feat(cli): accept more file types on retain-files

.gitignore

@@ -29,7 +29,7 @@ nltk_data/
 
 # Monitoring stack (Prometheus/Grafana binaries and data)
 .monitoring/
-.pgbouncer/
+.pgbouncer
 
 # Large benchmark datasets (will be downloaded automatically)
 **/longmemeval_s_cleaned.json

CLAUDE.md

@@ -199,38 +199,6 @@ When adding or modifying parameters in the dataplane API (hindsight-api), you mu
 - Pydantic models for request/response
 - Ruff for linting (line-length 120)
 - No Python files at project root - maintain clean directory structure
-- **Never use multi-item tuple return values** - prefer dataclass or Pydantic model for structured returns
-
-### Type Safety with Pydantic Models
-**NEVER use raw `dict` types for structured data.** Always use Pydantic models:
-- Use Pydantic `BaseModel` for all data structures passed between functions
-- Add `@field_validator` for type coercion (e.g., ensuring datetimes are timezone-aware)
-- Avoid `dict.get()` patterns - use typed model attributes instead
-- Parse external data (JSON, API responses) into Pydantic models at the boundary
-- This catches type errors at parse time, not deep in business logic
-
-```python
-# BAD - error-prone dict access
-def process(data: dict) -> str:
-    return data.get("name", "")  # No validation, silent failures
-
-# GOOD - typed and validated
-class UserData(BaseModel):
-    name: str
-    created_at: datetime
-
-    @field_validator("created_at", mode="before")
-    @classmethod
-    def ensure_tz_aware(cls, v):
-        if isinstance(v, str):
-            v = datetime.fromisoformat(v.replace("Z", "+00:00"))
-        if v.tzinfo is None:
-            return v.replace(tzinfo=timezone.utc)
-        return v
-
-def process(data: UserData) -> str:
-    return data.name  # Type-safe, validated at construction
-```
 
 ### TypeScript Style
 - Next.js App Router for control plane

hindsight-api/hindsight_api/alembic/versions/h3c4d5e6f7g8_mental_models_v4.py

@@ -1,112 +0,0 @@
-"""mental_models_v4
-
-Revision ID: h3c4d5e6f7g8
-Revises: g2a3b4c5d6e7
-Create Date: 2026-01-08 00:00:00.000000
-
-This migration implements the v4 mental models system:
-1. Deletes existing observation memory_units (observations now in mental models)
-2. Adds mission column to banks (replacing background)
-3. Creates mental_models table with final schema
-
-Mental models can reference entities when an entity is "promoted" to a mental model.
-Summary content is stored as JSONB observations with per-observation fact attribution.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-# revision identifiers, used by Alembic.
-revision: str = "h3c4d5e6f7g8"
-down_revision: str | Sequence[str] | None = "g2a3b4c5d6e7"
-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 upgrade() -> None:
-    """Apply mental models v4 changes."""
-    schema = _get_schema_prefix()
-
-    # Step 1: Delete observation memory_units (cascades to unit_entities links)
-    # Observations are now handled through mental models, not memory_units
-    op.execute(f"DELETE FROM {schema}memory_units WHERE fact_type = 'observation'")
-
-    # Step 2: Drop observation-specific index (if it exists)
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_memory_units_observation_date")
-
-    # Step 3: Add mission column to banks (replacing background)
-    op.execute(f"ALTER TABLE {schema}banks ADD COLUMN IF NOT EXISTS mission TEXT")
-
-    # Migrate: copy background to mission if background column exists
-    # Use DO block to check column existence first (idempotent for re-runs)
-    schema_name = context.config.get_main_option("target_schema") or "public"
-    op.execute(f"""
-        DO $$
-        BEGIN
-            IF EXISTS (
-                SELECT 1 FROM information_schema.columns
-                WHERE table_schema = '{schema_name}' AND table_name = 'banks' AND column_name = 'background'
-            ) THEN
-                UPDATE {schema}banks
-                SET mission = background
-                WHERE mission IS NULL;
-            END IF;
-        END $$;
-    """)
-
-    # Remove background column (replaced by mission)
-    op.execute(f"ALTER TABLE {schema}banks DROP COLUMN IF EXISTS background")
-
-    # Step 4: Create mental_models table with final v4 schema (if not exists)
-    op.execute(f"""
-        CREATE TABLE IF NOT EXISTS {schema}mental_models (
-            id VARCHAR(64) NOT NULL,
-            bank_id VARCHAR(64) NOT NULL,
-            subtype VARCHAR(32) NOT NULL,
-            name VARCHAR(256) NOT NULL,
-            description TEXT NOT NULL,
-            entity_id UUID,
-            observations JSONB DEFAULT '{{"observations": []}}'::jsonb,
-            links VARCHAR[],
-            tags VARCHAR[] DEFAULT '{{}}',
-            last_updated TIMESTAMP WITH TIME ZONE,
-            created_at TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT now(),
-            PRIMARY KEY (id, bank_id),
-            FOREIGN KEY (bank_id) REFERENCES {schema}banks(bank_id) ON DELETE CASCADE,
-            FOREIGN KEY (entity_id) REFERENCES {schema}entities(id) ON DELETE SET NULL,
-            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)")
-    op.execute(f"CREATE INDEX IF NOT EXISTS idx_mental_models_entity_id ON {schema}mental_models(entity_id)")
-    # GIN index for efficient tags array filtering
-    op.execute(f"CREATE INDEX IF NOT EXISTS idx_mental_models_tags ON {schema}mental_models USING GIN(tags)")
-
-
-def downgrade() -> None:
-    """Revert mental models v4 changes."""
-    schema = _get_schema_prefix()
-
-    # Drop mental_models table (cascades to indexes)
-    op.execute(f"DROP TABLE IF EXISTS {schema}mental_models CASCADE")
-
-    # Add back background column to banks
-    op.execute(f"ALTER TABLE {schema}banks ADD COLUMN IF NOT EXISTS background TEXT")
-
-    # Migrate mission back to background
-    op.execute(f"UPDATE {schema}banks SET background = mission WHERE background IS NULL")
-
-    # Remove mission column
-    op.execute(f"ALTER TABLE {schema}banks DROP COLUMN IF EXISTS mission")
-
-    # Note: Cannot restore deleted observations - they are lost on downgrade

hindsight-api/hindsight_api/alembic/versions/i4d5e6f7g8h9_delete_opinions.py

@@ -1,41 +0,0 @@
-"""delete_opinions
-
-Revision ID: i4d5e6f7g8h9
-Revises: h3c4d5e6f7g8
-Create Date: 2026-01-15 00:00:00.000000
-
-This migration removes opinion facts from memory_units.
-Opinions are no longer a separate fact type - they are now represented
-through mental model observations with confidence scores.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-# revision identifiers, used by Alembic.
-revision: str = "i4d5e6f7g8h9"
-down_revision: str | Sequence[str] | None = "h3c4d5e6f7g8"
-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 upgrade() -> None:
-    """Delete opinion memory_units."""
-    schema = _get_schema_prefix()
-
-    # Delete opinion memory_units (cascades to unit_entities links)
-    # Opinions are now handled through mental model observations
-    op.execute(f"DELETE FROM {schema}memory_units WHERE fact_type = 'opinion'")
-
-
-def downgrade() -> None:
-    """Cannot restore deleted opinions."""
-    # Note: Cannot restore deleted opinions - they are lost on downgrade
-    pass

hindsight-api/hindsight_api/alembic/versions/j5e6f7g8h9i0_mental_model_versions.py

@@ -1,95 +0,0 @@
-"""mental_model_versions
-
-Revision ID: j5e6f7g8h9i0
-Revises: i4d5e6f7g8h9
-Create Date: 2026-01-16 00:00:00.000000
-
-This migration adds versioning support for mental models:
-1. Creates mental_model_versions table to store observation snapshots
-2. Adds version column to mental_models for tracking current version
-
-This enables changelog/diff functionality for mental model observations.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-# revision identifiers, used by Alembic.
-revision: str = "j5e6f7g8h9i0"
-down_revision: str | Sequence[str] | None = "i4d5e6f7g8h9"
-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 upgrade() -> None:
-    """Create mental_model_versions table and add version tracking."""
-    schema = _get_schema_prefix()
-
-    # Create mental_model_versions table for storing observation snapshots
-    op.execute(f"""
-        CREATE TABLE {schema}mental_model_versions (
-            id SERIAL PRIMARY KEY,
-            mental_model_id VARCHAR(64) NOT NULL,
-            bank_id VARCHAR(64) NOT NULL,
-            version INT NOT NULL,
-            observations JSONB NOT NULL DEFAULT '{{"observations": []}}'::jsonb,
-            created_at TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT now(),
-            FOREIGN KEY (mental_model_id, bank_id)
-                REFERENCES {schema}mental_models(id, bank_id) ON DELETE CASCADE,
-            UNIQUE (mental_model_id, bank_id, version)
-        )
-    """)
-
-    # Index for efficient version queries (get latest, list versions)
-    op.execute(f"""
-        CREATE INDEX idx_mental_model_versions_lookup
-        ON {schema}mental_model_versions(mental_model_id, bank_id, version DESC)
-    """)
-
-    # Add version column to mental_models to track current version
-    op.execute(f"""
-        ALTER TABLE {schema}mental_models
-        ADD COLUMN IF NOT EXISTS version INT NOT NULL DEFAULT 0
-    """)
-
-    # Migrate existing mental models: create version 1 for any that have observations
-    op.execute(f"""
-        INSERT INTO {schema}mental_model_versions (mental_model_id, bank_id, version, observations, created_at)
-        SELECT id, bank_id, 1, observations, COALESCE(last_updated, created_at)
-        FROM {schema}mental_models
-        WHERE observations IS NOT NULL
-          AND observations != '{{"observations": []}}'::jsonb
-          AND (observations->'observations') IS NOT NULL
-          AND jsonb_array_length(observations->'observations') > 0
-    """)
-
-    # Update version to 1 for migrated mental models
-    op.execute(f"""
-        UPDATE {schema}mental_models
-        SET version = 1
-        WHERE observations IS NOT NULL
-          AND observations != '{{"observations": []}}'::jsonb
-          AND (observations->'observations') IS NOT NULL
-          AND jsonb_array_length(observations->'observations') > 0
-    """)
-
-
-def downgrade() -> None:
-    """Remove mental_model_versions table and version column."""
-    schema = _get_schema_prefix()
-
-    # Drop index
-    op.execute(f"DROP INDEX IF EXISTS {schema}idx_mental_model_versions_lookup")
-
-    # Drop versions table
-    op.execute(f"DROP TABLE IF EXISTS {schema}mental_model_versions")
-
-    # Remove version column from mental_models
-    op.execute(f"ALTER TABLE {schema}mental_models DROP COLUMN IF EXISTS version")

hindsight-api/hindsight_api/alembic/versions/k6f7g8h9i0j1_add_directive_subtype.py

@@ -1,58 +0,0 @@
-"""add_directive_subtype
-
-Revision ID: k6f7g8h9i0j1
-Revises: j5e6f7g8h9i0
-Create Date: 2026-01-16 00:00:00.000000
-
-This migration adds 'directive' to the mental_models subtype constraint.
-Directives are hard rules with user-provided observations that the reflect agent must follow.
-"""
-
-from collections.abc import Sequence
-
-from alembic import context, op
-
-# revision identifiers, used by Alembic.
-revision: str = "k6f7g8h9i0j1"
-down_revision: str | Sequence[str] | None = "j5e6f7g8h9i0"
-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 upgrade() -> None:
-    """Add 'directive' to mental_models subtype constraint."""
-    schema = _get_schema_prefix()
-
-    # Drop existing constraint
-    op.execute(f"ALTER TABLE {schema}mental_models DROP CONSTRAINT IF EXISTS ck_mental_models_subtype")
-
-    # Create new constraint with 'directive' added
-    op.execute(f"""
-        ALTER TABLE {schema}mental_models
-        ADD CONSTRAINT ck_mental_models_subtype
-        CHECK (subtype IN ('structural', 'emergent', 'pinned', 'learned', 'directive'))
-    """)
-
-
-def downgrade() -> None:
-    """Remove 'directive' from mental_models subtype constraint."""
-    schema = _get_schema_prefix()
-
-    # First delete any directives (cannot downgrade if they exist)
-    op.execute(f"DELETE FROM {schema}mental_models WHERE subtype = 'directive'")
-
-    # Drop constraint with directive
-    op.execute(f"ALTER TABLE {schema}mental_models DROP CONSTRAINT IF EXISTS ck_mental_models_subtype")
-
-    # Recreate original constraint without directive
-    op.execute(f"""
-        ALTER TABLE {schema}mental_models
-        ADD CONSTRAINT ck_mental_models_subtype
-        CHECK (subtype IN ('structural', 'emergent', 'pinned', 'learned'))
-    """)

hindsight-api/hindsight_api/api/mcp.py

@@ -196,7 +196,7 @@ def create_mcp_server(memory: MemoryEngine) -> FastMCP:
         Each bank is an isolated memory store (like a separate "brain").
 
         Returns:
-            JSON list of banks with their IDs, names, dispositions, and missions.
+            JSON list of banks with their IDs, names, dispositions, and backgrounds.
         """
         try:
             banks = await memory.list_banks(request_context=RequestContext())
@@ -206,7 +206,7 @@ def create_mcp_server(memory: MemoryEngine) -> FastMCP:
             return f'{{"error": "{e}", "banks": []}}'
 
     @mcp.tool()
-    async def create_bank(bank_id: str, name: str | None = None, mission: str | None = None) -> str:
+    async def create_bank(bank_id: str, name: str | None = None, background: str | None = None) -> str:
         """
         Create a new memory bank or get an existing one.
 
@@ -216,18 +216,18 @@ def create_mcp_server(memory: MemoryEngine) -> FastMCP:
         Args:
             bank_id: Unique identifier for the bank (e.g., 'user-123', 'agent-alpha')
             name: Optional human-friendly name for the bank
-            mission: Optional mission describing who the agent is and what they're trying to accomplish
+            background: Optional background context about the bank's owner/purpose
         """
         try:
             # get_bank_profile auto-creates bank if it doesn't exist
             profile = await memory.get_bank_profile(bank_id, request_context=RequestContext())
 
-            # Update name/mission if provided
-            if name is not None or mission is not None:
+            # Update name/background if provided
+            if name is not None or background is not None:
                 await memory.update_bank(
                     bank_id,
                     name=name,
-                    mission=mission,
+                    background=background,
                     request_context=RequestContext(),
                 )
                 # Fetch updated profile

hindsight-api/hindsight_api/config.py

@@ -76,7 +76,6 @@ ENV_RECALL_MAX_CONCURRENT = "HINDSIGHT_API_RECALL_MAX_CONCURRENT"
 ENV_RECALL_CONNECTION_BUDGET = "HINDSIGHT_API_RECALL_CONNECTION_BUDGET"
 ENV_MCP_LOCAL_BANK_ID = "HINDSIGHT_API_MCP_LOCAL_BANK_ID"
 ENV_MCP_INSTRUCTIONS = "HINDSIGHT_API_MCP_INSTRUCTIONS"
-ENV_MENTAL_MODEL_REFRESH_CONCURRENCY = "HINDSIGHT_API_MENTAL_MODEL_REFRESH_CONCURRENCY"
 
 # Observation thresholds
 ENV_OBSERVATION_MIN_FACTS = "HINDSIGHT_API_OBSERVATION_MIN_FACTS"
@@ -107,9 +106,6 @@ ENV_TASK_BACKEND = "HINDSIGHT_API_TASK_BACKEND"
 ENV_TASK_BACKEND_MEMORY_BATCH_SIZE = "HINDSIGHT_API_TASK_BACKEND_MEMORY_BATCH_SIZE"
 ENV_TASK_BACKEND_MEMORY_BATCH_INTERVAL = "HINDSIGHT_API_TASK_BACKEND_MEMORY_BATCH_INTERVAL"
 
-# Reflect agent settings
-ENV_REFLECT_MAX_ITERATIONS = "HINDSIGHT_API_REFLECT_MAX_ITERATIONS"
-
 # Default values
 DEFAULT_DATABASE_URL = "pg0"
 DEFAULT_LLM_PROVIDER = "openai"
@@ -149,7 +145,6 @@ DEFAULT_MPFP_TOP_K_NEIGHBORS = 20  # Fan-out limit per node in MPFP graph traver
 DEFAULT_RECALL_MAX_CONCURRENT = 32  # Max concurrent recall operations per worker
 DEFAULT_RECALL_CONNECTION_BUDGET = 4  # Max concurrent DB connections per recall operation
 DEFAULT_MCP_LOCAL_BANK_ID = "mcp"
-DEFAULT_MENTAL_MODEL_REFRESH_CONCURRENCY = 8  # Max concurrent mental model refreshes
 
 # Observation thresholds
 DEFAULT_OBSERVATION_MIN_FACTS = 5  # Min facts required to generate entity observations
@@ -177,9 +172,6 @@ DEFAULT_TASK_BACKEND = "memory"  # Options: "memory", "noop"
 DEFAULT_TASK_BACKEND_MEMORY_BATCH_SIZE = 10
 DEFAULT_TASK_BACKEND_MEMORY_BATCH_INTERVAL = 1.0  # seconds
 
-# Reflect agent settings
-DEFAULT_REFLECT_MAX_ITERATIONS = 10  # Max tool call iterations before forcing response
-
 # Default MCP tool descriptions (can be customized via env vars)
 DEFAULT_MCP_RETAIN_DESCRIPTION = """Store important information to long-term memory.
 
@@ -269,7 +261,6 @@ class HindsightConfig:
     mpfp_top_k_neighbors: int
     recall_max_concurrent: int
     recall_connection_budget: int
-    mental_model_refresh_concurrency: int
 
     # Observation thresholds
     observation_min_facts: int
@@ -300,9 +291,6 @@ class HindsightConfig:
     task_backend_memory_batch_size: int
     task_backend_memory_batch_interval: float
 
-    # Reflect agent settings
-    reflect_max_iterations: int
-
     @classmethod
     def from_env(cls) -> "HindsightConfig":
         """Create configuration from environment variables."""
@@ -353,9 +341,6 @@ class HindsightConfig:
             recall_connection_budget=int(
                 os.getenv(ENV_RECALL_CONNECTION_BUDGET, str(DEFAULT_RECALL_CONNECTION_BUDGET))
             ),
-            mental_model_refresh_concurrency=int(
-                os.getenv(ENV_MENTAL_MODEL_REFRESH_CONCURRENCY, str(DEFAULT_MENTAL_MODEL_REFRESH_CONCURRENCY))
-            ),
             # Optimization flags
             skip_llm_verification=os.getenv(ENV_SKIP_LLM_VERIFICATION, "false").lower() == "true",
             lazy_reranker=os.getenv(ENV_LAZY_RERANKER, "false").lower() == "true",
@@ -395,8 +380,6 @@ class HindsightConfig:
             task_backend_memory_batch_interval=float(
                 os.getenv(ENV_TASK_BACKEND_MEMORY_BATCH_INTERVAL, str(DEFAULT_TASK_BACKEND_MEMORY_BATCH_INTERVAL))
             ),
-            # Reflect agent settings
-            reflect_max_iterations=int(os.getenv(ENV_REFLECT_MAX_ITERATIONS, str(DEFAULT_REFLECT_MAX_ITERATIONS))),
         )
 
     def get_llm_base_url(self) -> str:

hindsight-api/hindsight_api/engine/interface.py

@@ -160,14 +160,14 @@ class MemoryEngineInterface(ABC):
         request_context: "RequestContext",
     ) -> dict[str, Any]:
         """
-        Get bank profile including disposition and mission.
+        Get bank profile including disposition and background.
 
         Args:
             bank_id: The memory bank ID.
             request_context: Request context for authentication.
 
         Returns:
-            Bank profile dict with bank_id, name, disposition, and mission.
+            Bank profile dict.
         """
         ...
 
@@ -190,44 +190,25 @@ class MemoryEngineInterface(ABC):
         ...
 
     @abstractmethod
-    async def merge_bank_mission(
+    async def merge_bank_background(
         self,
         bank_id: str,
         new_info: str,
         *,
+        update_disposition: bool = True,
         request_context: "RequestContext",
     ) -> dict[str, Any]:
         """
-        Merge new mission information into bank profile.
+        Merge new background information into bank profile.
 
         Args:
             bank_id: The memory bank ID.
-            new_info: New mission information to merge.
+            new_info: New background information to merge.
+            update_disposition: Whether to infer disposition from background.
             request_context: Request context for authentication.
 
         Returns:
-            Updated mission info.
-        """
-        ...
-
-    @abstractmethod
-    async def set_bank_mission(
-        self,
-        bank_id: str,
-        mission: str,
-        *,
-        request_context: "RequestContext",
-    ) -> dict[str, Any]:
-        """
-        Set the bank's mission (replaces existing).
-
-        Args:
-            bank_id: The memory bank ID.
-            mission: The mission text.
-            request_context: Request context for authentication.
-
-        Returns:
-            Dict with bank_id and mission.
+            Updated background info.
         """
         ...
 
@@ -537,7 +518,7 @@ class MemoryEngineInterface(ABC):
         bank_id: str,
         *,
         request_context: "RequestContext",
-    ) -> dict[str, Any]:
+    ) -> list[dict[str, Any]]:
         """
         List async operations for a bank.
 
@@ -546,7 +527,7 @@ class MemoryEngineInterface(ABC):
             request_context: Request context for authentication.
 
         Returns:
-            Dict with 'total' (int) and 'operations' (list of operation dicts).
+            List of operation dicts with id, task_type, status, etc.
         """
         ...
 
@@ -580,16 +561,16 @@ class MemoryEngineInterface(ABC):
         bank_id: str,
         *,
         name: str | None = None,
-        mission: str | None = None,
+        background: str | None = None,
         request_context: "RequestContext",
     ) -> dict[str, Any]:
         """
-        Update bank name and/or mission.
+        Update bank name and/or background.
 
         Args:
             bank_id: The memory bank ID.
             name: New bank name (optional).
-            mission: New mission text (optional, replaces existing).
+            background: New background text (optional, replaces existing).
             request_context: Request context for authentication.
 
         Returns:

hindsight-api/hindsight_api/engine/llm_wrapper.py

@@ -209,10 +209,10 @@ class LLMProvider:
             OutputTooLongError: If output exceeds token limits.
             Exception: Re-raises API errors after retries exhausted.
         """
-        semaphore_start = time.time()
+        queue_start_time = time.time()
         async with _global_llm_semaphore:
-            semaphore_wait_time = time.time() - semaphore_start
             start_time = time.time()
+            semaphore_wait_time = start_time - queue_start_time
 
             # Handle Mock provider (for testing)
             if self.provider == "mock":
@@ -318,44 +318,43 @@ class LLMProvider:
 
             last_exception = None
 
-            # Prepare response format ONCE before the retry loop
-            # (to avoid appending schema to messages on every retry)
-            if response_format is not None:
-                schema = None
-                if hasattr(response_format, "model_json_schema"):
-                    schema = response_format.model_json_schema()
-
-                if strict_schema and schema is not None:
-                    # Use OpenAI's strict JSON schema enforcement
-                    # This guarantees all required fields are returned
-                    call_params["response_format"] = {
-                        "type": "json_schema",
-                        "json_schema": {
-                            "name": "response",
-                            "strict": True,
-                            "schema": schema,
-                        },
-                    }
-                else:
-                    # Soft enforcement: add schema to prompt and use json_object mode
-                    if schema is not None:
-                        schema_msg = f"\n\nYou must respond with valid JSON matching this schema:\n{json.dumps(schema, indent=2)}"
-
-                        if call_params["messages"] and call_params["messages"][0].get("role") == "system":
-                            call_params["messages"][0]["content"] += schema_msg
-                        elif call_params["messages"]:
-                            call_params["messages"][0]["content"] = (
-                                schema_msg + "\n\n" + call_params["messages"][0]["content"]
-                            )
-                    if self.provider not in ("lmstudio", "ollama"):
-                        # LM Studio and Ollama don't support json_object response format reliably
-                        # We rely on the schema in the system message instead
-                        call_params["response_format"] = {"type": "json_object"}
-
             for attempt in range(max_retries + 1):
                 try:
                     if response_format is not None:
+                        schema = None
+                        if hasattr(response_format, "model_json_schema"):
+                            schema = response_format.model_json_schema()
+
+                        if strict_schema and schema is not None:
+                            # Use OpenAI's strict JSON schema enforcement
+                            # This guarantees all required fields are returned
+                            call_params["response_format"] = {
+                                "type": "json_schema",
+                                "json_schema": {
+                                    "name": "response",
+                                    "strict": True,
+                                    "schema": schema,
+                                },
+                            }
+                        else:
+                            # Soft enforcement: add schema to prompt and use json_object mode
+                            if schema is not None:
+                                schema_msg = f"\n\nYou must respond with valid JSON matching this schema:\n{json.dumps(schema, indent=2)}"
+
+                                if call_params["messages"] and call_params["messages"][0].get("role") == "system":
+                                    call_params["messages"][0]["content"] += schema_msg
+                                elif call_params["messages"]:
+                                    call_params["messages"][0]["content"] = (
+                                        schema_msg + "\n\n" + call_params["messages"][0]["content"]
+                                    )
+                            if self.provider not in ("lmstudio", "ollama"):
+                                # LM Studio and Ollama don't support json_object response format reliably
+                                # We rely on the schema in the system message instead
+                                call_params["response_format"] = {"type": "json_object"}
+
+                        logger.debug(f"Sending request to {self.provider}/{self.model} (timeout={self.timeout})")
                         response = await self._client.chat.completions.create(**call_params)
+                        logger.debug(f"Received response from {self.provider}/{self.model}")
 
                         content = response.choices[0].message.content
 
@@ -468,11 +467,13 @@ class LLMProvider:
 
                 except APIConnectionError as e:
                     last_exception = e
-                    status_code = getattr(e, "status_code", None) or getattr(
-                        getattr(e, "response", None), "status_code", None
-                    )
-                    logger.warning(f"APIConnectionError (HTTP {status_code}), attempt {attempt + 1}: {str(e)[:200]}")
                     if attempt < max_retries:
+                        status_code = getattr(e, "status_code", None) or getattr(
+                            getattr(e, "response", None), "status_code", None
+                        )
+                        logger.warning(
+                            f"Connection error, retrying... (attempt {attempt + 1}/{max_retries + 1}) - status_code={status_code}, message={e}"
+                        )
                         backoff = min(initial_backoff * (2**attempt), max_backoff)
                         await asyncio.sleep(backoff)
                         continue
@@ -486,45 +487,6 @@ class LLMProvider:
                         logger.error(f"Auth error (HTTP {e.status_code}), not retrying: {str(e)}")
                         raise
 
-                    # Handle tool_use_failed error - model outputted in tool call format
-                    # Convert to expected JSON format and continue
-                    if e.status_code == 400 and response_format is not None:
-                        try:
-                            error_body = e.body if hasattr(e, "body") else {}
-                            if isinstance(error_body, dict):
-                                error_info: dict[str, Any] = error_body.get("error") or {}
-                                if error_info.get("code") == "tool_use_failed":
-                                    failed_gen = error_info.get("failed_generation", "")
-                                    if failed_gen:
-                                        # Parse the tool call format and convert to actions format
-                                        tool_call = json.loads(failed_gen)
-                                        tool_name = tool_call.get("name", "")
-                                        tool_args = tool_call.get("arguments", {})
-                                        # Convert to actions format: {"actions": [{"tool": "name", ...args}]}
-                                        converted = {"actions": [{"tool": tool_name, **tool_args}]}
-                                        if skip_validation:
-                                            result = converted
-                                        else:
-                                            result = response_format.model_validate(converted)
-
-                                        # Record metrics for this successful recovery
-                                        duration = time.time() - start_time
-                                        metrics = get_metrics_collector()
-                                        metrics.record_llm_call(
-                                            provider=self.provider,
-                                            model=self.model,
-                                            scope=scope,
-                                            duration=duration,
-                                            input_tokens=0,
-                                            output_tokens=0,
-                                            success=True,
-                                        )
-                                        if return_usage:
-                                            return result, TokenUsage(input_tokens=0, output_tokens=0, total_tokens=0)
-                                        return result
-                        except (json.JSONDecodeError, KeyError, TypeError):
-                            pass  # Failed to parse tool_use_failed, continue with normal retry
-
                     last_exception = e
                     if attempt < max_retries:
                         backoff = min(initial_backoff * (2**attempt), max_backoff)
@@ -535,416 +497,14 @@ class LLMProvider:
                         logger.error(f"API error after {max_retries + 1} attempts: {str(e)}")
                         raise
 
-                except Exception:
+                except Exception as e:
+                    logger.error(f"Unexpected error during LLM call: {type(e).__name__}: {str(e)}")
                     raise
 
             if last_exception:
                 raise last_exception
             raise RuntimeError("LLM call failed after all retries with no exception captured")
 
-    async def call_with_tools(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        max_completion_tokens: int | None = None,
-        temperature: float | None = None,
-        scope: str = "tools",
-        max_retries: int = 5,
-        initial_backoff: float = 1.0,
-        max_backoff: float = 30.0,
-        tool_choice: str | dict[str, Any] = "auto",
-    ) -> "LLMToolCallResult":
-        """
-        Make an LLM API call with tool/function calling support.
-
-        Args:
-            messages: List of message dicts. Can include tool results with role='tool'.
-            tools: List of tool definitions in OpenAI format.
-            max_completion_tokens: Maximum tokens in response.
-            temperature: Sampling temperature (0.0-2.0).
-            scope: Scope identifier for tracking.
-            max_retries: Maximum retry attempts.
-            initial_backoff: Initial backoff time in seconds.
-            max_backoff: Maximum backoff time in seconds.
-            tool_choice: How to choose tools - "auto", "none", "required", or {"type": "function", "function": {"name": "..."}}
-
-        Returns:
-            LLMToolCallResult with content and/or tool_calls.
-        """
-        from .response_models import LLMToolCall, LLMToolCallResult
-
-        async with _global_llm_semaphore:
-            start_time = time.time()
-
-            # Handle Mock provider
-            if self.provider == "mock":
-                return await self._call_with_tools_mock(messages, tools, scope)
-
-            # Handle Anthropic separately (uses different tool format)
-            if self.provider == "anthropic":
-                return await self._call_with_tools_anthropic(
-                    messages, tools, max_completion_tokens, max_retries, initial_backoff, max_backoff, start_time, scope
-                )
-
-            # Handle Gemini (convert to Gemini tool format)
-            if self.provider == "gemini":
-                return await self._call_with_tools_gemini(
-                    messages, tools, max_retries, initial_backoff, max_backoff, start_time, scope
-                )
-
-            # OpenAI-compatible providers (OpenAI, Groq, Ollama, LMStudio)
-            call_params: dict[str, Any] = {
-                "model": self.model,
-                "messages": messages,
-                "tools": tools,
-                "tool_choice": tool_choice,
-            }
-
-            if max_completion_tokens is not None:
-                call_params["max_completion_tokens"] = max_completion_tokens
-            if temperature is not None:
-                call_params["temperature"] = temperature
-
-            # Provider-specific parameters
-            if self.provider == "groq":
-                call_params["seed"] = DEFAULT_LLM_SEED
-
-            last_exception = None
-
-            for attempt in range(max_retries + 1):
-                try:
-                    response = await self._client.chat.completions.create(**call_params)
-
-                    message = response.choices[0].message
-                    finish_reason = response.choices[0].finish_reason
-
-                    # Extract tool calls if present
-                    tool_calls: list[LLMToolCall] = []
-                    if message.tool_calls:
-                        for tc in message.tool_calls:
-                            try:
-                                args = json.loads(tc.function.arguments) if tc.function.arguments else {}
-                            except json.JSONDecodeError:
-                                args = {"_raw": tc.function.arguments}
-                            tool_calls.append(LLMToolCall(id=tc.id, name=tc.function.name, arguments=args))
-
-                    content = message.content
-
-                    # Record metrics
-                    duration = time.time() - start_time
-                    usage = response.usage
-                    input_tokens = usage.prompt_tokens or 0 if usage else 0
-                    output_tokens = usage.completion_tokens or 0 if usage else 0
-
-                    metrics = get_metrics_collector()
-                    metrics.record_llm_call(
-                        provider=self.provider,
-                        model=self.model,
-                        scope=scope,
-                        duration=duration,
-                        input_tokens=input_tokens,
-                        output_tokens=output_tokens,
-                        success=True,
-                    )
-
-                    return LLMToolCallResult(content=content, tool_calls=tool_calls, finish_reason=finish_reason)
-
-                except APIConnectionError as e:
-                    last_exception = e
-                    if attempt < max_retries:
-                        await asyncio.sleep(min(initial_backoff * (2**attempt), max_backoff))
-                        continue
-                    raise
-
-                except APIStatusError as e:
-                    if e.status_code in (401, 403):
-                        raise
-                    last_exception = e
-                    if attempt < max_retries:
-                        await asyncio.sleep(min(initial_backoff * (2**attempt), max_backoff))
-                        continue
-                    raise
-
-                except Exception:
-                    raise
-
-            if last_exception:
-                raise last_exception
-            raise RuntimeError("Tool call failed after all retries")
-
-    async def _call_with_tools_mock(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        scope: str,
-    ) -> "LLMToolCallResult":
-        """Handle mock tool calls for testing."""
-        from .response_models import LLMToolCallResult
-
-        call_record = {
-            "provider": self.provider,
-            "model": self.model,
-            "messages": messages,
-            "tools": [t.get("function", {}).get("name") for t in tools],
-            "scope": scope,
-        }
-        self._mock_calls.append(call_record)
-
-        if self._mock_response is not None:
-            if isinstance(self._mock_response, LLMToolCallResult):
-                return self._mock_response
-            # Allow setting just tool calls as a list
-            if isinstance(self._mock_response, list):
-                from .response_models import LLMToolCall
-
-                return LLMToolCallResult(
-                    tool_calls=[
-                        LLMToolCall(id=f"mock_{i}", name=tc["name"], arguments=tc.get("arguments", {}))
-                        for i, tc in enumerate(self._mock_response)
-                    ],
-                    finish_reason="tool_calls",
-                )
-
-        return LLMToolCallResult(content="mock response", finish_reason="stop")
-
-    async def _call_with_tools_anthropic(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        max_completion_tokens: int | None,
-        max_retries: int,
-        initial_backoff: float,
-        max_backoff: float,
-        start_time: float,
-        scope: str,
-    ) -> "LLMToolCallResult":
-        """Handle Anthropic tool calling."""
-        from anthropic import APIConnectionError, APIStatusError
-
-        from .response_models import LLMToolCall, LLMToolCallResult
-
-        # Convert OpenAI tool format to Anthropic format
-        anthropic_tools = []
-        for tool in tools:
-            func = tool.get("function", {})
-            anthropic_tools.append(
-                {
-                    "name": func.get("name", ""),
-                    "description": func.get("description", ""),
-                    "input_schema": func.get("parameters", {"type": "object", "properties": {}}),
-                }
-            )
-
-        # Convert messages - handle tool results
-        system_prompt = None
-        anthropic_messages = []
-        for msg in messages:
-            role = msg.get("role", "user")
-            content = msg.get("content", "")
-
-            if role == "system":
-                system_prompt = (system_prompt + "\n\n" + content) if system_prompt else content
-            elif role == "tool":
-                # Anthropic uses tool_result blocks
-                anthropic_messages.append(
-                    {
-                        "role": "user",
-                        "content": [
-                            {"type": "tool_result", "tool_use_id": msg.get("tool_call_id", ""), "content": content}
-                        ],
-                    }
-                )
-            elif role == "assistant" and msg.get("tool_calls"):
-                # Convert assistant tool calls
-                tool_use_blocks = []
-                for tc in msg["tool_calls"]:
-                    tool_use_blocks.append(
-                        {
-                            "type": "tool_use",
-                            "id": tc.get("id", ""),
-                            "name": tc.get("function", {}).get("name", ""),
-                            "input": json.loads(tc.get("function", {}).get("arguments", "{}")),
-                        }
-                    )
-                anthropic_messages.append({"role": "assistant", "content": tool_use_blocks})
-            else:
-                anthropic_messages.append({"role": role, "content": content})
-
-        call_params: dict[str, Any] = {
-            "model": self.model,
-            "messages": anthropic_messages,
-            "tools": anthropic_tools,
-            "max_tokens": max_completion_tokens or 4096,
-        }
-        if system_prompt:
-            call_params["system"] = system_prompt
-
-        last_exception = None
-        for attempt in range(max_retries + 1):
-            try:
-                response = await self._anthropic_client.messages.create(**call_params)
-
-                # Extract content and tool calls
-                content_parts = []
-                tool_calls: list[LLMToolCall] = []
-
-                for block in response.content:
-                    if block.type == "text":
-                        content_parts.append(block.text)
-                    elif block.type == "tool_use":
-                        tool_calls.append(LLMToolCall(id=block.id, name=block.name, arguments=block.input or {}))
-
-                content = "".join(content_parts) if content_parts else None
-                finish_reason = "tool_calls" if tool_calls else "stop"
-
-                # Record metrics
-                metrics = get_metrics_collector()
-                metrics.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    duration=time.time() - start_time,
-                    input_tokens=response.usage.input_tokens or 0,
-                    output_tokens=response.usage.output_tokens or 0,
-                    success=True,
-                )
-
-                return LLMToolCallResult(content=content, tool_calls=tool_calls, finish_reason=finish_reason)
-
-            except (APIConnectionError, APIStatusError) as e:
-                if isinstance(e, APIStatusError) and e.status_code in (401, 403):
-                    raise
-                last_exception = e
-                if attempt < max_retries:
-                    await asyncio.sleep(min(initial_backoff * (2**attempt), max_backoff))
-                    continue
-                raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("Anthropic tool call failed")
-
-    async def _call_with_tools_gemini(
-        self,
-        messages: list[dict[str, Any]],
-        tools: list[dict[str, Any]],
-        max_retries: int,
-        initial_backoff: float,
-        max_backoff: float,
-        start_time: float,
-        scope: str,
-    ) -> "LLMToolCallResult":
-        """Handle Gemini tool calling."""
-        from .response_models import LLMToolCall, LLMToolCallResult
-
-        # Convert tools to Gemini format
-        gemini_tools = []
-        for tool in tools:
-            func = tool.get("function", {})
-            gemini_tools.append(
-                genai_types.Tool(
-                    function_declarations=[
-                        genai_types.FunctionDeclaration(
-                            name=func.get("name", ""),
-                            description=func.get("description", ""),
-                            parameters=func.get("parameters"),
-                        )
-                    ]
-                )
-            )
-
-        # Convert messages
-        system_instruction = None
-        gemini_contents = []
-        for msg in messages:
-            role = msg.get("role", "user")
-            content = msg.get("content", "")
-
-            if role == "system":
-                system_instruction = (system_instruction + "\n\n" + content) if system_instruction else content
-            elif role == "tool":
-                # Gemini uses function_response
-                gemini_contents.append(
-                    genai_types.Content(
-                        role="user",
-                        parts=[
-                            genai_types.Part(
-                                function_response=genai_types.FunctionResponse(
-                                    name=msg.get("name", ""),
-                                    response={"result": content},
-                                )
-                            )
-                        ],
-                    )
-                )
-            elif role == "assistant":
-                gemini_contents.append(genai_types.Content(role="model", parts=[genai_types.Part(text=content)]))
-            else:
-                gemini_contents.append(genai_types.Content(role="user", parts=[genai_types.Part(text=content)]))
-
-        config = genai_types.GenerateContentConfig(
-            system_instruction=system_instruction,
-            tools=gemini_tools,
-        )
-
-        last_exception = None
-        for attempt in range(max_retries + 1):
-            try:
-                response = await self._gemini_client.aio.models.generate_content(
-                    model=self.model,
-                    contents=gemini_contents,
-                    config=config,
-                )
-
-                # Extract content and tool calls
-                content = None
-                tool_calls: list[LLMToolCall] = []
-
-                if response.candidates and response.candidates[0].content:
-                    for part in response.candidates[0].content.parts:
-                        if hasattr(part, "text") and part.text:
-                            content = part.text
-                        if hasattr(part, "function_call") and part.function_call:
-                            fc = part.function_call
-                            tool_calls.append(
-                                LLMToolCall(
-                                    id=f"gemini_{len(tool_calls)}",
-                                    name=fc.name,
-                                    arguments=dict(fc.args) if fc.args else {},
-                                )
-                            )
-
-                finish_reason = "tool_calls" if tool_calls else "stop"
-
-                # Record metrics
-                metrics = get_metrics_collector()
-                input_tokens = response.usage_metadata.prompt_token_count if response.usage_metadata else 0
-                output_tokens = response.usage_metadata.candidates_token_count if response.usage_metadata else 0
-                metrics.record_llm_call(
-                    provider=self.provider,
-                    model=self.model,
-                    scope=scope,
-                    duration=time.time() - start_time,
-                    input_tokens=input_tokens,
-                    output_tokens=output_tokens,
-                    success=True,
-                )
-
-                return LLMToolCallResult(content=content, tool_calls=tool_calls, finish_reason=finish_reason)
-
-            except genai_errors.APIError as e:
-                if e.code in (401, 403):
-                    raise
-                last_exception = e
-                if attempt < max_retries:
-                    await asyncio.sleep(min(initial_backoff * (2**attempt), max_backoff))
-                    continue
-                raise
-
-        if last_exception:
-            raise last_exception
-        raise RuntimeError("Gemini tool call failed")
-
     async def _call_anthropic(
         self,
         messages: list[dict[str, str]],

hindsight-api/hindsight_api/engine/mental_models/__init__.py

@@ -1,18 +0,0 @@
-"""
-Mental models module for Hindsight.
-
-Mental models are synthesized summaries that represent understanding. They come
-in different subtypes based on how they were created:
-
-- Structural: Derived from the bank's mission (e.g., "Be a PM for engineering team")
-  These are created upfront based on what any agent with this role would need.
-
-- Emergent: Discovered from data patterns (named entities, temporal clusters, etc.)
-  These surface organically as facts are retained.
-
-- Pinned: User-defined models that persist across refreshes.
-"""
-
-from .models import MentalModel, MentalModelSubtype
-
-__all__ = ["MentalModel", "MentalModelSubtype"]

hindsight-api/hindsight_api/engine/mental_models/emergent.py

@@ -1,311 +0,0 @@
-"""
-Emergent mental model detection and promotion.
-
-Emergent models are discovered from data patterns:
-- Named entity extraction (people, projects, systems)
-- Temporal clustering (events with multiple references)
-- Causal patterns ("Because X, we do Y")
-- Behavioral anchors ("After X, we started Y")
-- Reference frequency (anything mentioned repeatedly)
-
-When a pattern is detected, it goes through a mission filter to check relevance,
-and if relevant, is promoted to a mental model.
-"""
-
-import logging
-from typing import TYPE_CHECKING
-
-from pydantic import BaseModel, Field
-
-from .models import EmergentCandidate
-
-if TYPE_CHECKING:
-    from ..llm_wrapper import LLMConfig
-
-logger = logging.getLogger(__name__)
-
-
-class MissionFilterCandidate(BaseModel):
-    """Result of mission filtering for a single candidate."""
-
-    name: str
-    promote: bool = Field(description="True if this is a specific named entity worth tracking")
-    reason: str = Field(description="Brief explanation for the decision")
-
-
-class MissionFilterResponse(BaseModel):
-    """Response from LLM for mission filtering."""
-
-    candidates: list[MissionFilterCandidate] = Field(description="Filtering decision for each candidate")
-
-
-def build_mission_filter_prompt(mission: str, candidates: list[EmergentCandidate]) -> str:
-    """Build the prompt for filtering candidates by mission relevance."""
-    candidate_list = "\n".join(
-        [f"- {c.name} (mentions: {c.mention_count}, method: {c.detection_method})" for c in candidates]
-    )
-
-    return f"""Filter these detected entities. For each one, decide: promote=true or promote=false.
-
-MISSION: {mission}
-
-DETECTED ENTITIES:
-{candidate_list}
-
-=== DECISION RULES ===
-
-Set promote=true ONLY for specific, named entities:
-- Person names: "John", "Maria", "Alice Chen", "Dr. Smith"
-- Named organizations: "Google", "Acme Corp", "Frontend Team"
-- Named places: "Central Park Zoo", "NYC Office", "Building A"
-- Named projects: "Project Phoenix", "Auth Service v2"
-
-Set promote=false for EVERYTHING ELSE, including:
-- Common English words: user, support, help, family, kids, parents, friends, people, team, photo, nature, park, office, home, work, school, joy, love, hope, fear, anger, gratitude, kindness, passion, motivation, inspiration, encouragement, positivity, energy, community, connection, commitment, collaboration, growth, impact, difference, success, progress, change, education, volunteering, veterans, homeless, shelter, meeting, project, system, process, event
-- Generic categories (even capitalized): Users, Customers, Team, Family, Kids, Veterans, Community
-- Abstract concepts: motivation, inspiration, gratitude, commitment, resilience
-
-THE TEST: Is this a specific name you'd find in a contact list or org chart?
-- "John" → YES (promote=true)
-- "kids" → NO (promote=false)
-- "community" → NO (promote=false)
-- "Maria" → YES (promote=true)
-- "park" → NO (promote=false)
-
-When in doubt, set promote=false."""
-
-
-def get_mission_filter_system_message() -> str:
-    """System message for mission filtering."""
-    return """You filter entities for promotion. Output JSON with 'candidates' array.
-
-Rules:
-- promote=true ONLY for specific names (people, organizations, named places/projects)
-- promote=false for common words, generic categories, abstract concepts
-
-Examples:
-- "John" → promote=true (person name)
-- "kids" → promote=false (generic category)
-- "community" → promote=false (abstract concept)
-- "Google" → promote=true (organization name)
-- "motivation" → promote=false (abstract concept)
-
-When in doubt, promote=false. Most entities should be rejected."""
-
-
-async def filter_candidates_by_mission(
-    llm_config: "LLMConfig",
-    mission: str,
-    candidates: list[EmergentCandidate],
-) -> list[EmergentCandidate]:
-    """
-    Filter emergent candidates to keep only specific, named entities.
-
-    Args:
-        llm_config: LLM configuration
-        mission: The bank's mission (used for context)
-        candidates: List of detected candidates
-
-    Returns:
-        Filtered list of candidates that are specific named entities
-    """
-    if not candidates:
-        return []
-
-    if not mission:
-        # No mission = no filtering, keep all candidates
-        logger.debug("[EMERGENT] No mission set, skipping filter")
-        return candidates
-
-    prompt = build_mission_filter_prompt(mission, candidates)
-
-    try:
-        result = await llm_config.call(
-            messages=[
-                {"role": "system", "content": get_mission_filter_system_message()},
-                {"role": "user", "content": prompt},
-            ],
-            response_format=MissionFilterResponse,
-            scope="mental_model_mission_filter",
-        )
-
-        # Build name -> promote map
-        promote_map = {c.name: c.promote for c in result.candidates}
-
-        # Filter candidates
-        filtered = []
-        for candidate in candidates:
-            if candidate.name in promote_map:
-                if promote_map[candidate.name]:
-                    filtered.append(candidate)
-                    logger.debug(f"[EMERGENT] Promoting '{candidate.name}'")
-                else:
-                    logger.debug(f"[EMERGENT] Rejecting '{candidate.name}'")
-            else:
-                # Candidate not in response - reject by default
-                logger.debug(f"[EMERGENT] '{candidate.name}' not in response, rejecting")
-
-        logger.info(f"[EMERGENT] Mission filter: {len(filtered)}/{len(candidates)} candidates promoted")
-        return filtered
-
-    except Exception as e:
-        logger.warning(f"[EMERGENT] Mission filter failed, rejecting all candidates: {e}")
-        return []
-
-
-async def evaluate_emergent_models(
-    llm_config: "LLMConfig",
-    models: list[dict],
-) -> list[str]:
-    """
-    Evaluate existing emergent models to check if they should be kept.
-
-    This re-evaluates emergent models using the same filtering criteria
-    as new candidates. Models that are generic/abstract will be removed.
-
-    Args:
-        llm_config: LLM configuration
-        models: List of existing emergent model dicts with 'name', 'id'
-
-    Returns:
-        List of model IDs that should be REMOVED (no longer valid)
-    """
-    if not models:
-        return []
-
-    # Convert existing models to candidates for evaluation
-    candidates = [
-        EmergentCandidate(
-            name=m["name"],
-            detection_method="existing_emergent_model",
-            mention_count=0,
-        )
-        for m in models
-    ]
-
-    # Build a simple prompt for re-evaluation
-    names_list = "\n".join([f"- {m['name']}" for m in models])
-    prompt = f"""Re-evaluate these existing mental models. For each one, decide: promote=true (keep) or promote=false (remove).
-
-EXISTING MODELS:
-{names_list}
-
-=== DECISION RULES ===
-
-Set promote=true ONLY for specific, named entities:
-- Person names: "John", "Maria", "Alice Chen", "Dr. Smith"
-- Named organizations: "Google", "Acme Corp", "Frontend Team"
-- Named places: "Central Park Zoo", "NYC Office", "Building A"
-- Named projects: "Project Phoenix", "Auth Service v2"
-
-Set promote=false for EVERYTHING ELSE, including:
-- Common English words: user, support, help, family, kids, parents, friends, people, team, photo, nature, park, office, home, work, school, joy, love, hope, fear, anger, gratitude, kindness, passion, motivation, inspiration, encouragement, positivity, energy, community, connection, commitment, collaboration, growth, impact, difference, success, progress, change, education, volunteering, veterans, homeless, shelter, meeting, project, system, process, event
-- Generic categories (even capitalized): Users, Customers, Team, Family, Kids, Veterans, Community
-- Abstract concepts: motivation, inspiration, gratitude, commitment, resilience
-
-THE TEST: Is this a specific name you'd find in a contact list or org chart?
-- "John" → YES (promote=true)
-- "kids" → NO (promote=false)
-- "community" → NO (promote=false)
-
-When in doubt, set promote=false."""
-
-    try:
-        result = await llm_config.call(
-            messages=[
-                {"role": "system", "content": get_mission_filter_system_message()},
-                {"role": "user", "content": prompt},
-            ],
-            response_format=MissionFilterResponse,
-            scope="mental_model_emergent_evaluation",
-        )
-
-        # Build name -> promote map
-        promote_map = {c.name: c.promote for c in result.candidates}
-
-        # Find models to remove
-        models_to_remove = []
-        for model in models:
-            name = model["name"]
-            if name in promote_map:
-                if not promote_map[name]:
-                    models_to_remove.append(model["id"])
-                else:
-                    logger.debug(f"[EMERGENT] Keeping '{name}'")
-            else:
-                # Model not in response - remove to be safe
-                logger.info(f"[EMERGENT] '{name}' not in evaluation response, marking for removal")
-                models_to_remove.append(model["id"])
-
-        logger.info(f"[EMERGENT] Evaluation: {len(models_to_remove)}/{len(models)} emergent models marked for removal")
-        return models_to_remove
-
-    except Exception as e:
-        logger.warning(f"[EMERGENT] Evaluation failed, keeping all models: {e}")
-        return []
-
-
-async def detect_entity_candidates(
-    pool,
-    bank_id: str,
-    min_mentions: int = 5,
-    top_percent: int = 20,
-) -> list[EmergentCandidate]:
-    """
-    Detect entities that are candidates for promotion to mental models.
-
-    Args:
-        pool: Database connection pool
-        bank_id: Bank identifier
-        min_mentions: Minimum mention count to consider
-        top_percent: Only consider top X% by mention count
-
-    Returns:
-        List of entity candidates
-    """
-    from ..db_utils import acquire_with_retry
-    from ..memory_engine import fq_table
-
-    candidates = []
-
-    async with acquire_with_retry(pool) as conn:
-        # Get entities that meet criteria and don't already have mental models
-        rows = await conn.fetch(
-            f"""
-            WITH ranked AS (
-                SELECT
-                    e.id,
-                    e.canonical_name,
-                    e.mention_count,
-                    PERCENT_RANK() OVER (ORDER BY e.mention_count DESC) as rank_pct
-                FROM {fq_table("entities")} e
-                LEFT JOIN {fq_table("mental_models")} mm
-                    ON mm.entity_id = e.id AND mm.bank_id = e.bank_id
-                WHERE e.bank_id = $1
-                  AND e.mention_count >= $2
-                  AND mm.id IS NULL  -- Not already a mental model
-            )
-            SELECT id, canonical_name, mention_count
-            FROM ranked
-            WHERE rank_pct <= $3
-            ORDER BY mention_count DESC
-            LIMIT 50
-            """,
-            bank_id,
-            min_mentions,
-            top_percent / 100.0,
-        )
-
-        for row in rows:
-            candidates.append(
-                EmergentCandidate(
-                    name=row["canonical_name"],
-                    detection_method="named_entity_extraction",
-                    mention_count=row["mention_count"],
-                    entity_id=str(row["id"]),
-                    relevance_score=0.0,
-                )
-            )
-
-    logger.debug(f"[EMERGENT] Detected {len(candidates)} entity candidates")
-    return candidates

hindsight-api/hindsight_api/engine/mental_models/models.py

@@ -1,98 +0,0 @@
-"""
-Pydantic models for mental models.
-"""
-
-from datetime import datetime, timezone
-from enum import Enum
-
-from pydantic import BaseModel, Field
-
-
-class MentalModelSubtype(str, Enum):
-    """Subtype of mental model - how it was created."""
-
-    STRUCTURAL = "structural"  # Derived from mission, created upfront
-    EMERGENT = "emergent"  # Discovered from data patterns
-    LEARNED = "learned"  # Formed through reflection
-    PINNED = "pinned"  # User-defined topic, observations LLM-generated
-    DIRECTIVE = "directive"  # User-defined hard rules, observations user-provided
-
-
-class MentalModel(BaseModel):
-    """
-    A mental model representing synthesized understanding.
-
-    Mental models are the agent's consolidated knowledge. Unlike raw facts,
-    mental models provide:
-    - A one-liner description for quick scanning/retrieval
-    - A full summary for deep understanding
-    - Links to related mental models
-    """
-
-    id: str = Field(description="Unique identifier within the bank")
-    bank_id: str = Field(description="Bank this mental model belongs to")
-    subtype: MentalModelSubtype = Field(description="How this model was created")
-    name: str = Field(description="Human-readable name")
-    description: str = Field(description="One-liner for quick scanning and retrieval matching")
-    summary: str | None = Field(default=None, description="Full synthesized understanding")
-
-    # References
-    entity_id: str | None = Field(default=None, description="Reference to entities table when type=entity")
-    source_facts: list[str] = Field(default_factory=list, description="Fact IDs used to generate summary")
-    links: list[str] = Field(default_factory=list, description="Related mental model IDs")
-
-    # Tags for scoped visibility (similar to document tags)
-    tags: list[str] = Field(default_factory=list, description="Tags for scoped visibility filtering")
-
-    # Timestamps
-    last_updated: datetime | None = Field(default=None, description="When summary was last regenerated")
-    created_at: datetime = Field(
-        default_factory=lambda: datetime.now(timezone.utc), description="When this model was created"
-    )
-
-
-class StructuralModelTemplate(BaseModel):
-    """
-    A template for a structural mental model.
-
-    Generated by LLM based on the bank's mission. Represents what any agent
-    with this role would need to track.
-    """
-
-    id: str = Field(default="", description="Existing model ID to keep, or empty for new models")
-    name: str = Field(description="Human-readable name")
-    description: str = Field(description="What this model should track")
-    initial_probes: list[str] = Field(default_factory=list, description="Initial search queries to populate this model")
-
-
-class StructuralModelDerivationResponse(BaseModel):
-    """Response from LLM for structural model derivation."""
-
-    templates: list[StructuralModelTemplate] = Field(description="Structural model templates derived from the mission")
-
-
-class EmergentCandidate(BaseModel):
-    """
-    A candidate for promotion to emergent mental model.
-
-    Detected through pattern analysis of facts.
-    """
-
-    name: str = Field(description="Name of the detected pattern/entity")
-    detection_method: str = Field(description="How this candidate was detected")
-    mention_count: int = Field(default=0, description="How many times referenced")
-    entity_id: str | None = Field(default=None, description="Entity ID if detected as entity")
-    relevance_score: float = Field(default=0.0, description="Score from mission filter (0-1)")
-
-
-class ResearchResult(BaseModel):
-    """
-    Result from the research endpoint.
-
-    Contains the answer along with the mental models and facts used.
-    """
-
-    answer: str = Field(description="The synthesized answer")
-    mental_models_used: list[str] = Field(default_factory=list, description="IDs of mental models that contributed")
-    facts_used: list[str] = Field(default_factory=list, description="Fact IDs that contributed")
-    question_type: str | None = Field(default=None, description="Detected question type (WHO, WHAT, HOW, etc.)")

