hindsight-api 0.2.1__py3-none-any.whl → 0.4.0__py3-none-any.whl

hindsight_api/engine/response_models.py

@@ -10,8 +10,94 @@ from typing import Any
 
 from pydantic import BaseModel, ConfigDict, Field
 
-# Valid fact types for recall operations (excludes 'observation' which is internal)
-VALID_RECALL_FACT_TYPES = frozenset(["world", "experience", "opinion"])
+# Valid fact types for recall operations (excludes 'opinion' which is deprecated)
+VALID_RECALL_FACT_TYPES = frozenset(["world", "experience", "observation"])
+
+
+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.")
+    input_tokens: int = Field(default=0, description="Input tokens used in this call")
+    output_tokens: int = Field(default=0, description="Output tokens used in this call")
+
+
+class ToolCallTrace(BaseModel):
+    """A single tool call made during reflect."""
+
+    tool: str = Field(description="Tool name: lookup, recall, learn, expand")
+    reason: str | None = Field(default=None, description="Agent's reasoning for making this tool call")
+    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 ObservationRef(BaseModel):
+    """Reference to an observation accessed during reflect."""
+
+    id: str = Field(description="Observation ID")
+    name: str = Field(description="Observation name")
+    type: str = Field(description="Observation type: entity, concept, event")
+    subtype: str = Field(description="Observation 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")
+    content: str = Field(description="Directive content")
+
+
+class TokenUsage(BaseModel):
+    """
+    Token usage metrics for LLM calls.
+
+    Tracks input/output tokens for a single request to enable
+    per-request cost tracking and monitoring.
+    """
+
+    model_config = ConfigDict(
+        json_schema_extra={
+            "example": {
+                "input_tokens": 1500,
+                "output_tokens": 500,
+                "total_tokens": 2000,
+            }
+        }
+    )
+
+    input_tokens: int = Field(default=0, description="Number of input/prompt tokens consumed")
+    output_tokens: int = Field(default=0, description="Number of output/completion tokens generated")
+    total_tokens: int = Field(default=0, description="Total tokens (input + output)")
+
+    def __add__(self, other: "TokenUsage") -> "TokenUsage":
+        """Allow aggregating token usage from multiple calls."""
+        return TokenUsage(
+            input_tokens=self.input_tokens + other.input_tokens,
+            output_tokens=self.output_tokens + other.output_tokens,
+            total_tokens=self.total_tokens + other.total_tokens,
+        )
 
 
 class DispositionTraits(BaseModel):
@@ -54,6 +140,7 @@ class MemoryFact(BaseModel):
                 "metadata": {"source": "slack"},
                 "chunk_id": "bank123_session_abc123_0",
                 "activation": 0.95,
+                "tags": ["user_a", "session_123"],
             }
         }
     )
@@ -71,6 +158,7 @@ class MemoryFact(BaseModel):
     chunk_id: str | None = Field(
         None, description="ID of the chunk this fact was extracted from (format: bank_id_document_id_chunk_index)"
     )
+    tags: list[str] | None = Field(None, description="Visibility scope tags associated with this fact")
 
 
 class ChunkInfo(BaseModel):
@@ -81,6 +169,28 @@ class ChunkInfo(BaseModel):
     truncated: bool = Field(default=False, description="Whether the chunk was truncated due to token limits")
 
 
+class ObservationResult(BaseModel):
+    """An observation result from recall (consolidated knowledge synthesized from facts)."""
+
+    id: str = Field(description="Unique observation ID")
+    text: str = Field(description="The observation text")
+    proof_count: int = Field(description="Number of facts supporting this observation")
+    relevance: float = Field(default=0.0, description="Relevance score to the query")
+    tags: list[str] | None = Field(default=None, description="Tags for visibility scoping")
+    source_memory_ids: list[str] = Field(
+        default_factory=list, description="IDs of facts that contribute to this observation"
+    )
+
+
+class MentalModelResult(BaseModel):
+    """A mental model result from recall (stored reflect response)."""
+
+    id: str = Field(description="Unique mental model ID")
+    name: str = Field(description="Human-readable name")
+    content: str = Field(description="The synthesized content")
+    relevance: float = Field(default=0.0, description="Relevance score to the query")
+
+
 class RecallResult(BaseModel):
     """
     Result from a recall operation.
@@ -144,22 +254,47 @@ class ReflectResult(BaseModel):
                     ],
                     "experience": [],
                     "opinion": [],
+                    "mental_models": [],
+                    "directives": [
+                        {
+                            "id": "directive-123",
+                            "name": "Response Style",
+                            "rules": ["Always be concise"],
+                        }
+                    ],
                 },
                 "new_opinions": ["Machine learning has great potential in healthcare"],
                 "structured_output": {"summary": "ML in healthcare", "confidence": 0.9},
+                "usage": {"input_tokens": 1500, "output_tokens": 500, "total_tokens": 2000},
             }
         }
     )
 
