fix(memory): biographer tool type hints for Ollama (v1.3.2)

- Change `str | None` to `str` with empty default for memory_type
- Remove `keywords` parameter from store_insight (auto-generated anyway)
- Ollama's OpenAI API doesn't handle union types with None properly

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.env.example

@@ -21,13 +21,18 @@ SEARXNG_TIMEOUT=30
 # Redis Configuration
 REDIS_HOST=redis-shared
 REDIS_PORT=6379
-REDIS_DB=1
+REDIS_MEMORY_DB=1
+REDIS_BENCHMARK_DB=6
 REDIS_TIMEOUT=5
 
+# Qdrant Configuraton
+QDRANT_HOST=qdrant
+QDRANT_PORT=6333
+
 # Logging
 LOG_LEVEL=INFO
 ENABLE_BENCHMARKS=true
 # Note: Log format is auto-selected based on ENVIRONMENT (console for dev, json for production)
 
 # CORS (comma-separated list)
-CORS_ORIGINS=*
+CORS_ORIGINS=["*"]

.gitea/workflows/build.yml

@@ -13,16 +13,23 @@ jobs:
       - name: Login to Gitea Registry
         uses: docker/login-action@v3
         with:
-          registry: git.schweitz.net
+          registry: git.schweitz.internal
           username: ${{ secrets.REGISTRY_USER }}
           password: ${{ secrets.REGISTRY_PASSWORD }}
 
       - name: Build and push
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v6
         with:
           context: .
           push: true
           provenance: false
+          sbom: false
           tags: |
-            git.schweitz.net/jpmschweitzer/tatlock:latest
+            git.schweitz.internal/jpmschweitzer/tatlock:latest
-            git.schweitz.net/jpmschweitzer/tatlock:${{ github.ref_name }}
+            git.schweitz.internal/jpmschweitzer/tatlock:${{ github.ref_name }}
+
+      - name: Trigger Watchtower update
+        if: success()
+        run: |
+          curl -sf -H "Authorization: Bearer ${{ secrets.WATCHTOWER_TOKEN }}" \
+            http://watchtower:8080/v1/update

CHANGELOG.md

@@ -7,6 +7,48 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.3.2] - 2025-12-14
+
+### Fixed
+
+- **Memory**: Fix biographer tool type hints for Ollama compatibility (remove `| None` union types)
+
+## [1.3.1] - 2025-12-14
+
+### Fixed
+
+- **Memory**: Add biographer to delegation wrappers (was returning raw tools causing Ollama error)
+- **Config**: Add Qdrant host/port to .env.example
+
+## [1.3.0] - 2025-12-14
+
+### Fixed
+
+- **Memory**: Update Qdrant client to use `query_points` API (qdrant-client >= 1.10)
+
+### Changed
+
+- **Config**: Rename `REDIS_DB` to `REDIS_BENCHMARK_DB` for clarity
+- **Config**: Update Redis defaults to match stack allocation (benchmark=6, memory=1)
+
+## [1.2.5] - 2025-12-14
+
+### Fixed
+
+- **Dependencies**: Add missing `pydantic-settings` (not included in pydantic-ai-slim)
+
+## [1.2.4] - 2025-12-14
+
+### Added
+
+- **CI**: Trigger Watchtower update after successful image push
+
+## [1.2.3] - 2025-12-14
+
+### Fixed
+
+- **CI**: Upgrade to build-push-action@v6, disable provenance and sbom for Gitea registry
+
 ## [1.2.2] - 2025-12-13
 
 ### Fixed

DEPENDENCY_SLIM.md

@@ -1,72 +0,0 @@
-# Dependency Slimming: pydantic-ai → pydantic-ai-slim
-
-**Date**: 2025-12-13
-**Version**: Post v1.2.0
-
-## Change
-
-Switched from `pydantic-ai` to `pydantic-ai-slim[openai]` to reduce container image size.
-
-### Before
-```
-pydantic-ai>=1.27,<1.28
-```
-
-This installs SDKs for ALL LLM providers:
-- anthropic
-- boto3 + botocore (AWS Bedrock)
-- cohere
-- google-genai + google-auth
-- groq
-- huggingface-hub
-
-Total packages: ~158
-
-### After
-```
-pydantic-ai-slim[openai]>=1.27,<1.28
-```
-
-Only installs the OpenAI-compatible SDK. Ollama works through this interface.
-
-Expected packages: ~80-90 (significant reduction)
-
-## Why This Works
-
-Tatlock uses Ollama exclusively, which implements the OpenAI-compatible API. The code uses:
-```python
-from pydantic_ai.models.openai import OpenAIChatModel
-from pydantic_ai.providers.ollama import OllamaProvider
-
-model = OpenAIChatModel(
-    model_name=config.OLLAMA_DEFAULT_MODEL,
-    provider=OllamaProvider(base_url=f"{config.OLLAMA_HOST}/v1")
-)
-```
-
-This pattern only requires the `openai` extra, not the full pydantic-ai package.
-
-## Rollback Instructions
-
-If this change breaks things:
-
-1. Revert requirements.txt:
-```diff
-- pydantic-ai-slim[openai]>=1.27,<1.28
-+ pydantic-ai>=1.27,<1.28
-```
-
-2. Reinstall dependencies:
-```bash
-pip install -r requirements.txt
-```
-
-3. Delete this file once confirmed stable.
-
-## Testing Checklist
-
-- [ ] Unit tests pass
-- [ ] Integration tests pass (with Ollama running)
-- [ ] Wakeup script e2e test passes
-- [ ] Container builds successfully
-- [ ] Container runs correctly

