message dicts. Can include tool results with role='tool'.
-            tools: List of tool definitions in OpenAI format.
-            max_completion_tokens: Maximum tokens in response.
-            temperature: Sampling temperature (0.0-2.0).
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            tool_choice: How to choose tools - "auto", "none", "required", or specific function.
-
-        Returns:
-            LLMToolCallResult with content and/or tool_calls.
-        """
-        pass
-
-    async def supports_batch_api(self) -> bool:
-        """
-        Check if this provider supports batch API operations.
-
-        Returns:
-            True if provider supports submit_batch/get_batch_status/retrieve_batch_results
-        """
-        return False
-
-    async def submit_batch(
-        self,
-        requests: list[dict[str, Any]],
-        endpoint: str = "/v1/chat/completions",
-        completion_window: str = "24h",
-    ) -> dict[str, Any]:
-        """
-        Submit a batch of requests to the provider's batch API.
-
-        Args:
-            requests: List of request dicts in JSONL format (custom_id, method, url, body)
-            endpoint: API endpoint for the batch (e.g., "/v1/chat/completions")
-            completion_window: Completion window (e.g., "24h")
-
-        Returns:
-            Dict with batch metadata: {"batch_id": str, "status": str, ...}
-
-        Raises:
-            NotImplementedError: If provider doesn't support batch API
-        """
-        raise NotImplementedError(f"Batch API not supported for provider: {self.provider}")
-
-    async def get_batch_status(self, batch_id: str) -> dict[str, Any]:
-        """
-        Get the status of a batch job.
-
-        Args:
-            batch_id: Batch identifier returned from submit_batch
-
-        Returns:
-            Dict with status info: {"batch_id": str, "status": str, "completed_at": str, ...}
-
-        Raises:
-            NotImplementedError: If provider doesn't support batch API
-        """
-        raise NotImplementedError(f"Batch API not supported for provider: {self.provider}")
-
-    async def retrieve_batch_results(self, batch_id: str) -> list[dict[str, Any]]:
-        """
-        Retrieve completed batch results.
-
-        Args:
-            batch_id: Batch identifier returned from submit_batch
-
-        Returns:
-            List of result dicts (one per request, matched by custom_id)
-
-        Raises:
-            NotImplementedError: If provider doesn't support batch API
-        """
-        raise NotImplementedError(f"Batch API not supported for provider: {self.provider}")
-
-    @abstractmethod
-    async def cleanup(self) -> None:
-        """Clean up resources (close connections, etc.)."""
-        pass
-
-
-class OutputTooLongError(Exception):
-    """
-    Bridge exception raised when LLM output exceeds token limits.
-
-    This wraps provider-specific errors (e.g., OpenAI's LengthFinishReasonError)
-    to allow callers to handle output length issues without depending on
-    provider-specific implementations.
-    """
-
-    pass

hindsight-api-slim/hindsight_api/engine/llm_wrapper.py

@@ -1,782 +0,0 @@
-"""
-LLM wrapper for unified configuration across providers.
-"""
-
-import asyncio
-import json
-import logging
-import os
-import re
-import time
-import uuid
-from pathlib import Path
-from typing import Any
-
-import httpx
-from openai import APIConnectionError, APIStatusError, AsyncOpenAI, LengthFinishReasonError
-
-# Vertex AI imports (conditional - for LLMProvider to pass credentials to GeminiLLM)
-try:
-    import google.auth
-    from google.oauth2 import service_account
-
-    VERTEXAI_AVAILABLE = True
-except ImportError:
-    VERTEXAI_AVAILABLE = False
-
-from ..config import (
-    DEFAULT_LLM_MAX_CONCURRENT,
-    DEFAULT_LLM_TIMEOUT,
-    ENV_LLM_GROQ_SERVICE_TIER,
-    ENV_LLM_MAX_CONCURRENT,
-    ENV_LLM_TIMEOUT,
-)
-from ..metrics import get_metrics_collector
-from .response_models import TokenUsage
-
-# Seed applied to every Groq request for deterministic behavior.
-DEFAULT_LLM_SEED = 4242
-
-logger = logging.getLogger(__name__)
-
-# Disable httpx logging
-logging.getLogger("httpx").setLevel(logging.WARNING)
-
-# Global semaphore to limit concurrent LLM requests across all instances
-# Set HINDSIGHT_API_LLM_MAX_CONCURRENT=1 for local LLMs (LM Studio, Ollama)
-_llm_max_concurrent = int(os.getenv(ENV_LLM_MAX_CONCURRENT, str(DEFAULT_LLM_MAX_CONCURRENT)))
-_global_llm_semaphore = asyncio.Semaphore(_llm_max_concurrent)
-
-
-def sanitize_llm_output(text: str | None) -> str | None:
-    """
-    Sanitize text by removing characters that break downstream systems.
-
-    Removes:
-    - ASCII control characters (0x00-0x08, 0x0B-0x0C, 0x0E-0x1F, 0x7F): break
-      json.loads and PostgreSQL UTF-8 encoding; tab (0x09), newline (0x0A), and
-      carriage return (0x0D) are preserved as they are valid in text and JSON.
-    - Unicode surrogates (U+D800-U+DFFF): Invalid in UTF-8, break LLM APIs
-
-    Surrogate characters are used in UTF-16 encoding but cannot be encoded
-    in UTF-8. They can appear in Python strings from improperly decoded data
-    (e.g., from JavaScript or broken files). Control characters commonly appear
-    in LLM output embedded inside JSON string values.
-    """
-    if text is None:
-        return None
-    if not text:
-        return text
-    return re.sub(r"[\x00-\x08\x0b\x0c\x0e-\x1f\x7f\ud800-\udfff]", "", text)
-
-
-class OutputTooLongError(Exception):
-    """
-    Bridge exception raised when LLM output exceeds token limits.
-
-    This wraps provider-specific errors (e.g., OpenAI's LengthFinishReasonError)
-    to allow callers to handle output length issues without depending on
-    provider-specific implementations.
-    """
-
-    pass
-
-
-def parse_llm_json(raw: str) -> Any:
-    """
-    Robustly parse JSON returned by an LLM.
-
-    Handles common LLM output quirks:
-    1. Markdown code fences (```json ... ```) — strip them before parsing.
-    2. Embedded control characters (\\x00-\\x1f, \\x7f) — replace with space
-       and retry if the initial parse fails.
-
-    Args:
-        raw: Raw text returned by the LLM.
-
-    Returns:
-        Parsed Python object (dict, list, etc.).
-
-    Raises:
-        json.JSONDecodeError: If the text cannot be parsed even after cleanup.
-    """
-    text = raw.strip()
-
-    # Strip markdown code fences (some models wrap JSON in ```json ... ```)
-    if text.startswith("```"):
-        text = text.split("\n", 1)[1] if "\n" in text else text[3:]
-        if text.endswith("```"):
-            text = text[:-3]
-        text = text.strip()
-
-    try:
-        return json.loads(text)
-    except json.JSONDecodeError:
-        # Some models (e.g. Gemini) embed raw control characters inside JSON
-        # string values. Replacing them with a space usually produces valid JSON.
-        cleaned = re.sub(r"[\x00-\x1f\x7f]", " ", text)
-        return json.loads(cleaned)
-
-
-_PROVIDERS_WITHOUT_API_KEY = frozenset(
-    {
-        "ollama",
-        "lmstudio",
-        "openai-codex",
-        "claude-code",
-        "mock",
-        "vertexai",
-    }
-)
-
-
-def requires_api_key(provider: str) -> bool:
-    """Return True if the given provider requires an API key to operate."""
-    return provider.lower() not in _PROVIDERS_WITHOUT_API_KEY
-
-
-def create_llm_provider(
-    provider: str,
-    api_key: str,
-    base_url: str,
-    model: str,
-    reasoning_effort: str,
-    groq_service_tier: str | None = None,
-    openai_service_tier: str | None = None,
-    vertexai_project_id: str | None = None,
-    vertexai_region: str | None = None,
-    vertexai_credentials: Any = None,
-    gemini_safety_settings: list | None = None,
-) -> Any:  # Returns LLMInterface
-    """
-    Factory function to create the appropriate LLM provider implementation.
-
-    Args:
-        provider: Provider name ("openai", "groq", "ollama", "gemini", "anthropic", etc.).
-        api_key: API key (may be None for local providers or OAuth providers).
-        base_url: Base URL for the API.
-        model: Model name.
-        reasoning_effort: Reasoning effort level for supported providers.
-        groq_service_tier: Groq service tier (for Groq provider) - "on_demand", "flex", or "auto".
-        openai_service_tier: OpenAI service tier (for OpenAI provider) - None (default) or "flex" (50% cheaper).
-        vertexai_project_id: Vertex AI project ID (for VertexAI provider).
-        vertexai_region: Vertex AI region (for VertexAI provider).
-        vertexai_credentials: Vertex AI credentials object (for VertexAI provider).
-
-    Returns:
-        LLMInterface implementation for the specified provider.
-    """
-    from .llm_interface import LLMInterface
-    from .providers import (
-        AnthropicLLM,
-        ClaudeCodeLLM,
-        CodexLLM,
-        GeminiLLM,
-        MockLLM,
-        OpenAICompatibleLLM,
-    )
-
-    provider_lower = provider.lower()
-
-    if provider_lower == "openai-codex":
-        return CodexLLM(
-            provider=provider,
-            api_key=api_key,
-            base_url=base_url,
-            model=model,
-            reasoning_effort=reasoning_effort,
-        )
-
-    elif provider_lower == "claude-code":
-        return ClaudeCodeLLM(
-            provider=provider,
-            api_key=api_key,
-            base_url=base_url,
-            model=model,
-            reasoning_effort=reasoning_effort,
-        )
-
-    elif provider_lower == "mock":
-        return MockLLM(
-            provider=provider,
-            api_key=api_key,
-            base_url=base_url,
-            model=model,
-            reasoning_effort=reasoning_effort,
-        )
-
-    elif provider_lower in ("gemini", "vertexai"):
-        return GeminiLLM(
-            provider=provider,
-            api_key=api_key,
-            base_url=base_url,
-            model=model,
-            reasoning_effort=reasoning_effort,
-            vertexai_project_id=vertexai_project_id,
-            vertexai_region=vertexai_region,
-            vertexai_credentials=vertexai_credentials,
-            gemini_safety_settings=gemini_safety_settings,
-        )
-
-    elif provider_lower == "anthropic":
-        return AnthropicLLM(
-            provider=provider,
-            api_key=api_key,
-            base_url=base_url,
-            model=model,
-            reasoning_effort=reasoning_effort,
-        )
-
-    elif provider_lower in ("openai", "groq", "ollama", "lmstudio", "minimax"):
-        return OpenAICompatibleLLM(
-            provider=provider,
-            api_key=api_key,
-            base_url=base_url,
-            model=model,
-            reasoning_effort=reasoning_effort,
-            groq_service_tier=groq_service_tier,
-            openai_service_tier=openai_service_tier,
-        )
-
-    else:
-        raise ValueError(f"Unknown provider: {provider}")
-
-
-class LLMProvider:
-    """
-    Unified LLM provider.
-
-    Supports OpenAI, Groq, Ollama (OpenAI-compatible), and Gemini.
-    """
-
-    def __init__(
-        self,
-        provider: str,
-        api_key: str,
-        base_url: str,
-        model: str,
-        reasoning_effort: str = "low",
-        groq_service_tier: str | None = None,
-        openai_service_tier: str | None = None,
-        gemini_safety_settings: list | None = None,
-    ):
-        """
-        Initialize LLM provider.
-
-        Args:
-            provider: Provider name ("openai", "groq", "ollama", "gemini", "anthropic", "lmstudio").
-            api_key: API key.
-            base_url: Base URL for the API.
-            model: Model name.
-            reasoning_effort: Reasoning effort level for supported providers.
-            groq_service_tier: Groq service tier ("on_demand", "flex", "auto") - from config.
-            openai_service_tier: OpenAI service tier (None or "flex") - from config.
-            gemini_safety_settings: Safety settings for Gemini/VertexAI providers.
-        """
-        self.provider = provider.lower()
-        self.api_key = api_key
-        self.base_url = base_url
-        self.model = model
-        self.reasoning_effort = reasoning_effort
-        # Service tiers from hierarchical config (not env vars)
-        self.groq_service_tier = groq_service_tier
-        self.openai_service_tier = openai_service_tier
-        # Gemini safety settings (instance default; can be overridden per-request via context var)
-        self.gemini_safety_settings = gemini_safety_settings
-
-        # Validate provider
-        valid_providers = [
-            "openai",
-            "groq",
-            "ollama",
-            "gemini",
-            "anthropic",
-            "lmstudio",
-            "vertexai",
-            "openai-codex",
-            "claude-code",
-            "mock",
-            "minimax",
-        ]
-        if self.provider not in valid_providers:
-            raise ValueError(f"Invalid LLM provider: {self.provider}. Must be one of: {', '.join(valid_providers)}")
-
-        # Set default base URLs
-        if not self.base_url:
-            if self.provider == "groq":
-                self.base_url = "https://api.groq.com/openai/v1"
-            elif self.provider == "ollama":
-                self.base_url = "http://localhost:11434/v1"
-            elif self.provider == "lmstudio":
-                self.base_url = "http://localhost:1234/v1"
-            elif self.provider == "minimax":
-                self.base_url = "https://api.minimax.io/v1"
-
-        # Prepare Vertex AI config (if applicable)
-        vertexai_project_id = None
-        vertexai_region = None
-        vertexai_credentials = None
-
-        if self.provider == "vertexai":
-            from ..config import get_config
-
-            config = get_config()
-
-            vertexai_project_id = config.llm_vertexai_project_id
-            if not vertexai_project_id:
-                raise ValueError(
-                    "HINDSIGHT_API_LLM_VERTEXAI_PROJECT_ID is required for Vertex AI provider. "
-                    "Set it to your GCP project ID."
-                )
-
-            vertexai_region = config.llm_vertexai_region or "us-central1"
-            service_account_key = config.llm_vertexai_service_account_key
-
-            # Load explicit service account credentials if provided
-            if service_account_key:
-                if not VERTEXAI_AVAILABLE:
-                    raise ValueError(
-                        "Vertex AI service account auth requires 'google-auth' package. "
-                        "Install with: pip install google-auth"
-                    )
-                vertexai_credentials = service_account.Credentials.from_service_account_file(
-                    service_account_key,
-                    scopes=["https://www.googleapis.com/auth/cloud-platform"],
-                )
-                logger.info(f"Vertex AI: Using service account key: {service_account_key}")
-
-            # Strip google/ prefix from model name — native SDK uses bare names
-            if self.model.startswith("google/"):
-                self.model = self.model[len("google/") :]
-
-            logger.info(
-                f"Vertex AI: project={vertexai_project_id}, region={vertexai_region}, "
-                f"model={self.model}, auth={'service_account' if service_account_key else 'ADC'}"
-            )
-
-        # For Gemini/VertexAI providers: read safety settings from global config if not explicitly provided
-        # Use _get_raw_config() to bypass StaticConfigProxy (which blocks configurable fields),
-        # since LLMProvider initialization legitimately needs the server-level default.
-        if self.provider in ("gemini", "vertexai") and self.gemini_safety_settings is None:
-            from ..config import _get_raw_config
-
-            try:
-                raw_config = _get_raw_config()
-                self.gemini_safety_settings = raw_config.llm_gemini_safety_settings
-            except Exception:
-                pass  # Config may not be initialized in test environments
-
-        # Create provider implementation using factory
-        self._provider_impl = create_llm_provider(
-            provider=self.provider,
-            api_key=self.api_key,
-            base_url=self.base_url,
-            model=self.model,
-            reasoning_effort=self.reasoning_effort,
-            groq_service_tier=self.groq_service_tier,
-            openai_service_tier=self.openai_service_tier,
-            vertexai_project_id=vertexai_project_id,
-            vertexai_region=vertexai_region,
-            vertexai_credentials=vertexai_credentials,
-            gemini_safety_settings=self.gemini_safety_settings,
-        )
-
-        # Backward compatibility: Keep mock provider properties
-        self._mock_calls: list[dict] = []
-        self._mock_response: Any = None
-
-    @property
-    def _client(self) -> Any:
-        """
-        Get the OpenAI client for OpenAI-compatible providers.
-
-        This property provides backward compatibility for code that directly accesses
-        the _client attribute (e.g., benchmarks, memory_engine).
-
-        Returns:
-            AsyncOpenAI client instance for OpenAI-compatible providers, or None for other providers.
-        """
-        from .providers.openai_compatible_llm import OpenAICompatibleLLM
-
-        if isinstance(self._provider_impl, OpenAICompatibleLLM):
-            return self._provider_impl._client
-        return None
-
-    @property
-    def _gemini_client(self) -> Any:
-        """
-        Get the Gemini client for Gemini/VertexAI providers.
-
-        This property provides backward compatibility for code that directly accesses
-        the _gemini_client attribute.
-
-        Returns:
-            genai.Client instance for Gemini/VertexAI providers, or None for other providers.
-        """
-        from .providers.gemini_llm import GeminiLLM
-
-        if isinstance(self._provider_impl, GeminiLLM):
-            return self._provider_impl._client
-        return None
-
-    async def verify_connection(self) -> None:
-        """
-        Verify that the LLM provider is configured correctly by making a simple test call.
-
-        Raises:
-            RuntimeError: If the connection test fails.
-        """
-        await self._provider_impl.verify_connection()
-
-    async def call(
-        self,
-        messages: list[dict[str, str]],
-        response_format: Any | None = None,
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "memory",
-        max_retries: int = 10,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 60.0,
-        skip_validation: bool = False,
-        strict_schema: bool = False,
-        return_usage: bool = False,
-    ) -> Any:
-        """
-        Make an LLM API call with retry logic.
-
-        Args:
-            messages: List of message dicts with 'role' and 'content'.
-            response_format: Optional Pydantic model for structured output.
-            max_completion_tokens: Maximum tokens in response.
-            temperature: Sampling temperature (0.0-2.0).
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            skip_validation: Return raw JSON without Pydantic validation.
-            strict_schema: Use strict JSON schema enforcement (OpenAI only). Guarantees all required fields.
-            return_usage: If True, return tuple (result, TokenUsage) instead of just result.
-
-        Returns:
-            If return_usage=False: Parsed response if response_format is provided, otherwise text content.
-            If return_usage=True: Tuple of (result, TokenUsage) with token counts from the LLM call.
-
-        Raises:
-            OutputTooLongError: If output exceeds token limits.
-            Exception: Re-raises API errors after retries exhausted.
-        """
-        async with _global_llm_semaphore:
-            # Delegate to provider implementation
-            result = await self._provider_impl.call(
-                messages=messages,
-                response_format=response_format,
-                max_completion_tokens=max_completion_tokens,
-                temperature=temperature,
-                scope=scope,
-                max_retries=max_retries,
-                initial_backoff=initial_backoff,
-                max_backoff=max_backoff,
-                skip_validation=skip_validation,
-                strict_schema=strict_schema,
-                return_usage=return_usage,
-            )
-
-            # Backward compatibility: Update mock call tracking for mock provider
-            # This allows existing tests using LLMProvider._mock_calls to continue working
-            if self.provider == "mock":
-                from .providers.mock_llm import MockLLM
-
-                if isinstance(self._provider_impl, MockLLM):
-                    # Sync the mock calls from provider implementation to wrapper
-                    self._mock_calls = self._provider_impl.get_mock_calls()
-
-            return result
-
-    async def call_with_tools(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "tools",
-        max_retries: int = 5,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 30.0,
-        tool_choice: str | dict[str, Any] = "auto",
-    ) -> "LLMToolCallResult":
-        """
-        Make an LLM API call with tool/function calling support.
-
-        Args:
-            messages: List of message dicts. Can include tool results with role='tool'.
-            tools: List of tool definitions in OpenAI format.
-            max_completion_tokens: Maximum tokens in response.
-            temperature: Sampling temperature (0.0-2.0).
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            tool_choice: How to choose tools - "auto", "none", "required", or {"type": "function", "function": {"name": "..."}}
-
-        Returns:
-            LLMToolCallResult with content and/or tool_calls.
-        """
-        async with _global_llm_semaphore:
-            # Delegate to provider implementation
-            result = await self._provider_impl.call_with_tools(
-                messages=messages,
-                tools=tools,
-                max_completion_tokens=max_completion_tokens,
-                temperature=temperature,
-                scope=scope,
-                max_retries=max_retries,
-                initial_backoff=initial_backoff,
-                max_backoff=max_backoff,
-                tool_choice=tool_choice,
-            )
-
-            # Backward compatibility: Update mock call tracking for mock provider
-            # This allows existing tests using LLMProvider._mock_calls to continue working
-            if self.provider == "mock":
-                from .providers.mock_llm import MockLLM
-
-                if isinstance(self._provider_impl, MockLLM):
-                    # Sync the mock calls from provider implementation to wrapper
-                    self._mock_calls = self._provider_impl.get_mock_calls()
-
-            return result
-
-    def set_response_callback(self, fn: Any) -> None:
-        """Set a callback invoked on each call() instead of the fixed mock response."""
-        if self.provider == "mock":
-            from .providers.mock_llm import MockLLM
-
-            if isinstance(self._provider_impl, MockLLM):
-                self._provider_impl.set_response_callback(fn)
-
-    def set_mock_response(self, response: Any) -> None:
-        """Set the response to return from mock calls."""
-        # Backward compatibility: Store in both wrapper and provider implementation
-        self._mock_response = response
-        if self.provider == "mock":
-            from .providers.mock_llm import MockLLM
-
-            if isinstance(self._provider_impl, MockLLM):
-                self._provider_impl.set_mock_response(response)
-
-    def get_mock_calls(self) -> list[dict]:
-        """Get the list of recorded mock calls."""
-        # Backward compatibility: Read from provider implementation if mock provider
-        if self.provider == "mock":
-            from .providers.mock_llm import MockLLM
-
-            if isinstance(self._provider_impl, MockLLM):
-                return self._provider_impl.get_mock_calls()
-        return self._mock_calls
-
-    def clear_mock_calls(self) -> None:
-        """Clear the recorded mock calls."""
-        # Backward compatibility: Clear in both wrapper and provider implementation
-        self._mock_calls = []
-        if self.provider == "mock":
-            from .providers.mock_llm import MockLLM
-
-            if isinstance(self._provider_impl, MockLLM):
-                self._provider_impl.clear_mock_calls()
-
-    def _load_codex_auth(self) -> tuple[str, str]:
-        """
-        Load OAuth credentials from ~/.codex/auth.json.
-
-        Returns:
-            Tuple of (access_token, account_id).
-
-        Raises:
-            FileNotFoundError: If auth file doesn't exist.
-            ValueError: If auth file is invalid.
-        """
-        auth_file = Path.home() / ".codex" / "auth.json"
-
-        if not auth_file.exists():
-            raise FileNotFoundError(
-                f"Codex auth file not found: {auth_file}\nRun 'codex auth login' to authenticate with ChatGPT Plus/Pro."
-            )
-
-        with open(auth_file) as f:
-            data = json.load(f)
-
-        # Validate auth structure
-        auth_mode = data.get("auth_mode")
-        if auth_mode != "chatgpt":
-            raise ValueError(f"Expected auth_mode='chatgpt', got: {auth_mode}")
-
-        tokens = data.get("tokens", {})
-        access_token = tokens.get("access_token")
-        account_id = tokens.get("account_id")
-
-        if not access_token:
-            raise ValueError("No access_token found in Codex auth file. Run 'codex auth login' again.")
-
-        return access_token, account_id
-
-    def _verify_claude_code_available(self) -> None:
-        """
-        Verify that Claude Agent SDK can be imported and is properly configured.
-
-        Raises:
-            ImportError: If Claude Agent SDK is not installed.
-            RuntimeError: If Claude Code is not authenticated.
-        """
-        try:
-            # Import Claude Agent SDK
-            # Reduce Claude Agent SDK logging verbosity
-            import logging as sdk_logging
-
-            from claude_agent_sdk import query  # noqa: F401  # type: ignore[unresolved-import]
-
-            sdk_logging.getLogger("claude_agent_sdk").setLevel(sdk_logging.WARNING)
-            sdk_logging.getLogger("claude_agent_sdk._internal").setLevel(sdk_logging.WARNING)
-
-            logger.debug("Claude Agent SDK imported successfully")
-        except ImportError as e:
-            raise ImportError(
-                "Claude Agent SDK not installed. Run: uv add claude-agent-sdk or pip install claude-agent-sdk"
-            ) from e
-
-        # SDK will automatically check for authentication when first used
-        # No need to verify here - let it fail gracefully on first call with helpful error
-
-    def with_config(self, config: Any) -> "ConfiguredLLMProvider":
-        """
-        Return a configured wrapper for a specific bank operation.
-
-        The wrapper applies per-bank overrides (e.g. Gemini safety settings)
-        to every ``call()`` / ``call_with_tools()`` invocation without
-        changing the underlying provider or its long-lived client connection.
-
-        Args:
-            config: Resolved ``HindsightConfig`` for the current bank/request.
-
-        Returns:
-            A ``ConfiguredLLMProvider`` that delegates to this provider with
-            the supplied config applied.
-        """
-        return ConfiguredLLMProvider(self, config.llm_gemini_safety_settings)
-
-    async def cleanup(self) -> None:
-        """Clean up resources."""
-        pass
-
-    @classmethod
-    def for_memory(cls) -> "LLMProvider":
-        """Create provider for memory operations from environment variables."""
-        provider = os.getenv("HINDSIGHT_API_LLM_PROVIDER", "groq")
-        api_key = os.getenv("HINDSIGHT_API_LLM_API_KEY", "")
-
-        # API key not needed for openai-codex (uses OAuth), claude-code (uses Keychain OAuth),
-        # ollama (local), or vertexai (uses GCP service account credentials)
-        if not api_key and provider not in ("openai-codex", "claude-code", "ollama", "vertexai"):
-            raise ValueError(
-                "HINDSIGHT_API_LLM_API_KEY environment variable is required (unless using openai-codex or claude-code)"
-            )
-
-        base_url = os.getenv("HINDSIGHT_API_LLM_BASE_URL", "")
-        model = os.getenv("HINDSIGHT_API_LLM_MODEL", "openai/gpt-oss-120b")
-
-        return cls(provider=provider, api_key=api_key, base_url=base_url, model=model, reasoning_effort="low")
-
-    @classmethod
-    def for_answer_generation(cls) -> "LLMProvider":
-        """Create provider for answer generation. Falls back to memory config if not set."""
-        provider = os.getenv("HINDSIGHT_API_ANSWER_LLM_PROVIDER", os.getenv("HINDSIGHT_API_LLM_PROVIDER", "groq"))
-        api_key = os.getenv("HINDSIGHT_API_ANSWER_LLM_API_KEY", os.getenv("HINDSIGHT_API_LLM_API_KEY", ""))
-
-        # API key not needed for openai-codex (uses OAuth), claude-code (uses Keychain OAuth),
-        # ollama (local), or vertexai (uses GCP service account credentials)
-        if not api_key and provider not in ("openai-codex", "claude-code", "ollama", "vertexai"):
-            raise ValueError(
-                "HINDSIGHT_API_LLM_API_KEY or HINDSIGHT_API_ANSWER_LLM_API_KEY environment variable is required "
-                "(unless using openai-codex or claude-code)"
-            )
-
-        base_url = os.getenv("HINDSIGHT_API_ANSWER_LLM_BASE_URL", os.getenv("HINDSIGHT_API_LLM_BASE_URL", ""))
-        model = os.getenv("HINDSIGHT_API_ANSWER_LLM_MODEL", os.getenv("HINDSIGHT_API_LLM_MODEL", "openai/gpt-oss-120b"))
-
-        return cls(provider=provider, api_key=api_key, base_url=base_url, model=model, reasoning_effort="high")
-
-    @classmethod
-    def for_judge(cls) -> "LLMProvider":
-        """Create provider for judge/evaluator operations. Falls back to memory config if not set."""
-        provider = os.getenv("HINDSIGHT_API_JUDGE_LLM_PROVIDER", os.getenv("HINDSIGHT_API_LLM_PROVIDER", "groq"))
-        api_key = os.getenv("HINDSIGHT_API_JUDGE_LLM_API_KEY", os.getenv("HINDSIGHT_API_LLM_API_KEY", ""))
-
-        # API key not needed for openai-codex (uses OAuth), claude-code (uses Keychain OAuth),
-        # ollama (local), or vertexai (uses GCP service account credentials)
-        if not api_key and provider not in ("openai-codex", "claude-code", "ollama", "vertexai"):
-            raise ValueError(
-                "HINDSIGHT_API_LLM_API_KEY or HINDSIGHT_API_JUDGE_LLM_API_KEY environment variable is required "
-                "(unless using openai-codex or claude-code)"
-            )
-
-        base_url = os.getenv("HINDSIGHT_API_JUDGE_LLM_BASE_URL", os.getenv("HINDSIGHT_API_LLM_BASE_URL", ""))
-        model = os.getenv("HINDSIGHT_API_JUDGE_LLM_MODEL", os.getenv("HINDSIGHT_API_LLM_MODEL", "openai/gpt-oss-120b"))
-
-        return cls(provider=provider, api_key=api_key, base_url=base_url, model=model, reasoning_effort="high")
-
-
-class ConfiguredLLMProvider:
-    """
-    Thin wrapper around LLMProvider that applies bank-specific config to every call.
-
-    Obtained via ``LLMProvider.with_config(resolved_config)``.  The wrapper
-    sets any provider-specific overrides (currently Gemini safety settings)
-    immediately before each call using a ContextVar token, then resets it
-    afterwards — so nesting is safe and the configuration cannot leak across
-    operations.
-
-    All attribute access falls through to the underlying provider so callers
-    that read ``llm.provider``, ``llm.model``, etc. continue to work without
-    any changes.
-    """
-
-    def __init__(self, provider: "LLMProvider", gemini_safety_settings: list | None) -> None:
-        # Use object.__setattr__ to avoid triggering __getattr__
-        object.__setattr__(self, "_provider", provider)
-        object.__setattr__(self, "_gemini_safety_settings", gemini_safety_settings)
-
-    # ── attribute passthrough ──────────────────────────────────────────────────
-
-    def __getattr__(self, name: str) -> Any:
-        return getattr(object.__getattribute__(self, "_provider"), name)
-
-    # ── overridden call methods ────────────────────────────────────────────────
-
-    async def call(self, messages: list[dict[str, Any]], **kwargs: Any) -> Any:
-        from .providers.gemini_llm import _safety_settings_ctx
-
-        token = _safety_settings_ctx.set(object.__getattribute__(self, "_gemini_safety_settings"))
-        try:
-            return await object.__getattribute__(self, "_provider").call(messages=messages, **kwargs)
-        finally:
-            _safety_settings_ctx.reset(token)
-
-    async def call_with_tools(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        **kwargs: Any,
-    ) -> "LLMToolCallResult":
-        from .providers.gemini_llm import _safety_settings_ctx
-
-        token = _safety_settings_ctx.set(object.__getattribute__(self, "_gemini_safety_settings"))
-        try:
-            return await object.__getattribute__(self, "_provider").call_with_tools(
-                messages=messages, tools=tools, **kwargs
-            )
-        finally:
-            _safety_settings_ctx.reset(token)
-
-
-# Backwards compatibility alias
-LLMConfig = LLMProvider

hindsight-api-slim/hindsight_api/engine/operation_metadata.py

@@ -1,69 +0,0 @@
-"""
-Typed metadata models for async operations.
-
-These dataclasses define the structure of result_metadata for different operation types.
-The metadata is exposed in the API for debugging purposes and may change without notice.
-"""
-
-from dataclasses import asdict, dataclass
-from typing import Any
-
-
-@dataclass
-class BatchRetainParentMetadata:
-    """Metadata for parent batch_retain operations (when split into sub-batches)."""
-
-    items_count: int
-    total_tokens: int
-    num_sub_batches: int
-    is_parent: bool = True
-
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dict for JSON serialization."""
-        return asdict(self)
-
-
-@dataclass
-class BatchRetainChildMetadata:
-    """Metadata for child batch_retain operations (individual sub-batches)."""
-
-    items_count: int
-    parent_operation_id: str
-    sub_batch_index: int
-    total_sub_batches: int
-
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dict for JSON serialization."""
-        return asdict(self)
-
-
-@dataclass
-class RetainMetadata:
-    """Metadata for regular retain operations (non-batched, deprecated async path)."""
-
-    items_count: int
-
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dict for JSON serialization."""
-        return asdict(self)
-
-
-@dataclass
-class ConsolidationMetadata:
-    """Metadata for consolidation operations."""
-
-    # Currently empty, but structure for future fields
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dict for JSON serialization."""
-        return asdict(self)
-
-
-@dataclass
-class RefreshMentalModelMetadata:
-    """Metadata for mental model refresh operations."""
-
-    mental_model_id: str
-
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dict for JSON serialization."""
-        return asdict(self)

