From eb3b4e55457c7c37d87b52a6b6eac6c4223ce5f7 Mon Sep 17 00:00:00 2001 From: "jinli.yl" Date: Thu, 20 Aug 2026 15:57:33 +0800 Subject: [PATCH] fix: recover embedding after transient health failure --- docs/en/memory_search.md | 4 + docs/zh/memory_search.md | 3 + .../embedding_store/base_embedding_store.py | 15 ++- .../embedding_store/local_embedding_store.py | 26 ++++- .../file_store/faiss_local_file_store.py | 11 +- .../components/file_store/local_file_store.py | 99 +++++++++++++---- .../file_store/zvec_local_file_store.py | 12 +- reme/config/beam.yaml | 1 + reme/config/daily_cookbook.yaml | 1 + reme/config/default.yaml | 1 + reme/config/lme.yaml | 1 + tests/unit/test_file_store_consistency.py | 105 +++++++++++++++++- tests/unit/test_local_embedding_store.py | 43 +++++++ 13 files changed, 284 insertions(+), 38 deletions(-) diff --git a/docs/en/memory_search.md b/docs/en/memory_search.md index 3beb80b4..c4fc8437 100644 --- a/docs/en/memory_search.md +++ b/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`: diff --git a/docs/zh/memory_search.md b/docs/zh/memory_search.md index 502e2bec..f65900e6 100644 --- a/docs/zh/memory_search.md +++ b/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： diff --git a/reme/components/embedding_store/base_embedding_store.py b/reme/components/embedding_store/base_embedding_store.py index cc3cbed5..a6f9e9cc 100644 --- a/reme/components/embedding_store/base_embedding_store.py +++ b/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: diff --git a/reme/components/embedding_store/local_embedding_store.py b/reme/components/embedding_store/local_embedding_store.py index 930d9af4..f08ff531 100644 --- a/reme/components/embedding_store/local_embedding_store.py +++ b/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 diff --git a/reme/components/file_store/faiss_local_file_store.py b/reme/components/file_store/faiss_local_file_store.py index 5fdf7846..4122cb59 100644 --- a/reme/components/file_store/faiss_local_file_store.py +++ b/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 diff --git a/reme/components/file_store/local_file_store.py b/reme/components/file_store/local_file_store.py index 889a792a..95cc320a 100644 --- a/reme/components/file_store/local_file_store.py +++ b/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] = [] diff --git a/reme/components/file_store/zvec_local_file_store.py b/reme/components/file_store/zvec_local_file_store.py index 80129eed..3dbd3457 100644 --- a/reme/components/file_store/zvec_local_file_store.py +++ b/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. diff --git a/reme/config/beam.yaml b/reme/config/beam.yaml index 22bd9fe4..223f4710 100644 --- a/reme/config/beam.yaml +++ b/reme/config/beam.yaml @@ -497,6 +497,7 @@ components: default: backend: local as_embedding: default + health_check_timeout: 5.0 as_llm: default: diff --git a/reme/config/daily_cookbook.yaml b/reme/config/daily_cookbook.yaml index aa15e890..d9b340bf 100644 --- a/reme/config/daily_cookbook.yaml +++ b/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: diff --git a/reme/config/default.yaml b/reme/config/default.yaml index 95a0bad5..d384d73d 100644 --- a/reme/config/default.yaml +++ b/reme/config/default.yaml @@ -740,6 +740,7 @@ components: # default: # backend: local # as_embedding: default +# health_check_timeout: 5.0 as_llm: default: diff --git a/reme/config/lme.yaml b/reme/config/lme.yaml index 2c823946..3f478d8d 100644 --- a/reme/config/lme.yaml +++ b/reme/config/lme.yaml @@ -490,6 +490,7 @@ components: default: backend: local as_embedding: default + health_check_timeout: 5.0 as_llm: default: diff --git a/tests/unit/test_file_store_consistency.py b/tests/unit/test_file_store_consistency.py index cd61cbdd..83cac4e0 100644 --- a/tests/unit/test_file_store_consistency.py +++ b/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()) diff --git a/tests/unit/test_local_embedding_store.py b/tests/unit/test_local_embedding_store.py index 5ac1d925..47f663a5 100644 --- a/tests/unit/test_local_embedding_store.py +++ b/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."""