hy-memory 2.0.7__tar.gz → 2.0.8__tar.gz

{hy_memory-2.0.7/hy_memory.egg-info → hy_memory-2.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hy-memory
-Version: 2.0.7
+Version: 2.0.8
 Summary: HY Memory - Industrial-grade dual-system cognitive memory framework
 Author: alvinfei
 License-Expression: Apache-2.0

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/agent/extractor.py

@@ -1177,7 +1177,7 @@ class Extractor:
                         if not tc_id:
                             logger.error(
                                 f"[extractor] tool_call_id is empty! "
-                                f"raw tc: {json.dumps(tc_raw, ensure_ascii=False, default=str)[:500]}"
+                                f"raw_keys={list(tc_raw.keys())}"
                             )
                         try:
                             t_res = await tool_registry.dispatch(
@@ -1311,11 +1311,12 @@ class Extractor:
                 if parsed is None:
                     if not all_tool_calls:
                         logger.warning(
-                            f"[extractor] JSON parse failed: {raw_text[:200]}"
+                            f"[extractor] JSON parse failed ({len(raw_text)} chars)"
                         )
+                        logger.debug(f"[extractor] unparsable output: {raw_text[:200]!r}")
                         return ExtractResult(
                             success=False,
-                            error=f"JSON parse failed: {raw_text[:200]}",
+                            error=f"JSON parse failed ({len(raw_text)} chars)",
                             error_code="JSON_PARSE_FAILED",
                             raw_response=raw_text,
                             tokens_used=total_tokens,

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/agent/llm_provider.py

@@ -129,8 +129,7 @@ def _parse_tool_calls_list(raw_calls: list, _json) -> List[Dict[str, Any]]:
         tc_id = tc.get("id") or ""
         if not tc_id:
             logger.error(
-                f"[llm] tool_call missing 'id'! raw: "
-                f"{_json.dumps(tc, ensure_ascii=False, default=str)[:500]}"
+                f"[llm] tool_call missing 'id'! keys={list(tc.keys())}"
             )
 
         # 保留原始 tc 完整结构，只规范化 arguments

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/agent/mem_agent.py

@@ -234,7 +234,7 @@ class MemAgent:
                     f"identity={len(identity)} facts={len(facts)} "
                     f"basic_info={basic_field_count}fields"
                 )
-                logger.info(f"MemAgent: extracted_info={extract_result.info}")
+                logger.debug(f"MemAgent: extracted_info={extract_result.info}")
 
             # 3. 冲突检测（如果有已有记忆）
             if mode == ProcessMode.FULL and existing_memories:

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/agent/reconciler.py

@@ -50,7 +50,7 @@ def is_canonical_state_node(node: Any) -> bool:
 
 
 def _log_ops_detail(ops: List["ReconcileOp"]) -> None:
-    """以单条 INFO（JSON list）输出 reconcile 的逐条结果，便于线上 debug。"""
+    """以单条 DEBUG（JSON list）输出 reconcile 的逐条结果；含记忆正文，不进 INFO。"""
     if not ops:
         return
     view = [
@@ -68,7 +68,7 @@ def _log_ops_detail(ops: List["ReconcileOp"]) -> None:
         }
         for o in ops
     ]
-    logger.info(
+    logger.debug(
         f"[reconciler] ops detail: {json.dumps(view, ensure_ascii=False, default=str)}"
     )
 