     text: str = Field(description="The formulated answer text")
-    based_on: dict[str, list[MemoryFact]] = Field(
-        description="Facts used to formulate the answer, organized by type (world, experience, opinion)"
+    based_on: dict[str, Any] = Field(
+        description="Facts used to formulate the answer, organized by type (world, experience, opinion, mental_models, directives)"
     )
     new_opinions: list[str] = Field(default_factory=list, description="List of newly formed opinions during reflection")
     structured_output: dict[str, Any] | None = Field(
         default=None,
         description="Structured output parsed according to the provided response schema. Only present when response_schema was provided.",
     )
+    usage: TokenUsage | None = Field(
+        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.",
+    )
+    directives_applied: list[DirectiveRef] = Field(
+        default_factory=list,
+        description="Directive mental models that were applied during this reflection.",
+    )
 
 
 class Opinion(BaseModel):
@@ -223,3 +358,32 @@ 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/engine/retain/bank_utils.py

@@ -1,5 +1,5 @@
 """
-bank profile utilities for disposition and background management.
+bank profile utilities for disposition and mission management.
 """
 
 import json
@@ -27,19 +27,18 @@ class BankProfile(TypedDict):
 
     name: str
     disposition: DispositionTraits
-    background: str
+    mission: str
 
 
-class BackgroundMergeResponse(BaseModel):
-    """LLM response for background merge with disposition inference."""
+class MissionMergeResponse(BaseModel):
+    """LLM response for mission merge."""
 
-    background: str = Field(description="Merged background in first person perspective")
-    disposition: DispositionTraits = Field(description="Inferred disposition traits (skepticism, literalism, empathy)")
+    mission: str = Field(description="Merged mission in first person perspective")
 
 
 async def get_bank_profile(pool, bank_id: str) -> BankProfile:
     """
-    Get bank profile (name, disposition + background).
+    Get bank profile (name, disposition + mission).
     Auto-creates bank with default values if not exists.
 
     Args:
@@ -47,13 +46,13 @@ async def get_bank_profile(pool, bank_id: str) -> BankProfile:
         bank_id: bank IDentifier
 
     Returns:
-        BankProfile with name, typed DispositionTraits, and background
+        BankProfile with name, typed DispositionTraits, and mission
     """
     async with acquire_with_retry(pool) as conn:
         # Try to get existing bank
         row = await conn.fetchrow(
             f"""
-            SELECT name, disposition, background
+            SELECT name, disposition, mission
             FROM {fq_table("banks")} WHERE bank_id = $1
             """,
             bank_id,
@@ -66,13 +65,15 @@ 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), background=row["background"]
+                name=row["name"],
+                disposition=DispositionTraits(**disposition_data),
+                mission=row["mission"] or "",
             )
 
         # Bank doesn't exist, create with defaults
         await conn.execute(
             f"""
-            INSERT INTO {fq_table("banks")} (bank_id, name, disposition, background)
+            INSERT INTO {fq_table("banks")} (bank_id, name, disposition, mission)
             VALUES ($1, $2, $3::jsonb, $4)
             ON CONFLICT (bank_id) DO NOTHING
             """,
@@ -82,7 +83,7 @@ async def get_bank_profile(pool, bank_id: str) -> BankProfile:
             "",
         )
 
-        return BankProfile(name=bank_id, disposition=DispositionTraits(**DEFAULT_DISPOSITION), background="")
+        return BankProfile(name=bank_id, disposition=DispositionTraits(**DEFAULT_DISPOSITION), mission="")
 
 
 async def update_bank_disposition(pool, bank_id: str, disposition: dict[str, int]) -> None:
@@ -110,244 +111,121 @@ async def update_bank_disposition(pool, bank_id: str, disposition: dict[str, int
         )
 
 
-async def merge_bank_background(pool, llm_config, bank_id: str, new_info: str, update_disposition: bool = True) -> dict:
+async def set_bank_mission(pool, bank_id: str, mission: str) -> None:
     """
-    Merge new background information with existing background using LLM.
+    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.
     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 background merging
+        llm_config: LLM configuration for mission merging
         bank_id: bank IDentifier
-        new_info: New background information to add/merge
-        update_disposition: If True, infer Big Five traits from background (default: True)
+        new_info: New mission information to add/merge
 
