Skip to content
Python

fix: stop authority-invalid HY retries (#78)

feitianxiang0afe787c95b6
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 816967e..a58a85a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -20,6 +20,14 @@ Hy Memory and MemHub are versioned and released independently.
or governed and visibility data.
- Serialized each SDK SQLite store's shared connection lifecycle so concurrent
history/cache operations cannot race with `close()` and crash the process.
+- Scoped Coding reconciliation targets to the current HY authority,
+ conversation, and workspace, preventing near-duplicate sessions from
+ mutating an experience or working fact owned by another evidence context.
+- Kept post-write authority verification failures available for read-only
+ reconciliation while preventing automatic or generic confirmed retries from
+ invoking the model again. Automatic reconciliation skips those sticky rows
+ before applying its batch limit, and linked durable jobs exclusively own
+ retry scheduling for their memory tasks.
- Clarified that `add(metadata=...)` carries legacy SDK processing options,
while persistent caller business context belongs in `meta`.
- Added an opt-in `get(..., include_raw=True)` path for reading `L1_RAW`
diff --git a/hy_memory/coding/fact_reconciler.py b/hy_memory/coding/fact_reconciler.py
index 571bb28..91da943 100644
--- a/hy_memory/coding/fact_reconciler.py
+++ b/hy_memory/coding/fact_reconciler.py
@@ -466,7 +466,13 @@ class WorkingFactReconciler:
return [], []
candidates = await self._retrieve_candidates(
- drafts, user_id=user_id, source=source,
+ drafts,
+ user_id=user_id,
+ agent_id=agent_id,
+ session_id=session_id,
+ workspace_id=workspace_id,
+ branch=branch,
+ source=source,
)
try:
@@ -499,7 +505,15 @@ class WorkingFactReconciler:
# ------------------------------------------------------------
async def _retrieve_candidates(
- self, drafts: List[WorkingFactDraft], *, user_id: str, source: str
+ self,
+ drafts: List[WorkingFactDraft],
+ *,
+ user_id: str,
+ agent_id: str,
+ session_id: Optional[str],
+ workspace_id: Optional[str],
+ branch: Optional[str],
+ source: str,
) -> List[List[WorkingFact]]:
"""每条 draft 用 statement 召回同 user 的 top-N active 事实。
@@ -512,6 +526,10 @@ class WorkingFactReconciler:
关掉时整份召回原样交给 LLM。适用于 subject 不是稳定实体名的数据集(自由文本、
位置标签),那里精确字符串相等会把同实体判成不同主体,反而拦掉真实更新。
"""
+ # Empty/legacy session metadata remains readable, but cannot prove
+ # conversation authority for a destructive SUPERSEDE.
+ if not session_id:
+ return [[] for _ in drafts]
try:
embeddings = await self.embed_service.embed_batch(
[d.statement for d in drafts]
@@ -525,6 +543,10 @@ class WorkingFactReconciler:
try:
hits = await self.store.search_facts(
emb, user_id=user_id, top=self.candidates_per_draft,
+ agent_id=agent_id,
+ session_id=session_id,
+ workspace_id=workspace_id,
+ branch=branch,
# 写入侧同样接词面通道:候选选错了 LLM 就没有机会判对。这里不传
# min_score——写入侧要的是"有哪些可能的前身",让 LLM 看更宽的名单,
# 阈值过滤是读取侧的事。
@@ -794,6 +816,15 @@ class WorkingFactReconciler:
old = await self.store.get_fact(old_id, user_id=user_id)
if old is None:
continue
+ if (
+ old.agent_id != agent_id
+ or old.session_id != session_id
+ or old.workspace_id != workspace_id
+ ):
+ logger.warning(
+ f"[fact-reconcile] refused cross-authority SUPERSEDE: {old.fact_id}"
+ )
+ continue
# 闸门在候选阶段已经拦过一道,这里再拦一次:候选是按 statement 召回的,
# 而 LLM 只能覆盖候选名单里的 id,理论上到不了这儿。真到了就说明前面
# 哪一环漏了,宁可让这次覆盖不生效——多留一条旧事实是可恢复的,删掉
diff --git a/hy_memory/coding/reconciler.py b/hy_memory/coding/reconciler.py
index 55deb9f..ed36dd6 100644
--- a/hy_memory/coding/reconciler.py
+++ b/hy_memory/coding/reconciler.py
@@ -240,7 +240,7 @@ class CodingMemoryReconciler:
)
# 3. 校验 + 执行
- executed = await self._execute(ops, drafts)
+ executed = await self._execute(ops, drafts, candidates_per_draft)
logger.info(
f"[coding-reconcile] drafts={len(drafts)} ops={len(executed)} "
+ ", ".join(f"{a}={sum(1 for o in executed if o.action == a)}"
@@ -263,6 +263,12 @@ class CodingMemoryReconciler:
"""
result: List[List[CodingMemory]] = []
for d in drafts:
+ # A coding mutation must be attributable to one conversation.
+ # Empty/legacy session metadata stays readable through ordinary
+ # search, but it cannot authorize UPDATE/DELETE.
+ if not d.session_id:
+ result.append([])
+ continue
try:
# task 为主入口,search_keys 为附加入口(去重、去空)
queries = [d.task] + [k for k in (d.search_keys or []) if k and k != d.task]
@@ -274,6 +280,8 @@ class CodingMemoryReconciler:
hits = await self.store.search_by_query_embedding(
emb,
user_id=d.user_id,
+ agent_id=d.agent_id,
+ session_id=d.session_id,
workspace_id=d.workspace_id,
branch=d.branch,
top=self.candidates_per_draft * 4,
@@ -415,6 +423,7 @@ class CodingMemoryReconciler:
self,
ops: List[ReconcileOp],
drafts: List[CodingMemoryDraft],
+ candidates_per_draft: List[List[CodingMemory]],
) -> List[ReconcileOp]:
"""
校验 + 执行 ops。返回成功执行的 ops(filter 掉无效 op)。
@@ -454,6 +463,11 @@ class CodingMemoryReconciler:
if not op.target_experience_id:
logger.warning(f"[coding-reconcile] drop UPDATE missing target: {op.to_dict()}")
continue
+ if not self._target_was_offered(op, candidates_per_draft):
+ logger.warning(
+ f"[coding-reconcile] drop UPDATE outside authority scope: {op.to_dict()}"
+ )
+ continue
if op.draft_idx in consumed:
logger.warning(f"[coding-reconcile] drop UPDATE on consumed draft: {op.to_dict()}")
continue
@@ -476,6 +490,11 @@ class CodingMemoryReconciler:
if not op.target_experience_id:
logger.warning(f"[coding-reconcile] drop DELETE missing target: {op.to_dict()}")
continue
+ if not self._target_was_offered(op, candidates_per_draft):
+ logger.warning(
+ f"[coding-reconcile] drop DELETE outside authority scope: {op.to_dict()}"
+ )
+ 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:
@@ -512,6 +531,19 @@ class CodingMemoryReconciler:
return executed
+ @staticmethod
+ def _target_was_offered(
+ op: ReconcileOp,
+ candidates_per_draft: List[List[CodingMemory]],
+ ) -> bool:
+ """Only mutate a target frozen into this draft's scoped candidate set."""
+ if op.draft_idx is None or not (0 <= op.draft_idx < len(candidates_per_draft)):
+ return False
+ return any(
+ candidate.experience_id == op.target_experience_id
+ for candidate in candidates_per_draft[op.draft_idx]
+ )
+
@staticmethod
def _infer_user_id(
op: ReconcileOp, drafts: List[CodingMemoryDraft]
diff --git a/hy_memory/coding/store.py b/hy_memory/coding/store.py
index 84a6ac6..9124601 100644
--- a/hy_memory/coding/store.py
+++ b/hy_memory/coding/store.py
@@ -529,10 +529,20 @@ class CodingMemoryStore:
"""覆盖式更新一条 coding memory。"""
# 拿旧 keys 长度,先删旧 VDB rows
prev = await self.get_by_id(memory.experience_id, user_id=memory.user_id)
- prev_key_count = (1 + len(prev.search_keys)) if prev else 0
+ if prev is None:
+ raise ValueError("coding_memory_update_target_missing")
+ if (
+ not prev.session_id
+ or not memory.session_id
+ or prev.agent_id != memory.agent_id
+ or prev.session_id != memory.session_id
+ or prev.workspace_id != memory.workspace_id
+ ):
+ raise ValueError("coding_memory_update_authority_mismatch")
+ prev_key_count = 1 + len(prev.search_keys)
memory.updated_at = datetime.utcnow()
- if memory.created_at is None and prev is not None:
+ if memory.created_at is None:
memory.created_at = prev.created_at
await _run_in_pool(self._upsert_sql_sync, memory)
# 删旧 VDB
@@ -671,6 +681,8 @@ class CodingMemoryStore:
query_embedding: List[float],
user_id: str,
*,
+ agent_id: Optional[str] = None,
+ session_id: Optional[str] = None,
workspace_id: Optional[str] = None,
branch: Optional[str] = None,
top: int = 40,
@@ -688,21 +700,28 @@ class CodingMemoryStore:
},
...
