fix: make retain max completion tokens configurable

CLAUDE.md

@@ -84,29 +84,15 @@ PostgreSQL with pgvector. Schema managed via Alembic migrations in `hindsight-ap
 
 Key tables: `banks`, `memory_units`, `documents`, `entities`, `entity_links`
 
-### Database Backups (IMPORTANT)
-**Before any operation that may affect the database, run a backup:**
-```bash
-docker exec hindsight /backups/backup.sh
-```
-
-Operations requiring backup:
-- Running database migrations
-- Modifying Alembic migration files
-- Rebuilding Docker images
-- Resetting or recreating containers
-- Any schema changes
-- Bulk data operations
-
-Backups are stored in `~/hindsight-backups/` on the host.
-
-To restore:
-```bash
-docker exec -it hindsight /backups/restore.sh <backup-file.sql.gz>
-```
-
 ## Key Conventions
 
+### Code Quality
+**Always run the lint script after making Python or TypeScript/Node changes:**
+```bash
+./scripts/hooks/lint.sh
+```
+This runs the same checks as the pre-commit hook (Ruff for Python, ESLint/Prettier for TypeScript).
+
 ### Memory Banks
 - Each bank is isolated (no cross-bank data access)
 - Banks have dispositions (skepticism, literalism, empathy traits 1-5) affecting reflect
@@ -127,6 +113,29 @@ docker exec -it hindsight /backups/restore.sh <backup-file.sql.gz>
 - Next.js App Router for control plane
 - Tailwind CSS with shadcn/ui components
 
+### Adding New API Configuration Flags
+
+When adding a new environment variable configuration:
+
+1. **config.py** (`hindsight-api/hindsight_api/config.py`):
+   - Add `ENV_*` constant for the environment variable name
+   - Add `DEFAULT_*` constant for the default value
+   - Add field to `HindsightConfig` dataclass
+   - Add initialization in `from_env()` method
+
+2. **main.py** (`hindsight-api/hindsight_api/main.py`):
+   - Add field to the manual `HindsightConfig()` constructor call (search for "CLI override")
+
+3. **Use the config** in code:
+   ```python
+   from ...config import get_config
+   config = get_config()
+   value = config.your_new_field
+   ```
+
+4. **Documentation** (`hindsight-docs/docs/developer/configuration.md`):
+   - Add to appropriate section table with Variable, Description, Default
+
 ## Environment Setup
 
 ```bash

hindsight-api/hindsight_api/config.py

@@ -42,6 +42,9 @@ ENV_MCP_INSTRUCTIONS = "HINDSIGHT_API_MCP_INSTRUCTIONS"
 ENV_OBSERVATION_MIN_FACTS = "HINDSIGHT_API_OBSERVATION_MIN_FACTS"
 ENV_OBSERVATION_TOP_ENTITIES = "HINDSIGHT_API_OBSERVATION_TOP_ENTITIES"
 
+# Retain settings
+ENV_RETAIN_MAX_COMPLETION_TOKENS = "HINDSIGHT_API_RETAIN_MAX_COMPLETION_TOKENS"
+
 # Optimization flags
 ENV_SKIP_LLM_VERIFICATION = "HINDSIGHT_API_SKIP_LLM_VERIFICATION"
 ENV_LAZY_RERANKER = "HINDSIGHT_API_LAZY_RERANKER"
@@ -72,6 +75,9 @@ DEFAULT_MCP_LOCAL_BANK_ID = "mcp"
 DEFAULT_OBSERVATION_MIN_FACTS = 5  # Min facts required to generate entity observations
 DEFAULT_OBSERVATION_TOP_ENTITIES = 5  # Max entities to process per retain batch
 
+# Retain settings
+DEFAULT_RETAIN_MAX_COMPLETION_TOKENS = 64000  # Max tokens for fact extraction LLM call
+
 # Default MCP tool descriptions (can be customized via env vars)
 DEFAULT_MCP_RETAIN_DESCRIPTION = """Store important information to long-term memory.
 
@@ -134,6 +140,9 @@ class HindsightConfig:
     observation_min_facts: int
     observation_top_entities: int
 
+    # Retain settings
+    retain_max_completion_tokens: int
+
     # Optimization flags
     skip_llm_verification: bool
     lazy_reranker: bool
@@ -174,6 +183,10 @@ class HindsightConfig:
             observation_top_entities=int(
                 os.getenv(ENV_OBSERVATION_TOP_ENTITIES, str(DEFAULT_OBSERVATION_TOP_ENTITIES))
             ),
+            # Retain settings
+            retain_max_completion_tokens=int(
+                os.getenv(ENV_RETAIN_MAX_COMPLETION_TOKENS, str(DEFAULT_RETAIN_MAX_COMPLETION_TOKENS))
+            ),
         )
 
     def get_llm_base_url(self) -> str:
@@ -220,6 +233,19 @@ class HindsightConfig:
         logger.info(f"Graph retriever: {self.graph_retriever}")
 
 
+# Cached config instance
+_config_cache: HindsightConfig | None = None
+
+
 def get_config() -> HindsightConfig:
-    """Get the current configuration from environment variables."""
-    return HindsightConfig.from_env()
+    """Get the cached configuration, loading from environment on first call."""
+    global _config_cache
+    if _config_cache is None:
+        _config_cache = HindsightConfig.from_env()
+    return _config_cache
+
+
+def clear_config_cache() -> None:
+    """Clear the config cache. Useful for testing or reloading config."""
+    global _config_cache
+    _config_cache = None

hindsight-api/hindsight_api/engine/retain/fact_extraction.py

@@ -14,6 +14,7 @@ from typing import Literal
 
 from pydantic import BaseModel, ConfigDict, Field, field_validator
 
+from ...config import get_config
 from ..llm_wrapper import LLMConfig, OutputTooLongError
 
 
@@ -583,6 +584,7 @@ WHAT TO EXTRACT vs SKIP
     # Retry logic for JSON validation errors
     max_retries = 2
     last_error = None
+    config = get_config()
 
     # Sanitize input text to prevent Unicode encoding errors (e.g., unpaired surrogates)
     sanitized_chunk = _sanitize_text(chunk)
@@ -608,7 +610,7 @@ Text:
                 response_format=FactExtractionResponse,
                 scope="memory_extract_facts",
                 temperature=0.1,
-                max_completion_tokens=65000,
+                max_completion_tokens=config.retain_max_completion_tokens,
                 skip_validation=True,  # Get raw JSON, we'll validate leniently
             )
 

hindsight-api/hindsight_api/main.py

@@ -184,6 +184,7 @@ def main():
             graph_retriever=config.graph_retriever,
             observation_min_facts=config.observation_min_facts,
             observation_top_entities=config.observation_top_entities,
+            retain_max_completion_tokens=config.retain_max_completion_tokens,
             skip_llm_verification=config.skip_llm_verification,
             lazy_reranker=config.lazy_reranker,
         )

hindsight-docs/docs/developer/configuration.md

@@ -183,6 +183,14 @@ Controls when the system generates entity observations (summaries about entities
 | `HINDSIGHT_API_OBSERVATION_MIN_FACTS` | Minimum facts about an entity before generating observations | `5` |
 | `HINDSIGHT_API_OBSERVATION_TOP_ENTITIES` | Max entities to process per retain batch | `5` |
 
+### Retain
+
+Controls the retain (memory ingestion) pipeline.
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `HINDSIGHT_API_RETAIN_MAX_COMPLETION_TOKENS` | Max completion tokens for fact extraction LLM calls | `64000` |
+
 ### Local MCP Server
 
 Configuration for the local MCP server (`hindsight-local-mcp` command).