fix

.claude-plugin/marketplace.json

@@ -1,15 +0,0 @@
-{
-  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
-  "name": "hindsight",
-  "description": "Official Hindsight integrations for Claude Code",
-  "owner": {
-    "name": "vectorize-io"
-  },
-  "plugins": [
-    {
-      "name": "hindsight-memory",
-      "description": "Automatic long-term memory for Claude Code via Hindsight",
-      "source": "./hindsight-integrations/claude-code"
-    }
-  ]
-}

.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, volcano
+# Supported providers: openai, groq, ollama, gemini, anthropic, lmstudio, vertexai
 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
@@ -20,11 +20,6 @@ HINDSIGHT_API_LLM_BASE_URL=https://api.openai.com/v1
 # 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
@@ -44,7 +39,6 @@ HINDSIGHT_API_LOG_LEVEL=info
 
 # Database (Optional - uses embedded pg0 by default)
 # HINDSIGHT_API_DATABASE_URL=postgresql://user:pass@host:5432/db
-# HINDSIGHT_API_MIGRATION_DATABASE_URL=  # Direct PostgreSQL URL for migrations (bypasses PgBouncer). Falls back to DATABASE_URL.
 # HINDSIGHT_API_DATABASE_SCHEMA=public  # PostgreSQL schema name (default: public)
 
 # Vector Extension (Optional - uses pgvector by default)

.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

@@ -1,111 +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" >> $GITHUB_OUTPUT
-        elif [ -f "hindsight-integrations/${{ steps.info.outputs.integration }}/package.json" ]; then
-          echo "type=typescript" >> $GITHUB_OUTPUT
-        else
-          echo "type=plugin" >> $GITHUB_OUTPUT
-        fi
-
-    # ── Python integrations (litellm, pydantic-ai, crewai) ──────────────────
-
-    - name: Install uv
-      if: steps.type.outputs.type == 'python'
-      uses: astral-sh/setup-uv@v7
-      with:
-        enable-cache: true
-
-    - name: Set up Python
-      if: steps.type.outputs.type == 'python'
-      uses: actions/setup-python@v6
-      with:
-        python-version-file: ".python-version"
-
-    - name: Build Python package
-      if: steps.type.outputs.type == 'python'
-      working-directory: ./hindsight-integrations/${{ 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) ────────────────────
-
-    # ── Plugin integrations (claude-code) — no package to publish ───────────
-
-    - name: Plugin release
-      if: steps.type.outputs.type == 'plugin'
-      run: |
-        echo "Plugin integration ${{ steps.info.outputs.integration }} v${{ steps.info.outputs.version }} — no package to publish."
-        echo "Users install via: claude plugin marketplace add vectorize-io/hindsight --sparse hindsight-integrations"
-
-    # ── 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'
@@ -144,21 +133,119 @@ 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
         retention-days: 1
 
+  release-openclaw-integration:
+    runs-on: ubuntu-latest
+    environment: npm
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Node.js
+      uses: actions/setup-node@v4
+      with:
+        node-version: '22'
+        registry-url: 'https://registry.npmjs.org'
+
+    - name: Install dependencies
+      working-directory: ./hindsight-integrations/openclaw
+      run: npm ci
+
+    - name: Build
+      working-directory: ./hindsight-integrations/openclaw
+      run: npm run build
+
+    - name: Publish to npm
+      working-directory: ./hindsight-integrations/openclaw
+      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: ${{ secrets.NPM_TOKEN }}
+
+    - name: Pack for GitHub release
+      working-directory: ./hindsight-integrations/openclaw
+      run: npm pack
+
+    - name: Upload artifacts
+      uses: actions/upload-artifact@v4
+      with:
+        name: openclaw-integration
+        path: hindsight-integrations/openclaw/*.tgz
+        retention-days: 1
+
+  release-ai-sdk-integration:
+    runs-on: ubuntu-latest
+    environment: npm
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Node.js
+      uses: actions/setup-node@v4
+      with:
+        node-version: '22'
+        registry-url: 'https://registry.npmjs.org'
+
+    - name: Install dependencies
+      working-directory: ./hindsight-integrations/ai-sdk
+      run: npm ci
+
+    - name: Build
+      working-directory: ./hindsight-integrations/ai-sdk
+      run: npm run build
+
+    - name: Publish to npm
+      working-directory: ./hindsight-integrations/ai-sdk
+      run: |
+        set +e
+        OUTPUT=$(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 }}
+
+    - name: Pack for GitHub release
+      working-directory: ./hindsight-integrations/ai-sdk
+      run: npm pack
+
+    - name: Upload artifacts
+      uses: actions/upload-artifact@v4
+      with:
+        name: ai-sdk-integration
+        path: hindsight-integrations/ai-sdk/*.tgz
+        retention-days: 1
+
   release-control-plane:
     runs-on: ubuntu-latest
     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 +268,11 @@ 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 +290,7 @@ 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 +313,9 @@ 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
@@ -253,7 +333,7 @@ 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 }}
@@ -294,7 +374,7 @@ jobs:
               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 +388,13 @@ 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 }}
@@ -326,7 +406,7 @@ 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: |
@@ -342,7 +422,7 @@ 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
@@ -361,7 +441,7 @@ jobs:
 
     # 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
@@ -379,7 +459,7 @@ jobs:
       packages: write
 
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v4
 
     - name: Install Helm
       uses: azure/setup-helm@v4
@@ -399,7 +479,7 @@ 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
@@ -407,55 +487,67 @@ jobs:
 
   create-github-release:
     runs-on: ubuntu-latest
-    needs: [release-python-packages, release-typescript-client, release-control-plane, release-rust-cli, release-docker-images, release-helm-chart]
+    needs: [release-python-packages, release-typescript-client, release-openclaw-integration, release-ai-sdk-integration, release-control-plane, release-rust-cli, release-docker-images, release-helm-chart]
     permissions:
       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 OpenClaw Integration
+      uses: actions/download-artifact@v4
+      with:
+        name: openclaw-integration
+        path: ./artifacts/openclaw-integration
+
+    - name: Download AI SDK Integration
+      uses: actions/download-artifact@v4
+      with:
+        name: ai-sdk-integration
+        path: ./artifacts/ai-sdk-integration
+
     - 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
@@ -465,13 +557,16 @@ 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
+        # OpenClaw Integration
+        cp artifacts/openclaw-integration/*.tgz release-assets/ || true
+        # AI SDK Integration
+        cp artifacts/ai-sdk-integration/*.tgz release-assets/ || true
         # Control Plane
         cp artifacts/control-plane/*.tgz release-assets/ || true
         # Rust CLI binaries

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)
@@ -72,7 +72,7 @@ cd hindsight-control-plane && npm run dev
 ## 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 +81,9 @@ 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 +101,7 @@ 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 +111,13 @@ 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 +154,7 @@ 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
@@ -251,7 +251,7 @@ Fields must be categorized as either **hierarchical** (can be overridden per-ten
 
 #### Adding a New Configuration Field
 
-1. **config.py** (`hindsight-api-slim/hindsight_api/config.py`):
+1. **config.py** (`hindsight-api/hindsight_api/config.py`):
    - Add `ENV_*` constant for the environment variable name (e.g., `ENV_MY_SETTING = "HINDSIGHT_API_MY_SETTING"`)
    - Add `DEFAULT_*` constant for the default value
    - Add field to `HindsightConfig` dataclass with type annotation
@@ -268,7 +268,7 @@ Fields must be categorized as either **hierarchical** (can be overridden per-ten
    # 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**:
@@ -308,19 +308,19 @@ 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)
+- `HINDSIGHT_API_ENABLE_BANK_CONFIG_API`: Enable per-bank config API (default: false, disabled for security)

README.md

@@ -7,12 +7,10 @@
 [![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)
-[![gitcgr](https://gitcgr.com/badge/vectorize-io/hindsight.svg)](https://gitcgr.com/vectorize-io/hindsight)
 ![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>
 
 ---
@@ -38,7 +36,7 @@ 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.
 
@@ -71,7 +69,7 @@ docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
 >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`, `lmstudio`, and `minimax`. 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`, and `lmstudio`. The documentation provides more details on [supported models](https://hindsight.vectorize.io/developer/models).
 
 
 
@@ -183,7 +181,7 @@ 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")
@@ -309,5 +307,3 @@ 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/standalone/Dockerfile

@@ -42,22 +42,25 @@ 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 .
@@ -167,11 +170,6 @@ 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)
@@ -323,11 +321,6 @@ 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)

docker/standalone/start-all.sh

@@ -1,28 +1,6 @@
 #!/bin/bash
 set -e
 
-# =============================================================================
-# Embedded pg0 data integrity check (#675)
-#
-# When using embedded pg0, check if the data directory has existing PostgreSQL
-# data before starting. If the directory exists but appears empty/corrupt
-# (e.g., missing PG_VERSION file), log a warning. This helps diagnose data
-# loss scenarios where a container restart caused the data directory to be
-# wiped despite a volume mount being present.
-# =============================================================================
-PG0_DATA_DIR="${HOME}/.pg0"
-if [ -d "$PG0_DATA_DIR" ]; then
-    # Look for actual PostgreSQL data directories (pg0 creates subdirs per instance)
-    if compgen -G "$PG0_DATA_DIR"/*/PG_VERSION > /dev/null 2>&1; then
-        echo "✅ Existing pg0 data directory detected at $PG0_DATA_DIR"
-    elif [ "$(ls -A "$PG0_DATA_DIR" 2>/dev/null)" ]; then
-        echo "⚠️  WARNING: pg0 data directory exists at $PG0_DATA_DIR but no PG_VERSION found."
-        echo "   This may indicate data corruption or an incomplete previous shutdown."
-        echo "   If you see all migrations running from scratch after this, your data may have been lost."
-        echo "   See: https://github.com/vectorize-io/hindsight/issues/675"
-    fi
-fi
-
 # Service flags (default to true if not set)
 ENABLE_API="${HINDSIGHT_ENABLE_API:-true}"
 ENABLE_CP="${HINDSIGHT_ENABLE_CP:-true}"
@@ -93,95 +71,24 @@ if [ "${HINDSIGHT_WAIT_FOR_DEPS:-false}" = "true" ]; then
     done
 fi
 
-# =============================================================================
-# Graceful shutdown handler (#675)
-#
-# Docker sends SIGTERM on `docker stop`/`docker restart`. Without a trap, child
-# processes (hindsight-api + pg0, control-plane) are killed abruptly. For the
-# embedded pg0 database this can cause data loss when the data directory is on
-# a Docker volume that gets remounted after restart.
-#
-# The trap forwards SIGTERM to all tracked child PIDs so that:
-#   - hindsight-api receives the signal and can run its shutdown hooks
-#   - pg0 gets a clean PostgreSQL shutdown (checkpoint + WAL flush)
-#   - The control-plane Node.js process exits cleanly
-# =============================================================================
-# Guard against concurrent cleanup (e.g., child crash + SIGTERM arriving together)
-SHUTTING_DOWN=false
-
-cleanup() {
-    if $SHUTTING_DOWN; then return; fi
-    SHUTTING_DOWN=true
-
-    echo ""
-    echo "🛑 Received shutdown signal, stopping services gracefully..."
-    for pid in "${PIDS[@]}"; do
-        if kill -0 "$pid" 2>/dev/null; then
-            kill -TERM "$pid" 2>/dev/null
-        fi
-    done
-    # Give processes time to shut down cleanly (pg0 needs to flush WAL).
-    # NOTE: Docker's default stop_grace_period is 10s. If you use the default,
-    # either set stop_grace_period: 30s in your compose file / docker stop -t 30,
-    # or Docker will SIGKILL the container before this timeout expires.
-    local timeout=30
-    for ((i=1; i<=timeout; i++)); do
-        local all_stopped=true
-        for pid in "${PIDS[@]}"; do
-            if kill -0 "$pid" 2>/dev/null; then
-                all_stopped=false
-                break
-            fi
-        done
-        if $all_stopped; then
-            echo "✅ All services stopped cleanly"
-            exit 0
-        fi
-        sleep 1
-    done
-    # Force kill if still running after timeout
-    echo "⚠️  Timeout reached, forcing shutdown..."
-    for pid in "${PIDS[@]}"; do
-        if kill -0 "$pid" 2>/dev/null; then
-            kill -9 "$pid" 2>/dev/null
-        fi
-    done
-    exit 1
-}
-trap cleanup SIGTERM SIGINT
-
 # Track PIDs for wait
 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 ${API_STARTUP_WAIT_SECONDS}s"
-        exit 1
-    fi
 else
     echo "API disabled (HINDSIGHT_ENABLE_API=false)"
 fi
@@ -190,8 +97,7 @@ fi
 if [ "$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
@@ -204,7 +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"
@@ -217,21 +123,8 @@ if [ ${#PIDS[@]} -eq 0 ]; then
     exit 1
 fi
 
-# Wait for any process to exit (use wait -n with trap-safe loop)
-while true; do
-    # wait -n returns when any child exits; it also returns on signal delivery
-    # (the trap handler will run and exit, so this loop is just for robustness).
-    # `&& true` prevents `set -e` from killing the script when wait -n returns
-    # non-zero (child exited with error or no backgrounded children remain).
-    wait -n && true
-    # Check if any tracked PID has exited
-    for pid in "${PIDS[@]}"; do
-        if ! kill -0 "$pid" 2>/dev/null; then
-            wait "$pid" 2>/dev/null
-            exit_code=$?
-            echo "⚠️  Service (PID $pid) exited with code $exit_code"
-            # Trigger cleanup for remaining services
-            cleanup
-        fi
-    done
-done
+# Wait for any process to exit
+wait -n
+
+# Exit with status of first exited process
+exit $?

docker/test-image.sh

@@ -13,9 +13,9 @@
 #   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)
+#   GROQ_API_KEY                                - Required for API/standalone images (LLM verification)
+#   HINDSIGHT_API_LLM_PROVIDER                  - LLM provider (default: groq)
+#   HINDSIGHT_API_LLM_MODEL                     - LLM model (default: llama-3.3-70b-versatile)
 #   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)
@@ -34,7 +34,7 @@
 #   ./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 GROQ_API_KEY=gsk_xxx
 #   export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
 #   export HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=sk-xxx
 #   export HINDSIGHT_API_RERANKER_PROVIDER=cohere
@@ -49,9 +49,6 @@
 
 set -euo pipefail
 
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-REPO_ROOT="$(dirname "$SCRIPT_DIR")"
-
 # Colors for output
 RED='\033[0;31m'
 GREEN='\033[0;32m'
@@ -63,8 +60,8 @@ IMAGE="${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="${HINDSIGHT_API_LLM_MODEL:-gpt-4o-mini}"
+LLM_PROVIDER="${HINDSIGHT_API_LLM_PROVIDER:-groq}"
+LLM_MODEL="${HINDSIGHT_API_LLM_MODEL:-llama-3.3-70b-versatile}"
 
 # Validate arguments
 if [ -z "$IMAGE" ]; then
@@ -91,9 +88,9 @@ else
 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${NC}"
-    echo "Set it with: export HINDSIGHT_API_LLM_API_KEY=your-api-key"
+if [ "$NEEDS_LLM" = true ] && [ -z "${GROQ_API_KEY:-}" ]; then
+    echo -e "${RED}Error: GROQ_API_KEY environment variable is required for API/standalone images${NC}"
+    echo "Set it with: export GROQ_API_KEY=your-api-key"
     exit 2
 fi
 
@@ -126,25 +123,9 @@ 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="$DOCKER_CMD -e HINDSIGHT_API_LLM_API_KEY=${GROQ_API_KEY}"
     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}"
@@ -181,21 +162,6 @@ for i in $(seq 1 "$TIMEOUT"); do
         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

docker/test-slim-local.sh

@@ -6,17 +6,24 @@
 # It expects API keys to be set in environment variables.
 #
 # Usage:
+#   export GROQ_API_KEY=gsk_xxx
 #   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
+#   GROQ_API_KEY=gsk_xxx OPENAI_API_KEY=sk_xxx COHERE_API_KEY=xxx ./docker/test-slim-local.sh
 #
 
 set -euo pipefail
 
 # Check for required API keys
+if [ -z "${GROQ_API_KEY:-}" ]; then
+    echo "❌ Error: GROQ_API_KEY environment variable is required"
+    echo "Set it with: export GROQ_API_KEY=gsk_xxx"
+    exit 1
+fi
+
 if [ -z "${OPENAI_API_KEY:-}" ]; then
     echo "❌ Error: OPENAI_API_KEY environment variable is required"
     echo "Set it with: export OPENAI_API_KEY=sk-xxx"
@@ -34,10 +41,7 @@ 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=$OPENAI_API_KEY
-export HINDSIGHT_API_LLM_MODEL=gpt-4o-mini
+# Set up external providers
 export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openai
 export HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=$OPENAI_API_KEY
 export HINDSIGHT_API_RERANKER_PROVIDER=cohere

helm/hindsight/Chart.yaml

@@ -2,8 +2,8 @@ apiVersion: v2
 name: hindsight
 description: Hindsight helm chart
 type: application
-version: 0.4.20
-appVersion: "0.4.20"
+version: 0.4.11
+appVersion: "0.4.11"
 keywords:
   - ai
   - memory

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 = "0.4.20"
-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/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-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/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/b3c4d5e6f7a8_add_content_hash_to_chunks.py

@@ -1,32 +0,0 @@
-"""add content_hash to chunks table for delta retain
-
-Revision ID: b3c4d5e6f7a8
-Revises: a3b4c5d6e7f8
-Create Date: 2026-03-25
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "b3c4d5e6f7a8"
-down_revision: str | Sequence[str] | None = "a3b4c5d6e7f8"
-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()
-    # Add content_hash column to chunks table for delta comparison
-    op.execute(f"ALTER TABLE {schema}chunks ADD COLUMN IF NOT EXISTS content_hash TEXT")
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}chunks DROP COLUMN IF EXISTS content_hash")

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

@@ -1,59 +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
-
-import sqlalchemy as sa
-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 most PostgreSQL installations as a contrib module.
-    # It enables fast similarity lookups via GIN indexes, used for entity name matching.
-    # On managed services (e.g. Azure Flexible Server), the extension may not be
-    # available or may require manual enablement.  We gracefully skip the index
-    # creation if the extension cannot be loaded — the entity resolver will
-    # auto-detect and fall back to the "full" lookup strategy at runtime.  See #626.
-    conn = op.get_bind()
-    try:
-        conn.execute(sa.text("CREATE EXTENSION IF NOT EXISTS pg_trgm"))
-    except Exception:
-        # Extension not available (managed Postgres, insufficient privileges, etc.)
-        # Roll back the failed statement and skip index creation.
-        conn.execute(sa.text("ROLLBACK"))
-        conn.execute(sa.text("BEGIN"))
-        return
-
-    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/c2d3e4f5g6h7_add_audit_log_table.py

@@ -1,61 +0,0 @@
-"""Add audit_log table for feature usage tracking.
-
-Merge migration that combines the two existing heads (a3b4c5d6e7f8 + c8e5f2a3b4d1).
-
-Stores raw request/response as JSONB for expandability without future migrations.
-The metadata JSONB column allows adding arbitrary fields in the future.
-
-Revision ID: c2d3e4f5g6h7
-Revises: a3b4c5d6e7f8, c8e5f2a3b4d1
-Create Date: 2026-03-26
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "c2d3e4f5g6h7"
-down_revision: str | Sequence[str] | None = ("a3b4c5d6e7f8", "c8e5f2a3b4d1")
-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"""
-        CREATE TABLE IF NOT EXISTS {schema}audit_log (
-            id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
-            action TEXT NOT NULL,
-            transport TEXT NOT NULL,
-            bank_id TEXT,
-            started_at TIMESTAMPTZ NOT NULL DEFAULT NOW(),
-            ended_at TIMESTAMPTZ,
-            request JSONB,
-            response JSONB,
-            metadata JSONB DEFAULT '{{}}'::jsonb
-        )
-        """
-    )
-
-    op.execute(
-        f"CREATE INDEX IF NOT EXISTS idx_audit_log_action_started ON {schema}audit_log (action, started_at DESC)"
-    )
-    op.execute(f"CREATE INDEX IF NOT EXISTS idx_audit_log_bank_started ON {schema}audit_log (bank_id, started_at DESC)")
-    op.execute(f"CREATE INDEX IF NOT EXISTS idx_audit_log_started ON {schema}audit_log (started_at DESC)")
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_audit_log_started")
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_audit_log_bank_started")
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_audit_log_action_started")
-    op.execute(f"DROP TABLE IF EXISTS {schema}audit_log")

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/c5d6e7f8a9b0_add_bank_id_to_memory_links.py

@@ -1,49 +0,0 @@
-"""Add bank_id column to memory_links for direct filtering
-
-The stats endpoint JOINs memory_links to memory_units just to filter by
-bank_id.  With millions of links this takes 18+ seconds.  Adding bank_id
-directly to memory_links lets Postgres push the filter down before the JOIN.
-
-Revision ID: c5d6e7f8a9b0
-Revises: b3c4d5e6f7a8
-Create Date: 2026-03-26
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-revision: str = "c5d6e7f8a9b0"
-down_revision: str | Sequence[str] | None = "b3c4d5e6f7a8"
-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()
-
-    # 1. Add nullable column
-    op.execute(f"ALTER TABLE {schema}memory_links ADD COLUMN IF NOT EXISTS bank_id TEXT")
-
-    # 2. Backfill from memory_units
-    op.execute(f"""
-        UPDATE {schema}memory_links ml
-        SET bank_id = mu.bank_id
-        FROM {schema}memory_units mu
-        WHERE ml.from_unit_id = mu.id
-          AND ml.bank_id IS NULL
-    """)
-
-    # 3. Set NOT NULL
-    op.execute(f"ALTER TABLE {schema}memory_links ALTER COLUMN bank_id SET NOT NULL")
-
-
-
-def downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}memory_links DROP COLUMN IF EXISTS bank_id")

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

@@ -1,57 +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.
-    """
-    from alembic import context
-
-    schema = context.config.get_main_option("target_schema")
-    schema_prefix = f'"{schema}".' if schema else ""
-    # Use raw SQL with IF EXISTS so this is safe on schemas where the FK was
-    # already dropped or never existed under this name.
-    op.execute(f"ALTER TABLE {schema_prefix}memory_units DROP CONSTRAINT IF EXISTS memory_units_chunk_fkey")
-    # Use a DO block so the ADD is also idempotent: if the FK already exists (e.g.
-    # the schema was provisioned after the base migration already added it) the
-    # duplicate_object exception is swallowed rather than failing the migration.
-    op.execute(
-        f"""
-        DO $$ BEGIN
-            ALTER TABLE {schema_prefix}memory_units
-                ADD CONSTRAINT memory_units_chunk_fkey
-                FOREIGN KEY (chunk_id)
-                REFERENCES {schema_prefix}chunks (chunk_id)
-                ON DELETE CASCADE;
-        EXCEPTION
-            WHEN duplicate_object THEN NULL;
-        END $$;
-        """
-    )
-
-
-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/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/engine/audit.py

@@ -1,209 +0,0 @@
-"""Audit logging for feature usage tracking.
-
-Provides fire-and-forget audit logging of all mutating and core operations
-(retain, recall, reflect, bank CRUD, etc.) across HTTP, MCP, and system transports.
-"""
-
-from __future__ import annotations
-
-import asyncio
-import json
-import logging
-import uuid
-from collections.abc import Callable
-from contextlib import asynccontextmanager
-from dataclasses import dataclass, field
-from datetime import datetime, timezone
-from typing import Any
-
-import asyncpg
-
-from ..engine.db_utils import acquire_with_retry
-
-logger = logging.getLogger(__name__)
-
-
-@dataclass
-class AuditEntry:
-    """A single audit log entry."""
-
-    action: str
-    transport: str  # "http", "mcp", "system"
-    bank_id: str | None = None
-    started_at: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
-    ended_at: datetime | None = None
-    request: dict[str, Any] | None = None
-    response: dict[str, Any] | None = None
-    metadata: dict[str, Any] = field(default_factory=dict)
-
-
-def _json_default(obj: Any) -> str:
-    """JSON serializer for objects not serializable by default."""
-    if isinstance(obj, datetime):
-        return obj.isoformat()
-    if isinstance(obj, uuid.UUID):
-        return str(obj)
-    if isinstance(obj, bytes):
-        return "<bytes>"
-    if isinstance(obj, set):
-        return list(obj)
-    return str(obj)
-
-
-def _safe_json(data: Any) -> str | None:
-    """Serialize data to JSON string, returning None on failure."""
-    if data is None:
-        return None
-    try:
-        return json.dumps(data, default=_json_default)
-    except Exception:
-        logger.debug("Failed to serialize audit data", exc_info=True)
-        return None
-
-
-_SWEEP_INTERVAL_SECONDS = 3600  # Run retention sweep every hour
-
-
-class AuditLogger:
-    """Fire-and-forget audit log writer with optional retention sweep."""
-
-    def __init__(
-        self,
-        pool_getter: Callable[[], asyncpg.Pool | None],
-        schema_getter: Callable[[], str],
-        enabled: bool,
-        allowed_actions: list[str],
-        retention_days: int = -1,
-    ) -> None:
-        self._pool_getter = pool_getter
-        self._schema_getter = schema_getter
-        self._enabled = enabled
-        self._allowed_actions: frozenset[str] | None = frozenset(allowed_actions) if allowed_actions else None
-        self._retention_days = retention_days
-        self._sweep_task: asyncio.Task | None = None
-
-    def is_enabled(self, action: str) -> bool:
-        """Check if audit logging is enabled for this action."""
-        if not self._enabled:
-            return False
-        if self._allowed_actions is not None:
-            return action in self._allowed_actions
-        return True
-
-    def log_fire_and_forget(self, entry: AuditEntry) -> None:
-        """Schedule an audit write as a background task."""
-        if not self.is_enabled(entry.action):
-            return
-        try:
-            asyncio.create_task(self._safe_log(entry))
-        except RuntimeError:
-            # No running event loop (e.g. during shutdown)
-            logger.debug("Cannot schedule audit log write: no running event loop")
-
-    async def _safe_log(self, entry: AuditEntry) -> None:
-        """Write audit entry to DB. Errors are logged, never raised."""
-        pool = self._pool_getter()
-        if pool is None:
-            logger.debug("Audit log skipped: pool not available")
-            return
-        try:
-            schema = self._schema_getter()
-            table = f"{schema}.audit_log"
-            async with acquire_with_retry(pool, max_retries=1) as conn:
-                await conn.execute(
-                    f"""
-                    INSERT INTO {table}
-                        (id, action, transport, bank_id, started_at, ended_at, request, response, metadata)
-                    VALUES
-                        ($1, $2, $3, $4, $5, $6, $7::jsonb, $8::jsonb, $9::jsonb)
-                    """,
-                    uuid.uuid4(),
-                    entry.action,
-                    entry.transport,
-                    entry.bank_id,
-                    entry.started_at,
-                    entry.ended_at,
-                    _safe_json(entry.request),
-                    _safe_json(entry.response),
-                    _safe_json(entry.metadata) or "{}",
-                )
-        except Exception as e:
-            logger.warning(f"Audit log write failed for action={entry.action}: {e}")
-
-    def start_retention_sweep(self) -> None:
-        """Start the periodic retention sweep if retention is configured."""
-        if self._retention_days <= 0 or not self._enabled:
-            return
-        try:
-            self._sweep_task = asyncio.create_task(self._sweep_loop())
-        except RuntimeError:
-            logger.debug("Cannot start retention sweep: no running event loop")
-
-    async def stop_retention_sweep(self) -> None:
-        """Stop the periodic retention sweep."""
-        if self._sweep_task and not self._sweep_task.done():
-            self._sweep_task.cancel()
-            try:
-                await self._sweep_task
-            except asyncio.CancelledError:
-                pass
-            self._sweep_task = None
-
-    async def _sweep_loop(self) -> None:
-        """Periodically delete audit log entries older than retention_days."""
-        while True:
-            await self._run_sweep()
-            await asyncio.sleep(_SWEEP_INTERVAL_SECONDS)
-
-    async def _run_sweep(self) -> None:
-        """Delete expired audit log entries. Concurrent-safe via row-level deletes."""
-        pool = self._pool_getter()
-        if pool is None:
-            return
-        try:
-            schema = self._schema_getter()
-            table = f"{schema}.audit_log"
-            async with acquire_with_retry(pool, max_retries=1) as conn:
-                result = await conn.execute(
-                    f"DELETE FROM {table} WHERE started_at < NOW() - INTERVAL '{self._retention_days} days'"
-                )
-                if result and result != "DELETE 0":
-                    logger.info(f"Audit log retention sweep: {result}")
-        except Exception as e:
-            logger.warning(f"Audit log retention sweep failed: {e}")
-
-
-@asynccontextmanager
-async def audit_context(
-    audit_logger: AuditLogger | None,
-    action: str,
-    transport: str,
-    bank_id: str | None = None,
-    request: dict[str, Any] | None = None,
-    metadata: dict[str, Any] | None = None,
-):
-    """Async context manager that times the operation and writes audit on exit.
-
-    Usage:
-        async with audit_context(logger, "retain", "http", bank_id, request_dict) as entry:
-            result = await do_work()
-            entry.response = result_dict
-    """
-    if audit_logger is None or not audit_logger.is_enabled(action):
-        entry = AuditEntry(action=action, transport=transport, bank_id=bank_id)
-        yield entry
-        return
-
-    entry = AuditEntry(
-        action=action,
-        transport=transport,
-        bank_id=bank_id,
-        started_at=datetime.now(timezone.utc),
-        request=request,
-        metadata=metadata or {},
-    )
-    try:
-        yield entry
-    finally:
-        entry.ended_at = datetime.now(timezone.utc)
-        audit_logger.log_fire_and_forget(entry)

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/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/providers/litellm_llm.py

@@ -1,380 +0,0 @@
-"""
-LiteLLM LLM provider for universal model support.
-
-This provider enables using 100+ LLM providers via the LiteLLM SDK, including:
-- AWS Bedrock (bedrock/anthropic.claude-3-5-sonnet-...)
-- Azure OpenAI (azure/gpt-4o)
-- Together AI (together_ai/meta-llama/...)
-- Any other LiteLLM-supported provider
-
-Uses litellm.acompletion() for async chat completions.
-Authentication for cloud providers (e.g., AWS Bedrock via boto3 credential chain)
-is handled automatically by LiteLLM.
-"""
-
-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 LiteLLMLLM(LLMInterface):
-    """
-    LLM provider using the LiteLLM SDK for universal model support.
-
-    Supports any model accessible via litellm.acompletion(), including AWS Bedrock,
-    Azure OpenAI, Together AI, Fireworks AI, and more.
-
-    Model names follow LiteLLM conventions with provider prefixes:
-    - bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0
-    - azure/gpt-4o
-    - together_ai/meta-llama/Llama-3-70b-chat-hf
-    - fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct
-    """
-
-    def __init__(
-        self,
-        provider: str,
-        api_key: str,
-        base_url: str,
-        model: str,
-        reasoning_effort: str = "low",
-        timeout: float = 300.0,
-        **kwargs: Any,
-    ):
-        super().__init__(provider, api_key, base_url, model, reasoning_effort, **kwargs)
-        self.timeout = timeout
-        self._litellm: Any = None
-
-        try:
-            import litellm
-
-            self._litellm = litellm
-            # Suppress LiteLLM's verbose logging
-            litellm.suppress_debug_info = True  # type: ignore[assignment]
-            # Drop unsupported params instead of raising errors (e.g. tool_choice on some Bedrock models)
-            litellm.drop_params = True  # type: ignore[assignment]
-            logging.getLogger("LiteLLM").setLevel(logging.WARNING)
-            logger.info(f"LiteLLM SDK initialized for model: {self.model}")
-        except ImportError as e:
-            raise RuntimeError("LiteLLM SDK not installed. Run: uv add litellm or pip install litellm") from e
-
-    async def verify_connection(self) -> None:
-        try:
-            test_messages = [{"role": "user", "content": "test"}]
-            await self.call(
-                messages=test_messages,
-                max_completion_tokens=50,
-                temperature=0.0,
-                scope="verification",
-                max_retries=0,
-            )
-            logger.info("LiteLLM connection verified successfully")
-        except OutputTooLongError:
-            # Truncation is fine for verification — it means the connection works
-            logger.info("LiteLLM connection verified successfully (response truncated)")
-        except Exception as e:
-            logger.error(f"LiteLLM connection verification failed: {e}")
-            raise RuntimeError(f"Failed to verify LiteLLM connection: {e}") from e
-
-    def _build_common_kwargs(
-        self,
-        messages: list[dict[str, Any]],
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-    ) -> dict[str, Any]:
-        """Build common kwargs for litellm calls."""
-        kwargs: dict[str, Any] = {
-            "model": self.model,
-            "messages": messages,
-            "timeout": self.timeout,
-        }
-
-        if self.api_key:
-            kwargs["api_key"] = self.api_key
-        if self.base_url:
-            kwargs["api_base"] = self.base_url
-        if max_completion_tokens is not None:
-            kwargs["max_completion_tokens"] = max_completion_tokens
-        if temperature is not None:
-            kwargs["temperature"] = temperature
-
-        return kwargs
-
-    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:
-        start_time = time.time()
-
-        call_kwargs = self._build_common_kwargs(messages, max_completion_tokens, temperature)
-
-        # Add JSON schema response format if provided
-        if response_format is not None and hasattr(response_format, "model_json_schema"):
-            schema = response_format.model_json_schema()
-            call_kwargs["response_format"] = {
-                "type": "json_schema",
-                "json_schema": {
-                    "name": response_format.__name__ if hasattr(response_format, "__name__") else "response",
-                    "schema": schema,
-                    "strict": strict_schema,
-                },
-            }
-
-        last_exception = None
-
-        for attempt in range(max_retries + 1):
-            try:
-                response = await self._litellm.acompletion(**call_kwargs)
-
-                content = response.choices[0].message.content or ""
-                finish_reason = response.choices[0].finish_reason
-
-                # Check for length-limited output
-                if finish_reason == "length":
-                    raise OutputTooLongError("LiteLLM response was truncated due to token limit")
-
-                if response_format is not None:
-                    # Strip markdown code fences if present
-                    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:
-                        json_data = json.loads(content)
-
-                    if skip_validation:
-                        result = json_data
-                    else:
-                        result = response_format.model_validate(json_data)
-                else:
-                    result = content
-
-                # Extract usage
-                input_tokens = getattr(response.usage, "prompt_tokens", 0) or 0
-                output_tokens = getattr(response.usage, "completion_tokens", 0) or 0
-                total_tokens = input_tokens + output_tokens
-
-                # 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 _serialize_for_span, 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=_serialize_for_span(result),
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    duration=duration,
-                    finish_reason=finish_reason,
-                    error=None,
-                )
-
-                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 OutputTooLongError:
-                raise
-
-            except json.JSONDecodeError as e:
-                last_exception = e
-                if attempt < max_retries:
-                    logger.warning("LiteLLM returned invalid JSON, retrying...")
-                    backoff = min(initial_backoff * (2**attempt), max_backoff)
-                    await asyncio.sleep(backoff)
-                    continue
-                else:
-                    logger.error(f"LiteLLM returned invalid JSON after {max_retries + 1} attempts")
-                    raise
-
-            except Exception as e:
-                error_str = str(e).lower()
-                # Fast fail on auth errors
-                if "401" in error_str or "403" in error_str or "unauthorized" in error_str:
-                    logger.error(f"LiteLLM auth error, not retrying: {e}")
-                    raise
-
-                last_exception = e
-                if attempt < max_retries:
-                    # Retry on rate limits, connection errors, server errors
-                    is_retryable = any(
-                        keyword in error_str
-                        for keyword in ("rate", "limit", "timeout", "connection", "500", "502", "503", "529")
-                    )
-                    if is_retryable:
-                        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"LiteLLM API error after {attempt + 1} attempts: {e}")
-                raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("LiteLLM 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:
-        start_time = time.time()
-
-        call_kwargs = self._build_common_kwargs(messages, max_completion_tokens, temperature)
-        call_kwargs["tools"] = tools
-        call_kwargs["tool_choice"] = tool_choice
-
-        last_exception = None
-        for attempt in range(max_retries + 1):
-            try:
-                response = await self._litellm.acompletion(**call_kwargs)
-
-                message = response.choices[0].message
-                content = message.content
-                finish_reason = response.choices[0].finish_reason
-
-                # Extract tool calls
-                tool_calls: list[LLMToolCall] = []
-                if message.tool_calls:
-                    for tc in message.tool_calls:
-                        arguments = tc.function.arguments
-                        if isinstance(arguments, str):
-                            arguments = json.loads(arguments)
-                        tool_calls.append(
-                            LLMToolCall(
-                                id=tc.id,
-                                name=tc.function.name,
-                                arguments=arguments,
-                            )
-                        )
-
-                # Extract usage
-                input_tokens = getattr(response.usage, "prompt_tokens", 0) or 0
-                output_tokens = getattr(response.usage, "completion_tokens", 0) 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
-
-                span_recorder = get_span_recorder()
-                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 or ("tool_calls" if tool_calls else "stop"),
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                )
-
-            except Exception as e:
-                error_str = str(e).lower()
-                if "401" in error_str or "403" in error_str or "unauthorized" in error_str:
-                    raise
-
-                last_exception = e
-                if attempt < max_retries:
-                    is_retryable = any(
-                        keyword in error_str
-                        for keyword in ("rate", "limit", "timeout", "connection", "500", "502", "503", "529")
-                    )
-                    if is_retryable:
-                        await asyncio.sleep(min(initial_backoff * (2**attempt), max_backoff))
-                        continue
-
-                logger.error(f"LiteLLM tool call error after {attempt + 1} attempts: {e}")
-                raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("LiteLLM tool call failed after all retries")
-
-    async def cleanup(self) -> None:
-        """Clean up resources."""
-        pass

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

@@ -1,78 +0,0 @@
-"""
-No-op LLM provider for chunk-only storage mode.
-
-When the LLM provider is set to "none", the system operates without any LLM dependency.
-Retain uses chunks mode (no fact extraction), and reflect/consolidation are disabled.
-This provider acts as a safety net — if any code path unexpectedly tries to call the LLM,
-it raises a clear error instead of a confusing connection failure.
-"""
-
-import logging
-from typing import Any
-
-from ..llm_interface import LLMInterface
-from ..response_models import LLMToolCallResult
-
-logger = logging.getLogger(__name__)
-
-
-class LLMNotAvailableError(Exception):
-    """Raised when an operation requires an LLM but the provider is set to 'none'."""
-
-    pass
-
-
-class NoneLLM(LLMInterface):
-    """
-    No-op LLM provider that rejects all LLM calls.
-
-    Used when HINDSIGHT_API_LLM_PROVIDER=none to run Hindsight as a chunk store
-    with semantic search but without LLM-based features (fact extraction, reflect,
-    consolidation).
-    """
-
-    async def verify_connection(self) -> None:
-        """No-op — no LLM connection to verify."""
-        logger.debug("NoneLLM: no LLM connection to verify (provider=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:
-        """Raise LLMNotAvailableError — no LLM is configured."""
-        raise LLMNotAvailableError(
-            "LLM provider is set to 'none'. This operation requires an LLM. "
-            "Set HINDSIGHT_API_LLM_PROVIDER to a real provider (e.g., openai, anthropic, gemini)."
-        )
-
-    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:
-        """Raise LLMNotAvailableError — no LLM is configured."""
-        raise LLMNotAvailableError(
-            "LLM provider is set to 'none'. This operation requires an LLM. "
-            "Set HINDSIGHT_API_LLM_PROVIDER to a real provider (e.g., openai, anthropic, gemini)."
-        )
-
-    async def cleanup(self) -> None:
-        """No-op — nothing to clean up."""
-        pass