hindsight-api-slim/hindsight_api/engine/parsers/__init__.py

@@ -1,128 +0,0 @@
-"""File parser implementations."""
-
-import logging
-from dataclasses import dataclass
-
-from .base import FileParser, UnsupportedFileTypeError
-from .iris import IrisParser
-from .markitdown import MarkitdownParser
-
-__all__ = [
-    "FileParser",
-    "UnsupportedFileTypeError",
-    "IrisParser",
-    "MarkitdownParser",
-    "FileParserRegistry",
-    "ConvertResult",
-]
-
-
-@dataclass
-class ConvertResult:
-    """Result of a successful file conversion."""
-
-    content: str
-    parser_name: str
-
-
-logger = logging.getLogger(__name__)
-
-
-class FileParserRegistry:
-    """Registry for file parsers with auto-detection."""
-
-    def __init__(self):
-        """Initialize empty parser registry."""
-        self._parsers: dict[str, FileParser] = {}
-
-    def register(self, parser: FileParser):
-        """
-        Register a parser.
-
-        Args:
-            parser: FileParser instance
-        """
-        self._parsers[parser.name()] = parser
-
-    def get_parser(
-        self,
-        name: str | None,
-        filename: str,
-        content_type: str | None = None,
-    ) -> FileParser:
-        """
-        Get parser by name or auto-detect.
-
-        Args:
-            name: Parser name (e.g., "markitdown") or None for auto-detect
-            filename: File name for auto-detection
-            content_type: MIME type (optional)
-
-        Returns:
-            FileParser instance
-
-        Raises:
-            ValueError: If no suitable parser found
-        """
-        if name:
-            # Explicit parser requested — return it directly, let the parser
-            # raise UnsupportedFileTypeError from convert() if needed
-            if name not in self._parsers:
-                raise ValueError(f"Parser '{name}' not found. Available: {list(self._parsers.keys())}")
-            return self._parsers[name]
-
-        # Auto-detect parser
-        for parser in self._parsers.values():
-            if parser.supports(filename, content_type):
-                return parser
-
-        raise ValueError(f"No parser found for {filename}. Available parsers: {list(self._parsers.keys())}")
-
-    async def convert_with_fallback(
-        self,
-        parsers: list[str],
-        file_data: bytes,
-        filename: str,
-        content_type: str | None = None,
-    ) -> ConvertResult:
-        """
-        Try each parser in order, falling back on failure or empty content.
-
-        Moves to the next parser if the current one raises UnsupportedFileTypeError
-        or returns empty content. Any other exception (RuntimeError, network error,
-        etc.) also triggers a fallback so the chain is exhausted before failing.
-
-        Args:
-            parsers: Ordered list of parser names to try
-            file_data: Raw file bytes
-            filename: Original filename
-            content_type: MIME type (optional)
-
-        Returns:
-            ConvertResult with the parsed content and the name of the parser that succeeded
-
-        Raises:
-            ValueError: If a parser name is not registered
-            RuntimeError: If all parsers fail or return empty content
-        """
-        last_error: Exception | None = None
-        for name in parsers:
-            parser = self.get_parser(name, filename, content_type)
-            try:
-                content = await parser.convert(file_data, filename)
-                if content and content.strip():
-                    return ConvertResult(content=content, parser_name=name)
-                logger.warning(f"Parser '{name}' returned empty content for '{filename}', trying next")
-                last_error = RuntimeError(f"Parser '{name}' returned no content for '{filename}'")
-            except UnsupportedFileTypeError as e:
-                logger.warning(f"Parser '{name}' does not support '{filename}', trying next: {e}")
-                last_error = e
-            except Exception as e:
-                logger.warning(f"Parser '{name}' failed for '{filename}', trying next: {e}")
-                last_error = e
-
-        raise last_error or RuntimeError(f"No parsers available for '{filename}'")
-
-    def list_parsers(self) -> list[str]:
-        """Get list of registered parser names."""
-        return list(self._parsers.keys())

hindsight-api-slim/hindsight_api/engine/parsers/base.py

@@ -1,58 +0,0 @@
-"""Abstract base class for file parsers."""
-
-from abc import ABC, abstractmethod
-
-
-class UnsupportedFileTypeError(Exception):
-    """Raised by a parser when it does not support the given file type."""
-
-    pass
-
-
-class FileParser(ABC):
-    """Abstract base for file to markdown parsers."""
-
-    @abstractmethod
-    async def convert(self, file_data: bytes, filename: str) -> str:
-        """
-        Parse file to markdown.
-
-        Args:
-            file_data: Raw file bytes
-            filename: Original filename (used for format detection)
-
-        Returns:
-            Markdown content as string
-
-        Raises:
-            UnsupportedFileTypeError: If the file type is not supported by this parser
-            RuntimeError: If parsing fails for another reason
-        """
-        pass
-
-    def supports(self, filename: str, content_type: str | None = None) -> bool:
-        """
-        Check if parser supports this file type.
-
-        Override this for local/static extension-based filtering.
-        Parsers that delegate to a remote service should leave this as True
-        and raise UnsupportedFileTypeError from convert() instead.
-
-        Args:
-            filename: File name (used for extension check)
-            content_type: MIME type (optional)
-
-        Returns:
-            True if this parser can handle the file (default: True)
-        """
-        return True
-
-    @abstractmethod
-    def name(self) -> str:
-        """
-        Get parser name.
-
-        Returns:
-            Parser name (e.g., "markitdown")
-        """
-        pass

hindsight-api-slim/hindsight_api/engine/parsers/iris.py

@@ -1,138 +0,0 @@
-"""Iris parser implementation using the Vectorize Iris HTTP API."""
-
-import asyncio
-import logging
-import mimetypes
-import time
-
-import httpx
-
-from .base import FileParser, UnsupportedFileTypeError
-
-logger = logging.getLogger(__name__)
-
-_IRIS_BASE_URL = "https://api.vectorize.io/v1"
-_DEFAULT_POLL_INTERVAL = 2.0  # seconds
-_DEFAULT_TIMEOUT = 300.0  # seconds
-
-
-class IrisParser(FileParser):
-    """
-    Iris file parser using the Vectorize Iris cloud extraction service.
-
-    Uploads files to the Vectorize Iris API, starts an extraction job,
-    and polls until the text is ready. The API determines which file types
-    are supported — UnsupportedFileTypeError is raised if the file is rejected.
-
-    Authentication:
-        Requires HINDSIGHT_API_FILE_PARSER_IRIS_TOKEN and
-        HINDSIGHT_API_FILE_PARSER_IRIS_ORG_ID environment variables,
-        or pass them explicitly via the constructor.
-    """
-
-    def __init__(
-        self,
-        token: str,
-        org_id: str,
-        poll_interval: float = _DEFAULT_POLL_INTERVAL,
-        timeout: float = _DEFAULT_TIMEOUT,
-    ):
-        """
-        Initialize iris parser.
-
-        Args:
-            token: Vectorize API token
-            org_id: Vectorize organization ID
-            poll_interval: Seconds between status poll requests (default: 2)
-            timeout: Maximum seconds to wait for extraction (default: 300)
-        """
-        self._token = token
-        self._org_id = org_id
-        self._poll_interval = poll_interval
-        self._timeout = timeout
-        self._auth_headers = {"Authorization": f"Bearer {token}"}
-
-    async def convert(self, file_data: bytes, filename: str) -> str:
-        """
-        Parse file to text using the Vectorize Iris API.
-
-        Raises:
-            UnsupportedFileTypeError: If the Iris API rejects the file type (4xx)
-            RuntimeError: If extraction fails for another reason
-        """
-        content_type = mimetypes.guess_type(filename)[0] or "application/octet-stream"
-
-        async with httpx.AsyncClient(timeout=httpx.Timeout(30.0, read=120.0)) as client:
-            # Step 1: Request a presigned upload URL
-            init_resp = await client.post(
-                f"{_IRIS_BASE_URL}/org/{self._org_id}/files",
-                headers=self._auth_headers,
-                json={"name": filename, "contentType": content_type},
-            )
-            _raise_for_status(init_resp, filename, "file upload init")
-            init_data = init_resp.json()
-            file_id: str = init_data["fileId"]
-            upload_url: str = init_data["uploadUrl"]
-
-            # Step 2: Upload the file bytes to the presigned URL (no auth header)
-            # Ensure file_data is plain bytes (GCS storage may return obstore.Bytes)
-            upload_resp = await client.put(
-                upload_url,
-                content=bytes(file_data),
-                headers={"Content-Type": content_type},
-            )
-            _raise_for_status(upload_resp, filename, "file upload")
-
-            # Step 3: Start extraction
-            extract_resp = await client.post(
-                f"{_IRIS_BASE_URL}/org/{self._org_id}/extraction",
-                headers=self._auth_headers,
-                json={"fileId": file_id},
-            )
-            _raise_for_status(extract_resp, filename, "start extraction")
-            extraction_id: str = extract_resp.json()["extractionId"]
-
-            # Step 4: Poll until ready or timeout
-            deadline = time.monotonic() + self._timeout
-            while True:
-                status_resp = await client.get(
-                    f"{_IRIS_BASE_URL}/org/{self._org_id}/extraction/{extraction_id}",
-                    headers=self._auth_headers,
-                )
-                _raise_for_status(status_resp, filename, "poll extraction status")
-                status_data = status_resp.json()
-
-                if status_data.get("ready"):
-                    data = status_data.get("data", {})
-                    if not data.get("success"):
-                        error = data.get("error", "unknown error")
-                        raise RuntimeError(f"Iris extraction failed for '{filename}': {error}")
-                    text = data.get("text")
-                    if not text:
-                        raise RuntimeError(f"No content extracted from '{filename}'")
-                    return text
-
-                if time.monotonic() >= deadline:
-                    raise RuntimeError(f"Iris extraction timed out after {self._timeout}s for '{filename}'")
-
-                await asyncio.sleep(self._poll_interval)
-
-    def name(self) -> str:
-        """Get parser name."""
-        return "iris"
-
-
-def _raise_for_status(response: httpx.Response, filename: str, step: str) -> None:
-    """
-    Raise an appropriate error including the response body on HTTP errors.
-
-    Raises UnsupportedFileTypeError for 4xx responses (file rejected by the API),
-    RuntimeError for other HTTP errors.
-    """
-    if not response.is_error:
-        return
-    body = response.text or "<empty>"
-    msg = f"Iris API error during {step} for '{filename}': {response.status_code} {response.reason_phrase} — {body}"
-    if response.is_client_error:
-        raise UnsupportedFileTypeError(msg)
-    raise RuntimeError(msg)

hindsight-api-slim/hindsight_api/engine/parsers/markitdown.py

@@ -1,109 +0,0 @@
-"""Markitdown parser implementation."""
-
-import asyncio
-import logging
-import tempfile
-from pathlib import Path
-
-from .base import FileParser
-
-logger = logging.getLogger(__name__)
-
-
-class MarkitdownParser(FileParser):
-    """
-    Markitdown file parser.
-
-    Uses Microsoft's markitdown library to convert various file formats
-    to markdown including PDF, Office docs, images (via OCR), audio, HTML.
-
-    Supported formats:
-    - PDF (.pdf)
-    - Word (.docx, .doc)
-    - PowerPoint (.pptx, .ppt)
-    - Excel (.xlsx, .xls)
-    - Images (.jpg, .jpeg, .png) - with OCR
-    - HTML (.html, .htm)
-    - Text (.txt, .md)
-    - Audio (.mp3, .wav) - with transcription
-    """
-
-    def __init__(self):
-        """Initialize markitdown parser."""
-        # Lazy import to avoid requiring markitdown for all users
-        try:
-            from markitdown import MarkItDown
-
-            self._markitdown = MarkItDown()
-        except ImportError as e:
-            raise ImportError(
-                "markitdown package is required for file parsing. Install with: pip install markitdown"
-            ) from e
-
-    async def convert(self, file_data: bytes, filename: str) -> str:
-        """Parse file to markdown using markitdown."""
-        # markitdown is synchronous, so we run it in executor to avoid blocking
-        loop = asyncio.get_event_loop()
-        return await loop.run_in_executor(None, self._convert_sync, file_data, filename)
-
-    def _convert_sync(self, file_data: bytes, filename: str) -> str:
-        """Synchronous parsing (runs in thread pool)."""
-        # Write to temp file (markitdown requires file path)
-        with tempfile.NamedTemporaryFile(suffix=Path(filename).suffix, delete=False) as tmp:
-            tmp.write(file_data)
-            tmp_path = tmp.name
-
-        try:
-            # Parse using markitdown
-            result = self._markitdown.convert(tmp_path)
-
-            if not result or not result.text_content:
-                raise RuntimeError(f"No content extracted from '{filename}'")
-
-            return result.text_content
-
-        except Exception as e:
-            logger.error(f"Markitdown parsing failed for {filename}: {e}")
-            raise RuntimeError(f"Failed to parse '{filename}': {e}") from e
-
-        finally:
-            # Clean up temp file
-            try:
-                Path(tmp_path).unlink()
-            except Exception:
-                pass
-
-    def supports(self, filename: str, content_type: str | None = None) -> bool:
-        """Check if markitdown supports this file type."""
-        # Supported extensions (from markitdown docs)
-        supported_extensions = {
-            # Documents
-            ".pdf",
-            ".docx",
-            ".doc",
-            ".pptx",
-            ".ppt",
-            ".xlsx",
-            ".xls",
-            # Images (with OCR)
-            ".jpg",
-            ".jpeg",
-            ".png",
-            # Web
-            ".html",
-            ".htm",
-            # Text
-            ".txt",
-            ".md",
-            ".csv",
-            # Audio (with transcription)
-            ".mp3",
-            ".wav",
-        }
-
-        ext = Path(filename).suffix.lower()
-        return ext in supported_extensions
-
-    def name(self) -> str:
-        """Get parser name."""
-        return "markitdown"

hindsight-api-slim/hindsight_api/engine/providers/__init__.py

@@ -1,14 +0,0 @@
-"""
-LLM provider implementations.
-
-This package contains concrete implementations of the LLMInterface for various providers.
-"""
-
-from .anthropic_llm import AnthropicLLM
-from .claude_code_llm import ClaudeCodeLLM
-from .codex_llm import CodexLLM
-from .gemini_llm import GeminiLLM
-from .mock_llm import MockLLM
-from .openai_compatible_llm import OpenAICompatibleLLM
-
-__all__ = ["AnthropicLLM", "ClaudeCodeLLM", "CodexLLM", "GeminiLLM", "MockLLM", "OpenAICompatibleLLM"]

hindsight-api-slim/hindsight_api/engine/providers/anthropic_llm.py

@@ -1,477 +0,0 @@
-"""
-Anthropic LLM provider using the Anthropic Python SDK.
-
-This provider enables using Claude models from Anthropic with support for:
-- Structured JSON output
-- Tool/function calling with proper format conversion
-- Extended thinking mode
-- Retry logic with exponential backoff
-"""
-
-import asyncio
-import json
-import logging
-import time
-from typing import Any
-
-from hindsight_api.engine.llm_interface import LLMInterface, OutputTooLongError
-from hindsight_api.engine.response_models import LLMToolCall, LLMToolCallResult, TokenUsage
-from hindsight_api.metrics import get_metrics_collector
-
-logger = logging.getLogger(__name__)
-
-
-class AnthropicLLM(LLMInterface):
-    """
-    LLM provider using Anthropic's Claude models.
-
-    Supports structured output, tool calling, and extended thinking mode.
-    Handles format conversion between OpenAI-style messages and Anthropic's format.
-    """
-
-    def __init__(
-        self,
-        provider: str,
-        api_key: str,
-        base_url: str,
-        model: str,
-        reasoning_effort: str = "low",
-        timeout: float = 300.0,
-        **kwargs: Any,
-    ):
-        """
-        Initialize Anthropic LLM provider.
-
-        Args:
-            provider: Provider name (should be "anthropic").
-            api_key: Anthropic API key.
-            base_url: Base URL for the API (optional, uses Anthropic default if empty).
-            model: Model name (e.g., "claude-sonnet-4-20250514").
-            reasoning_effort: Reasoning effort level (not used by Anthropic).
-            timeout: Request timeout in seconds.
-            **kwargs: Additional provider-specific parameters.
-        """
-        super().__init__(provider, api_key, base_url, model, reasoning_effort, **kwargs)
-
-        if not self.api_key:
-            raise ValueError("API key is required for Anthropic provider")
-
-        # Import and initialize Anthropic client
-        try:
-            from anthropic import AsyncAnthropic
-
-            client_kwargs: dict[str, Any] = {"api_key": self.api_key}
-            if self.base_url:
-                client_kwargs["base_url"] = self.base_url
-            if timeout:
-                client_kwargs["timeout"] = timeout
-
-            self._client = AsyncAnthropic(**client_kwargs)
-            logger.info(f"Anthropic client initialized for model: {self.model}")
-        except ImportError as e:
-            raise RuntimeError("Anthropic SDK not installed. Run: uv add anthropic or pip install anthropic") from e
-
-    async def verify_connection(self) -> None:
-        """
-        Verify that the Anthropic provider is configured correctly by making a simple test call.
-
-        Raises:
-            RuntimeError: If the connection test fails.
-        """
-        try:
-            test_messages = [{"role": "user", "content": "test"}]
-            await self.call(
-                messages=test_messages,
-                max_completion_tokens=10,
-                temperature=0.0,
-                scope="verification",
-                max_retries=0,
-            )
-            logger.info("Anthropic connection verified successfully")
-        except Exception as e:
-            logger.error(f"Anthropic connection verification failed: {e}")
-            raise RuntimeError(f"Failed to verify Anthropic connection: {e}") from e
-
-    async def call(
-        self,
-        messages: list[dict[str, str]],
-        response_format: Any | None = None,
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "memory",
-        max_retries: int = 10,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 60.0,
-        skip_validation: bool = False,
-        strict_schema: bool = False,
-        return_usage: bool = False,
-    ) -> Any:
-        """
-        Make an LLM API call with retry logic.
-
-        Args:
-            messages: List of message dicts with 'role' and 'content'.
-            response_format: Optional Pydantic model for structured output.
-            max_completion_tokens: Maximum tokens in response.
-            temperature: Sampling temperature (0.0-2.0).
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            skip_validation: Return raw JSON without Pydantic validation.
-            strict_schema: Use strict JSON schema enforcement (not supported by Anthropic).
-            return_usage: If True, return tuple (result, TokenUsage) instead of just result.
-
-        Returns:
-            If return_usage=False: Parsed response if response_format is provided, otherwise text content.
-            If return_usage=True: Tuple of (result, TokenUsage) with token counts.
-
-        Raises:
-            OutputTooLongError: If output exceeds token limits.
-            Exception: Re-raises API errors after retries exhausted.
-        """
-        from anthropic import APIConnectionError, APIStatusError, RateLimitError
-
-        start_time = time.time()
-
-        # Convert OpenAI-style messages to Anthropic format
-        system_prompt = None
-        anthropic_messages = []
-
-        for msg in messages:
-            role = msg.get("role", "user")
-            content = msg.get("content", "")
-
-            if role == "system":
-                if system_prompt:
-                    system_prompt += "\n\n" + content
-                else:
-                    system_prompt = content
-            else:
-                anthropic_messages.append({"role": role, "content": content})
-
-        # Add JSON schema instruction if response_format is provided
-        if response_format is not None and hasattr(response_format, "model_json_schema"):
-            schema = response_format.model_json_schema()
-            schema_msg = f"\n\nYou must respond with valid JSON matching this schema:\n{json.dumps(schema, indent=2)}"
-            if system_prompt:
-                system_prompt += schema_msg
-            else:
-                system_prompt = schema_msg
-
-        # Prepare parameters
-        call_params: dict[str, Any] = {
-            "model": self.model,
-            "messages": anthropic_messages,
-            "max_tokens": max_completion_tokens if max_completion_tokens is not None else 4096,
-        }
-
-        if system_prompt:
-            call_params["system"] = system_prompt
-
-        if temperature is not None:
-            call_params["temperature"] = temperature
-
-        last_exception = None
-
-        for attempt in range(max_retries + 1):
-            try:
-                response = await self._client.messages.create(**call_params)
-
-                # Anthropic response content is a list of blocks
-                content = ""
-                for block in response.content:
-                    if block.type == "text":
-                        content += block.text
-
-                if response_format is not None:
-                    # Models may wrap JSON in markdown code blocks
-                    clean_content = content
-                    if "```json" in content:
-                        clean_content = content.split("```json")[1].split("```")[0].strip()
-                    elif "```" in content:
-                        clean_content = content.split("```")[1].split("```")[0].strip()
-
-                    try:
-                        json_data = json.loads(clean_content)
-                    except json.JSONDecodeError:
-                        # Fallback to parsing raw content if markdown stripping failed
-                        json_data = json.loads(content)
-
-                    if skip_validation:
-                        result = json_data
-                    else:
-                        result = response_format.model_validate(json_data)
-                else:
-                    result = content
-
-                # Record metrics and log slow calls
-                duration = time.time() - start_time
-                input_tokens = response.usage.input_tokens or 0 if response.usage else 0
-                output_tokens = response.usage.output_tokens or 0 if response.usage else 0
-                total_tokens = input_tokens + output_tokens
-
-                # Record LLM metrics
-                metrics = get_metrics_collector()
-                metrics.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    duration=duration,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    success=True,
-                )
-
-                # Record trace span
-                from hindsight_api.tracing import _serialize_for_span, get_span_recorder
-
-                finish_reason = response.stop_reason if hasattr(response, "stop_reason") else None
-                span_recorder = get_span_recorder()
-                span_recorder.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    messages=messages,
-                    response_content=_serialize_for_span(result),
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    duration=duration,
-                    finish_reason=finish_reason,
-                    error=None,
-                )
-
-                # Log slow calls
-                if duration > 10.0:
-                    logger.info(
-                        f"slow llm call: scope={scope}, model={self.provider}/{self.model}, "
-                        f"input_tokens={input_tokens}, output_tokens={output_tokens}, "
-                        f"time={duration:.3f}s"
-                    )
-
-                if return_usage:
-                    token_usage = TokenUsage(
-                        input_tokens=input_tokens,
-                        output_tokens=output_tokens,
-                        total_tokens=total_tokens,
-                    )
-                    return result, token_usage
-                return result
-
-            except json.JSONDecodeError as e:
-                last_exception = e
-                if attempt < max_retries:
-                    logger.warning("Anthropic returned invalid JSON, retrying...")
-                    backoff = min(initial_backoff * (2**attempt), max_backoff)
-                    await asyncio.sleep(backoff)
-                    continue
-                else:
-                    logger.error(f"Anthropic returned invalid JSON after {max_retries + 1} attempts")
-                    raise
-
-            except (APIConnectionError, RateLimitError, APIStatusError) as e:
-                # Fast fail on 401/403
-                if isinstance(e, APIStatusError) and e.status_code in (401, 403):
-                    logger.error(f"Anthropic auth error (HTTP {e.status_code}), not retrying: {str(e)}")
-                    raise
-
-                last_exception = e
-                if attempt < max_retries:
-                    # Check if it's a rate limit or server error
-                    should_retry = isinstance(e, (APIConnectionError, RateLimitError)) or (
-                        isinstance(e, APIStatusError) and e.status_code >= 500
-                    )
-
-                    if should_retry:
-                        backoff = min(initial_backoff * (2**attempt), max_backoff)
-                        jitter = backoff * 0.2 * (2 * (time.time() % 1) - 1)
-                        await asyncio.sleep(backoff + jitter)
-                        continue
-
-                logger.error(f"Anthropic API error after {max_retries + 1} attempts: {str(e)}")
-                raise
-
-            except Exception as e:
-                logger.error(f"Unexpected error during Anthropic call: {type(e).__name__}: {str(e)}")
-                raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("Anthropic call failed after all retries")
-
-    async def call_with_tools(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "tools",
-        max_retries: int = 5,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 30.0,
-        tool_choice: str | dict[str, Any] = "auto",
-    ) -> LLMToolCallResult:
-        """
-        Make an LLM API call with tool/function calling support.
-
-        Args:
-            messages: List of message dicts. Can include tool results with role='tool'.
-            tools: List of tool definitions in OpenAI format.
-            max_completion_tokens: Maximum tokens in response.
-            temperature: Sampling temperature (0.0-2.0).
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            tool_choice: How to choose tools - "auto", "none", "required", or specific function.
-
-        Returns:
-            LLMToolCallResult with content and/or tool_calls.
-        """
-        from anthropic import APIConnectionError, APIStatusError
-
-        start_time = time.time()
-
-        # Convert OpenAI tool format to Anthropic format
-        anthropic_tools = []
-        for tool in tools:
-            func = tool.get("function", {})
-            anthropic_tools.append(
-                {
-                    "name": func.get("name", ""),
-                    "description": func.get("description", ""),
-                    "input_schema": func.get("parameters", {"type": "object", "properties": {}}),
-                }
-            )
-
-        # Convert messages - handle tool results
-        system_prompt = None
-        anthropic_messages = []
-        for msg in messages:
-            role = msg.get("role", "user")
-            content = msg.get("content", "")
-
-            if role == "system":
-                system_prompt = (system_prompt + "\n\n" + content) if system_prompt else content
-            elif role == "tool":
-                # Anthropic uses tool_result blocks
-                anthropic_messages.append(
-                    {
-                        "role": "user",
-                        "content": [
-                            {"type": "tool_result", "tool_use_id": msg.get("tool_call_id", ""), "content": content}
-                        ],
-                    }
-                )
-            elif role == "assistant" and msg.get("tool_calls"):
-                # Convert assistant tool calls
-                tool_use_blocks = []
-                for tc in msg["tool_calls"]:
-                    tool_use_blocks.append(
-                        {
-                            "type": "tool_use",
-                            "id": tc.get("id", ""),
-                            "name": tc.get("function", {}).get("name", ""),
-                            "input": json.loads(tc.get("function", {}).get("arguments", "{}")),
-                        }
-                    )
-                anthropic_messages.append({"role": "assistant", "content": tool_use_blocks})
-            else:
-                anthropic_messages.append({"role": role, "content": content})
-
-        call_params: dict[str, Any] = {
-            "model": self.model,
-            "messages": anthropic_messages,
-            "tools": anthropic_tools,
-            "max_tokens": max_completion_tokens or 4096,
-        }
-        if system_prompt:
-            call_params["system"] = system_prompt
-
-        if temperature is not None:
-            call_params["temperature"] = temperature
-
-        last_exception = None
-        for attempt in range(max_retries + 1):
-            try:
-                response = await self._client.messages.create(**call_params)
-
-                # Extract content and tool calls
-                content_parts = []
-                tool_calls: list[LLMToolCall] = []
-
-                for block in response.content:
-                    if block.type == "text":
-                        content_parts.append(block.text)
-                    elif block.type == "tool_use":
-                        tool_calls.append(LLMToolCall(id=block.id, name=block.name, arguments=block.input or {}))
-
-                content = "".join(content_parts) if content_parts else None
-                finish_reason = "tool_calls" if tool_calls else "stop"
-
-                # Extract token usage
-                input_tokens = response.usage.input_tokens or 0
-                output_tokens = response.usage.output_tokens or 0
-
-                # Record metrics
-                metrics = get_metrics_collector()
-                duration = time.time() - start_time
-                metrics.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    duration=duration,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    success=True,
-                )
-
-                # Record OpenTelemetry span
-                from hindsight_api.tracing import get_span_recorder
-
-                span_recorder = get_span_recorder()
-                # Convert LLMToolCall objects to dicts for span recording
-                tool_calls_dict = (
-                    [{"id": tc.id, "name": tc.name, "arguments": tc.arguments} for tc in tool_calls]
-                    if tool_calls
-                    else None
-                )
-                span_recorder.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    messages=messages,
-                    response_content=content,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    duration=duration,
-                    finish_reason=finish_reason,
-                    error=None,
-                    tool_calls=tool_calls_dict,
-                )
-
-                return LLMToolCallResult(
-                    content=content,
-                    tool_calls=tool_calls,
-                    finish_reason=finish_reason,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                )
-
-            except (APIConnectionError, APIStatusError) as e:
-                if isinstance(e, APIStatusError) and e.status_code in (401, 403):
-                    raise
-                last_exception = e
-                if attempt < max_retries:
-                    await asyncio.sleep(min(initial_backoff * (2**attempt), max_backoff))
-                    continue
-                raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("Anthropic tool call failed")
-
-    async def cleanup(self) -> None:
-        """Clean up resources (close Anthropic client connections)."""
-        if hasattr(self, "_client") and self._client:
-            await self._client.close()

