fix: recover embedding after transient health failure

docs/en/memory_search.md

@@ -117,6 +117,10 @@ Out of the box, search therefore uses primarily BM25 plus link expansion. After
 `SearchStep` runs vector and keyword recall together. Additionally, switching the `file_store` `backend` from `local` to
 `faiss` upgrades vector retrieval from a linear scan to a FAISS HNSW index, offering faster recall at scale.
 
+The embedding store accepts `health_check_timeout` for its startup probe. A temporary failure skips the current vector
+backfill while keeping BM25 available; a later successful provider request resumes the missing-vector backfill
+automatically.
+
 ## How to Search
 
 The `search` Job is also configured in `default.yaml`:

docs/zh/memory_search.md

@@ -106,6 +106,9 @@ file_store:
 所以开箱搜索主要是 BM25 + 链接展开。把 `embedding_store: default` 打开后，`SearchStep` 会同时跑向量召回和关键词召回。此时若将
 `file_store` 的 `backend` 从 `local` 改为 `faiss`，向量检索会从线性扫描升级为 FAISS HNSW 索引，在大规模 chunk 场景下召回效率更高。
 
+Embedding store 可通过 `health_check_timeout` 配置启动探测。临时失败只会跳过本次向量回填，BM25 仍可使用；
+后续真实请求成功后会自动恢复缺失向量的回填。
+
 ## 怎么搜索
 
 `search` Job 也是在 `default.yaml` 中配置：

reme/components/embedding_store/base_embedding_store.py

@@ -1,6 +1,7 @@
 """Base embedding store with abstract interface for caching and retrieval."""
 
 from abc import abstractmethod
+import math
 import unicodedata
 
 import numpy as np
@@ -25,14 +26,26 @@ class BaseEmbeddingStore(BaseComponent):
         max_input_length: int = 8192,
         max_retries: int = 3,
         quota_retry_delay: float | None = None,
+        health_check_timeout: float = 5.0,
         **kwargs,
     ):
         super().__init__(**kwargs)
+        if (
+            isinstance(health_check_timeout, bool)
+            or not isinstance(health_check_timeout, (int, float))
+            or not math.isfinite(health_check_timeout)
+            or health_check_timeout <= 0
+        ):
+            raise ValueError("health_check_timeout must be finite and greater than 0")
         self.max_batch_size = max_batch_size
         self.max_input_length = max_input_length
         self.max_retries = max_retries
         self.quota_retry_delay = quota_retry_delay
+        self.health_check_timeout = health_check_timeout
         self.is_healthy: bool = True
+        # Monotonic signal used by file stores to distinguish real provider
+        # recovery from cache-only results.
+        self.provider_success_count: int = 0
 
     def _truncate(self, text: str) -> str:
         """Truncate text using a CJK-aware character budget.
@@ -57,7 +70,7 @@ class BaseEmbeddingStore(BaseComponent):
         return text
 
     @abstractmethod
-    async def health_check(self, timeout: float = 2.0) -> bool:
+    async def health_check(self, timeout: float | None = None) -> bool:
         """Probe the provider; sets and returns is_healthy."""
 
     async def get_embedding(self, input_text: str, **kwargs) -> np.ndarray | None:

reme/components/embedding_store/local_embedding_store.py

@@ -68,8 +68,12 @@ class LocalEmbeddingStore(BaseEmbeddingStore):
     async def _close(self) -> None:
         await self.dump()
 
