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

hindsight_api/engine/search/tags.py

@@ -0,0 +1,172 @@
+"""
+Tags filtering utilities for retrieval.
+
+Provides SQL building functions for filtering memories by tags.
+Supports four matching modes via TagsMatch enum:
+- "any": OR matching, includes untagged memories (default, backward compatible)
+- "all": AND matching, includes untagged memories
+- "any_strict": OR matching, excludes untagged memories
+- "all_strict": AND matching, excludes untagged memories
+
+OR matching (any/any_strict): Memory matches if ANY of its tags overlap with request tags
+AND matching (all/all_strict): Memory matches if ALL request tags are present in its tags
+"""
+
+from typing import Literal
+
+TagsMatch = Literal["any", "all", "any_strict", "all_strict"]
+
+
+def _parse_tags_match(match: TagsMatch) -> tuple[str, bool]:
+    """
+    Parse TagsMatch into operator and include_untagged flag.
+
+    Returns:
+        Tuple of (operator, include_untagged)
+        - operator: "&&" for any/any_strict, "@>" for all/all_strict
+        - include_untagged: True for any/all, False for any_strict/all_strict
+    """
+    if match == "any":
+        return "&&", True
+    elif match == "all":
+        return "@>", True
+    elif match == "any_strict":
+        return "&&", False
+    elif match == "all_strict":
+        return "@>", False
+    else:
+        # Default to "any" behavior
+        return "&&", True
+
+
+def build_tags_where_clause(
+    tags: list[str] | None,
+    param_offset: int = 1,
+    table_alias: str = "",
+    match: TagsMatch = "any",
+) -> tuple[str, list, int]:
+    """
+    Build a SQL WHERE clause for filtering by tags.
+
+    Supports four matching modes:
+    - "any" (default): OR matching, includes untagged memories
+    - "all": AND matching, includes untagged memories
+    - "any_strict": OR matching, excludes untagged memories
+    - "all_strict": AND matching, excludes untagged memories
+
+    Args:
+        tags: List of tags to filter by. If None or empty, returns empty clause (no filtering).
+        param_offset: Starting parameter number for SQL placeholders (default 1).
+        table_alias: Optional table alias prefix (e.g., "mu." for "memory_units mu").
+        match: Matching mode. Defaults to "any".
+
+    Returns:
+        Tuple of (sql_clause, params, next_param_offset):
+        - sql_clause: SQL WHERE clause string
+        - params: List of parameter values to bind
+        - next_param_offset: Next available parameter number
+
+    Example:
+        >>> clause, params, next_offset = build_tags_where_clause(['user_a'], 3, 'mu.', 'any_strict')
+        >>> print(clause)  # "AND mu.tags IS NOT NULL AND mu.tags != '{}' AND mu.tags && $3"
+    """
+    if not tags:
+        return "", [], param_offset
+
+    column = f"{table_alias}tags" if table_alias else "tags"
+    operator, include_untagged = _parse_tags_match(match)
+
+    if include_untagged:
+        # Include untagged memories (NULL or empty array) OR matching tags
+        clause = f"AND ({column} IS NULL OR {column} = '{{}}' OR {column} {operator} ${param_offset})"
+    else:
+        # Strict: only memories with matching tags (exclude NULL and empty)
+        clause = f"AND {column} IS NOT NULL AND {column} != '{{}}' AND {column} {operator} ${param_offset}"
+
+    return clause, [tags], param_offset + 1
+
+
+def build_tags_where_clause_simple(
+    tags: list[str] | None,
+    param_num: int,
+    table_alias: str = "",
+    match: TagsMatch = "any",
+) -> str:
+    """
+    Build a simple SQL WHERE clause for tags filtering.
+
+    This is a convenience version that returns just the clause string,
+    assuming the caller will add the tags array to their params list.
+
+    Args:
+        tags: List of tags to filter by. If None or empty, returns empty string.
+        param_num: Parameter number to use in the clause.
+        table_alias: Optional table alias prefix.
+        match: Matching mode. Defaults to "any".
+
+    Returns:
+        SQL clause string or empty string.
+    """
+    if not tags:
+        return ""
+
+    column = f"{table_alias}tags" if table_alias else "tags"
+    operator, include_untagged = _parse_tags_match(match)
+
+    if include_untagged:
+        # Include untagged memories (NULL or empty array) OR matching tags
+        return f"AND ({column} IS NULL OR {column} = '{{}}' OR {column} {operator} ${param_num})"
+    else:
+        # Strict: only memories with matching tags (exclude NULL and empty)
+        return f"AND {column} IS NOT NULL AND {column} != '{{}}' AND {column} {operator} ${param_num}"
+
+
+def filter_results_by_tags(
+    results: list,
+    tags: list[str] | None,
+    match: TagsMatch = "any",
+) -> list:
+    """
+    Filter retrieval results by tags in Python (for post-processing).
+
+    Used when SQL filtering isn't possible (e.g., graph traversal results).
+
+    Args:
+        results: List of RetrievalResult objects with a 'tags' attribute.
+        tags: List of tags to filter by. If None or empty, returns all results.
+        match: Matching mode. Defaults to "any".
+
+    Returns:
+        Filtered list of results.
+    """
+    if not tags:
+        return results
+
+    _, include_untagged = _parse_tags_match(match)
+    is_any_match = match in ("any", "any_strict")
+
+    tags_set = set(tags)
+    filtered = []
+
+    for result in results:
+        result_tags = getattr(result, "tags", None)
+
+        # Check if untagged
+        is_untagged = result_tags is None or len(result_tags) == 0
+
+        if is_untagged:
+            if include_untagged:
+                filtered.append(result)
+            # else: skip untagged
+        else:
+            result_tags_set = set(result_tags)
+            if is_any_match:
+                # Any overlap
+                if result_tags_set & tags_set:
+                    filtered.append(result)
+            else:
+                # All tags must be present
+                if tags_set <= result_tags_set:
+                    filtered.append(result)
+
+    return filtered