]
- workspace_id / branch 是作用域过滤,规则见 _scope_where:不传则纯语义召回
- (行为与加过滤前完全一致);传了则只保留 SQLite 里落在作用域内的经验,并按
- 作用域的选择率放大向量取数,避免"先取 top-N 再过滤"把召回吃掉。
+ agent_id / session_id 是写授权作用域,传入时精确匹配;workspace_id / branch
+ 的规则见 _scope_where。不传任何作用域则维持纯语义召回;传了则只保留 SQLite
+ 里落在作用域内的经验,并按选择率放大向量取数,避免"先取 top-N 再过滤"把
+ 召回吃掉。
"""
if self._vec is None:
return []
allowed: Optional[Set[str]] = None
- if workspace_id:
+ if agent_id or session_id or workspace_id:
allowed, total = await _run_in_pool(
- self._scoped_experience_ids_sync, user_id, workspace_id, branch
+ self._authority_scoped_experience_ids_sync,
+ user_id,
+ agent_id,
+ session_id,
+ workspace_id,
+ branch,
)
if not allowed:
logger.info(
f"[coding-store] no experience in scope: "
+ f"agent_id={agent_id!r} session_id={session_id!r} "
f"workspace_id={workspace_id!r} branch={branch!r} "
f"(user has {total}); skip vdb search"
)
@@ -778,6 +797,8 @@ class CodingMemoryStore:
query_embedding: List[float],
user_id: str,
*,
+ agent_id: Optional[str] = None,
+ session_id: Optional[str] = None,
workspace_id: Optional[str] = None,
branch: Optional[str] = None,
top: int = 5,
@@ -791,8 +812,9 @@ class CodingMemoryStore:
SUPERSEDE 时向量行已被删掉,理论上召不到 superseded;这里再按 SQLite 的
status 过一道,避免两边不一致时把过期结论放出去。
- workspace_id / branch 是作用域过滤,规则见 _scope_where,语义与经验层一致:
- 不传不过滤,传了按 SQLite 里的值筛,并按选择率放大向量取数。
+ agent_id / session_id 是写授权作用域,传入时精确匹配;workspace_id / branch
+ 的规则见 _scope_where。不传任何作用域则不过滤,传了按 SQLite 里的值筛,并
+ 按选择率放大向量取数。
向量库按 top 的 4 倍过采样:向量行和 SQLite 行不是一个事务里写的,中间挂掉
就会留下"向量还在、SQLite 没了"的孤儿,软删时删向量失败也会留下 superseded
@@ -809,13 +831,19 @@ class CodingMemoryStore:
return []
fetch = top * 4
- if workspace_id:
+ if agent_id or session_id or workspace_id:
scoped, total = await _run_in_pool(
- self._count_active_facts_sync, user_id, workspace_id, branch
+ self._count_active_facts_sync,
+ user_id,
+ agent_id,
+ session_id,
+ workspace_id,
+ branch,
)
if not scoped:
logger.info(
f"[coding-store] no active fact in scope: "
+ f"agent_id={agent_id!r} session_id={session_id!r} "
f"workspace_id={workspace_id!r} branch={branch!r} "
f"(user has {total}); skip fact vdb search"
)
@@ -852,6 +880,8 @@ class CodingMemoryStore:
alive = [
(f, scores[f.fact_id]) for f in facts
if f.status == "active"
+ and (not agent_id or f.agent_id == agent_id)
+ and (not session_id or f.session_id == session_id)
and _scope_matches(f.workspace_id, f.branch, workspace_id, branch)
]
kept = [(f, s) for f, s in alive if s >= min_score]
@@ -1050,14 +1080,25 @@ class CodingMemoryStore:
by_id = {r["experience_id"]: _row_to_memory(r) for r in rows}
return [by_id[eid] for eid in experience_ids if eid in by_id]
- def _scoped_experience_ids_sync(
- self, user_id: str, workspace_id: str, branch: Optional[str]
+ def _authority_scoped_experience_ids_sync(
+ self,
+ user_id: str,
+ agent_id: Optional[str],
+ session_id: Optional[str],
+ workspace_id: Optional[str],
+ branch: Optional[str],
) -> Tuple[Set[str], int]:
- """返回 (落在作用域内的 experience_id 集合, 该 user 的经验总数)。
+ """返回 (落在授权作用域内的 experience_id 集合, 该 user 的经验总数)。
一次查询同时拿到过滤结果和选择率分母:前者供向量命中做交集,后者定放大倍数。
"""
scope_sql, scope_params = _scope_where(workspace_id, branch)
+ if agent_id:
+ scope_sql = f"agent_id = ? AND ({scope_sql})"
+ scope_params = [agent_id, *scope_params]
+ if session_id:
+ scope_sql = f"session_id = ? AND ({scope_sql})"
+ scope_params = [session_id, *scope_params]
with self._lock:
assert self._conn is not None
cur = self._conn.execute(
@@ -1069,13 +1110,24 @@ class CodingMemoryStore:
return {r["experience_id"] for r in rows if r["in_scope"]}, len(rows)
def _count_active_facts_sync(
- self, user_id: str, workspace_id: str, branch: Optional[str]
+ self,
+ user_id: str,
+ agent_id: Optional[str],
+ session_id: Optional[str],
+ workspace_id: Optional[str],
+ branch: Optional[str],
) -> Tuple[int, int]:
"""返回 (作用域内 active 事实数, 该 user 的 active 事实总数)。
事实层的过滤在 get_facts 拿到对象之后用 _scope_matches 做,这里只要选择率。
"""
scope_sql, scope_params = _scope_where(workspace_id, branch)
+ if agent_id:
+ scope_sql = f"agent_id = ? AND ({scope_sql})"
+ scope_params = [agent_id, *scope_params]
+ if session_id:
+ scope_sql = f"session_id = ? AND ({scope_sql})"
+ scope_params = [session_id, *scope_params]
with self._lock:
assert self._conn is not None
row = self._conn.execute(
diff --git a/memhub/apps/core/src/one_memory/api.py b/memhub/apps/core/src/one_memory/api.py
index 4df647e..087a02a 100644
--- a/memhub/apps/core/src/one_memory/api.py
+++ b/memhub/apps/core/src/one_memory/api.py
@@ -185,7 +185,12 @@ from one_memory.memory_queue import (
resolve_extraction_state,
)
from one_memory.memory_server.config_state import ConfigStore
-from one_memory.memory_tasks import MemoryTask, MemoryTaskStatus, MemoryTaskStore
+from one_memory.memory_tasks import (
+ NON_RETRYABLE_POST_WRITE_CODES,
+ MemoryTask,
+ MemoryTaskStatus,
+ MemoryTaskStore,
+)
from one_memory.model_presets import seed_preset_profile
from one_memory.model_probe import ModelProber, ModelProbeResult
from one_memory.model_profiles import (
@@ -1082,8 +1087,14 @@ def create_app(
drain_budget = production_drain_budget()
async def reconcile_unknown_writes() -> None:
- await app.state.memory_processing_supervisor.reconcile_unknown_outputs()
- unknown = await asyncio.to_thread(memory_write_queue.unknown_jobs, limit=128)
+ await app.state.memory_processing_supervisor.reconcile_unknown_outputs(
+ exclude_error_codes=NON_RETRYABLE_POST_WRITE_CODES,
+ )
+ unknown = await asyncio.to_thread(
+ memory_write_queue.unknown_jobs,
+ limit=128,
+ exclude_error_codes=NON_RETRYABLE_POST_WRITE_CODES,
+ )
for job in unknown:
await asyncio.to_thread(
memory_write_queue.resolve_unknown_from_linked_output,
diff --git a/memhub/apps/core/src/one_memory/memory_processing.py b/memhub/apps/core/src/one_memory/memory_processing.py
index 6694ba8..8b69ac2 100644
--- a/memhub/apps/core/src/one_memory/memory_processing.py
+++ b/memhub/apps/core/src/one_memory/memory_processing.py
@@ -1522,14 +1522,24 @@ class MemoryProcessingSupervisor:
await self._refresh_read_bridge(completed[-1].profile_snapshot)
return tuple(completed)
- async def reconcile_unknown_outputs(self, *, limit: int = 128) -> int:
+ async def reconcile_unknown_outputs(
+ self,
+ *,
+ limit: int = 128,
+ exclude_error_codes: tuple[str, ...] = (),
+ ) -> int:
"""Publish HY outputs that can be proven by an unknown task's request id.
This inquiry is read-only on HY and never invokes the model. Rows with
no exact match remain unknown for the person's explicit retry choice.