hindsight-api/hindsight_api/engine/mental_models/structural.py

@@ -1,228 +0,0 @@
-"""
-Structural mental model derivation from bank mission.
-
-Structural models are derived from the bank's mission - they represent what
-any agent with this role would need to track. For example:
-
-Mission: "Be a PM for engineering team"
-Structural models:
-  - Team Structure (who's on the team, roles)
-  - Project Overview (current projects, status)
-  - Processes (how releases work, how decisions are made)
-  - Key Systems (what we own, dependencies)
-"""
-
-import logging
-from typing import TYPE_CHECKING
-
-from pydantic import BaseModel, Field
-
-from .models import StructuralModelTemplate
-
-if TYPE_CHECKING:
-    from ..llm_wrapper import LLMConfig
-
-logger = logging.getLogger(__name__)
-
-
-class StructuralDerivationResponse(BaseModel):
-    """Response from LLM for structural model derivation."""
-
-    templates: list[StructuralModelTemplate] = Field(description="Structural model templates derived from the mission")
-
-
-class StructuralRelevanceResult(BaseModel):
-    """Result of evaluating a structural model's relevance to the mission."""
-
-    name: str
-    relevant: bool
-    reason: str
-
-
-class StructuralRelevanceResponse(BaseModel):
-    """Response from LLM for structural model relevance evaluation."""
-
-    models: list[StructuralRelevanceResult] = Field(description="Relevance evaluation for each model")
-
-
-def build_structural_derivation_prompt(mission: str, existing_models: list[dict] | None = None) -> str:
-    """Build the prompt for deriving structural models from a mission."""
-    existing_section = ""
-    if existing_models:
-        model_list = "\n".join([f"- id='{m['id']}' name='{m['name']}': {m['description']}" for m in existing_models])
-        existing_section = f"""
-EXISTING STRUCTURAL MODELS:
-{model_list}
-
-IMPORTANT: If keeping an existing model, you MUST return its EXACT 'id' value.
-Models not included in your output will be REMOVED.
-"""
-
-    return f"""Given this agent mission, identify the KEY THINGS to track to achieve it.
-
-MISSION: {mission}
-{existing_section}
-IMPORTANT CONSTRAINTS:
-- Return 0-3 structural models MAXIMUM (less is better!)
-- Only include models for SPECIFIC, CONCRETE things the agent needs to track
-- Each model must be DIRECTLY tied to achieving the mission
-- If the mission is simple, return 0 models (empty array is fine)
-- If existing models are provided and you want to keep one, use its EXACT id
-- Do NOT create near-duplicates (e.g., don't create "topic-map" if "topic-connections" exists)
-
-GOOD examples (specific, actionable):
-- Mission: "Be a PM for engineering team" → "Team Members" (track who's on the team)
-- Mission: "Track customer feedback" → "Customer Issues" (track specific complaints/requests)
-- Mission: "Manage project X" → "Project X Milestones" (track progress)
-
-BAD examples (too generic, don't create these):
-- "Processes", "Workflows", "Key Systems", "Important Events"
-- "Communication", "Collaboration", "Progress", "Status"
-- Generic role-based models not tied to the specific mission
-
-For each model:
-1. id: Use EXACT existing id if keeping a model, or leave empty for new models
-2. name: Short, specific name (e.g., "Team Members", "Sprint Goals")
-3. description: One line describing what to track
-4. initial_probes: 2-3 search queries to find relevant information
-
-Return ONLY the models that should exist. Existing models not in your output will be deleted."""
-
-
-def get_structural_derivation_system_message() -> str:
-    """System message for structural model derivation."""
-    return """You identify the key things to track for a mission. Be VERY selective.
-
-Rules:
-- Maximum 3 models (prefer fewer)
-- Only SPECIFIC, CONCRETE things - not generic categories
-- Each must DIRECTLY help achieve the mission
-- Empty array is valid if no models are truly needed
-- If existing models are shown and you want to keep one, return its EXACT id
-- Never create duplicates - if a similar model exists, keep the existing one
-
-Output JSON with 'templates' array (can be empty)."""
-
-
-def _normalize_id(text: str) -> str:
-    """Normalize a string to a canonical form for comparison.
-
-    Removes common suffixes, pluralization, and normalizes separators.
-    """
-    # Lowercase and normalize separators
-    normalized = text.lower().replace(" ", "-").replace("_", "-")
-
-    # Remove common suffixes that indicate the same concept
-    suffixes_to_remove = ["-map", "-list", "-overview", "-tracker", "-s"]
-    for suffix in suffixes_to_remove:
-        if normalized.endswith(suffix) and len(normalized) > len(suffix):
-            normalized = normalized[: -len(suffix)]
-
-    return normalized
-
-
-def _find_similar_existing_id(new_id: str, existing_models: list[dict]) -> str | None:
-    """Find an existing model ID that is similar to the new ID.
-
-    Returns the existing ID if a similar one is found, None otherwise.
-    """
-    if not existing_models:
-        return None
-
-    new_normalized = _normalize_id(new_id)
-
-    for model in existing_models:
-        existing_id = model.get("id", "")
-        existing_normalized = _normalize_id(existing_id)
-
-        # Check if one is a prefix of the other (normalized)
-        if new_normalized.startswith(existing_normalized) or existing_normalized.startswith(new_normalized):
-            return existing_id
-
-        # Check if they're the same when normalized
-        if new_normalized == existing_normalized:
-            return existing_id
-
-    return None
-
-
-async def derive_structural_models(
-    llm_config: "LLMConfig",
-    mission: str,
-    existing_models: list[dict] | None = None,
-) -> tuple[list[StructuralModelTemplate], list[str]]:
-    """
-    Derive structural model templates from a bank's mission.
-
-    This combines derivation and evaluation in one call. The LLM sees existing
-    models and decides which to keep. Any existing model not in the output
-    will be marked for removal.
-
-    Args:
-        llm_config: LLM configuration for calling the model
-        mission: The bank's mission (e.g., "Be a PM for engineering team")
-        existing_models: Optional list of existing model dicts with 'name', 'description', 'id'
-
-    Returns:
-        Tuple of (templates to create/keep, IDs of existing models to remove)
-
-    Raises:
-        Exception: If LLM call fails
-    """
-    prompt = build_structural_derivation_prompt(mission, existing_models)
-
-    result = await llm_config.call(
-        messages=[
-            {"role": "system", "content": get_structural_derivation_system_message()},
-            {"role": "user", "content": prompt},
-        ],
-        response_format=StructuralDerivationResponse,
-        scope="mental_model_structural_derivation",
-    )
-
-    templates = result.templates
-    logger.info(f"[STRUCTURAL] LLM returned {len(templates)} structural models")
-
-    # Build set of existing IDs for quick lookup
-    existing_ids = {m["id"] for m in existing_models} if existing_models else set()
-
-    # Process templates: validate IDs, deduplicate, assign stable IDs
-    processed_templates: list[StructuralModelTemplate] = []
-    kept_existing_ids: set[str] = set()
-
-    for template in templates:
-        # If LLM returned an ID, check if it's a valid existing ID
-        if template.id and template.id in existing_ids:
-            # LLM is keeping an existing model
-            kept_existing_ids.add(template.id)
-            processed_templates.append(template)
-            logger.info(f"[STRUCTURAL] Keeping existing model: {template.id}")
-        else:
-            # New model or LLM didn't return a valid ID
-            # Generate ID from name
-            generated_id = template.name.lower().replace(" ", "-").replace("_", "-")
-
-            # Check for similar existing models to prevent near-duplicates
-            similar_id = _find_similar_existing_id(generated_id, existing_models)
-            if similar_id and similar_id not in kept_existing_ids:
-                # Use the existing similar model instead of creating a new one
-                logger.info(f"[STRUCTURAL] Detected near-duplicate: '{generated_id}' matches existing '{similar_id}'")
-                template.id = similar_id
-                kept_existing_ids.add(similar_id)
-            else:
-                template.id = generated_id
-
-            processed_templates.append(template)
-
-    # Find existing models to remove (not kept in LLM output)
-    models_to_remove = []
-    if existing_models:
-        for model in existing_models:
-            if model["id"] not in kept_existing_ids:
-                logger.info(f"[STRUCTURAL] Marking '{model['name']}' (id={model['id']}) for removal")
-                models_to_remove.append(model["id"])
-
-    if models_to_remove:
-        logger.info(f"[STRUCTURAL] {len(models_to_remove)} existing models will be removed")
-
-    return processed_templates, models_to_remove

hindsight-api/hindsight_api/engine/reflect/__init__.py

@@ -1,20 +0,0 @@
-"""
-Reflect agent module for agentic reflection with tools.
-
-The reflect agent uses an iterative loop with tools to:
-1. Lookup mental models (existing knowledge)
-2. Recall facts (semantic + temporal search)
-3. Learn new insights (create/update mental models)
-4. Expand memories (get chunk/document context)
-"""
-
-from .agent import ReflectAgentResult, run_reflect_agent
-from .models import MentalModelInput, ReflectAction, ReflectActionBatch
-
-__all__ = [
-    "run_reflect_agent",
-    "ReflectAgentResult",
-    "ReflectAction",
-    "ReflectActionBatch",
-    "MentalModelInput",
-]

hindsight-api/hindsight_api/engine/reflect/agent.py

@@ -1,723 +0,0 @@
-"""
-Reflect agent - agentic loop for reflection with native tool calling.
-"""
-
-import asyncio
-import json
-import logging
-import time
-from typing import TYPE_CHECKING, Any, Awaitable, Callable
-
-from .models import DirectiveInfo, LLMCall, MentalModelInput, ReflectAgentResult, ToolCall
-from .prompts import FINAL_SYSTEM_PROMPT, _extract_directive_rules, build_final_prompt, build_system_prompt_for_tools
-from .tools_schema import get_reflect_tools
-
-
-def _build_directives_applied(directives: list[dict[str, Any]] | None) -> list[DirectiveInfo]:
-    """Build list of DirectiveInfo from directive mental models."""
-    if not directives:
-        return []
-
-    result = []
-    for directive in directives:
-        directive_id = directive.get("id", "")
-        directive_name = directive.get("name", "")
-        observations = directive.get("observations", [])
-
-        rules = []
-        for obs in observations:
-            # Support both Pydantic Observation objects and dicts
-            if hasattr(obs, "content"):
-                rules.append(obs.content)
-            elif isinstance(obs, dict) and obs.get("content"):
-                rules.append(obs["content"])
-
-        result.append(DirectiveInfo(id=directive_id, name=directive_name, rules=rules))
-
-    return result
-
-
-if TYPE_CHECKING:
-    from ..llm_wrapper import LLMProvider
-    from ..response_models import LLMToolCall
-
-logger = logging.getLogger(__name__)
-
-DEFAULT_MAX_ITERATIONS = 10
-
-
-async def _generate_structured_output(
-    answer: str,
-    response_schema: dict,
-    llm_config: "LLMProvider",
-    reflect_id: str,
-) -> dict[str, Any] | None:
-    """Generate structured output from an answer using the provided JSON schema.
-
-    Args:
-        answer: The text answer to extract structured data from
-        response_schema: JSON Schema for the expected output structure
-        llm_config: LLM provider for making the extraction call
-        reflect_id: Reflect ID for logging
-
-    Returns:
-        Structured output dict if successful, None otherwise
-    """
-    try:
-        from typing import Any as TypingAny
-
-        from pydantic import create_model
-
-        def _json_schema_type_to_python(field_schema: dict) -> type:
-            """Map JSON schema type to Python type for better LLM guidance."""
-            json_type = field_schema.get("type", "string")
-            if json_type == "array":
-                return list
-            elif json_type == "object":
-                return dict
-            elif json_type == "integer":
-                return int
-            elif json_type == "number":
-                return float
-            elif json_type == "boolean":
-                return bool
-            else:
-                return str
-
-        # Build fields from JSON schema properties
-        schema_props = response_schema.get("properties", {})
-        required_fields = set(response_schema.get("required", []))
-        fields: dict[str, TypingAny] = {}
-        for field_name, field_schema in schema_props.items():
-            field_type = _json_schema_type_to_python(field_schema)
-            default = ... if field_name in required_fields else None
-            fields[field_name] = (field_type, default)
-
-        if not fields:
-            return None
-
-        DynamicModel = create_model("StructuredResponse", **fields)
-
-        # Include the full schema in the prompt for better LLM guidance
-        schema_str = json.dumps(response_schema, indent=2)
-
-        # Call LLM with the answer to extract structured data
-        structured_prompt = f"""Based on this answer, extract the information into the requested structured format.
-
-Answer: {answer}
-
-JSON Schema to follow:
-```json
-{schema_str}
-```
-
-Return ONLY a valid JSON object that matches this exact schema. Pay special attention to field types:
-- "type": "array" means the value must be a JSON array/list, NOT a string
-- "type": "string" means the value must be a string
-- "type": "object" means the value must be a JSON object
-
-Do not include any explanation, only the JSON object."""
-
-        structured_result = await llm_config.call(
-            messages=[
-                {
-                    "role": "system",
-                    "content": "Extract structured data from the given answer. Return only valid JSON matching the provided schema exactly.",
-                },
-                {"role": "user", "content": structured_prompt},
-            ],
-            response_format=DynamicModel,
-            scope="reflect_structured",
-            skip_validation=True,  # We'll handle the dict ourselves
-        )
-
-        # Convert to dict
-        if hasattr(structured_result, "model_dump"):
-            structured_output = structured_result.model_dump()
-        elif isinstance(structured_result, dict):
-            structured_output = structured_result
-        else:
-            # Try to parse as JSON
-            structured_output = json.loads(str(structured_result))
-
-        logger.info(f"[REFLECT {reflect_id}] Generated structured output with {len(structured_output)} fields")
-        return structured_output
-
-    except Exception as e:
-        logger.warning(f"[REFLECT {reflect_id}] Failed to generate structured output: {e}")
-        return None
-
-
-async def run_reflect_agent(
-    llm_config: "LLMProvider",
-    bank_id: str,
-    query: str,
-    bank_profile: dict[str, Any],
-    lookup_fn: Callable[[str | None], Awaitable[dict[str, Any]]],
-    recall_fn: Callable[[str, int], Awaitable[dict[str, Any]]],
-    expand_fn: Callable[[list[str], str], Awaitable[dict[str, Any]]],
-    learn_fn: Callable[[MentalModelInput], Awaitable[dict[str, Any]]] | None = None,
-    context: str | None = None,
-    max_iterations: int = DEFAULT_MAX_ITERATIONS,
-    max_tokens: int | None = None,
-    response_schema: dict | None = None,
-    directives: list[dict[str, Any]] | None = None,
-) -> ReflectAgentResult:
-    """
-    Execute the reflect agent loop using native tool calling.
-
-    The agent iteratively calls tools to gather information and learn,
-    then provides a final answer via the done() tool.
-
-    Args:
-        llm_config: LLM provider for agent calls
-        bank_id: Bank identifier
-        query: Question to answer
-        bank_profile: Bank profile with name and mission
-        lookup_fn: Tool callback for lookup (model_id) -> result
-        recall_fn: Tool callback for recall (query, max_tokens) -> result
-        expand_fn: Tool callback for expand (memory_id, depth) -> result
-        learn_fn: Optional tool callback for learn (MentalModelInput) -> result.
-                  If None, learn tool is disabled.
-        context: Optional additional context
-        max_iterations: Maximum number of iterations before forcing response
-        max_tokens: Maximum tokens for the final response
-        response_schema: Optional JSON Schema for structured output in final response
-        directives: Optional list of directive mental models to inject as hard rules
-
-    Returns:
-        ReflectAgentResult with final answer and metadata
-    """
-    enable_learn = learn_fn is not None
-    reflect_id = f"{bank_id[:8]}-{int(time.time() * 1000) % 100000}"
-    start_time = time.time()
-
-    # Build directives_applied for the trace
-    directives_applied = _build_directives_applied(directives)
-
-    # Extract directive rules for tool schema (if any)
-    directive_rules = _extract_directive_rules(directives) if directives else None
-
-    # Get tools for this agent (with directive compliance field if directives exist)
-    tools = get_reflect_tools(enable_learn=enable_learn, directive_rules=directive_rules)
-
-    # Build initial messages (directives are injected into system prompt at START and END)
-    system_prompt = build_system_prompt_for_tools(bank_profile, context, directives=directives)
-    messages: list[dict[str, Any]] = [
-        {"role": "system", "content": system_prompt},
-        {"role": "user", "content": query},
-    ]
-
-    # Tracking
-    mental_models_created: list[str] = []
-    total_tools_called = 0
-    tool_trace: list[ToolCall] = []
-    tool_trace_summary: list[dict[str, Any]] = []
-    llm_trace: list[dict[str, Any]] = []
-    context_history: list[dict[str, Any]] = []  # For final prompt fallback
-
-    # Track available IDs for validation (prevents hallucinated citations)
-    available_memory_ids: set[str] = set()
-    available_model_ids: set[str] = set()
-
-    # Pre-fetch mental models so the agent always starts with this knowledge
-    prefetch_start = time.time()
-    models_result = await lookup_fn(None)  # List all mental models
-    prefetch_duration = int((time.time() - prefetch_start) * 1000)
-
-    # Track available model IDs
-    if isinstance(models_result, dict) and "models" in models_result:
-        for model in models_result["models"]:
-            if "id" in model:
-                available_model_ids.add(model["id"])
-
-    # Add to context history for the agent
-    context_history.append({"tool": "list_mental_models", "output": models_result})
-
-    # Add to tool trace
-    tool_trace.append(
-        ToolCall(
-            tool="list_mental_models",
-            input={"tool": "list_mental_models"},
-            output=models_result,
-            duration_ms=prefetch_duration,
-            iteration=0,
-        )
-    )
-    tool_trace_summary.append(
-        {
-            "tool": "list_mental_models",
-            "input_summary": "(prefetch)",
-            "duration_ms": prefetch_duration,
-            "output_chars": len(json.dumps(models_result, default=str)),
-        }
-    )
-    total_tools_called += 1
-
-    # Include in the user message so the agent sees it
-    models_info = json.dumps(models_result, indent=2, default=str)
-    messages[1]["content"] = f"{query}\n\n## Available Mental Models (pre-fetched)\n```json\n{models_info}\n```"
-
-    def _get_llm_trace() -> list[LLMCall]:
-        return [LLMCall(scope=c["scope"], duration_ms=c["duration_ms"]) for c in llm_trace]
-
-    def _log_completion(answer: str, iterations: int, forced: bool = False):
-        elapsed_ms = int((time.time() - start_time) * 1000)
-        tools_summary = (
-            ", ".join(
-                f"{t['tool']}({t['input_summary']})={t['duration_ms']}ms/{t.get('output_chars', 0)}c"
-                for t in tool_trace_summary
-            )
-            or "none"
-        )
-        llm_summary = ", ".join(f"{c['scope']}={c['duration_ms']}ms" for c in llm_trace) or "none"
-        total_llm_ms = sum(c["duration_ms"] for c in llm_trace)
-        total_tools_ms = sum(t["duration_ms"] for t in tool_trace_summary)
-
-        answer_preview = answer[:100] + "..." if len(answer) > 100 else answer
-        mode = "forced" if forced else "done"
-        logger.info(
-            f"[REFLECT {reflect_id}] {mode} | "
-            f"query='{query[:50]}...' | "
-            f"iterations={iterations} | "
-            f"llm=[{llm_summary}] ({total_llm_ms}ms) | "
-            f"tools=[{tools_summary}] ({total_tools_ms}ms) | "
-            f"answer='{answer_preview}' | "
-            f"total={elapsed_ms}ms"
-        )
-
-    for iteration in range(max_iterations):
-        is_last = iteration == max_iterations - 1
-
-        if is_last:
-            # Force text response on last iteration - no tools
-            prompt = build_final_prompt(query, context_history, bank_profile, context)
-            llm_start = time.time()
-            response = await llm_config.call(
-                messages=[
-                    {"role": "system", "content": FINAL_SYSTEM_PROMPT},
-                    {"role": "user", "content": prompt},
-                ],
-                scope="reflect_agent_final",
-                max_completion_tokens=max_tokens,
-            )
-            llm_trace.append({"scope": "final", "duration_ms": int((time.time() - llm_start) * 1000)})
-            answer = response.strip()
-
-            # Generate structured output if schema provided
-            structured_output = None
-            if response_schema and answer:
-                structured_output = await _generate_structured_output(answer, response_schema, llm_config, reflect_id)
-
-            _log_completion(answer, iteration + 1, forced=True)
-            return ReflectAgentResult(
-                text=answer,
-                structured_output=structured_output,
-                iterations=iteration + 1,
-                tools_called=total_tools_called,
-                mental_models_created=mental_models_created,
-                tool_trace=tool_trace,
-                llm_trace=_get_llm_trace(),
-                directives_applied=directives_applied,
-            )
-
-        # Call LLM with tools
-        llm_start = time.time()
-
-        try:
-            result = await llm_config.call_with_tools(
-                messages=messages,
-                tools=tools,
-                scope="reflect_agent",
-                tool_choice="required" if iteration == 0 else "auto",  # Force tool use on first iteration
-            )
-            llm_duration = int((time.time() - llm_start) * 1000)
-            llm_trace.append({"scope": f"agent_{iteration + 1}", "duration_ms": llm_duration})
-
-        except Exception:
-            llm_trace.append(
-                {"scope": f"agent_{iteration + 1}_err", "duration_ms": int((time.time() - llm_start) * 1000)}
-            )
-            # Guardrail: If no evidence gathered yet, retry
-            has_gathered_evidence = bool(available_memory_ids) or bool(available_model_ids)
-            if not has_gathered_evidence and iteration < max_iterations - 1:
-                continue
-            prompt = build_final_prompt(query, context_history, bank_profile, context)
-            llm_start = time.time()
-            response = await llm_config.call(
-                messages=[
-                    {"role": "system", "content": FINAL_SYSTEM_PROMPT},
-                    {"role": "user", "content": prompt},
-                ],
-                scope="reflect_agent_final",
-                max_completion_tokens=max_tokens,
-            )
-            llm_trace.append({"scope": "final", "duration_ms": int((time.time() - llm_start) * 1000)})
-            answer = response.strip()
-
-            # Generate structured output if schema provided
-            structured_output = None
-            if response_schema and answer:
-                structured_output = await _generate_structured_output(answer, response_schema, llm_config, reflect_id)
-
-            _log_completion(answer, iteration + 1, forced=True)
-            return ReflectAgentResult(
-                text=answer,
-                structured_output=structured_output,
-                iterations=iteration + 1,
-                tools_called=total_tools_called,
-                mental_models_created=mental_models_created,
-                tool_trace=tool_trace,
-                llm_trace=_get_llm_trace(),
-                directives_applied=directives_applied,
-            )
-
-        # No tool calls - LLM wants to respond with text
-        if not result.tool_calls:
-            if result.content:
-                answer = result.content.strip()
-
-                # Generate structured output if schema provided
-                structured_output = None
-                if response_schema and answer:
-                    structured_output = await _generate_structured_output(
-                        answer, response_schema, llm_config, reflect_id
-                    )
-
-                _log_completion(answer, iteration + 1)
-                return ReflectAgentResult(
-                    text=answer,
-                    structured_output=structured_output,
-                    iterations=iteration + 1,
-                    tools_called=total_tools_called,
-                    mental_models_created=mental_models_created,
-                    tool_trace=tool_trace,
-                    llm_trace=_get_llm_trace(),
-                    directives_applied=directives_applied,
-                )
-            # Empty response, force final
-            prompt = build_final_prompt(query, context_history, bank_profile, context)
-            llm_start = time.time()
-            response = await llm_config.call(
-                messages=[
-                    {"role": "system", "content": FINAL_SYSTEM_PROMPT},
-                    {"role": "user", "content": prompt},
-                ],
-                scope="reflect_agent_final",
-                max_completion_tokens=max_tokens,
-            )
-            llm_trace.append({"scope": "final", "duration_ms": int((time.time() - llm_start) * 1000)})
-            answer = response.strip()
-
-            # Generate structured output if schema provided
-            structured_output = None
-            if response_schema and answer:
-                structured_output = await _generate_structured_output(answer, response_schema, llm_config, reflect_id)
-
-            _log_completion(answer, iteration + 1, forced=True)
-            return ReflectAgentResult(
-                text=answer,
-                structured_output=structured_output,
-                iterations=iteration + 1,
-                tools_called=total_tools_called,
-                mental_models_created=mental_models_created,
-                tool_trace=tool_trace,
-                llm_trace=_get_llm_trace(),
-                directives_applied=directives_applied,
-            )
-
-        # Check for done tool call (handle both 'done' and 'functions.done')
-        done_call = next((tc for tc in result.tool_calls if tc.name == "done" or tc.name == "functions.done"), None)
-        if done_call:
-            # Guardrail: Require evidence before done
-            has_gathered_evidence = bool(available_memory_ids) or bool(available_model_ids)
-            if not has_gathered_evidence and iteration < max_iterations - 1:
-                # Add assistant message and fake tool result asking for evidence
-                messages.append(
-                    {
-                        "role": "assistant",
-                        "tool_calls": [_tool_call_to_dict(done_call)],
-                    }
-                )
-                messages.append(
-                    {
-                        "role": "tool",
-                        "tool_call_id": done_call.id,
-                        "content": json.dumps(
-                            {
-                                "error": "You must call recall() or list_mental_models() to gather evidence before providing your final answer."
-                            }
-                        ),
-                    }
-                )
-                continue
-
-            # Process done tool
-            return await _process_done_tool(
-                done_call,
-                available_memory_ids,
-                available_model_ids,
-                iteration + 1,
-                total_tools_called,
-                mental_models_created,
-                tool_trace,
-                _get_llm_trace(),
-                _log_completion,
-                reflect_id,
-                directives_applied=directives_applied,
-                llm_config=llm_config,
-                response_schema=response_schema,
-            )
-
-        # Execute other tools in parallel (exclude done and functions.done)
-        other_tools = [tc for tc in result.tool_calls if tc.name not in ("done", "functions.done")]
-        if other_tools:
-            # Add assistant message with tool calls
-            messages.append(
-                {
-                    "role": "assistant",
-                    "tool_calls": [_tool_call_to_dict(tc) for tc in other_tools],
-                }
-            )
-
-            # Execute tools in parallel
-            tool_tasks = [
-                _execute_tool_with_timing(tc, lookup_fn, recall_fn, expand_fn, learn_fn) for tc in other_tools
-            ]
-            tool_results = await asyncio.gather(*tool_tasks, return_exceptions=True)
-            total_tools_called += len(other_tools)
-
-            # Process results and add to messages
-            for tc, result_data in zip(other_tools, tool_results):
-                if isinstance(result_data, Exception):
-                    # Tool execution failed - log and raise to fail the request
-                    logger.error(f"[REFLECT {reflect_id}] Tool {tc.name} failed with exception: {result_data}")
-                    raise RuntimeError(f"Reflect tool '{tc.name}' failed: {result_data}")
-
-                output, duration_ms = result_data
-
-                # Check if tool returned an error response
-                if isinstance(output, dict) and "error" in output:
-                    logger.error(f"[REFLECT {reflect_id}] Tool {tc.name} returned error: {output['error']}")
-                    raise RuntimeError(f"Reflect tool '{tc.name}' error: {output['error']}")
-
-                # Track created mental models
-                if tc.name == "learn" and isinstance(output, dict) and "model_id" in output:
-                    mental_models_created.append(output["model_id"])
-
-                # Track available memory IDs from recall
-                if tc.name == "recall" and isinstance(output, dict) and "memories" in output:
-                    for memory in output["memories"]:
-                        if "id" in memory:
-                            available_memory_ids.add(memory["id"])
-
-                # Track available model IDs
-                if tc.name in ("list_mental_models", "get_mental_model") and isinstance(output, dict):
-                    if output.get("found") and "model" in output:
-                        model_id = output["model"].get("id")
-                        if model_id:
-                            available_model_ids.add(model_id)
-                    elif "models" in output:
-                        for model in output["models"]:
-                            if "id" in model:
-                                available_model_ids.add(model["id"])
-
-                # Add tool result message
-                messages.append(
-                    {
-                        "role": "tool",
-                        "tool_call_id": tc.id,
-                        "content": json.dumps(output, default=str),
-                    }
-                )
-
-                # Track for logging and context history
-                input_dict = {"tool": tc.name, **tc.arguments}
-                input_summary = _summarize_input(tc.name, tc.arguments)
-
-                tool_trace.append(
-                    ToolCall(
-                        tool=tc.name, input=input_dict, output=output, duration_ms=duration_ms, iteration=iteration + 1
-                    )
-                )
-
-                try:
-                    output_chars = len(json.dumps(output))
-                except (TypeError, ValueError):
-                    output_chars = len(str(output))
-
-                tool_trace_summary.append(
-                    {
-                        "tool": tc.name,
-                        "input_summary": input_summary,
-                        "duration_ms": duration_ms,
-                        "output_chars": output_chars,
-                    }
-                )
-
-                # Keep context history for fallback final prompt
-                context_history.append({"tool": tc.name, "input": input_dict, "output": output})
-
-    # Should not reach here
-    answer = "I was unable to formulate a complete answer within the iteration limit."
-    _log_completion(answer, max_iterations, forced=True)
-    return ReflectAgentResult(
-        text=answer,
-        iterations=max_iterations,
-        tools_called=total_tools_called,
-        mental_models_created=mental_models_created,
-        tool_trace=tool_trace,
-        llm_trace=_get_llm_trace(),
-        directives_applied=directives_applied,
-    )
-
-
-def _tool_call_to_dict(tc: "LLMToolCall") -> dict[str, Any]:
-    """Convert LLMToolCall to OpenAI message format."""
-    return {
-        "id": tc.id,
-        "type": "function",
-        "function": {
-            "name": tc.name,
-            "arguments": json.dumps(tc.arguments),
-        },
-    }
-
-
-async def _process_done_tool(
-    done_call: "LLMToolCall",
-    available_memory_ids: set[str],
-    available_model_ids: set[str],
-    iterations: int,
-    total_tools_called: int,
-    mental_models_created: list[str],
-    tool_trace: list[ToolCall],
-    llm_trace: list[LLMCall],
-    log_completion: Callable,
-    reflect_id: str,
-    directives_applied: list[DirectiveInfo],
-    llm_config: "LLMProvider | None" = None,
-    response_schema: dict | None = None,
-) -> ReflectAgentResult:
-    """Process the done tool call and return the result."""
-    args = done_call.arguments
-
-    answer = args.get("answer", "").strip()
-    if not answer:
-        answer = "No answer provided."
-
-    # Validate IDs
-    used_memory_ids = [mid for mid in args.get("memory_ids", []) if mid in available_memory_ids]
-    used_model_ids = [mid for mid in args.get("model_ids", []) if mid in available_model_ids]
-
-    # Generate structured output if schema provided
-    structured_output = None
-    if response_schema and llm_config and answer:
-        structured_output = await _generate_structured_output(answer, response_schema, llm_config, reflect_id)
-
-    log_completion(answer, iterations)
-    return ReflectAgentResult(
-        text=answer,
-        structured_output=structured_output,
-        iterations=iterations,
-        tools_called=total_tools_called,
-        mental_models_created=mental_models_created,
-        tool_trace=tool_trace,
-        llm_trace=llm_trace,
-        used_memory_ids=used_memory_ids,
-        used_model_ids=used_model_ids,
-        directives_applied=directives_applied,
-    )
-
-
-async def _execute_tool_with_timing(
-    tc: "LLMToolCall",
-    lookup_fn: Callable[[str | None], Awaitable[dict[str, Any]]],
-    recall_fn: Callable[[str, int], Awaitable[dict[str, Any]]],
-    expand_fn: Callable[[list[str], str], Awaitable[dict[str, Any]]],
-    learn_fn: Callable[[MentalModelInput], Awaitable[dict[str, Any]]] | None = None,
-) -> tuple[dict[str, Any], int]:
-    """Execute a tool call and return result with timing."""
-    start = time.time()
-    result = await _execute_tool(tc.name, tc.arguments, lookup_fn, recall_fn, expand_fn, learn_fn)
-    duration_ms = int((time.time() - start) * 1000)
-    return result, duration_ms
-
-
-async def _execute_tool(
-    tool_name: str,
-    args: dict[str, Any],
-    lookup_fn: Callable[[str | None], Awaitable[dict[str, Any]]],
-    recall_fn: Callable[[str, int], Awaitable[dict[str, Any]]],
-    expand_fn: Callable[[list[str], str], Awaitable[dict[str, Any]]],
-    learn_fn: Callable[[MentalModelInput], Awaitable[dict[str, Any]]] | None = None,
-) -> dict[str, Any]:
-    """Execute a single tool by name."""
-    # Normalize tool name - some LLMs return 'functions.done' instead of 'done'
-    if tool_name.startswith("functions."):
-        tool_name = tool_name[len("functions.") :]
-
-    if tool_name == "list_mental_models":
-        return await lookup_fn(None)
-
-    elif tool_name == "get_mental_model":
-        model_id = args.get("model_id")
-        if not model_id:
-            return {"error": "get_mental_model requires model_id"}
-        return await lookup_fn(model_id)
-
-    elif tool_name == "recall":
-        query = args.get("query")
-        if not query:
-            return {"error": "recall requires a query parameter"}
-        max_tokens = max(args.get("max_tokens") or 2048, 1000)  # Default 2048, min 1000
-        return await recall_fn(query, max_tokens)
-
-    elif tool_name == "learn":
-        if learn_fn is None:
-            return {"error": "learn tool is not available"}
-        name = args.get("name")
-        description = args.get("description")
-        if not name or not description:
-            return {"error": "learn requires name and description"}
-        return await learn_fn(MentalModelInput(name=name, description=description))
-
-    elif tool_name == "expand":
-        memory_ids = args.get("memory_ids", [])
-        if not memory_ids:
-            return {"error": "expand requires memory_ids"}
-        depth = args.get("depth", "chunk")
-        return await expand_fn(memory_ids, depth)
-
-    else:
-        return {"error": f"Unknown tool: {tool_name}"}
-
-
-def _summarize_input(tool_name: str, args: dict[str, Any]) -> str:
-    """Create a summary of tool input for logging, showing all params."""
-    if tool_name == "list_mental_models":
-        return "()"
-    elif tool_name == "get_mental_model":
-        return f"(model_id={args.get('model_id', '?')})"
-    elif tool_name == "recall":
-        query = args.get("query", "")
-        query_preview = f"'{query[:30]}...'" if len(query) > 30 else f"'{query}'"
-        # Show actual value used (default 2048, min 1000)
-        max_tokens = max(args.get("max_tokens") or 2048, 1000)
-        return f"(query={query_preview}, max_tokens={max_tokens})"
-    elif tool_name == "learn":
-        name = args.get("name", "?")
-        desc = args.get("description", "")
-        desc_preview = f"'{desc[:20]}...'" if len(desc) > 20 else f"'{desc}'"
-        return f"(name='{name}', description={desc_preview})"
-    elif tool_name == "expand":
-        memory_ids = args.get("memory_ids", [])
-        depth = args.get("depth", "chunk")
-        return f"(memory_ids=[{len(memory_ids)} ids], depth={depth})"
-    elif tool_name == "done":
-        answer = args.get("answer", "")
-        answer_preview = f"'{answer[:30]}...'" if len(answer) > 30 else f"'{answer}'"
-        memory_ids = args.get("memory_ids", [])
-        model_ids = args.get("model_ids", [])
-        return f"(answer={answer_preview}, memory_ids={len(memory_ids)}, model_ids={len(model_ids)})"
-    return str(args)

hindsight-api/hindsight_api/engine/reflect/models.py

@@ -1,114 +0,0 @@
-"""
-Pydantic models for the reflect agent.
-"""
-
-from typing import Any, Literal
-
-from pydantic import BaseModel, Field
-
-
-class MentalModelObservation(BaseModel):
-    """An observation within a mental model with its supporting memories."""
-
-    title: str = Field(description="Observation header (can be empty for intro)")
-    text: str = Field(description="Observation content - no headers, use lists/tables/bold")
-    memory_ids: list[str] = Field(default_factory=list, description="Memory IDs supporting this observation")
-
-
-class MentalModelInput(BaseModel):
-    """Input for the learn tool to create a mental model placeholder.
-
-    The agent only specifies name and description - the actual content/observations
-    are generated during refresh, similar to pinned models.
-    """
-
-    name: str = Field(description="Human-readable name for the mental model")
-    description: str = Field(description="What to track - used as prompt for content generation during refresh")
-    entity_id: str | None = Field(default=None, description="Optional link to existing entity ID")
-
-
-class AnswerSection(BaseModel):
-    """A section of the answer with its supporting evidence (DEPRECATED)."""
-
-    title: str = Field(description="Section header/title")
-    text: str = Field(description="Section content")
-    memory_ids: list[str] = Field(default_factory=list, description="Memory IDs supporting this section")
-    model_ids: list[str] = Field(default_factory=list, description="Mental model IDs supporting this section")
-
-
-class ReflectAction(BaseModel):
-    """Single action the reflect agent can take."""
-
-    tool: Literal["list_mental_models", "get_mental_model", "recall", "learn", "expand", "done"] = Field(
-        description="Tool to invoke: list_mental_models, get_mental_model, recall, learn, expand, or done"
-    )
-    # Tool-specific parameters
-    model_id: str | None = Field(default=None, description="Mental model ID for get_mental_model")
-    query: str | None = Field(default=None, description="Search query for recall")
-    max_tokens: int | None = Field(default=None, description="Max tokens for recall results (default 2048)")
-    mental_model: MentalModelInput | None = Field(default=None, description="Mental model to create/update for learn")
-    memory_ids: list[str] | None = Field(default=None, description="Memory unit IDs for expand (batched)")
-    depth: Literal["chunk", "document"] | None = Field(default=None, description="Expansion depth for expand")
-    sections: list[AnswerSection] | None = Field(default=None, description="DEPRECATED: Use answer field instead")
-    observations: list[MentalModelObservation] | None = Field(
-        default=None, description="Observations for done action (when output_mode=observations)"
-    )
-    # Plain text answer fields (for output_mode=answer)
-    answer: str | None = Field(default=None, description="Plain text answer for done action (no markdown)")
-    answer_memory_ids: list[str] | None = Field(
-        default=None, description="Memory IDs supporting the answer", alias="memory_ids"
-    )
-    answer_model_ids: list[str] | None = Field(
-        default=None, description="Mental model IDs supporting the answer", alias="model_ids"
-    )
-    reasoning: str | None = Field(default=None, description="Brief reasoning for this action")
-
-
-class ReflectActionBatch(BaseModel):
-    """Batch of actions for parallel execution."""
-
-    actions: list[ReflectAction] = Field(description="List of actions to execute in parallel")
-
-
-class ToolCall(BaseModel):
-    """A single tool call made during reflect."""
-
-    tool: str = Field(description="Tool name: lookup, recall, learn, expand")
-    input: dict = Field(description="Tool input parameters")
-    output: dict = Field(description="Tool output/result")
-    duration_ms: int = Field(description="Execution time in milliseconds")
-    iteration: int = Field(default=0, description="Iteration number (1-based) when this tool was called")
-
-
-class LLMCall(BaseModel):
-    """A single LLM call made during reflect."""
-
-    scope: str = Field(description="Call scope: agent_1, agent_2, final, etc.")
-    duration_ms: int = Field(description="Execution time in milliseconds")
-
-
-class DirectiveInfo(BaseModel):
-    """Information about a directive that was applied during reflect."""
-
-    id: str = Field(description="Directive mental model ID")
-    name: str = Field(description="Directive name")
-    rules: list[str] = Field(default_factory=list, description="Directive rules/observations that were applied")
-
-
-class ReflectAgentResult(BaseModel):
-    """Result from the reflect agent."""
-
-    text: str = Field(description="Final answer text")
-    structured_output: dict[str, Any] | None = Field(
-        default=None, description="Structured output parsed according to provided response_schema"
-    )
-    iterations: int = Field(default=0, description="Number of iterations taken")
-    tools_called: int = Field(default=0, description="Total number of tool calls made")
-    mental_models_created: list[str] = Field(default_factory=list, description="IDs of mental models created/updated")
-    tool_trace: list[ToolCall] = Field(default_factory=list, description="Trace of all tool calls made")
-    llm_trace: list[LLMCall] = Field(default_factory=list, description="Trace of all LLM calls made")
-    used_memory_ids: list[str] = Field(default_factory=list, description="Validated memory IDs actually used in answer")
-    used_model_ids: list[str] = Field(default_factory=list, description="Validated model IDs actually used in answer")
-    directives_applied: list[DirectiveInfo] = Field(
-        default_factory=list, description="Directive mental models that affected this reflection"
-    )

hindsight-api/hindsight_api/engine/reflect/observations.py

@@ -1,248 +0,0 @@
-"""
-Models and utilities for evidence-grounded observations with computed trends.
-
-Observations are part of mental models and represent patterns/beliefs derived
-from memories. Each observation must be grounded in specific evidence (quotes)
-from memories, and trends are computed algorithmically from evidence timestamps.
-"""
-
-from datetime import datetime, timedelta, timezone
-from enum import Enum
-
-from pydantic import BaseModel, Field, computed_field, field_validator
-
-
-class Trend(str, Enum):
-    """Computed trend for an observation based on evidence timestamps.
-
-    Trends indicate how an observation's evidence is distributed over time:
-    - STABLE: Evidence spread across time, continues to present
-    - STRENGTHENING: More/denser evidence recently than before
-    - WEAKENING: Evidence mostly old, sparse recently
-    - NEW: All evidence within recent window
-    - STALE: No evidence in recent window (may no longer apply)
-    """
-
-    STABLE = "stable"
-    STRENGTHENING = "strengthening"
-    WEAKENING = "weakening"
-    NEW = "new"
-    STALE = "stale"
-
-
-class ObservationEvidence(BaseModel):
-    """A single piece of evidence supporting an observation.
-
-    Each evidence item must include an exact quote from the source memory
-    to ensure observations are grounded and verifiable.
-    """
-
-    memory_id: str = Field(description="ID of the memory unit this evidence comes from")
-    quote: str = Field(description="Exact quote from the memory supporting the observation")
-    relevance: str = Field(default="", description="Brief explanation of how this quote supports the observation")
-    timestamp: datetime = Field(description="When the source memory was created")
-
-    @field_validator("timestamp", mode="before")
-    @classmethod
-    def ensure_timezone_aware(cls, v: datetime | str | None) -> datetime:
-        """Ensure timestamp is always timezone-aware UTC."""
-        if v is None:
-            return datetime.now(timezone.utc)
-        if isinstance(v, str):
-            # Parse ISO format string, handling 'Z' suffix
-            v = datetime.fromisoformat(v.replace("Z", "+00:00"))
-        if isinstance(v, datetime):
-            if v.tzinfo is None:
-                return v.replace(tzinfo=timezone.utc)
-            return v
-        raise ValueError(f"Invalid timestamp type: {type(v)}")
-
-
-class Observation(BaseModel):
-    """A single observation within a mental model.
-
-    Observations represent patterns, preferences, beliefs, or other insights
-    derived from memories. Each observation must be grounded in evidence
-    with exact quotes from source memories.
-    """
-
-    title: str = Field(description="Short summary title for the observation (5-10 words)")
-    content: str = Field(description="The observation content - detailed explanation of what we believe to be true")
-    evidence: list[ObservationEvidence] = Field(default_factory=list, description="Supporting evidence with quotes")
-    created_at: datetime = Field(
-        default_factory=lambda: datetime.now(timezone.utc), description="When this observation was first created"
-    )
-
-    @field_validator("created_at", mode="before")
-    @classmethod
-    def ensure_created_at_timezone_aware(cls, v: datetime | str | None) -> datetime:
-        """Ensure created_at is always timezone-aware UTC."""
-        if v is None:
-            return datetime.now(timezone.utc)
-        if isinstance(v, str):
-            v = datetime.fromisoformat(v.replace("Z", "+00:00"))
-        if isinstance(v, datetime):
-            if v.tzinfo is None:
-                return v.replace(tzinfo=timezone.utc)
-            return v
-        raise ValueError(f"Invalid created_at type: {type(v)}")
-
-    @computed_field
-    @property
-    def trend(self) -> Trend:
-        """Compute trend from evidence timestamps."""
-        return compute_trend(self.evidence)
-
-    @computed_field
-    @property
-    def evidence_span(self) -> dict[str, str | None]:
-        """Get the time span covered by evidence."""
-        if not self.evidence:
-            return {"from": None, "to": None}
-        timestamps = [e.timestamp for e in self.evidence]
-        return {
-            "from": min(timestamps).isoformat(),
-            "to": max(timestamps).isoformat(),
-        }
-
-    @computed_field
-    @property
-    def evidence_count(self) -> int:
-        """Number of evidence items supporting this observation."""
-        return len(self.evidence)
-
-
-def compute_trend(
-    evidence: list[ObservationEvidence],
-    now: datetime | None = None,
-    recent_days: int = 30,
-    old_days: int = 90,
-) -> Trend:
-    """Compute the trend for an observation based on evidence timestamps.
-
-    The trend indicates how the evidence is distributed over time:
-    - STABLE: Evidence spread across time, continues to present
-    - STRENGTHENING: More evidence recently than historically
-    - WEAKENING: Evidence mostly old, sparse recently
-    - NEW: All evidence is recent (within recent_days)
-    - STALE: No evidence in recent window
-
-    Args:
-        evidence: List of evidence items with timestamps
-        now: Reference time for calculations (defaults to current UTC time)
-        recent_days: Number of days to consider "recent" (default 30)
-        old_days: Number of days to consider "old" (default 90)
-
-    Returns:
-        Computed Trend enum value
-    """
-    if now is None:
-        now = datetime.now(timezone.utc)
-
-    # Ensure now is timezone-aware
-    if now.tzinfo is None:
-        now = now.replace(tzinfo=timezone.utc)
-
-    if not evidence:
-        return Trend.STALE
-
-    recent_cutoff = now - timedelta(days=recent_days)
-    old_cutoff = now - timedelta(days=old_days)
-
-    # Normalize timestamps to UTC for comparison
-    def normalize_ts(ts: datetime) -> datetime:
-        if ts.tzinfo is None:
-            return ts.replace(tzinfo=timezone.utc)
-        return ts
-
-    recent = [e for e in evidence if normalize_ts(e.timestamp) > recent_cutoff]
-    old = [e for e in evidence if normalize_ts(e.timestamp) < old_cutoff]
-    middle = [e for e in evidence if old_cutoff <= normalize_ts(e.timestamp) <= recent_cutoff]
-
-    # No recent evidence = stale
-    if not recent:
-        return Trend.STALE
-
-    # All evidence is recent = new
-    if not old and not middle:
-        return Trend.NEW
-
-    # Compare density (evidence per day)
-    recent_density = len(recent) / recent_days if recent_days > 0 else 0
-    older_period = old_days - recent_days
-    older_density = (len(old) + len(middle)) / older_period if older_period > 0 else 0
-
-    # Avoid division by zero
-    if older_density == 0:
-        return Trend.NEW
-
-    ratio = recent_density / older_density
-
-    if ratio > 1.5:
-        return Trend.STRENGTHENING
-    elif ratio < 0.5:
-        return Trend.WEAKENING
-    else:
-        return Trend.STABLE
-
-
-class CandidateObservation(BaseModel):
-    """A candidate observation generated during the seed phase.
-
-    Candidates are preliminary observations that need evidence validation
-    before becoming full observations.
-    """
-
-    content: str = Field(description="The proposed observation content")
-    seed_memory_ids: list[str] = Field(default_factory=list, description="Memory IDs that inspired this candidate")
-
-
-class CandidateWithEvidence(BaseModel):
-    """A candidate observation with gathered supporting and contradicting evidence."""
-
-    candidate: CandidateObservation
-    supporting_memories: list[dict] = Field(default_factory=list, description="Memories that support this observation")
-    contradicting_memories: list[dict] = Field(
-        default_factory=list, description="Memories that contradict this observation"
-    )
-
-
-class MentalModelSnapshot(BaseModel):
-    """A versioned snapshot of a mental model's observations.
-
-    Used for tracking changes over time and enabling diff views.
-    """
-
-    version: int = Field(description="Version number (1-indexed)")
-    observations: list[Observation] = Field(default_factory=list, description="Observations at this version")
-    created_at: datetime = Field(
-        default_factory=lambda: datetime.now(timezone.utc), description="When this version was created"
-    )
-    reflect_summary: str | None = Field(default=None, description="Summary of changes in this version")
-
-
-def verify_evidence_quotes(
-    observation: Observation,
-    memories: dict[str, str],
-) -> tuple[bool, list[str]]:
-    """Verify that all evidence quotes exist in the referenced memories.
-
-    Args:
-        observation: The observation to verify
-        memories: Dict mapping memory_id to memory content
-
-    Returns:
-        Tuple of (is_valid, list of error messages)
-    """
-    errors = []
-
-    for evidence in observation.evidence:
-        memory_content = memories.get(evidence.memory_id)
-        if memory_content is None:
-            errors.append(f"Memory {evidence.memory_id} not found")
-            continue
-
-        if evidence.quote not in memory_content:
-            errors.append(f"Quote not found in memory {evidence.memory_id}: '{evidence.quote[:50]}...'")
-
-    return len(errors) == 0, errors

