Skip to content
Python

feat(sdk): switch to turn the pipeline log off, keep conversation text out of INFO logs (2.0.8)

alvinfeidc762df78bb2
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 0a44dae..8c519a9 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -76,6 +76,24 @@ Hy Memory and MemHub are versioned and released independently.
`hy_node_permissions` proof table. Evidence, governed memories, model
profiles, SDK stores, and source/host grants are preserved.
+## Hy Memory 2.0.8 — 2026-10-28
+
+- New `MEMORY_PIPELINE_LOG_ENABLED` (default `true`) turns the pipeline JSONL
+ log (`{MEMORY_LOG_DIR}/<subdir>/<date>.log`) off. With `false` no JSONL
+ file or directory is written. When `MEMORY_PIPELINE_TRACE_ENABLED` is also
+ `false`, `store_pipeline_log` becomes a no-op that returns `True` at once:
+ no timing, redaction, background task or database write. The init log line
+ now states whether the JSONL log is on or off.
+- Conversation and memory text no longer appears in INFO or WARNING logs. The
+ `[add]` input, search queries and rewrites, coding experience tasks, fact
+ statements and subjects, reconcile op details, extracted info, embedding
+ inputs and unparsable model output moved to DEBUG. INFO lines keep ids,
+ counts and character lengths; parse-failure warnings remain but report only
+ the length of the output, e.g. `failed to parse output (812 chars)`. The
+ `[embed]` INFO line now carries `request.input_chars` instead of
+ `request.input`. The `JSON_PARSE_FAILED` error message from extraction no
+ longer embeds the model output either.
+
## Hy Memory 2.0.7 — 2026-10-28
- Published
diff --git a/docs/env_reference.md b/docs/env_reference.md
index f26caf9..7bd3841 100644
--- a/docs/env_reference.md
+++ b/docs/env_reference.md
@@ -191,6 +191,7 @@ SDK 不设置 Rerank Search 并发上限。开启后模型在 `HyMemoryClient`
| `MEMORY_LOG_FORMAT` | `text` | `text` / `json` |
| `MEMORY_LOG_DIR` | — | 统一日志根目录 |
| `MEMORY_TRACE_LOG_DIR` | — | JSONL 日志目录的兼容旧名;优先使用 `MEMORY_LOG_DIR` |
+| `MEMORY_PIPELINE_LOG_ENABLED` | `true` | 是否写 pipeline JSONL 日志(`{MEMORY_LOG_DIR}/<subdir>/<date>.log`);`false` 完全不写 |
| `MEMORY_PIPELINE_TRACE_ENABLED` | `true` | 是否写入 cache 的 pipeline trace 表 |
| `MEMORY_MEMORY_OPERATIONS_ENABLED` | `false` | 是否写入 memory operation 审计记录 |
| `MEMORY_HISTORY_ENABLE` | `true` | 是否启用历史记录 |
diff --git a/hy_memory/agent/extractor.py b/hy_memory/agent/extractor.py
index 8861600..5a81f44 100644
--- a/hy_memory/agent/extractor.py
+++ b/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,
diff --git a/hy_memory/agent/llm_provider.py b/hy_memory/agent/llm_provider.py
index 52a70b8..289f1ea 100644
--- a/hy_memory/agent/llm_provider.py
+++ b/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
diff --git a/hy_memory/agent/mem_agent.py b/hy_memory/agent/mem_agent.py
index 7c8db7b..e9ecb60 100644
--- a/hy_memory/agent/mem_agent.py
+++ b/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:
diff --git a/hy_memory/agent/reconciler.py b/hy_memory/agent/reconciler.py
index ce676ba..bf55cd4 100644
--- a/hy_memory/agent/reconciler.py
+++ b/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
