sensemaking 0.15.4 → 0.16.0

package/dist/esm/embed/static.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/embed/static.ts"],"sourcesContent":["import { existsSync, readFileSync } from 'node:fs';\nimport { join } from 'node:path';\nimport { SenseError } from '../errors.ts';\nimport { downloadModel, isDownloadable, MODEL_FILENAMES, MODEL_FILES, modelDir, readLanguages } from './store.ts';\nimport type { EmbedProvider } from './types.ts';\n\nconst BATCH_CAP = 64;\n\n// Model2Vec safetensors + pure-JS tokenizer. Encode convention from model2vec/model.py: no\n// special tokens, drop unk ids, mean-pool, L2-normalize.\nexport async function staticProvider(model: string): Promise<EmbedProvider> {\n  let dir: string;\n  let languages: string[] | undefined;\n  if (isDownloadable(model)) {\n    // Naming a HF id is consent: fetch whatever is missing now, announcing it on stderr.\n    dir = await downloadModel(model, (file, into) => console.error(`sense: fetching ${model}/${file} into ${into}`));\n    // Cached beside the repo; a local model directory has no card to read, so it has none.\n    const cached = readLanguages(model);\n    languages = cached && cached.length > 0 ? cached : undefined;\n  } else {\n    dir = modelDir(model);\n    for (const file of MODEL_FILES) {\n      if (!existsSync(join(dir, file))) {\n        throw new SenseError('EMBED_MODEL_MISSING', `embed model ${model} is not available (looked in ${dir}); expected ${MODEL_FILENAMES} in that directory`);\n      }\n    }\n  }\n\n  const raw = readFileSync(join(dir, 'model.safetensors'));\n  const headerLen = Number(raw.readBigUInt64LE(0));\n  const header = JSON.parse(raw.subarray(8, 8 + headerLen).toString('utf8')) as Record<string, { dtype: string; shape: number[]; data_offsets: number[] }>;\n  const entry = Object.entries(header).find(([k]) => k !== '__metadata__');\n  if (!entry || entry[1].dtype !== 'F32') throw new SenseError('EMBED_MODEL', `${model}: expected an F32 safetensors matrix`);\n  const spec = entry[1];\n  const dims = spec.shape[1];\n  const dataStart = raw.byteOffset + 8 + headerLen + spec.data_offsets[0];\n  const matrix = dataStart % 4 === 0 ? new Float32Array(raw.buffer, dataStart, spec.shape[0] * dims) : new Float32Array(raw.buffer.slice(dataStart, dataStart + spec.shape[0] * dims * 4));\n\n  const tokenizerJson = JSON.parse(readFileSync(join(dir, 'tokenizer.json'), 'utf8'));\n  // Lazy import: the tokenizer loads only on the semantic path, never at CLI startup.\n  const { Tokenizer } = await import('@huggingface/tokenizers');\n  const tok = new Tokenizer(tokenizerJson, {});\n  const unkId = tokenizerJson.model?.vocab?.[tokenizerJson.model?.unk_token] ?? -1;\n\n  function one(text: string): Float32Array {\n    // The tokenizer yields undefined (not the unk id) for tokens outside the vocab; an\n    // undefined id would index the matrix at NaN and poison the whole mean-pool -- and the\n    // int8 conversion then stores the NaN vector as all zeros, silently. Keep integers only.\n    const ids = (tok.encode(text, { add_special_tokens: false }).ids as number[]).filter((id) => Number.isInteger(id) && id !== unkId);\n    const v = new Float32Array(dims);\n    if (ids.length === 0) return v;\n    for (const id of ids) {\n      const off = id * dims;\n      for (let d = 0; d < dims; d++) v[d] += matrix[off + d];\n    }\n    let norm = 0;\n    for (let d = 0; d < dims; d++) {\n      v[d] /= ids.length;\n      norm += v[d] * v[d];\n    }\n    norm = Math.sqrt(norm) + 1e-32;\n    for (let d = 0; d < dims; d++) v[d] /= norm;\n    return v;\n  }\n\n  // Symmetric model: document and query embedding are the same call.