hindsight-api-slim/hindsight_api/engine/providers/claude_code_llm.py

@@ -1,518 +0,0 @@
-"""
-Claude Code LLM provider using Claude Agent SDK.
-
-This provider enables using Claude Pro/Max subscriptions for API calls
-via the Claude CLI authentication. It uses the Claude Agent SDK which
-automatically handles authentication via `claude auth login` credentials.
-"""
-
-import asyncio
-import json
-import logging
-import time
-from typing import Any
-
-from hindsight_api.engine.llm_interface import LLMInterface, OutputTooLongError
-from hindsight_api.engine.response_models import LLMToolCall, LLMToolCallResult, TokenUsage
-from hindsight_api.metrics import get_metrics_collector
-
-logger = logging.getLogger(__name__)
-
-
-class ClaudeCodeLLM(LLMInterface):
-    """
-    LLM provider using Claude Code authentication.
-
-    Authenticates using Claude Pro/Max credentials via `claude auth login`
-    and makes API calls through the Claude Agent SDK.
-    """
-
-    def __init__(
-        self,
-        provider: str,
-        api_key: str,  # Will be ignored, uses CLI auth
-        base_url: str,
-        model: str,
-        reasoning_effort: str = "low",
-        **kwargs: Any,
-    ):
-        """Initialize Claude Code LLM provider."""
-        super().__init__(provider, api_key, base_url, model, reasoning_effort, **kwargs)
-
-        # Verify Claude Agent SDK is available
-        try:
-            self._verify_claude_code_available()
-            logger.info("Claude Code: Using Claude Agent SDK (authentication via claude auth login)")
-        except Exception as e:
-            raise RuntimeError(
-                f"Failed to initialize Claude Code provider: {e}\n\n"
-                "To set up Claude Code authentication:\n"
-                "1. Install Claude Code CLI: npm install -g @anthropics/claude-code\n"
-                "2. Login with your Pro/Max plan: claude auth login\n"
-                "3. Verify authentication: claude --version\n\n"
-                "Or use a different provider (anthropic, openai, gemini) with API keys."
-            ) from e
-
-        # Metrics collector is imported at module level
-
-    def _verify_claude_code_available(self) -> None:
-        """
-        Verify that Claude Agent SDK can be imported and is properly configured.
-
-        Raises:
-            ImportError: If Claude Agent SDK is not installed.
-            RuntimeError: If Claude Code is not authenticated.
-        """
-        try:
-            # Import Claude Agent SDK
-            # Reduce Claude Agent SDK logging verbosity
-            import logging as sdk_logging
-
-            from claude_agent_sdk import query  # noqa: F401  # type: ignore[unresolved-import]
-
-            sdk_logging.getLogger("claude_agent_sdk").setLevel(sdk_logging.WARNING)
-            sdk_logging.getLogger("claude_agent_sdk._internal").setLevel(sdk_logging.WARNING)
-
-            logger.debug("Claude Agent SDK imported successfully")
-        except ImportError as e:
-            raise ImportError(
-                "Claude Agent SDK not installed. Run: uv add claude-agent-sdk or pip install claude-agent-sdk"
-            ) from e
-
-        # SDK will automatically check for authentication when first used
-        # No need to verify here - let it fail gracefully on first call with helpful error
-
-    async def verify_connection(self) -> None:
-        """
-        Verify that the Claude Code provider is configured correctly by making a simple test call.
-
-        Raises:
-            RuntimeError: If the connection test fails.
-        """
-        try:
-            test_messages = [{"role": "user", "content": "test"}]
-            await self.call(
-                messages=test_messages,
-                max_completion_tokens=10,
-                temperature=0.0,
-                scope="verification",
-                max_retries=0,
-            )
-            logger.info("Claude Code connection verified successfully")
-        except Exception as e:
-            logger.error(f"Claude Code connection verification failed: {e}")
-            raise RuntimeError(f"Failed to verify Claude Code connection: {e}") from e
-
-    async def call(
-        self,
-        messages: list[dict[str, str]],
-        response_format: Any | None = None,
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "memory",
-        max_retries: int = 10,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 60.0,
-        skip_validation: bool = False,
-        strict_schema: bool = False,
-        return_usage: bool = False,
-    ) -> Any:
-        """
-        Make an LLM API call with retry logic.
-
-        Args:
-            messages: List of message dicts with 'role' and 'content'.
-            response_format: Optional Pydantic model for structured output.
-            max_completion_tokens: Maximum tokens in response (ignored by Claude Agent SDK).
-            temperature: Sampling temperature (ignored by Claude Agent SDK).
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            skip_validation: Return raw JSON without Pydantic validation.
-            strict_schema: Use strict JSON schema enforcement (not supported).
-            return_usage: If True, return tuple (result, TokenUsage) instead of just result.
-
-        Returns:
-            If return_usage=False: Parsed response if response_format is provided, otherwise text content.
-            If return_usage=True: Tuple of (result, TokenUsage) with estimated token counts.
-
-        Raises:
-            OutputTooLongError: If output exceeds token limits (not supported by Claude Agent SDK).
-            Exception: Re-raises API errors after retries exhausted.
-        """
-        from claude_agent_sdk import (  # type: ignore[unresolved-import]
-            AssistantMessage,
-            ClaudeAgentOptions,
-            TextBlock,
-            query,
-        )
-
-        start_time = time.time()
-
-        # Build system prompt
-        system_prompt = ""
-        user_content = ""
-
-        for msg in messages:
-            role = msg.get("role", "user")
-            content = msg.get("content", "")
-
-            if role == "system":
-                system_prompt += ("\n\n" + content) if system_prompt else content
-            elif role == "user":
-                user_content += ("\n\n" + content) if user_content else content
-            elif role == "assistant":
-                # Claude Agent SDK doesn't support multi-turn easily in query()
-                # For now, prepend assistant messages to user content
-                user_content += f"\n\n[Previous assistant response: {content}]"
-
-        # Add JSON schema instruction if response_format is provided
-        if response_format is not None and hasattr(response_format, "model_json_schema"):
-            schema = response_format.model_json_schema()
-            schema_instruction = (
-                f"\n\nYou must respond with valid JSON matching this schema:\n{json.dumps(schema, indent=2)}\n\n"
-                "Respond with ONLY the JSON, no markdown formatting."
-            )
-            user_content += schema_instruction
-
-        # Configure SDK options
-        options = ClaudeAgentOptions(
-            system_prompt=system_prompt if system_prompt else None,
-            max_turns=1,  # Single-turn for API-style interactions
-            allowed_tools=[],  # Disable tools for standard LLM calls
-        )
-
-        # Call Claude Agent SDK
-        last_exception = None
-        for attempt in range(max_retries + 1):
-            try:
-                # Collect streaming response
-                full_text = ""
-
-                async for message in query(prompt=user_content, options=options):
-                    if isinstance(message, AssistantMessage):
-                        for block in message.content:
-                            if isinstance(block, TextBlock):
-                                full_text += block.text
-
-                # Handle structured output
-                if response_format is not None:
-                    # Models may wrap JSON in markdown
-                    clean_text = full_text
-                    if "```json" in full_text:
-                        clean_text = full_text.split("```json")[1].split("```")[0].strip()
-                    elif "```" in full_text:
-                        clean_text = full_text.split("```")[1].split("```")[0].strip()
-
-                    try:
-                        json_data = json.loads(clean_text)
-                    except json.JSONDecodeError as e:
-                        logger.warning(f"Claude Code JSON parse error (attempt {attempt + 1}/{max_retries + 1}): {e}")
-                        if attempt < max_retries:
-                            backoff = min(initial_backoff * (2**attempt), max_backoff)
-                            await asyncio.sleep(backoff)
-                            last_exception = e
-                            continue
-                        raise
-
-                    if skip_validation:
-                        result = json_data
-                    else:
-                        result = response_format.model_validate(json_data)
-                else:
-                    result = full_text
-
-                # Record metrics
-                duration = time.time() - start_time
-                metrics = get_metrics_collector()
-
-                # Estimate token usage (Claude Agent SDK doesn't report exact counts)
-                # Use character count / 4 as rough estimate (1 token ≈ 4 characters)
-                estimated_input = sum(len(m.get("content", "")) for m in messages) // 4
-                estimated_output = len(full_text) // 4
-
-                metrics.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    duration=duration,
-                    input_tokens=estimated_input,
-                    output_tokens=estimated_output,
-                    success=True,
-                )
-
-                # Record trace span
-                try:
-                    from hindsight_api.tracing import get_span_recorder
-
-                    span_recorder = get_span_recorder()
-                    span_recorder.record_llm_call(
-                        provider=self.provider,
-                        model=self.model,
-                        scope=scope,
-                        messages=messages,
-                        response_content=result if isinstance(result, str) else result.model_dump_json(),
-                        input_tokens=estimated_input,
-                        output_tokens=estimated_output,
-                        duration=duration,
-                        finish_reason=None,
-                        error=None,
-                    )
-                except Exception:
-                    pass  # logging failure must never affect the operation
-
-                # Log slow calls
-                if duration > 10.0:
-                    logger.info(
-                        f"slow llm call: scope={scope}, model={self.provider}/{self.model}, time={duration:.3f}s"
-                    )
-
-                if return_usage:
-                    token_usage = TokenUsage(
-                        input_tokens=estimated_input,
-                        output_tokens=estimated_output,
-                        total_tokens=estimated_input + estimated_output,
-                    )
-                    return result, token_usage
-
-                return result
-
-            except Exception as e:
-                last_exception = e
-
-                # Check for authentication errors
-                error_str = str(e).lower()
-                if "auth" in error_str or "login" in error_str or "credential" in error_str:
-                    logger.error(f"Claude Code authentication error: {e}")
-                    raise RuntimeError(
-                        f"Claude Code authentication failed: {e}\n\n"
-                        "Run 'claude auth login' to authenticate with Claude Pro/Max."
-                    ) from e
-
-                if attempt < max_retries:
-                    backoff = min(initial_backoff * (2**attempt), max_backoff)
-                    logger.warning(f"Claude Code error (attempt {attempt + 1}/{max_retries + 1}): {e}")
-                    await asyncio.sleep(backoff)
-                    continue
-                else:
-                    logger.error(f"Claude Code error after {max_retries + 1} attempts: {e}")
-                    raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("Claude Code call failed after all retries")
-
-    async def call_with_tools(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "tools",
-        max_retries: int = 5,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 30.0,
-        tool_choice: str | dict[str, Any] = "auto",
-    ) -> LLMToolCallResult:
-        """
-        Make an LLM API call with tool/function calling support using Claude Agent SDK.
-
-        This implementation uses ClaudeSDKClient (not query()) because custom tools via
-        SDK MCP servers are only supported with the client. Tools are converted from OpenAI
-        format to SDK MCP tools, and tool names are formatted as mcp__hindsight_tools__{name}.
-
-        Args:
-            messages: List of message dicts. Can include tool results with role='tool'.
-            tools: List of tool definitions in OpenAI format.
-            max_completion_tokens: Maximum tokens in response (not used by Claude Agent SDK).
-            temperature: Sampling temperature (not used by Claude Agent SDK).
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            tool_choice: How to choose tools (not used by Claude Agent SDK).
-
-        Returns:
-            LLMToolCallResult with content and/or tool_calls.
-        """
-        from claude_agent_sdk import (  # type: ignore[unresolved-import]
-            AssistantMessage,
-            ClaudeAgentOptions,
-            ClaudeSDKClient,
-            SdkMcpTool,
-            TextBlock,
-            ToolUseBlock,
-            create_sdk_mcp_server,
-        )
-
-        start_time = time.time()
-
-        # Convert OpenAI tool format to Claude Agent SDK SdkMcpTool format
-        sdk_tools: list[SdkMcpTool] = []
-        tool_names: list[str] = []
-
-        for tool in tools:
-            func = tool.get("function", {})
-            tool_name = func.get("name", "")
-            tool_description = func.get("description", "")
-            parameters = func.get("parameters", {})
-
-            # Create a handler with proper closure to avoid transport issues
-            def make_handler(name: str):
-                async def handler(args: dict[str, Any]) -> dict[str, Any]:
-                    # Return immediately with success - tool execution happens externally
-                    return {
-                        "content": [
-                            {
-                                "type": "text",
-                                "text": f"[Tool {name} called successfully]",
-                            }
-                        ]
-                    }
-
-                return handler
-
-            sdk_tools.append(
-                SdkMcpTool(
-                    name=tool_name,
-                    description=tool_description,
-                    input_schema=parameters,
-                    handler=make_handler(tool_name),
-                )
-            )
-            tool_names.append(tool_name)
-
-        # Create an MCP server with the tools
-        mcp_server = create_sdk_mcp_server(
-            name="hindsight_tools",
-            version="1.0.0",
-            tools=sdk_tools if sdk_tools else None,
-        )
-
-        # Build system prompt and user content from messages
-        system_prompt = ""
-        user_content = ""
-
-        for msg in messages:
-            role = msg.get("role", "user")
-            content = msg.get("content", "")
-
-            if role == "system":
-                system_prompt += ("\n\n" + content) if system_prompt else content
-            elif role == "user":
-                user_content += ("\n\n" + content) if user_content else content
-            elif role == "assistant":
-                # Include previous assistant messages as context
-                user_content += f"\n\n[Previous assistant response: {content}]"
-            elif role == "tool":
-                # Tool results are already in tool_results_map, append to user context
-                tool_call_id = msg.get("tool_call_id", "")
-                user_content += f"\n\n[Tool result for {tool_call_id}: {content}]"
-
-        # Format tool names for SDK MCP servers: mcp__{server_name}__{tool_name}
-        # This is required by the Claude Agent SDK for MCP server tools
-        allowed_tool_names = [f"mcp__hindsight_tools__{name}" for name in tool_names]
-
-        # Configure SDK options with MCP server
-        options = ClaudeAgentOptions(
-            system_prompt=system_prompt if system_prompt else None,
-            max_turns=1,  # Single-turn for API-style interactions
-            mcp_servers={"hindsight_tools": mcp_server} if sdk_tools else {},
-            allowed_tools=allowed_tool_names if allowed_tool_names else [],
-        )
-
-        # Call Claude Agent SDK with retry logic
-        last_exception = None
-        for attempt in range(max_retries + 1):
-            try:
-                full_text = ""
-                tool_calls: list[LLMToolCall] = []
-
-                # Use ClaudeSDKClient for tool calling support
-                # Note: query() does NOT support custom tools, only ClaudeSDKClient does
-                async with ClaudeSDKClient(options=options) as client:
-                    # Send the query
-                    await client.query(user_content)
-
-                    # Receive response
-                    async for message in client.receive_response():
-                        if isinstance(message, AssistantMessage):
-                            for block in message.content:
-                                if isinstance(block, TextBlock):
-                                    full_text += block.text
-                                elif isinstance(block, ToolUseBlock):
-                                    # SDK returns tool names with MCP prefix (mcp__hindsight_tools__{name})
-                                    # Strip the prefix to return original tool name expected by caller
-                                    tool_name = block.name
-                                    if tool_name.startswith("mcp__hindsight_tools__"):
-                                        tool_name = tool_name.replace("mcp__hindsight_tools__", "", 1)
-
-                                    tool_calls.append(
-                                        LLMToolCall(
-                                            id=block.id,
-                                            name=tool_name,
-                                            arguments=block.input,
-                                        )
-                                    )
-
-                # Record metrics
-                duration = time.time() - start_time
-                metrics = get_metrics_collector()
-
-                # Estimate token usage (Claude Agent SDK doesn't report exact counts)
-                estimated_input = sum(len(m.get("content", "")) for m in messages) // 4
-                estimated_output = len(full_text) // 4
-
-                metrics.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    duration=duration,
-                    input_tokens=estimated_input,
-                    output_tokens=estimated_output,
-                    success=True,
-                )
-
-                # Log slow calls
-                if duration > 10.0:
-                    logger.info(
-                        f"slow llm call: scope={scope}, model={self.provider}/{self.model}, time={duration:.3f}s"
-                    )
-
-                return LLMToolCallResult(
-                    content=full_text if full_text else None,
-                    tool_calls=tool_calls,
-                    finish_reason="tool_calls" if tool_calls else "stop",
-                    input_tokens=estimated_input,
-                    output_tokens=estimated_output,
-                )
-
-            except Exception as e:
-                last_exception = e
-
-                # Check for authentication errors
-                error_str = str(e).lower()
-                if "auth" in error_str or "login" in error_str or "credential" in error_str:
-                    logger.error(f"Claude Code authentication error: {e}")
-                    raise RuntimeError(
-                        f"Claude Code authentication failed: {e}\n\n"
-                        "Run 'claude auth login' to authenticate with Claude Pro/Max."
-                    ) from e
-
-                if attempt < max_retries:
-                    backoff = min(initial_backoff * (2**attempt), max_backoff)
-                    logger.warning(f"Claude Code tool call error (attempt {attempt + 1}/{max_retries + 1}): {e}")
-                    await asyncio.sleep(backoff)
-                    continue
-                else:
-                    logger.error(f"Claude Code tool call error after {max_retries + 1} attempts: {e}")
-                    raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("Claude Code tool call failed after all retries")
-
-    async def cleanup(self) -> None:
-        """Clean up resources (no HTTP client to close for Claude Agent SDK)."""
-        pass

hindsight-api-slim/hindsight_api/engine/providers/codex_llm.py

@@ -1,621 +0,0 @@
-"""
-OpenAI Codex LLM provider using ChatGPT Plus/Pro OAuth authentication.
-
-This provider enables using ChatGPT Plus/Pro subscriptions for API calls
-without separate OpenAI Platform API credits. It uses OAuth tokens from
-~/.codex/auth.json and communicates with the ChatGPT backend API.
-"""
-
-import asyncio
-import json
-import logging
-import os
-import time
-import uuid
-from pathlib import Path
-from typing import Any
-
-import httpx
-
-from hindsight_api.engine.llm_interface import LLMInterface, OutputTooLongError
-from hindsight_api.engine.response_models import LLMToolCall, LLMToolCallResult, TokenUsage
-from hindsight_api.metrics import get_metrics_collector
-
-logger = logging.getLogger(__name__)
-
-
-class CodexLLM(LLMInterface):
-    """
-    LLM provider using OpenAI Codex OAuth authentication.
-
-    Authenticates using ChatGPT Plus/Pro credentials stored in ~/.codex/auth.json
-    and makes API calls to chatgpt.com/backend-api/codex/responses.
-    """
-
-    def __init__(
-        self,
-        provider: str,
-        api_key: str,  # Will be ignored, reads from ~/.codex/auth.json
-        base_url: str,
-        model: str,
-        reasoning_effort: str = "low",
-        **kwargs: Any,
-    ):
-        """Initialize Codex LLM provider."""
-        super().__init__(provider, api_key, base_url, model, reasoning_effort, **kwargs)
-
-        # Load Codex OAuth credentials
-        try:
-            self.access_token, self.account_id = self._load_codex_auth()
-            logger.info(f"Loaded Codex OAuth credentials for account: {self.account_id}")
-        except Exception as e:
-            raise RuntimeError(
-                f"Failed to load Codex OAuth credentials from ~/.codex/auth.json: {e}\n\n"
-                "To set up Codex authentication:\n"
-                "1. Install Codex CLI: npm install -g @openai/codex\n"
-                "2. Login: codex auth login\n"
-                "3. Verify: ls ~/.codex/auth.json\n\n"
-                "Or use a different provider (openai, anthropic, gemini) with API keys."
-            ) from e
-
-        # Use ChatGPT backend API endpoint
-        if not self.base_url:
-            self.base_url = "https://chatgpt.com/backend-api"
-
-        # Normalize model name (strip openai/ prefix if present)
-        if self.model.startswith("openai/"):
-            self.model = self.model[len("openai/") :]
-
-        # Map reasoning effort to Codex reasoning summary format
-        # Codex supports: "auto", "concise", "detailed"
-        self.reasoning_summary = self._map_reasoning_effort(reasoning_effort)
-
-        # HTTP client for SSE streaming
-        self._client = httpx.AsyncClient(timeout=120.0)
-
-    def _load_codex_auth(self) -> tuple[str, str]:
-        """
-        Load OAuth credentials from ~/.codex/auth.json.
-
-        Returns:
-            Tuple of (access_token, account_id).
-
-        Raises:
-            FileNotFoundError: If auth file doesn't exist.
-            ValueError: If auth file is invalid.
-        """
-        auth_file = Path.home() / ".codex" / "auth.json"
-
-        if not auth_file.exists():
-            raise FileNotFoundError(
-                f"Codex auth file not found: {auth_file}\nRun 'codex auth login' to authenticate with ChatGPT Plus/Pro."
-            )
-
-        with open(auth_file) as f:
-            data = json.load(f)
-
-        # Validate auth structure
-        auth_mode = data.get("auth_mode")
-        if auth_mode != "chatgpt":
-            raise ValueError(f"Expected auth_mode='chatgpt', got: {auth_mode}")
-
-        tokens = data.get("tokens", {})
-        access_token = tokens.get("access_token")
-        account_id = tokens.get("account_id")
-
-        if not access_token:
-            raise ValueError("No access_token found in Codex auth file. Run 'codex auth login' again.")
-
-        return access_token, account_id
-
-    def _map_reasoning_effort(self, effort: str) -> str:
-        """
-        Map standard reasoning effort to Codex reasoning summary format.
-
-        Args:
-            effort: Standard effort level ("low", "medium", "high", "xhigh").
-
-        Returns:
-            Codex reasoning summary: "concise", "detailed", or "auto".
-        """
-        mapping = {
-            "low": "concise",
-            "medium": "auto",
-            "high": "detailed",
-            "xhigh": "detailed",
-        }
-        return mapping.get(effort.lower(), "auto")
-
-    async def verify_connection(self) -> None:
-        """Verify Codex connection by making a simple test call."""
-        try:
-            logger.info(f"Verifying Codex LLM: model={self.model}, account={self.account_id}...")
-            await self.call(
-                messages=[{"role": "user", "content": "Say 'ok'"}],
-                max_completion_tokens=10,
-                max_retries=2,
-                initial_backoff=0.5,
-                max_backoff=2.0,
-                scope="verification",
-            )
-            logger.info(f"Codex LLM verified: {self.model}")
-        except Exception as e:
-            raise RuntimeError(f"Codex LLM connection verification failed for {self.model}: {e}") from e
-
-    async def call(
-        self,
-        messages: list[dict[str, str]],
-        response_format: Any | None = None,
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "memory",
-        max_retries: int = 10,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 60.0,
-        skip_validation: bool = False,
-        strict_schema: bool = False,
-        return_usage: bool = False,
-    ) -> Any:
-        """Make API call to Codex backend with SSE streaming."""
-        start_time = time.time()
-
-        # Prepare system instructions
-        system_instruction = ""
-        user_messages = []
-
-        for msg in messages:
-            role = msg.get("role", "user")
-            content = msg.get("content", "")
-
-            if role == "system":
-                system_instruction += ("\n\n" + content) if system_instruction else content
-            else:
-                user_messages.append(msg)
-
-        # Add JSON schema instruction if response_format is provided
-        if response_format is not None and hasattr(response_format, "model_json_schema"):
-            schema = response_format.model_json_schema()
-            schema_msg = f"\n\nYou must respond with valid JSON matching this schema:\n{json.dumps(schema, indent=2)}"
-            system_instruction += schema_msg
-
-        # gpt-5.2-codex only supports "detailed" reasoning summary
-        reasoning_summary = "detailed" if "5.2" in self.model else self.reasoning_summary
-
-        # Build Codex request payload
-        payload = {
-            "model": self.model,
-            "instructions": system_instruction,
-            "input": [
-                {
-                    "type": "message",
-                    "role": msg.get("role", "user"),
-                    "content": msg.get("content", ""),
-                }
-                for msg in user_messages
-            ],
-            "tools": [],
-            "tool_choice": "auto",
-            "parallel_tool_calls": True,
-            "reasoning": {"summary": reasoning_summary},
-            "store": False,  # Codex uses stateless mode
-            "stream": True,  # SSE streaming
-            "include": ["reasoning.encrypted_content"],
-            "prompt_cache_key": str(uuid.uuid4()),
-        }
-
-        headers = {
-            "Authorization": f"Bearer {self.access_token}",
-            "Content-Type": "application/json",
-            "OpenAI-Account-ID": self.account_id,
-            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7)",
-            "Origin": "https://chatgpt.com",
-        }
-
-        url = f"{self.base_url}/codex/responses"
-        last_exception = None
-
-        for attempt in range(max_retries + 1):
-            try:
-                response = await self._client.post(url, json=payload, headers=headers, timeout=120.0)
-                response.raise_for_status()
-
-                # Parse SSE stream
-                content = await self._parse_sse_stream(response)
-
-                # Handle structured output
-                if response_format is not None:
-                    # Models may wrap JSON in markdown
-                    clean_content = content
-                    if "```json" in content:
-                        clean_content = content.split("```json")[1].split("```")[0].strip()
-                    elif "```" in content:
-                        clean_content = content.split("```")[1].split("```")[0].strip()
-
-                    try:
-                        json_data = json.loads(clean_content)
-                    except json.JSONDecodeError as e:
-                        logger.warning(f"Codex JSON parse error (attempt {attempt + 1}/{max_retries + 1}): {e}")
-                        if attempt < max_retries:
-                            backoff = min(initial_backoff * (2**attempt), max_backoff)
-                            await asyncio.sleep(backoff)
-                            last_exception = e
-                            continue
-                        raise
-
-                    if skip_validation:
-                        result = json_data
-                    else:
-                        result = response_format.model_validate(json_data)
-                else:
-                    result = content
-
-                # Record metrics
-                duration = time.time() - start_time
-                metrics = get_metrics_collector()
-                metrics.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    duration=duration,
-                    input_tokens=0,  # Codex doesn't report token counts in SSE
-                    output_tokens=0,
-                    success=True,
-                )
-
-                # Record trace span
-                from hindsight_api.tracing import get_span_recorder
-
-                # Estimate tokens for tracing
-                estimated_input = sum(len(m.get("content", "")) for m in messages) // 4
-                estimated_output = len(content) // 4
-                span_recorder = get_span_recorder()
-                span_recorder.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    messages=messages,
-                    response_content=result if isinstance(result, str) else json.dumps(result),
-                    input_tokens=estimated_input,
-                    output_tokens=estimated_output,
-                    duration=duration,
-                    finish_reason=None,
-                    error=None,
-                )
-
-                if return_usage:
-                    # Codex doesn't provide token counts, estimate based on content
-                    estimated_input = sum(len(m.get("content", "")) for m in messages) // 4
-                    estimated_output = len(content) // 4
-                    token_usage = TokenUsage(
-                        input_tokens=estimated_input,
-                        output_tokens=estimated_output,
-                        total_tokens=estimated_input + estimated_output,
-                    )
-                    return result, token_usage
-
-                return result
-
-            except httpx.HTTPStatusError as e:
-                last_exception = e
-                status_code = e.response.status_code
-
-                # Fast fail on auth errors
-                if status_code in (401, 403):
-                    logger.error(f"Codex auth error (HTTP {status_code}): {e.response.text[:200]}")
-                    raise RuntimeError(
-                        "Codex authentication failed. Your OAuth token may have expired.\n"
-                        "Run 'codex auth login' to re-authenticate."
-                    ) from e
-
-                # Log the actual error message from the API
-                error_detail = e.response.text[:500] if hasattr(e.response, "text") else str(e)
-
-                if attempt < max_retries:
-                    backoff = min(initial_backoff * (2**attempt), max_backoff)
-                    logger.warning(
-                        f"Codex HTTP error {status_code} (attempt {attempt + 1}/{max_retries + 1}): {error_detail}"
-                    )
-                    await asyncio.sleep(backoff)
-                    continue
-                else:
-                    logger.error(
-                        f"Codex HTTP error after {max_retries + 1} attempts: Status {status_code}, Detail: {error_detail}"
-                    )
-                    raise
-
-            except httpx.RequestError as e:
-                last_exception = e
-                if attempt < max_retries:
-                    backoff = min(initial_backoff * (2**attempt), max_backoff)
-                    logger.warning(f"Codex connection error (attempt {attempt + 1}/{max_retries + 1}): {e}")
-                    await asyncio.sleep(backoff)
-                    continue
-                else:
-                    logger.error(f"Codex connection error after {max_retries + 1} attempts: {e}")
-                    raise
-
-            except Exception as e:
-                logger.error(f"Unexpected Codex error: {type(e).__name__}: {e}")
-                raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("Codex call failed after all retries")
-
-    async def _parse_sse_stream(self, response: httpx.Response) -> str:
-        """
-        Parse Server-Sent Events (SSE) stream from Codex API.
-
-        Args:
-            response: HTTP response with SSE stream.
-
-        Returns:
-            Extracted text content from stream.
-        """
-        full_text = ""
-        event_type = None
-
-        async for line in response.aiter_lines():
-            if not line:
-                continue
-
-            # Track event type
-            if line.startswith("event: "):
-                event_type = line[7:]
-
-            # Parse data
-            elif line.startswith("data: "):
-                data_str = line[6:]
-                if data_str == "[DONE]":
-                    break
-
-                try:
-                    data = json.loads(data_str)
-
-                    # Extract content based on event type
-                    if event_type == "response.text.delta" and "delta" in data:
-                        full_text += data["delta"]
-                    elif event_type == "response.content_part.delta" and "delta" in data:
-                        full_text += data["delta"]
-                    # Check for item content
-                    elif "item" in data:
-                        item = data["item"]
-                        if "content" in item:
-                            content = item["content"]
-                            if isinstance(content, list):
-                                for part in content:
-                                    if isinstance(part, dict) and "text" in part:
-                                        full_text += part["text"]
-                            elif isinstance(content, str):
-                                full_text += content
-
-                except json.JSONDecodeError:
-                    # Skip malformed JSON events
-                    pass
-
-        return full_text
-
-    async def call_with_tools(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "tools",
-        max_retries: int = 5,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 30.0,
-        tool_choice: str | dict[str, Any] = "auto",
-    ) -> LLMToolCallResult:
-        """
-        Make API call with tool calling support.
-
-        Parses Codex SSE stream to extract tool calls from response.output_item.done events.
-        Tools are converted from OpenAI format to Codex format (flat structure at top level).
-
-        Args:
-            messages: List of message dicts. Can include tool results with role='tool'.
-            tools: List of tool definitions in OpenAI format.
-            max_completion_tokens: Maximum tokens in response.
-            temperature: Sampling temperature.
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            tool_choice: How to choose tools - "auto", "none", "required", or specific function.
-
-        Returns:
-            LLMToolCallResult with content and/or tool_calls.
-        """
-        start_time = time.time()
-
-        # Prepare system instructions
-        system_instruction = ""
-        user_messages = []
-
-        for msg in messages:
-            role = msg.get("role", "user")
-            content = msg.get("content", "")
-
-            if role == "system":
-                system_instruction += ("\n\n" + content) if system_instruction else content
-            elif role == "tool":
-                # Handle tool results
-                user_messages.append(
-                    {
-                        "type": "message",
-                        "role": "user",
-                        "content": f"Tool result: {content}",
-                    }
-                )
-            else:
-                user_messages.append(
-                    {
-                        "type": "message",
-                        "role": role,
-                        "content": content,
-                    }
-                )
-
-        # Convert tools to Codex format
-        # Codex expects tools with type and name/description/parameters at top level
-        codex_tools = []
-        for tool in tools:
-            func = tool.get("function", {})
-            codex_tools.append(
-                {
-                    "type": "function",
-                    "name": func.get("name", ""),
-                    "description": func.get("description", ""),
-                    "parameters": func.get("parameters", {}),
-                }
-            )
-
-        # gpt-5.2-codex only supports "detailed" reasoning summary
-        reasoning_summary = "detailed" if "5.2" in self.model else self.reasoning_summary
-
-        payload = {
-            "model": self.model,
-            "instructions": system_instruction,
-            "input": user_messages,
-            "tools": codex_tools,
-            "tool_choice": tool_choice,
-            "parallel_tool_calls": True,
-            "reasoning": {"summary": reasoning_summary},
-            "store": False,
-            "stream": True,
-            "include": ["reasoning.encrypted_content"],
-            "prompt_cache_key": str(uuid.uuid4()),
-        }
-
-        headers = {
-            "Authorization": f"Bearer {self.access_token}",
-            "Content-Type": "application/json",
-            "OpenAI-Account-ID": self.account_id,
-            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7)",
-            "Origin": "https://chatgpt.com",
-        }
-
-        url = f"{self.base_url}/codex/responses"
-
-        # Debug logging for troubleshooting
-        logger.debug(f"Codex tool call request: url={url}, model={payload['model']}, tools={len(codex_tools)}")
-
-        try:
-            response = await self._client.post(url, json=payload, headers=headers, timeout=120.0)
-
-            # Log response details on error
-            if response.status_code != 200:
-                logger.error(f"Codex API error {response.status_code}: {response.text[:500]}")
-
-            response.raise_for_status()
-
-            # Parse SSE for tool calls and content
-            content, tool_calls = await self._parse_sse_tool_stream(response)
-
-            duration = time.time() - start_time
-            metrics = get_metrics_collector()
-            metrics.record_llm_call(
-                provider=self.provider,
-                model=self.model,
-                scope=scope,
-                duration=duration,
-                input_tokens=0,
-                output_tokens=0,
-                success=True,
-            )
-
-            # Record OpenTelemetry span
-            from hindsight_api.tracing import get_span_recorder
-
-            span_recorder = get_span_recorder()
-            # Convert LLMToolCall objects to dicts for span recording
-            tool_calls_dict = (
-                [{"id": tc.id, "name": tc.name, "arguments": tc.arguments} for tc in tool_calls] if tool_calls else None
-            )
-            span_recorder.record_llm_call(
-                provider=self.provider,
-                model=self.model,
-                scope=scope,
-                messages=messages,
-                response_content=content,
-                input_tokens=0,  # Codex doesn't provide token counts
-                output_tokens=0,
-                duration=duration,
-                finish_reason="tool_calls" if tool_calls else "stop",
-                error=None,
-                tool_calls=tool_calls_dict,
-            )
-
-            return LLMToolCallResult(
-                content=content,
-                tool_calls=tool_calls,
-                finish_reason="tool_calls" if tool_calls else "stop",
-                input_tokens=0,
-                output_tokens=0,
-            )
-
-        except Exception as e:
-            logger.error(f"Codex tool call error: {e}")
-            raise
-
-    async def _parse_sse_tool_stream(self, response: httpx.Response) -> tuple[str | None, list[LLMToolCall]]:
-        """
-        Parse SSE stream for tool calls and content.
-
-        Returns:
-            Tuple of (content, tool_calls).
-        """
-        content = ""
-        tool_calls: list[LLMToolCall] = []
-        event_type = None
-
-        async for line in response.aiter_lines():
-            if not line:
-                continue
-
-            if line.startswith("event: "):
-                event_type = line[7:]
-
-            elif line.startswith("data: "):
-                data_str = line[6:]
-                if data_str == "[DONE]":
-                    break
-
-                try:
-                    data = json.loads(data_str)
-
-                    # Extract text content
-                    if event_type == "response.text.delta" and "delta" in data:
-                        content += data["delta"]
-
-                    # Extract completed tool calls from response.output_item.done
-                    elif event_type == "response.output_item.done":
-                        item = data.get("item", {})
-                        if item.get("type") == "function_call" and item.get("status") == "completed":
-                            tool_name = item.get("name", "")
-                            arguments_str = item.get("arguments", "{}")
-                            call_id = item.get("call_id", "")
-
-                            try:
-                                arguments = json.loads(arguments_str)
-                            except json.JSONDecodeError:
-                                logger.warning(f"Failed to parse tool arguments: {arguments_str}")
-                                arguments = {}
-
-                            tool_calls.append(
-                                LLMToolCall(
-                                    id=call_id,
-                                    name=tool_name,
-                                    arguments=arguments,
-                                )
-                            )
-
-                except json.JSONDecodeError as e:
-                    logger.warning(f"Failed to parse SSE data: {e}, data_str: {data_str[:200]}")
-
-        return content if content else None, tool_calls
-
-    async def cleanup(self) -> None:
-        """Clean up HTTP client."""
-        await self._client.aclose()