@@ -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
diff --git a/hy_memory/agent/tools/base.py b/hy_memory/agent/tools/base.py
index 667bfc6..bf457b3 100644
--- a/hy_memory/agent/tools/base.py
+++ b/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
diff --git a/hy_memory/client.py b/hy_memory/client.py
index 895a862..8473917 100644
--- a/hy_memory/client.py
+++ b/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
diff --git a/hy_memory/coding/extractor.py b/hy_memory/coding/extractor.py
index 1d65cff..82afde6 100644
--- a/hy_memory/coding/extractor.py
+++ b/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
diff --git a/hy_memory/coding/fact_reconciler.py b/hy_memory/coding/fact_reconciler.py
index 41ea32e..9cc946e 100644
--- a/hy_memory/coding/fact_reconciler.py
+++ b/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:
diff --git a/hy_memory/coding/judge.py b/hy_memory/coding/judge.py
index bfa28c1..d005174 100644
--- a/hy_memory/coding/judge.py
+++ b/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
diff --git a/hy_memory/coding/reconciler.py b/hy_memory/coding/reconciler.py
index 56aacc7..7cfff82 100644
--- a/hy_memory/coding/reconciler.py
+++ b/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 ""
diff --git a/hy_memory/coding/store.py b/hy_memory/coding/store.py
index e4e6033..0effea1 100644
--- a/hy_memory/coding/store.py
+++ b/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}"
)
diff --git a/hy_memory/core/embed_service.py b/hy_memory/core/embed_service.py
index 0f9de32..96fec8c 100644
--- a/hy_memory/core/embed_service.py
+++ b/hy_memory/core/embed_service.py
@@ -754,16 +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:
@@ -771,6 +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]
diff --git a/hy_memory/pipelines/_retrieval/reconcile_retrieval.py b/hy_memory/pipelines/_retrieval/reconcile_retrieval.py
index a5081e1..526aa0d 100644
--- a/hy_memory/pipelines/_retrieval/reconcile_retrieval.py
+++ b/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}"
)
diff --git a/hy_memory/pipelines/cross_domain_sweeper.py b/hy_memory/pipelines/cross_domain_sweeper.py
index 700423e..8843e40 100644
--- a/hy_memory/pipelines/cross_domain_sweeper.py
+++ b/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:
diff --git a/hy_memory/pipelines/reader_base.py b/hy_memory/pipelines/reader_base.py
index bc288d4..8bcacef 100644
--- a/hy_memory/pipelines/reader_base.py
+++ b/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
diff --git a/hy_memory/pipelines/system2_agent.py b/hy_memory/pipelines/system2_agent.py
index d16d242..2ace7a8 100644
--- a/hy_memory/pipelines/system2_agent.py
+++ b/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
diff --git a/hy_memory/utils/pipeline_log_writer.py b/hy_memory/utils/pipeline_log_writer.py
index 20220bb..7b3f1b7 100644
--- a/hy_memory/utils/pipeline_log_writer.py
+++ b/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,
diff --git a/hy_memory/utils/pipeline_observability.py b/hy_memory/utils/pipeline_observability.py
index a7d898e..371dc70 100644
--- a/hy_memory/utils/pipeline_observability.py