"""
reconciled = 0
- for task in await in_the_background(self.tasks.unknown_tasks, limit=limit):
+ tasks = await in_the_background(
+ self.tasks.unknown_tasks,
+ limit=limit,
+ exclude_error_codes=exclude_error_codes,
+ )
+ for task in tasks:
runner = self.runner_factory()
bridge: MemoryBridgeProtocol | None = None
try:
diff --git a/memhub/apps/core/src/one_memory/memory_server/durable_queue.py b/memhub/apps/core/src/one_memory/memory_server/durable_queue.py
index f3e3817..554fa75 100644
--- a/memhub/apps/core/src/one_memory/memory_server/durable_queue.py
+++ b/memhub/apps/core/src/one_memory/memory_server/durable_queue.py
@@ -38,10 +38,11 @@ from one_memory.memory_server.migrations import memory_write_jobs_sqlite_schema
from one_memory.memory_server.queue import build_reclaim_sqlite_statements
from one_memory.memory_server.registry import WriteRecord
from one_memory.memory_tasks import (
- POLICY_STOPPED_CODES as _TASK_POLICY_STOPPED_CODES,
+ NON_RETRYABLE_POST_WRITE_CODES,
+ MemoryTaskStatus,
)
from one_memory.memory_tasks import (
- MemoryTaskStatus,
+ POLICY_STOPPED_CODES as _TASK_POLICY_STOPPED_CODES,
)
from one_memory.service_levels import ServiceLevel, service_level_context
@@ -1542,9 +1543,13 @@ class DurableWriteQueue:
connection,
):
row = connection.execute(
- "SELECT state FROM memory_write_jobs WHERE job_id=?", (job_id,)
+ "SELECT state,last_error FROM memory_write_jobs WHERE job_id=?", (job_id,)
).fetchone()
- if row is None or str(row["state"]) != UNKNOWN:
+ if (
+ row is None
+ or str(row["state"]) != UNKNOWN
+ or str(row["last_error"]) in NON_RETRYABLE_POST_WRITE_CODES
+ ):
return 0
connection.execute(
"""
@@ -1701,8 +1706,15 @@ class DurableWriteQueue:
rows = connection.execute(
"SELECT job_id FROM memory_write_jobs "
"WHERE state=? AND attempts=1 AND attempts < max_attempts "
+ f"AND COALESCE(last_error, '') NOT IN "
+ f"({','.join('?' for _ in NON_RETRYABLE_POST_WRITE_CODES)}) "
"AND updated_at <= ? ORDER BY updated_at, job_id LIMIT ?",
- (UNKNOWN, older_than.isoformat(), limit),
+ (
+ UNKNOWN,
+ *NON_RETRYABLE_POST_WRITE_CODES,
+ older_than.isoformat(),
+ limit,
+ ),
).fetchall()
job_ids = tuple(str(row["job_id"]) for row in rows)
if not job_ids:
@@ -1766,6 +1778,7 @@ class DurableWriteQueue:
*,
limit: int = 128,
after_cursor: tuple[str, str] | None = None,
+ exclude_error_codes: tuple[str, ...] = (),
) -> tuple[UnknownWriteJob, ...]:
"""List unknown rows that still need an inquiry, in stable order.
@@ -1782,6 +1795,9 @@ class DurableWriteQueue:
"""
if type(limit) is not int or limit < 1:
raise ValueError("limit must be positive")
+ excluded = tuple(dict.fromkeys(exclude_error_codes))
+ if not all(isinstance(code, str) and code for code in excluded):
+ raise ValueError("exclude_error_codes must contain non-empty strings")
cursor_clause = ""
params: tuple[Any, ...] = ()
if after_cursor is not None:
@@ -1794,14 +1810,20 @@ class DurableWriteQueue:
updated_at, job_id = after_cursor
cursor_clause = "AND (updated_at, job_id) > (?, ?)"
params = (updated_at, job_id)
+ if excluded:
+ placeholders = ",".join("?" for _ in excluded)
+ excluded_clause = f"AND COALESCE(last_error, '') NOT IN ({placeholders})"
+ else:
+ excluded_clause = ""
with main_database(self.database_path).read(row_factory=sqlite3.Row) as connection:
rows = connection.execute(
"SELECT job_id, idempotency_key, created_at, updated_at, last_error "
"FROM memory_write_jobs "
"WHERE state=? "
f"{cursor_clause} "
+ f"{excluded_clause} "
"ORDER BY updated_at, job_id LIMIT ?",
- (UNKNOWN, *params, limit),
+ (UNKNOWN, *params, *excluded, limit),
).fetchall()
return tuple(
UnknownWriteJob(
diff --git a/memhub/apps/core/src/one_memory/memory_tasks.py b/memhub/apps/core/src/one_memory/memory_tasks.py
index c187cbc..5f48c26 100644
--- a/memhub/apps/core/src/one_memory/memory_tasks.py
+++ b/memhub/apps/core/src/one_memory/memory_tasks.py
@@ -67,6 +67,12 @@ POLICY_STOPPED_CODES = (
"hy_memory_evidence_changed",
)
+#: HY completed a write, but Core could not prove that the selected mutation
+#: target belonged to this task's frozen authority. Reconciliation may inspect
+#: HY by request id, but neither automatic nor user-confirmed generic retry may
+#: invoke the model again for these codes.
+NON_RETRYABLE_POST_WRITE_CODES = ("hy_memory_write_verification_authority_invalid",)
+
class MemoryTask(BaseModel):
model_config = ConfigDict(frozen=True, extra="forbid")
@@ -116,6 +122,24 @@ PROFILE_STOP_CODES = (
ACTIVE_WINDOW_DEFER_LIMIT = 2048
+def _task_only_unknown_clause(connection: sqlite3.Connection) -> str:
+ """Exclude tasks whose Evidence is already owned by the durable queue."""
+ linked_table = connection.execute(
+ "SELECT 1 FROM sqlite_master WHERE type='table' AND name='memory_write_job_evidence'"
+ ).fetchone()
+ if linked_table is None:
+ return ""
+ return """
+ AND NOT EXISTS (
+ SELECT 1
+ FROM memory_task_inputs AS inputs, json_each(inputs.refs_json) AS ref
+ JOIN memory_write_job_evidence AS linked
+ ON linked.evidence_id=json_extract(ref.value, '$.evidence_id')
+ WHERE inputs.task_id=memory_tasks.task_id
+ )
+ """
+
+
@dataclass(frozen=True, slots=True)
class ActiveMemoryTask:
"""One task plus only the evidence fields the scheduler needs."""
@@ -1314,7 +1338,7 @@ class MemoryTaskStore:
live_clause = f"task.task_id IN ({live_placeholders})" if live_ids else "0"
not_live_clause = f"task.task_id NOT IN ({live_placeholders})" if live_ids else "1"
excluded_clause = f"task.task_id NOT IN ({excluded_placeholders})" if excluded else "1"
- common = f"""
+ common_base = f"""
task.status IN (?,?,?,?)
AND coalesce(task.last_error_code, '') NOT IN (
'hy_memory_input_exceeds_window', 'model_content_outcome_unknown'
@@ -1333,7 +1357,33 @@ class MemoryTaskStore:
"""
moment = "coalesce(evidence.created_at, evidence.imported_at)"
+ def common_for(connection: sqlite3.Connection) -> str:
+ has_durable_queue = connection.execute(
+ "SELECT COUNT(*) FROM sqlite_master WHERE type='table' "
+ "AND name IN ('memory_write_jobs','memory_write_job_evidence')"
+ ).fetchone()[0]
+ if int(has_durable_queue) != 2:
+ return common_base
+ return (
+ common_base
+ + """
+ AND NOT EXISTS (
+ SELECT 1
+ FROM memory_task_inputs AS inputs, json_each(inputs.refs_json) AS ref
+ JOIN memory_write_job_evidence AS linked
+ ON linked.evidence_id=json_extract(ref.value, '$.evidence_id')
+ JOIN memory_write_jobs AS job ON job.job_id=linked.job_id
+ WHERE inputs.task_id=task.task_id
+ AND job.state IN (
+ 'pending', 'running', 'unknown',
+ 'waiting_for_permission', 'waiting_for_model'
+ )
+ )
+ """
+ )
+
def run(connection: sqlite3.Connection, *, defer: bool) -> list[sqlite3.Row]:
+ common = common_for(connection)
in_window = (
"1"
if extraction_since is None
@@ -1430,6 +1480,7 @@ class MemoryTaskStore:
def has_defer_candidate(connection: sqlite3.Connection) -> bool:
if extraction_since is None:
return False
+ common = common_for(connection)
row = connection.execute(
f"""
SELECT 1
@@ -2146,6 +2197,7 @@ class MemoryTaskStore:
*,
limit: int = 128,
after_cursor: tuple[str, str] | None = None,
+ exclude_error_codes: tuple[str, ...] = (),
) -> tuple[MemoryTask, ...]:
"""List `unknown` tasks that still need an external inquiry.