hindsight-api-slim/hindsight_api/engine/providers/gemini_llm.py

@@ -1,639 +0,0 @@
-"""
-Google Gemini/VertexAI LLM provider.
-
-This provider supports both:
-1. Gemini API (api.generativeai.google.com) with API key authentication
-2. Vertex AI with service account or Application Default Credentials (ADC)
-"""
-
-import asyncio
-import json
-import logging
-import os
-import time
-from contextvars import ContextVar
-from typing import Any
-
-from google import genai
-from google.genai import errors as genai_errors
-from google.genai import types as genai_types
-
-from hindsight_api.engine.llm_interface import LLMInterface, OutputTooLongError
-from hindsight_api.engine.llm_wrapper import parse_llm_json
-from hindsight_api.engine.response_models import LLMToolCall, LLMToolCallResult, TokenUsage
-from hindsight_api.metrics import get_metrics_collector
-
-logger = logging.getLogger(__name__)
-
-# Per-request Gemini safety settings override.
-# Set exclusively by ConfiguredLLMProvider.call() / call_with_tools() via token-based
-# set/reset, so it is properly scoped to each individual LLM call and never leaks.
-_safety_settings_ctx: ContextVar[list | None] = ContextVar("gemini_safety_settings", default=None)
-
-
-# Vertex AI imports (optional)
-try:
-    import google.auth
-    from google.oauth2 import service_account
-
-    VERTEXAI_AVAILABLE = True
-except ImportError:
-    VERTEXAI_AVAILABLE = False
-
-
-class GeminiLLM(LLMInterface):
-    """
-    LLM provider for Google Gemini and Vertex AI.
-
-    Supports:
-    - Gemini API: provider="gemini", requires api_key
-    - Vertex AI: provider="vertexai", requires project_id and region, uses ADC or service account
-    """
-
-    def __init__(
-        self,
-        provider: str,
-        api_key: str,
-        base_url: str,
-        model: str,
-        reasoning_effort: str = "low",
-        **kwargs: Any,
-    ):
-        """Initialize Gemini/VertexAI LLM provider."""
-        super().__init__(provider, api_key, base_url, model, reasoning_effort, **kwargs)
-
-        self._client = None
-        self._is_vertexai = self.provider == "vertexai"
-
-        # Safety settings: None means use Gemini's defaults
-        self._safety_settings: list | None = kwargs.get("gemini_safety_settings")
-
-        if self._is_vertexai:
-            self._init_vertexai(**kwargs)
-        else:
-            self._init_gemini()
-
-    def _init_gemini(self) -> None:
-        """Initialize Gemini API client."""
-        if not self.api_key:
-            raise ValueError("Gemini provider requires api_key")
-
-        self._client = genai.Client(api_key=self.api_key)
-        logger.info(f"Gemini API: model={self.model}")
-
-    def _init_vertexai(self, **kwargs: Any) -> None:
-        """Initialize Vertex AI client with project, region, and credentials."""
-        # Extract Vertex AI config from kwargs
-        project_id = kwargs.get("vertexai_project_id")
-        region = kwargs.get("vertexai_region", "us-central1")
-        service_account_key = kwargs.get("vertexai_service_account_key")
-        credentials = kwargs.get("vertexai_credentials")  # Pre-loaded credentials object
-
-        if not project_id:
-            raise ValueError(
-                "HINDSIGHT_API_LLM_VERTEXAI_PROJECT_ID is required for Vertex AI provider. "
-                "Set it to your GCP project ID."
-            )
-
-        auth_method = "ADC"
-
-        # Use pre-loaded credentials if provided (passed from LLMProvider)
-        if credentials is not None:
-            auth_method = "service_account"
-        # Otherwise, load explicit service account credentials if path provided
-        elif service_account_key:
-            if not VERTEXAI_AVAILABLE:
-                raise ValueError(
-                    "Vertex AI service account auth requires 'google-auth' package. "
-                    "Install with: pip install google-auth"
-                )
-            credentials = service_account.Credentials.from_service_account_file(
-                service_account_key,
-                scopes=["https://www.googleapis.com/auth/cloud-platform"],
-            )
-            auth_method = "service_account"
-            logger.info(f"Vertex AI: Using service account key: {service_account_key}")
-
-        # Strip google/ prefix from model name — native SDK uses bare names
-        # e.g. "google/gemini-2.0-flash-lite-001" -> "gemini-2.0-flash-lite-001"
-        if self.model.startswith("google/"):
-            self.model = self.model[len("google/") :]
-
-        # Create Vertex AI client
-        client_kwargs: dict[str, Any] = {
-            "vertexai": True,
-            "project": project_id,
-            "location": region,
-        }
-        if credentials is not None:
-            client_kwargs["credentials"] = credentials
-
-        self._client = genai.Client(**client_kwargs)
-
-        logger.info(f"Vertex AI: project={project_id}, region={region}, model={self.model}, auth={auth_method}")
-
-    async def verify_connection(self) -> None:
-        """
-        Verify that the Gemini/VertexAI provider is configured correctly.
-
-        Raises:
-            RuntimeError: If the connection test fails.
-        """
-        try:
-            logger.info(f"Verifying {self.provider.upper()}: model={self.model}...")
-            await self.call(
-                messages=[{"role": "user", "content": "Say 'ok'"}],
-                max_completion_tokens=100,
-                max_retries=2,
-                initial_backoff=0.5,
-                max_backoff=2.0,
-                scope="verification",
-            )
-            logger.info(f"{self.provider.upper()} connection verified successfully")
-        except Exception as e:
-            raise RuntimeError(f"Failed to verify {self.provider.upper()} connection: {e}") from e
-
-    async def call(
-        self,
-        messages: list[dict[str, str]],
-        response_format: Any | None = None,
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "memory",
-        max_retries: int = 10,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 60.0,
-        skip_validation: bool = False,
-        strict_schema: bool = False,
-        return_usage: bool = False,
-    ) -> Any:
-        """
-        Make a Gemini/VertexAI API call with retry logic.
-
-        Args:
-            messages: List of message dicts with 'role' and 'content'.
-            response_format: Optional Pydantic model for structured output.
-            max_completion_tokens: Maximum tokens in response (not supported by Gemini).
-            temperature: Sampling temperature (0.0-2.0).
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            skip_validation: Return raw JSON without Pydantic validation.
-            strict_schema: Use strict JSON schema enforcement (not supported by Gemini).
-            return_usage: If True, return tuple (result, TokenUsage).
-
-        Returns:
-            If return_usage=False: Parsed response if response_format provided, else text.
-            If return_usage=True: Tuple of (result, TokenUsage).
-        """
-        start_time = time.time()
-
-        # Convert OpenAI-style messages to Gemini format
-        system_instruction = None
-        gemini_contents = []
-
-        for msg in messages:
-            role = msg.get("role", "user")
-            content = msg.get("content", "")
-
-            if role == "system":
-                if system_instruction:
-                    system_instruction += "\n\n" + content
-                else:
-                    system_instruction = content
-            elif role == "assistant":
-                gemini_contents.append(genai_types.Content(role="model", parts=[genai_types.Part(text=content)]))
-            else:
-                gemini_contents.append(genai_types.Content(role="user", parts=[genai_types.Part(text=content)]))
-
-        # Add JSON schema instruction if response_format is provided
-        if response_format is not None and hasattr(response_format, "model_json_schema"):
-            schema = response_format.model_json_schema()
-            schema_msg = f"\n\nYou must respond with valid JSON matching this schema:\n{json.dumps(schema, indent=2)}"
-            if system_instruction:
-                system_instruction += schema_msg
-            else:
-                system_instruction = schema_msg
-
-        # Build generation config
-        config_kwargs: dict[str, Any] = {}
-        if system_instruction:
-            config_kwargs["system_instruction"] = system_instruction
-        if response_format is not None:
-            config_kwargs["response_mime_type"] = "application/json"
-            config_kwargs["response_schema"] = response_format
-        if temperature is not None:
-            config_kwargs["temperature"] = temperature
-
-        # Apply safety settings: context var (per-request bank override) takes precedence over instance default
-        effective_safety_settings = _safety_settings_ctx.get()
-        if effective_safety_settings is None:
-            effective_safety_settings = self._safety_settings
-        if effective_safety_settings is not None:
-            config_kwargs["safety_settings"] = [
-                genai_types.SafetySetting(category=s["category"], threshold=s["threshold"])
-                for s in effective_safety_settings
-            ]
-
-        generation_config = genai_types.GenerateContentConfig(**config_kwargs) if config_kwargs else None
-
-        last_exception = None
-
-        for attempt in range(max_retries + 1):
-            try:
-                response = await asyncio.wait_for(
-                    self._client.aio.models.generate_content(
-                        model=self.model,
-                        contents=gemini_contents,
-                        config=generation_config,
-                    ),
-                    timeout=90.0,  # Safety net for network hangs; valid slow responses are <90s
-                )
-
-                content = response.text
-
-                # Handle empty response
-                if content is None:
-                    block_reason = None
-                    if hasattr(response, "candidates") and response.candidates:
-                        candidate = response.candidates[0]
-                        if hasattr(candidate, "finish_reason"):
-                            block_reason = candidate.finish_reason
-
-                    if attempt < max_retries:
-                        logger.warning(f"Gemini returned empty response (reason: {block_reason}), retrying...")
-                        backoff = min(initial_backoff * (2**attempt), max_backoff)
-                        await asyncio.sleep(backoff)
-                        continue
-                    else:
-                        raise RuntimeError(f"Gemini returned empty response after {max_retries + 1} attempts")
-
-                # Parse structured output if requested
-                if response_format is not None:
-                    json_data = parse_llm_json(content)
-                    if skip_validation:
-                        result = json_data
-                    else:
-                        result = response_format.model_validate(json_data)
-                else:
-                    result = content
-
-                # Extract token usage
-                input_tokens = 0
-                output_tokens = 0
-                if hasattr(response, "usage_metadata") and response.usage_metadata:
-                    usage = response.usage_metadata
-                    input_tokens = usage.prompt_token_count or 0
-                    output_tokens = usage.candidates_token_count or 0
-
-                # Record metrics
-                duration = time.time() - start_time
-                metrics = get_metrics_collector()
-                metrics.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    duration=duration,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    success=True,
-                )
-
-                # Record trace span
-                from hindsight_api.tracing import get_span_recorder
-
-                finish_reason = None
-                if hasattr(response, "candidates") and response.candidates:
-                    if hasattr(response.candidates[0], "finish_reason"):
-                        finish_reason = str(response.candidates[0].finish_reason)
-                span_recorder = get_span_recorder()
-                from hindsight_api.tracing import _serialize_for_span
-
-                span_recorder.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    messages=messages,
-                    response_content=_serialize_for_span(result),
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    duration=duration,
-                    finish_reason=finish_reason,
-                    error=None,
-                )
-
-                # Log slow calls
-                if duration > 10.0 and input_tokens > 0:
-                    logger.info(
-                        f"slow llm call: scope={scope}, model={self.provider}/{self.model}, "
-                        f"input_tokens={input_tokens}, output_tokens={output_tokens}, "
-                        f"time={duration:.3f}s"
-                    )
-
-                if return_usage:
-                    token_usage = TokenUsage(
-                        input_tokens=input_tokens,
-                        output_tokens=output_tokens,
-                        total_tokens=input_tokens + output_tokens,
-                    )
-                    return result, token_usage
-                return result
-
-            except json.JSONDecodeError as e:
-                last_exception = e
-                if attempt < max_retries:
-                    logger.warning("Gemini returned invalid JSON, retrying...")
-                    backoff = min(initial_backoff * (2**attempt), max_backoff)
-                    await asyncio.sleep(backoff)
-                    continue
-                else:
-                    logger.error(f"Gemini returned invalid JSON after {max_retries + 1} attempts")
-                    raise
-
-            except genai_errors.APIError as e:
-                # Fast fail on auth errors - these won't recover with retries
-                if e.code in (401, 403):
-                    logger.error(f"Gemini auth error (HTTP {e.code}), not retrying: {str(e)}")
-                    raise
-
-                # Retry on retryable errors (rate limits, server errors, client errors)
-                if e.code in (400, 429, 500, 502, 503, 504) or (e.code and e.code >= 500):
-                    last_exception = e
-                    if attempt < max_retries:
-                        backoff = min(initial_backoff * (2**attempt), max_backoff)
-                        jitter = backoff * 0.2 * (2 * (time.time() % 1) - 1)
-                        await asyncio.sleep(backoff + jitter)
-                    else:
-                        logger.error(f"Gemini API error after {max_retries + 1} attempts: {str(e)}")
-                        raise
-                else:
-                    logger.error(f"Gemini API error: {type(e).__name__}: {str(e)}")
-                    raise
-
-            except Exception as e:
-                logger.error(f"Unexpected error during Gemini call: {type(e).__name__}: {str(e)}")
-                raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("Gemini call failed after all retries")
-
-    async def call_with_tools(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "tools",
-        max_retries: int = 5,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 30.0,
-        tool_choice: str | dict[str, Any] = "auto",
-    ) -> LLMToolCallResult:
-        """
-        Make a Gemini/VertexAI API call with tool/function calling support.
-
-        Args:
-            messages: List of message dicts. Can include tool results with role='tool'.
-            tools: List of tool definitions in OpenAI format.
-            max_completion_tokens: Maximum tokens (not supported by Gemini).
-            temperature: Sampling temperature.
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            tool_choice: How to choose tools (Gemini uses "auto" only).
-
-        Returns:
-            LLMToolCallResult with content and/or tool_calls.
-        """
-        start_time = time.time()
-
-        # Convert tools to Gemini format
-        gemini_tools = []
-        for tool in tools:
-            func = tool.get("function", {})
-            gemini_tools.append(
-                genai_types.Tool(
-                    function_declarations=[
-                        genai_types.FunctionDeclaration(
-                            name=func.get("name", ""),
-                            description=func.get("description", ""),
-                            parameters=func.get("parameters"),
-                        )
-                    ]
-                )
-            )
-
-        # Convert messages
-        system_instruction = None
-        gemini_contents = []
-        msg_list = list(messages)
-        i = 0
-        while i < len(msg_list):
-            msg = msg_list[i]
-            role = msg.get("role", "user")
-            content = msg.get("content", "")
-
-            if role == "system":
-                system_instruction = (system_instruction + "\n\n" + content) if system_instruction else content
-                i += 1
-            elif role == "tool":
-                # Gemini requires ALL tool responses for a given model turn to be grouped
-                # into a single Content with multiple FunctionResponse parts.
-                # Consecutive role="tool" messages correspond to one model turn's tool calls.
-                parts = []
-                while i < len(msg_list) and msg_list[i].get("role") == "tool":
-                    tool_msg = msg_list[i]
-                    tool_content = tool_msg.get("content", "")
-                    parts.append(
-                        genai_types.Part(
-                            function_response=genai_types.FunctionResponse(
-                                name=tool_msg.get("name", ""),
-                                response={"result": tool_content},
-                            )
-                        )
-                    )
-                    i += 1
-                gemini_contents.append(genai_types.Content(role="user", parts=parts))
-            elif role == "assistant":
-                tool_calls_in_msg = msg.get("tool_calls", [])
-                if tool_calls_in_msg:
-                    # Convert OpenAI-style tool_calls to Gemini function_call parts
-                    # This is required for proper multi-turn conversation history
-                    parts = []
-                    if content:
-                        parts.append(genai_types.Part(text=content))
-                    for tc in tool_calls_in_msg:
-                        fn = tc.get("function", {})
-                        fn_name = fn.get("name", "")
-                        fn_args_str = fn.get("arguments", "{}")
-                        fn_args = parse_llm_json(fn_args_str)
-                        thought_signature = tc.get("thought_signature")
-                        fc_kwargs: dict[str, Any] = {"name": fn_name, "args": fn_args}
-                        if thought_signature:
-                            fc_kwargs["thought_signature"] = thought_signature
-                        parts.append(genai_types.Part(function_call=genai_types.FunctionCall(**fc_kwargs)))
-                    gemini_contents.append(genai_types.Content(role="model", parts=parts))
-                else:
-                    gemini_contents.append(genai_types.Content(role="model", parts=[genai_types.Part(text=content)]))
-                i += 1
-            else:
-                gemini_contents.append(genai_types.Content(role="user", parts=[genai_types.Part(text=content)]))
-                i += 1
-
-        config_kwargs: dict[str, Any] = {"tools": gemini_tools}
-        if system_instruction:
-            config_kwargs["system_instruction"] = system_instruction
-        if temperature is not None:
-            config_kwargs["temperature"] = temperature
-
-        # Map OpenAI-style tool_choice to Gemini FunctionCallingConfig
-        if tool_choice == "required":
-            config_kwargs["tool_config"] = genai_types.ToolConfig(
-                function_calling_config=genai_types.FunctionCallingConfig(
-                    mode="ANY",
-                )
-            )
-        elif isinstance(tool_choice, dict) and tool_choice.get("type") == "function":
-            fn_name = tool_choice.get("function", {}).get("name")
-            if fn_name:
-                config_kwargs["tool_config"] = genai_types.ToolConfig(
-                    function_calling_config=genai_types.FunctionCallingConfig(
-                        mode="ANY",
-                        allowed_function_names=[fn_name],
-                    )
-                )
-        elif tool_choice == "none":
-            config_kwargs["tool_config"] = genai_types.ToolConfig(
-                function_calling_config=genai_types.FunctionCallingConfig(mode="NONE")
-            )
-        # "auto" is the default (no tool_config needed)
-
-        # Apply safety settings: context var (per-request bank override) takes precedence over instance default
-        effective_safety_settings = _safety_settings_ctx.get()
-        if effective_safety_settings is None:
-            effective_safety_settings = self._safety_settings
-        if effective_safety_settings is not None:
-            config_kwargs["safety_settings"] = [
-                genai_types.SafetySetting(category=s["category"], threshold=s["threshold"])
-                for s in effective_safety_settings
-            ]
-
-        config = genai_types.GenerateContentConfig(**config_kwargs)
-
-        last_exception = None
-        for attempt in range(max_retries + 1):
-            try:
-                response = await asyncio.wait_for(
-                    self._client.aio.models.generate_content(
-                        model=self.model,
-                        contents=gemini_contents,
-                        config=config,
-                    ),
-                    timeout=90.0,  # Safety net for network hangs; valid slow responses are <90s
-                )
-
-                # Extract content and tool calls
-                content = None
-                tool_calls: list[LLMToolCall] = []
-
-                if response.candidates and response.candidates[0].content:
-                    parts = response.candidates[0].content.parts
-                    if parts:
-                        for part in parts:
-                            if hasattr(part, "text") and part.text:
-                                content = part.text
-                            if hasattr(part, "function_call") and part.function_call:
-                                fc = part.function_call
-                                thought_signature = getattr(fc, "thought_signature", None)
-                                tool_calls.append(
-                                    LLMToolCall(
-                                        id=f"gemini_{len(tool_calls)}",
-                                        name=fc.name,
-                                        arguments=dict(fc.args) if fc.args else {},
-                                        thought_signature=thought_signature,
-                                    )
-                                )
-
-                finish_reason = "tool_calls" if tool_calls else "stop"
-
-                # Extract token usage
-                input_tokens = 0
-                output_tokens = 0
-                if response.usage_metadata:
-                    input_tokens = response.usage_metadata.prompt_token_count or 0
-                    output_tokens = response.usage_metadata.candidates_token_count or 0
-
-                # Record metrics
-                duration = time.time() - start_time
-                metrics = get_metrics_collector()
-                metrics.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    duration=duration,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    success=True,
-                )
-
-                # Record OpenTelemetry span
-                from hindsight_api.tracing import get_span_recorder
-
-                span_recorder = get_span_recorder()
-                # Convert LLMToolCall objects to dicts for span recording
-                tool_calls_dict = (
-                    [{"id": tc.id, "name": tc.name, "arguments": tc.arguments} for tc in tool_calls]
-                    if tool_calls
-                    else None
-                )
-                span_recorder.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    messages=messages,
-                    response_content=content,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    duration=duration,
-                    finish_reason=finish_reason,
-                    error=None,
-                    tool_calls=tool_calls_dict,
-                )
-
-                return LLMToolCallResult(
-                    content=content,
-                    tool_calls=tool_calls,
-                    finish_reason=finish_reason,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                )
-
-            except genai_errors.APIError as e:
-                # Fast fail on auth errors
-                if e.code in (401, 403):
-                    logger.error(f"Gemini auth error (HTTP {e.code}), not retrying: {str(e)}")
-                    raise
-
-                # Retry on retryable errors
-                last_exception = e
-                if attempt < max_retries:
-                    backoff = min(initial_backoff * (2**attempt), max_backoff)
-                    await asyncio.sleep(backoff)
-                    continue
-                raise
-
-            except Exception as e:
-                logger.error(f"Unexpected error during Gemini tool call: {type(e).__name__}: {str(e)}")
-                raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("Gemini tool call failed")
-
-    async def cleanup(self) -> None:
-        """Clean up resources (close connections, etc.)."""
-        # Gemini client doesn't require explicit cleanup
-        pass

hindsight-api-slim/hindsight_api/engine/providers/mock_llm.py

@@ -1,323 +0,0 @@
-"""
-Mock LLM provider for testing.
-
-This provider allows tests to record LLM calls and return configurable mock responses
-without making actual API calls to external LLM services.
-"""
-
-import logging
-from collections.abc import Callable
-from typing import Any
-
-from ..llm_interface import LLMInterface
-from ..response_models import LLMToolCall, LLMToolCallResult, TokenUsage
-
-logger = logging.getLogger(__name__)
-
-
-class MockLLM(LLMInterface):
-    """
-    Mock LLM provider for testing.
-
-    This provider records all calls and returns configurable mock responses,
-    enabling tests to verify LLM interactions without making real API calls.
-
-    Example:
-        # Create mock provider
-        mock_llm = MockLLM(provider="mock", api_key="", base_url="", model="mock-model")
-
-        # Set mock response
-        mock_llm.set_mock_response({"answer": "test"})
-
-        # Make calls
-        result = await mock_llm.call(
-            messages=[{"role": "user", "content": "test"}],
-            response_format=MyResponseModel
-        )
-
-        # Verify calls
-        calls = mock_llm.get_mock_calls()
-        assert len(calls) == 1
-        assert calls[0]["scope"] == "memory"
-    """
-
-    def __init__(
-        self,
-        provider: str,
-        api_key: str,
-        base_url: str,
-        model: str,
-        reasoning_effort: str = "low",
-        **kwargs: Any,
-    ):
-        """
-        Initialize mock LLM provider.
-
-        Args:
-            provider: Provider name (should be "mock").
-            api_key: Not used for mock provider.
-            base_url: Not used for mock provider.
-            model: Model name for tracking.
-            reasoning_effort: Not used for mock provider.
-            **kwargs: Additional parameters (not used).
-        """
-        super().__init__(provider, api_key, base_url, model, reasoning_effort, **kwargs)
-
-        # Storage for test verification
-        self._mock_calls: list[dict] = []
-        self._mock_response: Any = None
-        self._mock_exception: Exception | None = None
-        self._response_callback: Callable[[list[dict], str], Any] | None = None
-
-    async def verify_connection(self) -> None:
-        """
-        Verify mock provider (always succeeds).
-
-        Mock provider doesn't need connection verification since it doesn't
-        make real API calls.
-        """
-        logger.debug("Mock LLM: connection verification (always succeeds)")
-
-    async def call(
-        self,
-        messages: list[dict[str, str]],
-        response_format: Any | None = None,
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "memory",
-        max_retries: int = 10,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 60.0,
-        skip_validation: bool = False,
-        strict_schema: bool = False,
-        return_usage: bool = False,
-    ) -> Any:
-        """
-        Make a mock LLM API call.
-
-        Records the call for test verification and returns the configured mock response.
-
-        Args:
-            messages: List of message dicts with 'role' and 'content'.
-            response_format: Optional Pydantic model for structured output.
-            max_completion_tokens: Not used in mock.
-            temperature: Not used in mock.
-            scope: Scope identifier for tracking.
-            max_retries: Not used in mock.
-            initial_backoff: Not used in mock.
-            max_backoff: Not used in mock.
-            skip_validation: Return raw JSON without Pydantic validation.
-            strict_schema: Not used in mock.
-            return_usage: If True, return tuple (result, TokenUsage) instead of just result.
-
-        Returns:
-            If return_usage=False: Parsed response if response_format is provided, otherwise text content.
-            If return_usage=True: Tuple of (result, TokenUsage) with mock token counts.
-        """
-        # Record the call for test verification
-        call_record = {
-            "provider": self.provider,
-            "model": self.model,
-            "messages": messages,
-            "response_format": response_format.__name__
-            if response_format and hasattr(response_format, "__name__")
-            else str(response_format),
-            "scope": scope,
-        }
-        self._mock_calls.append(call_record)
-        logger.debug(f"Mock LLM call recorded: scope={scope}, model={self.model}")
-
-        # Raise mock exception if configured
-        if self._mock_exception is not None:
-            raise self._mock_exception
-
-        # Record trace span (minimal for mock provider)
-        from hindsight_api.tracing import get_span_recorder
-
-        span_recorder = get_span_recorder()
-        span_recorder.record_llm_call(
-            provider=self.provider,
-            model=self.model,
-            scope=scope,
-            messages=messages,
-            response_content="mock response",
-            input_tokens=10,
-            output_tokens=5,
-            duration=0.001,  # Mock calls are instant
-            finish_reason="stop",
-            error=None,
-        )
-
-        # Return mock response
-        if self._response_callback is not None:
-            result = self._response_callback(messages, scope)
-        elif self._mock_response is not None:
-            result = self._mock_response
-        elif response_format is not None:
-            # Try to create a minimal valid instance of the response format
-            try:
-                # For Pydantic models, try to create with minimal valid data
-                result = {"mock": True}
-            except Exception:
-                result = {"mock": True}
-        else:
-            result = "mock response"
-
-        if return_usage:
-            token_usage = TokenUsage(input_tokens=10, output_tokens=5, total_tokens=15)
-            return result, token_usage
-        return result
-
-    async def call_with_tools(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "tools",
-        max_retries: int = 5,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 30.0,
-        tool_choice: str | dict[str, Any] = "auto",
-    ) -> LLMToolCallResult:
-        """
-        Make a mock LLM API call with tool/function calling support.
-
-        Records the call for test verification and returns the configured mock response.
-
-        Args:
-            messages: List of message dicts. Can include tool results with role='tool'.
-            tools: List of tool definitions in OpenAI format.
-            max_completion_tokens: Not used in mock.
-            temperature: Not used in mock.
-            scope: Scope identifier for tracking.
-            max_retries: Not used in mock.
-            initial_backoff: Not used in mock.
-            max_backoff: Not used in mock.
-            tool_choice: Not used in mock.
-
-        Returns:
-            LLMToolCallResult with content and/or tool_calls.
-        """
-        # Record the call for test verification
-        call_record = {
-            "provider": self.provider,
-            "model": self.model,
-            "messages": messages,
-            "tools": [t.get("function", {}).get("name") for t in tools],
-            "scope": scope,
-        }
-        self._mock_calls.append(call_record)
-
-        # Raise mock exception if configured
-        if self._mock_exception is not None:
-            raise self._mock_exception
-
-        # Record OpenTelemetry span
-        from hindsight_api.tracing import get_span_recorder
-
-        span_recorder = get_span_recorder()
-
-        if self._response_callback is not None:
-            cb_result = self._response_callback(messages, scope)
-            if isinstance(cb_result, LLMToolCallResult):
-                result = cb_result
-            else:
-                result = LLMToolCallResult(
-                    content=str(cb_result) if cb_result is not None else "mock response", finish_reason="stop"
-                )
-        elif self._mock_response is not None:
-            if isinstance(self._mock_response, LLMToolCallResult):
-                result = self._mock_response
-            elif isinstance(self._mock_response, list):
-                # Allow setting just tool calls as a list
-                result = LLMToolCallResult(
-                    tool_calls=[
-                        LLMToolCall(id=f"mock_{i}", name=tc["name"], arguments=tc.get("arguments", {}))
-                        for i, tc in enumerate(self._mock_response)
-                    ],
-                    finish_reason="tool_calls",
-                )
-            else:
-                result = LLMToolCallResult(content="mock response", finish_reason="stop")
-        else:
-            result = LLMToolCallResult(content="mock response", finish_reason="stop")
-
-        # Record span with mock values
-        # Convert LLMToolCall objects to dicts for span recording
-        tool_calls_dict = (
-            [{"id": tc.id, "name": tc.name, "arguments": tc.arguments} for tc in result.tool_calls]
-            if result.tool_calls
-            else None
-        )
-        span_recorder.record_llm_call(
-            provider=self.provider,
-            model=self.model,
-            scope=scope,
-            messages=messages,
-            response_content=result.content,
-            input_tokens=10,  # Mock value
-            output_tokens=5,  # Mock value
-            duration=0.1,  # Mock value
-            finish_reason=result.finish_reason,
-            error=None,
-            tool_calls=tool_calls_dict,
-        )
-
-        return result
-
-    async def cleanup(self) -> None:
-        """Clean up resources (no-op for mock provider)."""
-        pass
-
-    def set_response_callback(self, fn: Callable[[list[dict], str], Any]) -> None:
-        """
-        Set a callback invoked on each call() instead of _mock_response.
-
-        The callback receives (messages, scope) and returns the response.
-        Useful for returning different responses per call (e.g., cycling
-        through a corpus in a benchmark).
-        """
-        self._response_callback = fn
-
-    def set_mock_response(self, response: Any) -> None:
-        """
-        Set the response to return from mock calls.
-
-        Args:
-            response: The response to return. Can be:
-                - A dict/Pydantic model for regular calls
-                - An LLMToolCallResult for tool calls
-                - A list of tool call dicts for tool calls
-                - Any other value to return as-is
-        """
-        self._mock_response = response
-
-    def set_mock_exception(self, exception: Exception) -> None:
-        """
-        Set an exception to raise from mock calls.
-
-        Args:
-            exception: The exception to raise on the next call.
-                      After raising, the exception is cleared.
-        """
-        self._mock_exception = exception
-
-    def get_mock_calls(self) -> list[dict]:
-        """
-        Get the list of recorded mock calls.
-
-        Returns:
-            List of call records, each containing:
-                - provider: Provider name
-                - model: Model name
-                - messages: Messages sent
-                - response_format/tools: Format or tools used
-                - scope: Call scope
-        """
-        return self._mock_calls
-
-    def clear_mock_calls(self) -> None:
-        """Clear the recorded mock calls and any set exception."""
-        self._mock_calls = []
-        self._mock_exception = None

