fix(opencode): fix message parsing, shared state, and post-compaction retain

Three bugs fixed: 1. msg.role → msg.info.role: OpenCode SDK wraps role inside info, so all messages were silently filtered out, breaking retain and recall (#941) 2. Move PluginState to module level so it persists across sessions instead of being recreated per plugin instantiation 3. Reset lastRetainedTurn after compaction so idle-retain resumes when the message list shrinks Co-Authored-By: Claude Opus 4.6 <[email protected]>
2026-04-13 09:04:11 -07:00
1388 changed files with 28927 additions and 137178 deletions
@@ -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 +81,17 @@ jobs:
      with:
        node-version: '22'
        registry-url: 'https://registry.npmjs.org'
-        cache: 'npm'
-        cache-dependency-path: package-lock.json

+    # Guard: fail fast if the integration's lockfile resolves any dep from a
+    # monorepo workspace (link=true) or a relative file path. The release
+    # runner has no pre-built workspace `dist/` so `npm run build` would
+    # later fail at tsc with "Cannot find module". See:
+    # https://github.com/vectorize-io/hindsight/issues/… (0.6.0 openclaw retry)
    - 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/${{ steps.info.outputs.integration }}
      run: npm ci
@@ -117,7 +106,7 @@ jobs:
      working-directory: ./hindsight-integrations/${{ 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 }}
@@ -314,7 +314,6 @@ jobs:
    permissions:
      contents: read
      packages: write
-      id-token: write
    strategy:
      matrix:
        include:
@@ -411,7 +410,6 @@ 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 +421,6 @@ 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:
@@ -524,12 +497,6 @@ jobs:
        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:
@@ -566,7 +533,6 @@ jobs:
        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
@@ -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
@@ -30,7 +30,7 @@ It eliminates the shortcomings of alternative techniques such as RAG and knowled

 Hindsight is the most accurate agent memory system ever tested according to benchmark performance. It has achieved state-of-the-art performance on the LongMemEval benchmark, widely used to assess memory system performance across a variety of conversational AI scenarios. The current reported performance of Hindsight and other agent memory solutions as of January 2026 is shown here:

-![Overview](./hindsight-docs/static/img/hindsight-benchmarks.png)
+![Overview](./hindsight-docs/static/img/hindsight-bench.jpg)

 The benchmark performance data for Hindsight has been independently reproduced by research collaborators at the Virginia Tech [Sanghani Center for Artificial Intelligence and Data Analytics](https://sanghani.cs.vt.edu/) and The Washington Post. Other scores are self-reported by software vendors.

@@ -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: 0.6.2
-appVersion: "0.6.2"
+version: 0.5.1
+appVersion: "0.5.1"
 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
@@ -18,17 +18,17 @@ 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";
+import { HindsightServer, consoleLogger } from '@vectorize-io/hindsight-all';
+import { HindsightClient } from '@vectorize-io/hindsight-client';

 const server = new HindsightServer({
-  profile: "my-app",
+  profile: 'my-app',
  port: 9077,
  env: {
-    HINDSIGHT_API_LLM_PROVIDER: "anthropic",
+    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",
+    HINDSIGHT_API_LLM_MODEL: 'claude-sonnet-4-20250514',
+    HINDSIGHT_EMBED_DAEMON_IDLE_TIMEOUT: '0',
  },
  logger: consoleLogger,
 });
@@ -37,11 +37,11 @@ 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",
+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?");
+const recall = await client.recall('user-123', 'what are the user preferences?');
 console.log(recall.results);

