fix: remove unused PluginState import from tools.ts

fix: review fixes for opencode integration
- Rename CI job from build-opencode-integration to test-opencode-integration to match naming convention for integrations that run tests - Fix tsconfig module resolution to Node16 (consistent with other integrations) - Extract shared makeConfig test helper to avoid duplication across 3 test files
2026-04-07 10:05:36 +02:00 · 2026-04-07 09:49:19 +02:00 · 2026-04-07 09:45:38 +02:00 · 2026-04-07 09:45:38 +02:00 · 2026-04-07 09:45:38 +02:00 · 2026-04-07 09:45:38 +02:00
1470 changed files with 33978 additions and 166827 deletions
@@ -157,16 +157,7 @@ If any files in `hindsight-integrations/` were added or changed, verify:
 - **Release process** — check that the integration name is in the `VALID_INTEGRATIONS` array in `scripts/release-integration.sh`. If missing, flag it.
 - **Code standards** — the integration code must follow all Python style rules (type hints, no raw dicts, no tuple returns, etc.).

-### 10. Check MCP tool registration completeness
-
-If any new MCP tools were added or existing tools renamed in `hindsight-api-slim/hindsight_api/mcp_tools.py`:
- **`_ALL_TOOLS` set** in `mcp_tools.py` — must include the new tool name
- **`tools_to_register` default set** in `register_mcp_tools()` in `mcp_tools.py` — must include the new tool name
- **`_SINGLE_BANK_TOOLS` set** in `hindsight-api-slim/hindsight_api/api/mcp.py` — must include the new tool if it is bank-scoped (not a bank-management tool like `list_banks`/`create_bank`)
- **`MCP_TOOL_GROUPS`** in `hindsight-control-plane/src/components/bank-config-view.tsx` — must include the new tool in the appropriate group for the UI tool selector
- **Tool count assertions** in tests (e.g., `test_mcp_tools.py`) — must be updated to reflect the new count
-
-### 11. Review against other coding standards
+### 10. Review against other coding standards

 Check the diff for violations of the standards listed above:
 - Python files at project root (not allowed)
@@ -178,7 +169,7 @@ Check the diff for violations of the standards listed above:
 - Premature abstractions or speculative helpers
 - Backwards-compatibility hacks (unused vars, re-exports, "removed" comments)

-### 12. Report findings
+### 11. Report findings

 Present a clear summary organized by severity:

@@ -2,7 +2,7 @@
 # Copy this file to .env and fill in your values

 # LLM Configuration (Required)
-# Supported providers: openai, groq, ollama, gemini, anthropic, lmstudio, vertexai, minimax, deepseek, zai, volcano
+# Supported providers: openai, groq, ollama, gemini, anthropic, lmstudio, vertexai, minimax, volcano
 HINDSIGHT_API_LLM_PROVIDER=openai
 HINDSIGHT_API_LLM_API_KEY=your-api-key-here
 HINDSIGHT_API_LLM_MODEL=gpt-4o-mini
@@ -25,16 +25,6 @@ HINDSIGHT_API_LLM_BASE_URL=https://api.openai.com/v1
 # HINDSIGHT_API_LLM_API_KEY=your-minimax-api-key
 # HINDSIGHT_API_LLM_MODEL=MiniMax-M2.7

-# Example: DeepSeek configuration (https://api.deepseek.com)
-# HINDSIGHT_API_LLM_PROVIDER=deepseek
-# HINDSIGHT_API_LLM_API_KEY=your-deepseek-api-key
-# HINDSIGHT_API_LLM_MODEL=deepseek-v4-flash  # or deepseek-v4-pro / deepseek-chat / deepseek-reasoner
-
-# Example: z.ai configuration (Zhipu GLM series, https://z.ai)
-# HINDSIGHT_API_LLM_PROVIDER=zai
-# HINDSIGHT_API_LLM_API_KEY=your-zai-api-key
-# HINDSIGHT_API_LLM_MODEL=glm-4.5-flash  # or glm-4.5-air for the paid tier
-
 # Example: LM Studio local configuration (Qwen 2.5 32B recommended)
 # HINDSIGHT_API_LLM_PROVIDER=lmstudio
 # HINDSIGHT_API_LLM_API_KEY=lmstudio
@@ -54,7 +44,6 @@ HINDSIGHT_API_LOG_LEVEL=info

 # Database (Optional - uses embedded pg0 by default)
 # HINDSIGHT_API_DATABASE_URL=postgresql://user:pass@host:5432/db
-# HINDSIGHT_API_READ_DATABASE_URL=  # Optional read-replica URL. When set, recall queries (semantic, BM25, graph, temporal) flow through a separate pool against this URL, offloading the primary. Typically points to a read-only endpoint (CNPG's <cluster>-ro service or Aurora reader endpoint).
 # 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)

@@ -65,25 +54,12 @@ HINDSIGHT_API_LOG_LEVEL=info
 # HINDSIGHT_API_VECTOR_EXTENSION=pgvectorscale  # Auto-detects pg_diskann on Azure

 # Embeddings Configuration (Optional - uses local by default)
-# Provider: "local" (default), "tei", "openai", "cohere", "google", "openrouter", "litellm", or "litellm-sdk"
+# Provider: "local" (default) or "tei" (HuggingFace Text Embeddings Inference)
 # HINDSIGHT_API_EMBEDDINGS_PROVIDER=local
 # For local provider:
 # HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL=BAAI/bge-small-en-v1.5
-# Optional for China network / restricted HF access:
-# HF_ENDPOINT=https://hf-mirror.com
 # For TEI provider:
 # HINDSIGHT_API_EMBEDDINGS_TEI_URL=http://localhost:8080
-# For OpenAI-compatible embeddings:
-# HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY=sk-xxxx
-# HINDSIGHT_API_EMBEDDINGS_OPENAI_MODEL=text-embedding-3-small
-# HINDSIGHT_API_EMBEDDINGS_OPENAI_BASE_URL=https://api.openai.com/v1
-#
-# IMPORTANT: Embedding keys require provider-specific names:
-# HINDSIGHT_API_EMBEDDINGS_{PROVIDER}_{PARAMETER}
-# (for example, HINDSIGHT_API_EMBEDDINGS_OPENAI_MODEL).
-#
-# DeepSeek note: DeepSeek is supported for LLM calls, but not for embeddings.
-# If using DeepSeek as LLM provider, keep embeddings on local/openai/cohere/google/etc.

 # Reranker Configuration (Optional - uses local by default)
 # Provider: "local" (default) or "tei" (HuggingFace Text Embeddings Inference)
@@ -107,15 +83,3 @@ HINDSIGHT_API_LOG_LEVEL=info
 # Custom service name and environment (optional, defaults: hindsight-api, development)
 # HINDSIGHT_API_OTEL_SERVICE_NAME=hindsight-production
 # HINDSIGHT_API_OTEL_DEPLOYMENT_ENVIRONMENT=production
-
-# -----------------------------------------------------------------------------
-# Control Plane (Optional)
-# -----------------------------------------------------------------------------
-
-# Dataplane API URL - where the CP proxies requests to
-# HINDSIGHT_CP_DATAPLANE_API_URL=http://localhost:8888
-
-# Optional: Require a shared access key to view the Control Plane UI.
-# When set, visitors see a login page and must enter the key before
-# accessing the dashboard or any /api/* routes (except /api/health).
-# HINDSIGHT_CP_ACCESS_KEY=your-shared-secret-key
@@ -34,7 +34,7 @@ jobs:
        env:
          UMAMI_URL: https://analytics.hindsight.vectorize.io
          UMAMI_WEBSITE_ID: ${{ secrets.UMAMI_WEBSITE_ID }}
-      - uses: actions/upload-pages-artifact@v5
+      - uses: actions/upload-pages-artifact@v4
        with:
          path: hindsight-docs/build
  deploy:
@@ -1,200 +0,0 @@
-name: Performance Tests
-
-on:
-  schedule:
-    # Run daily at 06:00 UTC
-    - cron: "0 6 * * *"
-  workflow_dispatch:
-    inputs:
-      scale:
-        description: "Test scale (perf-test)"
-        type: choice
-        options:
-          - tiny
-          - small
-          - medium
-          - large
-        default: large
-      suite:
-        description: "Perf-test suite to run (blank = all)"
-        type: choice
-        options:
-          - ""
-          - retain
-          - recall
-          - recall-with-observations
-          - consolidation
-        default: ""
-      locomo_conversations:
-        description: "LoComo conversation IDs (space-separated). Blank = curated set (conv-26 conv-30 conv-43)."
-        type: string
-        default: ""
-      locomo_skip:
-        description: "Skip LoComo job"
-        type: boolean
-        default: false
-      ref:
-        description: "Git ref to test (branch, tag, or SHA). Defaults to main."
-        type: string
-        default: ""
-
-concurrency:
-  group: perf-test
-  cancel-in-progress: true
-
-jobs:
-  perf-test:
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v6
-      with:
-        ref: ${{ inputs.ref || github.ref }}
-
-    - name: Install uv
-      uses: astral-sh/setup-uv@v7
-      with:
-        enable-cache: true
-        prune-cache: false
-
-    - name: Set up Python
-      uses: actions/setup-python@v6
-      with:
-        python-version-file: ".python-version"
-
-    - name: Cache HuggingFace models
-      uses: actions/cache@v5
-      with:
-        path: ~/.cache/huggingface
-        key: ${{ runner.os }}-huggingface-${{ hashFiles('hindsight-api-slim/pyproject.toml') }}
-        restore-keys: |
-          ${{ runner.os }}-huggingface-
-
-    - name: Pre-download models
-      working-directory: ./hindsight-api-slim
-      run: |
-        uv run --frozen --all-extras --index-strategy unsafe-best-match python -c "
-        from sentence_transformers import SentenceTransformer
-        print('Downloading embedding model...')
-        SentenceTransformer('BAAI/bge-small-en-v1.5')
-        print('Model downloaded successfully')
-        "
-
-    - name: Install hindsight-dev dependencies
-      run: |
-        cd hindsight-dev && uv sync --frozen --all-extras --index-strategy unsafe-best-match
-
-    - name: Run perf-test
-      run: |
-        SUITE_ARG=""
-        if [ -n "${{ inputs.suite }}" ]; then
-          SUITE_ARG="--suite ${{ inputs.suite }}"
-        fi
-        ./scripts/benchmarks/run-perf-test.sh \
-          --scale ${{ inputs.scale || 'large' }} \
-          $SUITE_ARG \
-          --output perf-results.json
-
-    - name: Upload perf results
-      if: always()
-      uses: actions/upload-artifact@v7
-      with:
-        name: perf-results-${{ github.sha }}
-        path: hindsight-dev/perf-results.json
-        retention-days: 90
-
-    # Publish enriched results (perf JSON + commit metadata) to the dashboard
-    # repo's gh-pages branch. The static site at
-    #   https://vectorize-io.github.io/hindsight-continuous-performance-monitor/
-    # reads data/index.json + data/<run>.json and renders charts client-side.
-    - name: Publish to dashboard
-      if: github.event_name == 'schedule' || github.event_name == 'push' || github.event_name == 'workflow_dispatch'
-      env:
-        PERF_DASHBOARD_TOKEN: ${{ secrets.PERF_DASHBOARD_TOKEN }}
-        GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      run: ./scripts/benchmarks/publish-perf-results.sh hindsight-dev/perf-results.json
-
-  locomo:
-    if: inputs.locomo_skip != true
-    runs-on: ubuntu-latest
-    env:
-      HINDSIGHT_API_LLM_PROVIDER: vertexai
-      HINDSIGHT_API_LLM_VERTEXAI_SERVICE_ACCOUNT_KEY: /tmp/gcp-credentials.json
-      HINDSIGHT_API_LLM_MODEL: google/gemini-2.5-flash-lite
-      HINDSIGHT_API_JUDGE_LLM_PROVIDER: vertexai
-      HINDSIGHT_API_JUDGE_LLM_MODEL: google/gemini-2.5-flash-lite
-      HINDSIGHT_API_ANSWER_LLM_PROVIDER: vertexai
-      HINDSIGHT_API_ANSWER_LLM_MODEL: google/gemini-2.5-flash
-    steps:
-    - uses: actions/checkout@v6
-      with:
-        ref: ${{ inputs.ref || github.ref }}
-
-    - name: Setup GCP credentials
-      run: |
-        printf '%s' '${{ secrets.GCP_VERTEXAI_CREDENTIALS }}' > /tmp/gcp-credentials.json
-        PROJECT_ID=$(jq -r '.project_id' /tmp/gcp-credentials.json)
-        echo "HINDSIGHT_API_LLM_VERTEXAI_PROJECT_ID=$PROJECT_ID" >> $GITHUB_ENV
-
-    - name: Install uv
-      uses: astral-sh/setup-uv@v7
-      with:
-        enable-cache: true
-        prune-cache: false
-
-    - name: Set up Python
-      uses: actions/setup-python@v6
-      with:
-        python-version-file: ".python-version"
-
-    - name: Cache HuggingFace models
-      uses: actions/cache@v5
-      with:
-        path: ~/.cache/huggingface
-        key: ${{ runner.os }}-huggingface-${{ hashFiles('hindsight-api-slim/pyproject.toml') }}
-        restore-keys: |
-          ${{ runner.os }}-huggingface-
-
-    - name: Pre-download models
-      working-directory: ./hindsight-api-slim
-      run: |
-        uv run --frozen --all-extras --index-strategy unsafe-best-match python -c "
-        from sentence_transformers import SentenceTransformer
-        print('Downloading embedding model...')
-        SentenceTransformer('BAAI/bge-small-en-v1.5')
-        print('Model downloaded successfully')
-        "
-
-    - name: Install hindsight-dev dependencies
-      run: |
-        cd hindsight-dev && uv sync --frozen --all-extras --index-strategy unsafe-best-match
-
-    - name: Run LoComo benchmark
-      # Curated 3-conversation subset (best/middle/worst by accuracy on the
-      # last successful full run): conv-26 (best), conv-30 (middle), conv-43
-      # (worst). Excludes conv-44, the bank with the largest unconsolidated
-      # set that has been pushing scheduled runs over the per-bank
-      # _wait_for_consolidation timeout. Override via workflow_dispatch with
-      # the locomo_conversations input.
-      run: |
-        CONVERSATIONS="${{ inputs.locomo_conversations }}"
-        if [ -z "$CONVERSATIONS" ]; then
-          CONVERSATIONS="conv-26 conv-30 conv-43"
-        fi
-        uv run python hindsight-dev/benchmarks/locomo/locomo_benchmark.py \
-          --wait-consolidation \
-          --conversation $CONVERSATIONS
-
-    - name: Upload LoComo results
-      if: always()
-      uses: actions/upload-artifact@v7
-      with:
-        name: locomo-results-${{ github.sha }}
-        path: hindsight-dev/benchmarks/locomo/results/
-        retention-days: 90
-
-    - name: Publish LoComo to dashboard
-      if: success() && (github.event_name == 'schedule' || github.event_name == 'push' || github.event_name == 'workflow_dispatch')
-      env:
-        PERF_DASHBOARD_TOKEN: ${{ secrets.PERF_DASHBOARD_TOKEN }}
-        GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      run: ./scripts/benchmarks/publish-locomo-results.sh hindsight-dev/benchmarks/locomo/results/benchmark_results.json
@@ -81,28 +81,8 @@ jobs:
      with:
        node-version: '22'
        registry-url: 'https://registry.npmjs.org'
-        cache: 'npm'
-        cache-dependency-path: package-lock.json

-    - name: Check integration lockfile
-      if: steps.type.outputs.type == 'typescript'
-      run: ./scripts/check-integration-lockfiles.sh
-
-    # Some integrations depend on workspace packages (hindsight-client,
-    # hindsight-all, hindsight-agent-sdk) via file: refs. Install from root
-    # so npm resolves them, then build the workspace deps before the integration.
-    - name: Install root workspace dependencies
-      if: steps.type.outputs.type == 'typescript'
-      run: npm ci
-
-    - name: Build workspace deps (hindsight-client, hindsight-all, hindsight-agent-sdk)
-      if: steps.type.outputs.type == 'typescript'
-      run: |
-        npm run build --workspace=hindsight-clients/typescript
-        npm run build --workspace=hindsight-all-npm
-        npm run build --workspace=hindsight-tools/hindsight-agent-sdk
-
-    - name: Install integration dependencies
+    - name: Install dependencies
      if: steps.type.outputs.type == 'typescript'
      working-directory: ./hindsight-integrations/${{ steps.info.outputs.integration }}
      run: npm ci
@@ -117,7 +97,7 @@ jobs:
      working-directory: ./hindsight-integrations/${{ steps.info.outputs.integration }}
      run: |
        set +e
-        OUTPUT=$(npm publish --access public --provenance 2>&1)
+        OUTPUT=$(npm publish --access public 2>&1)
        EXIT_CODE=$?
        echo "$OUTPUT"
        if [ $EXIT_CODE -ne 0 ]; then
@@ -1,65 +0,0 @@
-name: Release Tool
-
-on:
-  push:
-    tags:
-      - 'tools/**'
-
-jobs:
-  publish:
-    runs-on: ubuntu-latest
-
-    steps:
-    - uses: actions/checkout@v6
-
-    - name: Extract tool info
-      id: info
-      run: |
-        # refs/tags/tools/self-driving-agents/v0.0.1 → tool=self-driving-agents, version=0.0.1
-        TAG="${GITHUB_REF#refs/tags/}"
-        TOOL=$(echo "$TAG" | cut -d'/' -f2)
-        VERSION=$(echo "$TAG" | cut -d'/' -f3 | sed 's/^v//')
-        echo "tool=$TOOL" >> $GITHUB_OUTPUT
-        echo "version=$VERSION" >> $GITHUB_OUTPUT
-        echo "tag=$TAG" >> $GITHUB_OUTPUT
-        echo "Tool: $TOOL, Version: $VERSION"
-
-    - name: Set up Node.js
-      uses: actions/setup-node@v6
-      with:
-        node-version: '22'
-        registry-url: 'https://registry.npmjs.org'
-        cache: 'npm'
-        cache-dependency-path: package-lock.json
-
-    # Tools live under hindsight-tools/ and may depend on workspace packages
-    # (e.g. @vectorize-io/hindsight-client). Install from root so npm resolves
-    # workspace deps, then build any required workspace packages first.
-    - name: Install root workspace dependencies
-      run: npm ci
-
-    - name: Build hindsight-client (workspace dep)
-      run: npm run build --workspace=hindsight-clients/typescript
-
-    - name: Build hindsight-agent-sdk (workspace dep)
-      run: npm run build --workspace=hindsight-tools/hindsight-agent-sdk
-
-    - name: Build tool
-      run: npm run build --workspace=hindsight-tools/${{ steps.info.outputs.tool }}
-
-    - name: Publish to npm
-      working-directory: ./hindsight-tools/${{ steps.info.outputs.tool }}
-      run: |
-        set +e
-        OUTPUT=$(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 }}
@@ -150,55 +150,6 @@ jobs:
        path: hindsight-clients/typescript/*.tgz
        retention-days: 1

-  release-hindsight-all-npm:
-    runs-on: ubuntu-latest
-    environment: npm
-
-    steps:
-    - uses: actions/checkout@v6
-
-    - name: Set up Node.js
-      uses: actions/setup-node@v6
-      with:
-        node-version: '22'
-        registry-url: 'https://registry.npmjs.org'
-        cache: 'npm'
-        cache-dependency-path: package-lock.json
-
-    - name: Install dependencies
-      run: npm ci --workspace=hindsight-all-npm
-
-    - name: Build
-      run: npm run build --workspace=hindsight-all-npm
-
-    - name: Publish to npm
-      working-directory: ./hindsight-all-npm
-      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-all-npm
-      run: npm pack
-
-    - name: Upload artifacts
-      uses: actions/upload-artifact@v7
-      with:
-        name: hindsight-all-npm
-        path: hindsight-all-npm/*.tgz
-        retention-days: 1
-
  release-control-plane:
    runs-on: ubuntu-latest
    environment: npm
@@ -314,7 +265,6 @@ jobs:
    permissions:
      contents: read
      packages: write
-      id-token: write
    strategy:
      matrix:
        include:
@@ -411,7 +361,6 @@ jobs:

    # Build multi-platform and push to release tags
    - name: Build and push release images
-      id: build
      uses: docker/build-push-action@v7
      with:
        context: .
@@ -423,31 +372,6 @@ jobs:
        tags: ${{ steps.meta.outputs.tags }}
        labels: ${{ steps.meta.outputs.labels }}

-    - name: Install cosign
-      uses: sigstore/cosign-installer@v3
-
-    - name: Sign published images
-      env:
-        TAGS: ${{ steps.meta.outputs.tags }}
-        DIGEST: ${{ steps.build.outputs.digest }}
-      run: |
-        set -euo pipefail
-        refs=()
-        while IFS= read -r tag; do
-          [[ -z "${tag}" ]] && continue
-          refs+=("${tag}@${DIGEST}")
-        done <<< "${TAGS}"
-        cosign sign --yes "${refs[@]}"
-
-    - name: Verify signature on primary tag
-      env:
-        IMAGE: ghcr.io/${{ github.repository_owner }}/${{ matrix.image_name }}
-        DIGEST: ${{ steps.build.outputs.digest }}
-      run: |
-        cosign verify "${IMAGE}@${DIGEST}" \
-          --certificate-identity-regexp "^https://github\.com/${{ github.repository }}/\.github/workflows/release\.yml@.*" \
-          --certificate-oidc-issuer https://token.actions.githubusercontent.com
-
  release-helm-chart:
    runs-on: ubuntu-latest
    permissions:
@@ -483,7 +407,7 @@ jobs:

  create-github-release:
    runs-on: ubuntu-latest
-    needs: [release-python-packages, release-typescript-client, release-hindsight-all-npm, release-control-plane, release-rust-cli, release-docker-images, release-helm-chart]
+    needs: [release-python-packages, release-typescript-client, release-control-plane, release-rust-cli, release-docker-images, release-helm-chart]
    permissions:
      contents: write

@@ -512,24 +436,12 @@ jobs:
        name: control-plane
        path: ./artifacts/control-plane

-    - name: Download hindsight-embed npm wrapper
-      uses: actions/download-artifact@v8
-      with:
-        name: hindsight-all-npm
-        path: ./artifacts/hindsight-all-npm
-
    - name: Download Rust CLI (Linux)
      uses: actions/download-artifact@v8
      with:
        name: rust-cli-hindsight-linux-amd64
        path: ./artifacts/rust-cli-linux

-    - name: Download Rust CLI (Linux ARM)
-      uses: actions/download-artifact@v8
-      with:
-        name: rust-cli-hindsight-linux-arm64
-        path: ./artifacts/rust-cli-linux-arm64
-
    - name: Download Rust CLI (macOS Intel)
      uses: actions/download-artifact@v8
      with:
@@ -560,13 +472,10 @@ jobs:
        cp artifacts/python-packages/hindsight-embed/dist/* release-assets/ || true
        # TypeScript client
        cp artifacts/typescript-client/*.tgz release-assets/ || true
-        # hindsight-embed npm wrapper
-        cp artifacts/hindsight-all-npm/*.tgz release-assets/ || true
        # Control Plane
        cp artifacts/control-plane/*.tgz release-assets/ || true
        # Rust CLI binaries
        cp artifacts/rust-cli-linux/hindsight-linux-amd64 release-assets/ || true
-        cp artifacts/rust-cli-linux-arm64/hindsight-linux-arm64 release-assets/ || true
        cp artifacts/rust-cli-darwin-amd64/hindsight-darwin-amd64 release-assets/ || true
        cp artifacts/rust-cli-darwin-arm64/hindsight-darwin-arm64 release-assets/ || true
        # Helm chart
@@ -574,7 +483,7 @@ jobs:
        ls -la release-assets/

    - name: Create GitHub Release
-      uses: softprops/action-gh-release@v3
+      uses: softprops/action-gh-release@v2
      with:
        files: release-assets/*
        generate_release_notes: true
@@ -1,71 +0,0 @@
-name: Sign published images
-
-on:
-  workflow_dispatch:
-    inputs:
-      version:
-        description: 'Version to sign (without leading v, e.g. 0.6.0)'
-        required: true
-        type: string
-        default: '0.6.0'
-
-permissions:
-  contents: read
-  packages: write
-  id-token: write
-
-jobs:
-  sign:
-    name: Sign ${{ matrix.image }}:${{ inputs.version }}${{ matrix.suffix }}
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: false
-      matrix:
-        include:
-          - { image: hindsight-api, suffix: '' }
-          - { image: hindsight-api, suffix: '-slim' }
-          - { image: hindsight-control-plane, suffix: '' }
-          - { image: hindsight, suffix: '' }
-          - { image: hindsight, suffix: '-slim' }
-
-    steps:
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v4
-
-      - name: Log in to GHCR
-        uses: docker/login-action@v4
-        with:
-          registry: ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Install cosign
-        uses: sigstore/cosign-installer@v3
-
-      - name: Resolve image digest
-        id: resolve
-        env:
-          IMAGE: ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}
-          TAG: ${{ inputs.version }}${{ matrix.suffix }}
-        run: |
-          set -euo pipefail
-          DIGEST=$(docker buildx imagetools inspect "${IMAGE}:${TAG}" --format '{{json .Manifest.Digest}}' | tr -d '"')
-          if [[ -z "${DIGEST}" || "${DIGEST}" != sha256:* ]]; then
-            echo "Failed to resolve digest for ${IMAGE}:${TAG} (got: ${DIGEST})" >&2
-            exit 1
-          fi
-          echo "Resolved ${IMAGE}:${TAG} -> ${DIGEST}"
-          echo "ref=${IMAGE}@${DIGEST}" >> "$GITHUB_OUTPUT"
-
-      - name: Sign image
-        env:
-          REF: ${{ steps.resolve.outputs.ref }}
-        run: cosign sign --yes "${REF}"
-
-      - name: Verify signature
-        env:
-          REF: ${{ steps.resolve.outputs.ref }}
-        run: |
-          cosign verify "${REF}" \
-            --certificate-identity-regexp "^https://github\.com/${{ github.repository }}/\.github/workflows/sign-images\.yml@.*" \
-            --certificate-oidc-issuer https://token.actions.githubusercontent.com
@@ -1,7 +0,0 @@
-{
-  "semi": true,
-  "singleQuote": false,
-  "tabWidth": 2,
-  "trailingComma": "es5",
-  "printWidth": 100
-}
@@ -68,9 +68,8 @@ cd hindsight-control-plane && npm run dev
 ./scripts/benchmarks/run-locomo.sh

