{"version":3,"file":"embsearch-service.d.ts","sourceRoot":"","sources":["../../../src/core/embsearch/embsearch-service.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;GAcG;AAOH,OAAO,EACN,KAAK,eAAe,EAGpB,KAAK,sBAAsB,EAC3B,KAAK,qBAAqB,EAC1B,MAAM,aAAa,CAAC;AAuDrB,MAAM,MAAM,cAAc,GACvB;IAAE,KAAK,EAAE,MAAM,CAAA;CAAE,GACjB;IAAE,KAAK,EAAE,SAAS,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,GACpC;IAAE,KAAK,EAAE,aAAa,CAAC;IAAC,aAAa,EAAE,MAAM,CAAC;IAAC,UAAU,EAAE,MAAM,GAAG,IAAI,CAAA;CAAE,GAC1E;IAAE,KAAK,EAAE,UAAU,CAAC;IAAC,IAAI,EAAE,MAAM,CAAC;IAAC,KAAK,EAAE,MAAM,CAAA;CAAE,GAClD;IAAE,KAAK,EAAE,OAAO,CAAC;IAAC,UAAU,EAAE,MAAM,CAAA;CAAE,GACtC;IAAE,KAAK,EAAE,aAAa,CAAC;IAAC,MAAM,EAAE,MAAM,CAAA;CAAE,CAAC;AAE5C,MAAM,WAAW,uBAAuB;IACvC,GAAG,EAAE,MAAM,CAAC;IACZ,gFAAgF;IAChF,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;;;;;;;OAQG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB;;;;;;;OAOG;IACH,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB,wDAAwD;IACxD,cAAc,EAAE,MAAM,CAAC;IACvB;;;;OAIG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB;;;;;;;OAOG;IACH,WAAW,CAAC,EAAE,OAAO,CAAC;IACtB,wDAAwD;IACxD,UAAU,CAAC,EAAE,CAAC,KAAK,EAAE,cAAc,KAAK,IAAI,CAAC;CAC7C;AAED,MAAM,WAAW,WAAW;IAC3B,IAAI,EAAE,MAAM,CAAC;IACb,SAAS,EAAE,MAAM,CAAC;IAClB,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;CACd;AAED,MAAM,WAAW,gBAAiB,SAAQ,WAAW;IACpD,sFAAoF;IACpF,EAAE,EAAE,MAAM,CAAC;CACX;AAED,qBAAa,gBAAgB;IAC5B,OAAO,CAAC,QAAQ,CAAC,OAAO,CAA0B;IAClD,OAAO,CAAC,MAAM,CAA8B;IAC5C,OAAO,CAAC,IAAI,CAAwB;IACpC,OAAO,CAAC,KAAK,CAAqC;IAClD,OAAO,CAAC,QAAQ,CAAS;IACzB,iEAAiE;IACjE,OAAO,CAAC,gBAAgB,CAAS;IACjC,8DAA8D;IAC9D,OAAO,CAAC,WAAW,CAAS;IAC5B,wEAAwE;IACxE,OAAO,CAAC,YAAY,CAAS;IAE7B,YAAY,OAAO,EAAE,uBAAuB,EAE3C;IAED,QAAQ,IAAI,cAAc,CAEzB;IAED,oFAAoF;IACpF;;;;;OAKG;IACH,OAAO,IAAI,MAAM,GAAG,SAAS,CAE5B;IAED,WAAW,IAAI,OAAO,CAErB;IAED,OAAO,CAAC,QAAQ;IAKhB;;;OAGG;IACH,wBAAwB,IAAI,OAAO,CAElC;IAED;;;;;;;;;;;;;;;;;;;OAmBG;IACH,UAAU,CAAC,MAAM,CAAC,EAAE,WAAW,GAAG,MAAM,EAAE,CAezC;IAED,iEAAiE;IACjE,oBAAoB,IAAI,OAAO,CAE9B;IAED;;;;;;OAMG;IACG,MAAM,CAAC,KAAK,EAAE,MAAM,EAAE,QAAQ,EAAE,sBAAsB,EAAE,EAAE,CAAC,EAAE,MAAM,GAAG,OAAO,CAAC,qBAAqB,EAAE,CAAC,CAY3G;IAED,OAAO,CAAC,kBAAkB;IAQ1B;;;;;;;;;OASG;IACH,OAAO,CAAC,UAAU;YAeJ,aAAa;IAY3B;;;OAGG;IACG,KAAK,CAAC,MAAM,CAAC,EAAE,WAAW,GAAG,OAAO,CAAC,IAAI,CAAC,CAQ/C;YAEa,GAAG;YAiHH,iBAAiB;IAqF/B,OAAO,CAAC,WAAW;IAMnB,4DAA4D;IACtD,MAAM,CAAC,KAAK,EAAE,MAAM,EAAE,CAAC,SAAK,GAAG,OAAO,CAAC,WAAW,EAAE,CAAC,CAE1D;IAED,wEAAwE;IAClE,YAAY,CACjB,KAAK,EAAE,MAAM,EACb,CAAC,SAAK,EACN,IAAI,CAAC,EAAE,MAAM,EACb,SAAS,GAAE,eAAyB,GAClC,OAAO,CAAC,gBAAgB,EAAE,CAAC,CA2B7B;IAED;;;;;OAKG;IACH,kBAAkB,CACjB,GAAG,EAAE,MAAM,EACX,IAAI,EAAE,MAAM,GACV;QAAE,EAAE,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAC;QAAC,SAAS,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAA;KAAE,GAAG,SAAS,CAU9E;YAEa,WAAW;IAYzB,kEAAkE;IAC5D,OAAO,IAAI,OAAO,CAAC,IAAI,CAAC,CAW7B;CACD;AAWD,wBAAgB,wBAAwB,CAAC,GAAG,EAAE,MAAM,EAAE,OAAO,EAAE,gBAAgB,GAAG,IAAI,CAMrF;AAED,wBAAgB,mBAAmB,CAAC,GAAG,EAAE,MAAM,GAAG,gBAAgB,GAAG,SAAS,CAE7E;AAED,wBAAgB,0BAA0B,CAAC,GAAG,EAAE,MAAM,GAAG,IAAI,CAE5D","sourcesContent":["/**\n * Orchestrates semantic indexing and search for a repository.\n *\n * Lifecycle (all behind --enable-semantic-index):\n *  1. `start()` — resolve the embsearch binary, scan the repo (ignore-aware),\n *     apply the byte threshold. Under threshold → dormant. Over → spawn the\n *     daemon, verify the backend is not the mock embedder, then index changed\n *     files in the background in small batches, reporting progress.\n *  2. `search()` — top-k semantic query, mapping chunk ids back to\n *     `path:start-end` via the sidecar metadata.