fix(sdk): coding reconcile model failures fail the write, nothing half-applied

Experience reconcile no longer falls back to ADD-all, and fact reconcile no
longer inserts without superseding, when the model call fails, returns empty
content, or returns a reply that is not a JSON object with an ops list. The
write returns success=false, agent_error_code=RECONCILE_FAILED and the
cause in reconcile_error_code (LLM_UNAVAILABLE / EMPTY_RESPONSE /
JSON_PARSE_FAILED), the same as chat.

Each reconciler is split into plan() (retrieve + model decision, no store)
and apply() (store). CodingWriter plans both layers before applying either,
so a decision failure in either layer stores no experience or fact and
supersedes no older fact. reconcile() still runs plan + apply.

An experience reply of {"ops": []} is a valid "no changes" decision and
stores nothing. A non-empty ops list with no recognizable op is a parse
failure. A fact reply of {"ops": []} inserts without superseding.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

CHANGELOG.md

@@ -4,6 +4,124 @@ Hy Memory and MemHub are versioned and released independently.
 
 ## Unreleased
 
+- MemHub multi-user hardening (follow-up to #250):
+  - Read responses name the user they were read for: `user_id` (the one
+    asked for, `local` by default) is now on `GET /api/v2/memory-library`,
+    `/memory-library/layers`, `/user-profile`, `/home-summary`,
+    `/memories/graph`, `/raw`, and `POST /api/v2/context/search`,
+    `/api/v1/recall`, `/api/v2/memories/ask`. `ask/stream` carries it on its
+    first (`recall`) event. The Host Bridge context validator accepts the new
+    field and still accepts a Core without it.
+  - `DELETE /api/v2/memories/{id}` answers 404 `memory_not_found` for another
+    user's memory and for an id that does not exist (the same response, so
+    existence is still not revealed), and also when the SDK finds nothing to
+    delete; 204 only when the caller's own memory was deleted. The App treats
+    that 404 as already gone (a double-click delete no longer shows an
+    error); `memhub memories delete` prints "未找到记忆 <id>（可能已删除）",
+    exits 0, and its JSON is `state: "committed"` with `already_gone: true`.
+  - Hermes never reads a `profiles/` directory at any depth (scan, detect and
+    live sync), so a root granted above `~/.hermes` cannot pick up another
+    user's profile. Connecting refuses a root that is the `profiles`
+    container itself (422 `hermes_root_is_profiles_container`) and a root
+    equal to, containing or inside another user's active Hermes grant (409
+    `hermes_root_overlaps_other_user`, symlinks resolved); `local` on
+    `~/.hermes` with another user on `~/.hermes/profiles/<name>` stays
+    allowed. The CLI explains both codes.
+  - `memhub sources connect --user-id` with an invalid id now says the user
+    id need not equal the Hermes profile name (e.g. `--user-id wife-work
+    --root ~/.hermes/profiles/wife:work`).
+
+- Hy Memory: a model failure during a write now reports failure and stores
+  nothing. **Behaviour change for direct SDK users:** writes that used to
+  return `success: true` in a degraded state now return `success: false`;
+  retry them with a new `request_id` once the model is back.
+  - Reconcile (pro / ultra `add` and `add_extracted`): when the reconcile model
+    call fails, returns HTTP 200 with empty content, or returns a reply that
+    cannot be parsed, or reconcile raises before anything is stored, the write
+    used to fall back to adding every extracted memory as-is (no dedup or
+    evolution) and report success. That fallback is removed, with its
+    `degraded` / `degraded_reason` result fields. The write now returns
+    `success: false`, `error_code: 502`,
+    `agent_error_code: "RECONCILE_FAILED"`, and the cause in the new
+    `reconcile_error_code` (`LLM_UNAVAILABLE`, `EMPTY_RESPONSE`,
+    `JSON_PARSE_FAILED`, `RECONCILE_EXCEPTION`). None of the new memories are
+    stored, the episode counter does not advance, and `add` rolls back its
+    raw turn the same way as an extraction failure
+    (`l1_rollback.retry_safe: true`). An empty 200 reply was previously
+    counted as "no changes" and reported success with 0 memories; only a
+    literal `[]` reply still means that. `RECONCILE_ENABLED=false` is a
+    configuration choice and still writes directly.
+  - Working / coding path: an extraction model failure used to return
+    success with 0 operations. It now returns `success: false` with
+    `agent_error_code` `LLM_ERROR`, `EMPTY_RESPONSE` or `JSON_PARSE_FAILED`.
+    A model that answers with nothing worth remembering is still a success.
+    An embedding failure used to store the experience or fact without a
+    vector, where search never finds it, and report success; it now returns
+    `EMBEDDING_FAILED` and the node is not stored. A fact embedding is checked
+    before any older fact is superseded. A failed write no longer appends its
+    turns to the recent trace and records no `chain_rounds`.
+    With `MEMORY_CODING_VERBATIM_FALLBACK_ENABLED` turned on, extraction
+    failures keep the verbatim fallback.
+  - Working / coding reconcile: when the experience reconcile or the fact
+    reconcile model call fails, returns empty content, or returns a reply that
+    is not a JSON object with an `ops` list, the write returns
+    `success: false`, `agent_error_code: "RECONCILE_FAILED"` and the cause in
+    `reconcile_error_code` (`LLM_UNAVAILABLE`, `EMPTY_RESPONSE`,
+    `JSON_PARSE_FAILED`), the same as chat. Before, experience reconcile fell
+    back to adding every draft, and fact reconcile inserted the new fact
+    without superseding older ones. Both model decisions now run before
+    anything is stored, so a failure in either leaves no experience or fact
+    from the write and supersedes no older fact. An experience reply of
+    `{"ops": []}` is a valid "no changes" decision: the write succeeds and no
+    experience is stored. A non-empty `ops` list with no recognizable op is a
+    parse failure. A fact reply of `{"ops": []}` inserts the new fact without
+    superseding anything. Fact reconcile still makes no model call when there
+    are no candidates.
+
+- MemHub's DeepSeek Harness app page can grant recall again (#230). The
+  "一键插入应用" switch used to be greyed out with `unsupported_host`, and a
+  profile installed from the CLI stayed `install-only` with no way to approve
+  it. The one switch now covers every detected profile
+  (`deepseek-harness:<profile>`): on installs each profile's MCP patch and
+  grants recall, off removes the patch and revokes the grant. The page lists
+  each profile with its state, and names any profile that failed while
+  keeping the others. While the switch is on, a profile created later is
+  installed and granted automatically, without restarting MemHub; the Runtime
+  also no longer fails every host read when it meets a profile created after
+  it started. The harness docs no longer describe an unmounted sources page.
+
+- MemHub's `deepseek-harness` source imports session files whose names carry the
+  format generation: `session.v3.jsonl.zstd` and `session.v4.jsonl.zstd` are now
+  discovered alongside the original `session.jsonl[.zstd]`. Discovery accepts
+  any `session[.vN].jsonl[.zstd]` name and the header's `version` decides
+  whether the session is parsed (v0/v3/v4) or refused as `unsupported_schema`.
+  A refused file is reported and keeps no cursor, so the release that learns
+  its format reads it from the top.
+  v4 tool results, which are written as plain `text` blocks rather than
+  `tool-result` blocks, are read through the same clipping and credential
+  scrubbing path. Previously every versioned session was invisible: the import
+  job completed with `discovered 0` while the files sat on disk.
+
+## Hy Memory 2.0.12 — 2026-11-02
+
+- Intention dedup is now configurable per client
+  (`MemoryConfig.recall.intention_dedup_enabled`, default `true`;
+  `recall.intention_dedup_threshold`, default `MEMORY_DEDUP_THRESHOLD` or
+  `0.95`). Env defaults: `MEMORY_INTENTION_DEDUP_ENABLED`,
+  `MEMORY_INTENTION_DEDUP_THRESHOLD`. When on, behaviour is unchanged
+  (duplicates found at read time are still deleted); when off, no intention
+  dedup runs, at read time or within a write batch, and nothing is hidden,
+  dropped or deleted. The threshold applies to read-time dedup only. Refs #241.
+
+- MemHub pins `hy-memory==2.0.12` and exposes that intention dedup switch in
+  its memory-features setting (`GET`/`PUT /api/v1/settings/memory-features`,
+  `memhub settings features`): the feature `intention_dedup` (default on) and
+  the numeric `intention_dedup_threshold` (default 0.95, accepted 0.8–1.0,
+  anything else is 422 or a CLI usage error). Unset, both keep the SDK
+  default, so nothing changes for the App; a change rebuilds the SDK clients
+  like the other feature switches. The API answer gains `parameters`, and
+  `pipeline.features` can now carry the threshold as a number. Refs #241.
+
 ## MemHub 1.0.6 — 2026-11-02
 
 Build 37, on `hy-memory==2.0.11`. Linux x64/arm64 Runtime and macOS arm64

docs/env_reference.md

@@ -182,9 +182,29 @@ SDK 不设置 Rerank Search 并发上限。开启后模型在 `HyMemoryClient`
 | `MEMORY_RECALL_STRENGTH_TAU` | `180` | 衰减时间常数，天 |
 | `MEMORY_RECALL_ACCESS_TRACKING` | `true` | Strength 开启时是否回写访问信息 |
 | `MEMORY_ENTITY_STORE_ENABLED` | `false` | 是否维护独立 entity collection；当前 Reader 不直接读取 |
+| `MEMORY_INTENTION_DEDUP_ENABLED` | `true` | 是否对 L7 Intention 判重（读侧和写入侧批内）；见下文 |
+| `MEMORY_INTENTION_DEDUP_THRESHOLD` | `MEMORY_DEDUP_THRESHOLD`，再缺省为 `0.95` | Intention 读侧判重的 cosine 阈值 |
 
 旧数据可调用当前公开方法 `client.build_entity_store(user_id)` 补建 Entity Store。
 
+Intention 判重：开启时（默认，与以往行为一致），Search 召回的 L7 Intention 中，
+同 `user_id` + 同 `agent_id` + `memory_at` 同一天 + `valid_until` 相同、且 cosine ≥ 阈值的
+条目视为复本，只返回最早写入的一条，其余在后台从向量库**删除**。判重不区分内容中的项目、
+对象等语义差异，内容高度相似但对象不同的意图可能被误删；写入时同一批抽取结果也会做一次
+批内判重。关闭后这两处都不判重，不隐藏、不丢弃、也不删除意图。两项对应
+`MemoryConfig.recall.intention_dedup_enabled` /
+`recall.intention_dedup_threshold`，按 client 生效，环境变量只提供默认值：
+
+```python
+client = HyMemoryClient.from_config({
+    "recall": {"intention_dedup_enabled": False},
+})
+```
+
+`MEMORY_DEDUP_THRESHOLD` 同时被写入侧批内意图判重和 dedup 内核使用；
+`MEMORY_INTENTION_DEDUP_THRESHOLD` 只影响读侧 Intention 判重，写入侧批内判重的阈值
+仍取 `MEMORY_DEDUP_THRESHOLD`。
+
 ## 日志、Trace 与历史
 
 | 变量 | 默认值 | 说明 |

docs/multi_speaker_design.md

@@ -107,5 +107,5 @@ L1_RAW 保存的内容使用上述渲染格式。历史回读时：
 ```bash
 python -m pytest -q \
   tests/test_multi_speaker_format.py \
-  tests/test_reconcile_fallback.py
+  tests/test_reconcile_failure.py
 ```