@@ -1514,9 +1514,10 @@ class MemoryReconciler:
                 logger.warning(
                     f"[reconciler] RECONCILE JSON parse failed "
                     f"(attempt {_attempt+1}/{_MAX_PARSE_ATTEMPTS}), "
-                    f"retrying: raw="
-                    f"{raw_response[:200] if _log_llm_content_enabled() else '<redacted>'}"
+                    f"retrying: raw({len(raw_response or '')} chars)"
                 )
+                if _log_llm_content_enabled():
+                    logger.debug(f"[reconciler] unparsable raw={raw_response[:200]!r}")
 
             recon_elapsed = (_time.perf_counter() - t_recon) * 1000
 
@@ -1528,8 +1529,8 @@ class MemoryReconciler:
                     error_code = "LLM_UNAVAILABLE"
                 elif raw_response.strip():
                     error_msg = (
-                        f"RECONCILE JSON parse failed after {_n_attempts} attempts: "
-                        f"{raw_response[:200] if _log_llm_content_enabled() else '<redacted>'}"
+                        f"RECONCILE JSON parse failed after {_n_attempts} attempts "
+                        f"({len(raw_response)} chars)"
                     )
                     error_code = "JSON_PARSE_FAILED"
                 else:
@@ -1806,7 +1807,8 @@ class MemoryReconciler:
                 except Exception as _re:
                     logger.debug(f"[reconciler] json_repair failed: {_re}")
             if data is None:
-                logger.warning(f"[reconciler] failed to parse ops JSON: {text[:200]}")
+                logger.warning(f"[reconciler] failed to parse ops JSON ({len(text)} chars)")
+                logger.debug(f"[reconciler] unparsable ops output: {text[:200]!r}")
                 return []
 
         if not isinstance(data, list):
@@ -2018,11 +2020,11 @@ class MemoryReconciler:
                 if clash is not None:
                     logger.warning(
                         f"[reconciler] memory_id {clash} already touched by '{touched[clash]}', "
-                        f"current op '{op.op} ({op.reason[:60]})' dropped"
+                        f"current op '{op.op}' dropped"
                     )
                     continue
                 for t in target_ids:
-                    touched[t] = f"{op.op}({op.reason[:40]})"
+                    touched[t] = op.op
             validated.append(op)
 
         return validated

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/agent/tools/base.py

@@ -211,7 +211,9 @@ def parse_tool_calls_from_json(raw: Any) -> List[ToolCall]:
                 try:
                     args = json.loads(args_raw) if args_raw.strip() else {}
                 except json.JSONDecodeError:
-                    logger.warning(f"[tools] failed to parse arguments as JSON: {args_raw[:120]}")
+                    logger.warning(
+                        f"[tools] failed to parse arguments as JSON ({len(args_raw)} chars)"
+                    )
                     args = {}
             elif isinstance(args_raw, dict):
                 args = args_raw

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/client.py

@@ -744,7 +744,7 @@ class HyMemoryClient:
     def _install_pipeline_observability_hooks(self) -> None:
         """
         包装 cache.store_pipeline_log：
-        - Log：JSONL 文件，始终写入（环节级，不依赖 Trace 开关）
+        - Log：JSONL 文件，由 MEMORY_PIPELINE_LOG_ENABLED 控制（默认开启）
         - Trace：SQLite pipeline_logs，由 MEMORY_PIPELINE_TRACE_ENABLED 控制（Inspector）
         - 落盘 fire-and-forget，不阻塞 search/write 热路径
         """
@@ -958,7 +958,7 @@ class HyMemoryClient:
                 parsed_tool_calls = json.loads(raw_tool_calls) if raw_tool_calls else []
             except Exception:
                 logger.warning(
-                    "tool_calls 是非法 JSON 字符串，已忽略: %r", raw_tool_calls[:200]
+                    "tool_calls 是非法 JSON 字符串，已忽略 (%d chars)", len(raw_tool_calls)
                 )
                 parsed_tool_calls = []
             raw_tool_calls = parsed_tool_calls if isinstance(parsed_tool_calls, list) else []
@@ -3008,13 +3008,13 @@ class HyMemoryClient:
                 f"[add] writing {preview} user={uid} "
                 f"agent_id={agent_id} session_id={session_id} mode={self._mode}"
             )
-            logger.info(f"[add] messages detail: {[m.to_dict() for m in chat_messages]}")
+            logger.debug(f"[add] messages detail: {[m.to_dict() for m in chat_messages]}")
         else:
             logger.info(
                 f"[add] writing text({len(content)} chars) user={uid} "
-                f"agent_id={agent_id} session_id={session_id} mode={self._mode} "
-                f"content={content}"
+                f"agent_id={agent_id} session_id={session_id} mode={self._mode}"
             )
+            logger.debug(f"[add] text content={content!r}")
 
