diff --git a/offline-backend-20260512/backend/packages/harness/deerflow/knowledge/llm_extractor.py b/offline-backend-20260512/backend/packages/harness/deerflow/knowledge/llm_extractor.py
index fb7bbb63..5c86f697 100644
--- a/offline-backend-20260512/backend/packages/harness/deerflow/knowledge/llm_extractor.py
+++ b/offline-backend-20260512/backend/packages/harness/deerflow/knowledge/llm_extractor.py
@@ -265,11 +265,11 @@ async def extract_thread_llm_multi(
         raw = response.content if isinstance(response.content, str) else str(response.content)
         data = _parse_json(raw)
     except Exception:
-        logger.exception("Knowledge LLM extraction failed for thread %s; using rule-based fallback", thread_id)
+        logger.exception("[knowledge] thread %s — LLM extraction call failed; using rule-based fallback", thread_id)
         return []
 
     if not data:
-        logger.warning("Knowledge LLM extraction for thread %s returned no parsable JSON; using rule-based fallback", thread_id)
+        logger.warning("[knowledge] thread %s — LLM returned no parsable JSON; using rule-based fallback", thread_id)
         return []
 
     note_dicts = _notes_from_data(data)
@@ -279,10 +279,10 @@ async def extract_thread_llm_multi(
             # The model deliberately judged this conversation worthless (greeting,
             # meta chatter, no findings). Skip ingestion entirely — do NOT fall
             # back to the rule-based verbatim dump.
-            logger.info("Knowledge LLM judged thread %s not worth ingesting: %s", thread_id, reason)
+            logger.warning("[knowledge] thread %s SKIPPED — model judged not worth ingesting: %s", thread_id, reason)
             raise LLMRejectedIngest(reason or "no knowledge value")
         logger.warning(
-            "Knowledge LLM extraction for thread %s produced no notes (should_ingest=%s, reason=%r); using rule-based fallback",
+            "[knowledge] thread %s — LLM produced no notes (should_ingest=%s, reason=%r); using rule-based fallback",
             thread_id,
             data.get("should_ingest"),
             reason,
diff --git a/offline-backend-20260512/backend/packages/harness/deerflow/knowledge/service.py b/offline-backend-20260512/backend/packages/harness/deerflow/knowledge/service.py
index ec2453fb..78351be6 100644
--- a/offline-backend-20260512/backend/packages/harness/deerflow/knowledge/service.py
+++ b/offline-backend-20260512/backend/packages/harness/deerflow/knowledge/service.py
@@ -296,9 +296,9 @@ class KnowledgeService:
         effective_status = status
         if llm_fallback:
             logger.warning(
-                "Knowledge capture for thread %s fell back to rule-based extraction "
-                "(LLM distillation produced nothing usable); landing as draft. "
-                "Check extraction model '%s' / earlier logs for the cause.",
+                "[knowledge] thread %s — capture fell back to rule-based extraction "
+                "(LLM distillation produced nothing usable); landing as DRAFT. "
+                "Check extraction model '%s' / earlier [knowledge] logs for the cause.",
                 thread_id,
                 self.config.extract_model_name or "models[0]",
             )