docs/scene_coding_usage.md

@@ -150,7 +150,23 @@ working/coding 写入返回双层结果：
 }
 ```
 
-`scene="coding"` 还会返回 `chain_rounds`。出于历史兼容，该字段当前统计本次识别并处理
+抽取 LLM 调用失败、返回空 content 或回复解析不出 JSON，以及经验 / 事实向量化失败时，
+写入返回 `success=False`、`error_code=502`，`agent_error_code` 依次为 `LLM_ERROR`、
+`EMPTY_RESPONSE`、`JSON_PARSE_FAILED`、`EMBEDDING_FAILED`，`error_message` 以
+`[CODE]` 开头；没有向量的经验 / 事实不会落库，失败的写入也不追加对话 trace，换一个
+`request_id` 重跑即可。模型正常作答但没有值得记的内容仍是 `success=True`、0 条。
+显式开启 `MEMORY_CODING_VERBATIM_FALLBACK_ENABLED` 时抽取失败沿用原文兜底。
+
+经验层 / 事实层 reconcile 的模型决策同样不再兜底：LLM 调用失败、返回空 content 或回复
+不是带 `ops` 列表的 JSON 对象时，写入返回 `success=False`、
+`agent_error_code="RECONCILE_FAILED"`，原因在 `reconcile_error_code`（`LLM_UNAVAILABLE` /
+`EMPTY_RESPONSE` / `JSON_PARSE_FAILED`，与 chat 链路一致）。两层的模型决策都在落库之前
+完成，任何一层失败时本次一条经验 / 事实都不存，旧事实也不会被覆盖。经验层回复
+`{"ops": []}` 表示「无需任何操作」，写入成功、经验层不存；`ops` 非空却没有一条可识别的
+op 视为解析失败。事实层回复 `{"ops": []}` 表示都不覆盖、照常插入新事实；没有候选时不
+调用 LLM。
+
+`scene="coding"` 还会返回 `chain_rounds`（写入失败时不记录演进链，也不返回该字段）。出于历史兼容，该字段当前统计本次识别并处理
 的 diff hunk 数，而不保证等于最终合并后的唯一演进 round 数。`0` 表示没有识别到可记录
 的代码修改，不代表双层 memory 写入失败。
 

docs/usage.md

@@ -128,6 +128,14 @@ result = client.add(
 双层 reconcile 操作、`experience_ids`、`fact_ids` 等字段，完整结构见
 [scene_coding_usage.md](scene_coding_usage.md#4-返回结构)。
 
+写入失败时 `success=False`，`error_code` 为 HTTP 风格的整数，`agent_error_code` 给出稳定
+失败码。pro / ultra 的 reconcile（新事实与已有记忆判重、合并）模型调用失败、返回空
+content 或回复解析不出时，`add` 与 `add_extracted` 都报 `agent_error_code="RECONCILE_FAILED"`，
+具体原因在 `reconcile_error_code`（`LLM_UNAVAILABLE` / `EMPTY_RESPONSE` /
+`JSON_PARSE_FAILED` / `RECONCILE_EXCEPTION`）。此时本次一条新记忆都不落库，`add` 已写入
+的原始对话按抽取失败同样回滚（`l1_rollback.retry_safe=True`）；模型恢复后换一个
+`request_id` 重跑即可。`RECONCILE_ENABLED=false` 时不调用 reconcile，直接写入。
+
 `mode="lite"` 不执行 LLM 抽取，写入内容直接以 `L1_RAW` 形式保存。lite 的 Search 是
 严格的 raw-only 向量检索：无论调用方传入什么 `layers`、`scene` 或 `search_mode`，都只
 召回 `L1_RAW`，不会进入 working/coding、Schema 或 Intention 链路，也不会调用场景判断

hy_memory/agent/reconciler.py

@@ -136,10 +136,10 @@ class ReconcileResult:
     ops: List[ReconcileOp] = field(default_factory=list)
     success: bool = True
     error: Optional[str] = None
-    # True = reconcile 失败后走了「全部 ADD」兜底（见 _fallback_add_ops）。
-    # 结果仍然可用（success=True），但没有做过去重/演化判定，可能引入重复。
-    degraded: bool = False
-    degraded_reason: Optional[str] = None
+    # success=False 时的稳定失败码：LLM_UNAVAILABLE / EMPTY_RESPONSE /
+    # JSON_PARSE_FAILED / RECONCILE_EXCEPTION。失败时 ops 恒为空：writer 什么都
+    # 不落库，整次写入报失败，调用方换个 request_id 重跑即可（reconcile 会判重）。
+    error_code: Optional[str] = None
     # reconcile 链路 LLM token 消耗（search-query + reconcile 两次 LLM 调用之和）
     prompt_tokens: int = 0
     completion_tokens: int = 0
@@ -151,7 +151,7 @@ class ReconcileResult:
     # 用 content 作 key 而不是 node_id：新记忆此刻还没入库、没有 id。
     candidate_scores: Dict[str, List[Tuple[str, float]]] = field(default_factory=dict)
     # reconcile 候选检索已经为每条新 memory 算过 embedding。把原始文本对应向量交回
-    # writer，ADD-all / degraded ADD 可直接落库，避免同一事实再次请求 embedding。
+    # writer，原文不变的 ADD 可直接落库，避免同一事实再次请求 embedding。
     # 仅按完全相同 content 复用；LLM 改写后的 UPDATE/SUPERSEDE 会重新计算，防止错配。
     new_memory_embeddings: Dict[str, List[float]] = field(default_factory=dict)
 
@@ -394,49 +394,6 @@ class MemoryReconciler:
 
         return [], None
 
-    @staticmethod
-    def _fallback_add_ops(
-        new_memories: List[str],
-        new_memories_with_meta: Optional[List[Dict]] = None,
-    ) -> List[ReconcileOp]:
-        """reconcile 彻底失败时的兜底：把抽取结果**原样全部 ADD**。
-
-        为什么必须有这个兜底：reconcile 只是决定「新事实和旧记忆怎么合」。它挂了（网关 500、
-        JSON 解析不出）不代表抽取结果没价值 —— 此前的行为是把一整批完好的事实**全部丢弃**，
-        线上实测因此丢掉过整块内容（含评测题的正确答案）。宁可留重复也不要丢内容：
-        重复还能被后续 dedup / reconcile 收拾，丢了就永远找不回来。
-        """
-        metas = new_memories_with_meta or []
-        by_content = {
-            (m.get("content") or ""): m for m in metas if isinstance(m, dict)
-        }
-        ops: List[ReconcileOp] = []
-        for text in new_memories:
-            if not text:
-                continue
-            meta = by_content.get(text) or {}
-            ops.append(ReconcileOp(
-                op="ADD",
-                content=text,
-                layer=meta.get("layer"),
-                tags=meta.get("tags") or [],
-                owner=meta.get("owner"),
-                topic_paths=meta.get("topic_paths") or [],
-                event_facet=meta.get("event_facet") or {},
-                topic_assignments=meta.get("topic_assignments") or [],
-                topic_paths_provided=bool(
-                    meta.get("topic_paths_provided", "topic_paths" in meta)
-                ),
-                event_facet_provided=bool(
-                    meta.get("event_facet_provided", "event_facet" in meta)
-                ),
-                topic_assignments_provided=bool(meta.get(
-                    "topic_assignments_provided", "topic_assignments" in meta,
-                )),
-                reason="reconcile unavailable → stored as-is (degraded)",
-            ))
-        return ops
-
     async def reconcile(
         self,
         new_memories: List[str],
@@ -1088,8 +1045,8 @@ class MemoryReconciler:
                     )
                 except Exception as e:
                     # LLM 彻底不可用（provider 已按 max_retries 重试过，网关 500 /
-                    # 连接错误等）。**不能让它冒泡** —— 冒泡会让整批抽取结果连带丢弃。
-                    # 交给下面的 ADD-all 兜底。
+                    # 连接错误等）。不冒泡：下面统一记 RECONCILE 失败日志，再返回
+                    # success=False —— writer 不落任何新记忆，整次写入报失败。
                     _llm_error = f"{type(e).__name__}: {e}"
                     logger.warning(f"[reconciler] RECONCILE LLM unavailable: {_llm_error}")
                     break
@@ -1097,7 +1054,7 @@ class MemoryReconciler:
                 _tok_pt += response.prompt_tokens
                 _tok_ct += response.completion_tokens
                 _tok_total += response.tokens_used
-                raw_response = response.content
+                raw_response = response.content or ""
                 ops = self._parse_ops(raw_response)
                 ops = enforce_time_order(ops, current_time, candidate_map)
                 ops = self._inherit_exact_input_structure(
@@ -1106,7 +1063,9 @@ class MemoryReconciler:
                 if _structure_metadata_on:
                     ops = self._resolve_structure_references(ops, candidate_map)
 
-                _is_empty_array = self._strip_code_fence(raw_response) in ("[]", "")
+                # 只有字面量 "[]" 才是「模型判定无需任何操作」。HTTP 200 但 content
+                # 为空不是决策，是失败：按 EMPTY_RESPONSE 处理，不能当成 0 条成功。
+                _is_empty_array = self._strip_code_fence(raw_response) == "[]"
                 if ops or _is_empty_array:
                     _parse_ok = True
                     break
@@ -1136,7 +1095,7 @@ class MemoryReconciler:
                     error_msg = (
                         f"RECONCILE LLM returned empty response after {_n_attempts} attempts"
                     )
-                    error_code = "EMPTY_RESPONSE" 
+                    error_code = "EMPTY_RESPONSE"
                 logger.warning(f"[reconciler] {error_msg}")
 
                 if cache and request_id:
@@ -1153,14 +1112,13 @@ class MemoryReconciler:
                                 {
                                     "error": error_code,
                                     "message": error_msg,
-                                    "fallback": "ADD_ALL",
-                                    "fallback_count": len(new_memories or []),
+                                    "stored": 0,
                                 },
                                 ensure_ascii=False,
                             ),
                             elapsed_ms=recon_elapsed,
-                            # LLM 彻底不可用时 response 是 None —— 这行本身会抛
-                            # AttributeError，而它正好在兜底路径上，会把兜底也一起废掉
+                            # LLM 彻底不可用时 response 是 None —— 直接取属性会抛
+                            # AttributeError，把失败日志本身也废掉
                             prompt_tokens=getattr(response, "prompt_tokens", 0) or 0,
                             completion_tokens=getattr(response, "completion_tokens", 0) or 0,
                             total_tokens=getattr(response, "tokens_used", 0) or 0,
@@ -1170,22 +1128,16 @@ class MemoryReconciler:
                             f"[reconciler] store failed RECONCILE log failed: {e}"
                         )
 
-                # 兜底：JSON 解析不出来不等于抽取结果没价值 —— 全部 ADD，别丢内容。
-                _fb = self._fallback_add_ops(new_memories, new_memories_with_meta)
-                logger.warning(
-                    f"[reconciler] falling back to ADD-all: {len(_fb)} memories "
-                    f"({error_code})"
-                )
+                # 不做 ADD-all 兜底：没经过判重 / 演化的整批 ADD 会在重跑时产生重复，
+                # 而且调用方看到 success 就不会重试。这里报失败、不落库，由调用方重跑。
                 return ReconcileResult(
-                    ops=_fb,
-                    success=bool(_fb),
-                    error=None if _fb else error_msg,
-                    degraded=bool(_fb),
-                    degraded_reason=error_code,
+                    ops=[],
+                    success=False,
+                    error=error_msg,
+                    error_code=error_code,
                     prompt_tokens=_tok_pt,
                     completion_tokens=_tok_ct,
                     total_tokens=_tok_total,
-                    new_memory_embeddings=new_memory_embeddings,
                 )
 
             # 写 RECONCILE pipeline log
@@ -1250,20 +1202,14 @@ class MemoryReconciler:
 
         except Exception as e:
             logger.error(f"[reconciler] failed: {e}", exc_info=True)
-            # 兜底同样适用于「reconcile 链路任意环节炸了」（候选检索、embed、
-            # prompt 组装…）。此前这里返回 ops=[] → writer 直接丢弃整批抽取结果。
-            _fb = self._fallback_add_ops(new_memories, new_memories_with_meta)
-            if _fb:
-                logger.warning(
-                    f"[reconciler] falling back to ADD-all after unexpected error: "
-                    f"{len(_fb)} memories"
-                )
-                return ReconcileResult(
-                    ops=_fb, success=True,
-                    degraded=True, degraded_reason=f"EXCEPTION:{type(e).__name__}",
-                    new_memory_embeddings=dict(new_memory_embeddings or {}),
-                )
-            return ReconcileResult(ops=[], success=False, error=str(e))
+            # reconcile 链路任意环节炸了（候选检索、embed、prompt 组装…）：此时还
+            # 没有任何新记忆落库，报失败让整次写入可以干净地重跑。
+            return ReconcileResult(
+                ops=[],
+                success=False,
+                error=f"{type(e).__name__}: {e}",
+                error_code="RECONCILE_EXCEPTION",
+            )
 
     @staticmethod
     def _inherit_exact_input_structure(

hy_memory/client.py

@@ -134,6 +134,7 @@ _WRITE_DIAGNOSTIC_KEYS = (
     "agent_status",
     "agent_error_code",
     "agent_error",
+    "reconcile_error_code",
     "l1_rollback",
     "l1_rollback_failed",
     "partial_agent_persist",
@@ -3032,7 +3033,9 @@ class HyMemoryClient:
                 # 版本演进链层（scene="coding" 独有）。放在 writer.write 之后、返回
                 # 之前，因为它只依赖对话原文，与向量层写入结果无关。
                 # best-effort：这层挂不上不影响本次 add 的向量层产出。
-                if scene_variant == "coding":
+                # 向量层写入失败（success=False）时跳过：调用方会重跑整段，失败的
+                # 那次不该先把改动记进演进链。
+                if scene_variant == "coding" and resp.get("success"):
                     resp["chain_rounds"] = self._observe_chain(
                         chat_messages, user_id=uid,
                         workspace_id=workspace_id, branch=branch,

hy_memory/coding/__init__.py

@@ -12,6 +12,7 @@ HY Memory - Coding Memory 模块
 
 from .types import (
     CodingMemory,
+    CodingWriteError,
     CodingMemoryDraft,
     ReconcileOp,
     WorkingFact,
@@ -26,6 +27,7 @@ from .types import (
 
 __all__ = [
     "CodingMemory",
+    "CodingWriteError",
     "CodingMemoryDraft",
     "ReconcileOp",
     "WorkingFact",

hy_memory/coding/extractor.py

@@ -33,7 +33,7 @@ from .preproc import (
     prepare_extractor_messages,
 )
 from .judge import _store_coding_log
-from .types import CodingMemoryDraft, WorkingFactDraft
+from .types import CodingMemoryDraft, CodingWriteError, WorkingFactDraft
 
 
 
@@ -217,6 +217,10 @@ class CodingMemoryExtractor:
         Returns:
             (经验草稿, 事实草稿)。两层都可能为空。只有显式启用
             verbatim_fallback_enabled 时，模型没产出 fact 才调用 _verbatim_fact。
+
+        Raises:
+            CodingWriteError: 未开启原文兜底时，LLM 调用失败（LLM_ERROR）、返回空
+                content（EMPTY_RESPONSE）或回复解析不出 JSON 对象（JSON_PARSE_FAILED）。
         """
         if not messages:
             return [], []
@@ -268,8 +272,9 @@ class CodingMemoryExtractor:
             )
         except Exception as e:
             logger.warning(f"[coding-extract] LLM call failed: {e}")
-            # 经验层不兜底。事实层原文兜底也默认关闭，避免 assistant/tool 轨迹被
-            # 当作 statement 直接展示；仅在配置显式开启时保留旧行为。
+            # 经验层不兜底。事实层原文兜底默认关闭，避免 assistant/tool 轨迹被
+            # 当作 statement 直接展示；关闭时 LLM 失败抛 CodingWriteError(LLM_ERROR)，
+            # 整次写入报失败，而不是「成功、0 条」。仅在配置显式开启时保留旧行为。
             verbatim = (
                 self._verbatim_fact(messages)
                 if self.verbatim_fallback_enabled else None
@@ -296,9 +301,33 @@ class CodingMemoryExtractor:
                 ),
                 elapsed_ms=round((time.perf_counter() - _t0) * 1000, 2),
             )
+            if not self.verbatim_fallback_enabled:
+                raise CodingWriteError(
+                    "LLM_ERROR",
+                    f"coding extract LLM call failed: {type(e).__name__}: {e}",
+                ) from e
             return [], ([verbatim] if verbatim else [])
         _elapsed = round((time.perf_counter() - _t0) * 1000, 2)
 
+        # 模型答了且没有可记的内容（如 {"experiences": [], "fact": null}）是正常的空
+        # 抽取；200 但 content 为空、或回复解析不出 JSON 对象，是模型失败，不能当成
+        # 「成功、0 条」。原文兜底显式开启时沿用旧行为（交给下面的 verbatim 兜底）。
+        failure = self._output_failure(resp.content)
+        if failure is not None and not self.verbatim_fallback_enabled:
+            code, message = failure
+            await _store_coding_log(
+                self.cache, request_id=request_id, user_id=user_id, agent_id=agent_id,
+                session_id=session_id or "", step="CODING_EXTRACT", prompt=prompt,
+                response=resp.content or "",
+                parsed=json.dumps(
+                    {"drafts": 0, "error": code, "message": message},
+                    ensure_ascii=False,
+                ),
+                elapsed_ms=_elapsed, prompt_tokens=resp.prompt_tokens,
+                completion_tokens=resp.completion_tokens, total_tokens=resp.tokens_used,
+            )
+            raise CodingWriteError(code, message)
+
         raw_experiences, raw_facts = self._parse_output(resp.content)
 
         # 经验层的 files 走规则抽取（整段轨迹碰过的文件）；事实层的 files 由 LLM
@@ -478,12 +507,22 @@ class CodingMemoryExtractor:
         return "\n".join(rows)
 
     @classmethod
-    def _parse_output(
-        cls, text: str
-    ) -> Tuple[List[Dict[str, Any]], List[Dict[str, Any]]]:
-        """宽松解析 LLM 输出 JSON，返回 (experiences, facts) 两个原始列表。"""
+    def _output_failure(cls, text: Optional[str]) -> Optional[Tuple[str, str]]:
+        """回复本身是失败时返回 (error_code, message)；正常（含空抽取）返回 None。"""
+        if not (text or "").strip():
+            return "EMPTY_RESPONSE", "coding extract LLM returned empty response"
+        if cls._load_output_object(text) is None:
+            return (
+                "JSON_PARSE_FAILED",
+                f"coding extract output is not a JSON object ({len(text)} chars)",
+            )
+        return None
+
+    @staticmethod
+    def _load_output_object(text: Optional[str]) -> Optional[Dict[str, Any]]:
+        """宽松解析 LLM 输出，返回顶层 JSON 对象；解析不出返回 None。"""
         if not text:
-            return [], []
+            return None
         s = text.strip()
         # 去 markdown fence
         if s.startswith("```"):
@@ -509,8 +548,17 @@ class CodingMemoryExtractor:
                     obj = json.loads(s[start: end + 1])
                 except Exception:
                     obj = None
+        return obj if isinstance(obj, dict) else None
 
-        if not isinstance(obj, dict):
+    @classmethod
+    def _parse_output(
+        cls, text: str
+    ) -> Tuple[List[Dict[str, Any]], List[Dict[str, Any]]]:
+        """宽松解析 LLM 输出 JSON，返回 (experiences, facts) 两个原始列表。"""
+        if not text:
+            return [], []
+        obj = cls._load_output_object(text)
+        if obj is None:
             logger.warning(
                 f"[coding-extract] failed to parse output ({len(text or '')} chars)"
             )

hy_memory/coding/fact_reconciler.py

@@ -18,6 +18,7 @@ import json
 import logging
 import os
 import uuid
+from dataclasses import dataclass, field
 from datetime import datetime
 from typing import Any, Dict, List, Optional, Tuple
 
@@ -34,6 +35,7 @@ from .types import (
 
 
     MAX_FACT_CHAIN_ENTRIES,
+    CodingWriteError,
     FactReconcileOp,
     WorkingFact,
     WorkingFactDraft,
@@ -259,6 +261,16 @@ def build_chain_summary_prompt(
     return with_output_language(prompt, code, explicit=explicit is not None), code
 
 
+@dataclass
+class FactReconcilePlan:
+    """plan() 的产物：覆盖判定已完成、尚未落库。apply() 才执行 store 操作。"""
+
+    drafts: List[WorkingFactDraft]
+    candidates: List[List[WorkingFact]] = field(default_factory=list)
+    supersedes: Dict[int, List[str]] = field(default_factory=dict)
+    context: Dict[str, Any] = field(default_factory=dict)
+
+
 # ================================================================
 # WorkingFactReconciler
 # ================================================================
@@ -327,15 +339,63 @@ class WorkingFactReconciler:
         language: Optional[str] = None,
     ) -> Tuple[List[WorkingFact], List[FactReconcileOp]]:
         """
-        执行 reconcile + 持久化。memory_at 是这段对话的时间，记到新事实上。
-        language 为显式 prompt 语言码（None → zh/en 自动检测），同时用于演变总结。
+        执行 reconcile + 持久化（plan() 后紧接 apply()）。memory_at 是这段对话的
+        时间，记到新事实上。language 为显式 prompt 语言码（None → zh/en 自动检测），
+        同时用于演变总结。
 
         Returns:
-            (真正落库的新事实, 执行过的 ops)。LLM 挂掉时退化为全 INSERT 不覆盖，
-            宁可多留一条过期事实，也不因为一次调用失败丢结论。
+            (真正落库的新事实, 执行过的 ops)。
+
+        Raises:
+            CodingWriteError(RECONCILE_FAILED)：覆盖判定的 LLM 失败 / 空回复 /
+                解析不出。此时既不插入新事实，也不覆盖任何旧事实。
         """
+        plan = await self.plan(
+            drafts,
+            user_id=user_id,
+            agent_id=agent_id,
+            session_id=session_id,
+            workspace_id=workspace_id,
+            branch=branch,
+            source=source,
+            memory_at=memory_at,
+            language=language,
+        )
+        return await self.apply(plan)
+
+    async def plan(
+        self,
+        drafts: List[WorkingFactDraft],
+        *,
+        user_id: str,
+        agent_id: str = "default_agent",
+        session_id: Optional[str] = None,
+        workspace_id: Optional[str] = None,
+        branch: Optional[str] = None,
+        source: str = "default",
+        memory_at: Optional[datetime] = None,
+        language: Optional[str] = None,
+    ) -> FactReconcilePlan:
+        """检索 candidates + 覆盖判定，不落库。
+
+        没有任何候选时不调 LLM（全部 INSERT 是确定的结论，不是兜底）。调了 LLM 时，
+        有效回复 = JSON 对象且 "ops" 是列表（空列表 = 都不覆盖、只插入）。LLM 调用
+        失败（LLM_UNAVAILABLE）、200 但 content 为空（EMPTY_RESPONSE）、回复不是
+        上述形状（JSON_PARSE_FAILED）时抛 CodingWriteError(RECONCILE_FAILED)。
+        此前 LLM 失败会退化为全 INSERT 不覆盖，留下本该被接续的旧事实。
+        """
+        context = dict(
+            user_id=user_id,
+            agent_id=agent_id,
+            session_id=session_id,
+            workspace_id=workspace_id,
+            branch=branch,
+            source=source,
+            memory_at=memory_at,
+            language=language,
+        )
         if not drafts:
-            return [], []
+            return FactReconcilePlan(drafts=[], context=context)
 
         candidates = await self._retrieve_candidates(
             drafts,
@@ -349,27 +409,37 @@ class WorkingFactReconciler:
 
         try:
             supersedes = await self._llm_decide(drafts, candidates, language=language)
+        except CodingWriteError:
+            raise
         except Exception as e:
-            logger.warning(
-                f"[fact-reconcile] LLM decide failed, insert without supersede: {e}"
-            )
-            supersedes = {}
+            logger.warning(f"[fact-reconcile] LLM decide failed: {e}")
+            raise CodingWriteError(
+                "RECONCILE_FAILED",
+                f"working fact reconcile LLM call failed: {type(e).__name__}: {e}",
+                cause="LLM_UNAVAILABLE",
+            ) from e
 
+        return FactReconcilePlan(
+            drafts=list(drafts),
+            candidates=candidates,
+            supersedes=supersedes,
+            context=context,
+        )
+
+    async def apply(
+        self, plan: FactReconcilePlan,
+    ) -> Tuple[List[WorkingFact], List[FactReconcileOp]]:
+        """执行 plan() 的决策（覆盖旧事实 + 插入新事实）。"""
+        if not plan.drafts:
+            return [], []
         facts, ops = await self._execute(
-            drafts,
-            candidates,
-            supersedes,
-            user_id=user_id,
-            agent_id=agent_id,
-            session_id=session_id,
-            workspace_id=workspace_id,
-            branch=branch,
-            source=source,
-            memory_at=memory_at,
-            language=language,
+            plan.drafts,
+            plan.candidates,
+            plan.supersedes,
+            **plan.context,
         )
         logger.info(
-            f"[fact-reconcile] drafts={len(drafts)} inserted={len(facts)} "
+            f"[fact-reconcile] drafts={len(plan.drafts)} inserted={len(facts)} "
             f"superseded={sum(1 for o in ops if o.action == 'SUPERSEDE')}"
         )
         return facts, ops
@@ -473,6 +543,11 @@ class WorkingFactReconciler:
             max_tokens=self.max_tokens,
             audit_stage="coding_fact_reconcile",
         )
+        failure = self._reply_failure(resp.content)
+        if failure is not None:
+            code, message = failure
+            logger.warning(f"[fact-reconcile] {code}: {message}")
+            raise CodingWriteError("RECONCILE_FAILED", message, cause=code)
         return self._parse_ops(resp.content)
 
     # ------------------------------------------------------------
@@ -599,11 +674,24 @@ class WorkingFactReconciler:
             rows.append(f"for draft[{i}]:\n" + "\n".join(cand_rows))
         return "\n\n".join(rows) if rows else "(none)"
 
+    @classmethod
+    def _reply_failure(cls, text: Optional[str]) -> Optional[Tuple[str, str]]:
+        """回复本身是失败时返回 (cause, message)；有效回复（含 {"ops": []}）返回 None。"""
+        if not (text or "").strip():
+            return "EMPTY_RESPONSE", "working fact reconcile LLM returned empty response"
+        obj = cls._load_object(text)
+        if not isinstance(obj, dict) or not isinstance(obj.get("ops"), list):
+            return (
+                "JSON_PARSE_FAILED",
+                f"working fact reconcile output has no ops list ({len(text)} chars)",
+            )
+        return None
+
     @staticmethod
-    def _parse_ops(text: str) -> Dict[int, List[str]]:
-        """宽松解析 ops，返回 {draft_idx: [fact_id...]}。"""
+    def _load_object(text: Optional[str]) -> Optional[Dict[str, Any]]:
+        """宽松解析出顶层 JSON 对象；解析不出返回 None。"""
         if not text:
-            return {}
+            return None
         s = text.strip()
         # 去 markdown fence
         if s.startswith("```"):
@@ -621,7 +709,14 @@ class WorkingFactReconciler:
                     obj = json.loads(s[start: end + 1])
                 except Exception:
                     obj = None
+        return obj if isinstance(obj, dict) else None
 
+    @classmethod
+    def _parse_ops(cls, text: str) -> Dict[int, List[str]]:
+        """宽松解析 ops，返回 {draft_idx: [fact_id...]}。"""
+        if not text:
+            return {}
+        obj = cls._load_object(text)
         if not isinstance(obj, dict):
             logger.warning(
                 f"[fact-reconcile] failed to parse ops output ({len(text or '')} chars)"
@@ -689,6 +784,11 @@ class WorkingFactReconciler:
                 memory_at=memory_at,
             )
 
+            # 先确认新事实能向量化，再去覆盖旧事实：否则 embedding 挂掉时旧事实
+            # 已被软删、新事实又落不了库，这条结论就凭空没了。失败抛
+            # CodingWriteError(EMBEDDING_FAILED)，整次写入报失败。
+            new_embedding = await self.store.embed_fact(new_fact)
+
             allowed = {c.fact_id for c in (candidates[idx] if idx < len(candidates) else [])}
             targets = [
                 fid for fid in supersedes.get(idx, [])
@@ -769,7 +869,9 @@ class WorkingFactReconciler:
                         )
 
             try:
-                await self.store.insert_fact(new_fact)
+                await self.store.insert_fact(new_fact, embedding=new_embedding)
+            except CodingWriteError:
+                raise
             except Exception as e:
                 logger.warning(f"[fact-reconcile] INSERT failed: {e}")
                 continue

hy_memory/coding/reconciler.py

@@ -7,6 +7,9 @@ Coding Memory Reconciler
         （DELETE 由 LLM 在 draft 与 candidate 关系中观察到"明确否定/作废"时附带产出）
 
 执行端：reconcile() 调用 store 完成实际 ADD / UPDATE / DELETE 持久化操作。
+CodingWriter 分两步用：先 plan()（检索 + LLM 决策，不落库），等经验层与事实层的
+模型决策都成功后再 apply()（落库）。LLM 失败 / 空回复 / 解析不出时 plan() 抛
+CodingWriteError(RECONCILE_FAILED)，本次写入什么都不存。
 
 复用 LLMConfig.model（与 chat reconciler 共用）。
 
@@ -17,6 +20,7 @@ import json
 import logging
 import time
 import uuid
+from dataclasses import dataclass, field
 from typing import Any, Dict, List, Optional, Tuple
 
 from ..agent.llm_provider import LLMProvider
@@ -29,7 +33,7 @@ from ..prompts import (
 )
 from .judge import _store_coding_log
 from .store import CodingMemoryStore
-from .types import CodingMemory, CodingMemoryDraft, ReconcileOp
+from .types import CodingMemory, CodingMemoryDraft, CodingWriteError, ReconcileOp
 
 
 
@@ -93,6 +97,15 @@ def build_experience_reconcile_prompt(
     return with_output_language(prompt, code, explicit=explicit is not None), code
 
 
+@dataclass
+class ExperienceReconcilePlan:
+    """plan() 的产物：模型已决策、尚未落库。apply() 才执行 store 操作。"""
+
+    drafts: List[CodingMemoryDraft]
+    candidates_per_draft: List[List[CodingMemory]] = field(default_factory=list)
+    ops: List[ReconcileOp] = field(default_factory=list)
+
+
 # ================================================================
 # CodingMemoryReconciler
 # ================================================================
@@ -143,21 +156,52 @@ class CodingMemoryReconciler:
         language: Optional[str] = None,
     ) -> List[ReconcileOp]:
         """
-        执行 reconcile + 持久化。返回执行的 ReconcileOp[]（含成功执行的 ADD/UPDATE/DELETE/SKIP）。
+        执行 reconcile + 持久化（plan() 后紧接 apply()）。返回执行的 ReconcileOp[]
+        （含成功执行的 ADD/UPDATE/DELETE/SKIP）。
 
-        执行错误（如 LLM 失败）会 fail-safe 回退到对每个 draft 直接 ADD。
+        LLM 失败、空回复或解析不出时抛 CodingWriteError(RECONCILE_FAILED)，什么都
+        不落库——不再回退成「全部 ADD」。
+        """
+        plan = await self.plan(
+            drafts,
+            request_id=request_id,
+            user_id=user_id,
+            agent_id=agent_id,
+            session_id=session_id,
+            language=language,
+        )
+        return await self.apply(plan)
 
-        cache 非空时落 CODING_RECONCILE pipeline log——在 LLM 决策后、执行入库前打点，
-        这样即使 store 入库崩溃，reconcile 决策仍已可见（crash 不丢）。
+    async def plan(
+        self,
+        drafts: List[CodingMemoryDraft],
+        *,
+        request_id: str = "",
+        user_id: str = "",
+        agent_id: str = "default_agent",
+        session_id: str = "",
+        language: Optional[str] = None,
+    ) -> ExperienceReconcilePlan:
+        """检索 candidates + LLM 决策，不落库。
+
+        有效回复 = 一个 JSON 对象，其 "ops" 是列表：
+          - {"ops": []}：模型判定「无需任何操作」（与 chat reconcile 的 [] 同义），
+            成功、本层什么都不存；
+          - 非空列表：至少要有一条可识别的 op（ADD/UPDATE/DELETE/SKIP），否则视为
+            解析失败。漏掉的 draft 仍按原规则补 ADD（那是对有效回复的校验兜底，
+            不是模型失败兜底）。
+        LLM 调用失败（LLM_UNAVAILABLE）、200 但 content 为空（EMPTY_RESPONSE）、
+        回复不是上述形状（JSON_PARSE_FAILED）时抛 CodingWriteError(RECONCILE_FAILED)。
+
+        cache 非空时落 CODING_RECONCILE pipeline log（成功、失败都落）。
         """
         if not drafts:
-            return []
+            return ExperienceReconcilePlan(drafts=[])
 
         # 从 draft 回填 trace 身份（writer 通常显式传，这里兜底）
-        if drafts:
-            user_id = user_id or drafts[0].user_id
-            agent_id = agent_id or drafts[0].agent_id
-            session_id = session_id or (drafts[0].session_id or "")
+        user_id = user_id or drafts[0].user_id
+        agent_id = agent_id or drafts[0].agent_id
+        session_id = session_id or (drafts[0].session_id or "")
 
         # 1. 检索 candidates
         candidates_per_draft: List[List[CodingMemory]] = await self._retrieve_candidates(drafts)
@@ -167,19 +211,20 @@ class CodingMemoryReconciler:
         _decide_prompt = ""
         _decide_raw = ""
         _decide_resp = None
+        failure: Optional[Tuple[str, str]] = None
+        ops: List[ReconcileOp] = []
         try:
             ops, _decide_prompt, _decide_raw, _decide_resp = await self._llm_decide(
                 drafts, candidates_per_draft, language=language,
             )
+            failure = self._reply_failure(_decide_raw)
         except Exception as e:
-            logger.warning(f"[coding-reconcile] LLM decide failed, fallback to ADD-all: {e}")
-            ops = [ReconcileOp(action="ADD", draft_idx=i) for i in range(len(drafts))]
+            logger.warning(f"[coding-reconcile] LLM decide failed: {e}")
             _decide_raw = f"[LLM error] {type(e).__name__}: {str(e)[:300]}"
-
-        if not ops:
-            # LLM 输出无 ops，但有 drafts → fallback ADD-all
-            logger.info("[coding-reconcile] LLM returned no ops, fallback to ADD-all")
-            ops = [ReconcileOp(action="ADD", draft_idx=i) for i in range(len(drafts))]
+            failure = (
+                "LLM_UNAVAILABLE",
+                f"coding reconcile LLM call failed: {type(e).__name__}: {e}",
+            )
 
         _decide_elapsed = round((time.perf_counter() - _t0) * 1000, 2)
         # CODING_RECONCILE：LLM 决策完成即打点（执行入库之前，crash 不丢）
@@ -187,17 +232,42 @@ class CodingMemoryReconciler:
             self.cache, request_id=request_id, user_id=user_id, agent_id=agent_id,
             session_id=session_id, step="CODING_RECONCILE",
             prompt=_decide_prompt, response=_decide_raw,
-            parsed=json.dumps({"ops": [o.to_dict() for o in ops]}, ensure_ascii=False, default=str),
+            parsed=json.dumps(
+                {"error": failure[0], "message": failure[1], "stored": 0}
+                if failure else {"ops": [o.to_dict() for o in ops]},
+                ensure_ascii=False, default=str,
+            ),
             elapsed_ms=_decide_elapsed,
             prompt_tokens=getattr(_decide_resp, "prompt_tokens", 0) if _decide_resp else 0,
             completion_tokens=getattr(_decide_resp, "completion_tokens", 0) if _decide_resp else 0,
             total_tokens=getattr(_decide_resp, "tokens_used", 0) if _decide_resp else 0,
         )
+        if failure is not None:
+            code, message = failure
+            logger.warning(f"[coding-reconcile] {code}: {message}")
+            raise CodingWriteError("RECONCILE_FAILED", message, cause=code)
 
-        # 3. 校验 + 执行
-        executed = await self._execute(ops, drafts, candidates_per_draft)
+        return ExperienceReconcilePlan(
+            drafts=list(drafts),
+            candidates_per_draft=candidates_per_draft,
+            ops=ops,
+        )
+
+    async def apply(self, plan: ExperienceReconcilePlan) -> List[ReconcileOp]:
+        """执行 plan() 的决策（store ADD / UPDATE / DELETE）。"""
+        if not plan.drafts:
+            return []
+        if not plan.ops:
+            # 有效的 {"ops": []}：模型判定无需任何操作，本层什么都不存。
+            logger.info(
+                f"[coding-reconcile] drafts={len(plan.drafts)} LLM decided no ops"
+            )
+            return []
+        executed = await self._execute(
+            plan.ops, plan.drafts, plan.candidates_per_draft,
+        )
         logger.info(
-            f"[coding-reconcile] drafts={len(drafts)} ops={len(executed)} "
+            f"[coding-reconcile] drafts={len(plan.drafts)} ops={len(executed)} "
             + ", ".join(f"{a}={sum(1 for o in executed if o.action == a)}"
                         for a in ("ADD", "UPDATE", "DELETE", "SKIP"))
         )
@@ -316,11 +386,30 @@ class CodingMemoryReconciler:
             rows.append(f"for draft[{i}]:\n" + "\n".join(cand_rows))
         return "\n\n".join(rows) if rows else "(none)"
 
+    @classmethod
+    def _reply_failure(cls, text: Optional[str]) -> Optional[Tuple[str, str]]:
+        """回复本身是失败时返回 (cause, message)；有效回复（含 {"ops": []}）返回 None。"""
+        if not (text or "").strip():
+            return "EMPTY_RESPONSE", "coding reconcile LLM returned empty response"
+        obj = cls._load_object(text)
+        ops_raw = obj.get("ops") if isinstance(obj, dict) else None
+        if not isinstance(ops_raw, list):
+            return (
+                "JSON_PARSE_FAILED",
+                f"coding reconcile output has no ops list ({len(text)} chars)",
+            )
+        if ops_raw and not cls._parse_ops(text):
+            return (
+                "JSON_PARSE_FAILED",
+                f"coding reconcile output has no recognizable op ({len(text)} chars)",
+            )
+        return None
+
     @staticmethod
-    def _parse_ops(text: str) -> List[ReconcileOp]:
-        """宽松解析 ops 列表。"""
+    def _load_object(text: Optional[str]) -> Optional[Dict[str, Any]]:
+        """宽松解析出顶层 JSON 对象；解析不出返回 None。"""
         if not text:
-            return []
+            return None
         s = text.strip()
         # 去 markdown fence
         if s.startswith("```"):
@@ -344,8 +433,15 @@ class CodingMemoryReconciler:
                     obj = json.loads(s[start: end + 1])
                 except Exception:
                     obj = None
+        return obj if isinstance(obj, dict) else None
 
-        if not obj or not isinstance(obj, dict):
+    @classmethod
+    def _parse_ops(cls, text: str) -> List[ReconcileOp]:
+        """宽松解析 ops 列表。"""
+        if not text:
+            return []
+        obj = cls._load_object(text)
+        if not obj:
             logger.warning(
                 f"[coding-reconcile] failed to parse ops output ({len(text or '')} chars)"
             )
@@ -394,6 +490,9 @@ class CodingMemoryReconciler:
         - UPDATE  需 draft_idx 合法 + target_experience_id 非空
         - DELETE  需 target_experience_id 非空
         - SKIP    不执行任何 store 操作
+
+        向量化失败（CodingWriteError(EMBEDDING_FAILED)）不吞成「少执行一条」，
+        原样抛给 CodingWriter，整次写入报失败。
         """
         executed: List[ReconcileOp] = []
         # 已被 UPDATE 占用的 draft_idx → 防止同 draft 被重复 ADD/UPDATE
@@ -414,6 +513,8 @@ class CodingMemoryReconciler:
                     op.target_experience_id = memory.experience_id  # 回写 id 供 caller 读
                     executed.append(op)
                     consumed.add(op.draft_idx)
+                except CodingWriteError:
+                    raise
                 except Exception as e:
                     logger.warning(f"[coding-reconcile] ADD failed: {e}")
 
@@ -444,6 +545,8 @@ class CodingMemoryReconciler:
                     await self.store.update(memory)
                     executed.append(op)
                     consumed.add(op.draft_idx)
+                except CodingWriteError:
+                    raise
                 except Exception as e:
                     logger.warning(f"[coding-reconcile] UPDATE failed: {e}")
 
@@ -487,6 +590,8 @@ class CodingMemoryReconciler:
                     target_experience_id=memory.experience_id,
                     reason="fallback ADD (no LLM op)",
                 ))
+            except CodingWriteError:
+                raise
             except Exception as e:
                 logger.warning(f"[coding-reconcile] fallback ADD failed: {e}")
 

hy_memory/coding/store.py

@@ -44,7 +44,7 @@ from ..data.vector_store import create_vector_store
 from ..data.vector_store_base import VectorStoreBase
 from ..models.memory import MemoryLayer, MemoryNode, MemoryStatus
 from ..utils.async_executor import run_in_executor_guarded
-from .types import CodingMemory, WorkingFact
+from .types import CodingMemory, CodingWriteError, WorkingFact
 
 logger = logging.getLogger(__name__)
 
@@ -599,10 +599,15 @@ class CodingMemoryStore:
     # ------------------------------------------------------------
 
     async def insert(self, memory: CodingMemory) -> None:
-        """新增一条 coding memory（SQLite + VDB 全套）"""
+        """新增一条 coding memory（SQLite + VDB 全套）。
+
+        先向量化再落 SQLite：向量化失败抛 CodingWriteError(EMBEDDING_FAILED)，
+        什么都不写，不留一条没有向量、永远检索不到的经验。
+        """
         self._fill_timestamps(memory)
+        embeddings = await self._embed_vec_keys(memory)
         await _run_in_pool(self._upsert_sql_sync, memory)
-        await self._upsert_vec_keys(memory)
+        await self._upsert_vec_keys(memory, embeddings=embeddings)
         logger.info(
             f"[coding-store] inserted experience_id={memory.experience_id} "
             f"keys={1 + len(memory.search_keys)}"
@@ -627,6 +632,8 @@ class CodingMemoryStore:
         ):
             raise ValueError("coding_memory_update_authority_mismatch")
         prev_key_count = 1 + len(prev.search_keys)
+        # 先向量化：失败时旧经验（SQLite 与向量行）原样保留，不改一个字。
+        embeddings = await self._embed_vec_keys(memory)
 
         memory.updated_at = datetime.utcnow()
         if memory.created_at is None:
@@ -637,7 +644,7 @@ class CodingMemoryStore:
         # 删旧 VDB
         await self._delete_vec_keys_by_count(memory.experience_id, prev_key_count)
         # 写新 VDB
-        await self._upsert_vec_keys(memory)
+        await self._upsert_vec_keys(memory, embeddings=embeddings)
         logger.info(
             f"[coding-store] updated experience_id={memory.experience_id} "
             f"old_keys={prev_key_count} new_keys={1 + len(memory.search_keys)}"
@@ -1000,12 +1007,22 @@ class CodingMemoryStore:
     # 事实层
     # ------------------------------------------------------------
 
-    async def insert_fact(self, fact: WorkingFact) -> None:
-        """新增一条事实（SQLite + 事实 collection 各一行）。"""
+    async def insert_fact(
+        self, fact: WorkingFact, embedding: Optional[List[float]] = None,
+    ) -> None:
+        """新增一条事实（SQLite + 事实 collection 各一行）。
+
+        embedding 可由调用方预先用 embed_fact() 算好（fact reconcile 要在覆盖旧
+        事实之前确认新事实能向量化）；不传时这里算。向量化失败抛
+        CodingWriteError(EMBEDDING_FAILED)，什么都不写。
+        """
         if fact.created_at is None:
             fact.created_at = datetime.utcnow()
+        # 先向量化再落 SQLite，理由同 insert()：不落没有向量的事实。
+        if embedding is None:
+            embedding = await self.embed_fact(fact)
         await _run_in_pool(self._upsert_fact_sql_sync, fact)
-        await self._upsert_fact_vec(fact)
+        await self._upsert_fact_vec(fact, embedding=embedding)
         logger.info(f"[coding-store] inserted fact_id={fact.fact_id}")
         logger.debug(
             f"[coding-store] inserted fact_id={fact.fact_id} "
@@ -1574,25 +1591,64 @@ class CodingMemoryStore:
     # VDB 实现
     # ------------------------------------------------------------
 
-    async def _upsert_vec_keys(self, memory: CodingMemory) -> None:
-        """把 task + search_keys 写入 VDB（每行一个 MemoryNode）。"""
-        if self._vec is None:
-            return
-
+    @staticmethod
+    def _vec_key_texts(memory: CodingMemory) -> List[Tuple[str, str]]:
         all_keys: List[Tuple[str, str]] = [("task", memory.task)]
         for k in memory.search_keys:
             if k:
                 all_keys.append(("aspect", k))
+        return all_keys
+
+    async def _embed_vec_keys(
+        self, memory: CodingMemory
+    ) -> Optional[List[List[float]]]:
+        """写入链路用：向量化 task + search_keys，失败抛 CodingWriteError。
+
+        无 VDB 时返回 None（不需要向量）。
+        """
+        if self._vec is None:
+            return None
+        texts = [t for _, t in self._vec_key_texts(memory)]
+        try:
+            embeddings = await self.embed_service.embed_batch(texts)
+        except Exception as e:
+            logger.warning(f"[coding-store] embed_batch failed: {e}")
+            raise CodingWriteError(
+                "EMBEDDING_FAILED",
+                f"coding experience embedding failed: {type(e).__name__}: {e}",
+            ) from e
+        if len(embeddings or []) != len(texts) or not all(embeddings):
+            raise CodingWriteError(
+                "EMBEDDING_FAILED",
+                "coding experience embedding returned no vector",
+            )
+        return embeddings
+
+    async def _upsert_vec_keys(
+        self,
+        memory: CodingMemory,
+        embeddings: Optional[List[List[float]]] = None,
+    ) -> None:
+        """把 task + search_keys 写入 VDB（每行一个 MemoryNode）。
+
+        embeddings 由写入链路预先算好（见 _embed_vec_keys）；不传时现算，
+        失败只记 warning（edit_experience 的手动编辑路径沿用这一行为）。
+        """
+        if self._vec is None:
+            return
+
+        all_keys = self._vec_key_texts(memory)
         if not all_keys:
             return
 
         # batch embed
         texts = [t for _, t in all_keys]
-        try:
-            embeddings = await self.embed_service.embed_batch(texts)
-        except Exception as e:
-            logger.warning(f"[coding-store] embed_batch failed: {e}")
-            return
+        if embeddings is None:
+            try:
+                embeddings = await self.embed_service.embed_batch(texts)
+            except Exception as e:
+                logger.warning(f"[coding-store] embed_batch failed: {e}")
+                return
 
         nodes: List[MemoryNode] = []
         for i, ((kind, text), emb) in enumerate(zip(all_keys, embeddings)):
@@ -1623,7 +1679,34 @@ class CodingMemoryStore:
         except Exception as e:
             logger.warning(f"[coding-store] vdb upsert_batch failed: {e}")
 
-    async def _upsert_fact_vec(self, fact: WorkingFact) -> None:
+    @staticmethod
+    def _fact_vector_text(fact: WorkingFact) -> str:
+        return f"{fact.subject}: {fact.statement}" if fact.subject else fact.statement
+
+    async def embed_fact(self, fact: WorkingFact) -> Optional[List[float]]:
+        """写入链路用：向量化事实检索文本，失败抛 CodingWriteError。
+
+        无事实 VDB 或 statement 为空时返回 None（不需要向量）。
+        """
+        if self._fact_vec is None or not fact.statement:
+            return None
+        try:
+            embedding = await self.embed_service.embed(self._fact_vector_text(fact))
+        except Exception as e:
+            logger.warning(f"[coding-store] fact embed failed: {e}")
+            raise CodingWriteError(
+                "EMBEDDING_FAILED",
+                f"working fact embedding failed: {type(e).__name__}: {e}",
+            ) from e
+        if not embedding:
+            raise CodingWriteError(
+                "EMBEDDING_FAILED", "working fact embedding returned no vector",
+            )
+        return embedding
+
+    async def _upsert_fact_vec(
+        self, fact: WorkingFact, embedding: Optional[List[float]] = None,
+    ) -> None:
         """事实入向量库。一条事实一行，node_id 就是 fact_id。
 
         检索文本是 statement，前面缀上 subject（有的话）。subject 通常已经在
@@ -1634,14 +1717,14 @@ class CodingMemoryStore:
         """
         if self._fact_vec is None or not fact.statement:
             return
-        vector_text = (
-            f"{fact.subject}: {fact.statement}" if fact.subject else fact.statement
-        )
-        try:
-            embedding = await self.embed_service.embed(vector_text)
-        except Exception as e:
-            logger.warning(f"[coding-store] fact embed failed: {e}")
-            return
+        vector_text = self._fact_vector_text(fact)
+        if embedding is None:
+            # edit_fact 的手动编辑路径：现算，失败只记 warning。
+            try:
+                embedding = await self.embed_service.embed(vector_text)
+            except Exception as e:
+                logger.warning(f"[coding-store] fact embed failed: {e}")
+                return
 
         node = MemoryNode(
             node_id=fact.fact_id,

hy_memory/coding/types.py

@@ -25,6 +25,25 @@ FactStatus = Literal["active", "superseded"]
 MAX_FACT_CHAIN_ENTRIES = 8
 
 
+class CodingWriteError(RuntimeError):
+    """working / coding 写入链路里让整次写入失败的模型错误。
+
+    error_code 是稳定失败码，CodingWriter 原样透传为 agent_error_code：
+    - LLM_ERROR          抽取 LLM 调用失败
+    - EMPTY_RESPONSE     抽取 LLM 返回 200 但 content 为空
+    - JSON_PARSE_FAILED  抽取 LLM 的回复解析不出 JSON 对象
+    - EMBEDDING_FAILED   经验 / 事实向量化失败（不落没有向量的节点）
+    - RECONCILE_FAILED   经验 / 事实 reconcile 的模型决策失败；具体原因在 cause
+                         （LLM_UNAVAILABLE / EMPTY_RESPONSE / JSON_PARSE_FAILED），
+                         透传为 reconcile_error_code，与 chat 链路一致
+    """
+
+    def __init__(self, error_code: str, message: str, cause: Optional[str] = None):
+        super().__init__(message)
+        self.error_code = error_code
+        self.cause = cause
+
+
 def _epoch(value: Optional[datetime]) -> Optional[int]:
     """memory_at 对外是秒级 epoch，与 chat 一致。"""
     return int(value.timestamp()) if isinstance(value, datetime) else None

hy_memory/coding/writer.py

@@ -10,8 +10,9 @@ CodingWriter - 写入端协调器
              ├── recent history: 最近 K 个 user-turn（只作上下文）
              ├── new messages: 本次全部 turn（只做单条限长）
              ├── extractor.extract(...)            ← 一次 LLM 产出双层草稿
-             ├── reconciler.reconcile(经验草稿)     ← ADD/UPDATE/DELETE/SKIP
-             ├── fact_reconciler.reconcile(事实草稿) ← INSERT/SUPERSEDE
+             ├── reconciler.plan(经验草稿)          ← ADD/UPDATE/DELETE/SKIP 决策
+             ├── fact_reconciler.plan(事实草稿)      ← INSERT/SUPERSEDE 决策
+             ├── reconciler.apply / fact_reconciler.apply ← 两层决策都成功后才落库
              └── _crosslink(...)                   ← 同批全互链回填
 """
 
@@ -30,7 +31,7 @@ from .judge import classify_messages_is_coding
 from .preproc import has_any_tool_message, prepare_extractor_messages
 from .reconciler import CodingMemoryReconciler
 from .store import CodingMemoryStore
-from .types import FactReconcileOp, ReconcileOp, WorkingFact
+from .types import CodingWriteError, FactReconcileOp, ReconcileOp, WorkingFact
 
 logger = logging.getLogger(__name__)
 
@@ -104,6 +105,13 @@ class CodingWriter:
                 ],
                 "fact_ids": ["..."],         # 这趟真正落库的 fact_id
             }
+
+        模型失败（抽取 LLM 调用失败 / 空回复 / 解析不出）或向量化失败时返回
+        success=False，agent_error_code 为 LLM_ERROR / EMPTY_RESPONSE /
+        JSON_PARSE_FAILED / EMBEDDING_FAILED，error_code=502。经验层 / 事实层
+        reconcile 的模型决策失败时 agent_error_code=RECONCILE_FAILED，原因在
+        reconcile_error_code（LLM_UNAVAILABLE / EMPTY_RESPONSE / JSON_PARSE_FAILED），
+        本次什么都不落库。模型答了但没有值得记的内容仍是 success=True、0 条。
         """
         request_id = request_id or str(uuid.uuid4())
         t0 = time.perf_counter()
@@ -143,6 +151,10 @@ class CodingWriter:
         # 跟库里已有的什么关系是 reconcile 的事。把已有 task 摆到它面前，它会把
         # 一个其实不同的任务往清单里某个措辞上靠，reconciler 随后判成 UPDATE 合并
         # 掉，那个区别就没了——措辞对不上顶多多存一条，措辞被带偏是直接写错。
+        #
+        # 模型失败（LLM 调用失败 / 空回复 / 解析不出）抛 CodingWriteError：整次写入
+        # 报失败、什么都不存，连 trace 也不追加——调用方换个 request_id 重跑时，
+        # 历史窗口里不会多出这段本该是「新消息」的对话。
         try:
             drafts, fact_drafts = await self.extractor.extract(
                 messages,
@@ -156,26 +168,26 @@ class CodingWriter:
                 request_id=request_id,
                 language=language,
             )
-        finally:
-            # 历史服务于下一次 write；即使本次没跨过价值门槛，也不能丢掉上下文。
-            try:
-                await self.store.append_trace(
-                    current_messages,
-                    request_id=request_id,
-                    user_id=user_id,
-                    agent_id=agent_id or "default_agent",
-                    session_id=session_id,
-                    workspace_id=workspace_id,
-                    branch=branch,
-                    source=source,
-                )
-            except Exception as e:
-                logger.warning(f"[coding-write] append trace failed: {e}")
+        except CodingWriteError as e:
+            return self._failure_response(request_id, t0, e)
+
+        trace_kwargs = dict(
+            request_id=request_id,
+            user_id=user_id,
+            agent_id=agent_id or "default_agent",
+            session_id=session_id,
+            workspace_id=workspace_id,
+            branch=branch,
+            source=source,
+        )
 
         if not drafts and not fact_drafts:
+            # 模型答了、只是没有值得记的：正常的空抽取，仍算成功。历史服务于下一次
+            # write；即使本次没跨过价值门槛，也不能丢掉上下文。
             logger.info(
                 f"[coding-write] no drafts produced (value bar); request_id={request_id}"
             )
+            await self._append_trace(current_messages, **trace_kwargs)
             return self._empty_response(request_id, t0)
 
         # extractor 只负责内容；调用来源由 SDK 入口注入，不能交给 LLM 生成。
@@ -183,34 +195,51 @@ class CodingWriter:
             draft.source = source
             draft.memory_at = memory_at
 
-        # 3. 经验层 reconcile + 持久化
-        ops: List[ReconcileOp] = (
-            await self.reconciler.reconcile(
-                drafts,
-                request_id=request_id,
-                user_id=user_id,
-                agent_id=agent_id,
-                session_id=session_id or "",
-                language=language,
-            )
-            if drafts else []
-        )
-
-        # 4. 事实层 reconcile + 持久化（独立链路，不受经验层结果影响）
+        # 3. 两层 reconcile 的模型决策（只检索 + 调 LLM，不落库）
+        # 4. 两层决策都成功后才落库：经验层 apply → 事实层 apply
+        #
+        # 先把所有模型决策做完再写库，任何一层的决策失败（LLM 失败 / 空回复 /
+        # 解析不出 → CodingWriteError(RECONCILE_FAILED)）都发生在落库之前，本次
+        # 写入一条经验 / 事实都没存、也没覆盖旧事实，换个 request_id 重跑即干净。
+        # 两层决策互不依赖（各自检索各自的候选），提前做不改变结果。
+        #
+        # 向量化失败抛 CodingWriteError(EMBEDDING_FAILED)：不落没有向量的节点，
+        # 整次写入报失败。
         facts: List[WorkingFact] = []
         fact_ops: List[FactReconcileOp] = []
-        if fact_drafts:
-            facts, fact_ops = await self.fact_reconciler.reconcile(
-                fact_drafts,
-                user_id=user_id,
-                agent_id=agent_id,
-                session_id=session_id,
-                workspace_id=workspace_id,
-                branch=branch,
-                source=source,
-                memory_at=memory_at,
-                language=language,
+        ops: List[ReconcileOp] = []
+        try:
+            experience_plan = (
+                await self.reconciler.plan(
+                    drafts,
+                    request_id=request_id,
+                    user_id=user_id,
+                    agent_id=agent_id,
+                    session_id=session_id or "",
+                    language=language,
+                )
+                if drafts else None
             )
+            fact_plan = (
+                await self.fact_reconciler.plan(
+                    fact_drafts,
+                    user_id=user_id,
+                    agent_id=agent_id,
+                    session_id=session_id,
+                    workspace_id=workspace_id,
+                    branch=branch,
+                    source=source,
+                    memory_at=memory_at,
+                    language=language,
+                )
+                if fact_drafts else None
+            )
+            if experience_plan is not None:
+                ops = await self.reconciler.apply(experience_plan)
+            if fact_plan is not None:
+                facts, fact_ops = await self.fact_reconciler.apply(fact_plan)
+        except CodingWriteError as e:
+            return self._failure_response(request_id, t0, e)
 
         experience_ids = [op.target_experience_id for op in ops
                           if op.action in ("ADD", "UPDATE") and op.target_experience_id]
@@ -218,6 +247,7 @@ class CodingWriter:
 
         # 5. 同批全互链
         await self._crosslink(experience_ids, facts, user_id=user_id)
+        await self._append_trace(current_messages, **trace_kwargs)
 
         add_cnt = sum(1 for op in ops if op.action == "ADD")
         update_cnt = sum(1 for op in ops if op.action == "UPDATE")
@@ -298,6 +328,41 @@ class CodingWriter:
                         f"[coding-write] crosslink fact {f.fact_id} failed: {e}"
                     )
 
+    async def _append_trace(self, current_messages: List[ChatMessage], **kwargs) -> None:
+        """把本次对话追加进 recent trace（下一次 write 的历史上下文），best-effort。"""
+        try:
+            await self.store.append_trace(current_messages, **kwargs)
+        except Exception as e:
+            logger.warning(f"[coding-write] append trace failed: {e}")
+
+    def _failure_response(
+        self, request_id: str, t0: float, error: CodingWriteError,
+    ) -> Dict[str, Any]:
+        """模型 / 向量化失败：success=False，稳定失败码在 agent_error_code。
+
+        形状与 chat 链路的失败回执一致（error_code=502，error_message 带
+        「[CODE] 」前缀），调用方据 success 判定并重跑。
+        """
+        code = error.error_code
+        cause = getattr(error, "cause", None)
+        message = f"{cause}: {error}" if cause else str(error)
+        logger.warning(
+            f"[coding-write] failed: code={code} request_id={request_id}: {message}"
+        )
+        resp = self._empty_response(request_id, t0)
+        resp.update({
+            "success": False,
+            "error_code": 502,
+            "error_message": f"[{code}] {message}",
+            "agent_status": "failed",
+            "agent_error_code": code,
+            "agent_error": message,
+        })
+        if cause:
+            # 与 chat 链路一致：reconcile 失败的具体原因
+            resp["reconcile_error_code"] = cause
+        return resp
+
     def _empty_response(self, request_id: str, t0: float) -> Dict[str, Any]:
         return {
             "success": True,

hy_memory/config.py

@@ -432,6 +432,14 @@ class RecallConfig:
     retrieval_clauses_require_keyword: bool = None  # env: MEMORY_RETRIEVAL_CLAUSES_REQUIRE_KEYWORD
     retrieval_clauses_min_keyword_score: float = None  # normalized BM25 floor
     supplemental_propositions_enabled: bool = None  # env: MEMORY_SUPPLEMENTAL_PROPOSITIONS_ENABLED
+    # ── Intention（L7）判重 ──
+    # 开启（默认）：召回时同 user+agent+同天 memory_at+同 valid_until 且
+    # cosine≥阈值 的意图视为复本，只返回最早一条，其余异步从 VDB 删除（历史行为）。
+    # 关闭：读侧与写入侧批内都不判重——不隐藏、不丢弃、不删除任何意图。
+    intention_dedup_enabled: bool = None       # env: MEMORY_INTENTION_DEDUP_ENABLED
+    # 读侧意图判重 cosine 阈值。env: MEMORY_INTENTION_DEDUP_THRESHOLD，
+    # 未设置时回退到共享的 MEMORY_DEDUP_THRESHOLD（兼容旧部署），默认 0.95。
+    intention_dedup_threshold: float = None
 
     # 最小分数阈值
     min_score_threshold: float = 0.0
@@ -750,6 +758,15 @@ class RecallConfig:
             self.supplemental_propositions_enabled = _get_env_bool(
                 "MEMORY_SUPPLEMENTAL_PROPOSITIONS_ENABLED", False
             )
+        if self.intention_dedup_enabled is None:
+            self.intention_dedup_enabled = _get_env_bool(
+                "MEMORY_INTENTION_DEDUP_ENABLED", True
+            )
+        if self.intention_dedup_threshold is None:
+            self.intention_dedup_threshold = _get_env_float(
+                "MEMORY_INTENTION_DEDUP_THRESHOLD",
+                _get_env_float("MEMORY_DEDUP_THRESHOLD", 0.95),
+            )
 
 
 @dataclass
@@ -1384,6 +1401,8 @@ class MemoryConfig:
                 "supplemental_propositions_enabled": (
                     self.recall.supplemental_propositions_enabled
                 ),
+                "intention_dedup_enabled": self.recall.intention_dedup_enabled,
+                "intention_dedup_threshold": self.recall.intention_dedup_threshold,
             },
             "pipeline": {
                 "default_version": self.pipeline.default_version,

hy_memory/pipelines/_retrieval/intention.py

@@ -15,6 +15,9 @@ HY Memory - Intention (L7) 召回 + 惰性过期转换 + 复本判定
     → 视为同一个意图的复本（extractor 复读机 / 多 session 重复表达）。
     保留组里 `gmt_created` 最早的（老的先来先得，稳定 id）；
   - **异步删库**：其余复本 fire-and-forget 从 VDB 删除，不影响本次调用 RT。
+  - **开关**：判重受 `MemoryConfig.recall.intention_dedup_enabled`（默认开）与
+    `recall.intention_dedup_threshold` 控制，由 reader 按 client 配置传入。
+    关闭时完全跳过判重：不隐藏、不删除任何意图（写入侧批内判重同样跳过）。
 
 Q: 为什么要看 memory_at 和 valid_until？
 A: 意图是 point-in-time 信号。同一句"我周五要开会"，如果一条 memory_at 在
@@ -38,8 +41,14 @@ from ...models.memory import MemoryLayer, MemoryStatus
 logger = logging.getLogger(__name__)
 
 
-def _get_dedup_threshold() -> float:
-    """去重 cosine 阈值：沿用 dedup 内核的 MEMORY_DEDUP_THRESHOLD，默认 0.95。"""
+def _get_dedup_threshold(configured: Optional[float] = None) -> float:
+    """去重 cosine 阈值：优先用 client 配置；否则（或配置非法）沿用 dedup 内核的
+    MEMORY_DEDUP_THRESHOLD，默认 0.95。"""
+    try:
+        if configured is not None:
+            return float(configured)
+    except (TypeError, ValueError):
+        logger.warning(f"[intention] invalid dedup threshold: {configured!r}")
     try:
         return float(os.environ.get("MEMORY_DEDUP_THRESHOLD", 0.95))
     except (TypeError, ValueError):
@@ -244,6 +253,8 @@ async def recall_intentions(
     stats_out: Optional[Dict[str, Any]] = None,
     include_sources: Optional[List[str]] = None,
     exclude_sources: Optional[List[str]] = None,
+    dedup_enabled: bool = True,
+    dedup_threshold: Optional[float] = None,
 ) -> List[Dict[str, Any]]:
     """
     召回未过期的 L7_INTENTION 节点（VDB），惰性过期转 L2_FACT，判重并异步删复本。
@@ -260,6 +271,11 @@ async def recall_intentions(
         now: 当前时间（默认 datetime.now()，测试可注入）
         stats_out: 可选 dict，本函数把分段耗时与数量**原地回填**进去，供调用方落
             READ_INTENTION pipeline log。传 None 则完全不统计（零开销）。
+        dedup_enabled: 是否执行读侧判重（及复本异步删库）。False 时跳过判重，
+            所有未过期意图原样返回，不删除任何节点。默认 True（历史行为）。
+        dedup_threshold: 判重 cosine 阈值。None 时回退到 env
+            MEMORY_DEDUP_THRESHOLD（默认 0.95），兼容直接调用本函数的旧代码；
+            reader 总是传入 `recall.intention_dedup_threshold`。
 
     Returns:
         [{"node_id", "score", "node", "layer": "l7_intention", "source": "vdb_intention"}, ...]
@@ -272,7 +288,7 @@ async def recall_intentions(
     埋点字段（回填进 stats_out）:
       耗时(ms): vdb_search_ms / expire_ms / backfill_embed_ms / dedup_ms / total_ms
       数量: fetched / expired / survivors / dedup_dropped / returned
-      配置: fetch_limit / out_limit / dedup_threshold
+      配置: fetch_limit / out_limit / dedup_enabled / dedup_threshold
       说明: expire_ms、backfill_embed_ms 只有真的发生了对应操作才非 0，
             借此可判断慢在 VDB 检索、逐条过期转换、补拉向量还是判重计算。
     """
@@ -358,7 +374,7 @@ async def recall_intentions(
     _t = time.perf_counter()
     _backfilled = 0
     _missing_cnt = 0
-    if survivors:
+    if survivors and dedup_enabled:  # 补拉只为判重；关闭时无需这次 VDB 读
         missing_ids = [
             h.get("node_id") for h in survivors
             if h.get("node_id") and not getattr(h.get("node"), "embedding", None)
@@ -391,18 +407,23 @@ async def recall_intentions(
     )
 
     # 2. 判重：同 user + 同天 memory_at + valid_until 同日 + cosine≥threshold
+    #    dedup_enabled=False → 完全跳过：不隐藏、不删除。
     _t = time.perf_counter()
-    threshold = _get_dedup_threshold()
-    try:
-        kept, delete_ids = _partition_duplicates(survivors, threshold)
-    except Exception as e:
-        # 任何 dedup 异常 → 降级为不去重（返回全部 survivors 截断 limit）
-        logger.warning(f"[intention] dedup partition failed, degrade to raw: {e}")
+    threshold = _get_dedup_threshold(dedup_threshold)
+    if dedup_enabled:
+        try:
+            kept, delete_ids = _partition_duplicates(survivors, threshold)
+        except Exception as e:
+            # 任何 dedup 异常 → 降级为不去重（返回全部 survivors 截断 limit）
+            logger.warning(f"[intention] dedup partition failed, degrade to raw: {e}")
+            kept, delete_ids = survivors, []
+    else:
         kept, delete_ids = survivors, []
     # 纯 CPU（cosine 两两比较）；survivors 多时可能显著
     _stat(
         dedup_ms=round((time.perf_counter() - _t) * 1000, 2),
         dedup_dropped=len(delete_ids),
+        dedup_enabled=bool(dedup_enabled),
         dedup_threshold=threshold,
     )
 

hy_memory/pipelines/reader_base.py

@@ -1856,6 +1856,12 @@ class BaseReadPipeline(ReadPipeline):
                     stats_out=_intent_stats,
                     include_sources=request.include_sources,
                     exclude_sources=request.exclude_sources,
+                    dedup_enabled=bool(getattr(
+                        self.config.recall, "intention_dedup_enabled", True
+                    )),
+                    dedup_threshold=getattr(
+                        self.config.recall, "intention_dedup_threshold", None
+                    ),
                 )
                 await trace_log.log_intention(
                     stats=_intent_stats,

hy_memory/pipelines/writer.py

@@ -73,6 +73,19 @@ def _write_apply_verify_enabled() -> bool:
 _RECONCILE_LOOP_USER_LOCKS = weakref.WeakKeyDictionary()
 
 
+class ReconcileFailure(str):
+    """reconcile 失败时 `_reconcile_and_store` 返回的 error：仍是错误信息字符串，
+    另带稳定的失败码 `code`（LLM_UNAVAILABLE / EMPTY_RESPONSE / JSON_PARSE_FAILED /
+    RECONCILE_EXCEPTION），供 writer 透传给调用方。"""
+
+    code: str = "RECONCILE_FAILED"
+
+    def __new__(cls, message: str, code: str = "RECONCILE_FAILED"):
+        obj = super().__new__(cls, message)
+        obj.code = code
+        return obj
+
+
 def _reconcile_user_lock(user_id: str) -> asyncio.Lock:
     loop = asyncio.get_running_loop()
     locks = _RECONCILE_LOOP_USER_LOCKS.get(loop)
@@ -635,6 +648,7 @@ class MemoryWriter(WritePipeline):
         不查 VDB、不做"新写入 vs 库里已有"的对比，避免给 VDB 增加读压力。
         库内存量污染由 recall 侧异步删除逐步清理。best-effort：任何异常都
         回退到"不判重、全写入"，绝不影响 upsert 主流程。
+        `recall.intention_dedup_enabled=False` 时跳过批内判重，全部写入。
         """
         if not intentions:
             return []
@@ -660,7 +674,11 @@ class MemoryWriter(WritePipeline):
         # ============ 批内 dedup（不查 VDB，只对本批 intentions 互斥判重） ============
         keep_mask: List[bool] = [True] * len(intentions)
         try:
-            dropped = self._intention_batch_dedup(intentions, embeddings)
+            dropped = (
+                self._intention_batch_dedup(intentions, embeddings)
+                if getattr(self.config.recall, "intention_dedup_enabled", True)
+                else []
+            )
             for i in dropped:
                 if 0 <= i < len(keep_mask):
                     keep_mask[i] = False
@@ -1257,15 +1275,6 @@ class MemoryWriter(WritePipeline):
             recon_tokens 含 prompt/completion/total（reconcile 链路 LLM 消耗）
         """
         stored_ids: List[str] = []
-        # Episode：本次写入归属的内部会话 id（跨 write 把"一件事"归到一起）。
-        # 只数 user 侧记忆（与 rolling summary 只数 pending_user_count 一致）——
-        # agent 侧记忆若参与计数会把 episode 提前撑到上限、切得过碎，白付摘要的 token。
-        episode_id = await self._resolve_episode_id(
-            request, _count_user_owned(new_memories_meta)
-        )
-        session_episode_id = self._session_episode_id(request)
-        if session_episode_id:
-            episode_id = session_episode_id
         # 关系图用：收集本次落库的 (node, op)，供 graph 投影建边。
         # 收 op 是为了拿 op.related（LLM 标注的 typed 关系）。
         graph_payload: List[Tuple[Any, Any]] = []
@@ -1292,7 +1301,32 @@ class MemoryWriter(WritePipeline):
         )
 
         if not recon_result.success:
-            return [], recon_result.error, {"add": 0, "supersede": 0, "update": 0, "total": 0}, {"prompt": 0, "completion": 0, "total": 0}
+            # reconcile 失败：本次一条新记忆都不落库（不做 ADD-all 兜底），由调用方重跑。
+            # episode 状态也还没推进，重跑不会把同一批记忆重复计数。
+            error = ReconcileFailure(
+                recon_result.error or "reconcile failed",
+                code=recon_result.error_code or "RECONCILE_FAILED",
+            )
+            logger.warning(
+                f"TRACE_PERF [{req_id}] S1_RECONCILE_FAILED "
+                f"code={error.code} candidates={len(new_memory_texts)} stored=0"
+            )
+            return [], error, {"add": 0, "supersede": 0, "update": 0, "total": 0}, {
+                "prompt": recon_result.prompt_tokens,
+                "completion": recon_result.completion_tokens,
+                "total": recon_result.total_tokens,
+            }
+
+        # Episode：本次写入归属的内部会话 id（跨 write 把"一件事"归到一起）。
+        # 只数 user 侧记忆（与 rolling summary 只数 pending_user_count 一致）——
+        # agent 侧记忆若参与计数会把 episode 提前撑到上限、切得过碎，白付摘要的 token。
+        # 放在 reconcile 成功之后：失败的写入不能推进 episode 计数。
+        episode_id = await self._resolve_episode_id(
+            request, _count_user_owned(new_memories_meta)
+        )
+        session_episode_id = self._session_episode_id(request)
+        if session_episode_id:
+            episode_id = session_episode_id
 
         # 分类统计
         _op_counts = {}
@@ -1303,16 +1337,7 @@ class MemoryWriter(WritePipeline):
         logger.info(
             f"TRACE_PERF [{req_id}] S1_RECONCILE_DONE "
             f"ops={len(recon_result.ops)} candidates={len(new_memory_texts)} | {_op_counts_str}"
-            + (f" | DEGRADED({recon_result.degraded_reason})"
-               if getattr(recon_result, "degraded", False) else "")
         )
-        if getattr(recon_result, "degraded", False):
-            # 走了 ADD-all 兜底：内容保住了，但没做去重/演化判定。必须可观测，
-            # 否则线上只会看到"记忆变多了"而不知道为什么。
-            logger.warning(
-                f"[write] reconcile degraded → ADD-all "
-                f"({recon_result.degraded_reason}), {len(recon_result.ops)} memories stored as-is"
-            )
         # 逐条 op 详情由 reconciler 的 "[reconciler] ops detail" 单条 JSON list 输出，
         # 这里不再逐条打印（避免重复刷屏）。
 
@@ -2502,12 +2527,10 @@ class MemoryWriter(WritePipeline):
             response.extra["extract_tokens"] = {"prompt": 0, "completion": 0, "total": 0}
 
             if recon_error is not None:
-                response.success = False
-                response.error_code = 502
-                response.error_message = f"[RECONCILE_FAILED] {recon_error}"
-                response.extra["agent_status"] = "failed"
-                response.extra["agent_error"] = recon_error
-                response.extra["agent_nodes"] = 0
+                # 与 write() 一致：reconcile 失败不落任何记忆，报失败供调用方重跑。
+                self._mark_reconcile_failure(response, recon_error)
+                response.extra["agent_mode"] = "extracted"
+                logger.warning(f"[write_extracted] reconcile failed: {recon_error}")
                 return response
 
             response.success = True
@@ -3526,12 +3549,11 @@ class MemoryWriter(WritePipeline):
                 response.extra["reconcile_ops"] = ops_counts
                 response.extra["reconcile_tokens"] = recon_tokens
                 if recon_error is not None:
+                    # stored_ids 为空：reconcile 失败时一条新记忆都不落库，write()
+                    # 随后回滚 L1_RAW（retry_safe=True），换个 request_id 重跑即可。
                     response.extra["agent_stored_ids"] = stored_ids
-                    self._mark_agent_failure(
-                        response,
-                        error_code="RECONCILE_FAILED",
-                        error_message=recon_error,
-                        agent_nodes=len(stored_ids),
+                    self._mark_reconcile_failure(
+                        response, recon_error, agent_nodes=len(stored_ids),
                     )
                     logger.warning(f"[write] reconcile failed: {recon_error}")
                     return
@@ -3654,6 +3676,29 @@ class MemoryWriter(WritePipeline):
         response.error_code = 502
         response.error_message = f"[{code}] {message}"
 
+    @classmethod
+    def _mark_reconcile_failure(
+        cls,
+        response: WriteResponse,
+        recon_error: str,
+        *,
+        agent_nodes: int = 0,
+    ) -> None:
+        """reconcile 失败：agent_error_code 恒为 RECONCILE_FAILED，具体原因
+        （LLM_UNAVAILABLE / EMPTY_RESPONSE / JSON_PARSE_FAILED / RECONCILE_EXCEPTION）
+        放在 reconcile_error_code。"""
+        reason = getattr(recon_error, "code", "") or "RECONCILE_FAILED"
+        response.extra["reconcile_error_code"] = reason
+        cls._mark_agent_failure(
+            response,
+            error_code="RECONCILE_FAILED",
+            error_message=(
+                f"{reason}: {recon_error}"
+                if reason != "RECONCILE_FAILED" else str(recon_error)
+            ),
+            agent_nodes=agent_nodes,
+        )
+
     async def _handle_agent_failure(self, request, response, agent_result, tracer_span, extract_timing: Optional[Dict[str, Any]] = None) -> None:
         """处理 agent extract 失败的情况。"""
         if agent_result is None:

memhub/MEMORY.md

@@ -137,6 +137,15 @@ memhub profile
 `user-profile` / `memhub profile` 调用 SDK `get_user_profile()`，返回组装后的
 用户长期画像，不通过普通 Search 拼装。
 
+读接口都回显 `user_id`（实际读的用户，未指定时为 `local`）：
+`GET /api/v2/memory-library`、`/memory-library/layers`、`/user-profile`、
+`/user-profile/versions`、`/home-summary`、`/memories/graph`、`/raw`，
+`POST /api/v2/context/search`、`/api/v1/recall`、`/api/v2/memories/ask`；
+`/memories/ask/stream` 写在第一个 `recall` 事件上。
+`DELETE /api/v2/memories/{id}` 只在删掉调用者自己的记忆时回 204；另一个用户的
+记忆和不存在的 ID 一律回 404 `memory_not_found`（不暴露是否存在），调用方按
+「已不存在」处理。
+
 返回值：
 
 ```python

memhub/README.md

@@ -18,7 +18,7 @@ If you run into a problem, please open an Issue with the version, platform,repro
 
 ## 发行与平台合同
 
-源码当前固定使用公开 PyPI 正式版 `hy-memory==2.0.11`。MemHub 源码版本为 `1.0.6`
+源码当前固定使用公开 PyPI 正式版 `hy-memory==2.0.12`。MemHub 源码版本为 `1.0.6`
 （build 37），GitHub 仓库为
 [`Tencent-Hunyuan/Hy-Memory`](https://github.com/Tencent-Hunyuan/Hy-Memory)，npm 包名为
 `memhub-cli`。当前代码架构见
@@ -118,7 +118,7 @@ MemHub 的 SQLite 数据默认位于 `~/.one-memory`，不在 npm 包或 Runtime
 
 ## Hy Memory
 
-SDK 依赖固定为公开 PyPI 正式版 `hy-memory==2.0.11`。SDK 配置、权限边界及 search
+SDK 依赖固定为公开 PyPI 正式版 `hy-memory==2.0.12`。SDK 配置、权限边界及 search
 返回格式见 [`MEMORY.md`](MEMORY.md)。HY search 返回的 `content` 已包含 SDK 统一生成的
 逻辑时间和演化上下文；调用方不应再次转换时间戳或重复拼接 `When`。
 

memhub/SBOM.spdx.json

@@ -2352,7 +2352,7 @@
     {
       "SPDXID": "SPDXRef-Package-hy-memory",
       "name": "hy-memory",
-      "versionInfo": "2.0.11",
+      "versionInfo": "2.0.12",
       "downloadLocation": "NOASSERTION",
       "filesAnalyzed": false,
       "licenseConcluded": "Apache-2.0",

memhub/THIRD_PARTY_NOTICES.md

@@ -9,7 +9,7 @@ Per-package license texts are not reproduced here yet; the license
 column is filled in as part of release review, and the SBOM records
 `NOASSERTION` until then rather than guessing.
 