@@ -2160,6 +2212,9 @@ class MemoryTaskStore:
"""
if type(limit) is not int or limit < 1:
raise ValueError("limit must be positive")
+ excluded = tuple(dict.fromkeys(exclude_error_codes))
+ if not all(isinstance(code, str) and code for code in excluded):
+ raise ValueError("exclude_error_codes must contain non-empty strings")
if after_cursor is not None:
if (
not isinstance(after_cursor, tuple)
@@ -2173,13 +2228,19 @@ class MemoryTaskStore:
else:
cursor_clause = ""
params = ()
+ if excluded:
+ placeholders = ",".join("?" for _ in excluded)
+ excluded_clause = f"AND COALESCE(last_error_code, '') NOT IN ({placeholders})"
+ else:
+ excluded_clause = ""
with self._connect() as connection:
rows = connection.execute(
"SELECT * FROM memory_tasks "
"WHERE status=? "
f"{cursor_clause} "
+ f"{excluded_clause} "
"ORDER BY updated_at, task_id LIMIT ?",
- (MemoryTaskStatus.UNKNOWN, *params, limit),
+ (MemoryTaskStatus.UNKNOWN, *params, *excluded, limit),
).fetchall()
return tuple(self._to_task(row) for row in rows)
@@ -2211,20 +2272,26 @@ class MemoryTaskStore:
"""
now = datetime.now(UTC).isoformat()
with self._connect(writing=True) as connection:
+ task_only = _task_only_unknown_clause(connection)
+ blocked = ",".join("?" for _ in NON_RETRYABLE_POST_WRITE_CODES)
changed = connection.execute(
- """
+ f"""
UPDATE memory_tasks
SET status=?, runner_token=NULL, attempts=0,
last_error_code='model_content_manual_retry_requested', updated_at=?
WHERE task_id IN (
SELECT task_id FROM memory_tasks
- WHERE status=? ORDER BY updated_at, task_id LIMIT ?
+ WHERE status=?
+ AND COALESCE(last_error_code, '') NOT IN ({blocked})
+ {task_only}
+ ORDER BY updated_at, task_id LIMIT ?
)
""",
(
MemoryTaskStatus.PENDING,
now,
MemoryTaskStatus.UNKNOWN,
+ *NON_RETRYABLE_POST_WRITE_CODES,
limit,
),
)
@@ -2246,14 +2313,18 @@ class MemoryTaskStore:
raise ValueError("limit must be positive")
now = datetime.now(UTC).isoformat()
with self._connect(writing=True) as connection:
+ task_only = _task_only_unknown_clause(connection)
+ blocked = ",".join("?" for _ in NON_RETRYABLE_POST_WRITE_CODES)
changed = connection.execute(
- """
+ f"""
UPDATE memory_tasks
SET status=?, runner_token=NULL,
last_error_code='model_content_unknown_auto_retry', updated_at=?
WHERE task_id IN (
SELECT task_id FROM memory_tasks
WHERE status=? AND attempts=1 AND updated_at <= ?
+ AND COALESCE(last_error_code, '') NOT IN ({blocked})
+ {task_only}
ORDER BY updated_at, task_id LIMIT ?
)
""",
@@ -2262,6 +2333,7 @@ class MemoryTaskStore:
now,
MemoryTaskStatus.UNKNOWN,
older_than.isoformat(),
+ *NON_RETRYABLE_POST_WRITE_CODES,
limit,
),
)
diff --git a/memhub/apps/core/tests/test_memory_processing.py b/memhub/apps/core/tests/test_memory_processing.py
index 4d035e3..388ad29 100644
--- a/memhub/apps/core/tests/test_memory_processing.py
+++ b/memhub/apps/core/tests/test_memory_processing.py
@@ -4,7 +4,7 @@ import logging
import sqlite3
import threading
import time
-from datetime import UTC, datetime
+from datetime import UTC, datetime, timedelta
import pytest
@@ -56,7 +56,12 @@ from one_memory.memory_processing import (
)
from one_memory.memory_queue import classify
from one_memory.memory_server.config_state import ConfigStore
-from one_memory.memory_tasks import MemoryTaskKind, MemoryTaskStatus, MemoryTaskStore
+from one_memory.memory_tasks import (
+ NON_RETRYABLE_POST_WRITE_CODES,
+ MemoryTaskKind,
+ MemoryTaskStatus,
+ MemoryTaskStore,
+)
from one_memory.model_profiles import (
ModelCapabilities,
ModelProfileInput,
@@ -2613,6 +2618,123 @@ def test_an_unknown_task_without_inputs_does_not_end_the_reconcile_pass(tmp_path
assert [memory.memory_id for memory in governance.list(user_id="local")] == ["hy-recovered"]
+def test_sticky_authority_unknowns_do_not_starve_ordinary_reconciliation(tmp_path) -> None:
+ stores = _setup(tmp_path)
+ evidence, profiles, tasks, governance, secrets, profile = stores
+ record = _put(
+ evidence,
+ message_id="fair-unknown",
+ role="user",
+ written_by=WrittenBy.PERSON,
+ content="ordinary unknown remains reconcilable",
+ )
+ sticky = [
+ tasks.create(
+ request_id=f"sticky-authority-{index}",
+ user_id=record.user_id,
+ kind=MemoryTaskKind.EXTRACT,
+ input_ref=record.evidence_id,
+ profile=profile,
+ input_records=(record,),
+ )
+ for index in range(129)
+ ]
+ ordinary = tasks.create(
+ request_id="ordinary-unknown-after-sticky",
+ user_id=record.user_id,
+ kind=MemoryTaskKind.EXTRACT,
+ input_ref=record.evidence_id,
+ profile=profile,
+ input_records=(record,),
+ )
+ anchor = datetime(2026, 1, 1, tzinfo=UTC)
+ with sqlite3.connect(tasks.database_path) as connection, connection:
+ connection.executescript(
+ """
+ CREATE TABLE source_grants (
+ user_id TEXT NOT NULL, source_id TEXT NOT NULL,
+ root_path TEXT NOT NULL, candidate_kind TEXT NOT NULL,
+ granted_at TEXT NOT NULL, revoked_at TEXT,
+ PRIMARY KEY (user_id, source_id)
+ );
+ """
+ )
+ connection.execute(
+ "INSERT INTO source_grants VALUES (?,?,?,?,?,NULL)",
+ (
+ record.user_id,
+ record.source_id,
+ "/authorized",
+ "default",
+ datetime.now(UTC).isoformat(),
+ ),
+ )
+ for index, task in enumerate(sticky):
+ connection.execute(
+ "UPDATE memory_tasks SET status='unknown',last_error_code=?,updated_at=? "
+ "WHERE task_id=?",
+ (
+ "hy_memory_write_verification_authority_invalid",
+ (anchor + timedelta(seconds=index)).isoformat(),
+ task.task_id,
+ ),
+ )
+ connection.execute(
+ "UPDATE memory_tasks SET status='unknown',last_error_code=?,updated_at=? "
+ "WHERE task_id=?",
+ (
+ "model_content_outcome_unknown",
+ (anchor + timedelta(minutes=3)).isoformat(),
+ ordinary.task_id,
+ ),
+ )
+
+ class InquiryOnlyBridge(FakeBridge):
+ def __init__(self) -> None:
+ super().__init__(
+ outputs=(
+ HyMemoryOutput(
+ memory_id="ordinary-recovered",
+ content="ordinary unknown remains reconcilable",
+ layer="L2_FACT",
+ owner="user",
+ evidence_ids=(record.evidence_id,),
+ ),
+ )
+ )
+ self.inquiries: list[str] = []
+
+ async def outputs_for_request(self, **kwargs) -> tuple[HyMemoryOutput, ...]:
+ self.inquiries.append(str(kwargs["request_id"]))
+ return self.outputs or ()
+
+ bridge = InquiryOnlyBridge()
+ supervisor = MemoryProcessingSupervisor(
+ tasks=tasks,
+ profiles=profiles,
+ secrets=secrets,
+ evidence=evidence,
+ governance=governance,
+ data_dir=tmp_path,
+ runner_factory=lambda: _runner(tmp_path, stores, FakeBridge()),
+ bridge_factory=lambda _profile, _secret, _data_dir: bridge,
+ )
+
+ assert (
+ asyncio.run(
+ supervisor.reconcile_unknown_outputs(
+ limit=128,
+ exclude_error_codes=NON_RETRYABLE_POST_WRITE_CODES,
+ )
+ )
+ == 1
+ )
+ assert bridge.inquiries == ["ordinary-unknown-after-sticky"]
+ assert bridge.requests == []
+ assert tasks.require(ordinary.task_id).status is MemoryTaskStatus.COMPLETED
+ assert all(tasks.require(task.task_id).status is MemoryTaskStatus.UNKNOWN for task in sticky)
+
+
def test_two_workspaces_with_one_conversation_id_prepare_apart(tmp_path) -> None:
"""Cursor can reuse a conversation id across projects.
@@ -3441,6 +3563,58 @@ def test_digest_scopes_separate_applications_and_dates(tmp_path) -> None:
assert len({_hy_agent_id((record,)) for record in records}) == 3
+def test_workspace_requests_carry_conversation_authority_beyond_agent_scope(tmp_path) -> None:
+ """Same-day workspace scopes collide by design; session_id must separate writes."""