hindsight-api/hindsight_api/engine/reflect/prompts.py

@@ -1,762 +0,0 @@
-"""
-System prompts for the reflect agent.
-"""
-
-import json
-from typing import Any
-
-
-def _extract_directive_rules(directives: list[dict[str, Any]]) -> list[str]:
-    """
-    Extract directive rules as a list of strings.
-
-    Args:
-        directives: List of directive mental models with observations
-
-    Returns:
-        List of directive rule strings
-    """
-    rules = []
-    for directive in directives:
-        directive_name = directive.get("name", "")
-        observations = directive.get("observations", [])
-        if observations:
-            for obs in observations:
-                # Support both Pydantic Observation objects and dicts
-                if hasattr(obs, "title"):
-                    title = obs.title
-                    content = obs.content
-                else:
-                    title = obs.get("title", "")
-                    content = obs.get("content", "")
-                if title and content:
-                    rules.append(f"**{title}**: {content}")
-                elif content:
-                    rules.append(content)
-        elif directive_name:
-            # Fallback to description if no observations
-            desc = directive.get("description", "")
-            if desc:
-                rules.append(f"**{directive_name}**: {desc}")
-    return rules
-
-
-def build_directives_section(directives: list[dict[str, Any]]) -> str:
-    """
-    Build the directives section for the system prompt.
-
-    Directives are hard rules that MUST be followed in all responses.
-
-    Args:
-        directives: List of directive mental models with observations
-    """
-    if not directives:
-        return ""
-
-    rules = _extract_directive_rules(directives)
-    if not rules:
-        return ""
-
-    parts = [
-        "## DIRECTIVES (MANDATORY)",
-        "These are hard rules you MUST follow in ALL responses:",
-        "",
-    ]
-
-    for rule in rules:
-        parts.append(f"- {rule}")
-
-    parts.extend(
-        [
-            "",
-            "NEVER violate these directives, even if other context suggests otherwise.",
-            "IMPORTANT: Do NOT explain or justify how you handled directives in your answer. Just follow them silently.",
-            "",
-        ]
-    )
-    return "\n".join(parts)
-
-
-def build_directives_reminder(directives: list[dict[str, Any]]) -> str:
-    """
-    Build a reminder section for directives to place at the end of the prompt.
-
-    Args:
-        directives: List of directive mental models with observations
-    """
-    if not directives:
-        return ""
-
-    rules = _extract_directive_rules(directives)
-    if not rules:
-        return ""
-
-    parts = [
-        "",
-        "## REMINDER: MANDATORY DIRECTIVES",
-        "Before responding, ensure your answer complies with ALL of these directives:",
-        "",
-    ]
-
-    for i, rule in enumerate(rules, 1):
-        parts.append(f"{i}. {rule}")
-
-    parts.append("")
-    parts.append("Your response will be REJECTED if it violates any directive above.")
-    parts.append("Do NOT include any commentary about how you handled directives - just follow them.")
-    return "\n".join(parts)
-
-
-def build_system_prompt_for_tools(
-    bank_profile: dict[str, Any],
-    context: str | None = None,
-    directives: list[dict[str, Any]] | None = None,
-) -> str:
-    """
-    Build the system prompt for tool-calling reflect agent.
-
-    This is a simplified prompt since tools are defined separately via the tools parameter.
-
-    Args:
-        bank_profile: Bank profile with name and mission
-        context: Optional additional context
-        directives: Optional list of directive mental models to inject as hard rules
-    """
-    name = bank_profile.get("name", "Assistant")
-    mission = bank_profile.get("mission", "")
-
-    no_info_rule = (
-        "- Only say 'I don't have information' AFTER trying list_mental_models AND recall with no relevant results"
-    )
-
-    parts = []
-
-    # Inject directives at the VERY START for maximum prominence
-    if directives:
-        parts.append(build_directives_section(directives))
-
-    parts.extend(
-        [
-            "You are a reflection agent that answers questions by reasoning over retrieved memories.",
-            "",
-        ]
-    )
-
-    parts.extend(
-        [
-            "## CRITICAL RULES",
-            "- You must NEVER fabricate information that has no basis in retrieved data",
-            "- You SHOULD synthesize, infer, and reason from the retrieved memories",
-            "- You MUST call recall() before saying you don't have information",
-            no_info_rule,
-            "",
-            "## How to Reason",
-            "- If memories mention someone did an activity, you can infer they likely enjoyed it",
-            "- Synthesize a coherent narrative from related memories",
-            "- Be a thoughtful interpreter, not just a literal repeater",
-            "- When the exact answer isn't stated, use what IS stated to give the best answer",
-            "",
-            "## Query Strategy (IMPORTANT)",
-            "recall() uses semantic search. NEVER just echo the user's question - decompose it into targeted searches:",
-            "",
-            "BAD: User asks 'recurring lesson themes between students' → recall('recurring lesson themes between students')",
-            "GOOD: Break it down into component searches:",
-            "  1. recall('lessons') - find all lesson-related memories",
-            "  2. recall('teaching sessions') - alternative phrasing",
-            "  3. recall('student progress') - find student-related memories",
-            "  4. recall('topics taught') - find subject matter",
-            "",
-            "Think: What ENTITIES and CONCEPTS does this question involve? Search for each separately.",
-            "- Questions about patterns → search for the individual instances first",
-            "- Questions comparing things → search for each thing separately",
-            "- Questions about relationships → search for each party involved",
-            "",
-            "## Workflow",
-        ]
-    )
-
-    # Answer mode: include mental model lookup in workflow
-    parts.extend(
-        [
-            "1. Review the pre-fetched mental models for relevant synthesized knowledge",
-            "2. If relevant, call get_mental_model(model_id) for full observations",
-            "3. DECOMPOSE the question into component searches (see Query Strategy above)",
-            "   - Identify entities and concepts in the question",
-            "   - Search for each separately with targeted queries",
-            "4. Run multiple recall() calls - don't just echo the user's question",
-            "5. Use expand() if you need more context on specific memories",
-            "6. BEFORE answering: Check if any person/project/concept from the memories deserves a mental model - use learn() if so",
-            "7. When ready, call done() with your answer and supporting memory_ids",
-            "",
-            "## When to Use learn() - IMPORTANT",
-            "ACTIVELY look for opportunities to use learn() when you discover:",
-            "- A person mentioned in 2+ memories who has no mental model yet",
-            "- A project or concept the user asks about that has no mental model",
-            "- A pattern or topic worth tracking for future questions",
-            "",
-            "DO NOT wait to be asked - proactively create models when you see the need.",
-            "Example: learn(name='Project Alpha', description='Track goals, status, and key decisions for Project Alpha')",
-            "",
-            "## Output Format: Plain Text Answer",
-            "Call done() with a plain text 'answer' field.",
-            "- Do NOT use markdown formatting",
-            "- NEVER include memory IDs, UUIDs, or 'Memory references' in the answer text",
-            "- Put memory IDs ONLY in the memory_ids array parameter, not in the answer",
-        ]
-    )
-
-    parts.append("")
-    parts.append(f"## Memory Bank: {name}")
-
-    if mission:
-        parts.append(f"Mission: {mission}")
-
-    # Disposition traits
-    disposition = bank_profile.get("disposition", {})
-    if disposition:
-        traits = []
-        if "skepticism" in disposition:
-            traits.append(f"skepticism={disposition['skepticism']}")
-        if "literalism" in disposition:
-            traits.append(f"literalism={disposition['literalism']}")
-        if "empathy" in disposition:
-            traits.append(f"empathy={disposition['empathy']}")
-        if traits:
-            parts.append(f"Disposition: {', '.join(traits)}")
-
-    if context:
-        parts.append(f"\n## Additional Context\n{context}")
-
-    # Add directive reminder at the END for recency effect
-    if directives:
-        parts.append(build_directives_reminder(directives))
-
-    return "\n".join(parts)
-
-
-def build_agent_prompt(
-    query: str,
-    context_history: list[dict],
-    bank_profile: dict,
-    additional_context: str | None = None,
-) -> str:
-    """Build the user prompt for the reflect agent."""
-    parts = []
-
-    # Bank identity
-    name = bank_profile.get("name", "Assistant")
-    mission = bank_profile.get("mission", "")
-
-    parts.append(f"## Memory Bank Context\nName: {name}")
-    if mission:
-        parts.append(f"Mission: {mission}")
-
-    # Disposition traits if present
-    disposition = bank_profile.get("disposition", {})
-    if disposition:
-        traits = []
-        if "skepticism" in disposition:
-            traits.append(f"skepticism={disposition['skepticism']}")
-        if "literalism" in disposition:
-            traits.append(f"literalism={disposition['literalism']}")
-        if "empathy" in disposition:
-            traits.append(f"empathy={disposition['empathy']}")
-        if traits:
-            parts.append(f"Disposition: {', '.join(traits)}")
-
-    # Additional context from caller
-    if additional_context:
-        parts.append(f"\n## Additional Context\n{additional_context}")
-
-    # Tool call history
-    if context_history:
-        parts.append("\n## Tool Results (synthesize and reason from this data)")
-        for i, entry in enumerate(context_history, 1):
-            tool = entry["tool"]
-            output = entry["output"]
-            # Format as proper JSON for LLM readability
-            try:
-                output_str = json.dumps(output, indent=2, default=str)
-            except (TypeError, ValueError):
-                output_str = str(output)
-            parts.append(f"\n### Call {i}: {tool}\n```json\n{output_str}\n```")
-
-    # The question
-    parts.append(f"\n## Question\n{query}")
-
-    # Instructions
-    if context_history:
-        parts.append(
-            "\n## Instructions\n"
-            "Based on the tool results above, either call more tools or provide your final answer. "
-            "Synthesize and reason from the data - make reasonable inferences when helpful. "
-            "If you have related information, use it to give the best possible answer."
-        )
-    else:
-        parts.append(
-            "\n## Instructions\n"
-            "Start by calling list_mental_models() to see available mental models - they contain pre-synthesized knowledge. "
-            "If a relevant model exists, use get_mental_model(model_id) to get its observations. "
-            "Then use recall(query) for specific details not covered by mental models."
-        )
-
-    return "\n".join(parts)
-
-
-def build_final_prompt(
-    query: str,
-    context_history: list[dict],
-    bank_profile: dict,
-    additional_context: str | None = None,
-) -> str:
-    """Build the final prompt when forcing a text response (no tools)."""
-    parts = []
-
-    # Bank identity
-    name = bank_profile.get("name", "Assistant")
-    mission = bank_profile.get("mission", "")
-
-    parts.append(f"## Memory Bank Context\nName: {name}")
-    if mission:
-        parts.append(f"Mission: {mission}")
-
-    # Disposition traits if present
-    disposition = bank_profile.get("disposition", {})
-    if disposition:
-        traits = []
-        if "skepticism" in disposition:
-            traits.append(f"skepticism={disposition['skepticism']}")
-        if "literalism" in disposition:
-            traits.append(f"literalism={disposition['literalism']}")
-        if "empathy" in disposition:
-            traits.append(f"empathy={disposition['empathy']}")
-        if traits:
-            parts.append(f"Disposition: {', '.join(traits)}")
-
-    # Additional context from caller
-    if additional_context:
-        parts.append(f"\n## Additional Context\n{additional_context}")
-
-    # Tool call history
-    if context_history:
-        parts.append("\n## Retrieved Data (synthesize and reason from this data)")
-        for entry in context_history:
-            tool = entry["tool"]
-            output = entry["output"]
-            # Format as proper JSON for LLM readability
-            try:
-                output_str = json.dumps(output, indent=2, default=str)
-            except (TypeError, ValueError):
-                output_str = str(output)
-            parts.append(f"\n### From {tool}:\n```json\n{output_str}\n```")
-    else:
-        parts.append("\n## Retrieved Data\nNo data was retrieved.")
-
-    # The question
-    parts.append(f"\n## Question\n{query}")
-
-    # Final instructions
-    parts.append(
-        "\n## Instructions\n"
-        "Provide a thoughtful answer by synthesizing and reasoning from the retrieved data above. "
-        "You can make reasonable inferences from the memories, but don't completely fabricate information."
-        "If the exact answer isn't stated, use what IS stated to give the best possible answer. "
-        "Only say 'I don't have information' if the retrieved data is truly unrelated to the question."
-    )
-
-    return "\n".join(parts)
-
-
-FINAL_SYSTEM_PROMPT = """You are a thoughtful assistant that synthesizes answers from retrieved memories.
-
-Your approach:
-- Reason over the retrieved memories to answer the question
-- Make reasonable inferences when the exact answer isn't explicitly stated
-- Connect related memories to form a complete picture
-- Be helpful - if you have related information, use it to give the best possible answer
-
-Only say "I don't have information" if the retrieved data is truly unrelated to the question.
-Do NOT fabricate information that has no basis in the retrieved data."""
-
-
-# =============================================================================
-# 4-Phase Mental Model Reflect Prompts
-# =============================================================================
-
-SEED_PHASE_SYSTEM_PROMPT = """You are analyzing memories to discover NEW patterns and generate candidate observations.
-
-Your task is to identify potential observations (beliefs, preferences, patterns, behaviors) that could be part of a mental model about this person/topic.
-
-## Important: Avoid Redundancy
-If existing observations are provided, DO NOT generate candidates that are essentially the same.
-Focus on discovering NEW patterns not already covered by existing observations.
-
-## Rules
-- Generate 5-15 candidate observations for NEW patterns only
-- Each candidate should be specific and testable (can be supported or contradicted by evidence)
-- Note which memory IDs inspired each candidate (these are seeds, not final evidence)
-- Focus on patterns that appear MULTIPLE TIMES across many memories - the more the better
-- The best candidates are ones you can find 10, 20, or even 50+ supporting memories for
-- Skip patterns that are already covered by existing observations
-
-## Output Format
-Return a JSON array of candidate observations:
-```json
-{
-  "candidates": [
-    {
-      "content": "The specific observation/belief/pattern - be detailed and specific",
-      "seed_memory_ids": ["memory_id_1", "memory_id_2", "memory_id_3"]
-    }
-  ]
-}
-```
-
-Focus on patterns that appear multiple times or have strong signals. Don't generate obvious or trivial observations.
-Prefer candidates with MORE seed memories - they're more likely to be real patterns.
-Return an empty candidates array if no genuinely new patterns are found."""
-
-
-def build_seed_phase_prompt(
-    memories: list[dict],
-    topic: str | None = None,
-    existing_observations: list[dict] | None = None,
-) -> str:
-    """Build the user prompt for the seed phase.
-
-    Args:
-        memories: List of memories to analyze
-        topic: Optional topic focus for the mental model
-        existing_observations: Optional list of existing observations to avoid rediscovering
-    """
-    parts = []
-
-    if topic:
-        parts.append(f"## Topic Focus\n{topic}\n")
-
-    # Include existing observations so we don't rediscover them
-    if existing_observations:
-        parts.append("## Existing Observations (DO NOT regenerate these)")
-        parts.append("These patterns are already tracked. Focus on discovering NEW patterns:\n")
-        for i, obs in enumerate(existing_observations, 1):
-            title = obs.get("title", "")
-            content = obs.get("content", "")
-            parts.append(f"{i}. **{title}**: {content}\n")
-        parts.append("")
-
-    parts.append("## Memories to Analyze")
-    parts.append("Review these memories and identify patterns, preferences, beliefs, and behaviors:\n")
-
-    for mem in memories:
-        mem_id = mem.get("id", "unknown")
-        content = mem.get("content", mem.get("text", ""))
-        timestamp = mem.get("timestamp", mem.get("created_at", ""))
-        parts.append(f"[{mem_id}] ({timestamp}): {content}\n")
-
-    parts.append("\n## Instructions")
-    if existing_observations:
-        parts.append("Generate candidate observations for NEW patterns not already covered above.")
-        parts.append("If all patterns are already covered by existing observations, return an empty candidates array.")
-    else:
-        parts.append("Generate candidate observations based on patterns you see in these memories.")
-    parts.append("Look for: recurring themes, stated preferences, behavioral patterns, beliefs, values, goals.")
-
-    return "\n".join(parts)
-
-
-VALIDATE_PHASE_SYSTEM_PROMPT = """You are validating candidate observations against evidence.
-
-For each candidate, you have:
-- Supporting memories (evidence FOR the observation)
-- Contradicting memories (evidence AGAINST the observation)
-
-## Your Task
-1. Evaluate each candidate based on the evidence
-2. For valid candidates, extract EXACT QUOTES from supporting memories
-3. Discard candidates with insufficient or contradicting evidence
-4. Merge similar candidates into single, refined observations
-
-## Rules for Quotes
-- Quotes must be EXACT text from the memory, not paraphrased
-- Each quote should directly support the observation
-- The MORE evidence quotes, the BETTER - don't limit yourself, include ALL relevant quotes (10, 20, 50+)
-- Observations with only 1-2 quotes are weak and should be discarded unless the evidence is exceptionally strong
-- Stronger observations have more supporting evidence - aim for comprehensive coverage
-
-## Output Format
-Return validated observations with evidence:
-```json
-{
-  "observations": [
-    {
-      "title": "Short descriptive title (3-8 words) - like a headline",
-      "content": "The full observation content - detailed explanation of the pattern/belief",
-      "evidence": [
-        {
-          "memory_id": "exact_memory_id",
-          "quote": "Exact quote from the memory text",
-          "relevance": "Brief explanation of how this supports the observation",
-          "timestamp": "2024-01-15T10:00:00Z"
-        }
-      ]
-    }
-  ],
-  "discarded": [
-    {
-      "content": "The discarded candidate",
-      "reason": "Why it was discarded (insufficient evidence, contradicted, etc.)"
-    }
-  ],
-  "merged": [
-    {
-      "from": ["candidate 1 content", "candidate 2 content"],
-      "into": "The merged observation content"
-    }
-  ]
-}
-```
-
-## Title Guidelines
-- Title should be a SHORT label (like "Prefers morning meetings" or "Coffee enthusiast")
-- NOT a truncated version of the content
-- Think of it as a category/tag for the observation
-
-Be rigorous: only keep observations with clear, verifiable evidence from multiple memories."""
-
-
-def build_validate_phase_prompt(candidates_with_evidence: list[dict]) -> str:
-    """Build the user prompt for the validate phase."""
-    parts = ["## Candidates to Validate\n"]
-
-    for i, item in enumerate(candidates_with_evidence, 1):
-        candidate = item.get("candidate", {})
-        supporting = item.get("supporting_memories", [])
-        contradicting = item.get("contradicting_memories", [])
-
-        parts.append(f"### Candidate {i}: {candidate.get('content', '')}")
-
-        if supporting:
-            parts.append("\n**Supporting Evidence:**")
-            for mem in supporting:
-                mem_id = mem.get("id", "unknown")
-                content = mem.get("content", mem.get("text", ""))
-                timestamp = mem.get("timestamp", mem.get("created_at", ""))
-                parts.append(f"- [{mem_id}] ({timestamp}): {content}")
-
-        if contradicting:
-            parts.append("\n**Contradicting Evidence:**")
-            for mem in contradicting:
-                mem_id = mem.get("id", "unknown")
-                content = mem.get("content", mem.get("text", ""))
-                timestamp = mem.get("timestamp", mem.get("created_at", ""))
-                parts.append(f"- [{mem_id}] ({timestamp}): {content}")
-
-        if not supporting and not contradicting:
-            parts.append("\n*No additional evidence found*")
-
-        parts.append("")
-
-    parts.append("## Instructions")
-    parts.append("1. Evaluate each candidate based on its evidence")
-    parts.append("2. Keep candidates with strong supporting evidence")
-    parts.append("3. Discard candidates with no evidence or strong contradictions")
-    parts.append("4. Merge similar candidates")
-    parts.append("5. Extract EXACT quotes (copy-paste from memory text) for evidence")
-
-    return "\n".join(parts)
-
-
-COMPARE_PHASE_SYSTEM_PROMPT = """You are merging new observations with an existing mental model.
-
-You have:
-- EXISTING observations (from the current mental model)
-- NEW observations (from this reflect cycle)
-
-## Your Task
-Produce the final, complete mental model by:
-1. Keeping existing observations that are still valid
-2. Updating existing observations with new evidence (ADD new evidence to existing)
-3. Adding new observations that don't overlap with existing
-4. Removing existing observations that are contradicted by new evidence
-5. Merging overlapping observations
-
-## Rules
-- The final model should have no contradictions
-- Each observation must have evidence with exact quotes
-- COMBINE evidence from both existing and new observations
-- If an existing observation has new supporting evidence, ADD ALL the new evidence to it
-- Include ALL relevant evidence - the more quotes the better (10, 20, 50+ is great)
-- Observations with more evidence are more reliable - don't limit the number of quotes
-
-## Output Format
-Return the complete, final mental model:
-```json
-{
-  "observations": [
-    {
-      "title": "Short descriptive title (3-8 words)",
-      "content": "Full observation content - detailed explanation",
-      "evidence": [
-        {
-          "memory_id": "id",
-          "quote": "exact quote",
-          "relevance": "explanation",
-          "timestamp": "ISO timestamp"
-        }
-      ],
-      "created_at": "ISO timestamp of when observation was first created"
-    }
-  ],
-  "changes": {
-    "kept": ["Observation that was kept unchanged"],
-    "updated": [{"from": "old content", "to": "new content", "reason": "why"}],
-    "added": ["New observation that was added"],
-    "removed": [{"content": "removed observation", "reason": "why removed"}],
-    "merged": [{"from": ["obs1", "obs2"], "into": "merged observation"}]
-  }
-}
-```"""
-
-
-def build_compare_phase_prompt(
-    existing_observations: list[dict],
-    new_observations: list[dict],
-) -> str:
-    """Build the user prompt for the compare phase."""
-    parts = []
-
-    parts.append("## Existing Mental Model Observations")
-    if existing_observations:
-        for i, obs in enumerate(existing_observations, 1):
-            title = obs.get("title", "")
-            content = obs.get("content", obs.get("text", ""))
-            evidence = obs.get("evidence", [])
-            parts.append(f"\n### Existing {i}: {title}")
-            parts.append(f"Content: {content}")
-            if evidence:
-                parts.append(f"Evidence ({len(evidence)} items):")
-                for ev in evidence[:5]:  # Show max 5 evidence items
-                    parts.append(f'  - [{ev.get("memory_id", "?")}]: "{ev.get("quote", "")}"')
-                if len(evidence) > 5:
-                    parts.append(f"  ... and {len(evidence) - 5} more")
-    else:
-        parts.append("*No existing observations*")
-
-    parts.append("\n## New Observations from This Reflect")
-    if new_observations:
-        for i, obs in enumerate(new_observations, 1):
-            title = obs.get("title", "")
-            content = obs.get("content", "")
-            evidence = obs.get("evidence", [])
-            parts.append(f"\n### New {i}: {title}")
-            parts.append(f"Content: {content}")
-            if evidence:
-                parts.append(f"Evidence ({len(evidence)} items):")
-                for ev in evidence:
-                    parts.append(f'  - [{ev.get("memory_id", "?")}]: "{ev.get("quote", "")}"')
-    else:
-        parts.append("*No new observations*")
-
-    parts.append("\n## Instructions")
-    parts.append("Merge these into a coherent, non-contradictory mental model.")
-    parts.append("Preserve all valid evidence. Remove stale or contradicted observations.")
-
-    return "\n".join(parts)
-
-
-# =============================================================================
-# UPDATE EXISTING Phase Prompts (for diff-based refresh)
-# =============================================================================
-
-UPDATE_EXISTING_SYSTEM_PROMPT = """You are updating existing observations with newly found evidence.
-
-For each existing observation, you have been given:
-- The original observation (title, content, existing evidence)
-- Newly found supporting memories
-- Newly found contradicting memories
-
-## Your Task
-1. Extract EXACT QUOTES from new supporting memories to add to the observation
-2. Flag observations with strong contradicting evidence for potential removal
-3. Keep existing evidence intact - only ADD new evidence
-
-## Rules for Quotes
-- Quotes must be EXACT text from the memory, not paraphrased
-- Each quote should directly support the observation
-- Include ALL relevant quotes from the new memories
-
-## Output Format
-Return updated observations with new evidence:
-```json
-{
-  "updated_observations": [
-    {
-      "title": "Original title",
-      "content": "Original content",
-      "existing_evidence_count": 5,
-      "new_evidence": [
-        {
-          "memory_id": "exact_memory_id",
-          "quote": "Exact quote from the memory text",
-          "relevance": "Brief explanation of how this supports the observation",
-          "timestamp": "2024-01-15T10:00:00Z"
-        }
-      ],
-      "has_contradiction": false,
-      "contradiction_note": null
-    }
-  ]
-}
-```
-
-If an observation has strong contradicting evidence, set has_contradiction=true and explain in contradiction_note."""
-
-
-def build_update_existing_prompt(observations_with_evidence: list[dict]) -> str:
-    """Build the user prompt for the update existing phase.
-
-    Args:
-        observations_with_evidence: List of existing observations with new evidence found
-    """
-    parts = ["## Existing Observations to Update\n"]
-
-    for i, item in enumerate(observations_with_evidence, 1):
-        obs = item.get("observation", {})
-        supporting = item.get("supporting_memories", [])
-        contradicting = item.get("contradicting_memories", [])
-
-        title = obs.get("title", "")
-        content = obs.get("content", "")
-        existing_evidence = obs.get("evidence", [])
-
-        parts.append(f"### Observation {i}: {title}")
-        parts.append(f"Content: {content}")
-        parts.append(f"Existing evidence count: {len(existing_evidence)}")
-
-        if supporting:
-            parts.append("\n**New Supporting Memories:**")
-            for mem in supporting:
-                mem_id = mem.get("id", "unknown")
-                mem_content = mem.get("content", mem.get("text", ""))
-                timestamp = mem.get("timestamp", mem.get("created_at", ""))
-                parts.append(f"- [{mem_id}] ({timestamp}): {mem_content}")
-
-        if contradicting:
-            parts.append("\n**New Contradicting Memories:**")
-            for mem in contradicting:
-                mem_id = mem.get("id", "unknown")
-                mem_content = mem.get("content", mem.get("text", ""))
-                timestamp = mem.get("timestamp", mem.get("created_at", ""))
-                parts.append(f"- [{mem_id}] ({timestamp}): {mem_content}")
-
-        if not supporting and not contradicting:
-            parts.append("\n*No new evidence found*")
-
-        parts.append("")
-
-    parts.append("## Instructions")
-    parts.append("1. Extract EXACT quotes from new supporting memories")
-    parts.append("2. Flag observations with strong contradictions")
-    parts.append("3. Return the updated observations with new evidence added")
-
-    return "\n".join(parts)

hindsight-api/hindsight_api/engine/reflect/tools.py

@@ -1,450 +0,0 @@
-"""
-Tool implementations for the reflect agent.
-"""
-
-import logging
-import re
-import uuid
-from datetime import datetime, timezone
-from typing import TYPE_CHECKING, Any
-
-from .models import MentalModelInput
-from .observations import Observation, ObservationEvidence, Trend
-
-if TYPE_CHECKING:
-    from asyncpg import Connection
-
-    from ...api.http import RequestContext
-    from ..memory_engine import MemoryEngine
-
-logger = logging.getLogger(__name__)
-
-
-def generate_model_id(name: str) -> str:
-    """Generate a stable ID from mental model name."""
-    # Normalize: lowercase, replace spaces/special chars with hyphens
-    normalized = re.sub(r"[^a-z0-9]+", "-", name.lower()).strip("-")
-    # Truncate to reasonable length
-    return normalized[:50]
-
-
-def _parse_observations(observations_raw: list) -> list[Observation]:
-    """Parse raw observation dicts into typed Observation models."""
-    observations: list[Observation] = []
-    for obs in observations_raw:
-        if not isinstance(obs, dict):
-            continue
-
-        try:
-            parsed = Observation(
-                title=obs.get("title", ""),
-                content=obs.get("content", ""),
-                evidence=[
-                    ObservationEvidence(
-                        memory_id=ev.get("memory_id", ""),
-                        quote=ev.get("quote", ""),
-                        relevance=ev.get("relevance", ""),
-                        timestamp=ev.get("timestamp"),
-                    )
-                    for ev in obs.get("evidence", [])
-                    if isinstance(ev, dict)
-                ],
-                created_at=obs.get("created_at"),
-            )
-            observations.append(parsed)
-        except Exception as e:
-            logger.warning(f"Failed to parse observation: {e}")
-            continue
-
-    return observations
-
-
-async def tool_lookup(
-    conn: "Connection",
-    bank_id: str,
-    model_id: str | None = None,
-    tags: list[str] | None = None,
-    tags_match: str = "any",
-) -> dict[str, Any]:
-    """
-    List or get mental models.
-
-    Args:
-        conn: Database connection
-        bank_id: Bank identifier
-        model_id: Optional specific model ID to get (if None, lists all)
-        tags: Optional tags to filter models (when listing)
-        tags_match: How to match tags - "any" (OR), "all" (AND)
-
-    Returns:
-        Dict with either a list of models or a single model's details
-    """
-    if model_id:
-        # Get specific mental model with full details including observations
-        row = await conn.fetchrow(
-            """
-            SELECT id, subtype, name, description, observations, entity_id, last_updated
-            FROM mental_models
-            WHERE id = $1 AND bank_id = $2
-            """,
-            model_id,
-            bank_id,
-        )
-        if row:
-            # Parse observations JSON
-            obs_data = row["observations"] or {"observations": []}
-            if isinstance(obs_data, str):
-                import json
-
-                obs_data = json.loads(obs_data)
-            observations_raw = obs_data.get("observations", []) if isinstance(obs_data, dict) else obs_data
-
-            # Parse observations into typed models
-            observations = _parse_observations(observations_raw)
-
-            return {
-                "found": True,
-                "model": {
-                    "id": row["id"],
-                    "subtype": row["subtype"],
-                    "name": row["name"],
-                    "description": row["description"],
-                    "observations": observations,
-                    "entity_id": str(row["entity_id"]) if row["entity_id"] else None,
-                    "last_updated": row["last_updated"].isoformat() if row["last_updated"] else None,
-                },
-            }
-        return {"found": False, "model_id": model_id}
-    else:
-        # List mental models (compact: id, name, description only)
-        # Full observations are retrieved via get_mental_model(model_id)
-        # NOTE: Directives (subtype='directive') are excluded from listing -
-        # they are injected into the system prompt, not discoverable via tools
-        # Filter by tags if provided
-        if tags:
-            if tags_match == "all":
-                # All tags must match
-                rows = await conn.fetch(
-                    """
-                    SELECT id, subtype, name, description
-                    FROM mental_models
-                    WHERE bank_id = $1 AND tags @> $2::varchar[] AND subtype != 'directive'
-                    ORDER BY last_updated DESC NULLS LAST, created_at DESC
-                    """,
-                    bank_id,
-                    tags,
-                )
-            else:
-                # Any tag matches (OR) - default
-                rows = await conn.fetch(
-                    """
-                    SELECT id, subtype, name, description
-                    FROM mental_models
-                    WHERE bank_id = $1 AND tags && $2::varchar[] AND subtype != 'directive'
-                    ORDER BY last_updated DESC NULLS LAST, created_at DESC
-                    """,
-                    bank_id,
-                    tags,
-                )
-        else:
-            rows = await conn.fetch(
-                """
-                SELECT id, subtype, name, description
-                FROM mental_models
-                WHERE bank_id = $1 AND subtype != 'directive'
-                ORDER BY last_updated DESC NULLS LAST, created_at DESC
-                """,
-                bank_id,
-            )
-
-        return {
-            "count": len(rows),
-            "models": [
-                {
-                    "id": row["id"],
-                    "subtype": row["subtype"],
-                    "name": row["name"],
-                    "description": row["description"],
-                }
-                for row in rows
-            ],
-        }
-
-
-async def tool_recall(
-    memory_engine: "MemoryEngine",
-    bank_id: str,
-    query: str,
-    request_context: "RequestContext",
-    max_tokens: int = 2048,
-    max_results: int = 50,
-    tags: list[str] | None = None,
-    tags_match: str = "any",
-    connection_budget: int = 1,
-) -> dict[str, Any]:
-    """
-    Search memories using TEMPR retrieval.
-
-    Args:
-        memory_engine: Memory engine instance
-        bank_id: Bank identifier
-        query: Search query
-        request_context: Request context for authentication
-        max_tokens: Maximum tokens for results (default 2048)
-        max_results: Maximum number of results
-        tags: Filter by tags (includes untagged memories)
-        tags_match: How to match tags - "any" (OR), "all" (AND), or "exact"
-        connection_budget: Max DB connections for this recall (default 1 for internal ops)
-
-    Returns:
-        Dict with list of matching memories
-    """
-    result = await memory_engine.recall_async(
-        bank_id=bank_id,
-        query=query,
-        fact_type=["experience", "world"],  # Exclude opinions
-        max_tokens=max_tokens,
-        enable_trace=False,
-        request_context=request_context,
-        tags=tags,
-        tags_match=tags_match,
-        _connection_budget=connection_budget,
-    )
-
-    memories = []
-    for m in result.results[:max_results]:
-        memories.append(
-            {
-                "id": str(m.id),
-                "text": m.text,
-                "type": m.fact_type,
-                "entities": m.entities or [],
-                "occurred": m.occurred_start,  # Already ISO format string
-            }
-        )
-
-    return {
-        "query": query,
-        "count": len(memories),
-        "memories": memories,
-    }
-
-
-async def tool_learn(
-    conn: "Connection",
-    bank_id: str,
-    input: MentalModelInput,
-    tags: list[str] | None = None,
-) -> dict[str, Any]:
-    """
-    Create a mental model placeholder with subtype='learned'.
-
-    The agent only specifies name and description - actual observations are generated
-    in the background via refresh, similar to pinned models.
-
-    Args:
-        conn: Database connection
-        bank_id: Bank identifier
-        input: Mental model input data (name, description, optional entity_id)
-        tags: Tags to apply to new mental models (from reflect context)
-
-    Returns:
-        Dict with created model info including model_id for background generation
-    """
-    model_id = generate_model_id(input.name)
-
-    # Parse entity_id if provided
-    entity_uuid = None
-    if input.entity_id:
-        try:
-            entity_uuid = uuid.UUID(input.entity_id)
-        except ValueError:
-            logger.warning(f"Invalid entity_id format: {input.entity_id}")
-
-    # Check if model exists
-    existing = await conn.fetchrow(
-        "SELECT id FROM mental_models WHERE id = $1 AND bank_id = $2",
-        model_id,
-        bank_id,
-    )
-
-    if existing:
-        # Update description only - observations will be regenerated
-        await conn.execute(
-            """
-            UPDATE mental_models SET
-                description = $3,
-                entity_id = $4
-            WHERE id = $1 AND bank_id = $2
-            """,
-            model_id,
-            bank_id,
-            input.description,
-            entity_uuid,
-        )
-        status = "updated"
-    else:
-        # Insert new model placeholder - observations will be generated in background
-        await conn.execute(
-            """
-            INSERT INTO mental_models (id, bank_id, subtype, name, description, observations, entity_id, tags, created_at)
-            VALUES ($1, $2, 'learned', $3, $4, '{}'::jsonb, $5, $6, NOW())
-            """,
-            model_id,
-            bank_id,
-            input.name,
-            input.description,
-            entity_uuid,
-            tags or [],
-        )
-        status = "created"
-
-    logger.info(f"[REFLECT] Mental model '{model_id}' {status} in bank {bank_id} - pending background generation")
-
-    return {
-        "status": status,
-        "model_id": model_id,
-        "name": input.name,
-        "pending_generation": True,
-    }
-
-
-async def tool_expand(
-    conn: "Connection",
-    bank_id: str,
-    memory_ids: list[str],
-    depth: str,
-) -> dict[str, Any]:
-    """
-    Expand multiple memories to get chunk or document context.
-
-    Args:
-        conn: Database connection
-        bank_id: Bank identifier
-        memory_ids: List of memory unit IDs
-        depth: "chunk" or "document"
-
-    Returns:
-        Dict with results array, each containing memory, chunk, and optionally document data
-    """
-    if not memory_ids:
-        return {"error": "memory_ids is required and must not be empty"}
-
-    # Validate and convert UUIDs
-    valid_uuids: list[uuid.UUID] = []
-    errors: dict[str, str] = {}
-    for mid in memory_ids:
-        try:
-            valid_uuids.append(uuid.UUID(mid))
-        except ValueError:
-            errors[mid] = f"Invalid memory_id format: {mid}"
-
-    if not valid_uuids:
-        return {"error": "No valid memory IDs provided", "details": errors}
-
-    # Batch fetch all memory units
-    memories = await conn.fetch(
-        """
-        SELECT id, text, chunk_id, document_id, fact_type, context
-        FROM memory_units
-        WHERE id = ANY($1) AND bank_id = $2
-        """,
-        valid_uuids,
-        bank_id,
-    )
-    memory_map = {row["id"]: row for row in memories}
-
-    # Collect chunk_ids and document_ids for batch fetching
-    chunk_ids = [m["chunk_id"] for m in memories if m["chunk_id"]]
-    doc_ids_from_chunks: set[str] = set()
-    doc_ids_direct: set[str] = set()
-
-    # Batch fetch all chunks
-    chunk_map: dict[str, Any] = {}
-    if chunk_ids:
-        chunks = await conn.fetch(
-            """
-            SELECT chunk_id, chunk_text, chunk_index, document_id
-            FROM chunks
-            WHERE chunk_id = ANY($1)
-            """,
-            chunk_ids,
-        )
-        chunk_map = {row["chunk_id"]: row for row in chunks}
-        if depth == "document":
-            doc_ids_from_chunks = {c["document_id"] for c in chunks if c["document_id"]}
-
-    # Collect direct document IDs (memories without chunks)
-    if depth == "document":
-        for m in memories:
-            if not m["chunk_id"] and m["document_id"]:
-                doc_ids_direct.add(m["document_id"])
-
-    # Batch fetch all documents
-    doc_map: dict[str, Any] = {}
-    all_doc_ids = list(doc_ids_from_chunks | doc_ids_direct)
-    if all_doc_ids:
-        docs = await conn.fetch(
-            """
-            SELECT id, original_text, metadata, retain_params
-            FROM documents
-            WHERE id = ANY($1) AND bank_id = $2
-            """,
-            all_doc_ids,
-            bank_id,
-        )
-        doc_map = {row["id"]: row for row in docs}
-
-    # Build results
-    results: list[dict[str, Any]] = []
-    for mid, mem_uuid in zip(memory_ids, valid_uuids):
-        if mid in errors:
-            results.append({"memory_id": mid, "error": errors[mid]})
-            continue
-
-        memory = memory_map.get(mem_uuid)
-        if not memory:
-            results.append({"memory_id": mid, "error": f"Memory not found: {mid}"})
-            continue
-
-        item: dict[str, Any] = {
-            "memory_id": mid,
-            "memory": {
-                "id": str(memory["id"]),
-                "text": memory["text"],
-                "type": memory["fact_type"],
-                "context": memory["context"],
-            },
-        }
-
-        # Add chunk if available
-        if memory["chunk_id"] and memory["chunk_id"] in chunk_map:
-            chunk = chunk_map[memory["chunk_id"]]
-            item["chunk"] = {
-                "id": chunk["chunk_id"],
-                "text": chunk["chunk_text"],
-                "index": chunk["chunk_index"],
-                "document_id": chunk["document_id"],
-            }
-            # Add document if depth=document
-            if depth == "document" and chunk["document_id"] in doc_map:
-                doc = doc_map[chunk["document_id"]]
-                item["document"] = {
-                    "id": doc["id"],
-                    "full_text": doc["original_text"],
-                    "metadata": doc["metadata"],
-                    "retain_params": doc["retain_params"],
-                }
-        elif memory["document_id"] and depth == "document" and memory["document_id"] in doc_map:
-            # No chunk, but has document_id
-            doc = doc_map[memory["document_id"]]
-            item["document"] = {
-                "id": doc["id"],
-                "full_text": doc["original_text"],
-                "metadata": doc["metadata"],
-                "retain_params": doc["retain_params"],
-            }
-
-        results.append(item)
-
-    return {"results": results, "count": len(results)}

hindsight-api/hindsight_api/engine/reflect/tools_schema.py

@@ -1,218 +0,0 @@
-"""
-Tool schema definitions for the reflect agent.
-
-These are OpenAI-format tool definitions used with native tool calling.
-"""
-
-# Tool definitions in OpenAI format
-TOOL_LIST_MENTAL_MODELS = {
-    "type": "function",
-    "function": {
-        "name": "list_mental_models",
-        "description": "List all available mental models - your synthesized knowledge about entities, concepts, and events. Returns an array of models with id, name, and description.",
-        "parameters": {
-            "type": "object",
-            "properties": {},
-            "required": [],
-        },
-    },
-}
-
-TOOL_GET_MENTAL_MODEL = {
-    "type": "function",
-    "function": {
-        "name": "get_mental_model",
-        "description": "Get full details of a specific mental model including all observations and memory references.",
-        "parameters": {
-            "type": "object",
-            "properties": {
-                "model_id": {
-                    "type": "string",
-                    "description": "ID of the mental model (from list_mental_models results)",
-                },
-            },
-            "required": ["model_id"],
-        },
-    },
-}
-
-TOOL_RECALL = {
-    "type": "function",
-    "function": {
-        "name": "recall",
-        "description": "Search memories using semantic + temporal retrieval. Returns relevant memories from experience and world knowledge, each with an 'id' you can reference.",
-        "parameters": {
-            "type": "object",
-            "properties": {
-                "query": {
-                    "type": "string",
-                    "description": "Search query string",
-                },
-                "max_tokens": {
-                    "type": "integer",
-                    "description": "Optional limit on result size (default 2048). Use higher values for broader searches.",
-                },
-            },
-            "required": ["query"],
-        },
-    },
-}
-
-TOOL_LEARN = {
-    "type": "function",
-    "function": {
-        "name": "learn",
-        "description": "Create a new mental model to track an important recurring topic. Use when you discover a person, project, concept, or pattern that appears frequently and would benefit from synthesized knowledge. The model content will be generated automatically.",
-        "parameters": {
-            "type": "object",
-            "properties": {
-                "name": {
-                    "type": "string",
-                    "description": "Human-readable name (e.g., 'Project Alpha', 'John Smith', 'Product Strategy')",
-                },
-                "description": {
-                    "type": "string",
-                    "description": "What to track and synthesize (e.g., 'Track goals, milestones, blockers, and key decisions for Project Alpha')",
-                },
-            },
-            "required": ["name", "description"],
-        },
-    },
-}
-
-TOOL_EXPAND = {
-    "type": "function",
-    "function": {
-        "name": "expand",
-        "description": "Get more context for one or more memories. Memory hierarchy: memory -> chunk -> document.",
-        "parameters": {
-            "type": "object",
-            "properties": {
-                "memory_ids": {
-                    "type": "array",
-                    "items": {"type": "string"},
-                    "description": "Array of memory IDs from recall results (batch multiple for efficiency)",
-                },
-                "depth": {
-                    "type": "string",
-                    "enum": ["chunk", "document"],
-                    "description": "chunk: surrounding text chunk, document: full source document",
-                },
-            },
-            "required": ["memory_ids", "depth"],
-        },
-    },
-}
-
-TOOL_DONE_ANSWER = {
-    "type": "function",
-    "function": {
-        "name": "done",
-        "description": "Signal completion with your final answer. Use this when you have gathered enough information to answer the question.",
-        "parameters": {
-            "type": "object",
-            "properties": {
-                "answer": {
-                    "type": "string",
-                    "description": "Your response as plain text. Do NOT use markdown formatting. NEVER include memory IDs, UUIDs, or 'Memory references' in this text - put IDs only in memory_ids array.",
-                },
-                "memory_ids": {
-                    "type": "array",
-                    "items": {"type": "string"},
-                    "description": "Array of memory IDs that support your answer (put IDs here, NOT in answer text)",
-                },
-                "model_ids": {
-                    "type": "array",
-                    "items": {"type": "string"},
-                    "description": "Array of mental model IDs that support your answer",
-                },
-            },
-            "required": ["answer"],
-        },
-    },
-}
-
-
-def _build_done_tool_with_directives(directive_rules: list[str]) -> dict:
-    """
-    Build the done tool schema with directive compliance field.
-
-    When directives are present, adds a required field that forces the agent
-    to confirm compliance with each directive before submitting.
-
-    Args:
-        directive_rules: List of directive rule strings
-    """
-    from typing import Any, cast
-
-    # Build rules list for description
-    rules_list = "\n".join(f"  {i + 1}. {rule}" for i, rule in enumerate(directive_rules))
-
-    # Build the tool with directive compliance field
-    return {
-        "type": "function",
-        "function": {
-            "name": "done",
-            "description": (
-                "Signal completion with your final answer. IMPORTANT: You must confirm directive compliance before submitting. "
-                "Your answer will be REJECTED if it violates any directive."
-            ),
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "answer": {
-                        "type": "string",
-                        "description": "Your response as plain text. Do NOT use markdown formatting. NEVER include memory IDs, UUIDs, or 'Memory references' in this text - put IDs only in memory_ids array.",
-                    },
-                    "memory_ids": {
-                        "type": "array",
-                        "items": {"type": "string"},
-                        "description": "Array of memory IDs that support your answer (put IDs here, NOT in answer text)",
-                    },
-                    "model_ids": {
-                        "type": "array",
-                        "items": {"type": "string"},
-                        "description": "Array of mental model IDs that support your answer",
-                    },
-                    "directive_compliance": {
-                        "type": "string",
-                        "description": f"REQUIRED: Confirm your answer complies with ALL directives. List each directive and how your answer follows it:\n{rules_list}\n\nFormat: 'Directive 1: [how answer complies]. Directive 2: [how answer complies]...'",
-                    },
-                },
-                "required": ["answer", "directive_compliance"],
-            },
-        },
-    }
-
-
-def get_reflect_tools(enable_learn: bool = True, directive_rules: list[str] | None = None) -> list[dict]:
-    """
-    Get the list of tools for the reflect agent.
-
-    Args:
-        enable_learn: Whether to include the learn tool
-        directive_rules: Optional list of directive rule strings. If provided,
-                        the done() tool will require directive compliance confirmation.
-
-    Returns:
-        List of tool definitions in OpenAI format
-    """
-    tools = []
-
-    # Include mental model tools for lookup
-    tools.append(TOOL_LIST_MENTAL_MODELS)
-    tools.append(TOOL_GET_MENTAL_MODEL)
-    tools.append(TOOL_RECALL)
-
-    if enable_learn:
-        tools.append(TOOL_LEARN)
-
-    tools.append(TOOL_EXPAND)
-
-    # Use directive-aware done tool if directives are present
-    if directive_rules:
-        tools.append(_build_done_tool_with_directives(directive_rules))
-    else:
-        tools.append(TOOL_DONE_ANSWER)
-
-    return tools

hindsight-api/hindsight_api/engine/response_models.py

@@ -10,60 +10,8 @@ from typing import Any
 
 from pydantic import BaseModel, ConfigDict, Field
 
-# Valid fact types for recall operations (excludes 'observation' which is internal, and 'opinion' which is deprecated)
-VALID_RECALL_FACT_TYPES = frozenset(["world", "experience"])
-
-
-class LLMToolCall(BaseModel):
-    """A tool call requested by the LLM."""
-
-    id: str = Field(description="Unique identifier for this tool call")
-    name: str = Field(description="Name of the tool to call")
-    arguments: dict[str, Any] = Field(description="Arguments to pass to the tool")
-
-
-class LLMToolCallResult(BaseModel):
-    """Result from an LLM call that may include tool calls."""
-
-    content: str | None = Field(default=None, description="Text content if any")
-    tool_calls: list[LLMToolCall] = Field(default_factory=list, description="Tool calls requested by the LLM")
-    finish_reason: str | None = Field(default=None, description="Reason the LLM stopped: 'stop', 'tool_calls', etc.")
-
-
-class ToolCallTrace(BaseModel):
-    """A single tool call made during reflect."""
-
-    tool: str = Field(description="Tool name: lookup, recall, learn, expand")
-    input: dict = Field(description="Tool input parameters")
-    output: dict = Field(description="Tool output/result")
-    duration_ms: int = Field(description="Execution time in milliseconds")
-    iteration: int = Field(default=0, description="Iteration number (1-based) when this tool was called")
-
-
-class LLMCallTrace(BaseModel):
-    """A single LLM call made during reflect."""
-
-    scope: str = Field(description="Call scope: agent_1, agent_2, final, etc.")
-    duration_ms: int = Field(description="Execution time in milliseconds")
-
-
-class MentalModelRef(BaseModel):
-    """Reference to a mental model accessed during reflect."""
-
-    id: str = Field(description="Mental model ID")
-    name: str = Field(description="Mental model name")
-    type: str = Field(description="Mental model type: entity, concept, event")
-    subtype: str = Field(description="Mental model subtype: structural, emergent, learned")
-    description: str = Field(description="Brief description")
-    summary: str | None = Field(default=None, description="Full summary (when looked up in detail)")
-
-
-class DirectiveRef(BaseModel):
-    """Reference to a directive that was applied during reflect."""
-
-    id: str = Field(description="Directive mental model ID")
-    name: str = Field(description="Directive name")
-    rules: list[str] = Field(default_factory=list, description="Directive rules/observations that were applied")
+# Valid fact types for recall operations (excludes 'observation' which is internal)
+VALID_RECALL_FACT_TYPES = frozenset(["world", "experience", "opinion"])
 
 
 class TokenUsage(BaseModel):
@@ -250,22 +198,6 @@ class ReflectResult(BaseModel):
         default=None,
         description="Token usage metrics for the LLM calls made during this reflect operation.",
     )
-    tool_trace: list[ToolCallTrace] = Field(
-        default_factory=list,
-        description="Trace of tool calls made during reflection. Only present when include.tool_calls is enabled.",
-    )
-    llm_trace: list[LLMCallTrace] = Field(
-        default_factory=list,
-        description="Trace of LLM calls made during reflection. Only present when include.tool_calls is enabled.",
-    )
-    mental_models: list[MentalModelRef] = Field(
-        default_factory=list,
-        description="Mental models accessed during reflection, including directives (subtype='directive').",
-    )
-    directives_applied: list[DirectiveRef] = Field(
-        default_factory=list,
-        description="Directive mental models that were applied during this reflection.",
-    )
 
 
 class Opinion(BaseModel):
@@ -329,32 +261,3 @@ class EntityState(BaseModel):
     observations: list[EntityObservation] = Field(
         default_factory=list, description="List of observations about this entity"
     )
-
-
-class MentalModel(BaseModel):
-    """
-    A manually configured mental model for tracking specific topics/areas.
-
-    Mental models are user-defined focus areas that the agent should track
-    and maintain summaries for, unlike auto-extracted entities.
-    """
-
-    model_config = ConfigDict(
-        json_schema_extra={
-            "example": {
-                "id": "team-dynamics",
-                "name": "Team Dynamics",
-                "description": "Track how the team collaborates, communication patterns, conflicts, and resolutions",
-                "summary": "The team has strong collaboration...",
-                "summary_updated_at": "2024-01-15T10:30:00Z",
-                "created_at": "2024-01-10T08:00:00Z",
-            }
-        }
-    )
-
-    id: str = Field(description="Unique identifier (alphanumeric lowercase)")
-    name: str = Field(description="Display name for the mental model")
-    description: str = Field(description="Prompt/directions for what to track and summarize")
-    summary: str | None = Field(None, description="Generated summary based on relevant facts")
-    summary_updated_at: str | None = Field(None, description="ISO format date when summary was last updated")
-    created_at: str = Field(description="ISO format date when the mental model was created")

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

@@ -1,5 +1,5 @@
 """
-bank profile utilities for disposition and mission management.
+bank profile utilities for disposition and background management.
 """
 
 import json
@@ -27,18 +27,19 @@ class BankProfile(TypedDict):
 
     name: str
     disposition: DispositionTraits
-    mission: str
+    background: str
 
 
-class MissionMergeResponse(BaseModel):
-    """LLM response for mission merge."""
+class BackgroundMergeResponse(BaseModel):
+    """LLM response for background merge with disposition inference."""
 