 # Performance benchmarks
-./scripts/benchmarks/run-perf-test.sh                      # System perf (mock LLM + pg0)
-./scripts/benchmarks/run-perf-test.sh --scale tiny          # Quick smoke test
 ./scripts/benchmarks/run-consolidation.sh
+./scripts/benchmarks/run-retain-perf.sh --document <path>  # Requires API server running

 # Results viewer
 ./scripts/benchmarks/start-visualizer.sh  # View results at localhost:8001
@@ -123,17 +122,12 @@ Key tables: `banks`, `memory_units`, `documents`, `entities`, `entity_links`

 ### Adding Database Migrations

-Hindsight runs the same Alembic tree against PostgreSQL and Oracle 23ai. Each
-migration file dispatches through `run_for_dialect`, which calls either
-`_pg_upgrade` or `_oracle_upgrade` based on the live connection. A pytest lint
-(`tests/test_migration_shape.py`) fails CI if a migration omits the dispatcher.
-
 1. **Create a new migration file** in `hindsight-api-slim/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

-2. **Migration template** (the `script.py.mako` template scaffolds this; fill in the bodies):
+2. **Migration template**:
   ```python
   """Description of the migration

@@ -144,58 +138,25 @@ migration file dispatches through `run_for_dialect`, which calls either
   from collections.abc import Sequence
   from alembic import context, op

-   from hindsight_api.alembic._dialect import run_for_dialect
-
   revision: str = "f1a2b3c4d5e6"
   down_revision: str | Sequence[str] | None = "<previous_revision_id>"
   branch_labels: str | Sequence[str] | None = None
   depends_on: str | Sequence[str] | None = None

-
-   def _pg_schema_prefix() -> str:
-       """Schema-qualifier for raw SQL on PG (multi-tenant search_path)."""
+   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 _pg_upgrade() -> None:
-       schema = _pg_schema_prefix()
+   def upgrade() -> None:
+       schema = _get_schema_prefix()
       op.execute(f"CREATE INDEX ... ON {schema}table_name(...)")

-
-   def _pg_downgrade() -> None:
-       schema = _pg_schema_prefix()
-       op.execute(f"DROP INDEX IF EXISTS {schema}index_name")
-
-
-   def _oracle_upgrade() -> None:
-       # Oracle 23ai equivalent. Use op.get_bind().exec_driver_sql for forms
-       # that Alembic core does not model (vector/text indexes, partitions).
-       op.execute("CREATE INDEX ... ON table_name(...)")
-
-
-   def _oracle_downgrade() -> None:
-       op.execute("DROP INDEX IF EXISTS index_name")
-
-
-   def upgrade() -> None:
-       run_for_dialect(pg=_pg_upgrade, oracle=_oracle_upgrade)
-
-
   def downgrade() -> None:
-       run_for_dialect(pg=_pg_downgrade, oracle=_oracle_downgrade)
+       schema = _get_schema_prefix()
+       op.execute(f"DROP INDEX IF EXISTS {schema}index_name")
   ```

-   **Dialect-only migrations.** If a change genuinely doesn't apply to one
-   dialect (e.g. enabling `pg_trgm` is PG-only), omit the unused slot:
-   ```python
-   def upgrade() -> None:
-       run_for_dialect(pg=_pg_upgrade)  # oracle slot intentionally absent → no-op
-   ```
-   Make the asymmetry deliberate. Don't leave an Oracle slot empty just because
-   you didn't think about it — copy-pasting a PG migration without the Oracle
-   half is exactly how schemas drift.
-
 3. **Run migrations locally**:
   ```bash
   # Set database URL and run migrations for the base schema plus all tenants
@@ -261,10 +222,6 @@ Every new integration in `hindsight-integrations/` must satisfy all of the follo

 If any of these are missing, the integration is incomplete and must not be pushed or merged.

-### Changelogs
-
-Never add "Unreleased" entries to changelogs (e.g. `hindsight-docs/src/pages/changelog/**`). Changelog entries are written by the release script (`./scripts/release-integration.sh`) when a version is actually cut. If a bug fix or feature needs documenting before release, describe it in the PR/commit — the release tooling will surface it in the published changelog section.
-
 ### Adding New API Configuration Flags

 Configuration follows a hierarchical system: **Global (env vars) → Tenant (via extension) → Bank (database)**.
@@ -84,8 +84,6 @@ cd docker/docker-compose
 docker compose up 
 ```

-> Oracle AI Database is also supported for enterprise deployments with full feature parity. See the [storage documentation](https://hindsight.vectorize.io/developer/storage) for details.
-

 >API: http://localhost:8888
 >UI: http://localhost:9999
@@ -42,16 +42,6 @@
  },
  "workspace": {
    "members": {
-      "hindsight-all-npm": {
-        "packageJson": {
-          "dependencies": [
-            "npm:@types/node@22",
-            "npm:tsup@^8.5.1",
-            "npm:typescript@^5.7.0",
-            "npm:vitest@^4.1.2"
-          ]
-        }
-      },
      "hindsight-clients/typescript": {
        "packageJson": {
          "dependencies": [
@@ -68,7 +58,6 @@
      "hindsight-control-plane": {
        "packageJson": {
          "dependencies": [
-            "npm:@chenglou/pretext@^0.0.3",
            "npm:@eslint/eslintrc@^3.3.3",
            "npm:@eslint/js@^9.39.2",
            "npm:@radix-ui/react-alert-dialog@^1.1.15",
@@ -102,12 +91,11 @@
            "npm:eslint@^9.39.1",
            "npm:[email protected]",
            "npm:next-themes@~0.4.6",
-            "npm:next@^16.1.7",
+            "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-is@^19.2.4",
            "npm:react-markdown@^10.1.0",
            "npm:react18-json-view@~0.2.9",
            "npm:react@^19.2.0",
@@ -145,26 +133,6 @@
            "npm:typescript@~5.6.2"
          ]
        }
-      },
-      "hindsight-tools/hindsight-agent-sdk": {
-        "packageJson": {
-          "dependencies": [
-            "npm:@vectorize-io/hindsight-client@~0.5.6",
-            "npm:typescript@^5.4.0",
-            "npm:vitest@^4.1.2"
-          ]
-        }
-      },
-      "hindsight-tools/self-driving-agents": {
-        "packageJson": {
-          "dependencies": [
-            "npm:@clack/prompts@^1.2.0",
-            "npm:@vectorize-io/hindsight-client@~0.5.6",
-            "npm:picocolors@^1.1.0",
-            "npm:typescript@^5.4.0",
-            "npm:vitest@^4.1.2"
-          ]
-        }
      }
    }
  }
@@ -1,90 +0,0 @@
-name: hindsight
-# Docker Compose file for Hindsight with AlloyDB Omni and ScaNN
-# Uses Google's free AlloyDB Omni container image: https://hub.docker.com/r/google/alloydbomni
-#
-# Usage:
-# docker compose -f docker/docker-compose/alloydb/docker-compose.yaml up -d
-#
-# Make sure to set the required environment variables before running:
-# - HINDSIGHT_DB_PASSWORD: password for the AlloyDB Omni/PostgreSQL user
-# - Configure LLM provider variables as needed (see the hindsight service below)
-#
-# Optional environment variables with defaults:
-# - HINDSIGHT_VERSION: Hindsight application version (default: latest)
-# - HINDSIGHT_DB_VERSION: AlloyDB Omni image tag (default: 17)
-# - HINDSIGHT_DB_USER: database user (default: hindsight_user)
-# - HINDSIGHT_DB_NAME: database name (default: hindsight_db)
-
-services:
-  db:
-    image: google/alloydbomni:${HINDSIGHT_DB_VERSION:-17}
-    container_name: hindsight-db-alloydb
-    restart: always
-    ports:
-      - "5438:5432"
-    environment:
-      POSTGRES_USER: ${HINDSIGHT_DB_USER:-hindsight_user}
-      POSTGRES_PASSWORD: ${HINDSIGHT_DB_PASSWORD:-hindsight_password}
-      POSTGRES_DB: ${HINDSIGHT_DB_NAME:-hindsight_db}
-    volumes:
-      - alloydb_data:/var/lib/postgresql/data
-    networks:
-      - hindsight-net
-
-  alloydb-init:
-    image: google/alloydbomni:${HINDSIGHT_DB_VERSION:-17}
-    depends_on:
-      - db
-    environment:
-      - PGPASSWORD=${HINDSIGHT_DB_PASSWORD:-hindsight_password}
-    command:
-      - bash
-      - -c
-      - |
-        echo 'Waiting for AlloyDB Omni to be ready...'
-        until pg_isready -h hindsight-db-alloydb -p 5432 -U ${HINDSIGHT_DB_USER:-hindsight_user}; do
-          echo 'AlloyDB Omni is unavailable - sleeping'
-          sleep 2
-        done
-        echo 'AlloyDB Omni is ready - creating ${HINDSIGHT_DB_NAME:-hindsight_db} database'
-        psql -h hindsight-db-alloydb -p 5432 -U ${HINDSIGHT_DB_USER:-hindsight_user} -c 'CREATE DATABASE ${HINDSIGHT_DB_NAME:-hindsight_db};' 2>/dev/null || echo 'Database already exists'
-        echo 'Creating vector and alloydb_scann extensions'
-        psql -h hindsight-db-alloydb -p 5432 -U ${HINDSIGHT_DB_USER:-hindsight_user} -d ${HINDSIGHT_DB_NAME:-hindsight_db} -c 'CREATE EXTENSION IF NOT EXISTS vector;'
-        psql -h hindsight-db-alloydb -p 5432 -U ${HINDSIGHT_DB_USER:-hindsight_user} -d ${HINDSIGHT_DB_NAME:-hindsight_db} -c 'CREATE EXTENSION IF NOT EXISTS alloydb_scann CASCADE;'
-        echo 'Database and extensions created successfully'
-    restart: "no"
-    networks:
-      - hindsight-net
-
-  hindsight:
-    image: ghcr.io/vectorize-io/hindsight:${HINDSIGHT_VERSION:-latest}
-    container_name: hindsight-app
-    ports:
-      - "8888:8888"
-      - "9999:9999"
-    environment:
-      # LLM Configuration
-      HINDSIGHT_API_LLM_PROVIDER: ${HINDSIGHT_API_LLM_PROVIDER:-openai}
-      HINDSIGHT_API_LLM_API_KEY: ${OPENAI_API_KEY:-your-api-key}
-
-      # Database Configuration
-      HINDSIGHT_API_DATABASE_URL: postgresql://${HINDSIGHT_DB_USER:-hindsight_user}:${HINDSIGHT_DB_PASSWORD:-hindsight_password}@db:5432/${HINDSIGHT_DB_NAME:-hindsight_db}
-
-      # Vector and Text Search Extensions
-      HINDSIGHT_API_VECTOR_EXTENSION: scann
-      HINDSIGHT_API_TEXT_SEARCH_EXTENSION: native
-
-    depends_on:
-      db:
-        condition: service_started
-      alloydb-init:
-        condition: service_completed_successfully
-    networks:
-      - hindsight-net
-
-networks:
-  hindsight-net:
-    driver: bridge
-
-volumes:
-  alloydb_data:
@@ -1,34 +0,0 @@
-# Example: custom Hindsight image with non-default local models baked in.
-#
-# Use this pattern in production when you run a non-default embedder or
-# reranker. Baking models into the image removes the runtime dependency on
-# HuggingFace and lets the container registry handle caching per node, so
-# you don't need a model-cache PVC.
-#
-# Built on top of the slim image so only the deps and models you actually
-# use end up in the final image.
-FROM ghcr.io/vectorize-io/hindsight:latest-slim
-
-# Install the local-ml deps required to load sentence-transformers /
-# cross-encoder models at runtime. Pinned ranges mirror hindsight-api-slim's
-# `local-ml` extra in hindsight-api-slim/pyproject.toml. Use `uv pip
-# install` against the image's venv explicitly: the slim image's venv was
-# created by `uv sync` and does not ship its own `pip`, so a bare
-# `pip install` would fall back to user site-packages and not be visible
-# to the runtime python.
-RUN uv pip install --python /app/api/.venv/bin/python --no-cache \
-    'sentence-transformers>=3.3.0' \
-    'transformers>=4.53.0' \
-    'torch>=2.6.0'
-
-# Pre-download the models you want to use. Replace these with your own.
-# The defaults bundled in the full image are BAAI/bge-small-en-v1.5 and
-# cross-encoder/ms-marco-MiniLM-L-6-v2; here we pick multilingual variants
-# as a concrete non-default example.
-ARG EMBEDDER=sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
-ARG RERANKER=cross-encoder/mmarco-mMiniLMv2-L12-H384-v1
-ENV HF_HUB_DOWNLOAD_TIMEOUT=600
-RUN python -c "\
-from sentence_transformers import SentenceTransformer, CrossEncoder; \
-SentenceTransformer('${EMBEDDER}'); \
-CrossEncoder('${RERANKER}')"
@@ -1,81 +0,0 @@
-# Hindsight with Custom Local Models
-
-Example Docker Compose setup that builds a Hindsight image with **non-default
-local embedder and reranker models baked in at build time**.
-
-This is the recommended pattern for production when you use a non-default
-local model: the container registry caches model layers per node, pod
-startup is deterministic, and you don't need a model-cache PVC (or any
-runtime dependency on HuggingFace).
-
-## When to use this
-
- You override `HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL` or
-  `HINDSIGHT_API_RERANKER_LOCAL_MODEL` to a non-default model.
- You want pod startup to be deterministic and offline-capable.
- You'd otherwise reach for a Helm `modelCache` PVC just to avoid
-  re-downloading models.
-
-If you're using the **default** local models, the published full image
-(`ghcr.io/vectorize-io/hindsight:latest`) already bakes them in — you don't
-need this example.
-
-If you're using **external** providers (TEI, OpenAI, Cohere, ...) for
-embeddings and reranking, use the slim image directly — no models are
-needed in the image.
-
-## Quick start
-
-```bash
-export OPENAI_API_KEY=sk-xxx
-
-docker compose -f docker/docker-compose/custom-models/docker-compose.yaml up --build
-```
-
- API: http://localhost:8888
- Control Plane: http://localhost:9999
-
-## Using your own models
-
-Override the build args to bake different models:
-
-```bash
-docker compose -f docker/docker-compose/custom-models/docker-compose.yaml build \
-  --build-arg EMBEDDER=your-org/your-embedder \
-  --build-arg RERANKER=your-org/your-reranker
-```
-
-Then update the matching `HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL` and
-`HINDSIGHT_API_RERANKER_LOCAL_MODEL` values in `docker-compose.yaml` so the
-runtime points at the same model IDs.
-
-## Verifying the models are baked in
-
-`docker-compose.yaml` sets `HF_HUB_OFFLINE=1` and `TRANSFORMERS_OFFLINE=1`
-so that any attempt to download a model at runtime fails loudly instead of
-silently re-downloading. If the container starts and serves recall queries
-with these set, the models are correctly baked in.
-
-You can also inspect the image directly:
-
-```bash
-docker run --rm --entrypoint sh hindsight-custom-models-hindsight \
-  -c 'ls ~/.cache/huggingface/hub/'
-```
-
-## Why not a model-cache PVC?
-
-The Helm chart exposes an optional `api.persistence.modelCache` PVC for
-caching downloaded models across pod restarts. Compared to baking models
-into the image:
-
- A PVC adds storage cost — one PVC per worker replica with
-  `volumeClaimTemplates`.
- `ReadWriteOnce` (the default) pins pods to a node.
- The PVC needs lifecycle management on `helm uninstall` / `helm upgrade`
-  — without `helm.sh/resource-policy: keep` it is deleted on uninstall;
-  with it, storage keeps billing forever until manually cleaned up.
- Pod startup still depends on HuggingFace being reachable on first run.
-
-Image layers, by contrast, are pulled once per node and cached for free by
-the container runtime, with no orphaned-storage cleanup story.
@@ -1,44 +0,0 @@
-name: hindsight-custom-models
-# Example: run a custom Hindsight image with non-default local models baked
-# in at build time, so pod startup does not depend on HuggingFace at runtime.
-#
-# Quick start:
-#   export OPENAI_API_KEY=sk-xxx
-#   docker compose -f docker/docker-compose/custom-models/docker-compose.yaml up --build
-#
-# Required environment variables:
-# - OPENAI_API_KEY (or configure another LLM provider via HINDSIGHT_API_LLM_*)
-
-services:
-  hindsight:
-    build:
-      context: .
-      dockerfile: Dockerfile
-      # Override at build time to bake different models:
-      #   docker compose build --build-arg EMBEDDER=your-org/your-embedder
-      args:
-        EMBEDDER: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
-        RERANKER: cross-encoder/mmarco-mMiniLMv2-L12-H384-v1
-    container_name: hindsight-custom-models
-    ports:
-      - "8888:8888"
-      - "9999:9999"
-    environment:
-      HINDSIGHT_API_LLM_PROVIDER: ${HINDSIGHT_API_LLM_PROVIDER:-openai}
-      HINDSIGHT_API_LLM_API_KEY: ${OPENAI_API_KEY:-your-api-key}
-
-      # Point Hindsight at the models baked into the image above.
-      HINDSIGHT_API_EMBEDDINGS_PROVIDER: local
-      HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
-      HINDSIGHT_API_RERANKER_PROVIDER: local
-      HINDSIGHT_API_RERANKER_LOCAL_MODEL: cross-encoder/mmarco-mMiniLMv2-L12-H384-v1
-
-      # Fail fast if a model is missing from the image instead of silently
-      # falling back to a HuggingFace download at runtime.
-      HF_HUB_OFFLINE: "1"
-      TRANSFORMERS_OFFLINE: "1"
-    volumes:
-      - pg_data:/home/hindsight/.pg0
-
-volumes:
-  pg_data:
@@ -51,8 +51,6 @@ services:

      # Control Plane config
      HINDSIGHT_CP_DATAPLANE_API_URL: http://localhost:8888
-      # Optional: Require a shared access key for Control Plane UI access
-      # HINDSIGHT_CP_ACCESS_KEY: your-secret-key
    volumes:
      # Persist embedded pg0 database
      - hindsight_data:/app/data
@@ -172,10 +172,6 @@ USER hindsight
 # "Permission denied" error when mounting a fresh root-owned volume.
 RUN mkdir -p /home/hindsight/.pg0

-# Make /home/hindsight traversable when running with --user UID:GID overrides
-# (default 0700 blocks traversal by non-owner UIDs needed for bind-mount ownership matching)
-RUN chmod 755 /home/hindsight
-
 ENV PATH="/app/api/.venv/bin:${PATH}"

 # Pre-download tiktoken encoding (ALWAYS - required for token counting even in air-gapped envs)
@@ -332,10 +328,6 @@ USER hindsight
 # "Permission denied" error when mounting a fresh root-owned volume.
 RUN mkdir -p /home/hindsight/.pg0

-# Make /home/hindsight traversable when running with --user UID:GID overrides
-# (default 0700 blocks traversal by non-owner UIDs needed for bind-mount ownership matching)
-RUN chmod 755 /home/hindsight
-
 ENV PATH="/app/api/.venv/bin:${PATH}"

 # Pre-download tiktoken encoding (ALWAYS - required for token counting even in air-gapped envs)
@@ -2,8 +2,8 @@ apiVersion: v2
 name: hindsight
 description: Hindsight helm chart
 type: application
-version: 0.6.1
-appVersion: "0.6.1"
+version: 0.4.22
+appVersion: "0.4.22"
 keywords:
  - ai
  - memory
@@ -70,12 +70,6 @@ api:
  # Persistent volume for local model cache (reranker, embeddings)
  # Models are downloaded to /home/hindsight/.cache on first use.
  # Without persistence, models are re-downloaded on every pod restart.
-  #
-  # For production, prefer baking models into a custom image instead of
-  # enabling this PVC: image layers are pulled once per node and cached
-  # for free, while a PVC adds storage cost, pins pods to a node
-  # (ReadWriteOnce), and needs lifecycle management on uninstall/upgrade.
-  # See docs: developer/installation#bundling-custom-models-in-a-custom-image
  persistence:
    modelCache:
      enabled: false
@@ -174,10 +168,7 @@ worker:
  # affinity: {}