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/orchestrator.py

@@ -1,883 +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 import defaultdict
-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 ChunkMetadata, EntityLink, ExtractedFact, ProcessedFact, RetainContent, RetainContentDict
-
-logger = logging.getLogger(__name__)
-
-
-def _build_retain_params(contents_dicts, document_tags=None, doc_contents=None):
-    """Build retain_params and merged_tags from content dicts."""
-    if doc_contents is not None:
-        # Per-document mode: doc_contents is list of (idx, content_dict)
-        items = [item for _, item in doc_contents]
-    else:
-        items = contents_dicts
-
-    all_tags = set(document_tags or [])
-    for item in items:
-        item_tags = item.get("tags", []) or []
-        all_tags.update(item_tags)
-    merged_tags = list(all_tags)
-
-    retain_params = {}
-    if items:
-        first_item = items[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"]
-
-    return retain_params, merged_tags
-
-
-async def _insert_facts_and_links(
-    conn,
-    entity_resolver,
-    bank_id: str,
-    contents: list[RetainContent],
-    extracted_facts: list,
-    processed_facts: list[ProcessedFact],
-    config,
-    log_buffer: list[str],
-    outbox_callback=None,
-) -> list[list[str]]:
-    """
-    Shared pipeline: insert facts, process entities, create all link types.
-
-    Used by both the full retain and delta retain paths.
-
-    Returns:
-        List of unit ID lists mapped back to original content items.
-    """
-    unit_ids = await fact_storage.insert_facts_batch(conn, bank_id, processed_facts)
-    step_start = time.time()
-    log_buffer.append(f"  Insert facts: {len(unit_ids)} units in {time.time() - step_start:.3f}s")
-
-    if unit_ids:
-        # Process entities
-        step_start = time.time()
-        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,
-            processed_facts,
-            log_buffer,
-            user_entities_per_content=user_entities_per_content,
-            entity_labels=getattr(config, "entity_labels", None),
-        )
-        log_buffer.append(f"  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"  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 processed_facts]
-        semantic_link_count = await link_creation.create_semantic_links_batch(
-            conn, bank_id, unit_ids, embeddings_for_links
-        )
-        log_buffer.append(f"  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, bank_id)
-        log_buffer.append(
-            f"  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, bank_id, unit_ids, processed_facts)
-        log_buffer.append(f"  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 if unit_ids else [])
-
-    if outbox_callback:
-        await outbox_callback(conn)
-
-    return result_unit_ids
-
-
-async def _extract_and_embed(
-    contents: list[RetainContent],
-    llm_config,
-    agent_name: str,
-    config,
-    embeddings_model,
-    format_date_fn,
-    fact_type_override: str | None,
-    log_buffer: list[str],
-    pool=None,
-    operation_id: str | None = None,
-    schema: str | None = None,
-) -> tuple[list, list[ProcessedFact], list[ChunkMetadata], TokenUsage]:
-    """
-    Shared pipeline: extract facts from contents and generate embeddings.
-
-    Returns:
-        Tuple of (extracted_facts, processed_facts, chunks_metadata, usage)
-    """
-    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"  Extract facts: {len(extracted_facts)} facts, {len(chunks)} chunks "
-        f"from {len(contents)} contents in {time.time() - step_start:.3f}s"
-    )
-
-    if not extracted_facts:
-        return extracted_facts, [], chunks, usage
-
-    if fact_type_override:
-        for fact in extracted_facts:
-            fact.fact_type = fact_type_override
-
-    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"  Generate embeddings: {len(embeddings)} embeddings in {time.time() - step_start:.3f}s")
-
-    processed_facts = [ProcessedFact.from_extracted_fact(ef, emb) for ef, emb in zip(extracted_facts, embeddings)]
-
-    return extracted_facts, processed_facts, chunks, usage
-
-
-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.
-
-    Supports delta retain: when upserting a document that already has chunks,
-    only re-processes chunks whose content has changed. Unchanged chunks keep
-    their existing facts, entities, and links.
-    """
-    start_time = time.time()
-    total_chars = sum(len(item.get("content", "")) for item in contents_dicts)
-
-    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 = _build_contents(contents_dicts, document_tags)
-
-    # --- Delta retain: check if we can skip unchanged chunks ---
-    if is_first_batch:
-        delta_result = await _try_delta_retain(
-            pool,
-            embeddings_model,
-            llm_config,
-            entity_resolver,
-            format_date_fn,
-            bank_id,
-            contents_dicts,
-            contents,
-            config,
-            document_id,
-            fact_type_override,
-            document_tags,
-            agent_name,
-            log_buffer,
-            start_time,
-            operation_id,
-            schema,
-            outbox_callback,
-        )
-        if delta_result is not None:
-            return delta_result
-
-    # --- Full retain path ---
-    extracted_facts, processed_facts, chunks, usage = await _extract_and_embed(
-        contents,
-        llm_config,
-        agent_name,
-        config,
-        embeddings_model,
-        format_date_fn,
-        fact_type_override,
-        log_buffer,
-        pool,
-        operation_id,
-        schema,
-    )
-
-    if not extracted_facts:
-        await _handle_zero_facts_documents(
-            pool,
-            bank_id,
-            contents_dicts,
-            contents,
-            config,
-            document_id,
-            is_first_batch,
-            document_tags,
-            chunks,
-            log_buffer,
-            start_time,
-        )
-        return [[] for _ in contents], usage
-
-    # Group contents by document_id
-    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))
-
-    # 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
-        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
-        entity_resolver.discard_pending_stats()
-
-        async with acquire_with_retry(pool) as conn:
-            async with conn.transaction():
-                # Handle document tracking
-                step_start = time.time()
-                doc_id_mapping = {}
-
-                if document_id:
-                    combined_content = "\n".join([c.get("content", "") for c in contents_dicts])
-                    retain_params, merged_tags = _build_retain_params(contents_dicts, document_tags)
-                    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
-                else:
-                    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
-                            should_create_doc = (original_doc_id is not None) or chunks
-                            if should_create_doc:
-                                if actual_doc_id is None:
-                                    actual_doc_id = str(uuid.uuid4())
-                                doc_id_mapping[original_doc_id] = actual_doc_id
-                                combined_content = "\n".join([c.get("content", "") for _, c in doc_contents])
-                                retain_params, merged_tags = _build_retain_params(
-                                    contents_dicts, document_tags, doc_contents=doc_contents
-                                )
-                                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"  Document tracking: {len(document_ids_added)} documents in {time.time() - step_start:.3f}s"
-                    )
-
-                # Store chunks and map to facts
-                step_start = time.time()
-                chunk_id_map_by_doc = {}
-                if chunks:
-                    chunks_by_doc = defaultdict(list)
-                    for chunk in chunks:
-                        original_doc_id = contents_dicts[chunk.content_index].get("document_id")
-                        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)
-
-                    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)
-                        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"  Store chunks: {len(chunks)} chunks for {len(chunks_by_doc)} documents "
-                        f"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):
-                    original_doc_id = contents_dicts[fact.content_index].get("document_id")
-                    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
-                    if chunks and fact.chunk_index is not None:
-                        chunk_id = chunk_id_map_by_doc.get((actual_doc_id, fact.chunk_index))
-                        if chunk_id:
-                            processed_fact.chunk_id = chunk_id
-
-                # Insert facts and create all links (shared pipeline)
-                result_unit_ids = await _insert_facts_and_links(
-                    conn,
-                    entity_resolver,
-                    bank_id,
-                    contents,
-                    extracted_facts,
-                    processed_facts,
-                    config,
-                    log_buffer,
-                    outbox_callback,
-                )
-
-            await entity_resolver.flush_pending_stats()
-
-            total_time = time.time() - start_time
-            log_buffer.append(f"{'=' * 60}")
-            log_buffer.append(f"RETAIN_BATCH COMPLETE: {len(processed_facts)} 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
-
-
-# ---------------------------------------------------------------------------
-# Delta retain
-# ---------------------------------------------------------------------------
-
-
-async def _try_delta_retain(
-    pool,
-    embeddings_model,
-    llm_config,
-    entity_resolver,
-    format_date_fn,
-    bank_id,
-    contents_dicts,
-    contents,
-    config,
-    document_id,
-    fact_type_override,
-    document_tags,
-    agent_name,
-    log_buffer,
-    start_time,
-    operation_id,
-    schema,
-    outbox_callback,
-):
-    """
-    Attempt delta retain for a document upsert. Returns result tuple if delta
-    was performed, or None to fall back to full retain.
-    """
-    # Need a single document_id
-    effective_doc_id = document_id
-    if not effective_doc_id:
-        doc_ids = {item.get("document_id") for item in contents_dicts if item.get("document_id")}
-        if len(doc_ids) != 1:
-            return None
-        effective_doc_id = doc_ids.pop()
-
-    # Load existing chunks
-    async with acquire_with_retry(pool) as conn:
-        existing_chunks = await chunk_storage.load_existing_chunks(conn, bank_id, effective_doc_id)
-
-    if not existing_chunks:
-        return None
-
-    if any(c.content_hash is None for c in existing_chunks):
-        logger.info(f"Delta retain skipped for {effective_doc_id}: existing chunks lack content_hash (pre-migration)")
-        return None
-
-    # Chunk new content and classify changes
-    step_start = time.time()
-    new_chunks_with_contents = _chunk_contents_for_delta(contents, config)
-    log_buffer.append(
-        f"[delta] Chunked new content: {len(new_chunks_with_contents)} chunks in {time.time() - step_start:.3f}s"
-    )
-
-    existing_by_index = {c.chunk_index: c for c in existing_chunks}
-    new_hashes = {idx: chunk_storage.compute_chunk_hash(text) for idx, text in new_chunks_with_contents.items()}
-
-    unchanged_indices, changed_indices, new_indices, removed_indices = [], [], [], []
-    for idx, new_hash in new_hashes.items():
-        existing = existing_by_index.get(idx)
-        if existing and existing.content_hash == new_hash:
-            unchanged_indices.append(idx)
-        elif existing:
-            changed_indices.append(idx)
-        else:
-            new_indices.append(idx)
-    for idx in existing_by_index:
-        if idx not in new_hashes:
-            removed_indices.append(idx)
-
-    log_buffer.append(
-        f"[delta] Chunk diff: {len(unchanged_indices)} unchanged, "
-        f"{len(changed_indices)} changed, {len(new_indices)} new, "
-        f"{len(removed_indices)} removed"
-    )
-
-    if not unchanged_indices:
-        logger.info(f"Delta retain: no unchanged chunks for {effective_doc_id}, falling back to full retain")
-        return None
-
-    chunks_to_process = changed_indices + new_indices
-
-    if not chunks_to_process and not removed_indices:
-        # Nothing changed — just update document metadata/tags
-        log_buffer.append("[delta] No chunk changes detected — updating document metadata only")
-        return await _delta_metadata_only(
-            pool,
-            bank_id,
-            contents_dicts,
-            contents,
-            effective_doc_id,
-            document_tags,
-            log_buffer,
-            start_time,
-            outbox_callback,
-        )
-
-    # Build content items for only the changed/new chunks
-    delta_contents, delta_chunk_map = _build_delta_contents(contents, new_chunks_with_contents, chunks_to_process)
-
-    if not delta_contents:
-        return await _delta_metadata_only(
-            pool,
-            bank_id,
-            contents_dicts,
-            contents,
-            effective_doc_id,
-            document_tags,
-            log_buffer,
-            start_time,
-            outbox_callback,
-        )
-
-    # Extract facts and generate embeddings (shared pipeline)
-    extracted_facts, processed_facts, new_chunk_metadata, usage = await _extract_and_embed(
-        delta_contents,
-        llm_config,
-        agent_name,
-        config,
-        embeddings_model,
-        format_date_fn,
-        fact_type_override,
-        log_buffer,
-        pool,
-        operation_id,
-        schema,
-    )
-
-    # Database transaction
-    result_unit_ids: list[list[str]] = []
-    log_buffer_pre_db = len(log_buffer)
-
-    async def _run_delta_db_work() -> None:
-        nonlocal result_unit_ids
-        del log_buffer[log_buffer_pre_db:]
-        for pf in processed_facts:
-            pf.document_id = None
-            pf.chunk_id = None
-        entity_resolver.discard_pending_stats()
-
-        async with acquire_with_retry(pool) as conn:
-            async with conn.transaction():
-                # Update document metadata (no delete)
-                step_start = time.time()
-                combined_content = "\n".join([c.get("content", "") for c in contents_dicts])
-                retain_params, merged_tags = _build_retain_params(contents_dicts, document_tags)
-                await fact_storage.upsert_document_metadata(
-                    conn,
-                    bank_id,
-                    effective_doc_id,
-                    combined_content,
-                    retain_params,
-                    merged_tags,
-                )
-                log_buffer.append(f"  Document metadata update in {time.time() - step_start:.3f}s")
-
-                # Delete changed and removed chunks (cascades to memory_units and links)
-                step_start = time.time()
-                chunks_to_delete = [
-                    existing_by_index[idx].chunk_id
-                    for idx in changed_indices + removed_indices
-                    if idx in existing_by_index
-                ]
-                await chunk_storage.delete_chunks_by_ids(conn, chunks_to_delete)
-                log_buffer.append(
-                    f"  Deleted {len(chunks_to_delete)} chunks "
-                    f"({len(changed_indices)} changed + {len(removed_indices)} removed) "
-                    f"in {time.time() - step_start:.3f}s"
-                )
-
-                # Update tags on unchanged chunks' memory units
-                step_start = time.time()
-                updated_count = await fact_storage.update_memory_units_tags(
-                    conn, bank_id, effective_doc_id, merged_tags
-                )
-                log_buffer.append(
-                    f"  Updated tags on {updated_count} existing memory units in {time.time() - step_start:.3f}s"
-                )
-
-                # Store new/changed chunks
-                step_start = time.time()
-                chunk_id_map_by_doc = {}
-                if new_chunk_metadata:
-                    remapped_chunks = [
-                        ChunkMetadata(
-                            chunk_text=cm.chunk_text,
-                            fact_count=cm.fact_count,
-                            content_index=cm.content_index,
-                            chunk_index=delta_chunk_map.get(cm.chunk_index, cm.chunk_index),
-                        )
-                        for cm in new_chunk_metadata
-                    ]
-                    chunk_id_map = await chunk_storage.store_chunks_batch(
-                        conn, bank_id, effective_doc_id, remapped_chunks
-                    )
-                    for chunk_idx, chunk_id in chunk_id_map.items():
-                        chunk_id_map_by_doc[(effective_doc_id, chunk_idx)] = chunk_id
-                    log_buffer.append(
-                        f"  Stored {len(remapped_chunks)} new/changed chunks in {time.time() - step_start:.3f}s"
-                    )
-
-                # Map chunk_ids and document_ids to processed facts
-                for ef, pf in zip(extracted_facts, processed_facts):
-                    pf.document_id = effective_doc_id
-                    if ef.chunk_index is not None:
-                        original_idx = delta_chunk_map.get(ef.chunk_index, ef.chunk_index)
-                        chunk_id = chunk_id_map_by_doc.get((effective_doc_id, original_idx))
-                        if chunk_id:
-                            pf.chunk_id = chunk_id
-
-                # Insert facts and create all links (shared pipeline)
-                result_unit_ids = await _insert_facts_and_links(
-                    conn,
-                    entity_resolver,
-                    bank_id,
-                    contents,
-                    extracted_facts,
-                    processed_facts,
-                    config,
-                    log_buffer,
-                    outbox_callback,
-                )
-
-            await entity_resolver.flush_pending_stats()
-
-            total_time = time.time() - start_time
-            log_buffer.append(f"{'=' * 60}")
-            log_buffer.append(
-                f"DELTA RETAIN COMPLETE: {len(processed_facts)} new units, "
-                f"{len(unchanged_indices)} chunks unchanged in {total_time:.3f}s"
-            )
-            log_buffer.append(f"Document: {effective_doc_id}")
-            log_buffer.append(f"{'=' * 60}")
-            logger.info("\n" + "\n".join(log_buffer) + "\n")
-
-    await retry_with_backoff(_run_delta_db_work)
-    return result_unit_ids, usage
-
-
-async def _delta_metadata_only(
-    pool,
-    bank_id,
-    contents_dicts,
-    contents,
-    document_id,
-    document_tags,
-    log_buffer,
-    start_time,
-    outbox_callback,
-):
-    """Handle the case where no chunks changed — just update document metadata and tags."""
-    async with acquire_with_retry(pool) as conn:
-        async with conn.transaction():
-            combined_content = "\n".join([c.get("content", "") for c in contents_dicts])
-            retain_params, merged_tags = _build_retain_params(contents_dicts, document_tags)
-            await fact_storage.upsert_document_metadata(
-                conn,
-                bank_id,
-                document_id,
-                combined_content,
-                retain_params,
-                merged_tags,
-            )
-            await fact_storage.update_memory_units_tags(conn, bank_id, document_id, merged_tags)
-            if outbox_callback:
-                await outbox_callback(conn)
-
-    total_time = time.time() - start_time
-    log_buffer.append(f"DELTA RETAIN (no changes): metadata updated in {total_time:.3f}s")
-    logger.info("\n" + "\n".join(log_buffer) + "\n")
-    return [[] for _ in contents], TokenUsage()
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-
-def _build_contents(contents_dicts: list[RetainContentDict], document_tags: list[str] | None) -> list[RetainContent]:
-    """Convert content dicts to RetainContent objects."""
-    contents = []
-    for item in contents_dicts:
-        item_tags = item.get("tags", []) or []
-        merged_tags = list(set(item_tags + (document_tags or [])))
-
-        if "event_date" in item and item["event_date"] is None:
-            event_date_value = None
-        elif item.get("event_date"):
-            event_date_value = parse_datetime_flexible(item["event_date"])
-        else:
-            event_date_value = utcnow()
-
-        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)
-    return contents
-
-
-async def _handle_zero_facts_documents(
-    pool,
-    bank_id,
-    contents_dicts,
-    contents,
-    config,
-    document_id,
-    is_first_batch,
-    document_tags,
-    chunks,
-    log_buffer,
-    start_time,
-):
-    """Handle document tracking when zero facts were extracted."""
-    docs_tracked = 0
-    async with acquire_with_retry(pool) as conn:
-        async with conn.transaction():
-            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))
-
-            if document_id:
-                combined_content = "\n".join([c.get("content", "") for c in contents_dicts])
-                retain_params, merged_tags = _build_retain_params(contents_dicts, document_tags)
-                await fact_storage.handle_document_tracking(
-                    conn, bank_id, document_id, combined_content, is_first_batch, retain_params, merged_tags
-                )
-                docs_tracked += 1
-            else:
-                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():
-                        should_create_doc = (original_doc_id is not None) or chunks
-                        if not should_create_doc:
-                            continue
-                        actual_doc_id = original_doc_id or str(uuid.uuid4())
-                        combined_content = "\n".join([c.get("content", "") for _, c in doc_contents])
-                        retain_params, merged_tags = _build_retain_params(
-                            contents_dicts, document_tags, doc_contents=doc_contents
-                        )
-                        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 "
-        f"in {total_time:.3f}s ({doc_status}, no facts)"
-    )
-
-
-def _chunk_contents_for_delta(contents: list[RetainContent], config) -> dict[int, str]:
-    """
-    Chunk contents the same way fact_extraction does, returning a map of
-    global_chunk_index -> chunk_text.
-    """
-    result = {}
-    global_chunk_idx = 0
-    for content in contents:
-        chunk_size = getattr(config, "retain_chunk_size", 120000)
-        chunks = fact_extraction.chunk_text(content.content, chunk_size)
-        for chunk_text in chunks:
-            result[global_chunk_idx] = chunk_text
-            global_chunk_idx += 1
-    return result
-
-
-def _build_delta_contents(
-    original_contents: list[RetainContent],
-    new_chunks_with_contents: dict[int, str],
-    chunks_to_process: list[int],
-) -> tuple[list[RetainContent], dict[int, int]]:
-    """
-    Build RetainContent items containing only the chunks that need processing.
-
-    Returns:
-        - List of RetainContent items (one per chunk to process)
-        - Map of delta_chunk_index -> original_chunk_index
-    """
-    if not chunks_to_process or not original_contents:
-        return [], {}
-
-    template_content = original_contents[0]
-    delta_contents = []
-    delta_chunk_map = {}
-
-    for original_chunk_idx in sorted(chunks_to_process):
-        chunk_text = new_chunks_with_contents.get(original_chunk_idx)
-        if not chunk_text:
-            continue
-        delta_content = RetainContent(
-            content=chunk_text,
-            context=template_content.context,
-            event_date=template_content.event_date,
-            metadata=template_content.metadata,
-            entities=template_content.entities,
-            tags=template_content.tags,
-            observation_scopes=template_content.observation_scopes,
-        )
-        delta_contents.append(delta_content)
-        delta_chunk_map[len(delta_contents) - 1] = original_chunk_idx
-
-    return delta_contents, delta_chunk_map
-
-
-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/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/gcs.py

@@ -1,105 +0,0 @@
-"""Google Cloud Storage backend using obstore."""
-
-import logging
-import os
-from datetime import datetime, timedelta, timezone
-
-import obstore as obs
-from obstore.store import GCSStore
-
-from .base import FileStorage
-
-logger = logging.getLogger(__name__)
-
-
-def _make_google_auth_credential_provider():
-    """Create a credential provider using google.auth (supports all credential types).
-
-    obstore's built-in credential parsing only supports service_account and
-    authorized_user JSON types.  This provider uses the google-auth library
-    which additionally handles external_account (Workload Identity Federation),
-    impersonated credentials, and metadata-server credentials.
-    """
-    import google.auth
-    import google.auth.transport.requests
-
-    credentials, _ = google.auth.default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
-    request = google.auth.transport.requests.Request()
-
-    def _provide():
-        credentials.refresh(request)
-        expiry = credentials.expiry
-        if expiry and expiry.tzinfo is None:
-            expiry = expiry.replace(tzinfo=timezone.utc)
-        return {"token": credentials.token, "expires_at": expiry}
-
-    return _provide
-
-
-class GCSFileStorage(FileStorage):
-    """
-    Google Cloud Storage backend.
-
-    Uses obstore (Rust-backed) for high-throughput async access to GCS.
-    Supports Application Default Credentials, service account keys, and explicit credentials.
-    """
-
-    def __init__(
-        self,
-        bucket: str,
-        service_account_key: str | None = None,
-    ):
-        kwargs: dict = {}
-        if service_account_key:
-            kwargs["service_account_key"] = service_account_key
-        else:
-            # Use google.auth credential provider for broad credential type support
-            # (service_account, authorized_user, external_account, metadata server, etc.)
-            try:
-                kwargs["credential_provider"] = _make_google_auth_credential_provider()
-                logger.info("Using google.auth credential provider for GCS")
-            except Exception as e:
-                logger.warning(
-                    f"Failed to create google.auth credential provider, falling back to obstore defaults: {e}"
-                )
-
-        # Workaround for https://github.com/developmentseed/obstore/issues/605
-        # obstore's Rust layer doesn't support external_account credentials (Workload
-        # Identity Federation) and eagerly parses GOOGLE_APPLICATION_CREDENTIALS even
-        # when credential_provider is given. Per the obstore maintainer's guidance,
-        # remove env vars so the Rust code doesn't try to authenticate itself.
-        # google.auth (used by credential_provider above) has already loaded credentials.
-        gac = os.environ.pop("GOOGLE_APPLICATION_CREDENTIALS", None)
-        try:
-            self._store = GCSStore(bucket, **kwargs)
-        finally:
-            if gac is not None:
-                os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = gac
-        logger.info(f"Initialized GCS file storage: bucket={bucket}")
-
-    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 GCS")
-        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():
-                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/main.py

@@ -1,302 +0,0 @@
-"""
-Command-line interface for Hindsight API.
-
-Run the server with:
-    hindsight-api
-
-Run as background daemon:
-    hindsight-api --daemon
-
-Stop with Ctrl+C.
-"""
-
-import argparse
-import asyncio
-import atexit
-import dataclasses
-import os
-import signal
-import sys
-import warnings
-
-import uvicorn
-
-from . import MemoryEngine, __version__
-from .api import create_app
-from .banner import print_banner
-from .config import DEFAULT_WORKERS, ENV_WORKERS, HindsightConfig, _get_raw_config
-from .daemon import (
-    DEFAULT_DAEMON_PORT,
-    DEFAULT_IDLE_TIMEOUT,
-    IdleTimeoutMiddleware,
-    daemonize,
-)
-from .extensions import DefaultExtensionContext, OperationValidatorExtension, TenantExtension, load_extension
-
-# Filter deprecation warnings from third-party libraries
-warnings.filterwarnings("ignore", message="websockets.legacy is deprecated")
-warnings.filterwarnings("ignore", message="websockets.server.WebSocketServerProtocol is deprecated")
-
-# Disable tokenizers parallelism to avoid warnings
-os.environ["TOKENIZERS_PARALLELISM"] = "false"
-
-# Global reference for cleanup
-_memory: MemoryEngine | None = None
-
-
-def _cleanup():
-    """Synchronous cleanup function to stop resources on exit."""
-    global _memory
-    if _memory is not None and _memory._pg0 is not None:
-        try:
-            loop = asyncio.new_event_loop()
-            loop.run_until_complete(_memory._pg0.stop())
-            loop.close()
-            print("\npg0 stopped.")
-        except Exception as e:
-            print(f"\nError stopping pg0: {e}")
-
-
-def _signal_handler(signum, frame):
-    """Handle SIGINT/SIGTERM to ensure cleanup."""
-    print(f"\nReceived signal {signum}, shutting down...")
-    _cleanup()
-    sys.exit(0)
-
-
-def main():
-    """Main entry point for the CLI."""
-    global _memory
-
-    # Load configuration from environment (for CLI args defaults)
-    config = _get_raw_config()
-
-    parser = argparse.ArgumentParser(
-        prog="hindsight-api",
-        description="Hindsight API Server",
-    )
-
-    # Server options
-    parser.add_argument(
-        "--host", default=config.host, help=f"Host to bind to (default: {config.host}, env: HINDSIGHT_API_HOST)"
-    )
-    parser.add_argument(
-        "--port",
-        type=int,
-        default=config.port,
-        help=f"Port to bind to (default: {config.port}, env: HINDSIGHT_API_PORT)",
-    )
-    parser.add_argument(
-        "--log-level",
-        default=config.log_level,
-        choices=["critical", "error", "warning", "info", "debug", "trace"],
-        help=f"Log level (default: {config.log_level}, env: HINDSIGHT_API_LOG_LEVEL)",
-    )
-
-    # Development options
-    parser.add_argument("--reload", action="store_true", help="Enable auto-reload on code changes (development only)")
-    parser.add_argument(
-        "--workers",
-        type=int,
-        default=int(os.getenv(ENV_WORKERS, str(DEFAULT_WORKERS))),
-        help=f"Number of worker processes (env: {ENV_WORKERS}, default: {DEFAULT_WORKERS})",
-    )
-
-    # Access log options
-    parser.add_argument("--access-log", action="store_true", help="Enable access log")
-    parser.add_argument("--no-access-log", dest="access_log", action="store_false", help="Disable access log (default)")
-    parser.set_defaults(access_log=False)
-
-    # Proxy options
-    parser.add_argument(
-        "--proxy-headers", action="store_true", help="Enable X-Forwarded-Proto, X-Forwarded-For headers"
-    )
-    parser.add_argument(
-        "--forwarded-allow-ips", default=None, help="Comma separated list of IPs to trust with proxy headers"
-    )
-
-    # SSL options
-    parser.add_argument("--ssl-keyfile", default=None, help="SSL key file")
-    parser.add_argument("--ssl-certfile", default=None, help="SSL certificate file")
-
-    # Daemon mode options
-    parser.add_argument(
-        "--daemon",
-        action="store_true",
-        help=f"Run as background daemon (uses port {DEFAULT_DAEMON_PORT}, auto-exits after idle)",
-    )
-    parser.add_argument(
-        "--idle-timeout",
-        type=int,
-        default=DEFAULT_IDLE_TIMEOUT,
-        help=f"Idle timeout in seconds before auto-exit in daemon mode (default: {DEFAULT_IDLE_TIMEOUT})",
-    )
-
-    args = parser.parse_args()
-
-    # Daemon mode handling
-    if args.daemon:
-        # Use port from args (may be custom for profiles)
-        if args.port == config.port:  # No custom port specified
-            args.port = DEFAULT_DAEMON_PORT
-        args.host = "127.0.0.1"  # Only bind to localhost for security
-
-        # Fork into background
-        # No lockfile needed - port binding prevents duplicate daemons
-        daemonize()
-
-    # Print banner (not in daemon mode)
-    if not args.daemon:
-        print()
-        print_banner()
-
-    # Configure Python logging based on log level
-    # Update config with CLI override if provided
-    if args.log_level != config.log_level:
-        config = dataclasses.replace(config, host=args.host, port=args.port, log_level=args.log_level)
-    config.configure_logging()
-    if not args.daemon:
-        config.log_config()
-
-    # Register cleanup handlers
-    atexit.register(_cleanup)
-    signal.signal(signal.SIGINT, _signal_handler)
-    signal.signal(signal.SIGTERM, _signal_handler)
-
-    # Load operation validator extension if configured
-    operation_validator = load_extension("OPERATION_VALIDATOR", OperationValidatorExtension)
-    if operation_validator:
-        import logging
-
-        logging.info(f"Loaded operation validator: {operation_validator.__class__.__name__}")
-
-    # Load tenant extension if configured
-    tenant_extension = load_extension("TENANT", TenantExtension)
-    if tenant_extension:
-        import logging
-
-        logging.info(f"Loaded tenant extension: {tenant_extension.__class__.__name__}")
-
-    # Create MemoryEngine (reads configuration from environment)
-    _memory = MemoryEngine(
-        operation_validator=operation_validator,
-        tenant_extension=tenant_extension,
-        run_migrations=config.run_migrations_on_startup,
-    )
-
-    # Set extension context on tenant extension (needed for schema provisioning)
-    if tenant_extension:
-        extension_context = DefaultExtensionContext(
-            database_url=config.database_url,
-            memory_engine=_memory,
-        )
-        tenant_extension.set_context(extension_context)
-        logging.info("Extension context set on tenant extension")
-
-    # Create FastAPI app
-    app = create_app(
-        memory=_memory,
-        http_api_enabled=True,
-        mcp_api_enabled=config.mcp_enabled,
-        mcp_mount_path="/mcp",
-        initialize_memory=True,
-    )
-
-    # Wrap with idle timeout middleware in daemon mode
-    idle_middleware = None
-    if args.daemon:
-        idle_middleware = IdleTimeoutMiddleware(app, idle_timeout=args.idle_timeout)
-        app = idle_middleware
-
-    # Prepare uvicorn config
-    # When using workers or reload, we must use import string so each worker can import the app
-    use_import_string = args.workers > 1 or args.reload
-    # Check for uvloop/winloop availability
-    import sys
-
-    loop_impl = "asyncio"
-    if sys.platform == "win32":
-        try:
-            import winloop
-
-            winloop.install()  # Patches asyncio globally — uvicorn uses "asyncio" but gets winloop
-            loop_impl = "asyncio"  # Tell uvicorn "asyncio" — it's now winloop underneath
-            print("winloop installed as asyncio event loop policy (Windows uvloop port)")
-        except ImportError:
-            print("winloop not installed, using default asyncio event loop")
-    else:
-        try:
-            import uvloop  # noqa: F401
-
-            loop_impl = "uvloop"
-            print("uvloop available, will use for event loop")
-        except ImportError:
-            print("uvloop not installed, using default asyncio event loop")
-
-    uvicorn_config = {
-        "app": "hindsight_api.server:app" if use_import_string else app,
-        "host": args.host,
-        "port": args.port,
-        "log_level": args.log_level,
-        "access_log": args.access_log,
-        "proxy_headers": args.proxy_headers,
-        "ws": "wsproto",  # Use wsproto instead of websockets to avoid deprecation warnings
-        "loop": loop_impl,  # Explicitly set event loop implementation
-        "timeout_keep_alive": 30,  # Exceed aiohttp's 15s client timeout so the client always closes first
-        "timeout_graceful_shutdown": 5,  # Cap graceful shutdown at 5s; also enables force-kill on second Ctrl+C
-    }
-
-    # Add optional parameters if provided
-    if args.reload:
-        uvicorn_config["reload"] = True
-    if args.workers > 1:
-        uvicorn_config["workers"] = args.workers
-    if args.forwarded_allow_ips:
-        uvicorn_config["forwarded_allow_ips"] = args.forwarded_allow_ips
-    if args.ssl_keyfile:
-        uvicorn_config["ssl_keyfile"] = args.ssl_keyfile
-    if args.ssl_certfile:
-        uvicorn_config["ssl_certfile"] = args.ssl_certfile
-
-    # Print startup info (not in daemon mode)
-    if not args.daemon:
-        from .banner import print_startup_info
-
-        print_startup_info(
-            host=args.host,
-            port=args.port,
-            database_url=config.database_url,
-            llm_provider=config.llm_provider,
-            llm_model=config.llm_model,
-            embeddings_provider=config.embeddings_provider,
-            reranker_provider=config.reranker_provider,
-            mcp_enabled=config.mcp_enabled,
-            version=__version__,
-            vector_extension=config.vector_extension,
-            text_search_extension=config.text_search_extension,
-        )
-
-    # Start idle checker in daemon mode
-    if idle_middleware is not None:
-        # Start the idle checker in a background thread with its own event loop
-        import logging
-        import threading
-
-        def run_idle_checker():
-            import time
-
-            time.sleep(2)  # Wait for uvicorn to start
-            try:
-                loop = asyncio.new_event_loop()
-                asyncio.set_event_loop(loop)
-                loop.run_until_complete(idle_middleware._check_idle())
-            except Exception as e:
-                logging.error(f"Idle checker error: {e}", exc_info=True)
-
-        threading.Thread(target=run_idle_checker, daemon=True).start()
-
-    uvicorn.run(**uvicorn_config)
-
-
-if __name__ == "__main__":
-    main()

hindsight-api-slim/hindsight_api/mcp_local.py

@@ -1,40 +0,0 @@
-"""
-Local MCP server entry point for use with Claude Code (HTTP transport).
-
-This is a thin wrapper around the main hindsight-api server that pre-configures
-sensible defaults for local use (embedded PostgreSQL via pg0, warning log level).
-
-The full API runs on localhost:8888. Configure Claude Code's MCP settings:
-    claude mcp add --transport http hindsight http://localhost:8888/mcp/
-
-Or pinned to a specific bank (single-bank mode):
-    claude mcp add --transport http hindsight http://localhost:8888/mcp/default/
-
-Run with:
-    hindsight-local-mcp
-
-Or with uvx:
-    uvx hindsight-api@latest hindsight-local-mcp
-
-Environment variables:
-    HINDSIGHT_API_LLM_API_KEY: Required. API key for LLM provider.
-    HINDSIGHT_API_LLM_PROVIDER: Optional. LLM provider (default: "openai").
-    HINDSIGHT_API_LLM_MODEL: Optional. LLM model (default: "gpt-4o-mini").
-    HINDSIGHT_API_DATABASE_URL: Optional. Override database URL (default: pg0://hindsight-mcp).
-"""
-
-import os
-
-
-def main() -> None:
-    """Start the Hindsight API server with local defaults."""
-    # Set local defaults (only if not already configured by the user)
-    os.environ.setdefault("HINDSIGHT_API_DATABASE_URL", "pg0://hindsight-mcp")
-
-    from hindsight_api.main import main as api_main
-
-    api_main()
-
-
-if __name__ == "__main__":
-    main()

hindsight-api-slim/hindsight_api/webhooks/__init__.py

@@ -1,13 +0,0 @@
-"""Webhook system for Hindsight API event notifications."""
-
-from .manager import WebhookManager
-from .models import ConsolidationEventData, RetainEventData, WebhookConfig, WebhookEvent, WebhookEventType
-
-__all__ = [
-    "WebhookManager",
-    "WebhookConfig",
-    "WebhookEvent",
-    "WebhookEventType",
-    "ConsolidationEventData",
-    "RetainEventData",
-]

hindsight-api-slim/hindsight_api/webhooks/manager.py

@@ -1,242 +0,0 @@
-"""Webhook manager for delivering event notifications."""
-
-import hashlib
-import hmac
-import json
-import logging
-import uuid
-from datetime import datetime, timezone
-from typing import TYPE_CHECKING
-
-import asyncpg
-
-from .models import WebhookConfig, WebhookEvent, WebhookHttpConfig
-
-if TYPE_CHECKING:
-    from hindsight_api.extensions.tenant import TenantExtension
-
-logger = logging.getLogger(__name__)
-
-# Retry delay schedule in seconds: 5 retries after the first attempt.
-# Fast early retries catch transient failures; later retries handle longer outages.
-RETRY_DELAYS = [5, 300, 1800, 7200, 18000]
-MAX_ATTEMPTS = len(RETRY_DELAYS) + 1  # first attempt + len(RETRY_DELAYS) retries
-
-
-def _fq_table(table: str, schema: str | None = None) -> str:
-    """Get fully-qualified table name with optional schema prefix."""
-    if schema:
-        return f'"{schema}".{table}'
-    return table
-
-
-def _parse_http_config(value: str | dict | None) -> WebhookHttpConfig:
-    """Parse http_config column value (JSONB returned as text or dict) into a model."""
-    if value is None:
-        return WebhookHttpConfig()
-    if isinstance(value, str):
-        return WebhookHttpConfig.model_validate_json(value)
-    return WebhookHttpConfig.model_validate(value)
-
-
-class WebhookManager:
-    """
-    Manages webhook registration and event firing.
-
-    Supports both global webhooks (configured via env vars) and per-bank
-    webhooks stored in the database. Deliveries are queued as async_operations
-    tasks (operation_type='webhook_delivery') and picked up by the worker poller.
-    """
-
-    def __init__(
-        self,
-        pool: asyncpg.Pool,
-        global_webhooks: list[WebhookConfig],
-        tenant_extension: "TenantExtension | None" = None,
-    ):
-        self._pool = pool
-        self._global_webhooks = global_webhooks
-        self._tenant_extension = tenant_extension
-
-    def _sign_payload(self, secret: str, payload_bytes: bytes) -> str:
-        """Compute HMAC-SHA256 signature for a payload."""
-        return "sha256=" + hmac.new(secret.encode(), payload_bytes, hashlib.sha256).hexdigest()
-
-    async def fire_event(self, event: WebhookEvent, schema: str | None = None) -> None:
-        """
-        Queue webhook deliveries for an event as async_operations tasks.
-
-        Loads per-bank and global webhooks, inserts pending webhook_delivery tasks for
-        any webhook whose event_types list matches the fired event type. The worker
-        poller picks these up and calls MemoryEngine._handle_webhook_delivery().
-
-        Args:
-            event: The event to deliver.
-            schema: Database schema (for multi-tenant). None = default schema.
-        """
-        webhook_table = _fq_table("webhooks", schema)
-        ops_table = _fq_table("async_operations", schema)
-        now = datetime.now(timezone.utc)
-        payload_str = event.model_dump_json()
-
-        try:
-            # Load per-bank webhooks from DB (bank-specific + global NULL rows)
-            rows = await self._pool.fetch(
-                f"""
-                SELECT id, bank_id, url, secret, event_types, enabled, http_config::text
-                FROM {webhook_table}
-                WHERE (bank_id = $1 OR bank_id IS NULL) AND enabled = true
-                """,
-                event.bank_id,
-            )
-
-            db_webhooks = [
-                WebhookConfig(
-                    id=str(row["id"]),
-                    bank_id=row["bank_id"],
-                    url=row["url"],
-                    secret=row["secret"],
-                    event_types=list(row["event_types"]) if row["event_types"] else [],
-                    enabled=row["enabled"],
-                    http_config=_parse_http_config(row["http_config"]),
-                )
-                for row in rows
-            ]
-
-            # Merge with global webhooks from env config
-            all_webhooks = self._global_webhooks + db_webhooks
-            matched = 0
-
-            for webhook in all_webhooks:
-                if not webhook.enabled:
-                    continue
-                if event.event.value not in webhook.event_types:
-                    continue
-
-                operation_id = uuid.uuid4()
-                webhook_id = webhook.id if webhook.id else None
-
-                task_payload = json.dumps(
-                    {
-                        "type": "webhook_delivery",
-                        "operation_id": str(operation_id),
-                        "bank_id": event.bank_id,
-                        "url": webhook.url,
-                        "secret": webhook.secret,
-                        "event_type": event.event.value,
-                        "payload": payload_str,
-                        "webhook_id": webhook_id,
-                        "http_config": webhook.http_config.model_dump(),
-                    }
-                )
-
-                await self._pool.execute(
-                    f"""
-                    INSERT INTO {ops_table}
-                      (operation_id, bank_id, operation_type, status, task_payload, result_metadata, created_at, updated_at)
-                    VALUES ($1, $2, 'webhook_delivery', 'pending', $3::jsonb, '{{}}'::jsonb, $4, $4)
-                    """,
-                    operation_id,
-                    event.bank_id,
-                    task_payload,
-                    now,
-                )
-                matched += 1
-
-            logger.debug(f"Fired webhook event {event.event} for bank {event.bank_id}: {matched} delivery(ies) queued")
-
-        except Exception as e:
-            logger.error(f"Failed to queue webhook deliveries for event {event.event}: {e}")
-
-    async def fire_event_with_conn(
-        self, event: WebhookEvent, conn: asyncpg.Connection, schema: str | None = None
-    ) -> None:
-        """
-        Queue webhook deliveries within an existing database connection/transaction.
-
-        Identical to fire_event() but uses the provided connection instead of acquiring
-        one from the pool. Use this to atomically insert delivery tasks in the same
-        transaction as the primary operation (transactional outbox pattern).
-
-        Args:
-            event: The event to deliver.
-            conn: Existing asyncpg connection (may be inside an active transaction).
-            schema: Database schema (for multi-tenant). None = default schema.
-        """
-        webhook_table = _fq_table("webhooks", schema)
-        ops_table = _fq_table("async_operations", schema)
-        now = datetime.now(timezone.utc)
-        payload_str = event.model_dump_json()
-
-        try:
-            rows = await conn.fetch(
-                f"""
-                SELECT id, bank_id, url, secret, event_types, enabled, http_config::text
-                FROM {webhook_table}
-                WHERE (bank_id = $1 OR bank_id IS NULL) AND enabled = true
-                """,
-                event.bank_id,
-            )
-
-            db_webhooks = [
-                WebhookConfig(
-                    id=str(row["id"]),
-                    bank_id=row["bank_id"],
-                    url=row["url"],
-                    secret=row["secret"],
-                    event_types=list(row["event_types"]) if row["event_types"] else [],
-                    enabled=row["enabled"],
-                    http_config=_parse_http_config(row["http_config"]),
-                )
-                for row in rows
-            ]
-
-            all_webhooks = self._global_webhooks + db_webhooks
-            matched = 0
-
-            for webhook in all_webhooks:
-                if not webhook.enabled:
-                    continue
-                if event.event.value not in webhook.event_types:
-                    continue
-
-                operation_id = uuid.uuid4()
-                webhook_id = webhook.id if webhook.id else None
-
-                task_payload = json.dumps(
-                    {
-                        "type": "webhook_delivery",
-                        "operation_id": str(operation_id),
-                        "bank_id": event.bank_id,
-                        "url": webhook.url,
-                        "secret": webhook.secret,
-                        "event_type": event.event.value,
-                        "payload": payload_str,
-                        "webhook_id": webhook_id,
-                        "http_config": webhook.http_config.model_dump(),
-                    }
-                )
-
-                await conn.execute(
-                    f"""
-                    INSERT INTO {ops_table}
-                      (operation_id, bank_id, operation_type, status, task_payload, result_metadata, created_at, updated_at)
-                    VALUES ($1, $2, 'webhook_delivery', 'pending', $3::jsonb, '{{}}'::jsonb, $4, $4)
-                    """,
-                    operation_id,
-                    event.bank_id,
-                    task_payload,
-                    now,
-                )
-                matched += 1
-
-            logger.debug(
-                f"Fired webhook event {event.event} for bank {event.bank_id}: {matched} delivery(ies) queued (in-transaction)"
-            )
-
-        except Exception as e:
-            logger.error(
-                f"Failed to queue webhook deliveries (in-transaction) for event {event.event}: {e}. "
-                "CRITICAL: The enclosing database transaction is now aborted and will roll back all changes."
-            )
-            raise