-    mission: str = Field(description="Merged mission in first person perspective")
+    background: str = Field(description="Merged background in first person perspective")
+    disposition: DispositionTraits = Field(description="Inferred disposition traits (skepticism, literalism, empathy)")
 
 
 async def get_bank_profile(pool, bank_id: str) -> BankProfile:
     """
-    Get bank profile (name, disposition + mission).
+    Get bank profile (name, disposition + background).
     Auto-creates bank with default values if not exists.
 
     Args:
@@ -46,13 +47,13 @@ async def get_bank_profile(pool, bank_id: str) -> BankProfile:
         bank_id: bank IDentifier
 
     Returns:
-        BankProfile with name, typed DispositionTraits, and mission
+        BankProfile with name, typed DispositionTraits, and background
     """
     async with acquire_with_retry(pool) as conn:
         # Try to get existing bank
         row = await conn.fetchrow(
             f"""
-            SELECT name, disposition, mission
+            SELECT name, disposition, background
             FROM {fq_table("banks")} WHERE bank_id = $1
             """,
             bank_id,
@@ -65,15 +66,13 @@ async def get_bank_profile(pool, bank_id: str) -> BankProfile:
                 disposition_data = json.loads(disposition_data)
 
             return BankProfile(
-                name=row["name"],
-                disposition=DispositionTraits(**disposition_data),
-                mission=row["mission"] or "",
+                name=row["name"], disposition=DispositionTraits(**disposition_data), background=row["background"]
             )
 
         # Bank doesn't exist, create with defaults
         await conn.execute(
             f"""
-            INSERT INTO {fq_table("banks")} (bank_id, name, disposition, mission)
+            INSERT INTO {fq_table("banks")} (bank_id, name, disposition, background)
             VALUES ($1, $2, $3::jsonb, $4)
             ON CONFLICT (bank_id) DO NOTHING
             """,
@@ -83,7 +82,7 @@ async def get_bank_profile(pool, bank_id: str) -> BankProfile:
             "",
         )
 
-        return BankProfile(name=bank_id, disposition=DispositionTraits(**DEFAULT_DISPOSITION), mission="")
+        return BankProfile(name=bank_id, disposition=DispositionTraits(**DEFAULT_DISPOSITION), background="")
 
 
 async def update_bank_disposition(pool, bank_id: str, disposition: dict[str, int]) -> None:
@@ -111,121 +110,244 @@ async def update_bank_disposition(pool, bank_id: str, disposition: dict[str, int
         )
 
 
-async def set_bank_mission(pool, bank_id: str, mission: str) -> None:
+async def merge_bank_background(pool, llm_config, bank_id: str, new_info: str, update_disposition: bool = True) -> dict:
     """
-    Set bank mission (replacing any existing mission).
-
-    Args:
-        pool: Database connection pool
-        bank_id: bank IDentifier
-        mission: The mission text
-    """
-    # Ensure bank exists first
-    await get_bank_profile(pool, bank_id)
-
-    async with acquire_with_retry(pool) as conn:
-        await conn.execute(
-            f"""
-            UPDATE {fq_table("banks")}
-            SET mission = $2,
-                updated_at = NOW()
-            WHERE bank_id = $1
-            """,
-            bank_id,
-            mission,
-        )
-
-
-async def merge_bank_mission(pool, llm_config, bank_id: str, new_info: str) -> dict:
-    """
-    Merge new mission information with existing mission using LLM.
+    Merge new background information with existing background using LLM.
     Normalizes to first person ("I") and resolves conflicts.
+    Optionally infers disposition traits from the merged background.
 
     Args:
         pool: Database connection pool
-        llm_config: LLM configuration for mission merging
+        llm_config: LLM configuration for background merging
         bank_id: bank IDentifier
-        new_info: New mission information to add/merge
+        new_info: New background information to add/merge
+        update_disposition: If True, infer Big Five traits from background (default: True)
 
     Returns:
-        Dict with 'mission' (str) key
+        Dict with 'background' (str) and optionally 'disposition' (dict) keys
     """
     # Get current profile
     profile = await get_bank_profile(pool, bank_id)
-    current_mission = profile["mission"]
+    current_background = profile["background"]
 
-    # Use LLM to merge missions
-    result = await _llm_merge_mission(llm_config, current_mission, new_info)
+    # Use LLM to merge backgrounds and optionally infer disposition
+    result = await _llm_merge_background(llm_config, current_background, new_info, infer_disposition=update_disposition)
 
-    merged_mission = result["mission"]
+    merged_background = result["background"]
+    inferred_disposition = result.get("disposition")
 
     # Update in database
     async with acquire_with_retry(pool) as conn:
-        await conn.execute(
-            f"""
-            UPDATE {fq_table("banks")}
-            SET mission = $2,
-                updated_at = NOW()
-            WHERE bank_id = $1
-            """,
-            bank_id,
-            merged_mission,
-        )
+        if inferred_disposition:
+            # Update both background and disposition
+            await conn.execute(
+                f"""
+                UPDATE {fq_table("banks")}
+                SET background = $2,
+                    disposition = $3::jsonb,
+                    updated_at = NOW()
+                WHERE bank_id = $1
+                """,
+                bank_id,
+                merged_background,
+                json.dumps(inferred_disposition),
+            )
+        else:
+            # Update only background
+            await conn.execute(
+                f"""
+                UPDATE {fq_table("banks")}
+                SET background = $2,
+                    updated_at = NOW()
+                WHERE bank_id = $1
+                """,
+                bank_id,
+                merged_background,
+            )
 
-    return {"mission": merged_mission}
+    response = {"background": merged_background}
+    if inferred_disposition:
+        response["disposition"] = inferred_disposition
+
+    return response
 
 
-async def _llm_merge_mission(llm_config, current: str, new_info: str) -> dict:
+async def _llm_merge_background(llm_config, current: str, new_info: str, infer_disposition: bool = False) -> dict:
     """
-    Use LLM to intelligently merge mission information.
+    Use LLM to intelligently merge background information.
+    Optionally infer Big Five disposition traits from the merged background.
 
     Args:
         llm_config: LLM configuration to use
-        current: Current mission text
+        current: Current background text
         new_info: New information to merge
+        infer_disposition: If True, also infer disposition traits
 
     Returns:
-        Dict with 'mission' (str) key
+        Dict with 'background' (str) and optionally 'disposition' (dict) keys
     """
-    prompt = f"""You are helping maintain an agent's mission statement.
+    if infer_disposition:
+        prompt = f"""You are helping maintain a memory bank's background/profile and infer their disposition. You MUST respond with ONLY valid JSON.
 
-Current mission: {current if current else "(empty)"}
+Current background: {current if current else "(empty)"}
 
 New information to add: {new_info}
 
 Instructions:
-1. Merge the new information with the current mission
-2. If there are conflicts, the NEW information overwrites the old
+1. Merge the new information with the current background
+2. If there are conflicts (e.g., different birthplaces), the NEW information overwrites the old
+3. Keep additions that don't conflict
+4. Output in FIRST PERSON ("I") perspective
+5. Be concise - keep merged background under 500 characters
+6. Infer disposition traits from the merged background (each 1-5 integer):
+   - Skepticism: 1-5 (1=trusting, takes things at face value; 5=skeptical, questions everything)
+   - Literalism: 1-5 (1=flexible interpretation, reads between lines; 5=literal, exact interpretation)
+   - Empathy: 1-5 (1=detached, focuses on facts; 5=empathetic, considers emotional context)
+
+CRITICAL: You MUST respond with ONLY a valid JSON object. No markdown, no code blocks, no explanations. Just the JSON.
+
+Format:
+{{
+  "background": "the merged background text in first person",
+  "disposition": {{
+    "skepticism": 3,
+    "literalism": 3,
+    "empathy": 3
+  }}
+}}
+
+Trait inference examples:
+- "I'm a lawyer" → skepticism: 4, literalism: 5, empathy: 2
+- "I'm a therapist" → skepticism: 2, literalism: 2, empathy: 5
+- "I'm an engineer" → skepticism: 3, literalism: 4, empathy: 3
+- "I've been burned before by trusting people" → skepticism: 5, literalism: 3, empathy: 3
+- "I try to understand what people really mean" → skepticism: 3, literalism: 2, empathy: 4
+- "I take contracts very seriously" → skepticism: 4, literalism: 5, empathy: 2"""
+    else:
+        prompt = f"""You are helping maintain a memory bank's background/profile.
+
+Current background: {current if current else "(empty)"}
+
+New information to add: {new_info}
+
+Instructions:
+1. Merge the new information with the current background
+2. If there are conflicts (e.g., different birthplaces), the NEW information overwrites the old
 3. Keep additions that don't conflict
 4. Output in FIRST PERSON ("I") perspective
 5. Be concise - keep it under 500 characters
-6. Return ONLY the merged mission text, no explanations
+6. Return ONLY the merged background text, no explanations
 
-Merged mission:"""
+Merged background:"""
 
     try:
+        # Prepare messages
         messages = [{"role": "user", "content": prompt}]
 
+        if infer_disposition:
+            # Use structured output with Pydantic model for disposition inference
+            try:
+                parsed = await llm_config.call(
+                    messages=messages,
+                    response_format=BackgroundMergeResponse,
+                    scope="bank_background",
+                    temperature=0.3,
+                    max_completion_tokens=8192,
+                )
+                logger.info(f"Successfully got structured response: background={parsed.background[:100]}")
+
+                # Convert Pydantic model to dict format
+                return {"background": parsed.background, "disposition": parsed.disposition.model_dump()}
+            except Exception as e:
+                logger.warning(f"Structured output failed, falling back to manual parsing: {e}")
+                # Fall through to manual parsing below
+
+        # Manual parsing fallback or non-disposition merge
         content = await llm_config.call(
-            messages=messages, scope="bank_mission", temperature=0.3, max_completion_tokens=8192
+            messages=messages, scope="bank_background", temperature=0.3, max_completion_tokens=8192
         )
 
-        logger.info(f"LLM response for mission merge (first 500 chars): {content[:500]}")
+        logger.info(f"LLM response for background merge (first 500 chars): {content[:500]}")
 
-        merged = content.strip()
-        if not merged or merged.lower() in ["(empty)", "none", "n/a"]:
-            merged = new_info if new_info else ""
-        return {"mission": merged}
+        if infer_disposition:
+            # Parse JSON response - try multiple extraction methods
+            result = None
+
+            # Method 1: Direct parse
+            try:
+                result = json.loads(content)
+                logger.info("Successfully parsed JSON directly")
+            except json.JSONDecodeError:
+                pass
+
+            # Method 2: Extract from markdown code blocks
+            if result is None:
+                # Remove markdown code blocks
+                code_block_match = re.search(r"```(?:json)?\s*(\{.*?\})\s*```", content, re.DOTALL)
+                if code_block_match:
+                    try:
+                        result = json.loads(code_block_match.group(1))
+                        logger.info("Successfully extracted JSON from markdown code block")
+                    except json.JSONDecodeError:
+                        pass
+
+            # Method 3: Find nested JSON structure
+            if result is None:
+                # Look for JSON object with nested structure
+                json_match = re.search(
+                    r'\{[^{}]*"background"[^{}]*"disposition"[^{}]*\{[^{}]*\}[^{}]*\}', content, re.DOTALL
+                )
+                if json_match:
+                    try:
+                        result = json.loads(json_match.group())
+                        logger.info("Successfully extracted JSON using nested pattern")
+                    except json.JSONDecodeError:
+                        pass
+
+            # All parsing methods failed - use fallback
+            if result is None:
+                logger.warning(f"Failed to extract JSON from LLM response. Raw content: {content[:200]}")
+                # Fallback: use new_info as background with default disposition
+                return {
+                    "background": new_info if new_info else current if current else "",
+                    "disposition": DEFAULT_DISPOSITION.copy(),
+                }
+
+            # Validate disposition values
+            disposition = result.get("disposition", {})
+            for key in ["skepticism", "literalism", "empathy"]:
+                if key not in disposition:
+                    disposition[key] = 3  # Default to neutral
+                else:
+                    # Clamp to [1, 5] and convert to int
+                    disposition[key] = max(1, min(5, int(disposition[key])))
+
+            result["disposition"] = disposition
+
+            # Ensure background exists
+            if "background" not in result or not result["background"]:
+                result["background"] = new_info if new_info else ""
+
+            return result
+        else:
+            # Just background merge
+            merged = content
+            if not merged or merged.lower() in ["(empty)", "none", "n/a"]:
+                merged = new_info if new_info else ""
+            return {"background": merged}
 
     except Exception as e:
-        logger.error(f"Error merging mission with LLM: {e}")
+        logger.error(f"Error merging background with LLM: {e}")
         # Fallback: just append new info
         if current:
             merged = f"{current} {new_info}".strip()
         else:
             merged = new_info
 
-        return {"mission": merged}
+        result = {"background": merged}
+        if infer_disposition:
+            result["disposition"] = DEFAULT_DISPOSITION.copy()
+        return result
 
 
 async def list_banks(pool) -> list:
@@ -236,12 +358,12 @@ async def list_banks(pool) -> list:
         pool: Database connection pool
 
     Returns:
-        List of dicts with bank_id, name, disposition, mission, created_at, updated_at
+        List of dicts with bank_id, name, disposition, background, created_at, updated_at
     """
     async with acquire_with_retry(pool) as conn:
         rows = await conn.fetch(
             f"""
-            SELECT bank_id, name, disposition, mission, created_at, updated_at
+            SELECT bank_id, name, disposition, background, created_at, updated_at
             FROM {fq_table("banks")}
             ORDER BY updated_at DESC
             """
@@ -259,7 +381,7 @@ async def list_banks(pool) -> list:
                     "bank_id": row["bank_id"],
                     "name": row["name"],
                     "disposition": disposition_data,
-                    "mission": row["mission"] or "",
+                    "background": row["background"],
                     "created_at": row["created_at"].isoformat() if row["created_at"] else None,
                     "updated_at": row["updated_at"].isoformat() if row["updated_at"] else None,
                 }

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

@@ -126,7 +126,7 @@ async def ensure_bank_exists(conn, bank_id: str) -> None:
     """
     await conn.execute(
         f"""
-        INSERT INTO {fq_table("banks")} (bank_id, disposition, mission)
+        INSERT INTO {fq_table("banks")} (bank_id, disposition, background)
         VALUES ($1, $2::jsonb, $3)
         ON CONFLICT (bank_id) DO UPDATE
         SET updated_at = NOW()

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

@@ -0,0 +1,254 @@
+"""
+Observation regeneration for retain pipeline.
+
+Regenerates entity observations as part of the retain transaction.
+"""
+
+import logging
+import time
+import uuid
+from datetime import UTC, datetime
+
+from ...config import get_config
+from ..memory_engine import fq_table
+from ..search import observation_utils
+from . import embedding_utils
+from .types import EntityLink
+
+logger = logging.getLogger(__name__)
+
+
+def utcnow():
+    """Get current UTC time."""
+    return datetime.now(UTC)
+
+
+# Simple dataclass-like container for facts (avoid importing from memory_engine)
+class MemoryFactForObservation:
+    def __init__(self, id: str, text: str, fact_type: str, context: str, occurred_start: str | None):
+        self.id = id
+        self.text = text
+        self.fact_type = fact_type
+        self.context = context
+        self.occurred_start = occurred_start
+
+
+async def regenerate_observations_batch(
+    conn, embeddings_model, llm_config, bank_id: str, entity_links: list[EntityLink], log_buffer: list[str] = None
+) -> None:
+    """
+    Regenerate observations for top entities in this batch.
+
+    Called INSIDE the retain transaction for atomicity - if observations
+    fail, the entire retain batch is rolled back.
+
+    Args:
+        conn: Database connection (from the retain transaction)
+        embeddings_model: Embeddings model for generating observation embeddings
+        llm_config: LLM configuration for observation extraction
+        bank_id: Bank identifier
+        entity_links: Entity links from this batch
+        log_buffer: Optional log buffer for timing
+    """
+    config = get_config()
+    TOP_N_ENTITIES = config.observation_top_entities
+    MIN_FACTS_THRESHOLD = config.observation_min_facts
+
+    if not entity_links:
+        return
+
+    # Count mentions per entity in this batch
+    entity_mention_counts: dict[str, int] = {}
+    for link in entity_links:
+        if link.entity_id:
+            entity_id = str(link.entity_id)
+            entity_mention_counts[entity_id] = entity_mention_counts.get(entity_id, 0) + 1
+
+    if not entity_mention_counts:
+        return
+
+    # Sort by mention count descending and take top N
+    sorted_entities = sorted(entity_mention_counts.items(), key=lambda x: x[1], reverse=True)
+    entities_to_process = [e[0] for e in sorted_entities[:TOP_N_ENTITIES]]
+
+    obs_start = time.time()
+
+    # Convert to UUIDs
+    entity_uuids = [uuid.UUID(eid) if isinstance(eid, str) else eid for eid in entities_to_process]
+
+    # Batch query for entity names
+    entity_rows = await conn.fetch(
+        f"""
+        SELECT id, canonical_name FROM {fq_table("entities")}
+        WHERE id = ANY($1) AND bank_id = $2
+        """,
+        entity_uuids,
+        bank_id,
+    )
+    entity_names = {row["id"]: row["canonical_name"] for row in entity_rows}
+
+    # Batch query for fact counts
+    fact_counts = await conn.fetch(
+        f"""
+        SELECT ue.entity_id, COUNT(*) as cnt
+        FROM {fq_table("unit_entities")} ue
+        JOIN {fq_table("memory_units")} mu ON ue.unit_id = mu.id
+        WHERE ue.entity_id = ANY($1) AND mu.bank_id = $2
+        GROUP BY ue.entity_id
+        """,
+        entity_uuids,
+        bank_id,
+    )
+    entity_fact_counts = {row["entity_id"]: row["cnt"] for row in fact_counts}
+
+    # Filter entities that meet the threshold
+    entities_with_names = []
+    for entity_id in entities_to_process:
+        entity_uuid = uuid.UUID(entity_id) if isinstance(entity_id, str) else entity_id
+        if entity_uuid not in entity_names:
+            continue
+        fact_count = entity_fact_counts.get(entity_uuid, 0)
+        if fact_count >= MIN_FACTS_THRESHOLD:
+            entities_with_names.append((entity_id, entity_names[entity_uuid]))
+
+    if not entities_with_names:
+        return
+
+    # Process entities SEQUENTIALLY (asyncpg doesn't allow concurrent queries on same connection)
+    # We must use the same connection to stay in the retain transaction
+    total_observations = 0
+
+    for entity_id, entity_name in entities_with_names:
+        try:
+            obs_ids = await _regenerate_entity_observations(
+                conn, embeddings_model, llm_config, bank_id, entity_id, entity_name
+            )
+            total_observations += len(obs_ids)
+        except Exception as e:
+            logger.error(f"[OBSERVATIONS] Error processing entity {entity_id}: {e}")
+
+    obs_time = time.time() - obs_start
+    if log_buffer is not None:
+        log_buffer.append(
+            f"[11] Observations: {total_observations} observations for {len(entities_with_names)} entities in {obs_time:.3f}s"
+        )
+
+
+async def _regenerate_entity_observations(
+    conn, embeddings_model, llm_config, bank_id: str, entity_id: str, entity_name: str
+) -> list[str]:
+    """
+    Regenerate observations for a single entity.
+
+    Uses the provided connection (part of retain transaction).
+
+    Args:
+        conn: Database connection (from the retain transaction)
+        embeddings_model: Embeddings model
+        llm_config: LLM configuration
+        bank_id: Bank identifier
+        entity_id: Entity UUID
+        entity_name: Canonical name of the entity
+
+    Returns:
+        List of created observation IDs
+    """
+    entity_uuid = uuid.UUID(entity_id) if isinstance(entity_id, str) else entity_id
+
+    # Get all facts mentioning this entity (exclude observations themselves)
+    rows = await conn.fetch(
+        f"""
+        SELECT mu.id, mu.text, mu.context, mu.occurred_start, mu.fact_type
+        FROM {fq_table("memory_units")} mu
+        JOIN {fq_table("unit_entities")} ue ON mu.id = ue.unit_id
+        WHERE mu.bank_id = $1
+          AND ue.entity_id = $2
+          AND mu.fact_type IN ('world', 'experience')
+        ORDER BY mu.occurred_start DESC
+        LIMIT 50
+        """,
+        bank_id,
+        entity_uuid,
+    )
+
+    if not rows:
+        return []
+
+    # Convert to fact objects for observation extraction
+    facts = []
+    for row in rows:
+        occurred_start = row["occurred_start"].isoformat() if row["occurred_start"] else None
+        facts.append(
+            MemoryFactForObservation(
+                id=str(row["id"]),
+                text=row["text"],
+                fact_type=row["fact_type"],
+                context=row["context"],
+                occurred_start=occurred_start,
+            )
+        )
+
+    # Extract observations using LLM
+    observations = await observation_utils.extract_observations_from_facts(llm_config, entity_name, facts)
+
+    if not observations:
+        return []
+
+    # Delete old observations for this entity
+    await conn.execute(
+        f"""
+        DELETE FROM {fq_table("memory_units")}
+        WHERE id IN (
+            SELECT mu.id
+            FROM {fq_table("memory_units")} mu
+            JOIN {fq_table("unit_entities")} ue ON mu.id = ue.unit_id
+            WHERE mu.bank_id = $1
+              AND mu.fact_type = 'observation'
+              AND ue.entity_id = $2
+        )
+        """,
+        bank_id,
+        entity_uuid,
+    )
+
+    # Generate embeddings for new observations
+    embeddings = await embedding_utils.generate_embeddings_batch(embeddings_model, observations)
+
+    # Insert new observations
+    current_time = utcnow()
+    created_ids = []
+
+    for obs_text, embedding in zip(observations, embeddings):
+        result = await conn.fetchrow(
+            f"""
+            INSERT INTO {fq_table("memory_units")} (
+                bank_id, text, embedding, context, event_date,
+                occurred_start, occurred_end, mentioned_at,
+                fact_type, access_count
+            )
+            VALUES ($1, $2, $3, $4, $5, $6, $7, $8, 'observation', 0)
+            RETURNING id
+            """,
+            bank_id,
+            obs_text,
+            str(embedding),
+            f"observation about {entity_name}",
+            current_time,
+            current_time,
+            current_time,
+            current_time,
+        )
+        obs_id = str(result["id"])
+        created_ids.append(obs_id)
+
+        # Link observation to entity
+        await conn.execute(
+            f"""
+            INSERT INTO {fq_table("unit_entities")} (unit_id, entity_id)
+            VALUES ($1, $2)
+            """,
+            uuid.UUID(obs_id),
+            entity_uuid,
+        )
+
+    return created_ids

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

@@ -9,6 +9,7 @@ import time
 import uuid
 from datetime import UTC, datetime
 
+from ...config import get_config
 from ..db_utils import acquire_with_retry
 from . import bank_utils
 
@@ -27,8 +28,9 @@ from . import (
     fact_extraction,
     fact_storage,
     link_creation,
+    observation_regeneration,
 )
-from .types import EntityLink, ExtractedFact, ProcessedFact, RetainContent, RetainContentDict
+from .types import ExtractedFact, ProcessedFact, RetainContent, RetainContentDict
 
 logger = logging.getLogger(__name__)
 
@@ -38,6 +40,7 @@ async def retain_batch(
     embeddings_model,
     llm_config,
     entity_resolver,
+    task_backend,
     format_date_fn,
     duplicate_checker_fn,
     bank_id: str,
@@ -56,6 +59,7 @@ async def retain_batch(
         embeddings_model: Embeddings model for generating embeddings
         llm_config: LLM configuration for fact extraction
         entity_resolver: Entity resolver for entity processing
+        task_backend: Task backend for background jobs
         format_date_fn: Function to format datetime to readable string
         duplicate_checker_fn: Function to check for duplicate facts
         bank_id: Bank identifier
@@ -404,9 +408,27 @@ async def retain_batch(
             causal_link_count = await link_creation.create_causal_links_batch(conn, unit_ids, non_duplicate_facts)
             log_buffer.append(f"[10] Causal links: {causal_link_count} links in {time.time() - step_start:.3f}s")
 
+            # Regenerate observations - sync (in transaction) or async (background task)
+            config = get_config()
+            if config.retain_observations_async:
+                # Queue for async processing after transaction commits
+                entity_ids_for_async = list(set(link.entity_id for link in entity_links)) if entity_links else []
+                log_buffer.append(
+                    f"[11] Observations: queued {len(entity_ids_for_async)} entities for async processing"
+                )
+            else:
+                # Run synchronously inside transaction for atomicity
+                await observation_regeneration.regenerate_observations_batch(
+                    conn, embeddings_model, llm_config, bank_id, entity_links, log_buffer
+                )
+                entity_ids_for_async = []
+
             # Map results back to original content items
             result_unit_ids = _map_results_to_contents(contents, extracted_facts, is_duplicate_flags, unit_ids)
 
+        # Trigger background tasks AFTER transaction commits
+        await _trigger_background_tasks(task_backend, bank_id, unit_ids, non_duplicate_facts, entity_ids_for_async)
+
         # Log final summary
         total_time = time.time() - start_time
         log_buffer.append(f"{'=' * 60}")
@@ -448,3 +470,35 @@ def _map_results_to_contents(
         result_unit_ids.append(content_unit_ids)
 
     return result_unit_ids
+
+
+async def _trigger_background_tasks(
+    task_backend,
+    bank_id: str,
+    unit_ids: list[str],
+    facts: list[ProcessedFact],
+    entity_ids_for_observations: list[str] | None = None,
+) -> None:
+    """Trigger background tasks after transaction commits."""
+    # Trigger opinion reinforcement if there are entities
+    fact_entities = [[e.name for e in fact.entities] for fact in facts]
+    if any(fact_entities):
+        await task_backend.submit_task(
+            {
+                "type": "reinforce_opinion",
+                "bank_id": bank_id,
+                "created_unit_ids": unit_ids,
+                "unit_texts": [fact.fact_text for fact in facts],
+                "unit_entities": fact_entities,
+            }
+        )
+
+    # Trigger observation regeneration if async mode is enabled
+    if entity_ids_for_observations:
+        await task_backend.submit_task(
+            {
+                "type": "regenerate_observations",
+                "bank_id": bank_id,
+                "entity_ids": entity_ids_for_observations,
+            }
+        )

hindsight-api/hindsight_api/engine/search/observation_utils.py

@@ -0,0 +1,125 @@
+"""
+Observation utilities for generating entity observations from facts.
+
+Observations are objective facts synthesized from multiple memory facts
+about an entity, without personality influence.
+"""
+
+import logging
+
+from pydantic import BaseModel, Field
+
+from ..response_models import MemoryFact
+
+logger = logging.getLogger(__name__)
+
+
+class Observation(BaseModel):
+    """An observation about an entity."""
+
+    observation: str = Field(description="The observation text - a factual statement about the entity")
+
+
+class ObservationExtractionResponse(BaseModel):
+    """Response containing extracted observations."""
+
+    observations: list[Observation] = Field(default_factory=list, description="List of observations about the entity")
+
+
+def format_facts_for_observation_prompt(facts: list[MemoryFact]) -> str:
+    """Format facts as text for observation extraction prompt."""
+    import json
+
+    if not facts:
+        return "[]"
+    formatted = []
+    for fact in facts:
+        fact_obj = {"text": fact.text}
+
+        # Add context if available
+        if fact.context:
+            fact_obj["context"] = fact.context
+
+        # Add occurred_start if available
+        if fact.occurred_start:
+            fact_obj["occurred_at"] = fact.occurred_start
+
+        formatted.append(fact_obj)
+
+    return json.dumps(formatted, indent=2)
+
+
+def build_observation_prompt(
+    entity_name: str,
+    facts_text: str,
+) -> str:
+    """Build the observation extraction prompt for the LLM."""
+    return f"""Based on the following facts about "{entity_name}", generate a list of key observations.
+
+FACTS ABOUT {entity_name.upper()}:
+{facts_text}
+
+Your task: Synthesize the facts into clear, objective observations about {entity_name}.
+
+GUIDELINES:
+1. Each observation should be a factual statement about {entity_name}
+2. Combine related facts into single observations where appropriate
+3. Be objective - do not add opinions, judgments, or interpretations
+4. Focus on what we KNOW about {entity_name}, not what we assume
+5. Include observations about: identity, characteristics, roles, relationships, activities
+6. Write in third person (e.g., "John is..." not "I think John is...")
+7. If there are conflicting facts, note the most recent or most supported one
+
+EXAMPLES of good observations:
+- "John works at Google as a software engineer"
+- "John is detail-oriented and methodical in his approach"
+- "John collaborates frequently with Sarah on the AI project"
+- "John joined the company in 2023"
+
+EXAMPLES of bad observations (avoid these):
+- "John seems like a good person" (opinion/judgment)
+- "John probably likes his job" (assumption)
+- "I believe John is reliable" (first-person opinion)
+
+Generate 3-7 observations based on the available facts. If there are very few facts, generate fewer observations."""
+
+
+def get_observation_system_message() -> str:
+    """Get the system message for observation extraction."""
+    return "You are an objective observer synthesizing facts about an entity. Generate clear, factual observations without opinions or personality influence. Be concise and accurate."
+
+
+async def extract_observations_from_facts(llm_config, entity_name: str, facts: list[MemoryFact]) -> list[str]:
+    """
+    Extract observations from facts about an entity using LLM.
+
+    Args:
+        llm_config: LLM configuration to use
+        entity_name: Name of the entity to generate observations about
+        facts: List of facts mentioning the entity
+
+    Returns:
+        List of observation strings
+    """
+    if not facts:
+        return []
+
+    facts_text = format_facts_for_observation_prompt(facts)
+    prompt = build_observation_prompt(entity_name, facts_text)
+
+    try:
+        result = await llm_config.call(
+            messages=[
+                {"role": "system", "content": get_observation_system_message()},
+                {"role": "user", "content": prompt},
+            ],
+            response_format=ObservationExtractionResponse,
+            scope="memory_extract_observation",
+        )
+
+        observations = [op.observation for op in result.observations]
+        return observations
+
+    except Exception as e:
+        logger.warning(f"Failed to extract observations for {entity_name}: {str(e)}")
+        return []

hindsight-api/hindsight_api/engine/search/think_utils.py

@@ -3,13 +3,31 @@ Think operation utilities for formulating answers based on agent and world facts
 """
 
 import logging
+import re
 from datetime import datetime
 
+from pydantic import BaseModel, Field
+
 from ..response_models import DispositionTraits, MemoryFact
 
 logger = logging.getLogger(__name__)
 
 
+class Opinion(BaseModel):
+    """An opinion formed by the bank."""
+
+    opinion: str = Field(description="The opinion or perspective with reasoning included")
+    confidence: float = Field(description="Confidence score for this opinion (0.0 to 1.0, where 1.0 is very confident)")
+
+
+class OpinionExtractionResponse(BaseModel):
+    """Response containing extracted opinions."""
+
+    opinions: list[Opinion] = Field(
+        default_factory=list, description="List of opinions formed with their supporting reasons and confidence scores"
+    )
+
+
 def describe_trait_level(value: int) -> str:
     """Convert trait value (1-5) to descriptive text."""
     levels = {1: "very low", 2: "low", 3: "moderate", 4: "high", 5: "very high"}
@@ -75,46 +93,17 @@ def format_facts_for_prompt(facts: list[MemoryFact]) -> str:
     return json.dumps(formatted, indent=2)
 
 
-def format_entity_summaries_for_prompt(entities: dict) -> str:
-    """Format entity summaries for inclusion in the reflect prompt.
-
-    Args:
-        entities: Dict mapping entity name to EntityState objects
-
-    Returns:
-        Formatted string with entity summaries, or empty string if no summaries
-    """
-    if not entities:
-        return ""
-
-    summaries = []
-    for name, state in entities.items():
-        # Get summary from observations (summary is stored as single observation)
-        if state.observations:
-            summary_text = state.observations[0].text
-            summaries.append(f"## {name}\n{summary_text}")
-
-    if not summaries:
-        return ""
-
-    return "\n\n".join(summaries)
-
-
 def build_think_prompt(
     agent_facts_text: str,
     world_facts_text: str,
+    opinion_facts_text: str,
     query: str,
     name: str,
     disposition: DispositionTraits,
     background: str,
     context: str | None = None,
-    entity_summaries_text: str | None = None,
 ) -> str:
-    """Build the think prompt for the LLM.
-
-    Note: opinion_facts_text parameter removed - opinions are now stored as mental models
-    and included via entity_summaries_text.
-    """
+    """Build the think prompt for the LLM."""
     disposition_desc = build_disposition_description(disposition)
 
     name_section = f"""
@@ -136,14 +125,6 @@ Your background:
 ADDITIONAL CONTEXT:
 {context}
 
-"""
-
-    entity_section = ""
-    if entity_summaries_text:
-        entity_section = f"""
-KEY PEOPLE, PLACES & THINGS I KNOW ABOUT:
-{entity_summaries_text}
-
 """
 
     return f"""Here's what I know and have experienced:
@@ -154,11 +135,14 @@ MY IDENTITY & EXPERIENCES:
 WHAT I KNOW ABOUT THE WORLD:
 {world_facts_text}
 
-{entity_section}{context_section}{name_section}{disposition_desc}{background_section}
+MY EXISTING OPINIONS & BELIEFS:
+{opinion_facts_text}
+
+{context_section}{name_section}{disposition_desc}{background_section}
 
 QUESTION: {query}
 
-Based on everything I know, believe, and who I am (including my name, disposition and background), here's what I genuinely think about this question. I'll draw on my experiences, knowledge, and personal traits to give you my honest perspective."""
+Based on everything I know, believe, and who I am (including my name, disposition and background), here's what I genuinely think about this question. I'll draw on my experiences, knowledge, opinions, and personal traits to give you my honest perspective."""
 
 
 def get_system_message(disposition: DispositionTraits) -> str:
@@ -191,11 +175,122 @@ def get_system_message(disposition: DispositionTraits) -> str:
     return f"You are a person with your own thoughts, experiences, opinions, and disposition. When asked a question, respond naturally like a human would - share what you genuinely think based on what you know and have experienced. {disposition_instruction} Be direct, express your views confidently, and use 'I think', 'I believe', 'in my view', etc. Respond in plain text without markdown formatting. IMPORTANT: Detect the language of the question and respond in the SAME language. Do not translate to English if the question is in another language."
 
 
+async def extract_opinions_from_text(llm_config, text: str, query: str) -> list[Opinion]:
+    """
+    Extract opinions with reasons and confidence from text using LLM.
+
+    Args:
+        llm_config: LLM configuration to use
+        text: Text to extract opinions from
+        query: The original query that prompted this response
+
+    Returns:
+        List of Opinion objects with text and confidence
+    """
+    extraction_prompt = f"""Extract any NEW opinions or perspectives from the answer below and rewrite them in FIRST-PERSON as if YOU are stating the opinion directly.
+
+ORIGINAL QUESTION:
+{query}
+
+ANSWER PROVIDED:
+{text}
+
+Your task: Find opinions in the answer and rewrite them AS IF YOU ARE THE ONE SAYING THEM.
+
+An opinion is a judgment, viewpoint, or conclusion that goes beyond just stating facts.
+
+IMPORTANT: Do NOT extract statements like:
+- "I don't have enough information"
+- "The facts don't contain information about X"
+- "I cannot answer because..."
+
+ONLY extract actual opinions about substantive topics.
+
+CRITICAL FORMAT REQUIREMENTS:
+1. **ALWAYS start with first-person phrases**: "I think...", "I believe...", "In my view...", "I've come to believe...", "Previously I thought... but now..."
+2. **NEVER use third-person**: Do NOT say "The speaker thinks..." or "They believe..." - always use "I"
+3. Include the reasoning naturally within the statement
+4. Provide a confidence score (0.0 to 1.0)
+
+CORRECT Examples (✓ FIRST-PERSON):
+- "I think Alice is more reliable because she consistently delivers on time and writes clean code"
+- "Previously I thought all engineers were equal, but now I feel that experience and track record really matter"
+- "I believe reliability is best measured by consistent output over time"
+- "I've come to believe that track records are more important than potential"
+
+WRONG Examples (✗ THIRD-PERSON - DO NOT USE):
+- "The speaker thinks Alice is more reliable"
+- "They believe reliability matters"
+- "It is believed that Alice is better"
+
+If no genuine opinions are expressed (e.g., the response just says "I don't know"), return an empty list."""
+
+    try:
+        result = await llm_config.call(
+            messages=[
+                {
+                    "role": "system",
+                    "content": "You are converting opinions from text into first-person statements. Always use 'I think', 'I believe', 'I feel', etc. NEVER use third-person like 'The speaker' or 'They'.",
+                },
+                {"role": "user", "content": extraction_prompt},
+            ],
+            response_format=OpinionExtractionResponse,
+            scope="memory_extract_opinion",
+        )
+
+        # Format opinions with confidence score and convert to first-person
+        formatted_opinions = []
+        for op in result.opinions:
+            # Convert third-person to first-person if needed
+            opinion_text = op.opinion
+
+            # Replace common third-person patterns with first-person
+            def singularize_verb(verb):
+                if verb.endswith("es"):
+                    return verb[:-1]  # believes -> believe
+                elif verb.endswith("s"):
+                    return verb[:-1]  # thinks -> think
+                return verb
+
+            # Pattern: "The speaker/user [verb]..." -> "I [verb]..."
+            match = re.match(
+                r"^(The speaker|The user|They|It is believed) (believes?|thinks?|feels?|says|asserts?|considers?)(\s+that)?(.*)$",
+                opinion_text,
+                re.IGNORECASE,
+            )
+            if match:
+                verb = singularize_verb(match.group(2))
+                that_part = match.group(3) or ""  # Keep " that" if present
+                rest = match.group(4)
+                opinion_text = f"I {verb}{that_part}{rest}"
+
+            # If still doesn't start with first-person, prepend "I believe that "
+            first_person_starters = [
+                "I think",
+                "I believe",
+                "I feel",
+                "In my view",
+                "I've come to believe",
+                "Previously I",
+            ]
+            if not any(opinion_text.startswith(starter) for starter in first_person_starters):
+                opinion_text = "I believe that " + opinion_text[0].lower() + opinion_text[1:]
+
+            formatted_opinions.append(Opinion(opinion=opinion_text, confidence=op.confidence))
+
+        return formatted_opinions
+
+    except Exception as e:
+        logger.warning(f"Failed to extract opinions: {str(e)}")
+        return []
+
+
 async def reflect(
     llm_config,
     query: str,
     experience_facts: list[str] = None,
     world_facts: list[str] = None,
+    opinion_facts: list[str] = None,
     name: str = "Assistant",
     disposition: DispositionTraits = None,
     background: str = "",
@@ -212,6 +307,7 @@ async def reflect(
         query: Question to answer
         experience_facts: List of experience/agent fact strings
         world_facts: List of world fact strings
+        opinion_facts: List of opinion fact strings
         name: Name of the agent/persona
         disposition: Disposition traits (defaults to neutral)
         background: Background information
@@ -232,15 +328,18 @@ async def reflect(
 
     agent_results = to_memory_facts(experience_facts or [], "experience")
     world_results = to_memory_facts(world_facts or [], "world")
+    opinion_results = to_memory_facts(opinion_facts or [], "opinion")
 
     # Format facts for prompt
     agent_facts_text = format_facts_for_prompt(agent_results)
     world_facts_text = format_facts_for_prompt(world_results)
+    opinion_facts_text = format_facts_for_prompt(opinion_results)
 
     # Build prompt
     prompt = build_think_prompt(
         agent_facts_text=agent_facts_text,
         world_facts_text=world_facts_text,
+        opinion_facts_text=opinion_facts_text,
         query=query,
         name=name,
         disposition=disposition,

hindsight-api/hindsight_api/extensions/__init__.py

@@ -27,8 +27,6 @@ from hindsight_api.extensions.operation_validator import (
     RecallResult,
     ReflectContext,
     ReflectResultContext,
-    RefreshMentalModelContext,
-    RefreshMentalModelResult,
     RetainContext,
     RetainResult,
     ValidationResult,
@@ -56,8 +54,6 @@ __all__ = [
     "RecallResult",
     "ReflectContext",
     "ReflectResultContext",
-    "RefreshMentalModelContext",
-    "RefreshMentalModelResult",
     "RetainContext",
     "RetainResult",
     "ValidationResult",

hindsight-api/hindsight_api/extensions/operation_validator.py

@@ -97,18 +97,6 @@ class ReflectContext:
     context: str | None = None
 
 
-@dataclass
-class RefreshMentalModelContext:
-    """Context for a refresh mental model operation validation (pre-operation).
-
-    Contains ALL user-provided parameters for the refresh mental model operation.
-    """
-
-    bank_id: str
-    model_id: str
-    request_context: "RequestContext"
-
-
 # =============================================================================
 # Post-operation Contexts (includes results)
 # =============================================================================
@@ -176,27 +164,6 @@ class ReflectResultContext:
     error: str | None = None
 
 
-@dataclass
-class RefreshMentalModelResult:
-    """Result context for post-refresh-mental-model hook.
-
-    Contains the operation parameters and the result including token usage.
-    """
-
-    bank_id: str
-    model_id: str
-    request_context: "RequestContext"
-    # Result
-    model_name: str | None = None
-    observations_count: int = 0
-    input_tokens: int = 0
-    output_tokens: int = 0
-    total_tokens: int = 0
-    duration_ms: int = 0
-    success: bool = True
-    error: str | None = None
-
-
 class OperationValidatorExtension(Extension, ABC):
     """
     Validates and hooks into retain/recall/reflect operations.
@@ -298,25 +265,6 @@ class OperationValidatorExtension(Extension, ABC):
         """
         ...
 
-    @abstractmethod
-    async def validate_refresh_mental_model(self, ctx: RefreshMentalModelContext) -> ValidationResult:
-        """
-        Validate a refresh mental model operation before execution.
-
-        Called before the refresh mental model operation is processed.
-        Return ValidationResult.reject() to prevent the operation from executing.
-
-        Args:
-            ctx: Context containing all user-provided parameters:
-                - bank_id: Bank identifier
-                - model_id: Mental model ID to refresh
-                - request_context: Request context with auth info
-
-        Returns:
-            ValidationResult indicating whether the operation is allowed.
-        """
-        ...
-
     # =========================================================================
     # Post-operation hooks (optional - override to implement)
     # =========================================================================
@@ -377,28 +325,3 @@ class OperationValidatorExtension(Extension, ABC):
                 - error: Error message (if failed)
         """
         pass
-
-    async def on_refresh_mental_model_complete(self, result: RefreshMentalModelResult) -> None:
-        """
-        Called after a refresh mental model operation completes (success or failure).
-
-        Override this method to implement post-operation logic such as:
-        - Token usage tracking and billing
-        - Audit logging
-        - Metrics collection
-
-        Args:
-            result: Result context containing:
-                - bank_id: Bank identifier
-                - model_id: Mental model ID
-                - request_context: Request context with auth info
-                - model_name: Name of the mental model (if success)
-                - observations_count: Number of observations generated
-                - input_tokens: Number of input tokens used
-                - output_tokens: Number of output tokens used
-                - total_tokens: Total tokens used (input + output)
-                - duration_ms: Total operation duration in milliseconds
-                - success: Whether the operation succeeded
-                - error: Error message (if failed)
-        """
-        pass

hindsight-api/hindsight_api/main.py

@@ -221,8 +221,6 @@ def main():
             task_backend=config.task_backend,
             task_backend_memory_batch_size=config.task_backend_memory_batch_size,
             task_backend_memory_batch_interval=config.task_backend_memory_batch_interval,
-            reflect_max_iterations=config.reflect_max_iterations,
-            mental_model_refresh_concurrency=config.mental_model_refresh_concurrency,
         )
     config.configure_logging()
     if not args.daemon:

hindsight-api/tests/test_agents_api.py

@@ -1,5 +1,5 @@
 """
-Tests for agent management API (profile, disposition).
+Tests for agent management API (profile, disposition, background).
 """
 import pytest
 import uuid
@@ -25,12 +25,15 @@ class TestAgentProfile:
 
         assert profile is not None
         assert "disposition" in profile
+        assert "background" in profile
 
         disposition = profile["disposition"]
         assert disposition.skepticism == 3
         assert disposition.literalism == 3
         assert disposition.empathy == 3
 
+        assert profile["background"] == ""
+
     @pytest.mark.asyncio
     async def test_update_agent_disposition(self, memory: MemoryEngine, request_context):
         """Test updating agent disposition traits."""
@@ -73,10 +76,63 @@ class TestAgentProfile:
         for agent in agents:
             assert "bank_id" in agent
             assert "disposition" in agent
+            assert "background" in agent
             assert "created_at" in agent
             assert "updated_at" in agent
 
 
+class TestAgentBackground:
+    """Tests for agent background management."""
+
+    @pytest.mark.asyncio
+    async def test_merge_agent_background(self, memory: MemoryEngine, request_context):
+        """Test merging agent background information."""
+        bank_id = unique_agent_id("test_profile_merge")
+
+        profile = await memory.get_bank_profile(bank_id, request_context=request_context)
+        assert profile["background"] == ""
+
+        result1 = await memory.merge_bank_background(
+            bank_id,
+            "I was born in Texas",
+            update_disposition=False,
+            request_context=request_context,
+        )
+        assert "Texas" in result1["background"]
+
+        result2 = await memory.merge_bank_background(
+            bank_id,
+            "I have 10 years of startup experience",
+            update_disposition=False,
+            request_context=request_context,
+        )
+        assert "Texas" in result2["background"] or "startup" in result2["background"]
+
+        final_profile = await memory.get_bank_profile(bank_id, request_context=request_context)
+        assert final_profile["background"] != ""
+
+    @pytest.mark.asyncio
+    async def test_merge_background_handles_conflicts(self, memory: MemoryEngine, request_context):
+        """Test that merging background handles conflicts (new overwrites old)."""
+        bank_id = unique_agent_id("test_profile_conflict")
+
+        result1 = await memory.merge_bank_background(
+            bank_id,
+            "I was born in Colorado",
+            update_disposition=False,
+            request_context=request_context,
+        )
+        assert "Colorado" in result1["background"]
+
+        result2 = await memory.merge_bank_background(
+            bank_id,
+            "You were born in Texas",
+            update_disposition=False,
+            request_context=request_context,
+        )
+        assert "Texas" in result2["background"]
+
+
 class TestAgentEndpoint:
     """Tests for agent PUT endpoint logic."""
 