-## hy-memory 2.0.11
+## hy-memory 2.0.12
 
 License: Apache-2.0
 

memhub/apps/cli/src/cli.ts

@@ -1938,7 +1938,7 @@ async function runCommand(
       return reject(
         descriptor,
         asJson,
-        "--user-id 和 --root 只能用于接入单个 hermes 来源（Hermes profile），用户 ID 只能是 1–64 位字母、数字、点、下划线或连字符。",
+        "--user-id 和 --root 只能用于接入单个 hermes 来源（Hermes profile），用户 ID 只能是 1–64 位字母、数字、点、下划线或连字符。用户 ID 不必等于 Hermes profile 名，例如 --user-id wife-work --root ~/.hermes/profiles/wife:work。",
       );
     }
     if (!parsed) return usage();
@@ -2328,29 +2328,41 @@ async function runCommand(
               ...userIdParameters(userId),
             }),
           );
+    // A delete answered 404 `memory_not_found` is already gone (deleted
+    // before, or never this user's): what was asked for holds, so it exits 0
+    // as committed and says so, instead of failing a retry or a double run.
+    const alreadyGone =
+      parsed.kind === "delete" &&
+      outcome.state === "rejected" &&
+      outcome.code === "memory_not_found";
+    const state = alreadyGone ? "committed" : outcome.state;
     const document = {
       schema_version: 2,
       product: PRODUCT,
       command: `memories ${parsed.kind}`,
-      state: outcome.state,
+      state,
       operation: parsed.kind,
       memory_id: parsed.memoryId,
-      ...(outcome.state === "committed"
-        ? parsed.kind === "update"
-          ? { result: outcome.data }
-          : {}
-        : { code: outcome.code }),
+      ...(alreadyGone
+        ? { already_gone: true }
+        : outcome.state === "committed"
+          ? parsed.kind === "update"
+            ? { result: outcome.data }
+            : {}
+          : { code: outcome.code }),
     };
     emit(
       asJson
         ? `${JSON.stringify(document)}\n`
-        : outcome.state === "committed"
-          ? `已${parsed.kind === "update" ? "更新" : "删除"}记忆 ${parsed.memoryId}\n`
-          : outcome.code === "memory_id_ambiguous"
-            ? "这个 ID 同时存在于多个场景；请加 --kind（以及 --variant）指明是哪一条。\n"
-            : `操作失败：${outcome.code}\n`,
+        : alreadyGone
+          ? `未找到记忆 ${parsed.memoryId}（可能已删除），无需再删。\n`
+          : outcome.state === "committed"
+            ? `已${parsed.kind === "update" ? "更新" : "删除"}记忆 ${parsed.memoryId}\n`
+            : outcome.code === "memory_id_ambiguous"
+              ? "这个 ID 同时存在于多个场景；请加 --kind（以及 --variant）指明是哪一条。\n"
+              : `操作失败：${outcome.code}\n`,
     );
-    return outcome.state === "committed" ? EXIT_OK : EXIT_FAILED;
+    return state === "committed" ? EXIT_OK : EXIT_FAILED;
   }
   if (
     named === "settings" &&

memhub/apps/cli/src/command-catalog.ts

@@ -258,7 +258,7 @@ export const COMMANDS: readonly CommandDescriptor[] = [
   {
     name: "sources",
     summary:
-      "列出来源，直接接入来源，或按 request id 查接入回执。connect 不加 --import 只授权（处理保持冻结：不导入历史、不扫描新会话）；加 --import 同时导入历史并开启持续同步，返回 request id。目录来自环境变量覆盖的来源必须加 --confirm-overrides。Hermes 的每个 profile 是一个独立用户：用 --user-id 和 --root 接入，授权并导入历史（会自动排除 ~/.hermes/profiles/**，各用户互不读取）。",
+      "列出来源，直接接入来源，或按 request id 查接入回执。connect 不加 --import 只授权（处理保持冻结：不导入历史、不扫描新会话）；加 --import 同时导入历史并开启持续同步，返回 request id。目录来自环境变量覆盖的来源必须加 --confirm-overrides。Hermes 的每个 profile 是一个独立用户：用 --user-id 和 --root 接入，授权并导入历史（任何层级的 profiles/ 目录都会被排除，各用户互不读取）。--root 不能是 profiles 目录本身，也不能与另一个用户的 Hermes 目录相同或互相包含（~/.hermes 与 ~/.hermes/profiles/<name> 除外）。",
     usage:
       "memhub sources list [--json]\n            memhub sources connect <id> [<id> ...] [--import] [--confirm-overrides] [--request-id <uuid>] [--json]\n            memhub sources connect hermes --user-id <id> --root <path> [--import] [--request-id <uuid>] [--json]\n            memhub sources connect --all-detected [--import] [--confirm-overrides] [--json]\n            memhub sources receipt <request-id> [--json]",
     options: [
@@ -270,7 +270,7 @@ export const COMMANDS: readonly CommandDescriptor[] = [
       {
         flag: "--user-id <id>",
         summary:
-          "只用于 hermes：这条接入属于哪个用户（默认 local）。和 --root 一起接入一个 Hermes profile，例如 --user-id wife --root ~/.hermes/profiles/wife；其他来源只能是 local。",
+          "只用于 hermes：这条接入属于哪个用户（默认 local）。和 --root 一起接入一个 Hermes profile，例如 --user-id wife --root ~/.hermes/profiles/wife；用户 ID 不必等于 profile 名，例如 --user-id wife-work --root ~/.hermes/profiles/wife:work。其他来源只能是 local。",
       },
       {
         flag: "--root <path>",
@@ -397,7 +397,7 @@ export const COMMANDS: readonly CommandDescriptor[] = [
   {
     name: "memories",
     summary:
-      "列出、搜索、查看、添加、修改或物理删除记忆（对话、工作、编码三个场景）。add 和 App 的「添加记忆」是同一个入口；delete 不可逆，需 --yes。",
+      "列出、搜索、查看、添加、修改或物理删除记忆（对话、工作、编码三个场景）。add 和 App 的「添加记忆」是同一个入口；delete 不可逆，需 --yes；要删的记忆已不存在（或不属于该用户）时提示未找到，按已删除处理并退出 0。",
     usage:
       "memhub memories list [--scene <all|chat|working|coding>] [--source <id>] [--query <text>] [--status <state>] [--offset <n>] [--limit <n>] [--user-id <id>] [--json]\n            memhub memories show <memory-id> [--kind <kind>] [--variant <variant>] [--user-id <id>] [--json]\n            memhub memories add <text> [--request-id <uuid>] [--user-id <id>] [--json]\n            memhub memories add --content-file <path> [--request-id <uuid>] [--user-id <id>] [--json]\n            memhub memories add-status <request-id> [--user-id <id>] [--json]\n            memhub memories update <memory-id> --content-file <path> [--kind <kind>] [--variant <variant>] [--task <text>] [--user-id <id>] [--json]\n            memhub memories delete <memory-id> [--kind <kind>] [--variant <variant>] [--yes] [--user-id <id>] [--json]",
     options: [
@@ -461,11 +461,12 @@ export const COMMANDS: readonly CommandDescriptor[] = [
   {
     name: "settings",
     summary:
-      "查看或切换记忆模式（lite / pro / ultra）。lite 不调用模型，只在原始对话里检索；pro 由模型提取记忆（System 1）；ultra 在 pro 之上每晚自动进化（System 2，使用知识图谱）。任何模式都保留全部原始对话。切换不迁移数据：已处理的不会重做，排队中的和新的按新模式处理；需 --yes，不加时只显示计划。环境变量 ONE_MEMORY_GRAPH_STORE 会强制 ultra。settings features 查看或开关 SDK 的可选检索与提取功能（全局设置，默认全部保持 SDK 默认值）：graph_rerank 图谱重排（仅 ultra）、same_series_timeline 同系列时间线（需 graph_rerank）、episode_recall 片段召回（pro / ultra，需先开 session_episodes 写入片段）、session_episodes 片段写入、episode_summary 片段摘要（每个片段一次模型调用）、intention 意图提取（默认开）、few_shot 提取示例；set 需 --yes，不加时只显示计划；reset 恢复默认值。settings language 查看或设置界面语言（App 切换语言时会自动设置）：简体中文（zh-Hans）和 system 不指定 SDK 语言，SDK 照旧自动识别中文或英文；其余语言（en、zh-Hant、ja、es、de、pt、fr、ko、ru、id）会让提取等 SDK 提示使用该语言，立即生效。",
+      "查看或切换记忆模式（lite / pro / ultra）。lite 不调用模型，只在原始对话里检索；pro 由模型提取记忆（System 1）；ultra 在 pro 之上每晚自动进化（System 2，使用知识图谱）。任何模式都保留全部原始对话。切换不迁移数据：已处理的不会重做，排队中的和新的按新模式处理；需 --yes，不加时只显示计划。环境变量 ONE_MEMORY_GRAPH_STORE 会强制 ultra。settings features 查看或开关 SDK 的可选检索与提取功能（全局设置，默认全部保持 SDK 默认值）：graph_rerank 图谱重排（仅 ultra）、same_series_timeline 同系列时间线（需 graph_rerank）、episode_recall 片段召回（pro / ultra，需先开 session_episodes 写入片段）、session_episodes 片段写入、episode_summary 片段摘要（每个片段一次模型调用）、intention 意图提取（默认开）、intention_dedup 意图判重（默认开；关闭则检索与写入都不判重、不删除意图）、few_shot 提取示例，以及数值 intention_dedup_threshold 意图判重阈值（默认 0.95，可设 0.8–1.0）；set 需 --yes，不加时只显示计划；reset 恢复默认值。settings language 查看或设置界面语言（App 切换语言时会自动设置）：简体中文（zh-Hans）和 system 不指定 SDK 语言，SDK 照旧自动识别中文或英文；其余语言（en、zh-Hant、ja、es、de、pt、fr、ko、ru、id）会让提取等 SDK 提示使用该语言，立即生效。",
     usage:
       "memhub settings mode [lite|pro|ultra] [--yes] [--json]\n" +
       "            memhub settings features [--json]\n" +
       "            memhub settings features set <name>=<true|false> [...] [--yes] [--json]\n" +
+      "            memhub settings features set intention_dedup_threshold=<0.8-1.0> [--yes] [--json]\n" +
       "            memhub settings features reset [<name> ...] [--json]\n" +
       "            memhub settings language [<code>|system] [--json]",
     options: [
@@ -476,7 +477,7 @@ export const COMMANDS: readonly CommandDescriptor[] = [
       {
         flag: "features set <name>=<true|false>",
         summary:
-          "开关一个或多个 SDK 功能；功能在当前模式下不生效时会注明原因（例如 graph_rerank 需要 ultra）。",
+          "开关一个或多个 SDK 功能；功能在当前模式下不生效时会注明原因（例如 graph_rerank 需要 ultra）。intention_dedup_threshold 取 0.8–1.0 的数值。",
       },
       {
         flag: "features reset [<name> ...]",

memhub/apps/cli/src/headless-flows.ts

@@ -348,12 +348,25 @@ export function parseApiKey(bytes: Buffer | null): string | undefined {
   return value;
 }
 
+/** What to do about a refusal whose code alone does not say. */
+const FLOW_CODE_HINTS: Record<string, string> = {
+  hermes_root_is_profiles_container:
+    "--root 指向的是 profiles 目录本身；请指向其中一个 profile，例如 ~/.hermes/profiles/wife。",
+  hermes_root_overlaps_other_user:
+    "--root 与另一个用户已接入的 Hermes 目录相同或互相包含，会读到对方的记录；请换一个目录，或先撤销对方的接入。~/.hermes 与 ~/.hermes/profiles/<name> 可以分属两个用户。",
+};
+
 export function renderFlowText(document: FlowDocument): string {
   const lines = [
     `操作状态：${document.state}`,
     `操作 ID：${document.operation_id ?? "无"}`,
     "code" in document ? `代码：${document.code}` : "已返回有界回执。",
   ];
+  const hint =
+    "code" in document && typeof document.code === "string"
+      ? FLOW_CODE_HINTS[document.code]
+      : undefined;
+  if (hint) lines.push(hint);
   // A partial success or an all-rejected batch must name each source that was
   // not accepted; a bare "partial" leaves the user with nothing to act on.
   if (

memhub/apps/cli/src/memories-cli.test.ts

@@ -366,6 +366,33 @@ describe("memories update / delete pass the namespace", () => {
     );
   });
 
+  it("reports a delete answered 404 as already gone and exits 0", async () => {
+    transport.delete.mockResolvedValue({
+      status: 404,
+      data: { detail: "memory_not_found" },
+    });
+    const json = await capturedRun([
+      "memories",
+      "delete",
+      "gone-1",
+      "--yes",
+      "--json",
+    ]);
+    expect(json.code).toBe(0);
+    expect(JSON.parse(json.stdout)).toEqual({
+      schema_version: 2,
+      product: expect.any(String),
+      command: "memories delete",
+      state: "committed",
+      operation: "delete",
+      memory_id: "gone-1",
+      already_gone: true,
+    });
+    const text = await capturedRun(["memories", "delete", "gone-1", "--yes"]);
+    expect(text.code).toBe(0);
+    expect(text.stdout).toContain("未找到记忆 gone-1");
+  });
+
   it("explains an ambiguous id instead of a bare code", async () => {
     transport.delete.mockResolvedValue({
       status: 409,

memhub/apps/cli/src/memory-features-cli.test.ts

@@ -36,15 +36,17 @@ const DEFAULTS: Record<string, boolean> = {
   session_episodes: false,
   episode_summary: false,
   intention: true,
+  intention_dedup: true,
   few_shot: false,
 };
+const THRESHOLD_DEFAULT = 0.95;
 
 function featuresState(
-  configured: Record<string, boolean> = {},
+  configured: Record<string, boolean | number> = {},
   mode = "pro",
   extra: Record<string, unknown> = {},
 ) {
-  const nonDefault: Record<string, boolean> = {};
+  const nonDefault: Record<string, boolean | number> = {};
   const features = Object.entries(DEFAULTS).map(([name, fallback]) => {
     const enabled = configured[name] ?? fallback;
     if (enabled !== fallback) nonDefault[name] = enabled;
@@ -70,7 +72,34 @@ function featuresState(
       description: name,
     };
   });
-  return { mode, features, non_default: nonDefault, ...extra };
+  const threshold =
+    (configured.intention_dedup_threshold as number | undefined) ??
+    THRESHOLD_DEFAULT;
+  if (threshold !== THRESHOLD_DEFAULT)
+    nonDefault.intention_dedup_threshold = threshold;
+  const dedupOn =
+    (configured.intention_dedup as boolean | undefined) ??
+    DEFAULTS.intention_dedup;
+  const parameters = [
+    {
+      name: "intention_dedup_threshold",
+      value: threshold,
+      configured:
+        "intention_dedup_threshold" in configured
+          ? configured.intention_dedup_threshold
+          : null,
+      default: THRESHOLD_DEFAULT,
+      minimum: 0.8,
+      maximum: 1,
+      active: dedupOn,
+      reason: dedupOn ? null : "requires_intention_dedup",
+      requires_feature: "intention_dedup",
+      sdk_field: "recall.intention_dedup_threshold",
+      env: "MEMORY_INTENTION_DEDUP_THRESHOLD",
+      description: "threshold",
+    },
+  ];
+  return { mode, features, parameters, non_default: nonDefault, ...extra };
 }
 
 beforeEach(() => {
@@ -110,11 +139,16 @@ describe("memhub settings features", () => {
     expect(result.code).toBe(0);
     const json = JSON.parse(result.stdout);
     expect(json.state).toBe("ok");
-    expect(json.features.features).toHaveLength(7);
+    expect(json.features.features).toHaveLength(8);
+    expect(json.features.parameters[0].name).toBe("intention_dedup_threshold");
     expect(transport.put).not.toHaveBeenCalled();
     const text = (await capturedRun(["settings", "features"])).stdout;
     expect(text).toContain("graph_rerank：关（默认）");
     expect(text).toContain("intention：开（默认）");
+    expect(text).toContain("intention_dedup：开（默认）");
+    expect(text).toContain(
+      "intention_dedup_threshold：0.95（默认，可设 0.8–1）",
+    );
     expect(text).toContain("先开启 session_episodes");
   });
 
@@ -160,6 +194,130 @@ describe("memhub settings features", () => {
     );
   });
 
+  it("turns intention dedup off and sets its threshold, round trip", async () => {
+    transport.put.mockResolvedValueOnce({
+      status: 200,
+      data: featuresState({ intention_dedup: false }, "pro", {
+        changed: ["intention_dedup"],
+      }),
+    });
+    const off = await capturedRun([
+      "settings",
+      "features",
+      "set",
+      "intention_dedup=false",
+      "--yes",
+      "--json",
+    ]);
+    expect(off.code).toBe(0);
+    expect(transport.put).toHaveBeenLastCalledWith(
+      "/api/v1/settings/memory-features",
+      { intention_dedup: false },
+      undefined,
+    );
+    const offJson = JSON.parse(off.stdout);
+    expect(offJson.state).toBe("committed");
+    expect(offJson.changed).toEqual(["intention_dedup"]);
+    expect(offJson.features.parameters[0].reason).toBe(
+      "requires_intention_dedup",
+    );
+
+    transport.get.mockResolvedValue({
+      status: 200,
+      data: featuresState({ intention_dedup: false }),
+    });
+    transport.put.mockResolvedValueOnce({
+      status: 200,
+      data: featuresState(
+        { intention_dedup: true, intention_dedup_threshold: 0.9 },
+        "pro",
+        { changed: ["intention_dedup", "intention_dedup_threshold"] },
+      ),
+    });
+    const on = await capturedRun([
+      "settings",
+      "features",
+      "set",
+      "intention_dedup=true",
+      "intention_dedup_threshold=0.9",
+      "--yes",
+    ]);
+    expect(on.code).toBe(0);
+    expect(transport.put).toHaveBeenLastCalledWith(
+      "/api/v1/settings/memory-features",
+      { intention_dedup: true, intention_dedup_threshold: 0.9 },
+      undefined,
+    );
+    expect(on.stdout).toContain(
+      "已更新：intention_dedup、intention_dedup_threshold",
+    );
+    expect(on.stdout).toContain("intention_dedup_threshold：0.9（已设置");
+
+    transport.get.mockResolvedValue({
+      status: 200,
+      data: featuresState({ intention_dedup_threshold: 0.9 }),
+    });
+    transport.put.mockResolvedValueOnce({
+      status: 200,
+      data: featuresState({}, "pro", {
+        changed: ["intention_dedup_threshold"],
+      }),
+    });
+    const reset = await capturedRun([
+      "settings",
+      "features",
+      "reset",
+      "intention_dedup_threshold",
+    ]);
+    expect(reset.code).toBe(0);
+    expect(transport.put).toHaveBeenLastCalledWith(
+      "/api/v1/settings/memory-features",
+      { intention_dedup_threshold: null },
+      undefined,
+    );
+  });
+
+  it("previews a threshold without --yes and refuses one out of range", async () => {
+    const preview = await capturedRun([
+      "settings",
+      "features",
+      "set",
+      "intention_dedup_threshold=0.85",
+    ]);
+    expect(preview.code).toBe(0);
+    expect(preview.stdout).toContain("- intention_dedup_threshold = 0.85");
+    for (const value of ["0.5", "0.79", "1.01", "2", "-0.9", "abc", "1e0"]) {
+      const result = await capturedRun([
+        "settings",
+        "features",
+        "set",
+        `intention_dedup_threshold=${value}`,
+        "--yes",
+      ]);
+      expect(result.code, value).toBe(2);
+    }
+    expect(transport.put).not.toHaveBeenCalled();
+  });
+
+  it("does not send a threshold to a Runtime that does not list it", async () => {
+    const { parameters: _unused, ...older } = featuresState();
+    transport.get.mockResolvedValue({ status: 200, data: older });
+    const result = await capturedRun([
+      "settings",
+      "features",
+      "set",
+      "intention_dedup_threshold=0.9",
+      "--yes",
+      "--json",
+    ]);
+    expect(result.code).toBe(1);
+    expect(JSON.parse(result.stdout)).toMatchObject({
+      state: "rejected",
+      code: "memory_feature_unsupported",
+    });
+    expect(transport.put).not.toHaveBeenCalled();
+  });
+
   it("does nothing when the values are already set", async () => {
     transport.get.mockResolvedValue({
       status: 200,
@@ -210,6 +368,8 @@ describe("memhub settings features", () => {
       ["settings", "features", "set", "graph_rerank=yes"],
       ["settings", "features", "set", "graph_rerank"],
       ["settings", "features", "set", "few_shot=true", "few_shot=false"],
+      ["settings", "features", "set", "intention_dedup=0.9"],
+      ["settings", "features", "set", "intention_dedup_threshold=true"],
       ["settings", "features", "reset", "nope"],
       ["settings", "features", "toggle"],
     ]) {
@@ -269,7 +429,11 @@ describe("status pipeline features", () => {
         last_evolve_at: null,
         graph_build: { state: "idle", users: {} },
         evolve: { mode: "pro", schedule: null, running: [], users: {} },
-        features: { episode_recall: true, intention: false },
+        features: {
+          episode_recall: true,
+          intention: false,
+          intention_dedup_threshold: 0.9,
+        },
       },
     };
     const report = await composeStatusReport({
@@ -284,9 +448,12 @@ describe("status pipeline features", () => {
     expect(report.pipeline?.features).toEqual({
       episode_recall: true,
       intention: false,
+      intention_dedup_threshold: 0.9,
     });
     const text = renderStatusText(report, "MemHub");
-    expect(text).toContain("SDK 功能：episode_recall=开、intention=关");
+    expect(text).toContain(
+      "SDK 功能：episode_recall=开、intention=关、intention_dedup_threshold=0.9",
+    );
   });
 });
 

memhub/apps/cli/src/memory-features-flow.ts

@@ -2,7 +2,8 @@
  * `memhub settings features [set <name>=<true|false> ... | reset [<name> ...]]`.
  *
  * The SDK's optional retrieval and extraction features (graph rerank, episode
- * recall, the episode write side, intention, few-shot). One global setting in
+ * recall, the episode write side, intention and its dedup, few-shot), plus the
+ * intention dedup threshold, the one numeric setting. One global setting in
  * the Runtime; an unset feature keeps the SDK default, so an install nobody
  * touched behaves as before. `set` prints its plan first and needs `--yes`,
  * like `settings mode`, because some features spend model calls; `reset`
@@ -20,10 +21,19 @@ export const MEMORY_FEATURES = [
   "session_episodes",
   "episode_summary",
   "intention",
+  "intention_dedup",
   "few_shot",
 ] as const;
 export type MemoryFeature = (typeof MEMORY_FEATURES)[number];
 
+/** Numeric settings, with the range the Runtime accepts (inclusive). */
+export const MEMORY_PARAMETERS = {
+  intention_dedup_threshold: { minimum: 0.8, maximum: 1 },
+} as const;
+export type MemoryParameter = keyof typeof MEMORY_PARAMETERS;
+export type MemorySetting = MemoryFeature | MemoryParameter;
+type SettingValues = Partial<Record<MemorySetting, boolean | number>>;
+
 const FEATURE_LABEL: Record<MemoryFeature, string> = {
   graph_rerank: "图谱重排（沿知识图谱的边传播支持度；仅 ultra）",
   same_series_timeline:
@@ -33,6 +43,8 @@ const FEATURE_LABEL: Record<MemoryFeature, string> = {
   session_episodes: "片段写入（同一会话提取的记忆归入同一片段）",
   episode_summary: "片段摘要（片段结束时总结一次；每个片段一次模型调用）",
   intention: "意图提取（随事实一起提取用户的计划与意图）",
+  intention_dedup:
+    "意图判重（检索时把同一天、相似度达到阈值的意图视为重复，只返回最早一条并删除其余；关闭则不判重、不删除）",
   few_shot: "提取示例（在提取提示里附上示例；不加调用，输入更长）",
 };
 
@@ -41,21 +53,42 @@ const REASON_TEXT: Record<string, string> = {
   requires_pro: "lite 模式下不生效（需要 pro 或 ultra）",
   requires_ultra: "当前模式下不生效（需要 ultra）",
   requires_graph_rerank: "需要先开启并生效 graph_rerank",
+  requires_intention_dedup: "intention_dedup 已关闭，阈值不起作用",
+};
+
+const PARAMETER_LABEL: Record<MemoryParameter, string> = {
+  intention_dedup_threshold: "意图判重阈值（余弦相似度，越高保留越多）",
 };
 
 export type FeaturesCommand =
   | { kind: "show" }
   | {
       kind: "set";
-      values: Partial<Record<MemoryFeature, boolean>>;
+      values: SettingValues;
       confirmed: boolean;
     }
-  | { kind: "reset"; names: MemoryFeature[] };
+  | { kind: "reset"; names: MemorySetting[] };
 
 function isFeature(value: string): value is MemoryFeature {
   return (MEMORY_FEATURES as readonly string[]).includes(value);
 }
 
+function isParameter(value: string): value is MemoryParameter {
+  return Object.hasOwn(MEMORY_PARAMETERS, value);
+}
+
+function isSetting(value: string): value is MemorySetting {
+  return isFeature(value) || isParameter(value);
+}
+
+/** A parameter's value: a plain decimal in its range; null = usage. */
+function parameterValue(name: MemoryParameter, raw: string): number | null {
+  if (!/^\d+(\.\d+)?$/.test(raw)) return null;
+  const value = Number(raw);
+  const { minimum, maximum } = MEMORY_PARAMETERS[name];
+  return value >= minimum && value <= maximum ? value : null;
+}
+
 /** Arguments after `settings features`; null = usage. */
 export function parseFeaturesCommand(
   values: readonly string[],
@@ -68,18 +101,28 @@ export function parseFeaturesCommand(
   const positional = tail.filter((value) => value !== "--yes");
   if (verb === "set") {
     if (positional.length === 0) return null;
-    const parsed: Partial<Record<MemoryFeature, boolean>> = {};
+    const parsed: SettingValues = {};
     for (const item of positional) {
-      const match = /^([a-z_]+)=(true|false)$/.exec(item);
-      if (!match || !isFeature(match[1]) || match[1] in parsed) return null;
-      parsed[match[1]] = match[2] === "true";
+      const match = /^([a-z_]+)=(.+)$/.exec(item);
+      if (!match || match[1] in parsed) return null;
+      const [, name, raw] = match;
+      if (isFeature(name)) {
+        if (raw !== "true" && raw !== "false") return null;
+        parsed[name] = raw === "true";
+      } else if (isParameter(name)) {
+        const value = parameterValue(name, raw);
+        if (value === null) return null;
+        parsed[name] = value;
+      } else {
+        return null;
+      }
     }
     return { kind: "set", values: parsed, confirmed: yes === 1 };
   }
   if (verb === "reset") {
     if (new Set(positional).size !== positional.length) return null;
-    if (!positional.every(isFeature)) return null;
-    return { kind: "reset", names: positional as MemoryFeature[] };
+    if (!positional.every(isSetting)) return null;
+    return { kind: "reset", names: positional as MemorySetting[] };
   }
   return null;
 }
@@ -96,11 +139,26 @@ export interface FeatureState {
   description: string;
 }
 
+export interface ParameterState {
+  name: MemoryParameter;
+  value: number;
+  configured: number | null;
+  default: number;
+  minimum: number;
+  maximum: number;
+  active: boolean;
+  reason: string | null;
+  requires_feature: string;
+  description: string;
+}
+
 export interface FeaturesState {
   mode: string;
   features: FeatureState[];
-  non_default: Partial<Record<MemoryFeature, boolean>>;
-  changed?: MemoryFeature[];
+  /** Absent from a Runtime older than the intention dedup threshold. */
+  parameters?: ParameterState[];
+  non_default: SettingValues;
+  changed?: MemorySetting[];
 }
 
 function featuresState(value: unknown): FeaturesState | null {
@@ -125,6 +183,20 @@ function featuresState(value: unknown): FeaturesState | null {
       return null;
     }
   }
+  if (item.parameters !== undefined) {
+    if (!Array.isArray(item.parameters)) return null;
+    for (const parameter of item.parameters) {
+      if (
+        !parameter ||
+        typeof parameter !== "object" ||
+        typeof (parameter as ParameterState).name !== "string" ||
+        typeof (parameter as ParameterState).value !== "number" ||
+        typeof (parameter as ParameterState).active !== "boolean"
+      ) {
+        return null;
+      }
+    }
+  }
   return item as unknown as FeaturesState;
 }
 
@@ -137,12 +209,12 @@ export type FeaturesDocument = {
   | {
       state: "preview";
       features: FeaturesState;
-      target: Partial<Record<MemoryFeature, boolean>>;
+      target: SettingValues;
       applied: false;
       next_step: string;
     }
   | { state: "unchanged"; features: FeaturesState }
-  | { state: "committed"; features: FeaturesState; changed: MemoryFeature[] }
+  | { state: "committed"; features: FeaturesState; changed: MemorySetting[] }
   | { state: "rejected" | "unknown" | "unavailable"; code: string }
 );
 
@@ -170,13 +242,23 @@ export async function runFeaturesCommand(
   if (command.kind === "show") {
     return { ...BASE, state: "ok", features: current };
   }
+  // What a person set, per name this Runtime lists; null = the default.
+  const configured = new Map<string, boolean | number | null>([
+    ...current.features.map(
+      (feature) => [feature.name, feature.configured] as const,
+    ),
+    ...(current.parameters ?? []).map(
+      (parameter) => [parameter.name, parameter.configured] as const,
+    ),
+  ]);
   let body: Record<string, unknown>;
   if (command.kind === "set") {
-    const configured = new Map(
-      current.features.map((feature) => [feature.name, feature.configured]),
-    );
+    if (Object.keys(command.values).some((name) => !configured.has(name))) {
+      // An older Runtime does not know the name; it would answer 422.
+      return { ...BASE, state: "rejected", code: "memory_feature_unsupported" };
+    }
     const differs = Object.entries(command.values).some(
-      ([name, value]) => configured.get(name as MemoryFeature) !== value,
+      ([name, value]) => configured.get(name) !== value,
     );
     if (!differs) return { ...BASE, state: "unchanged", features: current };
     if (!command.confirmed) {
@@ -197,16 +279,10 @@ export async function runFeaturesCommand(
     const names =
       command.names.length > 0
         ? command.names
-        : current.features
-            .filter((feature) => feature.configured !== null)
-            .map((feature) => feature.name);
-    if (
-      names.every(
-        (name) =>
-          current.features.find((feature) => feature.name === name)
-            ?.configured === null,
-      )
-    ) {
+        : [...configured]
+            .filter(([, value]) => value !== null)
+            .map(([name]) => name as MemorySetting);
+    if (names.every((name) => (configured.get(name) ?? null) === null)) {
       return { ...BASE, state: "unchanged", features: current };
     }
     body = Object.fromEntries(names.map((name) => [name, null]));
@@ -233,6 +309,16 @@ export function featuresExitCode(document: FeaturesDocument): number {
     : 1;
 }
 
+function parameterLine(parameter: ParameterState): string {
+  const label = PARAMETER_LABEL[parameter.name] ?? parameter.name;
+  const origin = parameter.configured === null ? "默认" : "已设置";
+  const activity =
+    !parameter.active && parameter.reason
+      ? `，${REASON_TEXT[parameter.reason] ?? parameter.reason}`
+      : "";
+  return `${parameter.name}：${parameter.value}（${origin}${activity}，可设 ${parameter.minimum}–${parameter.maximum}）— ${label}`;
+}
+
 function featureLine(feature: FeatureState): string {
   const label = FEATURE_LABEL[feature.name] ?? feature.name;
   const value = feature.enabled ? "开" : "关";
@@ -251,6 +337,8 @@ export function renderFeaturesText(document: FeaturesDocument): string {
   const state = document.features;
   const lines = [`当前模式：${state.mode}`];
   for (const feature of state.features) lines.push(featureLine(feature));
+  for (const parameter of state.parameters ?? [])
+    lines.push(parameterLine(parameter));
   lines.push(
     "片段召回（episode_recall）只对带片段的记忆有用：先开启 session_episodes，之后提取的记忆才会带片段。",
   );
@@ -258,7 +346,9 @@ export function renderFeaturesText(document: FeaturesDocument): string {
   if (document.state === "preview") {
     lines.push("将设置：");
     for (const [name, value] of Object.entries(document.target)) {
-      lines.push(`- ${name} = ${value ? "开" : "关"}`);
+      lines.push(
+        `- ${name} = ${typeof value === "number" ? value : value ? "开" : "关"}`,
+      );
     }
     lines.push(`未执行任何改动。确认后运行：${document.next_step}`);
   }

memhub/apps/cli/src/memory-language-cli.test.ts

@@ -30,8 +30,7 @@ vi.mock("@one-memory/runtime-control", async (importOriginal) => ({
 }));
 
 function languageState(uiLanguage: string | null, extra = {}) {
-  const sdk =
-    uiLanguage === null || uiLanguage === "zh-Hans" ? "auto" : uiLanguage;
+  const sdk = uiLanguage === null ? "auto" : uiLanguage;
   return {
     ui_language: uiLanguage,
     sdk_language: sdk,
@@ -95,7 +94,7 @@ describe("memhub settings language", () => {
     });
     expect(transport.put).not.toHaveBeenCalled();
     const text = (await capturedRun(["settings", "language"])).stdout;
-    expect(text).toContain("界面语言：跟随系统（未选择）");
+    expect(text).toContain("界面语言：未设置（SDK 自动识别）");
     expect(text).toContain("SDK 提示语言：auto");
   });
 

memhub/apps/cli/src/memory-language-flow.ts

@@ -2,10 +2,11 @@
  * `memhub settings language [<code>|system]`.
  *
  * The display language the App reports to the Runtime (`ui_language`), and
- * the SDK prompt language it implies. zh-Hans and "system" (no explicit
- * choice) pass no language, so the SDK keeps detecting Chinese or English as
- * before; every other code, en included, makes extraction and the other SDK
- * prompts use that language. A change applies at once: a write in flight
+ * the SDK prompt language it implies. Every code, zh-Hans and en included,
+ * makes extraction and the other SDK prompts use that language; "system"
+ * (no language set) passes none, so the SDK keeps detecting Chinese or
+ * English as before. The App sends the language it shows, so it is only
+ * unset on an install without the App. A change applies at once: a write in flight
  * finishes in the old language, the next ones use the new one. The App sends
  * its own choice again whenever it changes there.
  */
@@ -162,14 +163,14 @@ export function renderLanguageText(document: LanguageDocument): string {
   const lines = [
     `界面语言：${
       state.ui_language === null
-        ? "跟随系统（未选择）"
+        ? "未设置（SDK 自动识别）"
         : `${state.ui_language}（${NAMES[state.ui_language]}）`
     }`,
     `SDK 提示语言：${sdkText(state.sdk_language)}`,
   ];
   if (document.state === "ok") {
     lines.push(
-      `可选：${UI_LANGUAGES.join("、")}、system。简体中文和 system 不指定语言，其余语言（包括 en）会让 SDK 使用该语言。`,
+      `可选：${UI_LANGUAGES.join("、")}、system。任一语言（包括 zh-Hans、en）都会让 SDK 使用该语言；system 不指定语言，SDK 自动识别中文或英文。`,
     );
   }
   if (document.state === "unchanged") lines.push("没有需要改动的设置。");

memhub/apps/cli/src/status-report.ts

@@ -85,7 +85,7 @@ export interface PipelineSummary {
   >;
   graph_build: string | null;
   /** SDK features (`memory_features`) whose value differs from the default. */
-  features: Record<string, boolean>;
+  features: Record<string, boolean | number>;
   /** The App's display language; null = never chosen or "follow the system". */
   ui_language: string | null;
   /** The SDK prompt language: `auto` (zh/en detection) or the code passed. */
@@ -134,12 +134,13 @@ export function describePipeline(value: unknown): PipelineSummary | null {
       };
     }
   }
-  const features: Record<string, boolean> = {};
+  const features: Record<string, boolean | number> = {};
   if (item.features && typeof item.features === "object") {
     for (const [name, value] of Object.entries(
       item.features as Record<string, unknown>,
     )) {
-      if (typeof value === "boolean") features[name] = value;
+      if (typeof value === "boolean" || typeof value === "number")
+        features[name] = value;
     }
   }
   const graph =
@@ -357,7 +358,10 @@ export function pipelineLine(pipeline: PipelineSummary): string {
   if (changed.length > 0) {
     parts.push(
       `；SDK 功能：${changed
-        .map(([name, value]) => `${name}=${value ? "开" : "关"}`)
+        .map(
+          ([name, value]) =>
+            `${name}=${typeof value === "number" ? value : value ? "开" : "关"}`,
+        )
         .join("、")}`,
     );
   }

memhub/apps/cli/src/user-id-cli.test.ts

@@ -373,6 +373,48 @@ describe("sources connect for a Hermes profile", () => {
     }
     expect(transport.post).not.toHaveBeenCalled();
   });
+
+  it("says the user id need not equal the Hermes profile name", async () => {
+    const result = await capturedRun([
+      "sources",
+      "connect",
+      "hermes",
+      "--user-id",
+      "wife:work",
+      "--root",
+      "~/.hermes/profiles/wife:work",
+    ]);
+    expect(result.code).toBe(2);
+    expect(result.stderr).toContain("用户 ID 不必等于 Hermes profile 名");
+    expect(result.stderr).toContain(
+      "--user-id wife-work --root ~/.hermes/profiles/wife:work",
+    );
+    expect(transport.post).not.toHaveBeenCalled();
+  });
+
+  it("explains a refused overlapping or profiles-container root", async () => {
+    for (const code of [
+      "hermes_root_is_profiles_container",
+      "hermes_root_overlaps_other_user",
+    ]) {
+      transport.post.mockResolvedValueOnce({
+        status: code.endsWith("container") ? 422 : 409,
+        data: { detail: code },
+      });
+      const result = await capturedRun([
+        "sources",
+        "connect",
+        "hermes",
+        "--user-id",
+        "kid",
+        "--root",
+        "/profiles",
+      ]);
+      expect(result.code).toBe(1);
+      expect(result.stdout).toContain(code);
+      expect(result.stdout).toContain("--root");
+    }
+  });
 });
 
 async function capturedRun(arguments_: string[]) {

memhub/apps/core/pyproject.toml

@@ -12,7 +12,7 @@ dependencies = [
     "fastapi>=0.141.1",
     "filelock>=3.32.4",
     # Public SDK version validated against MemHub's permission and recall contracts.
-    "hy-memory==2.0.11",
+    "hy-memory==2.0.12",
     # chromadb arrives through the HY SDK; locked here so an unrelated upgrade
     # cannot move the SDK's store. Built-in embedding consumes numpy directly.
     "chromadb==1.5.9",

memhub/apps/core/src/one_memory/api.py

@@ -130,6 +130,7 @@ from one_memory.hy_sdk_types import (
 from one_memory.imports.access import (
     AuthorizedSourceRoot,
     SourceAccessError,
+    resolved_source_root,
     root_identity_matches,
     source_root_identity,
 )
@@ -169,6 +170,11 @@ from one_memory.imports.locations import SourceLocation, inspect_source_location
 from one_memory.imports.models import EvidenceRecord
 from one_memory.imports.runner import live_sync_arrival
 from one_memory.imports.sources.common import SourceInstallState
+from one_memory.imports.sources.hermes import (
+    HERMES_ROOT_IS_PROFILES_CONTAINER,
+    hermes_root_conflict,
+    hermes_root_is_profiles_container,
+)
 from one_memory.imports.sources.registry import (
     RootCandidateKind,
     SourceRegistration,
@@ -198,12 +204,17 @@ from one_memory.memory_evolution import (
 )
 from one_memory.memory_features import (
     FEATURES,
+    PARAMETERS,
+    SETTING_NAMES,
     FeatureCost,
     FeatureOverrides,
     FeatureReason,
     FeatureSide,
     MemoryFeatureName,
     MemoryFeatures,
+    MemoryParameterName,
+    MemorySettingName,
+    SettingValue,
     effective_features,
     feature_activity,
     non_default_features,
@@ -526,11 +537,25 @@ class SdkMemoryUpdateRequest(BaseModel):
 class SdkUserProfileResponse(BaseModel):
     model_config = ConfigDict(extra="forbid")
 
+    #: The user whose profile this is: the `user_id` asked for, else `local`.
+    user_id: str
     request_id: str
     profile: dict[str, object] | None
     elapsed_ms: float = Field(ge=0)
 
 
+class SdkMemoryLibraryPage(HySdkMemoryPage):
+    """`GET /api/v2/memory-library`: one SDK page and the user it was read for."""
+
+    model_config = ConfigDict(frozen=True, extra="forbid")
+
+    user_id: str
+
+    @classmethod
+    def of(cls, page: HySdkMemoryPage, user_id: str) -> "SdkMemoryLibraryPage":
+        return cls(**dict(page), user_id=user_id)
+
+
 class SdkProfileVersionsResponse(HySdkProfileVersions):
     model_config = ConfigDict(frozen=True, extra="forbid")
 
@@ -585,6 +610,8 @@ class SdkRawItem(HySdkRawRecord):
 class SdkRawPage(BaseModel):
     model_config = ConfigDict(extra="forbid")
 
+    #: The user whose raw turns these are.
+    user_id: str
     items: tuple[SdkRawItem, ...] = ()
     total: int = Field(ge=0)
     offset: int = Field(ge=0)
@@ -598,6 +625,8 @@ class SdkRawPage(BaseModel):
 class SdkLayerCounts(BaseModel):
     model_config = ConfigDict(extra="forbid")
 
+    #: The user whose memories were counted.
+    user_id: str
     #: Every SDK layer, zero when empty.
     layers: dict[str, int]
     total: int = Field(ge=0)
@@ -763,10 +792,11 @@ class PipelineStatus(BaseModel):
     last_evolve_at: datetime | None = None
     graph_build: GraphBuildState
     #: The SDK features (`memory_features`) whose value differs from the SDK
-    #: default; empty while every feature is at its default.
-    features: dict[MemoryFeatureName, bool] = Field(default_factory=dict)
+    #: default; empty while every feature is at its default. A parameter
+    #: (`intention_dedup_threshold`) appears as its number.
+    features: dict[MemorySettingName, SettingValue] = Field(default_factory=dict)
     #: The display language the App last reported (`ui_language`); null =
-    #: never chosen or "follow the system".
+    #: none set (the App sends the language it shows, even following the system).
     ui_language: UiLanguage | None = None
     #: The SDK prompt language: `auto` (the SDK detects zh/en) or a code.
     sdk_language: str = SDK_LANGUAGE_AUTO
@@ -777,9 +807,9 @@ class UiLanguageState(BaseModel):
 
     model_config = ConfigDict(extra="forbid")
 
-    #: What the App reported; null = never chosen or "follow the system".
+    #: What the App reported; null = none set (CLI/API-only, or `system`).
     ui_language: UiLanguage | None
-    #: What SDK clients are built with: `auto` (zh-Hans or no choice: the SDK
+    #: What SDK clients are built with: `auto` (no language set: the SDK
     #: detects zh/en, as before) or the code passed as `MemoryConfig.language`.
     sdk_language: str
     languages: tuple[UiLanguage, ...] = UI_LANGUAGES
@@ -824,6 +854,30 @@ class MemoryFeatureState(BaseModel):
     description: str
 
 
+class MemoryParameterState(BaseModel):
+    """One numeric setting in `GET /api/v1/settings/memory-features`."""
+
+    model_config = ConfigDict(extra="forbid")
+
+    name: MemoryParameterName
+    #: What clients are built with: `configured`, else `default`.
+    value: float
+    #: What a person set; null = not set, the SDK default applies.
+    configured: float | None
+    #: The SDK default (its code default, or its own env var when set).
+    default: float
+    #: The range a `PUT` accepts, inclusive.
+    minimum: float
+    maximum: float
+    #: Whether it acts: exactly when `requires_feature` acts.
+    active: bool
+    reason: FeatureReason | None
+    requires_feature: MemoryFeatureName
+    sdk_field: str
+    env: str
+    description: str
+
+
 class MemoryFeaturesState(BaseModel):
     """`GET /api/v1/settings/memory-features`."""
 
@@ -831,15 +885,16 @@ class MemoryFeaturesState(BaseModel):
 
     mode: MemoryMode
     features: tuple[MemoryFeatureState, ...]
+    parameters: tuple[MemoryParameterState, ...] = ()
     #: Same as `pipeline.features`: the values that differ from the defaults.
-    non_default: dict[MemoryFeatureName, bool]
+    non_default: dict[MemorySettingName, SettingValue]
 
 
 class MemoryFeaturesChange(MemoryFeaturesState):
     """`PUT /api/v1/settings/memory-features`: the new state and what changed."""
 
-    #: Features whose value changed; empty = nothing rebuilt.
-    changed: tuple[MemoryFeatureName, ...] = ()
+    #: Features and parameters whose value changed; empty = nothing rebuilt.
+    changed: tuple[MemorySettingName, ...] = ()
 
 
 def memory_mode_effects(
@@ -967,6 +1022,8 @@ class AskMemoryRequest(SdkSearchFilters):
 
 class SdkHomeSummary(BaseModel):
     schema_version: Literal[2] = 2
+    #: The user the card was read for.
+    user_id: str
     memory_count: int
     latest: HySdkMemoryRecord | None
     observed_at: datetime
@@ -993,6 +1050,8 @@ class MemoryGraphEdge(BaseModel):
 
 
 class MemoryGraphResponse(BaseModel):
+    #: The user whose memories were mapped.
+    user_id: str
     total_memories: int
     projected_memories: int
     nodes: tuple[MemoryGraphNode, ...]
@@ -2667,6 +2726,7 @@ def create_app(
         )
         if not root_identity_matches(registration.candidate.path, request.expected_root_id):
             raise HTTPException(status_code=409, detail="source_identity_changed")
+        await _refuse_overlapping_root(source_id, registration.candidate.path, DEFAULT_USER_ID)
         root_changed = prior is not None and prior.root_id != request.expected_root_id
         if root_changed:
             source_jobs = [job for job in _job_store(app).list_jobs() if job.source_id == source_id]
@@ -3067,6 +3127,20 @@ def create_app(
         registrations = [_require_registration(app, source_id) for source_id in source_ids]
         if request.request_id is None:
             raise HTTPException(status_code=409, detail="source_confirmation_required")
+        for registration in registrations:
+            if registration.descriptor.source_id in MULTI_USER_SOURCES:
+                try:
+                    resolved = await asyncio.to_thread(
+                        app.state.source_candidate_store.resolve, registration
+                    )
+                except SourceCandidateError:
+                    # The connect below reports the missing candidate itself.
+                    continue
+                await _refuse_overlapping_root(
+                    registration.descriptor.source_id,
+                    resolved.candidate.path,
+                    DEFAULT_USER_ID,
+                )
         history_after = await _onboarding_history_after(
             request,
             registrations,
@@ -3166,6 +3240,42 @@ def create_app(
                 raise
         return ConnectSourcesResponse(**result.model_dump())
 
+    async def _refuse_overlapping_root(source_id: str, root: Path, user_id: str) -> None:
+        """Refuse a Hermes root that would read another user's files.
+
+        422 `hermes_root_is_profiles_container` for `.../profiles` itself;
+        409 `hermes_root_overlaps_other_user` for a root equal to, holding or
+        inside another user's active grant, unless one is the other's
+        `profiles/<name>` (the scan never enters `profiles/`).
+        """
+        if source_id not in MULTI_USER_SOURCES:
+            return
+        if hermes_root_is_profiles_container(root):
+            raise HTTPException(status_code=422, detail=HERMES_ROOT_IS_PROFILES_CONTAINER)
+
+        def conflict_with_others() -> str | None:
+            try:
+                mine = resolved_source_root(root)
+            except SourceAccessError:
+                # Unreadable or missing: the grant that follows refuses it
+                # with its own code.
+                return None
+            others = [
+                Path(path)
+                for receipt, path in _grant_store(app).grants()
+                if receipt.source_id == source_id
+                and receipt.user_id != user_id
+                and receipt.revoked_at is None
+            ]
+            return hermes_root_conflict(mine, others)
+
+        conflict = await asyncio.to_thread(conflict_with_others)
+        if conflict is not None:
+            raise HTTPException(
+                status_code=422 if conflict == HERMES_ROOT_IS_PROFILES_CONTAINER else 409,
+                detail=conflict,
+            )
+
     async def _connect_other_root(request: ConnectSourcesRequest) -> ConnectSourcesResponse:
         """Grant one Hermes root to a user: `~/.hermes/profiles/<name>` for its own user.
 
@@ -3195,6 +3305,7 @@ def create_app(
                 root = Path(request.root)
                 if not root.is_absolute():
                     raise HTTPException(status_code=422, detail="source_root_must_be_absolute")
+                await _refuse_overlapping_root(source_id, root, request.user_id)
                 # Named outright by the caller, like an environment override:
                 # no saved candidate may replace it, and naming it confirms it.
                 registration = replace(
@@ -3730,6 +3841,7 @@ def create_app(
             raise _sdk_http_error(error, "hy_memory_list_failed") from None
         total = stats.get("total") if isinstance(stats, dict) else None
         return SdkHomeSummary(
+            user_id=user_id,
             memory_count=total if isinstance(total, int) and total >= 0 else page.total,
             latest=page.memories[0] if page.memories else None,
             observed_at=datetime.now(UTC),
@@ -3737,7 +3849,7 @@ def create_app(
 
     @app.get(
         "/api/v2/memory-library",
-        response_model=HySdkMemoryPage,
+        response_model=SdkMemoryLibraryPage,
         dependencies=strict,
     )
     async def sdk_memory_library(
@@ -3754,7 +3866,7 @@ def create_app(
         exclude_sources: list[str] | None = Query(default=None),  # noqa: B008
         session_ids: list[str] | None = Query(default=None),  # noqa: B008
         agent_ids: list[str] | None = Query(default=None),  # noqa: B008
-    ) -> HySdkMemoryPage:
+    ) -> SdkMemoryLibraryPage:
         """One page of memories across chat, working and coding.
 