         # mode → agent_mode 映射
         # lite: 不调 LLM agent
@@ -4034,14 +4034,14 @@ class HyMemoryClient:
             decided_variant = HyMemoryClient._scene_variant(scene)
             logger.info(
                 f"[search] scene explicit={decided_scene} (no LLM judge); "
-                f"target={effective_target_query!r}"
+                f"target({len(effective_target_query or '')} chars)"
             )
         elif not agentic_enabled and not queries_supplied:
             # 默认 light search 仅指 query="..."：固定 normal，绝不调用 LLM。
             decided_scene = "normal"
             logger.info(
                 f"[search] search_mode=default single-query scene=normal (no LLM); "
-                f"target={target_query!r}"
+                f"target({len(target_query or '')} chars)"
             )
         elif agentic_enabled:
             # agentic：单/多 query 都强制一次 LLM 完成三分类 + rewrite + 时间解析。
@@ -4076,14 +4076,18 @@ class HyMemoryClient:
                 rewrite_created_after = ar.get("created_after")
                 logger.info(
                     f"[search] agentic scene={decided_scene} via rewrite-LLM "
-                    f"(classify={want_classify}); orig={target_query!r} "
-                    f"effective={effective_target_query!r} rewrite_used={rewrite_used} "
+                    f"(classify={want_classify}); rewrite_used={rewrite_used} "
                     f"created_after={rewrite_created_after}"
                 )
+                logger.debug(
+                    f"[search] agentic rewrite: orig={target_query!r} "
+                    f"effective={effective_target_query!r}"
+                )
             else:
                 decided_scene = "normal"
                 logger.info(
-                    f"[search] agentic rewrite-LLM fallback=normal; target={target_query!r}"
+                    f"[search] agentic rewrite-LLM fallback=normal; "
+                    f"target({len(target_query or '')} chars)"
                 )
         elif rewrite_enabled and not _too_long:
             # default + queries= 的原逻辑：配置开启时一次 LLM 做 rewrite/time，
@@ -4162,7 +4166,7 @@ class HyMemoryClient:
             decided_scene = "normal"
             logger.info(
                 f"[search] default multi-query features disabled; no LLM; "
-                f"target={target_query!r}"
+                f"target({len(target_query or '')} chars)"
             )
 
         # ────────────────────────────────────────────────────────────
@@ -4215,7 +4219,7 @@ class HyMemoryClient:
             else:
                 logger.info(
                     f"[search] routing to PRODUCTIVITY path variant={decided_variant}: "
-                    f"target={effective_target_query!r} "
+                    f"target({len(effective_target_query or '')} chars) "
                     f"workspace_id={workspace_id!r} branch={branch!r}"
                 )
                 return await self._search_coding(
@@ -4243,9 +4247,11 @@ class HyMemoryClient:
         # Chat 召回链路（原有逻辑）
         # ────────────────────────────────────────────────────────────
         logger.info(
-            f"[search] query='{effective_target_query}' user_ids={effective_user_ids} "
+            f"[search] query({len(effective_target_query or '')} chars) "
+            f"user_ids={effective_user_ids} "
             f"agent_ids={effective_agent_ids} session_ids={effective_session_ids} limit={limit}"
         )
+        logger.debug(f"[search] query={effective_target_query!r}")
 
