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

hindsight_api/engine/retain/fact_storage.py

@@ -41,10 +41,10 @@ async def insert_facts_batch(
     contexts = []
     fact_types = []
     confidence_scores = []
-    access_counts = []
     metadata_jsons = []
     chunk_ids = []
     document_ids = []
+    tags_list = []
 
     for fact in facts:
         fact_texts.append(fact.fact_text)
@@ -60,21 +60,35 @@ async def insert_facts_batch(
         fact_types.append(fact.fact_type)
         # confidence_score is only for opinion facts
         confidence_scores.append(1.0 if fact.fact_type == "opinion" else None)
-        access_counts.append(0)  # Initial access count
         metadata_jsons.append(json.dumps(fact.metadata))
         chunk_ids.append(fact.chunk_id)
         # Use per-fact document_id if available, otherwise fallback to batch-level document_id
         document_ids.append(fact.document_id if fact.document_id else document_id)
+        # Convert tags to JSON string for proper batch insertion (PostgreSQL unnest doesn't handle 2D arrays well)
+        tags_list.append(json.dumps(fact.tags if fact.tags else []))
 
     # Batch insert all facts
+    # Note: tags are passed as JSON strings and converted back to varchar[] via jsonb_array_elements_text + array_agg
     results = await conn.fetch(
         f"""
-        INSERT INTO {fq_table("memory_units")} (bank_id, text, embedding, event_date, occurred_start, occurred_end, mentioned_at,
-                                 context, fact_type, confidence_score, access_count, metadata, chunk_id, document_id)
-        SELECT $1, * FROM unnest(
-            $2::text[], $3::vector[], $4::timestamptz[], $5::timestamptz[], $6::timestamptz[], $7::timestamptz[],
-            $8::text[], $9::text[], $10::float[], $11::int[], $12::jsonb[], $13::text[], $14::text[]
+        WITH input_data AS (
+            SELECT * FROM unnest(
+                $2::text[], $3::vector[], $4::timestamptz[], $5::timestamptz[], $6::timestamptz[], $7::timestamptz[],
+                $8::text[], $9::text[], $10::float[], $11::jsonb[], $12::text[], $13::text[], $14::jsonb[]
+            ) AS t(text, embedding, event_date, occurred_start, occurred_end, mentioned_at,
+                   context, fact_type, confidence_score, metadata, chunk_id, document_id, tags_json)
         )
+        INSERT INTO {fq_table("memory_units")} (bank_id, text, embedding, event_date, occurred_start, occurred_end, mentioned_at,
+                                 context, fact_type, confidence_score, metadata, chunk_id, document_id, tags)
+        SELECT
+            $1,
+            text, embedding, event_date, occurred_start, occurred_end, mentioned_at,
+            context, fact_type, confidence_score, metadata, chunk_id, document_id,
+            COALESCE(
+                (SELECT array_agg(elem) FROM jsonb_array_elements_text(tags_json) AS elem),
+                '{{}}'::varchar[]
+            )
+        FROM input_data
         RETURNING id
         """,
         bank_id,
@@ -87,10 +101,10 @@ async def insert_facts_batch(
         contexts,
         fact_types,
         confidence_scores,
-        access_counts,
         metadata_jsons,
         chunk_ids,
         document_ids,
+        tags_list,
     )
 
     unit_ids = [str(row["id"]) for row in results]
@@ -109,7 +123,7 @@ async def ensure_bank_exists(conn, bank_id: str) -> None:
     """
     await conn.execute(
         f"""
-        INSERT INTO {fq_table("banks")} (bank_id, disposition, background)
+        INSERT INTO {fq_table("banks")} (bank_id, disposition, mission)
         VALUES ($1, $2::jsonb, $3)
         ON CONFLICT (bank_id) DO UPDATE
         SET updated_at = NOW()
@@ -121,7 +135,13 @@ async def ensure_bank_exists(conn, bank_id: str) -> None:
 
 
 async def handle_document_tracking(
-    conn, bank_id: str, document_id: str, combined_content: str, is_first_batch: bool, retain_params: dict | None = None
+    conn,
+    bank_id: str,
+    document_id: str,
+    combined_content: str,
+    is_first_batch: bool,
+    retain_params: dict | None = None,
+    document_tags: list[str] | None = None,
 ) -> None:
     """
     Handle document tracking in the database.
@@ -133,6 +153,7 @@ async def handle_document_tracking(
         combined_content: Combined content text from all content items
         is_first_batch: Whether this is the first batch (for chunked operations)
         retain_params: Optional parameters passed during retain (context, event_date, etc.)
+        document_tags: Optional list of tags to associate with the document
     """
     import hashlib
 
