fix(sdk): intention dedup switch also gates write-batch dedup

When intention_dedup_enabled is off, no intention dedup should run, but
the writer's batch dedup still dropped near-duplicate intentions from
one extraction. Gate it on the same switch. Its threshold stays on
MEMORY_DEDUP_THRESHOLD.

Also skip the embedding backfill when dedup is off, since only dedup
uses it, and fall back to the env default on an invalid configured
threshold so a bad value cannot fail the read.

Refs #241

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

CHANGELOG.md

@@ -4,6 +4,15 @@ Hy Memory and MemHub are versioned and released independently.
 
 ## Unreleased
 
+- SDK: 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 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 |

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

@@ -635,6 +635,7 @@ 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 +661,11 @@ 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

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

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

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

@@ -2,11 +2,10 @@
  * `memhub settings language [<code>|system]`.
  *
  * The display language the App reports to the Runtime (`ui_language`), and
- * 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
+ * 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
  * finishes in the old language, the next ones use the new one. The App sends
  * its own choice again whenever it changes there.
  */
@@ -163,14 +162,14 @@ export function renderLanguageText(document: LanguageDocument): string {
   const lines = [
     `界面语言：${
       state.ui_language === null
-        ? "未设置（SDK 自动识别）"
+        ? "跟随系统（未选择）"
         : `${state.ui_language}（${NAMES[state.ui_language]}）`
     }`,
     `SDK 提示语言：${sdkText(state.sdk_language)}`,
   ];
   if (document.state === "ok") {
     lines.push(
-      `可选：${UI_LANGUAGES.join("、")}、system。任一语言（包括 zh-Hans、en）都会让 SDK 使用该语言；system 不指定语言，SDK 自动识别中文或英文。`,
+      `可选：${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。`,
     );
   }
   if (document.state === "unchanged") lines.push("没有需要改动的设置。");

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

@@ -766,7 +766,7 @@ class PipelineStatus(BaseModel):
     #: default; empty while every feature is at its default.
     features: dict[MemoryFeatureName, bool] = Field(default_factory=dict)
     #: The display language the App last reported (`ui_language`); null =
-    #: none set (the App sends the language it shows, even following the system).
+    #: never chosen or "follow 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 +777,9 @@ class UiLanguageState(BaseModel):
 
     model_config = ConfigDict(extra="forbid")
 
-    #: What the App reported; null = none set (CLI/API-only, or `system`).
+    #: What the App reported; null = never chosen or "follow the system".
     ui_language: UiLanguage | None
-    #: What SDK clients are built with: `auto` (no language set: the SDK
+    #: What SDK clients are built with: `auto` (zh-Hans or no choice: the SDK
     #: detects zh/en, as before) or the code passed as `MemoryConfig.language`.
     sdk_language: str
     languages: tuple[UiLanguage, ...] = UI_LANGUAGES
@@ -4616,9 +4616,9 @@ def create_app(
     async def put_ui_language(request: UiLanguageUpdate) -> UiLanguageChange:
         """Record the App's display language; one global setting, not per user.
 
-        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
+        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
         SDK clients like a feature change: a write in flight finishes in the
         old language. Nothing stored is migrated and no collection is renamed.
         """

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

@@ -367,8 +367,8 @@ 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 (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
+    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
     the collection identity never depends on it.
     """
     if language is not None:

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 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.
+    #: 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.
     ui_language: UiLanguage | None = None
 
     @field_validator("sources")

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

@@ -3,19 +3,14 @@
 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 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.
+absent (never chosen, or "follow the system") means no explicit choice.
 
 The owner's rule for the SDK:
 
-- 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.
+- 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.
 
 The language never names a collection; a change rebuilds the SDK handles the
 way a mode or feature change does (#218 use count).
@@ -56,6 +51,8 @@ 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"
 
@@ -69,9 +66,8 @@ 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.
-
-    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)
+    """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

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 (#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
+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
 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 is passed to the SDK, zh-Hans included.
-PASSED = ("en", "zh-Hans", "zh-Hant", "ja", "es", "de", "pt", "fr", "ko", "ru", "id")
+#: Every code except zh-Hans is passed to the SDK.
+PASSED = ("en", "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 PASSED == UI_LANGUAGES
+    assert ("en", "zh-Hans", *PASSED[1:]) == 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"
@@ -60,20 +60,19 @@ def test_eleven_codes_and_the_legacy_chinese_code() -> None:
     assert normalize_ui_language(None) is None
 