  # Persistent volume for local model cache (reranker, embeddings)
-  # Uses volumeClaimTemplates since worker is a StatefulSet — one PVC per
-  # replica. For production, prefer baking models into a custom image; see
-  # api.persistence.modelCache above and docs:
-  # developer/installation#bundling-custom-models-in-a-custom-image
+  # Uses volumeClaimTemplates since worker is a StatefulSet.
  persistence:
    modelCache:
      enabled: false
@@ -1,4 +0,0 @@
-node_modules
-dist
-*.tgz
-.DS_Store
@@ -1,80 +0,0 @@
-# @vectorize-io/hindsight-all
-
-Node.js equivalent of the Python [`hindsight-all`](https://pypi.org/project/hindsight-all/) package — programmatic lifecycle manager for a local Hindsight daemon. Use this when you want to embed Hindsight in a Node application without hand-rolling subprocess management.
-
-This package deliberately does **not** ship an HTTP client. Once the daemon is running, talk to it with [`@vectorize-io/hindsight-client`](https://www.npmjs.com/package/@vectorize-io/hindsight-client) against `server.getBaseUrl()`. The two packages compose — one owns the daemon process, the other owns the HTTP API surface.
-
-## Requirements
-
- **Node.js >= 22** — uses global `fetch` and `AbortSignal.timeout`.
- **`uv` / `uvx`** on `PATH` — used to download and run the underlying `hindsight-embed` daemon on first use. Install via <https://docs.astral.sh/uv/>.
-
-## Install
-
-```bash
-npm install @vectorize-io/hindsight-all @vectorize-io/hindsight-client
-```
-
-## Example
-
-```ts
-import { HindsightServer, consoleLogger } from "@vectorize-io/hindsight-all";
-import { HindsightClient } from "@vectorize-io/hindsight-client";
-
-const server = new HindsightServer({
-  profile: "my-app",
-  port: 9077,
-  env: {
-    HINDSIGHT_API_LLM_PROVIDER: "anthropic",
-    HINDSIGHT_API_LLM_API_KEY: process.env.ANTHROPIC_API_KEY,
-    HINDSIGHT_API_LLM_MODEL: "claude-sonnet-4-20250514",
-    HINDSIGHT_EMBED_DAEMON_IDLE_TIMEOUT: "0",
-  },
-  logger: consoleLogger,
-});
-
-await server.start();
-
-const client = new HindsightClient({ baseUrl: server.getBaseUrl() });
-
-await client.retain("user-123", "User prefers dark mode and concise answers.", {
-  documentId: "pref-2026-04-01",
-});
-
-const recall = await client.recall("user-123", "what are the user preferences?");
-console.log(recall.results);
-
-await server.stop();
-```
-
-For a remote Hindsight API, skip `HindsightServer` entirely and just point `HindsightClient` at the remote URL.
-
-## Open config — forward-compatible with new daemon flags
-
-`HindsightServerOptions` is designed so every new environment variable or CLI flag in the underlying Hindsight daemon can be used without waiting for a wrapper release:
-
- **`env`** accepts an arbitrary `Record<string, string>`. Every entry is exported into the daemon process and written into the profile config via `--env KEY=VALUE`.
- **`extraProfileCreateArgs`** / **`extraDaemonStartArgs`** append raw args to the respective commands.
-
-## Development against a local checkout
-
-If you're hacking on the Python `hindsight-embed` package in the same monorepo, point the server at the local path — it'll use `uv run --directory <path>` instead of `uvx`:
-
-```ts
-new HindsightServer({
-  embedPackagePath: "/path/to/hindsight-embed",
-  // ...
-});
-```
-
-## API surface
-
- `HindsightServer` — daemon lifecycle (`start`, `stop`, `checkHealth`, `getBaseUrl`, `getProfile`).
- `Logger` interface plus `silentLogger` (default) and `consoleLogger` helpers.
- `getEmbedCommand(opts)` — low-level helper that returns the `[cmd, ...args]` tuple used to invoke the underlying Python CLI.
-
-For memory operations (retain, recall, reflect, bank management, stats) use [`@vectorize-io/hindsight-client`](https://www.npmjs.com/package/@vectorize-io/hindsight-client).
-
-## License
-
-MIT
@@ -1,57 +0,0 @@
-{
-  "name": "@vectorize-io/hindsight-all",
-  "version": "0.6.1",
-  "description": "Node.js programmatic lifecycle manager for Hindsight — embeds a local hindsight daemon in a Node application. Pair with @vectorize-io/hindsight-client for memory operations.",
-  "main": "dist/index.js",
-  "types": "dist/index.d.ts",
-  "type": "module",
-  "exports": {
-    ".": {
-      "types": "./dist/index.d.ts",
-      "import": "./dist/index.js"
-    }
-  },
-  "keywords": [
-    "hindsight",
-    "hindsight-all",
-    "memory",
-    "ai",
-    "agent",
-    "long-term-memory",
-    "llm",
-    "embedded-server"
-  ],
-  "author": "Vectorize <[email protected]>",
-  "license": "MIT",
-  "repository": {
-    "type": "git",
-    "url": "https://github.com/vectorize-io/hindsight.git",
-    "directory": "hindsight-all-npm"
-  },
-  "files": [
-    "dist",
-    "README.md"
-  ],
-  "scripts": {
-    "build": "tsup",
-    "dev": "tsup --watch",
-    "clean": "rm -rf dist",
-    "test": "vitest run src",
-    "test:watch": "vitest src",
-    "prepublishOnly": "npm run clean && npm run build"
-  },
-  "devDependencies": {
-    "@types/node": "^22.0.0",
-    "tsup": "^8.5.1",
-    "typescript": "^5.7.0",
-    "vitest": "^4.1.2"
-  },
-  "engines": {
-    "node": ">=22"
-  },
-  "overrides": {
-    "rollup": "^4.59.0",
-    "picomatch": ">=2.3.2 <3.0.0 || >=4.0.4",
-    "vite": ">=8.0.5"
-  }
-}
@@ -1,36 +0,0 @@
-import { describe, it, expect } from "vitest";
-import { getEmbedCommand } from "./command.js";
-
-describe("getEmbedCommand", () => {
-  it("defaults to uvx hindsight-embed@latest", () => {
-    expect(getEmbedCommand()).toEqual(["uvx", "hindsight-embed@latest"]);
-  });
-
-  it("honours an explicit version", () => {
-    expect(getEmbedCommand({ embedVersion: "0.5.0" })).toEqual(["uvx", "[email protected]"]);
-  });
-
-  it("treats an empty version as latest", () => {
-    expect(getEmbedCommand({ embedVersion: "" })).toEqual(["uvx", "hindsight-embed@latest"]);
-  });
-
-  it("uses uv run --directory when a local path is given", () => {
-    expect(getEmbedCommand({ embedPackagePath: "/abs/path" })).toEqual([
-      "uv",
-      "run",
-      "--directory",
-      "/abs/path",
-      "hindsight-embed",
-    ]);
-  });
-
-  it("local path takes precedence over version", () => {
-    expect(getEmbedCommand({ embedPackagePath: "/abs/path", embedVersion: "0.5.0" })).toEqual([
-      "uv",
-      "run",
-      "--directory",
-      "/abs/path",
-      "hindsight-embed",
-    ]);
-  });
-});
@@ -1,25 +0,0 @@
-/**
- * Resolve the command that invokes the `hindsight-embed` Python CLI.
- *
- * - If `embedPackagePath` is set, runs the package from a local checkout via
- *   `uv run --directory <path> hindsight-embed`. Used for in-repo development.
- * - Otherwise runs it via `uvx hindsight-embed@<version>` so no global install
- *   is required.
- *
- * Returns the argv as `[command, ...baseArgs]` suitable for `spawn()` /
- * `execFile()` (never shell-interpolated).
- */
-export interface EmbedCommandOptions {
-  /** Version spec passed to uvx (e.g. "latest", "0.5.0"). Default: "latest". */
-  embedVersion?: string;
-  /** Local checkout path. When set, overrides `embedVersion` and uses `uv run`. */
-  embedPackagePath?: string;
-}
-
-export function getEmbedCommand(opts: EmbedCommandOptions = {}): string[] {
-  if (opts.embedPackagePath) {
-    return ["uv", "run", "--directory", opts.embedPackagePath, "hindsight-embed"];
-  }
-  const version = opts.embedVersion && opts.embedVersion.length > 0 ? opts.embedVersion : "latest";
-  return ["uvx", `hindsight-embed@${version}`];
-}
@@ -1,7 +0,0 @@
-export { HindsightServer } from "./server.js";
-export { getEmbedCommand } from "./command.js";
-export { silentLogger, consoleLogger } from "./logger.js";
-
-export type { Logger } from "./logger.js";
-export type { EmbedCommandOptions } from "./command.js";
-export type { HindsightServerOptions } from "./types.js";
@@ -1,29 +0,0 @@
-/**
- * Pluggable logger interface.
- *
- * This package does not own any logging infrastructure — consumers inject
- * whatever they want (console, pino, openclaw's logger, a no-op). The default
- * is silent so embedding this package never adds noise to an unrelated app.
- */
-export interface Logger {
-  debug(msg: string): void;
-  info(msg: string): void;
-  warn(msg: string): void;
-  error(msg: string): void;
-}
-
-/** Logger that drops every call. Used when no logger is passed. */
-export const silentLogger: Logger = {
-  debug: () => {},
-  info: () => {},
-  warn: () => {},
-  error: () => {},
-};
-
-/** Logger that writes to the standard console. Handy for CLIs and tests. */
-export const consoleLogger: Logger = {
-  debug: (msg) => console.debug(msg),
-  info: (msg) => console.log(msg),
-  warn: (msg) => console.warn(msg),
-  error: (msg) => console.error(msg),
-};
@@ -1,35 +0,0 @@
-import { describe, it, expect } from "vitest";
-import { HindsightServer } from "./server.js";
-
-describe("HindsightServer construction", () => {
-  it("defaults base URL to http://127.0.0.1:8888", () => {
-    const server = new HindsightServer();
-    expect(server.getBaseUrl()).toBe("http://127.0.0.1:8888");
-    expect(server.getProfile()).toBe("default");
-  });
-
-  it("honours custom profile, port, and host", () => {
-    const server = new HindsightServer({ profile: "app", port: 9077, host: "0.0.0.0" });
-    expect(server.getProfile()).toBe("app");
-    expect(server.getBaseUrl()).toBe("http://0.0.0.0:9077");
-  });
-
-  it("accepts open env pass-through without complaining about unknown keys", () => {
-    const server = new HindsightServer({
-      env: {
-        HINDSIGHT_API_LLM_PROVIDER: "openai",
-        HINDSIGHT_API_LLM_MODEL: "gpt-4o-mini",
-        // A field that does not exist today — should still be accepted
-        HINDSIGHT_FUTURE_FLAG: "enabled",
-      },
-    });
-    expect(server).toBeInstanceOf(HindsightServer);
-  });
-
-  it("exposes checkHealth that returns false when no daemon is running", async () => {
-    // Random high port that nothing is listening on.
-    const server = new HindsightServer({ port: 1, readyTimeoutMs: 100 });
-    const healthy = await server.checkHealth();
-    expect(healthy).toBe(false);
-  });
-});
@@ -1,322 +0,0 @@
-import { spawn } from "child_process";
-import { getEmbedCommand } from "./command.js";
-import { silentLogger } from "./logger.js";
-import type { Logger } from "./logger.js";
-import type { HindsightServerOptions } from "./types.js";
-
-const DEFAULT_PORT = 8888;
-const DEFAULT_HOST = "127.0.0.1";
-const DEFAULT_PROFILE = "default";
-const DEFAULT_READY_TIMEOUT_MS = 30_000;
-const DEFAULT_READY_POLL_INTERVAL_MS = 1_000;
-
-/**
- * Manages the lifecycle of a local Hindsight daemon from a Node.js process.
- *
- * On {@link start}, this class:
- *   1. Resolves the `hindsight-embed` command (via `uvx` or a local `uv run`).
- *   2. Runs `profile create <name> --merge --port <port> [--env K=V ...]`
- *      with every entry in {@link HindsightServerOptions.env} forwarded as
- *      an `--env` flag.
- *   3. Runs `daemon --profile <name> start` and waits for the start command
- *      to exit.
- *   4. Polls `http://host:port/health` until it returns `200` or the
- *      `readyTimeoutMs` budget is exhausted.
- *
- * On {@link stop}, it runs `daemon --profile <name> stop` and returns once
- * the command exits (or after a short grace period).
- *
- * This is the Node.js equivalent of the Python `hindsight-all` package's
- * `HindsightServer`: a thin programmatic lifecycle wrapper around the
- * Hindsight daemon. It does NOT ship an HTTP client — once `start()`
- * resolves, use `@vectorize-io/hindsight-client` against `getBaseUrl()` for
- * retain / recall / reflect.
- *
- * The class is deliberately transparent about the daemon: new CLI flags or
- * environment variables never require a code change here — callers can pass
- * them via `env`, `extraProfileCreateArgs`, or `extraDaemonStartArgs`.
- */
-export class HindsightServer {
-  private readonly profile: string;
-  private readonly port: number;
-  private readonly host: string;
-  private readonly baseUrl: string;
-  private readonly embedVersion: string | undefined;
-  private readonly embedPackagePath: string | undefined;
-  private readonly userEnv: Record<string, string | undefined>;
-  private readonly extraProfileCreateArgs: string[];
-  private readonly extraDaemonStartArgs: string[];
-  private readonly platformCpuWorkaround: boolean;
-  private readonly readyTimeoutMs: number;
-  private readonly readyPollIntervalMs: number;
-  private readonly logger: Logger;
-
-  constructor(opts: HindsightServerOptions = {}) {
-    this.profile = opts.profile ?? DEFAULT_PROFILE;
-    this.port = opts.port ?? DEFAULT_PORT;
-    this.host = opts.host ?? DEFAULT_HOST;
-    this.baseUrl = `http://${this.host}:${this.port}`;
-    this.embedVersion = opts.embedVersion;
-    this.embedPackagePath = opts.embedPackagePath;
-    this.userEnv = opts.env ?? {};
-    this.extraProfileCreateArgs = opts.extraProfileCreateArgs ?? [];
-    this.extraDaemonStartArgs = opts.extraDaemonStartArgs ?? [];
-    this.platformCpuWorkaround = opts.platformCpuWorkaround ?? process.platform === "darwin";
-    this.readyTimeoutMs = opts.readyTimeoutMs ?? DEFAULT_READY_TIMEOUT_MS;
-    this.readyPollIntervalMs = opts.readyPollIntervalMs ?? DEFAULT_READY_POLL_INTERVAL_MS;
-    this.logger = opts.logger ?? silentLogger;
-  }
-
-  /** The base URL the daemon listens on (`http://host:port`). */
-  getBaseUrl(): string {
-    return this.baseUrl;
-  }
-
-  /** The profile name this server operates on. */
-  getProfile(): string {
-    return this.profile;
-  }
-
-  /**
-   * Ensure the daemon is configured and running. Idempotent — the underlying
-   * `profile create --merge` and `daemon start` commands tolerate re-runs.
-   */
-  async start(): Promise<void> {
-    this.logger.info(`[hindsight] starting daemon for profile "${this.profile}"`);
-
-    const env = this.buildEnv();
-    await this.configureProfile(env);
-    await this.startDaemon(env);
-    await this.waitForReady();
-
-    this.logger.info(`[hindsight] daemon ready at ${this.baseUrl}`);
-  }
-
-  /** Stop the daemon. Never throws — logs and resolves even on failure. */
-  async stop(): Promise<void> {
-    this.logger.info(`[hindsight] stopping daemon for profile "${this.profile}"`);
-
-    const [cmd, ...baseArgs] = getEmbedCommand({
-      embedVersion: this.embedVersion,
-      embedPackagePath: this.embedPackagePath,
-    });
-    const args = [...baseArgs, "daemon", "--profile", this.profile, "stop"];
-
-    const child = spawn(cmd, args, { stdio: "pipe" });
-    this.pipeOutput(child, "daemon.stop");
-
-    await new Promise<void>((resolve) => {
-      const timeout = setTimeout(() => {
-        this.logger.warn(`[hindsight] daemon stop timed out after 5s`);
-        resolve();
-      }, 5_000);
-      child.on("exit", () => {
-        clearTimeout(timeout);
-        this.logger.info(`[hindsight] daemon stopped`);
-        resolve();
-      });
-      child.on("error", (err) => {
-        clearTimeout(timeout);
-        this.logger.warn(`[hindsight] error stopping daemon: ${err.message}`);
-        resolve();
-      });
-    });
-  }
-
-  /** Probe `/health` once with a short timeout. */
-  async checkHealth(): Promise<boolean> {
-    try {
-      const res = await fetch(`${this.baseUrl}/health`, {
-        signal: AbortSignal.timeout(2_000),
-      });
-      return res.ok;
-    } catch {
-      return false;
-    }
-  }
-
-  // -------------------------------------------------------------------------
-  // Internal
-  // -------------------------------------------------------------------------
-
-  /**
-   * Merge the process env, the caller-supplied `env`, and (on macOS) the
-   * embeddings CPU workaround. Caller-supplied values always win over the
-   * workaround; undefined values are dropped.
-   */
-  private buildEnv(): NodeJS.ProcessEnv {
-    const merged: NodeJS.ProcessEnv = { ...process.env };
-
-    if (this.platformCpuWorkaround && process.platform === "darwin") {
-      merged["HINDSIGHT_API_EMBEDDINGS_LOCAL_FORCE_CPU"] = "1";
-      merged["HINDSIGHT_API_RERANKER_LOCAL_FORCE_CPU"] = "1";
-    }
-
-    for (const [key, value] of Object.entries(this.userEnv)) {
-      if (value !== undefined) {
-        merged[key] = value;
-      }
-    }
-
-    return merged;
-  }
-
-  /**
-   * Run `profile create <name> --merge --port <port> [--env K=V ...]`.
-   * Every entry in the merged env that was passed via {@link userEnv} (or
-   * auto-applied by the CPU workaround) is forwarded as `--env`.
-   */
-  private async configureProfile(env: NodeJS.ProcessEnv): Promise<void> {
-    this.logger.info(`[hindsight] configuring profile "${this.profile}"`);
-
-    const [cmd, ...baseArgs] = getEmbedCommand({
-      embedVersion: this.embedVersion,
-      embedPackagePath: this.embedPackagePath,
-    });
-    const createArgs = [
-      ...baseArgs,
-      "profile",
-      "create",
-      this.profile,
-      "--merge",
-      "--port",
-      String(this.port),
-    ];
-
-    // Forward every env var that the caller intended for the daemon as --env.
-    // We only forward keys the caller explicitly set (userEnv) plus the CPU
-    // workaround values — not the entire process.env, to avoid leaking random
-    // host state into profile config.
-    const envForProfile = this.collectProfileEnv(env);
-    for (const [key, value] of Object.entries(envForProfile)) {
-      createArgs.push("--env", `${key}=${value}`);
-    }
-
-    createArgs.push(...this.extraProfileCreateArgs);
-
-    await this.runCommand(cmd, createArgs, env, "profile.create");
-  }
-
-  /** Collect only the env vars that should be written into the profile file. */
-  private collectProfileEnv(env: NodeJS.ProcessEnv): Record<string, string> {
-    const out: Record<string, string> = {};
-
-    // 1. User-supplied env — always forwarded.
-    for (const [key, value] of Object.entries(this.userEnv)) {
-      if (value !== undefined) {
-        out[key] = value;
-      }
-    }
-
-    // 2. CPU workaround — only if auto-applied and not already overridden.
-    if (this.platformCpuWorkaround && process.platform === "darwin") {
-      const cpuKeys = [
-        "HINDSIGHT_API_EMBEDDINGS_LOCAL_FORCE_CPU",
-        "HINDSIGHT_API_RERANKER_LOCAL_FORCE_CPU",
-      ];
-      for (const key of cpuKeys) {
-        if (!(key in out) && env[key] !== undefined) {
-          out[key] = env[key] as string;
-        }
-      }
-    }
-
-    return out;
-  }
-
-  private async startDaemon(env: NodeJS.ProcessEnv): Promise<void> {
-    const [cmd, ...baseArgs] = getEmbedCommand({
-      embedVersion: this.embedVersion,
-      embedPackagePath: this.embedPackagePath,
-    });
-    const args = [
-      ...baseArgs,
-      "daemon",
-      "--profile",
-      this.profile,
-      "start",
-      ...this.extraDaemonStartArgs,
-    ];
-
-    await this.runCommand(cmd, args, env, "daemon.start");
-  }
-
-  /**
-   * Spawn `cmd` with `args`, pipe its output through the logger, and resolve
-   * once it exits with code 0. Rejects on non-zero exit or spawn error.
-   */
-  private async runCommand(
-    cmd: string,
-    args: string[],
-    env: NodeJS.ProcessEnv,
-    label: string
-  ): Promise<void> {
-    const child = spawn(cmd, args, { stdio: "pipe", env });
-    let output = "";
-    child.stdout?.on("data", (data: Buffer) => {
-      const text = data.toString();
-      output += text;
-      for (const line of text.trimEnd().split("\n")) {
-        if (line) this.logger.info(`[hindsight:${label}] ${line}`);
-      }
-    });
-    child.stderr?.on("data", (data: Buffer) => {
-      const text = data.toString();
-      output += text;
-      for (const line of text.trimEnd().split("\n")) {
-        if (line) this.logger.warn(`[hindsight:${label}] ${line}`);
-      }
-    });
-
-    await new Promise<void>((resolve, reject) => {
-      child.on("exit", (code) => {
-        if (code === 0) {
-          resolve();
-        } else {
-          reject(new Error(`${label} failed with code ${code}: ${output.trim()}`));
-        }
-      });
-      child.on("error", (err) => {
-        reject(new Error(`${label} failed to spawn: ${err.message}`, { cause: err }));
-      });
-    });
-  }
-
-  /** Stream a spawned child's stdout/stderr through the logger without blocking. */
-  private pipeOutput(child: ReturnType<typeof spawn>, label: string): void {
-    child.stdout?.on("data", (data: Buffer) => {
-      for (const line of data.toString().trimEnd().split("\n")) {
-        if (line) this.logger.info(`[hindsight:${label}] ${line}`);
-      }
-    });
-    child.stderr?.on("data", (data: Buffer) => {
-      for (const line of data.toString().trimEnd().split("\n")) {
-        if (line) this.logger.warn(`[hindsight:${label}] ${line}`);
-      }
-    });
-  }
-
-  /** Poll `/health` until it succeeds or `readyTimeoutMs` elapses. */
-  private async waitForReady(): Promise<void> {
-    const deadline = Date.now() + this.readyTimeoutMs;
-    let attempt = 0;
-    while (Date.now() < deadline) {
-      attempt++;
-      try {
-        const res = await fetch(`${this.baseUrl}/health`, {
-          signal: AbortSignal.timeout(this.readyPollIntervalMs),
-        });
-        if (res.ok) {
-          this.logger.debug(`[hindsight] health check passed (attempt ${attempt})`);
-          return;
-        }
-      } catch {
-        // expected while the daemon is still booting
-      }
-      await new Promise((resolve) => setTimeout(resolve, this.readyPollIntervalMs));
-    }
-    throw new Error(
-      `Hindsight daemon did not become ready within ${this.readyTimeoutMs}ms at ${this.baseUrl}`
-    );
-  }
-}
@@ -1,54 +0,0 @@
-import type { Logger } from "./logger.js";
-
-/**
- * Options for {@link HindsightServer}.
- *
- * The server is intentionally thin and pass-through: anything configurable
- * on the daemon side (env vars or CLI flags) can be set here without needing
- * a new dedicated option. Use {@link env} for `HINDSIGHT_*` / `OPENAI_API_KEY` /
- * custom provider settings, and the two `extra*` arrays to append raw CLI
- * args to `profile create` or `daemon start`.
- *
- * For talking to the daemon after `start()`, use `@vectorize-io/hindsight-client`
- * against `server.getBaseUrl()`. This package does not ship its own HTTP
- * client.
- */
-export interface HindsightServerOptions {
-  /** Profile name used for `--profile <name>` on every sub-command. Default: `"default"`. */
-  profile?: string;
-  /** TCP port the daemon listens on. Default: `8888`. */
-  port?: number;
-  /** Hostname the daemon binds to (for health checks). Default: `127.0.0.1`. */
-  host?: string;
-  /** Version of the underlying `hindsight-embed` PyPI package to run via `uvx`. Default: `"latest"`. */
-  embedVersion?: string;
-  /** Local path to a `hindsight-embed` checkout — takes precedence over `embedVersion`. */
-  embedPackagePath?: string;
-  /**
-   * Environment variables passed to the daemon process AND written into the
-   * profile via repeated `--env KEY=VALUE` flags. This is the preferred way
-   * to surface any `HINDSIGHT_API_*` / `HINDSIGHT_EMBED_*` setting — adding a
-   * new daemon env var never requires a wrapper update.
-   *
-   * Values of `undefined` are dropped (so you can spread conditionally).
-   */
-  env?: Record<string, string | undefined>;
-  /** Extra args appended verbatim to `hindsight-embed profile create <name> --merge ...`. */
-  extraProfileCreateArgs?: string[];
-  /** Extra args appended verbatim to `hindsight-embed daemon --profile <name> start ...`. */
-  extraDaemonStartArgs?: string[];
-  /**
-   * On macOS, automatically set
-   * `HINDSIGHT_API_EMBEDDINGS_LOCAL_FORCE_CPU=1` and
-   * `HINDSIGHT_API_RERANKER_LOCAL_FORCE_CPU=1` to avoid Metal/MPS crashes in
-   * daemon mode. Default: `true` on `darwin`, ignored elsewhere. Any value set
-   * explicitly in {@link env} wins over the auto-applied value.
-   */
-  platformCpuWorkaround?: boolean;
-  /** Max time (ms) to wait for `/health` to return 200. Default: `30_000`. */
-  readyTimeoutMs?: number;
-  /** Polling interval (ms) while waiting for `/health`. Default: `1_000`. */
-  readyPollIntervalMs?: number;
-  /** Optional pluggable logger. Default: silent. */
-  logger?: Logger;
-}
@@ -1,18 +0,0 @@
-{
-  "compilerOptions": {
-    "target": "ES2022",
-    "module": "ES2022",
-    "lib": ["ES2022"],
-    "moduleResolution": "node",
-    "declaration": true,
-    "outDir": "./dist",
-    "rootDir": "./src",
-    "strict": true,
-    "esModuleInterop": true,
-    "skipLibCheck": true,
-    "forceConsistentCasingInFileNames": true,
-    "resolveJsonModule": true
-  },
-  "include": ["src/**/*"],
-  "exclude": ["node_modules", "dist", "src/**/*.test.ts"]
-}
@@ -1,11 +0,0 @@
-import { defineConfig } from "tsup";
-
-export default defineConfig({
-  entry: ["src/index.ts"],
-  format: ["esm"],
-  dts: true,
-  outDir: "dist",
-  clean: true,
-  sourcemap: true,
-  bundle: true,
-});
@@ -1,8 +0,0 @@
-import { defineConfig } from "vitest/config";
-
-export default defineConfig({
-  test: {
-    include: ["src/**/*.test.ts"],
-    environment: "node",
-  },
-});
@@ -4,12 +4,12 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "hindsight-all-slim"
-version = "0.6.1"
+version = "0.4.22"
 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==0.6.1",
+    "hindsight-api-slim>=0.4.17",
    "hindsight-client>=0.0.7",
    "hindsight-embed>=0.1.0",
 ]
@@ -71,7 +71,7 @@ class HindsightEmbedded:
        llm_model: Model name to use
        llm_base_url: Optional custom base URL for LLM API
        database_url: Optional database URL override (default: profile-specific pg0)
-        idle_timeout: Seconds before daemon auto-exits when idle (default: 0, disabled)
+        idle_timeout: Seconds before daemon auto-exits when idle (default: 300)
        log_level: Daemon log level (default: "info")
        ui: Whether to start the control plane web UI alongside the daemon (default: False)
        ui_port: Port for the UI. Defaults to daemon_port + 10000.
@@ -86,7 +86,7 @@ class HindsightEmbedded:
        llm_model: str = "openai/gpt-oss-120b",
        llm_base_url: Optional[str] = None,
        database_url: Optional[str] = None,
-        idle_timeout: int = 0,
+        idle_timeout: int = 300,
        log_level: str = "info",
        ui: bool = False,
        ui_port: Optional[int] = None,
@@ -102,7 +102,7 @@ class HindsightEmbedded:
            llm_model: Model name to use
            llm_base_url: Optional custom base URL for LLM API
            database_url: Optional database URL override
-            idle_timeout: Seconds before daemon auto-exits when idle (0 = disabled)
+            idle_timeout: Seconds before daemon auto-exits when idle
            log_level: Daemon log level
            ui: Whether to start the control plane web UI alongside the daemon
            ui_port: Port for the UI (defaults to daemon_port + 10000)
@@ -142,37 +142,14 @@ class HindsightEmbedded:
        self._memories_api: Optional[MemoriesAPI] = None

    def _ensure_started(self):
-        """Ensure daemon is running (thread-safe), restarting if crashed."""
+        """Ensure daemon is running (thread-safe)."""
        if self._started and self._client is not None:
-            if self._manager.is_running(self.profile):
-                return
-            # Daemon crashed — reset state and fall through to restart
-            logger.warning(
-                "Daemon for profile '%s' is no longer responsive, restarting...",
-                self.profile,
-            )
-            try:
-                self._client.close()
-            except Exception:
-                logger.debug("Error closing stale client", exc_info=True)
-            self._client = None
-            self._started = False
+            return

        with self._lock:
            # Double-check after acquiring lock
            if self._started and self._client is not None:
-                if self._manager.is_running(self.profile):
-                    return
-                logger.warning(
-                    "Daemon for profile '%s' is no longer responsive (lock path), restarting...",
-                    self.profile,
-                )
-                try:
-                    self._client.close()
-                except Exception:
-                    logger.debug("Error closing stale client", exc_info=True)
-                self._client = None
-                self._started = False
+                return

            if self._closed:
                raise RuntimeError(
@@ -213,32 +190,12 @@ class HindsightEmbedded:
        if self._closed:
            return

-        acquired = self._lock.acquire(timeout=5.0)
-        if not acquired:
-            # Lock is held by another thread (e.g. _ensure_started).
-            # Mark closed to prevent new operations but skip shared-state
-            # teardown — the daemon's idle timeout handles the rest.
-            logger.warning(
-                "Cleanup lock acquisition timed out for profile '%s'; "
-                "marking closed, daemon will idle-stop on its own",
-                self.profile,
-            )
-            self._closed = True
-            return
-
-        try:
+        with self._lock:
            if self._closed:
                return

            if self._client is not None:
-                try:
-                    self._client.close()
-                except Exception:
-                    logger.debug(
-                        "Error closing client for profile '%s'",
-                        self.profile,
-                        exc_info=True,
-                    )
+                self._client.close()
                self._client = None

            # Stop UI if it was started
@@ -252,8 +209,6 @@ class HindsightEmbedded:
                self._manager.stop(self.profile)

            self._closed = True
-        finally:
-            self._lock.release()

    def close(self, stop_daemon: bool = False):
        """
@@ -276,10 +231,23 @@ class HindsightEmbedded:
        This allows HindsightEmbedded to expose all HindsightClient methods
        without manually wrapping each one.
        """
-        # Ensure server is started (and restart if crashed) before proxying
+        # Ensure server is started before proxying
        self._ensure_started()

-        return getattr(self._client, name)
+        # Get the attribute from the underlying client
+        attr = getattr(self._client, name)
+
+        # If it's a callable, wrap it to ensure server is started
+        # (shouldn't be needed since _ensure_started already called, but defensive)
+        if callable(attr):
+
+            def wrapper(*args, **kwargs):
+                self._ensure_started()
+                return attr(*args, **kwargs)
+
+            return wrapper
+
+        return attr

    def __enter__(self):
        """Context manager entry - ensures server is started."""
@@ -404,8 +372,11 @@ class HindsightEmbedded:
        """
        Get the underlying Hindsight client for direct access.