\n *  3. `dispose()` — save + close the daemon.\n *\n * Every failure degrades to `unavailable` with a reason; nothing here ever\n * blocks session startup or affects grep/find.\n */\n\nimport { execFileSync } from \"child_process\";\nimport { readFileSync, rmSync } from \"fs\";\nimport { minimatch } from \"minimatch\";\nimport { ensureTool } from \"../../utils/tools-manager.js\";\nimport { chunkFile } from \"./chunker.js\";\nimport {\n\ttype DaemonRetriever,\n\tEmbSearchClient,\n\ttype EmbSearchDaemonInfo,\n\ttype EmbSearchRerankPassage,\n\ttype EmbSearchRerankResult,\n} from \"./client.js\";\nimport {\n\temptyIndexMeta,\n\ttype FileMeta,\n\tgetEmbsearchStoreDir,\n\tgetVectorStoreDir,\n\thashContent,\n\ttype IndexMeta,\n\tloadIndexMeta,\n\tsaveIndexMeta,\n} from \"./index-meta.js\";\nimport { type RepoScanFile, scanRepo } from \"./repo-scan.js\";\n\n/** Chunks per bulk request. Small enough that a concurrent query is never\n *  stuck long behind one padded batch inference. */\nconst BULK_BATCH_SIZE = 48;\n/** Yield between batches so background indexing doesn't starve the session. */\nconst BATCH_YIELD_MS = 15;\n/** The Rust mock backend's model id — semantically meaningless, never index with it. */\nconst MOCK_MODEL_ID = \"mock-hash-v1\";\n/**\n * First embsearch release serving `retriever: \"lexical\"`.\n *\n * The guard matters because the daemon does not reject unknown request fields:\n * an older binary silently ignores `retriever` and answers with dense results.\n * Fusing that list a second time as a \"bm25\" leg would double-count it and\n * corrupt the ranking with no error anywhere — so refuse instead of degrading.\n */\nconst MIN_LEXICAL_RETRIEVER_VERSION = [0, 2, 0] as const;\n/**\n * First embsearch release serving the `rerank` op.\n *\n * Necessary but no longer sufficient. Releases from 0.3.1 carry the op without\n * the ~23 MB cross-encoder weights — they measured worse than the\n * deterministic reranker on five of six query classes, so they are no longer\n * bundled — and such a daemon answers `rerank` with an error. The version is\n * therefore only the floor for *asking*; `info.rerank` is the answer, and\n * {@link EmbsearchService.supportsCrossEncoder} needs both.\n */\nconst MIN_RERANK_VERSION = [0, 3, 0] as const;\n\n/** `embsearch 0.2.0` -> [0, 2, 0]; undefined when it cannot be parsed. */\nfunction parseBinaryVersion(output: string): number[] | undefined {\n\tconst match = output.match(/(\\d+)\\.(\\d+)\\.(\\d+)/);\n\treturn match ? [Number(match[1]), Number(match[2]), Number(match[3])] : undefined;\n}\n\nfunction atLeast(version: readonly number[], minimum: readonly number[]): boolean {\n\tfor (let i = 0; i < minimum.length; i++) {\n\t\tconst part = version[i] ?? 0;\n\t\tif (part !== minimum[i]) return part > minimum[i];\n\t}\n\treturn true;\n}\n\nexport type EmbsearchState =\n\t| { phase: \"idle\" }\n\t| { phase: \"skipped\"; reason: string }\n\t| { phase: \"downloading\"; receivedBytes: number; totalBytes: number | null }\n\t| { phase: \"indexing\"; done: number; total: number }\n\t| { phase: \"ready\"; chunkCount: number }\n\t| { phase: \"unavailable\"; reason: string };\n\nexport interface EmbsearchServiceOptions {\n\tcwd: string;\n\t/** Explicit binary path (settings override). Default: \"embsearch\" from PATH. */\n\tbinaryPath?: string;\n\t/**\n\t * Model directory handed to the daemon as `--model`, overriding the model\n\t * bundled in the binary.