 await server.stop();
@@ -62,7 +62,7 @@ If you're hacking on the Python `hindsight-embed` package in the same monorepo,

 ```ts
 new HindsightServer({
-  embedPackagePath: "/path/to/hindsight-embed",
+  embedPackagePath: '/path/to/hindsight-embed',
  // ...
 });
 ```
@@ -1,6 +1,6 @@
 {
  "name": "@vectorize-io/hindsight-all",
-  "version": "0.6.2",
+  "version": "0.5.1",
  "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",
@@ -1,36 +1,32 @@
-import { describe, it, expect } from "vitest";
-import { getEmbedCommand } from "./command.js";
+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"]);
+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('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('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('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",
-    ]);
+  it('local path takes precedence over version', () => {
+    expect(
+      getEmbedCommand({ embedPackagePath: '/abs/path', embedVersion: '0.5.0' }),
+    ).toEqual(['uv', 'run', '--directory', '/abs/path', 'hindsight-embed']);
  });
 });
@@ -18,8 +18,8 @@ export interface EmbedCommandOptions {

 export function getEmbedCommand(opts: EmbedCommandOptions = {}): string[] {
  if (opts.embedPackagePath) {
-    return ["uv", "run", "--directory", opts.embedPackagePath, "hindsight-embed"];
+    return ['uv', 'run', '--directory', opts.embedPackagePath, 'hindsight-embed'];
  }
-  const version = opts.embedVersion && opts.embedVersion.length > 0 ? opts.embedVersion : "latest";
-  return ["uvx", `hindsight-embed@${version}`];
+  const version = opts.embedVersion && opts.embedVersion.length > 0 ? opts.embedVersion : 'latest';
+  return ['uvx', `hindsight-embed@${version}`];
 }
@@ -1,7 +1,7 @@
-export { HindsightServer } from "./server.js";
-export { getEmbedCommand } from "./command.js";
-export { silentLogger, consoleLogger } from "./logger.js";
+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";
+export type { Logger } from './logger.js';
+export type { EmbedCommandOptions } from './command.js';
+export type { HindsightServerOptions } from './types.js';
@@ -1,32 +1,32 @@
-import { describe, it, expect } from "vitest";
-import { HindsightServer } from "./server.js";
+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", () => {
+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");
+    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('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", () => {
+  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",
+        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",
+        HINDSIGHT_FUTURE_FLAG: 'enabled',
      },
    });
    expect(server).toBeInstanceOf(HindsightServer);
  });

-  it("exposes checkHealth that returns false when no daemon is running", async () => {
+  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();
@@ -1,12 +1,12 @@
-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";
+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_HOST = '127.0.0.1';
+const DEFAULT_PROFILE = 'default';
 const DEFAULT_READY_TIMEOUT_MS = 30_000;
 const DEFAULT_READY_POLL_INTERVAL_MS = 1_000;

@@ -61,7 +61,7 @@ export class HindsightServer {
    this.userEnv = opts.env ?? {};
    this.extraProfileCreateArgs = opts.extraProfileCreateArgs ?? [];
    this.extraDaemonStartArgs = opts.extraDaemonStartArgs ?? [];
-    this.platformCpuWorkaround = opts.platformCpuWorkaround ?? process.platform === "darwin";
+    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;
@@ -100,22 +100,22 @@ export class HindsightServer {
      embedVersion: this.embedVersion,
      embedPackagePath: this.embedPackagePath,
    });
-    const args = [...baseArgs, "daemon", "--profile", this.profile, "stop"];
+    const args = [...baseArgs, 'daemon', '--profile', this.profile, 'stop'];

-    const child = spawn(cmd, args, { stdio: "pipe" });
-    this.pipeOutput(child, "daemon.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", () => {
+      child.on('exit', () => {
        clearTimeout(timeout);
        this.logger.info(`[hindsight] daemon stopped`);
        resolve();
      });
-      child.on("error", (err) => {
+      child.on('error', (err) => {
        clearTimeout(timeout);
        this.logger.warn(`[hindsight] error stopping daemon: ${err.message}`);
        resolve();
@@ -147,9 +147,9 @@ export class HindsightServer {
  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";
+    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)) {
@@ -175,11 +175,11 @@ export class HindsightServer {
    });
    const createArgs = [
      ...baseArgs,
-      "profile",
-      "create",
+      'profile',
+      'create',
      this.profile,
-      "--merge",
-      "--port",
+      '--merge',
+      '--port',
      String(this.port),
    ];