hindsight-api-slim/hindsight_api/engine/providers/openai_compatible_llm.py

@@ -1,947 +0,0 @@
-"""
-OpenAI-compatible LLM provider supporting OpenAI, Groq, Ollama, LMStudio, and MiniMax.
-
-This provider handles all OpenAI API-compatible models including:
-- OpenAI: GPT-4, GPT-4o, GPT-5, o1, o3 (reasoning models)
-- Groq: Fast inference with seed control and service tiers
-- Ollama: Local models with native streaming API support
-- LMStudio: Local models with OpenAI-compatible API
-- MiniMax: MiniMax-M2.7 models with 1M context window
-
-Features:
-- Reasoning models with extended thinking (o1, o3, GPT-5 families)
-- Strict JSON schema enforcement (OpenAI)
-- Provider-specific parameters (Groq seed, service tier)
-- Native Ollama streaming for better structured output
-- Automatic token limit handling per model family
-"""
-
-import asyncio
-import io
-import json
-import logging
-import os
-import re
-import time
-from typing import Any
-
-import httpx
-from openai import APIConnectionError, APIStatusError, AsyncOpenAI, LengthFinishReasonError
-
-from hindsight_api.config import DEFAULT_LLM_TIMEOUT, ENV_LLM_TIMEOUT
-from hindsight_api.engine.llm_interface import LLMInterface, OutputTooLongError
-from hindsight_api.engine.response_models import LLMToolCall, LLMToolCallResult, TokenUsage
-from hindsight_api.metrics import get_metrics_collector
-
-logger = logging.getLogger(__name__)
-
-# Seed applied to every Groq request for deterministic behavior
-DEFAULT_LLM_SEED = 4242
-
-
-class OpenAICompatibleLLM(LLMInterface):
-    """
-    LLM provider for OpenAI-compatible APIs.
-
-    Supports:
-    - OpenAI: Standard models (GPT-4, GPT-4o) and reasoning models (o1, o3, GPT-5)
-    - Groq: Fast inference with seed control and service tiers
-    - Ollama: Local models with native streaming API for better structured output
-    - LMStudio: Local models with OpenAI-compatible API
-    - MiniMax: MiniMax-M2.7 models via OpenAI-compatible API (https://api.minimax.io/v1)
-    """
-
-    def __init__(
-        self,
-        provider: str,
-        api_key: str,
-        base_url: str,
-        model: str,
-        reasoning_effort: str = "low",
-        timeout: float | None = None,
-        groq_service_tier: str | None = None,
-        **kwargs: Any,
-    ):
-        """
-        Initialize OpenAI-compatible LLM provider.
-
-        Args:
-            provider: Provider name ("openai", "groq", "ollama", "lmstudio").
-            api_key: API key (optional for ollama/lmstudio).
-            base_url: Base URL for the API (uses defaults for groq/ollama/lmstudio if empty).
-            model: Model name.
-            reasoning_effort: Reasoning effort level for supported models ("low", "medium", "high").
-            timeout: Request timeout in seconds (uses env var or 300s default).
-            groq_service_tier: Groq service tier ("on_demand", "flex", "auto").
-            **kwargs: Additional provider-specific parameters.
-        """
-        super().__init__(provider, api_key, base_url, model, reasoning_effort, **kwargs)
-
-        # Validate provider
-        valid_providers = ["openai", "groq", "ollama", "lmstudio", "minimax"]
-        if self.provider not in valid_providers:
-            raise ValueError(f"OpenAICompatibleLLM only supports: {', '.join(valid_providers)}. Got: {self.provider}")
-
-        # Set default base URLs
-        if not self.base_url:
-            if self.provider == "groq":
-                self.base_url = "https://api.groq.com/openai/v1"
-            elif self.provider == "ollama":
-                self.base_url = "http://localhost:11434/v1"
-            elif self.provider == "lmstudio":
-                self.base_url = "http://localhost:1234/v1"
-            elif self.provider == "minimax":
-                self.base_url = "https://api.minimax.io/v1"
-
-        # For ollama/lmstudio, use dummy key if not provided
-        if self.provider in ("ollama", "lmstudio") and not self.api_key:
-            self.api_key = "local"
-
-        # Validate API key for cloud providers
-        if self.provider in ("openai", "groq", "minimax") and not self.api_key:
-            raise ValueError(f"API key is required for {self.provider}")
-
-        # Service tier configuration (from config, not env vars)
-        self.groq_service_tier = groq_service_tier
-        self.openai_service_tier = kwargs.get("openai_service_tier")
-
-        # Get timeout config
-        self.timeout = timeout or float(os.getenv(ENV_LLM_TIMEOUT, str(DEFAULT_LLM_TIMEOUT)))
-
-        # Create OpenAI client
-        client_kwargs: dict[str, Any] = {"api_key": self.api_key, "max_retries": 0}
-        if self.base_url:
-            client_kwargs["base_url"] = self.base_url
-        if self.timeout:
-            client_kwargs["timeout"] = self.timeout
-
-        self._client = AsyncOpenAI(**client_kwargs)
-        logger.info(
-            f"OpenAI-compatible client initialized: provider={self.provider}, model={self.model}, "
-            f"base_url={self.base_url or 'default'}"
-        )
-
-    async def verify_connection(self) -> None:
-        """
-        Verify that the provider is configured correctly by making a simple test call.
-
-        Raises:
-            RuntimeError: If the connection test fails.
-        """
-        try:
-            logger.info(f"Verifying connection: {self.provider}/{self.model}")
-            await self.call(
-                messages=[{"role": "user", "content": "Say 'ok'"}],
-                max_completion_tokens=100,
-                max_retries=2,
-                initial_backoff=0.5,
-                max_backoff=2.0,
-                scope="verification",
-            )
-            logger.info(f"Connection verified: {self.provider}/{self.model}")
-        except Exception as e:
-            raise RuntimeError(f"Connection verification failed for {self.provider}/{self.model}: {e}") from e
-
-    def _supports_reasoning_model(self) -> bool:
-        """Check if the current model is a reasoning model (o1, o3, GPT-5, DeepSeek)."""
-        model_lower = self.model.lower()
-        return any(x in model_lower for x in ["gpt-5", "o1", "o3", "deepseek"])
-
-    def _get_max_reasoning_tokens(self) -> int | None:
-        """Get max reasoning tokens for reasoning models."""
-        model_lower = self.model.lower()
-
-        # GPT-4 and GPT-4.1 models have different caps
-        if any(x in model_lower for x in ["gpt-4.1", "gpt-4-"]):
-            return 32000
-        elif "gpt-4o" in model_lower:
-            return 16384
-
-        return None
-
-    async def call(
-        self,
-        messages: list[dict[str, str]],
-        response_format: Any | None = None,
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "memory",
-        max_retries: int = 10,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 60.0,
-        skip_validation: bool = False,
-        strict_schema: bool = False,
-        return_usage: bool = False,
-    ) -> Any:
-        """
-        Make an LLM API call with retry logic.
-
-        Args:
-            messages: List of message dicts with 'role' and 'content'.
-            response_format: Optional Pydantic model for structured output.
-            max_completion_tokens: Maximum tokens in response.
-            temperature: Sampling temperature (0.0-2.0).
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            skip_validation: Return raw JSON without Pydantic validation.
-            strict_schema: Use strict JSON schema enforcement (OpenAI only).
-            return_usage: If True, return tuple (result, TokenUsage) instead of just result.
-
-        Returns:
-            If return_usage=False: Parsed response if response_format is provided, otherwise text content.
-            If return_usage=True: Tuple of (result, TokenUsage) with token counts.
-
-        Raises:
-            OutputTooLongError: If output exceeds token limits.
-            Exception: Re-raises API errors after retries exhausted.
-        """
-        # Handle Ollama with native API for structured output (better schema enforcement)
-        if self.provider == "ollama" and response_format is not None:
-            return await self._call_ollama_native(
-                messages=messages,
-                response_format=response_format,
-                max_completion_tokens=max_completion_tokens,
-                temperature=temperature,
-                max_retries=max_retries,
-                initial_backoff=initial_backoff,
-                max_backoff=max_backoff,
-                skip_validation=skip_validation,
-                scope=scope,
-                return_usage=return_usage,
-            )
-
-        start_time = time.time()
-
-        # Build call parameters
-        call_params: dict[str, Any] = {
-            "model": self.model,
-            "messages": messages,
-        }
-
-        # Check if model supports reasoning parameter
-        is_reasoning_model = self._supports_reasoning_model()
-
-        # Apply model-specific token limits
-        if max_completion_tokens is not None:
-            max_tokens_cap = self._get_max_reasoning_tokens()
-            if max_tokens_cap and max_completion_tokens > max_tokens_cap:
-                max_completion_tokens = max_tokens_cap
-            # For reasoning models, enforce minimum to ensure space for reasoning + output
-            if is_reasoning_model and max_completion_tokens < 16000:
-                max_completion_tokens = 16000
-            call_params["max_completion_tokens"] = max_completion_tokens
-
-        # Temperature - reasoning models don't support custom temperature
-        if temperature is not None and not is_reasoning_model:
-            # MiniMax requires temperature in (0.0, 1.0] — clamp accordingly
-            if self.provider == "minimax":
-                temperature = max(0.01, min(temperature, 1.0))
-            call_params["temperature"] = temperature
-
-        # Set reasoning_effort for reasoning models
-        if is_reasoning_model:
-            call_params["reasoning_effort"] = self.reasoning_effort
-
-        # Provider-specific parameters
-        if self.provider == "groq":
-            call_params["seed"] = DEFAULT_LLM_SEED
-            extra_body: dict[str, Any] = {}
-            # Add service_tier if configured
-            if self.groq_service_tier:
-                extra_body["service_tier"] = self.groq_service_tier
-            # Add reasoning parameters for reasoning models
-            if is_reasoning_model:
-                extra_body["include_reasoning"] = False
-            if extra_body:
-                call_params["extra_body"] = extra_body
-
-        # Prepare response format ONCE before retry loop
-        if response_format is not None:
-            schema = None
-            if hasattr(response_format, "model_json_schema"):
-                schema = response_format.model_json_schema()
-
-            if strict_schema and schema is not None:
-                # Use OpenAI's strict JSON schema enforcement
-                call_params["response_format"] = {
-                    "type": "json_schema",
-                    "json_schema": {
-                        "name": "response",
-                        "strict": True,
-                        "schema": schema,
-                    },
-                }
-            else:
-                # Soft enforcement: add schema to prompt and use json_object mode
-                if schema is not None:
-                    schema_msg = (
-                        f"\n\nYou must respond with valid JSON matching this schema:\n{json.dumps(schema, indent=2)}"
-                    )
-
-                    if call_params["messages"] and call_params["messages"][0].get("role") == "system":
-                        first_msg = call_params["messages"][0]
-                        if isinstance(first_msg, dict) and isinstance(first_msg.get("content"), str):
-                            first_msg["content"] += schema_msg
-                    elif call_params["messages"]:
-                        first_msg = call_params["messages"][0]
-                        if isinstance(first_msg, dict) and isinstance(first_msg.get("content"), str):
-                            first_msg["content"] = schema_msg + "\n\n" + first_msg["content"]
-                if self.provider not in ("lmstudio", "ollama"):
-                    # LM Studio and Ollama don't support json_object response format reliably
-                    call_params["response_format"] = {"type": "json_object"}
-
-        last_exception = None
-
-        for attempt in range(max_retries + 1):
-            try:
-                if response_format is not None:
-                    response = await self._client.chat.completions.create(**call_params)
-
-                    content = response.choices[0].message.content
-
-                    # Strip reasoning model thinking tags
-                    # Supports: <think>, <thinking>, <reasoning>, |startthink|/|endthink|
-                    if content:
-                        original_len = len(content)
-                        content = re.sub(r"<think>.*?</think>", "", content, flags=re.DOTALL)
-                        content = re.sub(r"<thinking>.*?</thinking>", "", content, flags=re.DOTALL)
-                        content = re.sub(r"<reasoning>.*?</reasoning>", "", content, flags=re.DOTALL)
-                        content = re.sub(r"\|startthink\|.*?\|endthink\|", "", content, flags=re.DOTALL)
-                        content = content.strip()
-                        if len(content) < original_len:
-                            logger.debug(f"Stripped {original_len - len(content)} chars of reasoning tokens")
-
-                    # For local models, they may wrap JSON in markdown code blocks
-                    if self.provider in ("lmstudio", "ollama"):
-                        clean_content = content
-                        if "```json" in content:
-                            clean_content = content.split("```json")[1].split("```")[0].strip()
-                        elif "```" in content:
-                            clean_content = content.split("```")[1].split("```")[0].strip()
-                        try:
-                            json_data = json.loads(clean_content)
-                        except json.JSONDecodeError:
-                            # Fallback to parsing raw content
-                            json_data = json.loads(content)
-                    else:
-                        # Log raw LLM response for debugging JSON parse issues
-                        try:
-                            json_data = json.loads(content)
-                        except json.JSONDecodeError as json_err:
-                            # Truncate content for logging
-                            content_preview = content[:500] if content else "<empty>"
-                            if content and len(content) > 700:
-                                content_preview = f"{content[:500]}...TRUNCATED...{content[-200:]}"
-                            logger.warning(
-                                f"JSON parse error from LLM response (attempt {attempt + 1}/{max_retries + 1}): {json_err}\n"
-                                f"  Model: {self.provider}/{self.model}\n"
-                                f"  Content length: {len(content) if content else 0} chars\n"
-                                f"  Content preview: {content_preview!r}\n"
-                                f"  Finish reason: {response.choices[0].finish_reason if response.choices else 'unknown'}"
-                            )
-                            # Retry on JSON parse errors
-                            if attempt < max_retries:
-                                backoff = min(initial_backoff * (2**attempt), max_backoff)
-                                await asyncio.sleep(backoff)
-                                last_exception = json_err
-                                continue
-                            else:
-                                logger.error(f"JSON parse error after {max_retries + 1} attempts, giving up")
-                                raise
-
-                    if skip_validation:
-                        result = json_data
-                    else:
-                        result = response_format.model_validate(json_data)
-                else:
-                    response = await self._client.chat.completions.create(**call_params)
-                    result = response.choices[0].message.content
-
-                # Record token usage metrics
-                duration = time.time() - start_time
-                usage = response.usage
-                input_tokens = usage.prompt_tokens or 0 if usage else 0
-                output_tokens = usage.completion_tokens or 0 if usage else 0
-                total_tokens = usage.total_tokens or 0 if usage else 0
-
-                # Record LLM metrics
-                metrics = get_metrics_collector()
-                metrics.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    duration=duration,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    success=True,
-                )
-
-                # Record trace span
-                from hindsight_api.tracing import _serialize_for_span, get_span_recorder
-
-                finish_reason = response.choices[0].finish_reason if response.choices else None
-                span_recorder = get_span_recorder()
-                span_recorder.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    messages=messages,
-                    response_content=_serialize_for_span(result),
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    duration=duration,
-                    finish_reason=finish_reason,
-                    error=None,
-                )
-
-                # Log slow calls
-                if duration > 10.0 and usage:
-                    ratio = max(1, output_tokens) / max(1, input_tokens)
-                    cached_tokens = 0
-                    if hasattr(usage, "prompt_tokens_details") and usage.prompt_tokens_details:
-                        cached_tokens = getattr(usage.prompt_tokens_details, "cached_tokens", 0) or 0
-                    cache_info = f", cached_tokens={cached_tokens}" if cached_tokens > 0 else ""
-                    logger.info(
-                        f"slow llm call: scope={scope}, model={self.provider}/{self.model}, "
-                        f"input_tokens={input_tokens}, output_tokens={output_tokens}, "
-                        f"total_tokens={total_tokens}{cache_info}, time={duration:.3f}s, ratio out/in={ratio:.2f}"
-                    )
-
-                if return_usage:
-                    token_usage = TokenUsage(
-                        input_tokens=input_tokens,
-                        output_tokens=output_tokens,
-                        total_tokens=total_tokens,
-                    )
-                    return result, token_usage
-                return result
-
-            except LengthFinishReasonError as e:
-                logger.warning(f"LLM output exceeded token limits: {str(e)}")
-                raise OutputTooLongError(
-                    "LLM output exceeded token limits. Input may need to be split into smaller chunks."
-                ) from e
-
-            except APIConnectionError as e:
-                last_exception = e
-                status_code = getattr(e, "status_code", None) or getattr(
-                    getattr(e, "response", None), "status_code", None
-                )
-                logger.warning(f"APIConnectionError (HTTP {status_code}), attempt {attempt + 1}: {str(e)[:200]}")
-                if attempt < max_retries:
-                    backoff = min(initial_backoff * (2**attempt), max_backoff)
-                    await asyncio.sleep(backoff)
-                    continue
-                else:
-                    logger.error(f"Connection error after {max_retries + 1} attempts: {str(e)}")
-                    raise
-
-            except APIStatusError as e:
-                # Fast fail only on 401 (unauthorized) and 403 (forbidden)
-                if e.status_code in (401, 403):
-                    logger.error(f"Auth error (HTTP {e.status_code}), not retrying: {str(e)}")
-                    raise
-
-                # Handle tool_use_failed error - model outputted in tool call format
-                if e.status_code == 400 and response_format is not None:
-                    try:
-                        error_body = e.body if hasattr(e, "body") else {}
-                        if isinstance(error_body, dict):
-                            error_info: dict[str, Any] = error_body.get("error") or {}
-                            if error_info.get("code") == "tool_use_failed":
-                                failed_gen = error_info.get("failed_generation", "")
-                                if failed_gen:
-                                    # Parse tool call format and convert to expected format
-                                    tool_call = json.loads(failed_gen)
-                                    tool_name = tool_call.get("name", "")
-                                    tool_args = tool_call.get("arguments", {})
-                                    converted = {"actions": [{"tool": tool_name, **tool_args}]}
-                                    if skip_validation:
-                                        result = converted
-                                    else:
-                                        result = response_format.model_validate(converted)
-
-                                    # Record metrics
-                                    duration = time.time() - start_time
-                                    metrics = get_metrics_collector()
-                                    metrics.record_llm_call(
-                                        provider=self.provider,
-                                        model=self.model,
-                                        scope=scope,
-                                        duration=duration,
-                                        input_tokens=0,
-                                        output_tokens=0,
-                                        success=True,
-                                    )
-                                    if return_usage:
-                                        return result, TokenUsage(input_tokens=0, output_tokens=0, total_tokens=0)
-                                    return result
-                    except (json.JSONDecodeError, KeyError, TypeError):
-                        pass  # Failed to parse tool_use_failed, continue with normal retry
-
-                last_exception = e
-                if attempt < max_retries:
-                    backoff = min(initial_backoff * (2**attempt), max_backoff)
-                    jitter = backoff * 0.2 * (2 * (time.time() % 1) - 1)
-                    sleep_time = backoff + jitter
-                    await asyncio.sleep(sleep_time)
-                else:
-                    logger.error(f"API error after {max_retries + 1} attempts: {str(e)}")
-                    raise
-
-            except Exception:
-                raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("LLM call failed after all retries with no exception captured")
-
-    async def call_with_tools(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "tools",
-        max_retries: int = 5,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 30.0,
-        tool_choice: str | dict[str, Any] = "auto",
-    ) -> LLMToolCallResult:
-        """
-        Make an LLM API call with tool/function calling support.
-
-        Args:
-            messages: List of message dicts. Can include tool results with role='tool'.
-            tools: List of tool definitions in OpenAI format.
-            max_completion_tokens: Maximum tokens in response.
-            temperature: Sampling temperature (0.0-2.0).
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            tool_choice: How to choose tools - "auto", "none", "required", or specific function.
-
-        Returns:
-            LLMToolCallResult with content and/or tool_calls.
-        """
-        start_time = time.time()
-
-        # Normalize named tool_choice dicts to "required" + filter tools.
-        # Some providers (e.g. LM Studio, Ollama) reject the OpenAI named format
-        # {"type": "function", "function": {"name": "..."}}.  The semantics are
-        # identical to tool_choice="required" with the tools list restricted to
-        # just the requested tool, so we apply that transformation universally.
-        if isinstance(tool_choice, dict) and tool_choice.get("type") == "function":
-            forced_name = tool_choice.get("function", {}).get("name")
-            if forced_name:
-                filtered = [t for t in tools if t.get("function", {}).get("name") == forced_name]
-                if filtered:
-                    tools = filtered
-                tool_choice = "required"
-
-        # Build call parameters
-        call_params: dict[str, Any] = {
-            "model": self.model,
-            "messages": messages,
-            "tools": tools,
-            "tool_choice": tool_choice,
-        }
-
-        if max_completion_tokens is not None:
-            call_params["max_completion_tokens"] = max_completion_tokens
-        if temperature is not None:
-            # MiniMax requires temperature in (0.0, 1.0] — clamp accordingly
-            if self.provider == "minimax":
-                temperature = max(0.01, min(temperature, 1.0))
-            call_params["temperature"] = temperature
-
-        # Provider-specific parameters
-        if self.provider == "groq":
-            call_params["seed"] = DEFAULT_LLM_SEED
-
-        last_exception = None
-
-        for attempt in range(max_retries + 1):
-            try:
-                response = await self._client.chat.completions.create(**call_params)
-
-                message = response.choices[0].message
-                finish_reason = response.choices[0].finish_reason
-
-                # Extract tool calls if present
-                tool_calls: list[LLMToolCall] = []
-                if message.tool_calls:
-                    for tc in message.tool_calls:
-                        try:
-                            args = json.loads(tc.function.arguments) if tc.function.arguments else {}
-                        except json.JSONDecodeError:
-                            args = {"_raw": tc.function.arguments}
-                        tool_calls.append(LLMToolCall(id=tc.id, name=tc.function.name, arguments=args))
-
-                content = message.content
-
-                # Record metrics
-                duration = time.time() - start_time
-                usage = response.usage
-                input_tokens = usage.prompt_tokens or 0 if usage else 0
-                output_tokens = usage.completion_tokens or 0 if usage else 0
-
-                metrics = get_metrics_collector()
-                metrics.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    duration=duration,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    success=True,
-                )
-
-                # Record OpenTelemetry span
-                from hindsight_api.tracing import get_span_recorder
-
-                span_recorder = get_span_recorder()
-                # Convert LLMToolCall objects to dicts for span recording
-                tool_calls_dict = (
-                    [{"id": tc.id, "name": tc.name, "arguments": tc.arguments} for tc in tool_calls]
-                    if tool_calls
-                    else None
-                )
-                span_recorder.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    messages=messages,
-                    response_content=content,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    duration=duration,
-                    finish_reason=finish_reason,
-                    error=None,
-                    tool_calls=tool_calls_dict,
-                )
-
-                return LLMToolCallResult(
-                    content=content,
-                    tool_calls=tool_calls,
-                    finish_reason=finish_reason,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                )
-
-            except APIConnectionError as e:
-                last_exception = e
-                if attempt < max_retries:
-                    await asyncio.sleep(min(initial_backoff * (2**attempt), max_backoff))
-                    continue
-                raise
-
-            except APIStatusError as e:
-                if e.status_code in (401, 403):
-                    raise
-                last_exception = e
-                if attempt < max_retries:
-                    await asyncio.sleep(min(initial_backoff * (2**attempt), max_backoff))
-                    continue
-                raise
-
-            except Exception:
-                raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("Tool call failed after all retries")
-
-    async def _call_ollama_native(
-        self,
-        messages: list[dict[str, str]],
-        response_format: Any,
-        max_completion_tokens: int | None,
-        temperature: float | None,
-        max_retries: int,
-        initial_backoff: float,
-        max_backoff: float,
-        skip_validation: bool,
-        scope: str = "memory",
-        return_usage: bool = False,
-    ) -> Any:
-        """
-        Call Ollama using native API with JSON schema enforcement.
-
-        Ollama's native API supports passing a full JSON schema in the 'format' parameter,
-        which provides better structured output control than the OpenAI-compatible API.
-        """
-        start_time = time.time()
-
-        # Get the JSON schema from the Pydantic model
-        schema = response_format.model_json_schema() if hasattr(response_format, "model_json_schema") else None
-
-        # Build the base URL for Ollama's native API
-        # Default OpenAI-compatible URL is http://localhost:11434/v1
-        # Native API is at http://localhost:11434/api/chat
-        base_url = self.base_url or "http://localhost:11434/v1"
-        if base_url.endswith("/v1"):
-            native_url = base_url[:-3] + "/api/chat"
-        else:
-            native_url = base_url.rstrip("/") + "/api/chat"
-
-        # Build request payload
-        payload: dict[str, Any] = {
-            "model": self.model,
-            "messages": messages,
-            "stream": False,
-        }
-
-        # Add schema as format parameter for structured output
-        if schema:
-            payload["format"] = schema
-
-        # Add optional parameters with optimized defaults for Ollama
-        options: dict[str, Any] = {
-            "num_ctx": 16384,  # 16k context window for larger prompts
-            "num_batch": 512,  # Optimal batch size for prompt processing
-        }
-        if max_completion_tokens:
-            options["num_predict"] = max_completion_tokens
-        if temperature is not None:
-            options["temperature"] = temperature
-        payload["options"] = options
-
-        last_exception = None
-
-        async with httpx.AsyncClient(timeout=300.0) as client:
-            for attempt in range(max_retries + 1):
-                try:
-                    response = await client.post(native_url, json=payload)
-                    response.raise_for_status()
-
-                    result = response.json()
-                    content = result.get("message", {}).get("content", "")
-
-                    # Parse JSON response
-                    try:
-                        json_data = json.loads(content)
-                    except json.JSONDecodeError as json_err:
-                        content_preview = content[:500] if content else "<empty>"
-                        if content and len(content) > 700:
-                            content_preview = f"{content[:500]}...TRUNCATED...{content[-200:]}"
-                        logger.warning(
-                            f"Ollama JSON parse error (attempt {attempt + 1}/{max_retries + 1}): {json_err}\n"
-                            f"  Model: ollama/{self.model}\n"
-                            f"  Content length: {len(content) if content else 0} chars\n"
-                            f"  Content preview: {content_preview!r}"
-                        )
-                        if attempt < max_retries:
-                            backoff = min(initial_backoff * (2**attempt), max_backoff)
-                            await asyncio.sleep(backoff)
-                            last_exception = json_err
-                            continue
-                        else:
-                            raise
-
-                    # Extract token usage from Ollama response
-                    duration = time.time() - start_time
-                    input_tokens = result.get("prompt_eval_count", 0) or 0
-                    output_tokens = result.get("eval_count", 0) or 0
-                    total_tokens = input_tokens + output_tokens
-
-                    # Record LLM metrics
-                    metrics = get_metrics_collector()
-                    metrics.record_llm_call(
-                        provider=self.provider,
-                        model=self.model,
-                        scope=scope,
-                        duration=duration,
-                        input_tokens=input_tokens,
-                        output_tokens=output_tokens,
-                        success=True,
-                    )
-
-                    # Validate against Pydantic model or return raw JSON
-                    if skip_validation:
-                        validated_result = json_data
-                    else:
-                        validated_result = response_format.model_validate(json_data)
-
-                    if return_usage:
-                        token_usage = TokenUsage(
-                            input_tokens=input_tokens,
-                            output_tokens=output_tokens,
-                            total_tokens=total_tokens,
-                        )
-                        return validated_result, token_usage
-                    return validated_result
-
-                except httpx.HTTPStatusError as e:
-                    last_exception = e
-                    if attempt < max_retries:
-                        logger.warning(
-                            f"Ollama HTTP error (attempt {attempt + 1}/{max_retries + 1}): {e.response.status_code}"
-                        )
-                        backoff = min(initial_backoff * (2**attempt), max_backoff)
-                        await asyncio.sleep(backoff)
-                        continue
-                    else:
-                        logger.error(f"Ollama HTTP error after {max_retries + 1} attempts: {e}")
-                        raise
-
-                except httpx.RequestError as e:
-                    last_exception = e
-                    if attempt < max_retries:
-                        logger.warning(f"Ollama connection error (attempt {attempt + 1}/{max_retries + 1}): {e}")
-                        backoff = min(initial_backoff * (2**attempt), max_backoff)
-                        await asyncio.sleep(backoff)
-                        continue
-                    else:
-                        logger.error(f"Ollama connection error after {max_retries + 1} attempts: {e}")
-                        raise
-
-                except Exception as e:
-                    logger.error(f"Unexpected error during Ollama call: {type(e).__name__}: {e}")
-                    raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("Ollama call failed after all retries")
-
-    async def supports_batch_api(self) -> bool:
-        """Check if this provider supports batch API operations."""
-        # Only OpenAI and Groq support batch API
-        return self.provider in ("openai", "groq")
-
-    async def submit_batch(
-        self,
-        requests: list[dict[str, Any]],
-        endpoint: str = "/v1/chat/completions",
-        completion_window: str = "24h",
-    ) -> dict[str, Any]:
-        """
-        Submit a batch of requests to OpenAI/Groq Batch API.
-
-        Args:
-            requests: List of request dicts with custom_id, method, url, body
-            endpoint: API endpoint (e.g., "/v1/chat/completions")
-            completion_window: Completion window (e.g., "24h")
-
-        Returns:
-            Dict with batch metadata including batch_id
-
-        Raises:
-            NotImplementedError: If provider doesn't support batch API
-        """
-        if not await self.supports_batch_api():
-            raise NotImplementedError(f"Batch API not supported for provider: {self.provider}")
-
-        logger.info(f"Submitting batch with {len(requests)} requests to {self.provider}")
-
-        # Format requests as JSONL
-        jsonl_content = "\n".join(json.dumps(req) for req in requests)
-
-        # Upload file to provider (wrap in BytesIO with filename)
-        file_bytes = io.BytesIO(jsonl_content.encode("utf-8"))
-        file_bytes.name = "batch_input.jsonl"  # OpenAI SDK needs a filename
-
-        file_response = await self._client.files.create(
-            file=file_bytes,
-            purpose="batch",
-        )
-
-        logger.debug(f"Uploaded batch file: {file_response.id}")
-
-        # Create batch
-        batch_response = await self._client.batches.create(
-            input_file_id=file_response.id,
-            endpoint=endpoint,
-            completion_window=completion_window,
-        )
-
-        logger.info(f"Batch submitted: {batch_response.id}, status={batch_response.status}")
-
-        return {
-            "batch_id": batch_response.id,
-            "status": batch_response.status,
-            "input_file_id": file_response.id,
-            "created_at": batch_response.created_at,
-            "request_count": len(requests),
-        }
-
-    async def get_batch_status(self, batch_id: str) -> dict[str, Any]:
-        """
-        Get the status of a batch job.
-
-        Args:
-            batch_id: Batch identifier
-
-        Returns:
-            Dict with status info (batch_id, status, completed_at, etc.)
-        """
-        if not await self.supports_batch_api():
-            raise NotImplementedError(f"Batch API not supported for provider: {self.provider}")
-
-        batch = await self._client.batches.retrieve(batch_id)
-
-        result = {
-            "batch_id": batch.id,
-            "status": batch.status,
-            "created_at": batch.created_at,
-            "request_counts": {
-                "total": batch.request_counts.total if batch.request_counts else 0,
-                "completed": batch.request_counts.completed if batch.request_counts else 0,
-                "failed": batch.request_counts.failed if batch.request_counts else 0,
-            },
-        }
-
-        if batch.completed_at:
-            result["completed_at"] = batch.completed_at
-        if batch.output_file_id:
-            result["output_file_id"] = batch.output_file_id
-        if batch.error_file_id:
-            result["error_file_id"] = batch.error_file_id
-        if batch.errors:
-            result["errors"] = batch.errors
-
-        return result
-
-    async def retrieve_batch_results(self, batch_id: str) -> list[dict[str, Any]]:
-        """
-        Retrieve completed batch results.
-
-        Args:
-            batch_id: Batch identifier
-
-        Returns:
-            List of result dicts (one per request, matched by custom_id)
-        """
-        if not await self.supports_batch_api():
-            raise NotImplementedError(f"Batch API not supported for provider: {self.provider}")
-
-        # Get batch status
-        batch = await self._client.batches.retrieve(batch_id)
-
-        if batch.status != "completed":
-            raise ValueError(f"Batch {batch_id} is not completed yet (status: {batch.status})")
-
-        if not batch.output_file_id:
-            raise ValueError(f"Batch {batch_id} has no output file")
-
-        # Download results file
-        logger.debug(f"Downloading results for batch {batch_id} from file {batch.output_file_id}")
-        file_content = await self._client.files.content(batch.output_file_id)
-
-        # Parse JSONL results
-        results = []
-        for line in file_content.text.strip().split("\n"):
-            if line:
-                results.append(json.loads(line))
-
-        logger.info(f"Retrieved {len(results)} results for batch {batch_id}")
-
-        return results
-
-    async def cleanup(self) -> None:
-        """Clean up resources (close OpenAI client connections)."""
-        if hasattr(self, "_client") and self._client:
-            await self._client.close()

hindsight-api-slim/hindsight_api/engine/retain/entity_labels.py

@@ -1,194 +0,0 @@
-"""
-Entity labels models and helpers for retain pipeline.
-
-Defines a controlled vocabulary of key:value classification labels
-(e.g., 'pedagogy:scaffolding', 'interest:active') that are extracted
-at retain time and stored as entities.
-"""
-
-from typing import Literal
-
-from pydantic import BaseModel, Field, create_model
-
-
-class LabelValue(BaseModel):
-    """A single allowed value for a label group."""
-
-    value: str
-    description: str = ""
-
-
-class LabelGroup(BaseModel):
-    """A label group (dimension) with its type and allowed values."""
-
-    key: str
-    description: str = ""
-    type: Literal["value", "multi-values", "text"] = "value"
-    optional: bool = True
-    tag: bool = False
-    values: list[LabelValue] = []
-
-
-class EntityLabelsConfig(BaseModel):
-    """Entity labels configuration for a bank (controlled vocabulary)."""
-
-    attributes: list[LabelGroup] = []
-
-
-def parse_entity_labels(raw: dict | list | None) -> EntityLabelsConfig | None:
-    """
-    Parse raw entity labels config into EntityLabelsConfig.
-
-    Accepts:
-    - None → returns None
-    - list → list of attribute dicts (each may use legacy free_values/multi_value or new type field)
-    - dict → {attributes: [...]}
-
-    Legacy migration (backward-compat):
-    - free_values=True          → type="text"
-    - multi_value=True          → type="multi-values"
-    - neither / free_values=False → type="value"
-
-    Args:
-        raw: Raw entity labels config from bank config
-
-    Returns:
-        EntityLabelsConfig or None if raw is None/empty
-    """
-    if raw is None:
-        return None
-
-    if isinstance(raw, list):
-        if not raw:
-            return None
-        attributes = [LabelGroup.model_validate(_migrate_label_group(a)) for a in raw]
-        return EntityLabelsConfig(attributes=attributes)
-
-    if isinstance(raw, dict):
-        attrs_raw = raw.get("attributes", [])
-        if not attrs_raw:
-            return None
-        attributes = [LabelGroup.model_validate(_migrate_label_group(a)) for a in attrs_raw]
-        return EntityLabelsConfig(attributes=attributes)
-
-    return None
-
-
-def _migrate_label_group(raw: dict) -> dict:
-    """Migrate legacy free_values/multi_value fields to the new type field."""
-    if not isinstance(raw, dict) or "type" in raw:
-        return raw
-    patched = dict(raw)
-    if patched.get("free_values"):
-        patched["type"] = "text"
-    elif patched.get("multi_value"):
-        patched["type"] = "multi-values"
-    else:
-        patched["type"] = "value"
-    # Remove legacy keys so Pydantic doesn't error on unknown fields
-    patched.pop("free_values", None)
-    patched.pop("multi_value", None)
-    return patched
-
-
-def build_labels_model(labels_cfg: EntityLabelsConfig) -> type[BaseModel] | None:
-    """
-    Build a dynamic Pydantic model for structured label extraction.
-
-    Each LabelGroup becomes a typed field based on its type:
-    - type="text"                        → str | None  (always optional)
-    - type="value",   optional=True      → Literal["v1","v2"] | None
-    - type="value",   optional=False     → Literal["v1","v2"]  (required)
-    - type="multi-values"                → list[Literal["v1","v2"]]
-
-    Args:
-        labels_cfg: Parsed EntityLabelsConfig
-
-    Returns:
-        Dynamic Pydantic model class, or None if no groups defined
-    """
-    fields: dict = {}
-    for group in labels_cfg.attributes:
-        if not group.key:
-            continue
-        description = group.description or group.key
-
-        if group.type == "text":
-            # Free-form: any string value accepted, always optional
-            fields[group.key] = (str | None, Field(default=None, description=description))
-        else:
-            # Enum-constrained: must have defined values
-            if not group.values:
-                continue
-            values = tuple(v.value for v in group.values if v.value)
-            if not values:
-                continue
-            # Literal[("v1", "v2")] is equivalent to Literal["v1", "v2"] in Python 3.11+
-            literal_type = Literal[values]  # type: ignore[valid-type]
-            if group.type == "multi-values":
-                fields[group.key] = (
-                    list[literal_type],  # type: ignore[valid-type]
-                    Field(default_factory=list, description=description),
-                )
-            elif group.optional:
-                fields[group.key] = (
-                    literal_type | None,  # type: ignore[valid-type]
-                    Field(default=None, description=description),
-                )
-            else:
-                fields[group.key] = (
-                    literal_type,  # type: ignore[valid-type]
-                    Field(description=description),
-                )
-
-    if not fields:
-        return None
-
-    return create_model("Labels", **fields)
-
-
-def is_label_entity(text: str, labels_cfg: EntityLabelsConfig, labels_lookup: set[str]) -> bool:
-    """
-    Return True if entity text belongs to any configured label group.
-
-    For enum groups: checks the pre-built lookup set.
-    For text groups: checks that the text starts with a known key prefix.
-    """
-    if text.lower() in labels_lookup:
-        return True
-    for group in labels_cfg.attributes:
-        if group.type == "text" and group.key and text.lower().startswith(f"{group.key.lower()}:"):
-            return True
-    return False
-
-
-def build_labels_lookup(labels_cfg: EntityLabelsConfig | list | None) -> set[str]:
-    """
-    Build a set of valid 'key:value' label strings (lowercase) for fast lookup.
-
-    Accepts either EntityLabelsConfig or raw list/None for backwards compatibility.
-
-    Args:
-        labels_cfg: EntityLabelsConfig, raw list of attribute dicts, or None
-
-    Returns:
-        Set of lowercase 'key:value' strings
-    """
-    if labels_cfg is None:
-        return set()
-
-    # Accept raw list/dict for backwards compatibility
-    if not isinstance(labels_cfg, EntityLabelsConfig):
-        parsed = parse_entity_labels(labels_cfg)
-        if parsed is None:
-            return set()
-        labels_cfg = parsed
-
-    valid = set()
-    for group in labels_cfg.attributes:
-        if group.type == "text":
-            continue  # No fixed vocabulary — all values accepted in post-processing
-        for v in group.values:
-            if group.key and v.value:
-                valid.add(f"{group.key}:{v.value}".lower())
-    return valid