 
-def test_only_an_unset_language_leaves_the_sdk_to_detect() -> None:
+def test_only_zh_hans_and_no_choice_leave_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_no_language_builds_the_config_of_before(tmp_path) -> None:
+def test_zh_hans_and_no_choice_build_the_config_of_before(tmp_path) -> None:
+    before = repr(dataclasses.asdict(_config(tmp_path, None)))
     assert _config(tmp_path, None).language is None
-    assert _config(tmp_path, sdk_language("zh-Hans")).language == "zh-Hans"
+    assert repr(dataclasses.asdict(_config(tmp_path, sdk_language("zh-Hans")))) == before
 
 
 @pytest.mark.parametrize("code", PASSED)
@@ -283,31 +282,17 @@ 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 is passed explicitly: Chinese prompts, handles rebuilt (#243).
+        # zh-Hans: recorded, but the SDK still detects zh/en; nothing rebuilt.
         body = (
             await client.put("/api/v1/settings/ui-language", json={"ui_language": "zh-Hans"})
         ).json()
-        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"]
+        assert body == {**current, "ui_language": "zh-Hans", "rebuilt": False}
+        assert retired == [] and reads.current_language() is None
 
         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 == ["zh-Hans", "ja"]
+        assert retired == ["ja"]
 
         # An explicit English choice forces English prompts.
         body = (await client.put("/api/v1/settings/ui-language", json={"ui_language": "en"})).json()
@@ -317,7 +302,7 @@ 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"
 
-        # Unset (CLI `settings language system`): auto again.
+        # Back to "follow the 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/desktop/src/build-identity-config.test.ts

@@ -15,13 +15,9 @@ 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).toContain(
-    "const releaseCommit = resolveReleaseCommit(process.env.ONE_MEMORY_COMMIT)",
+  expect(config).toMatch(
+    /process\.env\.ONE_MEMORY_COMMIT\?\.trim\(\) \|\| readSourceCommit\(\)/,
   );
-  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 { GuiLocale, LanguageSnapshot } from "@one-memory/i18n";
+import type { LanguageSnapshot } from "@one-memory/i18n";
 import { describe, expect, it, vi } from "vitest";
 import { coreUiLanguage, installCoreLanguageSync } from "./core-language-sync";
 
@@ -21,16 +21,11 @@ function source(initial: LanguageSnapshot) {
 const settle = () => new Promise((resolve) => setTimeout(resolve, 0));
 
 describe("Core language sync", () => {
-  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("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("sends the stored choice once at launch, then every change", async () => {
@@ -43,33 +38,29 @@ describe("Core language sync", () => {
     await settle();
     language.change({ preference: "system", locale: "en", revision: 2 });
     await settle();
-    expect(send.mock.calls).toEqual([["es"], ["ja"], ["en"]]);
+    expect(send.mock.calls).toEqual([["es"], ["ja"], [null]]);
     dispose();
     language.change({ preference: "de", locale: "de", revision: 3 });
     await settle();
     expect(send).toHaveBeenCalledTimes(3);
   });
 
-  it("an untouched install sends the system language the GUI shows", async () => {
+  it("an untouched install sends null, which leaves the SDK on auto", async () => {
     const language = source({
       preference: "system",
-      locale: "zh-Hans",
+      locale: "ja",
       revision: 0,
     });
     const send = vi.fn(async () => {});
     installCoreLanguageSync({ language, send });
     await settle();
-    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);
+    expect(send.mock.calls).toEqual([[null]]);
   });
 
   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) => Promise<void>>()
+      .fn<(value: string | null) => Promise<void>>()
       .mockRejectedValueOnce(new Error("core_unavailable"))
       .mockResolvedValue(undefined);
     const reportError = vi.fn();

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

@@ -1,37 +1,35 @@
-import type { GuiLocale, LanguageSnapshot } from "@one-memory/i18n";
+import type { GuiLocale, LanguagePreference } from "@one-memory/i18n";
 import type { NativeLanguageSource } from "./native-language";
 
-/**
- * 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;
+/** What Core is told: a code, or null for "follow the system". */
+export function coreUiLanguage(
+  preference: LanguagePreference,
+): GuiLocale | null {
+  return preference === "system" ? null : preference;
 }
 