-        Ensures daemon is started (and restarts it if it has crashed) before
-        returning the client.
+        WARNING: Using this property directly means daemon restarts won't be
+        handled automatically. Prefer using the API namespaces (banks, mental_models,
+        directives, memories) or direct method calls on HindsightEmbedded instead.
+
+        Ensures daemon is started before returning the client.

        Returns:
            Hindsight: The underlying client instance
@@ -416,8 +387,9 @@ class HindsightEmbedded:

            embedded = HindsightEmbedded(profile="myapp", ...)

+            # Direct access (not recommended - daemon crashes won't be handled)
            client = embedded.client
-            banks = client.list_banks()
+            banks = client.list_banks()  # If daemon crashes, this will fail
            ```
        """
        self._ensure_started()
@@ -431,13 +403,8 @@ class HindsightEmbedded:

    @property
    def is_running(self) -> bool:
-        """Check if the client is initialized and the daemon is responsive."""
-        return (
-            self._started
-            and not self._closed
-            and self._client is not None
-            and self._manager.is_running(self.profile)
-        )
+        """Check if the client is initialized."""
+        return self._started and not self._closed and self._client is not None

    @property
    def ui_url(self) -> str:
@@ -4,12 +4,12 @@ build-backend = "hatchling.build"

 [project]
 name = "hindsight-all"
-version = "0.6.1"
+version = "0.4.22"
 description = "Hindsight: Agent Memory That Works Like Human Memory - All-in-One Bundle"
 readme = "README.md"
 requires-python = ">=3.11"
 dependencies = [
-    "hindsight-api-slim[all]==0.6.1",
+    "hindsight-api-slim[all]>=0.4.17",
    "hindsight-client>=0.0.7",
    "hindsight-embed>=0.1.0",
 ]
@@ -20,9 +20,6 @@ hindsight-client = { workspace = true }
 hindsight-embed = { workspace = true }

 [project.optional-dependencies]
-local-llm = [
-    "hindsight-api-slim[local-llm]==0.6.1",
-]
 test = [
    "pytest>=7.0.0",
    "pytest-asyncio>=0.21.0",
@@ -1,56 +0,0 @@
-"""
-Unit test for _cleanup lock timeout behavior.
-
-Verifies that _cleanup completes even when the lock is held by another thread,
-instead of hanging indefinitely (fixes #952).
-"""
-
-import threading
-import time
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-
-def test_cleanup_completes_when_lock_held():
-    """
-    _cleanup should complete (best-effort) even when self._lock is held
-    by another thread, e.g. during a long _ensure_started call.
-    """
-    with patch.dict("sys.modules", {
-        "hindsight_client": MagicMock(),
-        "hindsight_embed": MagicMock(),
-        "hindsight.api_namespaces": MagicMock(),
-    }):
-        from hindsight.embedded import HindsightEmbedded
-
-        client = HindsightEmbedded.__new__(HindsightEmbedded)
-        client.profile = "test"
-        client._lock = threading.Lock()
-        client._closed = False
-        client._client = None
-        client._started = False
-        client._ui = False
-
-        # Simulate another thread holding the lock
-        client._lock.acquire()
-
-        cleanup_done = threading.Event()
-
-        def run_cleanup():
-            client._cleanup()
-            cleanup_done.set()
-
-        t = threading.Thread(target=run_cleanup)
-        t.start()
-
-        # Cleanup should complete within the timeout (5s) + margin
-        assert cleanup_done.wait(timeout=8.0), (
-            "_cleanup hung instead of timing out on lock acquisition"
-        )
-
-        # Release the lock from the simulating thread
-        client._lock.release()
-        t.join(timeout=1.0)
-
-        assert client._closed, "Client should be marked as closed after cleanup"
@@ -401,42 +401,3 @@ def test_embedded_ui_flag(llm_config):

    finally:
        client.close()
-
-
-def test_embedded_daemon_crash_recovery(llm_config):
-    """
-    Test that HindsightEmbedded recovers when the daemon crashes.
-
-    Simulates a crash by stopping the daemon, then verifies
-    that the next operation transparently restarts it.
-    """
-    profile = f"test_crash_{uuid.uuid4().hex[:8]}"
-    bank_id = f"bank_{uuid.uuid4().hex[:8]}"
-
-    client = HindsightEmbedded(profile=profile, log_level="info", **llm_config)
-
-    try:
-        # Start daemon and store a memory
-        result = client.retain(bank_id=bank_id, content="Before crash")
-        assert result.success, "Initial retain should succeed"
-        assert client.is_running, "Daemon should be running"
-
-        original_url = client.url
-
-        # Simulate daemon crash by stopping it
-        client._manager.stop(client.profile)
-        assert not client._manager.is_running(client.profile), (
-            "Daemon should be stopped after simulated crash"
-        )
-
-        # Next operation should transparently restart the daemon
-        result2 = client.retain(bank_id=bank_id, content="After crash recovery")
-        assert result2.success, "Retain after crash recovery should succeed"
-        assert client.is_running, "Daemon should be running again after recovery"
-
-        # Verify recall still works
-        recall_result = client.recall(bank_id=bank_id, query="crash")
-        assert isinstance(recall_result.results, list), "Recall should return results"
-
-    finally:
-        client.close()
@@ -46,4 +46,4 @@ __all__ = [
    "RemoteTEICrossEncoder",
    "LLMConfig",
 ]
-__version__ = "0.6.1"
+__version__ = "0.4.22"
@@ -1,170 +0,0 @@
-"""Shared PostgreSQL vector-extension dispatch helpers."""
-
-from __future__ import annotations
-
-import logging
-
-from sqlalchemy import text
-from sqlalchemy.engine import Connection
-
-logger = logging.getLogger(__name__)
-
-# Extensions a user can set via HINDSIGHT_API_VECTOR_EXTENSION.
-CONFIGURABLE_EXTENSIONS = ("pgvector", "pgvectorscale", "vchord", "scann")
-
-# Extensions detect_vector_extension() can return. pg_diskann is a runtime-only
-# resolution from a configured "pgvectorscale" backend on Azure (uses a different
-# WITH clause), never a value the user sets directly.
-RESOLVED_EXTENSIONS = (*CONFIGURABLE_EXTENSIONS, "pg_diskann")
-
-# Backwards-compatible alias for older imports.
-VALID_EXTENSIONS = CONFIGURABLE_EXTENSIONS
-
-SCANN_MIN_ROWS_FOR_AUTO_INDEX = 10_000
-
-
-_EXTENSION_NAMES = {
-    "pgvector": "vector",
-    "pgvectorscale": "vectorscale",
-    "vchord": "vchord",
-    "scann": "alloydb_scann",
-}
-
-_INDEX_USING_CLAUSES = {
-    "pgvector": "USING hnsw (embedding vector_cosine_ops)",
-    "pgvectorscale": "USING diskann (embedding vector_cosine_ops) WITH (num_neighbors = 50)",
-    "pg_diskann": "USING diskann (embedding vector_cosine_ops) WITH (max_neighbors = 50)",
-    "vchord": "USING vchordrq (embedding vector_l2_ops)",
-    "scann": "USING scann (embedding cosine) WITH (mode = 'AUTO')",
-}
-
-_INDEX_TYPE_KEYWORDS = {
-    "pgvector": "hnsw",
-    "pgvectorscale": "diskann",
-    "pg_diskann": "diskann",
-    "vchord": "vchordrq",
-    "scann": "scann",
-}
-
-_EXTENSION_INSTALL_SQL = {
-    "pgvector": ("CREATE EXTENSION IF NOT EXISTS vector",),
-    "pgvectorscale": (
-        "CREATE EXTENSION IF NOT EXISTS vector",
-        "CREATE EXTENSION IF NOT EXISTS vectorscale CASCADE",
-    ),
-    "vchord": ("CREATE EXTENSION IF NOT EXISTS vchord CASCADE",),
-    "scann": (
-        "CREATE EXTENSION IF NOT EXISTS vector",
-        "CREATE EXTENSION IF NOT EXISTS alloydb_scann CASCADE",
-    ),
-}
-
-_INSTALL_HINTS = {
-    "pgvector": "CREATE EXTENSION vector;",
-    "pgvectorscale": "CREATE EXTENSION vector; then CREATE EXTENSION vectorscale CASCADE; (or pg_diskann on Azure)",
-    "vchord": "CREATE EXTENSION vchord CASCADE;",
-    "scann": "CREATE EXTENSION vector; then CREATE EXTENSION alloydb_scann CASCADE;",
-}
-
-
-def validate_extension(name: str) -> str:
-    """Return a normalized configurable vector extension name or raise.
-
-    Used at the user-facing config boundary; pg_diskann is rejected here because
-    it is a detection-time alias, never a value the user sets directly.
-    """
-    ext = name.lower()
-    if ext not in CONFIGURABLE_EXTENSIONS:
-        valid = ", ".join(CONFIGURABLE_EXTENSIONS)
-        raise ValueError(f"Invalid vector_extension: {name}. Must be one of: {valid}")
-    return ext
-
-
-def _normalize_resolved(name: str) -> str:
-    """Normalize either a user-configurable or detect-time extension name."""
-    ext = name.lower()
-    if ext not in RESOLVED_EXTENSIONS:
-        valid = ", ".join(RESOLVED_EXTENSIONS)
-        raise ValueError(f"Unknown vector extension: {name}. Must be one of: {valid}")
-    return ext
-
-
-def pg_extension_name(ext: str) -> str:
-    """Return the PostgreSQL extension name for a configured vector backend."""
-    return _EXTENSION_NAMES[validate_extension(ext)]
-
-
-def index_using_clause(ext: str) -> str:
-    """Return the CREATE INDEX USING clause for the vector backend."""
-    return _INDEX_USING_CLAUSES[_normalize_resolved(ext)]
-
-
-def index_type_keyword(ext: str) -> str:
-    """Return the keyword that identifies this index type in pg_indexes.indexdef."""
-    return _INDEX_TYPE_KEYWORDS[_normalize_resolved(ext)]
-
-
-def minimum_rows_for_index(ext: str) -> int:
-    """Return the minimum populated embedding rows before creating this index type."""
-    return SCANN_MIN_ROWS_FOR_AUTO_INDEX if _normalize_resolved(ext) == "scann" else 0
-
-
-def should_defer_index_creation(ext: str, row_count: int) -> bool:
-    """Return True when index creation should wait for more embeddings."""
-    minimum_rows = minimum_rows_for_index(ext)
-    return minimum_rows > 0 and row_count < minimum_rows
-
-
-def uses_per_bank_vector_indexes(ext: str) -> bool:
-    """Return whether the backend should create per-bank partial vector indexes."""
-    return _normalize_resolved(ext) != "scann"
-
-
-def bootstrap_extension(conn: Connection, ext: str) -> None:
-    """Install the configured vector extension and any prerequisites if possible."""
-    normalized = validate_extension(ext)
-    for statement in _EXTENSION_INSTALL_SQL[normalized]:
-        conn.execute(text(statement))
-
-
-def detect_vector_extension(conn: Connection, vector_extension: str = "pgvector") -> str:
-    """Validate the configured vector extension exists and return the index backend."""
-    configured_ext = validate_extension(vector_extension)
-
-    if configured_ext == "pgvectorscale":
-        pgvector_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vector'")).scalar()
-        if not pgvector_check:
-            raise RuntimeError(
-                "DiskANN (pgvectorscale/pg_diskann) requires pgvector to be installed. "
-                f"Install it with: {_INSTALL_HINTS['pgvectorscale']}"
-            )
-
-        vectorscale_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vectorscale'")).scalar()
-        pg_diskann_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'pg_diskann'")).scalar()
-
-        if vectorscale_check:
-            logger.debug("Using vector extension: pgvectorscale (DiskANN)")
-            return "pgvectorscale"
-        if pg_diskann_check:
-            logger.debug("Using vector extension: pg_diskann (Azure DiskANN)")
-            return "pg_diskann"
-
-        raise RuntimeError(
-            "Configured vector extension 'pgvectorscale' not found. Install either:\n"
-            "  - pgvectorscale (open source): CREATE EXTENSION vectorscale CASCADE;\n"
-            "  - pg_diskann (Azure): CREATE EXTENSION pg_diskann CASCADE;"
-        )
-
-    extension_name = pg_extension_name(configured_ext)
-    extension_check = conn.execute(
-        text("SELECT 1 FROM pg_extension WHERE extname = :extension_name"),
-        {"extension_name": extension_name},
-    ).scalar()
-    if not extension_check:
-        raise RuntimeError(
-            f"Configured vector extension '{configured_ext}' not found. "
-            f"Install it with: {_INSTALL_HINTS[configured_ext]}"
-        )
-
-    logger.debug("Using configured vector extension: %s", configured_ext)
-    return configured_ext
@@ -1,7 +1,5 @@
-"""PostgreSQL-only admin utilities (backup, restore, migration, worker management).
-
-Not supported on Oracle backends. Uses asyncpg.connect() directly, binary COPY,
-TRUNCATE CASCADE, and REFRESH MATERIALIZED VIEW — all inherently PG-specific.
+"""
+Hindsight Admin CLI - backup and restore operations.
 """

 import asyncio
@@ -17,10 +15,15 @@ import asyncpg
 import typer

 from ..config import DEFAULT_DATABASE_SCHEMA, HindsightConfig
-from ..engine.schema import fq_table_explicit as _fq_table
 from ..extensions import TenantExtension, load_extension
 from ..pg0 import parse_pg0_url, resolve_database_url

+
+def _fq_table(table: str, schema: str) -> str:
+    """Get fully-qualified table name with schema prefix."""
+    return f"{schema}.{table}"
+
+
 # Setup logging
 logging.basicConfig(
    level=logging.INFO,
@@ -372,140 +375,6 @@ def decommission_worker(
        typer.echo(f"No tasks found for worker '{worker_id}'")


-async def _decommission_all_workers(db_url: str, schema: str = "public") -> list[dict[str, Any]]:
-    """Release all processing tasks from all workers, setting them back to pending status."""
-    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)
-
-    conn = await asyncpg.connect(resolved_url)
-    try:
-        table = _fq_table("async_operations", schema)
-        rows = await conn.fetch(
-            f"""
-            UPDATE {table}
-            SET status = 'pending', worker_id = NULL, claimed_at = NULL, updated_at = now()
-            WHERE status = 'processing'
-            RETURNING operation_id, worker_id, operation_type
-            """,
-        )
-        return [dict(r) for r in rows]
-    finally:
-        await conn.close()
-
-
-@app.command(name="decommission-workers")
-def decommission_workers(
-    schema: str = typer.Option("public", "--schema", "-s", help="Database schema"),
-    yes: bool = typer.Option(False, "--yes", "-y", help="Skip confirmation prompt"),
-):
-    """Release all processing tasks from all workers (sets status back to pending).
-
-    Use this command to recover from situations where one or more workers have crashed
-    or been removed without graceful shutdown. All tasks currently in 'processing' status
-    will be released back to the queue regardless of which worker owns them.
-    """
-    config = HindsightConfig.from_env()
-
-    if not config.database_url:
-        typer.echo("Error: Database URL not configured.", err=True)
-        typer.echo("Set HINDSIGHT_API_DATABASE_URL environment variable.", err=True)
-        raise typer.Exit(1)
-
-    if not yes:
-        typer.confirm(
-            "This will release ALL processing tasks from ALL workers back to pending. Continue?",
-            abort=True,
-        )
-
-    typer.echo(f"Decommissioning all workers (schema: {schema})...")
-
-    released = asyncio.run(_decommission_all_workers(config.database_url, schema))
-
-    if released:
-        # Group by worker_id for summary
-        by_worker: dict[str, int] = {}
-        for row in released:
-            wid = row["worker_id"] or "unknown"
-            by_worker[wid] = by_worker.get(wid, 0) + 1
-
-        typer.echo(f"Released {len(released)} task(s):")
-        for wid, count in by_worker.items():
-            typer.echo(f"  {wid}: {count} task(s)")
-    else:
-        typer.echo("No processing tasks found")
-
-
-async def _worker_status(db_url: str, schema: str = "public") -> list[dict[str, Any]]:
-    """Get all processing tasks grouped by worker with their last update time."""
-    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)
-
-    conn = await asyncpg.connect(resolved_url)
-    try:
-        table = _fq_table("async_operations", schema)
-        rows = await conn.fetch(
-            f"""
-            SELECT worker_id, operation_id, operation_type, bank_id,
-                   claimed_at, updated_at,
-                   now() - claimed_at AS running_for,
-                   now() - updated_at AS last_update_ago
-            FROM {table}
-            WHERE status = 'processing'
-            ORDER BY worker_id, claimed_at
-            """,
-        )
-        return [dict(r) for r in rows]
-    finally:
-        await conn.close()
-
-
-@app.command(name="worker-status")
-def worker_status(
-    schema: str = typer.Option("public", "--schema", "-s", help="Database schema"),
-):
-    """Show all currently processing tasks grouped by worker.
-
-    Displays each worker's active tasks with operation type, bank, how long
-    the task has been running, and when it was last updated. Useful for
-    identifying dead workers with orphaned tasks.
-    """
-    config = HindsightConfig.from_env()
-
-    if not config.database_url:
-        typer.echo("Error: Database URL not configured.", err=True)
-        typer.echo("Set HINDSIGHT_API_DATABASE_URL environment variable.", err=True)
-        raise typer.Exit(1)
-
-    rows = asyncio.run(_worker_status(config.database_url, schema))
-
-    if not rows:
-        typer.echo("No processing tasks found")
-        return
-
-    # Group by worker_id
-    by_worker: dict[str, list[dict[str, Any]]] = {}
-    for row in rows:
-        wid = row["worker_id"] or "unknown"
-        by_worker.setdefault(wid, []).append(row)
-
-    typer.echo(f"Processing tasks across {len(by_worker)} worker(s):\n")
-    for wid, tasks in by_worker.items():
-        typer.echo(f"Worker: {wid} ({len(tasks)} task(s))")
-        for task in tasks:
-            op_id = str(task["operation_id"])[:8]
-            running_for = task["running_for"]
-            last_update = task["last_update_ago"]
-            typer.echo(
-                f"  {op_id}  {task['operation_type']:<20s} bank={task['bank_id']}"
-                f"  running={running_for}  last_update={last_update} ago"
-            )
-        typer.echo("")
-
-
 def main():
    app()

@@ -1,42 +0,0 @@
-"""Dialect dispatcher for Alembic migrations.
-
-Each migration file declares a ``_pg_upgrade``/``_oracle_upgrade`` (and matching
-downgrades) function and routes ``upgrade()``/``downgrade()`` through
-``run_for_dialect``. The helper inspects the live connection's dialect name and
-runs the matching function — or no-ops if the migration doesn't apply to the
-current backend.
-
-Use ``None`` (or omit the kwarg) when a migration intentionally has no effect
-on a dialect; the helper treats it as a no-op.
-"""
-
-from __future__ import annotations
-
-from collections.abc import Callable
-
-from alembic import op
-
-DialectFn = Callable[[], None]
-_SUPPORTED = ("postgresql", "oracle")
-
-
-def run_for_dialect(
-    *,
-    pg: DialectFn | None = None,
-    oracle: DialectFn | None = None,
-) -> None:
-    """Dispatch to the function matching the current bind's dialect.
-
-    Args:
-        pg: Function to run when the active bind is PostgreSQL.
-        oracle: Function to run when the active bind is Oracle.
-
-    Unrecognized dialects raise; an explicit ``None`` for the active dialect
-    is a no-op (the migration deliberately does nothing here).
-    """
-    name = op.get_bind().dialect.name
-    if name not in _SUPPORTED:
-        raise RuntimeError(f"Unsupported dialect for migration dispatch: {name!r}. Expected one of {_SUPPORTED}.")
-    fn = {"postgresql": pg, "oracle": oracle}[name]
-    if fn is not None:
-        fn()
@@ -1,37 +1,28 @@
 """
-Alembic environment for Hindsight.
-
-Supports two dialects:
-
-* PostgreSQL (sync psycopg2 driver) — default; uses ``search_path`` for
-  multi-tenant schema isolation and forces read-write transactions to work
-  around Supabase's read-only-by-default sessions.
-* Oracle 23ai (``oracledb`` driver) — uses ``CURRENT_SCHEMA`` for tenant
-  isolation; no equivalent of ``search_path`` or read-only session quirks.
-
-Each migration file dispatches its DDL through ``alembic._dialect.run_for_dialect``
-so a single revision tree serves both backends.
+Alembic environment configuration for SQLAlchemy with pgvector.
+Uses synchronous psycopg2 driver for migrations to avoid pgbouncer issues.
 """

 import logging
 import os
 from pathlib import Path
-from urllib.parse import parse_qsl, urlencode, urlsplit, urlunsplit

 from alembic import context
 from dotenv import load_dotenv
-from sqlalchemy import Connection, engine_from_config, pool
-from sqlalchemy.engine import Engine
+from sqlalchemy import engine_from_config, pool

-from hindsight_api.db_url import is_oracle_url, to_libpq_url
+# Import your models here
 from hindsight_api.models import Base


-def load_env() -> None:
-    """Load environment variables from .env (skipped if already configured)."""
+# Load environment variables based on HINDSIGHT_API_DATABASE_URL env var or default to local
+def load_env():
+    """Load environment variables from .env"""
+    # Check if HINDSIGHT_API_DATABASE_URL is already set (e.g., by CI/CD)
    if os.getenv("HINDSIGHT_API_DATABASE_URL"):
        return

+    # Look for .env file in the parent directory (root of the workspace)
    root_dir = Path(__file__).parent.parent.parent
    env_file = root_dir / ".env"

@@ -41,45 +32,30 @@ def load_env() -> None:

 load_env()

+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
 config = context.config
+
+# Note: We don't call fileConfig() here to avoid overriding the application's logging configuration.
+# Alembic will use the existing logging configuration from the application.
+
+# add your model's MetaData object here
+# for 'autogenerate' support
 target_metadata = Base.metadata

-
-def _normalize_oracle_url(url: str) -> str:
-    """Coerce an Oracle URL into the SQLAlchemy form the oracledb dialect expects.
-
-    Two issues to handle:
-
-    1. Force the ``oracle+oracledb`` driver — bare ``oracle://`` defaults to
-       cx_Oracle.
-    2. Map a path-style service to ``?service_name=...``. SQLAlchemy's oracledb
-       dialect treats the URL path as a *SID* (legacy), but Oracle Free /
-       Autonomous DB only register a service name. Without this rewrite we get
-       ``DPY-6003: SID "FREEPDB1" is not registered`` even though the listener
-       is happy to accept the same name as a service.
-    """
-    parts = urlsplit(url)
-    if not parts.scheme.startswith("oracle"):
-        return url
-
-    new_scheme = "oracle+oracledb" if parts.scheme == "oracle" else parts.scheme
-    service = parts.path.lstrip("/")
-    new_query = parts.query
-    new_path = parts.path
-
-    # Promote /SERVICE to ?service_name=SERVICE unless the caller already
-    # supplied an explicit ?sid= or ?service_name=.
-    if service and "service_name=" not in new_query and "sid=" not in new_query:
-        params = [(k, v) for k, v in parse_qsl(new_query, keep_blank_values=True)]
-        params.append(("service_name", service))
-        new_query = urlencode(params)
-        new_path = ""
-
-    return urlunsplit((new_scheme, parts.netloc, new_path, new_query, parts.fragment))
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.