         # rewrite 抽出的时间下界与用户显式 created_after 取更晚者（更严格）
         effective_created_after = created_after

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/coding/extractor.py

@@ -1166,7 +1166,10 @@ class CodingMemoryExtractor:
                     obj = None
 
         if not isinstance(obj, dict):
-            logger.warning(f"[coding-extract] failed to parse output: {text!r}")
+            logger.warning(
+                f"[coding-extract] failed to parse output ({len(text or '')} chars)"
+            )
+            logger.debug(f"[coding-extract] unparsable output: {text!r}")
             return [], []
 
         # "memories" 是双层化之前的 key，老 prompt 缓存 / 旧模型可能还这么回

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/coding/fact_reconciler.py

@@ -570,9 +570,12 @@ class WorkingFactReconciler:
                     kept.append(fact)
             if blocked:
                 logger.info(
-                    f"[fact-reconcile] subject gate blocked {len(blocked)} candidate(s) "
-                    f"for subject={draft.subject!r}: "
-                    + ", ".join(f"{f.fact_id}({f.subject!r})" for f in blocked)
+                    f"[fact-reconcile] subject gate blocked {len(blocked)} candidate(s): "
+                    + ", ".join(f.fact_id for f in blocked)
+                )
+                logger.debug(
+                    f"[fact-reconcile] subject gate: draft subject={draft.subject!r} "
+                    f"blocked subjects={[f.subject for f in blocked]!r}"
                 )
             result.append(kept)
         return result
@@ -745,7 +748,10 @@ class WorkingFactReconciler:
                     obj = None
 
         if not isinstance(obj, dict):
-            logger.warning(f"[fact-reconcile] failed to parse ops output: {text!r}")
+            logger.warning(
+                f"[fact-reconcile] failed to parse ops output ({len(text or '')} chars)"
+            )
+            logger.debug(f"[fact-reconcile] unparsable ops output: {text!r}")
             return {}
         ops_raw = obj.get("ops")
         if not isinstance(ops_raw, list):
@@ -835,8 +841,11 @@ class WorkingFactReconciler:
                 # 别的主体的状态不是。闸门关掉时这道复查一并跳过，否则闸门就没关干净。
                 if self.subject_gate and _subject_conflict(draft.subject, old.subject):
                     logger.warning(
-                        f"[fact-reconcile] refused cross-subject SUPERSEDE: "
-                        f"{old.fact_id}({old.subject!r}) by draft subject {draft.subject!r}"
+                        f"[fact-reconcile] refused cross-subject SUPERSEDE: {old.fact_id}"
+                    )
+                    logger.debug(
+                        f"[fact-reconcile] cross-subject: old subject={old.subject!r} "
+                        f"draft subject={draft.subject!r}"
                     )
                     continue
                 try:

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/coding/judge.py

@@ -195,8 +195,10 @@ async def classify_messages_scene(
         result = _parse_scene_json(resp.content)
         if result is None:
             logger.warning(
-                f"[coding-judge] failed to parse classify_messages output: {resp.content!r}; defaulting to chat"
+                f"[coding-judge] failed to parse classify_messages output "
+                f"({len(resp.content or '')} chars); defaulting to chat"
             )
+            logger.debug(f"[coding-judge] unparsable classify_messages output: {resp.content!r}")
             await _store_coding_log(
                 cache, request_id=request_id, user_id=user_id, agent_id=agent_id,
                 session_id=session_id, step="CODING_JUDGE", prompt=prompt,
@@ -207,9 +209,8 @@ async def classify_messages_scene(
             return "chat"
         scene = result["scene"]
         parsed = {**result, "is_coding": scene != "chat"}
-        logger.info(
-            f"[coding-judge] scene={scene} reason={result.get('reason', '')!r}"
-        )
+        logger.info(f"[coding-judge] scene={scene}")
+        logger.debug(f"[coding-judge] scene={scene} reason={result.get('reason', '')!r}")
         await _store_coding_log(
             cache, request_id=request_id, user_id=user_id, agent_id=agent_id,
             session_id=session_id, step="CODING_JUDGE", prompt=prompt,
@@ -295,8 +296,10 @@ async def classify_queries_scene(
         result = _parse_scene_json(resp.content)
         if result is None:
             logger.warning(
-                f"[coding-judge] failed to parse classify_queries output: {resp.content!r}; defaulting to chat"
+                f"[coding-judge] failed to parse classify_queries output "
+                f"({len(resp.content or '')} chars); defaulting to chat"
             )
+            logger.debug(f"[coding-judge] unparsable classify_queries output: {resp.content!r}")
             return "chat"
         scene = result["scene"]
         logger.info(f"[coding-judge] queries scene={scene}")
@@ -422,15 +425,18 @@ async def classify_and_rewrite_queries(
     scene = _parse_scene_label(head)
     if scene is None:
         logger.warning(
-            f"[coding-judge] classify_and_rewrite unrecognized head={head!r}; falling back to chat"
+            f"[coding-judge] classify_and_rewrite unrecognized head "
+            f"({len(head)} chars); falling back to chat"
         )
+        logger.debug(f"[coding-judge] classify_and_rewrite unrecognized head={head!r}")
         return {"scene": "chat", "is_coding": False, "rewrite_query": rewrite, "ok": False}
     is_coding = scene != "chat"
 