@@ -189,12 +189,12 @@ export class HindsightServer {
    // 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('--env', `${key}=${value}`);
    }

    createArgs.push(...this.extraProfileCreateArgs);

-    await this.runCommand(cmd, createArgs, env, "profile.create");
+    await this.runCommand(cmd, createArgs, env, 'profile.create');
  }

  /** Collect only the env vars that should be written into the profile file. */
@@ -209,10 +209,10 @@ export class HindsightServer {
    }

    // 2. CPU workaround — only if auto-applied and not already overridden.
-    if (this.platformCpuWorkaround && process.platform === "darwin") {
+    if (this.platformCpuWorkaround && process.platform === 'darwin') {
      const cpuKeys = [
-        "HINDSIGHT_API_EMBEDDINGS_LOCAL_FORCE_CPU",
-        "HINDSIGHT_API_RERANKER_LOCAL_FORCE_CPU",
+        'HINDSIGHT_API_EMBEDDINGS_LOCAL_FORCE_CPU',
+        'HINDSIGHT_API_RERANKER_LOCAL_FORCE_CPU',
      ];
      for (const key of cpuKeys) {
        if (!(key in out) && env[key] !== undefined) {
@@ -231,14 +231,14 @@ export class HindsightServer {
    });
    const args = [
      ...baseArgs,
-      "daemon",
-      "--profile",
+      'daemon',
+      '--profile',
      this.profile,
-      "start",
+      'start',
      ...this.extraDaemonStartArgs,
    ];

-    await this.runCommand(cmd, args, env, "daemon.start");
+    await this.runCommand(cmd, args, env, 'daemon.start');
  }

  /**
@@ -249,34 +249,34 @@ export class HindsightServer {
    cmd: string,
    args: string[],
    env: NodeJS.ProcessEnv,
-    label: string
+    label: string,
  ): Promise<void> {
-    const child = spawn(cmd, args, { stdio: "pipe", env });
-    let output = "";
-    child.stdout?.on("data", (data: Buffer) => {
+    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")) {
+      for (const line of text.trimEnd().split('\n')) {
        if (line) this.logger.info(`[hindsight:${label}] ${line}`);
      }
    });
-    child.stderr?.on("data", (data: Buffer) => {
+    child.stderr?.on('data', (data: Buffer) => {
      const text = data.toString();
      output += text;
-      for (const line of text.trimEnd().split("\n")) {
+      for (const line of text.trimEnd().split('\n')) {
        if (line) this.logger.warn(`[hindsight:${label}] ${line}`);
      }
    });

    await new Promise<void>((resolve, reject) => {
-      child.on("exit", (code) => {
+      child.on('exit', (code) => {
        if (code === 0) {
          resolve();
        } else {
          reject(new Error(`${label} failed with code ${code}: ${output.trim()}`));
        }
      });
-      child.on("error", (err) => {
+      child.on('error', (err) => {
        reject(new Error(`${label} failed to spawn: ${err.message}`, { cause: err }));
      });
    });
@@ -284,13 +284,13 @@ export class HindsightServer {

  /** 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")) {
+    child.stdout?.on('data', (data: Buffer) => {
+      for (const line of data.toString().trimEnd().split('\n')) {
        if (line) this.logger.info(`[hindsight:${label}] ${line}`);
      }
    });
-    child.stderr?.on("data", (data: Buffer) => {
-      for (const line of data.toString().trimEnd().split("\n")) {
+    child.stderr?.on('data', (data: Buffer) => {
+      for (const line of data.toString().trimEnd().split('\n')) {
        if (line) this.logger.warn(`[hindsight:${label}] ${line}`);
      }
    });
@@ -316,7 +316,7 @@ export class HindsightServer {
      await new Promise((resolve) => setTimeout(resolve, this.readyPollIntervalMs));
    }
    throw new Error(
-      `Hindsight daemon did not become ready within ${this.readyTimeoutMs}ms at ${this.baseUrl}`
+      `Hindsight daemon did not become ready within ${this.readyTimeoutMs}ms at ${this.baseUrl}`,
    );
  }
 }
@@ -1,4 +1,4 @@
-import type { Logger } from "./logger.js";
+import type { Logger } from './logger.js';