hindsight_api/engine/search/think_utils.py

@@ -3,31 +3,13 @@ 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"}
@@ -93,17 +75,46 @@ 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."""
+    """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.
+    """
     disposition_desc = build_disposition_description(disposition)
 
     name_section = f"""
@@ -125,6 +136,14 @@ 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:
@@ -135,14 +154,11 @@ MY IDENTITY & EXPERIENCES:
 WHAT I KNOW ABOUT THE WORLD:
 {world_facts_text}
 
-MY EXISTING OPINIONS & BELIEFS:
-{opinion_facts_text}
-
-{context_section}{name_section}{disposition_desc}{background_section}
+{entity_section}{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, opinions, 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, and personal traits to give you my honest perspective."""
 
 
 def get_system_message(disposition: DispositionTraits) -> str:
@@ -172,117 +188,7 @@ def get_system_message(disposition: DispositionTraits) -> str:
         " ".join(instructions) if instructions else "Balance your disposition traits when interpreting information."
     )
 
-    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."
-
-
-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 []
+    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 reflect(
@@ -290,7 +196,6 @@ async def reflect(
     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 = "",
@@ -307,7 +212,6 @@ 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
@@ -328,18 +232,15 @@ 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/engine/search/trace.py

@@ -11,6 +11,13 @@ from typing import Any, Literal
 from pydantic import BaseModel, Field
 
 
+class TemporalConstraint(BaseModel):
+    """Detected temporal constraint from query analysis."""
+
+    start: datetime | None = Field(default=None, description="Start of temporal range")
+    end: datetime | None = Field(default=None, description="End of temporal range")
+
+
 class QueryInfo(BaseModel):
     """Information about the search query."""
 
@@ -19,6 +26,11 @@ class QueryInfo(BaseModel):
     timestamp: datetime = Field(description="When the query was executed")
     budget: int = Field(description="Maximum nodes to explore")
     max_tokens: int = Field(description="Maximum tokens to return in results")
+    tags: list[str] | None = Field(default=None, description="Tags filter applied to recall")
+    tags_match: str | None = Field(default=None, description="Tags matching mode: any, all, any_strict, all_strict")
+    temporal_constraint: TemporalConstraint | None = Field(
+        default=None, description="Detected temporal range from query"
+    )
 
 
 class EntryPoint(BaseModel):
@@ -73,7 +85,6 @@ class NodeVisit(BaseModel):
     text: str = Field(description="Memory unit text content")
     context: str = Field(description="Memory unit context")
     event_date: datetime | None = Field(default=None, description="When the memory occurred")
-    access_count: int = Field(description="Number of times accessed before this search")
 
     # How this node was reached
     is_entry_point: bool = Field(description="Whether this is an entry point")

hindsight_api/engine/search/tracer.py

@@ -22,6 +22,7 @@ from .trace import (
     SearchPhaseMetrics,
     SearchSummary,
     SearchTrace,
+    TemporalConstraint,
     WeightComponents,
 )
 
@@ -45,7 +46,14 @@ class SearchTracer:
         json_output = trace.to_json()
     """
 
-    def __init__(self, query: str, budget: int, max_tokens: int):
+    def __init__(
+        self,
+        query: str,
+        budget: int,
+        max_tokens: int,
+        tags: list[str] | None = None,
+        tags_match: str | None = None,
+    ):
         """
         Initialize tracer.
 