-    async def health_check(self, timeout: float = 5.0) -> bool:
+    async def health_check(self, timeout: float | None = None) -> bool:
+        timeout = self.health_check_timeout if timeout is None else timeout
+        if not isinstance(timeout, (int, float)) or not np.isfinite(timeout) or timeout <= 0:
+            raise ValueError("timeout must be finite and greater than 0")
         tag = f"[EMBEDDING HEALTH CHECK] name={self.name} workspace_dir={self.workspace_path}"
+        started_at = asyncio.get_running_loop().time()
         try:
             # Provider construction may synchronously import an SDK and build
             # its HTTP client. Keep that one-time work outside the request
@@ -82,13 +86,18 @@ class LocalEmbeddingStore(BaseEmbeddingStore):
             if len(result[0]) != self.dimensions:
                 raise RuntimeError(f"embedding dimension mismatch: {len(result[0])} != {self.dimensions}")
             self.is_healthy = True
-            self.logger.info(f"{tag} -> OK")
+            elapsed = asyncio.get_running_loop().time() - started_at
+            self.logger.info(f"{tag} -> OK timeout={timeout}s elapsed={elapsed:.3f}s")
         except asyncio.TimeoutError:
             self.is_healthy = False
-            self.logger.error(f"{tag} -> FAIL timeout({timeout}s)")
-        except Exception as e:
+            elapsed = asyncio.get_running_loop().time() - started_at
+            self.logger.error(f"{tag} -> FAIL timeout={timeout}s elapsed={elapsed:.3f}s error=timeout({timeout}s)")
+        except Exception as exc:  # Provider SDKs expose many exception types.
             self.is_healthy = False
-            self.logger.error(f"{tag} -> FAIL {type(e).__name__}: {e}")
+            elapsed = asyncio.get_running_loop().time() - started_at
+            self.logger.error(
+                f"{tag} -> FAIL timeout={timeout}s elapsed={elapsed:.3f}s error={type(exc).__name__}: {exc}",
+            )
         return self.is_healthy
 
     # -- Public API --
@@ -143,6 +152,11 @@ class LocalEmbeddingStore(BaseEmbeddingStore):
         if bad_dims:
             details = ", ".join(f"{count} with dim {dim}" for dim, count in sorted(bad_dims.items()))
             self.logger.error(f"Embedding dimension mismatch in batch: expected {self.dimensions}; rejected {details}")
+        if out:
+            self.provider_success_count += 1
+            self.is_healthy = True
+        else:
+            self.is_healthy = False
         return out
 
     async def _call_with_retry(self, texts: list[str], **kwargs) -> list[list[float] | None] | None:
@@ -166,7 +180,9 @@ class LocalEmbeddingStore(BaseEmbeddingStore):
                     await asyncio.sleep(self.quota_retry_delay)
                     continue
                 self.logger.exception("Embedding request failed")
+                self.is_healthy = False
                 return None
+        self.is_healthy = False
         return None
 
     @staticmethod

reme/components/file_store/faiss_local_file_store.py

@@ -625,26 +625,29 @@ class FaissLocalFileStore(LocalFileStore):
     # -- search -----------------------------------------------------------
 
     async def vector_search(self, query: str, limit: int, search_filter: dict) -> list[FileChunk]:
+        index_empty = self._faiss_index is None or self._faiss_index.ntotal == 0
         if (
             self.embedding_store is None
             or not query
             or limit <= 0
-            or self._faiss_index is None
-            or self._faiss_index.ntotal == 0
+            or (index_empty and getattr(self.embedding_store, "is_healthy", True))
         ):
             return []
 
         query_embedding = None
+        provider_success_count = self._provider_success_count()
+        was_healthy = bool(getattr(self.embedding_store, "is_healthy", True))
         try:
             query_embedding = await self.embedding_store.get_embedding(query)
         except Exception as e:
-            self._disable_embedding(f"search: {type(e).__name__}: {e}")
+            self._mark_embedding_unhealthy(f"search: {type(e).__name__}: {e}")
         if query_embedding is None or not self._embedding_dim_matches(query_embedding):
             if query_embedding is not None:
-                self._disable_embedding(
+                self._mark_embedding_unhealthy(
                     f"search: query embedding dimension {len(query_embedding)} != {self.embedding_store.dimensions}",
                 )
             return []
+        self._recover_after_real_request(provider_success_count, was_healthy, True)
 