\n\t *\n\t * Only the eval harness sets this, to score two embedding models from one\n\t * binary. Pair it with a distinct `storeDir`: vectors from different models\n\t * are incompatible, and the daemon refuses to open a store built by another\n\t * model rather than mixing them.\n\t */\n\tmodelDir?: string;\n\t/**\n\t * Override the chunker's character cap.\n\t *\n\t * Only the eval harness sets this, to sweep the chunk window. It changes\n\t * what every vector in the store *is*, and nothing stored records it, so it\n\t * must be paired with a distinct `storeDir` exactly as `modelDir` is —\n\t * otherwise a run silently scores an index built at another cap.\n\t */\n\tchunkMaxChars?: number;\n\t/** Minimum indexable bytes before indexing kicks in. */\n\tthresholdBytes: number;\n\t/**\n\t * Override the store location. Only the eval harness sets this, so a\n\t * second index (e.g. a BM25-hybrid store) can exist for the same repo\n\t * without colliding with the primary one.\n\t */\n\tstoreDir?: string;\n\t/**\n\t * Create the store with the daemon's BM25 lexical index.\n\t *\n\t * Defaults to whatever the daemon can serve. Fixed at store creation, so an\n\t * existing store that disagrees is rebuilt once; when overriding this to\n\t * hold two different stores for one repo, pair it with a distinct\n\t * `storeDir` so they do not fight over the same directory.\n\t */\n\thybridStore?: boolean;\n\t/** Progress callback for UI (footer / stderr lines). */\n\tonProgress?: (state: EmbsearchState) => void;\n}\n\nexport interface SemanticHit {\n\tpath: string;\n\tstartLine: number;\n\tendLine: number;\n\tscore: number;\n}\n\nexport interface SemanticChunkHit extends SemanticHit {\n\t/** Per-build chunk id (`relpath#index`) — the fusion identity for hybrid search. */\n\tid: string;\n}\n\nexport class EmbsearchService {\n\tprivate readonly options: EmbsearchServiceOptions;\n\tprivate client: EmbSearchClient | undefined;\n\tprivate meta: IndexMeta | undefined;\n\tprivate state: EmbsearchState = { phase: \"idle\" };\n\tprivate disposed = false;\n\t/** Whether the resolved binary serves `retriever: \"lexical\"`. */\n\tprivate lexicalRetriever = false;\n\t/** Whether the store actually opened carries a BM25 index. */\n\tprivate hybridStore = false;\n\t/** Whether the resolved binary serves the cross-encoder `rerank` op. */\n\tprivate crossEncoder = false;\n\n\tconstructor(options: EmbsearchServiceOptions) {\n\t\tthis.options = options;\n\t}\n\n\tgetState(): EmbsearchState {\n\t\treturn this.state;\n\t}\n\n\t/** Semantic search is usable (index ready, or still building with partial data). */\n\t/**\n\t * Model id reported by the running daemon, once it is up.\n\t *\n\t * This — not the binary's version — identifies which model produced the\n\t * vectors in the store, because `--model` decouples the two.\n\t */\n\tmodelId(): string | undefined {\n\t\treturn this.meta?.modelId;\n\t}\n\n\tisAvailable(): boolean {\n\t\treturn this.state.phase === \"ready\" || this.state.phase === \"indexing\";\n\t}\n\n\tprivate setState(state: EmbsearchState): void {\n\t\tthis.state = state;\n\t\tthis.options.onProgress?.(state);\n\t}\n\n\t/**\n\t * Whether a BM25-only query will work: the daemon has to understand the\n\t * `lexical` retriever *and* the open store has to carry a BM25 index.\n\t */\n\tsupportsLexicalRetriever(): boolean {\n\t\treturn this.lexicalRetriever && this.hybridStore;\n\t}\n\n\t/**\n\t * Repo files whose on-disk content the index does not have — unknown to it,\n\t * or changed since it last read them.