 /**
 * Options for {@link HindsightServer}.
@@ -1,10 +1,10 @@
-import { defineConfig } from "tsup";
+import { defineConfig } from 'tsup';

 export default defineConfig({
-  entry: ["src/index.ts"],
-  format: ["esm"],
+  entry: ['src/index.ts'],
+  format: ['esm'],
  dts: true,
-  outDir: "dist",
+  outDir: 'dist',
  clean: true,
  sourcemap: true,
  bundle: true,
@@ -1,8 +1,8 @@
-import { defineConfig } from "vitest/config";
+import { defineConfig } from 'vitest/config';

 export default defineConfig({
  test: {
-    include: ["src/**/*.test.ts"],
-    environment: "node",
+    include: ['src/**/*.test.ts'],
+    environment: 'node',
  },
 });
@@ -4,12 +4,12 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "hindsight-all-slim"
-version = "0.6.2"
+version = "0.5.1"
 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==0.6.2",
+    "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(
@@ -276,10 +253,23 @@ 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 +394,11 @@ 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 +409,9 @@ 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 +425,8 @@ 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 = "0.6.2"
+version = "0.5.1"
 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]==0.6.2",
+    "hindsight-api-slim[all]>=0.4.17",
    "hindsight-client>=0.0.7",
    "hindsight-embed>=0.1.0",
 ]
@@ -21,7 +21,7 @@ hindsight-embed = { workspace = true }