         # get_embedding above yielded control; a concurrent clear() drops the
         # index to None once embedding is disabled, and a reindex may have swapped

reme/components/file_store/local_file_store.py

@@ -67,10 +67,12 @@ class LocalFileStore(BaseFileStore):
         self.file_chunks: dict[str, FileChunk] = {}
         self.chunks_path = self.component_metadata_path / f"file_chunks_{self.name}_{self.store_version}.jsonl.zst"
         self._embedding_backfill_task: asyncio.Task | None = None
+        self._closing = False
 
     # -- lifecycle ------------------------------------------------------------
 
     async def _start(self) -> None:
+        self._closing = False
         started_at = time.monotonic()
         self.component_metadata_path.mkdir(parents=True, exist_ok=True)
         await super()._start()
@@ -94,17 +96,57 @@ class LocalFileStore(BaseFileStore):
         )
 
     async def _close(self) -> None:
+        self._closing = True
         await self._cancel_embedding_backfill()
         await self.dump()
         self.file_chunks.clear()
         await super()._close()
 
-    def _disable_embedding(self, reason: str) -> None:
-        """Drop embedding after a runtime failure; keyword search still works."""
+    def _mark_embedding_unhealthy(self, reason: str) -> None:
+        """Record a temporary provider failure while preserving the component."""
         if self.embedding_store is None:
             return
-        self.logger.error(f"{self.name}: embedding disabled, {reason}")
-        self.embedding_store = None
+        self.embedding_store.is_healthy = False
+        self.logger.error(f"{self.name}: embedding unavailable, {reason}; keyword search remains active")
+
+    def _provider_success_count(self) -> int | None:
+        if self.embedding_store is None:
+            return None
+        value = getattr(self.embedding_store, "provider_success_count", None)
+        return value if isinstance(value, int) else None
+
+    def _recover_after_real_request(
+        self,
+        previous_count: int | None,
+        was_healthy: bool,
+        valid_result: bool,
+    ) -> None:
+        """Schedule repair when a real, non-cache provider request recovers."""
+        if self.embedding_store is None or not valid_result:
+            return
+        current_count = self._provider_success_count()
+        provider_succeeded = (
+            current_count > previous_count if current_count is not None and previous_count is not None else True
+        )
+        if not provider_succeeded:
+            return
+        self.embedding_store.is_healthy = True
+        if not was_healthy:
+            self.logger.info(f"{self.name}: embedding provider recovered; scheduling missing-vector backfill")
+            self._start_embedding_backfill(skip_health_check=True)
+
+    async def resume_embedding(self, *, verified: bool = False) -> bool:
+        """Resume a configured provider and schedule a deduplicated repair.
+
+        Embedded applications may pass ``verified=True`` after they have already
+        made a successful real provider request, avoiding a redundant ping.
+        """
+        if self.embedding_store is None or self._closing:
+            return False
+        if verified:
+            self.embedding_store.is_healthy = True
+        self._start_embedding_backfill(skip_health_check=verified)
+        return True
 
     def _embedding_dim_matches(self, embedding: np.ndarray | None) -> bool:
         """Return whether an index embedding matches the active embedding model."""
@@ -228,9 +270,12 @@ class LocalFileStore(BaseFileStore):
             return
         self._drop_stale_embeddings(self.file_chunks.values(), "load")
 
-    def _start_embedding_backfill(self) -> None:
+    def _start_embedding_backfill(self, *, skip_health_check: bool = False) -> None:
         """Schedule startup embedding repair without delaying component readiness."""
         started_at = time.monotonic()
+        if self._closing:
+            self.logger.info(f"{self.name}: embedding backfill skipped: reason=closing")
+            return
         if not self.embedding_store:
             self.logger.info(
                 f"{self.name}: embedding backfill skipped: reason=embedding_disabled, "
@@ -250,7 +295,7 @@ class LocalFileStore(BaseFileStore):
             )
             return
         self._embedding_backfill_task = asyncio.create_task(
-            self._backfill_missing_embeddings(),
+            self._backfill_missing_embeddings(skip_health_check=skip_health_check),
             name=f"embedding-backfill:{self.name}",
         )
         self.logger.info(
@@ -285,7 +330,7 @@ class LocalFileStore(BaseFileStore):
             next_percent += _PROGRESS_LOG_PERCENT_STEP
         return next_percent
 