+++ b/hy_memory/utils/pipeline_observability.py
@@ -1,16 +1,20 @@
# -*- coding: utf-8 -*-
"""
-Pipeline 可观测性:Log(文件 JSONL,始终开启)与 Trace(SQLite pipeline_logs,可关闭)。
+Pipeline 可观测性:Log(文件 JSONL,默认开启,可关闭)与 Trace(SQLite pipeline_logs,可关闭)。
- Log:运维 tail/grep,每个环节即时一行,不依赖后续步骤成功与否。
- Trace:Inspector / 调试,落库 pipeline_logs(需 MEMORY_CACHE_BACKEND=sqlite 等持久化后端)。
环境变量:
+ MEMORY_PIPELINE_LOG_ENABLED — Log 写 JSONL 文件,默认 true;false 时完全不写
MEMORY_PIPELINE_TRACE_ENABLED — Trace 落库,默认 true;OpenClaw C 端可设 false
MEMORY_MEMORY_OPERATIONS_ENABLED — memory_operations 审计表落库,默认 false
MEMORY_LOG_DIR — Log 目录(优先)
MEMORY_TRACE_LOG_DIR — Log 目录(兼容旧名)
+Log 与 Trace 都关闭时不包装 store_pipeline_log,而是换成立即返回 True 的
+空操作:热路径不做任何计时、脱敏或后台任务,也不写库。
+
子目录({log_dir}/{subdir}/{date}.log)由 PipelineLogWriter 从每条记录的
user_id 前缀(第一个 "__" 左侧)切分;无前缀回落 "default"。该前缀是
通用 namespace,可用于项目、部署或数据分桶。
@@ -94,6 +98,16 @@ def is_pipeline_trace_enabled() -> bool:
)
+def is_pipeline_log_enabled() -> bool:
+ """是否把 pipeline step 写成 JSONL 文件({log_dir}/<subdir>/<date>.log)。默认开启。"""
+ return os.getenv("MEMORY_PIPELINE_LOG_ENABLED", "true").strip().lower() in (
+ "true",
+ "1",
+ "yes",
+ "on",
+ )
+
+
def is_memory_operations_enabled() -> bool:
"""是否将知识库变动写入 memory_operations 审计表。默认关闭(false)。"""
return os.getenv("MEMORY_MEMORY_OPERATIONS_ENABLED", "false").lower() in (
@@ -125,7 +139,7 @@ def redact_content(value: str) -> str:
def resolve_pipeline_log_dir() -> str:
"""
- JSONL pipeline log 根目录(始终使用,有默认值)。
+ JSONL pipeline log 根目录(MEMORY_PIPELINE_LOG_ENABLED 开启时使用,有默认值)。
优先级: MEMORY_LOG_DIR > MEMORY_TRACE_LOG_DIR > {MEMORY_DATA_DIR}/logs/pipeline
"""
@@ -228,6 +242,7 @@ def wrap_store_pipeline_log(
) -> Callable[..., Any]:
"""包装 cache.store_pipeline_log:计时同步、JSONL/DB 异步落盘,不堵主请求。
+ - log_writer 为 None 时不写 JSONL(MEMORY_PIPELINE_LOG_ENABLED=false)
- step-to-step elapsed_ms / event_at_ms 在调用瞬间打点(与业务墙钟对齐)
- event_at_ms:调用方传入非 0 值则直接复用(App 已在自己被调用的那一刻
同步打点,比这里更接近真实事件时刻);传 0 / 不传才用本地 time.time()
@@ -410,7 +425,8 @@ def wrap_store_pipeline_log(
try:
loop = asyncio.get_running_loop()
# JSONL 用线程池,与 loop 无亲和,留在当前 loop。
- _track_task(loop.create_task(_persist_jsonl()))
+ if log_writer is not None:
+ _track_task(loop.create_task(_persist_jsonl()))
# DB trace 用 cache pool(可能 aiomysql,绑定 owner_loop)。若当前不在
# owner_loop(如 search 走独立 loop),派发回 owner_loop 执行,避免跨 loop。
if trace_enabled:
@@ -446,25 +462,26 @@ def wrap_store_pipeline_log(
)
except RuntimeError:
# 无 running loop(极少见):退化为同步写,保证不丢日志
- try:
- log_writer.write_step(
- request_id=request_id,
- user_id=user_id,
- agent_id=agent_id,
- session_id=session_id,
- step=step,
- prompt=prompt,
- response=response,
- parsed=parsed,
- memory_ids=mem_ids,
- elapsed_ms=step_elapsed_ms,
- prompt_tokens=prompt_tokens,
- completion_tokens=completion_tokens,
- total_tokens=total_tokens,
- event_at_ms=event_at_ms,
- )
- except Exception:
- pass
+ if log_writer is not None:
+ try:
+ log_writer.write_step(
+ request_id=request_id,
+ user_id=user_id,
+ agent_id=agent_id,
+ session_id=session_id,
+ step=step,
+ prompt=prompt,
+ response=response,
+ parsed=parsed,
+ memory_ids=mem_ids,
+ elapsed_ms=step_elapsed_ms,
+ prompt_tokens=prompt_tokens,