 [project.optional-dependencies]
 local-llm = [
-    "hindsight-api-slim[local-llm]==0.6.2",
+    "hindsight-api-slim[local-llm]>=0.4.17",
 ]
 test = [
    "pytest>=7.0.0",
@@ -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__ = "0.6.2"
+__version__ = "0.5.1"
@@ -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)
@@ -1,117 +0,0 @@
-"""Repair mental_models.subtype on databases stuck at m3rg3h3ad5f6
-
-Three production deployments reported `column "subtype" of relation
-"mental_models" does not exist` on `create_mental_model` even after their
-container reported `Database migrations completed successfully` and
-`alembic_version` advanced to `m3rg3h3ad5f6` (see issue #1553, #1553#1
-confirmations from @4Lienau and @khanhduyvt0101).
-
-Both `h3c4d5e6f7g8_mental_models_v4` and `d5y6z7a8b9c0_backfill_mental_models_subtype`
-were meant to ensure `subtype` exists, but on databases that came through the
-`reflections -> mental_models` rename chain *and* whose alembic_version
-advanced past `d5y6z7a8b9c0` along an alternate path during the divergent-heads
-reorganization, neither column-add actually fired. The result is a head-tagged
-database with a v3-shaped `mental_models` table missing six columns:
-``subtype``, ``description``, ``entity_id``, ``observations``, ``links``,
-``last_updated``.
-
-This migration sits at the current head (`m3rg3h3ad5f6`) so every affected
-deployment will pick it up on next container start. It mirrors the column-add
-block from `d5y6z7a8b9c0_backfill_mental_models_subtype` using
-``ADD COLUMN IF NOT EXISTS`` so it is a no-op on databases where the columns
-are already present.
-
-Revision ID: 86f7a033d372
-Revises: m3rg3h3ad5f6
-Create Date: 2026-05-14
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-from hindsight_api.alembic._dialect import run_for_dialect
-
-revision: str = "86f7a033d372"
-down_revision: str | Sequence[str] | None = "m3rg3h3ad5f6"
-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)."""
-    schema = context.config.get_main_option("target_schema")
-    return f'"{schema}".' if schema else ""
-
-
-def _pg_upgrade() -> None:
-    """Idempotently ensure mental_models has the v4 column set.
-
-    Safe to re-apply on databases that already received the columns via
-    `h3c4d5e6f7g8_mental_models_v4` or `d5y6z7a8b9c0_backfill_mental_models_subtype` —
-    every column-add uses ``IF NOT EXISTS`` and the constraint is recreated
-    from scratch with the canonical v4 allowlist.
-    """
-    schema = _pg_schema_prefix()
-    bare_schema = schema.strip(".").strip('"') if schema else ""
-    schema_clause = f"AND table_schema = '{bare_schema}'" if bare_schema else ""
-
-    # Wrapped in a DO block so the existence check skips databases that
-    # predate the reflections -> mental_models rename chain (no table to
-    # repair). On those, every ALTER below would error.
-    op.execute(
-        f"""
-        DO $$
-        BEGIN
-            IF EXISTS (
-                SELECT 1 FROM information_schema.tables
-                WHERE table_name = 'mental_models'
-                  {schema_clause}
-            ) THEN
-                -- Add the six v4 columns idempotently.
-                ALTER TABLE {schema}mental_models
-                    ADD COLUMN IF NOT EXISTS subtype VARCHAR(32) NOT NULL DEFAULT 'structural';
-                ALTER TABLE {schema}mental_models
-                    ADD COLUMN IF NOT EXISTS description TEXT NOT NULL DEFAULT '';
-                ALTER TABLE {schema}mental_models
-                    ADD COLUMN IF NOT EXISTS entity_id UUID;
-                ALTER TABLE {schema}mental_models
-                    ADD COLUMN IF NOT EXISTS observations JSONB DEFAULT '{{"observations": []}}'::jsonb;
-                ALTER TABLE {schema}mental_models
-                    ADD COLUMN IF NOT EXISTS links VARCHAR[];
-                ALTER TABLE {schema}mental_models
-                    ADD COLUMN IF NOT EXISTS last_updated TIMESTAMP WITH TIME ZONE;
-
-                -- Recreate the CHECK constraint with the canonical v4 allowlist.
-                -- Existing rows with subtype = 'directive' (possible on databases
-                -- that ran the o0j1k2l3m4n5 directive-only path) are rewritten to
-                -- 'structural' first so the constraint add succeeds.
-                UPDATE {schema}mental_models SET subtype = 'structural' WHERE subtype = 'directive';
-
-                ALTER TABLE {schema}mental_models DROP CONSTRAINT IF EXISTS ck_mental_models_subtype;
-                ALTER TABLE {schema}mental_models
-                    ADD CONSTRAINT ck_mental_models_subtype
-                    CHECK (subtype IN ('structural', 'emergent', 'pinned', 'learned'));
-
-                CREATE INDEX IF NOT EXISTS idx_mental_models_subtype
-                    ON {schema}mental_models(bank_id, subtype);
-            END IF;
-        END$$;
-        """
-    )
-
-
-def _pg_downgrade() -> None:
-    """No-op: dropping these columns would corrupt v4 application code."""
-    pass
-
-
-def upgrade() -> None:
-    # PG-only: Oracle's baseline (o1a2b3c4d5e6) creates mental_models with its
-    # own subtype shape (chk_mm_subtype IN ('directive', 'pinned')) and a
-    # different table topology, so this PG-shaped repair does not apply.
-    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)
@@ -1,7 +1,7 @@
 """Merge 3 migration heads and add unit_entities composite index

 Revision ID: h3i4j5k6l7m8
-Revises: a4b5c6d7e8f9, g2h3i4j5k6l7
+Revises: a4b5c6d7e8f9, c2d3e4f5g6h7, g2h3i4j5k6l7
 Create Date: 2026-04-07