-    async def _backfill_missing_embeddings(self) -> None:
+    async def _backfill_missing_embeddings(self, *, skip_health_check: bool = False) -> None:
         """Background-repair persisted chunks that do not have usable vectors."""
         started_at = time.monotonic()
         if not self.embedding_store or not self.file_chunks:
@@ -313,18 +358,18 @@ class LocalFileStore(BaseFileStore):
         batch_size = max(1, int(getattr(self.embedding_store, "max_batch_size", 10)))
         self.logger.info(f"{self.name}: embedding backfill started: total={total}, batch_size={batch_size}")
         try:
-            health_check_started_at = time.monotonic()
-            is_healthy = await self.embedding_store.health_check()
-            self.logger.info(
-                f"{self.name}: embedding health check complete: healthy={is_healthy}, "
-                f"elapsed={time.monotonic() - health_check_started_at:.3f}s",
-            )
-            if not is_healthy:
-                self._disable_embedding("backfill health check failed")
-                self.logger.warning(
-                    f"{self.name}: embedding backfill failed: processed=0/{total}, reason=health check failed",
+            if not skip_health_check:
+                health_check_started_at = time.monotonic()
+                is_healthy = await self.embedding_store.health_check()
+                self.logger.info(
+                    f"{self.name}: embedding health check complete: healthy={is_healthy}, "
+                    f"elapsed={time.monotonic() - health_check_started_at:.3f}s",
                 )
-                return
+                if not is_healthy:
+                    self.logger.warning(
+                        f"{self.name}: embedding backfill skipped: processed=0/{total}, reason=health check failed",
+                    )
+                    return
 
             processed = 0
             batch_count = 0
@@ -349,7 +394,7 @@ class LocalFileStore(BaseFileStore):
             )
             raise
         except Exception as e:
-            self._disable_embedding(f"backfill: {type(e).__name__}: {e}")
+            self._mark_embedding_unhealthy(f"backfill: {type(e).__name__}: {e}")
             elapsed = time.monotonic() - started_at
             self.logger.exception(
                 f"{self.name}: embedding backfill failed: processed={processed if 'processed' in locals() else 0}/"
@@ -540,12 +585,19 @@ class LocalFileStore(BaseFileStore):
     async def _embed_pending(self, chunks: list[FileChunk]) -> None:
         if not (chunks and self.embedding_store):
             return
+        provider_success_count = self._provider_success_count()
+        was_healthy = bool(getattr(self.embedding_store, "is_healthy", True))
         try:
             await self.embedding_store.get_node_embeddings(chunks)
         except Exception as e:
-            self._disable_embedding(f"upsert: {type(e).__name__}: {e}")
+            self._mark_embedding_unhealthy(f"upsert: {type(e).__name__}: {e}")
             return
         self._drop_stale_embeddings(chunks, "upsert")
+        self._recover_after_real_request(
+            provider_success_count,
+            was_healthy,
+            any(chunk.embedding is not None for chunk in chunks),
+        )
 
     async def delete(self, path: str | list[str]) -> None:
         assert self.file_graph is not None
@@ -604,18 +656,21 @@ class LocalFileStore(BaseFileStore):
         if self.embedding_store is None or not query or limit <= 0:
             return []
 