@@ -91,6 +147,7 @@ class TestAgentEndpoint:
                 literalism=5,
                 empathy=2
             ),
+            background="I am a creative software engineer"
         )
 
         profile = await memory.get_bank_profile(bank_id, request_context=request_context)
@@ -102,10 +159,55 @@ class TestAgentEndpoint:
                 request_context=request_context,
             )
 
+        if request.background is not None:
+            pool = await memory._get_pool()
+            async with pool.acquire() as conn:
+                await conn.execute(
+                    """
+                    UPDATE banks
+                    SET background = $2,
+                        updated_at = NOW()
+                    WHERE bank_id = $1
+                    """,
+                    bank_id,
+                    request.background
+                )
+
         final_profile = await memory.get_bank_profile(bank_id, request_context=request_context)
 
         assert final_profile["disposition"].skepticism == 4
         assert final_profile["disposition"].literalism == 5
+        assert final_profile["background"] == "I am a creative software engineer"
+
+    @pytest.mark.asyncio
+    async def test_put_agent_partial_update(self, memory: MemoryEngine, request_context):
+        """Test updating only background."""
+        bank_id = unique_agent_id("test_put_partial")
+
+        request = CreateBankRequest(
+            background="I am a data scientist"
+        )
+
+        profile = await memory.get_bank_profile(bank_id, request_context=request_context)
+
+        if request.background is not None:
+            pool = await memory._get_pool()
+            async with pool.acquire() as conn:
+                await conn.execute(
+                    """
+                    UPDATE banks
+                    SET background = $2,
+                        updated_at = NOW()
+                    WHERE bank_id = $1
+                    """,
+                    bank_id,
+                    request.background
+                )
+
+        final_profile = await memory.get_bank_profile(bank_id, request_context=request_context)
+
+        assert final_profile["disposition"].skepticism == 3  # Default
+        assert final_profile["background"] == "I am a data scientist"
 
 
 class TestAgentDispositionIntegration:
@@ -123,6 +225,13 @@ class TestAgentDispositionIntegration:
         }
         await memory.update_bank_disposition(bank_id, disposition, request_context=request_context)
 
+        await memory.merge_bank_background(
+            bank_id,
+            "I am a creative artist who values innovation over tradition",
+            update_disposition=False,
+            request_context=request_context,
+        )
+
         await memory.retain_batch_async(
             bank_id=bank_id,
             contents=[

hindsight-api/tests/test_emergent_filtering.py

@@ -1,516 +0,0 @@
-"""Tests for emergent entity filtering."""
-
-import pytest
-from unittest.mock import AsyncMock, MagicMock
-
-from hindsight_api.engine.mental_models.emergent import (
-    build_mission_filter_prompt,
-    evaluate_emergent_models,
-    filter_candidates_by_mission,
-    MissionFilterResponse,
-    MissionFilterCandidate,
-)
-from hindsight_api.engine.mental_models.models import EmergentCandidate
-
-
-class TestBuildMissionFilterPrompt:
-    """Test prompt building for mission filtering."""
-
-    def test_prompt_contains_mission(self):
-        """Test that prompt includes the mission."""
-        candidates = [
-            EmergentCandidate(
-                name="Alice",
-                detection_method="named_entity_extraction",
-                mention_count=10,
-            )
-        ]
-        prompt = build_mission_filter_prompt("Be a PM for engineering team", candidates)
-        assert "Be a PM for engineering team" in prompt
-
-    def test_prompt_contains_candidates(self):
-        """Test that prompt includes all candidates."""
-        candidates = [
-            EmergentCandidate(
-                name="Alice Chen",
-                detection_method="named_entity_extraction",
-                mention_count=10,
-            ),
-            EmergentCandidate(
-                name="Project Phoenix",
-                detection_method="named_entity_extraction",
-                mention_count=5,
-            ),
-        ]
-        prompt = build_mission_filter_prompt("Track projects", candidates)
-        assert "Alice Chen" in prompt
-        assert "Project Phoenix" in prompt
-
-    def test_prompt_contains_rejection_guidance(self):
-        """Test that prompt contains guidance to reject generic entities."""
-        candidates = [
-            EmergentCandidate(
-                name="test",
-                detection_method="named_entity_extraction",
-                mention_count=1,
-            )
-        ]
-        prompt = build_mission_filter_prompt("Test mission", candidates)
-
-        # Should contain rejection guidance for generic terms
-        assert "promote=false" in prompt
-        assert "kids" in prompt  # Example of generic term to reject
-        assert "community" in prompt  # Example of abstract concept to reject
-        assert "motivation" in prompt  # Example of abstract concept to reject
-
-
-class TestFilterCandidatesByMission:
-    """Test the filter_candidates_by_mission function."""
-
-    @pytest.fixture
-    def mock_llm_config(self):
-        """Create a mock LLM config."""
-        config = MagicMock()
-        config.call = AsyncMock()
-        return config
-
-    async def test_empty_candidates(self, mock_llm_config):
-        """Test with empty candidate list."""
-        result = await filter_candidates_by_mission(
-            llm_config=mock_llm_config,
-            mission="Test mission",
-            candidates=[],
-        )
-        assert result == []
-        mock_llm_config.call.assert_not_called()
-
-    async def test_no_mission_keeps_all(self, mock_llm_config):
-        """Test that no mission keeps all candidates (skips filtering)."""
-        candidates = [
-            EmergentCandidate(
-                name="Alice",
-                detection_method="named_entity_extraction",
-                mention_count=10,
-            )
-        ]
-        result = await filter_candidates_by_mission(
-            llm_config=mock_llm_config,
-            mission="",  # Empty mission
-            candidates=candidates,
-        )
-        assert len(result) == 1
-        assert result[0].name == "Alice"
-        mock_llm_config.call.assert_not_called()
-
-    async def test_filters_by_promote_flag(self, mock_llm_config):
-        """Test that candidates are filtered by promote flag."""
-        candidates = [
-            EmergentCandidate(
-                name="Alice Chen",
-                detection_method="named_entity_extraction",
-                mention_count=10,
-            ),
-            EmergentCandidate(
-                name="community",
-                detection_method="named_entity_extraction",
-                mention_count=5,
-            ),
-        ]
-
-        # Mock LLM response - Alice is promoted, community is not
-        mock_llm_config.call.return_value = MissionFilterResponse(
-            candidates=[
-                MissionFilterCandidate(name="Alice Chen", promote=True, reason="Specific person"),
-                MissionFilterCandidate(name="community", promote=False, reason="Generic abstract concept"),
-            ]
-        )
-
-        result = await filter_candidates_by_mission(
-            llm_config=mock_llm_config,
-            mission="Be a PM for engineering team",
-            candidates=candidates,
-        )
-
-        assert len(result) == 1
-        assert result[0].name == "Alice Chen"
-
-    async def test_rejects_generic_entities(self, mock_llm_config):
-        """Test that generic entities are rejected."""
-        # These are all generic/abstract terms that should be rejected
-        generic_names = [
-            "user", "support", "community", "family", "motivation",
-            "photo", "gratitude", "difference", "volunteering",
-            "kids", "veterans", "impact", "kindness", "encouragement",
-            "education", "nature", "joy", "positivity", "inspiration",
-            "help", "commitment", "passion", "energy", "connection",
-        ]
-        candidates = [
-            EmergentCandidate(
-                name=name,
-                detection_method="named_entity_extraction",
-                mention_count=10,
-            )
-            for name in generic_names
-        ]
-
-        # Add some valid candidates
-        valid_candidates = [
-            EmergentCandidate(
-                name="John",
-                detection_method="named_entity_extraction",
-                mention_count=10,
-            ),
-            EmergentCandidate(
-                name="Maria",
-                detection_method="named_entity_extraction",
-                mention_count=8,
-            ),
-            EmergentCandidate(
-                name="Max",
-                detection_method="named_entity_extraction",
-                mention_count=6,
-            ),
-        ]
-        candidates.extend(valid_candidates)
-
-        # Mock LLM response - reject all generic, promote only specific names
-        response_candidates = [
-            MissionFilterCandidate(name=name, promote=False, reason="Generic/abstract term")
-            for name in generic_names
-        ]
-        response_candidates.extend([
-            MissionFilterCandidate(name=c.name, promote=True, reason="Specific person name")
-            for c in valid_candidates
-        ])
-
-        mock_llm_config.call.return_value = MissionFilterResponse(candidates=response_candidates)
-
-        result = await filter_candidates_by_mission(
-            llm_config=mock_llm_config,
-            mission="Be a health coach",
-            candidates=candidates,
-        )
-
-        # Should only have John, Maria, and Max
-        result_names = {c.name for c in result}
-        assert result_names == {"John", "Maria", "Max"}
-
-    async def test_accepts_specific_named_entities(self, mock_llm_config):
-        """Test that specific named entities are accepted."""
-        # These should all be accepted
-        valid_names = [
-            "Alice Chen",       # Full name
-            "Dr. Smith",        # Title + name
-            "John",             # First name (when it's clearly a person)
-            "Google",           # Organization
-            "Frontend Team",    # Named team
-            "Project Phoenix",  # Named project
-            "NYC Office",       # Named place
-            "Q4 Planning",      # Named event
-            "Sprint 23 Review", # Named meeting
-        ]
-        candidates = [
-            EmergentCandidate(
-                name=name,
-                detection_method="named_entity_extraction",
-                mention_count=10,
-            )
-            for name in valid_names
-        ]
-
-        # Mock LLM response - promote all
-        response_candidates = [
-            MissionFilterCandidate(name=name, promote=True, reason="Specific named entity")
-            for name in valid_names
-        ]
-        mock_llm_config.call.return_value = MissionFilterResponse(candidates=response_candidates)
-
-        result = await filter_candidates_by_mission(
-            llm_config=mock_llm_config,
-            mission="Be a PM for engineering team",
-            candidates=candidates,
-        )
-
-        # Should have all valid names
-        result_names = {c.name for c in result}
-        assert result_names == set(valid_names)
-
-    async def test_llm_error_rejects_all_candidates(self, mock_llm_config):
-        """Test that LLM errors result in rejecting all candidates (fail-safe)."""
-        candidates = [
-            EmergentCandidate(
-                name="Alice",
-                detection_method="named_entity_extraction",
-                mention_count=10,
-            )
-        ]
-
-        mock_llm_config.call.side_effect = Exception("LLM error")
-
-        result = await filter_candidates_by_mission(
-            llm_config=mock_llm_config,
-            mission="Test mission",
-            candidates=candidates,
-        )
-
-        # Should reject all candidates on error (fail-safe)
-        assert len(result) == 0
-
-    async def test_missing_candidate_in_response_is_rejected(self, mock_llm_config):
-        """Test that candidates not in LLM response are rejected by default."""
-        candidates = [
-            EmergentCandidate(
-                name="Alice",
-                detection_method="named_entity_extraction",
-                mention_count=10,
-            ),
-            EmergentCandidate(
-                name="Bob",
-                detection_method="named_entity_extraction",
-                mention_count=5,
-            ),
-        ]
-
-        # Mock LLM response - only includes Alice, not Bob
-        mock_llm_config.call.return_value = MissionFilterResponse(
-            candidates=[
-                MissionFilterCandidate(name="Alice", promote=True, reason="Specific person"),
-            ]
-        )
-
-        result = await filter_candidates_by_mission(
-            llm_config=mock_llm_config,
-            mission="Test mission",
-            candidates=candidates,
-        )
-
-        # Only Alice should be in result (Bob was missing from response, so rejected)
-        assert len(result) == 1
-        assert result[0].name == "Alice"
-
-
-class TestEvaluateEmergentModels:
-    """Test the evaluate_emergent_models function for cleanup of existing models."""
-
-    @pytest.fixture
-    def mock_llm_config(self):
-        """Create a mock LLM config."""
-        config = MagicMock()
-        config.call = AsyncMock()
-        return config
-
-    async def test_empty_models(self, mock_llm_config):
-        """Test with empty model list."""
-        result = await evaluate_emergent_models(
-            llm_config=mock_llm_config,
-            models=[],
-        )
-        assert result == []
-        mock_llm_config.call.assert_not_called()
-
-    async def test_removes_generic_models(self, mock_llm_config):
-        """Test that generic/abstract models are marked for removal."""
-        models = [
-            {"id": "id-kids", "name": "kids"},
-            {"id": "id-community", "name": "community"},
-            {"id": "id-motivation", "name": "motivation"},
-            {"id": "id-john", "name": "John"},
-            {"id": "id-maria", "name": "Maria"},
-        ]
-
-        # Mock LLM response - reject generic, keep specific names
-        mock_llm_config.call.return_value = MissionFilterResponse(
-            candidates=[
-                MissionFilterCandidate(name="kids", promote=False, reason="Generic category"),
-                MissionFilterCandidate(name="community", promote=False, reason="Abstract concept"),
-                MissionFilterCandidate(name="motivation", promote=False, reason="Abstract concept"),
-                MissionFilterCandidate(name="John", promote=True, reason="Person name"),
-                MissionFilterCandidate(name="Maria", promote=True, reason="Person name"),
-            ]
-        )
-
-        result = await evaluate_emergent_models(
-            llm_config=mock_llm_config,
-            models=models,
-        )
-
-        # Should return IDs of generic models to remove
-        assert set(result) == {"id-kids", "id-community", "id-motivation"}
-
-    async def test_keeps_specific_named_models(self, mock_llm_config):
-        """Test that specific named models are kept."""
-        models = [
-            {"id": "id-john", "name": "John"},
-            {"id": "id-google", "name": "Google"},
-            {"id": "id-project", "name": "Project Phoenix"},
-        ]
-
-        # Mock LLM response - keep all
-        mock_llm_config.call.return_value = MissionFilterResponse(
-            candidates=[
-                MissionFilterCandidate(name="John", promote=True, reason="Person name"),
-                MissionFilterCandidate(name="Google", promote=True, reason="Organization"),
-                MissionFilterCandidate(name="Project Phoenix", promote=True, reason="Named project"),
-            ]
-        )
-
-        result = await evaluate_emergent_models(
-            llm_config=mock_llm_config,
-            models=models,
-        )
-
-        # No models should be removed
-        assert result == []
-
-    async def test_llm_error_keeps_all_models(self, mock_llm_config):
-        """Test that LLM errors result in keeping all models (safe default)."""
-        models = [
-            {"id": "id-kids", "name": "kids"},
-            {"id": "id-john", "name": "John"},
-        ]
-
-        mock_llm_config.call.side_effect = Exception("LLM error")
-
-        result = await evaluate_emergent_models(
-            llm_config=mock_llm_config,
-            models=models,
-        )
-
-        # Should keep all models on error (return empty removal list)
-        assert result == []
-
-    async def test_missing_model_in_response_is_removed(self, mock_llm_config):
-        """Test that models not in LLM response are marked for removal."""
-        models = [
-            {"id": "id-alice", "name": "Alice"},
-            {"id": "id-bob", "name": "Bob"},
-        ]
-
-        # Mock LLM response - only includes Alice
-        mock_llm_config.call.return_value = MissionFilterResponse(
-            candidates=[
-                MissionFilterCandidate(name="Alice", promote=True, reason="Person name"),
-            ]
-        )
-
-        result = await evaluate_emergent_models(
-            llm_config=mock_llm_config,
-            models=models,
-        )
-
-        # Bob should be marked for removal (missing from response)
-        assert result == ["id-bob"]
-
-
-class TestRemovedEntitiesNotRepromoted:
-    """Test that entities removed by evaluation are not re-promoted.
-
-    This tests the fix for a bug where:
-    1. evaluate_emergent_models returns model IDs to remove (e.g., 'entity-maya')
-    2. We delete those models
-    3. detect_entity_candidates finds the same entities (now eligible since model was deleted)
-    4. filter_candidates_by_goal approves them (different LLM call)
-    5. BUG: We were re-promoting the same entities we just removed
-
-    The fix tracks removed entity_ids and excludes them from promotion.
-    """
-
-    async def test_removed_entity_ids_excluded_from_promotion(self):
-        """Test that entities whose models were removed are not re-promoted."""
-        from hindsight_api.engine.mental_models.models import EmergentCandidate
-
-        # Simulate the scenario from the bug:
-        # - existing_emergent has model 'entity-maya' with entity_id='uuid-maya'
-        # - evaluate_emergent_models says to remove 'entity-maya'
-        # - detect_entity_candidates returns 'Maya' with entity_id='uuid-maya' (now eligible)
-        # - filter_candidates_by_goal says to promote 'Maya'
-        # - But we should NOT promote because we just removed it
-
-        existing_emergent = [
-            {"id": "entity-maya", "name": "Maya", "entity_id": "uuid-maya"},
-            {"id": "entity-alex", "name": "Alex", "entity_id": "uuid-alex"},
-            {"id": "entity-john", "name": "John", "entity_id": "uuid-john"},  # This one will be kept
-        ]
-
-        # Models to remove (evaluate_emergent_models would return these)
-        models_to_remove = ["entity-maya", "entity-alex"]
-
-        # Build model_id -> entity_id mapping (this is what the fix does)
-        model_to_entity = {m["id"]: m.get("entity_id") for m in existing_emergent}
-
-        # Track removed entity_ids
-        removed_entity_ids: set[str] = set()
-        for model_id in models_to_remove:
-            entity_id = model_to_entity.get(model_id)
-            if entity_id:
-                removed_entity_ids.add(str(entity_id))
-
-        # Verify we tracked the right entity_ids
-        assert removed_entity_ids == {"uuid-maya", "uuid-alex"}
-
-        # Now simulate candidates that were detected (includes removed entities)
-        candidates = [
-            EmergentCandidate(
-                name="Maya", entity_id="uuid-maya", detection_method="named_entity", mention_count=10
-            ),
-            EmergentCandidate(
-                name="Alex", entity_id="uuid-alex", detection_method="named_entity", mention_count=8
-            ),
-            EmergentCandidate(
-                name="NewPerson", entity_id="uuid-new", detection_method="named_entity", mention_count=5
-            ),
-        ]
-
-        # Filter out candidates whose entity was just removed (the fix)
-        filtered_candidates = [c for c in candidates if c.entity_id not in removed_entity_ids]
-
-        # Only NewPerson should remain - Maya and Alex were removed and should not be re-promoted
-        assert len(filtered_candidates) == 1
-        assert filtered_candidates[0].name == "NewPerson"
-        assert filtered_candidates[0].entity_id == "uuid-new"
-
-    async def test_candidates_without_matching_removal_are_kept(self):
-        """Test that candidates not in the removed set are still promoted."""
-        from hindsight_api.engine.mental_models.models import EmergentCandidate
-
-        # No models removed
-        removed_entity_ids: set[str] = set()
-
-        candidates = [
-            EmergentCandidate(
-                name="Alice", entity_id="uuid-alice", detection_method="named_entity", mention_count=10
-            ),
-            EmergentCandidate(
-                name="Bob", entity_id="uuid-bob", detection_method="named_entity", mention_count=8
-            ),
-        ]
-
-        # Filter (should keep all since nothing was removed)
-        filtered_candidates = [c for c in candidates if c.entity_id not in removed_entity_ids]
-
-        assert len(filtered_candidates) == 2
-        assert {c.name for c in filtered_candidates} == {"Alice", "Bob"}
-
-    async def test_partial_removal_keeps_other_candidates(self):
-        """Test that only removed entities are excluded, others pass through."""
-        from hindsight_api.engine.mental_models.models import EmergentCandidate
-
-        # Only one entity removed
-        removed_entity_ids = {"uuid-removed"}
-
-        candidates = [
-            EmergentCandidate(
-                name="Removed", entity_id="uuid-removed", detection_method="named_entity", mention_count=10
-            ),
-            EmergentCandidate(
-                name="Kept1", entity_id="uuid-kept1", detection_method="named_entity", mention_count=8
-            ),
-            EmergentCandidate(
-                name="Kept2", entity_id="uuid-kept2", detection_method="named_entity", mention_count=5
-            ),
-        ]
-
-        filtered_candidates = [c for c in candidates if c.entity_id not in removed_entity_ids]
-
-        assert len(filtered_candidates) == 2
-        assert {c.name for c in filtered_candidates} == {"Kept1", "Kept2"}

hindsight-api/tests/test_extensions.py

@@ -17,8 +17,6 @@ from hindsight_api.extensions import (
     RecallResult,
     ReflectContext,
     ReflectResultContext,
-    RefreshMentalModelContext,
-    RefreshMentalModelResult,
     RequestContext,
     RetainContext,
     RetainResult,
@@ -95,7 +93,6 @@ class RateLimitingValidator(OperationValidatorExtension):
         self.retain_counts: dict[str, int] = defaultdict(int)
         self.recall_counts: dict[str, int] = defaultdict(int)
         self.reflect_counts: dict[str, int] = defaultdict(int)
-        self.refresh_mental_model_counts: dict[str, int] = defaultdict(int)
 
     async def validate_retain(self, ctx: RetainContext) -> ValidationResult:
         self.retain_counts[ctx.bank_id] += 1
@@ -121,16 +118,6 @@ class RateLimitingValidator(OperationValidatorExtension):
             )
         return ValidationResult.accept()
 
-    async def validate_refresh_mental_model(
-        self, ctx: RefreshMentalModelContext
-    ) -> ValidationResult:
-        self.refresh_mental_model_counts[ctx.bank_id] += 1
-        if self.refresh_mental_model_counts[ctx.bank_id] > self.max_attempts:
-            return ValidationResult.reject(
-                f"Refresh mental model limit exceeded for bank {ctx.bank_id}"
-            )
-        return ValidationResult.accept()
-
 
 class TrackingValidator(OperationValidatorExtension):
     """
@@ -145,12 +132,10 @@ class TrackingValidator(OperationValidatorExtension):
         self.pre_retain_calls: list[RetainContext] = []
         self.pre_recall_calls: list[RecallContext] = []
         self.pre_reflect_calls: list[ReflectContext] = []
-        self.pre_refresh_mental_model_calls: list[RefreshMentalModelContext] = []
         # Post-hook tracking
         self.post_retain_calls: list[RetainResult] = []
         self.post_recall_calls: list[RecallResult] = []
         self.post_reflect_calls: list[ReflectResultContext] = []
-        self.post_refresh_mental_model_calls: list[RefreshMentalModelResult] = []
 
     async def validate_retain(self, ctx: RetainContext) -> ValidationResult:
         self.pre_retain_calls.append(ctx)
@@ -164,12 +149,6 @@ class TrackingValidator(OperationValidatorExtension):
         self.pre_reflect_calls.append(ctx)
         return ValidationResult.accept()
 
-    async def validate_refresh_mental_model(
-        self, ctx: RefreshMentalModelContext
-    ) -> ValidationResult:
-        self.pre_refresh_mental_model_calls.append(ctx)
-        return ValidationResult.accept()
-
     async def on_retain_complete(self, result: RetainResult) -> None:
         self.post_retain_calls.append(result)
 
@@ -179,11 +158,6 @@ class TrackingValidator(OperationValidatorExtension):
     async def on_reflect_complete(self, result: ReflectResultContext) -> None:
         self.post_reflect_calls.append(result)
 
-    async def on_refresh_mental_model_complete(
-        self, result: RefreshMentalModelResult
-    ) -> None:
-        self.post_refresh_mental_model_calls.append(result)
-
 
 class TestMemoryEngineValidation:
     """Tests for validation integration with MemoryEngine.
@@ -541,105 +515,6 @@ class TestOperationHooksParameters:
         assert len(validator.pre_recall_calls) == 1
         assert len(validator.post_recall_calls) == 1
 
-    @pytest.mark.asyncio
-    async def test_refresh_mental_model_pre_hook_receives_all_parameters(
-        self, memory_with_tracking_validator
-    ):
-        """Pre-refresh-mental-model hook receives all user-provided parameters."""
-        import uuid
-
-        memory, validator = memory_with_tracking_validator
-        bank_id = f"test-refresh-mm-params-{uuid.uuid4().hex[:8]}"
-        ctx = RequestContext(api_key="test-key")
-
-        # Create bank first (get_bank_profile auto-creates if needed)
-        await memory.get_bank_profile(bank_id, request_context=ctx)
-
-        # Create a pinned mental model
-        model = await memory.create_mental_model(
-            bank_id=bank_id,
-            name="Test Model",
-            description="Test description",
-            subtype="pinned",
-            request_context=ctx,
-        )
-
-        assert model is not None
-        model_id = model["id"]
-
-        # Attempt to refresh (may not actually refresh if no data, but hook should be called)
-        try:
-            await memory.refresh_mental_model(
-                bank_id=bank_id,
-                model_id=model_id,
-                request_context=ctx,
-            )
-        except Exception:
-            pass  # May fail if no data
-
-        # Check pre-hook was called
-        assert len(validator.pre_refresh_mental_model_calls) == 1
-        pre_ctx = validator.pre_refresh_mental_model_calls[0]
-        assert pre_ctx.bank_id == bank_id
-        assert pre_ctx.model_id == model_id
-        assert pre_ctx.request_context == ctx
-
-    @pytest.mark.asyncio
-    async def test_refresh_mental_model_post_hook_receives_token_usage(
-        self, memory_with_tracking_validator
-    ):
-        """Post-refresh-mental-model hook receives token usage information."""
-        import uuid
-
-        memory, validator = memory_with_tracking_validator
-        bank_id = f"test-refresh-mm-tokens-{uuid.uuid4().hex[:8]}"
-        ctx = RequestContext(api_key="test-key")
-
-        # Store some content first
-        await memory.retain_batch_async(
-            bank_id=bank_id,
-            contents=[
-                {"content": "Alice is a software engineer who works on machine learning."},
-                {"content": "Alice enjoys hiking and outdoor activities on weekends."},
-                {"content": "Alice has been working at the company for 5 years."},
-            ],
-            request_context=ctx,
-        )
-
-        # Create a pinned mental model
-        model = await memory.create_mental_model(
-            bank_id=bank_id,
-            name="Alice Profile",
-            description="Profile of Alice including work and hobbies",
-            subtype="pinned",
-            request_context=ctx,
-        )
-
-        if model:
-            model_id = model["id"]
-
-            # Refresh the mental model
-            result = await memory.refresh_mental_model(
-                bank_id=bank_id,
-                model_id=model_id,
-                request_context=ctx,
-            )
-
-            # Check post-hook was called with token usage
-            if validator.post_refresh_mental_model_calls:
-                post_result = validator.post_refresh_mental_model_calls[0]
-                assert post_result.bank_id == bank_id
-                assert post_result.model_id == model_id
-                assert post_result.request_context == ctx
-                assert post_result.success is True
-                assert post_result.error is None
-
-                # Token usage should be populated (may be 0 if refresh was skipped)
-                assert post_result.total_tokens >= 0
-                assert post_result.input_tokens >= 0
-                assert post_result.output_tokens >= 0
-                assert post_result.duration_ms >= 0
-
 
 class TestTenantExtension:
     """Tests for TenantExtension and ApiKeyTenantExtension."""

hindsight-api/tests/test_fact_extraction_quality.py

@@ -947,3 +947,172 @@ so the algorithm learns to box out. See you next week!
                     raise e
 
 
+# =============================================================================
+# DISPOSITION INFERENCE TESTS
+# =============================================================================
+
+class TestDispositionInference:
+    """Tests for LLM-based disposition trait inference from background."""
+
+    @pytest.mark.asyncio
+    async def test_background_merge_with_disposition_inference(self, memory, request_context):
+        """Test that background merge infers disposition traits by default."""
+        import uuid
+        bank_id = f"test_infer_{uuid.uuid4().hex[:8]}"
+
+        result = await memory.merge_bank_background(
+            bank_id,
+            "I am a creative software engineer who loves innovation and trying new technologies",
+            update_disposition=True,
+            request_context=request_context,
+        )
+
+        assert "background" in result
+        assert "disposition" in result
+
+        background = result["background"]
+        disposition = result["disposition"]
+
+        assert "creative" in background.lower() or "innovation" in background.lower()
+
+        # Check that new traits are present with valid values (1-5)
+        required_traits = ["skepticism", "literalism", "empathy"]
+        for trait in required_traits:
+            assert trait in disposition
+            assert 1 <= disposition[trait] <= 5
+
+    @pytest.mark.asyncio
+    async def test_background_merge_without_disposition_inference(self, memory, request_context):
+        """Test that background merge skips disposition inference when disabled."""
+        import uuid
+        bank_id = f"test_no_infer_{uuid.uuid4().hex[:8]}"
+
+        initial_profile = await memory.get_bank_profile(bank_id, request_context=request_context)
+        initial_disposition = initial_profile["disposition"]
+
+        result = await memory.merge_bank_background(
+            bank_id,
+            "I am a data scientist",
+            update_disposition=False,
+            request_context=request_context,
+        )
+
+        assert "background" in result
+        assert "disposition" not in result
+
+        final_profile = await memory.get_bank_profile(bank_id, request_context=request_context)
+        final_disposition = final_profile["disposition"]
+
+        assert initial_disposition == final_disposition
+
+    @pytest.mark.asyncio
+    async def test_disposition_inference_for_lawyer(self, memory, request_context):
+        """Test disposition inference for lawyer profile (high skepticism, high literalism)."""
+        import uuid
+        bank_id = f"test_lawyer_{uuid.uuid4().hex[:8]}"
+
+        result = await memory.merge_bank_background(
+            bank_id,
+            "I am a lawyer who focuses on contract details and never takes claims at face value",
+            update_disposition=True,
+            request_context=request_context,
+        )
+
+        disposition = result["disposition"]
+
+        # Lawyers should have higher skepticism and literalism
+        assert disposition["skepticism"] >= 3
+        assert disposition["literalism"] >= 3
+
+    @pytest.mark.asyncio
+    async def test_disposition_inference_for_therapist(self, memory, request_context):
+        """Test disposition inference for therapist profile (high empathy)."""
+        import uuid
+        bank_id = f"test_therapist_{uuid.uuid4().hex[:8]}"
+
+        result = await memory.merge_bank_background(
+            bank_id,
+            "I am a therapist who deeply understands and connects with people's emotional struggles",
+            update_disposition=True,
+            request_context=request_context,
+        )
+
+        disposition = result["disposition"]
+
+        # Therapists should have higher empathy
+        assert disposition["empathy"] >= 3
+
+    @pytest.mark.asyncio
+    async def test_disposition_updates_in_database(self, memory, request_context):
+        """Test that inferred disposition is actually stored in database."""
+        import uuid
+        bank_id = f"test_db_update_{uuid.uuid4().hex[:8]}"
+
+        result = await memory.merge_bank_background(
+            bank_id,
+            "I am an innovative designer",
+            update_disposition=True,
+            request_context=request_context,
+        )
+
+        inferred_disposition = result["disposition"]
+
+        profile = await memory.get_bank_profile(bank_id, request_context=request_context)
+        db_disposition = profile["disposition"]
+
+        # Compare values (db_disposition is a Pydantic model)
+        assert db_disposition.skepticism == inferred_disposition["skepticism"]
+        assert db_disposition.literalism == inferred_disposition["literalism"]
+        assert db_disposition.empathy == inferred_disposition["empathy"]
+
+    @pytest.mark.asyncio
+    async def test_multiple_background_merges_update_disposition(self, memory, request_context):
+        """Test that each background merge can update disposition."""
+        import uuid
+        bank_id = f"test_multi_merge_{uuid.uuid4().hex[:8]}"
+
+        result1 = await memory.merge_bank_background(
+            bank_id,
+            "I am a software engineer",
+            update_disposition=True,
+            request_context=request_context,
+        )
+        disposition1 = result1["disposition"]
+
+        result2 = await memory.merge_bank_background(
+            bank_id,
+            "I love creative problem solving and innovation",
+            update_disposition=True,
+            request_context=request_context,
+        )
+        disposition2 = result2["disposition"]
+
+        assert "engineer" in result2["background"].lower() or "software" in result2["background"].lower()
+        assert "creative" in result2["background"].lower() or "innovation" in result2["background"].lower()
+
+    @pytest.mark.asyncio
+    async def test_background_merge_conflict_resolution_with_disposition(self, memory, request_context):
+        """Test that conflicts are resolved and disposition reflects final background."""
+        import uuid
+        bank_id = f"test_conflict_{uuid.uuid4().hex[:8]}"
+
+        await memory.merge_bank_background(
+            bank_id,
+            "I was born in Colorado and prefer stability",
+            update_disposition=True,
+            request_context=request_context,
+        )
+
+        result = await memory.merge_bank_background(
+            bank_id,
+            "You were born in Texas and are very skeptical of people",
+            update_disposition=True,
+            request_context=request_context,
+        )
+
+        background = result["background"]
+        disposition = result["disposition"]
+
+        assert "texas" in background.lower()
+        # Higher skepticism expected from "very skeptical of people"
+        assert disposition["skepticism"] >= 3

hindsight-api/tests/test_fact_ordering.py

@@ -51,7 +51,7 @@ Marcus: Yeah, I realized I was being too optimistic about their defense.
     results = await memory.recall_async(
         bank_id=bank_id,
         query="Marcus prediction Rams",
-        fact_type=['experience', 'world'],
+        fact_type=['opinion', 'experience', 'world'],
         budget=Budget.LOW,
         max_tokens=8192,
         request_context=request_context,
@@ -61,8 +61,8 @@ Marcus: Yeah, I realized I was being too optimistic about their defense.
     for i, result in enumerate(results.results):
         print(f"{i+1}. [{result.mentioned_at}] {result.text[:100]}")
 
-    # Get all facts (Marcus's predictions/statements)
-    agent_facts = results.results
+    # Get all opinion facts (Marcus's predictions/statements)
+    agent_facts = [r for r in results.results if r.fact_type == 'opinion']
 
     print(f"\n=== Agent facts (Marcus's statements) ===")
     for i, fact in enumerate(agent_facts):
@@ -70,7 +70,6 @@ Marcus: Yeah, I realized I was being too optimistic about their defense.
 
     # Check that agent facts have different timestamps
     if len(agent_facts) >= 2:
-        # Parse timestamps
         timestamps = [datetime.fromisoformat(f.mentioned_at.replace('Z', '+00:00')) for f in agent_facts]
 
         # Verify timestamps are different (have time offsets)
@@ -78,40 +77,42 @@ Marcus: Yeah, I realized I was being too optimistic about their defense.
         assert len(unique_timestamps) == len(timestamps), \
             f"Expected unique timestamps for each fact, but got duplicates: {timestamps}"
 
-        # Sort facts by timestamp for ordering check
-        # Note: recall returns by relevance, not time order
-        sorted_facts = sorted(agent_facts, key=lambda f: datetime.fromisoformat(f.mentioned_at.replace('Z', '+00:00')))
-        sorted_timestamps = [datetime.fromisoformat(f.mentioned_at.replace('Z', '+00:00')) for f in sorted_facts]
-
-        # Verify sorted timestamps are in ascending order
-        for i in range(len(sorted_timestamps) - 1):
-            assert sorted_timestamps[i] < sorted_timestamps[i + 1], \
-                f"Facts should have sequential timestamps. Fact {i} ({sorted_timestamps[i]}) >= Fact {i+1} ({sorted_timestamps[i+1]})"
+        # Verify timestamps are in order (ascending)
+        for i in range(len(timestamps) - 1):
+            assert timestamps[i] < timestamps[i + 1], \
+                f"Facts should be ordered by time. Fact {i} ({timestamps[i]}) >= Fact {i+1} ({timestamps[i+1]})"
 
         # Verify reasonable time spacing (should be ~10 seconds apart)
-        time_diffs = [(sorted_timestamps[i+1] - sorted_timestamps[i]).total_seconds() for i in range(len(sorted_timestamps) - 1)]
+        time_diffs = [(timestamps[i+1] - timestamps[i]).total_seconds() for i in range(len(timestamps) - 1)]
         print(f"\n=== Time differences between facts: {time_diffs} seconds ===")
 
         # Each fact should be 10+ seconds apart (allowing for some flexibility)
         for diff in time_diffs:
             assert diff >= 5, f"Expected at least 5 seconds between facts, got {diff}"
 
-        # Update agent_facts to be sorted for subsequent checks
-        agent_facts = sorted_facts
-        timestamps = sorted_timestamps
-
         print(f"\n✅ All {len(agent_facts)} agent facts have properly ordered timestamps")
 
-    # Verify that facts capture the key information
-    # Note: LLM may merge related predictions into single facts
+    # Verify that retrieval returns facts in chronological order
+    # The first prediction should come before the changed prediction
     agent_texts = [f.text.lower() for f in agent_facts]
-    all_text = " ".join(agent_texts)
 
-    # Look for evidence of the predictions being captured (may be merged or separate)
-    has_prediction_info = '27' in all_text or 'rams' in all_text or 'prediction' in all_text
+    # Look for evidence of the sequence
+    has_first_prediction = any('27' in text and '24' in text for text in agent_texts)
+    has_changed_prediction = any('chang' in text or 'by 3' in text or 'realized' in text for text in agent_texts)
 
-    assert has_prediction_info, "Facts should contain information about Marcus's predictions"
-    print(f"\n✅ Facts capture prediction information")
+    if has_first_prediction and has_changed_prediction:
+        # Find indices
+        first_idx = next(i for i, text in enumerate(agent_texts) if '27' in text and '24' in text)
+        changed_idx = next(i for i, text in enumerate(agent_texts) if 'chang' in text or 'by 3' in text or 'realized' in text)
+
+        print(f"\nFirst prediction at index {first_idx}: {agent_facts[first_idx].text[:100]}")
+        print(f"Changed prediction at index {changed_idx}: {agent_facts[changed_idx].text[:100]}")
+
+        # The original prediction should come before the changed one
+        assert timestamps[first_idx] < timestamps[changed_idx], \
+            "Original prediction should have earlier timestamp than changed prediction"
+
+        print(f"\n✅ Temporal ordering preserved: First prediction came before changed prediction")
 
     # Cleanup
     await memory.delete_bank(bank_id, request_context=request_context)
@@ -155,14 +156,14 @@ Alice: I reconsidered the team's experience level.
     results = await memory.recall_async(
         bank_id=bank_id,
         query="Alice preference React Vue",
-        fact_type=['experience', 'world'],
+        fact_type=['opinion', 'experience'],
         budget=Budget.LOW,
         max_tokens=8192,
         request_context=request_context,
     )
 
     print(f"\n=== Retrieved {len(results.results)} agent facts ===")
-    agent_facts = results.results
+    agent_facts = [r for r in results.results if r.fact_type in ('opinion', 'experience')]
 
     for i, fact in enumerate(agent_facts):
         print(f"{i+1}. [{fact.mentioned_at}] {fact.text[:80]}")

hindsight-api/tests/test_http_api_integration.py

@@ -60,6 +60,17 @@ async def test_full_api_workflow(api_client, test_bank_id):
     assert response.status_code == 200
     profile = response.json()
     assert "disposition" in profile
+    assert "background" in profile
+
+    # Add background
+    response = await api_client.post(
+        f"/v1/default/banks/{test_bank_id}/background",
+        json={
+            "content": "A software engineer passionate about AI and memory systems."
+        }
+    )
+    assert response.status_code == 200
+    assert "software engineer" in response.json()["background"].lower()
 
     # ================================================================
     # 2. Memory Storage
@@ -233,9 +244,7 @@ async def test_full_api_workflow(api_client, test_bank_id):
     response = await api_client.get(f"/v1/default/banks/{test_bank_id}/profile")
     assert response.status_code == 200
     updated_profile = response.json()
-    assert updated_profile["disposition"]["skepticism"] == 4
-    assert updated_profile["disposition"]["literalism"] == 3
-    assert updated_profile["disposition"]["empathy"] == 4
+    assert "software engineer" in updated_profile["background"].lower()
 
     # ================================================================
     # 8. Test Entity Endpoints
@@ -280,11 +289,11 @@ async def test_full_api_workflow(api_client, test_bank_id):
         entity_detail = response.json()
         assert "id" in entity_detail
 
-        # Test regenerate observations (deprecated - returns 410 Gone)
+        # Test regenerate observations
         response = await api_client.post(
             f"/v1/default/banks/{test_bank_id}/entities/{entity_id}/regenerate"
         )
-        assert response.status_code == 410  # Deprecated endpoint
+        assert response.status_code == 200
 
     # ================================================================
     # 9. List All Banks (should include our test bank)
@@ -836,8 +845,9 @@ async def test_reflect_structured_output(api_client):
     assert response.status_code == 200
     result = response.json()
 
-    # Verify text field exists (may contain text even with structured output)
+    # Verify text field exists (empty when using structured output)
     assert "text" in result
+    assert result["text"] == ""
 
     # Verify structured output exists and has expected structure
     assert "structured_output" in result
@@ -969,24 +979,20 @@ async def test_reflect_returns_token_usage(api_client):
     assert "text" in result
     assert len(result["text"]) > 0
 
-    # Verify usage field exists (may be None for agentic reflect which makes multiple LLM calls)
+    # Verify usage field exists and has expected structure
     assert "usage" in result, "Response should include 'usage' field"
     usage = result["usage"]
+    assert usage is not None, "Usage should not be None for reflect"
+    assert "input_tokens" in usage, "Usage should have 'input_tokens'"
+    assert "output_tokens" in usage, "Usage should have 'output_tokens'"
+    assert "total_tokens" in usage, "Usage should have 'total_tokens'"
 
-    # Usage is optional - agentic reflect doesn't aggregate multiple LLM call usages
-    if usage is not None:
-        assert "input_tokens" in usage, "Usage should have 'input_tokens'"
-        assert "output_tokens" in usage, "Usage should have 'output_tokens'"
-        assert "total_tokens" in usage, "Usage should have 'total_tokens'"
+    # Verify token counts are valid
+    assert usage["input_tokens"] > 0, f"Expected input_tokens > 0, got {usage['input_tokens']}"
+    assert usage["output_tokens"] >= 0, f"Expected output_tokens >= 0, got {usage['output_tokens']}"
+    assert usage["total_tokens"] == usage["input_tokens"] + usage["output_tokens"]
 
-        # Verify token counts are valid
-        assert usage["input_tokens"] > 0, f"Expected input_tokens > 0, got {usage['input_tokens']}"
-        assert usage["output_tokens"] >= 0, f"Expected output_tokens >= 0, got {usage['output_tokens']}"
-        assert usage["total_tokens"] == usage["input_tokens"] + usage["output_tokens"]
-
-        print(f"Reflect token usage: input={usage['input_tokens']}, output={usage['output_tokens']}, total={usage['total_tokens']}")
-    else:
-        print("Reflect usage is None (expected for agentic reflect)")
+    print(f"Reflect token usage: input={usage['input_tokens']}, output={usage['output_tokens']}, total={usage['total_tokens']}")
 
 
 @pytest.mark.asyncio

hindsight-api/tests/test_llm_tools.py

@@ -1,325 +0,0 @@
-"""
-Tests for LLM tool calling functionality.
-"""
-
-import pytest
-
-from hindsight_api.engine.llm_wrapper import LLMProvider
-from hindsight_api.engine.response_models import LLMToolCall, LLMToolCallResult
-
-
-# Sample tools for testing
-SAMPLE_TOOLS = [
-    {
-        "type": "function",
-        "function": {
-            "name": "get_weather",
-            "description": "Get weather for a location",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "location": {"type": "string", "description": "City name"},
-                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
-                },
-                "required": ["location"],
-            },
-        },
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "search",
-            "description": "Search for information",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "query": {"type": "string", "description": "Search query"},
-                },
-                "required": ["query"],
-            },
-        },
-    },
-]
-
-
-class TestMockToolCalling:
-    """Test tool calling with mock provider."""
-
-    @pytest.mark.asyncio
-    async def test_call_with_tools_returns_tool_calls(self):
-        """Test that mock provider can return tool calls."""
-        llm = LLMProvider(provider="mock", api_key="", base_url="", model="mock")
-
-        # Set mock response to return tool calls
-        llm.set_mock_response([
-            {"name": "get_weather", "arguments": {"location": "Paris", "unit": "celsius"}},
-        ])
-
-        result = await llm.call_with_tools(
-            messages=[{"role": "user", "content": "What's the weather in Paris?"}],
-            tools=SAMPLE_TOOLS,
-        )
-
-        assert isinstance(result, LLMToolCallResult)
-        assert len(result.tool_calls) == 1
-        assert result.tool_calls[0].name == "get_weather"
-        assert result.tool_calls[0].arguments == {"location": "Paris", "unit": "celsius"}
-        assert result.finish_reason == "tool_calls"
-
-    @pytest.mark.asyncio
-    async def test_call_with_tools_returns_content(self):
-        """Test that mock provider can return plain content."""
-        llm = LLMProvider(provider="mock", api_key="", base_url="", model="mock")
-
-        # Default mock response is plain content
-        result = await llm.call_with_tools(
-            messages=[{"role": "user", "content": "Hello"}],
-            tools=SAMPLE_TOOLS,
-        )
-
-        assert isinstance(result, LLMToolCallResult)
-        assert result.content == "mock response"
-        assert len(result.tool_calls) == 0
-        assert result.finish_reason == "stop"
-
-    @pytest.mark.asyncio
-    async def test_call_with_tools_records_calls(self):
-        """Test that mock calls are recorded."""
-        llm = LLMProvider(provider="mock", api_key="", base_url="", model="mock")
-        llm.clear_mock_calls()
-
-        await llm.call_with_tools(
-            messages=[{"role": "user", "content": "Test message"}],
-            tools=SAMPLE_TOOLS,
-            scope="test_scope",
-        )
-
-        calls = llm.get_mock_calls()
-        assert len(calls) == 1
-        assert calls[0]["scope"] == "test_scope"
-        assert "get_weather" in calls[0]["tools"]
-        assert "search" in calls[0]["tools"]
-
-    @pytest.mark.asyncio
-    async def test_call_with_tools_multiple_tool_calls(self):
-        """Test handling multiple tool calls in one response."""
-        llm = LLMProvider(provider="mock", api_key="", base_url="", model="mock")
-
-        llm.set_mock_response([
-            {"name": "get_weather", "arguments": {"location": "Paris"}},
-            {"name": "search", "arguments": {"query": "weather forecast"}},
-        ])
-
-        result = await llm.call_with_tools(
-            messages=[{"role": "user", "content": "Weather in Paris and search for forecasts"}],
-            tools=SAMPLE_TOOLS,
-        )
-
-        assert len(result.tool_calls) == 2
-        assert result.tool_calls[0].name == "get_weather"
-        assert result.tool_calls[1].name == "search"
-
-    @pytest.mark.asyncio
-    async def test_call_with_tools_accepts_llm_tool_call_result(self):
-        """Test that mock can accept LLMToolCallResult directly."""
-        llm = LLMProvider(provider="mock", api_key="", base_url="", model="mock")
-
-        expected_result = LLMToolCallResult(
-            content="Here's the info",
-            tool_calls=[LLMToolCall(id="call_123", name="search", arguments={"query": "test"})],
-            finish_reason="tool_calls",
-        )
-        llm.set_mock_response(expected_result)
-
-        result = await llm.call_with_tools(
-            messages=[{"role": "user", "content": "Search for test"}],
-            tools=SAMPLE_TOOLS,
-        )
-
-        assert result == expected_result
-
-
-class TestToolCallConversation:
-    """Test tool call conversation flow."""
-
-    @pytest.mark.asyncio
-    async def test_tool_result_message_format(self):
-        """Test that tool result messages can be passed in subsequent calls."""
-        llm = LLMProvider(provider="mock", api_key="", base_url="", model="mock")
-
-        # First call returns tool call
-        llm.set_mock_response([{"name": "get_weather", "arguments": {"location": "Paris"}}])
-
-        result1 = await llm.call_with_tools(
-            messages=[{"role": "user", "content": "What's the weather?"}],
-            tools=SAMPLE_TOOLS,
-        )
-
-        # Build conversation with tool result
-        messages = [
-            {"role": "user", "content": "What's the weather?"},
-            {
-                "role": "assistant",
-                "tool_calls": [
-                    {
-                        "id": result1.tool_calls[0].id,
-                        "type": "function",
-                        "function": {
-                            "name": result1.tool_calls[0].name,
-                            "arguments": '{"location": "Paris"}',
-                        },
-                    }
-                ],
-            },
-            {
-                "role": "tool",
-                "tool_call_id": result1.tool_calls[0].id,
-                "content": '{"temperature": 20, "conditions": "sunny"}',
-            },
-        ]
-
-        # Second call should work with tool result in history
-        llm.set_mock_response(None)  # Reset to default
-        result2 = await llm.call_with_tools(
-            messages=messages,
-            tools=SAMPLE_TOOLS,
-        )
-
-        assert result2.content == "mock response"
-
-
-class TestToolSchemas:
-    """Test tool schema handling."""
-
-    @pytest.mark.asyncio
-    async def test_empty_tools_list(self):
-        """Test calling with empty tools list."""
-        llm = LLMProvider(provider="mock", api_key="", base_url="", model="mock")
-
-        result = await llm.call_with_tools(
-            messages=[{"role": "user", "content": "Hello"}],
-            tools=[],
-        )
-
-        assert result.content == "mock response"
-
-    @pytest.mark.asyncio
-    async def test_tool_with_no_required_params(self):
-        """Test tool with no required parameters."""
-        llm = LLMProvider(provider="mock", api_key="", base_url="", model="mock")
-
-        tools = [
-            {
-                "type": "function",
-                "function": {
-                    "name": "list_items",
-                    "description": "List all items",
-                    "parameters": {"type": "object", "properties": {}, "required": []},
-                },
-            }
-        ]
-
-        llm.set_mock_response([{"name": "list_items", "arguments": {}}])
-
-        result = await llm.call_with_tools(
-            messages=[{"role": "user", "content": "List items"}],
-            tools=tools,
-        )
-
-        assert len(result.tool_calls) == 1
-        assert result.tool_calls[0].name == "list_items"
-        assert result.tool_calls[0].arguments == {}
-
-
-class TestReflectToolSchemas:
-    """Test reflect agent tool schemas."""
-
-    def test_get_reflect_tools_default(self):
-        """Test getting default reflect tools."""
-        from hindsight_api.engine.reflect.tools_schema import get_reflect_tools
-
-        tools = get_reflect_tools()
-
-        tool_names = [t["function"]["name"] for t in tools]
-        assert "list_mental_models" in tool_names
-        assert "get_mental_model" in tool_names
-        assert "recall" in tool_names
-        assert "learn" in tool_names
-        assert "expand" in tool_names
-        assert "done" in tool_names
-
-    def test_get_reflect_tools_without_learn(self):
-        """Test getting reflect tools without learn."""
-        from hindsight_api.engine.reflect.tools_schema import get_reflect_tools
-
-        tools = get_reflect_tools(enable_learn=False)
-
-        tool_names = [t["function"]["name"] for t in tools]
-        assert "learn" not in tool_names
-        assert "recall" in tool_names
-        assert "done" in tool_names
-
-    def test_get_reflect_tools_answer_mode(self):
-        """Test getting reflect tools with answer output mode."""
-        from hindsight_api.engine.reflect.tools_schema import get_reflect_tools
-
-        tools = get_reflect_tools()
-
-        done_tool = next(t for t in tools if t["function"]["name"] == "done")
-        params = done_tool["function"]["parameters"]["properties"]
-
-        assert "answer" in params
-        assert "memory_ids" in params
-        assert "model_ids" in params
-
-
-class TestLLMToolCallResult:
-    """Test LLMToolCallResult model."""
-
-    def test_tool_call_result_defaults(self):
-        """Test default values for LLMToolCallResult."""
-        result = LLMToolCallResult()
-
-        assert result.content is None
-        assert result.tool_calls == []
-        assert result.finish_reason is None
-
-    def test_tool_call_result_with_content(self):
-        """Test LLMToolCallResult with content."""
-        result = LLMToolCallResult(content="Hello", finish_reason="stop")
-
-        assert result.content == "Hello"
-        assert result.tool_calls == []
-        assert result.finish_reason == "stop"
-
-    def test_tool_call_result_with_tool_calls(self):
-        """Test LLMToolCallResult with tool calls."""
-        result = LLMToolCallResult(
-            tool_calls=[
-                LLMToolCall(id="call_1", name="test_tool", arguments={"arg": "value"}),
-            ],
-            finish_reason="tool_calls",
-        )
-
-        assert result.content is None
-        assert len(result.tool_calls) == 1
-        assert result.tool_calls[0].name == "test_tool"
-        assert result.finish_reason == "tool_calls"
-
-
-class TestLLMToolCall:
-    """Test LLMToolCall model."""
-
-    def test_tool_call_basic(self):
-        """Test basic LLMToolCall creation."""
-        call = LLMToolCall(id="call_123", name="get_weather", arguments={"location": "Paris"})
-
-        assert call.id == "call_123"
-        assert call.name == "get_weather"
-        assert call.arguments == {"location": "Paris"}
-
-    def test_tool_call_empty_arguments(self):
-        """Test LLMToolCall with empty arguments."""
-        call = LLMToolCall(id="call_456", name="list_items", arguments={})
-
-        assert call.arguments == {}

hindsight-api/tests/test_main_module.py

@@ -363,7 +363,6 @@ from hindsight_api.extensions import (
     RetainContext,
     RecallContext,
     ReflectContext,
-    RefreshMentalModelContext,
 )
 