hindsight-api-slim/hindsight_api/webhooks/models.py

@@ -1,51 +0,0 @@
-"""Pydantic models for the webhook system."""
-
-from datetime import datetime
-from enum import StrEnum
-
-from pydantic import BaseModel, Field
-
-
-class WebhookEventType(StrEnum):
-    CONSOLIDATION_COMPLETED = "consolidation.completed"
-    RETAIN_COMPLETED = "retain.completed"
-
-
-class ConsolidationEventData(BaseModel):
-    observations_created: int | None = None
-    observations_updated: int | None = None
-    observations_deleted: int | None = None
-    error_message: str | None = None
-
-
-class RetainEventData(BaseModel):
-    document_id: str | None = None
-    tags: list[str] | None = None
-
-
-class WebhookEvent(BaseModel):
-    event: WebhookEventType
-    bank_id: str
-    operation_id: str
-    status: str  # "completed" or "failed"
-    timestamp: datetime
-    data: ConsolidationEventData | RetainEventData
-
-
-class WebhookHttpConfig(BaseModel):
-    """HTTP delivery configuration for a webhook."""
-
-    method: str = Field(default="POST", description="HTTP method: GET or POST")
-    timeout_seconds: int = Field(default=30, description="HTTP request timeout in seconds")
-    headers: dict[str, str] = Field(default_factory=dict, description="Custom HTTP headers")
-    params: dict[str, str] = Field(default_factory=dict, description="Custom HTTP query parameters")
-
-
-class WebhookConfig(BaseModel):
-    id: str
-    bank_id: str | None
-    url: str
-    secret: str | None
-    event_types: list[str]
-    enabled: bool
-    http_config: WebhookHttpConfig = Field(default_factory=WebhookHttpConfig)

hindsight-api-slim/hindsight_api/worker/exceptions.py

@@ -1,9 +0,0 @@
-from datetime import datetime
-
-
-class RetryTaskAt(Exception):
-    """Raise from a task handler to schedule a retry at a specific time."""
-
-    def __init__(self, retry_at: datetime, message: str = ""):
-        self.retry_at = retry_at
-        super().__init__(message)

hindsight-api-slim/pyproject.toml

@@ -1,211 +0,0 @@
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
-
-[project]
-name = "hindsight-api-slim"
-version = "0.4.20"
-description = "Hindsight: Agent Memory That Works Like Human Memory"
-readme = "README.md"
-requires-python = ">=3.11"
-dependencies = [
-    "asyncpg>=0.29.0",
-    "python-dotenv>=1.0.0",
-    "openai>=1.0.0",
-    "pydantic>=2.0.0",
-    "rich>=13.0.0",
-    "langchain-text-splitters>=0.3.0",
-    "fastapi[standard]>=0.120.3",
-    "uvicorn>=0.38.0",
-    "wsproto>=1.0.0",
-    "sqlalchemy>=2.0.44",
-    "alembic>=1.17.1",
-    "pgvector>=0.4.1",
-    "greenlet>=3.2.4",
-    "psycopg2-binary>=2.9.11",
-    "tiktoken>=0.12.0",
-    "httpx>=0.27.0",
-    "PyJWT[crypto]>=2.8.0",
-    "fastmcp>=2.14.0", # CVE-2025-66416
-    "python-dateutil>=2.8.0",
-    "opentelemetry-api>=1.20.0",
-    "opentelemetry-sdk>=1.20.0",
-    "opentelemetry-instrumentation-fastapi>=0.41b0",
-    "opentelemetry-exporter-prometheus>=0.41b0",
-    "opentelemetry-exporter-otlp-proto-http>=1.20.0",
-    "opentelemetry-semantic-conventions>=0.41b0",
-    "dateparser>=1.2.2",
-    "google-genai>=1.0.0",
-    "google-auth>=2.0.0",
-    "anthropic>=0.40.0",
-    "typer>=0.9.0",
-    "cohere>=5.0.0",
-    "litellm>=1.0.0,<=1.82.6", # 1.82.7+ contains a supply chain attack (malicious .pth credential stealer)
-    "markitdown[pdf,docx,pptx,xlsx,xls]>=0.1.4", # File to markdown conversion
-    "obstore>=0.4.0", # S3/GCS/Azure object storage client (Rust-backed)
-    "winloop>=0.1.0; sys_platform == 'win32'",
-    "uvloop>=0.22.1; sys_platform != 'win32'",
-    # Transitive dependency security fixes
-    "pyasn1>=0.6.3", # DoS vulnerability fix
-    "urllib3>=2.6.3", # Decompression-bomb safeguards bypass fix
-    "langchain-core>=1.2.11", # Serialization injection + SSRF vulnerability fix
-    "langsmith>=0.6.3", # SSRF via tracing header injection fix
-    "protobuf>=6.33.5", # JSON recursion depth bypass fix
-    "pillow>=12.1.1", # Out-of-bounds write in PSD image loading fix
-    "cryptography>=46.0.5", # Subgroup attack vulnerability fix
-    "filelock>=3.20.1", # TOCTOU race condition fix
-    "authlib>=1.6.9", # Account takeover/JWS header injection vulnerability fix
-    "pyjwt>=2.12.0", # Accepts unknown crit header extensions fix
-    "orjson>=3.11.6", # Unbounded recursion DoS fix
-    "python-multipart>=0.0.22", # Arbitrary file write via non-default configuration fix
-    "tornado>=6.5.5", # DoS multipart/incomplete cookie validation fix
-    "aiohttp>=3.13.3", # Multiple DoS vulnerabilities
-    "claude-agent-sdk>=0.1.27",
-    "boto3>=1.42.74",
-]
-
-[project.optional-dependencies]
-local-ml = [
-    # Local ML models for embeddings/reranking
-    "sentence-transformers>=3.3.0",
-    "transformers>=4.53.0", # Security fixes for ReDoS vulnerabilities
-    "torch>=2.6.0", # CVE fix for remote code execution
-    "einops>=0.8.2",
-    "flashrank>=0.2.0",
-    # Apple Silicon local inference
-    "mlx>=0.31.0",
-    "mlx-lm>=0.31.1",
-    "safetensors>=0.6.2",
-]
-embedded-db = [
-    "pg0-embedded>=0.11.0",
-]
-all = [
-    "hindsight-api-slim[local-ml,embedded-db]",
-]
-test = [
-    "pytest>=7.0.0",
-    "pytest-asyncio>=0.21.0",
-    "pytest-timeout>=2.4.0",
-    "pytest-xdist>=3.0.0",
-    "filelock>=3.20.1",  # TOCTOU race condition fix
-    "testcontainers>=4.0.0",
-]
-
-[project.scripts]
-hindsight-api = "hindsight_api.main:main"
-hindsight-worker = "hindsight_api.worker.main:main"
-hindsight-local-mcp = "hindsight_api.mcp_local:main"
-hindsight-admin = "hindsight_api.admin.cli:main"
-
-[tool.hatch.build.targets.wheel]
-packages = ["hindsight_api"]
-
-[tool.hatch.build.targets.wheel.sources]
-"hindsight_api" = "hindsight_api"
-
-[tool.hatch.build.targets.sdist]
-include = [
-    "hindsight_api/**/*",
-]
-
-[tool.hatch.build]
-include = [
-    "hindsight_api/**/*.py",
-    "hindsight_api/alembic/**/*",
-]
-
-[tool.pytest.ini_options]
-log_cli = true
-log_cli_level = "INFO"
-log_cli_format = "%(asctime)s - %(levelname)s - %(name)s - %(message)s"
-log_cli_date_format = "%Y-%m-%d %H:%M:%S"
-addopts = "--timeout 300 -n 8 --dist loadgroup --durations=10 -v"
-asyncio_mode = "auto"
-asyncio_default_fixture_loop_scope = "function"
-log_auto_indent = true
-filterwarnings = [
-    "ignore:The @wait_container_is_ready decorator is deprecated:DeprecationWarning",
-    "ignore::RuntimeWarning:asyncio",
-]
-
-[dependency-groups]
-dev = [
-    "pytest>=9.0.0",
-    "pytest-asyncio>=1.3.0",
-    "pytest-timeout>=2.4.0",
-    "pytest-xdist>=3.8.0",
-    "python-dotenv>=1.2.1",
-    "filelock>=3.20.1",  # TOCTOU race condition fix
-    "ruff>=0.8.0",
-    "ty>=0.0.1",
-    "testcontainers>=4.0.0",
-]
-
-[tool.ruff]
-line-length = 120
-target-version = "py311"
-exclude = [
-    "tests/",
-    "**/tests/",
-]
-
-[tool.ruff.lint]
-select = [
-    "E",      # pycodestyle errors
-    "W",      # pycodestyle warnings
-    "F",      # Pyflakes
-    "I",      # isort
-]
-ignore = [
-    "E501",   # line too long (handled by formatter)
-    "E402",   # module import not at top of file
-    "F401",   # unused import (too noisy during development)
-    "F841",   # unused variable (too noisy during development)
-    "F811",   # redefined while unused
-    "F821",   # undefined name (forward references in type hints)
-]
-
-[tool.ruff.lint.isort]
-known-third-party = ["alembic"]
-
-[tool.ruff.format]
-quote-style = "double"
-indent-style = "space"
-
-[tool.uv]
-# Use explicit index for PyTorch to prevent the pytorch index from serving
-# non-pytorch packages (e.g. markupsafe) with incompatible wheels
-[[tool.uv.index]]
-name = "pytorch-cpu"
-url = "https://download.pytorch.org/whl/cpu"
-explicit = true
-
-[tool.uv.sources]
-# Route torch to the CPU-only PyTorch index; everything else uses PyPI
-torch = { index = "pytorch-cpu" }
-
-[tool.ty]
-# Type checking configuration
-# ty is an extremely fast Python type checker from Astral (same team as ruff/uv)
-
-[tool.ty.environment]
-python-version = "3.11"
-
-[tool.ty.src]
-exclude = [
-    "tests/",
-    "hindsight_api/alembic/",
-]
-
-[tool.ty.rules]
-# Disable noisy rules while keeping important ones
-invalid-argument-type = "ignore"    # False positives with **kwargs patterns
-invalid-return-type = "ignore"      # Often intentional in async code
-invalid-parameter-default = "ignore" # Optional params with None default
-possibly-missing-attribute = "ignore" # Common with Optional types
-invalid-raise = "ignore"            # False positives with exception tracking
-call-non-callable = "ignore"        # False positives with Optional types
-invalid-key = "ignore"              # Pydantic ConfigDict not understood
-invalid-method-override = "ignore"  # Intentional signature differences
-unresolved-reference = "ignore"     # Forward references not always resolved

hindsight-api-slim/tests/test_audit_log.py

@@ -1,449 +0,0 @@
-"""
-Tests for the audit log feature.
-
-Tests the audit log list, stats, filtering, and pagination endpoints.
-Verifies that audit entries are created for operations when audit logging is enabled.
-"""
-
-import asyncio
-
-import httpx
-import pytest
-import pytest_asyncio
-
-from hindsight_api.api import create_app
-from hindsight_api.config import get_config
-
-
-@pytest_asyncio.fixture
-async def audit_api_client(memory):
-    """Create a test client with audit logging enabled."""
-    # Enable audit logging on the memory engine's audit logger
-    memory._audit_logger._enabled = True
-    memory._audit_logger._allowed_actions = None  # All actions
-
-    app = create_app(memory, initialize_memory=False)
-    transport = httpx.ASGITransport(app=app)
-    async with httpx.AsyncClient(transport=transport, base_url="http://test") as client:
-        yield client
-
-
-@pytest.fixture
-def bank_id():
-    """Provide a unique bank ID for audit tests."""
-    from datetime import datetime
-
-    return f"audit_test_{datetime.now().timestamp()}"
-
-
-@pytest.mark.asyncio
-async def test_audit_log_list_empty(audit_api_client, bank_id):
-    """Test listing audit logs for a bank with no entries returns empty."""
-    # Create the bank first
-    await audit_api_client.put(
-        f"/v1/default/banks/{bank_id}",
-        json={"name": "Audit Test Bank"},
-    )
-
-    # Small delay for fire-and-forget audit writes
-    await asyncio.sleep(0.5)
-
-    response = await audit_api_client.get(f"/v1/default/banks/{bank_id}/audit-logs")
-    assert response.status_code == 200
-    data = response.json()
-    assert data["bank_id"] == bank_id
-    assert "total" in data
-    assert "items" in data
-    assert "limit" in data
-    assert "offset" in data
-    assert isinstance(data["items"], list)
-
-
-@pytest.mark.asyncio
-async def test_audit_log_created_for_retain(audit_api_client, bank_id):
-    """Test that a retain operation creates an audit log entry."""
-    # Create bank
-    await audit_api_client.put(
-        f"/v1/default/banks/{bank_id}",
-        json={"name": "Audit Test Bank"},
-    )
-
-    # Perform a retain
-    response = await audit_api_client.post(
-        f"/v1/default/banks/{bank_id}/memories",
-        json={
-            "items": [{"content": "Alice likes cats", "context": "preferences"}],
-        },
-    )
-    assert response.status_code == 200
-
-    # Wait for fire-and-forget audit writes
-    await asyncio.sleep(1.0)
-
-    # List audit logs - should have entries for create_bank and retain
-    response = await audit_api_client.get(f"/v1/default/banks/{bank_id}/audit-logs")
-    assert response.status_code == 200
-    data = response.json()
-    assert data["total"] >= 1
-
-    actions = [item["action"] for item in data["items"]]
-    assert "retain" in actions, f"Expected 'retain' in audit actions, got: {actions}"
-
-
-@pytest.mark.asyncio
-async def test_audit_log_entry_fields(audit_api_client, bank_id):
-    """Test that audit log entries have all expected fields."""
-    # Create bank + recall to generate entries
-    await audit_api_client.put(
-        f"/v1/default/banks/{bank_id}",
-        json={"name": "Audit Test Bank"},
-    )
-
-    await audit_api_client.post(
-        f"/v1/default/banks/{bank_id}/memories/recall",
-        json={"query": "test query"},
-    )
-
-    await asyncio.sleep(1.0)
-
-    response = await audit_api_client.get(f"/v1/default/banks/{bank_id}/audit-logs")
-    assert response.status_code == 200
-    data = response.json()
-    assert data["total"] >= 1
-
-    # Check the recall entry has all fields
-    recall_entries = [item for item in data["items"] if item["action"] == "recall"]
-    assert len(recall_entries) >= 1, f"Expected recall entry, got actions: {[i['action'] for i in data['items']]}"
-
-    entry = recall_entries[0]
-    assert entry["id"] is not None
-    assert entry["action"] == "recall"
-    assert entry["transport"] == "http"
-    assert entry["bank_id"] == bank_id
-    assert entry["started_at"] is not None
-    assert entry["ended_at"] is not None
-    # Request should contain the recall parameters
-    assert entry["request"] is not None
-    assert "query" in entry["request"]
-    # Response should contain the recall results
-    assert entry["response"] is not None
-
-
-@pytest.mark.asyncio
-async def test_audit_log_filter_by_action(audit_api_client, bank_id):
-    """Test filtering audit logs by action type."""
-    # Create bank and do retain + recall
-    await audit_api_client.put(
-        f"/v1/default/banks/{bank_id}",
-        json={"name": "Audit Test Bank"},
-    )
-    await audit_api_client.post(
-        f"/v1/default/banks/{bank_id}/memories",
-        json={"items": [{"content": "test content", "context": "test"}]},
-    )
-    await audit_api_client.post(
-        f"/v1/default/banks/{bank_id}/memories/recall",
-        json={"query": "test"},
-    )
-
-    await asyncio.sleep(1.0)
-
-    # Filter by retain only
-    response = await audit_api_client.get(
-        f"/v1/default/banks/{bank_id}/audit-logs",
-        params={"action": "retain"},
-    )
-    assert response.status_code == 200
-    data = response.json()
-    for item in data["items"]:
-        assert item["action"] == "retain"
-
-    # Filter by recall only
-    response = await audit_api_client.get(
-        f"/v1/default/banks/{bank_id}/audit-logs",
-        params={"action": "recall"},
-    )
-    assert response.status_code == 200
-    data = response.json()
-    for item in data["items"]:
-        assert item["action"] == "recall"
-
-
-@pytest.mark.asyncio
-async def test_audit_log_filter_by_transport(audit_api_client, bank_id):
-    """Test filtering audit logs by transport type."""
-    await audit_api_client.put(
-        f"/v1/default/banks/{bank_id}",
-        json={"name": "Audit Test Bank"},
-    )
-
-    await asyncio.sleep(0.5)
-
-    # Filter by http transport
-    response = await audit_api_client.get(
-        f"/v1/default/banks/{bank_id}/audit-logs",
-        params={"transport": "http"},
-    )
-    assert response.status_code == 200
-    data = response.json()
-    for item in data["items"]:
-        assert item["transport"] == "http"
-
-    # Filter by mcp transport - should be empty (no MCP calls in this test)
-    response = await audit_api_client.get(
-        f"/v1/default/banks/{bank_id}/audit-logs",
-        params={"transport": "mcp"},
-    )
-    assert response.status_code == 200
-    data = response.json()
-    assert data["total"] == 0
-
-
-@pytest.mark.asyncio
-async def test_audit_log_filter_by_date_range(audit_api_client, bank_id):
-    """Test filtering audit logs by date range."""
-    from datetime import datetime, timedelta, timezone
-
-    await audit_api_client.put(
-        f"/v1/default/banks/{bank_id}",
-        json={"name": "Audit Test Bank"},
-    )
-
-    await asyncio.sleep(0.5)
-
-    now = datetime.now(timezone.utc)
-
-    # Filter with start_date in the past - should include entries
-    past = (now - timedelta(hours=1)).isoformat()
-    response = await audit_api_client.get(
-        f"/v1/default/banks/{bank_id}/audit-logs",
-        params={"start_date": past},
-    )
-    assert response.status_code == 200
-    data = response.json()
-    assert data["total"] >= 1
-
-    # Filter with start_date in the future - should be empty
-    future = (now + timedelta(hours=1)).isoformat()
-    response = await audit_api_client.get(
-        f"/v1/default/banks/{bank_id}/audit-logs",
-        params={"start_date": future},
-    )
-    assert response.status_code == 200
-    data = response.json()
-    assert data["total"] == 0
-
-
-@pytest.mark.asyncio
-async def test_audit_log_pagination(audit_api_client, bank_id):
-    """Test audit log pagination with limit and offset."""
-    await audit_api_client.put(
-        f"/v1/default/banks/{bank_id}",
-        json={"name": "Audit Test Bank"},
-    )
-
-    # Generate multiple audit entries
-    for i in range(5):
-        await audit_api_client.post(
-            f"/v1/default/banks/{bank_id}/memories/recall",
-            json={"query": f"test query {i}"},
-        )
-
-    await asyncio.sleep(1.5)
-
-    # Get first page
-    response = await audit_api_client.get(
-        f"/v1/default/banks/{bank_id}/audit-logs",
-        params={"limit": 2, "offset": 0},
-    )
-    assert response.status_code == 200
-    page1 = response.json()
-    assert len(page1["items"]) == 2
-    assert page1["limit"] == 2
-    assert page1["offset"] == 0
-    assert page1["total"] >= 5  # At least 5 recall + 1 create_bank
-
-    # Get second page
-    response = await audit_api_client.get(
-        f"/v1/default/banks/{bank_id}/audit-logs",
-        params={"limit": 2, "offset": 2},
-    )
-    assert response.status_code == 200
-    page2 = response.json()
-    assert len(page2["items"]) == 2
-    assert page2["offset"] == 2
-
-    # Entries should be different between pages
-    page1_ids = {item["id"] for item in page1["items"]}
-    page2_ids = {item["id"] for item in page2["items"]}
-    assert page1_ids.isdisjoint(page2_ids), "Pages should not overlap"
-
-
-@pytest.mark.asyncio
-async def test_audit_log_stats(audit_api_client, bank_id):
-    """Test the audit log stats endpoint returns correct structure."""
-    await audit_api_client.put(
-        f"/v1/default/banks/{bank_id}",
-        json={"name": "Audit Test Bank"},
-    )
-
-    await audit_api_client.post(
-        f"/v1/default/banks/{bank_id}/memories/recall",
-        json={"query": "stats test"},
-    )
-
-    await asyncio.sleep(1.0)
-
-    # Get stats for last 24h
-    response = await audit_api_client.get(
-        f"/v1/default/banks/{bank_id}/audit-logs/stats",
-        params={"period": "1d"},
-    )
-    assert response.status_code == 200
-    data = response.json()
-    assert data["bank_id"] == bank_id
-    assert data["period"] == "1d"
-    assert data["trunc"] == "day"
-    assert "buckets" in data
-    assert isinstance(data["buckets"], list)
-
-    # Should have at least one bucket with our operations
-    assert len(data["buckets"]) >= 1
-    bucket = data["buckets"][0]
-    assert "time" in bucket
-    assert "actions" in bucket
-    assert "total" in bucket
-    assert bucket["total"] >= 1
-
-
-@pytest.mark.asyncio
-async def test_audit_log_stats_filter_by_action(audit_api_client, bank_id):
-    """Test stats endpoint filters by action."""
-    await audit_api_client.put(
-        f"/v1/default/banks/{bank_id}",
-        json={"name": "Audit Test Bank"},
-    )
-
-    await audit_api_client.post(
-        f"/v1/default/banks/{bank_id}/memories/recall",
-        json={"query": "test"},
-    )
-
-    await asyncio.sleep(1.0)
-
-    # Stats filtered by recall
-    response = await audit_api_client.get(
-        f"/v1/default/banks/{bank_id}/audit-logs/stats",
-        params={"period": "1d", "action": "recall"},
-    )
-    assert response.status_code == 200
-    data = response.json()
-    for bucket in data["buckets"]:
-        # All actions in buckets should be "recall" only
-        for action_name in bucket["actions"]:
-            assert action_name == "recall"
-
-
-@pytest.mark.asyncio
-async def test_audit_log_stats_periods(audit_api_client, bank_id):
-    """Test stats endpoint supports different periods."""
-    await audit_api_client.put(
-        f"/v1/default/banks/{bank_id}",
-        json={"name": "Audit Test Bank"},
-    )
-
-    await asyncio.sleep(0.5)
-
-    for period, expected_trunc in [("1d", "day"), ("7d", "day"), ("30d", "day")]:
-        response = await audit_api_client.get(
-            f"/v1/default/banks/{bank_id}/audit-logs/stats",
-            params={"period": period},
-        )
-        assert response.status_code == 200
-        data = response.json()
-        assert data["period"] == period
-        assert data["trunc"] == expected_trunc
-
-
-@pytest.mark.asyncio
-async def test_audit_log_disabled(memory):
-    """Test that no audit logs are created when audit logging is disabled."""
-    # Ensure audit logging is disabled
-    memory._audit_logger._enabled = False
-
-    app = create_app(memory, initialize_memory=False)
-    transport = httpx.ASGITransport(app=app)
-    async with httpx.AsyncClient(transport=transport, base_url="http://test") as client:
-        from datetime import datetime
-
-        bid = f"audit_disabled_test_{datetime.now().timestamp()}"
-
-        await client.put(f"/v1/default/banks/{bid}", json={"name": "No Audit"})
-        await client.post(
-            f"/v1/default/banks/{bid}/memories/recall",
-            json={"query": "test"},
-        )
-
-        await asyncio.sleep(0.5)
-
-        response = await client.get(f"/v1/default/banks/{bid}/audit-logs")
-        assert response.status_code == 200
-        data = response.json()
-        assert data["total"] == 0, "No audit entries should exist when audit logging is disabled"
-
-
-@pytest.mark.asyncio
-async def test_audit_log_action_allowlist(memory):
-    """Test that only allowed actions are audited when allowlist is set."""
-    memory._audit_logger._enabled = True
-    memory._audit_logger._allowed_actions = frozenset({"recall"})  # Only audit recall
-
-    app = create_app(memory, initialize_memory=False)
-    transport = httpx.ASGITransport(app=app)
-    async with httpx.AsyncClient(transport=transport, base_url="http://test") as client:
-        from datetime import datetime
-
-        bid = f"audit_allowlist_test_{datetime.now().timestamp()}"
-
-        # create_bank should NOT be audited
-        await client.put(f"/v1/default/banks/{bid}", json={"name": "Allowlist Test"})
-        # recall should be audited
-        await client.post(
-            f"/v1/default/banks/{bid}/memories/recall",
-            json={"query": "allowlist test"},
-        )
-
-        await asyncio.sleep(1.0)
-
-        response = await client.get(f"/v1/default/banks/{bid}/audit-logs")
-        assert response.status_code == 200
-        data = response.json()
-        actions = [item["action"] for item in data["items"]]
-        assert "recall" in actions, "recall should be audited"
-        assert "create_bank" not in actions, "create_bank should NOT be audited (not in allowlist)"
-
-
-@pytest.mark.asyncio
-async def test_audit_log_ordered_by_most_recent(audit_api_client, bank_id):
-    """Test that audit logs are returned ordered by most recent first."""
-    await audit_api_client.put(
-        f"/v1/default/banks/{bank_id}",
-        json={"name": "Order Test Bank"},
-    )
-
-    for i in range(3):
-        await audit_api_client.post(
-            f"/v1/default/banks/{bank_id}/memories/recall",
-            json={"query": f"order test {i}"},
-        )
-        await asyncio.sleep(0.2)  # Small gap between requests
-
-    await asyncio.sleep(1.0)
-
-    response = await audit_api_client.get(f"/v1/default/banks/{bank_id}/audit-logs")
-    assert response.status_code == 200
-    data = response.json()
-
-    # Check descending order by started_at
-    timestamps = [item["started_at"] for item in data["items"] if item["started_at"]]
-    assert timestamps == sorted(timestamps, reverse=True), "Audit logs should be ordered most recent first"

hindsight-api-slim/tests/test_combined_scoring.py

@@ -1,171 +0,0 @@
-"""
-Tests for combined scoring (apply_combined_scoring).
-
-The function applies multiplicative recency/temporal boosts to the cross-encoder
-score so that the relative influence of these signals is proportional to the base
-relevance score, independent of the cross-encoder model's score calibration.
-"""
-
-from datetime import datetime, timedelta, timezone
-from unittest.mock import MagicMock
-
-import pytest
-
-from hindsight_api.engine.search.reranking import apply_combined_scoring, _RECENCY_ALPHA, _TEMPORAL_ALPHA
-from hindsight_api.engine.search.types import MergedCandidate, RetrievalResult, ScoredResult
-
-UTC = timezone.utc
-NOW = datetime(2024, 6, 1, tzinfo=UTC)
-
-
-def _make_result(
-    ce_norm: float,
-    occurred_start: datetime | None = None,
-    temporal_proximity: float | None = None,
-) -> ScoredResult:
-    retrieval = MagicMock(spec=RetrievalResult)
-    retrieval.occurred_start = occurred_start
-    retrieval.temporal_proximity = temporal_proximity
-
-    candidate = MagicMock(spec=MergedCandidate)
-    candidate.retrieval = retrieval
-    candidate.rrf_score = 0.05
-
-    return ScoredResult(
-        candidate=candidate,
-        cross_encoder_score=1.0,
-        cross_encoder_score_normalized=ce_norm,
-        weight=ce_norm,
-    )
-
-
-class TestBoostFormula:
-    def test_neutral_signals_leave_score_unchanged(self):
-        """recency=0.5 and temporal=0.5 both produce boost=1.0, so weight == ce."""
-        sr = _make_result(ce_norm=0.6)
-        apply_combined_scoring([sr], now=NOW)
-        assert abs(sr.weight - 0.6) < 1e-9
-
-    def test_max_recency_boost(self):
-        """A memory from today (recency≈1.0) should boost by (1 + alpha*0.5)."""
-        sr = _make_result(ce_norm=0.5, occurred_start=NOW)
-        apply_combined_scoring([sr], now=NOW)
-        expected = 0.5 * (1.0 + _RECENCY_ALPHA * 0.5) * 1.0  # temporal neutral
-        assert abs(sr.weight - expected) < 1e-6
-
-    def test_min_recency_penalty(self):
-        """A memory from >365 days ago (recency=0.1) should penalise score."""
-        old = NOW - timedelta(days=400)
-        sr = _make_result(ce_norm=0.5, occurred_start=old)
-        apply_combined_scoring([sr], now=NOW)
-        expected = 0.5 * (1.0 + _RECENCY_ALPHA * (0.1 - 0.5)) * 1.0
-        assert abs(sr.weight - expected) < 1e-6
-
-    def test_max_temporal_boost(self):
-        """temporal_proximity=1.0 should boost by (1 + alpha*0.5)."""
-        sr = _make_result(ce_norm=0.5, temporal_proximity=1.0)
-        apply_combined_scoring([sr], now=NOW)
-        expected = 0.5 * 1.0 * (1.0 + _TEMPORAL_ALPHA * 0.5)  # recency neutral
-        assert abs(sr.weight - expected) < 1e-6
-
-    def test_temporal_none_is_neutral(self):
-        """temporal_proximity=None must be treated as 0.5 (no boost/penalty)."""
-        sr_none = _make_result(ce_norm=0.5, temporal_proximity=None)
-        sr_half = _make_result(ce_norm=0.5, temporal_proximity=0.5)
-        apply_combined_scoring([sr_none], now=NOW)
-        apply_combined_scoring([sr_half], now=NOW)
-        assert abs(sr_none.weight - sr_half.weight) < 1e-9
-
-    def test_both_signals_combined(self):
-        """Both boosts are applied multiplicatively."""
-        sr = _make_result(ce_norm=0.5, occurred_start=NOW, temporal_proximity=1.0)
-        apply_combined_scoring([sr], now=NOW)
-        recency_boost = 1.0 + _RECENCY_ALPHA * (1.0 - 0.5)
-        temporal_boost = 1.0 + _TEMPORAL_ALPHA * (1.0 - 0.5)
-        expected = 0.5 * recency_boost * temporal_boost
-        assert abs(sr.weight - expected) < 1e-6
-
-    def test_boost_is_proportional_to_ce(self):
-        """The absolute boost from recency scales with the CE score."""
-        sr_high = _make_result(ce_norm=0.9, occurred_start=NOW)
-        sr_low = _make_result(ce_norm=0.3, occurred_start=NOW)
-        apply_combined_scoring([sr_high, sr_low], now=NOW)
-
-        # Both get the same recency boost factor — absolute gain is proportional to CE
-        boost_factor = 1.0 + _RECENCY_ALPHA * 0.5
-        assert abs(sr_high.weight - 0.9 * boost_factor) < 1e-6
-        assert abs(sr_low.weight - 0.3 * boost_factor) < 1e-6
-
-    def test_boost_capped(self):
-        """Max boost: recency=1.0 + temporal=1.0 gives ≤21% uplift on CE."""
-        sr = _make_result(ce_norm=1.0, occurred_start=NOW, temporal_proximity=1.0)
-        apply_combined_scoring([sr], now=NOW)
-        assert sr.weight <= 1.0 * (1 + _RECENCY_ALPHA / 2) * (1 + _TEMPORAL_ALPHA / 2) + 1e-9
-
-    def test_rrf_normalized_always_zero(self):
-        """RRF is excluded from scoring; rrf_normalized is set to 0.0 for trace clarity."""
-        sr = _make_result(ce_norm=0.5)
-        apply_combined_scoring([sr], now=NOW)
-        assert sr.rrf_normalized == 0.0
-
-    def test_combined_score_equals_weight(self):
-        """combined_score and weight must stay in sync."""
-        sr = _make_result(ce_norm=0.7, occurred_start=NOW, temporal_proximity=0.8)
-        apply_combined_scoring([sr], now=NOW)
-        assert sr.combined_score == sr.weight
-
-    def test_model_calibration_independence(self):
-        """
-        A low-calibration model (low CE scores) and a high-calibration model
-        (high CE scores) should produce the same ranking for identical content.
-
-        With additive scoring the recency term would dominate for low-CE models;
-        with multiplicative boosting the relative ranking is stable.
-        """
-        recent = NOW - timedelta(days=10)
-        old = NOW - timedelta(days=300)
-
-        # High-calibration model: clear winner is #1 (more relevant, slightly older)
-        h_relevant = _make_result(ce_norm=0.85, occurred_start=old)
-        h_recent = _make_result(ce_norm=0.60, occurred_start=recent)
-        apply_combined_scoring([h_relevant, h_recent], now=NOW)
-        assert h_relevant.weight > h_recent.weight, "High-CE model: relevance should win"
-
-        # Low-calibration model: same relative difference, just compressed scores
-        l_relevant = _make_result(ce_norm=0.34, occurred_start=old)
-        l_recent = _make_result(ce_norm=0.24, occurred_start=recent)
-        apply_combined_scoring([l_relevant, l_recent], now=NOW)
-        assert l_relevant.weight > l_recent.weight, "Low-CE model: relevance should still win"
-
-    def test_no_occurred_start_defaults_recency_neutral(self):
-        """Missing occurred_start → recency=0.5 → no boost/penalty."""
-        sr = _make_result(ce_norm=0.5, occurred_start=None)
-        apply_combined_scoring([sr], now=NOW)
-        assert sr.recency == 0.5
-        assert abs(sr.weight - 0.5) < 1e-9
-
-    def test_timezone_naive_occurred_start_handled(self):
-        """Naive datetimes in occurred_start should not raise."""
-        naive_date = datetime(2024, 1, 1)  # no tzinfo
-        sr = _make_result(ce_norm=0.5, occurred_start=naive_date)
-        apply_combined_scoring([sr], now=NOW)  # must not raise
-        assert 0.0 < sr.weight < 1.0
-
-    def test_custom_alpha_values(self):
-        """Custom alpha parameters are respected."""
-        sr = _make_result(ce_norm=0.5, occurred_start=NOW)
-        apply_combined_scoring([sr], now=NOW, recency_alpha=0.4, temporal_alpha=0.0)
-        expected = 0.5 * (1.0 + 0.4 * 0.5) * 1.0
-        assert abs(sr.weight - expected) < 1e-6
-
-    def test_future_event_recency_capped_at_one(self):
-        """Events in the future must not produce recency > 1.0, keeping boost within bounds."""
-        future = NOW + timedelta(days=180)
-        sr = _make_result(ce_norm=0.5, occurred_start=future)
-        apply_combined_scoring([sr], now=NOW)
-        assert sr.recency == 1.0
-        expected_max_boost = 1.0 + _RECENCY_ALPHA * 0.5
-        assert sr.weight <= 0.5 * expected_max_boost + 1e-9
-
-    def test_empty_list_is_noop(self):
-        apply_combined_scoring([], now=NOW)  # must not raise