@@ -149,13 +170,14 @@ async def handle_document_tracking(
     # Insert document (or update if exists from concurrent operations)
     await conn.execute(
         f"""
-        INSERT INTO {fq_table("documents")} (id, bank_id, original_text, content_hash, metadata, retain_params)
-        VALUES ($1, $2, $3, $4, $5, $6)
+        INSERT INTO {fq_table("documents")} (id, bank_id, original_text, content_hash, metadata, retain_params, tags)
+        VALUES ($1, $2, $3, $4, $5, $6, $7)
         ON CONFLICT (id, bank_id) DO UPDATE
         SET original_text = EXCLUDED.original_text,
             content_hash = EXCLUDED.content_hash,
             metadata = EXCLUDED.metadata,
             retain_params = EXCLUDED.retain_params,
+            tags = EXCLUDED.tags,
             updated_at = NOW()
         """,
         document_id,
@@ -164,4 +186,5 @@ async def handle_document_tracking(
         content_hash,
         json.dumps({}),  # Empty metadata dict
         json.dumps(retain_params) if retain_params else None,
+        document_tags or [],
     )

hindsight_api/engine/retain/link_utils.py

@@ -479,14 +479,18 @@ async def create_temporal_links_batch_per_fact(
 
         if links:
             insert_start = time_mod.time()
-            await conn.executemany(
-                f"""
-                INSERT INTO {fq_table("memory_links")} (from_unit_id, to_unit_id, link_type, weight, entity_id)
-                VALUES ($1, $2, $3, $4, $5)
-                ON CONFLICT (from_unit_id, to_unit_id, link_type, COALESCE(entity_id, '00000000-0000-0000-0000-000000000000'::uuid)) DO NOTHING
-                """,
-                links,
-            )
+            # Batch inserts to avoid timeout on large batches
+            BATCH_SIZE = 1000
+            for batch_start in range(0, len(links), BATCH_SIZE):
+                batch = links[batch_start : batch_start + BATCH_SIZE]
+                await conn.executemany(
+                    f"""
+                    INSERT INTO {fq_table("memory_links")} (from_unit_id, to_unit_id, link_type, weight, entity_id)
+                    VALUES ($1, $2, $3, $4, $5)
+                    ON CONFLICT (from_unit_id, to_unit_id, link_type, COALESCE(entity_id, '00000000-0000-0000-0000-000000000000'::uuid)) DO NOTHING
+                    """,
+                    batch,
+                )
             _log(log_buffer, f"      [7.4] Insert {len(links)} temporal links: {time_mod.time() - insert_start:.3f}s")
 
         return len(links)
@@ -644,14 +648,18 @@ async def create_semantic_links_batch(
 
         if all_links:
             insert_start = time_mod.time()
-            await conn.executemany(
-                f"""
-                INSERT INTO {fq_table("memory_links")} (from_unit_id, to_unit_id, link_type, weight, entity_id)
-                VALUES ($1, $2, $3, $4, $5)
-                ON CONFLICT (from_unit_id, to_unit_id, link_type, COALESCE(entity_id, '00000000-0000-0000-0000-000000000000'::uuid)) DO NOTHING
-                """,
-                all_links,
-            )
+            # Batch inserts to avoid timeout on large batches
+            BATCH_SIZE = 1000
+            for batch_start in range(0, len(all_links), BATCH_SIZE):
+                batch = all_links[batch_start : batch_start + BATCH_SIZE]
+                await conn.executemany(
+                    f"""
+                    INSERT INTO {fq_table("memory_links")} (from_unit_id, to_unit_id, link_type, weight, entity_id)
+                    VALUES ($1, $2, $3, $4, $5)
+                    ON CONFLICT (from_unit_id, to_unit_id, link_type, COALESCE(entity_id, '00000000-0000-0000-0000-000000000000'::uuid)) DO NOTHING
+                    """,
+                    batch,
+                )
             _log(
                 log_buffer, f"      [8.3] Insert {len(all_links)} semantic links: {time_mod.time() - insert_start:.3f}s"
             )
@@ -746,17 +754,14 @@ async def create_causal_links_batch(
         causal_relations_per_fact: List of causal relations for each fact.
             Each element is a list of dicts with:
             - target_fact_index: Index into unit_ids for the target fact
-            - relation_type: "causes", "caused_by", "enables", or "prevents"
+            - relation_type: "caused_by"
             - strength: Float in [0.0, 1.0] representing relationship strength
 