\n\t *\n\t * This is the set BM25 is structurally blind to, and the only place the\n\t * grep leg still earns its keep once BM25 is available. An agent that edits\n\t * a file and immediately searches for what it wrote is asking about exactly\n\t * these files; the index cannot answer until the next pass.\n\t *\n\t * Compares mtime and size only, never hashing: the check runs per query, and\n\t * a false positive merely lets grep cover a file BM25 already covers, while\n\t * a false negative would lose the edit.\n\t *\n\t * Deliberately uncached. A cache here caches the *absence* of an edit, which\n\t * is the one thing this must never do — an agent writes a file and searches\n\t * for it in the same breath. A 1s TTL was tried and cost the live-edit set\n\t * 75% to 100% of its score depending on how the timing fell, which is worse\n\t * than wrong: it was non-deterministic. One scan is ~25ms over ~1k files and\n\t * happens once per search, against retrieval that already costs more.\n\t */\n\tstaleFiles(signal?: AbortSignal): string[] {\n\t\tif (!this.meta) return [];\n\t\tconst meta = this.meta;\n\t\tconst files: string[] = [];\n\t\ttry {\n\t\t\tfor (const file of scanRepo(this.options.cwd, signal).files) {\n\t\t\t\tconst known = meta.files[file.rel];\n\t\t\t\tif (!known || known.mtimeMs !== file.mtimeMs || known.size !== file.size) files.push(file.rel);\n\t\t\t}\n\t\t} catch {\n\t\t\t// A failed scan must not silently narrow the grep leg to nothing;\n\t\t\t// report no staleness and let the indexed legs answer.\n\t\t\treturn [];\n\t\t}\n\t\treturn files;\n\t}\n\n\t/** Whether the running daemon can score with a cross-encoder. */\n\tsupportsCrossEncoder(): boolean {\n\t\treturn this.crossEncoder;\n\t}\n\n\t/**\n\t * Cross-encoder rerank of caller-supplied passages.\n\t *\n\t * Unlike the retrievers this does not consult the index at all — it scores\n\t * exactly the text passed in, which is why the caller sends its expanded\n\t * windows rather than chunk ids.\n\t */\n\tasync rerank(query: string, passages: EmbSearchRerankPassage[], k: number): Promise<EmbSearchRerankResult[]> {\n\t\tif (!this.client || this.client.isClosed) {\n\t\t\tthrow new Error(\"semantic index is not available\");\n\t\t}\n\t\tif (!this.crossEncoder) {\n\t\t\tthrow new Error(\n\t\t\t\t`this embsearch daemon cannot rerank (needs >= ${MIN_RERANK_VERSION.join(\".\")} reporting ` +\n\t\t\t\t\t\"`rerank: true`); released binaries ship without cross-encoder weights — start the daemon \" +\n\t\t\t\t\t\"with --reranker-model <dir>\",\n\t\t\t);\n\t\t}\n\t\treturn await this.client.rerank(query, passages, k);\n\t}\n\n\tprivate probeBinaryVersion(binary: string): number[] | undefined {\n\t\ttry {\n\t\t\treturn parseBinaryVersion(execFileSync(binary, [\"--version\"], { encoding: \"utf-8\", timeout: 10_000 }));\n\t\t} catch {\n\t\t\treturn undefined;\n\t\t}\n\t}\n\n\t/**\n\t * What the store on disk says about itself, read straight from its manifest.\n\t *\n\t * `store-info` exists precisely for the case where the daemon will not open\n\t * the store: a `serve` pairs a store with an embedder and refuses the pair\n\t * when their models disagree, so at that moment nothing else can tell us\n\t * what built it. Returns undefined when there is no readable store — which\n\t * includes a binary too old to have the subcommand, and so degrades to the\n\t * previous behaviour rather than guessing.\n\t */\n\tprivate probeStore(binary: string, storeDir: string): { modelId: string; live: number } | undefined {\n\t\ttry {\n\t\t\tconst out = execFileSync(binary, [\"store-info\", \"--path\", getVectorStoreDir(storeDir), \"--json\"], {\n\t\t\t\tencoding: \"utf-8\",\n\t\t\t\ttimeout: 10_000,\n\t\t\t\tstdio: [\"ignore\", \"pipe\", \"ignore\"],\n\t\t\t});\n\t\t\tconst parsed = JSON.parse(out) as { model_id?: string; live?: number };\n\t\t\tif (typeof parsed.model_id !