hindsight-api-slim/tests/test_consolidation_failure_recovery.py

@@ -1,476 +0,0 @@
-"""Tests for consolidation failure handling: adaptive batch splitting, consolidation_failed_at,
-and the recovery API.
-
-These tests use a mock LLM to simulate LLM failures deterministically, without making real
-API calls. All tests insert memories directly into the database to bypass retain's LLM calls
-and focus exclusively on the consolidation code paths.
-"""
-
-import uuid
-from unittest.mock import MagicMock
-
-import pytest
-import pytest_asyncio
-
-from hindsight_api.engine.consolidation.consolidator import run_consolidation_job
-from hindsight_api.engine.memory_engine import MemoryEngine
-from hindsight_api.engine.providers.mock_llm import MockLLM
-from hindsight_api.engine.task_backend import SyncTaskBackend
-
-
-@pytest_asyncio.fixture(scope="function")
-async def memory_no_llm_verify(pg0_db_url, embeddings, cross_encoder, query_analyzer):
-    """MemoryEngine with mock LLM.
-
-    Migrations are already applied by the session-scoped pg0_db_url fixture, so
-    run_migrations=False avoids advisory-lock serialization overhead per test.
-    """
-    mem = MemoryEngine(
-        db_url=pg0_db_url,
-        memory_llm_provider="mock",
-        memory_llm_api_key="",
-        memory_llm_model="mock",
-        embeddings=embeddings,
-        cross_encoder=cross_encoder,
-        query_analyzer=query_analyzer,
-        pool_min_size=1,
-        pool_max_size=5,
-        run_migrations=False,
-        task_backend=SyncTaskBackend(),
-        skip_llm_verification=True,
-    )
-    await mem.initialize()
-    yield mem
-    try:
-        if mem._pool and not mem._pool._closing:
-            await mem.close()
-    except Exception:
-        pass
-
-
-@pytest.fixture(autouse=True)
-def enable_observations():
-    """Enable observations for all tests in this module."""
-    from hindsight_api.config import _get_raw_config
-
-    config = _get_raw_config()
-    original = config.enable_observations
-    config.enable_observations = True
-    yield
-    config.enable_observations = original
-
-
-def _make_failing_mock_llm(*, fail_first_n: int = 999) -> MockLLM:
-    """Return a MockLLM that raises ValueError for the first `fail_first_n` consolidation calls."""
-    mock_llm = MockLLM(provider="mock", api_key="", base_url="", model="mock-model")
-    call_count = 0
-
-    def callback(messages, scope):
-        nonlocal call_count
-        if scope == "consolidation":
-            call_count += 1
-            if call_count <= fail_first_n:
-                raise ValueError(f"Simulated LLM failure (call {call_count})")
-        # Return empty response — no creates/updates/deletes
-        from hindsight_api.engine.consolidation.consolidator import _ConsolidationBatchResponse
-
-        return _ConsolidationBatchResponse()
-
-    mock_llm.set_response_callback(callback)
-    return mock_llm
-
-
-def _make_always_success_mock_llm() -> MockLLM:
-    """Return a MockLLM that always succeeds with an empty consolidation response."""
-    mock_llm = MockLLM(provider="mock", api_key="", base_url="", model="mock-model")
-
-    def callback(messages, scope):
-        from hindsight_api.engine.consolidation.consolidator import _ConsolidationBatchResponse
-
-        return _ConsolidationBatchResponse()
-
-    mock_llm.set_response_callback(callback)
-    return mock_llm
-
-
-def _inject_mock_llm(memory: MemoryEngine, mock_llm: MockLLM) -> None:
-    """Replace memory._consolidation_llm_config with a wrapper that returns mock_llm from with_config."""
-    wrapper = MagicMock()
-    wrapper.with_config.return_value = mock_llm
-    memory._consolidation_llm_config = wrapper
-
-
-async def _insert_memories(conn, bank_id: str, texts: list[str]) -> list[uuid.UUID]:
-    """Insert experience memories directly, bypassing LLM-based retain."""
-    ids = []
-    for text in texts:
-        mem_id = uuid.uuid4()
-        await conn.execute(
-            """
-            INSERT INTO memory_units (id, bank_id, text, fact_type, created_at)
-            VALUES ($1, $2, $3, 'experience', now())
-            """,
-            mem_id,
-            bank_id,
-            text,
-        )
-        ids.append(mem_id)
-    return ids
-
-
-class TestAdaptiveBatchSplitting:
-    """Verify that a failing batch is halved and retried until batch_size=1 succeeds."""
-
-    @pytest.mark.asyncio
-    async def test_splitting_recovers_all_memories(self, memory_no_llm_verify: MemoryEngine, request_context):
-        """When a batch of 2 fails, both are retried individually and succeed."""
-        bank_id = f"test-split-recovery-{uuid.uuid4().hex[:8]}"
-        await memory_no_llm_verify.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            mem_ids = await _insert_memories(
-                conn,
-                bank_id,
-                [
-                    "Alice runs marathons every spring.",
-                    "Alice trained for six months for her last race.",
-                ],
-            )
-
-        # Exhaust all 3 retries for batch=2 (calls 1-3 fail), then each batch=1 succeeds (calls 4-5)
-        mock_llm = _make_failing_mock_llm(fail_first_n=3)
-        _inject_mock_llm(memory_no_llm_verify, mock_llm)
-
-        result = await run_consolidation_job(
-            memory_engine=memory_no_llm_verify,
-            bank_id=bank_id,
-            request_context=request_context,
-        )
-
-        assert result["status"] == "completed"
-        assert result["memories_processed"] == 2
-        assert result["memories_failed"] == 0
-
-        # Both memories must have consolidated_at set and consolidation_failed_at NULL
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            rows = await conn.fetch(
-                """
-                SELECT id, consolidated_at, consolidation_failed_at
-                FROM memory_units
-                WHERE bank_id = $1 AND fact_type = 'experience'
-                """,
-                bank_id,
-            )
-        assert len(rows) == 2
-        for row in rows:
-            assert row["consolidated_at"] is not None, f"Memory {row['id']} should have consolidated_at set"
-            assert row["consolidation_failed_at"] is None, (
-                f"Memory {row['id']} should NOT have consolidation_failed_at set"
-            )
-
-        # LLM called 5 times: 3 retries failed (batch=2) + 1 succeeded (batch=1) + 1 succeeded (batch=1)
-        consolidation_calls = [c for c in mock_llm.get_mock_calls() if c["scope"] == "consolidation"]
-        assert len(consolidation_calls) == 5
-
-        await memory_no_llm_verify.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_splitting_with_larger_batch(self, memory_no_llm_verify: MemoryEngine, request_context):
-        """A batch of 4 that always fails at size>1 resolves to 4 individual calls."""
-        bank_id = f"test-split-large-{uuid.uuid4().hex[:8]}"
-        await memory_no_llm_verify.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            await _insert_memories(
-                conn,
-                bank_id,
-                [
-                    "Bob plays chess competitively.",
-                    "Bob won a regional chess tournament.",
-                    "Bob practices tactics every morning.",
-                    "Bob coaches youth chess on weekends.",
-                ],
-            )
-
-        # Exhaust all 3 retries for batch=4 (calls 1-3 fail), then both batch=2 halves succeed
-        # (calls 4-5). This verifies that halving once is sufficient when batch=2 works.
-        mock_llm = _make_failing_mock_llm(fail_first_n=3)
-        _inject_mock_llm(memory_no_llm_verify, mock_llm)
-
-        result = await run_consolidation_job(
-            memory_engine=memory_no_llm_verify,
-            bank_id=bank_id,
-            request_context=request_context,
-        )
-
-        assert result["memories_processed"] == 4
-        assert result["memories_failed"] == 0
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            rows = await conn.fetch(
-                "SELECT consolidated_at, consolidation_failed_at FROM memory_units "
-                "WHERE bank_id = $1 AND fact_type = 'experience'",
-                bank_id,
-            )
-        assert all(r["consolidated_at"] is not None for r in rows)
-        assert all(r["consolidation_failed_at"] is None for r in rows)
-
-        await memory_no_llm_verify.delete_bank(bank_id, request_context=request_context)
-
-
-class TestConsolidationFailedAt:
-    """Verify that consolidation_failed_at is set — and consolidated_at is NOT — when all retries fail."""
-
-    @pytest.mark.asyncio
-    async def test_single_memory_permanent_failure(self, memory_no_llm_verify: MemoryEngine, request_context):
-        """A single memory that exhausts all LLM retries gets consolidation_failed_at, not consolidated_at."""
-        bank_id = f"test-perm-fail-{uuid.uuid4().hex[:8]}"
-        await memory_no_llm_verify.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            (mem_id,) = await _insert_memories(conn, bank_id, ["Carol enjoys painting watercolors."])
-
-        # Always fail
-        mock_llm = _make_failing_mock_llm(fail_first_n=999)
-        _inject_mock_llm(memory_no_llm_verify, mock_llm)
-
-        result = await run_consolidation_job(
-            memory_engine=memory_no_llm_verify,
-            bank_id=bank_id,
-            request_context=request_context,
-        )
-
-        assert result["memories_failed"] == 1
-        assert result["memories_processed"] == 1
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            row = await conn.fetchrow(
-                "SELECT consolidated_at, consolidation_failed_at FROM memory_units WHERE id = $1",
-                mem_id,
-            )
-
-        assert row["consolidated_at"] is None, "consolidated_at must NOT be set for a permanently failed memory"
-        assert row["consolidation_failed_at"] is not None, "consolidation_failed_at must be set"
-
-        await memory_no_llm_verify.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_failed_memory_excluded_from_next_run(self, memory_no_llm_verify: MemoryEngine, request_context):
-        """A memory marked consolidation_failed_at is not re-processed on the next consolidation run."""
-        bank_id = f"test-excluded-{uuid.uuid4().hex[:8]}"
-        await memory_no_llm_verify.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            (mem_id,) = await _insert_memories(conn, bank_id, ["Dave collects vinyl records."])
-            # Manually stamp consolidation_failed_at to simulate a prior failed run
-            await conn.execute(
-                "UPDATE memory_units SET consolidation_failed_at = NOW() WHERE id = $1",
-                mem_id,
-            )
-
-        # Even with a healthy LLM, the memory should be skipped
-        mock_llm = _make_always_success_mock_llm()
-        _inject_mock_llm(memory_no_llm_verify, mock_llm)
-
-        result = await run_consolidation_job(
-            memory_engine=memory_no_llm_verify,
-            bank_id=bank_id,
-            request_context=request_context,
-        )
-
-        # No unconsolidated memories to pick up (consolidation_failed_at ≠ NULL, consolidated_at = NULL
-        # but the SELECT filters on consolidated_at IS NULL AND fact_type IN ('experience','world'))
-        assert result["status"] in ("no_new_memories", "completed")
-        if result["status"] == "completed":
-            assert result["memories_processed"] == 0
-
-        # Memory still has consolidation_failed_at set and consolidated_at NULL
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            row = await conn.fetchrow(
-                "SELECT consolidated_at, consolidation_failed_at FROM memory_units WHERE id = $1",
-                mem_id,
-            )
-        assert row["consolidated_at"] is None
-        assert row["consolidation_failed_at"] is not None
-
-        await memory_no_llm_verify.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_partial_batch_failure(self, memory_no_llm_verify: MemoryEngine, request_context):
-        """In a batch of 2, if only the first individual retry fails, the second still succeeds."""
-        bank_id = f"test-partial-fail-{uuid.uuid4().hex[:8]}"
-        await memory_no_llm_verify.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            mem_ids = await _insert_memories(
-                conn,
-                bank_id,
-                [
-                    "Eve speaks three languages fluently.",
-                    "Eve learned Japanese in two years.",
-                ],
-            )
-
-        # Exhaust 3 retries for batch=2 (calls 1-3), exhaust 3 retries for first batch=1 (calls 4-6),
-        # second batch=1 succeeds (call 7)
-        mock_llm = _make_failing_mock_llm(fail_first_n=6)
-        _inject_mock_llm(memory_no_llm_verify, mock_llm)
-
-        result = await run_consolidation_job(
-            memory_engine=memory_no_llm_verify,
-            bank_id=bank_id,
-            request_context=request_context,
-        )
-
-        assert result["memories_processed"] == 2
-        assert result["memories_failed"] == 1
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            rows = {
-                str(r["id"]): r
-                for r in await conn.fetch(
-                    "SELECT id, consolidated_at, consolidation_failed_at FROM memory_units "
-                    "WHERE bank_id = $1 AND fact_type = 'experience'",
-                    bank_id,
-                )
-            }
-
-        # One should have failed, one should have succeeded
-        failed = [r for r in rows.values() if r["consolidation_failed_at"] is not None]
-        succeeded = [r for r in rows.values() if r["consolidated_at"] is not None]
-        assert len(failed) == 1
-        assert len(succeeded) == 1
-        # They must be different memories
-        assert str(failed[0]["id"]) != str(succeeded[0]["id"])
-
-        await memory_no_llm_verify.delete_bank(bank_id, request_context=request_context)
-
-
-class TestRecoverConsolidation:
-    """Verify the retry_failed_consolidation() method and the /consolidation/recover endpoint."""
-
-    @pytest.mark.asyncio
-    async def test_recover_resets_failed_memories(self, memory_no_llm_verify: MemoryEngine, request_context):
-        """retry_failed_consolidation resets consolidation_failed_at and consolidated_at."""
-        bank_id = f"test-recover-reset-{uuid.uuid4().hex[:8]}"
-        await memory_no_llm_verify.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            ids = await _insert_memories(
-                conn,
-                bank_id,
-                [
-                    "Frank is a competitive cyclist.",
-                    "Frank completed the Tour de France route.",
-                ],
-            )
-            # Mark both as failed
-            for mem_id in ids:
-                await conn.execute(
-                    "UPDATE memory_units SET consolidation_failed_at = NOW() WHERE id = $1",
-                    mem_id,
-                )
-
-        result = await memory_no_llm_verify.retry_failed_consolidation(
-            bank_id, request_context=request_context
-        )
-
-        assert result["retried_count"] == 2
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            rows = await conn.fetch(
-                "SELECT consolidated_at, consolidation_failed_at FROM memory_units "
-                "WHERE bank_id = $1 AND fact_type = 'experience'",
-                bank_id,
-            )
-        assert all(r["consolidation_failed_at"] is None for r in rows), "consolidation_failed_at must be cleared"
-        assert all(r["consolidated_at"] is None for r in rows), "consolidated_at must also be cleared"
-
-        await memory_no_llm_verify.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_recover_returns_zero_when_none_failed(self, memory_no_llm_verify: MemoryEngine, request_context):
-        """retry_failed_consolidation returns 0 when no memories have failed."""
-        bank_id = f"test-recover-zero-{uuid.uuid4().hex[:8]}"
-        await memory_no_llm_verify.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        result = await memory_no_llm_verify.retry_failed_consolidation(
-            bank_id, request_context=request_context
-        )
-
-        assert result["retried_count"] == 0
-
-        await memory_no_llm_verify.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_recover_then_consolidate_succeeds(self, memory_no_llm_verify: MemoryEngine, request_context):
-        """After recovery, the memory is picked up by the next consolidation run."""
-        bank_id = f"test-recover-consolidate-{uuid.uuid4().hex[:8]}"
-        await memory_no_llm_verify.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            (mem_id,) = await _insert_memories(conn, bank_id, ["Grace is an expert rock climber."])
-            await conn.execute(
-                "UPDATE memory_units SET consolidation_failed_at = NOW() WHERE id = $1", mem_id
-            )
-
-        # Recover
-        recover_result = await memory_no_llm_verify.retry_failed_consolidation(
-            bank_id, request_context=request_context
-        )
-        assert recover_result["retried_count"] == 1
-
-        # Now consolidate with a healthy LLM
-        mock_llm = _make_always_success_mock_llm()
-        _inject_mock_llm(memory_no_llm_verify, mock_llm)
-
-        run_result = await run_consolidation_job(
-            memory_engine=memory_no_llm_verify,
-            bank_id=bank_id,
-            request_context=request_context,
-        )
-
-        assert run_result["memories_processed"] == 1
-        assert run_result["memories_failed"] == 0
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            row = await conn.fetchrow(
-                "SELECT consolidated_at, consolidation_failed_at FROM memory_units WHERE id = $1",
-                mem_id,
-            )
-        assert row["consolidated_at"] is not None, "Memory should be consolidated after recovery"
-        assert row["consolidation_failed_at"] is None
-
-        await memory_no_llm_verify.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_recover_endpoint_via_http(self, memory_no_llm_verify: MemoryEngine, request_context):
-        """The POST /consolidation/recover endpoint returns the correct retried_count."""
-        import httpx
-
-        from hindsight_api.api.http import create_app
-
-        bank_id = f"test-recover-http-{uuid.uuid4().hex[:8]}"
-        await memory_no_llm_verify.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        async with memory_no_llm_verify._pool.acquire() as conn:
-            ids = await _insert_memories(
-                conn,
-                bank_id,
-                ["Henry is a professional chef.", "Henry trained at Le Cordon Bleu."],
-            )
-            for mem_id in ids:
-                await conn.execute(
-                    "UPDATE memory_units SET consolidation_failed_at = NOW() WHERE id = $1", mem_id
-                )
-
-        app = create_app(memory_no_llm_verify, initialize_memory=False)
-        transport = httpx.ASGITransport(app=app)
-        async with httpx.AsyncClient(transport=transport, base_url="http://test") as client:
-            response = await client.post(f"/v1/default/banks/{bank_id}/consolidation/recover")
-
-        assert response.status_code == 200
-        body = response.json()
-        assert body["retried_count"] == 2
-
-        await memory_no_llm_verify.delete_bank(bank_id, request_context=request_context)

hindsight-api-slim/tests/test_delta_retain.py

@@ -1,842 +0,0 @@
-"""
-Tests for delta retain — upsert optimization that only re-processes changed chunks.
-"""
-
-import logging
-from datetime import datetime, timezone
-
-import pytest
-
-from hindsight_api import RequestContext
-from hindsight_api.engine.memory_engine import Budget
-
-logger = logging.getLogger(__name__)
-
-
-def _ts():
-    return datetime.now(timezone.utc).timestamp()
-
-
-# ============================================================
-# Core Delta Retain Tests
-# ============================================================
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_unchanged_content_skips_llm(memory, request_context):
-    """
-    When upserting a document with identical content, no new facts should be
-    extracted (LLM is not called for unchanged chunks). The existing facts
-    should be preserved.
-    """
-    bank_id = f"test_delta_unchanged_{_ts()}"
-    document_id = "conversation-001"
-
-    try:
-        content = "Alice works at Google. Bob works at Microsoft."
-
-        # First retain — full processing
-        v1_units = await memory.retain_async(
-            bank_id=bank_id,
-            content=content,
-            context="team info",
-            document_id=document_id,
-            request_context=request_context,
-        )
-        assert len(v1_units) > 0, "v1 should create facts"
-
-        # Get v1 document state
-        doc_v1 = await memory.get_document(document_id, bank_id, request_context=request_context)
-        v1_unit_count = doc_v1["memory_unit_count"]
-
-        # Second retain — same content, should use delta path (no new facts)
-        v2_units = await memory.retain_async(
-            bank_id=bank_id,
-            content=content,
-            context="team info",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        # No new units should be returned (nothing changed)
-        assert v2_units == [], "Delta retain with unchanged content should return empty unit list"
-
-        # Existing facts should still be there
-        doc_v2 = await memory.get_document(document_id, bank_id, request_context=request_context)
-        assert doc_v2["memory_unit_count"] == v1_unit_count, "Existing facts should be preserved"
-
-        # Verify recall still works
-        result = await memory.recall_async(
-            bank_id=bank_id,
-            query="Where does Alice work?",
-            budget=Budget.MID,
-            max_tokens=1000,
-            request_context=request_context,
-        )
-        assert len(result.results) > 0, "Should still recall facts after delta retain"
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_appended_content(memory, request_context):
-    """
-    When a conversation grows (new content appended), only new chunks should
-    be processed. Facts from unchanged chunks should be preserved.
-    """
-    bank_id = f"test_delta_append_{_ts()}"
-    document_id = "growing-conversation"
-
-    try:
-        # First version — short content (single chunk)
-        v1_content = "Alice is a software engineer at Google. She works on search infrastructure."
-
-        v1_units = await memory.retain_async(
-            bank_id=bank_id,
-            content=v1_content,
-            context="profile",
-            document_id=document_id,
-            request_context=request_context,
-        )
-        assert len(v1_units) > 0
-
-        # Get v1 facts via recall
-        v1_recall = await memory.recall_async(
-            bank_id=bank_id,
-            query="What does Alice do?",
-            budget=Budget.MID,
-            max_tokens=2000,
-            request_context=request_context,
-        )
-        v1_fact_texts = {r.text for r in v1_recall.results}
-
-        # Second version — original content + new content appended
-        # This should preserve facts from the first chunk and add new ones
-        v2_content = v1_content + "\n\nBob joined Google as a product manager in 2024. He previously worked at Meta on AR/VR products."
-
-        v2_units = await memory.retain_async(
-            bank_id=bank_id,
-            content=v2_content,
-            context="profile",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        # Should have facts about Bob from the new content
-        v2_recall = await memory.recall_async(
-            bank_id=bank_id,
-            query="What does Bob do?",
-            budget=Budget.MID,
-            max_tokens=2000,
-            request_context=request_context,
-        )
-        bob_facts = [r for r in v2_recall.results if "bob" in r.text.lower()]
-        assert len(bob_facts) > 0, "Should have facts about Bob from appended content"
-
-        # Should still have facts about Alice from original content
-        alice_recall = await memory.recall_async(
-            bank_id=bank_id,
-            query="What does Alice do?",
-            budget=Budget.MID,
-            max_tokens=2000,
-            request_context=request_context,
-        )
-        assert len(alice_recall.results) > 0, "Should still have Alice facts from original content"
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_modified_chunk(memory, request_context):
-    """
-    When content in the middle changes, that chunk should be re-processed
-    while other chunks are preserved.
-    """
-    bank_id = f"test_delta_modified_{_ts()}"
-    document_id = "changing-doc"
-
-    try:
-        # v1: Alice works at Google
-        v1_content = "Alice works at Google as a senior engineer."
-        v1_units = await memory.retain_async(
-            bank_id=bank_id,
-            content=v1_content,
-            context="team",
-            document_id=document_id,
-            request_context=request_context,
-        )
-        assert len(v1_units) > 0
-
-        # v2: Alice works at Microsoft (changed)
-        v2_content = "Alice works at Microsoft as a principal engineer."
-        v2_units = await memory.retain_async(
-            bank_id=bank_id,
-            content=v2_content,
-            context="team",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        # New facts should reflect the updated content
-        result = await memory.recall_async(
-            bank_id=bank_id,
-            query="Where does Alice work?",
-            budget=Budget.MID,
-            max_tokens=2000,
-            request_context=request_context,
-        )
-        all_texts = " ".join(r.text.lower() for r in result.results)
-        assert "microsoft" in all_texts, f"Should have updated fact about Microsoft, got: {all_texts}"
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-# ============================================================
-# Entity & Link Tests
-# ============================================================
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_entities_preserved_for_unchanged_chunks(memory, request_context):
-    """
-    Entities linked to unchanged chunks should be preserved after delta retain.
-    """
-    bank_id = f"test_delta_entities_{_ts()}"
-    document_id = "entity-doc"
-
-    try:
-        v1_content = "Alice works at Google. She is a senior engineer in the Cloud division."
-        v1_units = await memory.retain_async(
-            bank_id=bank_id,
-            content=v1_content,
-            context="team",
-            document_id=document_id,
-            request_context=request_context,
-        )
-        assert len(v1_units) > 0
-
-        # Check entities exist
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            v1_entities = await conn.fetch(
-                "SELECT canonical_name FROM entities WHERE bank_id = $1",
-                bank_id,
-            )
-        v1_entity_names = {e["canonical_name"].lower() for e in v1_entities}
-        assert len(v1_entity_names) > 0, "Should have entities after v1 retain"
-
-        # Upsert with same content — entities should persist
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=v1_content,
-            context="team",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        async with pool.acquire() as conn:
-            v2_entities = await conn.fetch(
-                "SELECT canonical_name FROM entities WHERE bank_id = $1",
-                bank_id,
-            )
-        v2_entity_names = {e["canonical_name"].lower() for e in v2_entities}
-
-        # All v1 entities should still exist
-        assert v1_entity_names.issubset(v2_entity_names), (
-            f"v1 entities {v1_entity_names} should be preserved, got {v2_entity_names}"
-        )
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_new_entities_created_for_new_chunks(memory, request_context):
-    """
-    New entities should be created for newly added chunks during delta retain.
-    """
-    bank_id = f"test_delta_new_entities_{_ts()}"
-    document_id = "entity-growth-doc"
-
-    try:
-        v1_content = "Alice works at Google."
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=v1_content,
-            context="team",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            v1_entities = await conn.fetch(
-                "SELECT canonical_name FROM entities WHERE bank_id = $1",
-                bank_id,
-            )
-        v1_entity_names = {e["canonical_name"].lower() for e in v1_entities}
-
-        # Append content mentioning new entities
-        v2_content = v1_content + "\n\nBob joined Facebook. He works with Charlie on the Reality Labs project."
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=v2_content,
-            context="team",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        async with pool.acquire() as conn:
-            v2_entities = await conn.fetch(
-                "SELECT canonical_name FROM entities WHERE bank_id = $1",
-                bank_id,
-            )
-        v2_entity_names = {e["canonical_name"].lower() for e in v2_entities}
-
-        # Should have more entities after adding content with new people/orgs
-        assert len(v2_entity_names) > len(v1_entity_names), (
-            f"Should have more entities after append: v1={v1_entity_names}, v2={v2_entity_names}"
-        )
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_links_preserved_for_unchanged_chunks(memory, request_context):
-    """
-    Memory links (temporal, semantic, entity) for unchanged chunks should be preserved.
-    """
-    bank_id = f"test_delta_links_{_ts()}"
-    document_id = "links-doc"
-
-    try:
-        content = "Alice is a senior engineer at Google Cloud. She mentors junior engineers and reviews their code."
-        v1_units = await memory.retain_async(
-            bank_id=bank_id,
-            content=content,
-            context="team",
-            document_id=document_id,
-            request_context=request_context,
-        )
-        assert len(v1_units) > 0
-
-        # Count links after v1
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            v1_link_count = await conn.fetchval(
-                """SELECT COUNT(*) FROM memory_links ml
-                   JOIN memory_units mu ON ml.from_unit_id = mu.id
-                   WHERE mu.bank_id = $1 AND mu.document_id = $2""",
-                bank_id,
-                document_id,
-            )
-
-        # Upsert with same content
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=content,
-            context="team",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        # Links should be preserved
-        async with pool.acquire() as conn:
-            v2_link_count = await conn.fetchval(
-                """SELECT COUNT(*) FROM memory_links ml
-                   JOIN memory_units mu ON ml.from_unit_id = mu.id
-                   WHERE mu.bank_id = $1 AND mu.document_id = $2""",
-                bank_id,
-                document_id,
-            )
-
-        assert v2_link_count == v1_link_count, (
-            f"Links should be preserved: v1={v1_link_count}, v2={v2_link_count}"
-        )
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-# ============================================================
-# Document Metadata & Tags Tests
-# ============================================================
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_document_metadata_updated(memory, request_context):
-    """
-    Document metadata (retain_params, tags) should be updated even when
-    chunk content hasn't changed.
-    """
-    bank_id = f"test_delta_meta_{_ts()}"
-    document_id = "metadata-doc"
-
-    try:
-        content = "Alice works at Google."
-
-        # v1 with initial tags
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=content,
-            context="initial context",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        doc_v1 = await memory.get_document(document_id, bank_id, request_context=request_context)
-        assert doc_v1 is not None
-
-        # v2 with updated context (same content — triggers delta path)
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=content,
-            context="updated context",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        doc_v2 = await memory.get_document(document_id, bank_id, request_context=request_context)
-        assert doc_v2 is not None
-        assert doc_v2["updated_at"] >= doc_v1["updated_at"], "Document should have updated timestamp"
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_tags_propagated_to_existing_units(memory, request_context):
-    """
-    When tags change during an upsert with unchanged content, the new tags
-    should be propagated to all existing memory units.
-    """
-    bank_id = f"test_delta_tags_{_ts()}"
-    document_id = "tags-doc"
-
-    try:
-        content = "Alice works at Google."
-
-        # v1 with tag "team-a"
-        await memory.retain_batch_async(
-            bank_id=bank_id,
-            contents=[{
-                "content": content,
-                "document_id": document_id,
-                "tags": ["team-a"],
-            }],
-            request_context=request_context,
-        )
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            v1_tags = await conn.fetch(
-                "SELECT tags FROM memory_units WHERE bank_id = $1 AND document_id = $2",
-                bank_id,
-                document_id,
-            )
-        assert all("team-a" in row["tags"] for row in v1_tags), "v1 units should have team-a tag"
-
-        # v2 with same content but different tags
-        await memory.retain_batch_async(
-            bank_id=bank_id,
-            contents=[{
-                "content": content,
-                "document_id": document_id,
-                "tags": ["team-b", "important"],
-            }],
-            request_context=request_context,
-        )
-
-        async with pool.acquire() as conn:
-            v2_tags = await conn.fetch(
-                "SELECT tags FROM memory_units WHERE bank_id = $1 AND document_id = $2",
-                bank_id,
-                document_id,
-            )
-        for row in v2_tags:
-            assert "team-b" in row["tags"], f"v2 units should have team-b tag, got {row['tags']}"
-            assert "important" in row["tags"], f"v2 units should have important tag, got {row['tags']}"
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-# ============================================================
-# Chunk Management Tests
-# ============================================================
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_removed_chunks_delete_facts(memory, request_context):
-    """
-    When content is shortened (chunks removed), facts from the removed
-    chunks should be deleted.
-    """
-    bank_id = f"test_delta_removed_{_ts()}"
-    document_id = "shrinking-doc"
-
-    try:
-        # v1: longer content with facts about Alice and Bob
-        v1_content = (
-            "Alice is a senior engineer at Google Cloud. "
-            "She leads the infrastructure team and has been there for 5 years.\n\n"
-            "Bob is a product manager at Facebook Reality Labs. "
-            "He previously worked at Amazon on Alexa voice products."
-        )
-
-        v1_units = await memory.retain_async(
-            bank_id=bank_id,
-            content=v1_content,
-            context="profiles",
-            document_id=document_id,
-            request_context=request_context,
-        )
-        assert len(v1_units) > 0
-
-        doc_v1 = await memory.get_document(document_id, bank_id, request_context=request_context)
-        v1_count = doc_v1["memory_unit_count"]
-
-        # v2: Completely different content — all chunks change
-        v2_content = "Charlie works at Netflix as a data scientist."
-        v2_units = await memory.retain_async(
-            bank_id=bank_id,
-            content=v2_content,
-            context="profiles",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        doc_v2 = await memory.get_document(document_id, bank_id, request_context=request_context)
-        assert doc_v2 is not None
-
-        # Should have facts about Charlie
-        result = await memory.recall_async(
-            bank_id=bank_id,
-            query="Who works at Netflix?",
-            budget=Budget.MID,
-            max_tokens=2000,
-            request_context=request_context,
-        )
-        all_texts = " ".join(r.text.lower() for r in result.results)
-        assert "charlie" in all_texts or "netflix" in all_texts, (
-            f"Should have facts about Charlie/Netflix after replacing content, got: {all_texts}"
-        )
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_chunks_have_content_hash(memory, request_context):
-    """
-    After retain, chunks should have content_hash populated.
-    """
-    bank_id = f"test_delta_hash_{_ts()}"
-    document_id = "hash-doc"
-
-    try:
-        content = "Alice works at Google as a software engineer."
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=content,
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            chunks = await conn.fetch(
-                "SELECT chunk_id, content_hash FROM chunks WHERE document_id = $1 AND bank_id = $2",
-                document_id,
-                bank_id,
-            )
-
-        assert len(chunks) > 0, "Should have stored chunks"
-        for chunk in chunks:
-            assert chunk["content_hash"] is not None, f"Chunk {chunk['chunk_id']} should have content_hash"
-            assert len(chunk["content_hash"]) == 64, "content_hash should be SHA256 hex (64 chars)"
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-# ============================================================
-# Backward Compatibility Tests
-# ============================================================
-
-
-@pytest.mark.asyncio
-async def test_retain_without_document_id_still_works(memory, request_context):
-    """
-    Retain without document_id should still work normally (no delta path).
-    """
-    bank_id = f"test_no_docid_{_ts()}"
-
-    try:
-        units = await memory.retain_async(
-            bank_id=bank_id,
-            content="Alice works at Google.",
-            context="test",
-            request_context=request_context,
-        )
-        assert len(units) > 0, "Should create facts without document_id"
-
-        result = await memory.recall_async(
-            bank_id=bank_id,
-            query="Where does Alice work?",
-            budget=Budget.MID,
-            max_tokens=1000,
-            request_context=request_context,
-        )
-        assert len(result.results) > 0
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_first_retain_full_path(memory, request_context):
-    """
-    First retain of a new document should use the full path (no delta possible).
-    """
-    bank_id = f"test_first_retain_{_ts()}"
-    document_id = "new-doc"
-
-    try:
-        units = await memory.retain_async(
-            bank_id=bank_id,
-            content="Alice works at Google.",
-            context="test",
-            document_id=document_id,
-            request_context=request_context,
-        )
-        assert len(units) > 0, "First retain should create facts via full path"
-
-        doc = await memory.get_document(document_id, bank_id, request_context=request_context)
-        assert doc is not None
-        assert doc["memory_unit_count"] > 0
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-# ============================================================
-# Edge Cases
-# ============================================================
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_empty_to_content(memory, request_context):
-    """
-    Going from gibberish (zero facts) to real content should work.
-    """
-    bank_id = f"test_delta_empty_{_ts()}"
-    document_id = "empty-to-content"
-
-    try:
-        # v1: content that probably produces zero facts
-        await memory.retain_async(
-            bank_id=bank_id,
-            content="!!!###$$$%%%",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        doc_v1 = await memory.get_document(document_id, bank_id, request_context=request_context)
-        assert doc_v1 is not None
-
-        # v2: real content
-        v2_units = await memory.retain_async(
-            bank_id=bank_id,
-            content="Alice works at Google as a senior engineer.",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        doc_v2 = await memory.get_document(document_id, bank_id, request_context=request_context)
-        assert doc_v2 is not None
-        assert doc_v2["memory_unit_count"] > 0 or len(v2_units) > 0, "Should have facts after updating with real content"
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_multiple_upserts(memory, request_context):
-    """
-    Multiple sequential upserts should work correctly, with delta optimization
-    kicking in after the first retain.
-    """
-    bank_id = f"test_delta_multi_{_ts()}"
-    document_id = "multi-upsert"
-
-    try:
-        # v1: initial
-        v1_content = "Alice works at Google."
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=v1_content,
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        # v2: same content (delta: no changes)
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=v1_content,
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        # v3: append
-        v3_content = v1_content + "\n\nBob works at Microsoft."
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=v3_content,
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        # v4: same as v3 (delta: no changes again)
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=v3_content,
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        # Final check: should have facts about both Alice and Bob
-        result = await memory.recall_async(
-            bank_id=bank_id,
-            query="Who works where?",
-            budget=Budget.MID,
-            max_tokens=2000,
-            request_context=request_context,
-        )
-        all_texts = " ".join(r.text.lower() for r in result.results)
-        assert "alice" in all_texts or "google" in all_texts, f"Should have Alice/Google facts, got: {all_texts}"
-
-        doc = await memory.get_document(document_id, bank_id, request_context=request_context)
-        assert doc is not None
-        assert doc["memory_unit_count"] > 0
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_with_user_entities(memory, request_context):
-    """
-    User-provided entities should work correctly with delta retain.
-    """
-    bank_id = f"test_delta_user_entities_{_ts()}"
-    document_id = "user-entity-doc"
-
-    try:
-        content = "The project is going well."
-
-        # v1 with user entities
-        await memory.retain_batch_async(
-            bank_id=bank_id,
-            contents=[{
-                "content": content,
-                "document_id": document_id,
-                "entities": [{"text": "Project Alpha", "type": "PROJECT"}],
-            }],
-            request_context=request_context,
-        )
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            v1_entities = await conn.fetch(
-                "SELECT canonical_name FROM entities WHERE bank_id = $1",
-                bank_id,
-            )
-        v1_names = {e["canonical_name"].lower() for e in v1_entities}
-
-        # v2 with additional entity, same content
-        # Note: same content = delta path (no re-extraction)
-        # The user entities for NEW chunks only get processed
-        v2_content = content + "\n\nThe timeline is on track for Q2 delivery."
-        await memory.retain_batch_async(
-            bank_id=bank_id,
-            contents=[{
-                "content": v2_content,
-                "document_id": document_id,
-                "entities": [
-                    {"text": "Project Alpha", "type": "PROJECT"},
-                    {"text": "Q2 Deadline", "type": "MILESTONE"},
-                ],
-            }],
-            request_context=request_context,
-        )
-
-        # Should have entities from both v1 and v2
-        async with pool.acquire() as conn:
-            v2_entities = await conn.fetch(
-                "SELECT canonical_name FROM entities WHERE bank_id = $1",
-                bank_id,
-            )
-        v2_names = {e["canonical_name"].lower() for e in v2_entities}
-
-        # v1 entities should be preserved
-        assert v1_names.issubset(v2_names), f"v1 entities should be preserved: {v1_names} not in {v2_names}"
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_delta_retain_recall_with_chunks(memory, request_context):
-    """
-    After delta retain, recall with include_chunks should return correct chunk data.
-    """
-    bank_id = f"test_delta_recall_chunks_{_ts()}"
-    document_id = "recall-chunks-doc"
-
-    try:
-        content = "Alice is a senior engineer at Google Cloud. She designs distributed systems."
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=content,
-            context="profile",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        # Upsert with same content (delta: no changes)
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=content,
-            context="profile",
-            document_id=document_id,
-            request_context=request_context,
-        )
-
-        # Recall with chunks
-        result = await memory.recall_async(
-            bank_id=bank_id,
-            query="What does Alice do?",
-            budget=Budget.MID,
-            max_tokens=2000,
-            include_chunks=True,
-            max_chunk_tokens=8192,
-            request_context=request_context,
-        )
-
-        assert len(result.results) > 0, "Should recall facts"
-
-        # Facts with chunk_ids should have corresponding chunks
-        facts_with_chunks = [r for r in result.results if r.chunk_id]
-        if facts_with_chunks and result.chunks:
-            for fact in facts_with_chunks:
-                assert fact.chunk_id in result.chunks, (
-                    f"Chunk {fact.chunk_id} should be in returned chunks"
-                )
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)

hindsight-api-slim/tests/test_entity_resolver.py

@@ -1,114 +0,0 @@
-"""
-Tests for EntityResolver edge cases.
-"""
-
-import uuid
-from datetime import datetime, timezone
-
-import asyncpg
-import pytest
-
-from hindsight_api.engine.entity_resolver import EntityResolver
-from hindsight_api.pg0 import resolve_database_url
-
-# ---------------------------------------------------------------------------
-# Unit tests for discard_pending_stats() — no database required
-# ---------------------------------------------------------------------------
-
-
-@pytest.mark.asyncio
-async def test_discard_pending_stats_clears_both_dicts():
-    """discard_pending_stats() must remove entries for the current task from
-    both _pending_stats and _pending_cooccurrences."""
-    resolver = EntityResolver(pool=None)  # type: ignore[arg-type]
-    key = resolver._task_key()
-
-    resolver._pending_stats[key] = [object()]  # type: ignore[list-item]
-    resolver._pending_cooccurrences[key] = [object()]  # type: ignore[list-item]
-
-    resolver.discard_pending_stats()
-
-    assert key not in resolver._pending_stats
-    assert key not in resolver._pending_cooccurrences
-
-
-@pytest.mark.asyncio
-async def test_discard_pending_stats_is_idempotent():
-    """Calling discard_pending_stats() when nothing is pending must not raise."""
-    resolver = EntityResolver(pool=None)  # type: ignore[arg-type]
-    resolver.discard_pending_stats()
-    resolver.discard_pending_stats()  # second call — still safe
-
-
-@pytest.mark.asyncio
-async def test_discard_pending_stats_does_not_affect_other_task_keys():
-    """discard_pending_stats() must only remove the current task's entries,
-    leaving entries keyed under other task IDs untouched."""
-    resolver = EntityResolver(pool=None)  # type: ignore[arg-type]
-    other_key = -1  # A fake key that can never be a real task id
-
-    resolver._pending_stats[other_key] = [object()]  # type: ignore[list-item]
-    resolver._pending_cooccurrences[other_key] = [object()]  # type: ignore[list-item]
-
-    resolver.discard_pending_stats()  # discards current task's key only
-
-    assert other_key in resolver._pending_stats, "other task's stats must be preserved"
-    assert other_key in resolver._pending_cooccurrences, "other task's cooccurrences must be preserved"
-
-
-@pytest.mark.asyncio
-async def test_resolve_entities_batch_handles_unicode_lower_conflicts(pg0_db_url):
-    """
-    Existing entities with PostgreSQL/Python lowercase mismatches should resolve
-    to the conflicted row instead of leaving a missing entity_id.
-    """
-    resolved_url = await resolve_database_url(pg0_db_url)
-    pool = await asyncpg.create_pool(resolved_url, min_size=1, max_size=2, command_timeout=30)
-    bank_id = f"test-entity-resolver-{uuid.uuid4().hex[:8]}"
-    event_date = datetime(2024, 1, 15, tzinfo=timezone.utc)
-    resolver = EntityResolver(pool=pool, entity_lookup="full")
-
-    try:
-        async with pool.acquire() as conn:
-            existing_entity_id = await conn.fetchval(
-                """
-                INSERT INTO entities (bank_id, canonical_name, first_seen, last_seen, mention_count)
-                VALUES ($1, $2, $3, $3, 1)
-                RETURNING id
-                """,
-                bank_id,
-                "İstanbul",
-                event_date,
-            )
-
-            resolved_ids = await resolver.resolve_entities_batch(
-                bank_id=bank_id,
-                entities_data=[
-                    {
-                        "text": "istanbul",
-                        "nearby_entities": [],
-                        "event_date": event_date,
-                    }
-                ],
-                context="unicode case mismatch",
-                unit_event_date=event_date,
-                conn=conn,
-            )
-
-            entity_rows = await conn.fetch(
-                """
-                SELECT id, canonical_name
-                FROM entities
-                WHERE bank_id = $1
-                ORDER BY canonical_name
-                """,
-                bank_id,
-            )
-
-        assert resolved_ids == [existing_entity_id]
-        assert len(entity_rows) == 1
-        assert entity_rows[0]["id"] == existing_entity_id
-        assert entity_rows[0]["canonical_name"] == "İstanbul"
-    finally:
-        await pool.execute("DELETE FROM entities WHERE bank_id = $1", bank_id)
-        await pool.close()

hindsight-api-slim/tests/test_entity_resolver_pg_trgm.py

@@ -1,163 +0,0 @@
-"""
-Unit tests for EntityResolver pg_trgm auto-detection (PR #626/#649).
-
-These tests verify:
-1. When entity_lookup="trigram" and pg_trgm IS available, the trigram path is used.
-2. When entity_lookup="trigram" and pg_trgm is NOT available, the resolver falls back
-   to entity_lookup="full" and uses the full-scan path.
-3. The pg_trgm check is only performed once (_pg_trgm_checked flag prevents re-checking).
-4. When entity_lookup="full" from the start, the trgm check is never performed.
-"""
-
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-from hindsight_api.engine.entity_resolver import EntityResolver
-
-
-def _make_conn(pg_trgm_available: bool) -> MagicMock:
-    """Create a minimal mock asyncpg connection for the pg_trgm availability check."""
-    conn = MagicMock()
-    conn.fetchval = AsyncMock(return_value=pg_trgm_available)
-    conn.fetch = AsyncMock(return_value=[])
-    conn.executemany = AsyncMock()
-    conn.fetchrow = AsyncMock(return_value=None)
-    return conn
-
-
-def _make_resolver(entity_lookup: str = "trigram") -> EntityResolver:
-    """Return an EntityResolver with a None pool (not needed for unit tests)."""
-    return EntityResolver(pool=None, entity_lookup=entity_lookup)  # type: ignore[arg-type]
-
-
-class TestPgTrgmAutoDetection:
-    """Unit tests for pg_trgm detection logic inside _resolve_entities_batch_impl."""
-
-    @pytest.mark.asyncio
-    async def test_falls_back_to_full_when_pg_trgm_unavailable(self):
-        """When pg_trgm is absent the resolver switches to 'full' and calls the full-scan path."""
-        resolver = _make_resolver(entity_lookup="trigram")
-        conn = _make_conn(pg_trgm_available=False)
-
-        with (
-            patch.object(resolver, "_resolve_entities_batch_full", new=AsyncMock(return_value=[])) as mock_full,
-            patch.object(resolver, "_resolve_entities_batch_trigram", new=AsyncMock(return_value=[])) as mock_trgm,
-        ):
-            await resolver._resolve_entities_batch_impl(
-                conn=conn,
-                bank_id="test-bank",
-                entities_data=[],
-                context="",
-                unit_event_date=None,
-            )
-
-        # Trigram path must NOT be called
-        mock_trgm.assert_not_called()
-        # Full-scan path must be called as the fallback
-        mock_full.assert_called_once()
-        # Strategy is permanently downgraded
-        assert resolver.entity_lookup == "full"
-        assert resolver._pg_trgm_checked is True
-
-    @pytest.mark.asyncio
-    async def test_uses_trigram_when_pg_trgm_available(self):
-        """When pg_trgm is present the trigram path is used."""
-        resolver = _make_resolver(entity_lookup="trigram")
-        conn = _make_conn(pg_trgm_available=True)
-
-        with (
-            patch.object(resolver, "_resolve_entities_batch_full", new=AsyncMock(return_value=[])) as mock_full,
-            patch.object(resolver, "_resolve_entities_batch_trigram", new=AsyncMock(return_value=[])) as mock_trgm,
-        ):
-            await resolver._resolve_entities_batch_impl(
-                conn=conn,
-                bank_id="test-bank",
-                entities_data=[],
-                context="",
-                unit_event_date=None,
-            )
-
-        mock_trgm.assert_called_once()
-        mock_full.assert_not_called()
-        assert resolver.entity_lookup == "trigram"
-        assert resolver._pg_trgm_checked is True
-
-    @pytest.mark.asyncio
-    async def test_pg_trgm_check_performed_only_once(self):
-        """The fetchval check is only issued on the first call; subsequent calls skip it."""
-        resolver = _make_resolver(entity_lookup="trigram")
-        conn = _make_conn(pg_trgm_available=True)
-
-        with patch.object(resolver, "_resolve_entities_batch_trigram", new=AsyncMock(return_value=[])):
-            # First call — check is issued
-            await resolver._resolve_entities_batch_impl(
-                conn=conn,
-                bank_id="test-bank",
-                entities_data=[],
-                context="",
-                unit_event_date=None,
-            )
-            # Second call — check must NOT be issued again
-            await resolver._resolve_entities_batch_impl(
-                conn=conn,
-                bank_id="test-bank",
-                entities_data=[],
-                context="",
-                unit_event_date=None,
-            )
-
-        # fetchval (the pg_trgm availability query) should be called exactly once
-        assert conn.fetchval.call_count == 1
-
-    @pytest.mark.asyncio
-    async def test_full_strategy_skips_pg_trgm_check(self):
-        """When entity_lookup='full' from the start, no pg_trgm check is ever issued."""
-        resolver = _make_resolver(entity_lookup="full")
-        conn = _make_conn(pg_trgm_available=False)
-
-        with patch.object(resolver, "_resolve_entities_batch_full", new=AsyncMock(return_value=[])):
-            await resolver._resolve_entities_batch_impl(
-                conn=conn,
-                bank_id="test-bank",
-                entities_data=[],
-                context="",
-                unit_event_date=None,
-            )
-
-        # fetchval should never be called when entity_lookup is already "full"
-        conn.fetchval.assert_not_called()
-
-    @pytest.mark.asyncio
-    async def test_fallback_is_sticky_across_calls(self):
-        """After falling back to 'full', subsequent calls also use the full path."""
-        resolver = _make_resolver(entity_lookup="trigram")
-        conn = _make_conn(pg_trgm_available=False)
-
-        with (
-            patch.object(resolver, "_resolve_entities_batch_full", new=AsyncMock(return_value=[])) as mock_full,
-            patch.object(resolver, "_resolve_entities_batch_trigram", new=AsyncMock(return_value=[])) as mock_trgm,
-        ):
-            # First call triggers the fallback
-            await resolver._resolve_entities_batch_impl(
-                conn=conn,
-                bank_id="b",
-                entities_data=[],
-                context="",
-                unit_event_date=None,
-            )
-            # Second call — _pg_trgm_checked is True so no re-check; entity_lookup=="full"
-            await resolver._resolve_entities_batch_impl(
-                conn=conn,
-                bank_id="b",
-                entities_data=[],
-                context="",
-                unit_event_date=None,
-            )
-
-        # Trigram path is never called
-        mock_trgm.assert_not_called()
-        # Full-scan path is called both times
-        assert mock_full.call_count == 2
-        # pg_trgm check was issued exactly once
-        assert conn.fetchval.call_count == 1