 def get_database_url() -> str:
-    """Resolve the migration URL from Alembic config or env, normalizing per-dialect."""
+    """
+    Get and process the database URL from config or environment.
+
+    Returns the URL with the correct driver (psycopg2) for migrations.
+    """
+    # Get database URL from config (set programmatically) or environment
    database_url = config.get_main_option("sqlalchemy.url")
    if not database_url:
        database_url = os.getenv("HINDSIGHT_API_DATABASE_URL")
@@ -89,18 +65,30 @@ def get_database_url() -> str:
                "Set HINDSIGHT_API_DATABASE_URL environment variable or pass database_url to run_migrations()."
            )

-    if is_oracle_url(database_url):
-        database_url = _normalize_oracle_url(database_url)
-    else:
-        # PG: convert SQLAlchemy-style asyncpg URLs and ?ssl= params to libpq form
-        # for the sync engine used during migrations.
-        database_url = to_libpq_url(database_url)
+    # For migrations, use psycopg2 (sync driver) to avoid pgbouncer prepared statement issues
+    if database_url.startswith("postgresql+asyncpg://"):
+        database_url = database_url.replace("postgresql+asyncpg://", "postgresql://", 1)
+    elif database_url.startswith("postgres+asyncpg://"):
+        database_url = database_url.replace("postgres+asyncpg://", "postgresql://", 1)

+    # Update config with processed URL for engine_from_config to use
    config.set_main_option("sqlalchemy.url", database_url)
+
    return database_url


 def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
    logging.info("running offline")
    database_url = get_database_url()

@@ -115,40 +103,14 @@ def run_migrations_offline() -> None:
        context.run_migrations()


-def _configure_pg_session(engine: Engine, connection: Connection, target_schema: str | None) -> None:
-    """PG-only: ensure the session is RW (Supabase) and bind ``search_path``."""
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode with synchronous engine."""
    from sqlalchemy import event, text

-    @event.listens_for(engine, "connect")
-    def set_read_write_mode(dbapi_connection, connection_record):
-        cursor = dbapi_connection.cursor()
-        cursor.execute("SET SESSION CHARACTERISTICS AS TRANSACTION READ WRITE")
-        if target_schema:
-            cursor.execute(f'CREATE SCHEMA IF NOT EXISTS "{target_schema}"')
-            cursor.execute(f'SET search_path TO "{target_schema}", public')
-        cursor.close()
+    get_database_url()  # Process and set the database URL in config

-    connection.execute(text("SET SESSION CHARACTERISTICS AS TRANSACTION READ WRITE"))
-    if target_schema:
-        connection.execute(text(f'CREATE SCHEMA IF NOT EXISTS "{target_schema}"'))
-        connection.execute(text(f'SET search_path TO "{target_schema}", public'))
-    connection.commit()
-
-
-def _configure_oracle_session(connection: Connection, target_schema: str | None) -> None:
-    """Oracle: switch the session's default schema; tolerate DDL contention."""
-    from sqlalchemy import text
-
-    # Wait up to 30s for DDL locks instead of failing immediately (ORA-00054).
-    connection.execute(text("ALTER SESSION SET DDL_LOCK_TIMEOUT = 30"))
-    if target_schema:
-        connection.execute(text(f'ALTER SESSION SET CURRENT_SCHEMA = "{target_schema}"'))
-
-
-def run_migrations_online() -> None:
-    database_url = get_database_url()
+    # Check if we're targeting a specific schema (for multi-tenant isolation)
    target_schema = config.get_main_option("target_schema")
-    is_oracle = is_oracle_url(database_url)

    connectable = engine_from_config(
        config.get_section(config.config_ini_section, {}),
@@ -156,19 +118,37 @@ def run_migrations_online() -> None:
        poolclass=pool.NullPool,
    )

-    with connectable.connect() as connection:
-        if is_oracle:
-            _configure_oracle_session(connection, target_schema)
-        else:
-            _configure_pg_session(connectable, connection, target_schema)
+    # Add event listener to ensure connection is in read-write mode
+    # This is needed for Supabase which may start connections in read-only mode
+    @event.listens_for(connectable, "connect")
+    def set_read_write_mode(dbapi_connection, connection_record):
+        cursor = dbapi_connection.cursor()
+        cursor.execute("SET SESSION CHARACTERISTICS AS TRANSACTION READ WRITE")
+        # If targeting a specific schema, set search_path
+        # Include public in search_path for access to shared extensions (pgvector)
+        if target_schema:
+            cursor.execute(f'CREATE SCHEMA IF NOT EXISTS "{target_schema}"')
+            cursor.execute(f'SET search_path TO "{target_schema}", public')
+        cursor.close()

+    with connectable.connect() as connection:
+        # Also explicitly set read-write mode on this connection
+        connection.execute(text("SET SESSION CHARACTERISTICS AS TRANSACTION READ WRITE"))
+
+        # If targeting a specific schema, set search_path
+        # Include public in search_path for access to shared extensions (pgvector)
+        if target_schema:
+            connection.execute(text(f'CREATE SCHEMA IF NOT EXISTS "{target_schema}"'))
+            connection.execute(text(f'SET search_path TO "{target_schema}", public'))
+
+        connection.commit()  # Commit the SET command
+
+        # Configure context with version_table_schema if using a specific schema
        context_opts = {
            "connection": connection,
            "target_metadata": target_metadata,
        }
-        if target_schema and not is_oracle:
-            # Oracle has no equivalent of PG's per-schema version table; the
-            # ``alembic_version`` table lives in CURRENT_SCHEMA implicitly.
+        if target_schema:
            context_opts["version_table_schema"] = target_schema

        context.configure(**context_opts)
@@ -176,12 +156,7 @@ def run_migrations_online() -> None:
        with context.begin_transaction():
            context.run_migrations()

-        # Always commit. PG needs it for the explicit RW-mode SET to persist;
-        # Oracle needs it because each DDL auto-commits but the trailing
-        # ``UPDATE alembic_version`` is plain DML that would otherwise stay in
-        # an open transaction and roll back when the connection closes —
-        # producing the "schema is created but the version row is one revision
-        # behind" failure mode.
+        # Explicit commit to ensure changes are persisted (especially for Supabase)
        connection.commit()


@@ -11,8 +11,6 @@ from alembic import op
 import sqlalchemy as sa
 ${imports if imports else ""}

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = ${repr(up_revision)}
 down_revision: Union[str, Sequence[str], None] = ${repr(down_revision)}
@@ -20,27 +18,11 @@ branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
 depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}


-def _pg_upgrade() -> None:
-    """PostgreSQL upgrade. Set to ``None`` below if this migration is Oracle-only."""
+def upgrade() -> None:
+    """Upgrade schema."""
    ${upgrades if upgrades else "pass"}


-def _pg_downgrade() -> None:
-    ${downgrades if downgrades else "pass"}
-
-
-def _oracle_upgrade() -> None:
-    """Oracle upgrade. Set to ``None`` below if this migration is Postgres-only."""
-    pass
-
-
-def _oracle_downgrade() -> None:
-    pass
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade, oracle=_oracle_upgrade)
-
-
 def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade, oracle=_oracle_downgrade)
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}
@@ -4,8 +4,8 @@ The previous GIN trigram index on canonical_name was case-sensitive, causing
 "Alice" and "alice" to have different trigram sets. This recreates it on
 LOWER(canonical_name) so the % operator matches case-insensitively.

-Revision ID: 2eee35aa3cfc
-Revises: d6e7f8a9b0c1
+Revision ID: d6e7f8a9b0c1
+Revises: c5d6e7f8a9b0
 Create Date: 2026-03-31
 """

@@ -13,10 +13,8 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "2eee35aa3cfc"
-down_revision: str | Sequence[str] | None = "d6e7f8a9b0c1"
+revision: str = "d6e7f8a9b0c1"
+down_revision: str | Sequence[str] | None = "c5d6e7f8a9b0"
 branch_labels: str | Sequence[str] | None = None
 depends_on: str | Sequence[str] | None = None

@@ -26,7 +24,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()
    # Drop the old case-sensitive trigram index
    op.execute("DROP INDEX IF EXISTS entities_canonical_name_trgm_idx")
@@ -37,7 +35,7 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    op.execute("DROP INDEX IF EXISTS entities_canonical_name_lower_trgm_idx")
    schema = _get_schema_prefix()
    # Restore original case-sensitive index
@@ -45,11 +43,3 @@ def _pg_downgrade() -> None:
        f"CREATE INDEX IF NOT EXISTS entities_canonical_name_trgm_idx "
        f"ON {schema}entities USING GIN (canonical_name gin_trgm_ops)"
    )
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -15,8 +15,6 @@ from pgvector.sqlalchemy import Vector
 from sqlalchemy import text
 from sqlalchemy.dialects import postgresql

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "5a366d414dce"
 down_revision: str | Sequence[str] | None = None
@@ -26,67 +24,52 @@ depends_on: str | Sequence[str] | None = None

 def _detect_vector_extension() -> str:
    """
-    Detect or validate vector extension for this immutable migration revision.
+    Detect or validate vector extension: 'pgvector', 'vchord', or 'pgvectorscale'.
    Respects HINDSIGHT_API_VECTOR_EXTENSION env var if set.
    """
    conn = op.get_bind()
    vector_extension = os.getenv("HINDSIGHT_API_VECTOR_EXTENSION", "pgvector").lower()

+    # Validate configured extension is installed
    if vector_extension == "pgvectorscale":
+        # pgvectorscale/DiskANN requires pgvector
        pgvector_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vector'")).scalar()
        if not pgvector_check:
            raise RuntimeError(
                "DiskANN requires pgvector. Install with: CREATE EXTENSION vector; then vectorscale or pg_diskann CASCADE;"
            )
+        # Check for either vectorscale (open source) or pg_diskann (Azure)
        vectorscale_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vectorscale'")).scalar()
        pg_diskann_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'pg_diskann'")).scalar()

        if vectorscale_check:
            return "pgvectorscale"
-        if pg_diskann_check:
+        elif pg_diskann_check:
            return "pg_diskann"
-        raise RuntimeError(
-            "Configured vector extension 'pgvectorscale' not found. Install either:\n"
-            "  - pgvectorscale: CREATE EXTENSION vectorscale CASCADE;\n"
-            "  - pg_diskann (Azure): CREATE EXTENSION pg_diskann CASCADE;"
-        )
-    if vector_extension == "vchord":
+        else:
+            raise RuntimeError(
+                "Configured vector extension 'pgvectorscale' not found. Install either:\n"
+                "  - pgvectorscale: CREATE EXTENSION vectorscale CASCADE;\n"
+                "  - pg_diskann (Azure): CREATE EXTENSION pg_diskann CASCADE;"
+            )
+    elif vector_extension == "vchord":
        vchord_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vchord'")).scalar()
        if not vchord_check:
            raise RuntimeError(
                "Configured vector extension 'vchord' not found. Install it with: CREATE EXTENSION vchord CASCADE;"
            )
        return "vchord"
-    if vector_extension == "scann":
-        scann_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'alloydb_scann'")).scalar()
-        if not scann_check:
-            raise RuntimeError(
-                "Configured vector extension 'scann' not found. Install it with: CREATE EXTENSION alloydb_scann CASCADE;"
-            )
-        return "scann"
-    if vector_extension == "pgvector":
+    elif vector_extension == "pgvector":
        pgvector_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vector'")).scalar()
        if not pgvector_check:
            raise RuntimeError(
                "Configured vector extension 'pgvector' not found. Install it with: CREATE EXTENSION vector;"
            )
        return "pgvector"
-    raise ValueError(
-        "Invalid HINDSIGHT_API_VECTOR_EXTENSION: "
-        f"{vector_extension}. Must be 'pgvector', 'vchord', 'pgvectorscale', or 'scann'"
-    )
-
-
-def _vector_index_using_clause(ext: str) -> str:
-    if ext == "pgvectorscale":
-        return "USING diskann (embedding vector_cosine_ops) WITH (num_neighbors = 50)"
-    if ext == "pg_diskann":
-        return "USING diskann (embedding vector_cosine_ops) WITH (max_neighbors = 50)"
-    if ext == "vchord":
-        return "USING vchordrq (embedding vector_l2_ops)"
-    if ext == "scann":
-        return "USING scann (embedding cosine) WITH (mode = 'AUTO')"
-    return "USING hnsw (embedding vector_cosine_ops)"
+    else:
+        raise ValueError(
+            f"Invalid HINDSIGHT_API_VECTOR_EXTENSION: {vector_extension}. Must be 'pgvector', 'vchord', or 'pgvectorscale'"
+        )


 def _detect_text_search_extension() -> str:
@@ -129,7 +112,7 @@ def _detect_text_search_extension() -> str:
        )


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Upgrade schema - create all tables from scratch."""

    # Note: pgvector extension is installed globally BEFORE migrations run
@@ -328,11 +311,36 @@ def _pg_upgrade() -> None:
    )
    # Create vector index - conditional based on available extension
    vector_ext = _detect_vector_extension()
-    if vector_ext != "scann":
-        op.execute(f"""
+
+    if vector_ext == "pgvectorscale":
+        # Use DiskANN index for pgvectorscale (disk-based, scalable)
+        op.execute("""
            CREATE INDEX idx_memory_units_embedding ON memory_units
-            {_vector_index_using_clause(vector_ext)}
+            USING diskann (embedding vector_cosine_ops)
+            WITH (num_neighbors = 50)
        """)
+    elif vector_ext == "pg_diskann":
+        # Use DiskANN index for pg_diskann (Azure)
+        op.execute("""
+            CREATE INDEX idx_memory_units_embedding ON memory_units
+            USING diskann (embedding vector_cosine_ops)
+            WITH (max_neighbors = 50)
+        """)
+    elif vector_ext == "vchord":
+        # Use vchordrq index for vchord (supports high-dimensional embeddings)
+        op.execute("""
+            CREATE INDEX idx_memory_units_embedding ON memory_units
+            USING vchordrq (embedding vector_l2_ops)
+        """)
+    else:  # pgvector
+        # Use HNSW index for pgvector
+        op.create_index(
+            "idx_memory_units_embedding",
+            "memory_units",
+            ["embedding"],
+            postgresql_using="hnsw",
+            postgresql_ops={"embedding": "vector_cosine_ops"},
+        )

    # Create full-text search index on search_vector
    # Index type depends on text search backend
@@ -455,7 +463,7 @@ def _pg_upgrade() -> None:
    op.create_index("idx_unit_entities_entity", "unit_entities", ["entity_id"])


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Downgrade schema - drop all tables."""

    # Drop tables in reverse dependency order
@@ -515,11 +523,3 @@ def _pg_downgrade() -> None:
    # Drop extensions (optional - comment out if you want to keep them)
    # op.execute('DROP EXTENSION IF EXISTS vector')
    # op.execute('DROP EXTENSION IF EXISTS "uuid-ossp"')
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,50 +0,0 @@
-"""Merge divergent migration heads for v0.5.3
-
-v0.5.3 shipped with two migration heads that were never unified:
-
-  * ``c4x5y6z7a8b9`` — delta-refresh chain
-    (``add_last_refreshed_source_query`` ->
-     ``add_structured_content_to_mental_models`` ->
-     ``backsweep_orphan_observations_v2``)
-
-  * ``h3i4j5k6l7m8`` — per-bank vector indexes / audit log chain
-    (the ``merge_heads_and_add_unit_entities_index`` subtree)
-
-Both fork from ``z1u2v3w4x5y6``. Upgrades from v0.5.2 still succeed — the
-walker applies the three c4x5 revisions and leaves the database stamped at
-both heads — but the result is a split DAG: ``alembic upgrade head``
-(singular) is ambiguous, and any future migration has to pick one head as
-its parent, orphaning the other.
-
-This revision linearises the DAG into a single head. It has no schema
-effect.
-
-Revision ID: 8c6fa6f7230b
-Revises: c4x5y6z7a8b9, h3i4j5k6l7m8
-Create Date: 2026-04-18
-"""
-
-from collections.abc import Sequence
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "8c6fa6f7230b"
-down_revision: str | Sequence[str] | None = ("c4x5y6z7a8b9", "h3i4j5k6l7m8")
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _pg_upgrade() -> None:
-    pass
-
-
-def _pg_downgrade() -> None:
-    pass
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,128 +0,0 @@
-"""Make memory_links.from_unit_id and memory_links.to_unit_id FKs deferrable.
-
-Revision ID: 9f8e7d6c5b4a
-Revises: o1a2b3c4d5e6
-Create Date: 2026-05-03
-
-Background
----------
-Concurrent retain (which INSERTs into ``memory_links``) and any code path
-that DELETEs a row whose deletion cascades into ``memory_links`` (e.g.
-delta-retain superseding chunks, which CASCADEs chunks → memory_units →
-memory_links) can deadlock under sustained single-tenant write load.
-
-The deadlock cycle:
-
-* Tx A: ``DELETE FROM chunks WHERE chunk_id = ANY(...)``
-  → CASCADE acquires row locks on memory_units, then on memory_links rows
-    where ``to_unit_id`` matches the deleted units.
-* Tx B: ``INSERT INTO memory_links (...)`` referencing one of the same
-  memory_units rows.
-  → The immediate FK check takes ``FOR KEY SHARE`` on those memory_units
-    rows.
-
-The two transactions take row locks on the same memory_units rows in
-opposite orders depending on which side started first. PostgreSQL detects
-the cycle and aborts one transaction; the loser is killed mid-batch, the
-winner continues. Workers then retry, but under sustained write load the
-pattern repeats.
-
-Fix
---
-Make both ``memory_links → memory_units`` FKs (``from_unit_id`` and
-``to_unit_id``) ``DEFERRABLE INITIALLY DEFERRED``. This pushes the FK
-check from INSERT time to COMMIT time:
-
-* INSERT no longer takes ``FOR KEY SHARE`` on the memory_units row → no
-  contention with the cascading DELETE's row lock.
-* At COMMIT the engine validates referential integrity in one shot. If a
-  cascade-DELETE has since removed the referenced unit, the INSERT
-  transaction commits OR fails with a clean FK violation (sqlstate
-  23503) instead of a deadlock (sqlstate 40P01).
-
-The ``WHERE EXISTS`` filter already in ``_bulk_insert_links`` continues to
-filter out the typical "stale unit_id" case at INSERT time; the deferred
-FK is only the backstop for the narrow race window between the EXISTS
-probe and COMMIT. ``ON DELETE CASCADE`` semantics are unchanged — only
-the *timing* of the constraint check moves.
-
-The ``entity_id`` FK on ``memory_links`` is not changed; entities are not
-involved in the observed deadlock cycle and leaving the constraint
-immediate keeps the error message specific when an entity row is missing.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "9f8e7d6c5b4a"
-down_revision: str | Sequence[str] | None = "o1a2b3c4d5e6"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _get_schema_prefix() -> str:
-    """Schema-qualifier for raw SQL on PG (multi-tenant search_path)."""
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-# The two FK constraints installed by the initial schema migration
-# (5a366d414dce_initial_schema), mapped to the column they constrain.
-# They reference memory_units(id) with ON DELETE CASCADE — that
-# semantics is preserved; only the deferral attribute changes.
-_FK_COLUMNS: dict[str, str] = {
-    "fk_memory_links_from_unit_id_memory_units": "from_unit_id",
-    "fk_memory_links_to_unit_id_memory_units": "to_unit_id",
-}
-
-
-def _pg_upgrade() -> None:
-    schema = _get_schema_prefix()
-    # PostgreSQL doesn't allow altering the deferrability of an existing
-    # constraint with ALTER CONSTRAINT — the constraint must be dropped
-    # and recreated. DROP IF EXISTS makes the migration safe to re-run
-    # on schemas where the constraint was already recreated.
-    for fk_name, column in _FK_COLUMNS.items():
-        op.execute(f"ALTER TABLE {schema}memory_links DROP CONSTRAINT IF EXISTS {fk_name}")
-        op.execute(
-            f"""
-            ALTER TABLE {schema}memory_links
-                ADD CONSTRAINT {fk_name}
-                FOREIGN KEY ({column})
-                REFERENCES {schema}memory_units (id)
-                ON DELETE CASCADE
-                DEFERRABLE INITIALLY DEFERRED
-            """
-        )
-
-
-def _pg_downgrade() -> None:
-    schema = _get_schema_prefix()
-    # Revert to the default (NOT DEFERRABLE) form so a downgrade actually
-    # restores the prior schema state, even though that re-introduces the
-    # deadlock window.
-    for fk_name, column in _FK_COLUMNS.items():
-        op.execute(f"ALTER TABLE {schema}memory_links DROP CONSTRAINT IF EXISTS {fk_name}")
-        op.execute(
-            f"""
-            ALTER TABLE {schema}memory_links
-                ADD CONSTRAINT {fk_name}
-                FOREIGN KEY ({column})
-                REFERENCES {schema}memory_units (id)
-                ON DELETE CASCADE
-            """
-        )
-
-
-def upgrade() -> None:
-    # PG-only: Oracle's deferrable-FK semantics differ and the deadlock
-    # cycle was only observed on PostgreSQL. Oracle slot intentionally
-    # absent → no-op there.
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -15,8 +15,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "a1b2c3d4e5f6"
 down_revision: str | Sequence[str] | None = "y0t1u2v3w4x5"
 branch_labels: str | Sequence[str] | None = None
@@ -29,7 +27,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Create file_storage table for BYTEA storage."""
    schema = _get_schema_prefix()

@@ -54,7 +52,7 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Remove file_storage table and related columns."""
    schema = _get_schema_prefix()

@@ -70,11 +68,3 @@ def _pg_downgrade() -> None:

    # Drop file_storage table
    op.execute(f"DROP TABLE IF EXISTS {schema}file_storage")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -18,8 +18,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "a2b3c4d5e6f7"
 down_revision: str | Sequence[str] | None = "aa2b3c4d5e6f"
 branch_labels: str | Sequence[str] | None = None
@@ -35,7 +33,7 @@ def _detect_text_search_extension() -> str:
    return os.getenv("HINDSIGHT_API_TEXT_SEARCH_EXTENSION", "native").lower()


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()
    table = f"{schema}memory_units"
    text_search_ext = _detect_text_search_extension()
@@ -67,7 +65,7 @@ def _pg_upgrade() -> None:
    # pg_textsearch: no change — index operates on the base `text` column only


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    schema = _get_schema_prefix()
    table = f"{schema}memory_units"
    text_search_ext = _detect_text_search_extension()
@@ -88,11 +86,3 @@ def _pg_downgrade() -> None:
        """)

    op.execute(f"ALTER TABLE {table} DROP COLUMN IF EXISTS text_signals")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -24,8 +24,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "a2b3c4d5e6f8"
 down_revision: str | Sequence[str] | None = "f7g8h9i0j1k2"
 branch_labels: str | Sequence[str] | None = None
@@ -37,7 +35,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()

    # CREATE INDEX CONCURRENTLY cannot run inside a transaction block.
@@ -50,15 +48,7 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+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")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,48 +0,0 @@
-"""Add last_refreshed_source_query column to mental_models
-
-Revision ID: a2v3w4x5y6z7
-Revises: z1u2v3w4x5y6
-Create Date: 2026-04-15
-
-Tracks the source_query that was used during the most recent refresh.
-Used by delta-mode refresh to detect when the query has changed: if it has,
-delta mode falls back to a full regeneration because the surgical-edit
-assumption (same topic, new facts) no longer holds.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "a2v3w4x5y6z7"
-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:
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def _pg_upgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"""
-        ALTER TABLE {schema}mental_models
-        ADD COLUMN IF NOT EXISTS last_refreshed_source_query TEXT
-    """)
-
-
-def _pg_downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}mental_models DROP COLUMN IF EXISTS last_refreshed_source_query")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -13,8 +13,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "a3b4c5d6e7f8"
 down_revision: str | Sequence[str] | None = "g7h8i9j0k1l2"
 branch_labels: str | Sequence[str] | None = None
@@ -27,7 +25,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()

    op.execute(
@@ -47,16 +45,8 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+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")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,7 +1,7 @@
 """Fix per-bank vector indexes to match configured extension

 Revision ID: a4b5c6d7e8f9
-Revises: 2eee35aa3cfc
+Revises: d6e7f8a9b0c1
 Create Date: 2026-04-01

 Migration d5e6f7a8b9c0 hardcoded HNSW when creating per-bank partial vector
@@ -11,8 +11,7 @@ was configured.