     logger.info(
         f"[coding-judge] classify_and_rewrite scene={scene} "
-        f"rewrite={rewrite!r}"
+        f"rewrite({len(rewrite)} chars)"
     )
+    logger.debug(f"[coding-judge] classify_and_rewrite rewrite={rewrite!r}")
     return {"scene": scene, "is_coding": is_coding, "rewrite_query": rewrite, "ok": True}
 
 
@@ -569,8 +575,9 @@ async def analyze_queries(
         parsed_scene = _parse_scene_label(head)
         if parsed_scene is None:
             logger.warning(
-                f"[coding-judge] analyze_queries unrecognized head={head!r}; ok=False"
+                f"[coding-judge] analyze_queries unrecognized head ({len(head)} chars); ok=False"
             )
+            logger.debug(f"[coding-judge] analyze_queries unrecognized head={head!r}")
             return {**fallback, "since_raw": ""}
         scene = parsed_scene
         idx = 1
@@ -589,9 +596,10 @@ async def analyze_queries(
     created_after = _since_to_created_after(since_raw, current_time)
 
     logger.info(
-        f"[coding-judge] analyze scene={scene} rewrite={rewrite!r} "
+        f"[coding-judge] analyze scene={scene} rewrite({len(rewrite)} chars) "
         f"since={since_raw!r} created_after={created_after}"
     )
+    logger.debug(f"[coding-judge] analyze rewrite={rewrite!r}")
     return {
         "scene": scene, "is_coding": scene != "chat", "rewrite_query": rewrite,
         "created_after": created_after, "since_raw": since_raw, "ok": True,
@@ -614,7 +622,10 @@ def _since_to_created_after(since_raw: str, current_time: str) -> Optional[float
             return dt.timestamp()
         except (ValueError, TypeError):
             continue
-    logger.warning(f"[coding-judge] analyze_queries unparsable SINCE={since_raw!r}")
+    logger.warning(
+        f"[coding-judge] analyze_queries unparsable SINCE ({len(since_raw)} chars)"
+    )
+    logger.debug(f"[coding-judge] analyze_queries unparsable SINCE={since_raw!r}")
     return None
 
 