hindsight-api-slim/hindsight_api/engine/retain/fact_storage.py

@@ -1,262 +0,0 @@
-"""
-Fact storage for retain pipeline.
-
-Handles insertion of facts into the database.
-"""
-
-import json
-import logging
-import uuid
-
-from ...config import get_config
-from ..memory_engine import fq_table
-from .bank_utils import DEFAULT_DISPOSITION, create_bank_hnsw_indexes
-from .fact_extraction import _sanitize_text
-from .types import ProcessedFact
-
-logger = logging.getLogger(__name__)
-
-
-async def insert_facts_batch(
-    conn, bank_id: str, facts: list[ProcessedFact], document_id: str | None = None
-) -> list[str]:
-    """
-    Insert facts into the database in batch.
-
-    Args:
-        conn: Database connection
-        bank_id: Bank identifier
-        facts: List of ProcessedFact objects to insert
-        document_id: Optional document ID to associate with facts
-
-    Returns:
-        List of unit IDs (UUIDs as strings) for the inserted facts
-    """
-    if not facts:
-        return []
-
-    # Prepare data for batch insert
-    fact_texts = []
-    embeddings = []
-    event_dates = []
-    occurred_starts = []
-    occurred_ends = []
-    mentioned_ats = []
-    contexts = []
-    fact_types = []
-    confidence_scores = []
-    metadata_jsons = []
-    chunk_ids = []
-    document_ids = []
-    tags_list = []
-    observation_scopes_list = []
-    text_signals_list = []
-
-    for fact in facts:
-        fact_texts.append(_sanitize_text(fact.fact_text))
-        # Convert embedding to string for asyncpg vector type
-        embeddings.append(str(fact.embedding))
-        # event_date: Use occurred_start if available, otherwise use mentioned_at
-        # This maintains backward compatibility while handling None occurred_start
-        event_dates.append(fact.occurred_start if fact.occurred_start is not None else fact.mentioned_at)
-        occurred_starts.append(fact.occurred_start)
-        occurred_ends.append(fact.occurred_end)
-        mentioned_ats.append(fact.mentioned_at)
-        contexts.append(_sanitize_text(fact.context))
-        fact_types.append(fact.fact_type)
-        # confidence_score is only for opinion facts
-        confidence_scores.append(1.0 if fact.fact_type == "opinion" else None)
-        metadata_jsons.append(json.dumps(fact.metadata))
-        chunk_ids.append(fact.chunk_id)
-        # Use per-fact document_id if available, otherwise fallback to batch-level document_id
-        document_ids.append(fact.document_id if fact.document_id else document_id)
-        # Convert tags to JSON string for proper batch insertion (PostgreSQL unnest doesn't handle 2D arrays well)
-        tags_list.append(json.dumps(fact.tags if fact.tags else []))
-        # observation_scopes: stored as JSONB (string or 2D array), None if not provided
-        observation_scopes_list.append(
-            json.dumps(fact.observation_scopes) if fact.observation_scopes is not None else None
-        )
-        # Build text_signals: entity names + date tokens for enriched BM25 indexing
-        signal_parts = []
-        if fact.entities:
-            signal_parts.extend(e.name for e in fact.entities)
-        if fact.occurred_start:
-            signal_parts.append(fact.occurred_start.strftime("%B %-d %Y"))
-        if fact.occurred_end and fact.occurred_end != fact.occurred_start:
-            signal_parts.append(fact.occurred_end.strftime("%B %-d %Y"))
-        text_signals_list.append(" ".join(signal_parts) if signal_parts else None)
-
-    # Batch insert all facts
-    # Note: tags are passed as JSON strings and converted back to varchar[] via jsonb_array_elements_text + array_agg
-    # Query varies based on text search backend
-    config = get_config()
-    if config.text_search_extension == "vchord":
-        # VectorChord: manually tokenize and insert search_vector
-        # text_signals (entity names etc.) are included in the tokenize input for enriched BM25
-        query = f"""
-            WITH input_data AS (
-                SELECT * FROM unnest(
-                    $2::text[], $3::vector[], $4::timestamptz[], $5::timestamptz[], $6::timestamptz[], $7::timestamptz[],
-                    $8::text[], $9::text[], $10::float[], $11::jsonb[], $12::text[], $13::text[], $14::jsonb[], $15::jsonb[], $16::text[]
-                ) AS t(text, embedding, event_date, occurred_start, occurred_end, mentioned_at,
-                       context, fact_type, confidence_score, metadata, chunk_id, document_id, tags_json,
-                       observation_scopes_json, text_signals)
-            )
-            INSERT INTO {fq_table("memory_units")} (bank_id, text, embedding, event_date, occurred_start, occurred_end, mentioned_at,
-                                     context, fact_type, confidence_score, metadata, chunk_id, document_id, tags,
-                                     observation_scopes, text_signals, search_vector)
-            SELECT
-                $1,
-                text, embedding, event_date, occurred_start, occurred_end, mentioned_at,
-                context, fact_type, confidence_score, metadata, chunk_id, document_id,
-                COALESCE(
-                    (SELECT array_agg(elem) FROM jsonb_array_elements_text(tags_json) AS elem),
-                    '{{}}'::varchar[]
-                ),
-                observation_scopes_json,
-                text_signals,
-                tokenize(
-                    COALESCE(text, '') || ' ' || COALESCE(context, '') || ' ' || COALESCE(text_signals, ''),
-                    'llmlingua2'
-                )::bm25_catalog.bm25vector
-            FROM input_data
-            RETURNING id
-        """
-    else:  # native or pg_textsearch
-        # Native PostgreSQL: search_vector is GENERATED ALWAYS (expression includes text_signals), don't include it
-        # pg_textsearch: indexes operate on base columns directly, don't populate search_vector
-        query = f"""
-            WITH input_data AS (
-                SELECT * FROM unnest(
-                    $2::text[], $3::vector[], $4::timestamptz[], $5::timestamptz[], $6::timestamptz[], $7::timestamptz[],
-                    $8::text[], $9::text[], $10::float[], $11::jsonb[], $12::text[], $13::text[], $14::jsonb[], $15::jsonb[], $16::text[]
-                ) AS t(text, embedding, event_date, occurred_start, occurred_end, mentioned_at,
-                       context, fact_type, confidence_score, metadata, chunk_id, document_id, tags_json,
-                       observation_scopes_json, text_signals)
-            )
-            INSERT INTO {fq_table("memory_units")} (bank_id, text, embedding, event_date, occurred_start, occurred_end, mentioned_at,
-                                     context, fact_type, confidence_score, metadata, chunk_id, document_id, tags,
-                                     observation_scopes, text_signals)
-            SELECT
-                $1,
-                text, embedding, event_date, occurred_start, occurred_end, mentioned_at,
-                context, fact_type, confidence_score, metadata, chunk_id, document_id,
-                COALESCE(
-                    (SELECT array_agg(elem) FROM jsonb_array_elements_text(tags_json) AS elem),
-                    '{{}}'::varchar[]
-                ),
-                observation_scopes_json,
-                text_signals
-            FROM input_data
-            RETURNING id
-        """
-
-    results = await conn.fetch(
-        query,
-        bank_id,
-        fact_texts,
-        embeddings,
-        event_dates,  # event_date: occurred_start if available, else mentioned_at
-        occurred_starts,
-        occurred_ends,
-        mentioned_ats,
-        contexts,
-        fact_types,
-        confidence_scores,
-        metadata_jsons,
-        chunk_ids,
-        document_ids,
-        tags_list,
-        observation_scopes_list,
-        text_signals_list,
-    )
-
-    unit_ids = [str(row["id"]) for row in results]
-    return unit_ids
-
-
-async def ensure_bank_exists(conn, bank_id: str) -> None:
-    """
-    Ensure bank exists in the database.
-
-    Creates bank with default values if it doesn't exist.
-
-    Args:
-        conn: Database connection
-        bank_id: Bank identifier
-    """
-    # Generate internal_id here so we control the value and can use it
-    # immediately for HNSW index creation without a RETURNING round-trip.
-    internal_id = uuid.uuid4()
-    inserted = await conn.fetchval(
-        f"""
-        INSERT INTO {fq_table("banks")} (bank_id, disposition, mission, internal_id)
-        VALUES ($1, $2::jsonb, $3, $4)
-        ON CONFLICT (bank_id) DO NOTHING
-        RETURNING bank_id
-        """,
-        bank_id,
-        json.dumps(DEFAULT_DISPOSITION),
-        "",
-        internal_id,
-    )
-    if inserted:
-        # Fresh insert — create per-bank HNSW indexes
-        await create_bank_hnsw_indexes(conn, bank_id, str(internal_id))
-
-
-async def handle_document_tracking(
-    conn,
-    bank_id: str,
-    document_id: str,
-    combined_content: str,
-    is_first_batch: bool,
-    retain_params: dict | None = None,
-    document_tags: list[str] | None = None,
-) -> None:
-    """
-    Handle document tracking in the database.
-
-    Args:
-        conn: Database connection
-        bank_id: Bank identifier
-        document_id: Document identifier
-        combined_content: Combined content text from all content items
-        is_first_batch: Whether this is the first batch (for chunked operations)
-        retain_params: Optional parameters passed during retain (context, event_date, etc.)
-        document_tags: Optional list of tags to associate with the document
-    """
-    import hashlib
-
-    # Sanitize and calculate content hash
-    combined_content = _sanitize_text(combined_content) or ""
-    content_hash = hashlib.sha256(combined_content.encode()).hexdigest()
-
-    # Always delete old document first if it exists (cascades to units and links)
-    # Only delete on the first batch to avoid deleting data we just inserted
-    if is_first_batch:
-        await conn.fetchval(
-            f"DELETE FROM {fq_table('documents')} WHERE id = $1 AND bank_id = $2 RETURNING id", document_id, bank_id
-        )
-
-    # Insert document (or update if exists from concurrent operations)
-    await conn.execute(
-        f"""
-        INSERT INTO {fq_table("documents")} (id, bank_id, original_text, content_hash, metadata, retain_params, tags)
-        VALUES ($1, $2, $3, $4, $5, $6, $7)
-        ON CONFLICT (id, bank_id) DO UPDATE
-        SET original_text = EXCLUDED.original_text,
-            content_hash = EXCLUDED.content_hash,
-            metadata = EXCLUDED.metadata,
-            retain_params = EXCLUDED.retain_params,
-            tags = EXCLUDED.tags,
-            updated_at = NOW()
-        """,
-        document_id,
-        bank_id,
-        combined_content,
-        content_hash,
-        json.dumps({}),  # Empty metadata dict
-        json.dumps(retain_params) if retain_params else None,
-        document_tags or [],
-    )

hindsight-api-slim/hindsight_api/engine/retain/orchestrator.py

@@ -1,544 +0,0 @@
-"""
-Main orchestrator for the retain pipeline.
-
-Coordinates all retain pipeline modules to store memories efficiently.
-"""
-
-import logging
-import time
-import uuid
-from collections.abc import Awaitable, Callable
-from datetime import UTC, datetime
-from typing import Any
-
-from ..db_utils import acquire_with_retry, retry_with_backoff
-from . import bank_utils
-
-
-def utcnow():
-    """Get current UTC time."""
-    return datetime.now(UTC)
-
-
-def parse_datetime_flexible(value: Any) -> datetime:
-    """
-    Parse a datetime value that could be either a datetime object or an ISO string.
-
-    This handles datetime values from both direct Python calls and deserialized JSON
-    (where datetime objects are serialized as ISO strings).
-
-    Args:
-        value: Either a datetime object or an ISO format string
-
-    Returns:
-        datetime object (timezone-aware)
-
-    Raises:
-        TypeError: If value is neither datetime nor string
-        ValueError: If string is not a valid ISO datetime
-    """
-    if isinstance(value, datetime):
-        # Ensure timezone-aware
-        if value.tzinfo is None:
-            return value.replace(tzinfo=UTC)
-        return value
-    elif isinstance(value, str):
-        # Parse ISO format string (handles both 'Z' and '+00:00' timezone formats)
-        dt = datetime.fromisoformat(value.replace("Z", "+00:00"))
-        # Ensure timezone-aware
-        if dt.tzinfo is None:
-            return dt.replace(tzinfo=UTC)
-        return dt
-    else:
-        raise TypeError(f"Expected datetime or string, got {type(value).__name__}")
-
-
-import asyncpg
-
-from ..response_models import TokenUsage
-from . import (
-    chunk_storage,
-    embedding_processing,
-    entity_processing,
-    fact_extraction,
-    fact_storage,
-    link_creation,
-)
-from .types import EntityLink, ExtractedFact, ProcessedFact, RetainContent, RetainContentDict
-
-logger = logging.getLogger(__name__)
-
-
-async def retain_batch(
-    pool,
-    embeddings_model,
-    llm_config,
-    entity_resolver,
-    format_date_fn,
-    bank_id: str,
-    contents_dicts: list[RetainContentDict],
-    config,
-    document_id: str | None = None,
-    is_first_batch: bool = True,
-    fact_type_override: str | None = None,
-    confidence_score: float | None = None,
-    document_tags: list[str] | None = None,
-    operation_id: str | None = None,
-    schema: str | None = None,
-    outbox_callback: Callable[["asyncpg.Connection"], Awaitable[None]] | None = None,
-) -> tuple[list[list[str]], TokenUsage]:
-    """
-    Process a batch of content through the retain pipeline.
-
-    Args:
-        pool: Database connection pool
-        embeddings_model: Embeddings model for generating embeddings
-        llm_config: LLM configuration for fact extraction
-        entity_resolver: Entity resolver for entity processing
-        format_date_fn: Function to format datetime to readable string
-        bank_id: Bank identifier
-        contents_dicts: List of content dictionaries
-        config: Resolved HindsightConfig for this bank
-        document_id: Optional document ID
-        is_first_batch: Whether this is the first batch
-        fact_type_override: Override fact type for all facts
-        confidence_score: Confidence score for opinions
-        document_tags: Tags applied to all items in this batch
-
-    Returns:
-        Tuple of (unit ID lists, token usage for fact extraction)
-    """
-    start_time = time.time()
-    total_chars = sum(len(item.get("content", "")) for item in contents_dicts)
-
-    # Buffer all logs
-    log_buffer = []
-    log_buffer.append(f"{'=' * 60}")
-    log_buffer.append(f"RETAIN_BATCH START: {bank_id}")
-    log_buffer.append(f"Batch size: {len(contents_dicts)} content items, {total_chars:,} chars")
-    log_buffer.append(f"{'=' * 60}")
-
-    # Get bank profile
-    profile = await bank_utils.get_bank_profile(pool, bank_id)
-    agent_name = profile["name"]
-
-    # Convert dicts to RetainContent objects
-    contents = []
-    for item in contents_dicts:
-        # Merge item-level tags with document-level tags
-        item_tags = item.get("tags", []) or []
-        merged_tags = list(set(item_tags + (document_tags or [])))
-
-        # Handle event_date: distinguish "not provided" (default to now) from
-        # "explicitly None" (caller opted into no timestamp).
-        if "event_date" in item and item["event_date"] is None:
-            event_date_value = None  # Caller explicitly signalled "unknown date"
-        elif item.get("event_date"):
-            event_date_value = parse_datetime_flexible(item["event_date"])
-        else:
-            event_date_value = utcnow()  # Backward-compatible default
-
-        content = RetainContent(
-            content=item["content"],
-            context=item.get("context", ""),
-            event_date=event_date_value,
-            metadata=item.get("metadata", {}),
-            entities=item.get("entities", []),
-            tags=merged_tags,
-            observation_scopes=item.get("observation_scopes"),
-        )
-        contents.append(content)
-
-    # Step 1: Extract facts from all contents
-    step_start = time.time()
-
-    extracted_facts, chunks, usage = await fact_extraction.extract_facts_from_contents(
-        contents, llm_config, agent_name, config, pool, operation_id, schema
-    )
-    log_buffer.append(
-        f"[1] Extract facts: {len(extracted_facts)} facts, {len(chunks)} chunks from {len(contents)} contents in {time.time() - step_start:.3f}s"
-    )
-
-    if not extracted_facts:
-        # Still need to create document if document_id was provided or chunks exist
-        from collections import defaultdict
-
-        docs_tracked = 0
-        async with acquire_with_retry(pool) as conn:
-            async with conn.transaction():
-                # Group contents by document_id (consistent with normal path)
-                contents_by_doc_early = defaultdict(list)
-                for idx, content_dict in enumerate(contents_dicts):
-                    doc_id = content_dict.get("document_id")
-                    contents_by_doc_early[doc_id].append((idx, content_dict))
-
-                if document_id:
-                    # Legacy: single document_id parameter
-                    combined_content = "\n".join([c.get("content", "") for c in contents_dicts])
-                    # Collect tags from all content items and merge with document_tags
-                    all_tags = set(document_tags or [])
-                    for item in contents_dicts:
-                        item_tags = item.get("tags", []) or []
-                        all_tags.update(item_tags)
-                    merged_tags = list(all_tags)
-
-                    retain_params = {}
-                    if contents_dicts:
-                        first_item = contents_dicts[0]
-                        if first_item.get("context"):
-                            retain_params["context"] = first_item["context"]
-                        if first_item.get("event_date"):
-                            retain_params["event_date"] = (
-                                first_item["event_date"].isoformat()
-                                if hasattr(first_item["event_date"], "isoformat")
-                                else str(first_item["event_date"])
-                            )
-                        if first_item.get("metadata"):
-                            retain_params["metadata"] = first_item["metadata"]
-                    await fact_storage.handle_document_tracking(
-                        conn, bank_id, document_id, combined_content, is_first_batch, retain_params, merged_tags
-                    )
-                    docs_tracked += 1
-                else:
-                    # Handle per-item document_ids and/or chunks (mirrors normal path logic)
-                    has_any_doc_ids = any(item.get("document_id") for item in contents_dicts)
-
-                    if has_any_doc_ids or chunks:
-                        for original_doc_id, doc_contents in contents_by_doc_early.items():
-                            should_create_doc = (original_doc_id is not None) or chunks
-                            if not should_create_doc:
-                                continue
-
-                            actual_doc_id = original_doc_id
-                            if actual_doc_id is None:
-                                # No document_id but have chunks - generate one
-                                actual_doc_id = str(uuid.uuid4())
-
-                            combined_content = "\n".join([c.get("content", "") for _, c in doc_contents])
-                            all_tags = set(document_tags or [])
-                            for _, item in doc_contents:
-                                item_tags = item.get("tags", []) or []
-                                all_tags.update(item_tags)
-                            merged_tags = list(all_tags)
-
-                            retain_params = {}
-                            if doc_contents:
-                                first_item = doc_contents[0][1]
-                                if first_item.get("context"):
-                                    retain_params["context"] = first_item["context"]
-                                if first_item.get("event_date"):
-                                    retain_params["event_date"] = (
-                                        first_item["event_date"].isoformat()
-                                        if hasattr(first_item["event_date"], "isoformat")
-                                        else str(first_item["event_date"])
-                                    )
-                                if first_item.get("metadata"):
-                                    retain_params["metadata"] = first_item["metadata"]
-                            await fact_storage.handle_document_tracking(
-                                conn,
-                                bank_id,
-                                actual_doc_id,
-                                combined_content,
-                                is_first_batch,
-                                retain_params,
-                                merged_tags,
-                            )
-                            docs_tracked += 1
-
-        total_time = time.time() - start_time
-        doc_status = f"{docs_tracked} document(s) tracked" if docs_tracked > 0 else "no document tracked"
-        logger.info(
-            f"RETAIN_BATCH COMPLETE: 0 facts extracted from {len(contents)} contents in {total_time:.3f}s ({doc_status}, no facts)"
-        )
-        return [[] for _ in contents], usage
-
-    # Apply fact_type_override if provided
-    if fact_type_override:
-        for fact in extracted_facts:
-            fact.fact_type = fact_type_override
-
-    # Step 2: Augment texts and generate embeddings
-    step_start = time.time()
-    augmented_texts = embedding_processing.augment_texts_with_dates(extracted_facts, format_date_fn)
-    embeddings = await embedding_processing.generate_embeddings_batch(embeddings_model, augmented_texts)
-    log_buffer.append(f"[2] Generate embeddings: {len(embeddings)} embeddings in {time.time() - step_start:.3f}s")
-
-    # Step 3: Convert to ProcessedFact objects (without chunk_ids yet)
-    processed_facts = [
-        ProcessedFact.from_extracted_fact(extracted_fact, embedding)
-        for extracted_fact, embedding in zip(extracted_facts, embeddings)
-    ]
-
-    # Group contents by document_id for document tracking and chunk storage
-    from collections import defaultdict
-
-    contents_by_doc = defaultdict(list)
-    for idx, content_dict in enumerate(contents_dicts):
-        doc_id = content_dict.get("document_id")
-        contents_by_doc[doc_id].append((idx, content_dict))
-
-    # Step 4: Database transaction (retried on deadlock)
-    result_unit_ids: list[list[str]] = []
-
-    log_buffer_pre_db = len(log_buffer)
-
-    async def _run_db_work() -> None:
-        nonlocal result_unit_ids
-
-        # Reset per-fact mutations and log buffer so each retry attempt starts clean
-        del log_buffer[log_buffer_pre_db:]
-        document_ids_added: list[str] = []
-        for pf in processed_facts:
-            pf.document_id = None
-            pf.chunk_id = None
-
-        async with acquire_with_retry(pool) as conn:
-            async with conn.transaction():
-                # Handle document tracking for all documents
-                step_start = time.time()
-                # Map None document_id to generated UUIDs
-                doc_id_mapping = {}  # Maps original doc_id (including None) to actual doc_id used
-
-                if document_id:
-                    # Legacy: single document_id parameter
-                    combined_content = "\n".join([c.get("content", "") for c in contents_dicts])
-                    retain_params = {}
-                    # Collect tags from all content items and merge with document_tags
-                    all_tags = set(document_tags or [])
-                    for item in contents_dicts:
-                        item_tags = item.get("tags", []) or []
-                        all_tags.update(item_tags)
-                    merged_tags = list(all_tags)
-
-                    if contents_dicts:
-                        first_item = contents_dicts[0]
-                        if first_item.get("context"):
-                            retain_params["context"] = first_item["context"]
-                        if first_item.get("event_date"):
-                            retain_params["event_date"] = (
-                                first_item["event_date"].isoformat()
-                                if hasattr(first_item["event_date"], "isoformat")
-                                else str(first_item["event_date"])
-                            )
-                        if first_item.get("metadata"):
-                            retain_params["metadata"] = first_item["metadata"]
-
-                    await fact_storage.handle_document_tracking(
-                        conn, bank_id, document_id, combined_content, is_first_batch, retain_params, merged_tags
-                    )
-                    document_ids_added.append(document_id)
-                    doc_id_mapping[None] = document_id  # For backwards compatibility
-                else:
-                    # Handle per-item document_ids (create documents if any item has document_id or if chunks exist)
-                    has_any_doc_ids = any(item.get("document_id") for item in contents_dicts)
-
-                    if has_any_doc_ids or chunks:
-                        for original_doc_id, doc_contents in contents_by_doc.items():
-                            actual_doc_id = original_doc_id
-
-                            # Only create document record if:
-                            # 1. Item has explicit document_id, OR
-                            # 2. There are chunks (need document for chunk storage)
-                            should_create_doc = (original_doc_id is not None) or chunks
-
-                            if should_create_doc:
-                                if actual_doc_id is None:
-                                    # No document_id but have chunks - generate one
-                                    actual_doc_id = str(uuid.uuid4())
-
-                                # Store mapping for later use
-                                doc_id_mapping[original_doc_id] = actual_doc_id
-
-                                # Combine content for this document
-                                combined_content = "\n".join([c.get("content", "") for _, c in doc_contents])
-
-                                # Collect tags from all content items for this document and merge with document_tags
-                                all_tags = set(document_tags or [])
-                                for _, item in doc_contents:
-                                    item_tags = item.get("tags", []) or []
-                                    all_tags.update(item_tags)
-                                merged_tags = list(all_tags)
-
-                                # Extract retain params from first content item
-                                retain_params = {}
-                                if doc_contents:
-                                    first_item = doc_contents[0][1]
-                                    if first_item.get("context"):
-                                        retain_params["context"] = first_item["context"]
-                                    if first_item.get("event_date"):
-                                        retain_params["event_date"] = (
-                                            first_item["event_date"].isoformat()
-                                            if hasattr(first_item["event_date"], "isoformat")
-                                            else str(first_item["event_date"])
-                                        )
-                                    if first_item.get("metadata"):
-                                        retain_params["metadata"] = first_item["metadata"]
-
-                                await fact_storage.handle_document_tracking(
-                                    conn,
-                                    bank_id,
-                                    actual_doc_id,
-                                    combined_content,
-                                    is_first_batch,
-                                    retain_params,
-                                    merged_tags,
-                                )
-                                document_ids_added.append(actual_doc_id)
-
-                if document_ids_added:
-                    log_buffer.append(
-                        f"[2.5] Document tracking: {len(document_ids_added)} documents in {time.time() - step_start:.3f}s"
-                    )
-
-                # Store chunks and map to facts for all documents
-                step_start = time.time()
-                chunk_id_map_by_doc = {}  # Maps (doc_id, chunk_index) -> chunk_id
-
-                if chunks:
-                    # Group chunks by their source document
-                    chunks_by_doc = defaultdict(list)
-                    for chunk in chunks:
-                        # chunk.content_index tells us which content this chunk came from
-                        original_doc_id = contents_dicts[chunk.content_index].get("document_id")
-                        # Map to actual document_id (handles None -> generated UUID mapping)
-                        actual_doc_id = doc_id_mapping.get(original_doc_id, original_doc_id)
-                        if actual_doc_id is None and document_id:
-                            actual_doc_id = document_id
-                        chunks_by_doc[actual_doc_id].append(chunk)
-
-                    # Store chunks for each document
-                    for doc_id, doc_chunks in chunks_by_doc.items():
-                        chunk_id_map = await chunk_storage.store_chunks_batch(conn, bank_id, doc_id, doc_chunks)
-                        # Store mapping with document context
-                        for chunk_idx, chunk_id in chunk_id_map.items():
-                            chunk_id_map_by_doc[(doc_id, chunk_idx)] = chunk_id
-
-                    log_buffer.append(
-                        f"[3] Store chunks: {len(chunks)} chunks for {len(chunks_by_doc)} documents in {time.time() - step_start:.3f}s"
-                    )
-
-                    # Map chunk_ids and document_ids to facts
-                    for fact, processed_fact in zip(extracted_facts, processed_facts):
-                        # Get the original document_id for this fact's source content
-                        original_doc_id = contents_dicts[fact.content_index].get("document_id")
-                        # Map to actual document_id (handles None -> generated UUID mapping)
-                        actual_doc_id = doc_id_mapping.get(original_doc_id, original_doc_id)
-                        if actual_doc_id is None and document_id:
-                            actual_doc_id = document_id
-
-                        # Set document_id on the fact
-                        processed_fact.document_id = actual_doc_id
-
-                        # Map chunk_id if this fact came from a chunk
-                        if fact.chunk_index is not None:
-                            # Look up chunk_id using (doc_id, chunk_index)
-                            chunk_id = chunk_id_map_by_doc.get((actual_doc_id, fact.chunk_index))
-                            if chunk_id:
-                                processed_fact.chunk_id = chunk_id
-                else:
-                    # No chunks - still need to set document_id on facts
-                    for fact, processed_fact in zip(extracted_facts, processed_facts):
-                        original_doc_id = contents_dicts[fact.content_index].get("document_id")
-                        # Map to actual document_id (handles None -> generated UUID mapping)
-                        actual_doc_id = doc_id_mapping.get(original_doc_id, original_doc_id)
-                        if actual_doc_id is None and document_id:
-                            actual_doc_id = document_id
-                        processed_fact.document_id = actual_doc_id
-
-                non_duplicate_facts = processed_facts
-
-                # Insert facts (document_id is now stored per-fact)
-                step_start = time.time()
-                unit_ids = await fact_storage.insert_facts_batch(conn, bank_id, non_duplicate_facts)
-                log_buffer.append(f"[5] Insert facts: {len(unit_ids)} units in {time.time() - step_start:.3f}s")
-
-                # Process entities
-                step_start = time.time()
-                # Build map of content_index -> user entities for merging
-                user_entities_per_content = {
-                    idx: content.entities for idx, content in enumerate(contents) if content.entities
-                }
-                entity_links = await entity_processing.process_entities_batch(
-                    entity_resolver,
-                    conn,
-                    bank_id,
-                    unit_ids,
-                    non_duplicate_facts,
-                    log_buffer,
-                    user_entities_per_content=user_entities_per_content,
-                    entity_labels=getattr(config, "entity_labels", None),
-                )
-                log_buffer.append(f"[6] Process entities: {len(entity_links)} links in {time.time() - step_start:.3f}s")
-
-                # Create temporal links
-                step_start = time.time()
-                temporal_link_count = await link_creation.create_temporal_links_batch(conn, bank_id, unit_ids)
-                log_buffer.append(f"[7] Temporal links: {temporal_link_count} links in {time.time() - step_start:.3f}s")
-
-                # Create semantic links
-                step_start = time.time()
-                embeddings_for_links = [fact.embedding for fact in non_duplicate_facts]
-                semantic_link_count = await link_creation.create_semantic_links_batch(
-                    conn, bank_id, unit_ids, embeddings_for_links
-                )
-                log_buffer.append(f"[8] Semantic links: {semantic_link_count} links in {time.time() - step_start:.3f}s")
-
-                # Insert entity links
-                step_start = time.time()
-                if entity_links:
-                    await entity_processing.insert_entity_links_batch(conn, entity_links)
-                log_buffer.append(
-                    f"[9] Entity links: {len(entity_links) if entity_links else 0} links in {time.time() - step_start:.3f}s"
-                )
-
-                # Create causal links
-                step_start = time.time()
-                causal_link_count = await link_creation.create_causal_links_batch(conn, unit_ids, non_duplicate_facts)
-                log_buffer.append(f"[10] Causal links: {causal_link_count} links in {time.time() - step_start:.3f}s")
-
-                # Map results back to original content items
-                result_unit_ids = _map_results_to_contents(contents, extracted_facts, unit_ids)
-
-                # Transactional outbox: queue any side-effect tasks (e.g. webhook deliveries)
-                # inside the same transaction so they are atomically committed with the retain data.
-                if outbox_callback:
-                    await outbox_callback(conn)
-
-            # Flush entity stats (mention_count / last_seen) now that the transaction
-            # has committed.  Uses a fresh pool connection — no locks held.
-            await entity_resolver.flush_pending_stats()
-
-            # Log final summary
-            total_time = time.time() - start_time
-            log_buffer.append(f"{'=' * 60}")
-            log_buffer.append(f"RETAIN_BATCH COMPLETE: {len(unit_ids)} units in {total_time:.3f}s")
-            if document_ids_added:
-                log_buffer.append(f"Documents: {', '.join(document_ids_added)}")
-            log_buffer.append(f"{'=' * 60}")
-
-            logger.info("\n" + "\n".join(log_buffer) + "\n")
-
-    await retry_with_backoff(_run_db_work)
-    return result_unit_ids, usage
-
-
-def _map_results_to_contents(
-    contents: list[RetainContent],
-    extracted_facts: list[ExtractedFact],
-    unit_ids: list[str],
-) -> list[list[str]]:
-    """Map created unit IDs back to original content items."""
-    facts_by_content: dict[int, list[int]] = {i: [] for i in range(len(contents))}
-    for i, fact in enumerate(extracted_facts):
-        facts_by_content[fact.content_index].append(i)
-
-    result_unit_ids = []
-    unit_idx = 0
-    for content_index in range(len(contents)):
-        content_unit_ids = []
-        for _ in facts_by_content[content_index]:
-            content_unit_ids.append(unit_ids[unit_idx])
-            unit_idx += 1
-        result_unit_ids.append(content_unit_ids)
-
-    return result_unit_ids