+ completion_tokens=completion_tokens,
+ total_tokens=total_tokens,
+ event_at_ms=event_at_ms,
+ )
+ except Exception:
+ pass
if trace_enabled:
try:
result = original_store(
@@ -496,6 +513,11 @@ def wrap_store_pipeline_log(
return _store_pipeline_observability
+async def _noop_store_pipeline_log(*args: Any, **kwargs: Any) -> bool:
+ """Log 与 Trace 都关闭时的 store_pipeline_log:不计时、不写文件、不写库。"""
+ return True
+
+
def install_pipeline_observability(
cache: Any,
*,
@@ -503,6 +525,9 @@ def install_pipeline_observability(
) -> None:
"""给 cache 安装 JSONL + Trace 包装(fire-and-forget)。
+ MEMORY_PIPELINE_LOG_ENABLED=false 时不写 JSONL;若 Trace 也关闭,
+ store_pipeline_log 被换成空操作(不包装、不写库)。
+
在 cache 所属 loop(write loop / _LoopThread)上调用,本函数会捕获该 loop
作为 owner_loop 传给包装器:search 走独立 loop 后,从 search loop 触发的 DB
落库会被派发回这个 owner_loop,避免跨 loop 用 aiomysql 污染连接池。
@@ -514,15 +539,31 @@ def install_pipeline_observability(
except RuntimeError:
owner_loop = None
- log_dir = resolve_pipeline_log_dir()
- log_writer = PipelineLogWriter(log_dir)
+ log_enabled = is_pipeline_log_enabled()
trace_enabled = is_pipeline_trace_enabled()
- logger.info(
- f"[{log_label}] Pipeline log (JSONL) enabled: {log_dir}/<subdir>/<date>.log "
- f"(subdir from user_id prefix before '__', else default) ; "
- f"pipeline trace (DB)={'on' if trace_enabled else 'off'} ; "
- f"persist=async(fire-and-forget)"
- )
+ if not log_enabled and not trace_enabled:
+ logger.info(
+ f"[{log_label}] Pipeline log (JSONL) disabled ; pipeline trace (DB)=off ; "
+ f"store_pipeline_log=no-op"
+ )
+ cache.store_pipeline_log = _noop_store_pipeline_log
+ return
+
+ log_writer = None
+ if log_enabled:
+ log_dir = resolve_pipeline_log_dir()
+ log_writer = PipelineLogWriter(log_dir)
+ logger.info(
+ f"[{log_label}] Pipeline log (JSONL) enabled: {log_dir}/<subdir>/<date>.log "
+ f"(subdir from user_id prefix before '__', else default) ; "
+ f"pipeline trace (DB)={'on' if trace_enabled else 'off'} ; "
+ f"persist=async(fire-and-forget)"
+ )
+ else:
+ logger.info(
+ f"[{log_label}] Pipeline log (JSONL) disabled ; "
+ f"pipeline trace (DB)=on ; persist=async(fire-and-forget)"
+ )
cache.store_pipeline_log = wrap_store_pipeline_log(
cache.store_pipeline_log,
log_writer=log_writer,
diff --git a/pyproject.toml b/pyproject.toml
index c2afd09..1588851 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
[project]
name = "hy-memory"
-version = "2.0.7"
+version = "2.0.8"
description = "HY Memory - Industrial-grade dual-system cognitive memory framework"
readme = "README.md"
requires-python = ">=3.9"
diff --git a/tests/coding/test_content_log_levels.py b/tests/coding/test_content_log_levels.py
new file mode 100644
index 0000000..6e8e7af
--- /dev/null
+++ b/tests/coding/test_content_log_levels.py
@@ -0,0 +1,140 @@
+# -*- coding: utf-8 -*-
+"""对话、记忆正文和模型输出只进 DEBUG,不进 INFO / WARNING。
+
+MemHub 等调用方默认以 INFO 运行;这些文本一旦进 INFO,就会写进常驻的
+hy_memory.log。这里逐条锁住曾经把正文打在 INFO / WARNING 的日志。
+"""
+
+import logging
+
+import pytest
+
+from hy_memory.agent.reconciler import ReconcileOp as AgentReconcileOp
+from hy_memory.agent.reconciler import _log_ops_detail
+from hy_memory.coding.extractor import CodingMemoryExtractor