 This migration detects the mismatch and recreates the affected indexes with
 the correct type. Skipped entirely when the configured extension is pgvector
-(the default) or scann. ScaNN uses global vector indexes because empty or tiny
-per-bank indexes cannot be built safely on AlloyDB.
+(the default), since those indexes are already correct.
 """

 import os
@@ -21,10 +20,8 @@ from collections.abc import Sequence
 from alembic import context, op
 from sqlalchemy import text

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "a4b5c6d7e8f9"
-down_revision: str | Sequence[str] | None = "2eee35aa3cfc"
+down_revision: str | Sequence[str] | None = "d6e7f8a9b0c1"
 branch_labels: str | Sequence[str] | None = None
 depends_on: str | Sequence[str] | None = None

@@ -40,47 +37,39 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _validate_extension(name: str) -> str:
-    ext = name.lower()
-    if ext not in {"pgvector", "pgvectorscale", "vchord", "scann"}:
-        raise ValueError(
-            f"Invalid HINDSIGHT_API_VECTOR_EXTENSION: {ext}. Must be 'pgvector', 'vchord', 'pgvectorscale', or 'scann'"
-        )
-    return ext
-
-
-def _index_type_keyword(ext: str) -> str:
+def _target_index_type() -> str | None:
+    """Return the target index type, or None if pgvector (no fix needed)."""
+    ext = os.getenv("HINDSIGHT_API_VECTOR_EXTENSION", "pgvector").lower()
    if ext == "pgvectorscale":
        return "diskann"
-    if ext == "vchord":
+    elif ext == "vchord":
        return "vchordrq"
-    if ext == "scann":
-        return "scann"
-    return "hnsw"
+    return None


-def _vector_index_using_clause(ext: str) -> str:
+def _vector_index_using_clause() -> str:
+    """Return the USING clause based on the configured vector extension."""
+    ext = os.getenv("HINDSIGHT_API_VECTOR_EXTENSION", "pgvector").lower()
    if ext == "pgvectorscale":
        return "USING diskann (embedding vector_cosine_ops) WITH (num_neighbors = 50)"
-    if ext == "vchord":
+    elif ext == "vchord":
        return "USING vchordrq (embedding vector_l2_ops)"
-    if ext == "scann":
-        return "USING scann (embedding cosine) WITH (mode = 'AUTO')"
-    return "USING hnsw (embedding vector_cosine_ops)"
+    else:
+        return "USING hnsw (embedding vector_cosine_ops)"


-def _pg_upgrade() -> None:
-    ext = _validate_extension(os.getenv("HINDSIGHT_API_VECTOR_EXTENSION", "pgvector"))
-    if ext in {"pgvector", "scann"}:
+def upgrade() -> None:
+    target = _target_index_type()
+    if target is None:
+        # pgvector — indexes are already HNSW, nothing to fix
        return
-    target = _index_type_keyword(ext)

    bind = op.get_bind()
    schema_name = context.config.get_main_option("target_schema")
    schema = _get_schema_prefix()
    table_ref = f'"{schema_name}".memory_units' if schema_name else "memory_units"
    banks_ref = f'"{schema_name}".banks' if schema_name else "banks"
-    using_clause = _vector_index_using_clause(ext)
+    using_clause = _vector_index_using_clause()
    pg_schema = schema_name or "public"

    rows = bind.execute(text(f"SELECT bank_id, internal_id FROM {banks_ref}")).fetchall()  # noqa: S608
@@ -124,10 +113,10 @@ def _pg_upgrade() -> None:
            )


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    # Downgrade recreates indexes as HNSW (the original hardcoded behavior)
-    ext = _validate_extension(os.getenv("HINDSIGHT_API_VECTOR_EXTENSION", "pgvector"))
-    if ext in {"pgvector", "scann"}:
+    target = _target_index_type()
+    if target is None:
        return

    bind = op.get_bind()
@@ -151,11 +140,3 @@ def _pg_downgrade() -> None:
                    f"WHERE fact_type = '{ft}' AND bank_id = '{escaped_bank_id}'"
                )
            )
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -12,8 +12,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "aa2b3c4d5e6f"
 down_revision: str | Sequence[str] | None = "z1u2v3w4x5y6"
 branch_labels: str | Sequence[str] | None = None
@@ -26,21 +24,13 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()
    op.execute(f"ALTER TABLE {schema}memory_units ALTER COLUMN event_date DROP NOT NULL")


-def _pg_downgrade() -> None:
+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")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -9,8 +9,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "b3c4d5e6f7a8"
 down_revision: str | Sequence[str] | None = "a3b4c5d6e7f8"
 branch_labels: str | Sequence[str] | None = None
@@ -23,20 +21,12 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+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 _pg_downgrade() -> None:
+def downgrade() -> None:
    schema = _get_schema_prefix()
    op.execute(f"ALTER TABLE {schema}chunks DROP COLUMN IF EXISTS content_hash")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -22,8 +22,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "b3c4d5e6f7g8"
 down_revision: str | Sequence[str] | None = "c1a2b3d4e5f6"
 branch_labels: str | Sequence[str] | None = None
@@ -35,7 +33,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()
    # Partial index on occurred_start (covers "occurred_start BETWEEN $4 AND $5")
    op.execute("COMMIT")
@@ -60,7 +58,7 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+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")
@@ -68,11 +66,3 @@ def _pg_downgrade() -> None:
    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")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,54 +0,0 @@
-"""Add structured_content JSONB column to mental_models
-
-Revision ID: b3w4x5y6z7a8
-Revises: a2v3w4x5y6z7
-Create Date: 2026-04-16
-
-Stores the structured representation of a mental model document (sections,
-blocks). The plain ``content`` column remains the rendered markdown shown to
-users. ``structured_content`` is the source of truth for delta-mode refreshes:
-each refresh applies a list of typed operations to the structured doc, then
-re-renders to markdown — so unchanged sections come through byte-identical
-without an LLM round-trip.
-
-Nullable: existing markdown-only mental models continue to work in full mode;
-the column is populated lazily the first time a model is refreshed in delta
-mode.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "b3w4x5y6z7a8"
-down_revision: str | Sequence[str] | None = "a2v3w4x5y6z7"
-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 _pg_upgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"""
-        ALTER TABLE {schema}mental_models
-        ADD COLUMN IF NOT EXISTS structured_content JSONB
-    """)
-
-
-def _pg_downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}mental_models DROP COLUMN IF EXISTS structured_content")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -14,8 +14,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "b4c5d6e7f8a9"
 down_revision: str | Sequence[str] | None = "a2b3c4d5e6f7"
 branch_labels: str | Sequence[str] | None = None
@@ -27,18 +25,10 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()
    op.execute(f"ALTER TABLE {schema}memory_units ADD COLUMN IF NOT EXISTS observation_scopes JSONB")


-def _pg_downgrade() -> None:
-    pass  # intentionally no-op — safe to leave the column in place
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
 def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
+    pass  # intentionally no-op — safe to leave the column in place
@@ -1,91 +0,0 @@
-"""Backfill entity_cooccurrences.last_cooccurred from memory_units event time
-
-Revision ID: b5d4e3f2a1c9
-Revises: o1a2b3c4d5e6
-Create Date: 2026-04-24
-
-The writer path in `entity_resolver.link_units_to_entities_batch` historically
-stamped `entity_cooccurrences.last_cooccurred` with `datetime.now(UTC)` at
-flush time, ignoring the source memory unit's event date. For normal online
-retains that's fine (now ≈ event time), but for any corpus that was
-backfilled in a single session — migrating from another memory system, for
-example — every co-occurrence collapsed to the import moment, which hid the
-underlying knowledge timeline from the dashboard's entity graph recency heat
-and from any downstream consumer of the column.
-
-The writer is fixed in the same change set to propagate the unit's event_date;
-this migration repairs historical rows by reading the true event time off
-`unit_entities × memory_units` (falling back to `created_at` when
-`mentioned_at` / `occurred_start` are NULL, so rows never regress).
-
-Oracle slot is intentionally absent: the Oracle baseline (`o1a2b3c4d5e6`)
-landed days before this fix, so any Oracle deployment runs the corrected
-writer against an effectively empty `entity_cooccurrences` — there is no
-historical residue on Oracle to repair. PG-only matches the asymmetry of
-the data, not negligence.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "b5d4e3f2a1c9"
-down_revision: str | Sequence[str] | None = "o1a2b3c4d5e6"
-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 _pg_upgrade() -> None:
-    schema = _get_schema_prefix()
-    # Recompute last_cooccurred from the true event time per entity pair.
-    # COALESCE picks the first non-null of mentioned_at / occurred_start /
-    # created_at so banks without event-time metadata still see a sane value
-    # (equivalent to the pre-fix behaviour) instead of NULL.
-    #
-    # The self-join on `unit_entities` is O(k²) per memory_unit in the number
-    # of distinct entities mentioned (k). For typical units k is small (single
-    # digits), but a bank with units containing hundreds of entities and tens
-    # of millions of co-occurrence rows may want to run this off-hours — the
-    # whole UPDATE is one statement, so it locks every targeted ec row for
-    # the duration. The migration is one-time; subsequent online writes
-    # already carry event time via the writer fix.
-    op.execute(
-        f"""
-        UPDATE {schema}entity_cooccurrences ec
-        SET last_cooccurred = sub.event_time
-        FROM (
-            SELECT
-                LEAST(ue1.entity_id, ue2.entity_id) AS e1,
-                GREATEST(ue1.entity_id, ue2.entity_id) AS e2,
-                MAX(COALESCE(mu.mentioned_at, mu.occurred_start, mu.created_at)) AS event_time
-            FROM {schema}memory_units mu
-            JOIN {schema}unit_entities ue1 ON ue1.unit_id = mu.id
-            JOIN {schema}unit_entities ue2 ON ue2.unit_id = mu.id AND ue1.entity_id <> ue2.entity_id
-            GROUP BY 1, 2
-        ) sub
-        WHERE ec.entity_id_1 = sub.e1 AND ec.entity_id_2 = sub.e2
-        """
-    )
-
-
-def _pg_downgrade() -> None:
-    # No-op: the previous column value was `now()` at the time of write and
-    # isn't recoverable. Rolling back the code is sufficient — new writes will
-    # revert to the old behaviour for subsequent retains.
-    pass
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)  # oracle slot intentionally absent — see header
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -12,8 +12,6 @@ import sqlalchemy as sa
 from alembic import op
 from sqlalchemy.dialects import postgresql

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "b7c4d8e9f1a2"
 down_revision: str | Sequence[str] | None = "5a366d414dce"
@@ -21,7 +19,7 @@ branch_labels: str | Sequence[str] | None = None
 depends_on: str | Sequence[str] | None = None


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Add chunks table and link memory_units to chunks."""

    # Create chunks table with single text PK (bank_id_document_id_chunk_index)
@@ -58,7 +56,7 @@ def _pg_upgrade() -> None:
    op.create_index("idx_memory_units_chunk_id", "memory_units", ["chunk_id"])


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Remove chunks table and chunk_id from memory_units."""

    # Drop index and foreign key from memory_units
@@ -70,11 +68,3 @@ def _pg_downgrade() -> None:
    op.drop_index("idx_chunks_bank_id", table_name="chunks")
    op.drop_index("idx_chunks_document_id", table_name="chunks")
    op.drop_table("chunks")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -14,8 +14,6 @@ from collections.abc import Sequence
 import sqlalchemy as sa
 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "c1a2b3d4e5f6"
 down_revision: str | Sequence[str] | None = "b4c5d6e7f8a9"
 branch_labels: str | Sequence[str] | None = None
@@ -27,7 +25,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+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
@@ -54,16 +52,8 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+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
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -14,8 +14,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "c2d3e4f5g6h7"
 down_revision: str | Sequence[str] | None = ("a3b4c5d6e7f8", "c8e5f2a3b4d1")
 branch_labels: str | Sequence[str] | None = None
@@ -28,7 +26,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()

    op.execute(
@@ -54,18 +52,10 @@ def _pg_upgrade() -> None:
    op.execute(f"CREATE INDEX IF NOT EXISTS idx_audit_log_started ON {schema}audit_log (started_at DESC)")


-def _pg_downgrade() -> None:
+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")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -9,8 +9,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "c3d4e5f6g7h8"
 down_revision: str | Sequence[str] | None = ("a2b3c4d5e6f7", "a2b3c4d5e6f8")
 branch_labels: str | Sequence[str] | None = None
@@ -22,19 +20,11 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+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 _pg_downgrade() -> None:
+def downgrade() -> None:
    schema = _get_schema_prefix()
    op.execute(f"ALTER TABLE {schema}mental_models DROP COLUMN IF EXISTS history")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,76 +0,0 @@
-"""backsweep_orphan_observations_v2
-
-Re-run of Pass 2 from migration ``g7h8i9j0k1l2_backsweep_orphan_observations``
-to sweep observations that became orphaned between then and now.
-
-Why we need it again:
-  ``fact_storage.handle_document_tracking`` (the retain/upsert path) deleted
-  the existing document via the FK cascade — which removes the source
-  ``memory_units`` — but never invalidated the observations derived from
-  them.  Only the explicit ``MemoryEngine.delete_document`` API called
-  ``_delete_stale_observations_for_memories``.  Every document re-ingest
-  therefore left orphan observations whose ``source_memory_ids`` arrays
-  pointed at IDs that no longer existed in ``memory_units``.
-
-  ``handle_document_tracking`` now calls the same cleanup helper before the
-  cascade, so no new orphans will accumulate going forward.  This migration
-  cleans up the historical residue.
-
-Identical to Pass 2 of g7h8i9j0k1l2.  Pass 1 (memory_units whose bank is
-gone) is intentionally not re-run; that scenario has no fresh source.
-
-Revision ID: c4x5y6z7a8b9
-Revises: b3w4x5y6z7a8
-Create Date: 2026-04-16
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "c4x5y6z7a8b9"
-down_revision: str | Sequence[str] | None = "b3w4x5y6z7a8"
-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 _pg_upgrade() -> None:
-    schema = _get_schema_prefix()
-    mu = f"{schema}memory_units"
-
-    # Delete observations whose 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 — the consolidation engine will refresh
-    # their text on the next pass.
-    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 _pg_downgrade() -> None:
-    # Deleted rows cannot be restored.
-    pass
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -13,8 +13,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "c5d6e7f8a9b0"
 down_revision: str | Sequence[str] | None = "b3c4d5e6f7a8"
 branch_labels: str | Sequence[str] | None = None
@@ -26,7 +24,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()

    # 1. Add nullable column
@@ -45,14 +43,6 @@ def _pg_upgrade() -> None:
    op.execute(f"ALTER TABLE {schema}memory_links ALTER COLUMN bank_id SET NOT NULL")


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    schema = _get_schema_prefix()
    op.execute(f"ALTER TABLE {schema}memory_links DROP COLUMN IF EXISTS bank_id")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -12,8 +12,6 @@ import sqlalchemy as sa
 from alembic import op
 from sqlalchemy.dialects import postgresql

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "c8e5f2a3b4d1"
 down_revision: str | Sequence[str] | None = "b7c4d8e9f1a2"
@@ -21,7 +19,7 @@ branch_labels: str | Sequence[str] | None = None
 depends_on: str | Sequence[str] | None = None


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Add retain_params JSONB column to documents table."""

    # Add retain_params column to store parameters passed during retain
@@ -31,7 +29,7 @@ def _pg_upgrade() -> None:
    op.create_index("idx_documents_retain_params", "documents", ["retain_params"], postgresql_using="gin")


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Remove retain_params column from documents table."""

    # Drop index
@@ -39,11 +37,3 @@ def _pg_downgrade() -> None:

    # Drop column
    op.drop_column("documents", "retain_params")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -34,8 +34,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "d2e3f4a5b6c7"
 down_revision: str | Sequence[str] | None = "b3c4d5e6f7g8"
 branch_labels: str | Sequence[str] | None = None
@@ -47,7 +45,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()

    # CREATE INDEX CONCURRENTLY cannot run inside a transaction block.
@@ -77,17 +75,9 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+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")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -18,8 +18,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "d4e5f6g7h8i9"
 down_revision: str | Sequence[str] | None = "d5e6f7a8b9c0"
 branch_labels: str | Sequence[str] | None = None
@@ -31,7 +29,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()
    # DROP + CREATE CONCURRENTLY must run outside a transaction block.
    op.execute("COMMIT")
@@ -44,7 +42,7 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+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")
@@ -53,11 +51,3 @@ def _pg_downgrade() -> None:
        f"ON {schema}memory_units USING GIN (source_memory_ids) "
        f"WHERE source_memory_ids IS NOT NULL"
    )
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -6,11 +6,10 @@ Create Date: 2026-03-11

 This migration:
 1. Adds internal_id UUID column to banks (stable identifier for index naming)
-2. For non-ScaNN backends, drops the global vector index (competes with
-   per-bank partial indexes)
-3. For non-ScaNN backends, creates per-(bank_id, fact_type) partial vector
-   indexes for all existing banks using the configured vector extension
-   (HNSW for pgvector, DiskANN for pgvectorscale, vchordrq for vchord).
+2. Drops the global vector index (competes with per-bank partial indexes)
+3. Creates per-(bank_id, fact_type) partial vector indexes for all existing banks
+   using the configured vector extension (HNSW for pgvector, DiskANN for
+   pgvectorscale, vchordrq for vchord).
   (new banks get indexes created at bank-creation time via bank_utils.create_bank_vector_indexes)

 Why per-(bank, fact_type) indexes:
@@ -18,8 +17,6 @@ Why per-(bank, fact_type) indexes:
  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 vector index competes for larger partitions (world, observation) and must be dropped.
- AlloyDB ScaNN uses global vector indexes with filtered vector search instead
-  because empty or tiny per-bank indexes cannot be built safely.
 """

 import os
@@ -28,8 +25,6 @@ from collections.abc import Sequence
 from alembic import context, op
 from sqlalchemy import text

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "d5e6f7a8b9c0"
 down_revision: str | Sequence[str] | None = "c3d4e5f6g7h8"
 branch_labels: str | Sequence[str] | None = None
@@ -42,31 +37,23 @@ _FACT_TYPES: dict[str, str] = {
 }


-def _configured_vector_extension() -> str:
-    ext = os.getenv("HINDSIGHT_API_VECTOR_EXTENSION", "pgvector").lower()
-    if ext not in {"pgvector", "pgvectorscale", "vchord", "scann"}:
-        raise ValueError(
-            f"Invalid HINDSIGHT_API_VECTOR_EXTENSION: {ext}. Must be 'pgvector', 'vchord', 'pgvectorscale', or 'scann'"
-        )
-    return ext
-
-
-def _vector_index_using_clause(ext: str) -> str:
-    if ext == "pgvectorscale":
-        return "USING diskann (embedding vector_cosine_ops) WITH (num_neighbors = 50)"
-    if ext == "vchord":
-        return "USING vchordrq (embedding vector_l2_ops)"
-    if ext == "scann":
-        return "USING scann (embedding cosine) WITH (mode = 'AUTO')"
-    return "USING hnsw (embedding vector_cosine_ops)"
-
-
 def _get_schema_prefix() -> str:
    schema = context.config.get_main_option("target_schema")
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def _vector_index_using_clause() -> str:
+    """Return the USING clause based on the configured vector extension."""
+    ext = os.getenv("HINDSIGHT_API_VECTOR_EXTENSION", "pgvector").lower()
+    if ext == "pgvectorscale":
+        return "USING diskann (embedding vector_cosine_ops) WITH (num_neighbors = 50)"
+    elif ext == "vchord":
+        return "USING vchordrq (embedding vector_l2_ops)"
+    else:
+        return "USING hnsw (embedding vector_cosine_ops)"
+
+
+def upgrade() -> None:
    schema = _get_schema_prefix()

    # 1. Add internal_id column to banks
@@ -75,14 +62,6 @@ def _pg_upgrade() -> None:
    )
    op.execute(f"ALTER TABLE {schema}banks ADD CONSTRAINT banks_internal_id_unique UNIQUE (internal_id)")

-    ext = _configured_vector_extension()
-    if ext == "scann":
-        # ScaNN should keep/use a global vector index. Per-bank partial indexes
-        # are created while banks are empty and can fail AlloyDB's ScaNN build
-        # requirements, so this migration leaves vector index reconciliation to
-        # runtime ensure_vector_extension once enough rows exist.
-        return
-
    # 2. Drop any fact_type-only partial 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")
@@ -98,7 +77,7 @@ def _pg_upgrade() -> None:
    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"
-    using_clause = _vector_index_using_clause(ext)
+    using_clause = _vector_index_using_clause()

    rows = bind.execute(text(f"SELECT bank_id, internal_id FROM {banks_ref}")).fetchall()  # noqa: S608
    for row in rows:
@@ -117,7 +96,7 @@ def _pg_upgrade() -> None:
            )


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    schema = _get_schema_prefix()

    # Drop per-bank HNSW indexes (iterate existing banks)
@@ -128,7 +107,7 @@ def _pg_downgrade() -> None:
    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 _FACT_TYPES.values():
+        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}"))

@@ -158,11 +137,3 @@ def _pg_downgrade() -> None:
    # 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")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,67 +0,0 @@
-"""Backfill mental_models.subtype for databases that ran h3c4d5e6f7g8 before the fix
-
-Migration h3c4d5e6f7g8 used CREATE TABLE IF NOT EXISTS to create the
-mental_models table with a subtype column. But on databases where the table
-already existed (from the reflections -> mental_models rename chain), the
-CREATE was a no-op and subtype was never added. A fix was later added to
-h3c4d5e6f7g8 (Step 4b), but databases that had already run the migration
-never re-execute it. This migration adds the missing columns idempotently.
-
-Revision ID: d5y6z7a8b9c0
-Revises: 8c6fa6f7230b
-Create Date: 2026-04-18
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "d5y6z7a8b9c0"
-down_revision: str | Sequence[str] | None = "8c6fa6f7230b"
-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 _pg_upgrade() -> None:
-    schema = _get_schema_prefix()
-
-    # Add columns that h3c4d5e6f7g8 intended to create but missed when
-    # the table already existed from the reflections rename chain.
-    for col_ddl in [
-        "subtype VARCHAR(32) NOT NULL DEFAULT 'structural'",
-        "description TEXT NOT NULL DEFAULT ''",
-        "entity_id UUID",
-        "observations JSONB DEFAULT '{\"observations\": []}'::jsonb",
-        "links VARCHAR[]",
-        "last_updated TIMESTAMP WITH TIME ZONE",
-    ]:
-        op.execute(f"ALTER TABLE {schema}mental_models ADD COLUMN IF NOT EXISTS {col_ddl}")
-
-    # Ensure the CHECK constraint exists
-    op.execute(f"ALTER TABLE {schema}mental_models DROP CONSTRAINT IF EXISTS ck_mental_models_subtype")
-    op.execute(f"""
-        ALTER TABLE {schema}mental_models
-        ADD CONSTRAINT ck_mental_models_subtype CHECK (subtype IN ('structural', 'emergent', 'pinned', 'learned'))
-    """)
-
-    op.execute(f"CREATE INDEX IF NOT EXISTS idx_mental_models_subtype ON {schema}mental_models(bank_id, subtype)")
-
-
-def _pg_downgrade() -> None:
-    # No-op: these columns are part of the intended schema
-    pass
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,49 +0,0 @@
-"""Drop unused metadata column from documents table
-
-Revision ID: d6e7f8a9b0c1
-Revises: c2d3e4f5g6h7, c5d6e7f8a9b0
-Create Date: 2026-03-30
-
-The metadata column on documents was always stored as an empty dict {}.
-Actual document metadata is stored inside retain_params.metadata.
-
-This migration was originally shipped in v0.4.22, then its file was deleted
-in v0.5.0 (and its revision ID accidentally reused by 2eee35aa3cfc).
-Restoring the file so that databases stamped at this revision can upgrade
-cleanly to v0.5.x+.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "d6e7f8a9b0c1"
-down_revision: str | Sequence[str] | None = ("c2d3e4f5g6h7", "c5d6e7f8a9b0")
-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 _pg_upgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}documents DROP COLUMN IF EXISTS metadata")
-
-
-def _pg_downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}documents ADD COLUMN IF NOT EXISTS metadata jsonb DEFAULT '{{}}'")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -8,8 +8,6 @@ Create Date: 2024-12-04 15:00:00.000000

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision = "d9f6a3b4c5e2"
 down_revision = "c8e5f2a3b4d1"
@@ -23,7 +21,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade():
+def upgrade():
    schema = _get_schema_prefix()

    # Drop old check constraint FIRST (before updating data)
@@ -40,7 +38,7 @@ def _pg_upgrade():
    )


-def _pg_downgrade():
+def downgrade():
    schema = _get_schema_prefix()

    # Drop new check constraint FIRST
@@ -53,11 +51,3 @@ def _pg_downgrade():
    op.create_check_constraint(
        "memory_units_fact_type_check", "memory_units", "fact_type IN ('world', 'bank', 'opinion', 'observation')"
    )
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -14,8 +14,6 @@ from collections.abc import Sequence
 import sqlalchemy as sa
 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "e0a1b2c3d4e5"
 down_revision: str | Sequence[str] | None = "rename_personality"
@@ -35,7 +33,7 @@ def _get_target_schema() -> str:
    return schema if schema else "public"


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Convert Big Five disposition to 3-trait disposition."""
    conn = op.get_bind()
    schema = _get_schema_prefix()
@@ -77,7 +75,7 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Convert back to Big Five disposition."""
    conn = op.get_bind()
    schema = _get_schema_prefix()
@@ -111,11 +109,3 @@ def _pg_downgrade() -> None:
        ALTER COLUMN disposition SET DEFAULT '{{"openness": 0.5, "conscientiousness": 0.5, "extraversion": 0.5, "agreeableness": 0.5, "neuroticism": 0.5, "bias_strength": 0.5}}'::jsonb
    """)
    )
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -12,8 +12,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "e4f5a6b7c8d9"
 down_revision: str | Sequence[str] | None = "d2e3f4a5b6c7"
 branch_labels: str | Sequence[str] | None = None
@@ -25,7 +23,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()

    op.execute(
@@ -56,17 +54,9 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+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")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -13,8 +13,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "e5f6g7h8i9j0"
 down_revision: str | Sequence[str] | None = "d4e5f6g7h8i9"
 branch_labels: str | Sequence[str] | None = None
@@ -26,7 +24,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()