     Returns:
         Number of causal links created
 
-    Causal link types:
-    - "causes": This fact directly causes the target fact (forward causation)
-    - "caused_by": This fact was caused by the target fact (backward causation)
-    - "enables": This fact enables/allows the target fact (enablement)
-    - "prevents": This fact prevents/blocks the target fact (prevention)
+    Causal link type:
+    - "caused_by": This fact was caused by the target fact
     """
     if not unit_ids or not causal_relations_per_fact:
         return 0
@@ -779,8 +784,8 @@ async def create_causal_links_batch(
                 relation_type = relation["relation_type"]
                 strength = relation.get("strength", 1.0)
 
-                # Validate relation_type - must match database constraint
-                valid_types = {"causes", "caused_by", "enables", "prevents"}
+                # Validate relation_type - only "caused_by" is supported (DB constraint)
+                valid_types = {"caused_by"}
                 if relation_type not in valid_types:
                     logger.error(
                         f"Invalid relation_type '{relation_type}' (type: {type(relation_type).__name__}) "

hindsight_api/engine/retain/orchestrator.py

@@ -18,6 +18,7 @@ def utcnow():
     return datetime.now(UTC)
 
 
+from ..response_models import TokenUsage
 from . import (
     chunk_storage,
     deduplication,
@@ -26,9 +27,8 @@ from . import (
     fact_extraction,
     fact_storage,
     link_creation,
-    observation_regeneration,
 )
-from .types import ExtractedFact, ProcessedFact, RetainContent, RetainContentDict
+from .types import EntityLink, ExtractedFact, ProcessedFact, RetainContent, RetainContentDict
 
 logger = logging.getLogger(__name__)
 
@@ -38,7 +38,6 @@ async def retain_batch(
     embeddings_model,
     llm_config,
     entity_resolver,
-    task_backend,
     format_date_fn,
     duplicate_checker_fn,
     bank_id: str,
@@ -47,7 +46,8 @@ async def retain_batch(
     is_first_batch: bool = True,
     fact_type_override: str | None = None,
     confidence_score: float | None = None,
-) -> list[list[str]]:
+    document_tags: list[str] | None = None,
+) -> tuple[list[list[str]], TokenUsage]:
     """
     Process a batch of content through the retain pipeline.
 
@@ -56,7 +56,6 @@ 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
@@ -65,9 +64,10 @@ async def retain_batch(
         is_first_batch: Whether this is the first batch
         fact_type_override: Override fact type for all facts
         confidence_score: Confidence score for opinions
+        document_tags: Tags applied to all items in this batch
 
     Returns:
-        List of unit ID lists (one list per content item)
+        Tuple of (unit ID lists, token usage for fact extraction)
     """
     start_time = time.time()
     total_chars = sum(len(item.get("content", "")) for item in contents_dicts)
@@ -86,12 +86,16 @@ async def retain_batch(
     # Convert dicts to RetainContent objects
     contents = []
     for item in contents_dicts:
+        # Merge item-level tags with document-level tags
+        item_tags = item.get("tags", []) or []
+        merged_tags = list(set(item_tags + (document_tags or [])))
         content = RetainContent(
             content=item["content"],
             context=item.get("context", ""),
             event_date=item.get("event_date") or utcnow(),
             metadata=item.get("metadata", {}),
             entities=item.get("entities", []),
+            tags=merged_tags,
         )
         contents.append(content)
 
@@ -99,7 +103,7 @@ async def retain_batch(
     step_start = time.time()
     extract_opinions = fact_type_override == "opinion"
 