+        provider_success_count = self._provider_success_count()
+        was_healthy = bool(getattr(self.embedding_store, "is_healthy", True))
         try:
             query_embedding = await self.embedding_store.get_embedding(query)
         except Exception as e:
-            self._disable_embedding(f"search: {type(e).__name__}: {e}")
+            self._mark_embedding_unhealthy(f"search: {type(e).__name__}: {e}")
             return []
         if query_embedding is None:
             return []
         if not self._embedding_dim_matches(query_embedding):
-            self._disable_embedding(
+            self._mark_embedding_unhealthy(
                 f"search: query embedding dimension {len(query_embedding)} != {self.embedding_store.dimensions}",
             )
             return []
+        self._recover_after_real_request(provider_success_count, was_healthy, True)
 
         top: list[tuple[float, int, FileChunk]] = []
         candidates: list[FileChunk] = []

reme/components/file_store/zvec_local_file_store.py

@@ -412,20 +412,26 @@ class ZvecLocalFileStore(LocalFileStore):
     # -- search -----------------------------------------------------------
 
     async def vector_search(self, query: str, limit: int, search_filter: dict) -> list[FileChunk]:
-        if self.embedding_store is None or not query or limit <= 0 or self._collection is None or not self._indexed_ids:
+        if self.embedding_store is None or not query or limit <= 0:
+            return []
+        index_empty = self._collection is None or not self._indexed_ids
+        if index_empty and getattr(self.embedding_store, "is_healthy", True):
             return []
 
         query_embedding = None
+        provider_success_count = self._provider_success_count()
+        was_healthy = bool(getattr(self.embedding_store, "is_healthy", True))
         try:
             query_embedding = await self.embedding_store.get_embedding(query)
         except Exception as e:
-            self._disable_embedding(f"search: {type(e).__name__}: {e}")
+            self._mark_embedding_unhealthy(f"search: {type(e).__name__}: {e}")
         if query_embedding is None or not self._embedding_dim_matches(query_embedding):
             if query_embedding is not None:
-                self._disable_embedding(
+                self._mark_embedding_unhealthy(
                     f"search: query embedding dimension {len(query_embedding)} != {self.embedding_store.dimensions}",
                 )
             return []
+        self._recover_after_real_request(provider_success_count, was_healthy, True)
 
         # get_embedding above yielded control; a concurrent clear() may have
         # swapped or dropped the collection. Re-read before dereferencing.

reme/config/beam.yaml

@@ -497,6 +497,7 @@ components:
     default:
       backend: local
       as_embedding: default
+      health_check_timeout: 5.0
 
   as_llm:
     default:

reme/config/daily_cookbook.yaml

@@ -453,6 +453,7 @@ components:
 #      as_embedding: default
 #      max_retries: 3
 #      quota_retry_delay: 60.0
+#      health_check_timeout: 5.0
 
   file_graph:
     default:

reme/config/default.yaml

@@ -740,6 +740,7 @@ components:
 #    default:
 #      backend: local
 #      as_embedding: default
+#      health_check_timeout: 5.0
 
   as_llm:
     default:

reme/config/lme.yaml

@@ -490,6 +490,7 @@ components:
     default:
       backend: local
       as_embedding: default
+      health_check_timeout: 5.0
 
   as_llm:
     default:

tests/unit/test_file_store_consistency.py

@@ -16,6 +16,7 @@ import pytest
 
 from reme.components.file_store import FaissLocalFileStore, LocalFileStore, ZvecLocalFileStore
 from reme.components.file_store import local_file_store as local_file_store_module
+from reme.components.embedding_store import LocalEmbeddingStore
 from reme.schema import FileChunk, FileNode
 from reme.utils.jsonl_zst import read_jsonl_zst, write_jsonl_zst
 
@@ -76,10 +77,38 @@ class CountingFakeEmbeddingStore(FakeEmbeddingStore):
 class UnhealthyCountingEmbeddingStore(CountingFakeEmbeddingStore):
     """Fake embedding store that fails the backfill health gate."""
 