+ evidence, _profiles, tasks, _governance, _secrets, profile = _setup(tmp_path)
+ first = _put(
+ evidence,
+ message_id="conversation-a",
+ role="user",
+ written_by=WrittenBy.PERSON,
+ content="same workspace, first conversation",
+ conversation_id="conversation-a",
+ workspace="repo-a",
+ created_at=datetime(2026, 10, 18, 8, tzinfo=UTC),
+ )
+ second = _put(
+ evidence,
+ message_id="conversation-b",
+ role="user",
+ written_by=WrittenBy.PERSON,
+ content="same workspace, second conversation",
+ conversation_id="conversation-b",
+ workspace="repo-a",
+ created_at=datetime(2026, 10, 18, 9, tzinfo=UTC),
+ )
+ next_day = _put(
+ evidence,
+ message_id="conversation-a-next-day",
+ role="user",
+ written_by=WrittenBy.PERSON,
+ content="same conversation on the next day",
+ conversation_id="conversation-a",
+ workspace="repo-a",
+ created_at=datetime(2026, 10, 19, 8, tzinfo=UTC),
+ )
+
+ requests = []
+ for record in (first, second, next_day):
+ task = tasks.create(
+ request_id=f"authority:{record.evidence_id}",
+ user_id=record.user_id,
+ kind=MemoryTaskKind.EXTRACT,
+ input_ref=record.evidence_id,
+ profile=profile,
+ input_records=(record,),
+ )
+ requests.append(MemoryTaskRunner._request(task, (record,)))
+
+ assert requests[0].agent_id == requests[1].agent_id
+ assert requests[0].session_id == "conversation-a"
+ assert requests[1].session_id == "conversation-b"
+ assert requests[2].agent_id != requests[0].agent_id
+
+
def test_cancelled_multi_source_lock_acquisition_releases_earlier_source(tmp_path) -> None:
evidence, profiles, tasks, governance, secrets, _profile = _setup(tmp_path)
first = _put(
diff --git a/memhub/apps/core/tests/test_memory_server_durable_queue.py b/memhub/apps/core/tests/test_memory_server_durable_queue.py
index 775d0a3..083d13a 100644
--- a/memhub/apps/core/tests/test_memory_server_durable_queue.py
+++ b/memhub/apps/core/tests/test_memory_server_durable_queue.py
@@ -3516,6 +3516,41 @@ def test_unknown_jobs_does_not_resolve_or_make_a_row_claimable(tmp_path) -> None
assert queue.resolve_unknown(found[0].job_id, found=False, detail="not in HY") == DEAD
+def test_unknown_jobs_can_exclude_sticky_authority_failures_before_limit(tmp_path) -> None:
+ path = tmp_path / "one-memory.sqlite3"
+ queue = DurableWriteQueue(path)
+ sticky = [
+ queue.submit(_request(key=f"sticky-{index}", evidence=(f"sticky-e{index}",)))
+ for index in range(129)
+ ]
+ ordinary = queue.submit(_request(key="ordinary", evidence=("ordinary-e",)))
+ anchor = datetime(2026, 1, 1, tzinfo=UTC)
+ with sqlite3.connect(path) as connection, connection:
+ for index, record in enumerate(sticky):
+ connection.execute(
+ "UPDATE memory_write_jobs SET state='unknown',attempts=1,hy_invoked=1,"
+ "last_error=?,updated_at=? WHERE job_id=?",
+ (
+ "hy_memory_write_verification_authority_invalid",
+ (anchor + timedelta(seconds=index)).isoformat(),
+ record.job_id,
+ ),
+ )
+ connection.execute(
+ "UPDATE memory_write_jobs SET state='unknown',attempts=1,hy_invoked=1,"
+ "last_error='model_content_outcome_unknown',updated_at=? WHERE job_id=?",
+ ((anchor + timedelta(minutes=3)).isoformat(), ordinary.job_id),
+ )
+
+ found = queue.unknown_jobs(
+ limit=128,
+ exclude_error_codes=("hy_memory_write_verification_authority_invalid",),
+ )
+
+ assert [job.job_id for job in found] == [ordinary.job_id]
+ assert all(queue.get(record.request_id).state == UNKNOWN for record in sticky)
+
+
def test_unknown_jobs_tolerates_a_row_resolved_between_pages(tmp_path) -> None:
"""Discovery is read-only and may overlap an inquiry from another worker.
@@ -4896,15 +4931,16 @@ def test_a_failure_after_the_call_still_parks_as_unknown(tmp_path) -> None:
record = queue.submit(_request(key="after-call", source="opencode"))
claimer = DurableWriteDrain(queue, execute=_never_execute, owner="after-call-owner")
assert claimer.claim(limit=1) == (record.job_id,)
+ recorder = _Recorder(
+ error=HyMemoryBridgeError("hy_memory_write_verification_authority_invalid"),
+ invoke_hy=True,
+ )
asyncio.run(
execute_job(
record.job_id,
queue=queue,
- supervisor=_Recorder(
- error=HyMemoryBridgeError("hy_memory_write_verification_authority_invalid"),
- invoke_hy=True,
- ),
+ supervisor=recorder,
evidence=_EvidenceStore({"e1"}),
owner="after-call-owner",
)
@@ -4918,6 +4954,16 @@ def test_a_failure_after_the_call_still_parks_as_unknown(tmp_path) -> None:
assert state == UNKNOWN
assert invoked == 1
+ assert len(recorder.seen) == 1
+ assert (
+ queue.retry_first_unknown_after_reconcile(
+ older_than=datetime.now(UTC) + timedelta(minutes=1)
+ )
+ == 0
+ )
+ assert queue.retry_unknown_confirmed(record.job_id) == 0
+ assert DurableWriteDrain(queue, execute=_never_execute).claim(limit=1) == ()
+ assert len(recorder.seen) == 1
def test_event_time_not_enqueue_order_drives_the_window(
diff --git a/memhub/apps/core/tests/test_memory_tasks.py b/memhub/apps/core/tests/test_memory_tasks.py
index 593f839..1f717a1 100644
--- a/memhub/apps/core/tests/test_memory_tasks.py
+++ b/memhub/apps/core/tests/test_memory_tasks.py
@@ -1113,6 +1113,109 @@ def test_task_only_unknown_is_automatically_retried_only_once(tmp_path) -> None:
assert store.require(task.task_id).status is MemoryTaskStatus.UNKNOWN
+def test_authority_invalid_task_is_never_reinvoked(tmp_path) -> None:
+ store, profile = _profile_and_tasks(tmp_path)
+ task = store.create(
+ request_id="authority-invalid",
+ user_id="local",
+ kind=MemoryTaskKind.EXTRACT,
+ input_ref="authority-evidence",
+ profile=profile,
+ )
+ with sqlite3.connect(store.database_path) as connection, connection:
+ connection.execute(
+ "UPDATE memory_tasks SET status=?,attempts=1,last_error_code=?,updated_at=? "
+ "WHERE task_id=?",
+ (
+ MemoryTaskStatus.UNKNOWN,
+ "hy_memory_write_verification_authority_invalid",
+ "2026-01-01T00:00:00+00:00",
+ task.task_id,
+ ),
+ )
+
+ cutoff = datetime(2026, 1, 1, 0, 5, tzinfo=UTC)
+ assert store.retry_first_unknown_after_reconcile(older_than=cutoff) == 0
+ assert store.retry_unknown_confirmed() == 0
+ retained = store.require(task.task_id)
+ assert retained.status is MemoryTaskStatus.UNKNOWN
+ assert retained.attempts == 1
+ assert retained.last_error_code == "hy_memory_write_verification_authority_invalid"
+
+
+def test_linked_unknown_is_retried_only_by_the_durable_job(tmp_path) -> None:
+ from one_memory.memory_server.contracts import BatchIdentity, WriteRequest
+ from one_memory.memory_server.durable_queue import DurableWriteQueue
+
+ store, profile = _profile_and_tasks(tmp_path)
+ evidence = EvidenceStore(store.database_path)
+ record = evidence.put(
+ EvidenceInput(
+ source_id="cursor",
+ conversation_id="linked-conversation",
+ message_id="linked-message",
+ role="user",
+ written_by=WrittenBy.PERSON,
+ verbatim="linked unknown",
+ created_at=datetime(2026, 1, 1, tzinfo=UTC),
+ origin_meta={EvidenceOrigin.FILE: OriginMetadata()},
+ )
+ ).record
+ task = store.create(
+ request_id="linked-task",
+ user_id="local",
+ kind=MemoryTaskKind.EXTRACT,
+ input_ref=record.evidence_id,
+ profile=profile,
+ input_records=(record,),
+ )
+ queue = DurableWriteQueue(store.database_path, evidence=evidence)
+ job = queue.submit(
+ WriteRequest(
+ internal_session_id="linked-session",
+ batch_identity=BatchIdentity(
+ internal_session_id="linked-session",
+ first_round=1,
+ last_round=1,
+ ),
+ evidence_ids=[record.evidence_id],
+ idempotency_key="linked-job",
+ source_id="cursor",
+ )
+ )
+ with sqlite3.connect(store.database_path) as connection, connection:
+ connection.execute(
+ "UPDATE memory_tasks SET status=?,attempts=1,last_error_code=?,updated_at=? "
+ "WHERE task_id=?",
+ (
+ MemoryTaskStatus.UNKNOWN,
+ "model_content_outcome_unknown",
+ "2026-01-01T00:00:00+00:00",
+ task.task_id,
+ ),
+ )
+ connection.execute(
+ "UPDATE memory_write_jobs SET state='unknown',attempts=1,hy_invoked=1,"