-    extracted_facts, chunks = await fact_extraction.extract_facts_from_contents(
+    extracted_facts, chunks, usage = await fact_extraction.extract_facts_from_contents(
         contents, llm_config, agent_name, extract_opinions
     )
     log_buffer.append(
@@ -129,7 +133,7 @@ async def retain_batch(
                         if first_item.get("metadata"):
                             retain_params["metadata"] = first_item["metadata"]
                     await fact_storage.handle_document_tracking(
-                        conn, bank_id, document_id, combined_content, is_first_batch, retain_params
+                        conn, bank_id, document_id, combined_content, is_first_batch, retain_params, document_tags
                     )
                 else:
                     # Check for per-item document_ids
@@ -157,14 +161,14 @@ async def retain_batch(
                             if first_item.get("metadata"):
                                 retain_params["metadata"] = first_item["metadata"]
                         await fact_storage.handle_document_tracking(
-                            conn, bank_id, doc_id, combined_content, is_first_batch, retain_params
+                            conn, bank_id, doc_id, combined_content, is_first_batch, retain_params, document_tags
                         )
 
         total_time = time.time() - start_time
         logger.info(
             f"RETAIN_BATCH COMPLETE: 0 facts extracted from {len(contents)} contents in {total_time:.3f}s (document tracked, no facts)"
         )
-        return [[] for _ in contents]
+        return [[] for _ in contents], usage
 
     # Apply fact_type_override if provided
     if fact_type_override:
@@ -223,7 +227,7 @@ async def retain_batch(
                         retain_params["metadata"] = first_item["metadata"]
 
                 await fact_storage.handle_document_tracking(
-                    conn, bank_id, document_id, combined_content, is_first_batch, retain_params
+                    conn, bank_id, document_id, combined_content, is_first_batch, retain_params, document_tags
                 )
                 document_ids_added.append(document_id)
                 doc_id_mapping[None] = document_id  # For backwards compatibility
@@ -267,7 +271,13 @@ async def retain_batch(
                                     retain_params["metadata"] = first_item["metadata"]
 
                             await fact_storage.handle_document_tracking(
-                                conn, bank_id, actual_doc_id, combined_content, is_first_batch, retain_params
+                                conn,
+                                bank_id,
+                                actual_doc_id,
+                                combined_content,
+                                is_first_batch,
+                                retain_params,
+                                document_tags,
                             )
                             document_ids_added.append(actual_doc_id)
 
@@ -344,7 +354,7 @@ async def retain_batch(
             non_duplicate_facts = deduplication.filter_duplicates(processed_facts, is_duplicate_flags)
 
             if not non_duplicate_facts:
-                return [[] for _ in contents]
+                return [[] for _ in contents], usage
 
             # Insert facts (document_id is now stored per-fact)
             step_start = time.time()
@@ -394,17 +404,9 @@ 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 INSIDE transaction for atomicity
-            await observation_regeneration.regenerate_observations_batch(
-                conn, embeddings_model, llm_config, bank_id, entity_links, log_buffer
-            )
-
             # 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 (opinion reinforcement only)
-        await _trigger_background_tasks(task_backend, bank_id, unit_ids, non_duplicate_facts)
-
         # Log final summary
         total_time = time.time() - start_time
         log_buffer.append(f"{'=' * 60}")
@@ -415,7 +417,7 @@ async def retain_batch(
 
         logger.info("\n" + "\n".join(log_buffer) + "\n")
 
-        return result_unit_ids
+        return result_unit_ids, usage
 
 
 def _map_results_to_contents(
@@ -446,24 +448,3 @@ 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],
-) -> None:
-    """Trigger opinion reinforcement as background task (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,
-            }
-        )

hindsight_api/engine/retain/types.py

@@ -21,6 +21,7 @@ class RetainContentDict(TypedDict, total=False):
         metadata: Custom key-value metadata (optional)
         document_id: Document ID for this content item (optional)
         entities: User-provided entities to merge with extracted entities (optional)
+        tags: Visibility scope tags for this content item (optional)
     """
 
     content: str  # Required
@@ -29,6 +30,7 @@ class RetainContentDict(TypedDict, total=False):
     metadata: dict[str, str]
     document_id: str
     entities: list[dict[str, str]]  # [{"text": "...", "type": "..."}]
+    tags: list[str]  # Visibility scope tags
 
 
 def _now_utc() -> datetime:
@@ -49,6 +51,7 @@ class RetainContent:
     event_date: datetime = field(default_factory=_now_utc)
     metadata: dict[str, str] = field(default_factory=dict)
     entities: list[dict[str, str]] = field(default_factory=list)  # User-provided entities
+    tags: list[str] = field(default_factory=list)  # Visibility scope tags
 