== \"string\") return undefined;\n\t\t\treturn { modelId: parsed.model_id, live: parsed.live ?? 0 };\n\t\t} catch {\n\t\t\treturn undefined;\n\t\t}\n\t}\n\n\tprivate async resolveBinary(): Promise<string | undefined> {\n\t\tif (this.options.binaryPath) {\n\t\t\treturn this.options.binaryPath;\n\t\t}\n\t\t// Surface the on-demand binary download through the same progress channel as\n\t\t// indexing, so the first-run fetch renders a progress bar instead of a stall.\n\t\t// A cached binary resolves without ever invoking this callback.\n\t\treturn await ensureTool(\"embsearch\", true, (receivedBytes, totalBytes) => {\n\t\t\tthis.setState({ phase: \"downloading\", receivedBytes, totalBytes });\n\t\t});\n\t}\n\n\t/**\n\t * Scan, threshold-check, and (when needed) index in the background.\n\t * Resolves when indexing completes or the feature settles dormant.\n\t */\n\tasync start(signal?: AbortSignal): Promise<void> {\n\t\ttry {\n\t\t\tawait this.run(signal);\n\t\t} catch (e) {\n\t\t\tconst reason = e instanceof Error ? e.message : String(e);\n\t\t\tthis.setState({ phase: \"unavailable\", reason });\n\t\t\tawait this.closeClient();\n\t\t}\n\t}\n\n\tprivate async run(signal?: AbortSignal): Promise<void> {\n\t\tconst binary = await this.resolveBinary();\n\t\tif (!binary) {\n\t\t\tthis.setState({\n\t\t\t\tphase: \"unavailable\",\n\t\t\t\treason: \"embsearch binary not found (PATH or embsearchBinaryPath setting)\",\n\t\t\t});\n\t\t\treturn;\n\t\t}\n\n\t\tconst scan = scanRepo(this.options.cwd, signal);\n\t\tif (scan.totalBytes < this.options.thresholdBytes) {\n\t\t\tthis.setState({\n\t\t\t\tphase: \"skipped\",\n\t\t\t\treason: `repo under threshold (${scan.totalBytes} < ${this.options.thresholdBytes} bytes)`,\n\t\t\t});\n\t\t\treturn;\n\t\t}\n\n\t\tconst binaryVersion = this.probeBinaryVersion(binary);\n\t\tthis.lexicalRetriever = binaryVersion !== undefined && atLeast(binaryVersion, MIN_LEXICAL_RETRIEVER_VERSION);\n\t\t// Provisional: the version says the daemon understands `rerank`. Whether\n\t\t// it can serve one is answered by `info` below, once the client is up.\n\t\tthis.crossEncoder = binaryVersion !== undefined && atLeast(binaryVersion, MIN_RERANK_VERSION);\n\n\t\tconst storeDir = this.options.storeDir ?? getEmbsearchStoreDir(this.options.cwd);\n\t\t// A hybrid store carries a BM25 index next to its vectors, which is what\n\t\t// lets search use BM25 as its lexical leg instead of ripgrep. Callers may\n\t\t// force it either way; by default it follows what the daemon can serve.\n\t\tconst wantHybrid = this.options.hybridStore ?? this.lexicalRetriever;\n\n\t\tconst openClient = async (): Promise<EmbSearchDaemonInfo> => {\n\t\t\tthis.client = new EmbSearchClient({\n\t\t\t\tbinaryPath: binary,\n\t\t\t\tstorePath: getVectorStoreDir(storeDir),\n\t\t\t\thybrid: wantHybrid,\n\t\t\t\tmodelDir: this.options.modelDir,\n\t\t\t});\n\t\t\tawait this.client.ready();\n\t\t\treturn await this.client.info();\n\t\t};\n\n\t\t/** Discard the store and start clean. The only recovery from a store the\n\t\t *  current binary cannot use — and the only way to be rid of vectors that\n\t\t *  outlived the metadata describing them. */\n\t\tconst rebuildFrom = async (why: string): Promise<EmbSearchDaemonInfo> => {\n\t\t\tconsole.error(`embsearch: rebuilding the index (${why})`);\n\t\t\tthis.setState({ phase: \"indexing\", done: 0, total: 0 });\n\t\t\tawait this.closeClient();\n\t\t\trmSync(storeDir, { recursive: true, force: true });\n\t\t\treturn await openClient();\n\t\t};\n\n\t\tlet info: EmbSearchDaemonInfo;\n\t\ttry {\n\t\t\tinfo = await openClient();\n\t\t} catch (err) {\n\t\t\t// The daemon refuses to open a store whose recorded model disagrees\n\t\t\t// with its own — correctly, since vectors from different models are\n\t\t\t// not comparable. But refusing is where it stopped: the store stayed\n\t\t\t// on disk, the daemon never came up, and this service went\n\t\t\t// permanently unavailable with a rebuild one directory-removal away.\n\t\t\t//\n\t\t\t// Only a store that is present and *readable* is treated this way. If\n\t\t\t// `store-info` cannot read it either, the problem is not a model\n\t\t\t// mismatch and destroying an index would be the wrong response, so\n\t\t\t// the original failure stands.\n\t\t\tconst store = this.probeStore(binary, storeDir);\n\t\t\tif (!store) throw err;\n\t\t\tinfo = await rebuildFrom(`built by model '${store.modelId}', which this binary cannot read`);\n\t\t}\n\n\t\t// Hybrid-ness is fixed when a store is created and `--hybrid` against an\n\t\t// existing plain store only warns, so an index built before this was the\n\t\t// default would silently stay dense-only and every BM25 query against it\n\t\t// would fail. Ask the store itself rather than trusting the sidecar, and\n\t\t// rebuild once when it disagrees. `info.hybrid` is undefined on daemons\n\t\t// too old to report it — those cannot serve BM25 anyway, so leave them be.\n\t\tif (wantHybrid && info.hybrid === false) {\n\t\t\tinfo = await rebuildFrom(\"the existing store carries no BM25 index\");\n\t\t}\n\t\tthis.hybridStore = info.hybrid === true;\n\t\t// A daemon old enough to omit the field is left on the version verdict —\n\t\t// back then the weights were bundled, so version did imply capability.\n\t\tif (info.rerank === false) this.crossEncoder = false;\n\t\tif (info.modelId === MOCK_MODEL_ID) {\n\t\t\tthrow new Error(\"embsearch binary uses the mock embedder (not semantic); install an onnx build\");\n\t\t}\n\n\t\t// Missing/stale sidecar (format, chunker, or model changed) → clean rebuild.\n\t\t//\n\t\t// Resetting the sidecar alone is not enough, and used to be all this did.\n\t\t// The sidecar is the only record of how many chunks each file produced,\n\t\t// so an empty one reports zero for every file — and `indexChangedFiles`\n\t\t// removes stale chunks by counting down from that number. Re-chunking a\n\t\t// file into *fewer* pieces then leaves its tail vectors (`path#N`,\n\t\t// `path#N+1`, …) in the store, holding text that no longer exists\n\t\t// anywhere, retrievable forever. Upserts hide it: chunk counts look\n\t\t// right, the sidecar looks right, and only search results are wrong.\n\t\t//\n\t\t// So when the sidecar cannot be trusted and the store is not already\n\t\t// empty, the store goes too.\n\t\tlet meta = loadIndexMeta(storeDir, info.modelId);\n\t\tif (!meta && info.count > 0) {\n\t\t\tinfo = await rebuildFrom(\"index metadata is missing or was written by a different chunker or model\");\n\t\t\tmeta = loadIndexMeta(storeDir, info.modelId);\n\t\t}\n\t\tthis.meta = meta ?? emptyIndexMeta(this.options.cwd, info.modelId);\n\t\tthis.meta.lastUsedMs = Date.now();\n\n\t\tawait this.indexChangedFiles(scan.files, storeDir, signal);\n\t}\n\n\tprivate async indexChangedFiles(files: RepoScanFile[], storeDir: string, signal?: AbortSignal): Promise<void> {\n\t\tconst meta = this.meta!;\n\t\tconst client = this.client!;\n\n\t\t// Diff scan vs sidecar: cheap mtime+size check first, hash only on delta.