+ "last_error='model_content_outcome_unknown',updated_at=? WHERE job_id=?",
+ ("2026-01-01T00:00:00+00:00", job.job_id),
+ )
+
+ cutoff = datetime(2026, 1, 1, 0, 5, tzinfo=UTC)
+ assert store.retry_first_unknown_after_reconcile(older_than=cutoff) == 0
+ assert store.require(task.task_id).status is MemoryTaskStatus.UNKNOWN
+ assert queue.retry_first_unknown_after_reconcile(older_than=cutoff) == 1
+ assert store.require(task.task_id).status is MemoryTaskStatus.PENDING
+ assert queue.get(job.request_id).state == "pending"
+ assert (
+ store.active_window(
+ now=datetime(2026, 1, 2, tzinfo=UTC),
+ fresh_window=timedelta(days=1),
+ extraction_window=None,
+ )
+ == []
+ )
+
+
def test_orphan_recovery_preserves_active_running_tasks(tmp_path) -> None:
store, profile = _profile_and_tasks(tmp_path)
active = store.create(
diff --git a/tests/coding/test_fact_reconciler.py b/tests/coding/test_fact_reconciler.py
index 868f8eb..9e00b91 100644
--- a/tests/coding/test_fact_reconciler.py
+++ b/tests/coding/test_fact_reconciler.py
@@ -107,6 +107,7 @@ class TestSupersede:
async def _seed_old(self, store, *, derived=None):
old = WorkingFact(
fact_id="f_old", user_id="u1",
+ session_id="test-session",
statement=(
"用户要修复 CI 的 npm run build;检查 .github/workflows/ci.yml 后"
"定位到 Node 18 报 ERR_OSSL_EVP_UNSUPPORTED,尚未修改。"
@@ -129,7 +130,7 @@ class TestSupersede:
[_draft(
"用户继续修复同一 CI 构建;把 .github/workflows/ci.yml 升到 Node 20,"
"npm run build 已通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
new_id = facts[0].fact_id
@@ -152,7 +153,7 @@ class TestSupersede:
[_draft(
"用户继续修复同一 CI 构建;把 .github/workflows/ci.yml 升到 Node 20,"
"npm run build 已通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
new_id = facts[0].fact_id
@@ -184,7 +185,9 @@ class TestSupersede:
coding_store, mock_embed,
_llm([{"draft_idx": 0, "supersedes": [target or prev_id]}]),
)
- facts, _ = await rec.reconcile([_draft(stmt)], user_id="u1")
+ facts, _ = await rec.reconcile(
+ [_draft(stmt)], user_id="u1", session_id="test-session"
+ )
prev_id = facts[0].fact_id
lineage = await coding_store.get_fact_ancestors(prev_id, user_id="u1")
@@ -208,6 +211,7 @@ class TestSupersede:
"配置完成但尚未发布。"
)],
user_id="u1",
+ session_id="test-session",
)
prompt = llm.calls[0]["prompt"]
@@ -234,7 +238,9 @@ class TestSupersede:
coding_store, mock_embed, _llm([{"draft_idx": 0, "supersedes": ["f_old"]}]),
)
await rec.reconcile(
- [_draft("config 位于 /etc/app/config.yaml")], user_id="u1",
+ [_draft("config 位于 /etc/app/config.yaml")],
+ user_id="u1",
+ session_id="test-session",
)
# 拿旧说法原文去搜,只能落到新事实(靠两者本身相似),
@@ -256,6 +262,34 @@ class TestSupersede:
old = await coding_store.get_fact("f_old", user_id="u1")
assert old.status == "active"
+ async def test_near_duplicate_fact_cannot_cross_authority_scope(
+ self, coding_store, mock_embed
+ ):
+ await coding_store.insert_fact(WorkingFact(
+ fact_id="f_old",
+ user_id="u1",
+ agent_id="scope:2026-10-18",
+ session_id="conversation-a",
+ workspace_id="repo-a",
+ statement="CI build now passes after upgrading Node",
+ ))
+ llm = _llm([{"draft_idx": 0, "supersedes": ["f_old"]}])
+ rec = WorkingFactReconciler(coding_store, mock_embed, llm)
+
+ _, ops = await rec.reconcile(
+ [_draft("CI build now passes after upgrading Node")],
+ user_id="u1",
+ agent_id="scope:2026-10-19",
+ session_id="conversation-b",
+ workspace_id="repo-a",
+ )
+
+ old = await coding_store.get_fact("f_old", user_id="u1")
+ assert old is not None
+ assert old.status == "active"
+ assert [op.action for op in ops] == ["INSERT"]
+ assert len(llm.calls) == 0
+
async def test_old_fact_superseded_only_once(self, coding_store, mock_embed):
"""两条新事实都声称覆盖同一条旧事实时,只让第一条生效。
@@ -274,6 +308,7 @@ class TestSupersede:
_draft("config 位于 /srv/app/config.yaml"),
],
user_id="u1",
+ session_id="test-session",
)
assert len(facts) == 2
assert sum(1 for o in ops if o.action == "SUPERSEDE") == 1
@@ -288,6 +323,7 @@ class TestChainSummary:
async def _seed_old(self, store):
await store.insert_fact(WorkingFact(
fact_id="f_old", user_id="u1",
+ session_id="test-session",
statement=(
"用户要迁移 app config;确认当前读取 /opt/app/config.yaml,"
"尚未修改配置加载逻辑。"
@@ -310,7 +346,7 @@ class TestChainSummary:
[_draft(
"用户继续迁移 app config;将加载路径改为 /etc/app/config.yaml,"
"配置加载测试通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
stored = await coding_store.get_fact(facts[0].fact_id, user_id="u1")
@@ -326,7 +362,7 @@ class TestChainSummary:
[_draft(
"用户继续迁移 app config;将加载路径改为 /etc/app/config.yaml,"
"配置加载测试通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
assert len(llm.calls) == 2, "SUPERSEDE 应触发第二次调用"
@@ -344,7 +380,11 @@ class TestChainSummary:
llm = _llm([])
rec = WorkingFactReconciler(coding_store, mock_embed, llm)
- await rec.reconcile([_draft("另一个话题的结论")], user_id="u1")
+ await rec.reconcile(
+ [_draft("另一个话题的结论")],
+ user_id="u1",
+ session_id="test-session",
+ )
assert len(llm.calls) == 1
async def test_prompt_carries_full_lineage(self, coding_store, mock_embed):
@@ -357,7 +397,7 @@ class TestChainSummary:
[_draft(
"用户继续迁移 app config;将加载路径改为 /etc/app/config.yaml,"
"配置加载测试通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
llm2 = _llm([{"draft_idx": 0, "supersedes": [facts[0].fact_id]}])
@@ -366,7 +406,7 @@ class TestChainSummary:
[_draft(
"用户继续完善同一 config 迁移;改由环境变量 APP_CONFIG 指定路径,"
"回归测试通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
prompt = llm2.calls[1]["prompt"]
@@ -393,7 +433,7 @@ class TestChainSummary:
[_draft(
"用户继续迁移 app config;将加载路径改为 /etc/app/config.yaml,"
"配置加载测试通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
assert sum(1 for o in ops if o.action == "SUPERSEDE") == 1
@@ -426,7 +466,7 @@ class TestChainSummary:
[_draft(
"用户继续迁移 app config;将加载路径改为 /etc/app/config.yaml,"
"配置加载测试通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
assert facts[0].fact_chain_summary == ""
@@ -436,7 +476,7 @@ class TestChainSummary:
[_draft(
"用户继续完善同一 config 迁移;改由环境变量 APP_CONFIG 指定路径,"
"回归测试通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
prompt = llm2.calls[1]["prompt"]
@@ -450,7 +490,8 @@ class TestChainSummary:
total = MAX_FACT_CHAIN_ENTRIES + 3
for i in range(total):
await coding_store.insert_fact(WorkingFact(
- fact_id=f"g{i}", user_id="u1", statement=f"第 {i} 代结论",
+ fact_id=f"g{i}", user_id="u1", session_id="test-session",
+ statement=f"第 {i} 代结论",
created_at=datetime(2026, 1, i + 1),
))
if prev:
@@ -459,7 +500,9 @@ class TestChainSummary:
llm = _llm([{"draft_idx": 0, "supersedes": [prev]}])
rec = WorkingFactReconciler(coding_store, mock_embed, llm)
- await rec.reconcile([_draft("最新结论")], user_id="u1")
+ await rec.reconcile(
+ [_draft("最新结论")], user_id="u1", session_id="test-session"
+ )
prompt = llm.calls[1]["prompt"]
assert "第 0 代结论" not in prompt, "最老的几代该被截掉"
@@ -478,7 +521,7 @@ class TestChainSummary:
[_draft(
"用户继续迁移 app config;将加载路径改为 /etc/app/config.yaml,"
"配置加载测试通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
entries = llm.calls[1]["prompt"].split(
"ENTRIES\n═══════════════════════════════════════════════════════════════════\n",
@@ -497,7 +540,7 @@ class TestChainSummary:
[_draft(
"用户继续迁移 app config;将加载路径改为 /etc/app/config.yaml,"
"配置加载测试通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
rec2 = WorkingFactReconciler(
@@ -509,7 +552,7 @@ class TestChainSummary:
[_draft(
"用户继续完善同一 config 迁移;改由环境变量 APP_CONFIG 指定路径,"
"回归测试通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
stored = await coding_store.get_fact(facts2[0].fact_id, user_id="u1")
@@ -526,7 +569,7 @@ class TestChainSummary:
[_draft(
"用户继续迁移 app config;将加载路径改为 /etc/app/config.yaml,"
"配置加载测试通过。"
- )], user_id="u1",
+ )], user_id="u1", session_id="test-session",
)
assert len(llm.calls) == 1
@@ -564,7 +607,8 @@ class TestFailSafe:
async def test_llm_failure_still_inserts(self, coding_store, mock_embed):
"""LLM 挂了宁可多留一条过期事实,也不能因为一次调用失败丢结论。"""
await coding_store.insert_fact(WorkingFact(