 /**
- * Keep Core's `ui_language` setting on the display language the GUI shows.
+ * Keep Core's `ui_language` setting on the display language a person chose.
  *
- * 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.
+ * 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.
  */
 export function installCoreLanguageSync(options: {
   language: NativeLanguageSource;
-  send(uiLanguage: GuiLocale): Promise<void>;
+  send(uiLanguage: GuiLocale | null): Promise<void>;
   reportError?(error: unknown): void;
 }): () => void {
   let closed = false;
-  let sent: GuiLocale | undefined;
+  let sent: GuiLocale | null | undefined;
   let queue: Promise<void> = Promise.resolve();
   const push = () => {
     queue = queue.then(async () => {
       if (closed) return;
-      const value = coreUiLanguage(options.language.read());
+      const value = coreUiLanguage(options.language.read().preference);
       if (value === sent) return;
       try {
         await options.send(value);

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

@@ -526,22 +526,7 @@ describe("hourly isolated desktop launch", () => {
     expect(resolvePackagedBuildNumber("-1")).toBeUndefined();
     expect(resolvePackagedBuildNumber(undefined, "3907")).toBe(3907);
     expect(resolvePackagedBuildNumber("3908", "3907")).toBe(3908);
-  });
-
-  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();
+    expect(resolvePackagedCommit(undefined, "388fd0e9")).toBe("388fd0e9");
+    expect(resolvePackagedCommit("not-a-sha", "388fd0e9")).toBe("388fd0e9");
   });
 });

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

@@ -143,12 +143,6 @@ 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,
@@ -156,7 +150,7 @@ export function resolvePackagedCommit(
   for (const value of [environmentValue, embeddedValue]) {
     if (typeof value !== "string") continue;
     const trimmed = value.trim();
-    if (/^[0-9a-f]{40}$/i.test(trimmed)) return trimmed.toLowerCase();
+    if (/^[0-9a-f]{7,40}$/i.test(trimmed)) return trimmed;
   }
   return undefined;
 }

memhub/apps/desktop/tsup.config.ts

@@ -11,20 +11,8 @@ const { resolveBuildNumber, resolveBuildVersion } =
   };
 const releaseVersion = resolveBuildVersion(process.env);
 const releaseBuildNumber = resolveBuildNumber(process.env);
-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();
-}
+const releaseCommit =
+  process.env.ONE_MEMORY_COMMIT?.trim() || readSourceCommit();
 
 function readSourceCommit(): string {
   try {

memhub/docs/cli/EXPERIENCE.md

@@ -189,14 +189,14 @@ 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   # 清除设置（不指定 SDK 语言）
+node apps/cli/dist/one-memory.cjs settings language system   # 跟随系统（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 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。
+- 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。
 - 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；`zh-Hans` 用户显示 `zh-Hans`）。API：`GET`/`PUT /api/v1/settings/ui-language`。
+- `status --json` 的 `pipeline.ui_language` / `pipeline.sdk_language`（`auto` 或语言代码）。API：`GET`/`PUT /api/v1/settings/ui-language`。
 