     Returns:
-        Dict with 'background' (str) and optionally 'disposition' (dict) keys
+        Dict with 'mission' (str) key
     """
     # Get current profile
     profile = await get_bank_profile(pool, bank_id)
-    current_background = profile["background"]
+    current_mission = profile["mission"]
 
-    # Use LLM to merge backgrounds and optionally infer disposition
-    result = await _llm_merge_background(llm_config, current_background, new_info, infer_disposition=update_disposition)
+    # Use LLM to merge missions
+    result = await _llm_merge_mission(llm_config, current_mission, new_info)
 
-    merged_background = result["background"]
-    inferred_disposition = result.get("disposition")
+    merged_mission = result["mission"]
 
     # Update in database
     async with acquire_with_retry(pool) as conn:
-        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,
-            )
-
-    response = {"background": merged_background}
-    if inferred_disposition:
-        response["disposition"] = inferred_disposition
+        await conn.execute(
+            f"""
+            UPDATE {fq_table("banks")}
+            SET mission = $2,
+                updated_at = NOW()
+            WHERE bank_id = $1
+            """,
+            bank_id,
+            merged_mission,
+        )
 
-    return response
+    return {"mission": merged_mission}
 
 
-async def _llm_merge_background(llm_config, current: str, new_info: str, infer_disposition: bool = False) -> dict:
+async def _llm_merge_mission(llm_config, current: str, new_info: str) -> dict:
     """
-    Use LLM to intelligently merge background information.
-    Optionally infer Big Five disposition traits from the merged background.
+    Use LLM to intelligently merge mission information.
 
     Args:
         llm_config: LLM configuration to use
-        current: Current background text
+        current: Current mission text
         new_info: New information to merge
-        infer_disposition: If True, also infer disposition traits
 
     Returns:
-        Dict with 'background' (str) and optionally 'disposition' (dict) keys
+        Dict with 'mission' (str) key
     """
-    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.
+    prompt = f"""You are helping maintain an agent's mission statement.
 
-Current background: {current if current else "(empty)"}
+Current mission: {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 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
+1. Merge the new information with the current mission
+2. If there are conflicts, 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 background text, no explanations
+6. Return ONLY the merged mission text, no explanations
 
-Merged background:"""
+Merged mission:"""
 
     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_background", temperature=0.3, max_completion_tokens=8192
+            messages=messages, scope="bank_mission", temperature=0.3, max_completion_tokens=8192
         )
 
-        logger.info(f"LLM response for background merge (first 500 chars): {content[:500]}")
-
-        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(),
-                }
+        logger.info(f"LLM response for mission merge (first 500 chars): {content[:500]}")
 
-            # 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}
+        merged = content.strip()
+        if not merged or merged.lower() in ["(empty)", "none", "n/a"]:
+            merged = new_info if new_info else ""
+        return {"mission": merged}
 
     except Exception as e:
-        logger.error(f"Error merging background with LLM: {e}")
+        logger.error(f"Error merging mission with LLM: {e}")
         # Fallback: just append new info
         if current:
             merged = f"{current} {new_info}".strip()
         else:
             merged = new_info
 
-        result = {"background": merged}
-        if infer_disposition:
-            result["disposition"] = DEFAULT_DISPOSITION.copy()
-        return result
+        return {"mission": merged}
 
 
 async def list_banks(pool) -> list:
@@ -358,12 +236,12 @@ async def list_banks(pool) -> list:
         pool: Database connection pool
 
     Returns:
-        List of dicts with bank_id, name, disposition, background, created_at, updated_at
+        List of dicts with bank_id, name, disposition, mission, created_at, updated_at
     """
     async with acquire_with_retry(pool) as conn:
         rows = await conn.fetch(
             f"""
-            SELECT bank_id, name, disposition, background, created_at, updated_at
+            SELECT bank_id, name, disposition, mission, created_at, updated_at
             FROM {fq_table("banks")}
             ORDER BY updated_at DESC
             """
@@ -381,7 +259,7 @@ async def list_banks(pool) -> list:
                     "bank_id": row["bank_id"],
                     "name": row["name"],
                     "disposition": disposition_data,
-                    "background": row["background"],
+                    "mission": row["mission"] or "",
                     "created_at": row["created_at"].isoformat() if row["created_at"] else None,
                     "updated_at": row["updated_at"].isoformat() if row["updated_at"] else None,
                 }