hindsight-api-slim/hindsight_api/engine/search/link_expansion_retrieval.py

@@ -1,493 +0,0 @@
-"""
-Link Expansion graph retrieval.
-
-Expands from semantic/temporal seeds through three parallel, first-class signals
-stored in memory_links:
-
-1. Entity links  — precomputed co-occurrence graph (created at retain time, bounded to
-                   MAX_LINKS_PER_ENTITY per entity). Score = number of distinct shared
-                   entities between the seed set and each candidate.
-2. Semantic links — precomputed kNN graph (each new fact linked to its top-5 most
-                    similar existing facts at insert time, similarity >= 0.7). Checked
-                    in both directions since the graph is not symmetric. Score = weight.
-3. Causal links  — explicit causal chains (causes/caused_by/enables/prevents).
-                   Score = weight + 1.0 (boosted as highest-quality signal).
-
-All three signals are bounded at retain time, so no LATERAL fan-out caps are needed
-at query time. Each expansion is a simple aggregation over a small result set.
-
-For non-observation fact types the three expansions are issued as a single CTE query
-(one roundtrip, one connection) with a `source` discriminator column so the Python
-merge step can apply per-signal score transformations.
-"""
-
-import logging
-import math
-import time
-
-from ..db_utils import acquire_with_retry
-from ..memory_engine import fq_table
-from .graph_retrieval import GraphRetriever
-from .tags import TagGroup, TagsMatch, filter_results_by_tag_groups, filter_results_by_tags
-from .types import MPFPTimings, RetrievalResult
-
-logger = logging.getLogger(__name__)
-
-
-async def _find_semantic_seeds(
-    conn,
-    query_embedding_str: str,
-    bank_id: str,
-    fact_type: str,
-    limit: int = 20,
-    threshold: float = 0.3,
-    tags: list[str] | None = None,
-    tags_match: TagsMatch = "any",
-    tag_groups: list[TagGroup] | None = None,
-) -> list[RetrievalResult]:
-    """Find semantic seeds via embedding search."""
-    from .tags import build_tag_groups_where_clause, build_tags_where_clause_simple
-
-    tags_clause = build_tags_where_clause_simple(tags, 6, match=tags_match)
-    tag_groups_param_start = 6 + (1 if tags else 0)
-    groups_clause, groups_params, _ = build_tag_groups_where_clause(tag_groups, tag_groups_param_start)
-    params = [query_embedding_str, bank_id, fact_type, threshold, limit]
-    if tags:
-        params.append(tags)
-    params.extend(groups_params)
-
-    rows = await conn.fetch(
-        f"""
-        SELECT id, text, context, event_date, occurred_start, occurred_end,
-               mentioned_at, fact_type, document_id, chunk_id, tags,
-               1 - (embedding <=> $1::vector) AS similarity
-        FROM {fq_table("memory_units")}
-        WHERE bank_id = $2
-          AND embedding IS NOT NULL
-          AND fact_type = $3
-          AND (1 - (embedding <=> $1::vector)) >= $4
-          {tags_clause}
-          {groups_clause}
-        ORDER BY embedding <=> $1::vector
-        LIMIT $5
-        """,
-        *params,
-    )
-    return [RetrievalResult.from_db_row(dict(r)) for r in rows]
-
-
-class LinkExpansionRetriever(GraphRetriever):
-    """
-    Graph retrieval via direct link expansion from seeds.
-
-    Runs three expansions through precomputed memory_links: entity co-occurrence,
-    semantic kNN, and causal chains, all bounded at retain time.
-
-    For non-observation fact types the three expansions are issued as a single CTE
-    query (one roundtrip, one connection slot) with a `source` discriminator column.
-    The Python merge step applies per-signal score transformations.
-    """
-
-    def __init__(
-        self,
-        causal_weight_threshold: float = 0.3,
-    ):
-        """
-        Args:
-            causal_weight_threshold: Minimum weight for causal links to follow.
-        """
-        self.causal_weight_threshold = causal_weight_threshold
-
-    @property
-    def name(self) -> str:
-        return "link_expansion"
-
-    async def retrieve(
-        self,
-        pool,
-        query_embedding_str: str,
-        bank_id: str,
-        fact_type: str,
-        budget: int,
-        query_text: str | None = None,
-        semantic_seeds: list[RetrievalResult] | None = None,
-        temporal_seeds: list[RetrievalResult] | None = None,
-        adjacency=None,
-        tags: list[str] | None = None,
-        tags_match: TagsMatch = "any",
-        tag_groups: list[TagGroup] | None = None,
-    ) -> tuple[list[RetrievalResult], MPFPTimings | None]:
-        """
-        Retrieve facts by expanding links from seeds.
-
-        Args:
-            pool: Database connection pool
-            query_embedding_str: Query embedding as string
-            bank_id: Memory bank ID
-            fact_type: Fact type to filter
-            budget: Maximum results to return
-            query_text: Original query text (unused)
-            semantic_seeds: Pre-computed semantic entry points
-            temporal_seeds: Pre-computed temporal entry points
-            adjacency: Unused, kept for interface compatibility
-            tags: Optional list of tags for visibility filtering
-
-        Returns:
-            Tuple of (results, timings)
-        """
-        start_time = time.time()
-        timings = MPFPTimings(fact_type=fact_type)
-
-        async with acquire_with_retry(pool) as conn:
-            # Find seeds if not provided
-            if semantic_seeds:
-                all_seeds = list(semantic_seeds)
-            else:
-                seeds_start = time.time()
-                all_seeds = await _find_semantic_seeds(
-                    conn,
-                    query_embedding_str,
-                    bank_id,
-                    fact_type,
-                    limit=20,
-                    threshold=0.3,
-                    tags=tags,
-                    tags_match=tags_match,
-                    tag_groups=tag_groups,
-                )
-                timings.seeds_time = time.time() - seeds_start
-                logger.debug(
-                    f"[LinkExpansion] Found {len(all_seeds)} semantic seeds for fact_type={fact_type} "
-                    f"(tags={tags}, tags_match={tags_match})"
-                )
-
-            if temporal_seeds:
-                all_seeds.extend(temporal_seeds)
-
-            if not all_seeds:
-                return [], timings
-
-            seed_ids = list({s.id for s in all_seeds})
-            timings.pattern_count = len(seed_ids)
-
-            query_start = time.time()
-
-            if fact_type == "observation":
-                entity_rows, semantic_rows, causal_rows = await self._expand_observations(conn, seed_ids, budget)
-            else:
-                entity_rows, semantic_rows, causal_rows = await self._expand_combined(conn, seed_ids, fact_type, budget)
-
-            timings.edge_load_time = time.time() - query_start
-            timings.db_queries = 1
-            timings.edge_count = len(entity_rows) + len(semantic_rows) + len(causal_rows)
-
-        # Merge results with additive intra-score: entity + semantic + causal ∈ [0, 3].
-        #
-        # Entity score: tanh(count × 0.5) maps shared-entity count to [0, 1]:
-        #   1 entity → 0.46,  2 → 0.76,  3 → 0.91,  4 → 0.96  (saturates naturally)
-        # Semantic score: similarity weight, already ∈ [0.7, 1.0].
-        # Causal score:   link weight, already ∈ [0, 1].
-        #
-        # Facts appearing in multiple signals accumulate higher scores, rewarding
-        # convergent evidence. The outer RRF uses rank position from this sorted list.
-        entity_scores: dict[str, float] = {}
-        semantic_scores: dict[str, float] = {}
-        causal_scores: dict[str, float] = {}
-        row_map: dict[str, dict] = {}
-
-        for row in entity_rows:
-            fact_id = str(row["id"])
-            entity_scores[fact_id] = math.tanh(row["score"] * 0.5)
-            row_map[fact_id] = dict(row)
-
-        for row in semantic_rows:
-            fact_id = str(row["id"])
-            semantic_scores[fact_id] = max(semantic_scores.get(fact_id, 0.0), row["score"])
-            row_map.setdefault(fact_id, dict(row))
-
-        for row in causal_rows:
-            fact_id = str(row["id"])
-            causal_scores[fact_id] = max(causal_scores.get(fact_id, 0.0), row["score"])
-            row_map.setdefault(fact_id, dict(row))
-
-        all_ids = set(entity_scores) | set(semantic_scores) | set(causal_scores)
-        score_map = {
-            fid: entity_scores.get(fid, 0.0) + semantic_scores.get(fid, 0.0) + causal_scores.get(fid, 0.0)
-            for fid in all_ids
-        }
-
-        sorted_ids = sorted(score_map.keys(), key=lambda x: score_map[x], reverse=True)[:budget]
-        rows = [row_map[fact_id] for fact_id in sorted_ids]
-
-        results = []
-        for row in rows:
-            result = RetrievalResult.from_db_row(dict(row))
-            result.activation = row["score"]
-            results.append(result)
-
-        if tags:
-            results = filter_results_by_tags(results, tags, match=tags_match)
-
-        if tag_groups:
-            results = filter_results_by_tag_groups(results, tag_groups)
-
-        timings.result_count = len(results)
-        timings.traverse = time.time() - start_time
-
-        logger.debug(
-            f"LinkExpansion: {len(results)} results from {len(seed_ids)} seeds "
-            f"in {timings.traverse * 1000:.1f}ms (query: {timings.edge_load_time * 1000:.1f}ms)"
-        )
-
-        return results, timings
-
-    async def _expand_combined(
-        self,
-        conn,
-        seed_ids: list,
-        fact_type: str,
-        budget: int,
-    ) -> tuple[list, list, list]:
-        """
-        Single-roundtrip CTE query combining entity, semantic, and causal expansions.
-
-        Uses a `source` discriminator column so the caller can apply per-signal
-        score transformations.  The three CTEs share one connection slot — important
-        for asyncpg which does not allow concurrent queries on the same connection.
-
-        Index coverage (requires migration d2e3f4a5b6c7):
-          entity:   idx_memory_links_entity_covering (from_unit_id) INCLUDE (to_unit_id, entity_id)
-                    WHERE link_type = 'entity'  → index-only scan, no heap reads
-          semantic incoming:
-                    idx_memory_links_to_type_weight (to_unit_id, link_type, weight DESC)
-                    → replaces costly BitmapAnd of two separate scans
-        """
-        ml = fq_table("memory_links")
-        mu = fq_table("memory_units")
-        all_rows = await conn.fetch(
-            f"""
-            WITH entity_expanded AS (
-                -- Entity co-occurrence: seeds → their precomputed entity-link neighbors.
-                -- Score = distinct shared entities (bounded at retain time to
-                -- MAX_LINKS_PER_ENTITY=50).  GROUP BY mu.id is sufficient because mu.id
-                -- is the primary key and functionally determines all other mu columns.
-                SELECT
-                    mu.id, mu.text, mu.context, mu.event_date, mu.occurred_start,
-                    mu.occurred_end, mu.mentioned_at,
-                    mu.fact_type, mu.document_id, mu.chunk_id, mu.tags,
-                    COUNT(DISTINCT ml.entity_id)::float AS score,
-                    'entity'::text AS source
-                FROM {ml} ml
-                JOIN {mu} mu ON mu.id = ml.to_unit_id
-                WHERE ml.from_unit_id = ANY($1::uuid[])
-                  AND ml.link_type = 'entity'
-                  AND mu.fact_type = $2
-                  AND mu.id != ALL($1::uuid[])
-                GROUP BY mu.id
-                ORDER BY score DESC
-                LIMIT $3
-            ),
-            semantic_expanded AS (
-                -- Semantic kNN: both outgoing (seeds → their kNN at insert time) and
-                -- incoming (facts inserted after seeds that found seeds as kNN).
-                -- Score = max similarity weight across both directions.
-                SELECT
-                    id, text, context, event_date, occurred_start,
-                    occurred_end, mentioned_at,
-                    fact_type, document_id, chunk_id, tags,
-                    MAX(weight) AS score,
-                    'semantic'::text AS source
-                FROM (
-                    SELECT
-                        mu.id, mu.text, mu.context, mu.event_date, mu.occurred_start,
-                        mu.occurred_end, mu.mentioned_at,
-                        mu.fact_type, mu.document_id, mu.chunk_id, mu.tags,
-                        ml.weight
-                    FROM {ml} ml
-                    JOIN {mu} mu ON mu.id = ml.to_unit_id
-                    WHERE ml.from_unit_id = ANY($1::uuid[])
-                      AND ml.link_type = 'semantic'
-                      AND mu.fact_type = $2
-                      AND mu.id != ALL($1::uuid[])
-                    UNION ALL
-                    SELECT
-                        mu.id, mu.text, mu.context, mu.event_date, mu.occurred_start,
-                        mu.occurred_end, mu.mentioned_at,
-                        mu.fact_type, mu.document_id, mu.chunk_id, mu.tags,
-                        ml.weight
-                    FROM {ml} ml
-                    JOIN {mu} mu ON mu.id = ml.from_unit_id
-                    WHERE ml.to_unit_id = ANY($1::uuid[])
-                      AND ml.link_type = 'semantic'
-                      AND mu.fact_type = $2
-                      AND mu.id != ALL($1::uuid[])
-                ) sem_raw
-                GROUP BY id, text, context, event_date, occurred_start,
-                         occurred_end, mentioned_at,
-                         fact_type, document_id, chunk_id, tags
-                ORDER BY score DESC
-                LIMIT $3
-            ),
-            causal_expanded AS (
-                -- Causal chains: explicit causes/enables/prevents links from seeds.
-                -- DISTINCT ON handles the case where a seed has multiple causal links
-                -- to the same target; best weight wins.
-                SELECT DISTINCT ON (mu.id)
-                    mu.id, mu.text, mu.context, mu.event_date, mu.occurred_start,
-                    mu.occurred_end, mu.mentioned_at,
-                    mu.fact_type, mu.document_id, mu.chunk_id, mu.tags,
-                    ml.weight AS score,
-                    'causal'::text AS source
-                FROM {ml} ml
-                JOIN {mu} mu ON ml.to_unit_id = mu.id
-                WHERE ml.from_unit_id = ANY($1::uuid[])
-                  AND ml.link_type IN ('causes', 'caused_by', 'enables', 'prevents')
-                  AND ml.weight >= $4
-                  AND mu.fact_type = $2
-                ORDER BY mu.id, ml.weight DESC
-                LIMIT $3
-            )
-            SELECT * FROM entity_expanded
-            UNION ALL
-            SELECT * FROM semantic_expanded
-            UNION ALL
-            SELECT * FROM causal_expanded
-            """,
-            seed_ids,
-            fact_type,
-            budget,
-            self.causal_weight_threshold,
-        )
-
-        entity_rows = [r for r in all_rows if r["source"] == "entity"]
-        semantic_rows = [r for r in all_rows if r["source"] == "semantic"]
-        causal_rows = [r for r in all_rows if r["source"] == "causal"]
-        return entity_rows, semantic_rows, causal_rows
-
-    async def _expand_observations(
-        self,
-        conn,
-        seed_ids: list,
-        budget: int,
-    ) -> tuple[list, list, list]:
-        """
-        Observation-specific expansion.
-
-        Observations don't have direct entity links in memory_links (they're created
-        by consolidation, not retain).  Instead, traverse source_memory_ids → world
-        facts → entities → other world facts → their observations.
-
-        Semantic and causal expansions run as a second combined CTE query.
-        """
-        source_ids_found: list = []
-        if logger.isEnabledFor(logging.DEBUG):
-            debug_rows = await conn.fetch(
-                f"""
-                SELECT id, source_memory_ids
-                FROM {fq_table("memory_units")}
-                WHERE id = ANY($1::uuid[])
-                """,
-                seed_ids,
-            )
-            for row in debug_rows:
-                if row["source_memory_ids"]:
-                    source_ids_found.extend(row["source_memory_ids"])
-            logger.debug(
-                f"[LinkExpansion] observation graph: {len(seed_ids)} seeds, "
-                f"{len(source_ids_found)} source_memory_ids found"
-            )
-
-        entity_rows = await conn.fetch(
-            f"""
-            WITH seed_sources AS (
-                SELECT DISTINCT unnest(source_memory_ids) AS source_id
-                FROM {fq_table("memory_units")}
-                WHERE id = ANY($1::uuid[])
-                  AND source_memory_ids IS NOT NULL
-            ),
-            connected_sources AS (
-                -- Mirror the non-observation entity expansion: follow pre-bounded entity
-                -- links in memory_links (capped to MAX_LINKS_PER_ENTITY=50 at retain time).
-                -- Score = number of distinct shared entities, same as the non-obs path.
-                SELECT DISTINCT ml.to_unit_id AS source_id
-                FROM seed_sources ss
-                JOIN {fq_table("memory_links")} ml ON ml.from_unit_id = ss.source_id
-                WHERE ml.link_type = 'entity'
-            ),
-            connected_array AS (
-                SELECT array_agg(source_id) AS source_ids FROM connected_sources
-            )
-            SELECT
-                mu.id, mu.text, mu.context, mu.event_date, mu.occurred_start,
-                mu.occurred_end, mu.mentioned_at,
-                mu.fact_type, mu.document_id, mu.chunk_id, mu.tags,
-                (SELECT COUNT(DISTINCT s) FROM unnest(mu.source_memory_ids) s WHERE s = ANY(ca.source_ids))::float AS score
-            FROM {fq_table("memory_units")} mu, connected_array ca
-            WHERE mu.fact_type = 'observation'
-              AND mu.id != ALL($1::uuid[])
-              AND ca.source_ids IS NOT NULL
-              AND mu.source_memory_ids && ca.source_ids
-            ORDER BY score DESC
-            LIMIT $2
-            """,
-            seed_ids,
-            budget,
-        )
-        logger.debug(f"[LinkExpansion] observation graph: found {len(entity_rows)} connected observations")
-
-        # Semantic + causal for observations in one query
-        ml = fq_table("memory_links")
-        mu = fq_table("memory_units")
-        sem_causal_rows = await conn.fetch(
-            f"""
-            WITH semantic_expanded AS (
-                SELECT
-                    id, text, context, event_date, occurred_start,
-                    occurred_end, mentioned_at,
-                    fact_type, document_id, chunk_id, tags,
-                    MAX(weight) AS score,
-                    'semantic'::text AS source
-                FROM (
-                    SELECT mu.id, mu.text, mu.context, mu.event_date, mu.occurred_start,
-                           mu.occurred_end, mu.mentioned_at, mu.fact_type, mu.document_id,
-                           mu.chunk_id, mu.tags, ml.weight
-                    FROM {ml} ml JOIN {mu} mu ON mu.id = ml.to_unit_id
-                    WHERE ml.from_unit_id = ANY($1::uuid[])
-                      AND ml.link_type = 'semantic' AND mu.fact_type = 'observation'
-                      AND mu.id != ALL($1::uuid[])
-                    UNION ALL
-                    SELECT mu.id, mu.text, mu.context, mu.event_date, mu.occurred_start,
-                           mu.occurred_end, mu.mentioned_at, mu.fact_type, mu.document_id,
-                           mu.chunk_id, mu.tags, ml.weight
-                    FROM {ml} ml JOIN {mu} mu ON mu.id = ml.from_unit_id
-                    WHERE ml.to_unit_id = ANY($1::uuid[])
-                      AND ml.link_type = 'semantic' AND mu.fact_type = 'observation'
-                      AND mu.id != ALL($1::uuid[])
-                ) sem_raw
-                GROUP BY id, text, context, event_date, occurred_start, occurred_end,
-                         mentioned_at, fact_type, document_id, chunk_id, tags
-                ORDER BY score DESC LIMIT $2
-            ),
-            causal_expanded AS (
-                SELECT DISTINCT ON (mu.id)
-                    mu.id, mu.text, mu.context, mu.event_date, mu.occurred_start,
-                    mu.occurred_end, mu.mentioned_at, mu.fact_type, mu.document_id,
-                    mu.chunk_id, mu.tags, ml.weight AS score, 'causal'::text AS source
-                FROM {ml} ml JOIN {mu} mu ON ml.to_unit_id = mu.id
-                WHERE ml.from_unit_id = ANY($1::uuid[])
-                  AND ml.link_type IN ('causes', 'caused_by', 'enables', 'prevents')
-                  AND ml.weight >= $3 AND mu.fact_type = 'observation'
-                ORDER BY mu.id, ml.weight DESC LIMIT $2
-            )
-            SELECT * FROM semantic_expanded
-            UNION ALL
-            SELECT * FROM causal_expanded
-            """,
-            seed_ids,
-            budget,
-            self.causal_weight_threshold,
-        )
-
-        semantic_rows = [r for r in sem_causal_rows if r["source"] == "semantic"]
-        causal_rows = [r for r in sem_causal_rows if r["source"] == "causal"]
-        return entity_rows, semantic_rows, causal_rows

hindsight-api-slim/hindsight_api/engine/search/retrieval.py

@@ -1,690 +0,0 @@
-"""
-Retrieval module for 4-way parallel search.
-
-Implements:
-1. Semantic retrieval (vector similarity)
-2. BM25 retrieval (keyword/full-text search)
-3. Graph retrieval (via pluggable GraphRetriever interface)
-4. Temporal retrieval (time-aware search with spreading)
-"""
-
-import asyncio
-import logging
-from dataclasses import dataclass, field
-from datetime import UTC, datetime
-from typing import Optional
-
-from ...config import get_config
-from ..db_utils import acquire_with_retry
-from ..memory_engine import fq_table
-from .graph_retrieval import BFSGraphRetriever, GraphRetriever
-from .link_expansion_retrieval import LinkExpansionRetriever
-from .mpfp_retrieval import MPFPGraphRetriever
-from .tags import TagGroup, TagsMatch, build_tag_groups_where_clause, build_tags_where_clause_simple
-from .types import MPFPTimings, RetrievalResult
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class ParallelRetrievalResult:
-    """Result from parallel retrieval across all methods."""
-
-    semantic: list[RetrievalResult]
-    bm25: list[RetrievalResult]
-    graph: list[RetrievalResult]
-    temporal: list[RetrievalResult] | None
-    timings: dict[str, float] = field(default_factory=dict)
-    temporal_constraint: tuple | None = None  # (start_date, end_date)
-    mpfp_timings: list[MPFPTimings] = field(default_factory=list)  # MPFP sub-step timings per fact type
-    max_conn_wait: float = 0.0  # Maximum connection acquisition wait time across all methods
-
-
-@dataclass
-class MultiFactTypeRetrievalResult:
-    """Result from retrieval across all fact types."""
-
-    # Results per fact type
-    results_by_fact_type: dict[str, ParallelRetrievalResult]
-    # Aggregate timings
-    timings: dict[str, float] = field(default_factory=dict)
-    # Max connection wait across all operations
-    max_conn_wait: float = 0.0
-
-
-# Default graph retriever instance (can be overridden)
-_default_graph_retriever: GraphRetriever | None = None
-
-
-def get_default_graph_retriever() -> GraphRetriever:
-    """Get or create the default graph retriever based on config."""
-    global _default_graph_retriever
-    if _default_graph_retriever is None:
-        config = get_config()
-        retriever_type = config.graph_retriever.lower()
-        if retriever_type == "mpfp":
-            _default_graph_retriever = MPFPGraphRetriever()
-            logger.info(
-                f"Using MPFP graph retriever (top_k_neighbors={_default_graph_retriever.config.top_k_neighbors})"
-            )
-        elif retriever_type == "bfs":
-            _default_graph_retriever = BFSGraphRetriever()
-            logger.info("Using BFS graph retriever")
-        elif retriever_type == "link_expansion":
-            _default_graph_retriever = LinkExpansionRetriever()
-            logger.info("Using LinkExpansion graph retriever")
-        else:
-            logger.warning(f"Unknown graph retriever '{retriever_type}', falling back to link_expansion")
-            _default_graph_retriever = LinkExpansionRetriever()
-    return _default_graph_retriever
-
-
-def set_default_graph_retriever(retriever: GraphRetriever) -> None:
-    """Set the default graph retriever (for configuration/testing)."""
-    global _default_graph_retriever
-    _default_graph_retriever = retriever
-
-
-async def retrieve_semantic_bm25_combined(
-    conn,
-    query_emb_str: str,
-    query_text: str,
-    bank_id: str,
-    fact_types: list[str],
-    limit: int,
-    tags: list[str] | None = None,
-    tags_match: TagsMatch = "any",
-    tag_groups: list[TagGroup] | None = None,
-) -> dict[str, tuple[list[RetrievalResult], list[RetrievalResult]]]:
-    """
-    Combined semantic + BM25 retrieval for multiple fact types in a single query.
-
-    Uses UNION ALL of per-fact_type subqueries so that each arm has its own
-    ORDER BY ... LIMIT, enabling the partial HNSW indexes per fact_type instead
-    of forcing a full sequential scan (which the previous window-function approach
-    caused by using PARTITION BY inside ROW_NUMBER()).
-
-    Requires partial HNSW indexes per fact_type (idx_mu_emb_world,
-    idx_mu_emb_observation, idx_mu_emb_experience), created automatically by
-    Alembic migration a3b4c5d6e7f8_add_partial_hnsw_indexes.py.
-
-    HNSW is approximate — semantic arms over-fetch by 5x (min 100) and trim to
-    limit in Python to compensate.  ef_search=200 is set globally on pool
-    connections at init time (see memory_engine.py) to improve recall on sparse
-    graphs.
-
-    fact_type values are inlined as literals (safe: they come from a controlled
-    internal enum, never from user input).
-
-    Args:
-        conn: Database connection
-        query_emb_str: Query embedding as string
-        query_text: Query text for BM25
-        bank_id: Bank ID
-        fact_types: List of fact types to retrieve
-        limit: Maximum results per method per fact type
-        tags: Optional tags to filter by
-        tags_match: Tag matching mode
-
-    Returns:
-        Dict mapping fact_type -> (semantic_results, bm25_results)
-    """
-    import re
-
-    result_dict: dict[str, tuple[list[RetrievalResult], list[RetrievalResult]]] = {ft: ([], []) for ft in fact_types}
-
-    sanitized_text = re.sub(r"[^\w\s]", " ", query_text.lower())
-    tokens = [token for token in sanitized_text.split() if token]
-
-    # Over-fetch for HNSW approximation; semantic results trimmed to limit in Python.
-    hnsw_fetch = max(limit * 5, 100)
-
-    cols = (
-        "id, text, context, event_date, occurred_start, occurred_end, mentioned_at, "
-        "fact_type, document_id, chunk_id, tags"
-    )
-    table = fq_table("memory_units")
-
-    # --- Parameter layout ---
-    # $1 = query_emb_str  (semantic arms)
-    # $2 = bank_id
-    # $3 = limit          (BM25 LIMIT; semantic uses inlined hnsw_fetch literal)
-    # $4 = bm25_text      (only when tokens present)
-    # $N = tags           (N=4 when no tokens, N=5 when tokens present)
-    # $M+ = tag_groups params (one per leaf, starting after tags param)
-    tags_param_idx = 5 if tokens else 4
-    tags_clause = build_tags_where_clause_simple(tags, tags_param_idx, match=tags_match)
-
-    # tag_groups params start immediately after the tags param slot
-    tag_groups_param_start = tags_param_idx + (1 if tags else 0)
-    groups_clause, groups_params, _ = build_tag_groups_where_clause(tag_groups, tag_groups_param_start)
-
-    # --- Semantic UNION ALL arms (one per fact_type) ---
-    # Each arm has its own ORDER BY embedding <=> $1 LIMIT {hnsw_fetch}, which
-    # lets the planner use the partial HNSW index for that fact_type.
-    sem_arms = []
-    for ft in fact_types:
-        sem_arms.append(
-            f"(SELECT {cols},"
-            f"        1 - (embedding <=> $1::vector) AS similarity,"
-            f"        NULL::float AS bm25_score,"
-            f"        'semantic' AS source"
-            f" FROM {table}"
-            f" WHERE bank_id = $2"
-            f"   AND fact_type = '{ft}'"
-            f"   AND embedding IS NOT NULL"
-            f"   AND (1 - (embedding <=> $1::vector)) >= 0.3"
-            f"   {tags_clause}"
-            f"   {groups_clause}"
-            f" ORDER BY embedding <=> $1::vector"
-            f" LIMIT {hnsw_fetch})"
-        )
-
-    arms = sem_arms
-
-    # --- BM25 UNION ALL arms (one per fact_type, only when tokens present) ---
-    if tokens:
-        config = get_config()
-        if config.text_search_extension == "vchord":
-            bm25_score_expr = (
-                "search_vector <&> to_bm25query('idx_memory_units_text_search', tokenize($4, 'llmlingua2'))"
-            )
-            bm25_order_by = f"{bm25_score_expr} DESC"
-            bm25_where_filter = ""
-            bm25_text_param: str = query_text
-        elif config.text_search_extension == "pg_textsearch":
-            bm25_score_expr = "-(text <@> to_bm25query($4, 'idx_memory_units_text_search'))"
-            bm25_order_by = "text <@> to_bm25query($4, 'idx_memory_units_text_search') ASC"
-            bm25_where_filter = ""
-            bm25_text_param = query_text
-        else:  # native
-            query_tsquery = " | ".join(tokens)
-            bm25_score_expr = "ts_rank_cd(search_vector, to_tsquery('english', $4))"
-            bm25_order_by = f"{bm25_score_expr} DESC"
-            bm25_where_filter = "AND search_vector @@ to_tsquery('english', $4)"
-            bm25_text_param = query_tsquery
-
-        for ft in fact_types:
-            arms.append(
-                f"(SELECT {cols},"
-                f"        NULL::float AS similarity,"
-                f"        {bm25_score_expr} AS bm25_score,"
-                f"        'bm25' AS source"
-                f" FROM {table}"
-                f" WHERE bank_id = $2"
-                f"   AND fact_type = '{ft}'"
-                f"   {bm25_where_filter}"
-                f"   {tags_clause}"
-                f"   {groups_clause}"
-                f" ORDER BY {bm25_order_by}"
-                f" LIMIT $3)"
-            )
-
-    query = "\nUNION ALL\n".join(arms)
-
-    params: list = [query_emb_str, bank_id, limit]
-    if tokens:
-        params.append(bm25_text_param)
-    if tags:
-        params.append(tags)
-    params.extend(groups_params)
-
-    rows = await conn.fetch(query, *params)
-
-    # Group results; trim semantic to limit (over-fetched for HNSW approximation).
-    sem_counts: dict[str, int] = {ft: 0 for ft in fact_types}
-    for r in rows:
-        row = dict(r)
-        source = row.pop("source")
-        ft = row.get("fact_type")
-        if ft not in result_dict:
-            continue
-        if source == "semantic":
-            if sem_counts[ft] < limit:
-                result_dict[ft][0].append(RetrievalResult.from_db_row(row))
-                sem_counts[ft] += 1
-        else:
-            result_dict[ft][1].append(RetrievalResult.from_db_row(row))
-
-    return result_dict
-
-
-async def retrieve_temporal_combined(
-    conn,
-    query_emb_str: str,
-    bank_id: str,
-    fact_types: list[str],
-    start_date: datetime,
-    end_date: datetime,
-    budget: int,
-    semantic_threshold: float = 0.1,
-    tags: list[str] | None = None,
-    tags_match: TagsMatch = "any",
-    tag_groups: list[TagGroup] | None = None,
-) -> dict[str, list[RetrievalResult]]:
-    """
-    Temporal retrieval for multiple fact types in a single query.
-
-    Batches the entry point query using window functions to get top-N per fact type,
-    then runs spreading for each fact type.
-
-    Args:
-        conn: Database connection
-        query_emb_str: Query embedding as string
-        bank_id: Bank ID
-        fact_types: List of fact types to retrieve
-        start_date: Start of time range
-        end_date: End of time range
-        budget: Node budget for spreading per fact type
-        semantic_threshold: Minimum semantic similarity to include
-
-    Returns:
-        Dict mapping fact_type -> list of RetrievalResult
-    """
-    from ..memory_engine import fq_table
-
-    # Ensure dates are timezone-aware
-    if start_date.tzinfo is None:
-        start_date = start_date.replace(tzinfo=UTC)
-    if end_date.tzinfo is None:
-        end_date = end_date.replace(tzinfo=UTC)
-
-    # Build tags clause
-    # Entry point query: fixed params are $1-$6, tags at $7
-    tags_clause = build_tags_where_clause_simple(tags, 7, match=tags_match)
-    tag_groups_param_start = 7 + (1 if tags else 0)
-    groups_clause, groups_params, _ = build_tag_groups_where_clause(tag_groups, tag_groups_param_start)
-    params: list = [query_emb_str, bank_id, fact_types, start_date, end_date, semantic_threshold]
-    if tags:
-        params.append(tags)
-    params.extend(groups_params)
-
-    # Two-phase entry point query:
-    # Phase 1 (date_ranked): rank by date only — no embedding computation — for all units in
-    #   the temporal window. This lets the planner use date indexes for filtering.
-    # Phase 2 (sim_ranked): join back to memory_units for only the top-50-per-type candidates
-    #   and compute embedding similarity for that small set (≤ 50 × len(fact_types) rows).
-    # This avoids computing embedding distances for potentially thousands of date-range rows.
-    entry_points = await conn.fetch(
-        f"""
-        WITH date_ranked AS MATERIALIZED (
-            SELECT id, fact_type,
-                   ROW_NUMBER() OVER (
-                       PARTITION BY fact_type
-                       ORDER BY COALESCE(occurred_start, mentioned_at, occurred_end) DESC NULLS LAST
-                   ) AS rn
-            FROM {fq_table("memory_units")}
-            WHERE bank_id = $2
-              AND fact_type = ANY($3)
-              AND embedding IS NOT NULL
-              AND (
-                  (occurred_start IS NOT NULL AND occurred_end IS NOT NULL
-                   AND occurred_start <= $5 AND occurred_end >= $4)
-                  OR
-                  (mentioned_at IS NOT NULL AND mentioned_at BETWEEN $4 AND $5)
-                  OR
-                  (occurred_start IS NOT NULL AND occurred_start BETWEEN $4 AND $5)
-                  OR
-                  (occurred_end IS NOT NULL AND occurred_end BETWEEN $4 AND $5)
-              )
-              {tags_clause}
-              {groups_clause}
-        ),
-        sim_ranked AS (
-            SELECT mu.id, mu.text, mu.context, mu.event_date, mu.occurred_start, mu.occurred_end, mu.mentioned_at, mu.fact_type, mu.document_id, mu.chunk_id, mu.tags,
-                   1 - (mu.embedding <=> $1::vector) AS similarity,
-                   ROW_NUMBER() OVER (PARTITION BY mu.fact_type ORDER BY mu.embedding <=> $1::vector) AS sim_rn
-            FROM date_ranked dr
-            JOIN {fq_table("memory_units")} mu ON mu.id = dr.id
-            WHERE dr.rn <= 50
-              AND (1 - (mu.embedding <=> $1::vector)) >= $6
-        )
-        SELECT id, text, context, event_date, occurred_start, occurred_end, mentioned_at, fact_type, document_id, chunk_id, tags, similarity
-        FROM sim_ranked
-        WHERE sim_rn <= 10
-        """,
-        *params,
-    )
-
-    if not entry_points:
-        return {ft: [] for ft in fact_types}
-
-    # Group entry points by fact type
-    entries_by_ft: dict[str, list] = {ft: [] for ft in fact_types}
-    for ep in entry_points:
-        ft = ep["fact_type"]
-        if ft in entries_by_ft:
-            entries_by_ft[ft].append(ep)
-
-    # Calculate shared temporal parameters
-    total_days = (end_date - start_date).total_seconds() / 86400
-    mid_date = start_date + (end_date - start_date) / 2
-
-    # Process each fact type (spreading needs to stay per fact type due to link filtering)
-    results_by_ft: dict[str, list[RetrievalResult]] = {}
-
-    for ft in fact_types:
-        ft_entry_points = entries_by_ft.get(ft, [])
-        if not ft_entry_points:
-            results_by_ft[ft] = []
-            continue
-
-        results = []
-        visited = set()
-        node_scores = {}
-
-        # Process entry points
-        for ep in ft_entry_points:
-            unit_id = str(ep["id"])
-            visited.add(unit_id)
-
-            # Calculate temporal proximity
-            best_date = None
-            if ep["occurred_start"] is not None and ep["occurred_end"] is not None:
-                best_date = ep["occurred_start"] + (ep["occurred_end"] - ep["occurred_start"]) / 2
-            elif ep["occurred_start"] is not None:
-                best_date = ep["occurred_start"]
-            elif ep["occurred_end"] is not None:
-                best_date = ep["occurred_end"]
-            elif ep["mentioned_at"] is not None:
-                best_date = ep["mentioned_at"]
-
-            if best_date:
-                days_from_mid = abs((best_date - mid_date).total_seconds() / 86400)
-                temporal_proximity = 1.0 - min(days_from_mid / (total_days / 2), 1.0) if total_days > 0 else 1.0
-            else:
-                temporal_proximity = 0.5
-
-            ep_result = RetrievalResult.from_db_row(dict(ep))
-            ep_result.temporal_score = temporal_proximity
-            ep_result.temporal_proximity = temporal_proximity
-            results.append(ep_result)
-            node_scores[unit_id] = (ep["similarity"], 1.0)
-
-        # Spreading through temporal links (same as single-fact-type version)
-        frontier = list(node_scores.keys())
-        budget_remaining = budget - len(ft_entry_points)
-        batch_size = 20
-        # Per-source neighbor limit: lets the planner use the composite index
-        # (from_unit_id, link_type, weight DESC) with early termination, avoiding
-        # a full scan of all links from all source nodes before sorting.
-        per_source_limit = 10
-        # Safety cap on BFS iterations to prevent runaway spreading in dense graphs.
-        max_iterations = 5
-        iteration = 0
-
-        # Build tags clause for spreading (use param 7 since 1-6 are used)
-        spreading_tags_clause = build_tags_where_clause_simple(tags, 7, table_alias="mu.", match=tags_match)
-        spreading_groups_param_start = 7 + (1 if tags else 0)
-        spreading_groups_clause, spreading_groups_params, _ = build_tag_groups_where_clause(
-            tag_groups, spreading_groups_param_start, table_alias="mu."
-        )
-
-        while frontier and budget_remaining > 0 and iteration < max_iterations:
-            iteration += 1
-            batch_ids = frontier[:batch_size]
-            frontier = frontier[batch_size:]
-
-            # $1=query_emb, $2=batch_ids, $3=fact_type, $4=threshold, $5=per_source_limit, $6=bank_id, $7=tags, $M+=tag_groups
-            spreading_params = [query_emb_str, batch_ids, ft, semantic_threshold, per_source_limit, bank_id]
-            if tags:
-                spreading_params.append(tags)
-            spreading_params.extend(spreading_groups_params)
-
-            # LATERAL join: for each source node, fetch top-K neighbors by weight using
-            # the existing idx_memory_links_from_type_weight index with early-exit semantics.
-            # This avoids scanning all temporal links from all source nodes before sorting.
-            # bank_id on memory_units lets the planner use idx_memory_units_bank_fact_type.
-            neighbors = await conn.fetch(
-                f"""
-                SELECT src.from_unit_id, mu.id, mu.text, mu.context, mu.event_date, mu.occurred_start, mu.occurred_end, mu.mentioned_at, mu.fact_type, mu.document_id, mu.chunk_id, mu.tags,
-                       l.weight, l.link_type,
-                       1 - (mu.embedding <=> $1::vector) AS similarity
-                FROM unnest($2::uuid[]) AS src(from_unit_id)
-                CROSS JOIN LATERAL (
-                    SELECT ml.to_unit_id, ml.weight, ml.link_type
-                    FROM {fq_table("memory_links")} ml
-                    WHERE ml.from_unit_id = src.from_unit_id
-                      AND ml.link_type IN ('temporal', 'causes', 'caused_by', 'enables', 'prevents')
-                      AND ml.weight >= 0.1
-                    ORDER BY ml.weight DESC
-                    LIMIT $5
-                ) l
-                JOIN {fq_table("memory_units")} mu ON mu.id = l.to_unit_id
-                WHERE mu.bank_id = $6
-                  AND mu.fact_type = $3
-                  AND mu.embedding IS NOT NULL
-                  AND (1 - (mu.embedding <=> $1::vector)) >= $4
-                  {spreading_tags_clause}
-                  {spreading_groups_clause}
-                """,
-                *spreading_params,
-            )
-
-            for n in neighbors:
-                neighbor_id = str(n["id"])
-                if neighbor_id in visited:
-                    continue
-
-                visited.add(neighbor_id)
-                budget_remaining -= 1
-
-                parent_id = str(n["from_unit_id"])
-                _, parent_temporal_score = node_scores.get(parent_id, (0.5, 0.5))
-
-                neighbor_best_date = None
-                if n["occurred_start"] is not None and n["occurred_end"] is not None:
-                    neighbor_best_date = n["occurred_start"] + (n["occurred_end"] - n["occurred_start"]) / 2
-                elif n["occurred_start"] is not None:
-                    neighbor_best_date = n["occurred_start"]
-                elif n["occurred_end"] is not None:
-                    neighbor_best_date = n["occurred_end"]
-                elif n["mentioned_at"] is not None:
-                    neighbor_best_date = n["mentioned_at"]
-
-                if neighbor_best_date:
-                    days_from_mid = abs((neighbor_best_date - mid_date).total_seconds() / 86400)
-                    neighbor_temporal_proximity = (
-                        1.0 - min(days_from_mid / (total_days / 2), 1.0) if total_days > 0 else 1.0
-                    )
-                else:
-                    neighbor_temporal_proximity = 0.3
-
-                link_type = n["link_type"]
-                if link_type in ("causes", "caused_by"):
-                    causal_boost = 2.0
-                elif link_type in ("enables", "prevents"):
-                    causal_boost = 1.5
-                else:
-                    causal_boost = 1.0
-
-                propagated_temporal = parent_temporal_score * n["weight"] * causal_boost * 0.7
-                combined_temporal = max(neighbor_temporal_proximity, propagated_temporal)
-
-                neighbor_result = RetrievalResult.from_db_row(dict(n))
-                neighbor_result.temporal_score = combined_temporal
-                neighbor_result.temporal_proximity = neighbor_temporal_proximity
-                results.append(neighbor_result)
-
-                if budget_remaining > 0 and combined_temporal > 0.2:
-                    node_scores[neighbor_id] = (n["similarity"], combined_temporal)
-                    frontier.append(neighbor_id)
-
-                if budget_remaining <= 0:
-                    break
-
-        results_by_ft[ft] = results
-
-    return results_by_ft
-
-
-async def retrieve_all_fact_types_parallel(
-    pool,
-    query_text: str,
-    query_embedding_str: str,
-    bank_id: str,
-    fact_types: list[str],
-    thinking_budget: int,
-    question_date: datetime | None = None,
-    query_analyzer: Optional["QueryAnalyzer"] = None,
-    graph_retriever: GraphRetriever | None = None,
-    tags: list[str] | None = None,
-    tags_match: TagsMatch = "any",
-    tag_groups: list[TagGroup] | None = None,
-) -> MultiFactTypeRetrievalResult:
-    """
-    Optimized retrieval for multiple fact types using batched queries.
-
-    This reduces database round-trips by:
-    1. Combining semantic + BM25 into one CTE query for ALL fact types (1 query instead of 2N)
-    2. Running graph retrieval per fact type in parallel (N parallel tasks)
-    3. Running temporal retrieval per fact type in parallel (N parallel tasks)
-
-    Args:
-        pool: Database connection pool
-        query_text: Query text
-        query_embedding_str: Query embedding as string
-        bank_id: Bank ID
-        fact_types: List of fact types to retrieve
-        thinking_budget: Budget for graph traversal and retrieval limits
-        question_date: Optional date when question was asked (for temporal filtering)
-        query_analyzer: Query analyzer to use (defaults to TransformerQueryAnalyzer)
-        graph_retriever: Graph retrieval strategy (defaults to configured retriever)
-
-    Returns:
-        MultiFactTypeRetrievalResult with results organized by fact type
-    """
-    import time
-
-    retriever = graph_retriever or get_default_graph_retriever()
-    start_time = time.time()
-    timings: dict[str, float] = {}
-
-    # Step 1: Extract temporal constraint first (CPU work, no DB)
-    # Do this before DB queries so we know if we need temporal retrieval
-    temporal_extraction_start = time.time()
-    from .temporal_extraction import extract_temporal_constraint
-
-    temporal_constraint = extract_temporal_constraint(query_text, reference_date=question_date, analyzer=query_analyzer)
-    temporal_extraction_time = time.time() - temporal_extraction_start
-    timings["temporal_extraction"] = temporal_extraction_time
-
-    # Step 2: Run semantic + BM25 + temporal combined in ONE connection!
-    # This reduces connection usage from 2 to 1 for these operations
-    semantic_bm25_start = time.time()
-    temporal_results_by_ft: dict[str, list[RetrievalResult]] = {}
-    temporal_time = 0.0
-
-    async with acquire_with_retry(pool) as conn:
-        conn_wait = time.time() - semantic_bm25_start
-
-        # Semantic + BM25 combined
-        semantic_bm25_results = await retrieve_semantic_bm25_combined(
-            conn,
-            query_embedding_str,
-            query_text,
-            bank_id,
-            fact_types,
-            thinking_budget,
-            tags=tags,
-            tags_match=tags_match,
-            tag_groups=tag_groups,
-        )
-        semantic_bm25_time = time.time() - semantic_bm25_start
-
-        # Temporal combined (if constraint detected) - same connection!
-        if temporal_constraint:
-            tc_start, tc_end = temporal_constraint
-            temporal_start = time.time()
-            temporal_results_by_ft = await retrieve_temporal_combined(
-                conn,
-                query_embedding_str,
-                bank_id,
-                fact_types,
-                tc_start,
-                tc_end,
-                budget=thinking_budget,
-                semantic_threshold=0.1,
-                tags=tags,
-                tags_match=tags_match,
-                tag_groups=tag_groups,
-            )
-            temporal_time = time.time() - temporal_start
-
-    timings["semantic_bm25_combined"] = semantic_bm25_time
-    timings["temporal_combined"] = temporal_time
-
-    # Step 3: Run graph retrieval for each fact type in parallel
-    async def run_graph_for_fact_type(ft: str) -> tuple[str, list[RetrievalResult], float, MPFPTimings | None]:
-        graph_start = time.time()
-        results, mpfp_timing = await retriever.retrieve(
-            pool=pool,
-            query_embedding_str=query_embedding_str,
-            bank_id=bank_id,
-            fact_type=ft,
-            budget=thinking_budget,
-            query_text=query_text,
-            semantic_seeds=None,
-            temporal_seeds=None,
-            tags=tags,
-            tags_match=tags_match,
-            tag_groups=tag_groups,
-        )
-        return ft, results, time.time() - graph_start, mpfp_timing
-
-    # Run graph for all fact types in parallel
-    graph_tasks = [run_graph_for_fact_type(ft) for ft in fact_types]
-    graph_results_list = await asyncio.gather(*graph_tasks)
-
-    # Organize results by fact type
-    results_by_fact_type: dict[str, ParallelRetrievalResult] = {}
-    max_conn_wait = conn_wait  # Single connection for semantic+bm25+temporal
-    all_mpfp_timings: list[MPFPTimings] = []
-
-    for ft in fact_types:
-        # Get semantic + bm25 results for this fact type
-        semantic_results, bm25_results = semantic_bm25_results.get(ft, ([], []))
-
-        # Find graph results for this fact type
-        graph_results = []
-        graph_time = 0.0
-        mpfp_timing = None
-        for gr in graph_results_list:
-            if gr[0] == ft:
-                graph_results = gr[1]
-                graph_time = gr[2]
-                mpfp_timing = gr[3]
-                if mpfp_timing:
-                    all_mpfp_timings.append(mpfp_timing)
-                break
-
-        # Get temporal results for this fact type from combined result
-        temporal_results = temporal_results_by_ft.get(ft) if temporal_constraint else None
-        if temporal_results is not None and len(temporal_results) == 0:
-            temporal_results = None
-
-        results_by_fact_type[ft] = ParallelRetrievalResult(
-            semantic=semantic_results,
-            bm25=bm25_results,
-            graph=graph_results,
-            temporal=temporal_results,
-            timings={
-                "semantic": semantic_bm25_time / 2,  # Approximate split
-                "bm25": semantic_bm25_time / 2,
-                "graph": graph_time,
-                "temporal": temporal_time,  # Same for all fact types (single query)
-                "temporal_extraction": temporal_extraction_time,
-            },
-            temporal_constraint=temporal_constraint,
-            mpfp_timings=[mpfp_timing] if mpfp_timing else [],
-            max_conn_wait=max_conn_wait,
-        )
-
-    total_time = time.time() - start_time
-    timings["total"] = total_time
-
-    return MultiFactTypeRetrievalResult(
-        results_by_fact_type=results_by_fact_type,
-        timings=timings,
-        max_conn_wait=max_conn_wait,
-    )