 ## 8. 召回（recall）
 

tests/test_intention_dedup_switch.py

@@ -0,0 +1,346 @@
+# -*- coding: utf-8 -*-
+"""
+Intention（L7）读侧判重开关（issue #241）。
+
+覆盖：
+  1. 默认开启：行为不变，复本只返回最早一条，其余异步删库；
+  2. 关闭：不隐藏、不删除，两条意图都返回；
+  3. 阈值生效：cosine 低于阈值不判重，高于阈值判重；
+  4. reader 按 client 的 MemoryConfig.recall 读取开关/阈值，而非调用时的 env；
+  5. MemoryConfig 默认值与 env 回退；
+  6. 写入侧批内判重同样受开关控制；阈值不影响写入侧；
+  7. 关闭时不为判重补拉 embedding；配置阈值非法时不影响召回。
+"""
+
+from __future__ import annotations
+
+import uuid
+from datetime import datetime
+
+import pytest
+
+from hy_memory.config import MemoryConfig
+from hy_memory.pipelines.base import ReadRequest
+from hy_memory.pipelines._retrieval.intention import recall_intentions
+
+from tests.test_intention_dedup import (
+    _FakeVectorStore,
+    _make_intention_node,
+    _run,
+)
+
+
+_MA = datetime(2025, 8, 6)
+_VU = datetime(2025, 8, 31, 23, 59)
+_NOW = datetime(2025, 8, 6, 12, 0)
+
+
+def _unit(vec):
+    n = sum(x * x for x in vec) ** 0.5 or 1.0
+    return [x / n for x in vec]
+
+
+def _seed_project_pair(vs, *, emb_a, emb_b):
+    """A / B 两个项目的近似意图：同 user/agent/同天/同截止日。A 更早写入。"""
+    a = _make_intention_node(
+        "A 项目每周一触发发布前校验流程", memory_at=_MA, valid_until=_VU,
+        gmt_created=datetime(2025, 8, 1), embedding=emb_a,
+    )
+    b = _make_intention_node(
+        "B 项目每周一触发发布前校验流程", memory_at=_MA, valid_until=_VU,
+        gmt_created=datetime(2025, 8, 2), embedding=emb_b,
+    )
+    _run(vs.upsert(a))
+    _run(vs.upsert(b))
+    return a, b
+
+
+# ============================================================================
+# recall_intentions 参数
+# ============================================================================
+
+
+def test_default_on_keeps_earliest_and_deletes_duplicate():
+    vs = _FakeVectorStore()
+    emb = _unit([1.0, 0.0])
+    a, b = _seed_project_pair(vs, emb_a=emb, emb_b=list(emb))
+    stats = {}
+    result = _run(recall_intentions(
+        vs, emb, user_ids=["u1"], limit=10, now=_NOW, stats_out=stats,
+    ))
+    assert [h["node_id"] for h in result] == [a.node_id]
+    assert vs.delete_calls == [b.node_id]
+    assert stats["dedup_enabled"] is True
+    assert stats["dedup_dropped"] == 1
+
+
+def test_off_returns_both_and_deletes_nothing():
+    vs = _FakeVectorStore()
+    emb = _unit([1.0, 0.0])
+    a, b = _seed_project_pair(vs, emb_a=emb, emb_b=list(emb))
+    stats = {}
+    result = _run(recall_intentions(
+        vs, emb, user_ids=["u1"], limit=10, now=_NOW, stats_out=stats,
+        dedup_enabled=False,
+    ))
+    assert {h["node_id"] for h in result} == {a.node_id, b.node_id}
+    assert vs.delete_calls == []
+    assert stats["dedup_enabled"] is False
+    assert stats["dedup_dropped"] == 0
+
+
+def test_threshold_respected():
+    # cosine(a, b) = 0.9
+    emb_a = _unit([1.0, 0.0])
+    emb_b = _unit([0.9, (1 - 0.81) ** 0.5])
+
+    # 默认 0.95 → 0.9 不算复本
+    vs = _FakeVectorStore()
+    _seed_project_pair(vs, emb_a=emb_a, emb_b=emb_b)
+    result = _run(recall_intentions(
+        vs, emb_a, user_ids=["u1"], limit=10, now=_NOW, dedup_threshold=0.95,
+    ))
+    assert len(result) == 2
+    assert vs.delete_calls == []
+
+    # 调低到 0.85 → 判重，删较晚的 B
+    vs = _FakeVectorStore()
+    a, b = _seed_project_pair(vs, emb_a=emb_a, emb_b=emb_b)
+    stats = {}
+    result = _run(recall_intentions(
+        vs, emb_a, user_ids=["u1"], limit=10, now=_NOW,
+        dedup_threshold=0.85, stats_out=stats,
+    ))
+    assert [h["node_id"] for h in result] == [a.node_id]
+    assert vs.delete_calls == [b.node_id]
+    assert stats["dedup_threshold"] == 0.85
+
+
+def test_explicit_threshold_wins_over_env(monkeypatch):
+    monkeypatch.setenv("MEMORY_DEDUP_THRESHOLD", "0.5")
+    emb_a = _unit([1.0, 0.0])
+    emb_b = _unit([0.9, (1 - 0.81) ** 0.5])
+    vs = _FakeVectorStore()
+    _seed_project_pair(vs, emb_a=emb_a, emb_b=emb_b)