 
@@ -395,6 +394,3 @@ class MockOperationValidator(OperationValidatorExtension):
 
     async def validate_reflect(self, ctx: ReflectContext) -> ValidationResult:
         return ValidationResult.accept()
-
-    async def validate_refresh_mental_model(self, ctx: RefreshMentalModelContext) -> ValidationResult:
-        return ValidationResult.accept()

hindsight-api/tests/test_observation_trends.py

@@ -1,405 +0,0 @@
-"""Tests for observation trend computation and evidence-grounded models."""
-
-from datetime import datetime, timedelta, timezone
-
-import pytest
-
-from hindsight_api.engine.reflect.observations import (
-    CandidateObservation,
-    Observation,
-    ObservationEvidence,
-    Trend,
-    compute_trend,
-    verify_evidence_quotes,
-)
-
-
-class TestComputeTrend:
-    """Tests for the compute_trend function."""
-
-    def test_empty_evidence_returns_stale(self):
-        """No evidence should return STALE trend."""
-        trend = compute_trend([])
-        assert trend == Trend.STALE
-
-    def test_all_recent_evidence_returns_new(self):
-        """All evidence within recent window (30 days) should return NEW trend.
-
-        Scenario: User just started using the app and mentioned they like coffee twice.
-        Both mentions are within the last 2 weeks, so this is a NEW observation.
-        """
-        now = datetime.now(timezone.utc)
-        evidence = [
-            ObservationEvidence(
-                memory_id="mem-coffee-morning",
-                quote="I always start my day with a large black coffee",
-                relevance="Shows preference for coffee and morning routine",
-                timestamp=now - timedelta(days=5),
-            ),
-            ObservationEvidence(
-                memory_id="mem-coffee-meeting",
-                quote="grabbed coffee before the standup meeting",
-                relevance="Confirms regular coffee consumption",
-                timestamp=now - timedelta(days=10),
-            ),
-        ]
-
-        trend = compute_trend(evidence, now=now)
-        assert trend == Trend.NEW
-
-    def test_no_recent_evidence_returns_stale(self):
-        """No evidence in recent window should return STALE trend.
-
-        Scenario: User mentioned running 3 months ago but hasn't mentioned it since.
-        The observation about running as a hobby may no longer be accurate.
-        """
-        now = datetime.now(timezone.utc)
-        evidence = [
-            ObservationEvidence(
-                memory_id="mem-running-march",
-                quote="training for a half marathon in the spring",
-                relevance="Shows interest in running",
-                timestamp=now - timedelta(days=60),
-            ),
-            ObservationEvidence(
-                memory_id="mem-running-feb",
-                quote="went for a 10k run this morning",
-                relevance="Active runner",
-                timestamp=now - timedelta(days=100),
-            ),
-        ]
-
-        trend = compute_trend(evidence, now=now)
-        assert trend == Trend.STALE
-
-    def test_stable_evidence_distribution(self):
-        """Evidence spread evenly across time should return STABLE trend.
-
-        Scenario: User has consistently mentioned working remotely over 4 months.
-        Evidence is well-distributed, indicating a stable, ongoing preference.
-        """
-        now = datetime.now(timezone.utc)
-        evidence = [
-            # Recent (within 30 days)
-            ObservationEvidence(
-                memory_id="mem-remote-jan",
-                quote="working from my home office today",
-                relevance="Current remote work",
-                timestamp=now - timedelta(days=5),
-            ),
-            ObservationEvidence(
-                memory_id="mem-remote-dec",
-                quote="the flexibility of remote work is great",
-                relevance="Values remote work",
-                timestamp=now - timedelta(days=15),
-            ),
-            # Middle period (30-90 days)
-            ObservationEvidence(
-                memory_id="mem-remote-nov",
-                quote="set up a standing desk at home",
-                relevance="Invested in home office",
-                timestamp=now - timedelta(days=45),
-            ),
-            ObservationEvidence(
-                memory_id="mem-remote-oct",
-                quote="prefer async communication over meetings",
-                relevance="Remote work style preference",
-                timestamp=now - timedelta(days=60),
-            ),
-            # Older (90+ days)
-            ObservationEvidence(
-                memory_id="mem-remote-sep",
-                quote="switched to fully remote last quarter",
-                relevance="Original transition to remote",
-                timestamp=now - timedelta(days=100),
-            ),
-            ObservationEvidence(
-                memory_id="mem-remote-aug",
-                quote="negotiated remote work in my new contract",
-                relevance="Intentional choice for remote",
-                timestamp=now - timedelta(days=120),
-            ),
-        ]
-
-        trend = compute_trend(evidence, now=now)
-        assert trend == Trend.STABLE
-
-    def test_strengthening_trend(self):
-        """Much more recent evidence than older should return STRENGTHENING trend.
-
-        Scenario: User has been increasingly talking about learning Python recently
-        after mentioning it once months ago. Interest appears to be growing.
-        """
-        now = datetime.now(timezone.utc)
-        evidence = [
-            # Lots of recent evidence - actively learning
-            ObservationEvidence(
-                memory_id="mem-python-project",
-                quote="finished my first Python project - a web scraper",
-                relevance="Completed Python project",
-                timestamp=now - timedelta(days=2),
-            ),
-            ObservationEvidence(
-                memory_id="mem-python-course",
-                quote="halfway through the Python bootcamp",
-                relevance="Active learning",
-                timestamp=now - timedelta(days=5),
-            ),
-            ObservationEvidence(
-                memory_id="mem-python-book",
-                quote="reading Fluent Python, it's excellent",
-                relevance="Deepening knowledge",
-                timestamp=now - timedelta(days=10),
-            ),
-            ObservationEvidence(
-                memory_id="mem-python-practice",
-                quote="solved 50 LeetCode problems in Python",
-                relevance="Practicing skills",
-                timestamp=now - timedelta(days=15),
-            ),
-            ObservationEvidence(
-                memory_id="mem-python-ide",
-                quote="set up VS Code with all the Python extensions",
-                relevance="Setting up environment",
-                timestamp=now - timedelta(days=20),
-            ),
-            # Only one old mention - initial interest
-            ObservationEvidence(
-                memory_id="mem-python-start",
-                quote="thinking about learning Python someday",
-                relevance="Initial interest",
-                timestamp=now - timedelta(days=100),
-            ),
-        ]
-
-        trend = compute_trend(evidence, now=now)
-        assert trend == Trend.STRENGTHENING
-
-    def test_weakening_trend(self):
-        """Much less recent evidence than older should return WEAKENING trend.
-
-        Scenario: User was very active in a book club last year but mentions
-        have tapered off. The observation about being a book club member
-        may be becoming less relevant.
-        """
-        now = datetime.now(timezone.utc)
-        evidence = [
-            # Only one recent mention
-            ObservationEvidence(
-                memory_id="mem-book-recent",
-                quote="haven't had time for book club lately",
-                relevance="Reduced participation",
-                timestamp=now - timedelta(days=10),
-            ),
-            # Lots of older evidence - was very active
-            ObservationEvidence(
-                memory_id="mem-book-aug",
-                quote="hosting book club at my place next week",
-                relevance="Active organizer",
-                timestamp=now - timedelta(days=40),
-            ),
-            ObservationEvidence(
-                memory_id="mem-book-july",
-                quote="leading the discussion on 1984",
-                relevance="Active participant",
-                timestamp=now - timedelta(days=50),
-            ),
-            ObservationEvidence(
-                memory_id="mem-book-june",
-                quote="we picked The Midnight Library for June",
-                relevance="Regular member",
-                timestamp=now - timedelta(days=60),
-            ),
-            ObservationEvidence(
-                memory_id="mem-book-may",
-                quote="book club was amazing tonight",
-                relevance="Enthusiastic member",
-                timestamp=now - timedelta(days=100),
-            ),
-            ObservationEvidence(
-                memory_id="mem-book-april",
-                quote="joined a new book club in my neighborhood",
-                relevance="Started participation",
-                timestamp=now - timedelta(days=110),
-            ),
-            ObservationEvidence(
-                memory_id="mem-book-march",
-                quote="excited to finally join a book club",
-                relevance="Initial enthusiasm",
-                timestamp=now - timedelta(days=120),
-            ),
-        ]
-
-        trend = compute_trend(evidence, now=now)
-        assert trend == Trend.WEAKENING
-
-
-class TestObservationModel:
-    """Tests for the Observation model."""
-
-    def test_observation_computed_trend(self):
-        """Observation should have computed trend property based on evidence."""
-        now = datetime.now(timezone.utc)
-        obs = Observation(
-            title="Morning meeting preference",
-            content="Prefers morning meetings over afternoon ones",
-            evidence=[
-                ObservationEvidence(
-                    memory_id="mem-morning-standup",
-                    quote="I'm most productive in morning meetings",
-                    relevance="Direct preference statement",
-                    timestamp=now - timedelta(days=5),
-                ),
-            ],
-            created_at=now,
-        )
-
-        assert obs.trend == Trend.NEW
-        assert obs.evidence_count == 1
-
-    def test_observation_evidence_span(self):
-        """Observation should compute evidence span correctly.
-
-        The span shows the date range of supporting evidence, helping
-        understand how long this pattern has been observed.
-        """
-        now = datetime.now(timezone.utc)
-        old_time = now - timedelta(days=100)
-        recent_time = now - timedelta(days=5)
-
-        obs = Observation(
-            title="Values work-life balance",
-            content="Values work-life balance highly",
-            evidence=[
-                ObservationEvidence(
-                    memory_id="mem-balance-old",
-                    quote="turned down a promotion because of the hours",
-                    relevance="Prioritized balance over advancement",
-                    timestamp=old_time,
-                ),
-                ObservationEvidence(
-                    memory_id="mem-balance-recent",
-                    quote="always log off by 6pm no matter what",
-                    relevance="Maintains boundaries",
-                    timestamp=recent_time,
-                ),
-            ],
-            created_at=now,
-        )
-
-        evidence_span = obs.evidence_span
-        assert evidence_span["from"] == old_time.isoformat()
-        assert evidence_span["to"] == recent_time.isoformat()
-
-    def test_observation_empty_evidence_span(self):
-        """Observation with no evidence should have null span."""
-        obs = Observation(
-            title="Test observation",
-            content="Test observation without evidence",
-            evidence=[],
-        )
-
-        evidence_span = obs.evidence_span
-        assert evidence_span["from"] is None
-        assert evidence_span["to"] is None
-
-
-class TestVerifyEvidenceQuotes:
-    """Tests for evidence quote verification.
-
-    This ensures the LLM isn't hallucinating quotes - every quote
-    must actually appear in the source memory.
-    """
-
-    def test_valid_quotes(self):
-        """Should return True when quotes exist in their source memories."""
-        obs = Observation(
-            title="Enjoys hiking",
-            content="Enjoys hiking on weekends",
-            evidence=[
-                ObservationEvidence(
-                    memory_id="mem-hiking-trip",
-                    quote="went hiking at Mount Tam",
-                    relevance="Shows hiking activity",
-                    timestamp=datetime.now(timezone.utc),
-                ),
-            ],
-        )
-
-        memories = {
-            "mem-hiking-trip": "Had a great Saturday - went hiking at Mount Tam with friends and saw amazing views."
-        }
-        is_valid, errors = verify_evidence_quotes(obs, memories)
-
-        assert is_valid is True
-        assert len(errors) == 0
-
-    def test_invalid_quote(self):
-        """Should return False when quote doesn't exist in memory.
-
-        This catches LLM hallucinations where it fabricates quotes.
-        """
-        obs = Observation(
-            title="Loves spicy food",
-            content="Loves spicy food",
-            evidence=[
-                ObservationEvidence(
-                    memory_id="mem-dinner",
-                    quote="I love extra hot salsa",
-                    relevance="Shows spicy food preference",
-                    timestamp=datetime.now(timezone.utc),
-                ),
-            ],
-        )
-
-        memories = {"mem-dinner": "Had tacos for dinner. The guacamole was really fresh."}
-        is_valid, errors = verify_evidence_quotes(obs, memories)
-
-        assert is_valid is False
-        assert len(errors) == 1
-        assert "Quote not found" in errors[0]
-
-    def test_missing_memory(self):
-        """Should return False when referenced memory doesn't exist.
-
-        This catches cases where the LLM references a memory ID that
-        was never actually retrieved.
-        """
-        obs = Observation(
-            title="Has a dog named Max",
-            content="Has a dog named Max",
-            evidence=[
-                ObservationEvidence(
-                    memory_id="mem-pet-story",
-                    quote="took Max to the vet",
-                    relevance="Shows pet ownership",
-                    timestamp=datetime.now(timezone.utc),
-                ),
-            ],
-        )
-
-        memories = {"mem-different-id": "Some unrelated memory content"}
-        is_valid, errors = verify_evidence_quotes(obs, memories)
-
-        assert is_valid is False
-        assert len(errors) == 1
-        assert "not found" in errors[0]
-
-
-class TestCandidateObservation:
-    """Tests for candidate observation model.
-
-    Candidates are generated in the SEED phase and validated
-    before becoming full observations.
-    """
-
-    def test_create_candidate(self):
-        """Should create candidate with content and seed memories."""
-        candidate = CandidateObservation(
-            content="User prefers async communication over meetings",
-            seed_memory_ids=["mem-slack-pref", "mem-meeting-decline"],
-        )
-
-        assert candidate.content == "User prefers async communication over meetings"
-        assert len(candidate.seed_memory_ids) == 2
-        assert "mem-slack-pref" in candidate.seed_memory_ids

hindsight-api/tests/test_observations.py

@@ -1,9 +1,5 @@
 """
 Test observation generation and entity state functionality.
-
-NOTE: Observations are now stored as summaries on the entities table,
-not as separate memory_units. The observations list in EntityState is
-populated from the summary for backwards compatibility.
 """
 import pytest
 from hindsight_api.engine.memory_engine import Budget
@@ -12,16 +8,21 @@ from datetime import datetime, timezone
 
 
 @pytest.mark.asyncio
-async def test_entity_extraction_on_retain(memory, request_context):
+async def test_observation_generation_on_put(memory, request_context):
     """
-    Test that entities are extracted when new facts are added.
+    Test that observations are generated SYNCHRONOUSLY when new facts are added.
 
-    This test stores multiple facts and verifies entities are extracted.
+    Observations are generated during retain when:
+    - Entity has >= 5 facts (MIN_FACTS_THRESHOLD)
+    - Entity is in top 5 by mention count
+
+    This test stores enough facts to trigger automatic observation generation.
     """
-    bank_id = f"test_entity_extraction_{datetime.now(timezone.utc).timestamp()}"
+    bank_id = f"test_obs_{datetime.now(timezone.utc).timestamp()}"
 
     try:
-        # Store multiple facts about John
+        # Store multiple facts about John to reach the MIN_FACTS_THRESHOLD (5)
+        # Each retain call should extract at least one fact about John
         contents = [
             "John is a software engineer at Google.",
             "John is detail-oriented and methodical in his work.",
@@ -40,8 +41,9 @@ async def test_entity_extraction_on_retain(memory, request_context):
                 request_context=request_context,
             )
 
-        # Wait for background tasks
-        await memory.wait_for_background_tasks()
+        # Observations are generated SYNCHRONOUSLY during retain,
+        # so they should be available immediately after retain completes.
+        # No need to wait for background tasks for observations.
 
         # Find the John entity
         pool = await memory._get_pool()
@@ -56,7 +58,7 @@ async def test_entity_extraction_on_retain(memory, request_context):
                 bank_id
             )
 
-            # Check the fact count for this entity
+            # Also check the fact count for this entity
             if entity_row:
                 fact_count = await conn.fetchval(
                     """
@@ -68,9 +70,30 @@ async def test_entity_extraction_on_retain(memory, request_context):
                 print(f"Entity: {entity_row['canonical_name']} has {fact_count} linked facts")
 
         assert entity_row is not None, "John entity should have been extracted"
+
+        entity_id = str(entity_row['id'])
+        entity_name = entity_row['canonical_name']
         print(f"\n=== Found Entity ===")
-        print(f"Entity: {entity_row['canonical_name']} (id: {entity_row['id']})")
-        print(f"Entity was successfully extracted")
+        print(f"Entity: {entity_name} (id: {entity_id})")
+
+        # Get observations for the entity - should be available immediately
+        observations = await memory.get_entity_observations(bank_id, entity_id, limit=10, request_context=request_context)
+
+        print(f"\n=== Observations for {entity_name} ===")
+        print(f"Total observations: {len(observations)}")
+        for obs in observations:
+            print(f"  - {obs.text}")
+
+        # Verify observations were created (requires >= 5 facts)
+        assert len(observations) > 0, \
+            f"Observations should have been generated synchronously during retain (entity has {fact_count} facts, threshold is 5)"
+
+        # Check that observations mention relevant content
+        obs_texts = " ".join([o.text.lower() for o in observations])
+        assert any(keyword in obs_texts for keyword in ["google", "engineer", "ai", "machine learning", "detail"]), \
+            "Observations should contain relevant information about John"
+
+        print(f"✓ Observations were successfully generated synchronously during retain")
 
     finally:
         # Cleanup
@@ -83,7 +106,7 @@ async def test_entity_extraction_on_retain(memory, request_context):
 @pytest.mark.asyncio
 async def test_regenerate_entity_observations(memory, request_context):
     """
-    Test explicit regeneration of summary for an entity.
+    Test explicit regeneration of observations for an entity.
     """
     bank_id = f"test_regen_obs_{datetime.now(timezone.utc).timestamp()}"
 
@@ -116,7 +139,7 @@ async def test_regenerate_entity_observations(memory, request_context):
             entity_id = str(entity_row['id'])
             entity_name = entity_row['canonical_name']
 
-            # Manually regenerate summary (via observations API for backwards compat)
+            # Manually regenerate observations
             created_ids = await memory.regenerate_entity_observations(
                 bank_id=bank_id,
                 entity_id=entity_id,
@@ -124,25 +147,23 @@ async def test_regenerate_entity_observations(memory, request_context):
                 request_context=request_context,
             )
 
-            print(f"\n=== Regenerated Summary ===")
-            print(f"Created {len(created_ids)} summary for {entity_name}")
+            print(f"\n=== Regenerated Observations ===")
+            print(f"Created {len(created_ids)} observations for {entity_name}")
 
-            # Get entity state
-            state = await memory.get_entity_state(
-                bank_id, entity_id, entity_name, request_context=request_context
-            )
-            for obs in state.observations:
+            # Get the observations
+            observations = await memory.get_entity_observations(bank_id, entity_id, limit=10, request_context=request_context)
+            for obs in observations:
                 print(f"  - {obs.text}")
 
-            # Verify summary was created
+            # Verify observations were created
             if len(created_ids) > 0:
-                assert len(state.observations) == 1, "Should have exactly 1 observation (the summary)"
-                print(f"Summary regenerated successfully")
+                assert len(observations) == len(created_ids), "Should have same number of observations as created IDs"
+                print(f"✓ Observations regenerated successfully")
             else:
-                print(f"Note: No summary was regenerated")
+                print(f"⚠ Note: No observations were regenerated")
 
         else:
-            print(f"Note: No 'Sarah' entity was extracted")
+            print(f"⚠ Note: No 'Sarah' entity was extracted")
 
     finally:
         # Cleanup
@@ -153,14 +174,19 @@ async def test_regenerate_entity_observations(memory, request_context):
 
 
 @pytest.mark.asyncio
-async def test_entity_state_retrieval(memory, request_context):
+async def test_manual_regenerate_with_few_facts(memory, request_context):
     """
-    Test retrieving entity state with facts.
+    Test that manual regeneration works even with fewer than 5 facts.
+
+    This is important because:
+    - Automatic generation during retain requires MIN_FACTS_THRESHOLD (5)
+    - But manual regeneration via API should work with any number of facts
+    - The UI triggers manual regeneration, so it should work regardless of fact count
     """
-    bank_id = f"test_entity_state_{datetime.now(timezone.utc).timestamp()}"
+    bank_id = f"test_manual_regen_{datetime.now(timezone.utc).timestamp()}"
 
     try:
-        # Store facts
+        # Store only 2 facts - below the automatic threshold
         await memory.retain_async(
             bank_id=bank_id,
             content="Alice works at Google as a senior software engineer.",
@@ -194,25 +220,51 @@ async def test_entity_state_retrieval(memory, request_context):
         entity_id = str(entity_row['id'])
         entity_name = entity_row['canonical_name']
 
-        # Check fact count
+        # Check fact count - should be < 5
         async with pool.acquire() as conn:
             fact_count = await conn.fetchval(
                 "SELECT COUNT(*) FROM unit_entities WHERE entity_id = $1",
                 entity_row['id']
             )
 
-        print(f"\n=== Entity State Test ===")
+        print(f"\n=== Manual Regeneration Test ===")
         print(f"Entity: {entity_name} (id: {entity_id})")
         print(f"Linked facts: {fact_count}")
 
-        # Get entity state
-        state = await memory.get_entity_state(
-            bank_id, entity_id, entity_name, request_context=request_context
+        # Verify we're testing with fewer than the automatic threshold
+        assert fact_count < 5, f"Test requires < 5 facts, but entity has {fact_count}"
+
+        # Before regeneration - should have no observations (auto threshold not met)
+        obs_before = await memory.get_entity_observations(bank_id, entity_id, limit=10, request_context=request_context)
+        print(f"Observations before manual regenerate: {len(obs_before)}")
+
+        # Manually regenerate observations - this should work regardless of fact count
+        created_ids = await memory.regenerate_entity_observations(
+            bank_id=bank_id,
+            entity_id=entity_id,
+            entity_name=entity_name,
+            request_context=request_context,
         )
 
-        assert state.entity_id == entity_id
-        assert state.canonical_name == entity_name
-        print(f"Entity state retrieved successfully")
+        print(f"Observations created by manual regenerate: {len(created_ids)}")
+
+        # Get observations after regeneration
+        observations = await memory.get_entity_observations(bank_id, entity_id, limit=10, request_context=request_context)
+        print(f"Observations after manual regenerate: {len(observations)}")
+        for obs in observations:
+            print(f"  - {obs.text}")
+
+        # Manual regeneration should create observations even with < 5 facts
+        assert len(observations) > 0, \
+            f"Manual regeneration should create observations even with only {fact_count} facts. " \
+            f"The LLM should synthesize at least 1 observation from the available facts."
+
+        # Verify observations contain relevant content
+        obs_texts = " ".join([o.text.lower() for o in observations])
+        assert any(keyword in obs_texts for keyword in ["google", "engineer", "hiking", "photography", "alice"]), \
+            "Observations should contain relevant information about Alice"
+
+        print(f"✓ Manual regeneration works with {fact_count} facts (below automatic threshold of 5)")
 
     finally:
         # Cleanup
@@ -225,16 +277,16 @@ async def test_entity_state_retrieval(memory, request_context):
 @pytest.mark.asyncio
 async def test_search_with_include_entities(memory, request_context):
     """
-    Test that search with include_entities=True returns entity information.
+    Test that search with include_entities=True returns entity observations.
 
     This test verifies that:
-    1. Entities are extracted after retain
-    2. Entity info is returned in recall results with include_entities=True
+    1. Observations are generated during retain (when entity has >= 5 facts)
+    2. Observations are returned in recall results with include_entities=True
     """
     bank_id = f"test_search_ent_{datetime.now(timezone.utc).timestamp()}"
 
     try:
-        # Store facts about Alice
+        # Store enough facts about Alice to trigger observation generation (>= 5 facts)
         contents = [
             "Alice is a data scientist who works on recommendation systems at Netflix.",
             "Alice presented her research at the ML conference last month.",
@@ -253,8 +305,7 @@ async def test_search_with_include_entities(memory, request_context):
                 request_context=request_context,
             )
 
-        # Wait for background tasks
-        await memory.wait_for_background_tasks()
+        # Observations are generated synchronously during retain, no need to wait
 
         # Search with include_entities=True
         result = await memory.recall_async(
@@ -264,7 +315,7 @@ async def test_search_with_include_entities(memory, request_context):
             budget=Budget.LOW,
             max_tokens=2000,
             include_entities=True,
-            max_entity_tokens=5000,
+            max_entity_tokens=500,
             request_context=request_context,
         )
 
@@ -275,28 +326,40 @@ async def test_search_with_include_entities(memory, request_context):
             if fact.entities:
                 print(f"    Entities: {', '.join(fact.entities)}")
 
+        print(f"\n=== Entity Observations in Recall ===")
+        if result.entities:
+            for name, state in result.entities.items():
+                print(f"\n{name}:")
+                for obs in state.observations:
+                    print(f"  - {obs.text}")
+        else:
+            print("No entity observations returned")
+
         # Verify results
         assert len(result.results) > 0, "Should find some facts"
 
         # Check if entities are included in facts
         facts_with_entities = [f for f in result.results if f.entities]
         assert len(facts_with_entities) > 0, "Some facts should have entity information"
-        print(f"{len(facts_with_entities)} facts have entity information")
+        print(f"✓ {len(facts_with_entities)} facts have entity information")
 
-        # Check if entity info is returned
-        if result.entities:
-            print(f"Entity info included for {len(result.entities)} entities")
+        # Check if entity observations are included in recall
+        assert result.entities is not None and len(result.entities) > 0, \
+            "Entity observations should be included in recall results"
+        print(f"✓ Entity observations included for {len(result.entities)} entities")
 
-            # Verify Alice entity is in results
-            alice_found = False
-            for name, state in result.entities.items():
-                assert state.canonical_name == name, "Entity canonical_name should match key"
-                assert state.entity_id, "Entity should have an ID"
-                if "alice" in name.lower():
-                    alice_found = True
-                    print(f"Alice entity found: {name}")
+        # Verify Alice entity has observations
+        alice_found = False
+        for name, state in result.entities.items():
+            assert state.canonical_name == name, "Entity canonical_name should match key"
+            assert state.entity_id, "Entity should have an ID"
+            if "alice" in name.lower():
+                alice_found = True
+                assert len(state.observations) > 0, \
+                    "Alice should have observations (generated during retain)"
+                print(f"✓ Alice has {len(state.observations)} observations in recall result")
 
-            assert alice_found, "Alice entity should be in recall results"
+        assert alice_found, "Alice entity should be in recall results"
 
     finally:
         # Cleanup
@@ -372,10 +435,7 @@ async def test_get_entity_state(memory, request_context):
 @pytest.mark.asyncio
 async def test_observation_fact_type_in_database(memory, request_context):
     """
-    Test that observations are NOT stored as memory_units with fact_type='observation'.
-
-    NOTE: Observations are now handled via mental models, not as memory_units
-    or entity summaries.
+    Test that observations are stored with correct fact_type in database.
     """
     bank_id = f"test_obs_db_{datetime.now(timezone.utc).timestamp()}"
 
@@ -391,7 +451,7 @@ async def test_observation_fact_type_in_database(memory, request_context):
 
         await memory.wait_for_background_tasks()
 
-        # Check that NO observations exist in memory_units
+        # Check that observations have correct fact_type
         pool = await memory._get_pool()
         async with pool.acquire() as conn:
             observations = await conn.fetch(
@@ -403,11 +463,17 @@ async def test_observation_fact_type_in_database(memory, request_context):
                 bank_id
             )
 
-        print(f"\n=== Observation Records in memory_units ===")
-        print(f"Found {len(observations)} observation records (should be 0)")
+        print(f"\n=== Observation Records in Database ===")
+        print(f"Found {len(observations)} observation records")
+        for obs in observations:
+            print(f"  - fact_type: {obs['fact_type']}")
+            print(f"    text: {obs['text']}")
+            print(f"    context: {obs['context']}")
 
-        # Observations are no longer stored as memory_units
-        assert len(observations) == 0, "Observations should NOT be stored as memory_units"
+        if len(observations) > 0:
+            for obs in observations:
+                assert obs['fact_type'] == 'observation', "All observation records should have fact_type='observation'"
+            print(f"✓ All observations have correct fact_type")
 
     finally:
         # Cleanup
@@ -418,183 +484,23 @@ async def test_observation_fact_type_in_database(memory, request_context):
 
 
 @pytest.mark.asyncio
-async def test_entity_mention_counts(memory, request_context):
+async def test_user_entity_prioritized_for_observations(memory, request_context):
     """
-    Test that entity mention counts are tracked correctly.
+    Test that the 'user' entity gets observations even when many other entities exist.
 
-    This test creates entities with varying mention counts and verifies
-    that the counts are accurate.
+    The retain pipeline only regenerates observations for TOP_N_ENTITIES (5) entities,
+    sorted by mention count. This test verifies that the most mentioned entity ('user')
+    gets prioritized and receives observations.
+
+    This is critical because 'user' is often the most important entity in personal memory.
     """
-    bank_id = f"test_mention_counts_{datetime.now(timezone.utc).timestamp()}"
+    bank_id = f"test_user_priority_{datetime.now(timezone.utc).timestamp()}"
 
     try:
-        # Create content with varying entity mention counts:
-        # - "HighMention Corp" mentioned 10+ times
-        # - "LowMention Ltd" mentioned 1 time
-        contents = [
-            # High mentions - HighMention Corp
-            "HighMention Corp is a tech company based in San Francisco.",
-            "HighMention Corp was founded in 2010 by experienced entrepreneurs.",
-            "HighMention Corp has over 500 employees worldwide.",
-            "HighMention Corp specializes in cloud computing solutions.",
-            "HighMention Corp recently raised $50 million in Series C funding.",
-            "HighMention Corp has partnerships with major tech companies.",
-            "HighMention Corp is known for its innovative culture.",
-            "HighMention Corp offers competitive salaries and benefits.",
-            "HighMention Corp has offices in 5 countries.",
-            "HighMention Corp won the best workplace award last year.",
-            # Low mentions - LowMention Ltd
-            "LowMention Ltd is a small consulting firm.",
-        ]
-
-        for i, content in enumerate(contents):
-            await memory.retain_async(
-                bank_id=bank_id,
-                content=content,
-                context="company info",
-                event_date=datetime(2024, 1, 15 + i, tzinfo=timezone.utc),
-                request_context=request_context,
-            )
-
-        # Wait for background tasks
-        await memory.wait_for_background_tasks()
-
-        # Check entity mention counts
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            entities = await conn.fetch(
-                """
-                SELECT e.id, e.canonical_name, e.mention_count
-                FROM entities e
-                WHERE e.bank_id = $1
-                ORDER BY e.mention_count DESC
-                """,
-                bank_id
-            )
-
-        print(f"\n=== Entity Mention Counts Test ===")
-        print(f"Total entities: {len(entities)}")
-
-        high_mention_entity = None
-        low_mention_entity = None
-
-        for entity in entities:
-            name = entity['canonical_name'].lower()
-            mention_count = entity['mention_count']
-
-            print(f"  {entity['canonical_name']}: mentions={mention_count}")
-
-            if "highmention" in name:
-                high_mention_entity = entity
-            elif "lowmention" in name:
-                low_mention_entity = entity
-
-        # Verify HighMention Corp has higher mention count
-        if high_mention_entity and low_mention_entity:
-            assert high_mention_entity['mention_count'] > low_mention_entity['mention_count'], \
-                "HighMention Corp should have more mentions than LowMention Ltd"
-            print("PASS: Entity mention counts are tracked correctly")
-
-    finally:
-        # Cleanup
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            await conn.execute("DELETE FROM memory_units WHERE bank_id = $1", bank_id)
-            await conn.execute("DELETE FROM entities WHERE bank_id = $1", bank_id)
-
-
-@pytest.mark.asyncio
-async def test_entity_mention_ranking(memory, request_context):
-    """
-    Test that entity mention counts correctly rank entities.
-
-    This test:
-    1. Creates an entity with 6 mentions
-    2. Adds more entities with higher mention counts
-    3. Verifies entities are ranked correctly by mention count
-    """
-    bank_id = f"test_ranking_{datetime.now(timezone.utc).timestamp()}"
-
-    try:
-        # Phase 1: Create "OriginalEntity" with 6 mentions
-        print("\n=== Phase 1: Create OriginalEntity with 6 mentions ===")
-        for i in range(6):
-            await memory.retain_async(
-                bank_id=bank_id,
-                content=f"OriginalEntity is mentioned here in fact {i+1}.",
-                context="test",
-                event_date=datetime(2024, 1, 1 + i, tzinfo=timezone.utc),
-                request_context=request_context,
-            )
-
-        await memory.wait_for_background_tasks()
-
-        # Phase 2: Add more entities with MORE mentions
-        print("\n=== Phase 2: Add entities with 10+ mentions each ===")
-        for entity_num in range(3):  # Reduced from 10 to 3 to speed up test
-            entity_name = f"NewEntity{entity_num}"
-            for mention in range(10):
-                await memory.retain_async(
-                    bank_id=bank_id,
-                    content=f"{entity_name} is a very important entity, mention {mention+1}.",
-                    context="test",
-                    event_date=datetime(2024, 2, 1 + mention, tzinfo=timezone.utc),
-                    request_context=request_context,
-                )
-
-        await memory.wait_for_background_tasks()
-
-        # Phase 3: Verify entities are ranked by mention count
-        print("\n=== Phase 3: Check entity ranking ===")
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            all_entities = await conn.fetch(
-                """
-                SELECT canonical_name, mention_count
-                FROM entities
-                WHERE bank_id = $1
-                ORDER BY mention_count DESC
-                """,
-                bank_id
-            )
-
-        print(f"\nAll entities by mention count:")
-        for e in all_entities:
-            print(f"  {e['canonical_name']}: mentions={e['mention_count']}")
-
-        # Verify new entities have higher counts than OriginalEntity
-        original = next((e for e in all_entities if 'originalentity' in e['canonical_name'].lower()), None)
-        new_entities = [e for e in all_entities if 'newentity' in e['canonical_name'].lower()]
-
-        assert original is not None, "OriginalEntity should exist"
-        assert len(new_entities) > 0, "NewEntity entities should exist"
-
-        # Verify entities are created and have mention counts
-        # Note: LLM may merge mentions, so we just check that new entities exist
-        print(f"OriginalEntity mentions: {original['mention_count']}")
-        for new_entity in new_entities:
-            print(f"{new_entity['canonical_name']} mentions: {new_entity['mention_count']}")
-
-        print("PASS: Entities are created with mention counts tracked")
-
-    finally:
-        # Cleanup
-        pool = await memory._get_pool()
-        async with pool.acquire() as conn:
-            await conn.execute("DELETE FROM memory_units WHERE bank_id = $1", bank_id)
-            await conn.execute("DELETE FROM entities WHERE bank_id = $1", bank_id)
-
-
-@pytest.mark.asyncio
-async def test_user_entity_extraction(memory, request_context):
-    """
-    Test that the 'user' entity is correctly extracted when mentioned frequently.
-    """
-    bank_id = f"test_user_entity_{datetime.now(timezone.utc).timestamp()}"
-
-    try:
-        # Create content where 'user' is mentioned many times
+        # Create content where 'user' (the user) is mentioned many times
+        # along with several other entities
         contents = [
+            # User mentioned frequently
             "The user loves hiking in the mountains during summer.",
             "The user works as a software engineer at Microsoft.",
             "The user has a dog named Max who is a golden retriever.",
@@ -604,8 +510,11 @@ async def test_user_entity_extraction(memory, request_context):
             # Other entities mentioned fewer times
             "Sarah is a friend who works at Google.",
             "Bob is a colleague from the data science team.",
+            "Tokyo is a city the user visited last year.",
+            "Python is the user's favorite programming language.",
         ]
 
+        # Retain all content in a single batch for efficiency
         for i, content in enumerate(contents):
             await memory.retain_async(
                 bank_id=bank_id,
@@ -615,12 +524,12 @@ async def test_user_entity_extraction(memory, request_context):
                 request_context=request_context,
             )
 
-        # Wait for background tasks
-        await memory.wait_for_background_tasks()
+        # Observations are generated synchronously during retain
 
         # Find the 'user' entity
         pool = await memory._get_pool()
         async with pool.acquire() as conn:
+            # Find user entity (may be named "user", "the user", etc.)
             user_entity = await conn.fetchrow(
                 """
                 SELECT e.id, e.canonical_name,
@@ -635,7 +544,7 @@ async def test_user_entity_extraction(memory, request_context):
                 bank_id
             )
 
-            # Get all entities with their fact counts
+            # Get all entities with their fact counts to verify prioritization
             all_entities = await conn.fetch(
                 """
                 SELECT e.id, e.canonical_name,
@@ -655,10 +564,41 @@ async def test_user_entity_extraction(memory, request_context):
 
         # Verify user entity exists
         assert user_entity is not None, "User entity should have been extracted"
+        user_entity_id = str(user_entity['id'])
+        user_entity_name = user_entity['canonical_name']
+        user_fact_count = user_entity['fact_count']
+
         print(f"\n=== User Entity ===")
-        print(f"Entity: {user_entity['canonical_name']} (id: {user_entity['id']})")
-        print(f"Fact count: {user_entity['fact_count']}")
-        print(f"User entity was successfully extracted")
+        print(f"Entity: {user_entity_name} (id: {user_entity_id})")
+        print(f"Fact count: {user_fact_count}")
+
+        # Verify user has enough facts for observations (>= MIN_FACTS_THRESHOLD of 5)
+        assert user_fact_count >= 5, \
+            f"User entity should have at least 5 facts, but has {user_fact_count}"
+
+        # Get observations for user entity
+        observations = await memory.get_entity_observations(bank_id, user_entity_id, limit=10, request_context=request_context)
+
+        print(f"\n=== User Entity Observations ===")
+        print(f"Total observations: {len(observations)}")
+        for obs in observations:
+            print(f"  - {obs.text}")
+
+        # Verify observations were generated for user (critical assertion)
+        assert len(observations) > 0, \
+            f"User entity should have observations (has {user_fact_count} facts, threshold is 5). " \
+            f"This may indicate that 'user' is not being prioritized in the top 5 entities by mention count."
+
+        # Verify observations mention relevant content about the user
+        obs_texts = " ".join([o.text.lower() for o in observations])
+        user_keywords = ["hiking", "software", "engineer", "dog", "max", "cooking",
+                        "italian", "mit", "dune", "microsoft"]
+        matching_keywords = [k for k in user_keywords if k in obs_texts]
+        assert len(matching_keywords) > 0, \
+            f"Observations should contain relevant information about the user. Keywords found: {matching_keywords}"
+
+        print(f"✓ User entity was prioritized and received {len(observations)} observations")
+        print(f"✓ Observations contain relevant keywords: {matching_keywords}")
 
     finally:
         # Cleanup

hindsight-api/tests/test_retain.py

@@ -465,7 +465,7 @@ async def test_occurred_dates_not_defaulted(memory, request_context):
             query="Tell me about Alice",
             budget=Budget.LOW,
             max_tokens=500,
-            fact_type=["world", "experience"],
+            fact_type=["world", "opinion"],
             request_context=request_context,
         )
 
@@ -2058,26 +2058,3 @@ async def test_user_provided_entities(memory, request_context):
 
     finally:
         await memory.delete_bank(bank_id, request_context=request_context)
-
-
-def test_recall_result_model_empty_construction():
-    """
-    Test that RecallResultModel can be constructed with empty results.
-
-    This is a regression test for the bug where constructing an empty RecallResultModel
-    would cause an UnboundLocalError because RecallResult was imported as RecallResultModel
-    but the code mistakenly used the wrong name.
-
-    The fix ensures RecallResultModel is used consistently throughout memory_engine.py.
-    """
-    from hindsight_api.engine.response_models import RecallResult
-
-    # This should not raise any errors
-    result = RecallResult(results=[], entities={}, chunks={})
-
-    assert result is not None, "Should create a result object"
-    assert result.results == [], "Should have empty results"
-    assert result.entities == {}, "Should have empty entities"
-    assert result.chunks == {}, "Should have empty chunks"
-
-    logger.info("✓ RecallResult empty construction works correctly")

hindsight-api/tests/test_server_module.py

@@ -257,7 +257,6 @@ from hindsight_api.extensions import (
     RetainContext,
     RecallContext,
     ReflectContext,
-    RefreshMentalModelContext,
 )
 
 
@@ -289,6 +288,3 @@ class MockOperationValidator(OperationValidatorExtension):
 
     async def validate_reflect(self, ctx: ReflectContext) -> ValidationResult:
         return ValidationResult.accept()
-
-    async def validate_refresh_mental_model(self, ctx: RefreshMentalModelContext) -> ValidationResult:
-        return ValidationResult.accept()

hindsight-api/tests/test_tags_visibility.py

@@ -467,12 +467,9 @@ async def test_reflect_with_tags_filters_memories(api_client, test_bank_id):
     # The response should mention Oscar's color (blue), not Peter's (red)
     # Note: We can check based_on facts if they're returned
     if result.get("based_on"):
-        based_on = result["based_on"]
-        memories = based_on.get("memories", []) if isinstance(based_on, dict) else []
-        fact_texts = [f["text"] for f in memories]
-        # Should use Oscar's memory (if facts are included)
-        if fact_texts:
-            assert any("Oscar" in t or "blue" in t for t in fact_texts), "Should use Oscar's memory"
+        fact_texts = [f["text"] for f in result["based_on"]]
+        # Should use Oscar's memory
+        assert any("Oscar" in t or "blue" in t for t in fact_texts), "Should use Oscar's memory"
 
 
 @pytest.mark.asyncio
@@ -716,15 +713,15 @@ async def test_list_tags_with_wildcard_suffix(api_client):
     """Test that list_tags filters with suffix wildcard pattern (*-admin)."""
     bank_id = f"list_tags_suffix_test_{datetime.now().timestamp()}"
 
-    # Store memories with various tags - use meaningful content for reliable fact extraction
+    # Store memories with various tags
     response = await api_client.post(
         f"/v1/default/banks/{bank_id}/memories",
         json={
             "items": [
-                {"content": "John has the role-admin permission and can manage user accounts.", "tags": ["role-admin"]},
-                {"content": "Sarah has super-admin access and can modify system settings.", "tags": ["super-admin"]},
-                {"content": "Mike is a standard role-user who can only view content.", "tags": ["role-user"]},
-                {"content": "Alice is a role-guest visitor with limited read access.", "tags": ["role-guest"]},
+                {"content": "Admin role memory for super admin.", "tags": ["role-admin"]},
+                {"content": "Super admin memory about permissions.", "tags": ["super-admin"]},
+                {"content": "User memory for standard users.", "tags": ["role-user"]},
+                {"content": "Guest memory for visitors.", "tags": ["role-guest"]},
             ]
         }
     )

hindsight-cli/src/api.rs

@@ -117,7 +117,6 @@ impl ApiClient {
         self.runtime.block_on(async {
             let request = types::CreateBankRequest {
                 name: Some(name.to_string()),
-                mission: None,
                 background: None,
                 disposition: None,
             };

hindsight-cli/src/commands/bank.rs

@@ -201,7 +201,7 @@ pub fn update_background(
         Ok(profile) => {
             if output_format == OutputFormat::Pretty {
                 ui::print_success("Background updated successfully");
-                println!("\n{}", profile.mission);
+                println!("\n{}", profile.background);
 
                 if !no_update_disposition {
                     if let (Some(old_p), Some(new_p)) =

hindsight-cli/src/ui.rs

@@ -172,11 +172,8 @@ pub fn print_think_response(response: &ReflectResponse) {
     println!("{}", response.text);
     println!();
 
-    if let Some(based_on) = &response.based_on {
-        let count = based_on.memories.len() + based_on.mental_models.len();
-        if count > 0 {
-            println!("{}", dim(&format!("Based on {} memory units", count)));
-        }
+    if !response.based_on.is_empty() {
+        println!("{}", dim(&format!("Based on {} memory units", response.based_on.len())));
     }
 
     // Display structured output if present
@@ -325,10 +322,10 @@ pub fn print_disposition(profile: &BankProfileResponse) {
     println!("{} {}", dim("Name:"), gradient_start(&profile.name));
     println!();
 
-    // Print mission if available
-    if !profile.mission.is_empty() {
-        println!("{}", gradient_mid("Mission:"));
-        for line in profile.mission.lines() {
+    // Print background if available
+    if !profile.background.is_empty() {
+        println!("{}", gradient_mid("Background:"));
+        for line in profile.background.lines() {
             println!("{}", line);
         }
         println!();

hindsight-clients/python/.openapi-generator/FILES

@@ -4,7 +4,6 @@ hindsight_client_api/api/banks_api.py
 hindsight_client_api/api/documents_api.py
 hindsight_client_api/api/entities_api.py
 hindsight_client_api/api/memory_api.py
-hindsight_client_api/api/mental_models_api.py
 hindsight_client_api/api/monitoring_api.py
 hindsight_client_api/api/operations_api.py
 hindsight_client_api/api_client.py
@@ -13,7 +12,6 @@ hindsight_client_api/configuration.py
 hindsight_client_api/exceptions.py
 hindsight_client_api/models/__init__.py
 hindsight_client_api/models/add_background_request.py
-hindsight_client_api/models/async_operation_submit_response.py
 hindsight_client_api/models/background_response.py
 hindsight_client_api/models/bank_list_item.py
 hindsight_client_api/models/bank_list_response.py
@@ -25,8 +23,6 @@ hindsight_client_api/models/chunk_data.py
 hindsight_client_api/models/chunk_include_options.py
 hindsight_client_api/models/chunk_response.py
 hindsight_client_api/models/create_bank_request.py
-hindsight_client_api/models/create_mental_model_request.py
-hindsight_client_api/models/created_mental_model.py
 hindsight_client_api/models/delete_document_response.py
 hindsight_client_api/models/delete_response.py
 hindsight_client_api/models/disposition_traits.py
@@ -45,35 +41,20 @@ hindsight_client_api/models/list_documents_response.py
 hindsight_client_api/models/list_memory_units_response.py
 hindsight_client_api/models/list_tags_response.py
 hindsight_client_api/models/memory_item.py
-hindsight_client_api/models/mental_model_freshness_response.py
-hindsight_client_api/models/mental_model_list_response.py
-hindsight_client_api/models/mental_model_observation_response.py
-hindsight_client_api/models/mental_model_response.py
-hindsight_client_api/models/observation_evidence_response.py
-hindsight_client_api/models/observation_input.py
 hindsight_client_api/models/operation_response.py
-hindsight_client_api/models/operation_status_response.py
 hindsight_client_api/models/operations_list_response.py
 hindsight_client_api/models/recall_request.py
 hindsight_client_api/models/recall_response.py
 hindsight_client_api/models/recall_result.py
-hindsight_client_api/models/reflect_based_on.py
 hindsight_client_api/models/reflect_fact.py
 hindsight_client_api/models/reflect_include_options.py
-hindsight_client_api/models/reflect_llm_call.py
-hindsight_client_api/models/reflect_mental_model.py
 hindsight_client_api/models/reflect_request.py
 hindsight_client_api/models/reflect_response.py
-hindsight_client_api/models/reflect_tool_call.py
-hindsight_client_api/models/reflect_trace.py
-hindsight_client_api/models/refresh_mental_models_request.py
 hindsight_client_api/models/retain_request.py
 hindsight_client_api/models/retain_response.py
 hindsight_client_api/models/tag_item.py
 hindsight_client_api/models/token_usage.py
-hindsight_client_api/models/tool_calls_include_options.py
 hindsight_client_api/models/update_disposition_request.py
-hindsight_client_api/models/update_mental_model_request.py
 hindsight_client_api/models/validation_error.py
 hindsight_client_api/models/validation_error_loc_inner.py
 hindsight_client_api/rest.py

hindsight-clients/python/hindsight_client/hindsight_client.py

@@ -115,7 +115,6 @@ class Hindsight:
         document_id: Optional[str] = None,
         metadata: Optional[Dict[str, str]] = None,
         entities: Optional[List[Dict[str, str]]] = None,
-        tags: Optional[List[str]] = None,
     ) -> RetainResponse:
         """
         Store a single memory (simplified interface).
@@ -128,14 +127,13 @@ class Hindsight:
             document_id: Optional document ID for grouping
             metadata: Optional user-defined metadata
             entities: Optional list of entities [{"text": "...", "type": "..."}]
-            tags: Optional list of tags for this memory
 
         Returns:
             RetainResponse with success status
         """
         return self.retain_batch(
             bank_id=bank_id,
-            items=[{"content": content, "timestamp": timestamp, "context": context, "metadata": metadata, "entities": entities, "tags": tags}],
+            items=[{"content": content, "timestamp": timestamp, "context": context, "metadata": metadata, "entities": entities}],
             document_id=document_id,
         )
 
@@ -145,17 +143,15 @@ class Hindsight:
         items: List[Dict[str, Any]],
         document_id: Optional[str] = None,
         retain_async: bool = False,
-        document_tags: Optional[List[str]] = None,
     ) -> RetainResponse:
         """
         Store multiple memories in batch.
 
         Args:
             bank_id: The memory bank ID
-            items: List of memory items with 'content' and optional 'timestamp', 'context', 'metadata', 'document_id', 'entities', 'tags'
+            items: List of memory items with 'content' and optional 'timestamp', 'context', 'metadata', 'document_id', 'entities'
             document_id: Optional document ID for grouping memories (applied to items that don't have their own)
             retain_async: If True, process asynchronously in background (default: False)
-            document_tags: Optional list of tags to apply to all memories in this batch
 
         Returns:
             RetainResponse with success status and item count
@@ -179,14 +175,12 @@ class Hindsight:
                     # Use item's document_id if provided, otherwise fall back to batch-level document_id
                     document_id=item.get("document_id") or document_id,
                     entities=entities,
-                    tags=item.get("tags"),
                 )
             )
 
         request_obj = retain_request.RetainRequest(
             items=memory_items,
             async_=retain_async,
-            document_tags=document_tags,
         )
 
         return _run_async(self._memory_api.retain_memories(bank_id, request_obj))
@@ -204,8 +198,6 @@ class Hindsight:
         max_entity_tokens: int = 500,
         include_chunks: bool = False,
         max_chunk_tokens: int = 8192,
-        tags: Optional[List[str]] = None,
-        tags_match: str = "any",
     ) -> RecallResponse:
         """
         Recall memories using semantic similarity.
@@ -222,9 +214,6 @@ class Hindsight:
             max_entity_tokens: Maximum tokens for entity observations (default: 500)
             include_chunks: Include raw text chunks in results (default: False)
             max_chunk_tokens: Maximum tokens for chunks (default: 8192)
-            tags: Optional list of tags to filter memories by
-            tags_match: How to match tags: 'any' (OR, includes untagged), 'all' (AND, includes untagged),
-                'any_strict' (OR, excludes untagged), 'all_strict' (AND, excludes untagged). Default: 'any'
 
         Returns:
             RecallResponse with results, optional entities, optional chunks, and optional trace
@@ -244,8 +233,6 @@ class Hindsight:
             trace=trace,
             query_timestamp=query_timestamp,
             include=include_opts,
-            tags=tags,
-            tags_match=tags_match,
         )
 
         return _run_async(self._memory_api.recall_memories(bank_id, request_obj))
@@ -258,8 +245,6 @@ class Hindsight:
         context: Optional[str] = None,
         max_tokens: Optional[int] = None,
         response_schema: Optional[Dict[str, Any]] = None,
-        tags: Optional[List[str]] = None,
-        tags_match: str = "any",
     ) -> ReflectResponse:
         """
         Generate a contextual answer based on bank identity and memories.
@@ -273,9 +258,6 @@ class Hindsight:
             response_schema: Optional JSON Schema for structured output. When provided,
                 the response will include a 'structured_output' field with the LLM
                 response parsed according to this schema.
-            tags: Optional list of tags to filter memories by
-            tags_match: How to match tags: 'any' (OR, includes untagged), 'all' (AND, includes untagged),
-                'any_strict' (OR, excludes untagged), 'all_strict' (AND, excludes untagged). Default: 'any'
 
         Returns:
             ReflectResponse with answer text, optionally facts used, and optionally
@@ -287,8 +269,6 @@ class Hindsight:
             context=context,
             max_tokens=max_tokens,
             response_schema=response_schema,
-            tags=tags,
-            tags_match=tags_match,
         )
 
         return _run_async(self._memory_api.reflect(bank_id, request_obj))

hindsight-clients/python/hindsight_client_api/__init__.py

@@ -21,7 +21,6 @@ from hindsight_client_api.api.banks_api import BanksApi
 from hindsight_client_api.api.documents_api import DocumentsApi
 from hindsight_client_api.api.entities_api import EntitiesApi
 from hindsight_client_api.api.memory_api import MemoryApi
-from hindsight_client_api.api.mental_models_api import MentalModelsApi
 from hindsight_client_api.api.monitoring_api import MonitoringApi
 from hindsight_client_api.api.operations_api import OperationsApi
 
@@ -38,7 +37,6 @@ from hindsight_client_api.exceptions import ApiException
 
 # import models into sdk package
 from hindsight_client_api.models.add_background_request import AddBackgroundRequest
-from hindsight_client_api.models.async_operation_submit_response import AsyncOperationSubmitResponse
 from hindsight_client_api.models.background_response import BackgroundResponse
 from hindsight_client_api.models.bank_list_item import BankListItem
 from hindsight_client_api.models.bank_list_response import BankListResponse
@@ -50,8 +48,6 @@ from hindsight_client_api.models.chunk_data import ChunkData
 from hindsight_client_api.models.chunk_include_options import ChunkIncludeOptions
 from hindsight_client_api.models.chunk_response import ChunkResponse
 from hindsight_client_api.models.create_bank_request import CreateBankRequest
-from hindsight_client_api.models.create_mental_model_request import CreateMentalModelRequest
-from hindsight_client_api.models.created_mental_model import CreatedMentalModel
 from hindsight_client_api.models.delete_document_response import DeleteDocumentResponse
 from hindsight_client_api.models.delete_response import DeleteResponse
 from hindsight_client_api.models.disposition_traits import DispositionTraits
@@ -70,34 +66,19 @@ from hindsight_client_api.models.list_documents_response import ListDocumentsRes
 from hindsight_client_api.models.list_memory_units_response import ListMemoryUnitsResponse
 from hindsight_client_api.models.list_tags_response import ListTagsResponse
 from hindsight_client_api.models.memory_item import MemoryItem
-from hindsight_client_api.models.mental_model_freshness_response import MentalModelFreshnessResponse
-from hindsight_client_api.models.mental_model_list_response import MentalModelListResponse
-from hindsight_client_api.models.mental_model_observation_response import MentalModelObservationResponse
-from hindsight_client_api.models.mental_model_response import MentalModelResponse
-from hindsight_client_api.models.observation_evidence_response import ObservationEvidenceResponse
-from hindsight_client_api.models.observation_input import ObservationInput
 from hindsight_client_api.models.operation_response import OperationResponse
-from hindsight_client_api.models.operation_status_response import OperationStatusResponse
 from hindsight_client_api.models.operations_list_response import OperationsListResponse
 from hindsight_client_api.models.recall_request import RecallRequest
 from hindsight_client_api.models.recall_response import RecallResponse
 from hindsight_client_api.models.recall_result import RecallResult
-from hindsight_client_api.models.reflect_based_on import ReflectBasedOn
 from hindsight_client_api.models.reflect_fact import ReflectFact
 from hindsight_client_api.models.reflect_include_options import ReflectIncludeOptions
-from hindsight_client_api.models.reflect_llm_call import ReflectLLMCall
-from hindsight_client_api.models.reflect_mental_model import ReflectMentalModel
 from hindsight_client_api.models.reflect_request import ReflectRequest
 from hindsight_client_api.models.reflect_response import ReflectResponse
-from hindsight_client_api.models.reflect_tool_call import ReflectToolCall
-from hindsight_client_api.models.reflect_trace import ReflectTrace
-from hindsight_client_api.models.refresh_mental_models_request import RefreshMentalModelsRequest
 from hindsight_client_api.models.retain_request import RetainRequest
 from hindsight_client_api.models.retain_response import RetainResponse
 from hindsight_client_api.models.tag_item import TagItem
 from hindsight_client_api.models.token_usage import TokenUsage
-from hindsight_client_api.models.tool_calls_include_options import ToolCallsIncludeOptions
 from hindsight_client_api.models.update_disposition_request import UpdateDispositionRequest
-from hindsight_client_api.models.update_mental_model_request import UpdateMentalModelRequest
 from hindsight_client_api.models.validation_error import ValidationError
 from hindsight_client_api.models.validation_error_loc_inner import ValidationErrorLocInner

hindsight-clients/python/hindsight_client_api/api/__init__.py

@@ -5,7 +5,6 @@ from hindsight_client_api.api.banks_api import BanksApi
 from hindsight_client_api.api.documents_api import DocumentsApi
 from hindsight_client_api.api.entities_api import EntitiesApi
 from hindsight_client_api.api.memory_api import MemoryApi
-from hindsight_client_api.api.mental_models_api import MentalModelsApi
 from hindsight_client_api.api.monitoring_api import MonitoringApi
 from hindsight_client_api.api.operations_api import OperationsApi
 

hindsight-clients/python/hindsight_client_api/api/banks_api.py

@@ -64,9 +64,9 @@ class BanksApi:
         _headers: Optional[Dict[StrictStr, Any]] = None,
         _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
     ) -> BackgroundResponse:
-        """(Deprecated) Add/merge memory bank background (deprecated)
+        """Add/merge memory bank background
 
-        Deprecated: Use PUT /mission instead. This endpoint now updates the mission field.
+        Add new background information or merge with existing. LLM intelligently resolves conflicts, normalizes to first person, and optionally infers disposition traits.
 