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/coding/reconciler.py

@@ -388,7 +388,10 @@ class CodingMemoryReconciler:
                     obj = None
 
         if not obj or not isinstance(obj, dict):
-            logger.warning(f"[coding-reconcile] failed to parse ops output: {text!r}")
+            logger.warning(
+                f"[coding-reconcile] failed to parse ops output ({len(text or '')} chars)"
+            )
+            logger.debug(f"[coding-reconcile] unparsable ops output: {text!r}")
             return []
         ops_raw = obj.get("ops") or []
         if not isinstance(ops_raw, list):
@@ -441,10 +444,10 @@ class CodingMemoryReconciler:
         for op in ops:
             if op.action == "ADD":
                 if op.draft_idx is None or not (0 <= op.draft_idx < len(drafts)):
-                    logger.warning(f"[coding-reconcile] drop invalid ADD: {op.to_dict()}")
+                    logger.warning(f"[coding-reconcile] drop invalid ADD: {_op_ref(op)}")
                     continue
                 if op.draft_idx in consumed:
-                    logger.warning(f"[coding-reconcile] drop ADD on consumed draft: {op.to_dict()}")
+                    logger.warning(f"[coding-reconcile] drop ADD on consumed draft: {_op_ref(op)}")
                     continue
                 d = drafts[op.draft_idx]
                 memory = self._draft_to_new_memory(d)
@@ -458,18 +461,18 @@ class CodingMemoryReconciler:
 
             elif op.action == "UPDATE":
                 if op.draft_idx is None or not (0 <= op.draft_idx < len(drafts)):
-                    logger.warning(f"[coding-reconcile] drop invalid UPDATE: {op.to_dict()}")
+                    logger.warning(f"[coding-reconcile] drop invalid UPDATE: {_op_ref(op)}")
                     continue
                 if not op.target_experience_id:
-                    logger.warning(f"[coding-reconcile] drop UPDATE missing target: {op.to_dict()}")
+                    logger.warning(f"[coding-reconcile] drop UPDATE missing target: {_op_ref(op)}")
                     continue
                 if not self._target_was_offered(op, candidates_per_draft):
                     logger.warning(
-                        f"[coding-reconcile] drop UPDATE outside authority scope: {op.to_dict()}"
+                        f"[coding-reconcile] drop UPDATE outside authority scope: {_op_ref(op)}"
                     )
                     continue
                 if op.draft_idx in consumed:
-                    logger.warning(f"[coding-reconcile] drop UPDATE on consumed draft: {op.to_dict()}")
+                    logger.warning(f"[coding-reconcile] drop UPDATE on consumed draft: {_op_ref(op)}")
                     continue
                 d = drafts[op.draft_idx]
                 memory = self._draft_to_new_memory(d, experience_id=op.target_experience_id)
@@ -488,17 +491,17 @@ class CodingMemoryReconciler:
 
             elif op.action == "DELETE":
                 if not op.target_experience_id:
-                    logger.warning(f"[coding-reconcile] drop DELETE missing target: {op.to_dict()}")
+                    logger.warning(f"[coding-reconcile] drop DELETE missing target: {_op_ref(op)}")
                     continue
                 if not self._target_was_offered(op, candidates_per_draft):
                     logger.warning(
-                        f"[coding-reconcile] drop DELETE outside authority scope: {op.to_dict()}"
+                        f"[coding-reconcile] drop DELETE outside authority scope: {_op_ref(op)}"
                     )
                     continue
                 # DELETE 需要知道 user_id；通过 draft_idx（如有）或第一个 draft 推断
                 user_id = self._infer_user_id(op, drafts)
                 if not user_id:
-                    logger.warning(f"[coding-reconcile] drop DELETE no user_id context: {op.to_dict()}")
+                    logger.warning(f"[coding-reconcile] drop DELETE no user_id context: {_op_ref(op)}")
                     continue
                 try:
                     ok = await self.store.delete(op.target_experience_id, user_id=user_id)
@@ -585,6 +588,14 @@ class CodingMemoryReconciler:
 # Helpers
 # ================================================================
 
+def _op_ref(op: ReconcileOp) -> str:
+    """op 的日志引用：只带动作与编号，不带 LLM 写的 reason。"""
+    return (
+        f"action={op.action} draft_idx={op.draft_idx} "
+        f"target={op.target_experience_id}"
+    )
+
+
 def _truncate(s: str, n: int) -> str:
     if not s:
         return ""