+    result = _run(recall_intentions(
+        vs, emb_a, user_ids=["u1"], limit=10, now=_NOW, dedup_threshold=0.95,
+    ))
+    assert len(result) == 2
+    assert vs.delete_calls == []
+
+
+def test_off_skips_embedding_backfill():
+    vs = _FakeVectorStore()
+    emb = _unit([1.0, 0.0])
+    _seed_project_pair(vs, emb_a=emb, emb_b=list(emb))
+
+    backfill_calls = []
+
+    async def _get_embeddings(ids):
+        backfill_calls.append(ids)
+        return {}
+
+    vs.get_embeddings = _get_embeddings
+    for n in vs._nodes.values():
+        n.embedding = None
+    result = _run(recall_intentions(
+        vs, emb, user_ids=["u1"], limit=10, now=_NOW, dedup_enabled=False,
+    ))
+    assert len(result) == 2
+    assert backfill_calls == []
+
+
+def test_invalid_threshold_degrades_to_env_default(monkeypatch):
+    monkeypatch.delenv("MEMORY_DEDUP_THRESHOLD", raising=False)
+    vs = _FakeVectorStore()
+    emb = _unit([1.0, 0.0])
+    a, b = _seed_project_pair(vs, emb_a=emb, emb_b=list(emb))
+    stats = {}
+    result = _run(recall_intentions(
+        vs, emb, user_ids=["u1"], limit=10, now=_NOW, stats_out=stats,
+        dedup_threshold="not-a-number",
+    ))
+    assert [h["node_id"] for h in result] == [a.node_id]
+    assert stats["dedup_threshold"] == 0.95
+
+
+# ============================================================================
+# 写入侧批内判重
+# ============================================================================
+
+
+class _SameVectorEmbed:
+    """所有文本同一向量：cosine=1，开启判重时必判为复本。"""
+
+    async def embed_batch(self, texts):
+        return [_unit([1.0, 0.0]) for _ in texts]
+
+    async def embed_queued(self, text):
+        return _unit([1.0, 0.0])
+
+
+def _store_batch(config_recall):
+    from hy_memory.pipelines.base import WriteRequest
+    from hy_memory.pipelines.writer import MemoryWriter
+
+    cfg = MemoryConfig.from_dict({"recall": config_recall})
+    vs = _FakeVectorStore()
+    writer = MemoryWriter(cfg, embed_service=_SameVectorEmbed(), vector_store=vs)
+    req = WriteRequest(
+        content="", messages=[], user_id="u1", agent_id="a1",
+        session_id="s1", request_id=uuid.uuid4().hex,
+    )
+    intentions = [
+        {"content": "A 项目每周一触发发布前校验流程", "tags": [], "valid_until": None},
+        {"content": "B 项目每周一触发发布前校验流程", "tags": [], "valid_until": None},
+    ]
+    return _run(writer._store_intentions(intentions, req, vs, req.request_id)), vs
+
+
+def test_write_batch_dedup_default_on_unchanged():
+    ids, vs = _store_batch({})
+    assert len(ids) == 1
+    assert [n.content for n in vs._nodes.values()] == [
+        "A 项目每周一触发发布前校验流程",
+    ]
+
+
+def test_write_batch_dedup_off_stores_both():
+    ids, vs = _store_batch({"intention_dedup_enabled": False})
+    assert len(ids) == 2
+    assert len(vs._nodes) == 2
+
+
+def test_read_threshold_does_not_change_write_batch_dedup(monkeypatch):
+    """intention_dedup_threshold 只管读侧；写入侧仍取 MEMORY_DEDUP_THRESHOLD。"""
+    monkeypatch.delenv("MEMORY_DEDUP_THRESHOLD", raising=False)
+    ids, _ = _store_batch({"intention_dedup_threshold": 1.5})
+    assert len(ids) == 1
+
+
+# ============================================================================
+# MemoryConfig
+# ============================================================================
+
+
+def test_config_defaults(monkeypatch):
+    for k in (
+        "MEMORY_INTENTION_DEDUP_ENABLED",
+        "MEMORY_INTENTION_DEDUP_THRESHOLD",
+        "MEMORY_DEDUP_THRESHOLD",
+    ):
+        monkeypatch.delenv(k, raising=False)
+    cfg = MemoryConfig()
+    assert cfg.recall.intention_dedup_enabled is True
+    assert cfg.recall.intention_dedup_threshold == 0.95
+
+
+def test_config_env_fallbacks(monkeypatch):
+    monkeypatch.setenv("MEMORY_INTENTION_DEDUP_ENABLED", "false")
+    monkeypatch.setenv("MEMORY_DEDUP_THRESHOLD", "0.9")