    # Remove orphaned async_operations rows whose bank no longer exists
@@ -69,15 +67,7 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+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")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -12,8 +12,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "f1a2b3c4d5e6"
 down_revision: str | Sequence[str] | None = "e0a1b2c3d4e5"
@@ -27,7 +25,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Add composite index for efficient graph retrieval edge loading."""
    schema = _get_schema_prefix()
    # Create composite index for efficient top-k per (from_node, link_type) queries
@@ -40,15 +38,7 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Remove the composite index."""
    schema = _get_schema_prefix()
    op.execute(f"DROP INDEX IF EXISTS {schema}idx_memory_links_from_type_weight")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -10,8 +10,6 @@ from collections.abc import Sequence

 from alembic import op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "f6g7h8i9j0k1"
 down_revision: str | Sequence[str] | None = "e5f6g7h8i9j0"
@@ -19,7 +17,7 @@ branch_labels: str | Sequence[str] | None = None
 depends_on: str | Sequence[str] | None = None


-def _pg_upgrade() -> 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
@@ -51,17 +49,9 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+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"
    )
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -12,8 +12,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "f7g8h9i0j1k2"
 down_revision: str | Sequence[str] | None = "e4f5a6b7c8d9"
 branch_labels: str | Sequence[str] | None = None
@@ -25,19 +23,11 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+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 _pg_downgrade() -> None:
+def downgrade() -> None:
    schema = _get_schema_prefix()
    op.execute(f"ALTER TABLE {schema}webhooks DROP COLUMN IF EXISTS http_config")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -12,8 +12,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "g2a3b4c5d6e7"
 down_revision: str | Sequence[str] | None = "f1a2b3c4d5e6"
@@ -27,7 +25,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Add tags column to memory_units and documents tables."""
    schema = _get_schema_prefix()

@@ -41,18 +39,10 @@ def _pg_upgrade() -> None:
    op.execute(f"ALTER TABLE {schema}documents ADD COLUMN IF NOT EXISTS tags VARCHAR[] NOT NULL DEFAULT '{{}}'")


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Remove tags columns and index."""
    schema = _get_schema_prefix()

    op.execute(f"DROP INDEX IF EXISTS {schema}idx_memory_units_tags")
    op.execute(f"ALTER TABLE {schema}memory_units DROP COLUMN IF EXISTS tags")
    op.execute(f"ALTER TABLE {schema}documents DROP COLUMN IF EXISTS tags")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -13,8 +13,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "g2h3i4j5k6l7"
 down_revision: str | Sequence[str] | None = "f1a2b3c4d5e6"
@@ -28,7 +26,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()

    # 1. Delete any remaining opinion rows
@@ -51,7 +49,7 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    schema = _get_schema_prefix()

    # Restore confidence_score column
@@ -83,11 +81,3 @@ def _pg_downgrade() -> None:
        f"CREATE INDEX idx_memory_units_opinion_date ON {schema}memory_units "
        f"(bank_id, event_date DESC) WHERE fact_type = 'opinion'"
    )
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -22,8 +22,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "g7h8i9j0k1l2"
 down_revision: str | Sequence[str] | None = "f6g7h8i9j0k1"
 branch_labels: str | Sequence[str] | None = None
@@ -35,7 +33,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    schema = _get_schema_prefix()
    mu = f"{schema}memory_units"
    banks = f"{schema}banks"
@@ -68,14 +66,6 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    # Deleted rows cannot be restored.
    pass
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -17,8 +17,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "h3c4d5e6f7g8"
 down_revision: str | Sequence[str] | None = "g2a3b4c5d6e7"
@@ -32,7 +30,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Apply mental models v4 changes."""
    schema = _get_schema_prefix()

@@ -87,26 +85,6 @@ def _pg_upgrade() -> None:
        )
    """)

-    # Step 4b: If the table already existed (from reflections rename chain),
-    # it won't have the v4 columns. Add them idempotently so the migration
-    # works regardless of whether CREATE TABLE above was a no-op.
-    for col_ddl in [
-        "subtype VARCHAR(32) NOT NULL DEFAULT 'directive'",
-        "description TEXT NOT NULL DEFAULT ''",
-        "entity_id UUID",
-        "observations JSONB DEFAULT '{\"observations\": []}'::jsonb",
-        "links VARCHAR[]",
-        "last_updated TIMESTAMP WITH TIME ZONE",
-    ]:
-        op.execute(f"ALTER TABLE {schema}mental_models ADD COLUMN IF NOT EXISTS {col_ddl}")
-
-    # Ensure the subtype CHECK constraint exists (may not if table was renamed)
-    op.execute(f"ALTER TABLE {schema}mental_models DROP CONSTRAINT IF EXISTS ck_mental_models_subtype")
-    op.execute(f"""
-        ALTER TABLE {schema}mental_models
-        ADD CONSTRAINT ck_mental_models_subtype CHECK (subtype IN ('structural', 'emergent', 'pinned', 'learned'))
-    """)
-
    # Step 5: Create indexes for efficient queries (if not exist)
    op.execute(f"CREATE INDEX IF NOT EXISTS idx_mental_models_bank_id ON {schema}mental_models(bank_id)")
    op.execute(f"CREATE INDEX IF NOT EXISTS idx_mental_models_subtype ON {schema}mental_models(bank_id, subtype)")
@@ -115,7 +93,7 @@ def _pg_upgrade() -> None:
    op.execute(f"CREATE INDEX IF NOT EXISTS idx_mental_models_tags ON {schema}mental_models USING GIN(tags)")


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Revert mental models v4 changes."""
    schema = _get_schema_prefix()

@@ -132,11 +110,3 @@ def _pg_downgrade() -> None:
    op.execute(f"ALTER TABLE {schema}banks DROP COLUMN IF EXISTS mission")

    # Note: Cannot restore deleted observations - they are lost on downgrade
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,52 +0,0 @@
-"""Merge 3 migration heads and add unit_entities composite index
-
-Revision ID: h3i4j5k6l7m8
-Revises: a4b5c6d7e8f9, g2h3i4j5k6l7
-Create Date: 2026-04-07
-
-Merges three unmerged migration heads into one, and adds a composite index
-(entity_id, unit_id) on unit_entities for index-only scans in the LATERAL
-entity expansion query.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "h3i4j5k6l7m8"
-down_revision: str | Sequence[str] | None = ("a4b5c6d7e8f9", "g2h3i4j5k6l7")
-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 _pg_upgrade() -> None:
-    schema = _get_schema_prefix()
-    # Composite index enables index-only scans for entity_id -> unit_id lookups
-    op.execute(
-        f"CREATE INDEX IF NOT EXISTS idx_unit_entities_entity_unit ON {schema}unit_entities (entity_id, unit_id)"
-    )
-    # Drop the now-redundant single-column index
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_unit_entities_entity")
-
-
-def _pg_downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_unit_entities_entity_unit")
-    # Restore the single-column index
-    op.execute(f"CREATE INDEX IF NOT EXISTS idx_unit_entities_entity ON {schema}unit_entities (entity_id)")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -13,8 +13,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "i4d5e6f7g8h9"
 down_revision: str | Sequence[str] | None = "h3c4d5e6f7g8"
@@ -28,7 +26,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Delete opinion memory_units."""
    schema = _get_schema_prefix()

@@ -37,15 +35,7 @@ def _pg_upgrade() -> None:
    op.execute(f"DELETE FROM {schema}memory_units WHERE fact_type = 'opinion'")


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Cannot restore deleted opinions."""
    # Note: Cannot restore deleted opinions - they are lost on downgrade
    pass
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,49 +0,0 @@
-"""Add 'cancelled' to async_operations status check constraint
-
-Revision ID: i4j5k6l7m8n9
-Revises: d5y6z7a8b9c0
-Create Date: 2026-04-23
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "i4j5k6l7m8n9"
-down_revision: str | Sequence[str] | None = "d5y6z7a8b9c0"
-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 _pg_upgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}async_operations DROP CONSTRAINT IF EXISTS async_operations_status_check")
-    op.execute(
-        f"ALTER TABLE {schema}async_operations ADD CONSTRAINT async_operations_status_check "
-        f"CHECK (status IN ('pending', 'processing', 'completed', 'failed', 'cancelled'))"
-    )
-
-
-def _pg_downgrade() -> None:
-    schema = _get_schema_prefix()
-    op.execute(f"ALTER TABLE {schema}async_operations DROP CONSTRAINT IF EXISTS async_operations_status_check")
-    op.execute(
-        f"ALTER TABLE {schema}async_operations ADD CONSTRAINT async_operations_status_check "
-        f"CHECK (status IN ('pending', 'processing', 'completed', 'failed'))"
-    )
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -15,8 +15,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "j5e6f7g8h9i0"
 down_revision: str | Sequence[str] | None = "i4d5e6f7g8h9"
@@ -30,7 +28,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Create mental_model_versions table and add version tracking."""
    schema = _get_schema_prefix()

@@ -83,7 +81,7 @@ def _pg_upgrade() -> None:
    """)


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Remove mental_model_versions table and version column."""
    schema = _get_schema_prefix()

@@ -95,11 +93,3 @@ def _pg_downgrade() -> None:

    # Remove version column from mental_models
    op.execute(f"ALTER TABLE {schema}mental_models DROP COLUMN IF EXISTS version")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -12,8 +12,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "k6f7g8h9i0j1"
 down_revision: str | Sequence[str] | None = "j5e6f7g8h9i0"
@@ -27,7 +25,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Add 'directive' to mental_models subtype constraint."""
    schema = _get_schema_prefix()

@@ -42,7 +40,7 @@ def _pg_upgrade() -> None:
    """)


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Remove 'directive' from mental_models subtype constraint."""
    schema = _get_schema_prefix()

@@ -58,11 +56,3 @@ def _pg_downgrade() -> None:
        ADD CONSTRAINT ck_mental_models_subtype
        CHECK (subtype IN ('structural', 'emergent', 'pinned', 'learned'))
    """)
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,38 +0,0 @@
-"""No-op: observation_sources table is Oracle-only
-
-Originally created the observation_sources junction table for all backends,
-but PG uses native array ops on the source_memory_ids column (faster at scale).
-Oracle creates this table in the o1a2b3c4d5e6 baseline migration instead.
-
-Kept as a no-op to preserve the Alembic revision chain.
-
-Revision ID: k6l7m8n9o0p1
-Revises: i4j5k6l7m8n9
-Create Date: 2026-04-24
-"""
-
-from collections.abc import Sequence
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "k6l7m8n9o0p1"
-down_revision: str | Sequence[str] | None = "i4j5k6l7m8n9"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _pg_upgrade() -> None:
-    # PG uses source_memory_ids[] array on memory_units — no junction table.
-    pass
-
-
-def _pg_downgrade() -> None:
-    pass
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -17,8 +17,6 @@ import sqlalchemy as sa
 from alembic import context, op
 from sqlalchemy.dialects import postgresql

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "l7g8h9i0j1k2"
 down_revision: str | Sequence[str] | None = "k6f7g8h9i0j1"
@@ -32,7 +30,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Add worker columns to async_operations."""
    schema = _get_schema_prefix()

@@ -80,7 +78,7 @@ def _pg_upgrade() -> None:
    )


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Remove worker columns from async_operations."""
    schema = _get_schema_prefix()

@@ -109,11 +107,3 @@ def _pg_downgrade() -> None:
        "worker_id",
        schema=context.config.get_main_option("target_schema") or None,
    )
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,31 +0,0 @@
-"""Merge divergent heads from deferrable FK and cooccurrence backfill
-
-Revision ID: m3rg3h3ad5f6
-Revises: 9f8e7d6c5b4a, b5d4e3f2a1c9
-Create Date: 2026-05-04
-"""
-
-from collections.abc import Sequence
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "m3rg3h3ad5f6"
-down_revision: tuple[str, ...] = ("9f8e7d6c5b4a", "b5d4e3f2a1c9")
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-def _pg_upgrade() -> None:
-    pass
-
-
-def _pg_downgrade() -> None:
-    pass
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -12,8 +12,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "m8h9i0j1k2l3"
 down_revision: str | Sequence[str] | None = "l7g8h9i0j1k2"
@@ -27,7 +25,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Change mental_models.id from VARCHAR(64) to TEXT."""
    schema = _get_schema_prefix()

@@ -35,17 +33,9 @@ def _pg_upgrade() -> None:
    op.execute(f"ALTER TABLE {schema}mental_models ALTER COLUMN id TYPE TEXT")


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Revert mental_models.id from TEXT to VARCHAR(64)."""
    schema = _get_schema_prefix()

    # Note: This may fail if any id values exceed 64 characters
    op.execute(f"ALTER TABLE {schema}mental_models ALTER COLUMN id TYPE VARCHAR(64)")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -16,8 +16,6 @@ from collections.abc import Sequence
 from alembic import context, op
 from sqlalchemy import text

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "n9i0j1k2l3m4"
 down_revision: str | Sequence[str] | None = "m8h9i0j1k2l3"
@@ -32,65 +30,53 @@ def _get_schema_prefix() -> str:


 def _detect_vector_extension() -> str:
-    """Detect or validate vector extension for this immutable migration revision."""
+    """
+    Detect or validate vector extension: 'pgvector', 'vchord', or 'pgvectorscale'.
+    Respects HINDSIGHT_API_VECTOR_EXTENSION env var if set.
+    """
    conn = op.get_bind()
    vector_extension = os.getenv("HINDSIGHT_API_VECTOR_EXTENSION", "pgvector").lower()

+    # Validate configured extension is installed
    if vector_extension == "pgvectorscale":
+        # pgvectorscale/DiskANN requires pgvector
        pgvector_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vector'")).scalar()
        if not pgvector_check:
            raise RuntimeError(
                "DiskANN requires pgvector. Install with: CREATE EXTENSION vector; then vectorscale or pg_diskann CASCADE;"
            )
+        # Check for either vectorscale (open source) or pg_diskann (Azure)
        vectorscale_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vectorscale'")).scalar()
        pg_diskann_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'pg_diskann'")).scalar()

        if vectorscale_check:
            return "pgvectorscale"
-        if pg_diskann_check:
+        elif pg_diskann_check:
            return "pg_diskann"
-        raise RuntimeError(
-            "Configured vector extension 'pgvectorscale' not found. Install either:\n"
-            "  - pgvectorscale: CREATE EXTENSION vectorscale CASCADE;\n"
-            "  - pg_diskann (Azure): CREATE EXTENSION pg_diskann CASCADE;"
-        )
-    if vector_extension == "vchord":
+        else:
+            raise RuntimeError(
+                "Configured vector extension 'pgvectorscale' not found. Install either:\n"
+                "  - pgvectorscale: CREATE EXTENSION vectorscale CASCADE;\n"
+                "  - pg_diskann (Azure): CREATE EXTENSION pg_diskann CASCADE;"
+            )
+    elif vector_extension == "vchord":
        vchord_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vchord'")).scalar()
        if not vchord_check:
            raise RuntimeError(
                "Configured vector extension 'vchord' not found. Install it with: CREATE EXTENSION vchord CASCADE;"
            )
        return "vchord"
-    if vector_extension == "scann":
-        scann_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'alloydb_scann'")).scalar()
-        if not scann_check:
-            raise RuntimeError(
-                "Configured vector extension 'scann' not found. Install it with: CREATE EXTENSION alloydb_scann CASCADE;"
-            )
-        return "scann"
-    if vector_extension == "pgvector":
+    elif vector_extension == "pgvector":
        pgvector_check = conn.execute(text("SELECT 1 FROM pg_extension WHERE extname = 'vector'")).scalar()
        if not pgvector_check:
            raise RuntimeError(
                "Configured vector extension 'pgvector' not found. Install it with: CREATE EXTENSION vector;"
            )
        return "pgvector"
-    raise ValueError(
-        "Invalid HINDSIGHT_API_VECTOR_EXTENSION: "
-        f"{vector_extension}. Must be 'pgvector', 'vchord', 'pgvectorscale', or 'scann'"
-    )
-
-
-def _vector_index_using_clause(ext: str) -> str:
-    if ext == "pgvectorscale":
-        return "USING diskann (embedding vector_cosine_ops) WITH (num_neighbors = 50)"
-    if ext == "pg_diskann":
-        return "USING diskann (embedding vector_cosine_ops) WITH (max_neighbors = 50)"
-    if ext == "vchord":
-        return "USING vchordrq (embedding vector_l2_ops)"
-    if ext == "scann":
-        return "USING scann (embedding cosine) WITH (mode = 'AUTO')"
-    return "USING hnsw (embedding vector_cosine_ops)"
+    else:
+        raise ValueError(
+            f"Invalid HINDSIGHT_API_VECTOR_EXTENSION: {vector_extension}. Must be 'pgvector', 'vchord', or 'pgvectorscale'"
+        )


 def _detect_text_search_extension() -> str:
@@ -133,7 +119,7 @@ def _detect_text_search_extension() -> str:
        )


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Create learnings and pinned_reflections tables."""
    schema = _get_schema_prefix()

@@ -170,12 +156,28 @@ def _pg_upgrade() -> None:
    # Indexes for learnings
    op.execute(f"CREATE INDEX idx_learnings_bank_id ON {schema}learnings(bank_id)")

-    # Create vector index based on detected extension. ScaNN is deferred because
-    # this table is empty during migration and AlloyDB rejects empty ScaNN builds.
-    if vector_ext != "scann":
+    # Create vector index based on detected extension
+    if vector_ext == "pgvectorscale":
        op.execute(f"""
            CREATE INDEX idx_learnings_embedding ON {schema}learnings
-            {_vector_index_using_clause(vector_ext)}
+            USING diskann (embedding vector_cosine_ops)
+            WITH (num_neighbors = 50)
+        """)
+    elif vector_ext == "pg_diskann":
+        op.execute(f"""
+            CREATE INDEX idx_learnings_embedding ON {schema}learnings
+            USING diskann (embedding vector_cosine_ops)
+            WITH (max_neighbors = 50)
+        """)
+    elif vector_ext == "vchord":
+        op.execute(f"""
+            CREATE INDEX idx_learnings_embedding ON {schema}learnings
+            USING vchordrq (embedding vector_l2_ops)
+        """)
+    else:  # pgvector
+        op.execute(f"""
+            CREATE INDEX idx_learnings_embedding ON {schema}learnings
+            USING hnsw (embedding vector_cosine_ops)
        """)

    op.execute(f"CREATE INDEX idx_learnings_tags ON {schema}learnings USING GIN(tags)")
@@ -233,12 +235,28 @@ def _pg_upgrade() -> None:
    # Indexes for pinned_reflections
    op.execute(f"CREATE INDEX idx_pinned_reflections_bank_id ON {schema}pinned_reflections(bank_id)")

-    # Create vector index based on detected extension. ScaNN is deferred because
-    # this table is empty during migration and AlloyDB rejects empty ScaNN builds.
-    if vector_ext != "scann":
+    # Create vector index based on detected extension
+    if vector_ext == "pgvectorscale":
        op.execute(f"""
            CREATE INDEX idx_pinned_reflections_embedding ON {schema}pinned_reflections
-            {_vector_index_using_clause(vector_ext)}
+            USING diskann (embedding vector_cosine_ops)
+            WITH (num_neighbors = 50)
+        """)
+    elif vector_ext == "pg_diskann":
+        op.execute(f"""
+            CREATE INDEX idx_pinned_reflections_embedding ON {schema}pinned_reflections
+            USING diskann (embedding vector_cosine_ops)
+            WITH (max_neighbors = 50)
+        """)
+    elif vector_ext == "vchord":
+        op.execute(f"""
+            CREATE INDEX idx_pinned_reflections_embedding ON {schema}pinned_reflections
+            USING vchordrq (embedding vector_l2_ops)
+        """)
+    else:  # pgvector
+        op.execute(f"""
+            CREATE INDEX idx_pinned_reflections_embedding ON {schema}pinned_reflections
+            USING hnsw (embedding vector_cosine_ops)
        """)

    op.execute(f"CREATE INDEX idx_pinned_reflections_tags ON {schema}pinned_reflections USING GIN(tags)")
@@ -286,7 +304,7 @@ def _pg_upgrade() -> None:
    """)


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Drop learnings and pinned_reflections tables."""
    schema = _get_schema_prefix()

@@ -297,11 +315,3 @@ def _pg_downgrade() -> None:
    # Remove columns from banks
    op.execute(f"ALTER TABLE {schema}banks DROP COLUMN IF EXISTS last_consolidated_at")
    op.execute(f"ALTER TABLE {schema}banks DROP COLUMN IF EXISTS mission_changed_at")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -16,8 +16,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "o0j1k2l3m4n5"
 down_revision: str | Sequence[str] | None = "n9i0j1k2l3m4"
@@ -31,7 +29,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Migrate data and clean up old mental models."""
    schema = _get_schema_prefix()

@@ -82,17 +80,15 @@ def _pg_upgrade() -> None:
    # 4. Drop the mental_model_versions table (no longer used)
    op.execute(f"DROP TABLE IF EXISTS {schema}mental_model_versions CASCADE")

-    # 5. Drop old constraints and add new one that allows current subtypes.
-    # 'pinned' is still used by the code for user-created mental models;
-    # 'directive' is used for system directives.
+    # 5. Drop old constraints and add new one that only allows 'directive'
    op.execute(f"ALTER TABLE {schema}mental_models DROP CONSTRAINT IF EXISTS ck_mental_models_subtype")
    op.execute(f"""
        ALTER TABLE {schema}mental_models
-        ADD CONSTRAINT ck_mental_models_subtype CHECK (subtype IN ('directive', 'pinned'))
+        ADD CONSTRAINT ck_mental_models_subtype CHECK (subtype = 'directive')
    """)


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Reverse the migration (data migration is one-way, so this just removes constraints)."""
    schema = _get_schema_prefix()

@@ -115,11 +111,3 @@ def _pg_downgrade() -> None:
    )