+    def __init__(self):
+        super().__init__()
+        self.is_healthy = False
+
     async def health_check(self, _timeout: float = 2.0) -> bool:
         return False
 
 
+class RecoveringEmbeddingStore(CountingFakeEmbeddingStore):
+    """Fake provider that starts unhealthy and records real recoveries."""
+
+    def __init__(self):
+        super().__init__()
+        self.is_healthy = False
+        self.provider_success_count = 0
+        self.health_calls = 0
+
+    async def health_check(self, _timeout: float = 2.0) -> bool:
+        self.health_calls += 1
+        return False
+
+    async def get_embedding(self, input_text: str, **kwargs) -> np.ndarray:
+        self.provider_success_count += 1
+        self.is_healthy = True
+        return await super().get_embedding(input_text, **kwargs)
+
+    async def get_node_embeddings(self, nodes: list[FileChunk], **kwargs) -> list[FileChunk]:
+        self.provider_success_count += 1
+        self.is_healthy = True
+        return await super().get_node_embeddings(nodes, **kwargs)
+
+
 class HealthCountingEmbeddingStore(FakeEmbeddingStore):
     """Fake provider that records eager health checks."""
 
@@ -153,6 +182,15 @@ def _new_local_store(name, **kwargs):
     return LocalFileStore(name=name, embedding_store="", **kwargs)
 
 
+def _new_faiss_store(name, **kwargs):
+    """Construct a FAISS store when the optional backend is installed."""
+    try:
+        store = FaissLocalFileStore(name=name, embedding_store="", **kwargs)
+    except ImportError:
+        pytest.skip("faiss is not installed")
+    return store
+
+
 def _new_zvec_store(name, **kwargs):
     """Construct a zvec store with embedding disabled at bind time."""
     try:
@@ -593,7 +631,7 @@ def test_background_embedding_backfill_uses_provider_batch_size():
 
 
 def test_load_skips_backfill_when_embedding_health_check_fails():
-    """Background backfill disables embeddings before batching when the provider is unhealthy."""
+    """Background backfill preserves an unhealthy provider for later recovery."""
 
     async def go():
         with tempfile.TemporaryDirectory() as tmp, temp_chdir(tmp):
@@ -610,13 +648,73 @@ def test_load_skips_backfill_when_embedding_health_check_fails():
             await store._embedding_backfill_task
 
             assert not fake.node_embedding_calls
-            assert store.embedding_store is None
+            assert store.embedding_store is fake
+            assert fake.is_healthy is False
             assert store.file_chunks["a"].embedding is None
             await store.close()
 
     run(go())
 
 
+@pytest.mark.parametrize("store_factory", [_new_local_store, _new_faiss_store, _new_zvec_store])
+def test_search_recovery_schedules_backfill_without_another_health_check(store_factory):
+    """A successful real search request repairs historical missing vectors."""
+
+    async def go():
+        with tempfile.TemporaryDirectory() as tmp, temp_chdir(tmp):
+            store = store_factory(name="t_embedding_search_recovery")
+            await store.start()
+            await set_chunks_with_graph(store, {"a": chunk("a", "a.md", "alpha text")})
+            fake = RecoveringEmbeddingStore()
+            store.embedding_store = fake
+
+            assert await store.vector_search("alpha", 5, {}) == []
+            await store._embedding_backfill_task
+
+            assert fake.is_healthy is True
+            assert fake.health_calls == 0
+            assert fake.node_embedding_calls == [["a"]]
+            assert store.file_chunks["a"].embedding.tolist() == [1.0, 0.0]
+            assert [item.id for item in await store.vector_search("alpha", 5, {})] == ["a"]
+            await store.close()
+
+    run(go())
+
+
+def test_cache_only_search_does_not_mark_provider_recovered():
+    """Cached vectors do not prove that the remote provider is available."""
+
+    async def go():
+        with tempfile.TemporaryDirectory() as tmp, temp_chdir(tmp):
+            embedding_store = LocalEmbeddingStore(name="t_embedding_cache_only_recovery")
+            embedding_store.as_embedding = type(
+                "CachedProvider",
+                (),
+                {
+                    "dimensions": 2,
+                    "vector_space_id": "cached-provider",
+                    "__call__": lambda self, texts, **_kwargs: asyncio.sleep(
+                        0,
+                        result=[[1.0, 0.0] for _ in texts],
+                    ),
+                },
+            )()
+            await embedding_store.get_embedding("alpha")
+            embedding_store.is_healthy = False
+
+            store = LocalFileStore(name="t_embedding_cache_only_recovery", embedding_store="")
+            await store.start()
+            await set_chunks_with_graph(store, {"a": chunk("a", "a.md", "historical text")})
+            store.embedding_store = embedding_store
+
+            assert await store.vector_search("alpha", 5, {}) == []
+            assert embedding_store.is_healthy is False
+            assert store._embedding_backfill_task is None
+            await store.close()
+
+    run(go())
+
+
 @pytest.mark.parametrize("store_factory", [_new_local_store, _new_zvec_store])
 def test_load_reembeds_persisted_chunks_with_stale_embedding_dimensions(store_factory):
     """Loading persisted chunks re-embeds vectors that do not match current dimensions."""
@@ -692,7 +790,8 @@ def test_upsert_drops_wrong_dimension_from_custom_embedding_store():
 