\n\t\tconst toIndex: Array<{ file: RepoScanFile; content: string; hash: string }> = [];\n\t\tconst seen = new Set<string>();\n\t\tfor (const file of files) {\n\t\t\tseen.add(file.rel);\n\t\t\tconst known = meta.files[file.rel];\n\t\t\tif (known && known.mtimeMs === file.mtimeMs && known.size === file.size) continue;\n\t\t\tlet content: string;\n\t\t\ttry {\n\t\t\t\tcontent = readFileSync(file.abs, \"utf-8\");\n\t\t\t} catch {\n\t\t\t\tcontinue;\n\t\t\t}\n\t\t\tconst hash = hashContent(content);\n\t\t\tif (known && known.hash === hash) {\n\t\t\t\t// Touched but unchanged — refresh stat info only.\n\t\t\t\tknown.mtimeMs = file.mtimeMs;\n\t\t\t\tknown.size = file.size;\n\t\t\t\tcontinue;\n\t\t\t}\n\t\t\ttoIndex.push({ file, content, hash });\n\t\t}\n\t\tconst toRemove = Object.keys(meta.files).filter((rel) => !seen.has(rel));\n\n\t\tif (toIndex.length === 0 && toRemove.length === 0) {\n\t\t\tsaveIndexMeta(storeDir, meta);\n\t\t\tthis.setState({ phase: \"ready\", chunkCount: this.countChunks(meta) });\n\t\t\treturn;\n\t\t}\n\n\t\t// Chunk changed files; count total upserts for exact progress.\n\t\tconst work: Array<{ rel: string; fileMeta: FileMeta; chunks: Array<{ id: string; text: string }> }> = [];\n\t\tlet totalChunks = 0;\n\t\tfor (const { file, content, hash } of toIndex) {\n\t\t\tconst chunks = chunkFile(file.rel, content, this.options.chunkMaxChars);\n\t\t\twork.push({\n\t\t\t\trel: file.rel,\n\t\t\t\tfileMeta: {\n\t\t\t\t\tmtimeMs: file.mtimeMs,\n\t\t\t\t\tsize: file.size,\n\t\t\t\t\thash,\n\t\t\t\t\tchunks: chunks.map((c) => [c.startLine, c.endLine]),\n\t\t\t\t},\n\t\t\t\tchunks: chunks.map((c) => ({ id: c.id, text: c.text })),\n\t\t\t});\n\t\t\ttotalChunks += chunks.length;\n\t\t}\n\n\t\tthis.setState({ phase: \"indexing\", done: 0, total: totalChunks });\n\n\t\t// Drop vectors of deleted files and superseded chunk tails.\n\t\tfor (const rel of toRemove) {\n\t\t\tfor (let i = 0; i < meta.files[rel].chunks.length; i++) await client.remove(`${rel}#${i}`);\n\t\t\tdelete meta.files[rel];\n\t\t}\n\n\t\tlet done = 0;\n\t\tfor (const item of work) {\n\t\t\tif (signal?.aborted || this.disposed) return;\n\t\t\tconst oldChunkCount = meta.files[item.rel]?.chunks.length ?? 0;\n\t\t\t// Remove old chunks beyond the new count (upsert covers the rest).\n\t\t\tfor (let i = item.chunks.length; i < oldChunkCount; i++) await client.remove(`${item.rel}#${i}`);\n\n\t\t\tfor (let offset = 0; offset < item.chunks.length; offset += BULK_BATCH_SIZE) {\n\t\t\t\tif (signal?.aborted || this.disposed) return;\n\t\t\t\tconst batch = item.chunks.slice(offset, offset + BULK_BATCH_SIZE);\n\t\t\t\tawait client.bulk(batch);\n\t\t\t\tdone += batch.length;\n\t\t\t\tthis.setState({ phase: \"indexing\", done, total: totalChunks });\n\t\t\t\t// Yield so queries and the event loop stay responsive.\n\t\t\t\tawait new Promise((resolve) => setTimeout(resolve, BATCH_YIELD_MS));\n\t\t\t}\n\t\t\tmeta.files[item.rel] = item.fileMeta;\n\t\t}\n\n\t\tawait client.compact();\n\t\tawait client.save();\n\t\tsaveIndexMeta(storeDir, meta);\n\t\tthis.setState({ phase: \"ready\", chunkCount: this.countChunks(meta) });\n\t}\n\n\tprivate countChunks(meta: IndexMeta): number {\n\t\tlet n = 0;\n\t\tfor (const rel of Object.keys(meta.files)) n += meta.files[rel].chunks.length;\n\t\treturn n;\n\t}\n\n\t/** Top-`k` semantic hits as `path` + line range + score. */\n\tasync search(query: string, k = 10): Promise<SemanticHit[]> {\n\t\treturn await this.searchChunks(query, k);\n\t}\n\n\t/** Top-`k` semantic hits including their chunk ids, for rank fusion. */\n\tasync searchChunks(\n\t\tquery: string,\n\t\tk = 10,\n\t\tglob?: string,\n\t\tretriever: DaemonRetriever = \"dense\",\n\t): Promise<SemanticChunkHit[]> {\n\t\tif (!this.client || this.client.isClosed || !this.meta) {\n\t\t\tthrow new Error(\"semantic index is not available\");\n\t\t}\n\t\tif (retriever === \"lexical\" && !this.lexicalRetriever) {\n\t\t\tthrow new Error(\n\t\t\t\t`embsearch is too old for retriever \"lexical\" (needs >= ${MIN_LEXICAL_RETRIEVER_VERSION.join(\".