hindsight-api-slim/tests/test_fact_extraction_metadata.py

@@ -1,61 +0,0 @@
-"""
-Unit tests for metadata inclusion in fact extraction LLM prompt.
-"""
-from datetime import datetime
-
-from hindsight_api.engine.retain.fact_extraction import _build_user_message
-
-
-def test_build_user_message_includes_metadata():
-    """Metadata key-value pairs should appear in the user message."""
-    event_date = datetime(2024, 6, 15, 12, 0, 0)
-    metadata = {"title": "Q2 Planning Doc", "source": "confluence", "author": "Alice"}
-
-    msg = _build_user_message(
-        chunk="Some content.",
-        chunk_index=0,
-        total_chunks=1,
-        event_date=event_date,
-        context="planning meeting",
-        metadata=metadata,
-    )
-
-    assert "title" in msg
-    assert "Q2 Planning Doc" in msg
-    assert "source" in msg
-    assert "confluence" in msg
-    assert "author" in msg
-    assert "Alice" in msg
-
-
-def test_build_user_message_no_metadata():
-    """When metadata is empty, the message should still be valid and not include a metadata section."""
-    event_date = datetime(2024, 6, 15, 12, 0, 0)
-
-    msg = _build_user_message(
-        chunk="Some content.",
-        chunk_index=0,
-        total_chunks=1,
-        event_date=event_date,
-        context="planning meeting",
-        metadata={},
-    )
-
-    assert "Some content." in msg
-    assert "Metadata:" not in msg
-
-
-def test_build_user_message_without_metadata_arg():
-    """Calling without metadata (default) should behave the same as empty metadata."""
-    event_date = datetime(2024, 6, 15, 12, 0, 0)
-
-    msg = _build_user_message(
-        chunk="Some content.",
-        chunk_index=0,
-        total_chunks=1,
-        event_date=event_date,
-        context="none",
-    )
-
-    assert "Some content." in msg
-    assert "Metadata:" not in msg

hindsight-api-slim/tests/test_fact_extraction_retry.py

@@ -1,141 +0,0 @@
-"""
-Unit tests for fact extraction retry logic.
-
-Tests the fix for the TypeError when LLM returns invalid JSON across all retries.
-Previously, `raise last_error` would raise None (TypeError) because last_error was
-only set in the BadRequestError handler, not when the LLM returned non-dict JSON.
-"""
-
-from datetime import datetime, timezone
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-
-def _make_config(llm_max_retries: int = 3, retain_llm_max_retries: int | None = None):
-    """Build a minimal HindsightConfig for fact extraction tests."""
-    from hindsight_api.config import HindsightConfig
-
-    cfg = MagicMock(spec=HindsightConfig)
-    cfg.retain_llm_max_retries = retain_llm_max_retries
-    cfg.llm_max_retries = llm_max_retries
-    cfg.retain_llm_initial_backoff = None
-    cfg.llm_initial_backoff = 0.0
-    cfg.retain_llm_max_backoff = None
-    cfg.llm_max_backoff = 0.0
-    cfg.retain_max_completion_tokens = 8192
-    cfg.retain_extraction_mode = "concise"
-    cfg.retain_extract_causal_links = False
-    cfg.retain_mission = None
-    return cfg
-
-
-def _make_llm_config(mock_response):
-    """Build a mock LLMProvider that returns the given response."""
-    from hindsight_api.engine.llm_wrapper import LLMProvider
-
-    llm = MagicMock(spec=LLMProvider)
-    llm.provider = "mock"
-    token_usage = MagicMock()
-    token_usage.__add__ = lambda self, other: self
-    llm.call = AsyncMock(return_value=(mock_response, token_usage))
-    return llm
-
-
-@pytest.mark.asyncio
-async def test_non_dict_json_all_retries_returns_empty():
-    """
-    When LLM returns non-dict JSON on every attempt, extraction should return []
-    without raising TypeError ('exceptions must derive from BaseException').
-
-    This was the bug: the loop ran range(2) times (hardcoded), but comparisons
-    used config.llm_max_retries (default 10). On the last loop iteration (attempt=1),
-    `attempt < 10 - 1` was True, so the code called `continue`, the loop
-    exhausted, and `raise last_error` raised None → TypeError.
-    """
-    from hindsight_api.engine.retain.fact_extraction import _extract_facts_from_chunk
-
-    # llm_max_retries=3 ensures the bug triggers with the old code (3 != 2 hardcoded)
-    config = _make_config(llm_max_retries=3, retain_llm_max_retries=None)
-
-    # Mock: always returns a list (non-dict), which is invalid
-    llm_config = _make_llm_config(mock_response=[{"invalid": "response"}])
-
-    with patch(
-        "hindsight_api.engine.retain.fact_extraction._build_extraction_prompt_and_schema",
-        return_value=("system prompt", MagicMock()),
-    ):
-        facts, usage = await _extract_facts_from_chunk(
-            chunk="Alice visited Paris in 2023.",
-            chunk_index=0,
-            total_chunks=1,
-            event_date=datetime(2023, 1, 1, tzinfo=timezone.utc),
-            context="travel notes",
-            llm_config=llm_config,
-            config=config,
-            agent_name="test-agent",
-        )
-
-    assert facts == []
-
-
-@pytest.mark.asyncio
-async def test_non_dict_json_with_default_max_retries_returns_empty():
-    """
-    Same scenario with the default llm_max_retries=10 (matching real default config).
-    The old code ran range(2) but checked against 10, always continuing until
-    the loop exhausted, then raised None → TypeError.
-    """
-    from hindsight_api.engine.retain.fact_extraction import _extract_facts_from_chunk
-
-    config = _make_config(llm_max_retries=10, retain_llm_max_retries=None)
-    llm_config = _make_llm_config(mock_response="not a dict at all")
-
-    with patch(
-        "hindsight_api.engine.retain.fact_extraction._build_extraction_prompt_and_schema",
-        return_value=("system prompt", MagicMock()),
-    ):
-        facts, usage = await _extract_facts_from_chunk(
-            chunk="Some text.",
-            chunk_index=0,
-            total_chunks=1,
-            event_date=datetime(2023, 6, 1, tzinfo=timezone.utc),
-            context="",
-            llm_config=llm_config,
-            config=config,
-            agent_name="agent",
-        )
-
-    assert facts == []
-
-
-@pytest.mark.asyncio
-async def test_retain_llm_max_retries_overrides_global():
-    """
-    When retain_llm_max_retries is set, it should be used for the loop range
-    and all comparisons (no shadowing bug).
-    """
-    from hindsight_api.engine.retain.fact_extraction import _extract_facts_from_chunk
-
-    # retain_llm_max_retries=5 should override llm_max_retries=10
-    config = _make_config(llm_max_retries=10, retain_llm_max_retries=5)
-    llm_config = _make_llm_config(mock_response=42)  # non-dict: integer
-
-    with patch(
-        "hindsight_api.engine.retain.fact_extraction._build_extraction_prompt_and_schema",
-        return_value=("system prompt", MagicMock()),
-    ):
-        facts, usage = await _extract_facts_from_chunk(
-            chunk="Bob likes Python.",
-            chunk_index=0,
-            total_chunks=1,
-            event_date=datetime(2024, 1, 1, tzinfo=timezone.utc),
-            context="",
-            llm_config=llm_config,
-            config=config,
-            agent_name="agent",
-        )
-
-    assert facts == []
-    # Verify it retried exactly retain_llm_max_retries times
-    assert llm_config.call.call_count == 5

hindsight-api-slim/tests/test_gemini_safety_settings.py

@@ -1,340 +0,0 @@
-"""
-Tests for Gemini safety settings feature.
-
-Verifies that:
-- Safety settings are read from env var and stored on GeminiLLM instances
-- Settings are applied to GenerateContentConfig in call() and call_with_tools()
-- The context variable override allows per-bank settings at request time
-- None (unset) means Gemini's default safety settings are used (no override)
-"""
-
-import os
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-pytest.importorskip("google.genai")
-
-
-SAMPLE_SAFETY_SETTINGS = [
-    {"category": "HARM_CATEGORY_HARASSMENT", "threshold": "BLOCK_NONE"},
-    {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"},
-    {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "BLOCK_NONE"},
-    {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "BLOCK_NONE"},
-]
-
-
-# ─── Config / env var parsing ─────────────────────────────────────────────────
-
-
-def test_gemini_safety_settings_parsed_from_env():
-    """Safety settings JSON from env var is parsed into HindsightConfig."""
-    import json
-
-    from hindsight_api.config import ENV_LLM_GEMINI_SAFETY_SETTINGS, HindsightConfig, clear_config_cache
-
-    settings_json = json.dumps(SAMPLE_SAFETY_SETTINGS)
-    with patch.dict(os.environ, {ENV_LLM_GEMINI_SAFETY_SETTINGS: settings_json}, clear=False):
-        clear_config_cache()
-        config = HindsightConfig.from_env()
-        assert config.llm_gemini_safety_settings == SAMPLE_SAFETY_SETTINGS
-        clear_config_cache()
-
-
-def test_gemini_safety_settings_default_is_none():
-    """When env var is not set, llm_gemini_safety_settings defaults to None."""
-    from hindsight_api.config import ENV_LLM_GEMINI_SAFETY_SETTINGS, HindsightConfig, clear_config_cache
-
-    env = {k: v for k, v in os.environ.items() if k != ENV_LLM_GEMINI_SAFETY_SETTINGS}
-    with patch.dict(os.environ, env, clear=True):
-        clear_config_cache()
-        config = HindsightConfig.from_env()
-        assert config.llm_gemini_safety_settings is None
-        clear_config_cache()
-
-
-def test_gemini_safety_settings_is_configurable_field():
-    """llm_gemini_safety_settings appears in configurable (per-bank) fields."""
-    from hindsight_api.config import HindsightConfig
-
-    assert "llm_gemini_safety_settings" in HindsightConfig.get_configurable_fields()
-
-
-def test_gemini_safety_settings_not_in_credential_fields():
-    """llm_gemini_safety_settings is NOT a credential — it is safe to expose via API."""
-    from hindsight_api.config import HindsightConfig
-
-    assert "llm_gemini_safety_settings" not in HindsightConfig.get_credential_fields()
-
-
-# ─── GeminiLLM instance ───────────────────────────────────────────────────────
-
-
-def _make_gemini_provider(safety_settings=None):
-    """Return a GeminiLLM instance with a mocked genai.Client."""
-    with patch("google.genai.Client") as mock_client_cls:
-        mock_client_cls.return_value = MagicMock()
-        from hindsight_api.engine.providers.gemini_llm import GeminiLLM
-
-        provider = GeminiLLM(
-            provider="gemini",
-            api_key="fake-api-key",
-            base_url="",
-            model="gemini-2.5-flash",
-            gemini_safety_settings=safety_settings,
-        )
-        # Replace client with a fresh mock so we can inspect calls
-        provider._client = MagicMock()
-        return provider
-
-
-def test_gemini_llm_stores_safety_settings():
-    """GeminiLLM stores safety settings passed at construction."""
-    provider = _make_gemini_provider(safety_settings=SAMPLE_SAFETY_SETTINGS)
-    assert provider._safety_settings == SAMPLE_SAFETY_SETTINGS
-
-
-def test_gemini_llm_no_safety_settings_is_none():
-    """GeminiLLM._safety_settings is None when not provided."""
-    provider = _make_gemini_provider(safety_settings=None)
-    assert provider._safety_settings is None
-
-
-# ─── call() applies safety settings ──────────────────────────────────────────
-
-
-@pytest.mark.asyncio
-async def test_call_applies_safety_settings():
-    """call() includes safety_settings in GenerateContentConfig when configured."""
-    from google.genai import types as genai_types
-
-    provider = _make_gemini_provider(safety_settings=SAMPLE_SAFETY_SETTINGS)
-
-    # Build a fake successful response
-    fake_response = MagicMock()
-    fake_response.text = "hello"
-    fake_response.candidates = [MagicMock(finish_reason="STOP")]
-    fake_response.usage_metadata = MagicMock(prompt_token_count=5, candidates_token_count=2)
-
-    provider._client.aio.models.generate_content = AsyncMock(return_value=fake_response)
-
-    await provider.call(
-        messages=[{"role": "user", "content": "hi"}],
-        scope="test",
-    )
-
-    # Inspect the config passed to generate_content
-    call_args = provider._client.aio.models.generate_content.call_args
-    config_arg = call_args.kwargs.get("config") or call_args.args[0] if call_args.args else None
-    # config may be in kwargs or positional; grab from kwargs
-    config_arg = call_args.kwargs.get("config")
-
-    assert config_arg is not None, "GenerateContentConfig should have been passed"
-    assert hasattr(config_arg, "safety_settings"), "Config should have safety_settings"
-    assert config_arg.safety_settings is not None
-
-    categories = [s.category.value if hasattr(s.category, "value") else str(s.category) for s in config_arg.safety_settings]
-    assert "HARM_CATEGORY_HARASSMENT" in categories
-    assert "HARM_CATEGORY_HATE_SPEECH" in categories
-    assert "HARM_CATEGORY_SEXUALLY_EXPLICIT" in categories
-    assert "HARM_CATEGORY_DANGEROUS_CONTENT" in categories
-
-    thresholds = [s.threshold.value if hasattr(s.threshold, "value") else str(s.threshold) for s in config_arg.safety_settings]
-    assert all(t == "BLOCK_NONE" for t in thresholds)
-
-
-@pytest.mark.asyncio
-async def test_call_no_safety_settings_omits_key():
-    """call() does NOT add safety_settings to GenerateContentConfig when none configured."""
-    provider = _make_gemini_provider(safety_settings=None)
-
-    fake_response = MagicMock()
-    fake_response.text = "hello"
-    fake_response.candidates = [MagicMock(finish_reason="STOP")]
-    fake_response.usage_metadata = MagicMock(prompt_token_count=5, candidates_token_count=2)
-
-    provider._client.aio.models.generate_content = AsyncMock(return_value=fake_response)
-
-    await provider.call(
-        messages=[{"role": "user", "content": "hi"}],
-        scope="test",
-    )
-
-    call_args = provider._client.aio.models.generate_content.call_args
-    config_arg = call_args.kwargs.get("config")
-
-    # When no safety settings, config is either None or lacks safety_settings
-    if config_arg is not None:
-        assert not hasattr(config_arg, "safety_settings") or config_arg.safety_settings is None
-
-
-# ─── call_with_tools() applies safety settings ────────────────────────────────
-
-
-@pytest.mark.asyncio
-async def test_call_with_tools_applies_safety_settings():
-    """call_with_tools() includes safety_settings in GenerateContentConfig."""
-    provider = _make_gemini_provider(safety_settings=SAMPLE_SAFETY_SETTINGS)
-
-    # Build a fake tool-use response (no tool calls, just text)
-    fake_part = MagicMock()
-    fake_part.text = "answer"
-    fake_part.function_call = None
-
-    fake_candidate = MagicMock()
-    fake_candidate.content = MagicMock(parts=[fake_part])
-
-    fake_response = MagicMock()
-    fake_response.candidates = [fake_candidate]
-    fake_response.usage_metadata = MagicMock(prompt_token_count=5, candidates_token_count=3)
-
-    provider._client.aio.models.generate_content = AsyncMock(return_value=fake_response)
-
-    tools = [
-        {
-            "type": "function",
-            "function": {
-                "name": "test_tool",
-                "description": "A test tool",
-                "parameters": {"type": "object", "properties": {}, "required": []},
-            },
-        }
-    ]
-
-    await provider.call_with_tools(
-        messages=[{"role": "user", "content": "hi"}],
-        tools=tools,
-        scope="test",
-    )
-
-    call_args = provider._client.aio.models.generate_content.call_args
-    config_arg = call_args.kwargs.get("config")
-
-    assert config_arg is not None
-    assert config_arg.safety_settings is not None
-    categories = [s.category.value if hasattr(s.category, "value") else str(s.category) for s in config_arg.safety_settings]
-    assert "HARM_CATEGORY_HARASSMENT" in categories
-
-
-# ─── with_config() override ───────────────────────────────────────────────────
-
-
-def _make_llm_provider(safety_settings=None):
-    """Return an LLMProvider (wrapping GeminiLLM) with a mocked genai.Client."""
-    with patch("google.genai.Client") as mock_client_cls:
-        mock_client_cls.return_value = MagicMock()
-        from hindsight_api.engine.llm_wrapper import LLMProvider
-
-        provider = LLMProvider(
-            provider="gemini",
-            api_key="fake-api-key",
-            base_url="",
-            model="gemini-2.5-flash",
-            gemini_safety_settings=safety_settings,
-        )
-        # Replace the underlying Gemini client with a fresh mock
-        provider._provider_impl._client = MagicMock()
-        return provider
-
-
-def _fake_response():
-    r = MagicMock()
-    r.text = "hello"
-    r.candidates = [MagicMock(finish_reason="STOP")]
-    r.usage_metadata = MagicMock(prompt_token_count=5, candidates_token_count=2)
-    return r
-
-
-def _make_config(safety_settings):
-    """Return a minimal config-like object with llm_gemini_safety_settings."""
-    cfg = MagicMock()
-    cfg.llm_gemini_safety_settings = safety_settings
-    return cfg
-
-
-@pytest.mark.asyncio
-async def test_with_config_overrides_instance_settings():
-    """with_config() settings take precedence over the provider instance defaults."""
-    instance_settings = [{"category": "HARM_CATEGORY_HARASSMENT", "threshold": "BLOCK_ONLY_HIGH"}]
-    override_settings = [{"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"}]
-
-    provider = _make_llm_provider(safety_settings=instance_settings)
-    provider._provider_impl._client.aio.models.generate_content = AsyncMock(return_value=_fake_response())
-
-    configured = provider.with_config(_make_config(override_settings))
-    await configured.call(messages=[{"role": "user", "content": "hi"}], scope="test")
-
-    config_arg = provider._provider_impl._client.aio.models.generate_content.call_args.kwargs.get("config")
-    assert config_arg is not None
-    categories = [s.category.value if hasattr(s.category, "value") else str(s.category) for s in config_arg.safety_settings]
-    # Should use override_settings (HATE_SPEECH), not instance_settings (HARASSMENT)
-    assert "HARM_CATEGORY_HATE_SPEECH" in categories
-    assert "HARM_CATEGORY_HARASSMENT" not in categories
-
-
-@pytest.mark.asyncio
-async def test_with_config_none_falls_back_to_instance():
-    """When with_config() supplies None, the instance default is used."""
-    instance_settings = [{"category": "HARM_CATEGORY_HARASSMENT", "threshold": "BLOCK_NONE"}]
-
-    provider = _make_llm_provider(safety_settings=instance_settings)
-    provider._provider_impl._client.aio.models.generate_content = AsyncMock(return_value=_fake_response())
-
-    configured = provider.with_config(_make_config(None))
-    await configured.call(messages=[{"role": "user", "content": "hi"}], scope="test")
-
-    config_arg = provider._provider_impl._client.aio.models.generate_content.call_args.kwargs.get("config")
-    assert config_arg is not None
-    categories = [s.category.value if hasattr(s.category, "value") else str(s.category) for s in config_arg.safety_settings]
-    assert "HARM_CATEGORY_HARASSMENT" in categories
-
-
-@pytest.mark.asyncio
-async def test_with_config_resets_after_call():
-    """The ContextVar is properly reset after a with_config() call (no leakage)."""
-    from hindsight_api.engine.providers.gemini_llm import _safety_settings_ctx
-
-    settings = [{"category": "HARM_CATEGORY_HARASSMENT", "threshold": "BLOCK_NONE"}]
-    provider = _make_llm_provider(safety_settings=None)
-    provider._provider_impl._client.aio.models.generate_content = AsyncMock(return_value=_fake_response())
-
-    before = _safety_settings_ctx.get()
-    configured = provider.with_config(_make_config(settings))
-    await configured.call(messages=[{"role": "user", "content": "hi"}], scope="test")
-    after = _safety_settings_ctx.get()
-
-    assert after == before  # ContextVar restored to its original value
-
-
-# ─── LLMProvider reads safety settings from config ────────────────────────────
-
-
-def test_llm_provider_reads_safety_settings_from_config():
-    """LLMProvider reads llm_gemini_safety_settings from global config for Gemini provider."""
-    import json
-
-    from hindsight_api.config import ENV_LLM_GEMINI_SAFETY_SETTINGS, clear_config_cache
-
-    settings_json = json.dumps(SAMPLE_SAFETY_SETTINGS)
-    env_overrides = {
-        "HINDSIGHT_API_LLM_PROVIDER": "gemini",
-        "HINDSIGHT_API_LLM_API_KEY": "fake-key",
-        ENV_LLM_GEMINI_SAFETY_SETTINGS: settings_json,
-    }
-
-    with patch.dict(os.environ, env_overrides, clear=False):
-        clear_config_cache()
-        with patch("google.genai.Client") as mock_client_cls:
-            mock_client_cls.return_value = MagicMock()
-            from hindsight_api.engine.llm_wrapper import LLMProvider
-
-            provider = LLMProvider(
-                provider="gemini",
-                api_key="fake-key",
-                base_url="",
-                model="gemini-2.5-flash",
-            )
-
-            assert provider.gemini_safety_settings == SAMPLE_SAFETY_SETTINGS
-
-        clear_config_cache()

hindsight-api-slim/tests/test_graph_filtering.py

@@ -1,171 +0,0 @@
-"""
-Tests for server-side filtering in the graph API endpoint.
-
-Verifies that q (text search) and tags filters work correctly
-when passed as query parameters to GET /v1/default/banks/{bank_id}/graph.
-"""
-from datetime import datetime
-
-import httpx
-import pytest
-import pytest_asyncio
-
-from hindsight_api.api import create_app
-
-
-@pytest_asyncio.fixture
-async def api_client(memory):
-    """Create an async test client for the FastAPI app."""
-    app = create_app(memory, initialize_memory=False)
-    transport = httpx.ASGITransport(app=app)
-    async with httpx.AsyncClient(transport=transport, base_url="http://test") as client:
-        yield client
-
-
-@pytest.fixture
-def test_bank_id():
-    """Provide a unique bank ID for this test run."""
-    return f"graph_filter_test_{datetime.now().timestamp()}"
-
-
-@pytest.mark.asyncio
-async def test_graph_no_filter_returns_all(api_client, test_bank_id):
-    """Without filters the graph endpoint returns all memories."""
-    response = await api_client.post(
-        f"/v1/default/banks/{test_bank_id}/memories",
-        json={
-            "items": [
-                {"content": "Alice loves hiking in the mountains.", "tags": ["user_alice"]},
-                {"content": "Bob enjoys swimming at the beach.", "tags": ["user_bob"]},
-            ]
-        },
-    )
-    assert response.status_code == 200
-
-    response = await api_client.get(f"/v1/default/banks/{test_bank_id}/graph")
-    assert response.status_code == 200
-    data = response.json()
-    assert "table_rows" in data
-    texts = [row["text"] for row in data["table_rows"]]
-    assert any("Alice" in t for t in texts)
-    assert any("Bob" in t for t in texts)
-
-
-@pytest.mark.asyncio
-async def test_graph_q_filter_returns_matching(api_client, test_bank_id):
-    """The q parameter filters memories by text content."""
-    response = await api_client.post(
-        f"/v1/default/banks/{test_bank_id}/memories",
-        json={
-            "items": [
-                {"content": "Alice loves hiking in the mountains."},
-                {"content": "Bob enjoys swimming at the beach."},
-            ]
-        },
-    )
-    assert response.status_code == 200
-
-    response = await api_client.get(f"/v1/default/banks/{test_bank_id}/graph", params={"q": "Alice"})
-    assert response.status_code == 200
-    data = response.json()
-    texts = [row["text"] for row in data["table_rows"]]
-    assert all("Alice" in t or "alice" in t.lower() for t in texts), (
-        f"Expected only Alice memories, got: {texts}"
-    )
-    assert not any("Bob" in t for t in texts)
-
-
-@pytest.mark.asyncio
-async def test_graph_q_filter_case_insensitive(api_client, test_bank_id):
-    """The q filter is case-insensitive."""
-    response = await api_client.post(
-        f"/v1/default/banks/{test_bank_id}/memories",
-        json={
-            "items": [
-                {"content": "Alice loves hiking in the mountains."},
-                {"content": "Bob enjoys swimming at the beach."},
-            ]
-        },
-    )
-    assert response.status_code == 200
-
-    response = await api_client.get(f"/v1/default/banks/{test_bank_id}/graph", params={"q": "alice"})
-    assert response.status_code == 200
-    data = response.json()
-    texts = [row["text"] for row in data["table_rows"]]
-    assert any("Alice" in t for t in texts)
-    assert not any("Bob" in t for t in texts)
-
-
-@pytest.mark.asyncio
-async def test_graph_tags_filter_returns_matching(api_client, test_bank_id):
-    """The tags parameter filters memories to only those with matching tags."""
-    response = await api_client.post(
-        f"/v1/default/banks/{test_bank_id}/memories",
-        json={
-            "items": [
-                {"content": "Alice loves hiking.", "tags": ["user_alice"]},
-                {"content": "Bob enjoys swimming.", "tags": ["user_bob"]},
-            ]
-        },
-    )
-    assert response.status_code == 200
-
-    response = await api_client.get(
-        f"/v1/default/banks/{test_bank_id}/graph",
-        params={"tags": "user_alice", "tags_match": "all_strict"},
-    )
-    assert response.status_code == 200
-    data = response.json()
-    texts = [row["text"] for row in data["table_rows"]]
-    assert any("Alice" in t for t in texts)
-    assert not any("Bob" in t for t in texts)
-
-
-@pytest.mark.asyncio
-async def test_graph_q_and_tags_filter_combined(api_client, test_bank_id):
-    """Combining q and tags filters applies both server-side."""
-    response = await api_client.post(
-        f"/v1/default/banks/{test_bank_id}/memories",
-        json={
-            "items": [
-                {"content": "Alice loves hiking.", "tags": ["user_alice"]},
-                {"content": "Alice also loves coding.", "tags": ["user_alice"]},
-                {"content": "Bob enjoys swimming.", "tags": ["user_bob"]},
-            ]
-        },
-    )
-    assert response.status_code == 200
-
-    response = await api_client.get(
-        f"/v1/default/banks/{test_bank_id}/graph",
-        params={"q": "hiking", "tags": "user_alice", "tags_match": "all_strict"},
-    )
-    assert response.status_code == 200
-    data = response.json()
-    texts = [row["text"] for row in data["table_rows"]]
-    assert any("hiking" in t.lower() for t in texts)
-    assert not any("coding" in t.lower() for t in texts)
-    assert not any("Bob" in t for t in texts)
-
-
-@pytest.mark.asyncio
-async def test_graph_q_filter_empty_results(api_client, test_bank_id):
-    """The q filter returns empty results when no memory matches."""
-    response = await api_client.post(
-        f"/v1/default/banks/{test_bank_id}/memories",
-        json={
-            "items": [
-                {"content": "Alice loves hiking."},
-            ]
-        },
-    )
-    assert response.status_code == 200
-
-    response = await api_client.get(
-        f"/v1/default/banks/{test_bank_id}/graph",
-        params={"q": "zzznomatchzzz"},
-    )
-    assert response.status_code == 200
-    data = response.json()
-    assert data["table_rows"] == []

hindsight-api-slim/tests/test_hnsw_indexes.py

@@ -1,193 +0,0 @@
-"""
-Tests for per-bank HNSW index lifecycle and UNION ALL retrieval.
-
-Covers:
-- _hnsw_index_name deterministic naming
-- Per-bank HNSW indexes created on bank creation (retain_async / ensure_bank_exists)
-- Per-bank HNSW indexes dropped on bank deletion
-- retrieve_semantic_bm25_combined groups results correctly by fact_type and source
-"""
-import uuid
-from datetime import datetime, timezone
-
-import pytest
-
-from hindsight_api.engine.retain.bank_utils import _HNSW_FACT_TYPES, _hnsw_index_name
-
-
-# ---------------------------------------------------------------------------
-# Unit tests — no DB required
-# ---------------------------------------------------------------------------
-
-
-class TestHnswIndexName:
-    def test_deterministic(self):
-        uid = "550e8400-e29b-41d4-a716-446655440000"
-        assert _hnsw_index_name("world", uid) == _hnsw_index_name("world", uid)
-
-    def test_strips_dashes(self):
-        uid = "550e8400-e29b-41d4-a716-446655440000"
-        name = _hnsw_index_name("world", uid)
-        # uid16 should be hex chars only
-        assert "-" not in name
-
-    def test_uses_first_16_hex_chars(self):
-        uid = "550e8400-e29b-41d4-a716-446655440000"
-        uid16 = uid.replace("-", "")[:16]  # "550e8400e29b41d4"
-        assert name_ends_with(name=_hnsw_index_name("world", uid), suffix=uid16)
-
-    def test_suffix_per_fact_type(self):
-        uid = "550e8400-e29b-41d4-a716-446655440000"
-        names = {ft: _hnsw_index_name(ft, uid) for ft in _HNSW_FACT_TYPES}
-        # All three names must be distinct
-        assert len(set(names.values())) == 3
-
-    def test_all_fact_types_covered(self):
-        assert set(_HNSW_FACT_TYPES) == {"world", "experience", "observation"}
-
-    def test_fits_pg_identifier_limit(self):
-        # PostgreSQL max identifier length is 63 chars
-        uid = "f" * 32  # simulated UUID without dashes
-        for ft in _HNSW_FACT_TYPES:
-            assert len(_hnsw_index_name(ft, uid)) <= 63
-
-
-def name_ends_with(name: str, suffix: str) -> bool:
-    return name.endswith(suffix)
-
-
-# ---------------------------------------------------------------------------
-# Integration tests — require DB (memory fixture)
-# ---------------------------------------------------------------------------
-
-
-async def _get_bank_hnsw_indexes(pool, bank_id: str) -> list[str]:
-    """Return index names for memory_units that match the per-bank pattern."""
-    async with pool.acquire() as conn:
-        rows = await conn.fetch(
-            """
-            SELECT indexname
-            FROM pg_indexes
-            WHERE tablename = 'memory_units'
-              AND indexname LIKE 'idx_mu_emb_%'
-              AND indexdef LIKE $1
-            ORDER BY indexname
-            """,
-            f"%bank_id = '{bank_id}'%",
-        )
-    return [row["indexname"] for row in rows]
-
-
-@pytest.mark.asyncio
-async def test_retain_creates_per_bank_hnsw_indexes(memory, request_context):
-    """retain_async on a new bank must create 3 per-(bank, fact_type) HNSW indexes."""
-    bank_id = f"test_hnsw_create_{uuid.uuid4().hex[:8]}"
-    try:
-        await memory.retain_async(
-            bank_id=bank_id,
-            content="Alice is a software engineer.",
-            request_context=request_context,
-        )
-        indexes = await _get_bank_hnsw_indexes(memory._pool, bank_id)
-        assert len(indexes) == 3, f"Expected 3 per-bank HNSW indexes, got: {indexes}"
-        for ft_short in _HNSW_FACT_TYPES.values():
-            assert any(ft_short in idx for idx in indexes), (
-                f"Missing index for fact_type short '{ft_short}' in {indexes}"
-            )
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_delete_bank_drops_hnsw_indexes(memory, request_context):
-    """delete_bank must drop all per-bank HNSW indexes."""
-    bank_id = f"test_hnsw_drop_{uuid.uuid4().hex[:8]}"
-
-    await memory.retain_async(
-        bank_id=bank_id,
-        content="Bob is a data scientist.",
-        request_context=request_context,
-    )
-    # Verify indexes exist before deletion
-    indexes_before = await _get_bank_hnsw_indexes(memory._pool, bank_id)
-    assert len(indexes_before) == 3
-
-    await memory.delete_bank(bank_id, request_context=request_context)
-
-    indexes_after = await _get_bank_hnsw_indexes(memory._pool, bank_id)
-    assert indexes_after == [], f"Indexes should be dropped after bank deletion, got: {indexes_after}"
-
-
-@pytest.mark.asyncio
-async def test_retain_idempotent_bank_creation(memory, request_context):
-    """Retaining into the same bank twice must not error and still have exactly 3 indexes."""
-    bank_id = f"test_hnsw_idem_{uuid.uuid4().hex[:8]}"
-    try:
-        await memory.retain_async(
-            bank_id=bank_id,
-            content="Carol is a product manager.",
-            request_context=request_context,
-        )
-        await memory.retain_async(
-            bank_id=bank_id,
-            content="Carol joined the company in 2022.",
-            request_context=request_context,
-        )
-        indexes = await _get_bank_hnsw_indexes(memory._pool, bank_id)
-        assert len(indexes) == 3
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_retrieve_semantic_bm25_grouped_by_fact_type(memory, request_context):
-    """
-    retrieve_semantic_bm25_combined must return a dict keyed by fact_type with
-    (semantic_list, bm25_list) tuples.  All returned facts must belong to their
-    declared fact_type.
-    """
-    from hindsight_api.engine.search.retrieval import retrieve_semantic_bm25_combined
-
-    bank_id = f"test_retrieval_{uuid.uuid4().hex[:8]}"
-    try:
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=(
-                "Alice is a software engineer at TechCorp. "
-                "She visited Paris in 2023 for a conference."
-            ),
-            context="background",
-            event_date=datetime(2023, 6, 1, tzinfo=timezone.utc),
-            request_context=request_context,
-        )
-
-        query_emb = memory.embeddings.encode(["software engineer Alice"])
-        query_emb_str = str(query_emb[0])
-
-        fact_types = ["world", "experience"]
-        async with memory._pool.acquire() as conn:
-            results = await retrieve_semantic_bm25_combined(
-                conn=conn,
-                query_emb_str=query_emb_str,
-                query_text="software engineer Alice",
-                bank_id=bank_id,
-                fact_types=fact_types,
-                limit=5,
-            )
-
-        # Must return an entry for every requested fact_type
-        assert set(results.keys()) == set(fact_types)
-
-        for ft, (sem, bm25) in results.items():
-            # Semantic and BM25 lists must be lists
-            assert isinstance(sem, list)
-            assert isinstance(bm25, list)
-            # All semantic results must declare the correct fact_type
-            for r in sem:
-                assert r.fact_type == ft, f"Semantic result has wrong fact_type: {r.fact_type}"
-            # All BM25 results must declare the correct fact_type
-            for r in bm25:
-                assert r.fact_type == ft, f"BM25 result has wrong fact_type: {r.fact_type}"
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)

hindsight-api-slim/tests/test_list_documents.py

@@ -1,174 +0,0 @@
-"""
-Tests for list_documents pagination and tags filtering.
-"""
-from datetime import datetime, timezone
-
-import pytest
-
-
-async def _retain_doc(memory, bank_id, document_id, tags, request_context):
-    """Helper to retain a document with given tags. Uses gibberish content to avoid LLM
-    fact extraction (documents are persisted even with zero facts)."""
-    await memory.retain_batch_async(
-        bank_id=bank_id,
-        contents=[{"content": f"xyzabc123 !@# $$$ {document_id}"}],
-        document_id=document_id,
-        document_tags=tags or None,
-        request_context=request_context,
-    )
-
-
-@pytest.mark.asyncio
-async def test_list_documents_offset_pagination(memory, request_context):
-    """offset parameter returns the correct slice of documents."""
-    bank_id = f"test_list_docs_offset_{datetime.now(timezone.utc).timestamp()}"
-
-    try:
-        for i in range(4):
-            await _retain_doc(memory, bank_id, f"doc-{i:02d}", [], request_context)
-
-        # All documents, ordered by created_at DESC → doc-03, doc-02, doc-01, doc-00
-        all_docs = await memory.list_documents(
-            bank_id=bank_id, limit=10, offset=0, request_context=request_context
-        )
-        assert all_docs["total"] == 4
-        assert len(all_docs["items"]) == 4
-        all_ids = [d["id"] for d in all_docs["items"]]
-
-        # offset=2 should skip the first two and return the remaining two
-        page2 = await memory.list_documents(
-            bank_id=bank_id, limit=10, offset=2, request_context=request_context
-        )
-        assert page2["total"] == 4  # total is always the full count
-        assert len(page2["items"]) == 2
-        assert [d["id"] for d in page2["items"]] == all_ids[2:]
-
-        # offset beyond total returns empty items but correct total
-        beyond = await memory.list_documents(
-            bank_id=bank_id, limit=10, offset=10, request_context=request_context
-        )
-        assert beyond["total"] == 4
-        assert beyond["items"] == []
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_list_documents_tags_filter_any_strict(memory, request_context):
-    """tags filter with any_strict returns only tagged documents that match."""
-    bank_id = f"test_list_docs_tags_{datetime.now(timezone.utc).timestamp()}"
-
-    try:
-        await _retain_doc(memory, bank_id, "doc-alpha", ["team-a"], request_context)
-        await _retain_doc(memory, bank_id, "doc-beta", ["team-b"], request_context)
-        await _retain_doc(memory, bank_id, "doc-both", ["team-a", "team-b"], request_context)
-        await _retain_doc(memory, bank_id, "doc-untagged", [], request_context)
-
-        # any_strict: only docs with at least one of the given tags, untagged excluded
-        result = await memory.list_documents(
-            bank_id=bank_id,
-            tags=["team-a"],
-            tags_match="any_strict",
-            request_context=request_context,
-        )
-        ids = {d["id"] for d in result["items"]}
-        assert ids == {"doc-alpha", "doc-both"}
-        assert result["total"] == 2
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_list_documents_tags_filter_any_includes_untagged(memory, request_context):
-    """tags filter with 'any' mode includes untagged documents."""
-    bank_id = f"test_list_docs_tags_any_{datetime.now(timezone.utc).timestamp()}"
-
-    try:
-        await _retain_doc(memory, bank_id, "doc-tagged", ["team-a"], request_context)
-        await _retain_doc(memory, bank_id, "doc-other", ["team-b"], request_context)
-        await _retain_doc(memory, bank_id, "doc-untagged", [], request_context)
-
-        result = await memory.list_documents(
-            bank_id=bank_id,
-            tags=["team-a"],
-            tags_match="any",
-            request_context=request_context,
-        )
-        ids = {d["id"] for d in result["items"]}
-        # "any" includes untagged + matching tagged
-        assert "doc-tagged" in ids
-        assert "doc-untagged" in ids
-        assert "doc-other" not in ids
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_list_documents_tags_filter_all_strict(memory, request_context):
-    """tags filter with all_strict returns only docs that have ALL the specified tags."""
-    bank_id = f"test_list_docs_tags_all_{datetime.now(timezone.utc).timestamp()}"
-
-    try:
-        await _retain_doc(memory, bank_id, "doc-a-only", ["team-a"], request_context)
-        await _retain_doc(memory, bank_id, "doc-a-and-b", ["team-a", "team-b"], request_context)
-        await _retain_doc(memory, bank_id, "doc-untagged", [], request_context)
-
-        result = await memory.list_documents(
-            bank_id=bank_id,
-            tags=["team-a", "team-b"],
-            tags_match="all_strict",
-            request_context=request_context,
-        )
-        ids = {d["id"] for d in result["items"]}
-        assert ids == {"doc-a-and-b"}
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_list_documents_no_tags_filter_returns_all(memory, request_context):
-    """When no tags filter is specified, all documents are returned."""
-    bank_id = f"test_list_docs_no_tags_{datetime.now(timezone.utc).timestamp()}"
-
-    try:
-        await _retain_doc(memory, bank_id, "doc-tagged", ["team-a"], request_context)
-        await _retain_doc(memory, bank_id, "doc-untagged", [], request_context)
-
-        result = await memory.list_documents(
-            bank_id=bank_id,
-            tags=None,
-            request_context=request_context,
-        )
-        ids = {d["id"] for d in result["items"]}
-        assert ids == {"doc-tagged", "doc-untagged"}
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_list_documents_tags_and_search_query_combined(memory, request_context):
-    """tags filter and q (search_query) can be combined."""
-    bank_id = f"test_list_docs_tags_q_{datetime.now(timezone.utc).timestamp()}"
-
-    try:
-        await _retain_doc(memory, bank_id, "report-2024", ["team-a"], request_context)
-        await _retain_doc(memory, bank_id, "report-2025", ["team-b"], request_context)
-        await _retain_doc(memory, bank_id, "summary-2024", ["team-a"], request_context)
-
-        result = await memory.list_documents(
-            bank_id=bank_id,
-            search_query="report",
-            tags=["team-a"],
-            tags_match="any_strict",
-            request_context=request_context,
-        )
-        ids = {d["id"] for d in result["items"]}
-        assert ids == {"report-2024"}
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)