+from hy_memory.coding.fact_reconciler import WorkingFactReconciler
+from hy_memory.coding.judge import classify_and_rewrite_queries
+from hy_memory.coding.reconciler import CodingMemoryReconciler
+from hy_memory.coding.types import CodingMemory, WorkingFact
+
+from tests.coding._helpers import MockLLMProvider
+
+SECRET = "SECRET-CONVERSATION-TEXT-42"
+
+
+def _above_debug(caplog):
+ return [
+ r.getMessage() for r in caplog.records
+ if r.name.startswith("hy_memory") and r.levelno > logging.DEBUG
+ ]
+
+
+def _debug(caplog):
+ return [
+ r.getMessage() for r in caplog.records
+ if r.name.startswith("hy_memory") and r.levelno == logging.DEBUG
+ ]
+
+
+def _assert_secret_only_at_debug(caplog):
+ assert not [m for m in _above_debug(caplog) if SECRET in m]
+ assert [m for m in _debug(caplog) if SECRET in m]
+
+
+class TestStoreInsertLogs:
+ async def test_experience_task_not_at_info(self, coding_store, caplog):
+ caplog.set_level(logging.DEBUG, logger="hy_memory")
+ await coding_store.insert(CodingMemory(
+ experience_id="e1", user_id="u1", task=SECRET, solution="S",
+ ))
+ info = [m for m in _above_debug(caplog) if "inserted experience_id=e1" in m]
+ assert info
+ _assert_secret_only_at_debug(caplog)
+
+ async def test_fact_statement_not_at_info(self, coding_store, caplog):
+ caplog.set_level(logging.DEBUG, logger="hy_memory")
+ await coding_store.insert_fact(WorkingFact(
+ fact_id="f1", user_id="u1", agent_id="a1", session_id="s1",
+ workspace_id="ws/a", statement=SECRET,
+ ))
+ info = [m for m in _above_debug(caplog) if "inserted fact_id=f1" in m]
+ assert info
+ _assert_secret_only_at_debug(caplog)
+
+
+class TestParseFailureWarnings:
+ """解析失败仍发 WARNING,但只带长度,模型输出进 DEBUG。"""
+
+ @pytest.mark.parametrize("parse", [
+ CodingMemoryExtractor._parse_output,
+ CodingMemoryReconciler._parse_ops,
+ WorkingFactReconciler._parse_ops,
+ ])
+ def test_warning_keeps_length_drops_text(self, parse, caplog):
+ caplog.set_level(logging.DEBUG, logger="hy_memory")
+ bad = f"not json {SECRET}"
+ parse(bad)
+ warnings = [
+ r.getMessage() for r in caplog.records
+ if r.levelno == logging.WARNING and "failed to parse" in r.getMessage()
+ ]
+ assert warnings and f"({len(bad)} chars)" in warnings[0]
+ _assert_secret_only_at_debug(caplog)
+
+
+class TestJudgeLogs:
+ async def test_rewrite_not_at_info(self, caplog):
+ caplog.set_level(logging.DEBUG, logger="hy_memory")
+ llm = MockLLMProvider(f"1\n{SECRET}")
+ result = await classify_and_rewrite_queries(["q"], llm)
+ assert result["rewrite_query"] == SECRET
+ _assert_secret_only_at_debug(caplog)
+
+ async def test_unrecognized_head_not_at_warning(self, caplog):
+ caplog.set_level(logging.DEBUG, logger="hy_memory")
+ llm = MockLLMProvider(f"{SECRET}\nrewrite")
+ result = await classify_and_rewrite_queries(["q"], llm)
+ assert result["ok"] is False
+ _assert_secret_only_at_debug(caplog)
+
+
+def test_reconciler_ops_detail_is_debug(caplog):
+ caplog.set_level(logging.DEBUG, logger="hy_memory")
+ _log_ops_detail([AgentReconcileOp(op="ADD", content=SECRET)])
+ _assert_secret_only_at_debug(caplog)
+
+
+class _StopAfterLogging(Exception):