- fact_id="f_old", user_id="u1", statement="config 位于 /opt/app/config.yaml",
+ fact_id="f_old", user_id="u1", session_id="test-session",
+ statement="config 位于 /opt/app/config.yaml",
))
rec = WorkingFactReconciler(coding_store, mock_embed, FailingLLMProvider())
@@ -578,7 +622,8 @@ class TestFailSafe:
async def test_unparsable_llm_output(self, coding_store, mock_embed):
await coding_store.insert_fact(WorkingFact(
- fact_id="f_old", user_id="u1", statement="config 位于 /opt/app/config.yaml",
+ fact_id="f_old", user_id="u1", session_id="test-session",
+ statement="config 位于 /opt/app/config.yaml",
))
rec = WorkingFactReconciler(
coding_store, mock_embed, MockLLMProvider("不是 JSON 的一段话")
@@ -592,7 +637,8 @@ class TestFailSafe:
async def test_markdown_fence_parsed(self, coding_store, mock_embed):
await coding_store.insert_fact(WorkingFact(
- fact_id="f_old", user_id="u1", statement="config 位于 /opt/app/config.yaml",
+ fact_id="f_old", user_id="u1", session_id="test-session",
+ statement="config 位于 /opt/app/config.yaml",
))
llm = MockLLMProvider([
"```json\n" + _ops_resp([{"draft_idx": 0, "supersedes": ["f_old"]}]) + "\n```",
@@ -601,7 +647,9 @@ class TestFailSafe:
rec = WorkingFactReconciler(coding_store, mock_embed, llm)
_, ops = await rec.reconcile(
- [_draft("config 位于 /etc/app/config.yaml")], user_id="u1",
+ [_draft("config 位于 /etc/app/config.yaml")],
+ user_id="u1",
+ session_id="test-session",
)
assert sum(1 for o in ops if o.action == "SUPERSEDE") == 1
@@ -618,7 +666,8 @@ class TestSubjectGateSwitch:
async def _seed(self, store, fact_id, subject, statement):
await store.insert_fact(WorkingFact(
- fact_id=fact_id, user_id="u1", subject=subject, statement=statement,
+ fact_id=fact_id, user_id="u1", session_id="test-session",
+ subject=subject, statement=statement,
))
async def test_gate_on_blocks_cross_subject_supersede(self, coding_store, mock_embed):
@@ -632,6 +681,7 @@ class TestSubjectGateSwitch:
_, ops = await rec.reconcile(
[WorkingFactDraft(subject="Bart", statement="Bart 的三日行程已排定,预算待定。")],
user_id="u1",
+ session_id="test-session",
)
assert [o.action for o in ops] == ["INSERT"]
assert (await coding_store.get_fact("f_emma", user_id="u1")).status == "active"
@@ -647,6 +697,7 @@ class TestSubjectGateSwitch:
facts, ops = await rec.reconcile(
[WorkingFactDraft(subject="Bart", statement="Bart 的三日行程已排定,预算待定。")],
user_id="u1",
+ session_id="test-session",
)
assert [o.action for o in ops] == ["SUPERSEDE", "INSERT"]
old = await coding_store.get_fact("f_emma", user_id="u1")
@@ -667,7 +718,8 @@ class TestSubjectGateSwitch:
[WorkingFactDraft(subject="Bart", statement="Bart 的行程。")],
[[old]],
{0: ["f_emma"]},
- user_id="u1", agent_id="a1", session_id=None, workspace_id=None,
+ user_id="u1", agent_id="default_agent",
+ session_id="test-session", workspace_id=None,
)
assert "SUPERSEDE" in [o.action for o in ops]
@@ -687,7 +739,8 @@ class TestSubjectGateSwitch:
[WorkingFactDraft(subject="deploy.sh", statement="新的部署脚本结论。")],
[[old]],
{0: [f"f_noneed_{gate}"]},
- user_id="u1", agent_id="a1", session_id=None, workspace_id=None,
+ user_id="u1", agent_id="default_agent",
+ session_id="test-session", workspace_id=None,
)
assert "SUPERSEDE" in [o.action for o in ops], f"gate={gate} 时空 subject 被误拦"
@@ -714,6 +767,7 @@ class TestDetailsInheritance:
async def test_ancestor_details_copied_verbatim(self, coding_store, mock_embed):
await coding_store.insert_fact(WorkingFact(
fact_id="f_old", user_id="u1", subject="Emma",
+ session_id="test-session",
statement="Emma 的行程草案已出,预算待核。",
details="日均餐费 $32.4-$57.6\n酒店评分 3.2-3.8",
))
@@ -726,6 +780,7 @@ class TestDetailsInheritance:
[WorkingFactDraft(subject="Emma", statement="Emma 的行程已定稿。",
details="航班 CA1234")],
user_id="u1",
+ session_id="test-session",
)
stored = await coding_store.get_fact(facts[0].fact_id, user_id="u1")
# 本代的 details 在,祖先的具体取值也一字不差地在
@@ -742,6 +797,7 @@ class TestDetailsInheritance:
"""
await coding_store.insert_fact(WorkingFact(
fact_id="f_g1", user_id="u1", subject="T",
+ session_id="test-session",
statement="第一代结论。", details="V1=" + "a" * 300,
))
prev = "f_g1"
@@ -756,6 +812,7 @@ class TestDetailsInheritance:
[WorkingFactDraft(subject="T", statement=f"第{gen}代结论。",
details=f"V{gen}=" + "a" * 300)],
user_id="u1",
+ session_id="test-session",
)
prev = facts[0].fact_id
stored = await coding_store.get_fact(prev, user_id="u1")
@@ -772,6 +829,7 @@ class TestDetailsInheritance:
"""预算是硬的,但被丢掉的代数必须写出来,不静默截断。"""
await coding_store.insert_fact(WorkingFact(
fact_id="f_old", user_id="u1", subject="T",
+ session_id="test-session",
statement="旧结论。", details="X=" + "b" * 8000,
))
rec = WorkingFactReconciler(
@@ -782,6 +840,7 @@ class TestDetailsInheritance:
facts, _ = await rec.reconcile(
[WorkingFactDraft(subject="T", statement="新结论。", details="Y=1")],
user_id="u1",
+ session_id="test-session",
)
stored = await coding_store.get_fact(facts[0].fact_id, user_id="u1")
assert "…(truncated)" in stored.details
@@ -790,6 +849,7 @@ class TestDetailsInheritance:
async def test_switch_off_keeps_details_untouched(self, coding_store, mock_embed):
await coding_store.insert_fact(WorkingFact(
fact_id="f_old", user_id="u1", subject="T",
+ session_id="test-session",
statement="旧结论。", details="祖先取值 Z=9",
))
rec = WorkingFactReconciler(
@@ -800,6 +860,7 @@ class TestDetailsInheritance:
facts, ops = await rec.reconcile(
[WorkingFactDraft(subject="T", statement="新结论。", details="Y=1")],
user_id="u1",
+ session_id="test-session",
)
# 覆盖照样发生,只是不过继
assert "SUPERSEDE" in [o.action for o in ops]
@@ -814,6 +875,7 @@ class TestDetailsInheritance:
"""
await coding_store.insert_fact(WorkingFact(
fact_id="f_old", user_id="u1", subject="T",
+ session_id="test-session",
statement="旧结论。", details="无关噪声 " + "q" * 2000,
))
rec = WorkingFactReconciler(
@@ -824,6 +886,7 @@ class TestDetailsInheritance:
facts, _ = await rec.reconcile(
[WorkingFactDraft(subject="T", statement="新结论。", details="Y=1")],
user_id="u1",
+ session_id="test-session",
)
new_id = facts[0].fact_id
emb = await coding_store.embed_service.embed("T 新结论。")
diff --git a/tests/coding/test_reconciler.py b/tests/coding/test_reconciler.py
index d040dce..5111f28 100644
--- a/tests/coding/test_reconciler.py
+++ b/tests/coding/test_reconciler.py
@@ -35,7 +35,8 @@ class TestReconcilerActions:
async def test_update(self, coding_store, mock_embed):
# 种入 m1
await coding_store.insert(CodingMemory(
- experience_id="m1", user_id="u1", task="T1",
+ experience_id="m1", user_id="u1", agent_id="scope-day-1",
+ workspace_id="repo-a", session_id="conversation-1", task="T1",
search_keys=["old"], solution="old",
))
llm = MockLLMProvider(_llm_resp([
@@ -44,23 +45,146 @@ class TestReconcilerActions:
]))
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
d = CodingMemoryDraft(task="T1", search_keys=["new1"], solution="new",
- user_id="u1")
+ user_id="u1", agent_id="scope-day-1",
+ workspace_id="repo-a", session_id="conversation-1")
ops = await rec.reconcile([d])
assert len(ops) == 1 and ops[0].action == "UPDATE"
got = await coding_store.get_by_id("m1", "u1")
assert got.solution == "new"
assert got.search_keys == ["new1"]
+ @pytest.mark.parametrize(
+ (
+ "old_agent",
+ "old_workspace",
+ "old_session",
+ "new_agent",
+ "new_workspace",
+ "new_session",
+ ),
+ [
+ (
+ "scope:same-day",
+ "repo-a",
+ "conversation-a",
+ "scope:same-day",
+ "repo-a",
+ "conversation-b",
+ ),
+ (
+ "scope:2026-10-18",
+ "repo-a",
+ "conversation-a",
+ "scope:2026-10-19",
+ "repo-a",
+ "conversation-a",
+ ),
+ (
+ "shared-scope",
+ "repo-a",
+ "conversation-a",
+ "shared-scope",
+ "repo-b",
+ "conversation-a",
+ ),
+ ],
+ )
+ async def test_update_target_must_match_frozen_authority_scope(
+ self,
+ coding_store,
+ mock_embed,
+ old_agent,
+ old_workspace,
+ old_session,
+ new_agent,
+ new_workspace,
+ new_session,
+ ):
+ """Near duplicates cannot cross conversation, date, or workspace authority."""