hindsight-api-slim/hindsight_api/engine/search/tags.py

@@ -1,390 +0,0 @@
-"""
-Tags filtering utilities for retrieval.
-
-Provides SQL building functions for filtering memories by tags.
-Supports four matching modes via TagsMatch enum:
-- "any": OR matching, includes untagged memories (default, backward compatible)
-- "all": AND matching, includes untagged memories
-- "any_strict": OR matching, excludes untagged memories
-- "all_strict": AND matching, excludes untagged memories
-
-OR matching (any/any_strict): Memory matches if ANY of its tags overlap with request tags
-AND matching (all/all_strict): Memory matches if ALL request tags are present in its tags
-"""
-
-from __future__ import annotations
-
-from typing import Annotated, Literal
-
-from pydantic import BaseModel, ConfigDict, Field
-
-TagsMatch = Literal["any", "all", "any_strict", "all_strict"]
-
-
-def _parse_tags_match(match: TagsMatch) -> tuple[str, bool]:
-    """
-    Parse TagsMatch into operator and include_untagged flag.
-
-    Returns:
-        Tuple of (operator, include_untagged)
-        - operator: "&&" for any/any_strict, "@>" for all/all_strict
-        - include_untagged: True for any/all, False for any_strict/all_strict
-    """
-    if match == "any":
-        return "&&", True
-    elif match == "all":
-        return "@>", True
-    elif match == "any_strict":
-        return "&&", False
-    elif match == "all_strict":
-        return "@>", False
-    else:
-        # Default to "any" behavior
-        return "&&", True
-
-
-def build_tags_where_clause(
-    tags: list[str] | None,
-    param_offset: int = 1,
-    table_alias: str = "",
-    match: TagsMatch = "any",
-) -> tuple[str, list, int]:
-    """
-    Build a SQL WHERE clause for filtering by tags.
-
-    Supports four matching modes:
-    - "any" (default): OR matching, includes untagged memories
-    - "all": AND matching, includes untagged memories
-    - "any_strict": OR matching, excludes untagged memories
-    - "all_strict": AND matching, excludes untagged memories
-
-    Args:
-        tags: List of tags to filter by. If None or empty, returns empty clause (no filtering).
-        param_offset: Starting parameter number for SQL placeholders (default 1).
-        table_alias: Optional table alias prefix (e.g., "mu." for "memory_units mu").
-        match: Matching mode. Defaults to "any".
-
-    Returns:
-        Tuple of (sql_clause, params, next_param_offset):
-        - sql_clause: SQL WHERE clause string
-        - params: List of parameter values to bind
-        - next_param_offset: Next available parameter number
-
-    Example:
-        >>> clause, params, next_offset = build_tags_where_clause(['user_a'], 3, 'mu.', 'any_strict')
-        >>> print(clause)  # "AND mu.tags IS NOT NULL AND mu.tags != '{}' AND mu.tags && $3"
-    """
-    if not tags:
-        return "", [], param_offset
-
-    column = f"{table_alias}tags" if table_alias else "tags"
-    operator, include_untagged = _parse_tags_match(match)
-
-    if include_untagged:
-        # Include untagged memories (NULL or empty array) OR matching tags
-        clause = f"AND ({column} IS NULL OR {column} = '{{}}' OR {column} {operator} ${param_offset})"
-    else:
-        # Strict: only memories with matching tags (exclude NULL and empty)
-        clause = f"AND {column} IS NOT NULL AND {column} != '{{}}' AND {column} {operator} ${param_offset}"
-
-    return clause, [tags], param_offset + 1
-
-
-def build_tags_where_clause_simple(
-    tags: list[str] | None,
-    param_num: int,
-    table_alias: str = "",
-    match: TagsMatch = "any",
-) -> str:
-    """
-    Build a simple SQL WHERE clause for tags filtering.
-
-    This is a convenience version that returns just the clause string,
-    assuming the caller will add the tags array to their params list.
-
-    Args:
-        tags: List of tags to filter by. If None or empty, returns empty string.
-        param_num: Parameter number to use in the clause.
-        table_alias: Optional table alias prefix.
-        match: Matching mode. Defaults to "any".
-
-    Returns:
-        SQL clause string or empty string.
-    """
-    if not tags:
-        return ""
-
-    column = f"{table_alias}tags" if table_alias else "tags"
-    operator, include_untagged = _parse_tags_match(match)
-
-    if include_untagged:
-        # Include untagged memories (NULL or empty array) OR matching tags
-        return f"AND ({column} IS NULL OR {column} = '{{}}' OR {column} {operator} ${param_num})"
-    else:
-        # Strict: only memories with matching tags (exclude NULL and empty)
-        return f"AND {column} IS NOT NULL AND {column} != '{{}}' AND {column} {operator} ${param_num}"
-
-
-def filter_results_by_tags(
-    results: list,
-    tags: list[str] | None,
-    match: TagsMatch = "any",
-) -> list:
-    """
-    Filter retrieval results by tags in Python (for post-processing).
-
-    Used when SQL filtering isn't possible (e.g., graph traversal results).
-
-    Args:
-        results: List of RetrievalResult objects with a 'tags' attribute.
-        tags: List of tags to filter by. If None or empty, returns all results.
-        match: Matching mode. Defaults to "any".
-
-    Returns:
-        Filtered list of results.
-    """
-    if not tags:
-        return results
-
-    _, include_untagged = _parse_tags_match(match)
-    is_any_match = match in ("any", "any_strict")
-
-    tags_set = set(tags)
-    filtered = []
-
-    for result in results:
-        result_tags = getattr(result, "tags", None)
-
-        # Check if untagged
-        is_untagged = result_tags is None or len(result_tags) == 0
-
-        if is_untagged:
-            if include_untagged:
-                filtered.append(result)
-            # else: skip untagged
-        else:
-            result_tags_set = set(result_tags)
-            if is_any_match:
-                # Any overlap
-                if result_tags_set & tags_set:
-                    filtered.append(result)
-            else:
-                # All tags must be present
-                if tags_set <= result_tags_set:
-                    filtered.append(result)
-
-    return filtered
-
-
-# =============================================================================
-# Compound tag group models (recursive boolean expressions)
-# =============================================================================
-
-
-class TagGroupLeaf(BaseModel):
-    """A leaf tag filter: matches memories by tag list and match mode."""
-
-    tags: list[str]
-    match: TagsMatch = "any_strict"
-
-
-class TagGroupAnd(BaseModel):
-    """Compound AND group: all child filters must match."""
-
-    model_config = ConfigDict(populate_by_name=True)
-    filters: list[TagGroup] = Field(alias="and")
-
-
-class TagGroupOr(BaseModel):
-    """Compound OR group: at least one child filter must match."""
-
-    model_config = ConfigDict(populate_by_name=True)
-    filters: list[TagGroup] = Field(alias="or")
-
-
-class TagGroupNot(BaseModel):
-    """Compound NOT group: child filter must NOT match."""
-
-    model_config = ConfigDict(populate_by_name=True)
-    filter: TagGroup = Field(alias="not")
-
-
-# TagGroup is a discriminated union; Pydantic will try left-to-right.
-# TagGroupLeaf is identified by the presence of 'tags'.
-# TagGroupAnd / TagGroupOr / TagGroupNot are compound (no 'tags' key).
-TagGroup = Annotated[
-    TagGroupLeaf | TagGroupAnd | TagGroupOr | TagGroupNot,
-    Field(union_mode="left_to_right"),
-]
-
-# Rebuild forward-reference models so recursive TagGroup is resolved.
-TagGroupAnd.model_rebuild()
-TagGroupOr.model_rebuild()
-TagGroupNot.model_rebuild()
-
-
-# =============================================================================
-# SQL builder for compound tag groups
-# =============================================================================
-
-
-def _build_group_clause(
-    group: TagGroup,
-    param_offset: int,
-    table_alias: str,
-) -> tuple[str, list, int]:
-    """
-    Recursively build an inner SQL clause (no leading AND/OR) for a single TagGroup.
-
-    Returns:
-        (inner_clause, params, next_param_offset)
-    """
-    if isinstance(group, TagGroupLeaf):
-        column = f"{table_alias}tags" if table_alias else "tags"
-        operator, include_untagged = _parse_tags_match(group.match)
-        if include_untagged:
-            clause = f"({column} IS NULL OR {column} = '{{}}' OR {column} {operator} ${param_offset})"
-        else:
-            clause = f"({column} IS NOT NULL AND {column} != '{{}}' AND {column} {operator} ${param_offset})"
-        return clause, [group.tags], param_offset + 1
-
-    elif isinstance(group, TagGroupAnd):
-        parts = []
-        params: list = []
-        offset = param_offset
-        for child in group.filters:
-            child_clause, child_params, offset = _build_group_clause(child, offset, table_alias)
-            parts.append(child_clause)
-            params.extend(child_params)
-        inner = " AND ".join(parts)
-        return f"({inner})", params, offset
-
-    elif isinstance(group, TagGroupOr):
-        parts = []
-        params = []
-        offset = param_offset
-        for child in group.filters:
-            child_clause, child_params, offset = _build_group_clause(child, offset, table_alias)
-            parts.append(child_clause)
-            params.extend(child_params)
-        inner = " OR ".join(parts)
-        return f"({inner})", params, offset
-
-    elif isinstance(group, TagGroupNot):
-        child_clause, child_params, next_offset = _build_group_clause(group.filter, param_offset, table_alias)
-        return f"NOT {child_clause}", child_params, next_offset
-
-    else:
-        # Should never happen with proper Pydantic validation
-        return "", [], param_offset
-
-
-def build_tag_groups_where_clause(
-    tag_groups: list[TagGroup] | None,
-    param_offset: int,
-    table_alias: str = "",
-) -> tuple[str, list, int]:
-    """
-    Build a SQL WHERE clause for compound tag group filtering.
-
-    Top-level groups are AND-ed together. Each group is a recursive boolean
-    expression (leaf, and, or, not).
-
-    Args:
-        tag_groups: List of TagGroup objects. If None or empty, returns empty clause.
-        param_offset: Starting parameter number for SQL placeholders.
-        table_alias: Optional table alias prefix (e.g., "mu." for "memory_units mu").
-
-    Returns:
-        Tuple of (sql_clause, params, next_param_offset):
-        - sql_clause: SQL WHERE clause string starting with "AND" (or empty string)
-        - params: List of parameter values to bind (one per leaf node)
-        - next_param_offset: Next available parameter number
-
-    Example:
-        >>> groups = [TagGroupLeaf(tags=["user:alice"], match="all_strict")]
-        >>> clause, params, next_offset = build_tag_groups_where_clause(groups, 3)
-        >>> print(clause)  # "AND (tags IS NOT NULL AND tags != '{}' AND tags @> $3)"
-    """
-    if not tag_groups:
-        return "", [], param_offset
-
-    all_params: list = []
-    all_clauses: list[str] = []
-    offset = param_offset
-
-    for group in tag_groups:
-        inner_clause, group_params, offset = _build_group_clause(group, offset, table_alias)
-        all_clauses.append(inner_clause)
-        all_params.extend(group_params)
-
-    combined = " AND ".join(all_clauses)
-    return f"AND {combined}", all_params, offset
-
-
-# =============================================================================
-# Python-side filter for compound tag groups (post-retrieval filtering)
-# =============================================================================
-
-
-def _match_group(result: object, group: TagGroup) -> bool:
-    """
-    Recursively evaluate a TagGroup against a retrieval result.
-
-    Args:
-        result: Any object with a 'tags' attribute (list[str] or None).
-        group: The TagGroup to evaluate.
-
-    Returns:
-        True if the result matches the group, False otherwise.
-    """
-    if isinstance(group, TagGroupLeaf):
-        result_tags = getattr(result, "tags", None)
-        is_untagged = result_tags is None or len(result_tags) == 0
-        _, include_untagged = _parse_tags_match(group.match)
-        is_any_match = group.match in ("any", "any_strict")
-        tags_set = set(group.tags)
-
-        if is_untagged:
-            return include_untagged
-        else:
-            result_tags_set = set(result_tags)
-            if is_any_match:
-                return bool(result_tags_set & tags_set)
-            else:
-                return tags_set <= result_tags_set
-
-    elif isinstance(group, TagGroupAnd):
-        return all(_match_group(result, child) for child in group.filters)
-
-    elif isinstance(group, TagGroupOr):
-        return any(_match_group(result, child) for child in group.filters)
-
-    elif isinstance(group, TagGroupNot):
-        return not _match_group(result, group.filter)
-
-    else:
-        return True
-
-
-def filter_results_by_tag_groups(
-    results: list,
-    tag_groups: list[TagGroup] | None,
-) -> list:
-    """
-    Filter retrieval results by compound tag groups in Python (for post-processing).
-
-    Used when SQL filtering isn't possible (e.g., graph traversal results).
-    Top-level groups are AND-ed together.
-
-    Args:
-        results: List of RetrievalResult objects with a 'tags' attribute.
-        tag_groups: List of TagGroup objects. If None or empty, returns all results.
-
-    Returns:
-        Filtered list of results where ALL top-level groups match.
-    """
-    if not tag_groups:
-        return results
-
-    return [r for r in results if all(_match_group(r, group) for group in tag_groups)]

hindsight-api-slim/hindsight_api/engine/storage/__init__.py

@@ -1,79 +0,0 @@
-"""File storage backends for uploaded files."""
-
-from collections.abc import Callable
-
-from .base import FileStorage
-from .postgresql import PostgreSQLFileStorage
-
-__all__ = ["FileStorage", "PostgreSQLFileStorage", "create_file_storage"]
-
-
-def create_file_storage(
-    storage_type: str,
-    pool_getter: Callable | None = None,
-    schema: str | None = None,
-    schema_getter: Callable | None = None,
-    **kwargs,
-) -> FileStorage:
-    """
-    Create file storage backend based on configuration.
-
-    Args:
-        storage_type: "native" (PostgreSQL BYTEA) or "s3" (S3-compatible object storage)
-        pool_getter: Database pool getter (required for native)
-        schema: Static database schema (for native single-tenant)
-        schema_getter: Callable returning current schema at query time (for native multi-tenant)
-        **kwargs: Additional args passed to storage backend
-
-    Returns:
-        FileStorage instance
-
-    Raises:
-        ValueError: If storage_type is unknown or required args are missing
-    """
-    if storage_type == "native":
-        if not pool_getter:
-            raise ValueError("pool_getter required for native (PostgreSQL) storage")
-        return PostgreSQLFileStorage(pool_getter=pool_getter, schema=schema, schema_getter=schema_getter)
-    elif storage_type == "s3":
-        from ...config import get_config
-        from .s3 import S3FileStorage
-
-        config = get_config()
-        bucket = config.file_storage_s3_bucket
-        if not bucket:
-            raise ValueError("HINDSIGHT_API_FILE_STORAGE_S3_BUCKET is required for S3 storage")
-        return S3FileStorage(
-            bucket=bucket,
-            region=config.file_storage_s3_region,
-            endpoint=config.file_storage_s3_endpoint,
-            access_key_id=config.file_storage_s3_access_key_id,
-            secret_access_key=config.file_storage_s3_secret_access_key,
-        )
-    elif storage_type == "gcs":
-        from ...config import get_config
-        from .gcs import GCSFileStorage
-
-        config = get_config()
-        bucket = config.file_storage_gcs_bucket
-        if not bucket:
-            raise ValueError("HINDSIGHT_API_FILE_STORAGE_GCS_BUCKET is required for GCS storage")
-        return GCSFileStorage(
-            bucket=bucket,
-            service_account_key=config.file_storage_gcs_service_account_key,
-        )
-    elif storage_type == "azure":
-        from ...config import get_config
-        from .azure import AzureFileStorage
-
-        config = get_config()
-        container = config.file_storage_azure_container
-        if not container:
-            raise ValueError("HINDSIGHT_API_FILE_STORAGE_AZURE_CONTAINER is required for Azure storage")
-        return AzureFileStorage(
-            container_name=container,
-            account_name=config.file_storage_azure_account_name,
-            account_key=config.file_storage_azure_account_key,
-        )
-    else:
-        raise ValueError(f"Unknown storage type: {storage_type}. Supported: 'native', 's3', 'gcs', 'azure'.")

hindsight-api-slim/hindsight_api/engine/storage/azure.py

@@ -1,62 +0,0 @@
-"""Azure Blob Storage backend using obstore."""
-
-import logging
-from datetime import timedelta
-
-import obstore as obs
-from obstore.store import AzureStore
-
-from .base import FileStorage
-
-logger = logging.getLogger(__name__)
-
-
-class AzureFileStorage(FileStorage):
-    """
-    Azure Blob Storage backend.
-
-    Uses obstore (Rust-backed) for high-throughput async access to Azure Blob Storage.
-    Supports account key, SAS token, and default Azure credentials.
-    """
-
-    def __init__(
-        self,
-        container_name: str,
-        account_name: str | None = None,
-        account_key: str | None = None,
-    ):
-        kwargs: dict = {}
-        if account_name:
-            kwargs["account_name"] = account_name
-        if account_key:
-            kwargs["account_key"] = account_key
-
-        self._store = AzureStore(container_name, **kwargs)
-        logger.info(f"Initialized Azure file storage: container={container_name}, account={account_name}")
-
-    async def store(self, file_data: bytes, key: str, metadata: dict[str, str] | None = None) -> str:
-        await obs.put_async(self._store, key, file_data)
-        logger.debug(f"Stored file {key} ({len(file_data)} bytes) in Azure")
-        return key
-
-    async def retrieve(self, key: str) -> bytes:
-        try:
-            response = await obs.get_async(self._store, key)
-            return await response.bytes_async()
-        except Exception as e:
-            if "not found" in str(e).lower() or "BlobNotFound" in str(e):
-                raise FileNotFoundError(f"File not found: {key}") from e
-            raise
-
-    async def delete(self, key: str) -> None:
-        await obs.delete_async(self._store, key)
-
-    async def exists(self, key: str) -> bool:
-        try:
-            await obs.head_async(self._store, key)
-            return True
-        except Exception:
-            return False
-
-    async def get_download_url(self, key: str, expires_in: int = 3600) -> str:
-        return await obs.sign_async(self._store, "GET", key, timedelta(seconds=expires_in))

hindsight-api-slim/hindsight_api/engine/storage/base.py

@@ -1,83 +0,0 @@
-"""Abstract base class for file storage backends."""
-
-from abc import ABC, abstractmethod
-
-
-class FileStorage(ABC):
-    """Abstract base for file storage backends."""
-
-    @abstractmethod
-    async def store(
-        self,
-        file_data: bytes,
-        key: str,
-        metadata: dict[str, str] | None = None,
-    ) -> str:
-        """
-        Store file and return storage key.
-
-        Args:
-            file_data: Raw file bytes
-            key: Storage key (e.g., "banks/{bank_id}/files/{file_id}.pdf")
-            metadata: Optional metadata to store with file
-
-        Returns:
-            Storage key that can be used to retrieve the file
-        """
-        pass
-
-    @abstractmethod
-    async def retrieve(self, key: str) -> bytes:
-        """
-        Retrieve file by storage key.
-
-        Args:
-            key: Storage key
-
-        Returns:
-            File data as bytes
-
-        Raises:
-            FileNotFoundError: If file does not exist
-        """
-        pass
-
-    @abstractmethod
-    async def delete(self, key: str) -> None:
-        """
-        Delete file by storage key.
-
-        Args:
-            key: Storage key
-        """
-        pass
-
-    @abstractmethod
-    async def exists(self, key: str) -> bool:
-        """
-        Check if file exists.
-
-        Args:
-            key: Storage key
-
-        Returns:
-            True if file exists, False otherwise
-        """
-        pass
-
-    @abstractmethod
-    async def get_download_url(self, key: str, expires_in: int = 3600) -> str:
-        """
-        Get a URL for downloading the file.
-
-        For PostgreSQL storage, this might be a relative API path.
-        For S3, this would be a pre-signed URL.
-
-        Args:
-            key: Storage key
-            expires_in: Expiration time in seconds (may be ignored for some backends)
-
-        Returns:
-            Download URL or path
-        """
-        pass