+ pass
+
+
+def _add_client():
+ from types import SimpleNamespace
+ from unittest.mock import AsyncMock
+
+ from hy_memory.client import HyMemoryClient
+
+ client = HyMemoryClient.__new__(HyMemoryClient)
+ client._mode = "lite"
+ client._config = SimpleNamespace(coding=None)
+ writer = SimpleNamespace(
+ VERSION="test", write=AsyncMock(side_effect=_StopAfterLogging),
+ )
+ client._registry = SimpleNamespace(get_writer=AsyncMock(return_value=writer))
+ return client
+
+
+ SECRET,
+ [{"role": "user", "content": SECRET}],
+])
+async def test_add_does_not_log_input_at_info(data, caplog):
+ caplog.set_level(logging.DEBUG, logger="hy_memory")
+ client = _add_client()
+ with pytest.raises(_StopAfterLogging):
+ await client._async_add_impl(data, user_id="u1")
+ assert [m for m in _above_debug(caplog) if m.startswith("[add] writing")]
+ _assert_secret_only_at_debug(caplog)
diff --git a/tests/test_embed_warning_log.py b/tests/test_embed_warning_log.py
index bb561e5..ae4e90e 100644
--- a/tests/test_embed_warning_log.py
+++ b/tests/test_embed_warning_log.py
@@ -90,7 +90,10 @@ class TestEmbedInfoLog:
assert payload["provider"] == "openai"
assert payload["model"] == "text-embedding-test"
assert payload["api"] == "https://example.com/v1/embeddings"
- assert payload["request"]["input"] == ["hello world"]
+ # 待向量化的原文不进 INFO,只记每条字符数
+ assert "input" not in payload["request"]
+ assert payload["request"]["input_chars"] == [11]
+ assert "hello world" not in info_msgs[0]
assert payload["request"]["dimensions"] == 8
assert payload["response"]["vector_dims"] == [8]
assert payload["response"]["vector_count"] == 1
diff --git a/tests/test_pipeline_observability.py b/tests/test_pipeline_observability.py
index 40f5b30..e81f81a 100644
--- a/tests/test_pipeline_observability.py
+++ b/tests/test_pipeline_observability.py
@@ -1,4 +1,4 @@
-"""Pipeline log(始终)与 trace(可关)分离。"""
+"""Pipeline log(默认开,可关)与 trace(可关)分离。"""
import asyncio
import json
@@ -10,6 +10,7 @@ from hy_memory.config import MemoryConfig
from hy_memory.data.cache_sqlite import SqliteCache
from hy_memory.utils.pipeline_observability import (
is_llm_content_logging_enabled,
+ is_pipeline_log_enabled,
is_pipeline_trace_enabled,
resolve_pipeline_log_dir,
)
@@ -39,6 +40,14 @@ class TestPipelineObservabilityConfig:
monkeypatch.setenv("MEMORY_DATA_DIR", str(tmp_path / "data"))
assert resolve_pipeline_log_dir() == str(tmp_path / "data" / "logs" / "pipeline")
+ def test_log_enabled_default(self, monkeypatch):
+ monkeypatch.delenv("MEMORY_PIPELINE_LOG_ENABLED", raising=False)
+ assert is_pipeline_log_enabled() is True
+
+ def test_log_disabled(self, monkeypatch):
+ monkeypatch.setenv("MEMORY_PIPELINE_LOG_ENABLED", "false")
+ assert is_pipeline_log_enabled() is False
+
def test_trace_enabled_default(self, monkeypatch):
monkeypatch.delenv("MEMORY_PIPELINE_TRACE_ENABLED", raising=False)
assert is_pipeline_trace_enabled() is True
@@ -91,6 +100,98 @@ class TestObservabilityHookBehavior:
run(_test())
+ def test_log_flag_on_writes_jsonl(self, env_setup, monkeypatch):
+ """显式开启与默认一致:照常写 JSONL。"""
+ monkeypatch.setenv("MEMORY_PIPELINE_LOG_ENABLED", "true")