 
 @dataclass
@@ -83,10 +86,10 @@ class CausalRelation:
     """
     Causal relationship between facts.
 
-    Represents how one fact causes, enables, or prevents another.
+    Represents how one fact was caused by another.
     """
 
-    relation_type: str  # "causes", "enables", "prevents", "caused_by"
+    relation_type: str  # "caused_by"
     target_fact_index: int  # Index of the target fact in the batch
     strength: float = 1.0  # Strength of the causal relationship
 
@@ -113,6 +116,7 @@ class ExtractedFact:
     context: str = ""
     mentioned_at: datetime | None = None
     metadata: dict[str, str] = field(default_factory=dict)
+    tags: list[str] = field(default_factory=list)  # Visibility scope tags
 
 
 @dataclass
@@ -158,6 +162,9 @@ class ProcessedFact:
     # Track which content this fact came from (for user entity merging)
     content_index: int = 0
 
+    # Visibility scope tags
+    tags: list[str] = field(default_factory=list)
+
     @property
     def is_duplicate(self) -> bool:
         """Check if this fact was marked as a duplicate."""
@@ -201,6 +208,7 @@ class ProcessedFact:
             causal_relations=extracted_fact.causal_relations,
             chunk_id=chunk_id,
             content_index=extracted_fact.content_index,
+            tags=extracted_fact.tags,
         )
 
 
@@ -232,6 +240,7 @@ class RetainBatch:
     document_id: str | None = None
     fact_type_override: str | None = None
     confidence_score: float | None = None
+    document_tags: list[str] = field(default_factory=list)  # Tags applied to all items
 
     # Extracted data (populated during processing)
     extracted_facts: list[ExtractedFact] = field(default_factory=list)

hindsight_api/engine/search/graph_retrieval.py

@@ -11,7 +11,8 @@ from abc import ABC, abstractmethod
 
 from ..db_utils import acquire_with_retry
 from ..memory_engine import fq_table
-from .types import RetrievalResult
+from .tags import TagsMatch, filter_results_by_tags
+from .types import MPFPTimings, RetrievalResult
 
 logger = logging.getLogger(__name__)
 
@@ -42,7 +43,10 @@ class GraphRetriever(ABC):
         query_text: str | None = None,
         semantic_seeds: list[RetrievalResult] | None = None,
         temporal_seeds: list[RetrievalResult] | None = None,
-    ) -> list[RetrievalResult]:
+        adjacency=None,  # TypedAdjacency, optional pre-loaded graph
+        tags: list[str] | None = None,  # Visibility scope tags for filtering
+        tags_match: TagsMatch = "any",  # How to match tags: 'any' (OR) or 'all' (AND)
+    ) -> tuple[list[RetrievalResult], MPFPTimings | None]:
         """
         Retrieve relevant facts via graph traversal.
 
@@ -55,9 +59,11 @@ class GraphRetriever(ABC):
             query_text: Original query text (optional, for some strategies)
             semantic_seeds: Pre-computed semantic entry points (from semantic retrieval)
             temporal_seeds: Pre-computed temporal entry points (from temporal retrieval)
+            adjacency: Pre-loaded typed adjacency graph (optional, for MPFP)
+            tags: Optional list of tags for visibility filtering (OR matching)
 
         Returns:
-            List of RetrievalResult objects with activation scores set
+            Tuple of (List of RetrievalResult with activation scores, optional timing info)
         """
         pass
 
@@ -111,7 +117,10 @@ class BFSGraphRetriever(GraphRetriever):
         query_text: str | None = None,
         semantic_seeds: list[RetrievalResult] | None = None,
         temporal_seeds: list[RetrievalResult] | None = None,
-    ) -> list[RetrievalResult]:
+        adjacency=None,  # Not used by BFS
+        tags: list[str] | None = None,
+        tags_match: TagsMatch = "any",
+    ) -> tuple[list[RetrievalResult], MPFPTimings | None]:
         """
         Retrieve facts using BFS spreading activation.
 