         Without `query`: `list_memories(scene="all")`, newest update first;
@@ -3800,7 +3912,7 @@ def create_app(
                         status_code=422,
                         detail="sdk_search_supports_active_status_only",
                     )
-                return await _library_search_page(
+                searched = await _library_search_page(
                     app,
                     client,
                     query=search_query,
@@ -3813,6 +3925,7 @@ def create_app(
                     user_id=user_id,
                     filters=filters,
                 )
+                return SdkMemoryLibraryPage.of(searched, user_id)
             raw = await asyncio.to_thread(
                 client.list_memories,
                 user_id=user_id,
@@ -3830,7 +3943,7 @@ def create_app(
                 raw, limit=limit, offset=offset
             )
             _log_skipped_sdk_memories(skipped)
-            return page
+            return SdkMemoryLibraryPage.of(page, user_id)
         except HTTPException:
             raise
         except Exception as error:
@@ -3876,6 +3989,7 @@ def create_app(
         except Exception as error:
             raise _sdk_http_error(error, "hy_memory_list_failed") from None
         return SdkLayerCounts(
+            user_id=user_id,
             layers=counts,
             total=sum(counts.values()),
             statuses=tuple(chosen) if chosen else None,
@@ -4036,6 +4150,7 @@ def create_app(
                     )
                 )
         return MemoryGraphResponse(
+            user_id=user_id,
             total_memories=total if isinstance(total, int) else len(memories),
             projected_memories=len(memories),
             nodes=tuple(nodes.values()),
@@ -4057,7 +4172,7 @@ def create_app(
             profile = HySdkUserProfile.from_sdk(value)
         except Exception as error:
             raise _sdk_http_error(error, "hy_memory_profile_read_failed") from None
-        return SdkUserProfileResponse.model_validate(profile.model_dump())
+        return SdkUserProfileResponse(user_id=user_id, **profile.model_dump())
 
     @app.get(
         "/api/v2/user-profile/versions",
@@ -4181,15 +4296,16 @@ def create_app(
         try:
             async with app.state.sdk_write_coordinator.use_client() as client:
                 # `delete` takes no user. Another user's memory is answered
-                # exactly like an id that does not exist: 204, nothing
-                # touched, so the status cannot tell that it exists.
+                # exactly like an id that does not exist: 404
+                # `memory_not_found`, nothing touched, so the status cannot
+                # tell that it exists. Callers read 404 as "already gone".
                 current = await asyncio.to_thread(
                     client.get, memory_id, **_namespace_kwargs(kind, variant)
                 )
-                if current is not None and not owns(
+                if current is None or not owns(
                     HySdkMemoryRecord.from_sdk(current).user_id, user_id
                 ):
-                    return Response(status_code=204)
+                    raise HTTPException(status_code=404, detail="memory_not_found")
                 result = await asyncio.to_thread(
                     client.delete, memory_id, **_namespace_kwargs(kind, variant)
                 )
@@ -4198,7 +4314,11 @@ def create_app(
             error_code = result.get("error_code")
             if error_code or result.get("partial") is True:
                 raise HySdkError(str(error_code or "hy_memory_delete_incomplete"))
-            if result.get("success") is not True and result.get("deleted_count") != 0:
+            if result.get("success") is not True:
+                # Read a moment ago, found by nobody now (a second delete won
+                # the race): the same answer as an id that never existed.
+                if result.get("deleted_count") == 0:
+                    raise HTTPException(status_code=404, detail="memory_not_found")
                 raise HySdkError("hy_memory_delete_rejected")
         except HTTPException:
             raise
@@ -4271,6 +4391,7 @@ def create_app(
                 and (before is None or at < before)
             )
         return SdkRawPage(
+            user_id=user_id,
             items=tuple(SdkRawItem.of(record) for record in records),
             total=page.total,
             offset=offset,
@@ -4303,6 +4424,7 @@ def create_app(
             )
         except MemoryAnswerError as error:
             raise HTTPException(status_code=503, detail=str(error)) from None
+        answer = answer.model_copy(update={"user_id": request.user_id})
         if request.question != "__om_probe__" and access is not None:
             from one_memory.call_event_recorder import ask_call_event, try_record
 
@@ -4344,6 +4466,9 @@ def create_app(
                 ):
                     if event.get("type") == "final":
                         final = event
+                    elif event.get("type") == "recall":
+                        # The first event names whose memories answer.
+                        event = {**event, "user_id": request.user_id}
                     yield _sse(_serialize_ask_event(event))
             except MemoryAnswerError:
                 yield _sse({"type": "error", "code": "memory_answer_failed"})
@@ -4422,7 +4547,7 @@ def create_app(
                 )
             except Exception:
                 app.state.call_event_recording_error = True
-        return receipt
+        return receipt.model_copy(update={"user_id": request.user_id})
 
     @app.get(
         "/api/v1/memory-processing",
@@ -4565,7 +4690,8 @@ def create_app(
         """Turn SDK features on or off; one global setting, not per user.
 
         A key sets that feature, null resets it to the SDK default, an absent
-        key is left as it is; an unknown key or a non-boolean is 422. A
+        key is left as it is; an unknown key, a non-boolean feature or an
+        `intention_dedup_threshold` outside its range is 422. A
         change rebuilds the SDK clients like a mode change: a write in flight
         finishes with the old features, the next job and search use the new
         ones. Nothing stored is migrated and no collection is renamed. See
@@ -4581,7 +4707,7 @@ def create_app(
             current = _memory_features(app)
             before = effective_features(previous, defaults)
             after = effective_features(current, defaults)
-            changed = tuple(spec.name for spec in FEATURES if before[spec.name] != after[spec.name])
+            changed = tuple(name for name in SETTING_NAMES if before[name] != after[name])
             if current != previous:
                 # Even a reset to the default value rebuilds: the client then
                 # carries no override at all, byte for byte the default config.
@@ -4616,9 +4742,9 @@ def create_app(
     async def put_ui_language(request: UiLanguageUpdate) -> UiLanguageChange:
         """Record the App's display language; one global setting, not per user.
 
-        zh-Hans and null pass no language to the SDK, which keeps detecting
-        zh/en as before; every other code (en included) is passed as
-        `MemoryConfig.language`. A change of that SDK language rebuilds the
+        Every code (zh-Hans and en included) is passed as
+        `MemoryConfig.language`; only null passes no language, so the SDK
+        keeps detecting zh/en as before. A change of that SDK language rebuilds the
         SDK clients like a feature change: a write in flight finishes in the
         old language. Nothing stored is migrated and no collection is renamed.
         """
@@ -6066,7 +6192,7 @@ def _ui_language_state(app: FastAPI) -> UiLanguageState:
 
 
 def _memory_features_state(
-    app: FastAPI, defaults: dict[str, bool] | None = None
+    app: FastAPI, defaults: dict[str, SettingValue] | None = None
 ) -> MemoryFeaturesState:
     defaults = sdk_feature_defaults() if defaults is None else defaults
     overrides = _memory_features(app)
@@ -6079,9 +6205,9 @@ def _memory_features_state(
         features.append(
             MemoryFeatureState(
                 name=spec.name,
-                enabled=effective[spec.name],
-                configured=configured.get(spec.name),
-                default=defaults[spec.name],
+                enabled=bool(effective[spec.name]),
+                configured=cast(bool | None, configured.get(spec.name)),
+                default=bool(defaults[spec.name]),
                 active=reason is None,
                 reason=reason,
                 side=spec.side,
@@ -6093,10 +6219,32 @@ def _memory_features_state(
                 description=spec.description,
             )
         )
+    parameters = []
+    for parameter in PARAMETERS:
+        reason = feature_activity(parameter.name, effective, mode)
+        parameters.append(
+            MemoryParameterState(
+                name=parameter.name,
+                value=float(effective[parameter.name]),
+                configured=cast(float | None, configured.get(parameter.name)),
+                default=float(defaults[parameter.name]),
+                minimum=parameter.minimum,
+                maximum=parameter.maximum,
+                active=reason is None,
+                reason=reason,
+                requires_feature=parameter.requires_feature,
+                sdk_field=parameter.sdk_field,
+                env=parameter.env,
+                description=parameter.description,
+            )
+        )
     return MemoryFeaturesState(
         mode=mode,
         features=tuple(features),
-        non_default=cast(dict[MemoryFeatureName, bool], non_default_features(overrides, defaults)),
+        parameters=tuple(parameters),
+        non_default=cast(
+            dict[MemorySettingName, SettingValue], non_default_features(overrides, defaults)
+        ),
     )
 
 
@@ -6117,7 +6265,7 @@ def _pipeline_status(app: FastAPI) -> PipelineStatus | None:
         last_evolve_at=max(finished, default=None),
         graph_build=state.graph_build,
         features=cast(
-            dict[MemoryFeatureName, bool],
+            dict[MemorySettingName, SettingValue],
             non_default_features(_memory_features(app), sdk_feature_defaults()),
         ),
         **_ui_language_state(app).model_dump(exclude={"languages"}),

memhub/apps/core/src/one_memory/context_models.py

@@ -155,6 +155,8 @@ class SdkContextSearchResponse(BaseModel):
     used_characters: int = Field(ge=0, le=20000)
     truncated: bool
     total_ms: float = Field(ge=0)
+    #: Whose memories were searched: the request's `user_id`, else `local`.
+    user_id: str = Field(min_length=1, max_length=64)
 
 
 class ContextLaneResult(BaseModel):

memhub/apps/core/src/one_memory/context_routes.py

@@ -261,6 +261,7 @@ def sdk_context_router(dependencies: Sequence[Depends]) -> APIRouter:
                 used_characters=0,
                 truncated=True,
                 total_ms=(time.monotonic() - started) * 1000,
+                user_id=value.user_id,
             )
             await record(final, timed_out=True)
             return final
@@ -306,6 +307,7 @@ def sdk_context_router(dependencies: Sequence[Depends]) -> APIRouter:
             used_characters=used,
             truncated=truncated,
             total_ms=(time.monotonic() - started) * 1000,
+            user_id=value.user_id,
         )
         await record(final, timed_out=False)
         return final

memhub/apps/core/src/one_memory/hy_runtime_config.py

@@ -14,7 +14,7 @@ from pathlib import Path
 from typing import Literal, cast
 
 HY_MEMORY_DISTRIBUTION = "hy-memory"
-HY_MEMORY_VERSION = "2.0.11"
+HY_MEMORY_VERSION = "2.0.12"
 HY_MEMORY_NAMESPACE = "governed-v2"
 DiagnosticLogLevel = Literal["error", "warning", "info", "debug"]
 

memhub/apps/core/src/one_memory/hy_sdk_migration.py

@@ -503,7 +503,7 @@ def _ensure_coding_schema(path: Path) -> None:
         CodingMemoryStore,
     )
 
-    # Relies on the pinned SDK's internals (hy-memory==2.0.11 is pinned exactly).
+    # Relies on the pinned SDK's internals (hy-memory==2.0.12 is pinned exactly).
     store = CodingMemoryStore.__new__(CodingMemoryStore)
     store._db_path = str(path)
     store._conn = None

memhub/apps/core/src/one_memory/hy_sdk_runtime.py

@@ -47,8 +47,10 @@ from one_memory.local_embedding import LocalEmbedder
 from one_memory.log_file import confine_hy_sdk_logging
 from one_memory.memory_features import (
     FEATURES,
-    FEATURES_BY_NAME,
+    PARAMETERS,
+    SETTINGS_BY_NAME,
     FeatureOverrides,
+    SettingValue,
     feature_overrides,
 )
 from one_memory.model_profiles import (
@@ -321,21 +323,27 @@ def sdk_relevance_floor() -> float:
     return min(1.0, max(0.0, value))
 
 
-def sdk_feature_defaults() -> dict[str, bool]:
-    """Each `memory_features` feature's SDK default, as a fresh config has it.
+def sdk_feature_defaults() -> dict[str, SettingValue]:
+    """Each `memory_features` setting's SDK default, as a fresh config has it.
 
     That is the SDK's code default unless the process environment sets the
     SDK's own variable (`FeatureSpec.env`), exactly what an unset feature
     leaves on a client.
     """
     config = MemoryConfig()
-    return {
+    defaults: dict[str, SettingValue] = {
         spec.name: bool(getattr(getattr(config, spec.section), spec.field)) for spec in FEATURES
     }
+    for parameter in PARAMETERS:
+        defaults[parameter.name] = float(
+            getattr(getattr(config, parameter.section), parameter.field)
+        )
+    return defaults
 
 
 def apply_sdk_features(
-    config: MemoryConfig, features: Mapping[str, bool] | Iterable[tuple[str, bool]]
+    config: MemoryConfig,
+    features: Mapping[str, SettingValue] | Iterable[tuple[str, SettingValue]],
 ) -> MemoryConfig:
     """Set each feature a person chose on its `MemoryConfig` field.
 
@@ -346,7 +354,7 @@ def apply_sdk_features(
     """
     values = dict(features.items() if isinstance(features, Mapping) else features)
     for name, value in feature_overrides(values):
-        spec = FEATURES_BY_NAME[name]
+        spec = SETTINGS_BY_NAME[name]
         setattr(getattr(config, spec.section), spec.field, value)
     return config
 
@@ -367,8 +375,8 @@ def language_kwargs(language: str | None) -> LanguageKwargs:
 def apply_sdk_language(config: MemoryConfig, language: str | None) -> MemoryConfig:
     """Set the SDK prompt language (`MemoryConfig.language`), when there is one.
 
-    None (zh-Hans, or no choice) sets nothing: the SDK detects zh/en as it
-    always did. Like a feature, the language never touches `vector_store`, so
+    None (no language set) sets nothing: the SDK detects zh/en as it always
+    did. Every display language, zh-Hans included, is set explicitly. Like a feature, the language never touches `vector_store`, so
     the collection identity never depends on it.
     """
     if language is not None:
@@ -383,7 +391,7 @@ def build_sdk_config(
     *,
     api_key: str | None,
     data_dir: Path,
-    features: Mapping[str, bool] | Iterable[tuple[str, bool]] = (),
+    features: Mapping[str, SettingValue] | Iterable[tuple[str, SettingValue]] = (),
     language: str | None = None,
 ) -> MemoryConfig:
     """Map a model snapshot and its embedding space to an SDK configuration.

memhub/apps/core/src/one_memory/imports/access.py

@@ -436,6 +436,11 @@ def root_identity_matches(root: Path, expected: str) -> bool:
     return _root_identity_matches_details(resolved, details, expected)
 
 
+def resolved_source_root(root: Path) -> Path:
+    """The real directory a root names (symlinks followed), as a grant records it."""
+    return _root_details(root)[0]
+
+
 def _check_root_identity(root: Path, expected: str | None) -> None:
     if expected is not None and not root_identity_matches(root, expected):
         raise SourceAccessError(SourceAccessErrorCode.SOURCE_IDENTITY_CHANGED)

memhub/apps/core/src/one_memory/imports/discovery.py

@@ -27,7 +27,7 @@ def discovered_off_loop(
     *,
     suffixes: frozenset[str],
     max_targets: int,
-    excluded_top_directories: frozenset[str] = frozenset(),
+    excluded_directory_names: frozenset[str] = frozenset(),
 ) -> AsyncIterator[SourceFileDiscoveryEvent]:
     """The same walk, for callers that have an event loop to keep free.
 
@@ -42,7 +42,7 @@ def discovered_off_loop(
             grant,
             suffixes=suffixes,
             max_targets=max_targets,
-            excluded_top_directories=excluded_top_directories,
+            excluded_directory_names=excluded_directory_names,
         ),
         scope_key=grant.source_id,
     )
@@ -53,15 +53,17 @@ def discover_source_files(
     *,
     suffixes: frozenset[str],
     max_targets: int,
-    excluded_top_directories: frozenset[str] = frozenset(),
+    excluded_directory_names: frozenset[str] = frozenset(),
 ) -> Iterator[SourceFileDiscoveryEvent]:
     """Metadata only: one lstat per candidate, no open and no per-file grant lookup.
 
     The grant and root identity are checked once before the walk. Each listed
     file keeps the grant's check, which runs again when that file is opened;
     the open itself refuses symlinks and any inode other than the one listed.
-    `excluded_top_directories` are directories directly under the root that
-    are never entered, such as another user's Hermes profiles.
+    `excluded_directory_names` are directory names never entered, at any
+    depth under the root, such as the `profiles` container that holds other
+    users' Hermes profiles. Any depth, because the granted root may sit above
+    the Hermes home (`~/.hermes` inside it is then `.hermes/profiles`).
     """
     grant.check_root()
     inspected = 0
@@ -69,12 +71,10 @@ def discover_source_files(
         grant.root,
         followlinks=False,
     ):
-        at_root = Path(directory) == grant.root
         child_directories[:] = sorted(
             child
             for child in child_directories
-            if not (Path(directory) / child).is_symlink()
-            and not (at_root and child in excluded_top_directories)
+            if not (Path(directory) / child).is_symlink() and child not in excluded_directory_names
         )
         for filename in sorted(filenames):
             if Path(filename).suffix.lower() not in suffixes:

memhub/apps/core/src/one_memory/imports/sources/common.py

@@ -209,6 +209,7 @@ class JsonlSourceAdapter:
         file_predicate: Callable[[AuthorizedSourceFile], bool] | None = None,
         suffixes: frozenset[str] = frozenset({".jsonl"}),
         header_selector: Callable[[dict[str, JsonValue]], bool] | None = None,
+        header_gate: Callable[[dict[str, JsonValue] | None], bool] | None = None,
     ) -> None:
         if descriptor.source_id != grant.source_id:
             raise ValueError("Descriptor and authorized root source IDs must match")
@@ -219,6 +220,10 @@ class JsonlSourceAdapter:
         self.file_predicate = file_predicate or (lambda _: True)
         self.suffixes = suffixes
         self.header_selector = header_selector
+        # False refuses the whole file before any record is read. It reports
+        # and leaves no cursor, so a release that learns the format reads the
+        # file from the top instead of finding it already behind a checkpoint.
+        self.header_gate = header_gate
         self._header_cache: dict[str, tuple[str, dict[str, JsonValue] | None]] = {}
         self._history_listing_cache: SourceListing | None = None
 
@@ -371,6 +376,9 @@ class JsonlSourceAdapter:
                 source_file, checkpoint, header = await asyncio.to_thread(
                     self._prepare, listed, options
                 )
+                if self.header_gate is not None and not self.header_gate(header):
+                    yield ScanFailure(reason_code=ScanIssueCode.UNSUPPORTED_SCHEMA)
+                    continue
                 _log.debug(
                     "import_file_read source=%s file=%d/%d file_bytes=%d planned_bytes=%d",
                     self.descriptor.source_id,
@@ -574,6 +582,9 @@ class JsonlSourceAdapter:
             # resumed scan starts past the header, and the records after it need
             # it just as much as the first batch did.
             header = await _read_header(reader, source_file, self.header_selector)
+            if self.header_gate is not None and not self.header_gate(header):
+                yield ScanFailure(reason_code=ScanIssueCode.UNSUPPORTED_SCHEMA)
+                continue
             last: SourceCursor = _start_cursor(source_file, options, checkpoint)
             async for raw in iterate_in_worker(
                 partial(reader, source_file, checkpoint=checkpoint),

memhub/apps/core/src/one_memory/imports/sources/deepseek_harness.py

@@ -1,3 +1,4 @@
+import re
 from pathlib import PurePosixPath
 
 from pydantic import JsonValue
@@ -37,6 +38,19 @@ DEEPSEEK_HARNESS_DESCRIPTOR = SourceDescriptor(
     ),
 )
 
+#: One session is one file, and the name carries the format generation it was
+#: written in: `session.jsonl[.zstd]` for the first format, then
+#: `session.v3.jsonl.zstd` and `session.v4.jsonl.zstd`. The version segment is
+#: part of the published on-disk contract, so discovery must accept it — the
+#: earlier exact-name match imported none of the versioned files.
+SESSION_FILE = re.compile(r"^session(?:\.v[0-9]+)?\.jsonl(?:\.zstd)?$")
+
+#: Session generations this parser has been verified against: the first format
+#: (header `version: 0`), v3 and v4. Discovery is intentionally wider than
+#: parsing: a future generation is found by pattern and then skipped from its
+#: header, so it is reported as unsupported instead of silently vanishing.
+SUPPORTED_SESSION_VERSIONS = frozenset({0, 3, 4})
+
 
 def create_deepseek_harness_adapter(
     grant: AuthorizedSourceRoot,
@@ -49,25 +63,43 @@ def create_deepseek_harness_adapter(
         grant=grant,
         parser=parse_deepseek_harness_record,
         source_version=source_version,
-        file_predicate=lambda source_file: (
-            source_file.relative_path.name in {"session.jsonl", "session.jsonl.zstd"}
-        ),
+        file_predicate=lambda source_file: bool(SESSION_FILE.match(source_file.relative_path.name)),
         suffixes=frozenset({".jsonl", ".zstd"}),
         header_selector=_is_session_header,
+        header_gate=_supported_session,
     )
 
 
 def _is_session_header(record: dict[str, JsonValue]) -> bool:
     """Harness writes the session's `cwd` once, in the first line only.
 
-    Verified against a session this machine produced: the header is
-    `{"type":"session","version":0,"id":...,"cwd":"/private/tmp/dsh-verify"}`
-    and no later record repeats it. Read per-record, `cwd` is therefore always
-    absent and every turn imports with no workspace.
+    Verified against sessions this machine produced: the header is
+    `{"type":"session","version":0|4,"id":...,"cwd":...}` and no later record
+    repeats it. Read per-record, `cwd` is therefore always absent and every turn
+    imports with no workspace.
     """
     return record.get("type") == "session"
 
 
+def _supported_session(header: dict[str, JsonValue] | None) -> bool:
+    """Whether the session's declared format generation is one we can read.
+
+    A missing header, or a header without `version`, is the first format — the
+    earliest files this adapter already read. Any declared version outside
+    `SUPPORTED_SESSION_VERSIONS` is refused rather than interpreted with today's
+    field rules: a future format may change field semantics, and importing it
+    wrongly is harder to undo than not importing it yet.
+    """
+    if header is None:
+        return True
+    version = header.get("version")
+    if version is None:
+        return True
+    if not isinstance(version, int) or isinstance(version, bool):
+        return False
+    return version in SUPPORTED_SESSION_VERSIONS
+
+
 def parse_deepseek_harness_record(
     record: dict[str, JsonValue],
     context: SourceRecordContext,
@@ -80,6 +112,11 @@ def parse_deepseek_harness_record(
     )
     event_type = record.get("type")
     data = as_record(record.get("data"))
+    if not _supported_session(context.header):
+        return ParsedSkip(
+            reason_code=ScanIssueCode.UNSUPPORTED_SCHEMA,
+            conversation_id=conversation_id,
+        )
     if event_type == "session":
         return ParsedSkip(reason_code=ScanIssueCode.UNKNOWN_RECORD)
     if data is None:
@@ -148,11 +185,18 @@ def _tool_message(
     """`tool/call` carries name and arguments; `tool/result` a user-role message.
 
     The same call also appears as a `tool-call` block in `assistant/message`;
-    only the event is read, so it is stored once.
+    only the event is read, so it is stored once. The first format and v3 wrap
+    the result in `tool-result` blocks; v4 writes plain `text` blocks, so both
+    shapes are read through the same clipping and credential-scrubbing path.
     """
     message = as_record(data.get("message"))
     if record.get("type") == "tool/result" and message is not None:
         text = tool_blocks_evidence(message.get("content"), block_types=frozenset({"tool-result"}))
+        if text is None:
+            text = tool_blocks_evidence(
+                [{"type": "tool-result", "content": message.get("content")}],
+                block_types=frozenset({"tool-result"}),
+            )
         message_id = first_string(message.get("id"), data.get("callId"))
     else:
         text = tool_evidence_text(data)

memhub/apps/core/src/one_memory/imports/sources/hermes.py

@@ -1,9 +1,9 @@
 import json
 import re
 import sqlite3
-from collections.abc import AsyncIterator, Iterator
+from collections.abc import AsyncIterator, Iterable, Iterator
 from functools import partial
-from pathlib import PurePosixPath
+from pathlib import Path, PurePosixPath
 
 from pydantic import JsonValue
 
@@ -88,7 +88,7 @@ class HermesSourceAdapter:
             self.grant,
             suffixes=frozenset({".jsonl", ".db"}),
             max_targets=10_000,
-            excluded_top_directories=frozenset({HERMES_PROFILES_DIRECTORY}),
+            excluded_directory_names=frozenset({HERMES_PROFILES_DIRECTORY}),
         ):
             if isinstance(item, AuthorizedSourceFile) and _is_hermes_target(
                 item.relative_path.as_posix()
@@ -102,7 +102,7 @@ class HermesSourceAdapter:
             self.grant,
             suffixes=frozenset({".jsonl", ".db"}),
             max_targets=options.max_scan_targets or 100_000,
-            excluded_top_directories=frozenset({HERMES_PROFILES_DIRECTORY}),
+            excluded_directory_names=frozenset({HERMES_PROFILES_DIRECTORY}),
         ):
             yield ScanProgressEvent(
                 phase=ScanPhase.DISCOVER,
@@ -253,16 +253,62 @@ def parse_hermes_rollout_record(
 #: own `state.db` and sessions. A profile is another person's history: it is
 #: read only through its own grant (its own MemHub user), never as part of the
 #: root above it. Hermes' own export skips this directory for the same reason.
+#:
+#: Skipped at any depth, not only directly under the root: a root granted
+#: above the Hermes home holds `.hermes/profiles/`. Hermes keeps nothing of
+#: its own under a directory of that name (its history is `state.db` and
+#: `sessions/`), so nothing real is lost.
 HERMES_PROFILES_DIRECTORY = "profiles"
 
 
 def _is_hermes_target(relative_path: str) -> bool:
     path = PurePosixPath(relative_path)
-    if path.parts and path.parts[0] == HERMES_PROFILES_DIRECTORY:
+    if HERMES_PROFILES_DIRECTORY in path.parts[:-1]:
         return False
     return path.name == "state.db" or (path.suffix == ".jsonl" and "sessions" in path.parts)
 
 
+def hermes_root_is_profiles_container(root: Path) -> bool:
+    """`profiles` itself holds everyone's profiles; it is never one person's history."""
+    return root.name == HERMES_PROFILES_DIRECTORY
+
+
+def hermes_root_conflict(mine: Path, other_users_roots: Iterable[Path]) -> str | None:
+    """Why the resolved root `mine` may not be granted beside other users' Hermes roots.
+
+    Paths are compared resolved (symlinks followed; the other users' roots are
+    resolved here). Two roots that are equal or nest would read the same files
+    for two users, except when one is exactly the other's `profiles/<name>`:
+    the scan above never enters `profiles/`, so the two stay apart (`local` on
+    `~/.hermes`, a user on `~/.hermes/profiles/<name>`). None when it may.
+    """
+    if hermes_root_is_profiles_container(mine):
+        return HERMES_ROOT_IS_PROFILES_CONTAINER
+    for other in other_users_roots:
+        theirs = _real(other)
+        if mine == theirs:
+            return HERMES_ROOT_OVERLAPS_OTHER_USER
+        for parent, child in ((mine, theirs), (theirs, mine)):
+            if parent in child.parents:
+                relative = child.relative_to(parent).parts
+                if len(relative) != 2 or relative[0] != HERMES_PROFILES_DIRECTORY:
+                    return HERMES_ROOT_OVERLAPS_OTHER_USER
+    return None
+
+
+#: 422: the root is the `profiles` container, not a profile.
+HERMES_ROOT_IS_PROFILES_CONTAINER = "hermes_root_is_profiles_container"
+#: 409: the root is, holds or sits inside another user's Hermes root.
+HERMES_ROOT_OVERLAPS_OTHER_USER = "hermes_root_overlaps_other_user"
+
+
+def _real(path: Path) -> Path:
+    try:
+        return path.expanduser().resolve(strict=False)
+    except (OSError, RuntimeError):
+        return path.expanduser().absolute()
+
+
 def _read_rollout(
     source_file: AuthorizedSourceFile,
     options: ScanOptions,

memhub/apps/core/src/one_memory/memory_features.py

@@ -21,6 +21,11 @@ exercises (query rewrite needs `queries=[...]`, session narratives need
 cross-encoder download, access write-back); and everything MemHub already
 controls elsewhere (pipeline log, trace, memory operations, telemetry, mode).
 
+Beside the on/off features there is one numeric parameter,
+`intention_dedup_threshold` (`PARAMETERS`): the cosine similarity at which the
+read-time intention dedup treats two intentions as copies. It is set, stored,
+reset and keyed exactly like a feature.
+
 No SDK import here: only `hy_sdk_runtime` and `hy_sdk_migration` import it.
 `config_state` imports this module, so it imports nothing from there.
 """
@@ -31,7 +36,7 @@ from collections.abc import Mapping
 from dataclasses import dataclass
 from typing import Literal
 
-from pydantic import BaseModel, ConfigDict, StrictBool
+from pydantic import BaseModel, ConfigDict, Field, StrictBool
 
 MemoryFeatureName = Literal[
     "graph_rerank",
@@ -40,8 +45,13 @@ MemoryFeatureName = Literal[
     "session_episodes",
     "episode_summary",
     "intention",
+    "intention_dedup",
     "few_shot",
 ]
+#: Numeric settings beside the on/off features.
+MemoryParameterName = Literal["intention_dedup_threshold"]
+#: Every key of the setting: a feature or a parameter.
+MemorySettingName = MemoryFeatureName | MemoryParameterName
 #: Read features change search; write features change what extraction stores.
 FeatureSide = Literal["read", "write"]
 #: none: no extra call. extra_query: one more store query per search.
@@ -49,9 +59,25 @@ FeatureSide = Literal["read", "write"]
 #: a longer extraction prompt.
 FeatureCost = Literal["none", "extra_query", "llm_call", "prompt_tokens"]
 #: Why an enabled feature does nothing right now (`active: false`).
-FeatureReason = Literal["disabled", "requires_pro", "requires_ultra", "requires_graph_rerank"]
+FeatureReason = Literal[
+    "disabled",
+    "requires_pro",
+    "requires_ultra",
+    "requires_graph_rerank",
+    "requires_intention_dedup",
+]
+#: A feature is on or off; a parameter is a number.
+type SettingValue = bool | float
 #: A client's features as a hashable key: sorted (name, value) pairs, set ones only.
-type FeatureOverrides = tuple[tuple[str, bool], ...]
+type FeatureOverrides = tuple[tuple[str, SettingValue], ...]
+
+#: The range a person may set `intention_dedup_threshold` to. With dedup on,
+#: the SDK deletes every intention at or above it from the store at read time,
+#: which cannot be undone; below 0.8 the embedding models MemHub uses score
+#: different plans on one topic as that close, so a lower value would delete
+#: intentions that are not copies. 1.0 keeps only exact copies' dedup.
+INTENTION_DEDUP_THRESHOLD_MIN = 0.8
+INTENTION_DEDUP_THRESHOLD_MAX = 1.0
 
 _MODE_RANK: dict[str, int] = {"lite": 0, "pro": 1, "ultra": 2}
 
@@ -169,6 +195,23 @@ FEATURES: tuple[FeatureSpec, ...] = (
             "No extra call."
         ),
     ),
+    FeatureSpec(
+        name="intention_dedup",
+        section="recall",
+        field="intention_dedup_enabled",
+        env="MEMORY_INTENTION_DEDUP_ENABLED",
+        side="read",
+        requires_mode="pro",
+        requires_feature=None,
+        cost="none",
+        description=(
+            "Treat same-day intentions (L7) with the same expiry and a cosine "
+            "similarity at or above intention_dedup_threshold as copies: a "
+            "search returns the earliest and deletes the others from the store. "
+            "On by default; off hides, drops and deletes no intention, at read "
+            "time or in a write batch. No extra call."
+        ),
+    ),
     FeatureSpec(
         name="few_shot",
         section="llm",
@@ -189,12 +232,57 @@ FEATURE_NAMES: tuple[MemoryFeatureName, ...] = tuple(spec.name for spec in FEATU
 FEATURES_BY_NAME: dict[str, FeatureSpec] = {spec.name: spec for spec in FEATURES}
 
 
+@dataclass(frozen=True)
+class ParameterSpec:
+    """A numeric setting; it acts only while `requires_feature` acts."""
+
+    name: MemoryParameterName
+    section: Literal["recall"]
+    field: str
+    env: str
+    minimum: float
+    maximum: float
+    requires_feature: MemoryFeatureName
+    description: str
+
+    @property
+    def sdk_field(self) -> str:
+        return f"{self.section}.{self.field}"
+
+
+PARAMETERS: tuple[ParameterSpec, ...] = (
+    ParameterSpec(
+        name="intention_dedup_threshold",
+        section="recall",
+        field="intention_dedup_threshold",
+        env="MEMORY_INTENTION_DEDUP_THRESHOLD",
+        minimum=INTENTION_DEDUP_THRESHOLD_MIN,
+        maximum=INTENTION_DEDUP_THRESHOLD_MAX,
+        requires_feature="intention_dedup",
+        description=(
+            "Cosine similarity at or above which intention_dedup treats two "
+            "intentions as copies. Higher keeps more. The SDK default is 0.95 "
+            "(MEMORY_DEDUP_THRESHOLD also sets it when its own env var is unset)."
+        ),
+    ),
+)
+PARAMETER_NAMES: tuple[MemoryParameterName, ...] = tuple(spec.name for spec in PARAMETERS)
+PARAMETERS_BY_NAME: dict[str, ParameterSpec] = {spec.name: spec for spec in PARAMETERS}
+#: Every key of the setting, features first, each in its catalog order.
+SETTING_NAMES: tuple[MemorySettingName, ...] = (*FEATURE_NAMES, *PARAMETER_NAMES)
+SETTINGS_BY_NAME: dict[str, FeatureSpec | ParameterSpec] = {
+    **FEATURES_BY_NAME,
+    **PARAMETERS_BY_NAME,
+}
+
+
 class MemoryFeatures(BaseModel):
     """`config.json` `memory_features`, and the `PUT` body.
 
     Every key is optional; absent (or null) means the SDK default. In a `PUT`
-    an absent key is left as it is and null resets it. Unknown keys and
-    non-boolean values are refused (422).
+    an absent key is left as it is and null resets it. Unknown keys,
+    non-boolean feature values and a threshold that is not a number in its
+    range are refused (422).
     """
 
     model_config = ConfigDict(frozen=True, extra="forbid", strict=True)
@@ -205,7 +293,14 @@ class MemoryFeatures(BaseModel):
     session_episodes: StrictBool | None = None
     episode_summary: StrictBool | None = None
     intention: StrictBool | None = None
+    intention_dedup: StrictBool | None = None
     few_shot: StrictBool | None = None
+    intention_dedup_threshold: float | None = Field(
+        default=None,
+        ge=INTENTION_DEDUP_THRESHOLD_MIN,
+        le=INTENTION_DEDUP_THRESHOLD_MAX,
+        allow_inf_nan=False,
+    )
 
     def overrides(self) -> FeatureOverrides:
         """The features a person set, as the client key."""
@@ -221,24 +316,47 @@ class MemoryFeatures(BaseModel):
         return MemoryFeatures(**{key: value for key, value in values.items() if value is not None})
 
 
-def feature_overrides(values: Mapping[str, bool]) -> FeatureOverrides:
-    unknown = set(values) - set(FEATURES_BY_NAME)
+def feature_overrides(values: Mapping[str, SettingValue]) -> FeatureOverrides:
+    unknown = set(values) - set(SETTINGS_BY_NAME)
     if unknown:
         raise ValueError("unknown_memory_feature")
-    return tuple(sorted((name, bool(value)) for name, value in values.items()))
+    return tuple(sorted((name, _setting_value(name, value)) for name, value in values.items()))
+
+
+def _setting_value(name: str, value: SettingValue) -> SettingValue:
+    parameter = PARAMETERS_BY_NAME.get(name)
+    if parameter is None:
+        return bool(value)
+    if isinstance(value, bool) or not parameter.minimum <= float(value) <= parameter.maximum:
+        raise ValueError("invalid_memory_feature_value")
+    return float(value)
 
 
 def effective_features(
-    overrides: FeatureOverrides, defaults: Mapping[str, bool]
-) -> dict[str, bool]:
-    """Every feature's value: what a person set, else the SDK default."""
-    values: dict[str, bool] = {spec.name: bool(defaults.get(spec.name, False)) for spec in FEATURES}
+    overrides: FeatureOverrides, defaults: Mapping[str, SettingValue]
+) -> dict[str, SettingValue]:
+    """Every setting's value: what a person set, else the SDK default."""
+    values: dict[str, SettingValue] = {
+        spec.name: bool(defaults.get(spec.name, False)) for spec in FEATURES
+    }
+    for parameter in PARAMETERS:
+        if parameter.name in defaults:
+            values[parameter.name] = float(defaults[parameter.name])
     values.update(dict(overrides))
     return values
 
 
-def feature_activity(name: str, effective: Mapping[str, bool], mode: str) -> FeatureReason | None:
-    """None when the feature acts in this mode; else why it does not."""
+def feature_activity(
+    name: str, effective: Mapping[str, SettingValue], mode: str
+) -> FeatureReason | None:
+    """None when the feature acts in this mode; else why it does not.
+
+    A parameter acts exactly when the feature it tunes acts.
+    """
+    parameter = PARAMETERS_BY_NAME.get(name)
+    if parameter is not None:
+        reason = feature_activity(parameter.requires_feature, effective, mode)
+        return "requires_intention_dedup" if reason == "disabled" else reason
     spec = FEATURES_BY_NAME[name]
     if not effective.get(name, False):
         return "disabled"
@@ -252,11 +370,12 @@ def feature_activity(name: str, effective: Mapping[str, bool], mode: str) -> Fea
 
 
 def non_default_features(
-    overrides: FeatureOverrides, defaults: Mapping[str, bool]
-) -> dict[str, bool]:
-    """The features whose value differs from the SDK default, for status."""
+    overrides: FeatureOverrides, defaults: Mapping[str, SettingValue]
+) -> dict[str, SettingValue]:
+    """The settings whose value differs from the SDK default, for status."""
+    baseline = effective_features((), defaults)
     return {
         name: value
         for name, value in effective_features(overrides, defaults).items()
-        if value != bool(defaults.get(name, False))
+        if value != baseline.get(name)
     }

memhub/apps/core/src/one_memory/memory_server/config_state.py

@@ -74,9 +74,9 @@ class ConfigDocument(BaseModel):
     #: SDK retrieval and extraction features a person set; an unset one keeps
     #: the SDK default. See `one_memory.memory_features`.
     memory_features: MemoryFeatures = Field(default_factory=MemoryFeatures)
-    #: The display language a person chose in the App; None = never chosen or
-    #: "follow the system". See `one_memory.ui_language` for what it does to
-    #: the SDK.
+    #: The display language the App shows (its choice, or the system language
+    #: it follows); None = none set. See `one_memory.ui_language` for what it
+    #: does to the SDK.
     ui_language: UiLanguage | None = None
 
     @field_validator("sources")

memhub/apps/core/src/one_memory/recall.py

@@ -135,6 +135,8 @@ class RecallReceipt(BaseModel):
     #: exists yet (`fallback_reason`). Raw hits are excerpts, not memories.
     mode: Literal["memory", "raw"] = "memory"
     fallback_reason: Literal["model_unavailable", "no_memories"] | None = None
+    #: Whose memories were searched: the request's `user_id`, else `local`.
+    user_id: str = DEFAULT_USER_ID
 
 
 class RecallTarget(Protocol):

memhub/apps/core/src/one_memory/sdk_memory_qa.py

@@ -33,7 +33,7 @@ from one_memory.model_profiles import (
 )
 from one_memory.sdk_search_options import SdkSearchFilters, SearchLane
 from one_memory.secrets import SecretStore, SecretStoreUnavailableError
-from one_memory.user_scope import owns
+from one_memory.user_scope import DEFAULT_USER_ID, owns
 
 _NO_GROUNDING = "现有记忆不足以回答这个问题。"
 _GROUNDING_LIMIT = 6
@@ -62,6 +62,8 @@ class SdkMemoryAnswer(BaseModel):
     answer: str
     memories: tuple[SdkAskMemory, ...]
     mode: Literal["generated", "extractive", "empty"]
+    #: Whose memories answered: the request's `user_id`, else `local`.
+    user_id: str = DEFAULT_USER_ID
 
 
 class _PromptMemory:

memhub/apps/core/src/one_memory/ui_language.py

@@ -3,14 +3,19 @@
 The App owns the choice (its language selector) and tells Core whenever it
 changes, so Core can build every SDK client with it. It is one global value in
 `config.json` (`ui_language`), beside `memory_mode` and `memory_features`;
-absent (never chosen, or "follow the system") means no explicit choice.
+absent means no language was set (a CLI/API-only install, or
+`settings language system`). An App that follows the system sends the
+language it resolved and shows, not null.
 
 The owner's rule for the SDK:
 
-- zh-Hans, or no explicit choice: pass no language. The SDK keeps detecting
-  Chinese or English from the text, exactly as before this setting existed.
-- Any other code, including en: pass it as `MemoryConfig.language`, so
-  extraction and the other prompts use that language.
+- Any supported code, zh-Hans and en included: pass it as
+  `MemoryConfig.language`, so extraction and the other prompts use that
+  language. Every display language is passed explicitly (#243).
+- No language at all (never set, as on a CLI/API-only install): pass no
+  language. The SDK keeps detecting Chinese or English from the text, exactly
+  as before this setting existed. The App does not leave it unset: it sends
+  the language it shows, including when it follows the system.
 