         :param bank_id: (required)
         :type bank_id: str
@@ -95,7 +95,6 @@ class BanksApi:
         :type _host_index: int, optional
         :return: Returns the result object.
         """ # noqa: E501
-        warnings.warn("POST /v1/default/banks/{bank_id}/background is deprecated.", DeprecationWarning)
 
         _param = self._add_bank_background_serialize(
             bank_id=bank_id,
@@ -141,9 +140,9 @@ class BanksApi:
         _headers: Optional[Dict[StrictStr, Any]] = None,
         _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
     ) -> ApiResponse[BackgroundResponse]:
-        """(Deprecated) Add/merge memory bank background (deprecated)
+        """Add/merge memory bank background
 
-        Deprecated: Use PUT /mission instead. This endpoint now updates the mission field.
+        Add new background information or merge with existing. LLM intelligently resolves conflicts, normalizes to first person, and optionally infers disposition traits.
 
         :param bank_id: (required)
         :type bank_id: str
@@ -172,7 +171,6 @@ class BanksApi:
         :type _host_index: int, optional
         :return: Returns the result object.
         """ # noqa: E501
-        warnings.warn("POST /v1/default/banks/{bank_id}/background is deprecated.", DeprecationWarning)
 
         _param = self._add_bank_background_serialize(
             bank_id=bank_id,
@@ -218,9 +216,9 @@ class BanksApi:
         _headers: Optional[Dict[StrictStr, Any]] = None,
         _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
     ) -> RESTResponseType:
-        """(Deprecated) Add/merge memory bank background (deprecated)
+        """Add/merge memory bank background
 
-        Deprecated: Use PUT /mission instead. This endpoint now updates the mission field.
+        Add new background information or merge with existing. LLM intelligently resolves conflicts, normalizes to first person, and optionally infers disposition traits.
 
         :param bank_id: (required)
         :type bank_id: str
@@ -249,7 +247,6 @@ class BanksApi:
         :type _host_index: int, optional
         :return: Returns the result object.
         """ # noqa: E501
-        warnings.warn("POST /v1/default/banks/{bank_id}/background is deprecated.", DeprecationWarning)
 
         _param = self._add_bank_background_serialize(
             bank_id=bank_id,
@@ -375,7 +372,7 @@ class BanksApi:
     ) -> BankProfileResponse:
         """Create or update memory bank
 
-        Create a new agent or update existing agent with disposition and mission. Auto-fills missing fields with defaults.
+        Create a new agent or update existing agent with disposition and background. Auto-fills missing fields with defaults.
 
         :param bank_id: (required)
         :type bank_id: str
@@ -451,7 +448,7 @@ class BanksApi:
     ) -> ApiResponse[BankProfileResponse]:
         """Create or update memory bank
 
-        Create a new agent or update existing agent with disposition and mission. Auto-fills missing fields with defaults.
+        Create a new agent or update existing agent with disposition and background. Auto-fills missing fields with defaults.
 
         :param bank_id: (required)
         :type bank_id: str
@@ -527,7 +524,7 @@ class BanksApi:
     ) -> RESTResponseType:
         """Create or update memory bank
 
-        Create a new agent or update existing agent with disposition and mission. Auto-fills missing fields with defaults.
+        Create a new agent or update existing agent with disposition and background. Auto-fills missing fields with defaults.
 
         :param bank_id: (required)
         :type bank_id: str
@@ -1236,7 +1233,7 @@ class BanksApi:
     ) -> BankProfileResponse:
         """Get memory bank profile
 
-        Get disposition traits and mission for a memory bank. Auto-creates agent with defaults if not exists.
+        Get disposition traits and background for a memory bank. Auto-creates agent with defaults if not exists.
 
         :param bank_id: (required)
         :type bank_id: str
@@ -1308,7 +1305,7 @@ class BanksApi:
     ) -> ApiResponse[BankProfileResponse]:
         """Get memory bank profile
 
-        Get disposition traits and mission for a memory bank. Auto-creates agent with defaults if not exists.
+        Get disposition traits and background for a memory bank. Auto-creates agent with defaults if not exists.
 
         :param bank_id: (required)
         :type bank_id: str
@@ -1380,7 +1377,7 @@ class BanksApi:
     ) -> RESTResponseType:
         """Get memory bank profile
 
-        Get disposition traits and mission for a memory bank. Auto-creates agent with defaults if not exists.
+        Get disposition traits and background for a memory bank. Auto-creates agent with defaults if not exists.
 
         :param bank_id: (required)
         :type bank_id: str
@@ -1757,312 +1754,6 @@ class BanksApi:
 
 
 
-    @validate_call
-    async def update_bank(
-        self,
-        bank_id: StrictStr,
-        create_bank_request: CreateBankRequest,
-        authorization: Optional[StrictStr] = None,
-        _request_timeout: Union[
-            None,
-            Annotated[StrictFloat, Field(gt=0)],
-            Tuple[
-                Annotated[StrictFloat, Field(gt=0)],
-                Annotated[StrictFloat, Field(gt=0)]
-            ]
-        ] = None,
-        _request_auth: Optional[Dict[StrictStr, Any]] = None,
-        _content_type: Optional[StrictStr] = None,
-        _headers: Optional[Dict[StrictStr, Any]] = None,
-        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
-    ) -> BankProfileResponse:
-        """Partial update memory bank
-
-        Partially update an agent's profile. Only provided fields will be updated.
-
-        :param bank_id: (required)
-        :type bank_id: str
-        :param create_bank_request: (required)
-        :type create_bank_request: CreateBankRequest
-        :param authorization:
-        :type authorization: str
-        :param _request_timeout: timeout setting for this request. If one
-                                 number provided, it will be total request
-                                 timeout. It can also be a pair (tuple) of
-                                 (connection, read) timeouts.
-        :type _request_timeout: int, tuple(int, int), optional
-        :param _request_auth: set to override the auth_settings for an a single
-                              request; this effectively ignores the
-                              authentication in the spec for a single request.
-        :type _request_auth: dict, optional
-        :param _content_type: force content-type for the request.
-        :type _content_type: str, Optional
-        :param _headers: set to override the headers for a single
-                         request; this effectively ignores the headers
-                         in the spec for a single request.
-        :type _headers: dict, optional
-        :param _host_index: set to override the host_index for a single
-                            request; this effectively ignores the host_index
-                            in the spec for a single request.
-        :type _host_index: int, optional
-        :return: Returns the result object.
-        """ # noqa: E501
-
-        _param = self._update_bank_serialize(
-            bank_id=bank_id,
-            create_bank_request=create_bank_request,
-            authorization=authorization,
-            _request_auth=_request_auth,
-            _content_type=_content_type,
-            _headers=_headers,
-            _host_index=_host_index
-        )
-
-        _response_types_map: Dict[str, Optional[str]] = {
-            '200': "BankProfileResponse",
-            '422': "HTTPValidationError",
-        }
-        response_data = await self.api_client.call_api(
-            *_param,
-            _request_timeout=_request_timeout
-        )
-        await response_data.read()
-        return self.api_client.response_deserialize(
-            response_data=response_data,
-            response_types_map=_response_types_map,
-        ).data
-
-
-    @validate_call
-    async def update_bank_with_http_info(
-        self,
-        bank_id: StrictStr,
-        create_bank_request: CreateBankRequest,
-        authorization: Optional[StrictStr] = None,
-        _request_timeout: Union[
-            None,
-            Annotated[StrictFloat, Field(gt=0)],
-            Tuple[
-                Annotated[StrictFloat, Field(gt=0)],
-                Annotated[StrictFloat, Field(gt=0)]
-            ]
-        ] = None,
-        _request_auth: Optional[Dict[StrictStr, Any]] = None,
-        _content_type: Optional[StrictStr] = None,
-        _headers: Optional[Dict[StrictStr, Any]] = None,
-        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
-    ) -> ApiResponse[BankProfileResponse]:
-        """Partial update memory bank
-
-        Partially update an agent's profile. Only provided fields will be updated.
-
-        :param bank_id: (required)
-        :type bank_id: str
-        :param create_bank_request: (required)
-        :type create_bank_request: CreateBankRequest
-        :param authorization:
-        :type authorization: str
-        :param _request_timeout: timeout setting for this request. If one
-                                 number provided, it will be total request
-                                 timeout. It can also be a pair (tuple) of
-                                 (connection, read) timeouts.
-        :type _request_timeout: int, tuple(int, int), optional
-        :param _request_auth: set to override the auth_settings for an a single
-                              request; this effectively ignores the
-                              authentication in the spec for a single request.
-        :type _request_auth: dict, optional
-        :param _content_type: force content-type for the request.
-        :type _content_type: str, Optional
-        :param _headers: set to override the headers for a single
-                         request; this effectively ignores the headers
-                         in the spec for a single request.
-        :type _headers: dict, optional
-        :param _host_index: set to override the host_index for a single
-                            request; this effectively ignores the host_index
-                            in the spec for a single request.
-        :type _host_index: int, optional
-        :return: Returns the result object.
-        """ # noqa: E501
-
-        _param = self._update_bank_serialize(
-            bank_id=bank_id,
-            create_bank_request=create_bank_request,
-            authorization=authorization,
-            _request_auth=_request_auth,
-            _content_type=_content_type,
-            _headers=_headers,
-            _host_index=_host_index
-        )
-
-        _response_types_map: Dict[str, Optional[str]] = {
-            '200': "BankProfileResponse",
-            '422': "HTTPValidationError",
-        }
-        response_data = await self.api_client.call_api(
-            *_param,
-            _request_timeout=_request_timeout
-        )
-        await response_data.read()
-        return self.api_client.response_deserialize(
-            response_data=response_data,
-            response_types_map=_response_types_map,
-        )
-
-
-    @validate_call
-    async def update_bank_without_preload_content(
-        self,
-        bank_id: StrictStr,
-        create_bank_request: CreateBankRequest,
-        authorization: Optional[StrictStr] = None,
-        _request_timeout: Union[
-            None,
-            Annotated[StrictFloat, Field(gt=0)],
-            Tuple[
-                Annotated[StrictFloat, Field(gt=0)],
-                Annotated[StrictFloat, Field(gt=0)]
-            ]
-        ] = None,
-        _request_auth: Optional[Dict[StrictStr, Any]] = None,
-        _content_type: Optional[StrictStr] = None,
-        _headers: Optional[Dict[StrictStr, Any]] = None,
-        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
-    ) -> RESTResponseType:
-        """Partial update memory bank
-
-        Partially update an agent's profile. Only provided fields will be updated.
-
-        :param bank_id: (required)
-        :type bank_id: str
-        :param create_bank_request: (required)
-        :type create_bank_request: CreateBankRequest
-        :param authorization:
-        :type authorization: str
-        :param _request_timeout: timeout setting for this request. If one
-                                 number provided, it will be total request
-                                 timeout. It can also be a pair (tuple) of
-                                 (connection, read) timeouts.
-        :type _request_timeout: int, tuple(int, int), optional
-        :param _request_auth: set to override the auth_settings for an a single
-                              request; this effectively ignores the
-                              authentication in the spec for a single request.
-        :type _request_auth: dict, optional
-        :param _content_type: force content-type for the request.
-        :type _content_type: str, Optional
-        :param _headers: set to override the headers for a single
-                         request; this effectively ignores the headers
-                         in the spec for a single request.
-        :type _headers: dict, optional
-        :param _host_index: set to override the host_index for a single
-                            request; this effectively ignores the host_index
-                            in the spec for a single request.
-        :type _host_index: int, optional
-        :return: Returns the result object.
-        """ # noqa: E501
-
-        _param = self._update_bank_serialize(
-            bank_id=bank_id,
-            create_bank_request=create_bank_request,
-            authorization=authorization,
-            _request_auth=_request_auth,
-            _content_type=_content_type,
-            _headers=_headers,
-            _host_index=_host_index
-        )
-
-        _response_types_map: Dict[str, Optional[str]] = {
-            '200': "BankProfileResponse",
-            '422': "HTTPValidationError",
-        }
-        response_data = await self.api_client.call_api(
-            *_param,
-            _request_timeout=_request_timeout
-        )
-        return response_data.response
-
-
-    def _update_bank_serialize(
-        self,
-        bank_id,
-        create_bank_request,
-        authorization,
-        _request_auth,
-        _content_type,
-        _headers,
-        _host_index,
-    ) -> RequestSerialized:
-
-        _host = None
-
-        _collection_formats: Dict[str, str] = {
-        }
-
-        _path_params: Dict[str, str] = {}
-        _query_params: List[Tuple[str, str]] = []
-        _header_params: Dict[str, Optional[str]] = _headers or {}
-        _form_params: List[Tuple[str, str]] = []
-        _files: Dict[
-            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
-        ] = {}
-        _body_params: Optional[bytes] = None
-
-        # process the path parameters
-        if bank_id is not None:
-            _path_params['bank_id'] = bank_id
-        # process the query parameters
-        # process the header parameters
-        if authorization is not None:
-            _header_params['authorization'] = authorization
-        # process the form parameters
-        # process the body parameter
-        if create_bank_request is not None:
-            _body_params = create_bank_request
-
-
-        # set the HTTP header `Accept`
-        if 'Accept' not in _header_params:
-            _header_params['Accept'] = self.api_client.select_header_accept(
-                [
-                    'application/json'
-                ]
-            )
-
-        # set the HTTP header `Content-Type`
-        if _content_type:
-            _header_params['Content-Type'] = _content_type
-        else:
-            _default_content_type = (
-                self.api_client.select_header_content_type(
-                    [
-                        'application/json'
-                    ]
-                )
-            )
-            if _default_content_type is not None:
-                _header_params['Content-Type'] = _default_content_type
-
-        # authentication setting
-        _auth_settings: List[str] = [
-        ]
-
-        return self.api_client.param_serialize(
-            method='PATCH',
-            resource_path='/v1/default/banks/{bank_id}',
-            path_params=_path_params,
-            query_params=_query_params,
-            header_params=_header_params,
-            body=_body_params,
-            post_params=_form_params,
-            files=_files,
-            auth_settings=_auth_settings,
-            collection_formats=_collection_formats,
-            _host=_host,
-            _request_auth=_request_auth
-        )
-
-
-
-
     @validate_call
     async def update_bank_disposition(
         self,

hindsight-clients/python/hindsight_client_api/api/entities_api.py

@@ -664,9 +664,9 @@ class EntitiesApi:
         _headers: Optional[Dict[StrictStr, Any]] = None,
         _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
     ) -> EntityDetailResponse:
-        """(Deprecated) Regenerate entity observations (deprecated)
+        """Regenerate entity observations
 
-        This endpoint is deprecated. Entity observations have been replaced by mental models.
+        Regenerate observations for an entity based on all facts mentioning it.
 
         :param bank_id: (required)
         :type bank_id: str
@@ -695,7 +695,6 @@ class EntitiesApi:
         :type _host_index: int, optional
         :return: Returns the result object.
         """ # noqa: E501
-        warnings.warn("POST /v1/default/banks/{bank_id}/entities/{entity_id}/regenerate is deprecated.", DeprecationWarning)
 
         _param = self._regenerate_entity_observations_serialize(
             bank_id=bank_id,
@@ -741,9 +740,9 @@ class EntitiesApi:
         _headers: Optional[Dict[StrictStr, Any]] = None,
         _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
     ) -> ApiResponse[EntityDetailResponse]:
-        """(Deprecated) Regenerate entity observations (deprecated)
+        """Regenerate entity observations
 
-        This endpoint is deprecated. Entity observations have been replaced by mental models.
+        Regenerate observations for an entity based on all facts mentioning it.
 
         :param bank_id: (required)
         :type bank_id: str
@@ -772,7 +771,6 @@ class EntitiesApi:
         :type _host_index: int, optional
         :return: Returns the result object.
         """ # noqa: E501
-        warnings.warn("POST /v1/default/banks/{bank_id}/entities/{entity_id}/regenerate is deprecated.", DeprecationWarning)
 
         _param = self._regenerate_entity_observations_serialize(
             bank_id=bank_id,
@@ -818,9 +816,9 @@ class EntitiesApi:
         _headers: Optional[Dict[StrictStr, Any]] = None,
         _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
     ) -> RESTResponseType:
-        """(Deprecated) Regenerate entity observations (deprecated)
+        """Regenerate entity observations
 
-        This endpoint is deprecated. Entity observations have been replaced by mental models.
+        Regenerate observations for an entity based on all facts mentioning it.
 
         :param bank_id: (required)
         :type bank_id: str
@@ -849,7 +847,6 @@ class EntitiesApi:
         :type _host_index: int, optional
         :return: Returns the result object.
         """ # noqa: E501
-        warnings.warn("POST /v1/default/banks/{bank_id}/entities/{entity_id}/regenerate is deprecated.", DeprecationWarning)
 
         _param = self._regenerate_entity_observations_serialize(
             bank_id=bank_id,

hindsight-clients/python/hindsight_client_api/api/operations_api.py

@@ -19,7 +19,6 @@ from typing_extensions import Annotated
 from pydantic import StrictStr
 from typing import Optional
 from hindsight_client_api.models.cancel_operation_response import CancelOperationResponse
-from hindsight_client_api.models.operation_status_response import OperationStatusResponse
 from hindsight_client_api.models.operations_list_response import OperationsListResponse
 
 from hindsight_client_api.api_client import ApiClient, RequestSerialized
@@ -333,299 +332,6 @@ class OperationsApi:
 
 
 
-    @validate_call
-    async def get_operation_status(
-        self,
-        bank_id: StrictStr,
-        operation_id: StrictStr,
-        authorization: Optional[StrictStr] = None,
-        _request_timeout: Union[
-            None,
-            Annotated[StrictFloat, Field(gt=0)],
-            Tuple[
-                Annotated[StrictFloat, Field(gt=0)],
-                Annotated[StrictFloat, Field(gt=0)]
-            ]
-        ] = None,
-        _request_auth: Optional[Dict[StrictStr, Any]] = None,
-        _content_type: Optional[StrictStr] = None,
-        _headers: Optional[Dict[StrictStr, Any]] = None,
-        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
-    ) -> OperationStatusResponse:
-        """Get operation status
-
-        Get the status of a specific async operation. Returns 'pending', 'completed', or 'failed'. Completed operations are removed from storage, so 'completed' means the operation finished successfully.
-
-        :param bank_id: (required)
-        :type bank_id: str
-        :param operation_id: (required)
-        :type operation_id: str
-        :param authorization:
-        :type authorization: str
-        :param _request_timeout: timeout setting for this request. If one
-                                 number provided, it will be total request
-                                 timeout. It can also be a pair (tuple) of
-                                 (connection, read) timeouts.
-        :type _request_timeout: int, tuple(int, int), optional
-        :param _request_auth: set to override the auth_settings for an a single
-                              request; this effectively ignores the
-                              authentication in the spec for a single request.
-        :type _request_auth: dict, optional
-        :param _content_type: force content-type for the request.
-        :type _content_type: str, Optional
-        :param _headers: set to override the headers for a single
-                         request; this effectively ignores the headers
-                         in the spec for a single request.
-        :type _headers: dict, optional
-        :param _host_index: set to override the host_index for a single
-                            request; this effectively ignores the host_index
-                            in the spec for a single request.
-        :type _host_index: int, optional
-        :return: Returns the result object.
-        """ # noqa: E501
-
-        _param = self._get_operation_status_serialize(
-            bank_id=bank_id,
-            operation_id=operation_id,
-            authorization=authorization,
-            _request_auth=_request_auth,
-            _content_type=_content_type,
-            _headers=_headers,
-            _host_index=_host_index
-        )
-
-        _response_types_map: Dict[str, Optional[str]] = {
-            '200': "OperationStatusResponse",
-            '422': "HTTPValidationError",
-        }
-        response_data = await self.api_client.call_api(
-            *_param,
-            _request_timeout=_request_timeout
-        )
-        await response_data.read()
-        return self.api_client.response_deserialize(
-            response_data=response_data,
-            response_types_map=_response_types_map,
-        ).data
-
-
-    @validate_call
-    async def get_operation_status_with_http_info(
-        self,
-        bank_id: StrictStr,
-        operation_id: StrictStr,
-        authorization: Optional[StrictStr] = None,
-        _request_timeout: Union[
-            None,
-            Annotated[StrictFloat, Field(gt=0)],
-            Tuple[
-                Annotated[StrictFloat, Field(gt=0)],
-                Annotated[StrictFloat, Field(gt=0)]
-            ]
-        ] = None,
-        _request_auth: Optional[Dict[StrictStr, Any]] = None,
-        _content_type: Optional[StrictStr] = None,
-        _headers: Optional[Dict[StrictStr, Any]] = None,
-        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
-    ) -> ApiResponse[OperationStatusResponse]:
-        """Get operation status
-
-        Get the status of a specific async operation. Returns 'pending', 'completed', or 'failed'. Completed operations are removed from storage, so 'completed' means the operation finished successfully.
-
-        :param bank_id: (required)
-        :type bank_id: str
-        :param operation_id: (required)
-        :type operation_id: str
-        :param authorization:
-        :type authorization: str
-        :param _request_timeout: timeout setting for this request. If one
-                                 number provided, it will be total request
-                                 timeout. It can also be a pair (tuple) of
-                                 (connection, read) timeouts.
-        :type _request_timeout: int, tuple(int, int), optional
-        :param _request_auth: set to override the auth_settings for an a single
-                              request; this effectively ignores the
-                              authentication in the spec for a single request.
-        :type _request_auth: dict, optional
-        :param _content_type: force content-type for the request.
-        :type _content_type: str, Optional
-        :param _headers: set to override the headers for a single
-                         request; this effectively ignores the headers
-                         in the spec for a single request.
-        :type _headers: dict, optional
-        :param _host_index: set to override the host_index for a single
-                            request; this effectively ignores the host_index
-                            in the spec for a single request.
-        :type _host_index: int, optional
-        :return: Returns the result object.
-        """ # noqa: E501
-
-        _param = self._get_operation_status_serialize(
-            bank_id=bank_id,
-            operation_id=operation_id,
-            authorization=authorization,
-            _request_auth=_request_auth,
-            _content_type=_content_type,
-            _headers=_headers,
-            _host_index=_host_index
-        )
-
-        _response_types_map: Dict[str, Optional[str]] = {
-            '200': "OperationStatusResponse",
-            '422': "HTTPValidationError",
-        }
-        response_data = await self.api_client.call_api(
-            *_param,
-            _request_timeout=_request_timeout
-        )
-        await response_data.read()
-        return self.api_client.response_deserialize(
-            response_data=response_data,
-            response_types_map=_response_types_map,
-        )
-
-
-    @validate_call
-    async def get_operation_status_without_preload_content(
-        self,
-        bank_id: StrictStr,
-        operation_id: StrictStr,
-        authorization: Optional[StrictStr] = None,
-        _request_timeout: Union[
-            None,
-            Annotated[StrictFloat, Field(gt=0)],
-            Tuple[
-                Annotated[StrictFloat, Field(gt=0)],
-                Annotated[StrictFloat, Field(gt=0)]
-            ]
-        ] = None,
-        _request_auth: Optional[Dict[StrictStr, Any]] = None,
-        _content_type: Optional[StrictStr] = None,
-        _headers: Optional[Dict[StrictStr, Any]] = None,
-        _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0,
-    ) -> RESTResponseType:
-        """Get operation status
-
-        Get the status of a specific async operation. Returns 'pending', 'completed', or 'failed'. Completed operations are removed from storage, so 'completed' means the operation finished successfully.
-
-        :param bank_id: (required)
-        :type bank_id: str
-        :param operation_id: (required)
-        :type operation_id: str
-        :param authorization:
-        :type authorization: str
-        :param _request_timeout: timeout setting for this request. If one
-                                 number provided, it will be total request
-                                 timeout. It can also be a pair (tuple) of
-                                 (connection, read) timeouts.
-        :type _request_timeout: int, tuple(int, int), optional
-        :param _request_auth: set to override the auth_settings for an a single
-                              request; this effectively ignores the
-                              authentication in the spec for a single request.
-        :type _request_auth: dict, optional
-        :param _content_type: force content-type for the request.
-        :type _content_type: str, Optional
-        :param _headers: set to override the headers for a single
-                         request; this effectively ignores the headers
-                         in the spec for a single request.
-        :type _headers: dict, optional
-        :param _host_index: set to override the host_index for a single
-                            request; this effectively ignores the host_index
-                            in the spec for a single request.
-        :type _host_index: int, optional
-        :return: Returns the result object.
-        """ # noqa: E501
-
-        _param = self._get_operation_status_serialize(
-            bank_id=bank_id,
-            operation_id=operation_id,
-            authorization=authorization,
-            _request_auth=_request_auth,
-            _content_type=_content_type,
-            _headers=_headers,
-            _host_index=_host_index
-        )
-
-        _response_types_map: Dict[str, Optional[str]] = {
-            '200': "OperationStatusResponse",
-            '422': "HTTPValidationError",
-        }
-        response_data = await self.api_client.call_api(
-            *_param,
-            _request_timeout=_request_timeout
-        )
-        return response_data.response
-
-
-    def _get_operation_status_serialize(
-        self,
-        bank_id,
-        operation_id,
-        authorization,
-        _request_auth,
-        _content_type,
-        _headers,
-        _host_index,
-    ) -> RequestSerialized:
-
-        _host = None
-
-        _collection_formats: Dict[str, str] = {
-        }
-
-        _path_params: Dict[str, str] = {}
-        _query_params: List[Tuple[str, str]] = []
-        _header_params: Dict[str, Optional[str]] = _headers or {}
-        _form_params: List[Tuple[str, str]] = []
-        _files: Dict[
-            str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]]
-        ] = {}
-        _body_params: Optional[bytes] = None
-
-        # process the path parameters
-        if bank_id is not None:
-            _path_params['bank_id'] = bank_id
-        if operation_id is not None:
-            _path_params['operation_id'] = operation_id
-        # process the query parameters
-        # process the header parameters
-        if authorization is not None:
-            _header_params['authorization'] = authorization
-        # process the form parameters
-        # process the body parameter
-
-
-        # set the HTTP header `Accept`
-        if 'Accept' not in _header_params:
-            _header_params['Accept'] = self.api_client.select_header_accept(
-                [
-                    'application/json'
-                ]
-            )
-
-
-        # authentication setting
-        _auth_settings: List[str] = [
-        ]
-
-        return self.api_client.param_serialize(
-            method='GET',
-            resource_path='/v1/default/banks/{bank_id}/operations/{operation_id}',
-            path_params=_path_params,
-            query_params=_query_params,
-            header_params=_header_params,
-            body=_body_params,
-            post_params=_form_params,
-            files=_files,
-            auth_settings=_auth_settings,
-            collection_formats=_collection_formats,
-            _host=_host,
-            _request_auth=_request_auth
-        )
-
-
-
-
     @validate_call
     async def list_operations(
         self,

hindsight-clients/python/hindsight_client_api/models/__init__.py

@@ -15,7 +15,6 @@
 
 # import models into model package
 from hindsight_client_api.models.add_background_request import AddBackgroundRequest
-from hindsight_client_api.models.async_operation_submit_response import AsyncOperationSubmitResponse
 from hindsight_client_api.models.background_response import BackgroundResponse
 from hindsight_client_api.models.bank_list_item import BankListItem
 from hindsight_client_api.models.bank_list_response import BankListResponse
@@ -27,8 +26,6 @@ from hindsight_client_api.models.chunk_data import ChunkData
 from hindsight_client_api.models.chunk_include_options import ChunkIncludeOptions
 from hindsight_client_api.models.chunk_response import ChunkResponse
 from hindsight_client_api.models.create_bank_request import CreateBankRequest
-from hindsight_client_api.models.create_mental_model_request import CreateMentalModelRequest
-from hindsight_client_api.models.created_mental_model import CreatedMentalModel
 from hindsight_client_api.models.delete_document_response import DeleteDocumentResponse
 from hindsight_client_api.models.delete_response import DeleteResponse
 from hindsight_client_api.models.disposition_traits import DispositionTraits
@@ -47,34 +44,19 @@ from hindsight_client_api.models.list_documents_response import ListDocumentsRes
 from hindsight_client_api.models.list_memory_units_response import ListMemoryUnitsResponse
 from hindsight_client_api.models.list_tags_response import ListTagsResponse
 from hindsight_client_api.models.memory_item import MemoryItem
-from hindsight_client_api.models.mental_model_freshness_response import MentalModelFreshnessResponse
-from hindsight_client_api.models.mental_model_list_response import MentalModelListResponse
-from hindsight_client_api.models.mental_model_observation_response import MentalModelObservationResponse
-from hindsight_client_api.models.mental_model_response import MentalModelResponse
-from hindsight_client_api.models.observation_evidence_response import ObservationEvidenceResponse
-from hindsight_client_api.models.observation_input import ObservationInput
 from hindsight_client_api.models.operation_response import OperationResponse
-from hindsight_client_api.models.operation_status_response import OperationStatusResponse
 from hindsight_client_api.models.operations_list_response import OperationsListResponse
 from hindsight_client_api.models.recall_request import RecallRequest
 from hindsight_client_api.models.recall_response import RecallResponse
 from hindsight_client_api.models.recall_result import RecallResult
-from hindsight_client_api.models.reflect_based_on import ReflectBasedOn
 from hindsight_client_api.models.reflect_fact import ReflectFact
 from hindsight_client_api.models.reflect_include_options import ReflectIncludeOptions
-from hindsight_client_api.models.reflect_llm_call import ReflectLLMCall
-from hindsight_client_api.models.reflect_mental_model import ReflectMentalModel
 from hindsight_client_api.models.reflect_request import ReflectRequest
 from hindsight_client_api.models.reflect_response import ReflectResponse
-from hindsight_client_api.models.reflect_tool_call import ReflectToolCall
-from hindsight_client_api.models.reflect_trace import ReflectTrace
-from hindsight_client_api.models.refresh_mental_models_request import RefreshMentalModelsRequest
 from hindsight_client_api.models.retain_request import RetainRequest
 from hindsight_client_api.models.retain_response import RetainResponse
 from hindsight_client_api.models.tag_item import TagItem
 from hindsight_client_api.models.token_usage import TokenUsage
-from hindsight_client_api.models.tool_calls_include_options import ToolCallsIncludeOptions
 from hindsight_client_api.models.update_disposition_request import UpdateDispositionRequest
-from hindsight_client_api.models.update_mental_model_request import UpdateMentalModelRequest
 from hindsight_client_api.models.validation_error import ValidationError
 from hindsight_client_api.models.validation_error_loc_inner import ValidationErrorLocInner

hindsight-clients/python/hindsight_client_api/models/add_background_request.py

@@ -24,10 +24,10 @@ from typing_extensions import Self
 
 class AddBackgroundRequest(BaseModel):
     """
-    Request model for adding/merging background information. Deprecated: use SetMissionRequest instead.
+    Request model for adding/merging background information.
     """ # noqa: E501
     content: StrictStr = Field(description="New background information to add or merge")
-    update_disposition: Optional[StrictBool] = Field(default=True, description="Deprecated - disposition is no longer auto-inferred from mission")
+    update_disposition: Optional[StrictBool] = Field(default=True, description="If true, infer disposition traits from the merged background (default: true)")
     __properties: ClassVar[List[str]] = ["content", "update_disposition"]
 
     model_config = ConfigDict(

hindsight-clients/python/hindsight_client_api/models/async_operation_submit_response.py

@@ -1,89 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, StrictStr
-from typing import Any, ClassVar, Dict, List
-from typing import Optional, Set
-from typing_extensions import Self
-
-class AsyncOperationSubmitResponse(BaseModel):
-    """
-    Response model for submitting an async operation.
-    """ # noqa: E501
-    operation_id: StrictStr
-    status: StrictStr
-    __properties: ClassVar[List[str]] = ["operation_id", "status"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of AsyncOperationSubmitResponse from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of AsyncOperationSubmitResponse from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "operation_id": obj.get("operation_id"),
-            "status": obj.get("status")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/background_response.py

@@ -25,12 +25,11 @@ from typing_extensions import Self
 
 class BackgroundResponse(BaseModel):
     """
-    Response model for background update. Deprecated: use MissionResponse instead.
+    Response model for background update.
     """ # noqa: E501
-    mission: StrictStr
-    background: Optional[StrictStr] = None
+    background: StrictStr
     disposition: Optional[DispositionTraits] = None
-    __properties: ClassVar[List[str]] = ["mission", "background", "disposition"]
+    __properties: ClassVar[List[str]] = ["background", "disposition"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -74,11 +73,6 @@ class BackgroundResponse(BaseModel):
         # override the default output from pydantic by calling `to_dict()` of disposition
         if self.disposition:
             _dict['disposition'] = self.disposition.to_dict()
-        # set to None if background (nullable) is None
-        # and model_fields_set contains the field
-        if self.background is None and "background" in self.model_fields_set:
-            _dict['background'] = None
-
         # set to None if disposition (nullable) is None
         # and model_fields_set contains the field
         if self.disposition is None and "disposition" in self.model_fields_set:
@@ -96,7 +90,6 @@ class BackgroundResponse(BaseModel):
             return cls.model_validate(obj)
 
         _obj = cls.model_validate({
-            "mission": obj.get("mission"),
             "background": obj.get("background"),
             "disposition": DispositionTraits.from_dict(obj["disposition"]) if obj.get("disposition") is not None else None
         })

hindsight-clients/python/hindsight_client_api/models/bank_list_item.py

@@ -30,10 +30,10 @@ class BankListItem(BaseModel):
     bank_id: StrictStr
     name: Optional[StrictStr] = None
     disposition: DispositionTraits
-    mission: Optional[StrictStr] = None
+    background: Optional[StrictStr] = None
     created_at: Optional[StrictStr] = None
     updated_at: Optional[StrictStr] = None
-    __properties: ClassVar[List[str]] = ["bank_id", "name", "disposition", "mission", "created_at", "updated_at"]
+    __properties: ClassVar[List[str]] = ["bank_id", "name", "disposition", "background", "created_at", "updated_at"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -82,10 +82,10 @@ class BankListItem(BaseModel):
         if self.name is None and "name" in self.model_fields_set:
             _dict['name'] = None
 
-        # set to None if mission (nullable) is None
+        # set to None if background (nullable) is None
         # and model_fields_set contains the field
-        if self.mission is None and "mission" in self.model_fields_set:
-            _dict['mission'] = None
+        if self.background is None and "background" in self.model_fields_set:
+            _dict['background'] = None
 
         # set to None if created_at (nullable) is None
         # and model_fields_set contains the field
@@ -112,7 +112,7 @@ class BankListItem(BaseModel):
             "bank_id": obj.get("bank_id"),
             "name": obj.get("name"),
             "disposition": DispositionTraits.from_dict(obj["disposition"]) if obj.get("disposition") is not None else None,
-            "mission": obj.get("mission"),
+            "background": obj.get("background"),
             "created_at": obj.get("created_at"),
             "updated_at": obj.get("updated_at")
         })

hindsight-clients/python/hindsight_client_api/models/bank_profile_response.py

@@ -17,8 +17,8 @@ import pprint
 import re  # noqa: F401
 import json
 
-from pydantic import BaseModel, ConfigDict, Field, StrictStr
-from typing import Any, ClassVar, Dict, List, Optional
+from pydantic import BaseModel, ConfigDict, StrictStr
+from typing import Any, ClassVar, Dict, List
 from hindsight_client_api.models.disposition_traits import DispositionTraits
 from typing import Optional, Set
 from typing_extensions import Self
@@ -30,9 +30,8 @@ class BankProfileResponse(BaseModel):
     bank_id: StrictStr
     name: StrictStr
     disposition: DispositionTraits
-    mission: StrictStr = Field(description="The agent's mission - who they are and what they're trying to accomplish")
-    background: Optional[StrictStr] = None
-    __properties: ClassVar[List[str]] = ["bank_id", "name", "disposition", "mission", "background"]
+    background: StrictStr
+    __properties: ClassVar[List[str]] = ["bank_id", "name", "disposition", "background"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -76,11 +75,6 @@ class BankProfileResponse(BaseModel):
         # override the default output from pydantic by calling `to_dict()` of disposition
         if self.disposition:
             _dict['disposition'] = self.disposition.to_dict()
-        # set to None if background (nullable) is None
-        # and model_fields_set contains the field
-        if self.background is None and "background" in self.model_fields_set:
-            _dict['background'] = None
-
         return _dict
 
     @classmethod
@@ -96,7 +90,6 @@ class BankProfileResponse(BaseModel):
             "bank_id": obj.get("bank_id"),
             "name": obj.get("name"),
             "disposition": DispositionTraits.from_dict(obj["disposition"]) if obj.get("disposition") is not None else None,
-            "mission": obj.get("mission"),
             "background": obj.get("background")
         })
         return _obj

hindsight-clients/python/hindsight_client_api/models/create_bank_request.py

@@ -29,9 +29,8 @@ class CreateBankRequest(BaseModel):
     """ # noqa: E501
     name: Optional[StrictStr] = None
     disposition: Optional[DispositionTraits] = None
-    mission: Optional[StrictStr] = None
     background: Optional[StrictStr] = None
-    __properties: ClassVar[List[str]] = ["name", "disposition", "mission", "background"]
+    __properties: ClassVar[List[str]] = ["name", "disposition", "background"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -85,11 +84,6 @@ class CreateBankRequest(BaseModel):
         if self.disposition is None and "disposition" in self.model_fields_set:
             _dict['disposition'] = None
 
-        # set to None if mission (nullable) is None
-        # and model_fields_set contains the field
-        if self.mission is None and "mission" in self.model_fields_set:
-            _dict['mission'] = None
-
         # set to None if background (nullable) is None
         # and model_fields_set contains the field
         if self.background is None and "background" in self.model_fields_set:
@@ -109,7 +103,6 @@ class CreateBankRequest(BaseModel):
         _obj = cls.model_validate({
             "name": obj.get("name"),
             "disposition": DispositionTraits.from_dict(obj["disposition"]) if obj.get("disposition") is not None else None,
-            "mission": obj.get("mission"),
             "background": obj.get("background")
         })
         return _obj

hindsight-clients/python/hindsight_client_api/models/create_mental_model_request.py

@@ -1,108 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field, StrictStr
-from typing import Any, ClassVar, Dict, List, Optional
-from hindsight_client_api.models.observation_input import ObservationInput
-from typing import Optional, Set
-from typing_extensions import Self
-
-class CreateMentalModelRequest(BaseModel):
-    """
-    Request model for creating a mental model.
-    """ # noqa: E501
-    name: StrictStr = Field(description="Human-readable name for the mental model")
-    description: StrictStr = Field(description="One-liner description for quick scanning")
-    subtype: Optional[StrictStr] = Field(default='pinned', description="Type of mental model: 'pinned' (observations LLM-generated) or 'directive' (observations user-provided)")
-    observations: Optional[List[ObservationInput]] = None
-    tags: Optional[List[StrictStr]] = Field(default=None, description="Tags for scoped visibility")
-    __properties: ClassVar[List[str]] = ["name", "description", "subtype", "observations", "tags"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of CreateMentalModelRequest from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # override the default output from pydantic by calling `to_dict()` of each item in observations (list)
-        _items = []
-        if self.observations:
-            for _item_observations in self.observations:
-                if _item_observations:
-                    _items.append(_item_observations.to_dict())
-            _dict['observations'] = _items
-        # set to None if observations (nullable) is None
-        # and model_fields_set contains the field
-        if self.observations is None and "observations" in self.model_fields_set:
-            _dict['observations'] = None
-
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of CreateMentalModelRequest from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "name": obj.get("name"),
-            "description": obj.get("description"),
-            "subtype": obj.get("subtype") if obj.get("subtype") is not None else 'pinned',
-            "observations": [ObservationInput.from_dict(_item) for _item in obj["observations"]] if obj.get("observations") is not None else None,
-            "tags": obj.get("tags")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/created_mental_model.py

@@ -1,91 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field, StrictStr
-from typing import Any, ClassVar, Dict, List
-from typing import Optional, Set
-from typing_extensions import Self
-
-class CreatedMentalModel(BaseModel):
-    """
-    A mental model created during reflection.
-    """ # noqa: E501
-    id: StrictStr = Field(description="Mental model ID")
-    name: StrictStr = Field(description="Human-readable name")
-    description: StrictStr = Field(description="What this model tracks")
-    __properties: ClassVar[List[str]] = ["id", "name", "description"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of CreatedMentalModel from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of CreatedMentalModel from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "id": obj.get("id"),
-            "name": obj.get("name"),
-            "description": obj.get("description")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/mental_model_freshness_response.py

@@ -1,98 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field, StrictBool, StrictInt, StrictStr
-from typing import Any, ClassVar, Dict, List, Optional
-from typing import Optional, Set
-from typing_extensions import Self
-
-class MentalModelFreshnessResponse(BaseModel):
-    """
-    Freshness information for a mental model.
-    """ # noqa: E501
-    is_up_to_date: StrictBool = Field(description="Whether the model has been refreshed since the last memory was added")
-    last_refresh_at: Optional[StrictStr]
-    memories_since_refresh: StrictInt = Field(description="Number of memories added since last refresh")
-    reasons: Optional[List[StrictStr]] = Field(default=None, description="Reasons why the model needs refresh (empty if up to date). Possible values: never_refreshed, new_memories, mission_changed, disposition_changed, directives_changed")
-    __properties: ClassVar[List[str]] = ["is_up_to_date", "last_refresh_at", "memories_since_refresh", "reasons"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of MentalModelFreshnessResponse from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # set to None if last_refresh_at (nullable) is None
-        # and model_fields_set contains the field
-        if self.last_refresh_at is None and "last_refresh_at" in self.model_fields_set:
-            _dict['last_refresh_at'] = None
-
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of MentalModelFreshnessResponse from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "is_up_to_date": obj.get("is_up_to_date"),
-            "last_refresh_at": obj.get("last_refresh_at"),
-            "memories_since_refresh": obj.get("memories_since_refresh"),
-            "reasons": obj.get("reasons")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/mental_model_list_response.py

@@ -1,95 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict
-from typing import Any, ClassVar, Dict, List
-from hindsight_client_api.models.mental_model_response import MentalModelResponse
-from typing import Optional, Set
-from typing_extensions import Self
-
-class MentalModelListResponse(BaseModel):
-    """
-    Response model for listing mental models.
-    """ # noqa: E501
-    items: List[MentalModelResponse]
-    __properties: ClassVar[List[str]] = ["items"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of MentalModelListResponse from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # override the default output from pydantic by calling `to_dict()` of each item in items (list)
-        _items = []
-        if self.items:
-            for _item_items in self.items:
-                if _item_items:
-                    _items.append(_item_items.to_dict())
-            _dict['items'] = _items
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of MentalModelListResponse from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "items": [MentalModelResponse.from_dict(_item) for _item in obj["items"]] if obj.get("items") is not None else None
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/mental_model_observation_response.py

@@ -1,107 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr
-from typing import Any, ClassVar, Dict, List, Optional
-from hindsight_client_api.models.observation_evidence_response import ObservationEvidenceResponse
-from typing import Optional, Set
-from typing_extensions import Self
-
-class MentalModelObservationResponse(BaseModel):
-    """
-    An observation within a mental model with its supporting evidence.
-    """ # noqa: E501
-    title: StrictStr = Field(description="Short summary title for the observation")
-    content: StrictStr = Field(description="The observation content - detailed explanation")
-    evidence: Optional[List[ObservationEvidenceResponse]] = Field(default=None, description="Supporting evidence with quotes")
-    created_at: StrictStr = Field(description="When this observation was first created (ISO format)")
-    trend: StrictStr = Field(description="Computed trend: stable, strengthening, weakening, new, stale")
-    evidence_count: StrictInt = Field(description="Number of evidence items supporting this observation")
-    evidence_span: Dict[str, Any] = Field(description="Time span of evidence: {from: iso_date, to: iso_date}")
-    __properties: ClassVar[List[str]] = ["title", "content", "evidence", "created_at", "trend", "evidence_count", "evidence_span"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of MentalModelObservationResponse from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # override the default output from pydantic by calling `to_dict()` of each item in evidence (list)
-        _items = []
-        if self.evidence:
-            for _item_evidence in self.evidence:
-                if _item_evidence:
-                    _items.append(_item_evidence.to_dict())
-            _dict['evidence'] = _items
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of MentalModelObservationResponse from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "title": obj.get("title"),
-            "content": obj.get("content"),
-            "evidence": [ObservationEvidenceResponse.from_dict(_item) for _item in obj["evidence"]] if obj.get("evidence") is not None else None,
-            "created_at": obj.get("created_at"),
-            "trend": obj.get("trend"),
-            "evidence_count": obj.get("evidence_count"),
-            "evidence_span": obj.get("evidence_span")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/mental_model_response.py

@@ -1,145 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr
-from typing import Any, ClassVar, Dict, List, Optional
-from hindsight_client_api.models.mental_model_freshness_response import MentalModelFreshnessResponse
-from hindsight_client_api.models.mental_model_observation_response import MentalModelObservationResponse
-from typing import Optional, Set
-from typing_extensions import Self
-
-class MentalModelResponse(BaseModel):
-    """
-    Response model for a mental model.
-    """ # noqa: E501
-    id: StrictStr
-    bank_id: StrictStr
-    subtype: StrictStr
-    name: StrictStr
-    description: StrictStr
-    observations: Optional[List[MentalModelObservationResponse]] = Field(default=None, description="Structured observations with per-observation fact attribution")
-    version: Optional[StrictInt] = Field(default=0, description="Version number of the mental model observations")
-    entity_id: Optional[StrictStr] = None
-    links: Optional[List[StrictStr]] = None
-    tags: Optional[List[StrictStr]] = None
-    last_updated: Optional[StrictStr] = None
-    last_refresh_at: Optional[StrictStr] = None
-    freshness: Optional[MentalModelFreshnessResponse] = None
-    created_at: StrictStr
-    __properties: ClassVar[List[str]] = ["id", "bank_id", "subtype", "name", "description", "observations", "version", "entity_id", "links", "tags", "last_updated", "last_refresh_at", "freshness", "created_at"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of MentalModelResponse from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # override the default output from pydantic by calling `to_dict()` of each item in observations (list)
-        _items = []
-        if self.observations:
-            for _item_observations in self.observations:
-                if _item_observations:
-                    _items.append(_item_observations.to_dict())
-            _dict['observations'] = _items
-        # override the default output from pydantic by calling `to_dict()` of freshness
-        if self.freshness:
-            _dict['freshness'] = self.freshness.to_dict()
-        # set to None if entity_id (nullable) is None
-        # and model_fields_set contains the field
-        if self.entity_id is None and "entity_id" in self.model_fields_set:
-            _dict['entity_id'] = None
-
-        # set to None if last_updated (nullable) is None
-        # and model_fields_set contains the field
-        if self.last_updated is None and "last_updated" in self.model_fields_set:
-            _dict['last_updated'] = None
-
-        # set to None if last_refresh_at (nullable) is None
-        # and model_fields_set contains the field
-        if self.last_refresh_at is None and "last_refresh_at" in self.model_fields_set:
-            _dict['last_refresh_at'] = None
-
-        # set to None if freshness (nullable) is None
-        # and model_fields_set contains the field
-        if self.freshness is None and "freshness" in self.model_fields_set:
-            _dict['freshness'] = None
-
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of MentalModelResponse from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "id": obj.get("id"),
-            "bank_id": obj.get("bank_id"),
-            "subtype": obj.get("subtype"),
-            "name": obj.get("name"),
-            "description": obj.get("description"),
-            "observations": [MentalModelObservationResponse.from_dict(_item) for _item in obj["observations"]] if obj.get("observations") is not None else None,
-            "version": obj.get("version") if obj.get("version") is not None else 0,
-            "entity_id": obj.get("entity_id"),
-            "links": obj.get("links"),
-            "tags": obj.get("tags"),
-            "last_updated": obj.get("last_updated"),
-            "last_refresh_at": obj.get("last_refresh_at"),
-            "freshness": MentalModelFreshnessResponse.from_dict(obj["freshness"]) if obj.get("freshness") is not None else None,
-            "created_at": obj.get("created_at")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/observation_evidence_response.py

@@ -1,93 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field, StrictStr
-from typing import Any, ClassVar, Dict, List
-from typing import Optional, Set
-from typing_extensions import Self
-
-class ObservationEvidenceResponse(BaseModel):
-    """
-    A single piece of evidence supporting an observation.
-    """ # noqa: E501
-    memory_id: StrictStr = Field(description="ID of the memory unit this evidence comes from")
-    quote: StrictStr = Field(description="Exact quote from the memory supporting the observation")
-    relevance: StrictStr = Field(description="Brief explanation of how this quote supports the observation")
-    timestamp: StrictStr = Field(description="When the source memory was created (ISO format)")
-    __properties: ClassVar[List[str]] = ["memory_id", "quote", "relevance", "timestamp"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of ObservationEvidenceResponse from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of ObservationEvidenceResponse from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "memory_id": obj.get("memory_id"),
-            "quote": obj.get("quote"),
-            "relevance": obj.get("relevance"),
-            "timestamp": obj.get("timestamp")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/observation_input.py

@@ -1,89 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field, StrictStr
-from typing import Any, ClassVar, Dict, List
-from typing import Optional, Set
-from typing_extensions import Self
-
-class ObservationInput(BaseModel):
-    """
-    Input model for a single observation.
-    """ # noqa: E501
-    title: StrictStr = Field(description="Short title/header for the observation")
-    content: StrictStr = Field(description="Content of the observation")
-    __properties: ClassVar[List[str]] = ["title", "content"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of ObservationInput from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of ObservationInput from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "title": obj.get("title"),
-            "content": obj.get("content")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/operation_response.py