             assert store.file_chunks["a"].embedding is None
             assert await store.vector_search("alpha", 5, {}) == []
-            assert store.embedding_store is None
+            assert store.embedding_store is not None
+            assert store.embedding_store.is_healthy is False
             await store.close()
 
     run(go())

tests/unit/test_local_embedding_store.py

@@ -6,6 +6,7 @@ import asyncio
 from types import SimpleNamespace
 
 import numpy as np
+import pytest
 
 from reme.components.as_embedding import DashScopeAsEmbedding, OllamaAsEmbedding, OpenAIAsEmbedding
 from reme.components.embedding_store.base_embedding_store import BaseEmbeddingStore
@@ -39,6 +40,20 @@ class BadHealthAsEmbedding:
         return [[1.0]]
 
 
+class FailingHealthAsEmbedding:
+    """Fake provider that records a failed health-check attempt."""
+
+    dimensions = 2
+    vector_space_id = "fakespace000"
+
+    def __init__(self):
+        self.calls = 0
+
+    async def __call__(self, _texts: list[str], **_kwargs):
+        self.calls += 1
+        raise ConnectionError("not ready")
+
+
 class FakeProviderModel:
     """Stand-in for a constructed AgentScope embedding model object."""
 
@@ -183,9 +198,37 @@ def test_health_check_starts_timeout_after_provider_initialization(monkeypatch):
         assert await store.health_check(timeout=5.0) is True
         assert events == ["initialized", "remote request"]
 
+
+def test_health_check_makes_one_attempt():
+    """A failed startup probe does not add hidden retries."""
+
+    async def go():
+        provider = FailingHealthAsEmbedding()
+        store = LocalEmbeddingStore(
+            name="t_local_embedding_health_retry",
+            health_check_timeout=3.0,
+        )
+        store.as_embedding = provider
+
+        assert await store.health_check() is False
+        assert provider.calls == 1
+
     run(go())
 
 
+@pytest.mark.parametrize(
+    ("kwargs", "message"),
+    [
+        ({"health_check_timeout": 0}, "health_check_timeout"),
+        ({"health_check_timeout": float("inf")}, "health_check_timeout"),
+    ],
+)
+def test_health_check_config_rejects_invalid_values(kwargs, message):
+    """Invalid probe policies fail during component construction."""
+    with pytest.raises(ValueError, match=message):
+        LocalEmbeddingStore(name="t_local_embedding_invalid_health_config", **kwargs)
+
+
 def test_insufficient_quota_waits_sixty_seconds_before_retry(monkeypatch):
     """Quota exhaustion uses the dedicated delay before ReMe retries."""