@@ -122,11 +131,14 @@ class BFSGraphRetriever(GraphRetriever):
         4. Return visited nodes up to budget
 
         Note: BFS finds its own entry points via embedding search.
-        The semantic_seeds and temporal_seeds parameters are accepted
+        The semantic_seeds, temporal_seeds, and adjacency parameters are accepted
         for interface compatibility but not used.
         """
         async with acquire_with_retry(pool) as conn:
-            return await self._retrieve_with_conn(conn, query_embedding_str, bank_id, fact_type, budget)
+            results = await self._retrieve_with_conn(
+                conn, query_embedding_str, bank_id, fact_type, budget, tags=tags, tags_match=tags_match
+            )
+            return results, None
 
     async def _retrieve_with_conn(
         self,
@@ -135,33 +147,46 @@ class BFSGraphRetriever(GraphRetriever):
         bank_id: str,
         fact_type: str,
         budget: int,
+        tags: list[str] | None = None,
+        tags_match: TagsMatch = "any",
     ) -> list[RetrievalResult]:
         """Internal implementation with connection."""
+        from .tags import build_tags_where_clause_simple
+
+        tags_clause = build_tags_where_clause_simple(tags, 6, match=tags_match)
+        params = [query_embedding_str, bank_id, fact_type, self.entry_point_threshold, self.entry_point_limit]
+        if tags:
+            params.append(tags)
 
         # Step 1: Find entry points
         entry_points = await conn.fetch(
             f"""
             SELECT id, text, context, event_date, occurred_start, occurred_end,
-                   mentioned_at, access_count, embedding, fact_type, document_id, chunk_id,
+                   mentioned_at, embedding, fact_type, document_id, chunk_id, tags,
                    1 - (embedding <=> $1::vector) AS similarity
             FROM {fq_table("memory_units")}
             WHERE bank_id = $2
               AND embedding IS NOT NULL
               AND fact_type = $3
               AND (1 - (embedding <=> $1::vector)) >= $4
+              {tags_clause}
             ORDER BY embedding <=> $1::vector
             LIMIT $5
             """,
-            query_embedding_str,
-            bank_id,
-            fact_type,
-            self.entry_point_threshold,
-            self.entry_point_limit,
+            *params,
         )
 
         if not entry_points:
+            logger.debug(
+                f"[BFS] No entry points found for fact_type={fact_type} (tags={tags}, tags_match={tags_match})"
+            )
             return []
 
+        logger.debug(
+            f"[BFS] Found {len(entry_points)} entry points for fact_type={fact_type} "
+            f"(tags={tags}, tags_match={tags_match})"
+        )
+
         # Step 2: BFS spreading activation
         visited = set()
         results = []
@@ -191,8 +216,8 @@ class BFSGraphRetriever(GraphRetriever):
                 neighbors = await conn.fetch(
                     f"""
                     SELECT mu.id, mu.text, mu.context, mu.occurred_start, mu.occurred_end,
-                           mu.mentioned_at, mu.access_count, mu.embedding, mu.fact_type,
-                           mu.document_id, mu.chunk_id,
+                           mu.mentioned_at, mu.embedding, mu.fact_type,
+                           mu.document_id, mu.chunk_id, mu.tags,
                            ml.weight, ml.link_type, ml.from_unit_id
                     FROM {fq_table("memory_links")} ml
                     JOIN {fq_table("memory_units")} mu ON ml.to_unit_id = mu.id
@@ -232,4 +257,8 @@ class BFSGraphRetriever(GraphRetriever):
                             neighbor_result = RetrievalResult.from_db_row(dict(n))
                             queue.append((neighbor_result, new_activation))
 
+        # Apply tags filtering (BFS may traverse into memories that don't match tags criteria)
+        if tags:
+            results = filter_results_by_tags(results, tags, match=tags_match)
+
         return results