@@ -29,7 +29,7 @@ class OperationResponse(BaseModel):
     id: StrictStr
     task_type: StrictStr
     items_count: StrictInt
-    document_id: Optional[StrictStr] = None
+    document_id: Optional[StrictStr]
     created_at: StrictStr
     status: StrictStr
     error_message: Optional[StrictStr]

hindsight-clients/python/hindsight_client_api/models/operation_status_response.py

@@ -1,131 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, StrictStr, field_validator
-from typing import Any, ClassVar, Dict, List, Optional
-from typing import Optional, Set
-from typing_extensions import Self
-
-class OperationStatusResponse(BaseModel):
-    """
-    Response model for getting a single operation status.
-    """ # noqa: E501
-    operation_id: StrictStr
-    status: StrictStr
-    operation_type: Optional[StrictStr] = None
-    created_at: Optional[StrictStr] = None
-    updated_at: Optional[StrictStr] = None
-    completed_at: Optional[StrictStr] = None
-    error_message: Optional[StrictStr] = None
-    __properties: ClassVar[List[str]] = ["operation_id", "status", "operation_type", "created_at", "updated_at", "completed_at", "error_message"]
-
-    @field_validator('status')
-    def status_validate_enum(cls, value):
-        """Validates the enum"""
-        if value not in set(['pending', 'completed', 'failed', 'not_found']):
-            raise ValueError("must be one of enum values ('pending', 'completed', 'failed', 'not_found')")
-        return value
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of OperationStatusResponse from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # set to None if operation_type (nullable) is None
-        # and model_fields_set contains the field
-        if self.operation_type is None and "operation_type" in self.model_fields_set:
-            _dict['operation_type'] = None
-
-        # set to None if created_at (nullable) is None
-        # and model_fields_set contains the field
-        if self.created_at is None and "created_at" in self.model_fields_set:
-            _dict['created_at'] = None
-
-        # set to None if updated_at (nullable) is None
-        # and model_fields_set contains the field
-        if self.updated_at is None and "updated_at" in self.model_fields_set:
-            _dict['updated_at'] = None
-
-        # set to None if completed_at (nullable) is None
-        # and model_fields_set contains the field
-        if self.completed_at is None and "completed_at" in self.model_fields_set:
-            _dict['completed_at'] = None
-
-        # set to None if error_message (nullable) is None
-        # and model_fields_set contains the field
-        if self.error_message is None and "error_message" in self.model_fields_set:
-            _dict['error_message'] = None
-
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of OperationStatusResponse from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "operation_id": obj.get("operation_id"),
-            "status": obj.get("status"),
-            "operation_type": obj.get("operation_type"),
-            "created_at": obj.get("created_at"),
-            "updated_at": obj.get("updated_at"),
-            "completed_at": obj.get("completed_at"),
-            "error_message": obj.get("error_message")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/operations_list_response.py

@@ -17,7 +17,7 @@ import pprint
 import re  # noqa: F401
 import json
 
-from pydantic import BaseModel, ConfigDict, StrictInt, StrictStr
+from pydantic import BaseModel, ConfigDict, StrictStr
 from typing import Any, ClassVar, Dict, List
 from hindsight_client_api.models.operation_response import OperationResponse
 from typing import Optional, Set
@@ -28,9 +28,8 @@ class OperationsListResponse(BaseModel):
     Response model for list operations endpoint.
     """ # noqa: E501
     bank_id: StrictStr
-    total: StrictInt
     operations: List[OperationResponse]
-    __properties: ClassVar[List[str]] = ["bank_id", "total", "operations"]
+    __properties: ClassVar[List[str]] = ["bank_id", "operations"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -91,7 +90,6 @@ class OperationsListResponse(BaseModel):
 
         _obj = cls.model_validate({
             "bank_id": obj.get("bank_id"),
-            "total": obj.get("total"),
             "operations": [OperationResponse.from_dict(_item) for _item in obj["operations"]] if obj.get("operations") is not None else None
         })
         return _obj

hindsight-clients/python/hindsight_client_api/models/reflect_based_on.py

@@ -1,105 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field
-from typing import Any, ClassVar, Dict, List, Optional
-from hindsight_client_api.models.reflect_fact import ReflectFact
-from hindsight_client_api.models.reflect_mental_model import ReflectMentalModel
-from typing import Optional, Set
-from typing_extensions import Self
-
-class ReflectBasedOn(BaseModel):
-    """
-    Evidence the response is based on: memories and mental models.
-    """ # noqa: E501
-    memories: Optional[List[ReflectFact]] = Field(default=None, description="Memory facts used to generate the response")
-    mental_models: Optional[List[ReflectMentalModel]] = Field(default=None, description="Mental models accessed during reflection")
-    __properties: ClassVar[List[str]] = ["memories", "mental_models"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of ReflectBasedOn from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # override the default output from pydantic by calling `to_dict()` of each item in memories (list)
-        _items = []
-        if self.memories:
-            for _item_memories in self.memories:
-                if _item_memories:
-                    _items.append(_item_memories.to_dict())
-            _dict['memories'] = _items
-        # override the default output from pydantic by calling `to_dict()` of each item in mental_models (list)
-        _items = []
-        if self.mental_models:
-            for _item_mental_models in self.mental_models:
-                if _item_mental_models:
-                    _items.append(_item_mental_models.to_dict())
-            _dict['mental_models'] = _items
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of ReflectBasedOn from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "memories": [ReflectFact.from_dict(_item) for _item in obj["memories"]] if obj.get("memories") is not None else None,
-            "mental_models": [ReflectMentalModel.from_dict(_item) for _item in obj["mental_models"]] if obj.get("mental_models") is not None else None
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/reflect_include_options.py

@@ -19,7 +19,6 @@ import json
 
 from pydantic import BaseModel, ConfigDict, Field
 from typing import Any, ClassVar, Dict, List, Optional
-from hindsight_client_api.models.tool_calls_include_options import ToolCallsIncludeOptions
 from typing import Optional, Set
 from typing_extensions import Self
 
@@ -28,8 +27,7 @@ class ReflectIncludeOptions(BaseModel):
     Options for including additional data in reflect results.
     """ # noqa: E501
     facts: Optional[Dict[str, Any]] = Field(default=None, description="Options for including facts (based_on) in reflect results.")
-    tool_calls: Optional[ToolCallsIncludeOptions] = None
-    __properties: ClassVar[List[str]] = ["facts", "tool_calls"]
+    __properties: ClassVar[List[str]] = ["facts"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -70,14 +68,6 @@ class ReflectIncludeOptions(BaseModel):
             exclude=excluded_fields,
             exclude_none=True,
         )
-        # override the default output from pydantic by calling `to_dict()` of tool_calls
-        if self.tool_calls:
-            _dict['tool_calls'] = self.tool_calls.to_dict()
-        # set to None if tool_calls (nullable) is None
-        # and model_fields_set contains the field
-        if self.tool_calls is None and "tool_calls" in self.model_fields_set:
-            _dict['tool_calls'] = None
-
         return _dict
 
     @classmethod
@@ -90,8 +80,7 @@ class ReflectIncludeOptions(BaseModel):
             return cls.model_validate(obj)
 
         _obj = cls.model_validate({
-            "facts": obj.get("facts"),
-            "tool_calls": ToolCallsIncludeOptions.from_dict(obj["tool_calls"]) if obj.get("tool_calls") is not None else None
+            "facts": obj.get("facts")
         })
         return _obj
 

hindsight-clients/python/hindsight_client_api/models/reflect_llm_call.py

@@ -1,89 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr
-from typing import Any, ClassVar, Dict, List
-from typing import Optional, Set
-from typing_extensions import Self
-
-class ReflectLLMCall(BaseModel):
-    """
-    An LLM call made during reflect agent execution.
-    """ # noqa: E501
-    scope: StrictStr = Field(description="Call scope: agent_1, agent_2, final, etc.")
-    duration_ms: StrictInt = Field(description="Execution time in milliseconds")
-    __properties: ClassVar[List[str]] = ["scope", "duration_ms"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of ReflectLLMCall from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of ReflectLLMCall from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "scope": obj.get("scope"),
-            "duration_ms": obj.get("duration_ms")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/reflect_mental_model.py

@@ -1,100 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field, StrictStr
-from typing import Any, ClassVar, Dict, List, Optional
-from typing import Optional, Set
-from typing_extensions import Self
-
-class ReflectMentalModel(BaseModel):
-    """
-    A mental model accessed during reflect.
-    """ # noqa: E501
-    id: StrictStr = Field(description="Mental model ID")
-    name: StrictStr = Field(description="Mental model name")
-    type: StrictStr = Field(description="Mental model type: entity, concept, event")
-    subtype: StrictStr = Field(description="Mental model subtype: structural, emergent, learned, directive")
-    observations: Optional[List[StrictStr]] = None
-    __properties: ClassVar[List[str]] = ["id", "name", "type", "subtype", "observations"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of ReflectMentalModel from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # set to None if observations (nullable) is None
-        # and model_fields_set contains the field
-        if self.observations is None and "observations" in self.model_fields_set:
-            _dict['observations'] = None
-
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of ReflectMentalModel from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "id": obj.get("id"),
-            "name": obj.get("name"),
-            "type": obj.get("type"),
-            "subtype": obj.get("subtype"),
-            "observations": obj.get("observations")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/reflect_response.py

@@ -17,11 +17,9 @@ import pprint
 import re  # noqa: F401
 import json
 
-from pydantic import BaseModel, ConfigDict, Field, StrictStr
+from pydantic import BaseModel, ConfigDict, StrictStr
 from typing import Any, ClassVar, Dict, List, Optional
-from hindsight_client_api.models.created_mental_model import CreatedMentalModel
-from hindsight_client_api.models.reflect_based_on import ReflectBasedOn
-from hindsight_client_api.models.reflect_trace import ReflectTrace
+from hindsight_client_api.models.reflect_fact import ReflectFact
 from hindsight_client_api.models.token_usage import TokenUsage
 from typing import Optional, Set
 from typing_extensions import Self
@@ -31,12 +29,10 @@ class ReflectResponse(BaseModel):
     Response model for think endpoint.
     """ # noqa: E501
     text: StrictStr
-    based_on: Optional[ReflectBasedOn] = None
+    based_on: Optional[List[ReflectFact]] = None
     structured_output: Optional[Dict[str, Any]] = None
     usage: Optional[TokenUsage] = None
-    trace: Optional[ReflectTrace] = None
-    mental_models_created: Optional[List[CreatedMentalModel]] = Field(default=None, description="Mental models created during this reflection (via the learn tool).")
-    __properties: ClassVar[List[str]] = ["text", "based_on", "structured_output", "usage", "trace", "mental_models_created"]
+    __properties: ClassVar[List[str]] = ["text", "based_on", "structured_output", "usage"]
 
     model_config = ConfigDict(
         populate_by_name=True,
@@ -77,27 +73,16 @@ class ReflectResponse(BaseModel):
             exclude=excluded_fields,
             exclude_none=True,
         )
-        # override the default output from pydantic by calling `to_dict()` of based_on
+        # override the default output from pydantic by calling `to_dict()` of each item in based_on (list)
+        _items = []
         if self.based_on:
-            _dict['based_on'] = self.based_on.to_dict()
+            for _item_based_on in self.based_on:
+                if _item_based_on:
+                    _items.append(_item_based_on.to_dict())
+            _dict['based_on'] = _items
         # override the default output from pydantic by calling `to_dict()` of usage
         if self.usage:
             _dict['usage'] = self.usage.to_dict()
-        # override the default output from pydantic by calling `to_dict()` of trace
-        if self.trace:
-            _dict['trace'] = self.trace.to_dict()
-        # override the default output from pydantic by calling `to_dict()` of each item in mental_models_created (list)
-        _items = []
-        if self.mental_models_created:
-            for _item_mental_models_created in self.mental_models_created:
-                if _item_mental_models_created:
-                    _items.append(_item_mental_models_created.to_dict())
-            _dict['mental_models_created'] = _items
-        # set to None if based_on (nullable) is None
-        # and model_fields_set contains the field
-        if self.based_on is None and "based_on" in self.model_fields_set:
-            _dict['based_on'] = None
-
         # set to None if structured_output (nullable) is None
         # and model_fields_set contains the field
         if self.structured_output is None and "structured_output" in self.model_fields_set:
@@ -108,11 +93,6 @@ class ReflectResponse(BaseModel):
         if self.usage is None and "usage" in self.model_fields_set:
             _dict['usage'] = None
 
-        # set to None if trace (nullable) is None
-        # and model_fields_set contains the field
-        if self.trace is None and "trace" in self.model_fields_set:
-            _dict['trace'] = None
-
         return _dict
 
     @classmethod
@@ -126,11 +106,9 @@ class ReflectResponse(BaseModel):
 
         _obj = cls.model_validate({
             "text": obj.get("text"),
-            "based_on": ReflectBasedOn.from_dict(obj["based_on"]) if obj.get("based_on") is not None else None,
+            "based_on": [ReflectFact.from_dict(_item) for _item in obj["based_on"]] if obj.get("based_on") is not None else None,
             "structured_output": obj.get("structured_output"),
-            "usage": TokenUsage.from_dict(obj["usage"]) if obj.get("usage") is not None else None,
-            "trace": ReflectTrace.from_dict(obj["trace"]) if obj.get("trace") is not None else None,
-            "mental_models_created": [CreatedMentalModel.from_dict(_item) for _item in obj["mental_models_created"]] if obj.get("mental_models_created") is not None else None
+            "usage": TokenUsage.from_dict(obj["usage"]) if obj.get("usage") is not None else None
         })
         return _obj
 

hindsight-clients/python/hindsight_client_api/models/reflect_tool_call.py

@@ -1,100 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field, StrictInt, StrictStr
-from typing import Any, ClassVar, Dict, List, Optional
-from typing import Optional, Set
-from typing_extensions import Self
-
-class ReflectToolCall(BaseModel):
-    """
-    A tool call made during reflect agent execution.
-    """ # noqa: E501
-    tool: StrictStr = Field(description="Tool name: lookup, recall, learn, expand")
-    input: Dict[str, Any] = Field(description="Tool input parameters")
-    output: Optional[Dict[str, Any]] = None
-    duration_ms: StrictInt = Field(description="Execution time in milliseconds")
-    iteration: Optional[StrictInt] = Field(default=0, description="Iteration number (1-based) when this tool was called")
-    __properties: ClassVar[List[str]] = ["tool", "input", "output", "duration_ms", "iteration"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of ReflectToolCall from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # set to None if output (nullable) is None
-        # and model_fields_set contains the field
-        if self.output is None and "output" in self.model_fields_set:
-            _dict['output'] = None
-
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of ReflectToolCall from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "tool": obj.get("tool"),
-            "input": obj.get("input"),
-            "output": obj.get("output"),
-            "duration_ms": obj.get("duration_ms"),
-            "iteration": obj.get("iteration") if obj.get("iteration") is not None else 0
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/reflect_trace.py

@@ -1,115 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field
-from typing import Any, ClassVar, Dict, List, Optional
-from hindsight_client_api.models.reflect_llm_call import ReflectLLMCall
-from hindsight_client_api.models.reflect_mental_model import ReflectMentalModel
-from hindsight_client_api.models.reflect_tool_call import ReflectToolCall
-from typing import Optional, Set
-from typing_extensions import Self
-
-class ReflectTrace(BaseModel):
-    """
-    Execution trace of LLM and tool calls during reflection.
-    """ # noqa: E501
-    tool_calls: Optional[List[ReflectToolCall]] = Field(default=None, description="Tool calls made during reflection")
-    llm_calls: Optional[List[ReflectLLMCall]] = Field(default=None, description="LLM calls made during reflection")
-    mental_models: Optional[List[ReflectMentalModel]] = Field(default=None, description="Mental models used during reflection (includes directives with subtype='directive')")
-    __properties: ClassVar[List[str]] = ["tool_calls", "llm_calls", "mental_models"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of ReflectTrace from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # override the default output from pydantic by calling `to_dict()` of each item in tool_calls (list)
-        _items = []
-        if self.tool_calls:
-            for _item_tool_calls in self.tool_calls:
-                if _item_tool_calls:
-                    _items.append(_item_tool_calls.to_dict())
-            _dict['tool_calls'] = _items
-        # override the default output from pydantic by calling `to_dict()` of each item in llm_calls (list)
-        _items = []
-        if self.llm_calls:
-            for _item_llm_calls in self.llm_calls:
-                if _item_llm_calls:
-                    _items.append(_item_llm_calls.to_dict())
-            _dict['llm_calls'] = _items
-        # override the default output from pydantic by calling `to_dict()` of each item in mental_models (list)
-        _items = []
-        if self.mental_models:
-            for _item_mental_models in self.mental_models:
-                if _item_mental_models:
-                    _items.append(_item_mental_models.to_dict())
-            _dict['mental_models'] = _items
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of ReflectTrace from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "tool_calls": [ReflectToolCall.from_dict(_item) for _item in obj["tool_calls"]] if obj.get("tool_calls") is not None else None,
-            "llm_calls": [ReflectLLMCall.from_dict(_item) for _item in obj["llm_calls"]] if obj.get("llm_calls") is not None else None,
-            "mental_models": [ReflectMentalModel.from_dict(_item) for _item in obj["mental_models"]] if obj.get("mental_models") is not None else None
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/refresh_mental_models_request.py

@@ -1,109 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, StrictStr, field_validator
-from typing import Any, ClassVar, Dict, List, Optional
-from typing import Optional, Set
-from typing_extensions import Self
-
-class RefreshMentalModelsRequest(BaseModel):
-    """
-    Request model for refresh mental models endpoint.
-    """ # noqa: E501
-    tags: Optional[List[StrictStr]] = None
-    subtype: Optional[StrictStr] = None
-    __properties: ClassVar[List[str]] = ["tags", "subtype"]
-
-    @field_validator('subtype')
-    def subtype_validate_enum(cls, value):
-        """Validates the enum"""
-        if value is None:
-            return value
-
-        if value not in set(['structural', 'emergent', 'pinned', 'learned']):
-            raise ValueError("must be one of enum values ('structural', 'emergent', 'pinned', 'learned')")
-        return value
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of RefreshMentalModelsRequest from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # set to None if tags (nullable) is None
-        # and model_fields_set contains the field
-        if self.tags is None and "tags" in self.model_fields_set:
-            _dict['tags'] = None
-
-        # set to None if subtype (nullable) is None
-        # and model_fields_set contains the field
-        if self.subtype is None and "subtype" in self.model_fields_set:
-            _dict['subtype'] = None
-
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of RefreshMentalModelsRequest from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "tags": obj.get("tags"),
-            "subtype": obj.get("subtype")
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/tool_calls_include_options.py

@@ -1,87 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, Field, StrictBool
-from typing import Any, ClassVar, Dict, List, Optional
-from typing import Optional, Set
-from typing_extensions import Self
-
-class ToolCallsIncludeOptions(BaseModel):
-    """
-    Options for including tool calls in reflect results.
-    """ # noqa: E501
-    output: Optional[StrictBool] = Field(default=True, description="Include tool outputs in the trace. Set to false to only include inputs (smaller payload).")
-    __properties: ClassVar[List[str]] = ["output"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of ToolCallsIncludeOptions from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of ToolCallsIncludeOptions from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "output": obj.get("output") if obj.get("output") is not None else True
-        })
-        return _obj
-
-

hindsight-clients/python/hindsight_client_api/models/update_mental_model_request.py

@@ -1,99 +0,0 @@
-# coding: utf-8
-
-"""
-    Hindsight HTTP API
-
-    HTTP API for Hindsight
-
-    The version of the OpenAPI document: 0.1.0
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
-
-    Do not edit the class manually.
-"""  # noqa: E501
-
-
-from __future__ import annotations
-import pprint
-import re  # noqa: F401
-import json
-
-from pydantic import BaseModel, ConfigDict, StrictStr
-from typing import Any, ClassVar, Dict, List, Optional
-from typing import Optional, Set
-from typing_extensions import Self
-
-class UpdateMentalModelRequest(BaseModel):
-    """
-    Request model for updating a mental model.
-    """ # noqa: E501
-    name: Optional[StrictStr] = None
-    description: Optional[StrictStr] = None
-    __properties: ClassVar[List[str]] = ["name", "description"]
-
-    model_config = ConfigDict(
-        populate_by_name=True,
-        validate_assignment=True,
-        protected_namespaces=(),
-    )
-
-
-    def to_str(self) -> str:
-        """Returns the string representation of the model using alias"""
-        return pprint.pformat(self.model_dump(by_alias=True))
-
-    def to_json(self) -> str:
-        """Returns the JSON representation of the model using alias"""
-        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
-        return json.dumps(self.to_dict())
-
-    @classmethod
-    def from_json(cls, json_str: str) -> Optional[Self]:
-        """Create an instance of UpdateMentalModelRequest from a JSON string"""
-        return cls.from_dict(json.loads(json_str))
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Return the dictionary representation of the model using alias.
-
-        This has the following differences from calling pydantic's
-        `self.model_dump(by_alias=True)`:
-
-        * `None` is only added to the output dict for nullable fields that
-          were set at model initialization. Other fields with value `None`
-          are ignored.
-        """
-        excluded_fields: Set[str] = set([
-        ])
-
-        _dict = self.model_dump(
-            by_alias=True,
-            exclude=excluded_fields,
-            exclude_none=True,
-        )
-        # set to None if name (nullable) is None
-        # and model_fields_set contains the field
-        if self.name is None and "name" in self.model_fields_set:
-            _dict['name'] = None
-
-        # set to None if description (nullable) is None
-        # and model_fields_set contains the field
-        if self.description is None and "description" in self.model_fields_set:
-            _dict['description'] = None
-
-        return _dict
-
-    @classmethod
-    def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
-        """Create an instance of UpdateMentalModelRequest from a dict"""
-        if obj is None:
-            return None
-
-        if not isinstance(obj, dict):
-            return cls.model_validate(obj)
-
-        _obj = cls.model_validate({
-            "name": obj.get("name"),
-            "description": obj.get("description")
-        })
-        return _obj
-
-

hindsight-clients/python/tests/test_main_operations.py

@@ -189,7 +189,8 @@ class TestReflect:
         """Test reflect with structured output via response_schema.
 
         When response_schema is provided, the response returns structured_output
-        field parsed according to the provided JSON schema.
+        field parsed according to the provided JSON schema. The text field is empty
+        since only a single LLM call is made for structured output.
         """
         from typing import Optional
         from pydantic import BaseModel
@@ -208,6 +209,8 @@ class TestReflect:
         )
 
         assert response is not None
+        # Text is empty when using structured output (single LLM call)
+        assert response.text == ""
 
         # Verify structured output is present and can be parsed into model
         assert response.structured_output is not None
@@ -507,6 +510,37 @@ class TestEntities:
             assert entity is not None
             assert entity.id == entity_id
 
+    def test_regenerate_entity_observations(self, client, bank_id):
+        """Test regenerating observations for an entity."""
+        import asyncio
+        from hindsight_client_api import ApiClient, Configuration
+        from hindsight_client_api.api import EntitiesApi
+
+        async def do_test():
+            config = Configuration(host=HINDSIGHT_API_URL)
+            api_client = ApiClient(config)
+            api = EntitiesApi(api_client)
+
+            # First list entities to get an ID
+            list_response = await api.list_entities(bank_id=bank_id)
+
+            if list_response.items and len(list_response.items) > 0:
+                entity_id = list_response.items[0].id
+
+                # Regenerate observations
+                result = await api.regenerate_entity_observations(
+                    bank_id=bank_id,
+                    entity_id=entity_id,
+                )
+                return entity_id, result
+            return None, None
+
+        entity_id, result = asyncio.get_event_loop().run_until_complete(do_test())
+
+        if entity_id:
+            assert result is not None
+            assert result.id == entity_id
+
 
 class TestDeleteBank:
     """Tests for bank deletion."""

hindsight-clients/typescript/generated/sdk.gen.ts

@@ -12,9 +12,6 @@ import type {
   ClearBankMemoriesData,
   ClearBankMemoriesErrors,
   ClearBankMemoriesResponses,
-  CreateMentalModelData,
-  CreateMentalModelErrors,
-  CreateMentalModelResponses,
   CreateOrUpdateBankData,
   CreateOrUpdateBankErrors,
   CreateOrUpdateBankResponses,
@@ -24,9 +21,6 @@ import type {
   DeleteDocumentData,
   DeleteDocumentErrors,
   DeleteDocumentResponses,
-  DeleteMentalModelData,
-  DeleteMentalModelErrors,
-  DeleteMentalModelResponses,
   GetAgentStatsData,
   GetAgentStatsErrors,
   GetAgentStatsResponses,
@@ -48,15 +42,6 @@ import type {
   GetMemoryData,
   GetMemoryErrors,
   GetMemoryResponses,
-  GetMentalModelData,
-  GetMentalModelErrors,
-  GetMentalModelResponses,
-  GetMentalModelVersionData,
-  GetMentalModelVersionErrors,
-  GetMentalModelVersionResponses,
-  GetOperationStatusData,
-  GetOperationStatusErrors,
-  GetOperationStatusResponses,
   HealthEndpointHealthGetData,
   HealthEndpointHealthGetResponses,
   ListBanksData,
@@ -71,12 +56,6 @@ import type {
   ListMemoriesData,
   ListMemoriesErrors,
   ListMemoriesResponses,
-  ListMentalModelsData,
-  ListMentalModelsErrors,
-  ListMentalModelsResponses,
-  ListMentalModelVersionsData,
-  ListMentalModelVersionsErrors,
-  ListMentalModelVersionsResponses,
   ListOperationsData,
   ListOperationsErrors,
   ListOperationsResponses,
@@ -91,27 +70,15 @@ import type {
   ReflectData,
   ReflectErrors,
   ReflectResponses,
-  RefreshMentalModelData,
-  RefreshMentalModelErrors,
-  RefreshMentalModelResponses,
-  RefreshMentalModelsData,
-  RefreshMentalModelsErrors,
-  RefreshMentalModelsResponses,
   RegenerateEntityObservationsData,
   RegenerateEntityObservationsErrors,
   RegenerateEntityObservationsResponses,
   RetainMemoriesData,
   RetainMemoriesErrors,
   RetainMemoriesResponses,
-  UpdateBankData,
   UpdateBankDispositionData,
   UpdateBankDispositionErrors,
   UpdateBankDispositionResponses,
-  UpdateBankErrors,
-  UpdateBankResponses,
-  UpdateMentalModelData,
-  UpdateMentalModelErrors,
-  UpdateMentalModelResponses,
 } from "./types.gen";
 
 export type Options<
@@ -315,11 +282,9 @@ export const getEntity = <ThrowOnError extends boolean = false>(
   >({ url: "/v1/default/banks/{bank_id}/entities/{entity_id}", ...options });
 
 /**
- * Regenerate entity observations (deprecated)
+ * Regenerate entity observations
  *
- * This endpoint is deprecated. Entity observations have been replaced by mental models.
- *
- * @deprecated
+ * Regenerate observations for an entity based on all facts mentioning it.
  */
 export const regenerateEntityObservations = <
   ThrowOnError extends boolean = false,
@@ -335,170 +300,6 @@ export const regenerateEntityObservations = <
     ...options,
   });
 
-/**
- * List mental models
- *
- * List all mental models for a bank, optionally filtered by subtype or tags.
- */
-export const listMentalModels = <ThrowOnError extends boolean = false>(
-  options: Options<ListMentalModelsData, ThrowOnError>,
-) =>
-  (options.client ?? client).get<
-    ListMentalModelsResponses,
-    ListMentalModelsErrors,
-    ThrowOnError
-  >({ url: "/v1/default/banks/{bank_id}/mental-models", ...options });
-
-/**
- * Create mental model
- *
- * Create a mental model. Supports two subtypes:
- * - 'pinned' (default): User-defined topic, observations are LLM-generated on refresh
- * - 'directive': User-defined hard rules, observations are provided at creation and never regenerated
- */
-export const createMentalModel = <ThrowOnError extends boolean = false>(
-  options: Options<CreateMentalModelData, ThrowOnError>,
-) =>
-  (options.client ?? client).post<
-    CreateMentalModelResponses,
-    CreateMentalModelErrors,
-    ThrowOnError
-  >({
-    url: "/v1/default/banks/{bank_id}/mental-models",
-    ...options,
-    headers: {
-      "Content-Type": "application/json",
-      ...options.headers,
-    },
-  });
-
-/**
- * Delete mental model
- *
- * Delete a mental model.
- */
-export const deleteMentalModel = <ThrowOnError extends boolean = false>(
-  options: Options<DeleteMentalModelData, ThrowOnError>,
-) =>
-  (options.client ?? client).delete<
-    DeleteMentalModelResponses,
-    DeleteMentalModelErrors,
-    ThrowOnError
-  >({
-    url: "/v1/default/banks/{bank_id}/mental-models/{model_id}",
-    ...options,
-  });
-
-/**
- * Get mental model
- *
- * Get a specific mental model by ID.
- */
-export const getMentalModel = <ThrowOnError extends boolean = false>(
-  options: Options<GetMentalModelData, ThrowOnError>,
-) =>
-  (options.client ?? client).get<
-    GetMentalModelResponses,
-    GetMentalModelErrors,
-    ThrowOnError
-  >({
-    url: "/v1/default/banks/{bank_id}/mental-models/{model_id}",
-    ...options,
-  });
-
-/**
- * Update mental model
- *
- * Update a mental model's name and/or description. Useful for editing directives.
- */
-export const updateMentalModel = <ThrowOnError extends boolean = false>(
-  options: Options<UpdateMentalModelData, ThrowOnError>,
-) =>
-  (options.client ?? client).patch<
-    UpdateMentalModelResponses,
-    UpdateMentalModelErrors,
-    ThrowOnError
-  >({
-    url: "/v1/default/banks/{bank_id}/mental-models/{model_id}",
-    ...options,
-    headers: {
-      "Content-Type": "application/json",
-      ...options.headers,
-    },
-  });
-
-/**
- * Refresh mental models (async)
- *
- * Submit a background job to refresh mental models for a bank. By default refreshes all subtypes. Optionally specify 'subtype' to only refresh 'structural' (from mission) or 'emergent' (from entities) models. Optionally pass tags to apply to newly created models. Use GET /banks/{bank_id}/operations to check progress.
- */
-export const refreshMentalModels = <ThrowOnError extends boolean = false>(
-  options: Options<RefreshMentalModelsData, ThrowOnError>,
-) =>
-  (options.client ?? client).post<
-    RefreshMentalModelsResponses,
-    RefreshMentalModelsErrors,
-    ThrowOnError
-  >({
-    url: "/v1/default/banks/{bank_id}/mental-models/refresh",
-    ...options,
-    headers: {
-      "Content-Type": "application/json",
-      ...options.headers,
-    },
-  });
-
-/**
- * Refresh mental model content (async)
- *
- * Submit a background job to refresh content for a specific mental model. This is useful for newly created learned models or to refresh content for any model.
- */
-export const refreshMentalModel = <ThrowOnError extends boolean = false>(
-  options: Options<RefreshMentalModelData, ThrowOnError>,
-) =>
-  (options.client ?? client).post<
-    RefreshMentalModelResponses,
-    RefreshMentalModelErrors,
-    ThrowOnError
-  >({
-    url: "/v1/default/banks/{bank_id}/mental-models/{model_id}/refresh",
-    ...options,
-  });
-
-/**
- * List mental model version history
- *
- * List all saved versions of a mental model's observations, ordered by version descending.
- */
-export const listMentalModelVersions = <ThrowOnError extends boolean = false>(
-  options: Options<ListMentalModelVersionsData, ThrowOnError>,
-) =>
-  (options.client ?? client).get<
-    ListMentalModelVersionsResponses,
-    ListMentalModelVersionsErrors,
-    ThrowOnError
-  >({
-    url: "/v1/default/banks/{bank_id}/mental-models/{model_id}/versions",
-    ...options,
-  });
-
-/**
- * Get specific mental model version
- *
- * Get observations from a specific version of a mental model.
- */
-export const getMentalModelVersion = <ThrowOnError extends boolean = false>(
-  options: Options<GetMentalModelVersionData, ThrowOnError>,
-) =>
-  (options.client ?? client).get<
-    GetMentalModelVersionResponses,
-    GetMentalModelVersionErrors,
-    ThrowOnError
-  >({
-    url: "/v1/default/banks/{bank_id}/mental-models/{model_id}/versions/{version}",
-    ...options,
-  });
-
 /**
  * List documents
  *
@@ -607,27 +408,10 @@ export const cancelOperation = <ThrowOnError extends boolean = false>(
     ...options,
   });
 
-/**
- * Get operation status
- *
- * Get the status of a specific async operation. Returns 'pending', 'completed', or 'failed'. Completed operations are removed from storage, so 'completed' means the operation finished successfully.
- */
-export const getOperationStatus = <ThrowOnError extends boolean = false>(
-  options: Options<GetOperationStatusData, ThrowOnError>,
-) =>
-  (options.client ?? client).get<
-    GetOperationStatusResponses,
-    GetOperationStatusErrors,
-    ThrowOnError
-  >({
-    url: "/v1/default/banks/{bank_id}/operations/{operation_id}",
-    ...options,
-  });
-
 /**
  * Get memory bank profile
  *
- * Get disposition traits and mission for a memory bank. Auto-creates agent with defaults if not exists.
+ * Get disposition traits and background for a memory bank. Auto-creates agent with defaults if not exists.
  */
 export const getBankProfile = <ThrowOnError extends boolean = false>(
   options: Options<GetBankProfileData, ThrowOnError>,
@@ -660,11 +444,9 @@ export const updateBankDisposition = <ThrowOnError extends boolean = false>(
   });
 
 /**
- * Add/merge memory bank background (deprecated)
+ * Add/merge memory bank background
  *
- * Deprecated: Use PUT /mission instead. This endpoint now updates the mission field.
- *
- * @deprecated
+ * Add new background information or merge with existing. LLM intelligently resolves conflicts, normalizes to first person, and optionally infers disposition traits.
  */
 export const addBankBackground = <ThrowOnError extends boolean = false>(
   options: Options<AddBankBackgroundData, ThrowOnError>,
@@ -696,31 +478,10 @@ export const deleteBank = <ThrowOnError extends boolean = false>(
     ThrowOnError
   >({ url: "/v1/default/banks/{bank_id}", ...options });
 
-/**
- * Partial update memory bank
- *
- * Partially update an agent's profile. Only provided fields will be updated.
- */
-export const updateBank = <ThrowOnError extends boolean = false>(
-  options: Options<UpdateBankData, ThrowOnError>,
-) =>
-  (options.client ?? client).patch<
-    UpdateBankResponses,
-    UpdateBankErrors,
-    ThrowOnError
-  >({
-    url: "/v1/default/banks/{bank_id}",
-    ...options,
-    headers: {
-      "Content-Type": "application/json",
-      ...options.headers,
-    },
-  });
-
 /**
  * Create or update memory bank
  *
- * Create a new agent or update existing agent with disposition and mission. Auto-fills missing fields with defaults.
+ * Create a new agent or update existing agent with disposition and background. Auto-fills missing fields with defaults.
  */
 export const createOrUpdateBank = <ThrowOnError extends boolean = false>(
   options: Options<CreateOrUpdateBankData, ThrowOnError>,

hindsight-clients/typescript/src/index.ts

@@ -102,8 +102,6 @@ export class HindsightClient {
             documentId?: string;
             async?: boolean;
             entities?: EntityInput[];
-            /** Optional list of tags for this memory */
-            tags?: string[];
         }
     ): Promise<RetainResponse> {
         const item: {
@@ -113,7 +111,6 @@ export class HindsightClient {
             metadata?: Record<string, string>;
             document_id?: string;
             entities?: EntityInput[];
-            tags?: string[];
         } = { content };
         if (options?.timestamp) {
             item.timestamp =
@@ -133,9 +130,6 @@ export class HindsightClient {
         if (options?.entities) {
             item.entities = options.entities;
         }
-        if (options?.tags) {
-            item.tags = options.tags;
-        }
 
         const response = await sdk.retainMemories({
             client: this.client,
@@ -198,10 +192,6 @@ export class HindsightClient {
             maxEntityTokens?: number;
             includeChunks?: boolean;
             maxChunkTokens?: number;
-            /** Optional list of tags to filter memories by */
-            tags?: string[];
-            /** How to match tags: 'any' (OR, includes untagged), 'all' (AND, includes untagged), 'any_strict' (OR, excludes untagged), 'all_strict' (AND, excludes untagged). Default: 'any' */
-            tagsMatch?: 'any' | 'all' | 'any_strict' | 'all_strict';
         }
     ): Promise<RecallResponse> {
         const response = await sdk.recallMemories({
@@ -218,8 +208,6 @@ export class HindsightClient {
                     entities: options?.includeEntities ? { max_tokens: options?.maxEntityTokens ?? 500 } : undefined,
                     chunks: options?.includeChunks ? { max_tokens: options?.maxChunkTokens ?? 8192 } : undefined,
                 },
-                tags: options?.tags,
-                tags_match: options?.tagsMatch,
             },
         });
 
@@ -232,14 +220,7 @@ export class HindsightClient {
     async reflect(
         bankId: string,
         query: string,
-        options?: {
-            context?: string;
-            budget?: Budget;
-            /** Optional list of tags to filter memories by */
-            tags?: string[];
-            /** How to match tags: 'any' (OR, includes untagged), 'all' (AND, includes untagged), 'any_strict' (OR, excludes untagged), 'all_strict' (AND, excludes untagged). Default: 'any' */
-            tagsMatch?: 'any' | 'all' | 'any_strict' | 'all_strict';
-        }
+        options?: { context?: string; budget?: Budget }
     ): Promise<ReflectResponse> {
         const response = await sdk.reflect({
             client: this.client,
@@ -248,8 +229,6 @@ export class HindsightClient {
                 query,
                 context: options?.context,
                 budget: options?.budget || 'low',
-                tags: options?.tags,
-                tags_match: options?.tagsMatch,
             },
         });
 

hindsight-control-plane/package.json

@@ -30,7 +30,6 @@
     "@radix-ui/react-alert-dialog": "^1.1.15",
     "@radix-ui/react-checkbox": "^1.3.3",
     "@radix-ui/react-dialog": "^1.1.15",
-    "@radix-ui/react-dropdown-menu": "^2.1.16",
     "@radix-ui/react-label": "^2.1.8",
     "@radix-ui/react-popover": "^1.1.15",
     "@radix-ui/react-radio-group": "^1.3.8",
@@ -38,10 +37,7 @@
     "@radix-ui/react-slider": "^1.3.6",
     "@radix-ui/react-slot": "^1.2.4",
     "@radix-ui/react-switch": "^1.2.6",
-    "@radix-ui/react-tabs": "^1.1.13",
-    "@radix-ui/react-tooltip": "^1.2.8",
     "@tailwindcss/postcss": "^4.1.17",
-    "@tailwindcss/typography": "^0.5.19",
     "@types/cytoscape": "^3.21.9",
     "@types/node": "^24.10.0",
     "@types/react": "^19.2.2",
@@ -60,7 +56,6 @@
     "react": "^19.2.0",
     "react-chrono": "^2.9.1",
     "react-dom": "^19.2.0",
-    "react-markdown": "^10.1.0",
     "react18-json-view": "^0.2.9",
     "recharts": "^3.5.1",
     "tailwind-merge": "^3.4.0",

hindsight-control-plane/src/app/api/banks/[bankId]/mental-models/[modelId]/refresh/route.ts

@@ -1,34 +0,0 @@
-import { NextResponse } from "next/server";
-import { sdk, lowLevelClient } from "@/lib/hindsight-client";
-
-export async function POST(
-  request: Request,
-  { params }: { params: Promise<{ bankId: string; modelId: string }> }
-) {
-  try {
-    const { bankId, modelId } = await params;
-
-    if (!bankId) {
-      return NextResponse.json({ error: "bank_id is required" }, { status: 400 });
-    }
-
-    if (!modelId) {
-      return NextResponse.json({ error: "model_id is required" }, { status: 400 });
-    }
-
-    const response = await sdk.refreshMentalModel({
-      client: lowLevelClient,
-      path: { bank_id: bankId, model_id: modelId },
-    });
-
-    if (response.error) {
-      console.error("API error refreshing mental model:", response.error);
-      return NextResponse.json({ error: "Failed to refresh mental model" }, { status: 500 });
-    }
-
-    return NextResponse.json(response.data, { status: 200 });
-  } catch (error) {
-    console.error("Error refreshing mental model:", error);
-    return NextResponse.json({ error: "Failed to refresh mental model" }, { status: 500 });
-  }
-}

hindsight-control-plane/src/app/api/banks/[bankId]/mental-models/[modelId]/route.ts

@@ -1,80 +0,0 @@
-import { NextResponse } from "next/server";
-import { sdk, lowLevelClient } from "@/lib/hindsight-client";
-
-const DATAPLANE_URL = process.env.HINDSIGHT_CP_DATAPLANE_API_URL || "http://localhost:8888";
-
-export async function PATCH(
-  request: Request,
-  { params }: { params: Promise<{ bankId: string; modelId: string }> }
-) {
-  try {
-    const { bankId, modelId } = await params;
-
-    if (!bankId) {
-      return NextResponse.json({ error: "bank_id is required" }, { status: 400 });
-    }
-
-    if (!modelId) {
-      return NextResponse.json({ error: "model_id is required" }, { status: 400 });
-    }
-
-    const body = await request.json();
-
-    // Call the dataplane API directly since SDK may not have the update method yet
-    const response = await fetch(
-      `${DATAPLANE_URL}/v1/default/banks/${bankId}/mental-models/${modelId}`,
-      {
-        method: "PATCH",
-        headers: { "Content-Type": "application/json" },
-        body: JSON.stringify(body),
-      }
-    );
-
-    if (!response.ok) {
-      const errorText = await response.text();
-      console.error("API error updating mental model:", errorText);
-      return NextResponse.json(
-        { error: errorText || "Failed to update mental model" },
-        { status: response.status }
-      );
-    }
-
-    const data = await response.json();
-    return NextResponse.json(data, { status: 200 });
-  } catch (error) {
-    console.error("Error updating mental model:", error);
-    return NextResponse.json({ error: "Failed to update mental model" }, { status: 500 });
-  }
-}
-
-export async function DELETE(
-  request: Request,
-  { params }: { params: Promise<{ bankId: string; modelId: string }> }
-) {
-  try {
-    const { bankId, modelId } = await params;
-
-    if (!bankId) {
-      return NextResponse.json({ error: "bank_id is required" }, { status: 400 });
-    }
-
-    if (!modelId) {
-      return NextResponse.json({ error: "model_id is required" }, { status: 400 });
-    }
-
-    const response = await sdk.deleteMentalModel({
-      client: lowLevelClient,
-      path: { bank_id: bankId, model_id: modelId },
-    });
-
-    if (response.error) {
-      console.error("API error deleting mental model:", response.error);
-      return NextResponse.json({ error: "Failed to delete mental model" }, { status: 500 });
-    }
-
-    return NextResponse.json(response.data, { status: 200 });
-  } catch (error) {
-    console.error("Error deleting mental model:", error);
-    return NextResponse.json({ error: "Failed to delete mental model" }, { status: 500 });
-  }
-}

hindsight-control-plane/src/app/api/banks/[bankId]/mental-models/[modelId]/versions/[version]/route.ts

@@ -1,47 +0,0 @@
-import { NextResponse } from "next/server";
-
-const DATAPLANE_URL = process.env.HINDSIGHT_CP_DATAPLANE_API_URL || "http://localhost:8888";
-
-export async function GET(
-  request: Request,
-  { params }: { params: Promise<{ bankId: string; modelId: string; version: string }> }
-) {
-  try {
-    const { bankId, modelId, version } = await params;
-
-    if (!bankId) {
-      return NextResponse.json({ error: "bank_id is required" }, { status: 400 });
-    }
-
-    if (!modelId) {
-      return NextResponse.json({ error: "model_id is required" }, { status: 400 });
-    }
-
-    if (!version) {
-      return NextResponse.json({ error: "version is required" }, { status: 400 });
-    }
-
-    const response = await fetch(
-      `${DATAPLANE_URL}/v1/default/banks/${bankId}/mental-models/${modelId}/versions/${version}`,
-      {
-        method: "GET",
-        headers: { "Content-Type": "application/json" },
-      }
-    );
-
-    if (!response.ok) {
-      const errorText = await response.text();
-      console.error("API error getting mental model version:", errorText);
-      return NextResponse.json(
-        { error: errorText || "Failed to get mental model version" },
-        { status: response.status }
-      );
-    }
-
-    const data = await response.json();
-    return NextResponse.json(data, { status: 200 });
-  } catch (error) {
-    console.error("Error getting mental model version:", error);
-    return NextResponse.json({ error: "Failed to get mental model version" }, { status: 500 });
-  }
-}

hindsight-control-plane/src/app/api/banks/[bankId]/mental-models/[modelId]/versions/route.ts

@@ -1,43 +0,0 @@
-import { NextResponse } from "next/server";
-
-const DATAPLANE_URL = process.env.HINDSIGHT_CP_DATAPLANE_API_URL || "http://localhost:8888";
-
-export async function GET(
-  request: Request,
-  { params }: { params: Promise<{ bankId: string; modelId: string }> }
-) {
-  try {
-    const { bankId, modelId } = await params;
-
-    if (!bankId) {
-      return NextResponse.json({ error: "bank_id is required" }, { status: 400 });
-    }
-
-    if (!modelId) {
-      return NextResponse.json({ error: "model_id is required" }, { status: 400 });
-    }
-
-    const response = await fetch(
-      `${DATAPLANE_URL}/v1/default/banks/${bankId}/mental-models/${modelId}/versions`,
-      {
-        method: "GET",
-        headers: { "Content-Type": "application/json" },
-      }
-    );
-
-    if (!response.ok) {
-      const errorText = await response.text();
-      console.error("API error listing mental model versions:", errorText);
-      return NextResponse.json(
-        { error: errorText || "Failed to list mental model versions" },
-        { status: response.status }
-      );
-    }
-
-    const data = await response.json();
-    return NextResponse.json(data, { status: 200 });
-  } catch (error) {
-    console.error("Error listing mental model versions:", error);
-    return NextResponse.json({ error: "Failed to list mental model versions" }, { status: 500 });
-  }
-}

hindsight-control-plane/src/app/api/banks/[bankId]/mental-models/refresh/route.ts

@@ -1,39 +0,0 @@
-import { NextResponse } from "next/server";
-import { sdk, lowLevelClient } from "@/lib/hindsight-client";
-
-export async function POST(request: Request, { params }: { params: Promise<{ bankId: string }> }) {
-  try {
-    const { bankId } = await params;
-
-    if (!bankId) {
-      return NextResponse.json({ error: "bank_id is required" }, { status: 400 });
-    }
-
-    // Parse request body for optional subtype filter
-    let body: { subtype?: "structural" | "emergent"; tags?: string[] } | undefined;
-    try {
-      const text = await request.text();
-      if (text) {
-        body = JSON.parse(text);
-      }
-    } catch {
-      // Empty body is fine
-    }
-
-    const response = await sdk.refreshMentalModels({
-      client: lowLevelClient,
-      path: { bank_id: bankId },
-      body: body,
-    });
-
-    if (response.error) {
-      console.error("API error refreshing mental models:", response.error);
-      return NextResponse.json({ error: "Failed to refresh mental models" }, { status: 500 });
-    }
-
-    return NextResponse.json(response.data, { status: 200 });
-  } catch (error) {
-    console.error("Error refreshing mental models:", error);
-    return NextResponse.json({ error: "Failed to refresh mental models" }, { status: 500 });
-  }
-}

hindsight-control-plane/src/app/api/banks/[bankId]/mental-models/route.ts

@@ -1,88 +0,0 @@
-import { NextResponse } from "next/server";
-import { sdk, lowLevelClient } from "@/lib/hindsight-client";
-
-const DATAPLANE_URL = process.env.HINDSIGHT_CP_DATAPLANE_API_URL || "http://localhost:8888";
-
-export async function GET(request: Request, { params }: { params: Promise<{ bankId: string }> }) {
-  try {
-    const { bankId } = await params;
-    const { searchParams } = new URL(request.url);
-    const subtype = searchParams.get("subtype");
-
-    if (!bankId) {
-      return NextResponse.json({ error: "bank_id is required" }, { status: 400 });
-    }
-
-    // If subtype is specified, call the dataplane API directly with the query param
-    if (subtype) {
-      const response = await fetch(
-        `${DATAPLANE_URL}/v1/default/banks/${bankId}/mental-models?subtype=${subtype}`,
-        { method: "GET" }
-      );
-
-      if (!response.ok) {
-        const errorText = await response.text();
-        console.error("API error listing mental models:", errorText);
-        return NextResponse.json(
-          { error: "Failed to list mental models" },
-          { status: response.status }
-        );
-      }
-
-      const data = await response.json();
-      return NextResponse.json(data, { status: 200 });
-    }
-
-    // Default: use SDK which excludes directives
-    const response = await sdk.listMentalModels({
-      client: lowLevelClient,
-      path: { bank_id: bankId },
-    });
-
-    if (response.error) {
-      console.error("API error listing mental models:", response.error);
-      return NextResponse.json({ error: "Failed to list mental models" }, { status: 500 });
-    }
-
-    return NextResponse.json(response.data, { status: 200 });
-  } catch (error) {
-    console.error("Error listing mental models:", error);
-    return NextResponse.json({ error: "Failed to list mental models" }, { status: 500 });
-  }
-}
-
-export async function POST(request: Request, { params }: { params: Promise<{ bankId: string }> }) {
-  try {
-    const { bankId } = await params;
-
-    if (!bankId) {
-      return NextResponse.json({ error: "bank_id is required" }, { status: 400 });
-    }
-
-    const body = await request.json();
-
-    // Call the dataplane API directly since SDK may not have the new endpoint yet
-    const response = await fetch(`${DATAPLANE_URL}/v1/default/banks/${bankId}/mental-models`, {
-      method: "POST",
-      headers: {
-        "Content-Type": "application/json",
-      },
-      body: JSON.stringify(body),
-    });
-
-    if (!response.ok) {
-      const errorText = await response.text();
-      console.error("API error creating mental model:", errorText);
-      return NextResponse.json(
-        { error: errorText || "Failed to create mental model" },
-        { status: response.status }
-      );
-    }
-
-    const data = await response.json();
-    return NextResponse.json(data, { status: 201 });
-  } catch (error) {
-    console.error("Error creating mental model:", error);
-    return NextResponse.json({ error: "Failed to create mental model" }, { status: 500 });
-  }
-}

hindsight-control-plane/src/app/api/banks/[bankId]/operations/[operationId]/route.ts

@@ -1,34 +0,0 @@
-import { NextResponse } from "next/server";
-import { sdk, lowLevelClient } from "@/lib/hindsight-client";
-
-export async function GET(
-  request: Request,
-  { params }: { params: Promise<{ bankId: string; operationId: string }> }
-) {
-  try {
-    const { bankId, operationId } = await params;
-
-    if (!bankId) {
-      return NextResponse.json({ error: "bank_id is required" }, { status: 400 });
-    }
-
-    if (!operationId) {
-      return NextResponse.json({ error: "operation_id is required" }, { status: 400 });
-    }
-
-    const response = await sdk.getOperationStatus({
-      client: lowLevelClient,
-      path: { bank_id: bankId, operation_id: operationId },
-    });
-
-    if (response.error) {
-      console.error("API error getting operation status:", response.error);
-      return NextResponse.json({ error: "Failed to get operation status" }, { status: 500 });
-    }
-
-    return NextResponse.json(response.data, { status: 200 });
-  } catch (error) {
-    console.error("Error getting operation status:", error);
-    return NextResponse.json({ error: "Failed to get operation status" }, { status: 500 });
-  }
-}