hindsight-api 0.2.1__py3-none-any.whl → 0.3.0__py3-none-any.whl

hindsight_api/engine/query_analyzer.py

@@ -84,7 +84,7 @@ class DateparserQueryAnalyzer(QueryAnalyzer):
 
     Performance:
     - ~10-50ms per query
-    - No model loading required
+    - No model loading required (lazy import on first use)
     """
 
     def __init__(self):
@@ -112,8 +112,6 @@ class DateparserQueryAnalyzer(QueryAnalyzer):
         Returns:
             QueryAnalysis with temporal_constraint if found
         """
-        self.load()
-
         if reference_date is None:
             reference_date = datetime.now()
 
@@ -123,6 +121,9 @@ class DateparserQueryAnalyzer(QueryAnalyzer):
         if period_result is not None:
             return QueryAnalysis(temporal_constraint=period_result)
 
+        # Lazy load dateparser (only imports on first call, then cached)
+        self.load()
+
         # Use dateparser's search_dates to find temporal expressions
         settings = {
             "RELATIVE_BASE": reference_date,

hindsight_api/engine/response_models.py

@@ -14,6 +14,37 @@ from pydantic import BaseModel, ConfigDict, Field
 VALID_RECALL_FACT_TYPES = frozenset(["world", "experience", "opinion"])
 
 
+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):
     """
     Disposition traits for a memory bank.
@@ -54,6 +85,7 @@ class MemoryFact(BaseModel):
                 "metadata": {"source": "slack"},
                 "chunk_id": "bank123_session_abc123_0",
                 "activation": 0.95,
+                "tags": ["user_a", "session_123"],
             }
         }
     )
@@ -71,6 +103,7 @@ 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):
@@ -147,6 +180,7 @@ class ReflectResult(BaseModel):
                 },
                 "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},
             }
         }
     )
@@ -160,6 +194,10 @@ class ReflectResult(BaseModel):
         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.",
+    )
 
 
 class Opinion(BaseModel):