+    monkeypatch.delenv("MEMORY_INTENTION_DEDUP_THRESHOLD", raising=False)
+    cfg = MemoryConfig()
+    assert cfg.recall.intention_dedup_enabled is False
+    # 未设专用阈值 → 回退共享 MEMORY_DEDUP_THRESHOLD（兼容旧部署）
+    assert cfg.recall.intention_dedup_threshold == 0.9
+
+    monkeypatch.setenv("MEMORY_INTENTION_DEDUP_THRESHOLD", "0.8")
+    assert MemoryConfig().recall.intention_dedup_threshold == 0.8
+
+
+def test_config_from_dict_overrides_env(monkeypatch):
+    monkeypatch.setenv("MEMORY_INTENTION_DEDUP_ENABLED", "true")
+    cfg = MemoryConfig.from_dict({"recall": {
+        "intention_dedup_enabled": False,
+        "intention_dedup_threshold": 0.99,
+    }})
+    assert cfg.recall.intention_dedup_enabled is False
+    assert cfg.recall.intention_dedup_threshold == 0.99
+    assert cfg.to_dict()["recall"]["intention_dedup_enabled"] is False
+
+
+# ============================================================================
+# reader：按 client 配置，而不是调用时的 env
+# ============================================================================
+
+
+def _reader_for(enabled: bool, vs):
+    from hy_memory.pipelines.reader_hybrid import HybridReadPipeline
+
+    cfg = MemoryConfig.from_dict({
+        "vector_store": {
+            "provider": "chroma",
+            "collection_name": f"t_intent_sw_{uuid.uuid4().hex[:8]}",
+            "embedding_dims": 2,
+        },
+        "recall": {"intention_dedup_enabled": enabled},
+    })
+    reader = HybridReadPipeline(cfg, vector_store=vs)
+    reader._vector_store = vs
+    reader._vector_store_initialized = True
+    return reader
+
+
+async def _no_keyword_hits(**kw):
+    return []
+
+
+def _read_project_pair(enabled: bool):
+    """经 reader 完整读路径召回 A/B 两条近似意图；返回 (返回的意图 id, 删库调用, a, b)。"""
+    vs = _FakeVectorStore()
+    vs.keyword_search = _no_keyword_hits
+    emb = _unit([1.0, 0.0])
+    a, b = _seed_project_pair(vs, emb_a=emb, emb_b=list(emb))
+    # 读路径用真实 now：让两条都未过期且同一天
+    today = datetime.now()
+    for n in (a, b):
+        n.memory_at = today
+        n.valid_until = None
+    reader = _reader_for(enabled, vs)
+    _run(reader.initialize())
+    resp = _run(reader.read(ReadRequest(
+        query="发布前校验", query_embedding=emb,
+        user_ids=["u1"], agent_ids=["a1"], limit=10, intention_limit=5,
+    )))
+    ids = {
+        m["memory_id"] for m in resp.memories
+        if m.get("layer") == "l7_intention"
+    }
+    return ids, list(vs.delete_calls), a, b
+
+
+@pytest.mark.parametrize("env_value", ["true", "false"])
+def test_reader_uses_per_client_config_not_env(monkeypatch, env_value):
+    """调用时的 env 与 client 配置无关：两个 client 一开一关，各自生效。"""
+    monkeypatch.setenv("MEMORY_INTENTION_DEDUP_ENABLED", env_value)
+    monkeypatch.setenv("MEMORY_DEDUP_THRESHOLD", "0.0")
+
+    ids_on, deleted_on, a, b = _read_project_pair(True)
+    assert ids_on == {a.node_id}
+    assert deleted_on == [b.node_id]
+
+    ids_off, deleted_off, a, b = _read_project_pair(False)
+    assert ids_off == {a.node_id, b.node_id}
+    assert deleted_off == []
+
+
+def test_reader_passes_client_threshold(monkeypatch):
+    monkeypatch.setenv("MEMORY_DEDUP_THRESHOLD", "0.1")
+    seen = []
+
+    async def _spy(*args, **kwargs):
+        seen.append(kwargs)
+        return []
+
+    monkeypatch.setattr("hy_memory.pipelines.reader_base.recall_intentions", _spy)
+    vs = _FakeVectorStore()
+    vs.keyword_search = _no_keyword_hits
+    reader = _reader_for(True, vs)
+    reader.config.recall.intention_dedup_threshold = 0.97
+    _run(reader.initialize())
+    _run(reader.read(ReadRequest(
+        query="发布前校验", query_embedding=_unit([1.0, 0.0]),
+        user_ids=["u1"], agent_ids=["a1"], limit=10, intention_limit=5,
+    )))
+    assert seen and seen[0]["dedup_enabled"] is True
+    assert seen[0]["dedup_threshold"] == 0.97