hindsight-api-slim/tests/test_llm_wrapper.py

@@ -1,37 +0,0 @@
-import pytest
-
-from hindsight_api.engine.llm_wrapper import sanitize_llm_output
-
-
-@pytest.mark.parametrize(
-    "input_text, expected",
-    [
-        # Null bytes stripped
-        ("hello\x00world", "helloworld"),
-        ("FIRST\u0000PAGE", "FIRSTPAGE"),
-        # Multiple null bytes
-        ("\x00\x00text\x00", "text"),
-        # Other control characters stripped (non-whitespace)
-        ("text\x01\x02\x03end", "textend"),
-        ("text\x08end", "textend"),  # backspace
-        ("text\x0cend", "textend"),  # form feed
-        ("text\x0bend", "textend"),  # vertical tab
-        ("text\x1fend", "textend"),  # unit separator
-        ("text\x7fend", "textend"),  # DEL
-        # Whitespace preserved
-        ("hello\tworld", "hello\tworld"),
-        ("hello\nworld", "hello\nworld"),
-        ("hello\r\nworld", "hello\r\nworld"),
-        # Unicode surrogates stripped
-        ("text\ud800end", "textend"),
-        ("text\udfffend", "textend"),
-        # Clean text unchanged
-        ("normal text", "normal text"),
-        ("unicode: café naïve", "unicode: café naïve"),
-        # Edge cases
-        ("", ""),
-        (None, None),
-    ],
-)
-def test_sanitize_llm_output(input_text, expected):
-    assert sanitize_llm_output(input_text) == expected

hindsight-api-slim/tests/test_lmstudio_tool_choice.py

@@ -1,321 +0,0 @@
-"""
-Reproduce issue #520: Reflect fails with LM Studio due to unsupported tool_choice format.
-
-The reflect agent forces tool selection via named tool_choice dicts on the first few iterations:
-  {"type": "function", "function": {"name": "search_mental_models"}}
-
-LM Studio (and Ollama) reject this format with HTTP 400:
-  "Tool choice of type 'function' is not supported. Use 'auto', 'none', or 'required'."
-
-The fix should convert named tool_choice to "required" and filter the tools list
-to only the requested tool for providers that don't support named tool_choice.
-"""
-
-import json
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-from openai import APIStatusError
-
-from hindsight_api.engine.providers.openai_compatible_llm import OpenAICompatibleLLM
-
-# Reflect agent tools (subset matching what agent.py uses)
-REFLECT_TOOLS = [
-    {
-        "type": "function",
-        "function": {
-            "name": "search_mental_models",
-            "description": "Search consolidated mental models",
-            "parameters": {
-                "type": "object",
-                "properties": {"query": {"type": "string"}},
-                "required": ["query"],
-            },
-        },
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "search_observations",
-            "description": "Search raw observations",
-            "parameters": {
-                "type": "object",
-                "properties": {"query": {"type": "string"}},
-                "required": ["query"],
-            },
-        },
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "recall",
-            "description": "Recall semantic memories",
-            "parameters": {
-                "type": "object",
-                "properties": {"query": {"type": "string"}},
-                "required": ["query"],
-            },
-        },
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "done",
-            "description": "Finish and return the answer",
-            "parameters": {
-                "type": "object",
-                "properties": {"answer": {"type": "string"}},
-                "required": ["answer"],
-            },
-        },
-    },
-]
-
-
-def _make_lmstudio_llm() -> OpenAICompatibleLLM:
-    return OpenAICompatibleLLM(
-        provider="lmstudio",
-        api_key="local",
-        base_url="http://localhost:1234/v1",
-        model="openai/gpt-oss-20b",
-    )
-
-
-def _lmstudio_400_error(msg: str = "Tool choice of type 'function' is not supported. Use 'auto', 'none', or 'required'.") -> APIStatusError:
-    """Simulate the HTTP 400 LM Studio returns for unsupported tool_choice format."""
-    mock_response = MagicMock()
-    mock_response.status_code = 400
-    mock_response.headers = {}
-    return APIStatusError(
-        message=msg,
-        response=mock_response,
-        body={"error": {"message": msg, "type": "invalid_request_error"}},
-    )
-
-
-def _make_tool_call_response(tool_name: str, arguments: dict) -> MagicMock:
-    """Build a mock successful tool call response from the LLM API."""
-    mock_tc = MagicMock()
-    mock_tc.id = "call_abc123"
-    mock_tc.function.name = tool_name
-    mock_tc.function.arguments = json.dumps(arguments)
-
-    mock_response = MagicMock()
-    mock_response.usage.prompt_tokens = 120
-    mock_response.usage.completion_tokens = 40
-    mock_response.usage.total_tokens = 160
-    mock_response.choices[0].finish_reason = "tool_calls"
-    mock_response.choices[0].message.content = None
-    mock_response.choices[0].message.tool_calls = [mock_tc]
-    return mock_response
-
-
-class TestLMStudioNamedToolChoiceBug:
-    """
-    Reproduces issue #520.
-
-    The reflect agent (agent.py lines 546-555) sets tool_choice to a named dict
-    on the first iterations to force sequential retrieval:
-
-        iteration=0, has_mental_models=True  → {"type": "function", "function": {"name": "search_mental_models"}}
-        iteration=0, has_mental_models=False → {"type": "function", "function": {"name": "search_observations"}}
-        iteration=1, has_mental_models=True  → {"type": "function", "function": {"name": "search_observations"}}
-        iteration=1 or (2 with models)       → {"type": "function", "function": {"name": "recall"}}
-
-    LM Studio rejects these dict formats with HTTP 400.
-    """
-
-    @pytest.mark.asyncio
-    async def test_lmstudio_named_tool_choice_no_longer_causes_400(self):
-        """
-        Regression test for issue #520: named tool_choice dict is converted to
-        "required" + filtered tools before the API call, so LM Studio never
-        sees the unsupported format and the 400 error no longer occurs.
-        """
-        llm = _make_lmstudio_llm()
-        named_tool_choice = {"type": "function", "function": {"name": "search_mental_models"}}
-        success_response = _make_tool_call_response("search_mental_models", {"query": "user name"})
-
-        with patch.object(llm._client.chat.completions, "create", new_callable=AsyncMock) as mock_create:
-            mock_create.return_value = success_response
-
-            # Should succeed — no 400 because the dict is converted before sending
-            result = await llm.call_with_tools(
-                messages=[{"role": "user", "content": "What is the user's name?"}],
-                tools=REFLECT_TOOLS,
-                tool_choice=named_tool_choice,
-                max_retries=0,
-            )
-
-        assert len(result.tool_calls) == 1
-        assert result.tool_calls[0].name == "search_mental_models"
-
-        sent_kwargs = mock_create.call_args.kwargs
-        assert sent_kwargs["tool_choice"] == "required"
-        assert len(sent_kwargs["tools"]) == 1
-        assert sent_kwargs["tools"][0]["function"]["name"] == "search_mental_models"
-
-    @pytest.mark.asyncio
-    @pytest.mark.parametrize(
-        "forced_tool_name",
-        ["search_mental_models", "search_observations", "recall"],
-    )
-    async def test_all_reflect_forced_tools_fail_on_lmstudio(self, forced_tool_name: str):
-        """
-        Each named tool_choice the reflect agent uses on iterations 0-2 triggers
-        the same 400 error on LM Studio.
-        """
-        llm = _make_lmstudio_llm()
-        named_tool_choice = {"type": "function", "function": {"name": forced_tool_name}}
-
-        with patch.object(llm._client.chat.completions, "create", new_callable=AsyncMock) as mock_create:
-            mock_create.side_effect = _lmstudio_400_error()
-
-            with pytest.raises(APIStatusError) as exc_info:
-                await llm.call_with_tools(
-                    messages=[{"role": "user", "content": "Test query"}],
-                    tools=REFLECT_TOOLS,
-                    tool_choice=named_tool_choice,
-                    max_retries=0,
-                )
-
-            assert exc_info.value.status_code == 400
-
-    @pytest.mark.asyncio
-    async def test_lmstudio_string_tool_choice_works_fine(self):
-        """
-        String tool_choice values ("auto", "none", "required") ARE supported by LM Studio.
-        Only the dict format {"type": "function", "function": {"name": "..."}} fails.
-        This test confirms the control case works.
-        """
-        llm = _make_lmstudio_llm()
-        success_response = _make_tool_call_response("search_mental_models", {"query": "user name"})
-
-        with patch.object(llm._client.chat.completions, "create", new_callable=AsyncMock) as mock_create:
-            mock_create.return_value = success_response
-
-            result = await llm.call_with_tools(
-                messages=[{"role": "user", "content": "What is the user's name?"}],
-                tools=REFLECT_TOOLS,
-                tool_choice="required",  # string form — LM Studio accepts this
-                max_retries=0,
-            )
-
-        assert len(result.tool_calls) == 1
-        assert result.tool_calls[0].name == "search_mental_models"
-
-        # Confirm "required" was sent, not a dict
-        sent_kwargs = mock_create.call_args.kwargs
-        assert sent_kwargs["tool_choice"] == "required"
-
-
-class TestExpectedFixBehavior:
-    """
-    Tests that document the EXPECTED behavior after the fix is applied.
-
-    For lmstudio (and ollama) providers, when tool_choice is a named dict:
-      {"type": "function", "function": {"name": "search_mental_models"}}
-
-    The fix should:
-      1. Convert tool_choice to "required"
-      2. Filter tools to only the requested tool
-
-    These tests currently FAIL (because the fix is not yet implemented).
-    After the fix is applied, they should PASS.
-    """
-
-    @pytest.mark.asyncio
-    async def test_fix_converts_named_tool_choice_to_required(self):
-        """
-        After fix: named tool_choice dict is converted to "required" for lmstudio.
-        The API receives tool_choice="required" instead of the unsupported dict.
-        """
-        llm = _make_lmstudio_llm()
-        named_tool_choice = {"type": "function", "function": {"name": "search_mental_models"}}
-        success_response = _make_tool_call_response("search_mental_models", {"query": "user name"})
-
-        with patch.object(llm._client.chat.completions, "create", new_callable=AsyncMock) as mock_create:
-            mock_create.return_value = success_response
-
-            result = await llm.call_with_tools(
-                messages=[{"role": "user", "content": "What is the user's name?"}],
-                tools=REFLECT_TOOLS,
-                tool_choice=named_tool_choice,
-                max_retries=0,
-            )
-
-        assert len(result.tool_calls) == 1
-        assert result.tool_calls[0].name == "search_mental_models"
-
-        sent_kwargs = mock_create.call_args.kwargs
-        # Fix: dict was converted to "required"
-        assert sent_kwargs["tool_choice"] == "required", (
-            f"Expected tool_choice='required', got {sent_kwargs['tool_choice']!r}"
-        )
-        # Fix: tools filtered to just the requested one
-        assert len(sent_kwargs["tools"]) == 1
-        assert sent_kwargs["tools"][0]["function"]["name"] == "search_mental_models"
-
-    @pytest.mark.asyncio
-    @pytest.mark.parametrize(
-        "forced_tool_name",
-        ["search_mental_models", "search_observations", "recall"],
-    )
-    async def test_fix_filters_tools_to_requested_tool(self, forced_tool_name: str):
-        """
-        After fix: tools list is filtered to only the forced tool so the model
-        can only call that one tool (equivalent to the named tool_choice behavior).
-        """
-        llm = _make_lmstudio_llm()
-        named_tool_choice = {"type": "function", "function": {"name": forced_tool_name}}
-        success_response = _make_tool_call_response(forced_tool_name, {"query": "test"})
-
-        with patch.object(llm._client.chat.completions, "create", new_callable=AsyncMock) as mock_create:
-            mock_create.return_value = success_response
-
-            await llm.call_with_tools(
-                messages=[{"role": "user", "content": "Test query"}],
-                tools=REFLECT_TOOLS,
-                tool_choice=named_tool_choice,
-                max_retries=0,
-            )
-
-        sent_kwargs = mock_create.call_args.kwargs
-        assert sent_kwargs["tool_choice"] == "required"
-        assert len(sent_kwargs["tools"]) == 1
-        assert sent_kwargs["tools"][0]["function"]["name"] == forced_tool_name
-
-    @pytest.mark.asyncio
-    async def test_fix_also_applies_to_openai_provider(self):
-        """
-        The fix is generalized: all providers convert named tool_choice to
-        "required" + filtered tools.  OpenAI natively supports the dict format
-        too, so the behaviour is semantically identical either way.
-        """
-        from hindsight_api.engine.providers.openai_compatible_llm import OpenAICompatibleLLM
-
-        openai_llm = OpenAICompatibleLLM(
-            provider="openai",
-            api_key="sk-test",
-            base_url="",
-            model="gpt-4o-mini",
-        )
-
-        named_tool_choice = {"type": "function", "function": {"name": "search_mental_models"}}
-        success_response = _make_tool_call_response("search_mental_models", {"query": "test"})
-
-        with patch.object(openai_llm._client.chat.completions, "create", new_callable=AsyncMock) as mock_create:
-            mock_create.return_value = success_response
-
-            await openai_llm.call_with_tools(
-                messages=[{"role": "user", "content": "Test"}],
-                tools=REFLECT_TOOLS,
-                tool_choice=named_tool_choice,
-                max_retries=0,
-            )
-
-        sent_kwargs = mock_create.call_args.kwargs
-        # Generalized fix applies to OpenAI too
-        assert sent_kwargs["tool_choice"] == "required"
-        assert len(sent_kwargs["tools"]) == 1
-        assert sent_kwargs["tools"][0]["function"]["name"] == "search_mental_models"

hindsight-api-slim/tests/test_migration_backsweep.py

@@ -1,154 +0,0 @@
-"""Tests for migration g7h8i9j0k1l2 (backsweep orphaned memory_units).
-
-Uses a dedicated pg0 instance (port 5562) so the test can control exactly
-which migrations have run before inserting the orphan seed data.
-"""
-
-import asyncio
-import uuid
-from pathlib import Path
-
-import pytest
-from alembic import command
-from alembic.config import Config
-from sqlalchemy import create_engine, text
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-_SCRIPT_LOCATION = str(Path(__file__).parent.parent / "hindsight_api" / "alembic")
-
-
-def _alembic_cfg(db_url: str) -> Config:
-    cfg = Config()
-    cfg.set_main_option("script_location", _SCRIPT_LOCATION)
-    cfg.set_main_option("sqlalchemy.url", db_url)
-    cfg.set_main_option("prepend_sys_path", ".")
-    cfg.set_main_option("path_separator", "os")
-    return cfg
-
-
-def _upgrade(db_url: str, revision: str) -> None:
-    command.upgrade(_alembic_cfg(db_url), revision)
-
-
-# ---------------------------------------------------------------------------
-# Fixture: fresh database at the revision just before the backsweep
-# ---------------------------------------------------------------------------
-
-@pytest.fixture(scope="module")
-def pre_backsweep_db_url():
-    """
-    Spin up a dedicated pg0 instance and run all migrations up to (but not
-    including) the backsweep revision so each test can seed orphan data and
-    then apply the backsweep itself.
-    """
-    from hindsight_api.pg0 import EmbeddedPostgres
-
-    pg0 = EmbeddedPostgres(name="hindsight-backsweep-test", port=5562)
-    loop = asyncio.new_event_loop()
-    try:
-        url = loop.run_until_complete(pg0.ensure_running())
-    finally:
-        loop.close()
-
-    # Migrate up to the revision just before the backsweep.
-    _upgrade(url, "f6g7h8i9j0k1")
-    return url
-
-
-# ---------------------------------------------------------------------------
-# The test
-# ---------------------------------------------------------------------------
-
-def test_backsweep_removes_orphans_and_preserves_legit_rows(pre_backsweep_db_url):
-    """
-    Seed four kinds of rows then apply the backsweep migration and verify:
-
-    Rows that MUST be deleted
-    ─────────────────────────
-    A. Any fact_type, bank_id missing from banks
-       → Pass 1 deletes these regardless of fact_type or source links.
-
-    B. observation, bank exists, but ALL source_memory_ids are gone
-       → Pass 2 deletes these.
-
-    Rows that MUST survive
-    ──────────────────────
-    C. observation, bank exists, at least ONE source_memory_id still live
-       → Pass 2 must not touch these.
-
-    D. Non-observation (world), bank exists, no sources (not relevant)
-       → Pass 1 must not touch these (bank exists).
-    """
-    db_url = pre_backsweep_db_url
-    engine = create_engine(db_url)
-
-    alive_bank = f"bank_{uuid.uuid4().hex[:8]}"
-    ghost_bank = f"bank_{uuid.uuid4().hex[:8]}"  # never inserted into banks
-
-    # UUIDs for memory units
-    id_pass1_world = uuid.uuid4()       # A: world unit, ghost bank
-    id_pass1_obs = uuid.uuid4()         # A: observation, ghost bank
-    id_pass2_obs = uuid.uuid4()         # B: observation, all sources gone
-    id_keep_obs = uuid.uuid4()          # C: observation with one live source
-    id_keep_world = uuid.uuid4()        # D: world unit, alive bank
-    id_live_source = uuid.uuid4()       # live source for C
-
-    with engine.connect() as conn:
-        # --- banks ---
-        conn.execute(text("INSERT INTO banks (bank_id) VALUES (:b)"), {"b": alive_bank})
-
-        # --- seed memory_units ---
-        def insert_mu(uid, bank, fact_type, sources=None):
-            src_arr = "{" + ",".join(str(s) for s in (sources or [])) + "}"
-            conn.execute(
-                text(
-                    """
-                    INSERT INTO memory_units
-                        (id, bank_id, text, fact_type, source_memory_ids)
-                    VALUES
-                        (:id, :bank, :text, :ft, CAST(:src AS uuid[]))
-                    """
-                ),
-                {"id": uid, "bank": bank, "text": "test", "ft": fact_type, "src": src_arr},
-            )
-
-        # A: ghost-bank rows (Pass 1 targets)
-        insert_mu(id_pass1_world, ghost_bank, "world")
-        insert_mu(id_pass1_obs, ghost_bank, "observation", sources=[uuid.uuid4()])
-
-        # B: observation with all-dead sources (Pass 2 target)
-        insert_mu(id_pass2_obs, alive_bank, "observation", sources=[uuid.uuid4(), uuid.uuid4()])
-
-        # C: observation with one live source (must survive)
-        insert_mu(id_live_source, alive_bank, "world")
-        insert_mu(id_keep_obs, alive_bank, "observation", sources=[id_live_source, uuid.uuid4()])
-
-        # D: world unit in alive bank (must survive)
-        insert_mu(id_keep_world, alive_bank, "world")
-
-        conn.commit()
-
-    # --- apply the backsweep ---
-    _upgrade(db_url, "g7h8i9j0k1l2")
-
-    # --- verify ---
-    with engine.connect() as conn:
-        def exists(uid):
-            return conn.execute(
-                text("SELECT 1 FROM memory_units WHERE id = :id"), {"id": uid}
-            ).fetchone() is not None
-
-        # Must be gone
-        assert not exists(id_pass1_world), "Pass 1: world unit with ghost bank should be deleted"
-        assert not exists(id_pass1_obs), "Pass 1: observation with ghost bank should be deleted"
-        assert not exists(id_pass2_obs), "Pass 2: observation with all-dead sources should be deleted"
-
-        # Must survive
-        assert exists(id_keep_obs), "observation with a live source must not be deleted"
-        assert exists(id_keep_world), "world unit in alive bank must not be deleted"
-        assert exists(id_live_source), "live source memory unit must not be deleted"
-
-    engine.dispose()

hindsight-api-slim/tests/test_migrations_thread_safety.py

@@ -1,48 +0,0 @@
-import threading
-import time
-
-from hindsight_api import migrations
-
-
-def test_run_migrations_internal_serializes_alembic_upgrade(monkeypatch):
-    max_concurrent_upgrades = 0
-    active_upgrades = 0
-    active_lock = threading.Lock()
-    start_barrier = threading.Barrier(2)
-
-    def fake_upgrade(_cfg, _revision):
-        nonlocal max_concurrent_upgrades, active_upgrades
-        with active_lock:
-            active_upgrades += 1
-            max_concurrent_upgrades = max(max_concurrent_upgrades, active_upgrades)
-        time.sleep(0.05)
-        with active_lock:
-            active_upgrades -= 1
-
-    monkeypatch.setattr(migrations.command, "upgrade", fake_upgrade)
-
-    errors = []
-
-    def run_in_thread(schema):
-        try:
-            start_barrier.wait()
-            migrations._run_migrations_internal(
-                "postgresql://user:pass@localhost/db",
-                "/tmp/alembic",
-                schema=schema,
-            )
-        except Exception as exc:  # pragma: no cover - diagnostic path
-            errors.append(exc)
-
-    threads = [
-        threading.Thread(target=run_in_thread, args=("tenant_alpha",)),
-        threading.Thread(target=run_in_thread, args=("tenant_beta",)),
-    ]
-
-    for thread in threads:
-        thread.start()
-    for thread in threads:
-        thread.join()
-
-    assert not errors
-    assert max_concurrent_upgrades == 1

hindsight-api-slim/tests/test_none_llm_provider.py

@@ -1,232 +0,0 @@
-"""
-Tests for the 'none' LLM provider mode.
-
-Verifies that when HINDSIGHT_API_LLM_PROVIDER=none:
-- Retain defaults to chunks mode (no LLM calls)
-- Reflect returns 400
-- Mental model refresh returns 400
-- Consolidation is skipped
-- NoneLLM.call() raises LLMNotAvailableError
-"""
-
-import os
-from datetime import datetime, timezone
-
-import httpx
-import pytest
-import pytest_asyncio
-
-from hindsight_api import LLMConfig, LocalSTEmbeddings, MemoryEngine, RequestContext
-from hindsight_api.api import create_app
-from hindsight_api.engine.cross_encoder import LocalSTCrossEncoder
-from hindsight_api.engine.memory_engine import Budget
-from hindsight_api.engine.providers.none_llm import LLMNotAvailableError, NoneLLM
-from hindsight_api.engine.query_analyzer import DateparserQueryAnalyzer
-from hindsight_api.engine.task_backend import SyncTaskBackend
-
-
-@pytest.fixture(scope="function")
-def request_context():
-    return RequestContext()
-
-
-@pytest_asyncio.fixture(scope="function")
-async def none_memory(pg0_db_url, embeddings, cross_encoder, query_analyzer):
-    """MemoryEngine with provider=none."""
-    mem = MemoryEngine(
-        db_url=pg0_db_url,
-        memory_llm_provider="none",
-        memory_llm_api_key=None,
-        memory_llm_model="none",
-        embeddings=embeddings,
-        cross_encoder=cross_encoder,
-        query_analyzer=query_analyzer,
-        pool_min_size=1,
-        pool_max_size=5,
-        run_migrations=False,
-        task_backend=SyncTaskBackend(),
-    )
-    await mem.initialize()
-    yield mem
-    try:
-        if mem._pool and not mem._pool._closing:
-            await mem.close()
-    except Exception:
-        pass
-
-
-@pytest_asyncio.fixture
-async def none_api_client(none_memory):
-    """HTTP test client backed by a none-provider MemoryEngine."""
-    app = create_app(none_memory, initialize_memory=False)
-    transport = httpx.ASGITransport(app=app)
-    async with httpx.AsyncClient(transport=transport, base_url="http://test") as client:
-        yield client
-
-
-# -- Unit tests for NoneLLM ---------------------------------------------------
-
-
-@pytest.mark.asyncio
-async def test_none_llm_call_raises():
-    """NoneLLM.call() should raise LLMNotAvailableError."""
-    llm = NoneLLM(provider="none", api_key="", base_url="", model="none")
-    with pytest.raises(LLMNotAvailableError):
-        await llm.call(messages=[{"role": "user", "content": "hello"}])
-
-
-@pytest.mark.asyncio
-async def test_none_llm_call_with_tools_raises():
-    """NoneLLM.call_with_tools() should raise LLMNotAvailableError."""
-    llm = NoneLLM(provider="none", api_key="", base_url="", model="none")
-    with pytest.raises(LLMNotAvailableError):
-        await llm.call_with_tools(
-            messages=[{"role": "user", "content": "hello"}],
-            tools=[{"type": "function", "function": {"name": "test", "parameters": {}}}],
-        )
-
-
-@pytest.mark.asyncio
-async def test_none_llm_verify_connection_succeeds():
-    """NoneLLM.verify_connection() should be a no-op."""
-    llm = NoneLLM(provider="none", api_key="", base_url="", model="none")
-    await llm.verify_connection()  # Should not raise
-
-
-# -- Config validation tests ---------------------------------------------------
-
-
-def test_config_forces_chunks_mode():
-    """When provider is 'none', config.validate() forces retain_extraction_mode='chunks'."""
-    from hindsight_api.config import HindsightConfig
-
-    config = HindsightConfig.from_env()
-    # Override to none for test
-    config.llm_provider = "none"
-    config.retain_extraction_mode = "facts"
-    config.enable_observations = True
-    config.validate()
-
-    assert config.retain_extraction_mode == "chunks"
-    assert config.enable_observations is False
-
-
-# -- Integration tests (require database) -------------------------------------
-
-
-@pytest.mark.asyncio
-async def test_retain_works_with_none_provider(none_memory, request_context):
-    """Retain should work with provider=none, storing chunks without LLM calls."""
-    bank_id = f"test_none_retain_{datetime.now(timezone.utc).timestamp()}"
-
-    unit_ids = await none_memory.retain_async(
-        bank_id=bank_id,
-        content="Alice is a software engineer. She works at TechCorp and loves Python.",
-        context="team info",
-        request_context=request_context,
-    )
-
-    assert len(unit_ids) > 0, "Should store chunks even without an LLM"
-
-
-@pytest.mark.asyncio
-async def test_recall_works_with_none_provider(none_memory, request_context):
-    """Recall should work with provider=none (uses embeddings, not LLM)."""
-    bank_id = f"test_none_recall_{datetime.now(timezone.utc).timestamp()}"
-
-    await none_memory.retain_async(
-        bank_id=bank_id,
-        content="Alice is a software engineer at TechCorp.",
-        context="team info",
-        request_context=request_context,
-    )
-
-    result = await none_memory.recall_async(
-        bank_id=bank_id,
-        query="Who is Alice?",
-        budget=Budget.LOW,
-        request_context=request_context,
-    )
-
-    assert len(result.results) > 0, "Should find results via semantic search"
-
-
-@pytest.mark.asyncio
-async def test_reflect_raises_with_none_provider(none_memory, request_context):
-    """Reflect should raise LLMNotAvailableError with provider=none."""
-    bank_id = f"test_none_reflect_{datetime.now(timezone.utc).timestamp()}"
-
-    with pytest.raises(LLMNotAvailableError):
-        await none_memory.reflect_async(
-            bank_id=bank_id,
-            query="What do you know?",
-            request_context=request_context,
-        )
-
-
-@pytest.mark.asyncio
-async def test_consolidation_skipped_with_none_provider(none_memory, request_context):
-    """Consolidation handler should skip when provider=none."""
-    result = await none_memory._handle_consolidation({"bank_id": "test_bank"})
-    assert result["skipped"] is True
-    assert result["memories_processed"] == 0
-
-
-@pytest.mark.asyncio
-async def test_mental_model_refresh_raises_with_none_provider(none_memory, request_context):
-    """Mental model refresh should raise LLMNotAvailableError with provider=none."""
-    bank_id = f"test_none_mm_{datetime.now(timezone.utc).timestamp()}"
-
-    with pytest.raises(LLMNotAvailableError):
-        await none_memory.submit_async_refresh_mental_model(
-            bank_id=bank_id,
-            mental_model_id="fake-id",
-            request_context=request_context,
-        )
-
-
-# -- HTTP API tests -----------------------------------------------------------
-
-
-@pytest.mark.asyncio
-async def test_http_reflect_returns_400(none_api_client):
-    """Reflect endpoint should return 400 when LLM provider is none."""
-    bank_id = f"test_none_http_{datetime.now(timezone.utc).timestamp()}"
-
-    response = await none_api_client.post(
-        f"/v1/default/banks/{bank_id}/reflect",
-        json={"query": "What do you know?"},
-    )
-    assert response.status_code == 400
-    assert "none" in response.json()["detail"].lower()
-
-
-@pytest.mark.asyncio
-async def test_http_retain_works(none_api_client):
-    """Retain endpoint should work with provider=none (chunks mode)."""
-    bank_id = f"test_none_http_retain_{datetime.now(timezone.utc).timestamp()}"
-
-    response = await none_api_client.post(
-        f"/v1/default/banks/{bank_id}/memories",
-        json={"items": [{"content": "Hello world", "context": "test"}]},
-    )
-    assert response.status_code == 200
-
-
-@pytest.mark.asyncio
-async def test_http_recall_works(none_api_client):
-    """Recall endpoint should work with provider=none."""
-    bank_id = f"test_none_http_recall_{datetime.now(timezone.utc).timestamp()}"
-
-    # Retain first
-    await none_api_client.post(
-        f"/v1/default/banks/{bank_id}/memories",
-        json={"items": [{"content": "Alice is an engineer.", "context": "test"}]},
-    )
-
-    # Recall
-    response = await none_api_client.post(
-        f"/v1/default/banks/{bank_id}/memories/recall",
-        json={"query": "Alice"},
-    )
-    assert response.status_code == 200

hindsight-api-slim/tests/test_observation_invalidation.py

@@ -1,735 +0,0 @@
-"""
-Tests for observation invalidation when source memories are deleted.
-
-These tests verify that:
-1. Observations are deleted (not just updated) when their source memories are removed
-2. Remaining source memories are reset for re-consolidation (consolidated_at=NULL)
-3. The clear_observations_for_memory method correctly clears observations and
-   resets the target memory itself for re-consolidation
-4. delete_bank(fact_type=...) also cleans up affected observations
-"""
-import uuid
-from unittest.mock import AsyncMock, patch
-
-import pytest
-
-from hindsight_api import RequestContext
-from hindsight_api.engine.memory_engine import MemoryEngine
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-async def _insert_memory(conn, bank_id: str, text: str, fact_type: str = "experience") -> uuid.UUID:
-    """Insert a memory unit directly, bypassing LLM retain pipeline."""
-    mem_id = uuid.uuid4()
-    await conn.execute(
-        """
-        INSERT INTO memory_units (id, bank_id, text, fact_type, event_date, created_at, updated_at, consolidated_at)
-        VALUES ($1, $2, $3, $4, NOW(), NOW(), NOW(), NOW())
-        """,
-        mem_id,
-        bank_id,
-        text,
-        fact_type,
-    )
-    return mem_id
-
-
-async def _insert_observation(
-    conn, bank_id: str, text: str, source_memory_ids: list[uuid.UUID]
-) -> uuid.UUID:
-    """Insert an observation unit directly."""
-    obs_id = uuid.uuid4()
-    await conn.execute(
-        """
-        INSERT INTO memory_units (
-            id, bank_id, text, fact_type, event_date, source_memory_ids, proof_count, created_at, updated_at
-        ) VALUES ($1, $2, $3, 'observation', NOW(), $4, $5, NOW(), NOW())
-        """,
-        obs_id,
-        bank_id,
-        text,
-        source_memory_ids,
-        len(source_memory_ids),
-    )
-    return obs_id
-
-
-async def _get_observation_ids(conn, bank_id: str) -> list[str]:
-    rows = await conn.fetch(
-        "SELECT id FROM memory_units WHERE bank_id = $1 AND fact_type = 'observation'",
-        bank_id,
-    )
-    return [str(r["id"]) for r in rows]
-
-
-async def _get_consolidated_at(conn, memory_id: uuid.UUID):
-    return await conn.fetchval(
-        "SELECT consolidated_at FROM memory_units WHERE id = $1",
-        memory_id,
-    )
-
-
-async def _ensure_bank(memory: MemoryEngine, bank_id: str, request_context: RequestContext):
-    await memory.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-
-# ---------------------------------------------------------------------------
-# Tests: delete_memory_unit
-# ---------------------------------------------------------------------------
-
-class TestDeleteMemoryUnitObservationCleanup:
-
-    @pytest.mark.asyncio
-    async def test_deleting_source_memory_removes_observation(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Deleting a source memory removes observations derived from it."""
-        bank_id = f"test-invalidate-del-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            m1 = await _insert_memory(conn, bank_id, "Alice loves hiking.")
-            m2 = await _insert_memory(conn, bank_id, "Alice goes hiking every weekend.")
-            obs_id = await _insert_observation(conn, bank_id, "Alice enjoys hiking regularly.", [m1, m2])
-
-        await memory.delete_memory_unit(str(m1), request_context=request_context)
-
-        async with pool.acquire() as conn:
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(obs_id) not in obs_ids, "Observation should have been deleted"
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_deleting_source_memory_resets_remaining_source_consolidated_at(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """After deleting a source memory, remaining source memories are reset for re-consolidation."""
-        bank_id = f"test-invalidate-reset-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            m1 = await _insert_memory(conn, bank_id, "Alice loves hiking.")
-            m2 = await _insert_memory(conn, bank_id, "Alice goes hiking every weekend.")
-            await _insert_observation(conn, bank_id, "Alice enjoys hiking regularly.", [m1, m2])
-
-            # Verify m2 starts with consolidated_at set
-            assert await _get_consolidated_at(conn, m2) is not None
-
-        # Patch out consolidation so it doesn't re-set consolidated_at before we can check it
-        with patch.object(memory, "submit_async_consolidation", new=AsyncMock()):
-            await memory.delete_memory_unit(str(m1), request_context=request_context)
-
-        async with pool.acquire() as conn:
-            # m2 should have consolidated_at reset to NULL
-            consolidated_at = await _get_consolidated_at(conn, m2)
-            assert consolidated_at is None, "Remaining source memory should be reset for re-consolidation"
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_deleting_non_source_memory_leaves_observations_intact(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Deleting a memory that is not a source of any observation leaves observations unchanged."""
-        bank_id = f"test-invalidate-noop-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            m1 = await _insert_memory(conn, bank_id, "Alice loves hiking.")
-            m2 = await _insert_memory(conn, bank_id, "Alice goes hiking every weekend.")
-            unrelated = await _insert_memory(conn, bank_id, "Bob likes cycling.")
-            obs_id = await _insert_observation(conn, bank_id, "Alice enjoys hiking regularly.", [m1, m2])
-
-        await memory.delete_memory_unit(str(unrelated), request_context=request_context)
-
-        async with pool.acquire() as conn:
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(obs_id) in obs_ids, "Observation should remain untouched"
-            # m1 and m2 should still be consolidated
-            assert await _get_consolidated_at(conn, m1) is not None
-            assert await _get_consolidated_at(conn, m2) is not None
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_deleting_sole_source_memory_removes_observation_no_remaining_reset(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """When an observation has only one source and it's deleted, observation is removed with no remaining memories to reset."""
-        bank_id = f"test-invalidate-sole-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            m1 = await _insert_memory(conn, bank_id, "Alice loves hiking.")
-            obs_id = await _insert_observation(conn, bank_id, "Alice enjoys hiking.", [m1])
-
-        await memory.delete_memory_unit(str(m1), request_context=request_context)
-
-        async with pool.acquire() as conn:
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(obs_id) not in obs_ids, "Observation should have been deleted"
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_deleting_observation_type_memory_does_not_trigger_invalidation(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Deleting a memory with fact_type='observation' directly does not trigger invalidation logic."""
-        bank_id = f"test-invalidate-obstype-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            m1 = await _insert_memory(conn, bank_id, "Alice loves hiking.")
-            obs_id = await _insert_observation(conn, bank_id, "Alice enjoys hiking.", [m1])
-
-        # Delete the observation directly (not the source memory)
-        await memory.delete_memory_unit(str(obs_id), request_context=request_context)
-
-        async with pool.acquire() as conn:
-            # Source memory should still be consolidated (not reset)
-            assert await _get_consolidated_at(conn, m1) is not None
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(obs_id) not in obs_ids
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-# ---------------------------------------------------------------------------
-# Tests: delete_document
-# ---------------------------------------------------------------------------
-
-class TestDeleteDocumentObservationCleanup:
-
-    @pytest.mark.asyncio
-    async def test_deleting_document_removes_observations(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Deleting a document removes observations derived from its memory units."""
-        bank_id = f"test-invalidate-doc-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-
-        # Create a document and attach memories to it
-        async with pool.acquire() as conn:
-            doc_id = str(uuid.uuid4())  # documents.id is TEXT
-            await conn.execute(
-                """
-                INSERT INTO documents (id, bank_id, original_text, content_hash, created_at, updated_at)
-                VALUES ($1, $2, 'some doc', 'hash123', NOW(), NOW())
-                """,
-                doc_id,
-                bank_id,
-            )
-            m1 = uuid.uuid4()
-            m2 = uuid.uuid4()
-            for mem_id, text in [(m1, "Alice loves hiking."), (m2, "Alice goes hiking every weekend.")]:
-                await conn.execute(
-                    """
-                    INSERT INTO memory_units (id, bank_id, text, fact_type, event_date, document_id, created_at, updated_at, consolidated_at)
-                    VALUES ($1, $2, $3, 'experience', NOW(), $4, NOW(), NOW(), NOW())
-                    """,
-                    mem_id,
-                    bank_id,
-                    text,
-                    doc_id,
-                )
-
-            # Standalone memory (not in document)
-            m3 = await _insert_memory(conn, bank_id, "Alice is an avid outdoor person.")
-
-            # Observation referencing both doc memories and the standalone memory
-            obs_id = await _insert_observation(
-                conn, bank_id, "Alice enjoys outdoor activities.", [m1, m2, m3]
-            )
-
-        # Patch out consolidation so it doesn't re-set consolidated_at before we can check it
-        with patch.object(memory, "submit_async_consolidation", new=AsyncMock()):
-            await memory.delete_document(str(doc_id), bank_id, request_context=request_context)
-
-        async with pool.acquire() as conn:
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(obs_id) not in obs_ids, "Observation should have been deleted"
-
-            # m3 (remaining source) should be reset for re-consolidation
-            consolidated_at = await _get_consolidated_at(conn, m3)
-            assert consolidated_at is None, "Remaining source memory should be reset"
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-# ---------------------------------------------------------------------------
-# Tests: delete_bank with fact_type filter
-# ---------------------------------------------------------------------------
-
-class TestDeleteBankByTypeObservationCleanup:
-
-    @pytest.mark.asyncio
-    async def test_clearing_experience_memories_removes_affected_observations(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Clearing all experience memories removes observations sourced from them."""
-        bank_id = f"test-invalidate-banktype-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            exp1 = await _insert_memory(conn, bank_id, "Alice went hiking last week.", "experience")
-            world1 = await _insert_memory(conn, bank_id, "Alice is a hiker.", "world")
-            obs_id = await _insert_observation(
-                conn, bank_id, "Alice is a regular hiker.", [exp1, world1]
-            )
-
-        # Patch out consolidation so it doesn't re-set consolidated_at before we can check it
-        with patch.object(memory, "submit_async_consolidation", new=AsyncMock()):
-            await memory.delete_bank(bank_id, fact_type="experience", request_context=request_context)
-
-        async with pool.acquire() as conn:
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(obs_id) not in obs_ids, "Observation should have been deleted"
-
-            # world1 (remaining source) should be reset for re-consolidation
-            consolidated_at = await _get_consolidated_at(conn, world1)
-            assert consolidated_at is None, "World memory should be reset for re-consolidation"
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_clearing_unrelated_type_leaves_observations_intact(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Clearing memories of a type that is not a source of any observation leaves observations untouched."""
-        bank_id = f"test-invalidate-banktype-noop-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            world1 = await _insert_memory(conn, bank_id, "Alice is a hiker.", "world")
-            obs_id = await _insert_observation(conn, bank_id, "Alice is a regular hiker.", [world1])
-
-        # Deleting 'experience' type should not affect observations sourced only from 'world'
-        await memory.delete_bank(bank_id, fact_type="experience", request_context=request_context)
-
-        async with pool.acquire() as conn:
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(obs_id) in obs_ids, "Observation should remain untouched"
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-# ---------------------------------------------------------------------------
-# Tests: clear_observations_for_memory
-# ---------------------------------------------------------------------------
-
-class TestClearObservationsForMemory:
-
-    @pytest.mark.asyncio
-    async def test_clears_observations_and_resets_all_source_memories(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Clearing observations for a memory deletes them and resets all related source memories."""
-        bank_id = f"test-clear-obs-mem-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            m1 = await _insert_memory(conn, bank_id, "Alice loves hiking.")
-            m2 = await _insert_memory(conn, bank_id, "Alice hikes every weekend.")
-            obs_id = await _insert_observation(conn, bank_id, "Alice is an avid hiker.", [m1, m2])
-
-        # Patch out consolidation so it doesn't re-set consolidated_at before we can check it
-        with patch.object(memory, "submit_async_consolidation", new=AsyncMock()):
-            result = await memory.clear_observations_for_memory(
-                bank_id, str(m1), request_context=request_context
-            )
-
-        assert result["deleted_count"] == 1
-
-        async with pool.acquire() as conn:
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(obs_id) not in obs_ids, "Observation should be deleted"
-
-            # Both m1 (target) and m2 (remaining source) should be reset
-            assert await _get_consolidated_at(conn, m1) is None, "Target memory should be reset"
-            assert await _get_consolidated_at(conn, m2) is None, "Remaining source should be reset"
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_no_observations_returns_zero(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Returns 0 when the memory has no associated observations."""
-        bank_id = f"test-clear-obs-noop-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            m1 = await _insert_memory(conn, bank_id, "Alice loves hiking.")
-
-        result = await memory.clear_observations_for_memory(
-            bank_id, str(m1), request_context=request_context
-        )
-
-        assert result["deleted_count"] == 0
-
-        async with pool.acquire() as conn:
-            # Memory should still be consolidated (no observations were cleared)
-            assert await _get_consolidated_at(conn, m1) is not None
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_only_clears_observations_referencing_target_memory(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Clearing observations for m1 does not affect observations that only reference m2."""
-        bank_id = f"test-clear-obs-selective-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            m1 = await _insert_memory(conn, bank_id, "Alice loves hiking.")
-            m2 = await _insert_memory(conn, bank_id, "Alice hikes every weekend.")
-            m3 = await _insert_memory(conn, bank_id, "Alice climbed a mountain.")
-
-            obs1_id = await _insert_observation(conn, bank_id, "Alice is an avid hiker.", [m1, m2])
-            obs2_id = await _insert_observation(conn, bank_id, "Alice is a mountaineer.", [m3])
-
-        result = await memory.clear_observations_for_memory(
-            bank_id, str(m1), request_context=request_context
-        )
-
-        assert result["deleted_count"] == 1
-
-        async with pool.acquire() as conn:
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(obs1_id) not in obs_ids, "obs1 (references m1) should be deleted"
-            assert str(obs2_id) in obs_ids, "obs2 (does not reference m1) should remain"
-
-            # m3 should still be consolidated
-            assert await _get_consolidated_at(conn, m3) is not None
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_multiple_observations_for_same_memory_all_cleared(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """All observations referencing the target memory are cleared in one call."""
-        bank_id = f"test-clear-obs-multi-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            m1 = await _insert_memory(conn, bank_id, "Alice loves hiking.")
-            m2 = await _insert_memory(conn, bank_id, "Alice hikes every weekend.")
-
-            obs1_id = await _insert_observation(conn, bank_id, "Alice hikes often.", [m1])
-            obs2_id = await _insert_observation(conn, bank_id, "Alice is outdoorsy.", [m1, m2])
-
-        # Patch out consolidation so it doesn't re-set consolidated_at before we can check it
-        with patch.object(memory, "submit_async_consolidation", new=AsyncMock()):
-            result = await memory.clear_observations_for_memory(
-                bank_id, str(m1), request_context=request_context
-            )
-
-        assert result["deleted_count"] == 2
-
-        async with pool.acquire() as conn:
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(obs1_id) not in obs_ids
-            assert str(obs2_id) not in obs_ids
-
-            # m1 and m2 should both be reset
-            assert await _get_consolidated_at(conn, m1) is None
-            assert await _get_consolidated_at(conn, m2) is None
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-# ---------------------------------------------------------------------------
-# Tests: update_document
-# ---------------------------------------------------------------------------
-
-
-async def _insert_document_with_memories(
-    conn, bank_id: str, doc_id: str, memories: list[tuple[str, str]]
-) -> list[uuid.UUID]:
-    """Insert a document and attach memory units to it. Returns list of memory UUIDs."""
-    await conn.execute(
-        """
-        INSERT INTO documents (id, bank_id, original_text, content_hash, created_at, updated_at)
-        VALUES ($1, $2, 'some doc', 'hash123', NOW(), NOW())
-        """,
-        doc_id,
-        bank_id,
-    )
-    mem_ids = []
-    for text, fact_type in memories:
-        mem_id = uuid.uuid4()
-        await conn.execute(
-            """
-            INSERT INTO memory_units (id, bank_id, text, fact_type, event_date, document_id, created_at, updated_at, consolidated_at)
-            VALUES ($1, $2, $3, $4, NOW(), $5, NOW(), NOW(), NOW())
-            """,
-            mem_id,
-            bank_id,
-            text,
-            fact_type,
-            doc_id,
-        )
-        mem_ids.append(mem_id)
-    return mem_ids
-
-
-class TestUpdateDocumentTagsObservationCleanup:
-
-    @pytest.mark.asyncio
-    async def test_update_tags_returns_updated_document(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """update_document returns the updated document with new tags."""
-        bank_id = f"test-tag-update-basic-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            doc_id = f"doc-{uuid.uuid4().hex[:8]}"
-            await _insert_document_with_memories(conn, bank_id, doc_id, [("Alice loves hiking.", "experience")])
-
-        result = await memory.update_document(
-            doc_id, bank_id, tags=["new-tag"], request_context=request_context
-        )
-
-        assert result is True
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_update_tags_returns_none_for_missing_document(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """update_document returns False when document does not exist."""
-        bank_id = f"test-tag-update-missing-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        result = await memory.update_document(
-            "nonexistent-doc", bank_id, tags=["tag"], request_context=request_context
-        )
-
-        assert result is False
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_update_tags_propagates_to_memory_units(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Changing document tags also updates all associated memory unit tags."""
-        bank_id = f"test-tag-update-propagate-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            doc_id = f"doc-{uuid.uuid4().hex[:8]}"
-            mem_ids = await _insert_document_with_memories(
-                conn, bank_id, doc_id, [("Alice loves hiking.", "experience"), ("Alice hikes weekly.", "world")]
-            )
-
-        with patch.object(memory, "submit_async_consolidation", new=AsyncMock()):
-            await memory.update_document(
-                doc_id, bank_id, tags=["new-tag"], request_context=request_context
-            )
-
-        async with pool.acquire() as conn:
-            for mem_id in mem_ids:
-                tags = await conn.fetchval(
-                    "SELECT tags FROM memory_units WHERE id = $1", mem_id
-                )
-                assert list(tags) == ["new-tag"], f"Memory unit {mem_id} should have updated tags"
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_update_tags_invalidates_observations(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Observations referencing the document's memory units are deleted on tag change."""
-        bank_id = f"test-tag-update-obs-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            doc_id = f"doc-{uuid.uuid4().hex[:8]}"
-            mem_ids = await _insert_document_with_memories(
-                conn, bank_id, doc_id, [("Alice loves hiking.", "experience")]
-            )
-            obs_id = await _insert_observation(conn, bank_id, "Alice is a hiker.", mem_ids)
-
-        with patch.object(memory, "submit_async_consolidation", new=AsyncMock()):
-            await memory.update_document(
-                doc_id, bank_id, tags=["new-tag"], request_context=request_context
-            )
-
-        async with pool.acquire() as conn:
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(obs_id) not in obs_ids, "Observation should have been invalidated"
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_update_tags_resets_consolidated_at_on_affected_units(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Affected memory units get consolidated_at reset for re-consolidation under new tags."""
-        bank_id = f"test-tag-update-reset-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            doc_id = f"doc-{uuid.uuid4().hex[:8]}"
-            mem_ids = await _insert_document_with_memories(
-                conn, bank_id, doc_id, [("Alice loves hiking.", "experience")]
-            )
-            obs_id = await _insert_observation(conn, bank_id, "Alice is a hiker.", mem_ids)
-
-            # Verify memory starts consolidated
-            assert await _get_consolidated_at(conn, mem_ids[0]) is not None
-
-        with patch.object(memory, "submit_async_consolidation", new=AsyncMock()):
-            await memory.update_document(
-                doc_id, bank_id, tags=["new-tag"], request_context=request_context
-            )
-
-        async with pool.acquire() as conn:
-            consolidated_at = await _get_consolidated_at(conn, mem_ids[0])
-            assert consolidated_at is None, "Memory unit should be reset for re-consolidation"
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_update_tags_triggers_consolidation_when_observations_invalidated(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """submit_async_consolidation is called when observations are invalidated."""
-        bank_id = f"test-tag-update-cons-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            doc_id = f"doc-{uuid.uuid4().hex[:8]}"
-            mem_ids = await _insert_document_with_memories(
-                conn, bank_id, doc_id, [("Alice loves hiking.", "experience")]
-            )
-            await _insert_observation(conn, bank_id, "Alice is a hiker.", mem_ids)
-
-        with patch.object(memory, "submit_async_consolidation", new=AsyncMock()) as mock_consolidate:
-            await memory.update_document(
-                doc_id, bank_id, tags=["new-tag"], request_context=request_context
-            )
-            mock_consolidate.assert_awaited_once()
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_update_tags_no_consolidation_when_no_observations(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """submit_async_consolidation is NOT called when no observations are invalidated."""
-        bank_id = f"test-tag-update-nocons-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            doc_id = f"doc-{uuid.uuid4().hex[:8]}"
-            await _insert_document_with_memories(
-                conn, bank_id, doc_id, [("Alice loves hiking.", "experience")]
-            )
-            # No observations inserted
-
-        with patch.object(memory, "submit_async_consolidation", new=AsyncMock()) as mock_consolidate:
-            await memory.update_document(
-                doc_id, bank_id, tags=["new-tag"], request_context=request_context
-            )
-            mock_consolidate.assert_not_awaited()
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_update_tags_resets_co_source_memories_from_other_documents(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Co-source memories from other documents that shared an invalidated observation are also reset."""
-        bank_id = f"test-tag-update-cosource-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            doc_id = f"doc-{uuid.uuid4().hex[:8]}"
-            doc_mem_ids = await _insert_document_with_memories(
-                conn, bank_id, doc_id, [("Alice loves hiking.", "experience")]
-            )
-            # Unrelated memory from another document — co-sourced in the same observation
-            other_mem = await _insert_memory(conn, bank_id, "Alice also rock-climbs.")
-            obs_id = await _insert_observation(
-                conn, bank_id, "Alice loves outdoor activities.", doc_mem_ids + [other_mem]
-            )
-
-            # Verify other_mem starts consolidated
-            assert await _get_consolidated_at(conn, other_mem) is not None
-
-        with patch.object(memory, "submit_async_consolidation", new=AsyncMock()):
-            await memory.update_document(
-                doc_id, bank_id, tags=["new-tag"], request_context=request_context
-            )
-
-        async with pool.acquire() as conn:
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(obs_id) not in obs_ids, "Observation should have been invalidated"
-
-            # other_mem (co-source from another document) must also be reset
-            consolidated_at = await _get_consolidated_at(conn, other_mem)
-            assert consolidated_at is None, "Co-source memory from other document should be reset"
-
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_update_tags_does_not_affect_unrelated_observations(
-        self, memory: MemoryEngine, request_context: RequestContext
-    ):
-        """Observations referencing memories from a different document are not affected."""
-        bank_id = f"test-tag-update-unrelated-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory, bank_id, request_context)
-
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            doc_id = f"doc-{uuid.uuid4().hex[:8]}"
-            mem_ids = await _insert_document_with_memories(
-                conn, bank_id, doc_id, [("Alice loves hiking.", "experience")]
-            )
-            # Unrelated memory not in the document
-            unrelated = await _insert_memory(conn, bank_id, "Bob likes cycling.")
-            unrelated_obs_id = await _insert_observation(
-                conn, bank_id, "Bob is a cyclist.", [unrelated]
-            )
-
-        with patch.object(memory, "submit_async_consolidation", new=AsyncMock()):
-            await memory.update_document(
-                doc_id, bank_id, tags=["new-tag"], request_context=request_context
-            )
-
-        async with pool.acquire() as conn:
-            obs_ids = await _get_observation_ids(conn, bank_id)
-            assert str(unrelated_obs_id) in obs_ids, "Unrelated observation should remain untouched"
-
-        await memory.delete_bank(bank_id, request_context=request_context)