 The language never names a collection; a change rebuilds the SDK handles the
 way a mode or feature change does (#218 use count).
@@ -51,8 +56,6 @@ UI_LANGUAGES: tuple[UiLanguage, ...] = (
 )
 #: Codes earlier App builds stored, and the code each one is now.
 LEGACY_UI_LANGUAGES: dict[str, UiLanguage] = {"zh-CN": "zh-Hans"}
-#: Display languages that leave the SDK's own zh/en detection in charge.
-AUTO_DETECTED: frozenset[str] = frozenset({"zh-Hans"})
 #: What status shows when no language is passed to the SDK.
 SDK_LANGUAGE_AUTO = "auto"
 
@@ -66,8 +69,9 @@ def normalize_ui_language(value: object) -> UiLanguage | None:
 
 
 def sdk_language(ui_language: str | None) -> str | None:
-    """The `MemoryConfig.language` for a display language; None = SDK auto-detect."""
-    language = normalize_ui_language(ui_language)
-    if language is None or language in AUTO_DETECTED:
-        return None
-    return language
+    """The `MemoryConfig.language` for a display language; None = SDK auto-detect.
+
+    Every supported code is passed as is; only an unset (or unknown) value
+    leaves the SDK to detect zh/en.
+    """
+    return normalize_ui_language(ui_language)

memhub/apps/core/tests/TEST_INDEX.md

@@ -25,6 +25,7 @@
 | `test_c1_cross_source_session_isolation.py` | `contract` | Same session name in two sources must stay two conversations. |
 | `test_c1_damage_per_source.py` | `contract` | Damage and unknown schema, per source: a bad record must not sink the import. |
 | `test_c1_deepseek_profiles.py` | `contract` | DeepSeek Harness has two profiles; only the headless session form is importable. |
+| `test_c1_deepseek_versioned_sessions.py` | `contract` | DeepSeek Harness versions its session file names; every generation must import. |
 | `test_c1_import_event_matrix.py` | `contract` | C1 owned matrix: existing history, new file, append, truncate/replace, restart, revoke. |
 | `test_c1_import_failure_injection.py` | `contract` | C1 failure injection: atomic receipt, disk-full, read-only source, rotation. |
 | `test_c1_import_instrumentation.py` | `contract` | Instrumented import accounting: bytes read, opens, hashes, jobs, duplicates. |
@@ -318,4 +319,4 @@
 | `test_workspace_recall.py` | `contract` | Workspace memories were unreachable from every host; these pin the way in. |
 | `test_write_queue_lease_renewal.py` | `contract` | Rule 8: a lease must outlive the work it covers, and be renewed while it runs. |
 
-共 313 个测试文件。
+共 314 个测试文件。

memhub/apps/core/tests/core_test_classification.py

@@ -14,8 +14,8 @@ from pathlib import Path
 import pytest
 
 PRIMARY_MARKERS = ("unit", "contract", "integration", "performance", "live")
-EXPECTED_TEST_FILE_COUNT = 313
-EXPECTED_TEST_FILES_SHA256 = "dcada5d5421767196a79e415dd47c2b6c6d67681972dbe81481b31867d318928"
+EXPECTED_TEST_FILE_COUNT = 314
+EXPECTED_TEST_FILES_SHA256 = "d745df3dfb964a8d2197c1ca3768728249d84ac4729305155ae1ef48428a19e4"
 
 # Pure transformations, validation models, parity checks and state machines.
 # This list is intentionally small: uncertain files default to contract.

memhub/apps/core/tests/test_c1_deepseek_versioned_sessions.py

@@ -0,0 +1,246 @@
+"""DeepSeek Harness versions its session file names; every generation must import.
+
+The first format writes `<session>/session.jsonl[.zstd]`; v3 and v4 write
+`session.v3.jsonl.zstd` / `session.v4.jsonl.zstd`. Discovery used to match only
+the two unversioned names, so every v3/v4 session was invisible to the import
+job — `discovered 0` while the files sat on disk. These tests pin the file-name
+contract, the header gate that keeps an unknown future version out of the
+database, and the upgrade path where a library imported before the fix picks up
+the versioned files on its next scan.
+"""
+
+import json
+from pathlib import Path
+
+import pytest
+import zstandard
+
+from one_memory.imports.adapters import ScanFailure, ScanIssueCode
+from one_memory.imports.sources import deepseek_harness
+from one_memory.imports.sources.deepseek_harness import (
+    DEEPSEEK_HARNESS_DESCRIPTOR,
+    create_deepseek_harness_adapter,
+)
+from tests.test_secondary_source_adapters import (
+    _cursors,
+    _evidence,
+    _evidence_text,
+    _grant,
+    _scan,
+    _skip_codes,
+)
+
+
+def _write_session(directory: Path, name: str, records: list[dict[str, object]]) -> None:
+    directory.mkdir(parents=True, exist_ok=True)
+    payload = "".join(f"{json.dumps(record)}\n" for record in records).encode()
+    (directory / name).write_bytes(zstandard.ZstdCompressor().compress(payload))
+
+
+def _conversation(version: int | None, *, directory: str = "run-a") -> list[dict[str, object]]:
+    header: dict[str, object] = {
+        "type": "session",
+        "version": version,
+        "id": directory,
+        "cwd": "/private/versioned-project",
+    }
+    return [
+        header,
+        {
+            "type": "user/message",
+            "seq": 1,
+            "data": {
+                "id": "human",
+                "role": "user",
+                "source": {"kind": "user"},
+                "content": [{"type": "text", "text": "visible human"}],
+            },
+        },
+        {
+            "type": "assistant/message",
+            "seq": 2,
+            "data": {
+                "message": {
+                    "id": "assistant",
+                    "role": "assistant",
+                    "content": [{"type": "text", "text": "visible assistant"}],
+                }
+            },
+        },
+    ]
+
+
+def _session_adapter(tmp_path: Path):
+    root = tmp_path / "dsh"
+    root.mkdir(parents=True, exist_ok=True)
+    return root, create_deepseek_harness_adapter(
+        _grant(DEEPSEEK_HARNESS_DESCRIPTOR.source_id, root, tmp_path)
+    )
+
+
+def test_versioned_v4_session_file_is_discovered_and_imported(tmp_path: Path) -> None:
+    root, adapter = _session_adapter(tmp_path)
+    session = root / "run-v4"
+    records = _conversation(4, directory="run-v4")
+    records.append(
+        {
+            "type": "tool/result",
+            "seq": 3,
+            "time": 1793341068763,
+            "data": {
+                "callId": "call-1",
+                "message": {"role": "tool", "content": [{"type": "text", "text": "tool output"}]},
+            },
+        }
+    )
+    _write_session(session, "session.v4.jsonl.zstd", records)
+    # A rotated backup next to the live file must not be imported as a second copy.
+    (session / "session.v4.jsonl.zstd.orig-20261027").write_bytes(
+        zstandard.ZstdCompressor().compress(b'{"type":"session","version":4}\n')
+    )
+
+    events = _scan(adapter)
+
+    assert _evidence_text(events) == ["visible human", "visible assistant", "tool output"]
+    evidence = _evidence(events)
+    assert {event.evidence.project for event in evidence} == {"versioned-project"}
+    assert {event.evidence.conversation_id for event in evidence} == {"run-v4"}
+
+
+def test_versioned_v3_session_file_is_discovered_and_imported(tmp_path: Path) -> None:
+    root, adapter = _session_adapter(tmp_path)
+    _write_session(root / "run-v3", "session.v3.jsonl.zstd", _conversation(3))
+
+    events = _scan(adapter)
+
+    assert _evidence_text(events) == ["visible human", "visible assistant"]
+
+
+def _tool_result(content: list[dict[str, object]]) -> dict[str, object]:
+    return {
+        "type": "tool/result",
+        "seq": 3,
+        "data": {"callId": "call-1", "message": {"role": "tool", "content": content}},
+    }
+
+
+def test_tool_output_imports_in_either_block_shape(tmp_path: Path) -> None:
+    """`tool/result` output written as `text` blocks used to be dropped.
+
+    Only `tool-result` blocks were read, so a session that writes plain `text`
+    blocks lost every tool output. Both shapes must arrive, in any generation.
+    """
+    root, adapter = _session_adapter(tmp_path)
+    v3 = _conversation(3, directory="run-v3-text")
+    v3.append(_tool_result([{"type": "text", "text": "v3 text output"}]))
+    _write_session(root / "run-v3-text", "session.v3.jsonl.zstd", v3)
+    v0 = _conversation(0, directory="run-v0-block")
+    v0.append(_tool_result([{"type": "tool-result", "content": "v0 block output"}]))
+    _write_session(root / "run-v0-block", "session.jsonl.zstd", v0)
+
+    texts = _evidence_text(_scan(adapter))
+
+    assert "v3 text output" in texts
+    assert "v0 block output" in texts
+
+
+def test_text_tool_output_is_scrubbed_like_block_output(tmp_path: Path) -> None:
+    root, adapter = _session_adapter(tmp_path)
+    secret = "sk-" + "a" * 40
+    records = _conversation(4, directory="run-secret")
+    records.append(_tool_result([{"type": "text", "text": f"token {secret} " + "x" * 5000}]))
+    _write_session(root / "run-secret", "session.v4.jsonl.zstd", records)
+
+    tool = _evidence_text(_scan(adapter))[-1]
+
+    assert secret not in tool
+    assert len(tool) < 2000
+
+
+def test_session_file_names_outside_the_contract_are_not_imported(tmp_path: Path) -> None:
+    root, adapter = _session_adapter(tmp_path)
+    for name in (
+        "session.v4.jsonl.zstd.orig-20261027",
+        "session.vx.jsonl.zstd",
+        "other.v4.jsonl.zstd",
+        "session.v4.json",
+    ):
+        _write_session(root / name.replace(".", "-"), name, _conversation(4))
+
+    assert _evidence(_scan(adapter)) == []
+
+
+def test_unknown_future_session_version_imports_nothing(tmp_path: Path) -> None:
+    root, adapter = _session_adapter(tmp_path)
+    records = _conversation(5)
+    records.append(
+        {
+            "type": "user/message",
+            "seq": 9,
+            "data": {
+                "id": "future",
+                "role": "user",
+                "source": {"kind": "user"},
+                "content": [{"type": "text", "text": "future generation payload"}],
+            },
+        }
+    )
+    _write_session(root / "run-v5", "session.v5.jsonl.zstd", records)
+
+    events = _scan(adapter)
+
+    assert _evidence(events) == []
+    assert ScanIssueCode.UNSUPPORTED_SCHEMA in _skip_codes(events)
+
+
+def test_unknown_session_version_is_reported_and_read_once_supported(
+    tmp_path: Path, monkeypatch: pytest.MonkeyPatch
+) -> None:
+    """Not importing a future format yet must stay "yet".
+
+    A cursor left behind by the refused scan would put the whole session behind
+    the checkpoint, so the release that learns the format would read nothing.
+    """
+    root, adapter = _session_adapter(tmp_path)
+    _write_session(root / "run-v5", "session.v5.jsonl.zstd", _conversation(5))
+
+    refused = _scan(adapter)
+
+    assert _cursors(refused) == {}
+    assert [event.reason_code for event in refused if isinstance(event, ScanFailure)] == [
+        ScanIssueCode.UNSUPPORTED_SCHEMA
+    ]
+
+    monkeypatch.setattr(deepseek_harness, "SUPPORTED_SESSION_VERSIONS", frozenset({0, 3, 4, 5}))
+    _, upgraded = _session_adapter(tmp_path)
+
+    assert _evidence_text(_scan(upgraded, cursors=_cursors(refused))) == [
+        "visible human",
+        "visible assistant",
+    ]
+
+
+def test_upgrade_scan_rediscovers_versioned_files_already_on_disk(tmp_path: Path) -> None:
+    """A library imported before this fix must pick up the files on its next scan.
+
+    The first scan sees only the unversioned session that the old predicate
+    matched; after the upgrade, the versioned file next to it is discovered by
+    the next scan while the already imported session stays deduplicated by the
+    cursor it left behind.
+    """
+    root, adapter = _session_adapter(tmp_path)
+    old = root / "run-old"
+    _write_session(old, "session.jsonl.zstd", _conversation(0, directory="run-old"))
+    first_scan = _scan(adapter)
+    assert _evidence_text(first_scan) == ["visible human", "visible assistant"]
+    assert _evidence(first_scan)[0].evidence.conversation_id == "run-old"
+
+    versioned = root / "run-v4"
+    _write_session(versioned, "session.v4.jsonl.zstd", _conversation(4, directory="run-v4"))
+    cursors = _cursors(first_scan)
+    assert cursors  # the old session left a cursor behind
+
+    upgrade_scan = _scan(adapter, cursors=cursors)
+
+    assert _evidence_text(upgrade_scan) == ["visible human", "visible assistant"]
+    assert {event.evidence.conversation_id for event in _evidence(upgrade_scan)} == {"run-v4"}

memhub/apps/core/tests/test_harness_contract_suite.py

@@ -193,7 +193,7 @@ def _qwenwork() -> Harness:
 
 def _deepseek() -> Harness:
     def write(path: Path, turns: list[Turn]) -> None:
-        # deepseek only accepts a file literally named session.jsonl, and nests
+        # deepseek only accepts files named session[.vN].jsonl[.zstd], and nests
         # the turn under "data".
         lines: list[dict] = [{"type": "session", "version": 0, "id": "s1", "cwd": "/w"}]
         for index, (role, text, _session) in enumerate(turns):
@@ -225,7 +225,7 @@ def _deepseek() -> Harness:
 
     from one_memory.imports.sources.deepseek_harness import create_deepseek_harness_adapter
 
-    # deepseek accepts only a file literally named session.jsonl.
+    # deepseek accepts only session[.vN].jsonl[.zstd]; the first format is used here.
     return Harness(
         "deepseek-harness",
         write,

memhub/apps/core/tests/test_memory_additions.py

@@ -293,6 +293,7 @@ def test_sdk_user_profile_http_returns_native_assembled_profile(tmp_path):
             response = await client.get("/api/v2/user-profile")
             assert response.status_code == 200, response.text
             assert response.json() == {
+                "user_id": "local",
                 "request_id": "profile-request",
                 "profile": {
                     "memory_id": "l0-head",

memhub/apps/core/tests/test_memory_features.py

@@ -28,6 +28,8 @@ from one_memory.memory_features import (
     FEATURE_NAMES,
     FEATURES,
     FEATURES_BY_NAME,
+    PARAMETERS,
+    SETTING_NAMES,
     MemoryFeatures,
     effective_features,
     feature_activity,
@@ -46,15 +48,20 @@ TODAY = {
     "session_episodes": False,
     "episode_summary": False,
     "intention": True,
+    "intention_dedup": True,
     "few_shot": False,
 }
+#: The same for the numeric settings.
+TODAY_PARAMETERS = {"intention_dedup_threshold": 0.95}
 
 
 @pytest.fixture(autouse=True)
 def _clean_sdk_env(monkeypatch):
     """The SDK's own env vars feed its defaults; tests start without them."""
-    for spec in FEATURES:
+    for spec in (*FEATURES, *PARAMETERS):
         monkeypatch.delenv(spec.env, raising=False)
+    # The threshold falls back to the SDK's shared dedup variable.
+    monkeypatch.delenv("MEMORY_DEDUP_THRESHOLD", raising=False)
     monkeypatch.delenv("ONE_MEMORY_GRAPH_STORE", raising=False)
 
 
@@ -95,17 +102,25 @@ def _field(config, name: str) -> bool:
 
 
 def test_the_document_names_exactly_the_catalog() -> None:
-    assert tuple(MemoryFeatures.model_fields) == FEATURE_NAMES
+    assert tuple(MemoryFeatures.model_fields) == SETTING_NAMES
     assert set(TODAY) == set(FEATURE_NAMES)
     # Each feature is a MemoryConfig field the SDK has; no env var is written.
     defaults = hy_sdk_runtime.sdk_feature_defaults()
-    assert set(defaults) == set(FEATURE_NAMES)
+    assert set(defaults) == set(SETTING_NAMES)
 
 
 def test_the_defaults_are_todays_behaviour() -> None:
-    assert hy_sdk_runtime.sdk_feature_defaults() == TODAY
+    everything = {**TODAY, **TODAY_PARAMETERS}
+    assert hy_sdk_runtime.sdk_feature_defaults() == everything
     assert MemoryFeatures().overrides() == ()
-    assert effective_features((), TODAY) == TODAY
+    assert effective_features((), everything) == everything
+
+
+@pytest.mark.parametrize("profile", PROFILES, ids=("builtin", "remote"))
+def test_intention_dedup_defaults_to_on_at_095_in_the_built_config(tmp_path, profile) -> None:
+    config = _config(tmp_path, profile)
+    assert config.recall.intention_dedup_enabled is True
+    assert config.recall.intention_dedup_threshold == 0.95
 
 
 def test_the_sdk_env_var_still_moves_the_default_of_an_unset_feature(monkeypatch) -> None:
@@ -126,6 +141,32 @@ def test_unknown_or_non_boolean_values_are_refused() -> None:
         )
 
 
+@pytest.mark.parametrize("bad", (0.79, 1.01, -1, 2, True, "0.9", float("nan"), float("inf")))
+def test_an_intention_dedup_threshold_outside_its_range_is_refused(bad) -> None:
+    with pytest.raises(ValidationError):
+        MemoryFeatures.model_validate({"intention_dedup_threshold": bad})
+
+
+def test_the_intention_dedup_threshold_range_is_inclusive() -> None:
+    for value in (0.8, 0.9, 1, 1.0):
+        document = MemoryFeatures.model_validate({"intention_dedup_threshold": value})
+        assert document.overrides() == (("intention_dedup_threshold", float(value)),)
+    with pytest.raises(ValueError, match="invalid_memory_feature_value"):
+        hy_sdk_runtime.build_sdk_config(
+            PROFILES[0],
+            api_key=None,
+            data_dir=Path("/tmp/unused"),
+            features={"intention_dedup_threshold": 0.5},
+        )
+
+
+def test_the_sdk_env_vars_still_move_the_threshold_default(monkeypatch) -> None:
+    monkeypatch.setenv("MEMORY_DEDUP_THRESHOLD", "0.9")
+    assert hy_sdk_runtime.sdk_feature_defaults()["intention_dedup_threshold"] == 0.9
+    monkeypatch.setenv("MEMORY_INTENTION_DEDUP_THRESHOLD", "0.97")
+    assert hy_sdk_runtime.sdk_feature_defaults()["intention_dedup_threshold"] == 0.97
+
+
 def test_merge_sets_resets_and_leaves_absent_keys_alone() -> None:
     saved = MemoryFeatures(graph_rerank=True, few_shot=True)
     update = MemoryFeatures.model_validate({"few_shot": None, "episode_recall": True})
@@ -165,6 +206,20 @@ def test_each_feature_reaches_the_built_memory_config(tmp_path, profile) -> None
                 assert _field(config, other.name) is TODAY[other.name], (spec.name, other.name)
 
 
+@pytest.mark.parametrize("profile", PROFILES, ids=("builtin", "remote"))
+def test_intention_dedup_on_off_and_threshold_reach_the_built_memory_config(
+    tmp_path, profile
+) -> None:
+    off = _config(tmp_path, profile, {"intention_dedup": False})
+    assert off.recall.intention_dedup_enabled is False
+    assert off.recall.intention_dedup_threshold == 0.95
+    on = _config(tmp_path, profile, {"intention_dedup": True, "intention_dedup_threshold": 0.9})
+    assert on.recall.intention_dedup_enabled is True
+    assert on.recall.intention_dedup_threshold == 0.9
+    # Nothing else moves.
+    assert _field(on, "intention") is True and _field(on, "graph_rerank") is False
+
+
 @pytest.mark.parametrize("profile", PROFILES, ids=("builtin", "remote"))
 def test_nothing_set_is_the_config_of_before_byte_for_byte(tmp_path, profile) -> None:
     before = repr(dataclasses.asdict(_config(tmp_path, profile)))
@@ -172,6 +227,8 @@ def test_nothing_set_is_the_config_of_before_byte_for_byte(tmp_path, profile) ->
     assert repr(dataclasses.asdict(_config(tmp_path, profile, {}))) == before
     # Setting every feature to its default value changes nothing either.
     assert repr(dataclasses.asdict(_config(tmp_path, profile, TODAY))) == before
+    everything = {**TODAY, **TODAY_PARAMETERS}
+    assert repr(dataclasses.asdict(_config(tmp_path, profile, everything))) == before
 
 
 @pytest.mark.parametrize("profile", PROFILES, ids=("builtin", "remote"))
@@ -190,6 +247,7 @@ def test_features_never_change_the_collection_identity(tmp_path, profile) -> Non
         {name: True for name in FEATURE_NAMES},
         {name: False for name in FEATURE_NAMES},
         {"graph_rerank": True, "episode_recall": True},
+        {"intention_dedup": False, "intention_dedup_threshold": 0.8},
     ):
         assert identity(_config(tmp_path, profile, values)) == baseline
 
@@ -243,6 +301,13 @@ def test_a_feature_needing_a_higher_mode_is_reported_inactive() -> None:
     series = effective_features((("same_series_timeline", True), ("graph_rerank", True)), TODAY)
     assert feature_activity("same_series_timeline", series, "pro") == "requires_ultra"
     assert feature_activity("same_series_timeline", series, "ultra") is None
+    defaults = {**TODAY, **TODAY_PARAMETERS}
+    assert feature_activity("intention_dedup", defaults, "pro") is None
+    assert feature_activity("intention_dedup_threshold", defaults, "pro") is None
+    assert feature_activity("intention_dedup_threshold", defaults, "lite") == "requires_pro"
+    off = effective_features((("intention_dedup", False),), defaults)
+    assert feature_activity("intention_dedup", off, "pro") == "disabled"
+    assert feature_activity("intention_dedup_threshold", off, "pro") == "requires_intention_dedup"
 
 
 # --- rebuilding handles -------------------------------------------------------
@@ -497,3 +562,99 @@ def test_features_api_get_put_reset_and_status(tmp_path, monkeypatch) -> None:
         assert (await client.get("/api/v1/settings/memory-features")).json()["non_default"] == {}
 
     run_app(tmp_path, monkeypatch, scenario)
+
+
+@pytest.mark.fresh_sdk
+def test_intention_dedup_api_on_off_threshold_and_422(tmp_path, monkeypatch) -> None:
+    built: list[tuple[bool, float]] = []
+    original = hy_sdk_runtime.build_sdk_config
+
+    def recording(*args, **kwargs):
+        config = original(*args, **kwargs)
+        built.append(
+            (config.recall.intention_dedup_enabled, config.recall.intention_dedup_threshold)
+        )
+        return config
+
+    monkeypatch.setattr(hy_sdk_runtime, "build_sdk_config", recording)
+
+    def built_now(app) -> tuple[bool, float]:
+        """What a client built with the read handle's current key carries."""
+        recording(
+            hy_sdk_runtime.builtin_retrieval_snapshot(),
+            api_key=None,
+            data_dir=tmp_path,
+            features=app.state.sdk_client_handle.current_features(),
+        )
+        return built[-1]
+
+    async def scenario(app, client):
+        path = "/api/v1/settings/memory-features"
+        current = (await client.get(path)).json()
+        dedup = _by_name(current)["intention_dedup"]
+        assert dedup["enabled"] is True and dedup["default"] is True
+        assert dedup["configured"] is None and dedup["active"] is True
+        assert dedup["sdk_field"] == "recall.intention_dedup_enabled"
+        assert dedup["env"] == "MEMORY_INTENTION_DEDUP_ENABLED"
+        (threshold,) = current["parameters"]
+        assert threshold == {
+            "name": "intention_dedup_threshold",
+            "value": 0.95,
+            "configured": None,
+            "default": 0.95,
+            "minimum": 0.8,
+            "maximum": 1.0,
+            "active": True,
+            "reason": None,
+            "requires_feature": "intention_dedup",
+            "sdk_field": "recall.intention_dedup_threshold",
+            "env": "MEMORY_INTENTION_DEDUP_THRESHOLD",
+            "description": threshold["description"],
+        }
+        assert built_now(app) == (True, 0.95)
+
+        off = await client.put(path, json={"intention_dedup": False})
+        assert off.status_code == 200, off.text
+        body = off.json()
+        assert body["changed"] == ["intention_dedup"]
+        assert body["non_default"] == {"intention_dedup": False}
+        assert body["parameters"][0]["active"] is False
+        assert body["parameters"][0]["reason"] == "requires_intention_dedup"
+        assert app.state.sdk_write_coordinator.memory_features() == (("intention_dedup", False),)
+        assert built_now(app) == (False, 0.95)
+
+        on = (
+            await client.put(path, json={"intention_dedup": True, "intention_dedup_threshold": 0.9})
+        ).json()
+        assert on["changed"] == ["intention_dedup", "intention_dedup_threshold"]
+        assert on["non_default"] == {"intention_dedup_threshold": 0.9}
+        assert on["parameters"][0]["value"] == 0.9 and on["parameters"][0]["active"] is True
+        expected = (("intention_dedup", True), ("intention_dedup_threshold", 0.9))
+        assert app.state.sdk_client_handle.current_features() == expected
+        assert built_now(app) == (True, 0.9)
+        processing = (await client.get("/api/v1/memory-processing")).json()
+        assert processing["pipeline"]["features"] == {"intention_dedup_threshold": 0.9}
+        saved = json.loads((tmp_path / "data" / "config.json").read_text())
+        assert saved["memory_features"] == {
+            "intention_dedup": True,
+            "intention_dedup_threshold": 0.9,
+        }
+
+        for bad in (0.5, 0.79, 1.5, -0.1, "0.9", True):
+            response = await client.put(path, json={"intention_dedup_threshold": bad})
+            assert response.status_code == 422, bad
+        assert (await client.put(path, json={"intention_dedup": "false"})).status_code == 422
+        # A refused body changes nothing.
+        assert app.state.sdk_client_handle.current_features() == expected
+
+        reset = (
+            await client.put(
+                path, json={"intention_dedup": None, "intention_dedup_threshold": None}
+            )
+        ).json()
+        assert reset["changed"] == ["intention_dedup_threshold"]
+        assert reset["non_default"] == {}
+        assert app.state.sdk_client_handle.current_features() == ()
+        assert built_now(app) == (True, 0.95)
+
+    run_app(tmp_path, monkeypatch, scenario)

memhub/apps/core/tests/test_multi_user_runtime.py

@@ -334,7 +334,9 @@ def test_another_users_memory_id_answers_404_for_read_update_and_delete(
 
         assert (await client.get(path)).status_code == 404
         assert (await client.put(path, json={"content": "stolen"})).status_code == 404
-        assert (await client.delete(path)).status_code == 204
+        refused = await client.delete(path)
+        assert refused.status_code == 404
+        assert refused.json()["detail"] == "memory_not_found"
         assert sdk.memories[wife_memory]["content"] == "wife drinks coffee"
 
         own = await client.get(path, params={"user_id": "wife"})
@@ -343,6 +345,36 @@ def test_another_users_memory_id_answers_404_for_read_update_and_delete(
         assert updated.status_code == 200
         assert (await client.delete(path, params={"user_id": "wife"})).status_code == 204
         assert wife_memory not in sdk.memories
+        # A second delete (a double click) finds nothing: 404, already gone.
+        again = await client.delete(path, params={"user_id": "wife"})
+        assert again.status_code == 404
+        assert again.json()["detail"] == "memory_not_found"
+
+    run_with_sdk(tmp_path, monkeypatch, scenario)
+
+
+@pytest.mark.fresh_sdk
+def test_a_delete_that_loses_the_race_answers_404_like_a_missing_id(tmp_path, monkeypatch) -> None:
+    """Read as the caller's own, then gone before the SDK deletes it."""
+
+    async def scenario(app, sdk, client):
+        await _write_both_users(app, sdk, client)
+        [mine] = [
+            memory_id
+            for memory_id, row in sdk.memories.items()
+            if row["content"] == "local drinks tea"
+        ]
+        original = sdk.delete
+
+        def raced(memory_id, kind=None, variant=None):
+            sdk.memories.pop(memory_id, None)
+            return original(memory_id, kind=kind, variant=variant)
+
+        sdk.delete = raced  # type: ignore[method-assign]
+        response = await client.delete(f"/api/v2/memories/{mine}")
+        missing = await client.delete("/api/v2/memories/no-such-memory")
+        assert _observed(response) == _observed(missing)
+        assert response.status_code == 404
 
     run_with_sdk(tmp_path, monkeypatch, scenario)
 
@@ -426,6 +458,52 @@ async def _true() -> bool:
     return True
 
 
+@pytest.mark.fresh_sdk
+@pytest.mark.parametrize("user", [None, "wife"])
+def test_every_read_echoes_the_user_it_was_read_for(tmp_path, monkeypatch, user) -> None:
+    """Each read names the user it answered for: the one asked for, else `local`."""
+
+    async def scenario(app, sdk, client):
+        await _write_both_users(app, sdk, client)
+        monkeypatch.setattr(
+            "one_memory.api._recall_model_ready", lambda _app: _true(), raising=True
+        )
+        app.state.recall_target = _sdk_recall_target(app, "local")
+        expected = user or "local"
+        params = {} if user is None else {"user_id": user}
+        body = {} if user is None else {"user_id": user}
+        reads = [
+            await client.get("/api/v2/memory-library", params=params),
+            await client.get("/api/v2/memory-library", params={**params, "query": "route"}),
+            await client.get("/api/v2/memory-library/layers", params=params),
+            await client.get("/api/v2/user-profile", params=params),
+            await client.get("/api/v2/home-summary", params=params),
+            await client.get("/api/v2/memories/graph", params=params),
+            await client.get("/api/v2/raw", params=params),
+            await client.post(
+                "/api/v2/context/search", json={"query": "drinks", "kinds": ["memory"], **body}
+            ),
+            await client.post("/api/v1/recall", json={"query": "drinks", **body}),
+            await client.post("/api/v2/memories/ask", json={"question": "what drink", **body}),
+        ]
+        for response in reads:
+            assert response.status_code == 200, (response.request.url, response.text)
+            assert response.json()["user_id"] == expected, response.request.url
+
+        async with client.stream(
+            "POST", "/api/v2/memories/ask/stream", json={"question": "what drink", **body}
+        ) as streamed:
+            events = [
+                json.loads(line[5:])
+                async for line in streamed.aiter_lines()
+                if line.startswith("data:")
+            ]
+        assert events[0]["type"] == "recall"
+        assert events[0]["user_id"] == expected
+
+    run_with_sdk(tmp_path, monkeypatch, scenario)
+
+
 @pytest.mark.fresh_sdk
 @pytest.mark.parametrize(
     ("method", "path", "kwargs"),
@@ -569,6 +647,26 @@ def test_a_hermes_root_scan_never_reads_its_profiles(tmp_path) -> None:
     assert _scan_texts(wife, tmp_path) == ["I am the wife", "hello", "wife's transcript"]
 
 
+def test_a_profiles_directory_is_skipped_at_any_depth(tmp_path) -> None:
+    """A root above the Hermes home still never reads `.hermes/profiles/**`."""
+    home = tmp_path / "home"
+    hermes, _wife = _hermes_homes(home)
+    (hermes / "sessions").mkdir()
+    (hermes / "sessions" / "own.jsonl").write_text(
+        json.dumps({"type": "message", "role": "user", "content": "own transcript"}) + "\n"
+    )
+    nested = hermes / "sessions" / "profiles" / "kid" / "sessions"
+    nested.mkdir(parents=True)
+    (nested / "k.jsonl").write_text(
+        json.dumps({"type": "message", "role": "user", "content": "kid's transcript"}) + "\n"
+    )
+
+    above = _scan_texts(home, tmp_path)
+    assert "I am the wife" not in above and "kid's transcript" not in above
+    assert set(above) == {"I am the husband", "hi", "own transcript"}
+    assert "kid's transcript" not in _scan_texts(hermes, tmp_path)
+
+
 def _jobs(database: Path) -> list[sqlite3.Row]:
     with sqlite3.connect(database) as db:
         db.row_factory = sqlite3.Row
@@ -719,6 +817,87 @@ def test_a_migrated_home_with_the_old_grant_triggers_can_connect_and_revoke(tmp_
     asyncio.run(scenario())
 
 
+async def _connect(client, user_id: str, root: Path | None = None, **extra):
+    body: dict[str, object] = {"source_ids": ["hermes"], "request_id": str(uuid4()), **extra}
+    if user_id != "local":
+        body["user_id"] = user_id
+    if root is not None:
+        body["root"] = str(root)
+    return await client.post("/api/v1/sources/connect", json=body)
+
+
+@pytest.mark.fresh_sdk
+def test_a_hermes_root_that_is_the_profiles_container_is_refused(tmp_path) -> None:
+    async def scenario():
+        home = tmp_path / "home"
+        hermes, _wife = _hermes_homes(home)
+        app = application(tmp_path, home=home)
+        async with app.router.lifespan_context(app), client_for(app) as client:
+            for user in ("wife", "local"):
+                refused = await _connect(client, user, hermes / "profiles")
+                assert refused.status_code == 422, refused.text
+                assert refused.json()["detail"] == "hermes_root_is_profiles_container"
+            assert app.state.source_grant_store.grants() == ()
+
+    asyncio.run(scenario())
+
+
+@pytest.mark.fresh_sdk
+def test_two_users_on_one_hermes_root_or_nested_roots_are_refused(tmp_path) -> None:
+    async def scenario():
+        home = tmp_path / "home"
+        hermes, wife = _hermes_homes(home)
+        (wife / "sessions").mkdir()
+        link = home / "hermes-link"
+        link.symlink_to(hermes, target_is_directory=True)
+        app = application(tmp_path, home=home)
+        async with app.router.lifespan_context(app), client_for(app) as client:
+            location = (await client.post("/api/v1/sources/hermes/location")).json()
+            local = await _connect(client, "local", source_roots={"hermes": location["root_id"]})
+            assert local.status_code == 200, local.text
+            # Same root, the same root through a symlink, a root inside it
+            # that is not `profiles/<name>`, and a root above it.
+            for root in (hermes, link, wife / "sessions", home):
+                refused = await _connect(client, "kid", root)
+                assert refused.status_code == 409, (root, refused.text)
+                assert refused.json()["detail"] == "hermes_root_overlaps_other_user"
+            # The standard layout: `local` on ~/.hermes, wife on its profile.
+            accepted = await _connect(client, "wife", wife)
+            assert accepted.status_code == 200, accepted.text
+            # Another user on wife's own root is refused too.
+            twin = await _connect(client, "wife2", wife)
+            assert twin.status_code == 409
+            # Once wife's grant is revoked her root is free again.
+            await client.post("/api/v1/sources/hermes/revoke", params={"user_id": "wife"})
+            assert (await _connect(client, "wife2", wife)).status_code == 200
+
+    asyncio.run(scenario())
+
+
+@pytest.mark.fresh_sdk
+def test_local_cannot_take_another_users_hermes_root(tmp_path) -> None:
+    """The check runs for `local`'s own connect too, not only for other users."""
+
+    async def scenario():
+        home = tmp_path / "home"
+        hermes, _wife = _hermes_homes(home)
+        other = home / "elsewhere" / ".hermes"
+        _hermes_state_db(other, [(1, "s", "user", "elsewhere")])
+        app = application(tmp_path, home=home)
+        async with app.router.lifespan_context(app), client_for(app) as client:
+            # wife took ~/.hermes itself, which is `local`'s default root.
+            taken = await _connect(client, "wife", hermes)
+            assert taken.status_code == 200, taken.text
+            location = (await client.post("/api/v1/sources/hermes/location")).json()
+            refused = await _connect(client, "local", source_roots={"hermes": location["root_id"]})
+            assert refused.status_code == 409, refused.text
+            assert refused.json()["detail"] == "hermes_root_overlaps_other_user"
+            # `local` on a root of its own that does not overlap is fine.
+            assert (await _connect(client, "local", other)).status_code == 200
+
+    asyncio.run(scenario())
+
+
 @pytest.mark.fresh_sdk
 def test_only_hermes_takes_another_user_or_a_custom_root(tmp_path) -> None:
     async def scenario():
@@ -852,7 +1031,7 @@ def test_another_users_id_answers_exactly_like_an_id_that_does_not_exist(
             other = await client.request(method, theirs, **kwargs)
             absent = await client.request(method, missing, **kwargs)
             assert _observed(other) == _observed(absent), (method, theirs)
-            assert other.status_code == (204 if method == "DELETE" else 404)
+            assert other.status_code == 404
         assert sdk.memories == before
 
     run_with_sdk(tmp_path, monkeypatch, scenario)

memhub/apps/core/tests/test_sdk_migration_bundle.py

@@ -91,7 +91,7 @@ def test_bundle_contains_management_sdk_config_and_verified_manifest(tmp_path):
     assert manifest["bundle_id"] == "migration-1"
     assert manifest["sdk_namespace"] == "governed-v2"
     assert manifest["runtime_build"] == "build-13"
-    assert manifest["snapshot_sdk_version"] == "2.0.11"
+    assert manifest["snapshot_sdk_version"] == "2.0.12"
     paths = {item["path"]: item for item in manifest["files"]}
     assert {
         "management/one-memory.sqlite3",

memhub/apps/core/tests/test_ui_language.py

@@ -1,8 +1,8 @@
 """The App's display language, and the SDK prompt language it implies.
 
-The owner's rule: zh-Hans, or no explicit choice, passes no language, so the
-SDK keeps detecting zh/en exactly as before; every other code (en included)
-is passed as `MemoryConfig.language` (hy-memory 2.0.11). A change rebuilds the
+The owner's rule (#243): every display language, zh-Hans and en included, is
+passed as `MemoryConfig.language` (hy-memory 2.0.11); only an unset language
+passes none, so the SDK keeps detecting zh/en exactly as before. A change rebuilds the
 handles the way a mode or feature change does, and the language never touches
 the vector collection identity.
 """
@@ -28,8 +28,8 @@ from one_memory.secrets import InMemorySecretStore
 from one_memory.ui_language import UI_LANGUAGES, normalize_ui_language, sdk_language
 
 TOKEN = "ui-language-test"
-#: Every code except zh-Hans is passed to the SDK.
-PASSED = ("en", "zh-Hant", "ja", "es", "de", "pt", "fr", "ko", "ru", "id")
+#: Every code is passed to the SDK, zh-Hans included.
+PASSED = ("en", "zh-Hans", "zh-Hant", "ja", "es", "de", "pt", "fr", "ko", "ru", "id")
 
 
 @pytest.fixture(autouse=True)
@@ -51,7 +51,7 @@ def _config(tmp_path: Path, language: str | None):
 
 
 def test_eleven_codes_and_the_legacy_chinese_code() -> None:
-    assert ("en", "zh-Hans", *PASSED[1:]) == UI_LANGUAGES
+    assert PASSED == UI_LANGUAGES
     assert len(UI_LANGUAGES) == 11
     # Earlier App builds stored zh-CN; it is zh-Hans now.
     assert normalize_ui_language("zh-CN") == "zh-Hans"
@@ -60,19 +60,20 @@ def test_eleven_codes_and_the_legacy_chinese_code() -> None:
     assert normalize_ui_language(None) is None
 
 
-def test_only_zh_hans_and_no_choice_leave_the_sdk_to_detect() -> None:
+def test_only_an_unset_language_leaves_the_sdk_to_detect() -> None:
     assert sdk_language(None) is None
-    assert sdk_language("zh-Hans") is None
-    assert sdk_language("zh-CN") is None
     assert sdk_language("system") is None
+    assert sdk_language("xx") is None
+    # zh-Hans is passed like every other code; the legacy zh-CN maps to it.
+    assert sdk_language("zh-Hans") == "zh-Hans"
+    assert sdk_language("zh-CN") == "zh-Hans"
     for code in PASSED:
         assert sdk_language(code) == code
 
 
-def test_zh_hans_and_no_choice_build_the_config_of_before(tmp_path) -> None:
-    before = repr(dataclasses.asdict(_config(tmp_path, None)))
+def test_no_language_builds_the_config_of_before(tmp_path) -> None:
     assert _config(tmp_path, None).language is None
-    assert repr(dataclasses.asdict(_config(tmp_path, sdk_language("zh-Hans")))) == before
+    assert _config(tmp_path, sdk_language("zh-Hans")).language == "zh-Hans"
 
 
 @pytest.mark.parametrize("code", PASSED)
@@ -282,17 +283,31 @@ def test_ui_language_api_get_put_and_status(tmp_path, monkeypatch) -> None:
         assert current["languages"] == list(UI_LANGUAGES)
         assert reads.current_language() is None and writes.sdk_language() is None
 
-        # zh-Hans: recorded, but the SDK still detects zh/en; nothing rebuilt.
+        # zh-Hans is passed explicitly: Chinese prompts, handles rebuilt (#243).
         body = (
             await client.put("/api/v1/settings/ui-language", json={"ui_language": "zh-Hans"})
         ).json()
-        assert body == {**current, "ui_language": "zh-Hans", "rebuilt": False}
-        assert retired == [] and reads.current_language() is None
+        assert body == {
+            **current,
+            "ui_language": "zh-Hans",
+            "sdk_language": "zh-Hans",
+            "rebuilt": True,
+        }
+        assert reads.current_language() == "zh-Hans" and writes.sdk_language() == "zh-Hans"
+        assert retired == ["zh-Hans"]
+        processing = (await client.get("/api/v1/memory-processing")).json()
+        assert processing["pipeline"]["sdk_language"] == "zh-Hans"
+
+        # The same value again changes nothing.
+        body = (
+            await client.put("/api/v1/settings/ui-language", json={"ui_language": "zh-Hans"})
+        ).json()
+        assert body["rebuilt"] is False and retired == ["zh-Hans"]
 
         body = (await client.put("/api/v1/settings/ui-language", json={"ui_language": "ja"})).json()
         assert body["sdk_language"] == "ja" and body["rebuilt"] is True
         assert reads.current_language() == "ja" and writes.sdk_language() == "ja"
-        assert retired == ["ja"]
+        assert retired == ["zh-Hans", "ja"]
 
         # An explicit English choice forces English prompts.
         body = (await client.put("/api/v1/settings/ui-language", json={"ui_language": "en"})).json()
@@ -302,7 +317,7 @@ def test_ui_language_api_get_put_and_status(tmp_path, monkeypatch) -> None:
         assert processing["pipeline"]["ui_language"] == "en"
         assert processing["pipeline"]["sdk_language"] == "en"
 
-        # Back to "follow the system": auto again.
+        # Unset (CLI `settings language system`): auto again.
         body = (await client.put("/api/v1/settings/ui-language", json={"ui_language": None})).json()
         assert body["sdk_language"] == "auto" and body["rebuilt"] is True
         assert reads.current_language() is None

memhub/apps/core/uv.lock

@@ -991,7 +991,7 @@ wheels = [
 
 [[package]]
 name = "hy-memory"
-version = "2.0.11"
+version = "2.0.12"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "chromadb" },
@@ -1008,9 +1008,9 @@ dependencies = [
     { name = "scikit-learn" },
     { name = "tiktoken" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/01/93/aec7d243259f6a315f38e8ebc21a9eea153a48fc13648fda149be7672788/hy_memory-2.0.11.tar.gz", hash = "sha256:96d6bd606d61052f127cd274aa6f8de8e7151d6250f1e89e4ef5b90e18ec7cb0", size = 1245738, upload-time = "2026-11-01T14:15:02.474Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/44/19/bcd0de44ae2011ee1ad70579996aad72e18f0ca292df22d1545db05db850/hy_memory-2.0.12.tar.gz", hash = "sha256:c1231596b4cf12595775541f81680d4819461cb69e4aa4dc449f876d4c3b6742", size = 1246969, upload-time = "2026-11-02T06:30:37.448Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/1a/85/1f5e6a13507a0cfcdce26f67c590df00d327a0f7d5c5b5483c3bd0fa2f85/hy_memory-2.0.11-py3-none-any.whl", hash = "sha256:c0173444a83c1197a49acaccb123f8286cea205b4838c1e83d106974f5bad259", size = 1315871, upload-time = "2026-11-01T14:14:58.764Z" },
+    { url = "https://files.pythonhosted.org/packages/75/9e/b64c7643c1bad1ddca4623a39bb62423bed0c22e7fd0d86be1ff73b2a17a/hy_memory-2.0.12-py3-none-any.whl", hash = "sha256:7a2332288197fafb89d5037eac7fef97df4c80794ead18159d21da84cde431df", size = 1316922, upload-time = "2026-11-02T06:30:35.105Z" },
 ]
 
 [[package]]
@@ -1837,7 +1837,7 @@ requires-dist = [
     { name = "fastapi", specifier = ">=0.141.1" },
     { name = "filelock", specifier = ">=3.32.4" },
     { name = "httpx", specifier = ">=0.28.1" },
-    { name = "hy-memory", specifier = "==2.0.11" },
+    { name = "hy-memory", specifier = "==2.0.12" },
     { name = "keyring", specifier = ">=25.7.0" },
     { name = "numpy", specifier = "==2.5.2" },
     { name = "onnxruntime", specifier = "==1.23.2" },

memhub/apps/desktop/src/background-tray.test.ts

@@ -9,7 +9,7 @@ import type {
   Tray,
 } from "electron";
 import { describe, expect, it, vi } from "vitest";
-import { installBackgroundTray } from "./background-tray";
+import { installBackgroundTray, type RuntimeHosting } from "./background-tray";
 import type { LoginPreference } from "./login-preference";
 
 async function flush() {
@@ -27,6 +27,7 @@ function fixture(
     status: "disabled",
   };
   let changed: (() => void) | undefined;
+  let hosting: RuntimeHosting | Error = "background-service";
   const languageSnapshot: LanguageSnapshot = {
     preference: "zh-Hans",
     locale: "zh-Hans",
@@ -50,6 +51,10 @@ function fixture(
     };
     return state;
   });
+  const readRuntimeHosting = vi.fn(async () => {
+    if (hosting instanceof Error) throw hosting;
+    return hosting;
+  });
   const open = vi.fn();
   const reportError = vi.fn();
   const install = () =>
@@ -77,6 +82,7 @@ function fixture(
       reportError,
       readLoginPreference,
       setLoginPreference,
+      readRuntimeHosting,
       ...(trial
         ? { allowLoginStartup: false, productName: "One Memory Trial" }
         : {}),
@@ -91,6 +97,7 @@ function fixture(
     menus,
     readLoginPreference,
     setLoginPreference,
+    readRuntimeHosting,
     open,
     reportError,
     install,
@@ -103,6 +110,9 @@ function fixture(
     setState(value: LoginPreference) {
       state = value;
     },
+    setHosting(value: RuntimeHosting | Error) {
+      hosting = value;
+    },
   };
 }
 
@@ -179,6 +189,50 @@ describe("native macOS background tray", () => {
     expect(f.tray.eventNames()).toEqual([]);
   });
 
+  it("says quitting stops the memory service when the App hosts it", async () => {
+    const f = fixture();
+    f.setHosting("app-hosted");
+    f.install();
+    await flush();
+    expect(f.menu()[3]?.label).toBe("退出 MemHub（同时停止记忆服务）");
+    f.changeLanguage("es");
+    await flush();
+    expect(f.menu()[3]?.label).toBe(
+      "Salir de MemHub (también detiene el servicio de memoria)",
+    );
+  });
+
+  it("re-reads who hosts the Runtime every time the menu opens", async () => {
+    const f = fixture();
+    f.install();
+    await flush();
+    expect(f.menu()[3]?.label).toContain("后台服务继续运行");
+
+    // The user turned the background service off in Settings.
+    f.setHosting("app-hosted");
+    f.tray.emit("mouse-down");
+    await flush();
+    expect(f.menu()[3]?.label).toContain("同时停止记忆服务");
+
+    f.setHosting("background-service");
+    f.tray.emit("right-click");
+    await flush();
+    expect(f.menu()[3]?.label).toContain("后台服务继续运行");
+    expect(f.readRuntimeHosting).toHaveBeenCalledTimes(3);
+  });
+
+  it("never claims quit stops the service when the state is unknown", async () => {
+    const f = fixture();
+    f.setHosting(new Error("launchctl timed out"));
+    f.install();
+    await flush();
+    expect(f.menu()[3]?.label).toContain("后台服务继续运行");
+    f.setHosting("unknown");
+    f.tray.emit("mouse-down");
+    await flush();
+    expect(f.menu()[3]?.label).toContain("后台服务继续运行");
+  });
+
   it("blocks login changes for trial, development and non-macOS builds", async () => {
     for (const f of [
       fixture(true, "darwin", true),

memhub/apps/desktop/src/background-tray.ts

@@ -10,6 +10,8 @@ import type {
 import type { LoginPreference } from "./login-preference";
 import type { NativeLanguageSource } from "./native-language";
 
+export type RuntimeHosting = "background-service" | "app-hosted" | "unknown";
+
 export const LOGIN_SERVICE_NAME = "com.tencent.onememory.runtime.plist";
 
 interface TrayOptions {
@@ -24,6 +26,9 @@ interface TrayOptions {
   reportError(message: string): void;
   readLoginPreference(): Promise<LoginPreference>;
   setLoginPreference(enabled: boolean): Promise<LoginPreference>;
+  /** Who keeps the Runtime alive, re-read on every menu refresh: the
+   * background service (quit leaves it running) or this App (quit stops it). */
+  readRuntimeHosting?(): Promise<RuntimeHosting>;
   allowLoginStartup?: boolean;
   productName?: string;
   language?: NativeLanguageSource;
@@ -67,6 +72,13 @@ export function installBackgroundTray(options: TrayOptions): () => void {
     } else {
       label += t("nativeDevelopmentUnavailable");
     }
+    let hosting: RuntimeHosting = "unknown";
+    try {
+      hosting = (await options.readRuntimeHosting?.()) ?? "unknown";
+    } catch {
+      hosting = "unknown";
+    }
+    if (disposed || current !== generation) return;
     tray.setContextMenu(
       options.buildMenu([
         { label: t("nativeOpen"), click: options.open },
@@ -92,7 +104,10 @@ export function installBackgroundTray(options: TrayOptions): () => void {
         },
         { type: "separator" },
         {
-          label: t("nativeQuit"),
+          // Unknown keeps the plain label: quit then stops nothing.
+          label: t(
+            hosting === "app-hosted" ? "nativeQuitStopsService" : "nativeQuit",
+          ),
           click: () => {
             if (!disposed) app.quit();
           },

memhub/apps/desktop/src/build-identity-config.test.ts

@@ -15,9 +15,13 @@ it("bakes fallback release identity when the packaging pipeline omits it", async
   expect(config).toMatch(
     /__ONE_MEMORY_BUILD_NUMBER__: JSON\.stringify\(\s*String\(releaseBuildNumber\)/,
   );
-  expect(config).toMatch(
-    /process\.env\.ONE_MEMORY_COMMIT\?\.trim\(\) \|\| readSourceCommit\(\)/,
+  expect(config).toContain(
+    "const releaseCommit = resolveReleaseCommit(process.env.ONE_MEMORY_COMMIT)",
   );
+  expect(config).toMatch(/if \(!trimmed\) return readSourceCommit\(\);/);
+  // A supplied commit must be the full 40-character form the runtime accepts.
+  expect(config).toContain("/^[0-9a-f]{40}$/i.test(trimmed)");
+  expect(config).toContain("return trimmed.toLowerCase();");
   expect(config).toMatch(
     /execFileSync\("git", \["rev-parse", "HEAD"\],[\s\S]*?encoding: "utf8"/,
   );

memhub/apps/desktop/src/core-language-sync.test.ts

@@ -1,4 +1,4 @@
-import type { LanguageSnapshot } from "@one-memory/i18n";
+import type { GuiLocale, LanguageSnapshot } from "@one-memory/i18n";
 import { describe, expect, it, vi } from "vitest";
 import { coreUiLanguage, installCoreLanguageSync } from "./core-language-sync";
 
@@ -21,11 +21,16 @@ function source(initial: LanguageSnapshot) {
 const settle = () => new Promise((resolve) => setTimeout(resolve, 0));
 
 describe("Core language sync", () => {
-  it("tells Core null for system and the code for an explicit choice", () => {
-    expect(coreUiLanguage("system")).toBeNull();
-    expect(coreUiLanguage("zh-Hans")).toBe("zh-Hans");
-    expect(coreUiLanguage("en")).toBe("en");
-    expect(coreUiLanguage("ja")).toBe("ja");
+  it("tells Core the language the GUI shows, system included", () => {
+    const shown = (
+      preference: LanguageSnapshot["preference"],
+      locale: GuiLocale,
+    ) => coreUiLanguage({ preference, locale, revision: 0 });
+    expect(shown("system", "zh-Hans")).toBe("zh-Hans");
+    expect(shown("system", "en")).toBe("en");
+    expect(shown("zh-Hans", "zh-Hans")).toBe("zh-Hans");
+    expect(shown("en", "en")).toBe("en");
+    expect(shown("ja", "ja")).toBe("ja");
   });
 
   it("sends the stored choice once at launch, then every change", async () => {
@@ -38,29 +43,33 @@ describe("Core language sync", () => {
     await settle();
     language.change({ preference: "system", locale: "en", revision: 2 });
     await settle();
-    expect(send.mock.calls).toEqual([["es"], ["ja"], [null]]);
+    expect(send.mock.calls).toEqual([["es"], ["ja"], ["en"]]);
     dispose();
     language.change({ preference: "de", locale: "de", revision: 3 });
     await settle();
     expect(send).toHaveBeenCalledTimes(3);
   });
 