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/coding/store.py

@@ -605,7 +605,11 @@ class CodingMemoryStore:
         await self._upsert_vec_keys(memory)
         logger.info(
             f"[coding-store] inserted experience_id={memory.experience_id} "
-            f"task={memory.task!r} keys={1 + len(memory.search_keys)}"
+            f"keys={1 + len(memory.search_keys)}"
+        )
+        logger.debug(
+            f"[coding-store] inserted experience_id={memory.experience_id} "
+            f"task={memory.task!r}"
         )
 
     async def update(self, memory: CodingMemory) -> None:
@@ -1002,7 +1006,8 @@ class CodingMemoryStore:
             fact.created_at = datetime.utcnow()
         await _run_in_pool(self._upsert_fact_sql_sync, fact)
         await self._upsert_fact_vec(fact)
-        logger.info(
+        logger.info(f"[coding-store] inserted fact_id={fact.fact_id}")
+        logger.debug(
             f"[coding-store] inserted fact_id={fact.fact_id} "
             f"statement={fact.statement!r}"
         )

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/core/embed_service.py

@@ -80,7 +80,7 @@ def _count_tokens(text: str) -> int:
     try:
         import tiktoken
 
-        return len(tiktoken.get_encoding("cl100k_base").encode(text))
+        return len(tiktoken.get_encoding("cl100k_base").encode(text, disallowed_special=()))
     except Exception:
         return len(text) // _CHARS_PER_TOKEN_FALLBACK + 1
 
@@ -98,7 +98,8 @@ def _truncate_for_embedding(text: str, limit: int = _EMBED_MAX_TOKENS) -> str:
         import tiktoken
 
         enc = tiktoken.get_encoding("cl100k_base")
-        ids = enc.encode(text)
+        # Input is ordinary user text, not a tokenizer control-token stream.
+        ids = enc.encode(text, disallowed_special=())
         if len(ids) <= limit:
             return text
         dropped = len(ids) - limit
@@ -753,16 +754,22 @@ class EmbedService:
         """
         打一条 INFO 级 embedding 请求日志（含 request_id / provider / model / api / 入参 / 出参）。
 
-        出参只含 vector 维度，不含向量数值。request_id 同时写入 message，
+        出参只含 vector 维度，不含向量数值。入参的 input 是待向量化的原文
+        （对话 / 记忆 / 查询），INFO 只记每条的字符数（input_chars），原文仅在
+        DEBUG 单独输出。request_id 同时写入 message，
         并依赖 log formatter 的 %(request_id)s（setup_logging 后生效）。
         """
+        texts = request_payload.get("input")
+        info_request = {k: v for k, v in request_payload.items() if k != "input"}
+        if isinstance(texts, list):
+            info_request["input_chars"] = [len(str(t)) for t in texts]
         payload = {
             "request_id": get_request_id(),
             "status": status,
             "provider": self._embed_config.provider,
             "model": self._embed_config.model,
             "api": api_url,
-            "request": request_payload,
+            "request": info_request,
             "response": response_payload,
         }
         try:
@@ -770,6 +777,10 @@ class EmbedService:
         except Exception:
             body = str(payload)
         logger.info(f"[embed] {body}")
+        if texts is not None and logger.isEnabledFor(logging.DEBUG):
+            logger.debug(
+                f"[embed] input: {json.dumps(texts, ensure_ascii=False, default=str)}"
+            )
 
     async def _embed_openai(
         self, texts: List[str]

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/pipelines/_retrieval/reconcile_retrieval.py