hindsight-api-slim/tests/test_op_cancellation.py

@@ -1,311 +0,0 @@
-"""Tests for operation cancellation when a bank is deleted.
-
-Covers:
-- CASCADE DELETE: deleting a bank removes async_operations and webhooks rows
-- _check_op_alive: returns True when op exists, False when deleted
-- _mark_operation_completed / _mark_operation_failed: graceful no-op when row is gone
-- Consolidation checkpoint: stops early after a batch commit if op was deleted
-- Retain checkpoint: stops between sub-batches if op was deleted
-"""
-
-import uuid
-from unittest.mock import AsyncMock, patch
-
-import pytest
-import pytest_asyncio
-
-from hindsight_api.engine.memory_engine import MemoryEngine
-
-
-pytestmark = pytest.mark.xdist_group("op_cancellation_tests")
-
-_BANK_PREFIX = "test-op-cancel"
-
-
-@pytest_asyncio.fixture
-async def pool(pg0_db_url):
-    import asyncpg
-    from hindsight_api.pg0 import resolve_database_url
-
-    resolved_url = await resolve_database_url(pg0_db_url)
-    p = await asyncpg.create_pool(resolved_url, min_size=1, max_size=5, command_timeout=30)
-    yield p
-    await p.close()
-
-
-@pytest_asyncio.fixture(autouse=True)
-async def cleanup(pool):
-    """Remove test rows before and after each test."""
-    await pool.execute(f"DELETE FROM banks WHERE bank_id LIKE '{_BANK_PREFIX}%'")
-    yield
-    await pool.execute(f"DELETE FROM banks WHERE bank_id LIKE '{_BANK_PREFIX}%'")
-
-
-async def _insert_bank(pool, bank_id: str):
-    await pool.execute(
-        "INSERT INTO banks (bank_id, name) VALUES ($1, $2) ON CONFLICT DO NOTHING",
-        bank_id,
-        bank_id,
-    )
-
-
-async def _insert_op(pool, bank_id: str, op_id: uuid.UUID | None = None) -> uuid.UUID:
-    op_id = op_id or uuid.uuid4()
-    await pool.execute(
-        """
-        INSERT INTO async_operations (operation_id, bank_id, operation_type, status)
-        VALUES ($1, $2, 'consolidation', 'processing')
-        """,
-        op_id,
-        bank_id,
-    )
-    return op_id
-
-
-# ---------------------------------------------------------------------------
-# CASCADE DELETE tests
-# ---------------------------------------------------------------------------
-
-
-class TestCascadeDeleteOnBankDeletion:
-    @pytest.mark.asyncio
-    async def test_bank_deletion_cascades_to_async_operations(self, pool):
-        bank_id = f"{_BANK_PREFIX}-{uuid.uuid4().hex[:8]}"
-        await _insert_bank(pool, bank_id)
-        op_id = await _insert_op(pool, bank_id)
-
-        # Verify op exists
-        row = await pool.fetchrow("SELECT operation_id FROM async_operations WHERE operation_id = $1", op_id)
-        assert row is not None
-
-        # Delete the bank — should cascade to async_operations
-        await pool.execute("DELETE FROM banks WHERE bank_id = $1", bank_id)
-
-        row = await pool.fetchrow("SELECT operation_id FROM async_operations WHERE operation_id = $1", op_id)
-        assert row is None, "async_operations row should be deleted by CASCADE"
-
-    @pytest.mark.asyncio
-    async def test_bank_deletion_cascades_to_webhooks(self, pool):
-        bank_id = f"{_BANK_PREFIX}-{uuid.uuid4().hex[:8]}"
-        await _insert_bank(pool, bank_id)
-        webhook_id = uuid.uuid4()
-        await pool.execute(
-            """
-            INSERT INTO webhooks (id, bank_id, url, event_types)
-            VALUES ($1, $2, 'https://example.com/hook', '{}')
-            """,
-            webhook_id,
-            bank_id,
-        )
-
-        row = await pool.fetchrow("SELECT id FROM webhooks WHERE id = $1", webhook_id)
-        assert row is not None
-
-        await pool.execute("DELETE FROM banks WHERE bank_id = $1", bank_id)
-
-        row = await pool.fetchrow("SELECT id FROM webhooks WHERE id = $1", webhook_id)
-        assert row is None, "webhooks row should be deleted by CASCADE"
-
-
-# ---------------------------------------------------------------------------
-# _check_op_alive tests
-# ---------------------------------------------------------------------------
-
-
-class TestCheckOpAlive:
-    @pytest.mark.asyncio
-    async def test_returns_true_when_op_exists(self, memory: MemoryEngine, request_context):
-        bank_id = f"{_BANK_PREFIX}-{uuid.uuid4().hex[:8]}"
-        await memory.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        op_id = uuid.uuid4()
-        async with memory._pool.acquire() as conn:
-            await conn.execute(
-                """
-                INSERT INTO async_operations (operation_id, bank_id, operation_type, status)
-                VALUES ($1, $2, 'consolidation', 'processing')
-                """,
-                op_id,
-                bank_id,
-            )
-
-        assert await memory._check_op_alive(str(op_id)) is True
-
-    @pytest.mark.asyncio
-    async def test_returns_false_when_op_deleted(self, memory: MemoryEngine, request_context):
-        bank_id = f"{_BANK_PREFIX}-{uuid.uuid4().hex[:8]}"
-        await memory.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        op_id = uuid.uuid4()
-        async with memory._pool.acquire() as conn:
-            await conn.execute(
-                """
-                INSERT INTO async_operations (operation_id, bank_id, operation_type, status)
-                VALUES ($1, $2, 'consolidation', 'processing')
-                """,
-                op_id,
-                bank_id,
-            )
-            await conn.execute("DELETE FROM async_operations WHERE operation_id = $1", op_id)
-
-        assert await memory._check_op_alive(str(op_id)) is False
-
-    @pytest.mark.asyncio
-    async def test_returns_false_after_bank_cascade_delete(self, memory: MemoryEngine, request_context):
-        bank_id = f"{_BANK_PREFIX}-{uuid.uuid4().hex[:8]}"
-        await memory.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        op_id = uuid.uuid4()
-        async with memory._pool.acquire() as conn:
-            await conn.execute(
-                """
-                INSERT INTO async_operations (operation_id, bank_id, operation_type, status)
-                VALUES ($1, $2, 'consolidation', 'processing')
-                """,
-                op_id,
-                bank_id,
-            )
-
-        # Delete the bank — cascades to the op row
-        await memory.delete_bank(bank_id=bank_id, request_context=request_context)
-
-        assert await memory._check_op_alive(str(op_id)) is False
-
-
-# ---------------------------------------------------------------------------
-# _mark_operation_completed / _mark_operation_failed graceful no-op
-# ---------------------------------------------------------------------------
-
-
-class TestMarkOperationGracefulOnMissingRow:
-    @pytest.mark.asyncio
-    async def test_mark_completed_does_not_raise_when_row_missing(self, memory: MemoryEngine):
-        # Row never existed — should log and return cleanly
-        missing_id = str(uuid.uuid4())
-        await memory._mark_operation_completed(missing_id)  # no exception
-
-    @pytest.mark.asyncio
-    async def test_mark_failed_does_not_raise_when_row_missing(self, memory: MemoryEngine):
-        missing_id = str(uuid.uuid4())
-        await memory._mark_operation_failed(missing_id, "some error", "traceback here")  # no exception
-
-    @pytest.mark.asyncio
-    async def test_mark_completed_and_fire_webhook_does_not_raise_when_row_missing(
-        self, memory: MemoryEngine
-    ):
-        missing_id = str(uuid.uuid4())
-        await memory._mark_operation_completed_and_fire_webhook(
-            operation_id=missing_id,
-            bank_id="nonexistent-bank",
-            status="completed",
-            result=None,
-        )  # no exception
-
-
-# ---------------------------------------------------------------------------
-# Consolidation checkpoint
-# ---------------------------------------------------------------------------
-
-
-class TestConsolidationCheckpoint:
-    @pytest.mark.asyncio
-    async def test_consolidation_stops_early_when_op_cancelled(self, memory: MemoryEngine, request_context):
-        """Consolidation returns 'cancelled' status after the first batch if _check_op_alive is False."""
-        from hindsight_api.config import _get_raw_config
-        from hindsight_api.engine.consolidation.consolidator import run_consolidation_job
-
-        config = _get_raw_config()
-        original = config.enable_observations
-        config.enable_observations = True
-
-        try:
-            bank_id = f"{_BANK_PREFIX}-{uuid.uuid4().hex[:8]}"
-            await memory.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-            # Insert a few unconsolidated memories directly so we control the batch without LLM
-            async with memory._pool.acquire() as conn:
-                for i in range(3):
-                    await conn.execute(
-                        """
-                        INSERT INTO memory_units
-                            (id, bank_id, text, fact_type, created_at, updated_at)
-                        VALUES (gen_random_uuid(), $1, $2, 'experience', NOW(), NOW())
-                        """,
-                        bank_id,
-                        f"Test memory {i} for cancellation test",
-                    )
-
-            op_id = str(uuid.uuid4())
-            call_count = 0
-
-            async def _fake_check(operation_id: str) -> bool:
-                nonlocal call_count
-                call_count += 1
-                # Return False on the very first checkpoint call
-                return False
-
-            with patch.object(memory, "_check_op_alive", side_effect=_fake_check):
-                result = await run_consolidation_job(
-                    memory_engine=memory,
-                    bank_id=bank_id,
-                    request_context=request_context,
-                    operation_id=op_id,
-                )
-
-            assert result["status"] == "cancelled"
-            assert call_count >= 1
-        finally:
-            config.enable_observations = original
-
-
-# ---------------------------------------------------------------------------
-# Retain checkpoint
-# ---------------------------------------------------------------------------
-
-
-class TestRetainCheckpoint:
-    @pytest.mark.asyncio
-    async def test_retain_stops_between_sub_batches_when_cancelled(
-        self, memory: MemoryEngine, request_context
-    ):
-        """retain_batch_async returns partial results if _check_op_alive is False between sub-batches."""
-        from hindsight_api.config import _get_raw_config
-
-        bank_id = f"{_BANK_PREFIX}-{uuid.uuid4().hex[:8]}"
-        await memory.get_bank_profile(bank_id=bank_id, request_context=request_context)
-
-        # Force sub-batch splitting by temporarily lowering the token threshold
-        config = _get_raw_config()
-        original_tokens = config.retain_batch_tokens
-        # Set threshold very low so each item becomes its own sub-batch
-        config.retain_batch_tokens = 1
-
-        try:
-            op_id = str(uuid.uuid4())
-            check_calls = 0
-
-            async def _fake_check(operation_id: str) -> bool:
-                nonlocal check_calls
-                check_calls += 1
-                # Cancel after the first sub-batch completes
-                return check_calls <= 1
-
-            contents = [
-                {"content": f"Memory item {i} about something interesting."} for i in range(4)
-            ]
-
-            with patch.object(memory, "_check_op_alive", side_effect=_fake_check):
-                result = await memory.retain_batch_async(
-                    bank_id=bank_id,
-                    contents=contents,
-                    request_context=request_context,
-                    operation_id=op_id,
-                )
-
-            # Should have stopped early: fewer results than total items
-            assert len(result) < len(contents), (
-                f"Expected early stop but got {len(result)}/{len(contents)} results"
-            )
-            assert check_calls >= 1
-        finally:
-            config.retain_batch_tokens = original_tokens

hindsight-api-slim/tests/test_reflect_source_facts_config.py

@@ -1,129 +0,0 @@
-"""
-Tests for reflect search_observations source_facts_max_tokens configuration.
-
-Verifies that the source_facts_max_tokens parameter correctly controls
-whether source facts are included in search_observations recall calls.
-"""
-
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import pytest
-
-from hindsight_api.engine.reflect.tools import tool_search_observations
-from hindsight_api.engine.response_models import RecallResult
-
-
-def _make_mock_engine(recall_result=None):
-    """Create a mock memory engine with a recall_async method."""
-    if recall_result is None:
-        recall_result = RecallResult(results=[], source_facts={})
-    engine = MagicMock()
-    engine.recall_async = AsyncMock(return_value=recall_result)
-    return engine
-
-
-@pytest.fixture
-def mock_request_context():
-    return MagicMock()
-
-
-class TestSearchObservationsSourceFacts:
-    """Test source_facts_max_tokens parameter in tool_search_observations."""
-
-    @pytest.mark.asyncio
-    async def test_default_disables_source_facts(self, mock_request_context):
-        """Default source_facts_max_tokens=-1 should disable source facts."""
-        engine = _make_mock_engine()
-
-        await tool_search_observations(
-            engine, "bank-1", "test query", mock_request_context
-        )
-
-        engine.recall_async.assert_called_once()
-        call_kwargs = engine.recall_async.call_args.kwargs
-        assert call_kwargs["include_source_facts"] is False
-        assert "max_source_facts_tokens" not in call_kwargs
-
-    @pytest.mark.asyncio
-    async def test_zero_enables_source_facts_unlimited(self, mock_request_context):
-        """source_facts_max_tokens=0 should enable source facts with no token limit."""
-        engine = _make_mock_engine()
-
-        await tool_search_observations(
-            engine, "bank-1", "test query", mock_request_context,
-            source_facts_max_tokens=0,
-        )
-
-        engine.recall_async.assert_called_once()
-        call_kwargs = engine.recall_async.call_args.kwargs
-        assert call_kwargs["include_source_facts"] is True
-        assert "max_source_facts_tokens" not in call_kwargs
-
-    @pytest.mark.asyncio
-    async def test_positive_enables_source_facts_with_limit(self, mock_request_context):
-        """source_facts_max_tokens>0 should enable source facts with a token budget."""
-        engine = _make_mock_engine()
-
-        await tool_search_observations(
-            engine, "bank-1", "test query", mock_request_context,
-            source_facts_max_tokens=5000,
-        )
-
-        engine.recall_async.assert_called_once()
-        call_kwargs = engine.recall_async.call_args.kwargs
-        assert call_kwargs["include_source_facts"] is True
-        assert call_kwargs["max_source_facts_tokens"] == 5000
-
-    @pytest.mark.asyncio
-    async def test_negative_one_disables_source_facts(self, mock_request_context):
-        """Explicit -1 should disable source facts (same as default)."""
-        engine = _make_mock_engine()
-
-        await tool_search_observations(
-            engine, "bank-1", "test query", mock_request_context,
-            source_facts_max_tokens=-1,
-        )
-
-        engine.recall_async.assert_called_once()
-        call_kwargs = engine.recall_async.call_args.kwargs
-        assert call_kwargs["include_source_facts"] is False
-        assert "max_source_facts_tokens" not in call_kwargs
-
-
-class TestReflectSourceFactsConfig:
-    """Test that reflect_source_facts_max_tokens is properly wired in HindsightConfig."""
-
-    def test_config_field_exists(self):
-        """reflect_source_facts_max_tokens should be a valid config field."""
-        from hindsight_api.config import HindsightConfig
-
-        import dataclasses
-
-        field_names = {f.name for f in dataclasses.fields(HindsightConfig)}
-        assert "reflect_source_facts_max_tokens" in field_names
-
-    def test_config_is_configurable(self):
-        """reflect_source_facts_max_tokens should be a configurable (per-bank) field."""
-        from hindsight_api.config import HindsightConfig
-
-        assert "reflect_source_facts_max_tokens" in HindsightConfig.get_configurable_fields()
-
-    def test_default_value_is_disabled(self):
-        """Default should be -1 (disabled)."""
-        from hindsight_api.config import DEFAULT_REFLECT_SOURCE_FACTS_MAX_TOKENS
-
-        assert DEFAULT_REFLECT_SOURCE_FACTS_MAX_TOKENS == -1
-
-    def test_env_var_constant_exists(self):
-        """Env var constant should be defined."""
-        from hindsight_api.config import ENV_REFLECT_SOURCE_FACTS_MAX_TOKENS
-
-        assert ENV_REFLECT_SOURCE_FACTS_MAX_TOKENS == "HINDSIGHT_API_REFLECT_SOURCE_FACTS_MAX_TOKENS"
-
-    @patch.dict("os.environ", {"HINDSIGHT_API_REFLECT_SOURCE_FACTS_MAX_TOKENS": "8000"})
-    def test_from_env_reads_value(self):
-        """from_env should parse the env var."""
-        from hindsight_api.config import HindsightConfig
-
-        config = HindsightConfig.from_env()
-        assert config.reflect_source_facts_max_tokens == 8000

hindsight-api-slim/tests/test_reranker_error_handling.py

@@ -1,71 +0,0 @@
-"""
-Regression test for UnboundLocalError in recall when the reranker raises.
-
-Before the fix, `scored_results` and `pre_filtered_count` were only assigned
-inside the `try` block, but referenced in the `finally` block.  If
-`reranker_instance.rerank()` (or `ensure_initialized()`) raised, the `finally`
-block crashed with `UnboundLocalError` instead of propagating the original
-exception.
-
-Fix: initialise both variables to safe defaults before the try/finally block.
-"""
-
-from datetime import datetime, timezone
-from unittest.mock import AsyncMock, patch
-
-import pytest
-
-
-@pytest.mark.asyncio
-async def test_recall_reranker_error_does_not_raise_unbound_local(memory, request_context):
-    """Recall must propagate the reranker's exception, not an UnboundLocalError."""
-    bank_id = f"test_reranker_err_{datetime.now(timezone.utc).timestamp()}"
-
-    try:
-        await memory.retain_async(
-            bank_id=bank_id,
-            content="Paris is the capital of France",
-            request_context=request_context,
-        )
-
-        # Simulate a reranker failure (e.g. Cohere API error on empty/small candidate set)
-        rerank_mock = AsyncMock(side_effect=RuntimeError("reranker API error"))
-        memory._cross_encoder_reranker._initialized = True  # skip ensure_initialized
-
-        with patch.object(memory._cross_encoder_reranker, "rerank", rerank_mock):
-            with pytest.raises(Exception, match="reranker API error"):
-                await memory.recall_async(
-                    bank_id=bank_id,
-                    query="capital of France",
-                    request_context=request_context,
-                )
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)
-
-
-@pytest.mark.asyncio
-async def test_recall_reranker_init_error_does_not_raise_unbound_local(memory, request_context):
-    """Same regression when ensure_initialized() raises (before pre_filtered_count is set)."""
-    bank_id = f"test_reranker_init_err_{datetime.now(timezone.utc).timestamp()}"
-
-    try:
-        await memory.retain_async(
-            bank_id=bank_id,
-            content="Paris is the capital of France",
-            request_context=request_context,
-        )
-
-        init_mock = AsyncMock(side_effect=RuntimeError("reranker init failed"))
-        memory._cross_encoder_reranker._initialized = False
-
-        with patch.object(memory._cross_encoder_reranker, "ensure_initialized", init_mock):
-            with pytest.raises(Exception, match="reranker init failed"):
-                await memory.recall_async(
-                    bank_id=bank_id,
-                    query="capital of France",
-                    request_context=request_context,
-                )
-
-    finally:
-        await memory.delete_bank(bank_id, request_context=request_context)

hindsight-api-slim/tests/test_source_facts_tokens.py

@@ -1,170 +0,0 @@
-"""Tests for source_facts token limiting in recall.
-
-Covers:
-- max_source_facts_tokens: total token budget across all source facts
-- max_source_facts_tokens_per_observation: per-observation cap
-
-Both parameters are tested at the recall_async level and verified to produce
-fewer source facts when the budget is tight vs. unlimited.
-"""
-
-import pytest
-
-from hindsight_api.config import _get_raw_config
-from hindsight_api.engine.memory_engine import Budget
-
-
-@pytest.fixture(autouse=True)
-def enable_observations():
-    config = _get_raw_config()
-    original = config.enable_observations
-    config.enable_observations = True
-    yield
-    config.enable_observations = original
-
-
-async def _setup_bank_with_observations(memory, bank_id, request_context):
-    """Retain several memories and trigger consolidation to produce observations with source facts."""
-    contents = [
-        "Alice is a software engineer who loves Python programming.",
-        "Alice has been working at TechCorp for 5 years.",
-        "Alice recently completed a machine learning certification course.",
-        "Alice mentors junior developers on the team.",
-        "Alice prefers functional programming patterns in her code.",
-    ]
-    for content in contents:
-        await memory.retain_async(
-            bank_id=bank_id,
-            content=content,
-            request_context=request_context,
-        )
-    await memory.run_consolidation(bank_id=bank_id, request_context=request_context)
-
-
-class TestRecallSourceFactsPerObservationCap:
-    @pytest.mark.asyncio
-    async def test_per_observation_cap_reduces_source_facts(self, memory, request_context):
-        """A tight per-observation token cap should return fewer source facts than unlimited."""
-        bank_id = "test-sf-per-obs-cap"
-        try:
-            await _setup_bank_with_observations(memory, bank_id, request_context)
-
-            result_limited = await memory.recall_async(
-                bank_id=bank_id,
-                query="Alice engineer",
-                fact_type=["observation"],
-                max_tokens=4096,
-                include_source_facts=True,
-                max_source_facts_tokens_per_observation=1,  # Effectively cuts all source facts
-                budget=Budget.MID,
-                request_context=request_context,
-            )
-
-            result_unlimited = await memory.recall_async(
-                bank_id=bank_id,
-                query="Alice engineer",
-                fact_type=["observation"],
-                max_tokens=4096,
-                include_source_facts=True,
-                max_source_facts_tokens_per_observation=-1,
-                budget=Budget.MID,
-                request_context=request_context,
-            )
-
-            unlimited_count = len(result_unlimited.source_facts) if result_unlimited.source_facts else 0
-            limited_count = len(result_limited.source_facts) if result_limited.source_facts else 0
-
-            if unlimited_count > 0:
-                assert limited_count <= unlimited_count, (
-                    f"Per-observation cap should yield fewer source facts ({limited_count} <= {unlimited_count})"
-                )
-        finally:
-            await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_per_observation_cap_does_not_mix_between_observations(self, memory, request_context):
-        """Each observation's source facts are capped independently — not as a shared pool."""
-        bank_id = "test-sf-per-obs-independent"
-        try:
-            await _setup_bank_with_observations(memory, bank_id, request_context)
-
-            # With a generous per-observation limit each observation can have facts;
-            # with a global limit of 1 token the first observation would consume the whole budget.
-            result_per_obs = await memory.recall_async(
-                bank_id=bank_id,
-                query="Alice engineer",
-                fact_type=["observation"],
-                max_tokens=4096,
-                include_source_facts=True,
-                max_source_facts_tokens=4096,   # large global budget
-                max_source_facts_tokens_per_observation=512,  # reasonable per-obs limit
-                budget=Budget.MID,
-                request_context=request_context,
-            )
-
-            # Should not raise; source_facts may be populated for multiple observations
-            assert result_per_obs.source_facts is not None or len(result_per_obs.results) == 0
-        finally:
-            await memory.delete_bank(bank_id, request_context=request_context)
-
-
-class TestRecallSourceFactsTotalBudget:
-    @pytest.mark.asyncio
-    async def test_total_budget_limits_source_facts(self, memory, request_context):
-        """A tight total token budget should return fewer source facts than unlimited."""
-        bank_id = "test-sf-total-budget"
-        try:
-            await _setup_bank_with_observations(memory, bank_id, request_context)
-
-            result_tight = await memory.recall_async(
-                bank_id=bank_id,
-                query="Alice engineer",
-                fact_type=["observation"],
-                max_tokens=4096,
-                include_source_facts=True,
-                max_source_facts_tokens=1,  # Effectively cuts all source facts
-                budget=Budget.MID,
-                request_context=request_context,
-            )
-
-            result_unlimited = await memory.recall_async(
-                bank_id=bank_id,
-                query="Alice engineer",
-                fact_type=["observation"],
-                max_tokens=4096,
-                include_source_facts=True,
-                max_source_facts_tokens=-1,
-                budget=Budget.MID,
-                request_context=request_context,
-            )
-
-            unlimited_count = len(result_unlimited.source_facts) if result_unlimited.source_facts else 0
-            tight_count = len(result_tight.source_facts) if result_tight.source_facts else 0
-
-            if unlimited_count > 0:
-                assert tight_count <= unlimited_count, (
-                    f"Total budget should yield fewer source facts ({tight_count} <= {unlimited_count})"
-                )
-        finally:
-            await memory.delete_bank(bank_id, request_context=request_context)
-
-    @pytest.mark.asyncio
-    async def test_no_source_facts_without_flag(self, memory, request_context):
-        """source_facts should be None when include_source_facts is not set."""
-        bank_id = "test-sf-no-flag"
-        try:
-            await _setup_bank_with_observations(memory, bank_id, request_context)
-
-            result = await memory.recall_async(
-                bank_id=bank_id,
-                query="Alice engineer",
-                fact_type=["observation"],
-                max_tokens=4096,
-                include_source_facts=False,  # default
-                budget=Budget.MID,
-                request_context=request_context,
-            )
-
-            assert result.source_facts is None or len(result.source_facts) == 0
-        finally:
-            await memory.delete_bank(bank_id, request_context=request_context)

hindsight-api-slim/tests/test_strip_code_fences.py

@@ -1,92 +0,0 @@
-"""Tests for _strip_code_fences helper in OpenAI-compatible LLM provider."""
-
-import pytest
-
-from hindsight_api.engine.providers.openai_compatible_llm import _strip_code_fences
-
-
-class TestStripCodeFences:
-    """Test markdown code fence stripping from LLM responses."""
-
-    def test_bare_json_unchanged(self):
-        """Bare JSON passes through unchanged."""
-        content = '{"facts": [{"what": "test"}]}'
-        assert _strip_code_fences(content) == content
-
-    def test_json_fence_stripped(self):
-        """```json ... ``` fences are stripped."""
-        content = '```json\n{"facts": [{"what": "test"}]}\n```'
-        assert _strip_code_fences(content) == '{"facts": [{"what": "test"}]}'
-
-    def test_plain_fence_stripped(self):
-        """``` ... ``` fences without language tag are stripped."""
-        content = '```\n{"facts": [{"what": "test"}]}\n```'
-        assert _strip_code_fences(content) == '{"facts": [{"what": "test"}]}'
-
-    def test_fence_with_trailing_whitespace(self):
-        """Fences with extra whitespace are handled."""
-        content = '```json\n{"facts": []}\n```\n'
-        result = _strip_code_fences(content)
-        assert result == '{"facts": []}'
-
-    def test_fence_with_leading_whitespace(self):
-        """Content with leading whitespace before fence."""
-        content = '  ```json\n{"facts": []}\n```'
-        # The function checks for ``` in content, not startswith
-        result = _strip_code_fences(content)
-        assert '{"facts": []}' in result
-
-    def test_no_fences_no_change(self):
-        """Content without any backticks passes through."""
-        content = "Just some text without fences"
-        assert _strip_code_fences(content) == content
-
-    def test_empty_string(self):
-        """Empty string passes through."""
-        assert _strip_code_fences("") == ""
-
-    def test_multiline_json(self):
-        """Multi-line JSON inside fences is preserved."""
-        content = '```json\n{\n  "facts": [\n    {"what": "line1"},\n    {"what": "line2"}\n  ]\n}\n```'
-        result = _strip_code_fences(content)
-        assert '"line1"' in result
-        assert '"line2"' in result
-        assert "```" not in result
-
-    def test_malformed_fence_returns_original(self):
-        """Malformed fences (missing closing) return something parseable."""
-        content = '```json\n{"facts": []}'
-        result = _strip_code_fences(content)
-        # Should attempt to strip and return best effort
-        assert isinstance(result, str)
-
-    def test_minimax_style_response(self):
-        """Real-world MiniMax response format."""
-        content = (
-            "```json\n"
-            "{\n"
-            '  "facts": [\n'
-            "    {\n"
-            '      "what": "Sebastian switched the Hindsight extraction LLM",\n'
-            '      "when": "2026-03-21",\n'
-            '      "where": "N/A",\n'
-            '      "who": "Sebastian",\n'
-            '      "why": "MiniMax wraps JSON in code fences",\n'
-            '      "fact_kind": "event",\n'
-            '      "fact_type": "world",\n'
-            '      "entities": [{"text": "Sebastian"}, {"text": "Hindsight"}],\n'
-            '      "labels": {"source_type": "stated", "domain": ["infrastructure"]}\n'
-            "    }\n"
-            "  ]\n"
-            "}\n"
-            "```"
-        )
-        result = _strip_code_fences(content)
-        assert not result.startswith("```")
-        assert not result.endswith("```")
-        # Should be valid JSON
-        import json
-
-        parsed = json.loads(result)
-        assert len(parsed["facts"]) == 1
-        assert parsed["facts"][0]["who"] == "Sebastian"