-  it("an untouched install sends null, which leaves the SDK on auto", async () => {
+  it("an untouched install sends the system language the GUI shows", async () => {
     const language = source({
       preference: "system",
-      locale: "ja",
+      locale: "zh-Hans",
       revision: 0,
     });
     const send = vi.fn(async () => {});
     installCoreLanguageSync({ language, send });
     await settle();
-    expect(send.mock.calls).toEqual([[null]]);
+    expect(send.mock.calls).toEqual([["zh-Hans"]]);
+    // Choosing the language already shown changes nothing Core sees.
+    language.change({ preference: "zh-Hans", locale: "zh-Hans", revision: 1 });
+    await settle();
+    expect(send).toHaveBeenCalledTimes(1);
   });
 
   it("reports a failed send and retries it with the next change", async () => {
     const language = source({ preference: "fr", locale: "fr", revision: 0 });
     const send = vi
-      .fn<(value: string | null) => Promise<void>>()
+      .fn<(value: string) => Promise<void>>()
       .mockRejectedValueOnce(new Error("core_unavailable"))
       .mockResolvedValue(undefined);
     const reportError = vi.fn();

memhub/apps/desktop/src/core-language-sync.ts

@@ -1,35 +1,37 @@
-import type { GuiLocale, LanguagePreference } from "@one-memory/i18n";
+import type { GuiLocale, LanguageSnapshot } from "@one-memory/i18n";
 import type { NativeLanguageSource } from "./native-language";
 
-/** What Core is told: a code, or null for "follow the system". */
-export function coreUiLanguage(
-  preference: LanguagePreference,
-): GuiLocale | null {
-  return preference === "system" ? null : preference;
+/**
+ * What Core is told: the language the GUI shows. "Follow the system" sends
+ * the language it resolved to, so the memories match the interface a person
+ * sees; the App never leaves the SDK to detect zh/en (#243).
+ */
+export function coreUiLanguage(snapshot: LanguageSnapshot): GuiLocale {
+  return snapshot.locale;
 }
 
 /**
- * Keep Core's `ui_language` setting on the display language a person chose.
+ * Keep Core's `ui_language` setting on the display language the GUI shows.
  *
- * Core builds every SDK client with it: zh-Hans and "follow the system" pass
- * no language (the SDK keeps detecting zh/en), any other choice sets the SDK
- * prompt language. Sent once when installed, so a choice made before this
- * existed reaches Core, then on every committed change; a value Core already
- * has is not sent again. Best effort: a failed send is reported and retried
- * with the next change or launch, and never blocks the GUI.
+ * Core builds every SDK client with it and passes it, zh-Hans included, as
+ * the SDK prompt language. Sent once when installed, so a choice made before
+ * this existed, or the system language followed at this launch, reaches
+ * Core; then on every committed change. A value Core already has is not sent
+ * again. Best effort: a failed send is reported and retried with the next
+ * change or launch, and never blocks the GUI.
  */
 export function installCoreLanguageSync(options: {
   language: NativeLanguageSource;
-  send(uiLanguage: GuiLocale | null): Promise<void>;
+  send(uiLanguage: GuiLocale): Promise<void>;
   reportError?(error: unknown): void;
 }): () => void {
   let closed = false;
-  let sent: GuiLocale | null | undefined;
+  let sent: GuiLocale | undefined;
   let queue: Promise<void> = Promise.resolve();
   const push = () => {
     queue = queue.then(async () => {
       if (closed) return;
-      const value = coreUiLanguage(options.language.read().preference);
+      const value = coreUiLanguage(options.language.read());
       if (value === sent) return;
       try {
         await options.send(value);

memhub/apps/desktop/src/isolated-runtime.test.ts

@@ -526,7 +526,22 @@ describe("hourly isolated desktop launch", () => {
     expect(resolvePackagedBuildNumber("-1")).toBeUndefined();
     expect(resolvePackagedBuildNumber(undefined, "3907")).toBe(3907);
     expect(resolvePackagedBuildNumber("3908", "3907")).toBe(3908);
-    expect(resolvePackagedCommit(undefined, "388fd0e9")).toBe("388fd0e9");
-    expect(resolvePackagedCommit("not-a-sha", "388fd0e9")).toBe("388fd0e9");
+  });
+
+  it("resolves only a full 40-character commit and lowercases it", () => {
+    // Every downstream check (packaged-runtime install, local install, release
+    // download, release scripts) requires 40 lowercase hex characters.
+    const embedded = "388fd0e9b3c41a2d5e6f7a8b9c0d1e2f3a4b5c6d";
+    expect(resolvePackagedCommit(undefined, embedded)).toBe(embedded);
+    expect(resolvePackagedCommit(embedded.toUpperCase())).toBe(embedded);
+    expect(
+      resolvePackagedCommit(` ${embedded.toUpperCase()} `, undefined),
+    ).toBe(embedded);
+    expect(resolvePackagedCommit("388fd0e9", embedded)).toBe(embedded);
+    expect(resolvePackagedCommit("388fd0e9")).toBeUndefined();
+    expect(resolvePackagedCommit("not-a-sha", embedded)).toBe(embedded);
+    expect(resolvePackagedCommit(`${embedded}0`, embedded)).toBe(embedded);
+    expect(resolvePackagedCommit("g".repeat(40), embedded)).toBe(embedded);
+    expect(resolvePackagedCommit(undefined, "unknown")).toBeUndefined();
   });
 });

memhub/apps/desktop/src/isolated-runtime.ts

@@ -143,6 +143,12 @@ export function resolvePackagedBuildNumber(
   return undefined;
 }
 
+/**
+ * The packaged-runtime install, local install, release download and release
+ * scripts all require a full 40-character lowercase commit. Normalise here so
+ * that one format crosses this boundary: an uppercase full SHA is lowercased,
+ * and a short or malformed value is skipped so it cannot shadow the next source.
+ */
 export function resolvePackagedCommit(
   environmentValue: unknown,
   embeddedValue?: unknown,
@@ -150,7 +156,7 @@ export function resolvePackagedCommit(
   for (const value of [environmentValue, embeddedValue]) {
     if (typeof value !== "string") continue;
     const trimmed = value.trim();
-    if (/^[0-9a-f]{7,40}$/i.test(trimmed)) return trimmed;
+    if (/^[0-9a-f]{40}$/i.test(trimmed)) return trimmed.toLowerCase();
   }
   return undefined;
 }

memhub/apps/desktop/src/login-preference.test.ts

@@ -5,6 +5,7 @@ import {
   claimRuntimeServiceForApp,
   claimRuntimeServiceForCli,
   enableRuntimeService,
+  type RuntimeServiceState,
   runtimeServiceEnableMarkerPath,
 } from "@one-memory/runtime-control";
 import { expect, it } from "vitest";
@@ -98,3 +99,25 @@ it("rejects unsupported and unconfirmed writes", async () => {
     ),
   ).rejects.toThrow("login_preference_unsupported");
 });
+
+it("reads a launchctl-disabled service as off and not switchable, asked fresh", async () => {
+  const dataDir = await appOwned();
+  let state: RuntimeServiceState = {
+    state: "disabled",
+    reason: "service-disabled-by-launchctl",
+    jobPid: null,
+  };
+  const serviceState = async () => state;
+
+  await expect(
+    readLoginPreference(dataDir, "darwin", true, serviceState),
+  ).resolves.toEqual({
+    supported: false,
+    enabled: false,
+    status: "disabled-by-system",
+  });
+  state = { state: "enabled", reason: "service-enabled", jobPid: 4321 };
+  await expect(
+    readLoginPreference(dataDir, "darwin", true, serviceState),
+  ).resolves.toEqual({ supported: true, enabled: true, status: "enabled" });
+});

memhub/apps/desktop/src/login-preference.ts

@@ -1,6 +1,7 @@
 import {
   disableRuntimeService,
   enableRuntimeService,
+  type RuntimeServiceState,
   readRuntimeServiceOwner,
   runtimeServiceEnabled,
   setAppRuntimeStartAtLogin,
@@ -12,10 +13,16 @@ export interface LoginPreference {
   status: string;
 }
 
+/** "Launch at login" is the background service switch: it writes the enable
+ * marker the LaunchAgent's `KeepAlive` waits on. On it means the Runtime
+ * outlives the App and quitting leaves it running; off means quitting stops
+ * it. `serviceState`, when given, is asked fresh so a `launchctl disable`
+ * override (which the switch cannot undo) reads as off, not as on. */
 export async function readLoginPreference(
   dataDir: string,
   platform: NodeJS.Platform,
   supported: boolean,
+  serviceState?: () => Promise<RuntimeServiceState>,
 ): Promise<LoginPreference> {
   if (platform !== "darwin" || !supported) {
     return { supported: false, enabled: false, status: "unsupported" };
@@ -28,6 +35,12 @@ export async function readLoginPreference(
     if (owner?.owner !== "app") {
       return { supported: false, enabled: false, status: "not-installed" };
     }
+    if (
+      serviceState &&
+      (await serviceState()).reason === "service-disabled-by-launchctl"
+    ) {
+      return { supported: false, enabled: false, status: "disabled-by-system" };
+    }
     return {
       supported: true,
       enabled: owner.start_at_login && (await runtimeServiceEnabled(dataDir)),
@@ -46,6 +59,7 @@ export async function setLoginPreference(
   platform: NodeJS.Platform,
   input: unknown,
   supported: boolean,
+  serviceState?: () => Promise<RuntimeServiceState>,
 ): Promise<LoginPreference> {
   if (
     !input ||
@@ -63,5 +77,5 @@ export async function setLoginPreference(
   await setAppRuntimeStartAtLogin(dataDir, input.openAtLogin);
   if (input.openAtLogin) await enableRuntimeService(dataDir);
   else await disableRuntimeService(dataDir);
-  return readLoginPreference(dataDir, platform, supported);
+  return readLoginPreference(dataDir, platform, supported, serviceState);
 }

memhub/apps/desktop/src/main.ts

@@ -23,7 +23,9 @@ import {
   type HostPermissionClient,
   installPackagedRuntime,
   installUserService,
+  queryRuntimeServiceState,
   RecallBrokerSupervisor,
+  type RuntimeServiceState,
   RuntimeSupervisor,
   readInstalledRuntimeSource,
   readPublishedCorePort,
@@ -110,6 +112,7 @@ import { showMigrationFailureDialog } from "./migration-failure-dialog";
 import { isAllowedNavigation } from "./navigation-policy";
 import { installDenyAllPermissionPolicy } from "./permissions";
 import { isHostPresent, recallHosts } from "./recall-hosts";
+import { reconcileRunningRuntime } from "./runtime-adoption";
 import { shutdownRuntime } from "./runtime-shutdown";
 import { createSourceChangeHandler } from "./source-change-handler";
 import { SourceDirectoryPicker } from "./source-directory-picker";
@@ -140,7 +143,12 @@ let runtimeSupervisor: RuntimeSupervisor | null = null;
 // Where the Runtime keeps its receipt. Stopping it on a full quit needs this,
 // and `stop` runs outside `initialize`, where the directory is chosen.
 let runtimeDataDir: string | null = null;
-let preserveManagedRuntimeOnQuit = false;
+// Whether quitting stops the Runtime is asked of the service manager at quit
+// time (`currentRuntimeServiceState`), never remembered from startup. The one
+// startup fact kept is a Runtime whose build could not be read: this App never
+// stops one it could not compare with its own.
+let preserveRuntimeOnQuitReason: string | null = null;
+let runtimeServiceManagedByApp = false;
 let disposeTray: (() => void) | null = null;
 let disposeApplicationMenu: (() => void) | null = null;
 let languagePreferences: LanguagePreferences | null = null;
@@ -247,6 +255,25 @@ if (trialProfile) {
   app.setPath("userData", hourlyUserDataDir);
 }
 
+/** Ask the service manager, now, whether the background service for this data
+ * dir is on. Never cached: quit and the tray each re-read it, so a switch made
+ * in Settings, by `memhub service`, or by `launchctl` counts immediately. */
+function currentRuntimeServiceState(): Promise<RuntimeServiceState> {
+  if (!runtimeDataDir) {
+    return Promise.resolve({
+      state: "unknown",
+      reason: "service-state-query-failed",
+      jobPid: null,
+    });
+  }
+  return queryRuntimeServiceState({
+    dataDir: runtimeDataDir,
+    home: app.getPath("home"),
+    platform: process.platform,
+    uid: process.getuid?.(),
+  });
+}
+
 function prepareProtocol(): void {
   protocol.registerSchemesAsPrivileged([
     {
@@ -498,6 +525,7 @@ async function initialize(isQuitting: () => boolean): Promise<void> {
     !preview &&
     (hostIntegrationEnabled || desktopTestIsolation !== null) &&
     installedApplication;
+  runtimeServiceManagedByApp = appManagedRuntime;
   const runningPackagedHost =
     app.isPackaged && !isolatedHourly
       ? await resolveRunningPackagedHostPaths({
@@ -594,9 +622,11 @@ async function initialize(isQuitting: () => boolean): Promise<void> {
     throw new Error("host_permission_store_unavailable");
   }
   if (isQuitting()) return;
-  const hosts = (await recallHosts(app.getPath("home"))).filter(
-    (host) => host.hostId !== "openclaw",
-  );
+  const scanHosts = async () =>
+    (await recallHosts(app.getPath("home"))).filter(
+      (host) => host.hostId !== "openclaw",
+    );
+  const hosts = await scanHosts();
   readDiagnosticSummary = async () => {
     const core = coreSupervisor;
     if (!core) return {};
@@ -851,14 +881,25 @@ async function initialize(isQuitting: () => boolean): Promise<void> {
   );
   ipcMain.handle("one-memory:get-login-preference", (event) => {
     assertAllowedRenderer(event.senderFrame?.url);
-    return readLoginPreference(dataDir, process.platform, appManagedRuntime);
+    return readLoginPreference(
+      dataDir,
+      process.platform,
+      appManagedRuntime,
+      currentRuntimeServiceState,
+    );
   });
   ipcMain.handle("one-memory:set-login-preference", (event, input: unknown) => {
     assertAllowedRenderer(event.senderFrame?.url);
     return observeDesktopAction(
       "login_preference",
       () =>
-        setLoginPreference(dataDir, process.platform, input, appManagedRuntime),
+        setLoginPreference(
+          dataDir,
+          process.platform,
+          input,
+          appManagedRuntime,
+          currentRuntimeServiceState,
+        ),
       { action: "set" },
     );
   });
@@ -876,10 +917,14 @@ async function initialize(isQuitting: () => boolean): Promise<void> {
   });
   ipcMain.handle("one-memory:recall-hosts", async (event) => {
     assertAllowedRenderer(event.senderFrame?.url);
+    // A Harness profile can appear at any time, and which ones exist is only
+    // knowable from the disk. In place, so `requireHost` sees it too. One
+    // directory read per list, next to an IPC round trip per host below.
+    hosts.splice(0, hosts.length, ...(await scanHosts()));
     if (connectionClient?.host) {
       const inspector = createConnectionClient({ dataDir });
       const rows: unknown[] = [];
-      for (const host of hosts) {
+      for (const host of [...hosts]) {
         const inspected = await inspector.host?.({
           hostId: host.hostId,
           operation: "inspect",
@@ -1169,7 +1214,6 @@ async function initialize(isQuitting: () => boolean): Promise<void> {
       const startAtLogin = owner?.owner === "app" ? owner.start_at_login : true;
       const previousOwner = owner;
       let runtimeChanged = false;
-      let transientRuntime = false;
       // Install whoever owns the service. Owner decides who starts and stops
       // it, not which build runs: skipping the install for a CLI owner (also
       // the App's own guess when its receipt is missing) left an upgraded App
@@ -1239,12 +1283,68 @@ async function initialize(isQuitting: () => boolean): Promise<void> {
         const frozen = await readSdkMigrationBlock(dataDir);
         if (frozen?.frozen !== undefined) throw new Error(frozen.code);
       }
-      const alreadyRunning = runtimeChanged
-        ? false
-        : await waitForRuntimeProcess({ dataDir, attempts: 4 }).then(
-            () => true,
-            () => false,
-          );
+      // One Runtime per data dir. A Runtime already serving it is adopted
+      // when it is this App's build or newer (silently; a newer one is never
+      // stopped or downgraded at startup); an older one is replaced (through
+      // launchd when it is the service's job), and one whose build cannot be
+      // read is adopted but never stopped.
+      const reconciled = await reconcileRunningRuntime({
+        app: {
+          ...(packagedBuildNumber === undefined
+            ? {}
+            : { buildNumber: packagedBuildNumber }),
+          ...(packagedCommit === undefined ? {} : { commit: packagedCommit }),
+        },
+        installedChanged: runtimeChanged,
+        findRunning: () =>
+          waitForRuntimeProcess({ dataDir, attempts: 4 }).then(
+            (attachment) =>
+              attachment.servicePid === null
+                ? null
+                : {
+                    pid: attachment.servicePid,
+                    build: attachment.runtimeBuild,
+                  },
+            () => null,
+          ),
+        queryServiceState: currentRuntimeServiceState,
+        stopRuntime: () => stopRuntimeProcess({ dataDir }),
+        log: ({ decision, service, running }) =>
+          diagnostics.log({
+            level: decision.action === "adopt-unverified" ? "warn" : "info",
+            component: "desktop.stable_runtime",
+            event: "stable_runtime.adoption",
+            outcome:
+              decision.action === "adopt-unverified" ? "degraded" : "succeeded",
+            details: {
+              action: decision.action,
+              reason:
+                "reason" in decision
+                  ? decision.reason
+                  : (service?.reason ?? "no-runtime-running"),
+              status: service?.state ?? "not-queried",
+              version:
+                running === null
+                  ? "none"
+                  : running.build === undefined
+                    ? "legacy"
+                    : String(running.build.buildNumber ?? "unknown"),
+            },
+          }),
+      });
+      preserveRuntimeOnQuitReason = reconciled.preserveReason;
+      if (reconciled.decision.action === "adopt-unverified") {
+        void dialog
+          .showMessageBox({
+            type: "warning",
+            message: "MemHub",
+            detail: stableRuntimeFailureDetail(
+              new Error("runtime_build_unknown"),
+            ),
+          })
+          .catch(() => undefined);
+      }
+      const alreadyRunning = reconciled.adopted;
       if (owner?.owner !== "cli") {
         const appBundle = path.resolve(path.dirname(process.execPath), "../..");
         owner = await claimRuntimeServiceForApp({
@@ -1258,8 +1358,13 @@ async function initialize(isQuitting: () => boolean): Promise<void> {
         // A durable `launchctl disable` override is a state to report, not a
         // failure to undo: `installUserService` never re-enables a service the
         // user or the system disabled. An explicit App launch may still own a
-        // transient Runtime for this UI session. Shutdown stops that process.
-        const serviceMode = await installServiceWithDisabledFallback({
+        // transient Runtime for this UI session; quit stops it because the
+        // service is disabled, which it decides by asking launchd again then.
+        // For an enabled service, `installUserService` restarts the job with
+        // `kickstart -k` (or re-bootstraps a changed plist), so an older
+        // Runtime is replaced through launchd rather than killed into a
+        // respawn of the old binary.
+        await installServiceWithDisabledFallback({
           install: async () => {
             await installUserService(layout, {
               uid: process.getuid?.(),
@@ -1291,12 +1396,10 @@ async function initialize(isQuitting: () => boolean): Promise<void> {
             });
           },
         });
-        transientRuntime = serviceMode === "transient";
       }
       if (owner?.owner === "app" && !startAtLogin) {
         await disableRuntimeService(dataDir);
       }
-      preserveManagedRuntimeOnQuit = !transientRuntime;
     } else if (standaloneRuntime) {
       if (
         !desktopBackgroundLaunch &&
@@ -1665,7 +1768,8 @@ if (desktopVersion !== null) {
             ? readLoginPreference(
                 runtimeDataDir,
                 process.platform,
-                preserveManagedRuntimeOnQuit,
+                runtimeServiceManagedByApp,
+                currentRuntimeServiceState,
               )
             : Promise.resolve({
                 supported: false,
@@ -1678,9 +1782,21 @@ if (desktopVersion !== null) {
             runtimeDataDir,
             process.platform,
             { openAtLogin: enabled, userConfirmed: true },
-            preserveManagedRuntimeOnQuit,
+            runtimeServiceManagedByApp,
+            currentRuntimeServiceState,
           );
         },
+        readRuntimeHosting: async () => {
+          if (!runtimeDataDir || !app.isPackaged) return "unknown";
+          // A Runtime whose build could not be read is never stopped by it.
+          if (preserveRuntimeOnQuitReason) return "unknown";
+          const service = await currentRuntimeServiceState();
+          return service.state === "enabled"
+            ? "background-service"
+            : service.state === "disabled"
+              ? "app-hosted"
+              : "unknown";
+        },
         ...(trialProfile
           ? { allowLoginStartup: false, productName: app.getName() }
           : {}),
@@ -1712,7 +1828,10 @@ if (desktopVersion !== null) {
         // stop and says so by taking the embedded path instead.
         dataDir: runtimeDataDir ?? "",
         standalone: app.isPackaged && runtimeDataDir !== null,
-        preserveManagedRuntime: preserveManagedRuntimeOnQuit,
+        // Asked now, not remembered from startup: the user may have switched
+        // the background service on or off since.
+        queryServiceState: currentRuntimeServiceState,
+        preserveReason: preserveRuntimeOnQuitReason,
         stopSupervisor: async () => {
           const results = await Promise.allSettled([
             runtimeSupervisor?.stop() ?? coreSupervisor?.stop(),

memhub/apps/desktop/src/runtime-adoption.test.ts

@@ -0,0 +1,233 @@
+import type { RuntimeServiceState } from "@one-memory/runtime-control";
+import { describe, expect, it, vi } from "vitest";
+
+import {
+  compareRuntimeBuild,
+  decideRuntimeAdoption,
+  type RunningRuntime,
+  reconcileRunningRuntime,
+} from "./runtime-adoption";
+
+const app = { buildNumber: 38, commit: "abcdef1234567" };
+const enabled = (jobPid: number | null): RuntimeServiceState => ({
+  state: "enabled",
+  reason: "service-enabled",
+  jobPid,
+});
+const disabled: RuntimeServiceState = {
+  state: "disabled",
+  reason: "service-disabled-by-launchctl",
+  jobPid: null,
+};
+const unknown: RuntimeServiceState = {
+  state: "unknown",
+  reason: "service-state-timeout",
+  jobPid: null,
+};
+const running = (
+  build: RunningRuntime["build"],
+  pid = 4321,
+): RunningRuntime => ({ pid, build });
+
+function reconcile(options: {
+  running: RunningRuntime | null;
+  service: RuntimeServiceState;
+  installedChanged?: boolean;
+}) {
+  const stopRuntime = vi.fn(async () => "stopped");
+  const queryServiceState = vi.fn(async () => options.service);
+  const result = reconcileRunningRuntime({
+    app,
+    installedChanged: options.installedChanged ?? false,
+    findRunning: async () => options.running,
+    queryServiceState,
+    stopRuntime,
+  });
+  return { result, stopRuntime, queryServiceState };
+}
+
+describe("comparing the running Runtime's build with the App's", () => {
+  it("compares build numbers, then commits both sides know", () => {
+    expect(compareRuntimeBuild(app, { buildNumber: 38, commit: null })).toBe(
+      "same",
+    );
+    expect(
+      compareRuntimeBuild(app, { buildNumber: 38, commit: "abcdef1" }),
+    ).toBe("same");
+    expect(
+      compareRuntimeBuild(app, { buildNumber: 38, commit: "0123456" }),
+    ).toBe("app-newer");
+    expect(compareRuntimeBuild(app, { buildNumber: 37, commit: null })).toBe(
+      "app-newer",
+    );
+    expect(compareRuntimeBuild(app, { buildNumber: 39, commit: null })).toBe(
+      "runtime-newer",
+    );
+  });
+
+  it("reads a receipt without build fields as a Runtime older than this App", () => {
+    expect(compareRuntimeBuild(app, undefined)).toBe("app-newer");
+  });
+
+  it("is unknown when either side cannot say", () => {
+    expect(compareRuntimeBuild(app, { buildNumber: null, commit: null })).toBe(
+      "unknown",
+    );
+    expect(compareRuntimeBuild({}, { buildNumber: 38, commit: null })).toBe(
+      "unknown",
+    );
+  });
+});
+
+describe("App start adopts or replaces a running Runtime", () => {
+  it("starts one when nothing runs, without asking the service manager", async () => {
+    const { result, stopRuntime, queryServiceState } = reconcile({
+      running: null,
+      service: enabled(null),
+    });
+    await expect(result).resolves.toMatchObject({
+      decision: { action: "start" },
+      adopted: false,
+    });
+    expect(queryServiceState).not.toHaveBeenCalled();
+    expect(stopRuntime).not.toHaveBeenCalled();
+  });
+
+  it("adopts the same build instead of starting a second Runtime", async () => {
+    const { result, stopRuntime } = reconcile({
+      running: running({ buildNumber: 38, commit: null }),
+      service: disabled,
+    });
+    await expect(result).resolves.toEqual({
+      decision: { action: "adopt" },
+      adopted: true,
+      preserveReason: null,
+    });
+    expect(stopRuntime).not.toHaveBeenCalled();
+  });
+
+  it("adopts the service's own job when the service is enabled", async () => {
+    const { result, stopRuntime } = reconcile({
+      running: running({ buildNumber: 38, commit: null }, 4321),
+      service: enabled(4321),
+    });
+    await expect(result).resolves.toMatchObject({
+      decision: { action: "adopt" },
+      adopted: true,
+    });
+    expect(stopRuntime).not.toHaveBeenCalled();
+  });
+
+  it("ends with one Runtime when a stray holds the lease beside an enabled service", async () => {
+    const { result, stopRuntime } = reconcile({
+      running: running({ buildNumber: 38, commit: null }, 777),
+      service: enabled(null),
+    });
+    await expect(result).resolves.toMatchObject({
+      decision: { action: "stop-then-start", reason: "stray-runtime" },
+      adopted: false,
+    });
+    expect(stopRuntime).toHaveBeenCalledOnce();
+  });
+
+  it("does not treat a Runtime as a stray when the service state is unknown", async () => {
+    const { result, stopRuntime } = reconcile({
+      running: running({ buildNumber: 38, commit: null }, 777),
+      service: unknown,
+    });
+    await expect(result).resolves.toMatchObject({
+      decision: { action: "adopt" },
+    });
+    expect(stopRuntime).not.toHaveBeenCalled();
+  });
+
+  it("replaces an older Runtime that is the service's job through the service manager", async () => {
+    const { result, stopRuntime } = reconcile({
+      running: running({ buildNumber: 37, commit: null }, 4321),
+      service: enabled(4321),
+    });
+    await expect(result).resolves.toMatchObject({
+      decision: { action: "replace-via-service" },
+      adopted: false,
+      preserveReason: null,
+    });
+    // No plain kill: launchd would answer it with a respawn of the old job.
+    expect(stopRuntime).not.toHaveBeenCalled();
+  });
+
+  it("replaces a legacy service job whose receipt has no build through launchd", async () => {
+    const { result, stopRuntime } = reconcile({
+      running: running(undefined, 4321),
+      service: enabled(4321),
+    });
+    await expect(result).resolves.toMatchObject({
+      decision: { action: "replace-via-service" },
+    });
+    expect(stopRuntime).not.toHaveBeenCalled();
+  });
+
+  it("stops an older transient or CLI-started Runtime, then starts the right one", async () => {
+    const { result, stopRuntime } = reconcile({
+      running: running({ buildNumber: 36, commit: null }, 999),
+      service: disabled,
+    });
+    await expect(result).resolves.toMatchObject({
+      decision: { action: "stop-then-start", reason: "app-newer" },
+      adopted: false,
+    });
+    expect(stopRuntime).toHaveBeenCalledOnce();
+  });
+
+  it("replaces a same-build Runtime when this launch moved `current`", () => {
+    expect(
+      decideRuntimeAdoption({
+        running: running({ buildNumber: 38, commit: null }, 4321),
+        app,
+        service: enabled(4321),
+        installedChanged: true,
+      }),
+    ).toEqual({ action: "replace-via-service" });
+  });
+
+  it("adopts a newer Runtime silently and leaves quit to the service state", async () => {
+    const { result, stopRuntime } = reconcile({
+      running: running({ buildNumber: 40, commit: null }, 999),
+      service: disabled,
+    });
+    // No special quit pass: with the service disabled, quit stops it like any
+    // adopted Runtime; with it enabled, quit preserves it.
+    await expect(result).resolves.toEqual({
+      decision: { action: "adopt-newer" },
+      adopted: true,
+      preserveReason: null,
+    });
+    expect(stopRuntime).not.toHaveBeenCalled();
+  });
+
+  it("never stops or downgrades a newer Runtime at startup, even beside an enabled service", async () => {
+    const { result, stopRuntime } = reconcile({
+      running: running({ buildNumber: 40, commit: null }, 999),
+      service: enabled(4321),
+      installedChanged: true,
+    });
+    await expect(result).resolves.toMatchObject({
+      decision: { action: "adopt-newer" },
+      adopted: true,
+    });
+    expect(stopRuntime).not.toHaveBeenCalled();
+  });
+
+  it("never kills a Runtime whose build cannot be read", async () => {
+    const { result, stopRuntime } = reconcile({
+      running: running({ buildNumber: null, commit: null }, 999),
+      service: disabled,
+      installedChanged: true,
+    });
+    await expect(result).resolves.toEqual({
+      decision: { action: "adopt-unverified" },
+      adopted: true,
+      preserveReason: "runtime-build-unknown",
+    });
+    expect(stopRuntime).not.toHaveBeenCalled();
+  });
+});

memhub/apps/desktop/src/runtime-adoption.ts

@@ -0,0 +1,158 @@
+import type {
+  RuntimeReceiptBuild,
+  RuntimeServiceState,
+} from "@one-memory/runtime-control";
+
+/** The build this App carries. */
+export interface AppBuild {
+  buildNumber?: number;
+  commit?: string;
+}
+
+/** The Runtime found serving the data dir when the App starts. */
+export interface RunningRuntime {
+  pid: number;
+  /** As published in its receipt; `undefined` for a receipt without the
+   * fields, which only a Runtime older than this App writes. */
+  build: RuntimeReceiptBuild | undefined;
+}
+
+export type RuntimeVersionRelation =
+  | "same"
+  | "app-newer"
+  | "runtime-newer"
+  | "unknown";
+
+export type RuntimeAdoption =
+  /** Nothing is running: install or start this App's Runtime. */
+  | { action: "start" }
+  /** Same build: use it as it is. */
+  | { action: "adopt" }
+  /** Its build cannot be compared: use it, never stop it, tell the user. */
+  | { action: "adopt-unverified" }
+  /** Older, and it is the service manager's job: replace it through the
+   * service manager, never with a plain kill launchd would answer with a
+   * respawn of whatever it last loaded. */
+  | { action: "replace-via-service" }
+  /** Older and transient/CLI-started, or a stray beside an enabled service:
+   * stop it gracefully, then install or start the right one. */
+  | { action: "stop-then-start"; reason: "app-newer" | "stray-runtime" }
+  /** Newer than this App: use it as it is, silently. Never stopped or
+   * downgraded at startup and never joined by a second Runtime; quit treats
+   * it like any adopted Runtime. */
+  | { action: "adopt-newer" };
+
+/** Compare by build number, then by commit when both sides know theirs. */
+export function compareRuntimeBuild(
+  app: AppBuild,
+  runtime: RuntimeReceiptBuild | undefined,
+): RuntimeVersionRelation {
+  if (app.buildNumber === undefined) return "unknown";
+  // Every Runtime that publishes its build carries the fields, even as null.
+  // A receipt without them predates that contract, and so this App.
+  if (runtime === undefined) return "app-newer";
+  if (runtime.buildNumber === null) return "unknown";
+  if (runtime.buildNumber < app.buildNumber) return "app-newer";
+  if (runtime.buildNumber > app.buildNumber) return "runtime-newer";
+  const appCommit = app.commit?.trim().toLowerCase();
+  if (
+    appCommit &&
+    runtime.commit &&
+    !appCommit.startsWith(runtime.commit) &&
+    !runtime.commit.startsWith(appCommit)
+  ) {
+    // Same build, different commit: the App's bundle takes over, exactly as
+    // `installPackagedRuntime({ replaceSameBuild: true })` already does.
+    return "app-newer";
+  }
+  return "same";
+}
+
+export function decideRuntimeAdoption(input: {
+  running: RunningRuntime | null;
+  app: AppBuild;
+  service: RuntimeServiceState;
+  /** This launch just moved `current` to the App's bundled Runtime, so the
+   * process still running was started from the install it replaced. */
+  installedChanged?: boolean;
+}): RuntimeAdoption {
+  const { running, service } = input;
+  if (running === null) return { action: "start" };
+  let relation = compareRuntimeBuild(input.app, running.build);
+  if (relation === "same" && input.installedChanged) relation = "app-newer";
+  if (relation === "runtime-newer") return { action: "adopt-newer" };
+  if (relation === "unknown") return { action: "adopt-unverified" };
+  const serviceJob = service.jobPid !== null && service.jobPid === running.pid;
+  if (relation === "app-newer") {
+    return serviceJob
+      ? { action: "replace-via-service" }
+      : { action: "stop-then-start", reason: "app-newer" };
+  }
+  // One Runtime per data dir: with the service on, the one that stays is the
+  // service's own job, not a transient or CLI process holding its lease.
+  if (service.state === "enabled" && !serviceJob) {
+    return { action: "stop-then-start", reason: "stray-runtime" };
+  }
+  return { action: "adopt" };
+}
+
+export interface RuntimeReconcileDependencies {
+  app: AppBuild;
+  installedChanged?: boolean;
+  findRunning(): Promise<RunningRuntime | null>;
+  queryServiceState(): Promise<RuntimeServiceState>;
+  /** Graceful stop of the one verified Runtime: in-flight writes finish. */
+  stopRuntime(): Promise<unknown>;
+  log?(event: {
+    decision: RuntimeAdoption;
+    service: RuntimeServiceState | null;
+    running: RunningRuntime | null;
+  }): Promise<void> | void;
+}
+
+export interface RuntimeReconcileResult {
+  decision: RuntimeAdoption;
+  /** The running Runtime stays and the caller must not start another. */
+  adopted: boolean;
+  /** Quit must leave the adopted Runtime alone whatever the service state:
+   * this App could not prove it is its own build. */
+  preserveReason: string | null;
+}
+
+/** Decide what to do with a Runtime already serving the data dir at App start,
+ * and do the part that has to happen before the normal start path runs. */
+export async function reconcileRunningRuntime(
+  dependencies: RuntimeReconcileDependencies,
+): Promise<RuntimeReconcileResult> {
+  const running = await dependencies.findRunning();
+  const service =
+    running === null ? null : await dependencies.queryServiceState();
+  const decision = decideRuntimeAdoption({
+    running,
+    app: dependencies.app,
+    service: service ?? {
+      state: "unknown",
+      reason: "service-state-query-failed",
+      jobPid: null,
+    },
+    installedChanged: dependencies.installedChanged ?? false,
+  });
+  await dependencies.log?.({ decision, service, running });
+  switch (decision.action) {
+    case "start":
+    case "replace-via-service":
+      return { decision, adopted: false, preserveReason: null };
+    case "stop-then-start":
+      await dependencies.stopRuntime();
+      return { decision, adopted: false, preserveReason: null };
+    case "adopt":
+    case "adopt-newer":
+      return { decision, adopted: true, preserveReason: null };
+    case "adopt-unverified":
+      return {
+        decision,
+        adopted: true,
+        preserveReason: "runtime-build-unknown",
+      };
+  }
+}

memhub/apps/desktop/src/runtime-shutdown.test.ts

@@ -1,96 +1,162 @@
+import type {
+  RuntimeServiceState,
+  StopAllRuntimesResult,
+} from "@one-memory/runtime-control";
 import { beforeEach, describe, expect, it, vi } from "vitest";
 
 import { shutdownRuntime } from "./runtime-shutdown";
 
-const { stopRuntimeProcess } = vi.hoisted(() => ({
-  stopRuntimeProcess: vi.fn<() => Promise<"stopped" | "not-running">>(
-    async () => "stopped",
-  ),
+const { stopAllRuntimeProcesses } = vi.hoisted(() => ({
+  stopAllRuntimeProcesses: vi.fn<
+    (options: { dataDir: string }) => Promise<StopAllRuntimesResult>
+  >(async () => ({ stopped: [4321], unverified: [] })),
 }));
 
-vi.mock("@one-memory/runtime-control", () => ({ stopRuntimeProcess }));
+vi.mock("@one-memory/runtime-control", () => ({ stopAllRuntimeProcesses }));
 
-const stopMock = vi.mocked(stopRuntimeProcess);
+const stopMock = vi.mocked(stopAllRuntimeProcesses);
+
+const enabled: RuntimeServiceState = {
+  state: "enabled",
+  reason: "service-enabled",
+  jobPid: 4321,
+};
+const disabled = (
+  reason: RuntimeServiceState["reason"] = "service-enable-marker-absent",
+): RuntimeServiceState => ({ state: "disabled", reason, jobPid: null });
+const unknown: RuntimeServiceState = {
+  state: "unknown",
+  reason: "service-state-timeout",
+  jobPid: null,
+};
 
 beforeEach(() => {
-  stopMock.mockClear();
-  stopMock.mockResolvedValue("stopped");
+  stopMock.mockReset();
+  stopMock.mockResolvedValue({ stopped: [4321], unverified: [] });
 });
 
-describe("BUG-12: a full quit stops the standalone Runtime process", () => {
-  it("detaches the UI without stopping a managed Runtime service", async () => {
+describe("App quit with the background service enabled", () => {
+  it("never stops the Runtime", async () => {
     const stopSupervisor = vi.fn(async () => {});
     const events: string[] = [];
 
     const result = await shutdownRuntime({
       dataDir: "/tmp/runtime-data",
       standalone: true,
-      preserveManagedRuntime: true,
+      queryServiceState: async () => enabled,
       stopSupervisor,
       onDiagnostic: (event) => {
         events.push(event.detail);
       },
     });
 
-    expect(result).toEqual({ runtime: "unchanged" });
+    expect(result).toEqual({
+      runtime: "preserved",
+      reason: "background-service-enabled",
+    });
     expect(stopSupervisor).toHaveBeenCalledOnce();
     expect(stopMock).not.toHaveBeenCalled();
-    expect(events).toEqual(["managed-runtime-preserved"]);
+    expect(events).toEqual(["runtime-preserved:background-service-enabled"]);
   });
 
-  it("stops the Runtime process in a packaged build", async () => {
-    const stopSupervisor = vi.fn(async () => {});
+  it("does not stop a transient Runtime this App started before the service was enabled", async () => {
+    // Startup fell back to a transient child (service launchctl-disabled) and
+    // the user re-enabled the service later. Nothing startup saw is an input
+    // here: quit asks the service manager again and preserves the Runtime.
+    const queryServiceState = vi.fn(async () => enabled);
 
     const result = await shutdownRuntime({
       dataDir: "/tmp/runtime-data",
       standalone: true,
-      stopSupervisor,
+      queryServiceState,
+      stopSupervisor: async () => {},
+    });
+
+    expect(queryServiceState).toHaveBeenCalledOnce();
+    expect(result.runtime).toBe("preserved");
+    expect(stopMock).not.toHaveBeenCalled();
+  });
+});
+
+describe("App quit with the background service disabled", () => {
+  it("stops every Runtime of the data dir: the App's child and an external one", async () => {
+    stopMock.mockResolvedValue({ stopped: [1111, 2222], unverified: [] });
+
+    const result = await shutdownRuntime({
+      dataDir: "/tmp/runtime-data",
+      standalone: true,
+      queryServiceState: async () => disabled(),
+      stopSupervisor: async () => {},
     });
 
     expect(result).toEqual({ runtime: "stopped" });
     expect(stopMock).toHaveBeenCalledWith({ dataDir: "/tmp/runtime-data" });
-    expect(stopSupervisor).toHaveBeenCalledOnce();
   });
 
-  it("does not touch a separate Runtime process in an embedded build", async () => {
-    const stopSupervisor = vi.fn(async () => {});
+  it.each([
+    "service-not-installed",
+    "service-disabled-by-launchctl",
+    "service-enable-marker-absent",
+  ] as const)("treats %s as disabled", async (reason) => {
+    const result = await shutdownRuntime({
+      dataDir: "/tmp/runtime-data",
+      standalone: true,
+      queryServiceState: async () => disabled(reason),
+    });
+
+    expect(result).toEqual({ runtime: "stopped" });
+    expect(stopMock).toHaveBeenCalledOnce();
+  });
+
+  it("reports a live lease owner it could not verify instead of signalling it", async () => {
+    stopMock.mockResolvedValue({ stopped: [], unverified: [9999] });
+    const events: string[] = [];
 
     const result = await shutdownRuntime({
       dataDir: "/tmp/runtime-data",
-      standalone: false,
-      stopSupervisor,
+      standalone: true,
+      queryServiceState: async () => disabled(),
+      onDiagnostic: (event) => {
+        events.push(`${event.outcome}:${event.detail}`);
+      },
     });
 
-    expect(result).toEqual({ runtime: "unchanged" });
-    expect(stopMock).not.toHaveBeenCalled();
-    expect(stopSupervisor).toHaveBeenCalledOnce();
+    expect(result).toEqual({
+      runtime: "failed",
+      detail: "unverified-runtime-left-running",
+    });
+    expect(events).toEqual(["degraded:unverified-runtime-left-running"]);
   });
 
   it("tears the supervisor down before it stops the process", async () => {
     const order: string[] = [];
     stopMock.mockImplementation(async () => {
       order.push("process");
-      return "stopped";
+      return { stopped: [4321], unverified: [] };
     });
 
     await shutdownRuntime({
       dataDir: "/tmp/runtime-data",
       standalone: true,
+      queryServiceState: async () => {
+        order.push("query");
+        return disabled();
+      },
       stopSupervisor: async () => {
         order.push("supervisor");
       },
     });
 
-    expect(order).toEqual(["supervisor", "process"]);
+    expect(order).toEqual(["supervisor", "query", "process"]);
   });
 
-  it("reports not-running instead of throwing when nothing is attached", async () => {
-    stopMock.mockResolvedValue("not-running");
+  it("reports not-running when nothing serves the data dir", async () => {
+    stopMock.mockResolvedValue({ stopped: [], unverified: [] });
 
     const result = await shutdownRuntime({
       dataDir: "/tmp/runtime-data",
       standalone: true,
-      stopSupervisor: async () => {},
+      queryServiceState: async () => disabled(),
     });
 
     expect(result).toEqual({ runtime: "not-running" });
@@ -103,7 +169,7 @@ describe("BUG-12: a full quit stops the standalone Runtime process", () => {
     const result = await shutdownRuntime({
       dataDir: "/tmp/runtime-data",
       standalone: true,
-      stopSupervisor: async () => {},
+      queryServiceState: async () => disabled(),
       onDiagnostic: async (event) => {
         events.push(event.outcome);
       },
@@ -117,24 +183,100 @@ describe("BUG-12: a full quit stops the standalone Runtime process", () => {
     const result = await shutdownRuntime({
       dataDir: "/tmp/runtime-data",
       standalone: true,
+      queryServiceState: async () => disabled(),
       stopSupervisor: async () => {
         throw new Error("supervisor exploded");
       },
     });
 
-    // The process is what must not be left behind; a supervisor error is not
-    // an excuse to skip it.
     expect(stopMock).toHaveBeenCalledOnce();
     expect(result).toEqual({
       runtime: "failed",
       detail: "supervisor exploded",
     });
   });
+});
+
+describe("App quit when the service state cannot be determined", () => {
+  it("stops nothing on a timeout and says so", async () => {
+    const events: string[] = [];
+
+    const result = await shutdownRuntime({
+      dataDir: "/tmp/runtime-data",
+      standalone: true,
+      queryServiceState: async () => unknown,
+      onDiagnostic: (event) => {
+        events.push(`${event.outcome}:${event.detail}`);
+      },
+    });
+
+    expect(result).toEqual({
+      runtime: "preserved",
+      reason: "service-state-unknown:service-state-timeout",
+    });
+    expect(stopMock).not.toHaveBeenCalled();
+    expect(events).toEqual([
+      "degraded:runtime-preserved:service-state-unknown:service-state-timeout",
+    ]);
+  });
+
+  it("stops nothing when the query itself throws", async () => {
+    const result = await shutdownRuntime({
+      dataDir: "/tmp/runtime-data",
+      standalone: true,
+      queryServiceState: async () => {
+        throw new Error("launchctl exploded");
+      },
+    });
+
+    expect(result).toEqual({
+      runtime: "preserved",
+      reason: "service-state-unknown:service-state-query-failed",
+    });
+    expect(stopMock).not.toHaveBeenCalled();
+  });
+});
+
+describe("Runtimes quit never touches", () => {
+  it("leaves a Runtime whose build could not be read, even with the service disabled", async () => {
+    const queryServiceState = vi.fn(async () => disabled());
+
+    const result = await shutdownRuntime({
+      dataDir: "/tmp/runtime-data",
+      standalone: true,
+      queryServiceState,
+      preserveReason: "runtime-build-unknown",
+    });
+
+    expect(result).toEqual({
+      runtime: "preserved",
+      reason: "runtime-build-unknown",
+    });
+    expect(stopMock).not.toHaveBeenCalled();
+  });
+
+  it("does not touch a separate Runtime process in an embedded build", async () => {
+    const stopSupervisor = vi.fn(async () => {});
+    const queryServiceState = vi.fn(async () => disabled());
+
+    const result = await shutdownRuntime({
+      dataDir: "/tmp/runtime-data",
+      standalone: false,
+      queryServiceState,
+      stopSupervisor,
+    });
+
+    expect(result).toEqual({ runtime: "unchanged" });
+    expect(stopMock).not.toHaveBeenCalled();
+    expect(queryServiceState).not.toHaveBeenCalled();
+    expect(stopSupervisor).toHaveBeenCalledOnce();
+  });
 
   it("reports a supervisor failure in an embedded build too", async () => {
     const result = await shutdownRuntime({
       dataDir: "/tmp/runtime-data",
       standalone: false,
+      queryServiceState: async () => disabled(),
       stopSupervisor: async () => {
         throw new Error("supervisor exploded");
       },

memhub/apps/desktop/src/runtime-shutdown.ts

@@ -1,13 +1,24 @@
-import { stopRuntimeProcess } from "@one-memory/runtime-control";
+import {
+  type RuntimeServiceState,
+  type StopAllRuntimesResult,
+  stopAllRuntimeProcesses,
+} from "@one-memory/runtime-control";
 
 export interface RuntimeShutdownOptions {
   dataDir: string;
   /** Packaged builds run the Runtime as their own process; a dev build's Core
    * is this process's child and is stopped by the supervisor. */
   standalone: boolean;
-  /** A managed OS service outlives Electron; a transient App-spawned Runtime
-   * is still stopped on quit. */
-  preserveManagedRuntime?: boolean;
+  /** Asks the service manager whether the background service is on. Called
+   * at quit time, every time: what startup saw may no longer be true. */
+  queryServiceState: () => Promise<RuntimeServiceState>;
+  /** Set when startup adopted a Runtime whose build it could not read. This
+   * App never stops such a Runtime. A newer Runtime gets no such pass: it
+   * follows the service state like any adopted Runtime. */
+  preserveReason?: string | null;
+  stopRuntimes?: (options: {
+    dataDir: string;
+  }) => Promise<StopAllRuntimesResult>;
   /** Tear down this process's supervisor state (Core child, broker). */
   stopSupervisor?: () => Promise<void>;
   onDiagnostic?: (event: {
@@ -19,16 +30,22 @@ export interface RuntimeShutdownOptions {
 export type RuntimeShutdownResult =
   | { runtime: "stopped" }
   | { runtime: "not-running" }
+  | { runtime: "preserved"; reason: string }
   | { runtime: "unchanged" }
   | { runtime: "failed"; detail: string };
 