@@ -53,10 +61,14 @@ class SearchTracer:
             query: Search query text
             budget: Maximum nodes to explore
             max_tokens: Maximum tokens to return in results
+            tags: Tags filter applied to recall
+            tags_match: Tags matching mode (any, all, any_strict, all_strict)
         """
         self.query_text = query
         self.budget = budget
         self.max_tokens = max_tokens
+        self.tags = tags
+        self.tags_match = tags_match
 
         # Trace data
         self.query_embedding: list[float] | None = None
@@ -66,6 +78,9 @@ class SearchTracer:
         self.pruned: list[PruningDecision] = []
         self.phase_metrics: list[SearchPhaseMetrics] = []
 
+        # Temporal constraint detected from query
+        self.temporal_constraint: TemporalConstraint | None = None
+
         # New 4-way retrieval tracking
         self.retrieval_results: list[RetrievalMethodResults] = []
         self.rrf_merged: list[RRFMergeResult] = []
@@ -88,6 +103,11 @@ class SearchTracer:
         """Record the query embedding."""
         self.query_embedding = embedding
 
+    def record_temporal_constraint(self, start: datetime | None, end: datetime | None):
+        """Record the detected temporal constraint from query analysis."""
+        if start is not None or end is not None:
+            self.temporal_constraint = TemporalConstraint(start=start, end=end)
+
     def add_entry_point(self, node_id: str, text: str, similarity: float, rank: int):
         """
         Record an entry point.
@@ -116,7 +136,6 @@ class SearchTracer:
         text: str,
         context: str,
         event_date: datetime | None,
-        access_count: int,
         is_entry_point: bool,
         parent_node_id: str | None,
         link_type: Literal["temporal", "semantic", "entity"] | None,
@@ -135,7 +154,6 @@ class SearchTracer:
             text: Memory unit text
             context: Memory unit context
             event_date: When the memory occurred
-            access_count: Access count before this search
             is_entry_point: Whether this is an entry point
             parent_node_id: Node that led here (None for entry points)
             link_type: Type of link from parent
@@ -174,7 +192,6 @@ class SearchTracer:
             text=text,
             context=context,
             event_date=event_date,
-            access_count=access_count,
             is_entry_point=is_entry_point,
             parent_node_id=parent_node_id,
             link_type=link_type,
@@ -313,8 +330,8 @@ class SearchTracer:
                 RetrievalResult(
                     rank=rank,
                     node_id=doc_id,
-                    text=data.get("text", ""),
-                    context=data.get("context", ""),
+                    text=data.get("text") or "",
+                    context=data.get("context") or "",
                     event_date=data.get("event_date"),
                     fact_type=data.get("fact_type") or fact_type,
                     score=score,
@@ -428,6 +445,9 @@ class SearchTracer:
             timestamp=datetime.now(UTC),
             budget=self.budget,
             max_tokens=self.max_tokens,
+            tags=self.tags,
+            tags_match=self.tags_match,
+            temporal_constraint=self.temporal_constraint,
         )
 
         # Create summary

hindsight_api/engine/search/types.py

@@ -10,6 +10,24 @@ from datetime import datetime
 from typing import Any
 
 
+@dataclass
+class MPFPTimings:
+    """Timing breakdown for a single MPFP retrieval call."""
+
+    fact_type: str
+    edge_count: int = 0  # Total edges loaded
+    db_queries: int = 0  # Number of DB queries for edge loading
+    edge_load_time: float = 0.0  # Time spent loading edges from DB
+    traverse: float = 0.0  # Total traversal time (includes edge loading)
+    pattern_count: int = 0  # Number of patterns executed
+    fusion: float = 0.0  # Time for RRF fusion
+    fetch: float = 0.0  # Time to fetch memory unit details
+    seeds_time: float = 0.0  # Time to find semantic seeds (if fallback used)
+    result_count: int = 0  # Number of results returned
+    # Detailed per-hop timing: list of {hop, exec_time, uncached, load_time, edges_loaded, total_time}
+    hop_details: list[dict] = field(default_factory=list)
+
+
 @dataclass
 class RetrievalResult:
     """
@@ -28,8 +46,8 @@ class RetrievalResult:
     mentioned_at: datetime | None = None
     document_id: str | None = None
     chunk_id: str | None = None
-    access_count: int = 0
     embedding: list[float] | None = None
+    tags: list[str] | None = None  # Visibility scope tags
 
     # Retrieval-specific scores (only one will be set depending on retrieval method)
     similarity: float | None = None  # Semantic retrieval
@@ -52,8 +70,8 @@ class RetrievalResult:
             mentioned_at=row.get("mentioned_at"),
             document_id=row.get("document_id"),
             chunk_id=row.get("chunk_id"),
-            access_count=row.get("access_count", 0),
             embedding=row.get("embedding"),
+            tags=row.get("tags"),
             similarity=row.get("similarity"),
             bm25_score=row.get("bm25_score"),
             activation=row.get("activation"),
@@ -136,8 +154,8 @@ class ScoredResult:
             "mentioned_at": self.retrieval.mentioned_at,
             "document_id": self.retrieval.document_id,
             "chunk_id": self.retrieval.chunk_id,
-            "access_count": self.retrieval.access_count,
             "embedding": self.retrieval.embedding,
+            "tags": self.retrieval.tags,
             "semantic_similarity": self.retrieval.similarity,
             "bm25_score": self.retrieval.bm25_score,
         }