@@ -115,11 +115,16 @@ class ReconcileHybridRetriever:
         fused_max = max(fused_all) if fused_all else 0.0
 
         base = (
-            f"[reconcile-hybrid][{req}] pool={pool_size} q_terms={q_terms!r} "
+            f"[reconcile-hybrid][{req}] pool={pool_size} q_terms={len(q_terms)} "
             f"raw_bm25 max={raw_max:.4f} nonzero={raw_nonzero}/{len(raw_bm25)} "
             f"bm25_norm max={norm_max:.4f} nonzero={norm_nonzero}/{len(bm25_norms)} "
             f"sem_max={sem_max:.4f} fused_max={fused_max:.4f} "
             f"kept={kept}/{len(fused_all)} min_score={self._cfg.min_score} "
+            f"query({len(query_text or '')} chars)"
+        )
+        # query 是待对账的新记忆原文，词项与预览只进 DEBUG
+        logger.debug(
+            f"[reconcile-hybrid][{req}] q_terms={q_terms!r} "
             f"query={q_preview!r} lemmatized={lem_preview!r}"
         )
 

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/pipelines/cross_domain_sweeper.py

@@ -692,9 +692,10 @@ class CrossDomainSweeper:
                 )
 
             logger.info(
-                f"[sweeper] Created L6 core {core_id[:12]}: '{core_content[:60]}' "
+                f"[sweeper] Created L6 core {core_id[:12]} "
                 f"from {len(cluster_ids)} basics, evidence_inherited={len(inherited_evidence_ids)}"
             )
+            logger.debug(f"[sweeper] L6 core {core_id[:12]} content={core_content[:60]!r}")
             return 1, 0, [core_id]
 
         except Exception as e:

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/pipelines/reader_base.py

@@ -3587,8 +3587,9 @@ class BaseReadPipeline(ReadPipeline):
                 f"hidden_l0={len(hidden_l0_hits)} fwd_l6={len(forward_l6)} rev_l6={len(reverse_l6)} "
                 f"fused_l6={len(fused_l6)} graph_intent={len(graph_intention_hits)} "
                 f"returned={len(final_results)} "
-                f"query='{request.query[:80]}'"
+                f"query({len(request.query or '')} chars)"
             )
+            logger.debug(f"[read/{self.VERSION}] query={request.query[:80]!r}")
 
             response.success = True
 

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/pipelines/system2_agent.py

@@ -2516,7 +2516,8 @@ def _parse_operations_json(text: str) -> Optional[List[Dict[str, Any]]]:
             return result
         return None
     except json.JSONDecodeError:
-        logger.warning(f"[S2-agent] JSON parse failed: {json_str[:200]}")
+        logger.warning(f"[S2-agent] JSON parse failed ({len(json_str)} chars)")
+        logger.debug(f"[S2-agent] unparsable output: {json_str[:200]!r}")
         return None
 
 

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/utils/async_executor.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import asyncio
 import concurrent.futures
+import contextvars
 import functools
 from concurrent.futures import Executor
 from typing import Any, Callable, Optional
@@ -39,7 +40,9 @@ async def run_in_executor_guarded(
 
 async def to_thread_guarded(func: Callable[..., Any], *args: Any, **kwargs: Any) -> Any:
     """Guarded equivalent of ``asyncio.to_thread`` using the default pool."""
-    return await run_in_executor_guarded(None, func, *args, **kwargs)
+    context = contextvars.copy_context()
+    call = functools.partial(func, *args, **kwargs)
+    return await run_in_executor_guarded(None, context.run, call)
 
 
 def concurrent_result_guarded(

{hy_memory-2.0.7 → hy_memory-2.0.8}/hy_memory/utils/pipeline_log_writer.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 """
-Pipeline Log Writer — 环节级 JSONL 日志（始终开启，与 SQLite Trace 分离）。
+Pipeline Log Writer — 环节级 JSONL 日志（默认开启，MEMORY_PIPELINE_LOG_ENABLED=false 关闭；
+与 SQLite Trace 分离）。
 
 目录: {log_dir}/{subdir}/{date}.log
 每行: request_id, namespace, user_id, agent_id, step, prompt, content, parsed,