-/** Stop everything a full quit has to stop.
+/** Stop everything a full quit has to stop, and nothing else.
  *
- * Quitting used to tear down this process's own handles and nothing else. In a
- * packaged build the Runtime is a separate process, so it outlived the app: the
- * window and the tray were gone and the Runtime was still there, and its
- * receipt still named a pid, so the next launch concluded it was already
- * running and attached to a process that no longer answered.
+ * Exactly one Runtime serves a data dir. Whether quitting the App ends it is
+ * decided here, at quit time, from the service manager's answer:
+ *
+ * - background service enabled: the Runtime is the user's background memory
+ *   service. Quit never stops it, whoever started the process, including a
+ *   transient Runtime this App started earlier.
+ * - background service disabled: the Runtime lives only while the App does.
+ *   Quit stops every Runtime of this data dir: the App's own child, one
+ *   `memhub start` launched, a leftover from an earlier session.
+ * - state unknown (query failed or timed out): stop nothing, and say so.
  *
  * A failure here is reported, never thrown. By the time this runs the app is
  * already quitting, and throwing would only turn a failure someone could see
@@ -39,15 +56,6 @@ export async function shutdownRuntime(
 ): Promise<RuntimeShutdownResult> {
   const stopSupervisor = options.stopSupervisor ?? (async () => {});
   const supervisorFailure = await settle(stopSupervisor);
-  if (options.preserveManagedRuntime) {
-    await options.onDiagnostic?.({
-      outcome: supervisorFailure ? "degraded" : "succeeded",
-      detail: supervisorFailure ?? "managed-runtime-preserved",
-    });
-    return supervisorFailure
-      ? { runtime: "failed", detail: supervisorFailure }
-      : { runtime: "unchanged" };
-  }
   if (!options.standalone) {
     if (supervisorFailure) {
       await options.onDiagnostic?.({
@@ -58,16 +66,52 @@ export async function shutdownRuntime(
     }
     return { runtime: "unchanged" };
   }
-  try {
-    const result = await stopRuntimeProcess({ dataDir: options.dataDir });
+  const preserved = async (
+    reason: string,
+    outcome: "succeeded" | "degraded",
+  ): Promise<RuntimeShutdownResult> => {
     await options.onDiagnostic?.({
-      outcome: supervisorFailure ? "degraded" : "succeeded",
-      detail: supervisorFailure ?? result,
+      outcome: supervisorFailure ? "degraded" : outcome,
+      detail: supervisorFailure ?? `runtime-preserved:${reason}`,
+    });
+    return supervisorFailure
+      ? { runtime: "failed", detail: supervisorFailure }
+      : { runtime: "preserved", reason };
+  };
+  if (options.preserveReason) {
+    return preserved(options.preserveReason, "succeeded");
+  }
+  const service = await options.queryServiceState().catch(
+    (): RuntimeServiceState => ({
+      state: "unknown",
+      reason: "service-state-query-failed",
+      jobPid: null,
+    }),
+  );
+  if (service.state === "enabled") {
+    return preserved("background-service-enabled", "succeeded");
+  }
+  if (service.state !== "disabled") {
+    // Fail safe: a Runtime stopped by mistake takes the user's background
+    // memory with it; one left running by mistake is only a process.
+    return preserved(`service-state-unknown:${service.reason}`, "degraded");
+  }
+  try {
+    const result = await (options.stopRuntimes ?? stopAllRuntimeProcesses)({
+      dataDir: options.dataDir,
+    });
+    const stopped = result.stopped.length > 0 ? "stopped" : "not-running";
+    const unverified =
+      result.unverified.length > 0 ? "unverified-runtime-left-running" : null;
+    await options.onDiagnostic?.({
+      outcome: supervisorFailure || unverified ? "degraded" : "succeeded",
+      detail: supervisorFailure ?? unverified ?? `${stopped}:${service.reason}`,
     });
     if (supervisorFailure) {
       return { runtime: "failed", detail: supervisorFailure };
     }
-    return { runtime: result };
+    if (unverified) return { runtime: "failed", detail: unverified };
+    return { runtime: stopped };
   } catch (error) {
     const detail = error instanceof Error ? error.message : "unknown";
     await options.onDiagnostic?.({ outcome: "degraded", detail });

memhub/apps/desktop/src/stable-runtime.ts

@@ -143,6 +143,7 @@ const SAFE_STABLE_RUNTIME_ERROR_CODES = new Set([
   "sdk_migration_status_unavailable",
   "sdk_migration_incomplete",
   "runtime_service_not_ready",
+  "runtime_build_unknown",
 ]);
 
 /** Every migration code is a stable token Core or the orchestrator chose;
@@ -242,6 +243,8 @@ export const STABLE_RUNTIME_USER_MESSAGES: Record<string, string> = {
     "记忆数据格式升级没有完成，MemHub 暂时无法打开。请重新启动重试；如果仍然失败，请把这个提示反馈给我们，原有记忆数据不会丢失。",
   runtime_service_not_ready:
     "记忆服务仍在首次启动，请稍候后重试。你的记忆数据不会受到影响。",
+  runtime_build_unknown:
+    "无法确认正在运行的 MemHub 后台版本，App 已连接到它，但不会停止或替换它。如遇问题，请更新 App 或重启后台服务；你的记忆数据不会受到影响。",
   desktop_start_failed:
     "MemHub 启动失败。请重新启动；如果仍然打不开，请重新安装，你的记忆数据不会受到影响。",
 };

memhub/apps/desktop/tsup.config.ts

@@ -11,8 +11,20 @@ const { resolveBuildNumber, resolveBuildVersion } =
   };
 const releaseVersion = resolveBuildVersion(process.env);
 const releaseBuildNumber = resolveBuildNumber(process.env);
-const releaseCommit =
-  process.env.ONE_MEMORY_COMMIT?.trim() || readSourceCommit();
+const releaseCommit = resolveReleaseCommit(process.env.ONE_MEMORY_COMMIT);
+
+// The runtime accepts only a full 40-character commit, so an explicitly
+// supplied malformed value fails the build instead of being baked and skipped.
+function resolveReleaseCommit(explicit: string | undefined): string {
+  const trimmed = explicit?.trim();
+  if (!trimmed) return readSourceCommit();
+  if (!/^[0-9a-f]{40}$/i.test(trimmed)) {
+    throw new Error(
+      `ONE_MEMORY_COMMIT must be a full 40-character hex commit, got ${JSON.stringify(trimmed)}`,
+    );
+  }
+  return trimmed.toLowerCase();
+}
 
 function readSourceCommit(): string {
   try {

memhub/apps/web/src/ApplicationDetail.profiles.test.tsx

@@ -0,0 +1,185 @@
+// @vitest-environment jsdom
+
+/**
+ * #230: DeepSeek Harness has no single host, so the app page used to grey the
+ * switch out with `unsupported_host` and offered no other way to grant recall.
+ * The one switch now covers every detected profile.
+ */
+
+import type { SourceResponse } from "@one-memory/contracts";
+import {
+  cleanup,
+  fireEvent,
+  render,
+  screen,
+  waitFor,
+  within,
+} from "@testing-library/react";
+import { afterEach, beforeEach, expect, it, vi } from "vitest";
+import { ApplicationDetail } from "./ApplicationDetail";
+import { readConnectionPreferences } from "./connection-preferences";
+import { resetConnectionReconcile } from "./connection-reconcile";
+import { harnessBridge } from "./harness-profiles.test-fixture";
+
+const source = {
+  source_id: "deepseek-harness",
+  display_name: "DeepSeek Harness",
+  authorized: true,
+  sync_enabled: true,
+  capabilities: {
+    historical_import: "implemented",
+    incremental_import: "implemented",
+    live_sync: "implemented",
+    recall: "implemented",
+    installer: "implemented",
+    verification: "real_replayed",
+  },
+} as SourceResponse;
+
+function renderDetail() {
+  return render(
+    <ApplicationDetail
+      source={source}
+      sources={[source]}
+      stale={false}
+      setSync={vi.fn()}
+      refresh={vi.fn().mockResolvedValue({ sources: [source] })}
+      onBack={vi.fn()}
+    />,
+  );
+}
+
+function profileItems() {
+  return within(
+    screen.getByRole("list", { name: "DeepSeek Harness 的 Profile" }),
+  )
+    .getAllByRole("listitem")
+    .map((item) => item.textContent);
+}
+
+beforeEach(() => {
+  window.localStorage.clear();
+  resetConnectionReconcile();
+});
+afterEach(() => {
+  cleanup();
+  window.oneMemory = undefined;
+  window.localStorage.clear();
+  resetConnectionReconcile();
+});
+
+it("lists every detected profile with its own state", async () => {
+  harnessBridge({ desktop: "approved", web: "not-installed" });
+  renderDetail();
+  await waitFor(() =>
+    expect(profileItems()).toEqual(["desktop：已接入", "web：未接入"]),
+  );
+  const insertion = screen.getByRole("switch", { name: "一键插入应用" });
+  expect(insertion.hasAttribute("disabled")).toBe(false);
+  expect(screen.queryByText(/当前安装不支持一键插入/)).toBeNull();
+});
+
+it("turns every profile on with the one switch and remembers the choice", async () => {
+  const { api, state } = harnessBridge({
+    desktop: "not-installed",
+    web: "not-installed",
+  });
+  renderDetail();
+  const insertion = await screen.findByRole("switch", { name: "一键插入应用" });
+  await waitFor(() => expect(profileItems()).toHaveLength(2));
+  expect(insertion.getAttribute("aria-checked")).toBe("false");
+  fireEvent.click(insertion);
+  await waitFor(() =>
+    expect(profileItems()).toEqual(["desktop：已接入", "web：已接入"]),
+  );
+  expect(api.installRecall.mock.calls.map(([hostId]) => hostId)).toEqual([
+    "deepseek-harness:desktop",
+    "deepseek-harness:web",
+  ]);
+  expect([...state.values()]).toEqual(["approved", "approved"]);
+  expect(insertion.getAttribute("aria-checked")).toBe("true");
+  // Not "未接通": the self-checks the grants recorded were read back.
+  await waitFor(() =>
+    expect(
+      screen.getByRole("button", { name: /已接通|未接通|检测中/ }).textContent,
+    ).toBe("已接通"),
+  );
+  // Remembered, so a profile found on a later launch is connected too.
+  expect(readConnectionPreferences().hostSourceIds).toEqual([
+    "deepseek-harness",
+  ]);
+});
+
+it("names the profile that failed and keeps the others on", async () => {
+  const { state } = harnessBridge(
+    { desktop: "not-installed", web: "not-installed" },
+    { failInstall: ["web"] },
+  );
+  renderDetail();
+  const insertion = await screen.findByRole("switch", { name: "一键插入应用" });
+  await waitFor(() => expect(profileItems()).toHaveLength(2));
+  fireEvent.click(insertion);
+  const alert = await screen.findByRole("alert");
+  expect(alert.textContent).toContain("以下 Profile 未能接入：web");
+  expect(alert.textContent).toContain("应用控制通道暂不可用");
+  await waitFor(() =>
+    expect(profileItems()).toEqual(["desktop：已接入", "web：未接入"]),
+  );
+  expect(state.get("deepseek-harness:desktop")).toBe("approved");
+  expect(insertion.getAttribute("aria-checked")).toBe("true");
+});
+
+it("turns every linked profile off with the one switch", async () => {
+  const { api, state } = harnessBridge({
+    desktop: "approved",
+    web: "approved",
+  });
+  renderDetail();
+  const insertion = await screen.findByRole("switch", { name: "一键插入应用" });
+  await waitFor(() =>
+    expect(insertion.getAttribute("aria-checked")).toBe("true"),
+  );
+  fireEvent.click(insertion);
+  await waitFor(() =>
+    expect(profileItems()).toEqual(["desktop：未接入", "web：未接入"]),
+  );
+  expect(api.uninstallRecall).toHaveBeenCalledTimes(2);
+  expect([...state.values()]).toEqual(["not-installed", "not-installed"]);
+  expect(insertion.getAttribute("aria-checked")).toBe("false");
+  expect(readConnectionPreferences().hostSourceIds).toEqual([]);
+});
+
+it("names the profile whose connection could not be removed", async () => {
+  harnessBridge(
+    { desktop: "approved", web: "approved" },
+    {
+      failUninstall: ["desktop"],
+    },
+  );
+  renderDetail();
+  const insertion = await screen.findByRole("switch", { name: "一键插入应用" });
+  await waitFor(() =>
+    expect(insertion.getAttribute("aria-checked")).toBe("true"),
+  );
+  fireEvent.click(insertion);
+  // Removal failed but revocation went through: the grant is gone, the file
+  // is left for the person to check.
+  expect((await screen.findByRole("alert")).textContent).toContain(
+    "已撤销以下 Profile 的记忆权限，但连接文件没有全部移除，请核对：desktop",
+  );
+});
+
+it("says how to get a profile when none is detected", async () => {
+  harnessBridge({});
+  renderDetail();
+  expect(
+    await screen.findByText(
+      "还没有检测到 DeepSeek Harness 的 Profile。创建 Profile 后再回到此页。",
+    ),
+  ).toBeTruthy();
+  expect(
+    screen
+      .getByRole("switch", { name: "一键插入应用" })
+      .hasAttribute("disabled"),
+  ).toBe(true);
+});

memhub/apps/web/src/ApplicationDetail.tsx

@@ -2,15 +2,21 @@ import type { SourceResponse } from "@one-memory/contracts";
 import type { MessageKey } from "@one-memory/i18n";
 import { useCallback, useEffect, useRef, useState } from "react";
 import { AppMark } from "./app-mark";
-import { connectionHostId, preferenceHasSource } from "./connection-hosts";
+import {
+  connectionHostId,
+  isProfileSource,
+  preferenceHasSource,
+  profileName,
+} from "./connection-hosts";
 import {
   readConnectionPreferences,
   writeConnectionPreference,
 } from "./connection-preferences";
 import { noteUserHostChoice } from "./connection-reconcile";
-import type { RecallLinkCheck } from "./global";
+import type { RecallHostStatus, RecallLinkCheck } from "./global";
 import {
   disconnectHost,
+  disconnectProfiles,
   enableHostConnection,
   hostCapabilities,
   hostConnectionApproved,
@@ -19,8 +25,11 @@ import {
   hostWriteReason,
   matchHost,
   probeHost,
+  profileHosts,
+  profileWriteFailures,
   refreshRecallHosts,
   setHostMemoryPermission,
+  sourceConnectionApproved,
   UNSUPPORTED_NOTE,
   useRecallHosts,
 } from "./host-state";
@@ -63,6 +72,24 @@ function connectionLabel(input: {
   return "未开启关联";
 }
 
+/** The recorded self-check across the profiles that may use memory: wired
+ * only when every one of them is, otherwise the first one that is not. */
+function profilesProbeState(profiles: RecallHostStatus[]) {
+  const linked = profiles.filter(hostConnectionApproved);
+  if (!linked.length) return null;
+  for (const host of linked) {
+    const state = host.selfCheck?.state ?? null;
+    if (state !== "wired") return state;
+  }
+  return "wired";
+}
+
+function profileList(hosts: readonly ProfileHost[]) {
+  return hosts.map((host) => profileName(host.hostId)).join(", ");
+}
+
+type ProfileHost = Pick<RecallHostStatus, "hostId">;
+
 function SourceIcon({ source }: { source: SourceResponse }) {
   return (
     <AppMark
@@ -215,7 +242,10 @@ export function ApplicationDetail({
       if (!mounted.current || version !== epoch.current) return;
       setRead({ sourceId: id, state: "ready" });
       setCheckedAt(new Date().toISOString());
-      if (matched?.installed) void probeLink(matched.hostId);
+      // A per-profile source has no single host to probe; its status comes
+      // from each profile's recorded self-check instead.
+      if (matched?.installed && !isProfileSource(id))
+        void probeLink(matched.hostId);
       else setLink(null);
     } catch {
       if (mounted.current && version === epoch.current)
@@ -292,10 +322,14 @@ export function ApplicationDetail({
   }
   const current = read.sourceId === source.source_id ? read : null;
   const host = matchHost(hosts, source.source_id);
+  const profileSource = isProfileSource(source.source_id);
+  const profiles = profileHosts(hosts, source.source_id);
   const loading = !current || current.state === "loading";
   const readFailed = current?.state === "error";
-  const approved = hostConnectionApproved(host);
-  const unsupported = hostConnectionUnsupported(host);
+  const approved = profileSource
+    ? sourceConnectionApproved(hosts, source.source_id)
+    : hostConnectionApproved(host);
+  const unsupported = !profileSource && hostConnectionUnsupported(host);
   const insertionChecked = insertionIntent ?? approved;
   const memoryChecked = memoryIntent ?? host?.permission?.state === "approved";
   const probing =
@@ -305,9 +339,10 @@ export function ApplicationDetail({
     loading ||
     readFailed ||
     (stale && current?.state !== "ready");
-  const probeState =
-    link?.probe.state ??
-    (linkPending || linkFailed ? null : (host?.selfCheck?.state ?? null));
+  const probeState = profileSource
+    ? profilesProbeState(profiles)
+    : (link?.probe.state ??
+      (linkPending || linkFailed ? null : (host?.selfCheck?.state ?? null)));
   const stateText = connectionLabel({
     approved,
     insertionOn: insertionChecked,
@@ -326,10 +361,43 @@ export function ApplicationDetail({
             ? { reason: failureNote(installError.failure) }
             : {}),
         });
+  async function applyProfiles(enabled: boolean) {
+    if (enabled) {
+      try {
+        await enableHostConnection(source.source_id);
+      } finally {
+        // Each grant records its self-check on the desktop, and the status row
+        // reads those; nothing else re-reads them while this page is open.
+        await refreshRecallHosts().catch(() => {});
+      }
+      return;
+    }
+    const results = await disconnectProfiles(source.source_id);
+    const failed = results.filter((item) => item.outcome.state === "failed");
+    const retained = results.filter(
+      (item) =>
+        item.outcome.state === "revoked" || item.outcome.state === "review",
+    );
+    if (retained.length)
+      setInstallError({
+        key: "appProfilesRevokedRetained",
+        params: { profiles: profileList(retained) },
+      });
+    const first = failed[0]?.outcome;
+    if (first?.state === "failed")
+      throw Object.assign(Error("disconnect_failed"), {
+        profiles: failed.map((item) => profileName(item.hostId)),
+        failure: {
+          reason: first.reason,
+          rereadFailed: first.rereadFailed,
+        } satisfies HostFailure,
+      });
+  }
   async function applyInsertion(enabled: boolean) {
     const bridge = window.oneMemory;
     if (!bridge) return;
     setInstallError("");
+    if (profileSource) return applyProfiles(enabled);
     if (enabled) {
       await enableHostConnection(source.source_id);
       void probeLink(hostId);
@@ -385,6 +453,30 @@ export function ApplicationDetail({
           }
           // A failed turn-on keeps the stored choice on; a failed turn-off
           // shows the grant that is really still there after the re-read.
+          // Per-profile sources name the profiles that failed; the others
+          // keep what they got.
+          const failedProfiles =
+            profileWriteFailures(error) ??
+            (error as { profiles?: string[] }).profiles ??
+            null;
+          if (failedProfiles) {
+            setInstallError({
+              key: wanted
+                ? "appProfilesConnectFailed"
+                : "appProfilesDisconnectFailed",
+              params: { profiles: failedProfiles.join(", ") },
+              failure: wanted
+                ? {
+                    reason: hostWriteReason(error),
+                    rereadFailed: hostRereadFailed(error),
+                  }
+                : ((error as { failure?: HostFailure }).failure ?? {
+                    reason: null,
+                    rereadFailed: false,
+                  }),
+            });
+            continue;
+          }
           setInstallError(
             wanted
               ? {
@@ -561,6 +653,31 @@ export function ApplicationDetail({
           <div>
             <h2>{text("一键插入应用")}</h2>
             <p>{text("安装记忆连接，并默认允许此应用使用已授权记忆。")}</p>
+            {profileSource &&
+              (profiles.length ? (
+                <>
+                  <ul
+                    className="r6-app-profiles"
+                    aria-label={t("appProfilesLabel", {
+                      name: source.display_name,
+                    })}
+                  >
+                    {profiles.map((profile) => (
+                      <li key={profile.hostId}>
+                        {t(
+                          hostConnectionApproved(profile)
+                            ? "appProfileOn"
+                            : "appProfileOff",
+                          { profile: profileName(profile.hostId) },
+                        )}
+                      </li>
+                    ))}
+                  </ul>
+                  <p>{t("appProfilesHint")}</p>
+                </>
+              ) : (
+                <p>{t("appProfilesNone", { name: source.display_name })}</p>
+              ))}
             {unsupported && (
               <p>{`${source.display_name} ${text(UNSUPPORTED_NOTE)}`}</p>
             )}
@@ -578,6 +695,7 @@ export function ApplicationDetail({
               stale ||
               appLocationNote !== null ||
               unsupported ||
+              (profileSource && !profiles.length) ||
               source.capabilities?.installer !== "implemented" ||
               source.capabilities?.recall !== "implemented" ||
               !hostCapabilities().install

memhub/apps/web/src/ApplicationsHome.tsx

@@ -31,6 +31,8 @@ import {
   hostBridgeAvailable,
   hostConnectionApproved,
   hostConnectionUnknown,
+  sourceConnectionApproved,
+  sourceConnectionIncomplete,
   useRecallHosts,
 } from "./host-state";
 import { subscribePoll } from "./poll-scheduler";
@@ -737,12 +739,7 @@ export function ApplicationsHome({
     failure.kind === "host"
       ? preferences.hostSourceIds.some((id) =>
           sameConnectionHost(id, failure.sourceId),
-        ) &&
-        !hosts.some(
-          (host) =>
-            hostConnectionApproved(host) &&
-            hostMatchesSource(failure.sourceId, host.hostId),
-        )
+        ) && sourceConnectionIncomplete(hosts, failure.sourceId)
       : preferences.syncSourceIds.includes(failure.sourceId) &&
         !imports.sources.some(
           (source) =>
@@ -754,14 +751,22 @@ export function ApplicationsHome({
   const autoFailureText = autoFailures
     .map((failure) =>
       failure.kind === "host"
-        ? t("apps.autoHostFailed", {
-            name: nameOf(failure.sourceId),
-            reason: failure.reason
-              ? t("apps.failureReason", {
-                  reason: localizeFailureReason(failure.reason),
-                })
-              : "",
-          })
+        ? t(
+            failure.profiles
+              ? "apps.autoHostProfilesFailed"
+              : "apps.autoHostFailed",
+            {
+              name: nameOf(failure.sourceId),
+              ...(failure.profiles
+                ? { profiles: failure.profiles.join(", ") }
+                : {}),
+              reason: failure.reason
+                ? t("apps.failureReason", {
+                    reason: localizeFailureReason(failure.reason),
+                  })
+                : "",
+            },
+          )
         : t("apps.autoSyncFailed", {
             name: nameOf(failure.sourceId),
             reason: localizeFailureReason(failure.reason),
@@ -1181,8 +1186,9 @@ export function ApplicationsHome({
                 t,
                 callState === "unavailable",
               ) || sourceSyncActivity(source.source_id, syncHealth, locale, t);
-            const host = hosts.find((item) =>
-              sourceMatchesHost(source.source_id, item.hostId),
+            const recallAllowed = sourceConnectionApproved(
+              hosts,
+              source.source_id,
             );
             return (
               <div className="r6-home-app-row" key={source.source_id}>
@@ -1193,8 +1199,7 @@ export function ApplicationsHome({
                     <p>
                       {source.sync_enabled
                         ? t("apps.syncEnabled")
-                        : host?.installed &&
-                            host.permission?.state === "approved"
+                        : recallAllowed
                           ? t("apps.recallAllowed")
                           : source.authorized
                             ? t("apps.historyAllowed")

memhub/apps/web/src/api.memory-library.test.ts

@@ -13,9 +13,18 @@ vi.mock("axios", () => ({
       delete: del,
       interceptors: { request: { use: vi.fn() } },
     }),
+    isAxiosError: (value: unknown) =>
+      typeof value === "object" && value !== null && "isAxiosError" in value,
   },
 }));
 
+function httpError(status: number, detail: string) {
+  return Object.assign(new Error(`http_${status}`), {
+    isAxiosError: true,
+    response: { status, data: { detail } },
+  });
+}
+
 import {
   deleteSdkMemory,
   getHomeSummary,
@@ -100,6 +109,18 @@ describe("paged memory library client", () => {
     expect(del).toHaveBeenLastCalledWith("/api/v2/memories/c1", undefined);
   });
 
+  it("treats a delete answered 404 memory_not_found as already gone", async () => {
+    del.mockRejectedValueOnce(httpError(404, "memory_not_found"));
+    await expect(deleteSdkMemory("gone")).resolves.toBeUndefined();
+
+    const other = httpError(404, "source_not_found");
+    del.mockRejectedValueOnce(other);
+    await expect(deleteSdkMemory("x")).rejects.toBe(other);
+    const failed = httpError(503, "hy_memory_delete_failed");
+    del.mockRejectedValueOnce(failed);
+    await expect(deleteSdkMemory("x")).rejects.toBe(failed);
+  });
+
   it("forwards cancellation for inactive or superseded views", async () => {
     const controller = new AbortController();
     get.mockResolvedValueOnce({

memhub/apps/web/src/api.ts

@@ -763,9 +763,25 @@ export async function deleteSdkMemory(
     ...(traceId ? { headers: { "X-One-Memory-Trace-Id": traceId } } : {}),
     ...(params ? { params } : {}),
   };
-  await client.delete(
-    `/api/v2/memories/${encodeURIComponent(memoryId)}`,
-    Object.keys(config).length ? config : undefined,
+  try {
+    await client.delete(
+      `/api/v2/memories/${encodeURIComponent(memoryId)}`,
+      Object.keys(config).length ? config : undefined,
+    );
+  } catch (reason) {
+    // 404 `memory_not_found`: already gone (a second click, or another
+    // window deleted it first). The memory is not there, which is what the
+    // person asked for, so it is not an error.
+    if (isMemoryNotFound(reason)) return;
+    throw reason;
+  }
+}
+
+function isMemoryNotFound(reason: unknown): boolean {
+  return (
+    axios.isAxiosError(reason) &&
+    reason.response?.status === 404 &&
+    apiErrorCode(reason) === "memory_not_found"
   );
 }
 

memhub/apps/web/src/application-detail.css

@@ -118,6 +118,14 @@
   margin: 0;
   overflow-wrap: anywhere;
 }
+.r6-app-profiles {
+  font-size: 13px;
+  color: #637786;
+  line-height: 1.8;
+  margin: 4px 0;
+  padding-left: 18px;
+  overflow-wrap: anywhere;
+}
 .r6-app-detail-actions {
   display: flex;
   gap: 12px;

memhub/apps/web/src/connection-hosts.ts

@@ -1,5 +1,6 @@
-/** Mirrors desktop `SOURCE_HOST`. OpenClaw and DeepSeek Harness profiles
- * are not accepted by one-click insertion. */
+/** Mirrors desktop `SOURCE_HOST`. OpenClaw is not accepted by one-click
+ * insertion; DeepSeek Harness has no single host and goes through
+ * `PROFILE_SOURCES` instead. */
 export const SOURCE_HOST: Readonly<Record<string, string>> = {
   cursor: "cursor",
   "claude-code": "claude-code",
@@ -14,6 +15,23 @@ export const SOURCE_HOST: Readonly<Record<string, string>> = {
 
 export const ONE_CLICK_SOURCES = new Set(Object.keys(SOURCE_HOST));
 
+/** Sources configured per profile. Each profile is its own host
+ * (`deepseek-harness:<profile>`, with its own patch, credential and grant), so
+ * the app's one switch covers every profile the desktop detected. */
+export const PROFILE_SOURCES: ReadonlySet<string> = new Set([
+  "deepseek-harness",
+]);
+
+export function isProfileSource(sourceId: string) {
+  return PROFILE_SOURCES.has(sourceId);
+}
+
+/** `deepseek-harness:web` -> `web`. */
+export function profileName(hostId: string) {
+  const colon = hostId.indexOf(":");
+  return colon < 0 ? hostId : hostId.slice(colon + 1);
+}
+
 export function connectionHostId(sourceId: string): string | null {
   return SOURCE_HOST[sourceId] ?? null;
 }

memhub/apps/web/src/connection-reconcile.ts

@@ -1,6 +1,10 @@
 import type { SourceResponse } from "@one-memory/contracts";
 import { useQuery } from "@tanstack/react-query";
-import { connectionHostId, sameConnectionHost } from "./connection-hosts";
+import {
+  connectionHostId,
+  isProfileSource,
+  sameConnectionHost,
+} from "./connection-hosts";
 import {
   readConnectionPreferences,
   writeConnectionPreference,
@@ -8,11 +12,13 @@ import {
 import {
   cachedRecallHosts,
   enableHostConnection,
-  hostConnectionApproved,
   hostConnectionUnsupported,
   hostWriteInFlight,
   hostWriteReason,
   matchHost,
+  profileHosts,
+  profileWriteFailures,
+  sourceConnectionIncomplete,
 } from "./host-state";
 import { onClientReset, queryClient } from "./query-client";
 import { latestSource, sourceWriteInFlight } from "./source-state";
@@ -37,6 +43,8 @@ export type AutoConnectFailure = {
   kind: "sync" | "host";
   sourceId: string;
   reason: string | null;
+  /** Which profiles of a per-profile source it was; the others are kept. */
+  profiles?: string[];
 };
 export type AutoConnectState = {
   running: string[];
@@ -53,8 +61,10 @@ queryClient.setQueryDefaults(AUTO_KEY, {
 });
 
 let flight: Promise<AutoConnectFailure[]> | null = null;
+const seenProfiles = new Map<string, Set<string>>();
 onClientReset(() => {
   flight = null;
+  seenProfiles.clear();
 });
 
 function autoState() {
@@ -148,8 +158,26 @@ export async function reconcileConnectionPreferences(
 function hostNeedsApply(sourceId: string) {
   const hosts = cachedRecallHosts();
   if (hosts === undefined) return false;
-  const host = matchHost(hosts, sourceId);
-  return !hostConnectionApproved(host) && !hostConnectionUnsupported(host);
+  return sourceConnectionIncomplete(hosts, sourceId);
+}
+
+/** `attempted` holds one apply per source, which is right until a per-profile
+ * source grows a profile: that one was never tried, so the remembered switch
+ * gets one more apply. A profile that fails is not retried on every poll. */
+function rearmNewProfiles(sourceIds: string[]) {
+  const hosts = cachedRecallHosts();
+  if (hosts === undefined) return;
+  for (const sourceId of sourceIds) {
+    if (!isProfileSource(sourceId)) continue;
+    const current = profileHosts(hosts, sourceId).map((host) => host.hostId);
+    const seen = seenProfiles.get(sourceId);
+    seenProfiles.set(sourceId, new Set([...(seen ?? []), ...current]));
+    if (!seen || current.every((hostId) => seen.has(hostId))) continue;
+    updateAuto((state) => ({
+      ...state,
+      attempted: state.attempted.filter((key) => key !== hostKey(sourceId)),
+    }));
+  }
 }
 
 /** Whether a remembered host is still waiting for (or in) its one apply. */
@@ -191,6 +219,7 @@ export function autoReconcile(
     if (hostConnectionUnsupported(matchHost(hosts, id)))
       writeConnectionPreference("host", id, false);
   const preferences = readConnectionPreferences();
+  rearmNewProfiles(preferences.hostSourceIds);
   const { attempted } = autoState();
   const only = options.only;
   const wantedHosts = only
@@ -256,6 +285,7 @@ export function retryAutoReconcile(options: ReconcileOptions) {
 
 export function resetConnectionReconcile() {
   flight = null;
+  seenProfiles.clear();
   queryClient.removeQueries({ queryKey: AUTO_KEY });
 }
 
@@ -301,12 +331,15 @@ async function runReconcile(
       // Per-app: other hosts keep going. Unsupported never succeeds on retry.
       if (error instanceof Error && error.message === "host_unsupported")
         writeConnectionPreference("host", sourceId, false);
-      else
+      else {
+        const profiles = profileWriteFailures(error);
         failures.push({
           kind: "host",
           sourceId,
           reason: hostWriteReason(error),
+          ...(profiles ? { profiles } : {}),
         });
+      }
     }
   }
   return failures;

memhub/apps/web/src/harness-profiles.test-fixture.ts

@@ -0,0 +1,120 @@
+/** A fake desktop bridge holding DeepSeek Harness profile hosts, for tests. */
+
+import { vi } from "vitest";
+import type { RecallHostStatus, RecallPermissionStatus } from "./global";
+
+type Bridge = NonNullable<typeof window.oneMemory>;
+type Grant =
+  | "not-installed"
+  | "install-only"
+  | "approved"
+  | "revoked"
+  | "unsupported";
+
+function permission(hostId: string, state: Grant): RecallPermissionStatus {
+  return {
+    hostId,
+    state,
+    reason: null,
+    receipt:
+      state === "not-installed" || state === "unsupported"
+        ? null
+        : {
+            hostId,
+            installationId: `install-${hostId}`,
+            revision: 1,
+            status: state,
+            allowedTools: state === "approved" ? ["om_recall"] : [],
+            allowedScopes: state === "approved" ? ["all-apps"] : [],
+          },
+  };
+}
+
+/** A desktop that knows a set of Harness profiles and keeps their state. */
+export function harnessBridge(
+  initial: Record<string, Grant>,
+  options: { failInstall?: string[]; failUninstall?: string[] } = {},
+) {
+  const state = new Map(
+    Object.entries(initial).map(([profile, grant]) => [
+      `deepseek-harness:${profile}`,
+      grant,
+    ]),
+  );
+  const hosts = (): RecallHostStatus[] =>
+    [...state].map(([hostId, grant]) => ({
+      hostId,
+      label: `DeepSeek Harness · ${hostId.split(":")[1]}`,
+      present: true,
+      installed: grant === "install-only" || grant === "approved",
+      permission: permission(hostId, grant),
+      // Recorded by the desktop when the grant lands, as on a real install.
+      selfCheck:
+        grant === "approved"
+          ? { state: "wired", detail: "", probed_at: "2026-11-02" }
+          : null,
+      skillDrift: null,
+    }));
+  const failing = (hostId: string, list: string[] = []) =>
+    list.some((profile) => hostId === `deepseek-harness:${profile}`);
+  const api = {
+    getRecallHosts: vi.fn(async () => hosts()),
+    getRecallPermission: vi.fn(async (hostId: string) =>
+      permission(hostId, state.get(hostId) ?? "not-installed"),
+    ),
+    previewRecallInstall: vi.fn(async (hostId: string) => ({
+      hostId,
+      hostLabel: hostId,
+      files: [],
+      fingerprint: `fp-${hostId}`,
+    })),
+    installRecall: vi.fn(async (hostId: string, _approved?: string) => {
+      if (failing(hostId, options.failInstall))
+        throw Error(
+          "Error invoking remote method 'one-memory:install-recall': Error: host_control_unavailable",
+        );
+      state.set(hostId, "install-only");
+      return {
+        hostId,
+        installed: true,
+        permission: permission(hostId, "install-only"),
+      };
+    }),
+    setRecallPermission: vi.fn(async (hostId: string, _input: unknown) => {
+      state.set(hostId, "approved");
+      return permission(hostId, "approved");
+    }),
+    revokeRecallPermission: vi.fn(async (hostId: string, _input: unknown) => {
+      state.set(hostId, "revoked");
+      return permission(hostId, "revoked");
+    }),
+    previewRecallUninstall: vi.fn(async (hostId: string) => ({
+      hostId,
+      hostLabel: hostId,
+      files: [],
+      review: [],
+      fingerprint: `fp-${hostId}`,
+    })),
+    uninstallRecall: vi.fn(async (hostId: string, _approved?: string) => {
+      if (failing(hostId, options.failUninstall))
+        throw Error(
+          "Error invoking remote method 'one-memory:uninstall-recall': Error: host_control_unavailable",
+        );
+      state.set(hostId, "not-installed");
+      return {
+        hostId,
+        installed: false,
+        permission: permission(hostId, "not-installed"),
+      };
+    }),
+    repairRecallCommands: vi.fn(async () => []),
+  };
+  window.oneMemory = api as unknown as Bridge;
+  return {
+    api,
+    state,
+    addProfile(profile: string) {
+      state.set(`deepseek-harness:${profile}`, "not-installed");
+    },
+  };
+}

memhub/apps/web/src/host-state.profiles.test.ts

@@ -0,0 +1,210 @@
+// @vitest-environment jsdom
+
+/**
+ * DeepSeek Harness is configured per profile: every `deepseek-harness:<profile>`
+ * is its own host with its own patch, credential and grant. The app page has
+ * one switch for all of them (#230). These pin what that switch does: on
+ * installs and grants every detected profile, off removes and revokes every
+ * linked one, a failing profile is named without undoing the others, and a
+ * profile that appears later is picked up by the remembered switch.
+ */
+
+import { afterEach, describe, expect, it } from "vitest";
+import { saveConnectionPreferences } from "./connection-preferences";
+import {
+  autoReconcile,
+  resetConnectionReconcile,
+} from "./connection-reconcile";
+import { harnessBridge } from "./harness-profiles.test-fixture";
+import {
+  disconnectProfiles,
+  enableHostConnection,
+  hostWriteReason,
+  ProfileWriteError,
+  profileHosts,
+  refreshRecallHosts,
+  sourceConnectionApproved,
+  sourceConnectionIncomplete,
+} from "./host-state";
+
+afterEach(() => {
+  window.oneMemory = undefined;
+  window.localStorage.clear();
+  resetConnectionReconcile();
+});
+
+describe("DeepSeek Harness profile hosts", () => {
+  it("lists only the profiles of the per-profile source", async () => {
+    harnessBridge({ desktop: "not-installed", web: "approved" });
+    const hosts = await refreshRecallHosts();
+    expect(
+      profileHosts(hosts, "deepseek-harness").map((host) => host.hostId),
+    ).toEqual(["deepseek-harness:desktop", "deepseek-harness:web"]);
+    expect(profileHosts(hosts, "cursor")).toEqual([]);
+    // One approved profile reads as on; the other is still to do.
+    expect(sourceConnectionApproved(hosts, "deepseek-harness")).toBe(true);
+    expect(sourceConnectionIncomplete(hosts, "deepseek-harness")).toBe(true);
+  });
+});
+
+describe("turning the DeepSeek Harness switch on", () => {
+  it("installs and grants every profile that is not approved yet", async () => {
+    const { api, state } = harnessBridge({
+      desktop: "not-installed",
+      headless: "revoked",
+      web: "approved",
+    });
+    await refreshRecallHosts();
+    await enableHostConnection("deepseek-harness");
+    expect(api.installRecall.mock.calls.map(([hostId]) => hostId)).toEqual([
+      "deepseek-harness:desktop",
+      "deepseek-harness:headless",
+    ]);
+    expect(api.setRecallPermission).toHaveBeenCalledWith(
+      "deepseek-harness:desktop",
+      expect.objectContaining({
+        allowedTools: ["om_recall", "om_conversations", "om_diagnostic_trace"],
+        allowedScopes: ["all-apps", "source:deepseek-harness"],
+        userConfirmed: true,
+      }),
+    );
+    expect([...state.values()]).toEqual(["approved", "approved", "approved"]);
+  });
+
+  it("keeps the profiles that worked and names the one that failed", async () => {
+    const { api, state } = harnessBridge(
+      { desktop: "not-installed", web: "not-installed" },
+      { failInstall: ["web"] },
+    );
+    await refreshRecallHosts();
+    const error = await enableHostConnection("deepseek-harness").catch(
+      (reason: unknown) => reason,
+    );
+    expect(error).toBeInstanceOf(ProfileWriteError);
+    expect((error as ProfileWriteError).profiles).toEqual(["web"]);
+    expect((error as Error).message).toContain("host_control_unavailable");
+    expect(state.get("deepseek-harness:desktop")).toBe("approved");
+    expect(state.get("deepseek-harness:web")).toBe("not-installed");
+    expect(api.setRecallPermission).toHaveBeenCalledTimes(1);
+    // The failure re-read lands the real state of every profile.
+    const hosts = await refreshRecallHosts();
+    expect(sourceConnectionApproved(hosts, "deepseek-harness")).toBe(true);
+  });
+});
+
+describe("turning the DeepSeek Harness switch off", () => {
+  it("removes and revokes every linked profile and leaves unlinked ones alone", async () => {
+    const { api, state } = harnessBridge({
+      desktop: "approved",
+      headless: "not-installed",
+      web: "approved",
+    });
+    await refreshRecallHosts();
+    const results = await disconnectProfiles("deepseek-harness");
+    expect(results.map((item) => [item.hostId, item.outcome.state])).toEqual([
+      ["deepseek-harness:desktop", "removed"],
+      ["deepseek-harness:web", "removed"],
+    ]);
+    expect(api.uninstallRecall).toHaveBeenCalledTimes(2);
+    expect(state.get("deepseek-harness:desktop")).toBe("not-installed");
+    expect(state.get("deepseek-harness:web")).toBe("not-installed");
+  });
+
+  it("revokes a profile whose files cannot be removed and still reaches the rest", async () => {
+    const { api, state } = harnessBridge(
+      { desktop: "approved", web: "approved" },
+      { failUninstall: ["desktop"] },
+    );
+    await refreshRecallHosts();
+    const results = await disconnectProfiles("deepseek-harness");
+    expect(results.map((item) => item.outcome.state)).toEqual([
+      "revoked",
+      "removed",
+    ]);
+    expect(api.revokeRecallPermission).toHaveBeenCalledWith(
+      "deepseek-harness:desktop",
+      expect.objectContaining({ userConfirmed: true }),
+    );
+    expect(state.get("deepseek-harness:desktop")).toBe("revoked");
+    expect(state.get("deepseek-harness:web")).toBe("not-installed");
+  });
+});
+
+describe("a profile created after the switch was turned on", () => {
+  it("is installed and granted by the remembered switch while the app is running", async () => {
+    saveConnectionPreferences({
+      syncSourceIds: [],
+      hostSourceIds: ["deepseek-harness"],
+    });
+    const harness = harnessBridge({ desktop: "not-installed" });
+    await refreshRecallHosts();
+    expect(await autoReconcile({ sources: [] })).toEqual([]);
+    expect(harness.api.installRecall).toHaveBeenCalledTimes(1);
+
+    // One attempt was already spent on this source; the new profile gets its own.
+    harness.addProfile("web");
+    await refreshRecallHosts();
+    expect(await autoReconcile({ sources: [] })).toEqual([]);
+    expect(harness.api.installRecall.mock.calls.at(-1)).toEqual([
+      "deepseek-harness:web",
+      "fp-deepseek-harness:web",
+    ]);
+    expect(harness.state.get("deepseek-harness:web")).toBe("approved");
+  });
+
+  it("does not retry a failing profile on every poll", async () => {
+    saveConnectionPreferences({
+      syncSourceIds: [],
+      hostSourceIds: ["deepseek-harness"],
+    });
+    const harness = harnessBridge(
+      { desktop: "approved", web: "not-installed" },
+      { failInstall: ["web"] },
+    );
+    await refreshRecallHosts();
+    expect(await autoReconcile({ sources: [] })).toEqual([
+      {
+        kind: "host",
+        sourceId: "deepseek-harness",
+        reason: "应用控制通道暂不可用",
+        profiles: ["web"],
+      },
+    ]);
+    await refreshRecallHosts();
+    expect(await autoReconcile({ sources: [] })).toBeNull();
+    expect(harness.api.installRecall).toHaveBeenCalledTimes(1);
+  });
+
+  it("stays out while the switch is off", async () => {
+    const harness = harnessBridge({ desktop: "not-installed" });
+    await refreshRecallHosts();
+    expect(await autoReconcile({ sources: [] })).toBeNull();
+    harness.addProfile("web");
+    await refreshRecallHosts();
+    expect(await autoReconcile({ sources: [] })).toBeNull();
+    expect(harness.api.installRecall).not.toHaveBeenCalled();
+  });
+});
+
+describe("a profile whose name MemHub cannot grant", () => {
+  it("is named with the real reason and does not hold up the others", async () => {
+    const { state } = harnessBridge({
+      My_Profile: "unsupported",
+      web: "not-installed",
+    });
+    await refreshRecallHosts();
+    const error = await enableHostConnection("deepseek-harness").catch(
+      (reason: unknown) => reason,
+    );
+    expect((error as ProfileWriteError).profiles).toEqual(["My_Profile"]);
+    expect(hostWriteReason(error)).toBe("appProfileNameUnsupported");
+    expect(state.get("deepseek-harness:web")).toBe("approved");
+    // Nothing is left for the remembered switch to keep trying.
+    expect(
+      sourceConnectionIncomplete(
+        await refreshRecallHosts(),
+        "deepseek-harness",
+      ),
+    ).toBe(false);
+  });
+});

memhub/apps/web/src/host-state.ts

@@ -1,5 +1,10 @@
 import { MutationObserver, useQuery } from "@tanstack/react-query";
-import { connectionHostId, hostMatchesSource } from "./connection-hosts";
+import {
+  connectionHostId,
+  hostMatchesSource,
+  isProfileSource,
+  profileName,
+} from "./connection-hosts";
 import type {
   RecallHostStatus,
   RecallPermissionStatus,
@@ -226,6 +231,7 @@ export function matchHost(
 
 const REASONS: Record<string, string> = {
   host_unsupported: "它没有 MCP 通道，无法发放可撤销的记忆凭证",
+  profile_name_unsupported: "appProfileNameUnsupported",
   unsupported_host: "当前安装不支持一键插入",
   connection_client_unavailable: "桌面端的连接组件不可用",
   noncanonical_data_dir_host_integration_disabled: "测试实例不接入应用",
@@ -350,18 +356,77 @@ export function hostWriteInFlight() {
   return queryClient.isMutating({ mutationKey: HOST_WRITE }) > 0;
 }
 
+/** A per-profile source writes to every profile, so it waits on each of them. */
 function sourceHost(sourceId: string) {
+  if (isProfileSource(sourceId))
+    return [
+      sourceId,
+      ...profileHosts(cachedRecallHosts(), sourceId).map((host) => host.hostId),
+    ];
   return [connectionHostId(sourceId) ?? sourceId];
 }
 