 Merges three unmerged migration heads into one, and adds a composite index
@@ -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 = "h3i4j5k6l7m8"
-down_revision: str | Sequence[str] | None = ("a4b5c6d7e8f9", "g2h3i4j5k6l7")
+down_revision: str | Sequence[str] | None = ("a4b5c6d7e8f9", "c2d3e4f5g6h7", "g2h3i4j5k6l7")
 branch_labels: str | Sequence[str] | None = None
 depends_on: 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()
    # Composite index enables index-only scans for entity_id -> unit_id lookups
    op.execute(
@@ -37,16 +35,8 @@ def _pg_upgrade() -> None:
    op.execute(f"DROP INDEX IF EXISTS {schema}idx_unit_entities_entity")


-def _pg_downgrade() -> None:
+def 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)
@@ -12,8 +12,6 @@ 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 = "rename_personality"
 down_revision: str | Sequence[str] | None = "d9f6a3b4c5e2"
@@ -27,7 +25,7 @@ def _get_target_schema() -> str:
    return schema if schema else "public"


-def _pg_upgrade() -> None:
+def upgrade() -> None:
    """Rename personality column to disposition in banks table (if it exists)."""
    conn = op.get_bind()
    target_schema = _get_target_schema()
@@ -71,7 +69,7 @@ def _pg_upgrade() -> None:
    # else: disposition already exists, nothing to do


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Revert disposition column back to personality."""
    conn = op.get_bind()
    target_schema = _get_target_schema()
@@ -85,11 +83,3 @@ def _pg_downgrade() -> None:
    )
    if result.fetchone():
        op.alter_column("banks", "disposition", new_column_name="personality")
-
-
-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 = "s4n5o6p7q8r9"
 down_revision: str | Sequence[str] | None = "r3m4n5o6p7q8"
 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()

    # Add consolidated_at column to memory_units
@@ -48,16 +46,8 @@ 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_unconsolidated")
    op.execute(f"ALTER TABLE {schema}memory_units DROP COLUMN IF EXISTS consolidated_at")
-
-
-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: str = "t5o6p7q8r9s0"
 down_revision: str | Sequence[str] | None = "s4n5o6p7q8r9"
 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:
    """Rename mental_model -> observation and reflections -> mental_models."""
    schema = _get_schema_prefix()

@@ -88,7 +86,7 @@ def _pg_upgrade() -> None:
    """)


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Reverse: observation -> mental_model and mental_models -> reflections."""
    schema = _get_schema_prefix()

@@ -134,11 +132,3 @@ def _pg_downgrade() -> None:
        ON {schema}memory_units(bank_id, fact_type)
        WHERE fact_type = 'mental_model'
    """)
-
-
-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 = "u6p7q8r9s0t1"
 down_revision: str | Sequence[str] | None = "t5o6p7q8r9s0"
 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:
    """Change mental_models.id from UUID 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 USING id::TEXT")


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

    # Note: This will fail if any id values are not valid UUIDs
    op.execute(f"ALTER TABLE {schema}mental_models ALTER COLUMN id TYPE UUID USING id::UUID")
-
-
-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 = "v7q8r9s0t1u2"
 down_revision: str | Sequence[str] | None = "u6p7q8r9s0t1"
 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:
    """Add max_tokens and trigger columns to mental_models."""
    schema = _get_schema_prefix()

@@ -44,17 +42,9 @@ def _pg_upgrade() -> None:
    """)


-def _pg_downgrade() -> None:
+def downgrade() -> None:
    """Remove max_tokens and trigger columns from mental_models."""
    schema = _get_schema_prefix()

    op.execute(f"ALTER TABLE {schema}mental_models DROP COLUMN IF EXISTS max_tokens")
    op.execute(f"ALTER TABLE {schema}mental_models DROP COLUMN IF EXISTS trigger")
-
-
-def upgrade() -> None:
-    run_for_dialect(pg=_pg_upgrade)
-
-
-def downgrade() -> None:
-    run_for_dialect(pg=_pg_downgrade)
--- a/Show More
+++ b/Show More