+ await coding_store.insert(CodingMemory(
+ experience_id="old-target", user_id="u1", agent_id=old_agent,
+ workspace_id=old_workspace, session_id=old_session,
+ task="fix flaky release", solution="old solution",
+ ))
+ llm = MockLLMProvider(_llm_resp([
+ {
+ "draft_idx": 0,
+ "action": "UPDATE",
+ "target_experience_id": "old-target",
+ "reason": "near duplicate",
+ },
+ ]))
+ rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
+ draft = CodingMemoryDraft(
+ task="fix flaky release",
+ solution="new solution",
+ user_id="u1",
+ agent_id=new_agent,
+ workspace_id=new_workspace,
+ session_id=new_session,
+ )
+
+ ops = await rec.reconcile([draft])
+
+ old = await coding_store.get_by_id("old-target", "u1")
+ assert old is not None
+ assert old.solution == "old solution"
+ assert old.agent_id == old_agent
+ assert old.workspace_id == old_workspace
+ assert old.session_id == old_session
+ assert len(ops) == 1
+ assert ops[0].action == "ADD"
+ assert ops[0].target_experience_id != "old-target"
+
+ @pytest.mark.parametrize("legacy_agent", ["", "default_agent", "scope:legacy"])
+ async def test_legacy_target_without_conversation_falls_back_to_add(
+ self, coding_store, mock_embed, legacy_agent
+ ):
+ await coding_store.insert(CodingMemory(
+ experience_id="legacy-target",
+ user_id="u1",
+ agent_id=legacy_agent,
+ session_id=None,
+ workspace_id="repo-a",
+ task="upgrade dependency",
+ solution="legacy solution",
+ ))
+ llm = MockLLMProvider(_llm_resp([
+ {
+ "draft_idx": 0,
+ "action": "UPDATE",
+ "target_experience_id": "legacy-target",
+ },
+ ]))
+ rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
+ draft = CodingMemoryDraft(
+ task="upgrade dependency",
+ solution="current solution",
+ user_id="u1",
+ agent_id=legacy_agent,
+ session_id="current-conversation",
+ workspace_id="repo-a",
+ )
+
+ ops = await rec.reconcile([draft])
+
+ legacy = await coding_store.get_by_id("legacy-target", "u1")
+ assert legacy is not None
+ assert legacy.solution == "legacy solution"
+ assert legacy.session_id is None
+ assert [op.action for op in ops] == ["ADD"]
+
async def test_skip(self, coding_store, mock_embed):
await coding_store.insert(CodingMemory(
experience_id="m1", user_id="u1", task="X", solution="Y",
+ session_id="conversation-1",
))
llm = MockLLMProvider(_llm_resp([
{"draft_idx": 0, "action": "SKIP", "reason": "duplicate"},
]))
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
d = CodingMemoryDraft(task="X", solution="Y",
- user_id="u1")
+ user_id="u1", session_id="conversation-1")
ops = await rec.reconcile([d])
assert len(ops) == 1 and ops[0].action == "SKIP"
# store 不变
@@ -71,7 +195,7 @@ class TestReconcilerActions:
# 旧记忆要被 DELETE
await coding_store.insert(CodingMemory(
experience_id="m_dep", user_id="u1", task="use old.sh",
- solution="old script",
+ solution="old script", session_id="conversation-1",
))
llm = MockLLMProvider(_llm_resp([
{"draft_idx": 0, "action": "ADD"},
@@ -80,7 +204,7 @@ class TestReconcilerActions:
]))
rec = CodingMemoryReconciler(coding_store, mock_embed, llm)
d = CodingMemoryDraft(task="use new CLI", solution="new way",
- user_id="u1")
+ user_id="u1", session_id="conversation-1")
ops = await rec.reconcile([d])
assert sorted(op.action for op in ops) == ["ADD", "DELETE"]
# 旧的没了
diff --git a/tests/coding/test_store.py b/tests/coding/test_store.py
index 121d500..dda9848 100644
--- a/tests/coding/test_store.py
+++ b/tests/coding/test_store.py
@@ -67,7 +67,8 @@ class TestStoreCRUD:
async def test_update_overrides(self, coding_store, mock_embed):
m = CodingMemory(experience_id="e1", user_id="u1", task="T",
- search_keys=["old1", "old2"], solution="old")
+ search_keys=["old1", "old2"], solution="old",
+ session_id="conversation-1")
await coding_store.insert(m)
# 旧 aspect 应可命中
@@ -90,6 +91,59 @@ class TestStoreCRUD:
assert got.solution == "new"
assert got.search_keys == ["new1"]
+ async def test_update_rejects_authority_scope_change(self, coding_store):
+ await coding_store.insert(CodingMemory(
+ experience_id="e1", user_id="u1", agent_id="scope-a",
+ workspace_id="repo-a", session_id="conversation-1",
+ task="T", solution="old",
+ ))
+ replacement = CodingMemory(
+ experience_id="e1", user_id="u1", agent_id="scope-b",
+ workspace_id="repo-a", session_id="conversation-1",
+ task="T", solution="new",
+ )
+
+ with pytest.raises(ValueError, match="coding_memory_update_authority_mismatch"):
+ await coding_store.update(replacement)
+
+ stored = await coding_store.get_by_id("e1", user_id="u1")
+ assert stored is not None
+ assert stored.agent_id == "scope-a"
+ assert stored.solution == "old"
+
+ async def test_update_rejects_conversation_change_and_legacy_empty_session(
+ self, coding_store
+ ):
+ for experience_id, old_session in (
+ ("different-conversation", "conversation-1"),
+ ("legacy-empty-session", None),
+ ):
+ await coding_store.insert(CodingMemory(
+ experience_id=experience_id,
+ user_id="u1",
+ agent_id="scope-a",
+ workspace_id="repo-a",
+ session_id=old_session,
+ task="T",
+ solution="old",
+ ))
+ replacement = CodingMemory(
+ experience_id=experience_id,
+ user_id="u1",
+ agent_id="scope-a",
+ workspace_id="repo-a",
+ session_id="conversation-2",
+ task="T",
+ solution="new",
+ )
+
+ with pytest.raises(ValueError, match="coding_memory_update_authority_mismatch"):
+ await coding_store.update(replacement)
+
+ stored = await coding_store.get_by_id(experience_id, user_id="u1")
+ assert stored is not None
+ assert stored.solution == "old"
+
async def test_delete(self, coding_store):
m = CodingMemory(experience_id="e1", user_id="u1", task="T",
search_keys=["k"], solution="S")
diff --git a/tests/coding/test_writer_e2e.py b/tests/coding/test_writer_e2e.py
index 99746d8..6e279c8 100644
--- a/tests/coding/test_writer_e2e.py
+++ b/tests/coding/test_writer_e2e.py
@@ -335,7 +335,7 @@ class TestDualLayerWrite:
from hy_memory.coding.types import CodingMemory
await coding_store.insert(CodingMemory(
experience_id="e1", user_id="u1", task="老 task", solution="旧 solution",
- source_fact_ids=["f_before"],
+ source_fact_ids=["f_before"], session_id="test-session",
))
llm = MockLLMProvider([
_extract_resp(
@@ -348,7 +348,9 @@ class TestDualLayerWrite:
])
writer = self._writer(coding_store, mock_embed, llm)
- resp = await writer.write(_coding_messages(), user_id="u1")
+ resp = await writer.write(
+ _coding_messages(), user_id="u1", session_id="test-session"
+ )
exp = await coding_store.get_by_id("e1", user_id="u1")
assert exp.solution == "新 solution"
assert exp.source_fact_ids == ["f_before", resp["fact_ids"][0]]