+/** Every detected profile host of a per-profile source, e.g. DeepSeek Harness. */
+export function profileHosts(
+  hosts: readonly RecallHostStatus[] | undefined,
+  sourceId: string,
+) {
+  if (!isProfileSource(sourceId)) return [];
+  return (hosts ?? []).filter((host) => host.hostId.startsWith(`${sourceId}:`));
+}
+
+/** The app switch reads as on: its host, or for a per-profile source any
+ * profile, may use memory. A failed profile is reported, not hidden. */
+export function sourceConnectionApproved(
+  hosts: readonly RecallHostStatus[] | undefined,
+  sourceId: string,
+) {
+  if (isProfileSource(sourceId))
+    return profileHosts(hosts, sourceId).some(hostConnectionApproved);
+  return hostConnectionApproved(matchHost(hosts, sourceId));
+}
+
+/** Something the switch would still do: a host, or any profile, that is
+ * neither approved nor unsupported. */
+export function sourceConnectionIncomplete(
+  hosts: readonly RecallHostStatus[] | undefined,
+  sourceId: string,
+) {
+  const pending = (host: RecallHostStatus | null) =>
+    !hostConnectionApproved(host) && !hostConnectionUnsupported(host);
+  if (isProfileSource(sourceId))
+    return profileHosts(hosts, sourceId).some(pending);
+  return pending(matchHost(hosts, sourceId));
+}
+
+/** Some profiles of a per-profile source could not be written; the others
+ * were kept. The message keeps the first cause so `hostWriteReason` names it. */
+export class ProfileWriteError extends Error {
+  readonly profiles: string[];
+  constructor(profiles: string[], cause: unknown) {
+    super(
+      `profile_write_failed ${cause instanceof Error ? cause.message : ""}`.trim(),
+    );
+    this.profiles = profiles;
+  }
+}
+
+/** The profile names a failed write left behind, if it was a profile write. */
+export function profileWriteFailures(error: unknown): string[] | null {
+  return error instanceof ProfileWriteError ? error.profiles : null;
+}
+
 type Connected = {
   hostId: string;
   installed: boolean;
   permission?: RecallPermissionStatus;
 };
 
-async function connect(sourceId: string): Promise<Connected | null> {
-  const hostId = connectionHostId(sourceId);
+type Bridge = NonNullable<ReturnType<typeof bridge>>;
+
+async function connect(sourceId: string): Promise<Connected[]> {
+  const profiles = isProfileSource(sourceId);
+  const hostId = profiles ? sourceId : connectionHostId(sourceId);
   const api = bridge();
   if (
     !hostId ||
@@ -371,12 +436,65 @@ async function connect(sourceId: string): Promise<Connected | null> {
     !api.setRecallPermission
   )
     throw Error("unsupported_host");
-  const existing = matchHost(await refreshRecallHosts(), sourceId);
-  if (hostConnectionUnsupported(existing)) throw Error("host_unsupported");
-  if (hostConnectionApproved(existing)) {
-    await api.repairRecallCommands?.();
-    return null;
+  const hosts = await refreshRecallHosts();
+  if (profiles) return connectProfiles(api, sourceId, hosts);
+  const result = await grantHost(
+    api,
+    hostId,
+    sourceId,
+    matchHost(hosts, sourceId),
+  );
+  await api.repairRecallCommands?.();
+  return result ? [result] : [];
+}
+
+/** One switch, every detected profile. A profile that fails does not undo
+ * the ones that worked; the error names it. Profiles already approved are
+ * left alone, so turning the switch on again only reaches what is missing. */
+async function connectProfiles(
+  api: Bridge,
+  sourceId: string,
+  hosts: RecallHostStatus[],
+): Promise<Connected[]> {
+  const profiles = profileHosts(hosts, sourceId);
+  if (!profiles.length) throw Error("profiles_not_found");
+  const connected: Connected[] = [];
+  const failed: string[] = [];
+  let cause: unknown;
+  for (const host of profiles) {
+    try {
+      const result = await grantHost(api, host.hostId, sourceId, host);
+      if (result) connected.push(result);
+    } catch (error) {
+      failed.push(profileName(host.hostId));
+      // Harness speaks MCP, so "unsupported" can only mean the id grammar
+      // refused this name; "no MCP channel" would send the person astray.
+      cause ??= hostConnectionUnsupported(host)
+        ? Error("profile_name_unsupported")
+        : error;
+    }
   }
+  if (failed.length < profiles.length) await api.repairRecallCommands?.();
+  if (failed.length) throw new ProfileWriteError(failed, cause);
+  return connected;
+}
+
+/** Installs and grants one host; null when it was already approved. */
+async function grantHost(
+  api: Bridge,
+  hostId: string,
+  sourceId: string,
+  existing: RecallHostStatus | null,
+): Promise<Connected | null> {
+  if (
+    !api.previewRecallInstall ||
+    !api.installRecall ||
+    !api.getRecallPermission ||
+    !api.setRecallPermission
+  )
+    throw Error("unsupported_host");
+  if (hostConnectionUnsupported(existing)) throw Error("host_unsupported");
+  if (hostConnectionApproved(existing)) return null;
   const preview = await api.previewRecallInstall(hostId);
   const installed = await api.installRecall(hostId, preview.fingerprint);
   let permission =
@@ -394,19 +512,19 @@ async function connect(sourceId: string): Promise<Connected | null> {
   }
   if (permission.receipt?.status !== "approved")
     throw Error("permission_not_approved");
-  await api.repairRecallCommands?.();
   return { hostId, installed: true, permission };
 }
 
-function landConnected(result: Connected | null) {
-  if (result)
+function landConnected(results: Connected[]) {
+  for (const result of results)
     landHost(result.hostId, {
       installed: result.installed,
       permission: result.permission,
     });
 }
 
-/** Installs and grants one host; resolves only once the grant is approved. */
+/** Installs and grants one host (or every profile of a per-profile source);
+ * resolves only once the grants are approved. */
 export const enableHostConnection = hostWrite(
   sourceHost,
   connect,
@@ -479,6 +597,22 @@ async function disconnect(hostId: string): Promise<Disconnected> {
   }
 }
 
+function landDisconnected({
+  hostId,
+  outcome,
+}: {
+  hostId: string;
+  outcome: DisconnectOutcome;
+}) {
+  if (outcome.state === "removed")
+    landHost(hostId, {
+      installed: false,
+      ...(outcome.permission ? { permission: outcome.permission } : {}),
+    });
+  else if (outcome.state !== "failed" && outcome.permission)
+    landHost(hostId, { permission: outcome.permission });
+}
+
 export const disconnectHost = hostWrite(
   (hostId: string) => [hostId],
   async (
@@ -489,14 +623,48 @@ export const disconnectHost = hostWrite(
     const rereadFailed = !(await rereadOnce());
     return { hostId, outcome: { ...result, rereadFailed } };
   },
-  ({ hostId, outcome }) => {
-    if (outcome.state === "removed")
-      landHost(hostId, {
-        installed: false,
-        ...(outcome.permission ? { permission: outcome.permission } : {}),
+  landDisconnected,
+);
+
+export type ProfileDisconnect = { hostId: string; outcome: DisconnectOutcome };
+
+/** Linked to MemHub at all: installed, or holding a receipt that is not yet
+ * revoked. A profile that never was has nothing to remove. */
+function profileLinked(host: RecallHostStatus) {
+  const status = host.permission?.receipt?.status;
+  return host.installed || (status !== undefined && status !== "revoked");
+}
+
+/** Turn a per-profile source off: each linked profile is removed and its grant
+ * revoked, exactly as one host would be. One failure does not stop the rest;
+ * every outcome is returned so the page can name the profile it concerns. */
+export const disconnectProfiles = hostWrite(
+  sourceHost,
+  async (sourceId: string): Promise<ProfileDisconnect[]> => {
+    const profiles = profileHosts(await refreshRecallHosts(), sourceId).filter(
+      profileLinked,
+    );
+    const results: ProfileDisconnect[] = [];
+    let anyFailed = false;
+    for (const host of profiles) {
+      const outcome = await disconnect(host.hostId);
+      anyFailed ||= outcome.state === "failed";
+      results.push({
+        hostId: host.hostId,
+        outcome:
+          outcome.state === "failed"
+            ? { ...outcome, rereadFailed: false }
+            : outcome,
       });
-    else if (outcome.state !== "failed" && outcome.permission)
-      landHost(hostId, { permission: outcome.permission });
+    }
+    if (anyFailed && !(await rereadOnce()))
+      for (const result of results)
+        if (result.outcome.state === "failed")
+          result.outcome = { ...result.outcome, rereadFailed: true };
+    return results;
+  },
+  (results) => {
+    for (const result of results) landDisconnected(result);
   },
 );
 

memhub/apps/web/src/state-boundaries.test.ts

@@ -91,7 +91,14 @@ describe("single state layer", () => {
   });
 
   it("reads and writes host connections only through host-state", () => {
-    expect(offenders(hostUses, ["host-state.ts", "global.d.ts"])).toEqual([]);
+    expect(
+      offenders(hostUses, [
+        "host-state.ts",
+        "global.d.ts",
+        // Test support: it is the fake bridge, and only tests import it.
+        "harness-profiles.test-fixture.ts",
+      ]),
+    ).toEqual([]);
   });
 
   it("reads and writes sources only through source-state", () => {

memhub/docs/ARCHITECTURE.md

@@ -282,7 +282,7 @@ Support is declared per immutable GitHub Release manifest:
 - Linux x64/arm64 Runtime on native GHA runners.
 - macOS arm64/x64 App/Runtime: Developer ID, notarization, native acceptance.
 - Windows is not supported.
-- `hy-memory==2.0.11` is the current stable SDK dependency; the release
+- `hy-memory==2.0.12` is the current stable SDK dependency; the release
   lock and [`../MEMORY.md`](../MEMORY.md) are authoritative when the pin changes.
 
 See [`INSTALLATION.md`](INSTALLATION.md).

memhub/docs/cli/EXPERIENCE.md

@@ -69,8 +69,14 @@ node apps/cli/dist/one-memory.cjs sources list
 ```
 
 - 只有 `hermes` 能带 `--user-id`（非 `local`）或 `--root`；其他来源带了会退 2，什么都不发。
+- 用户 ID 不必等于 profile 名：profile 名里有 `:` 等字符时另起一个，例如
+  `--user-id wife-work --root ~/.hermes/profiles/wife:work`。
 - `--root` 里的 `~` 由 CLI 展开为主目录，相对路径按当前目录解析成绝对路径。
-- 扫描 `~/.hermes` 时会排除 `profiles/**`，所以 `local` 不会读到 wife 的 `state.db`。
+- 扫描时任何层级名为 `profiles` 的目录都会被排除，所以 `local` 不会读到 wife 的 `state.db`，
+  即使授权的根在 `~/.hermes` 之上。
+- `--root` 不能是 `profiles` 目录本身（`hermes_root_is_profiles_container`），也不能与另一个
+  用户已接入的 Hermes 目录相同、包含它或在它之内（`hermes_root_overlaps_other_user`，解析
+  symlink 后比较）；`~/.hermes` 给 `local`、`~/.hermes/profiles/<name>` 给另一个用户是允许的。
 - App 不变：它只读写 `local`，其他来源也都固定是 `local`。
 
 ## 3. 看导入进度
@@ -140,7 +146,11 @@ node apps/cli/dist/one-memory.cjs write status <request_id> --user-id wife
 
 - 用户 ID 只能是 1–64 位字母、数字、`.`、`_`、`-`；其他写法退 2，不连 Runtime。
 - 不带 `--user-id`（或写 `--user-id local`）时请求里不出现 `user_id`，和以前完全一样。
-- 用户之间互相隔离：读、改、删另一个用户的记忆 ID 返回「未找到」；write 的 request id 也只属于提交它的用户。
+- 用户之间互相隔离：读、改、删另一个用户的记忆 ID 返回「未找到」（HTTP 404 `memory_not_found`，
+  与不存在的 ID 完全一样）；write 的 request id 也只属于提交它的用户。
+- `memories delete <id> --yes` 遇到「未找到」时按已删除处理：提示「未找到记忆 <id>（可能已删除）」，
+  退出 0；`--json` 为 `state: "committed"` 加 `already_gone: true`。App 里重复点删除也不再报错。
+- 读接口（`memories list`、`profile`、`recall` 等背后的 HTTP 响应）都带 `user_id`，即实际读的是哪个用户。
 
 ### 画像版本（`profile --versions`）
 
@@ -177,7 +187,7 @@ node apps/cli/dist/one-memory.cjs settings features reset
 ```
 
 - 全局设置，不分用户；没设置的功能保持 SDK 默认值，什么都不设时与以前完全一样（App 不变）。
-- 可设：`graph_rerank`（图谱重排，仅 ultra）、`same_series_timeline`（需 graph_rerank）、`episode_recall`（片段召回，pro 即可）、`session_episodes`（片段写入）、`episode_summary`（片段摘要，每个片段一次模型调用）、`intention`（默认开）、`few_shot`。
+- 可设：`graph_rerank`（图谱重排，仅 ultra）、`same_series_timeline`（需 graph_rerank）、`episode_recall`（片段召回，pro 即可）、`session_episodes`（片段写入）、`episode_summary`（片段摘要，每个片段一次模型调用）、`intention`（默认开）、`intention_dedup`（意图判重，默认开；关闭后检索和写入都不判重、不删除意图）、`few_shot`；以及数值 `intention_dedup_threshold`（意图判重的余弦阈值，默认 0.95，可设 0.8–1.0，例如 `settings features set intention_dedup_threshold=0.9 --yes`）。
 - 片段召回只对带片段的记忆有用：同时开 `session_episodes`，之后提取的记忆才按会话归入片段。
 - 在当前模式下不生效的功能照样保存，并注明原因（如 `graph_rerank` 在 pro 下「需要 ultra」）。
 - 修改会重建 SDK 客户端：正在写的一批按旧设置写完，之后的写入和检索用新设置；不迁移数据，不改集合名。
@@ -189,14 +199,14 @@ node apps/cli/dist/one-memory.cjs settings features reset
 ```bash
 node apps/cli/dist/one-memory.cjs settings language          # 界面语言和 SDK 提示语言
 node apps/cli/dist/one-memory.cjs settings language ja       # 设为日语，立即生效
-node apps/cli/dist/one-memory.cjs settings language system   # 跟随系统（不指定 SDK 语言）
+node apps/cli/dist/one-memory.cjs settings language system   # 清除设置（不指定 SDK 语言）
 ```
 
 - 可选 11 种：`en`、`zh-Hans`、`zh-Hant`、`ja`、`es`、`de`、`pt`、`fr`、`ko`、`ru`、`id`，以及 `system`；旧代码 `zh-CN` 按 `zh-Hans` 处理。
-- App 切换语言时会自动设置（Desktop 启动时也会同步一次已保存的选择）。全局设置，存于 `config.json` 的 `ui_language`；从未选择时不写入。
-- `zh-Hans` 和 `system` 不向 SDK 传语言，SDK 照旧自动识别中文或英文；其余语言（包括 `en`）作为 `MemoryConfig.language` 传给 SDK，提取等提示使用该语言。
+- App 切换语言时会自动设置；Desktop 每次启动也会同步一次界面实际显示的语言（App 选“跟随系统”时，发送它按系统语言解析出的语言，例如 `zh-Hans`）。全局设置，存于 `config.json` 的 `ui_language`；从未设置时不写入。
+- 所有语言（包括 `zh-Hans` 和 `en`）都作为 `MemoryConfig.language` 传给 SDK，提取等提示使用该语言；只有未设置（`system`，或只用 CLI/API、从未打开 App 的安装）时不向 SDK 传语言，SDK 照旧自动识别中文或英文。
 - 修改会像功能开关一样重建 SDK 客户端；不迁移数据，不改集合名（需要 hy-memory 2.0.11 的 `MemoryConfig.language`）。
-- `status --json` 的 `pipeline.ui_language` / `pipeline.sdk_language`（`auto` 或语言代码）。API：`GET`/`PUT /api/v1/settings/ui-language`。
+- `status --json` 的 `pipeline.ui_language` / `pipeline.sdk_language`（`auto` 或语言代码；`zh-Hans` 用户显示 `zh-Hans`）。API：`GET`/`PUT /api/v1/settings/ui-language`。
 
 ## 8. 召回（recall）
 

memhub/docs/contracts/host-context-transport-v1.md

@@ -5,6 +5,11 @@ Post-cutover hosts use SDK-native Context v2 at
 `POST /api/v2/context/search`. A v2 response is never converted into v1 by
 inventing revisions, Evidence IDs, paths, or adoption state.
 
+Since MemHub 1.0.6 the v2 response also carries `user_id`, the user whose
+memories were searched (`local` unless the request named one). The Host
+Bridge validator accepts it as an optional field, so a response from an older
+Core without it still validates; any other unknown field still fails closed.
+
 ## Transport
 
 - The Broker `/context` route (used by host hooks and `recall-cli --context`;

memhub/docs/contracts/memory-features-v1.md

@@ -32,6 +32,7 @@ prompt and no extra call.
 | `session_episodes` | `recall.session_episode_enabled` (`MEMORY_SESSION_EPISODE_ENABLED`) | off | pro or ultra | none |
 | `episode_summary` | `recall.episode_summary_enabled` (`MEMORY_EPISODE_SUMMARY_ENABLED`) | off | pro or ultra | LLM: one call per closed episode of 3+ memories |
 | `intention` | `llm.enable_intention` (`MEMORY_ENABLE_INTENTION`) | **on** | pro or ultra | none (off shortens the prompt) |
+| `intention_dedup` | `recall.intention_dedup_enabled` (`MEMORY_INTENTION_DEDUP_ENABLED`) | **on** | pro or ultra | none |
 | `few_shot` | `llm.few_shot_enabled` (`MEMORY_FEW_SHOT_ENABLED`) | off | pro or ultra | tokens (extraction and reconcile) |
 
 - **Graph rerank (usage A).** It propagates support over the graph edges
@@ -52,8 +53,32 @@ prompt and no extra call.
   write half of episodes, and both are off by default. Usage B only helps once
   episodes are being written. The SDK's session narrative (L3, `finalize_session`)
   is a separate feature and is not exposed (section 2).
-- **`intention`** is the only feature that is on by default. Turning it off
-  stops L7 intention memories from being extracted.
+- **`intention`** is on by default. Turning it off stops L7 intention
+  memories from being extracted.
+- **`intention_dedup`** (hy-memory 2.0.12) is on by default, which is what
+  every earlier version did. A search treats intentions of one user and agent
+  with the same `memory_at` day, the same `valid_until` day and a cosine
+  similarity at or above `intention_dedup_threshold` as copies: it returns the
+  earliest and deletes the others from the store. Off, no intention dedup
+  runs, at read time or within a write batch, and nothing is hidden, dropped
+  or deleted.
+
+### Parameters
+
+Numeric settings beside the features. Each tunes one feature and acts only
+while that feature acts.
+
+| Name | SDK field (env) | Default | Range | Tunes |
+|---|---|---|---|---|
+| `intention_dedup_threshold` | `recall.intention_dedup_threshold` (`MEMORY_INTENTION_DEDUP_THRESHOLD`, else `MEMORY_DEDUP_THRESHOLD`) | 0.95 | 0.8–1.0 inclusive | `intention_dedup` (read time only) |
+
+Why 0.8–1.0: with dedup on, every intention at or above the threshold is
+deleted from the store at read time, and that cannot be undone. Below about
+0.8 the embedding models MemHub ships or connects score different plans on
+one topic as that close, so a lower value would delete intentions that are
+not copies. Cosine similarity cannot exceed 1.0, and 1.0 keeps dedup for
+exact copies only. Someone who wants no dedup turns `intention_dedup` off
+rather than picking a threshold.
 
 ### Left out, and why
 
@@ -81,11 +106,12 @@ prompt and no extra call.
 holds only the features they set:
 
 ```json
-{"memory_mode": "pro", "memory_features": {"episode_recall": true, "session_episodes": true}}
+{"memory_mode": "pro", "memory_features": {"episode_recall": true, "intention_dedup_threshold": 0.9}}
 ```
 
-The values are strict booleans and unknown keys are refused, so a hand-edited
-file with an unknown feature fails to load (`config_invalid`), like any other
+Feature values are strict booleans, a parameter is a number in its range, and
+unknown keys are refused. So a hand-edited file with an unknown feature or an
+out-of-range threshold fails to load (`config_invalid`), like any other
 malformed setting.
 
 ## 3. How a setting reaches the SDK
@@ -104,7 +130,8 @@ malformed setting.
 - Each client's features are fixed when it is built, like its mode. Both the
   write handles (`SdkWriteCoordinator`) and the read handle
   (`ActiveProfileReadHandle`) are keyed by (profile, revision, mode,
-  features).
+  features). The features part of the key is the sorted (name, value) pairs
+  a person set, parameters included, so a new threshold is a new key.
 - A change runs `retire_stale_handles`, the #218 use count. An idle write
   handle closes at once, and a write in flight finishes with the features it
   started with. The next read builds a client with the new key. The old read
@@ -135,6 +162,22 @@ malformed setting.
       "description": "Usage A: propagate support over knowledge-graph edges ..."
     }
   ],
+  "parameters": [
+    {
+      "name": "intention_dedup_threshold",
+      "value": 0.95,
+      "configured": null,
+      "default": 0.95,
+      "minimum": 0.8,
+      "maximum": 1.0,
+      "active": true,
+      "reason": null,
+      "requires_feature": "intention_dedup",
+      "sdk_field": "recall.intention_dedup_threshold",
+      "env": "MEMORY_INTENTION_DEDUP_THRESHOLD",
+      "description": "Cosine similarity at or above which ..."
+    }
+  ],
   "non_default": {"graph_rerank": true}
 }
 ```
@@ -143,27 +186,32 @@ malformed setting.
 - `configured` is null when unset.
 - `default` is the SDK default: its code default, or its own env var when set.
 - `active` is false with a `reason` when the feature does nothing right now.
-  The reason is one of `disabled`, `requires_pro` (lite), `requires_ultra`, or
-  `requires_graph_rerank` (for `same_series_timeline`).
+  The reason is one of `disabled`, `requires_pro` (lite), `requires_ultra`,
+  `requires_graph_rerank` (for `same_series_timeline`), or
+  `requires_intention_dedup` (for the threshold while `intention_dedup` is off).
 - `cost` is one of `none`, `extra_query`, `llm_call`, `prompt_tokens`.
 - `features` always lists every feature, in the table's order.
+- `parameters` lists every parameter. `value` is what clients are built with;
+  `minimum` and `maximum` are the range a `PUT` accepts. A parameter is
+  active exactly when the feature it tunes is.
 
 ## 5. `PUT /api/v1/settings/memory-features`
 
 The body has any of the feature names as keys:
 
 - `true` or `false` sets that feature.
+- A JSON number sets a parameter, if it is in range (inclusive).
 - `null` resets it to the default.
 - An absent key is left as it is.
-- Anything else answers `422`, including a non-boolean, `"true"`, `1`, or an
-  unknown name.
+- Anything else answers `422`, including a non-boolean feature, `"true"`, `1`,
+  an unknown name, or a threshold outside 0.8–1.0, a string, or a boolean.
 
 ```json
-{"graph_rerank": true, "episode_recall": true, "few_shot": null}
+{"graph_rerank": true, "intention_dedup_threshold": 0.9, "few_shot": null}
 ```
 
-The answer is the state of section 4, plus `changed`: the features whose
-effective value changed, in the table's order. When the set of configured
+The answer is the state of section 4, plus `changed`: the features and then
+the parameters whose effective value changed, in the tables' order. When the set of configured
 features changes, the SDK clients are rebuilt (section 3). That includes a
 reset to a value equal to the default, after which the client carries no
 override at all.
@@ -172,10 +220,11 @@ override at all.
 
 `pipeline` in `GET /api/v1/memory-processing` (memory-mode contract §7) gains
 `features`, which lists the features whose effective value differs from the
-default. It is `{}` while every feature is at its default:
+default, and the parameters (as numbers) likewise. It is `{}` while every
+setting is at its default:
 
 ```json
-{"pipeline": {"mode": "pro", "...": "...", "features": {"episode_recall": true, "intention": false}}}
+{"pipeline": {"mode": "pro", "...": "...", "features": {"episode_recall": true, "intention_dedup_threshold": 0.9}}}
 ```
 
 `memhub status --json` and `memhub progress --json` carry it as
@@ -188,14 +237,19 @@ to the memory-mode line.
 memhub settings features                                       # list them
 memhub settings features set episode_recall=true session_episodes=true   # plan only
 memhub settings features set episode_recall=true session_episodes=true --yes
+memhub settings features set intention_dedup=false --yes        # no intention dedup
+memhub settings features set intention_dedup_threshold=0.9 --yes # a looser dedup
 memhub settings features reset few_shot                         # back to the default
 memhub settings features reset                                  # every set feature
 ```
 
 `set` prints its plan and needs `--yes`, like `settings mode`, because some
 features spend model calls. `reset` only returns features to their defaults,
-so it applies at once. Unknown names or values other than `true` / `false` are
-a usage error (exit 2) before the Runtime is asked.
+so it applies at once. Unknown names, feature values other than `true` /
+`false`, and a threshold that is not a plain decimal in 0.8–1.0 are a usage
+error (exit 2) before the Runtime is asked. Against an older Runtime that does
+not list the threshold, `set` answers `rejected` /
+`memory_feature_unsupported` without sending it.
 
 ## 8. Rules kept
 
@@ -216,6 +270,8 @@ a usage error (exit 2) before the Runtime is asked.
 | session_episodes | 片段写入：同一会话中提取的记忆归入同一片段。 | Episodes per conversation: memories extracted from one conversation share one episode. | Episodios por conversación: las memorias extraídas de una conversación comparten un episodio. |
 | episode_summary | 片段摘要：片段结束时总结一次（每个片段一次模型调用）。 | Episode summaries: each finished episode is summarized once (one model call per episode). | Resúmenes de episodio: cada episodio terminado se resume una vez (una llamada al modelo por episodio). |
 | intention | 意图提取：随事实一起记住你提到的计划和意图。 | Intentions: remembers the plans and intentions you mention, along with facts. | Intenciones: recuerda los planes e intenciones que mencionas, junto con los hechos. |
+| intention_dedup | 意图去重：同一天里几乎相同的意图只保留最早一条，其余删除。 | Intention dedup: of near-identical intentions from one day, keeps the earliest and deletes the rest. | Deduplicación de intenciones: de las intenciones casi idénticas de un mismo día, conserva la más antigua y borra las demás. |
+| intention_dedup_threshold | 去重阈值：越高，越少的意图被视为重复。 | Dedup threshold: the higher it is, the fewer intentions count as copies. | Umbral de deduplicación: cuanto más alto, menos intenciones cuentan como copias. |
 | few_shot | 提取示例：在提取提示中加入示例，可帮助较弱的模型（输入更长）。 | Extraction examples: adds examples to the extraction prompt, which can help a weaker model (longer input). | Ejemplos de extracción: añade ejemplos a la instrucción de extracción, lo que puede ayudar a un modelo más débil (entrada más larga). |
 | default | 默认 | Default | Predeterminado |
 | requires_ultra | 当前模式下不生效，需要 ultra。 | Has no effect in this mode; needs ultra. | No tiene efecto en este modo; requiere ultra. |

memhub/docs/contracts/source-adapter-v1.md

@@ -20,6 +20,20 @@ cursor。旧文件后续追加也必须能被再次发现，不能只有一个
 用户授权是读取前置条件。环境变量只用于发现候选根，不能代替授权。每个候选
 文件必须在打开时再次验证 realpath 归属、symlink、普通文件类型和大小预算。
 
+多用户（仅 Hermes）：一个授权根属于一个 `user_id`。Hermes 的扫描、检测和
+持续同步共用同一次遍历，**任何层级**名为 `profiles` 的目录都不进入（发现
+helper 的 `excluded_directory_names`），所以授权根即使在 `~/.hermes` 之上，
+也不会读到 `.hermes/profiles/<name>`。接入时 Core 拒绝：
+
+- 根的最后一段是 `profiles`（profiles 容器本身）：422
+  `hermes_root_is_profiles_container`；
+- 根（解析 symlink 后）与另一个用户未撤销的 Hermes 授权根相同、包含它或在
+  它之内：409 `hermes_root_overlaps_other_user`。唯一例外是一方正好是另一方
+  的 `profiles/<name>`（`local` 在 `~/.hermes`、另一个用户在
+  `~/.hermes/profiles/<name>`），因为上面的排除已把两者隔开。
+
+本机 `local` 的接入（`/sources/connect`、`/sources/{id}/authorize`）也走同一检查。
+
 ## Imported source record
 
 Adapter 输出的 `ScannedEvidence` 是兼容命名的导入中间表示。原文持久化与 raw

memhub/docs/harness-support/README.md

@@ -40,7 +40,7 @@ Preview 不会弹出给用户；开关点击本身被视为确认。关闭时通
 | [Qwen Code](qwen-code.md) | 开放 | MCP + Skill | 无自动 Hook | `$QWEN_HOME/projects` 扫描 |
 | [Pi](pi.md) | 开放 | CLI Skill，不使用 MCP | JS Capture Extension | Pi session 扫描 + Extension 实时入口 |
 | [OpenClaw](openclaw.md) | 正式产品冻结 | 当前没有；仅有未开放的底层 MCP 写入器 | 没有 Hook、Plugin 或 Prefetch | Adapter 也被冻结，开关不可用 |
-| [DeepSeek Harness](deepseek-harness.md) | 详情页排除，来源管理页按 Profile 接入 | Profile 级 MCP Patch | 无自动 Hook | `$DSH_HOME/sessions` 扫描 |
+| [DeepSeek Harness](deepseek-harness.md) | 开放；一个开关覆盖全部已检测 Profile | Profile 级 MCP Patch | 无自动 Hook | `$DSH_HOME/sessions` 扫描 |
 
 ## 同步开关的统一精确语义
 

memhub/docs/harness-support/deepseek-harness.md

@@ -1,28 +1,45 @@
 # DeepSeek Harness 一键插入支持
 
-更新日期：2026-10-18
+更新日期：2026-11-02
 
 ## 结论
 
-DeepSeek Harness 的 Profile 级 MCP 安装器已经实现，Profile Scoped Host ID（`deepseek-harness:<profile>`）在权限层按不透明标签处理，可正常走完 Preview 与安装。
+DeepSeek Harness 按 Profile 配置 MCP：每个 Profile 是一个独立 Host（`deepseek-harness:<profile>`），有自己的 `cordis.patch.yml`、Credential 与 Grant。应用详情页只有一个“一键插入应用”开关，它一次覆盖桌面检测到的全部 Profile：打开时逐个安装并授权，关闭时逐个移除并撤销。
 
 ## 接入方式和产品状态
 
 | 项目 | DeepSeek Harness 当前实现 |
 |---|---|
-| 应用详情页一键插入 | 有意排除，因为无法选择 Profile |
-| 来源管理页 Profile 安装 | 可用；每个 Profile 独立 Patch、Credential 与 Grant |
+| 应用详情页一键插入 | 可用；一个开关覆盖全部已检测 Profile，并列出每个 Profile 的状态 |
+| 首次导入批量连接 | 排除；在应用详情页打开开关 |
 | Harness 查询 MemHub | 通过 Profile 级 Cordis MCP Client |
 | Skill | 没有 |
 | Prompt 前自动 Prefetch | 没有 |
 | Capture Hook/Plugin | 没有 |
-| Harness 新会话进入 MemHub | Core 扫描 `$DSH_HOME/sessions` |
+| Harness 新会话进入 MemHub | Core 扫描 `$DSH_HOME/sessions`，按 `session[.vN].jsonl[.zstd]` 识别会话文件 |
+
+会话文件按写入时的格式版本命名：首版为 `session.jsonl` / `session.jsonl.zstd`，v3/v4 起为 `session.v3.jsonl.zstd` / `session.v4.jsonl.zstd`。来源扫描接受带版本号的名称；解析前再读文件头 `version` 字段，只导入已验证的 v0/v3/v4，未来未知版本不会被解析：整个文件以 `unsupported_schema` 报告，且不留下读取进度，将来支持该版本的发布会从头读取（错误导入比暂时漏导更难回滚）。`tool/result` 的输出无论写成 `tool-result` 块还是纯 `text` 块，都按同一条裁剪与凭据清洗路径导入。
 
 ## 两个开关分别做什么
 
-### “一键插入应用”
+### 打开“一键插入应用”
 
-应用详情页不可用。来源管理页对每个 Profile 写 `cordis.patch.yml`、创建独立 Credential 并授权；Host ID 形如 `deepseek-harness:<profile>`，冒号只作为标签存在，权限层的安装目录按 Host ID 摘要生成，不参与路径拼接。
+应用详情页对每个已检测、尚未获批的 Profile：
+
+1. 预览并写入该 Profile 的 `cordis.patch.yml` 受管块，创建独立 Credential；
+2. 授予 `om_recall`、`om_conversations`、`om_diagnostic_trace`，范围为 `all-apps` 与 `source:deepseek-harness`（与其他应用的一键插入相同）。
+
+已获批的 Profile 不会重装。某个 Profile 失败时，其他 Profile 的结果保留，页面提示失败的 Profile 名称；开关只要有一个 Profile 获批就显示为开。Host ID 里的冒号只作为标签存在，权限层的安装目录按 Host ID 摘要生成，不参与路径拼接。
+
+### 关闭“一键插入应用”
+
+对每个已接入的 Profile 先撤销 Credential，再删除受管块（与其他应用的关闭语义相同）。受管块被改过、无法删除时仍会撤销授权，页面列出需要核对的 Profile；撤销也失败的 Profile 会单独列出，它仍可使用记忆。从未接入的 Profile 不受影响。
+
+### 之后新建的 Profile
+
+桌面每次刷新应用接入状态时都会重新枚举 Profile（`$DSH_HOME/profiles/<profile>/cordis.yml`），应用首页打开时每 3 秒刷新一次；常驻的 Runtime 收到未知的 Profile Host ID 时也会重新读盘。开关的选择会被记住：开关为开时，新出现的 Profile 由应用首页自动安装并授权，不需要重启 MemHub。
+
+每个新 Profile 触发一次自动尝试；失败时应用首页会指明 Profile，不会每次轮询都重试，下次启动或点击重试时再试一次。开关为关时不会自动接入任何 Profile。
 
 ### 打开“同步开关”
 
@@ -32,12 +49,10 @@ DeepSeek Harness 的 Profile 级 MCP 安装器已经实现，Profile Scoped Host
 
 Core 停止扫描和 pending Job claim，running Job可结束，已有 Memory 保留。它不会修改任何 Profile 的 `cordis.patch.yml` 或 Credential。
 
-### 修复一键安装后的组合语义
+### 组合语义
 
-未来修复 Profile Host ID 后：
-
-- 某个 Profile 的一键插入只决定该 Profile 是否能查询 MemHub；
-- 全局同步开关决定 MemHub 是否继续读取整个 DeepSeek Harness 的 Session；
+- 一键插入决定已检测 Profile 是否能查询 MemHub；
+- 同步开关决定 MemHub 是否继续读取整个 DeepSeek Harness 的 Session；
 - 没有自动 Prefetch，也没有 Capture Hook。
 
 ## Profile 粒度
@@ -58,7 +73,7 @@ deepseek-harness:headless
 ...
 ```
 
-理论上每个 Profile 拥有独立 Patch、Journal、Credential 和 Grant；Core 会话同步仍按统一的 `deepseek-harness` 来源扫描 `$DSH_HOME/sessions`。
+每个 Profile 拥有独立 Patch、Journal、Credential 和 Grant；Core 会话同步仍按统一的 `deepseek-harness` 来源扫描 `$DSH_HOME/sessions`。
 
 ## MCP Patch
 
@@ -85,13 +100,15 @@ DeepSeek Harness 不安装 Skill，也不安装 Capture Hook；新会话进入 M
 
 ## UI 状态
 
-- 应用详情页排除 DeepSeek Harness，因为单一来源页无法选择 Profile。
-- 首次导入批量连接也排除它。
-- 来源管理页会列出每个 Profile，并显示独立安装按钮。
+- 应用详情页的“一键插入应用”下方列出每个已检测 Profile 及其“已接入 / 未接入”状态；没有检测到 Profile 时开关不可用，并提示创建 Profile 后回到此页。
+- Host ID 只接受小写字母、数字和连字符（最长 32 个字符）。名称不符合的 Profile 仍会列出，但无法授权，页面会指明它和原因，不影响其他 Profile。
+- 连接状态取各已接入 Profile 记录的自检结果：全部接通才显示“已接通”。
+- 首次导入批量连接排除 DeepSeek Harness。
+- CLI 的 `memhub host install deepseek-harness:<profile>` 只安装，不授权（状态停在 `install-only`）；授权入口只有应用详情页的开关，CLI 没有授权命令。
 
 ## 已修复：Profile Host ID 校验
 
-此前来源管理页安装会在写入 `cordis.patch.yml` 和创建 Credential 之前失败，原因是：
+此前 Profile 安装会在写入 `cordis.patch.yml` 和创建 Credential 之前失败，原因是：
 
 ```text
 系统生成 hostId = deepseek-harness:<profile>
@@ -101,18 +118,12 @@ HostGrantStore 也不接受冒号
 
 Host ID 是不可解释的标签：安装目录对它取摘要，不会把它拼进路径。现在权限层与 Grant 存储都接受一个可选的 `:<profile>` 段，因此 Profile 安装可以正常走完。这不是 DeepSeek Harness 不支持 MCP 的问题，而是 Profile Host ID 格式与权限校验不一致，现已对齐。
 
-## 修复后的权限语义风险
+## 已修复：应用详情页返回 `unsupported_host`
 
-来源管理页当前默认授权选择可能包含：
-
-- `om_recall`、`om_conversations`、`om_diagnostic_trace`（`om_ask` 已随 `MemHub_ask` 移除，旧授权仍可读取但不再授权任何工具）；
-- `all-apps`；
-- 所有已授权 Source 和 Workspace。
-
-这比应用详情页通用授权更宽。Host ID 修复后仍应确认是否希望每个 Profile 默认获得如此宽的权限。
+此前应用详情页按“一个来源对应一个 Host”接入，而 DeepSeek Harness 没有不带 Profile 的 Host，开关因此置灰并返回 `unsupported_host`，安装后的 Profile 也只能停在 `install-only`（#230）。现在开关直接作用于全部 `deepseek-harness:<profile>` Host，复用与其他应用相同的安装、授权、撤销与卸载接口。
 
 ## 重复安装与卸载
 
 底层 Patch 安装是幂等的：已有受管块时替换，不追加第二份。相同 Row ID 出现在 MemHub 哨兵块外时默认拒绝接管。
 
-正常卸载设计是先撤销该 Profile Credential，再删除受管块并保留其他 Patch；如果删完没有其他 Row，恢复 `[]`。用户修改过受管块时不强删。
+卸载先撤销该 Profile Credential，再删除受管块并保留其他 Patch；如果删完没有其他 Row，恢复 `[]`。用户修改过受管块时不强删。

memhub/packages/contracts/src/context.ts

@@ -118,6 +118,9 @@ export interface SdkContextSearchResponse {
   used_characters: number;
   truncated: boolean;
   total_ms: number;
+  /** Whose memories were searched; `local` unless the request named a user.
+   * Absent from a Core older than 1.0.6. */
+  user_id?: string;
 }
 
 /** Native Host Bridge wire response. Schemas stay distinct and are never adapted. */

memhub/packages/contracts/src/index.ts

@@ -425,6 +425,8 @@ export interface HomeSummary {
 
 export interface SdkHomeSummary {
   schema_version: 2;
+  /** The user the card was read for (`local` unless one was named). */
+  user_id?: string;
   memory_count: number;
   latest: SdkMemoryRecord | null;
   observed_at: string;
@@ -605,6 +607,8 @@ export interface SdkMemoryRecord {
 }
 
 export interface SdkMemoryPage {
+  /** `GET /api/v2/memory-library`: the user the page was read for. */
+  user_id?: string;
   memories: SdkMemoryRecord[];
   total: number;
   limit: number;
@@ -621,6 +625,8 @@ export interface SdkMemoryPage {
 }
 
 export interface SdkUserProfileResponse {
+  /** The user whose profile this is (`local` unless one was named). */
+  user_id?: string;
   request_id: string;
   profile: Record<string, unknown> | null;
   elapsed_ms: number;
@@ -649,6 +655,8 @@ export interface SdkRawRecord {
 }
 
 export interface SdkRawPage {
+  /** The user whose raw turns these are. */
+  user_id?: string;
   items: SdkRawRecord[];
   total: number;
   limit: number;
@@ -659,6 +667,8 @@ export interface SdkRawPage {
 
 /** `GET /api/v2/memory-library/layers`: memories per SDK layer. */
 export interface SdkLayerCounts {
+  /** The user whose memories were counted. */
+  user_id?: string;
   layers: Record<string, number>;
   total: number;
   statuses: string[] | null;
@@ -763,7 +773,8 @@ export type AskMemoryEvent =
   | { type: "error"; code: string };
 
 export type SdkAskMemoryEvent =
-  | { type: "recall"; memories: SdkAskMemory[] }
+  /** `user_id`: whose memories answer (Core 1.0.6+). */
+  | { type: "recall"; memories: SdkAskMemory[]; user_id?: string }
   | { type: "delta"; text: string }
   | {
       type: "final";
@@ -833,6 +844,8 @@ export interface RecallReceipt {
   fallback_reason?: "model_unavailable" | "no_memories" | null;
   /** Sources the caller was not allowed to read, left out of this result. */
   excluded_sources?: string[];
+  /** Whose memories were searched (`local` unless the request named a user). */
+  user_id?: string;
 }
 
 export interface LiveSyncHealth {
@@ -874,6 +887,8 @@ export interface MemoryGraphEdge {
 }
 
 export interface MemoryGraphResponse {
+  /** The user whose memories were mapped. */
+  user_id?: string;
   total_memories: number;
   projected_memories: number;
   nodes: MemoryGraphNode[];

memhub/packages/host-bridge/src/context-integration.test.ts

@@ -90,6 +90,11 @@ it("accepts only the SDK context shape", () => {
   ).toBe(false);
   expect(contextResponseInvalidField(mixed)).toBeNull();
   expect(contextResponseInvalidField(legacyShape)).toBe("response");
+  // Core 1.0.6 echoes whose memories were searched; an older Core does not.
+  expect(isSdkContextSearchResponse({ ...mixed, user_id: "local" })).toBe(true);
+  expect(isSdkContextSearchResponse({ ...mixed, user_id: "" })).toBe(false);
+  expect(isSdkContextSearchResponse({ ...mixed, user_id: 7 })).toBe(false);
+  expect(isSdkContextSearchResponse({ ...mixed, owner: "local" })).toBe(false);
 });
 
 async function fixture(

memhub/packages/host-bridge/src/context-protocol.ts

@@ -140,15 +140,22 @@ export function isSdkContextSearchResponse(
 ): value is SdkContextSearchResponse {
   if (
     !record(value) ||
-    !exact(value, [
-      "schema_version",
-      "request_id",
-      "state",
-      "items",
-      "used_characters",
-      "truncated",
-      "total_ms",
-    ]) ||
+    // `user_id` (whose memories were searched) is optional so a Core from
+    // before it was echoed still validates.
+    !exact(
+      value,
+      [
+        "schema_version",
+        "request_id",
+        "state",
+        "items",
+        "used_characters",
+        "truncated",
+        "total_ms",
+      ],
+      ["user_id"],
+    ) ||
+    (value.user_id !== undefined && !text(value.user_id, 1, 64)) ||
     value.schema_version !== 2 ||
     !text(value.request_id, 1, 64) ||
     !member(value.state, ["grounded", "empty", "partial", "unavailable"]) ||
@@ -223,8 +230,15 @@ function record(value: unknown): value is Record<string, unknown> {
 function only(value: Record<string, unknown>, keys: string[]): boolean {
   return Object.keys(value).every((key) => keys.includes(key));
 }
-function exact(value: Record<string, unknown>, keys: string[]): boolean {
-  return only(value, keys) && keys.every((key) => Object.hasOwn(value, key));
+function exact(
+  value: Record<string, unknown>,
+  keys: string[],
+  optional: string[] = [],
+): boolean {
+  return (
+    only(value, [...keys, ...optional]) &&
+    keys.every((key) => Object.hasOwn(value, key))
+  );
 }
 function text(value: unknown, min: number, max: number): value is string {
   return (

memhub/packages/i18n/src/gui-i18n-english.ts

@@ -545,6 +545,7 @@ const baseEnglishMessages = {
   nativeDevelopmentUnavailable: " (unavailable in development)",
   nativeOpen: "Open {product}",
   nativeQuit: "Quit {product} (background service keeps running)",
+  nativeQuitStopsService: "Quit {product} (also stops the memory service)",
   nativeLoginError: "Could not change the login startup setting. Please retry.",
   nativeMoveTitle: "Move MemHub to Applications first",
   nativeMoveDetail:
@@ -926,6 +927,23 @@ const baseEnglishMessages = {
     "Memory access was revoked, so {name} can no longer look up memories. Full removal could not be confirmed; review these paths manually: {paths}.",
   appRemovalReview:
     "Full connection removal could not be confirmed. Review these paths manually: {paths}.",
+  appProfilesLabel: "{name} profiles",
+  appProfileOn: "{profile}: connected",
+  appProfileOff: "{profile}: not connected",
+  appProfilesHint:
+    "The switch installs the memory connection and grants access for every detected profile, and revokes them all when turned off. While it is on, new profiles are connected automatically.",
+  appProfilesNone:
+    "No {name} profile was detected. Create a profile, then come back to this page.",
+  appProfilesConnectFailed:
+    "These profiles could not be connected: {profiles}. The other profiles were kept. {reason}",
+  appProfilesDisconnectFailed:
+    "These profiles could not be disconnected and can still use memories: {profiles}. Please retry. {reason}",
+  appProfilesRevokedRetained:
+    "Memory access was revoked for these profiles, but not all of their connection files were removed; review them: {profiles}.",
+  appProfileNameUnsupported:
+    "profile names may only use lowercase letters, digits and hyphens, up to 32 characters",
+  "apps.autoHostProfilesFailed":
+    "{name} could not connect these profiles automatically ({profiles}){reason}.",
   "Cursor 的连接凭证已更新。请完全退出并重新打开 Cursor，再开始新对话。":
     "Cursor's connection credential changed. Fully quit and reopen Cursor before starting a new conversation.",
   连接其他工具: "Connect other tools",

memhub/packages/i18n/src/gui-i18n-recovery.ts

@@ -13,6 +13,7 @@ export const recoveryChineseMessages = {
   nativeDevelopmentUnavailable: "（开发模式不可用）",
   nativeOpen: "打开 {product}",
   nativeQuit: "退出 {product}（后台服务继续运行）",
+  nativeQuitStopsService: "退出 {product}（同时停止记忆服务）",
   nativeLoginError: "无法更改登录启动设置，请重试。",
   nativeMoveTitle: "请先将 MemHub 拖到“应用程序”文件夹",
   nativeMoveDetail:
@@ -115,6 +116,8 @@ export const recoverySpanishMessages: Record<
   nativeDevelopmentUnavailable: " (no disponible en desarrollo)",
   nativeOpen: "Abrir {product}",
   nativeQuit: "Salir de {product} (el servicio sigue en segundo plano)",
+  nativeQuitStopsService:
+    "Salir de {product} (también detiene el servicio de memoria)",
   nativeLoginError:
     "No se pudo cambiar el inicio de sesión. Inténtalo de nuevo.",
   nativeMoveTitle: "Arrastra MemHub a la carpeta Aplicaciones primero",