+ monkeypatch.setenv("MEMORY_PIPELINE_TRACE_ENABLED", "false")
+
+ async def _test():
+ from datetime import date
+ from hy_memory.utils.pipeline_observability import (
+ drain_pipeline_log_tasks,
+ install_pipeline_observability,
+ )
+
+ config = MemoryConfig.from_dict({"cache": {"backend": "sqlite"}})
+ cache = SqliteCache(config)
+ await cache.initialize()
+ install_pipeline_observability(cache, log_label="test")
+ await cache.store_pipeline_log(
+ request_id="req-on", user_id="u1", agent_id="a1", step="S1_EMBED",
+ )
+ await drain_pipeline_log_tasks()
+
+ log_file = Path(env_setup) / "default" / f"{date.today().isoformat()}.log"
+ assert json.loads(log_file.read_text(encoding="utf-8").strip())["step"] == "S1_EMBED"
+ await cache.close()
+
+ run(_test())
+
+ def test_log_off_trace_off_is_noop(self, env_setup, monkeypatch):
+ """两者都关:不包装、不写文件、不写库,store_pipeline_log 直接返回 True。"""
+ monkeypatch.setenv("MEMORY_PIPELINE_LOG_ENABLED", "false")
+ monkeypatch.setenv("MEMORY_PIPELINE_TRACE_ENABLED", "false")
+
+ async def _test():
+ from hy_memory.utils.pipeline_observability import (
+ _noop_store_pipeline_log,
+ drain_pipeline_log_tasks,
+ install_pipeline_observability,
+ )
+
+ config = MemoryConfig.from_dict({"cache": {"backend": "sqlite"}})
+ cache = SqliteCache(config)
+ await cache.initialize()
+ original_store = cache.store_pipeline_log
+ install_pipeline_observability(cache, log_label="test")
+ assert cache.store_pipeline_log is _noop_store_pipeline_log
+
+ ok = await cache.store_pipeline_log(
+ request_id="req-off", user_id="ns__u1", agent_id="a1",
+ step="S1_EMBED", prompt="p", response="r",
+ )
+ await drain_pipeline_log_tasks()
+
+ assert ok is True
+ assert not Path(env_setup).exists()
+ # 原始 store 仍能写库,说明表本身可用;空操作确实没写
+ assert await cache.get_pipeline_logs(request_id="req-off") == []
+ await original_store(
+ request_id="req-probe", user_id="u1", agent_id="a1",
+ step="PROBE", prompt="", response="",
+ )
+ assert len(await cache.get_pipeline_logs(request_id="req-probe")) == 1
+ await cache.close()
+
+ run(_test())
+
+ def test_log_off_trace_on_writes_db_only(self, env_setup, monkeypatch):
+ """只关 Log:不写 JSONL,Trace 照常落库。"""
+ monkeypatch.setenv("MEMORY_PIPELINE_LOG_ENABLED", "false")
+ monkeypatch.setenv("MEMORY_PIPELINE_TRACE_ENABLED", "true")
+
+ async def _test():
+ from hy_memory.utils.pipeline_observability import (
+ drain_pipeline_log_tasks,
+ install_pipeline_observability,
+ )
+
+ config = MemoryConfig.from_dict({"cache": {"backend": "sqlite"}})
+ cache = SqliteCache(config)
+ await cache.initialize()
+ install_pipeline_observability(cache, log_label="test")
+ await cache.store_pipeline_log(
+ request_id="req-db", user_id="u1", agent_id="a1", step="S1_EMBED",
+ )
+ await drain_pipeline_log_tasks()
+
+ assert not Path(env_setup).exists()
+ logs = await cache.get_pipeline_logs(request_id="req-db")
+ assert [row["step"] for row in logs] == ["S1_EMBED"]
+ await cache.close()
+
+ run(_test())
+
def test_store_returns_before_slow_persist(self, env_setup, monkeypatch):
"""慢 DB / 慢磁盘不得堵住 await store_pipeline_log。"""
monkeypatch.setenv("MEMORY_PIPELINE_TRACE_ENABLED", "true")