Merge origin/main into feature/database-abstraction

Resolves conflicts in:
- memory_engine.py: integrated statement_timeout init callback with
  backend.initialize() abstraction
- retrieval.py: added extra_where param to dialect build_semantic_arm()
  and build_bm25_arm() methods to support created_after/created_before
  time range filtering from main
- openapi.json: took main's version (0.5.4)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: DK09876

.github/workflows/deploy-docs.yml

@@ -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@v4
+      - uses: actions/upload-pages-artifact@v5
         with:
           path: hindsight-docs/build
   deploy:

.github/workflows/perf-test.yml

@@ -0,0 +1,93 @@
+name: Performance Tests
+
+on:
+  schedule:
+    # Run daily at 06:00 UTC
+    - cron: "0 6 * * *"
+  workflow_dispatch:
+    inputs:
+      scale:
+        description: "Test scale"
+        type: choice
+        options:
+          - tiny
+          - small
+          - medium
+          - large
+        default: large
+      suite:
+        description: "Suite to run (blank = all)"
+        type: choice
+        options:
+          - ""
+          - retain
+          - recall
+        default: ""
+      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: |
+          ${{ runner.os }}-huggingface-
+
+    - name: Pre-download models
+      working-directory: ./hindsight-api-slim
+      run: |
+        uv run --frozen --all-extras --index-strategy unsafe-best-match python -c "
+        from sentence_transformers import SentenceTransformer
+        print('Downloading embedding model...')
+        SentenceTransformer('BAAI/bge-small-en-v1.5')
+        print('Model downloaded successfully')
+        "
+
+    - name: Install hindsight-dev dependencies
+      run: |
+        cd hindsight-dev && uv sync --frozen --all-extras --index-strategy unsafe-best-match
+
+    - name: Run perf tests
+      run: |
+        SUITE_ARG=""
+        if [ -n "${{ inputs.suite }}" ]; then
+          SUITE_ARG="--suite ${{ inputs.suite }}"
+        fi
+        ./scripts/benchmarks/run-perf-test.sh \
+          --scale ${{ inputs.scale || 'large' }} \
+          $SUITE_ARG \
+          --output perf-results.json
+
+    - name: Upload perf results
+      if: always()
+      uses: actions/upload-artifact@v4
+      with:
+        name: perf-results-${{ github.sha }}
+        path: hindsight-dev/perf-results.json
+        retention-days: 90

CLAUDE.md

@@ -68,8 +68,9 @@ 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

helm/hindsight/Chart.yaml

@@ -2,8 +2,8 @@ apiVersion: v2
 name: hindsight
 description: Hindsight helm chart
 type: application
-version: 0.5.3
-appVersion: "0.5.3"
+version: 0.5.4
+appVersion: "0.5.4"
 keywords:
   - ai
   - memory

hindsight-all-npm/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@vectorize-io/hindsight-all",
-  "version": "0.5.3",
+  "version": "0.5.4",
   "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",

hindsight-all-slim/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hindsight-all-slim"
-version = "0.5.3"
+version = "0.5.4"
 description = "Hindsight: Agent Memory That Works Like Human Memory - Slim All-in-One Bundle"
 readme = "README.md"
 requires-python = ">=3.11"

hindsight-all/hindsight/embedded.py

@@ -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: 300)
+        idle_timeout: Seconds before daemon auto-exits when idle (default: 0, disabled)
         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 @@ def __init__(
         llm_model: str = "openai/gpt-oss-120b",
         llm_base_url: Optional[str] = None,
         database_url: Optional[str] = None,
-        idle_timeout: int = 300,
+        idle_timeout: int = 0,
         log_level: str = "info",
         ui: bool = False,
         ui_port: Optional[int] = None,
@@ -102,7 +102,7 @@ def __init__(
             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
+            idle_timeout: Seconds before daemon auto-exits when idle (0 = disabled)
             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)
@@ -142,14 +142,37 @@ def __init__(
         self._memories_api: Optional[MemoriesAPI] = None
 
     def _ensure_started(self):
-        """Ensure daemon is running (thread-safe)."""
+        """Ensure daemon is running (thread-safe), restarting if crashed."""
         if self._started and self._client is not None:
-            return
+            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
 
         with self._lock:
             # Double-check after acquiring lock
             if self._started and self._client is not None:
-                return
+                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
 
             if self._closed:
                 raise RuntimeError(
@@ -253,23 +276,10 @@ def __getattr__(self, name: str):
         This allows HindsightEmbedded to expose all HindsightClient methods
         without manually wrapping each one.
         """
-        # Ensure server is started before proxying
+        # Ensure server is started (and restart if crashed) before proxying
         self._ensure_started()
 
-        # Get the attribute from the underlying client
-        attr = getattr(self._client, name)
-
-        # If it's a callable, wrap it to ensure server is started
-        # (shouldn't be needed since _ensure_started already called, but defensive)
-        if callable(attr):
-
-            def wrapper(*args, **kwargs):
-                self._ensure_started()
-                return attr(*args, **kwargs)
-
-            return wrapper
-
-        return attr
+        return getattr(self._client, name)
 
     def __enter__(self):
         """Context manager entry - ensures server is started."""
@@ -394,11 +404,8 @@ def client(self) -> Hindsight:
         """
         Get the underlying Hindsight client for direct access.
 
-        WARNING: Using this property directly means daemon restarts won't be
-        handled automatically. Prefer using the API namespaces (banks, mental_models,
-        directives, memories) or direct method calls on HindsightEmbedded instead.
-
-        Ensures daemon is started before returning the client.
+        Ensures daemon is started (and restarts it if it has crashed) before
+        returning the client.
 
         Returns:
             Hindsight: The underlying client instance
@@ -409,9 +416,8 @@ def client(self) -> Hindsight:
 
             embedded = HindsightEmbedded(profile="myapp", ...)
 
-            # Direct access (not recommended - daemon crashes won't be handled)
             client = embedded.client
-            banks = client.list_banks()  # If daemon crashes, this will fail
+            banks = client.list_banks()
             ```
         """
         self._ensure_started()
@@ -425,8 +431,13 @@ def url(self) -> str:
 
     @property
     def is_running(self) -> bool:
-        """Check if the client is initialized."""
-        return self._started and not self._closed and self._client is not None
+        """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)
+        )
 
     @property
     def ui_url(self) -> str:

hindsight-all/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "hindsight-all"
-version = "0.5.3"
+version = "0.5.4"
 description = "Hindsight: Agent Memory That Works Like Human Memory - All-in-One Bundle"
 readme = "README.md"
 requires-python = ">=3.11"

hindsight-all/tests/test_embedded.py

@@ -401,3 +401,42 @@ 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()

hindsight-api-slim/hindsight_api/__init__.py

@@ -46,4 +46,4 @@
     "RemoteTEICrossEncoder",
     "LLMConfig",
 ]
-__version__ = "0.5.3"
+__version__ = "0.5.4"