\")}); ` +\n\t\t\t\t\t\"an older daemon ignores the field and answers with dense results\",\n\t\t\t);\n\t\t}\n\t\tconst results = await this.client.query(query, k, retriever);\n\t\tconst hits: SemanticChunkHit[] = [];\n\t\tconst matchGlob = (rel: string): boolean => {\n\t\t\tif (!glob) return true;\n\t\t\treturn minimatch(rel, glob, { dot: true, matchBase: !glob.includes(\"/\") });\n\t\t};\n\t\tfor (const result of results) {\n\t\t\tconst sep = result.id.lastIndexOf(\"#\");\n\t\t\tif (sep === -1) continue;\n\t\t\tconst rel = result.id.slice(0, sep);\n\t\t\tif (!matchGlob(rel)) continue;\n\t\t\tconst chunkIndex = Number.parseInt(result.id.slice(sep + 1), 10);\n\t\t\tconst range = this.meta.files[rel]?.chunks[chunkIndex];\n\t\t\tif (!range) continue;\n\t\t\thits.push({ id: result.id, path: rel, startLine: range[0], endLine: range[1], score: result.score });\n\t\t}\n\t\treturn hits;\n\t}\n\n\t/**\n\t * Resolve a repo-relative path + line to its enclosing indexed chunk, or\n\t * undefined when the file/line is not covered by the index. Chunks overlap\n\t * by a few lines; the first (lowest-index) containing chunk wins so the\n\t * mapping is deterministic.\n\t */\n\tfindEnclosingChunk(\n\t\trel: string,\n\t\tline: number,\n\t): { id: string; path: string; startLine: number; endLine: number } | undefined {\n\t\tconst file = this.meta?.files[rel];\n\t\tif (!file) return undefined;\n\t\tfor (let i = 0; i < file.chunks.length; i++) {\n\t\t\tconst [startLine, endLine] = file.chunks[i];\n\t\t\tif (line >= startLine && line <= endLine) {\n\t\t\t\treturn { id: `${rel}#${i}`, path: rel, startLine, endLine };\n\t\t\t}\n\t\t}\n\t\treturn undefined;\n\t}\n\n\tprivate async closeClient(): Promise<void> {\n\t\tconst client = this.client;\n\t\tthis.client = undefined;\n\t\tif (client && !client.isClosed) {\n\t\t\ttry {\n\t\t\t\tawait client.close();\n\t\t\t} catch {\n\t\t\t\t// already dead\n\t\t\t}\n\t\t}\n\t}\n\n\t/** Persist state and shut the daemon down. Safe to call twice. */\n\tasync dispose(): Promise<void> {\n\t\tif (this.disposed) return;\n\t\tthis.disposed = true;\n\t\tif (this.client && !this.client.isClosed) {\n\t\t\ttry {\n\t\t\t\tawait this.client.save();\n\t\t\t} catch {\n\t\t\t\t// daemon may have exited; nothing to save\n\t\t\t}\n\t\t}\n\t\tawait this.closeClient();\n\t}\n}\n\n// --- Per-cwd service registry ---\n//\n// The search tool is constructed by the generic tool factory table and\n// only receives `cwd`; the service is created later during session init (flag\n// gated). This registry connects the two without threading a service instance\n// through every layer between main.ts and the tool factories.\n\nconst services = new Map<string, EmbsearchService>();\n\nexport function registerEmbsearchService(cwd: string, service: EmbsearchService): void {\n\tconst old = services.get(cwd);\n\tif (old && old !== service) {\n\t\told.dispose().catch(() => {});\n\t}\n\tservices.set(cwd, service);\n}\n\nexport function getEmbsearchService(cwd: string): EmbsearchService | undefined {\n\treturn services.get(cwd);\n}\n\nexport function unregisterEmbsearchService(cwd: string): void {\n\tservices.delete(cwd);\n}\n"]}