README.md

@@ -432,7 +432,7 @@ For LLM agent development guidelines and architectural decisions, see [AGENTS.md
 
 ## Version
 
-Current version: **1.2.2** - CI fix
+Current version: **1.3.2** - Biographer tool type hints fix
 
 ---
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tatlock"
-version = "1.2.2"
+version = "1.3.2"
 description = "OpenAI-compatible API with Ollama backend"
 requires-python = ">=3.12"
 dependencies = []

requirements.txt

@@ -14,6 +14,11 @@ uvicorn[standard]>=0.38,<0.39
 # Latest: 2.12.4 (Nov 5, 2025) - No known CVEs
 pydantic>=2.11,<2.13
 
+# Pydantic settings for configuration management
+# Required explicitly since pydantic-ai-slim doesn't include it
+# Latest: 2.12.0 (Dec 2025) - No known CVEs
+pydantic-settings>=2.12,<2.13
+
 # AI/LLM integration
 # PydanticAI: Agent framework for using Pydantic with LLMs
 # Using slim version with only openai extra (Ollama uses OpenAI-compatible API)

src/agents/biographer/tools.py

@@ -25,7 +25,7 @@ logger = get_logger(__name__)
 
 async def recall_semantic(
     query: str,
-    memory_type: str | None = None,
+    memory_type: str = "",
     limit: int = 5,
 ) -> str:
     """
@@ -64,7 +64,7 @@ async def recall_semantic(
             user=user,
             query_vector=query_vector,
             limit=limit,
-            memory_type=memory_type,
+            memory_type=memory_type if memory_type else None,
         )
 
         if not results:
@@ -111,7 +111,6 @@ async def recall_semantic(
 async def store_insight(
     key: str,
     value: str,
-    keywords: list[str] | None = None,
     importance: float = 0.5,
 ) -> str:
     """
@@ -128,7 +127,6 @@ async def store_insight(
     Args:
         key: Short identifier for the memory (e.g., "car", "employer", "pet")
         value: The actual information to remember
-        keywords: Optional keywords for better search (auto-extracted if not provided)
         importance: How important is this? 0.0 (trivial) to 1.0 (critical)
 
     Returns:
@@ -137,15 +135,12 @@ async def store_insight(
     Examples:
         store_insight("car", "User drives a Tesla Model 3")
         store_insight("employer", "Works at Acme Corp as software engineer", importance=0.8)
-        store_insight("coffee", "Prefers oat milk lattes", keywords=["coffee", "drink", "preference"])
     """
     try:
-        # Auto-generate keywords if not provided
+        # Auto-generate keywords from key and value
-        if not keywords:
+        keywords = [key]
-            keywords = [key]
+        words = value.lower().split()
-            # Extract simple keywords from value
+        keywords.extend([w for w in words if len(w) > 4][:5])
-            words = value.lower().split()
-            keywords.extend([w for w in words if len(w) > 4][:5])
 
         success = await memory_service.store_fact(
             key=key,

src/core/config.py

@@ -101,9 +101,9 @@ class Config(BaseSettings):
         default=6379,
         description="Redis server port"
     )
-    REDIS_DB: int = Field(
+    REDIS_BENCHMARK_DB: int = Field(
-        default=1,
+        default=6,
-        description="Redis database number"
+        description="Redis database number for benchmarks"
     )
     REDIS_TIMEOUT: int = Field(
         default=5,
@@ -146,7 +146,7 @@ class Config(BaseSettings):
 
     # Redis Memory Database (separate from benchmarks)
     REDIS_MEMORY_DB: int = Field(
-        default=2,
+        default=1,
         description="Redis database number for memory cache"
     )
     REDIS_MEMORY_TTL_HOURS: int = Field(
@@ -170,7 +170,7 @@ class Config(BaseSettings):
     @property
     def redis_url(self) -> str:
         """Construct Redis connection URL for benchmarks."""
-        return f"redis://{self.REDIS_HOST}:{self.REDIS_PORT}/{self.REDIS_DB}"
+        return f"redis://{self.REDIS_HOST}:{self.REDIS_PORT}/{self.REDIS_BENCHMARK_DB}"
 
     @property
     def redis_memory_url(self) -> str:

src/core/household_registry.py

@@ -223,12 +223,12 @@ class HouseholdRegistry:
             >>> # Returns: [delegate_to_librarian, calculate, datetime, ...]
             >>> # Instead of: [hybrid_search, search_wiki, create_wiki_page, ... (16 tools)]
         """
-        from src.agents.delegation import delegate_to_librarian
+        from src.agents.delegation import delegate_to_librarian, delegate_to_biographer
 
         # Map of expert names to their delegation wrappers
         delegation_wrappers = {
             "librarian": delegate_to_librarian,
-            # Future: "memory": delegate_to_memory,
+            "biographer": delegate_to_biographer,
             # Future: "home_automation": delegate_to_home_automation,
         }
 

src/core/qdrant.py

@@ -232,14 +232,14 @@ class MemoryQdrantClient:
                     ]
                 )
 
-            # Search
+            # Search using new Query API (qdrant-client >= 1.10)
-            results = self._client.search(
+            results = self._client.query_points(
                 collection_name=collection_name,
-                query_vector=query_vector,
+                query=query_vector,
                 limit=limit,
                 query_filter=query_filter,
                 score_threshold=score_threshold,
-            )
+            ).points
 
             # Format results
             memories = []