hindsight-api-slim/tests/test_validation_result_enrichment.py

@@ -1,269 +0,0 @@
-"""
-Unit tests for ValidationResult.accept_with() enrichment (PR #639).
-
-These tests verify:
-1. The accept_with() factory creates an accepted result with the correct enrichment fields.
-2. The engine applies enrichment to retain contents and recall tags/tag_groups.
-3. RecallContext carries tags/tags_match/tag_groups so validators can read filter state.
-"""
-
-import pytest
-
-from hindsight_api.extensions import (
-    OperationValidatorExtension,
-    RecallContext,
-    ReflectContext,
-    RetainContext,
-    ValidationResult,
-)
-from hindsight_api.models import RequestContext
-
-# ---------------------------------------------------------------------------
-# Pure unit tests for ValidationResult factory methods
-# ---------------------------------------------------------------------------
-
-
-class TestValidationResultAcceptWith:
-    """Unit tests for the accept_with() factory — no DB needed."""
-
-    def test_accept_is_allowed_with_no_enrichment(self):
-        result = ValidationResult.accept()
-        assert result.allowed is True
-        assert result.contents is None
-        assert result.tags is None
-        assert result.tags_match is None
-        assert result.tag_groups is None
-
-    def test_accept_with_contents(self):
-        contents = [{"content": "enriched text", "tags": ["injected"]}]
-        result = ValidationResult.accept_with(contents=contents)
-        assert result.allowed is True
-        assert result.contents == contents
-        assert result.tags is None
-        assert result.tag_groups is None
-
-    def test_accept_with_tags(self):
-        result = ValidationResult.accept_with(tags=["alpha", "beta"])
-        assert result.allowed is True
-        assert result.tags == ["alpha", "beta"]
-        assert result.contents is None
-        assert result.tag_groups is None
-
-    def test_accept_with_tags_match(self):
-        result = ValidationResult.accept_with(tags=["x"], tags_match="all")
-        assert result.allowed is True
-        assert result.tags_match == "all"
-
-    def test_accept_with_tag_groups(self):
-        tag_groups = [{"tags": ["env:prod"], "match": "all"}]
-        result = ValidationResult.accept_with(tag_groups=tag_groups)
-        assert result.allowed is True
-        assert result.tag_groups == tag_groups
-
-    def test_accept_with_all_fields(self):
-        contents = [{"content": "c"}]
-        tags = ["t1"]
-        tag_groups = [{"tags": ["g1"]}]
-        result = ValidationResult.accept_with(
-            contents=contents,
-            tags=tags,
-            tags_match="any",
-            tag_groups=tag_groups,
-        )
-        assert result.allowed is True
-        assert result.contents == contents
-        assert result.tags == tags
-        assert result.tags_match == "any"
-        assert result.tag_groups == tag_groups
-
-    def test_reject_ignores_enrichment_fields(self):
-        """reject() always sets allowed=False and leaves enrichment fields at their defaults."""
-        result = ValidationResult.reject("not allowed", status_code=403)
-        assert result.allowed is False
-        assert result.reason == "not allowed"
-        assert result.status_code == 403
-        assert result.contents is None
-        assert result.tags is None
-
-    def test_none_fields_mean_no_modification(self):
-        """None enrichment fields must not overwrite engine defaults."""
-        result = ValidationResult.accept_with(tags=None, tag_groups=None)
-        assert result.tags is None
-        assert result.tag_groups is None
-        # Engine should interpret None as "keep original" — we verify the contract here.
-
-
-# ---------------------------------------------------------------------------
-# Integration tests: engine applies enrichment from validator
-# ---------------------------------------------------------------------------
-
-
-class _ContentEnrichingValidator(OperationValidatorExtension):
-    """Validator that injects a tag into every retain content item."""
-
-    def __init__(self, injected_tag: str):
-        super().__init__({})
-        self.injected_tag = injected_tag
-
-    async def validate_retain(self, ctx: RetainContext) -> ValidationResult:
-        enriched = []
-        for item in ctx.contents:
-            new_item = dict(item)
-            new_item.setdefault("tags", [])
-            new_item["tags"] = list(new_item["tags"]) + [self.injected_tag]
-            enriched.append(new_item)
-        return ValidationResult.accept_with(contents=enriched)
-
-    async def validate_recall(self, ctx: RecallContext) -> ValidationResult:
-        return ValidationResult.accept()
-
-    async def validate_reflect(self, ctx: ReflectContext) -> ValidationResult:
-        return ValidationResult.accept()
-
-
-class _TagEnrichingValidator(OperationValidatorExtension):
-    """Validator that injects tags into every recall operation."""
-
-    def __init__(self, forced_tags: list[str]):
-        super().__init__({})
-        self.forced_tags = forced_tags
-
-    async def validate_retain(self, ctx: RetainContext) -> ValidationResult:
-        return ValidationResult.accept()
-
-    async def validate_recall(self, ctx: RecallContext) -> ValidationResult:
-        return ValidationResult.accept_with(tags=self.forced_tags, tags_match="all")
-
-    async def validate_reflect(self, ctx: ReflectContext) -> ValidationResult:
-        return ValidationResult.accept()
-
-
-class _RecallContextCapturingValidator(OperationValidatorExtension):
-    """Validator that captures the RecallContext for inspection."""
-
-    def __init__(self):
-        super().__init__({})
-        self.captured: list[RecallContext] = []
-
-    async def validate_retain(self, ctx: RetainContext) -> ValidationResult:
-        return ValidationResult.accept()
-
-    async def validate_recall(self, ctx: RecallContext) -> ValidationResult:
-        self.captured.append(ctx)
-        return ValidationResult.accept()
-
-    async def validate_reflect(self, ctx: ReflectContext) -> ValidationResult:
-        return ValidationResult.accept()
-
-
-@pytest.fixture
-def memory_with_content_enricher(memory):
-    validator = _ContentEnrichingValidator(injected_tag="validator-injected")
-    memory._operation_validator = validator
-    return memory, validator
-
-
-@pytest.fixture
-def memory_with_tag_enricher(memory):
-    validator = _TagEnrichingValidator(forced_tags=["forced-tag"])
-    memory._operation_validator = validator
-    return memory, validator
-
-
-@pytest.fixture
-def memory_with_recall_context_capture(memory):
-    validator = _RecallContextCapturingValidator()
-    memory._operation_validator = validator
-    return memory, validator
-
-
-class TestRetainContentEnrichment:
-    """Engine applies enriched contents returned by validate_retain."""
-
-    @pytest.mark.asyncio
-    async def test_enriched_contents_are_used_for_retain(self, memory_with_content_enricher):
-        """When validator returns accept_with(contents=...), engine uses those contents."""
-        memory, validator = memory_with_content_enricher
-        bank_id = "test-retain-enrichment"
-        ctx = RequestContext()
-
-        # Retain without any tags — validator should inject "validator-injected"
-        await memory.retain_batch_async(
-            bank_id=bank_id,
-            contents=[{"content": "Alice is an engineer."}],
-            request_context=ctx,
-        )
-
-        # Retrieve facts tagged with the injected tag to confirm enrichment was applied
-        result = await memory.recall_async(
-            bank_id=bank_id,
-            query="Alice",
-            tags=["validator-injected"],
-            request_context=ctx,
-        )
-        # The fact should be retrievable via the injected tag
-        assert result is not None
-
-
-class TestRecallTagEnrichment:
-    """Engine applies enriched tags returned by validate_recall."""
-
-    @pytest.mark.asyncio
-    async def test_enriched_tags_filter_recall_results(self, memory_with_tag_enricher):
-        """When validator returns accept_with(tags=...), engine filters recall by those tags."""
-        memory, validator = memory_with_tag_enricher
-        bank_id = "test-recall-tag-enrichment"
-        ctx = RequestContext()
-
-        # Retain one fact with the forced tag and one without
-        await memory.retain_batch_async(
-            bank_id=bank_id,
-            contents=[{"content": "Bob is a designer.", "tags": ["forced-tag"]}],
-            request_context=ctx,
-        )
-
-        # recall is called without tags but validator injects "forced-tag" + match=all
-        result = await memory.recall_async(
-            bank_id=bank_id,
-            query="Bob",
-            request_context=ctx,
-        )
-        # Should still get a result — the injected tag matches the stored fact
-        assert result is not None
-
-
-class TestRecallContextContainsTagFields:
-    """RecallContext passed to validate_recall carries tag filter state."""
-
-    @pytest.mark.asyncio
-    async def test_recall_context_carries_tags(self, memory_with_recall_context_capture):
-        """tags, tags_match, and tag_groups are present in RecallContext."""
-        memory, validator = memory_with_recall_context_capture
-        bank_id = "test-recall-ctx-tags"
-        ctx = RequestContext()
-
-        await memory.recall_async(
-            bank_id=bank_id,
-            query="test",
-            tags=["env:prod"],
-            tags_match="all",
-            request_context=ctx,
-        )
-
-        assert len(validator.captured) == 1
-        rc = validator.captured[0]
-        assert rc.tags == ["env:prod"]
-        assert rc.tags_match == "all"
-
-    @pytest.mark.asyncio
-    async def test_recall_context_tags_default_to_none(self, memory_with_recall_context_capture):
-        """When caller provides no tags, RecallContext.tags is None."""
-        memory, validator = memory_with_recall_context_capture
-        bank_id = "test-recall-ctx-no-tags"
-        ctx = RequestContext()
-
-        await memory.recall_async(bank_id=bank_id, query="test", request_context=ctx)
-
-        assert len(validator.captured) == 1
-        rc = validator.captured[0]
-        assert rc.tags is None

hindsight-api-slim/tests/test_webhooks.py

@@ -1,794 +0,0 @@
-"""Tests for the webhook system.
-
-Covers:
-- Unit tests for HMAC signing and retry constants (no DB required)
-- Integration tests for fire_event() using a real DB (inserts into async_operations)
-- Integration tests for _handle_webhook_delivery() on the memory engine
-- HTTP API integration tests for CRUD and delivery listing endpoints
-"""
-
-import json
-import uuid
-from datetime import datetime, timezone
-from unittest.mock import AsyncMock, MagicMock, patch
-
-import httpx
-import pytest
-import pytest_asyncio
-
-from hindsight_api.api import create_app
-from hindsight_api.engine.memory_engine import MemoryEngine
-from hindsight_api.webhooks.manager import MAX_ATTEMPTS, RETRY_DELAYS, WebhookManager
-from hindsight_api.webhooks.models import (
-    ConsolidationEventData,
-    RetainEventData,
-    WebhookConfig,
-    WebhookEvent,
-    WebhookEventType,
-)
-from hindsight_api.worker.exceptions import RetryTaskAt
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-
-def _make_event(bank_id: str = "bank-1") -> WebhookEvent:
-    return WebhookEvent(
-        event=WebhookEventType.CONSOLIDATION_COMPLETED,
-        bank_id=bank_id,
-        operation_id=uuid.uuid4().hex,
-        status="completed",
-        timestamp=datetime.now(timezone.utc),
-        data=ConsolidationEventData(observations_created=1),
-    )
-
-
-def _make_delivery_task(
-    bank_id: str = "bank-1",
-    url: str = "https://example.com/hook",
-    retry_count: int = 0,
-    webhook_id: str | None = None,
-) -> dict:
-    return {
-        "type": "webhook_delivery",
-        "bank_id": bank_id,
-        "url": url,
-        "secret": None,
-        "event_type": "consolidation.completed",
-        "payload": '{"event":"consolidation.completed"}',
-        "webhook_id": webhook_id,
-        "_retry_count": retry_count,
-    }
-
-
-# ---------------------------------------------------------------------------
-# Unit tests (no DB)
-# ---------------------------------------------------------------------------
-
-
-class TestHmacSigning:
-    """Unit tests for WebhookManager._sign_payload()."""
-
-    def _make_manager(self) -> WebhookManager:
-        """Create a WebhookManager with a dummy pool (not used for signing)."""
-        pool = MagicMock()
-        return WebhookManager(pool=pool, global_webhooks=[])
-
-    def test_hmac_signing_format(self):
-        """_sign_payload should return a string starting with 'sha256='."""
-        manager = self._make_manager()
-        sig = manager._sign_payload("my-secret", b"hello world")
-        assert sig.startswith("sha256="), f"Expected 'sha256=' prefix, got: {sig!r}"
-        hex_part = sig[len("sha256="):]
-        # SHA-256 hex digest is always 64 characters
-        assert len(hex_part) == 64
-        # Hex characters only
-        assert all(c in "0123456789abcdef" for c in hex_part)
-
-    def test_hmac_signing_is_deterministic(self):
-        """Same secret + payload always produces the same signature."""
-        manager = self._make_manager()
-        payload = b'{"event":"consolidation.completed"}'
-        sig1 = manager._sign_payload("secret-key", payload)
-        sig2 = manager._sign_payload("secret-key", payload)
-        assert sig1 == sig2
-
-    def test_hmac_signing_differs_with_different_secret(self):
-        """Different secrets must produce different signatures."""
-        manager = self._make_manager()
-        payload = b"payload"
-        sig1 = manager._sign_payload("secret-a", payload)
-        sig2 = manager._sign_payload("secret-b", payload)
-        assert sig1 != sig2
-
-    def test_hmac_signing_differs_with_different_payload(self):
-        """Different payloads must produce different signatures."""
-        manager = self._make_manager()
-        sig1 = manager._sign_payload("secret", b"payload-one")
-        sig2 = manager._sign_payload("secret", b"payload-two")
-        assert sig1 != sig2
-
-
-class TestRetryConstants:
-    """Unit tests to verify retry schedule constants."""
-
-    def test_retry_delays_values(self):
-        """RETRY_DELAYS must match the documented schedule."""
-        assert RETRY_DELAYS == [5, 300, 1800, 7200, 18000]
-
-    def test_max_attempts(self):
-        """MAX_ATTEMPTS should be len(RETRY_DELAYS) + 1."""
-        assert MAX_ATTEMPTS == 6
-        assert MAX_ATTEMPTS == len(RETRY_DELAYS) + 1
-
-
-# ---------------------------------------------------------------------------
-# DB integration tests
-# ---------------------------------------------------------------------------
-
-
-@pytest_asyncio.fixture
-async def webhook_manager(memory: MemoryEngine) -> WebhookManager:
-    """Return a WebhookManager backed by the test pool with no global webhooks."""
-    return WebhookManager(pool=memory._pool, global_webhooks=[])
-
-
-async def _ensure_bank(pool, bank_id: str) -> None:
-    """Upsert a minimal bank row so FK constraints on async_operations/webhooks pass."""
-    await pool.execute(
-        "INSERT INTO banks (bank_id, name) VALUES ($1, $2) ON CONFLICT DO NOTHING",
-        bank_id,
-        bank_id,
-    )
-
-
-class TestFireEvent:
-    """Integration tests for WebhookManager.fire_event()."""
-
-    @pytest.mark.asyncio
-    async def test_fire_event_creates_delivery(
-        self, memory: MemoryEngine, webhook_manager: WebhookManager
-    ):
-        """fire_event() inserts a pending webhook_delivery task in async_operations."""
-        bank_id = f"wh-test-{uuid.uuid4().hex[:8]}"
-        webhook_id = uuid.uuid4()
-
-        async with memory._pool.acquire() as conn:
-            await _ensure_bank(memory._pool, bank_id)
-            await conn.execute(
-                """
-                INSERT INTO webhooks (id, bank_id, url, secret, event_types, enabled, created_at, updated_at)
-                VALUES ($1, $2, $3, NULL, $4, true, NOW(), NOW())
-                """,
-                webhook_id,
-                bank_id,
-                "https://example.com/hook",
-                ["consolidation.completed"],
-            )
-
-        try:
-            event = _make_event(bank_id)
-            await webhook_manager.fire_event(event)
-
-            async with memory._pool.acquire() as conn:
-                rows = await conn.fetch(
-                    """
-                    SELECT status, task_payload
-                    FROM async_operations
-                    WHERE operation_type = 'webhook_delivery'
-                      AND bank_id = $1
-                      AND task_payload->>'webhook_id' = $2
-                    """,
-                    bank_id,
-                    str(webhook_id),
-                )
-
-            assert len(rows) == 1
-            assert rows[0]["status"] == "pending"
-            payload = rows[0]["task_payload"]
-            if isinstance(payload, str):
-                payload = json.loads(payload)
-            assert payload["event_type"] == "consolidation.completed"
-        finally:
-            async with memory._pool.acquire() as conn:
-                await conn.execute(
-                    "DELETE FROM async_operations WHERE operation_type = 'webhook_delivery' AND bank_id = $1",
-                    bank_id,
-                )
-                await conn.execute("DELETE FROM webhooks WHERE id = $1", webhook_id)
-
-    @pytest.mark.asyncio
-    async def test_fire_event_global_webhook(
-        self, memory: MemoryEngine
-    ):
-        """fire_event() also queues delivery tasks for global webhooks (not stored in DB)."""
-        bank_id = f"wh-global-{uuid.uuid4().hex[:8]}"
-        await _ensure_bank(memory._pool, bank_id)
-        global_webhook = WebhookConfig(
-            id="",  # No DB row
-            bank_id=None,
-            url="https://global.example.com/hook",
-            secret=None,
-            event_types=["consolidation.completed"],
-            enabled=True,
-        )
-        manager = WebhookManager(pool=memory._pool, global_webhooks=[global_webhook])
-
-        event = _make_event(bank_id)
-        await manager.fire_event(event)
-
-        async with memory._pool.acquire() as conn:
-            rows = await conn.fetch(
-                """
-                SELECT status, task_payload
-                FROM async_operations
-                WHERE operation_type = 'webhook_delivery'
-                  AND bank_id = $1
-                  AND task_payload->>'url' = 'https://global.example.com/hook'
-                ORDER BY created_at DESC
-                LIMIT 1
-                """
-                ,
-                bank_id,
-            )
-
-        assert len(rows) == 1
-        assert rows[0]["status"] == "pending"
-        payload = rows[0]["task_payload"]
-        if isinstance(payload, str):
-            payload = json.loads(payload)
-        assert payload["webhook_id"] is None  # global webhook has no DB row
-
-        # Cleanup
-        async with memory._pool.acquire() as conn:
-            await conn.execute(
-                "DELETE FROM async_operations WHERE operation_type = 'webhook_delivery' AND bank_id = $1",
-                bank_id,
-            )
-
-    @pytest.mark.asyncio
-    async def test_fire_event_no_match_if_event_type_mismatch(
-        self, memory: MemoryEngine, webhook_manager: WebhookManager
-    ):
-        """Webhooks registered for a different event type receive no delivery task."""
-        bank_id = f"wh-mismatch-{uuid.uuid4().hex[:8]}"
-        webhook_id = uuid.uuid4()
-
-        await _ensure_bank(memory._pool, bank_id)
-        async with memory._pool.acquire() as conn:
-            await conn.execute(
-                """
-                INSERT INTO webhooks (id, bank_id, url, secret, event_types, enabled, created_at, updated_at)
-                VALUES ($1, $2, $3, NULL, $4, true, NOW(), NOW())
-                """,
-                webhook_id,
-                bank_id,
-                "https://example.com/other-hook",
-                ["other.event"],
-            )
-
-        try:
-            event = _make_event(bank_id)
-            await webhook_manager.fire_event(event)
-
-            async with memory._pool.acquire() as conn:
-                count = await conn.fetchval(
-                    """
-                    SELECT COUNT(*) FROM async_operations
-                    WHERE operation_type = 'webhook_delivery' AND bank_id = $1
-                    """,
-                    bank_id,
-                )
-
-            assert count == 0
-        finally:
-            async with memory._pool.acquire() as conn:
-                await conn.execute("DELETE FROM webhooks WHERE id = $1", webhook_id)
-
-
-class TestHandleWebhookDelivery:
-    """Integration tests for MemoryEngine._handle_webhook_delivery()."""
-
-    @pytest.mark.asyncio
-    async def test_deliver_success(self, memory: MemoryEngine):
-        """A successful HTTP POST completes without raising."""
-        task_dict = _make_delivery_task(retry_count=0)
-
-        mock_response = MagicMock()
-        mock_response.raise_for_status = MagicMock()
-
-        with patch.object(memory._http_client, "post", new=AsyncMock(return_value=mock_response)):
-            # Should not raise
-            await memory._handle_webhook_delivery(task_dict)
-
-    @pytest.mark.asyncio
-    async def test_deliver_failure_raises_retry_task_at(self, memory: MemoryEngine):
-        """A failed HTTP POST raises RetryTaskAt when retries remain."""
-        task_dict = _make_delivery_task(retry_count=0)
-
-        with patch.object(
-            memory._http_client, "post", new=AsyncMock(side_effect=Exception("connection refused"))
-        ):
-            with pytest.raises(RetryTaskAt):
-                await memory._handle_webhook_delivery(task_dict)
-
-    @pytest.mark.asyncio
-    async def test_deliver_exhausted_retries_raises(self, memory: MemoryEngine):
-        """When retry_count reaches MAX_ATTEMPTS-1, a failure raises the original exception."""
-        task_dict = _make_delivery_task(retry_count=MAX_ATTEMPTS - 1)
-
-        with patch.object(
-            memory._http_client, "post", new=AsyncMock(side_effect=Exception("server error"))
-        ):
-            with pytest.raises(Exception, match="server error"):
-                await memory._handle_webhook_delivery(task_dict)
-
-    @pytest.mark.asyncio
-    async def test_deliver_retry_at_uses_delay_schedule(self, memory: MemoryEngine):
-        """RetryTaskAt.retry_at is approximately now + RETRY_DELAYS[retry_count]."""
-        from datetime import timedelta
-
-        task_dict = _make_delivery_task(retry_count=1)
-
-        with patch.object(
-            memory._http_client, "post", new=AsyncMock(side_effect=Exception("fail"))
-        ):
-            before = datetime.now(timezone.utc)
-            with pytest.raises(RetryTaskAt) as exc_info:
-                await memory._handle_webhook_delivery(task_dict)
-            after = datetime.now(timezone.utc)
-
-        retry_at = exc_info.value.retry_at
-        expected_delay = RETRY_DELAYS[1]  # retry_count=1
-        assert retry_at >= before + timedelta(seconds=expected_delay - 2)
-        assert retry_at <= after + timedelta(seconds=expected_delay + 2)
-
-    @pytest.mark.asyncio
-    async def test_execute_task_marks_operation_completed(self, memory: MemoryEngine):
-        """After a successful delivery, execute_task marks the async_operations row as completed."""
-        operation_id = str(uuid.uuid4())
-        bank_id = f"wh-exec-{uuid.uuid4().hex[:8]}"
-
-        await _ensure_bank(memory._pool, bank_id)
-        # Insert a real async_operations row so _mark_operation_completed has something to update
-        async with memory._pool.acquire() as conn:
-            await conn.execute(
-                """
-                INSERT INTO async_operations
-                  (operation_id, bank_id, operation_type, status, task_payload, result_metadata, created_at, updated_at)
-                VALUES ($1, $2, 'webhook_delivery', 'processing', '{}'::jsonb, '{}'::jsonb, NOW(), NOW())
-                """,
-                uuid.UUID(operation_id),
-                bank_id,
-            )
-
-        task_dict = {
-            **_make_delivery_task(bank_id=bank_id, retry_count=0),
-            "operation_id": operation_id,
-        }
-
-        mock_response = MagicMock()
-        mock_response.raise_for_status = MagicMock()
-
-        with patch.object(memory._http_client, "post", new=AsyncMock(return_value=mock_response)):
-            await memory.execute_task(task_dict)
-
-        async with memory._pool.acquire() as conn:
-            row = await conn.fetchrow(
-                "SELECT status FROM async_operations WHERE operation_id = $1",
-                uuid.UUID(operation_id),
-            )
-
-        assert row is not None
-        assert row["status"] == "completed", f"Expected 'completed', got '{row['status']}'"
-
-        # Cleanup
-        async with memory._pool.acquire() as conn:
-            await conn.execute(
-                "DELETE FROM async_operations WHERE operation_id = $1",
-                uuid.UUID(operation_id),
-            )
-
-
-# ---------------------------------------------------------------------------
-# HTTP API integration tests
-# ---------------------------------------------------------------------------
-
-
-@pytest_asyncio.fixture
-async def api_client(memory: MemoryEngine):
-    """Async HTTP test client wired to the FastAPI app."""
-    app = create_app(memory, initialize_memory=False)
-    transport = httpx.ASGITransport(app=app)
-    async with httpx.AsyncClient(transport=transport, base_url="http://test") as client:
-        yield client
-
-
-class TestWebhookHttpApi:
-    """HTTP API integration tests for webhook CRUD endpoints."""
-
-    @pytest.mark.asyncio
-    async def test_http_create_webhook(self, api_client: httpx.AsyncClient):
-        """POST /webhooks returns 201 and an id."""
-        bank_id = f"http-wh-{uuid.uuid4().hex[:8]}"
-        response = await api_client.post(
-            f"/v1/default/banks/{bank_id}/webhooks",
-            json={
-                "url": "https://example.com/create",
-                "event_types": ["consolidation.completed"],
-            },
-        )
-        assert response.status_code == 201, response.text
-        data = response.json()
-        assert "id" in data
-        assert data["url"] == "https://example.com/create"
-        assert data["bank_id"] == bank_id
-        assert data["secret"] is None  # secrets are never echoed back
-
-        # Cleanup
-        await api_client.delete(
-            f"/v1/default/banks/{bank_id}/webhooks/{data['id']}"
-        )
-
-    @pytest.mark.asyncio
-    async def test_http_list_webhooks(self, api_client: httpx.AsyncClient):
-        """GET /webhooks returns the webhooks registered for a bank."""
-        bank_id = f"http-wh-{uuid.uuid4().hex[:8]}"
-
-        create_resp = await api_client.post(
-            f"/v1/default/banks/{bank_id}/webhooks",
-            json={"url": "https://example.com/list", "event_types": ["consolidation.completed"]},
-        )
-        assert create_resp.status_code == 201
-        webhook_id = create_resp.json()["id"]
-
-        list_resp = await api_client.get(f"/v1/default/banks/{bank_id}/webhooks")
-        assert list_resp.status_code == 200
-        items = list_resp.json()["items"]
-        assert any(item["id"] == webhook_id for item in items)
-
-        # Cleanup
-        await api_client.delete(f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}")
-
-    @pytest.mark.asyncio
-    async def test_http_delete_webhook(self, api_client: httpx.AsyncClient):
-        """DELETE /webhooks/{id} removes the webhook; subsequent list returns empty for that bank."""
-        bank_id = f"http-wh-{uuid.uuid4().hex[:8]}"
-
-        create_resp = await api_client.post(
-            f"/v1/default/banks/{bank_id}/webhooks",
-            json={"url": "https://example.com/delete", "event_types": ["consolidation.completed"]},
-        )
-        assert create_resp.status_code == 201
-        webhook_id = create_resp.json()["id"]
-
-        delete_resp = await api_client.delete(
-            f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}"
-        )
-        assert delete_resp.status_code == 200
-        assert delete_resp.json()["success"] is True
-
-        list_resp = await api_client.get(f"/v1/default/banks/{bank_id}/webhooks")
-        assert list_resp.status_code == 200
-        ids = [item["id"] for item in list_resp.json()["items"]]
-        assert webhook_id not in ids
-
-    @pytest.mark.asyncio
-    async def test_http_delete_webhook_not_found(self, api_client: httpx.AsyncClient):
-        """DELETE with a non-existent webhook id returns 404."""
-        bank_id = f"http-wh-{uuid.uuid4().hex[:8]}"
-        missing_id = str(uuid.uuid4())
-        response = await api_client.delete(
-            f"/v1/default/banks/{bank_id}/webhooks/{missing_id}"
-        )
-        assert response.status_code == 404
-
-    @pytest.mark.asyncio
-    async def test_http_list_deliveries(
-        self, memory: MemoryEngine, api_client: httpx.AsyncClient
-    ):
-        """GET /webhooks/{id}/deliveries returns delivery records for a webhook."""
-        bank_id = f"http-wh-{uuid.uuid4().hex[:8]}"
-
-        # Create webhook via HTTP API
-        create_resp = await api_client.post(
-            f"/v1/default/banks/{bank_id}/webhooks",
-            json={
-                "url": "https://example.com/deliveries",
-                "event_types": ["consolidation.completed"],
-            },
-        )
-        assert create_resp.status_code == 201
-        webhook_id = create_resp.json()["id"]
-
-        # Insert a delivery row directly into async_operations
-        delivery_id = uuid.uuid4()
-        now = datetime.now(timezone.utc)
-        task_payload = json.dumps(
-            {
-                "type": "webhook_delivery",
-                "bank_id": bank_id,
-                "url": "https://example.com/deliveries",
-                "secret": None,
-                "event_type": "consolidation.completed",
-                "payload": '{"event":"consolidation.completed"}',
-                "webhook_id": webhook_id,
-            }
-        )
-        async with memory._pool.acquire() as conn:
-            await conn.execute(
-                """
-                INSERT INTO async_operations
-                  (operation_id, bank_id, operation_type, status, retry_count, task_payload, result_metadata, created_at, updated_at)
-                VALUES ($1, $2, 'webhook_delivery', 'completed', 0, $3::jsonb, '{}'::jsonb, $4, $4)
-                """,
-                delivery_id,
-                bank_id,
-                task_payload,
-                now,
-            )
-
-        try:
-            deliveries_resp = await api_client.get(
-                f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}/deliveries"
-            )
-            assert deliveries_resp.status_code == 200
-            items = deliveries_resp.json()["items"]
-            ids = [item["id"] for item in items]
-            assert str(delivery_id) in ids
-
-            # Verify shape of a delivery item
-            delivery = next(item for item in items if item["id"] == str(delivery_id))
-            assert delivery["status"] == "completed"
-            assert delivery["event_type"] == "consolidation.completed"
-            assert delivery["attempts"] == 1
-        finally:
-            async with memory._pool.acquire() as conn:
-                await conn.execute(
-                    "DELETE FROM async_operations WHERE operation_id = $1", delivery_id
-                )
-            await api_client.delete(
-                f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}"
-            )
-
-    @pytest.mark.asyncio
-    async def test_http_list_deliveries_webhook_not_found(self, api_client: httpx.AsyncClient):
-        """GET /webhooks/{id}/deliveries for a non-existent webhook returns 404."""
-        bank_id = f"http-wh-{uuid.uuid4().hex[:8]}"
-        missing_id = str(uuid.uuid4())
-        response = await api_client.get(
-            f"/v1/default/banks/{bank_id}/webhooks/{missing_id}/deliveries"
-        )
-        assert response.status_code == 404
-
-    @pytest.mark.asyncio
-    async def test_http_update_webhook_url(self, api_client: httpx.AsyncClient):
-        """PATCH /webhooks/{id} updates only the provided fields."""
-        bank_id = f"http-wh-{uuid.uuid4().hex[:8]}"
-
-        create_resp = await api_client.post(
-            f"/v1/default/banks/{bank_id}/webhooks",
-            json={"url": "https://example.com/original", "event_types": ["consolidation.completed"]},
-        )
-        assert create_resp.status_code == 201
-        webhook_id = create_resp.json()["id"]
-
-        patch_resp = await api_client.patch(
-            f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}",
-            json={"url": "https://example.com/updated"},
-        )
-        assert patch_resp.status_code == 200
-        data = patch_resp.json()
-        assert data["url"] == "https://example.com/updated"
-        # event_types should be unchanged
-        assert "consolidation.completed" in data["event_types"]
-
-        # Cleanup
-        await api_client.delete(f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}")
-
-    @pytest.mark.asyncio
-    async def test_http_update_webhook_event_types(self, api_client: httpx.AsyncClient):
-        """PATCH /webhooks/{id} can update event_types."""
-        bank_id = f"http-wh-{uuid.uuid4().hex[:8]}"
-
-        create_resp = await api_client.post(
-            f"/v1/default/banks/{bank_id}/webhooks",
-            json={"url": "https://example.com/hook", "event_types": ["consolidation.completed"]},
-        )
-        assert create_resp.status_code == 201
-        webhook_id = create_resp.json()["id"]
-
-        patch_resp = await api_client.patch(
-            f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}",
-            json={"event_types": ["retain.completed"]},
-        )
-        assert patch_resp.status_code == 200
-        data = patch_resp.json()
-        assert data["event_types"] == ["retain.completed"]
-
-        # Cleanup
-        await api_client.delete(f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}")
-
-    @pytest.mark.asyncio
-    async def test_http_update_webhook_enabled(self, api_client: httpx.AsyncClient):
-        """PATCH /webhooks/{id} can toggle enabled."""
-        bank_id = f"http-wh-{uuid.uuid4().hex[:8]}"
-
-        create_resp = await api_client.post(
-            f"/v1/default/banks/{bank_id}/webhooks",
-            json={"url": "https://example.com/hook", "event_types": ["consolidation.completed"]},
-        )
-        assert create_resp.status_code == 201
-        webhook_id = create_resp.json()["id"]
-        assert create_resp.json()["enabled"] is True
-
-        patch_resp = await api_client.patch(
-            f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}",
-            json={"enabled": False},
-        )
-        assert patch_resp.status_code == 200
-        assert patch_resp.json()["enabled"] is False
-
-        # Cleanup
-        await api_client.delete(f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}")
-
-    @pytest.mark.asyncio
-    async def test_http_update_webhook_http_config(self, api_client: httpx.AsyncClient):
-        """PATCH /webhooks/{id} can update http_config."""
-        bank_id = f"http-wh-{uuid.uuid4().hex[:8]}"
-
-        create_resp = await api_client.post(
-            f"/v1/default/banks/{bank_id}/webhooks",
-            json={"url": "https://example.com/hook", "event_types": ["consolidation.completed"]},
-        )
-        assert create_resp.status_code == 201
-        webhook_id = create_resp.json()["id"]
-
-        patch_resp = await api_client.patch(
-            f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}",
-            json={
-                "http_config": {
-                    "method": "POST",
-                    "timeout_seconds": 10,
-                    "headers": {"X-Custom": "value"},
-                    "params": {},
-                }
-            },
-        )
-        assert patch_resp.status_code == 200
-        data = patch_resp.json()
-        assert data["http_config"]["timeout_seconds"] == 10
-        assert data["http_config"]["headers"] == {"X-Custom": "value"}
-
-        # Cleanup
-        await api_client.delete(f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}")
-
-    @pytest.mark.asyncio
-    async def test_http_update_webhook_not_found(self, api_client: httpx.AsyncClient):
-        """PATCH /webhooks/{id} returns 404 for a non-existent webhook."""
-        bank_id = f"http-wh-{uuid.uuid4().hex[:8]}"
-        missing_id = str(uuid.uuid4())
-        response = await api_client.patch(
-            f"/v1/default/banks/{bank_id}/webhooks/{missing_id}",
-            json={"url": "https://example.com/new"},
-        )
-        assert response.status_code == 404
-
-    @pytest.mark.asyncio
-    async def test_http_update_webhook_no_fields(self, api_client: httpx.AsyncClient):
-        """PATCH /webhooks/{id} with empty body returns 422."""
-        bank_id = f"http-wh-{uuid.uuid4().hex[:8]}"
-
-        create_resp = await api_client.post(
-            f"/v1/default/banks/{bank_id}/webhooks",
-            json={"url": "https://example.com/hook", "event_types": ["consolidation.completed"]},
-        )
-        assert create_resp.status_code == 201
-        webhook_id = create_resp.json()["id"]
-
-        patch_resp = await api_client.patch(
-            f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}",
-            json={},
-        )
-        assert patch_resp.status_code == 422
-
-        # Cleanup
-        await api_client.delete(f"/v1/default/banks/{bank_id}/webhooks/{webhook_id}")
-
-
-# ---------------------------------------------------------------------------
-# retain.completed webhook tests
-# ---------------------------------------------------------------------------
-
-
-class TestRetainCompletedWebhook:
-    """Tests for the retain.completed webhook event."""
-
-    def test_retain_event_data_model(self):
-        """RetainEventData can be constructed with optional fields."""
-        data = RetainEventData(document_id="doc-123", tags=["tag1", "tag2"])
-        assert data.document_id == "doc-123"
-        assert data.tags == ["tag1", "tag2"]
-
-        empty = RetainEventData()
-        assert empty.document_id is None
-        assert empty.tags is None
-
-    def test_retain_event_type_value(self):
-        """WebhookEventType.RETAIN_COMPLETED has the correct string value."""
-        assert WebhookEventType.RETAIN_COMPLETED == "retain.completed"
-
-    @pytest.mark.asyncio
-    async def test_fire_retain_webhook_queues_per_document(
-        self, memory: MemoryEngine, webhook_manager: WebhookManager
-    ):
-        """_fire_retain_webhook queues one delivery task per content item."""
-        bank_id = f"wh-retain-{uuid.uuid4().hex[:8]}"
-        webhook_id = uuid.uuid4()
-
-        await _ensure_bank(memory._pool, bank_id)
-        async with memory._pool.acquire() as conn:
-            await conn.execute(
-                """
-                INSERT INTO webhooks (id, bank_id, url, secret, event_types, enabled, created_at, updated_at)
-                VALUES ($1, $2, $3, NULL, $4, true, NOW(), NOW())
-                """,
-                webhook_id,
-                bank_id,
-                "https://example.com/retain-hook",
-                ["retain.completed"],
-            )
-
-        try:
-            contents = [
-                {"content": "Alice works at Google", "document_id": "doc-1"},
-                {"content": "Bob loves Python", "document_id": "doc-2"},
-            ]
-            # Temporarily replace webhook manager on memory engine
-            original_manager = memory._webhook_manager
-            memory._webhook_manager = webhook_manager
-            try:
-                callback = memory._build_retain_outbox_callback(
-                    bank_id=bank_id,
-                    contents=contents,
-                    operation_id="test-op-123",
-                )
-                assert callback is not None
-                async with memory._pool.acquire() as conn:
-                    await callback(conn)
-            finally:
-                memory._webhook_manager = original_manager
-
-            async with memory._pool.acquire() as conn:
-                rows = await conn.fetch(
-                    """
-                    SELECT task_payload
-                    FROM async_operations
-                    WHERE operation_type = 'webhook_delivery'
-                      AND bank_id = $1
-                      AND task_payload->>'event_type' = 'retain.completed'
-                    ORDER BY created_at
-                    """,
-                    bank_id,
-                )
-
-            assert len(rows) == 2
-            payloads = []
-            for row in rows:
-                p = row["task_payload"]
-                if isinstance(p, str):
-                    p = json.loads(p)
-                payloads.append(p)
-
-            doc_ids_in_payloads = [json.loads(p["payload"]).get("data", {}).get("document_id") for p in payloads]
-            assert "doc-1" in doc_ids_in_payloads
-            assert "doc-2" in doc_ids_in_payloads
-        finally:
-            async with memory._pool.acquire() as conn:
-                await conn.execute(
-                    "DELETE FROM async_operations WHERE operation_type = 'webhook_delivery' AND bank_id = $1",
-                    bank_id,
-                )
-                await conn.execute("DELETE FROM webhooks WHERE id = $1", webhook_id)

hindsight-api/hindsight_api/__init__.py

@@ -46,4 +46,4 @@ __all__ = [
     "RemoteTEICrossEncoder",
     "LLMConfig",
 ]
-__version__ = "0.4.20"
+__version__ = "0.4.11"

hindsight-api/hindsight_api/admin/cli.py

@@ -14,8 +14,7 @@ from typing import Any
 import asyncpg
 import typer
 
-from ..config import DEFAULT_DATABASE_SCHEMA, HindsightConfig
-from ..extensions import TenantExtension, load_extension
+from ..config import HindsightConfig
 from ..pg0 import parse_pg0_url, resolve_database_url
 
 
@@ -215,81 +214,20 @@ def restore(
     typer.echo("Restore complete")
 
 
-async def _run_migration(
-    db_url: str,
-    schema: str | None = None,
-    base_schema: str = DEFAULT_DATABASE_SCHEMA,
-    embedding_dimension: int | None = None,
-) -> list[str]:
-    """Resolve database URL and run migrations for one schema or all discovered schemas."""
-    from ..migrations import (
-        ensure_embedding_dimension,
-        ensure_text_search_extension,
-        ensure_vector_extension,
-        run_migrations,
-    )
+async def _run_migration(db_url: str, schema: str = "public") -> None:
+    """Resolve database URL and run migrations."""
+    from ..migrations import run_migrations
 
     is_pg0, instance_name, _ = parse_pg0_url(db_url)
     if is_pg0:
         typer.echo(f"Starting embedded PostgreSQL (instance: {instance_name})...")
     resolved_url = await resolve_database_url(db_url)
-
-    config = HindsightConfig.from_env()
-    if schema:
-        schemas = [schema]
-    else:
-        tenant_extension = load_extension("TENANT", TenantExtension)
-
-        schemas = [base_schema or DEFAULT_DATABASE_SCHEMA]
-        if tenant_extension:
-            tenants = await tenant_extension.list_tenants()
-            schemas.extend(tenant.schema for tenant in tenants if tenant.schema)
-
-        # Preserve order while removing duplicates.
-        schemas = list(dict.fromkeys(schemas))
-
-    for schema in schemas:
-        run_migrations(resolved_url, schema=schema, migration_database_url=config.migration_database_url)
-
-    if embedding_dimension is not None:
-        for schema in schemas:
-            ensure_embedding_dimension(
-                resolved_url,
-                embedding_dimension,
-                schema=schema,
-                vector_extension=config.vector_extension,
-            )
-
-    for schema in schemas:
-        ensure_vector_extension(
-            resolved_url,
-            vector_extension=config.vector_extension,
-            schema=schema,
-        )
-
-    for schema in schemas:
-        ensure_text_search_extension(
-            resolved_url,
-            text_search_extension=config.text_search_extension,
-            schema=schema,
-        )
-
-    return schemas
+    run_migrations(resolved_url, schema=schema)
 
 
 @app.command(name="run-db-migration")
 def run_db_migration(
-    schema: str | None = typer.Option(
-        None,
-        "--schema",
-        "-s",
-        help="Database schema to run migrations on. If omitted, migrate the base schema and all discovered tenant schemas.",
-    ),
-    embedding_dimension: int | None = typer.Option(
-        None,
-        "--embedding-dimension",
-        help="Expected embedding dimension to enforce after migrations. Omit to skip dimension sync.",
-    ),
+    schema: str = typer.Option("public", "--schema", "-s", help="Database schema to run migrations on"),
 ):
     """Run database migrations to the latest version."""
     config = HindsightConfig.from_env()
@@ -299,21 +237,11 @@ def run_db_migration(
         typer.echo("Set HINDSIGHT_API_DATABASE_URL environment variable.", err=True)
         raise typer.Exit(1)
 
-    if schema:
-        typer.echo(f"Running database migrations for schema: {schema}...")
-    else:
-        typer.echo("Running database migrations for base schema and all discovered tenant schemas...")
+    typer.echo(f"Running database migrations (schema: {schema})...")
 
-    schemas = asyncio.run(
-        _run_migration(
-            config.database_url,
-            schema=schema,
-            base_schema=config.database_schema,
-            embedding_dimension=embedding_dimension,
-        )
-    )
+    asyncio.run(_run_migration(config.database_url, schema))
 
-    typer.echo(f"Database migrations completed successfully for {len(schemas)} schema(s)")
+    typer.echo("Database migrations completed successfully")
 
 
 async def _decommission_worker(db_url: str, worker_id: str, schema: str = "public") -> int:

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

@@ -34,7 +34,7 @@ def upgrade() -> None:
     # Create file_storage table (minimal: just key + data)
     op.execute(
         f"""
-        CREATE TABLE IF NOT EXISTS {schema}file_storage (
+        CREATE TABLE {schema}file_storage (
             storage_key TEXT PRIMARY KEY,
             data BYTEA NOT NULL
         )