    # Note: Data migration cannot be reversed - pinned_reflections and learnings data remains
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -1,445 +0,0 @@
-"""oracle_baseline
-
-Brings a fresh Oracle 23ai database up to the current schema in a single step.
-PostgreSQL is a no-op here — the prior 59 revisions already build the PG schema
-incrementally; this revision just closes the loop so both dialects share a
-single head from this point on.
-
-After this migration ships, *every* new revision must fill both the ``_pg_*``
-and ``_oracle_*`` slots (or explicitly leave one ``None``); a CI check enforces
-that.
-
-Tables mirror the PostgreSQL schema but use Oracle-native types:
-  - UUID                       -> RAW(16) DEFAULT SYS_GUID()
-  - TEXT / large VARCHAR        -> CLOB
-  - JSONB                       -> CLOB with IS JSON CHECK
-  - BOOLEAN                     -> NUMBER(1)
-  - FLOAT                       -> BINARY_DOUBLE
-  - VARCHAR[]                   -> CLOB (JSON array stored as string)
-  - BYTEA                       -> BLOB
-  - vector(384)                 -> VECTOR(384, FLOAT32) (Oracle 23ai native)
-
-Revision ID: o1a2b3c4d5e6
-Revises: k6l7m8n9o0p1
-Create Date: 2026-04-29
-"""
-
-from collections.abc import Sequence
-
-from alembic import op
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "o1a2b3c4d5e6"
-down_revision: str | Sequence[str] | None = "k6l7m8n9o0p1"
-branch_labels: str | Sequence[str] | None = None
-depends_on: str | Sequence[str] | None = None
-
-
-# ---------------------------------------------------------------------------
-# Tables — created in dependency order
-# ---------------------------------------------------------------------------
-
-_TABLES: tuple[str, ...] = (
-    """
-    CREATE TABLE IF NOT EXISTS banks (
-        bank_id           VARCHAR2(256)  NOT NULL,
-        internal_id       RAW(16)        DEFAULT SYS_GUID() NOT NULL,
-        name              VARCHAR2(512),
-        disposition       CLOB           DEFAULT '{"skepticism":3,"literalism":3,"empathy":3}' NOT NULL
-                                         CONSTRAINT banks_disposition_json CHECK (disposition IS JSON),
-        mission           CLOB,
-        personality       CLOB           DEFAULT '{}' NOT NULL
-                                         CONSTRAINT banks_personality_json CHECK (personality IS JSON),
-        config            CLOB           DEFAULT '{}' NOT NULL
-                                         CONSTRAINT banks_config_json CHECK (config IS JSON),
-        created_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        updated_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        CONSTRAINT pk_banks PRIMARY KEY (bank_id),
-        CONSTRAINT banks_internal_id_unique UNIQUE (internal_id)
-    )
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS documents (
-        id                VARCHAR2(512)  NOT NULL,
-        bank_id           VARCHAR2(256)  NOT NULL,
-        original_text     CLOB,
-        content_hash      VARCHAR2(128),
-        metadata          CLOB           DEFAULT '{}' NOT NULL
-                                         CONSTRAINT docs_metadata_json CHECK (metadata IS JSON),
-        retain_params     CLOB           CONSTRAINT docs_retain_params_json CHECK (retain_params IS JSON OR retain_params IS NULL),
-        file_storage_key  VARCHAR2(512),
-        file_original_name VARCHAR2(512),
-        file_content_type VARCHAR2(256),
-        tags              CLOB           DEFAULT '[]' NOT NULL,
-        created_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        updated_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        CONSTRAINT pk_documents PRIMARY KEY (id, bank_id),
-        CONSTRAINT fk_documents_bank FOREIGN KEY (bank_id) REFERENCES banks(bank_id) ON DELETE CASCADE
-    )
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS chunks (
-        chunk_id          VARCHAR2(512)  NOT NULL,
-        document_id       VARCHAR2(512)  NOT NULL,
-        bank_id           VARCHAR2(256)  NOT NULL,
-        chunk_index       NUMBER(10)     NOT NULL,
-        chunk_text        CLOB           NOT NULL,
-        content_hash      VARCHAR2(128),
-        created_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        CONSTRAINT pk_chunks PRIMARY KEY (chunk_id),
-        CONSTRAINT fk_chunks_document FOREIGN KEY (document_id, bank_id)
-            REFERENCES documents(id, bank_id) ON DELETE CASCADE
-    )
-    """,
-    # memory_units uses automatic list partitioning on bank_id at create time —
-    # no post-create ALTER required (we used to do that for legacy installs).
-    """
-    CREATE TABLE IF NOT EXISTS memory_units (
-        id                RAW(16)        DEFAULT SYS_GUID() NOT NULL,
-        bank_id           VARCHAR2(256)  NOT NULL,
-        document_id       VARCHAR2(512),
-        chunk_id          VARCHAR2(512),
-        text              CLOB           NOT NULL,
-        embedding         VECTOR(384, FLOAT32),
-        context           CLOB,
-        event_date        TIMESTAMP WITH TIME ZONE NOT NULL,
-        occurred_start    TIMESTAMP WITH TIME ZONE,
-        occurred_end      TIMESTAMP WITH TIME ZONE,
-        mentioned_at      TIMESTAMP WITH TIME ZONE,
-        fact_type         VARCHAR2(64)   DEFAULT 'world' NOT NULL,
-        confidence_score  BINARY_DOUBLE,
-        access_count      NUMBER(10)     DEFAULT 0 NOT NULL,
-        consolidated_at   TIMESTAMP WITH TIME ZONE,
-        observation_scopes CLOB          CONSTRAINT mu_obs_scopes_json CHECK (observation_scopes IS JSON OR observation_scopes IS NULL),
-        tags              CLOB           DEFAULT '[]' NOT NULL,
-        metadata          CLOB           DEFAULT '{}' NOT NULL
-                                         CONSTRAINT mu_metadata_json CHECK (metadata IS JSON),
-        proof_count       NUMBER(10)     DEFAULT 1,
-        source_memory_ids CLOB,
-        history           CLOB           DEFAULT '[]'
-                                         CONSTRAINT mu_history_json CHECK (history IS JSON OR history IS NULL),
-        text_signals      CLOB,
-        consolidation_failed_at TIMESTAMP WITH TIME ZONE,
-        search_vector     CLOB,
-        created_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        updated_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        CONSTRAINT pk_memory_units PRIMARY KEY (id),
-        CONSTRAINT fk_mu_document FOREIGN KEY (document_id, bank_id)
-            REFERENCES documents(id, bank_id) ON DELETE CASCADE,
-        CONSTRAINT fk_mu_chunk FOREIGN KEY (chunk_id)
-            REFERENCES chunks(chunk_id) ON DELETE SET NULL,
-        CONSTRAINT chk_mu_fact_type CHECK (fact_type IN ('world', 'experience', 'observation')),
-        CONSTRAINT chk_mu_confidence CHECK (
-            confidence_score IS NULL
-            OR (confidence_score >= 0.0 AND confidence_score <= 1.0)
-        )
-    )
-    PARTITION BY LIST (bank_id) AUTOMATIC
-    (PARTITION p_default VALUES ('__default__'))
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS entities (
-        id                RAW(16)        DEFAULT SYS_GUID() NOT NULL,
-        bank_id           VARCHAR2(256)  NOT NULL,
-        canonical_name    VARCHAR2(512)  NOT NULL,
-        metadata          CLOB           DEFAULT '{}' NOT NULL
-                                         CONSTRAINT ent_metadata_json CHECK (metadata IS JSON),
-        first_seen        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        last_seen         TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        mention_count     NUMBER(10)     DEFAULT 1 NOT NULL,
-        CONSTRAINT pk_entities PRIMARY KEY (id)
-    )
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS unit_entities (
-        unit_id           RAW(16)        NOT NULL,
-        entity_id         RAW(16)        NOT NULL,
-        CONSTRAINT pk_unit_entities PRIMARY KEY (unit_id, entity_id),
-        CONSTRAINT fk_ue_unit FOREIGN KEY (unit_id) REFERENCES memory_units(id) ON DELETE CASCADE,
-        CONSTRAINT fk_ue_entity FOREIGN KEY (entity_id) REFERENCES entities(id) ON DELETE CASCADE
-    )
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS entity_cooccurrences (
-        entity_id_1       RAW(16)        NOT NULL,
-        entity_id_2       RAW(16)        NOT NULL,
-        cooccurrence_count NUMBER(10)    DEFAULT 1 NOT NULL,
-        last_cooccurred   TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        CONSTRAINT pk_entity_cooccurrences PRIMARY KEY (entity_id_1, entity_id_2),
-        CONSTRAINT fk_ec_entity1 FOREIGN KEY (entity_id_1) REFERENCES entities(id) ON DELETE CASCADE,
-        CONSTRAINT fk_ec_entity2 FOREIGN KEY (entity_id_2) REFERENCES entities(id) ON DELETE CASCADE
-    )
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS memory_links (
-        from_unit_id      RAW(16)        NOT NULL,
-        to_unit_id        RAW(16)        NOT NULL,
-        link_type         VARCHAR2(64)   NOT NULL,
-        entity_id         RAW(16),
-        bank_id           VARCHAR2(256),
-        weight            BINARY_DOUBLE  DEFAULT 1.0 NOT NULL,
-        source_memory_ids CLOB,
-        created_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        CONSTRAINT fk_ml_from FOREIGN KEY (from_unit_id) REFERENCES memory_units(id) ON DELETE CASCADE,
-        CONSTRAINT fk_ml_to FOREIGN KEY (to_unit_id) REFERENCES memory_units(id) ON DELETE CASCADE,
-        CONSTRAINT fk_ml_entity FOREIGN KEY (entity_id) REFERENCES entities(id) ON DELETE CASCADE,
-        CONSTRAINT chk_ml_link_type CHECK (
-            link_type IN ('temporal', 'semantic', 'entity', 'causes', 'caused_by', 'enables', 'prevents')
-        ),
-        CONSTRAINT chk_ml_weight CHECK (weight >= 0.0 AND weight <= 1.0)
-    )
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS mental_models (
-        id                VARCHAR2(256)  NOT NULL,
-        bank_id           VARCHAR2(256)  NOT NULL,
-        subtype           VARCHAR2(32)   NOT NULL,
-        name              VARCHAR2(256)  NOT NULL,
-        description       CLOB           NOT NULL,
-        source_query      CLOB,
-        content           CLOB,
-        embedding         VECTOR(384, FLOAT32),
-        entity_id         RAW(16),
-        observations      CLOB           DEFAULT '{"observations":[]}' NOT NULL
-                                         CONSTRAINT mm_obs_json CHECK (observations IS JSON),
-        links             CLOB,
-        tags              CLOB           DEFAULT '[]' NOT NULL,
-        max_tokens        NUMBER(10)     DEFAULT 2048 NOT NULL,
-        "trigger"         CLOB           DEFAULT '{"refresh_after_consolidation":false}' NOT NULL
-                                         CONSTRAINT mm_trigger_json CHECK ("trigger" IS JSON),
-        structured_content CLOB          CONSTRAINT mm_sc_json CHECK (structured_content IS JSON OR structured_content IS NULL),
-        last_refreshed_source_query CLOB,
-        reflect_response  CLOB           CONSTRAINT mm_reflect_resp_json CHECK (reflect_response IS JSON OR reflect_response IS NULL),
-        history           CLOB           DEFAULT '[]' NOT NULL
-                                         CONSTRAINT mm_history_json CHECK (history IS JSON),
-        last_refreshed_at TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        last_updated      TIMESTAMP WITH TIME ZONE,
-        created_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        CONSTRAINT pk_mental_models PRIMARY KEY (id, bank_id),
-        CONSTRAINT fk_mm_bank FOREIGN KEY (bank_id) REFERENCES banks(bank_id) ON DELETE CASCADE,
-        CONSTRAINT fk_mm_entity FOREIGN KEY (entity_id) REFERENCES entities(id) ON DELETE SET NULL,
-        CONSTRAINT chk_mm_subtype CHECK (subtype IN ('directive', 'pinned'))
-    )
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS directives (
-        id                RAW(16)        DEFAULT SYS_GUID() NOT NULL,
-        bank_id           VARCHAR2(256)  NOT NULL,
-        name              VARCHAR2(256)  NOT NULL,
-        content           CLOB           NOT NULL,
-        priority          NUMBER(10)     DEFAULT 0 NOT NULL,
-        is_active         NUMBER(1)      DEFAULT 1 NOT NULL,
-        tags              CLOB           DEFAULT '[]' NOT NULL,
-        created_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        updated_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        CONSTRAINT pk_directives PRIMARY KEY (id),
-        CONSTRAINT fk_dir_bank FOREIGN KEY (bank_id) REFERENCES banks(bank_id) ON DELETE CASCADE
-    )
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS async_operations (
-        operation_id      RAW(16)        DEFAULT SYS_GUID() NOT NULL,
-        bank_id           VARCHAR2(256)  NOT NULL,
-        operation_type    VARCHAR2(128)  NOT NULL,
-        status            VARCHAR2(32)   DEFAULT 'pending' NOT NULL,
-        worker_id         VARCHAR2(256),
-        claimed_at        TIMESTAMP WITH TIME ZONE,
-        retry_count       NUMBER(10)     DEFAULT 0 NOT NULL,
-        next_retry_at     TIMESTAMP WITH TIME ZONE,
-        task_payload      CLOB           CONSTRAINT ao_payload_json CHECK (task_payload IS JSON OR task_payload IS NULL),
-        result_metadata   CLOB           DEFAULT '{}' NOT NULL
-                                         CONSTRAINT ao_result_json CHECK (result_metadata IS JSON),
-        error_message     CLOB,
-        created_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        updated_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        completed_at      TIMESTAMP WITH TIME ZONE,
-        CONSTRAINT pk_async_operations PRIMARY KEY (operation_id),
-        CONSTRAINT fk_ao_bank FOREIGN KEY (bank_id) REFERENCES banks(bank_id) ON DELETE CASCADE,
-        CONSTRAINT chk_ao_status CHECK (status IN ('pending', 'processing', 'completed', 'failed', 'cancelled'))
-    )
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS webhooks (
-        id                RAW(16)        DEFAULT SYS_GUID() NOT NULL,
-        bank_id           VARCHAR2(256)  NOT NULL,
-        url               VARCHAR2(2048) NOT NULL,
-        secret            VARCHAR2(512),
-        event_types       CLOB           DEFAULT '[]' NOT NULL,
-        http_config       CLOB           DEFAULT '{}' NOT NULL
-                                         CONSTRAINT wh_http_config_json CHECK (http_config IS JSON),
-        enabled           NUMBER(1)      DEFAULT 1 NOT NULL,
-        created_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        updated_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        CONSTRAINT pk_webhooks PRIMARY KEY (id),
-        CONSTRAINT fk_wh_bank FOREIGN KEY (bank_id) REFERENCES banks(bank_id) ON DELETE CASCADE
-    )
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS file_storage (
-        storage_key       VARCHAR2(512)  NOT NULL,
-        data              BLOB           NOT NULL,
-        CONSTRAINT pk_file_storage PRIMARY KEY (storage_key)
-    )
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS audit_log (
-        id                RAW(16)        DEFAULT SYS_GUID() NOT NULL,
-        action            VARCHAR2(128)  NOT NULL,
-        transport         VARCHAR2(64)   NOT NULL,
-        bank_id           VARCHAR2(256),
-        started_at        TIMESTAMP WITH TIME ZONE DEFAULT SYSTIMESTAMP NOT NULL,
-        ended_at          TIMESTAMP WITH TIME ZONE,
-        request           CLOB           CONSTRAINT al_request_json CHECK (request IS JSON OR request IS NULL),
-        response          CLOB           CONSTRAINT al_response_json CHECK (response IS JSON OR response IS NULL),
-        metadata          CLOB           DEFAULT '{}' NOT NULL
-                                         CONSTRAINT al_metadata_json CHECK (metadata IS JSON),
-        CONSTRAINT pk_audit_log PRIMARY KEY (id)
-    )
-    """,
-    """
-    CREATE TABLE IF NOT EXISTS observation_sources (
-        observation_id    RAW(16)        NOT NULL,
-        source_id         RAW(16)        NOT NULL,
-        CONSTRAINT pk_observation_sources PRIMARY KEY (observation_id, source_id),
-        CONSTRAINT fk_obs_src_observation FOREIGN KEY (observation_id)
-            REFERENCES memory_units(id) ON DELETE CASCADE
-    )
-    """,
-)
-
-
-# ---------------------------------------------------------------------------
-# B-tree indexes
-# ---------------------------------------------------------------------------
-
-_INDEXES: tuple[str, ...] = (
-    # documents
-    "CREATE INDEX idx_docs_bank_id ON documents(bank_id)",
-    "CREATE INDEX idx_docs_content_hash ON documents(content_hash)",
-    # chunks
-    "CREATE INDEX idx_chunks_document_id ON chunks(document_id)",
-    "CREATE INDEX idx_chunks_bank_id ON chunks(bank_id)",
-    # memory_units
-    "CREATE INDEX idx_mu_bank_id ON memory_units(bank_id)",
-    "CREATE INDEX idx_mu_document_id ON memory_units(document_id)",
-    "CREATE INDEX idx_mu_chunk_id ON memory_units(chunk_id)",
-    "CREATE INDEX idx_mu_event_date ON memory_units(event_date DESC)",
-    "CREATE INDEX idx_mu_bank_date ON memory_units(bank_id, event_date DESC)",
-    "CREATE INDEX idx_mu_access_count ON memory_units(access_count DESC)",
-    "CREATE INDEX idx_mu_fact_type ON memory_units(fact_type)",
-    "CREATE INDEX idx_mu_bank_fact_type ON memory_units(bank_id, fact_type)",
-    "CREATE INDEX idx_mu_bank_type_date ON memory_units(bank_id, fact_type, event_date DESC)",
-    # entities
-    "CREATE INDEX idx_ent_bank_id ON entities(bank_id)",
-    "CREATE INDEX idx_ent_canonical_name ON entities(canonical_name)",
-    "CREATE INDEX idx_ent_bank_name ON entities(bank_id, canonical_name)",
-    "CREATE UNIQUE INDEX idx_ent_bank_lower_name ON entities(bank_id, LOWER(canonical_name))",
-    # unit_entities
-    "CREATE INDEX idx_ue_unit ON unit_entities(unit_id)",
-    "CREATE INDEX idx_ue_entity ON unit_entities(entity_id)",
-    # entity_cooccurrences
-    "CREATE INDEX idx_ec_entity1 ON entity_cooccurrences(entity_id_1)",
-    "CREATE INDEX idx_ec_entity2 ON entity_cooccurrences(entity_id_2)",
-    "CREATE INDEX idx_ec_count ON entity_cooccurrences(cooccurrence_count DESC)",
-    # memory_links — function-based unique index uses NVL with the nil UUID raw
-    # to handle nullable entity_id (matches PG idx_memory_links_unique).
-    "CREATE UNIQUE INDEX idx_memory_links_unique ON memory_links("
-    "from_unit_id, to_unit_id, link_type, "
-    "NVL(entity_id, HEXTORAW('00000000000000000000000000000000')))",
-    "CREATE INDEX idx_ml_from_unit ON memory_links(from_unit_id)",
-    "CREATE INDEX idx_ml_to_unit ON memory_links(to_unit_id)",
-    "CREATE INDEX idx_ml_entity ON memory_links(entity_id)",
-    "CREATE INDEX idx_ml_link_type ON memory_links(link_type)",
-    "CREATE INDEX idx_ml_bank_id ON memory_links(bank_id)",
-    # directives
-    "CREATE INDEX idx_dir_bank_id ON directives(bank_id)",
-    "CREATE INDEX idx_dir_bank_active ON directives(bank_id, is_active)",
-    # mental_models
-    "CREATE INDEX idx_mm_bank_id ON mental_models(bank_id)",
-    "CREATE INDEX idx_mm_subtype ON mental_models(bank_id, subtype)",
-    "CREATE INDEX idx_mm_entity_id ON mental_models(entity_id)",
-    # async_operations
-    "CREATE INDEX idx_ao_bank_id ON async_operations(bank_id)",
-    "CREATE INDEX idx_ao_status ON async_operations(status)",
-    "CREATE INDEX idx_ao_bank_status ON async_operations(bank_id, status)",
-    "CREATE INDEX idx_ao_status_retry ON async_operations(status, next_retry_at)",
-    # webhooks
-    "CREATE INDEX idx_wh_bank_id ON webhooks(bank_id)",
-    # audit_log
-    "CREATE INDEX idx_al_action_started ON audit_log(action, started_at DESC)",
-    "CREATE INDEX idx_al_bank_started ON audit_log(bank_id, started_at DESC)",
-    "CREATE INDEX idx_al_started ON audit_log(started_at DESC)",
-    # observation_sources
-    "CREATE INDEX idx_obs_sources_source_id ON observation_sources(source_id, observation_id)",
-)
-
-_VECTOR_INDEX = (
-    "CREATE VECTOR INDEX idx_mu_embedding_hnsw ON memory_units(embedding) "
-    "ORGANIZATION NEIGHBOR PARTITIONS "
-    "DISTANCE COSINE "
-    "WITH TARGET ACCURACY 95"
-)
-
-# Oracle Text (CTXSYS.CONTEXT) — ``SYNC (ON COMMIT)`` makes it auto-update
-# without a maintenance job. Doubled single quotes for the embedded literal.
-_TEXT_INDEX = (
-    "BEGIN "
-    "EXECUTE IMMEDIATE '"
-    "CREATE INDEX idx_mu_content_text ON memory_units(text) "
-    "INDEXTYPE IS CTXSYS.CONTEXT "
-    "PARAMETERS (''SYNC (ON COMMIT)'')"
-    "'; "
-    "EXCEPTION WHEN OTHERS THEN "
-    "IF SQLCODE = -955 THEN NULL; ELSE RAISE; END IF; "
-    "END;"
-)
-
-
-def _execute_ignoring_955(sql: str) -> None:
-    """Run a CREATE statement and swallow ORA-00955 (object already exists).
-
-    Wraps the statement in PL/SQL so the exception handler runs server-side —
-    no round-trip cost for the common case.
-    """
-    block = (
-        "BEGIN "
-        "EXECUTE IMMEDIATE :stmt; "
-        "EXCEPTION WHEN OTHERS THEN "
-        "IF SQLCODE = -955 THEN NULL; ELSE RAISE; END IF; "
-        "END;"
-    )
-    op.get_bind().exec_driver_sql(block, {"stmt": sql.strip()})
-
-
-def _oracle_upgrade() -> None:
-    bind = op.get_bind()
-    # Tolerate concurrent DDL instead of failing immediately (ORA-00054).
-    bind.exec_driver_sql("ALTER SESSION SET DDL_LOCK_TIMEOUT = 30")
-
-    for ddl in _TABLES:
-        _execute_ignoring_955(ddl)
-
-    for idx in _INDEXES:
-        _execute_ignoring_955(idx)
-
-    # Hindsight on Oracle requires 23ai with VECTOR support (ASSM tablespace)
-    # and the CTXSYS package for full-text. Both index creations must succeed
-    # — the migration fails hard if either feature is unavailable, by design.
-    # We only swallow ORA-00955 (object already exists) so reruns are safe.
-    _execute_ignoring_955(_VECTOR_INDEX)
-    bind.exec_driver_sql(_TEXT_INDEX)
-
-
-def _oracle_downgrade() -> None:
-    # Baseline downgrades aren't supported — dropping every table here would
-    # destroy customer data. Use point-in-time recovery instead.
-    raise NotImplementedError("Cannot downgrade past the Oracle baseline.")
-
-
-def upgrade() -> None:
-    run_for_dialect(oracle=_oracle_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(oracle=_oracle_downgrade)
@@ -21,8 +21,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "p1k2l3m4n5o6"
 down_revision: str | Sequence[str] | None = "o0j1k2l3m4n5"
@@ -36,7 +34,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Implement new knowledge architecture."""
    schema = _get_schema_prefix()

@@ -128,7 +126,7 @@ def _pg_upgrade() -> None:
    """)


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Reverse the migration."""
    schema = _get_schema_prefix()

@@ -194,11 +192,3 @@ def _pg_downgrade() -> None:
    """)

    # Note: mental_models table recreation is complex and would need separate handling
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -12,8 +12,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 # revision identifiers, used by Alembic.
 revision: str = "q2l3m4n5o6p7"
 down_revision: str | Sequence[str] | None = "p1k2l3m4n5o6"
@@ -27,7 +25,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Add 'mental_model' to the fact_type check constraint."""
    schema = _get_schema_prefix()

@@ -40,7 +38,7 @@ def _pg_upgrade() -> None:
    """)


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Remove 'mental_model' from the fact_type check constraint."""
    schema = _get_schema_prefix()

@@ -50,11 +48,3 @@ def _pg_downgrade() -> None:
        ADD CONSTRAINT memory_units_fact_type_check
        CHECK (fact_type IN ('world', 'experience', 'opinion', 'observation'))
    """)
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
@@ -14,8 +14,6 @@ from collections.abc import Sequence

 from alembic import context, op

-from hindsight_api.alembic._dialect import run_for_dialect
-
 revision: str = "r3m4n5o6p7q8"
 down_revision: str | Sequence[str] | None = "q2l3m4n5o6p7"
 branch_labels: str | Sequence[str] | None = None
@@ -28,7 +26,7 @@ def _get_schema_prefix() -> str:
    return f'"{schema}".' if schema else ""


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Add reflect_response JSONB column to reflections."""
    schema = _get_schema_prefix()

@@ -39,7 +37,7 @@ def _pg_upgrade() -> None:
    """)


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Remove reflect_response column from reflections."""
    schema = _get_schema_prefix()

@@ -47,11 +45,3 @@ def _pg_downgrade() -> None:
        ALTER TABLE {schema}reflections
        DROP COLUMN IF EXISTS reflect_response
    """)
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Nicolò Boschi	3f978b446d	fix: remove unused PluginState import from tools.ts	2026-04-07 10:05:36 +02:00
Nicolò Boschi	a4a9d32480	fix: review fixes for opencode integration - Rename CI job from build-opencode-integration to test-opencode-integration to match naming convention for integrations that run tests - Fix tsconfig module resolution to Node16 (consistent with other integrations) - Extract shared makeConfig test helper to avoid duplication across 3 test files	2026-04-07 09:49:19 +02:00
DK09876andClaude Opus 4.6	8b4c7eeb8e	fix: recall retry semantics and README bank scoping clarity 1. recallForContext now returns { context, ok } to distinguish "no results" (ok=true) from "API error" (ok=false). System transform consumes the session on ok=true even with 0 results, so empty banks don't cause repeated queries. Only transient API failures preserve retry. 2. README clarifies that channel/user bank dimensions are process- scoped (set via env vars before launch), not per-session dynamic within a running OpenCode process. 89 tests pass. Co-Authored-By: Claude Opus 4.6 <[email protected]>	2026-04-07 09:45:38 +02:00
DK09876andClaude Opus 4.6	311b96a192	fix: docs/tools findings from second review round 1. Remove "session" from supported dynamic bank fields in docs — the implementation can't vary bank ID per session since it's derived once at plugin startup. 2. Explicit tools (retain, reflect) now call ensureBankMission() before API calls, so bankMission/retainMission are applied even when the agent uses tools exclusively without triggering hooks. 3. Added tests for mission setup via tools path. 88 tests pass. Co-Authored-By: Claude Opus 4.6 <[email protected]>	2026-04-07 09:45:38 +02:00
DK09876andClaude Opus 4.6	fdc48b1544	fix: address review findings for opencode integration 1. Pre-compaction retain now uses shared retainSession() helper, respecting retainMode, documentId, and session_id metadata consistently with idle-retain (was bypassing retention policy). 2. System transform recall is only consumed after successful injection. If Hindsight is briefly unavailable, the plugin retries on the next LLM call instead of permanently skipping recall for the session. 3. Config validation for retainMode and recallBudget — typos like "full_session" or "maximum" now log a warning and fall back to the default instead of silently changing retention semantics. 85 tests (6 new covering compaction documentId, recall retry, and config validation). Co-Authored-By: Claude Opus 4.6 <[email protected]>	2026-04-07 09:45:38 +02:00
DK09876andClaude Opus 4.6	ebb05cf9ca	feat: add OpenCode persistent memory plugin Add hindsight-opencode integration with: - Three custom tools: hindsight_retain, hindsight_recall, hindsight_reflect - Auto-retain on session.idle with document_id deduplication - Memory injection on session start via system transform hook - Memory preservation during context window compaction - Sliding window retain with retainOverlapTurns support - 4-level config hierarchy (defaults, user file, plugin options, env vars) - Dynamic bank ID derivation (agent, project, channel, user dimensions) - CI job, release script entry, docs page 79 tests across 6 test files. Co-Authored-By: Claude Opus 4.6 <[email protected]>	2026-04-07 09:45:38 +02:00