\n  return { id: `static:${model}`, dims, batchCap: BATCH_CAP, languages, embedDocuments: async (texts) => texts.map(one), embedQuery: async (text) => one(text) };\n}\n"],"names":["existsSync","readFileSync","join","SenseError","downloadModel","isDownloadable","MODEL_FILENAMES","MODEL_FILES","modelDir","readLanguages","BATCH_CAP","staticProvider","model","tokenizerJson","dir","languages","file","into","console","error","cached","length","undefined","raw","headerLen","Number","readBigUInt64LE","header","JSON","parse","subarray","toString","entry","Object","entries","find","k","dtype","spec","dims","shape","dataStart","byteOffset","data_offsets","matrix","Float32Array","buffer","slice","Tokenizer","tok","unkId","vocab","unk_token","one","text","ids","encode","add_special_tokens","filter","id","isInteger","v","off","d","norm","Math","sqrt","batchCap","embedDocuments","texts","map","embedQuery"],"mappings":"AAAA,SAASA,UAAU,EAAEC,YAAY,QAAQ,UAAU;AACnD,SAASC,IAAI,QAAQ,YAAY;AACjC,SAASC,UAAU,QAAQ,eAAe;AAC1C,SAASC,aAAa,EAAEC,cAAc,EAAEC,eAAe,EAAEC,WAAW,EAAEC,QAAQ,EAAEC,aAAa,QAAQ,aAAa;AAGlH,MAAMC,YAAY;AAElB,2FAA2F;AAC3F,yDAAyD;AACzD,OAAO,eAAeC,eAAeC,KAAa;;QAgCLC,sBAA7BA,4BAAAA;IA/Bd,IAAIC;IACJ,IAAIC;IACJ,IAAIV,eAAeO,QAAQ;QACzB,qFAAqF;QACrFE,MAAM,MAAMV,cAAcQ,OAAO,CAACI,MAAMC,OAASC,QAAQC,KAAK,CAAC,CAAC,gBAAgB,EAAEP,MAAM,CAAC,EAAEI,KAAK,MAAM,EAAEC,MAAM;QAC9G,uFAAuF;QACvF,MAAMG,SAASX,cAAcG;QAC7BG,YAAYK,UAAUA,OAAOC,MAAM,GAAG,IAAID,SAASE;IACrD,OAAO;QACLR,MAAMN,SAASI;QACf,KAAK,MAAMI,QAAQT,YAAa;YAC9B,IAAI,CAACP,WAAWE,KAAKY,KAAKE,QAAQ;gBAChC,MAAM,IAAIb,WAAW,uBAAuB,CAAC,YAAY,EAAES,MAAM,6BAA6B,EAAEE,IAAI,YAAY,EAAER,gBAAgB,kBAAkB,CAAC;YACvJ;QACF;IACF;IAEA,MAAMiB,MAAMtB,aAAaC,KAAKY,KAAK;IACnC,MAAMU,YAAYC,OAAOF,IAAIG,eAAe,CAAC;IAC7C,MAAMC,SAASC,KAAKC,KAAK,CAACN,IAAIO,QAAQ,CAAC,GAAG,IAAIN,WAAWO,QAAQ,CAAC;IAClE,MAAMC,QAAQC,OAAOC,OAAO,CAACP,QAAQQ,IAAI,CAAC,CAAC,CAACC,EAAE,GAAKA,MAAM;IACzD,IAAI,CAACJ,SAASA,KAAK,CAAC,EAAE,CAACK,KAAK,KAAK,OAAO,MAAM,IAAIlC,WAAW,eAAe,GAAGS,MAAM,oCAAoC,CAAC;IAC1H,MAAM0B,OAAON,KAAK,CAAC,EAAE;IACrB,MAAMO,OAAOD,KAAKE,KAAK,CAAC,EAAE;IAC1B,MAAMC,YAAYlB,IAAImB,UAAU,GAAG,IAAIlB,YAAYc,KAAKK,YAAY,CAAC,EAAE;IACvE,MAAMC,SAASH,YAAY,MAAM,IAAI,IAAII,aAAatB,IAAIuB,MAAM,EAAEL,WAAWH,KAAKE,KAAK,CAAC,EAAE,GAAGD,QAAQ,IAAIM,aAAatB,IAAIuB,MAAM,CAACC,KAAK,CAACN,WAAWA,YAAYH,KAAKE,KAAK,CAAC,EAAE,GAAGD,OAAO;IAErL,MAAM1B,gBAAgBe,KAAKC,KAAK,CAAC5B,aAAaC,KAAKY,KAAK,mBAAmB;IAC3E,oFAAoF;IACpF,MAAM,EAAEkC,SAAS,EAAE,GAAG,MAAM,MAAM,CAAC;IACnC,MAAMC,MAAM,IAAID,UAAUnC,eAAe,CAAC;IAC1C,MAAMqC,iBAAQrC,wBAAAA,cAAcD,KAAK,cAAnBC,6CAAAA,6BAAAA,sBAAqBsC,KAAK,cAA1BtC,iDAAAA,0BAA4B,EAACA,uBAAAA,cAAcD,KAAK,cAAnBC,2CAAAA,qBAAqBuC,SAAS,CAAC,uCAAI,CAAC;IAE/E,SAASC,IAAIC,IAAY;QACvB,mFAAmF;QACnF,uFAAuF;QACvF,yFAAyF;QACzF,MAAMC,MAAM,AAACN,IAAIO,MAAM,CAACF,MAAM;YAAEG,oBAAoB;QAAM,GAAGF,GAAG,CAAcG,MAAM,CAAC,CAACC,KAAOlC,OAAOmC,SAAS,CAACD,OAAOA,OAAOT;QAC5H,MAAMW,IAAI,IAAIhB,aAAaN;QAC3B,IAAIgB,IAAIlC,MAAM,KAAK,GAAG,OAAOwC;QAC7B,KAAK,MAAMF,MAAMJ,IAAK;YACpB,MAAMO,MAAMH,KAAKpB;YACjB,IAAK,IAAIwB,IAAI,GAAGA,IAAIxB,MAAMwB,IAAKF,CAAC,CAACE,EAAE,IAAInB,MAAM,CAACkB,MAAMC,EAAE;QACxD;QACA,IAAIC,OAAO;QACX,IAAK,IAAID,IAAI,GAAGA,IAAIxB,MAAMwB,IAAK;YAC7BF,CAAC,CAACE,EAAE,IAAIR,IAAIlC,MAAM;YAClB2C,QAAQH,CAAC,CAACE,EAAE,GAAGF,CAAC,CAACE,EAAE;QACrB;QACAC,OAAOC,KAAKC,IAAI,CAACF,QAAQ;QACzB,IAAK,IAAID,IAAI,GAAGA,IAAIxB,MAAMwB,IAAKF,CAAC,CAACE,EAAE,IAAIC;QACvC,OAAOH;IACT;IAEA,mEAAmE;IACnE,OAAO;QAAEF,IAAI,CAAC,OAAO,EAAE/C,OAAO;QAAE2B;QAAM4B,UAAUzD;QAAWK;QAAWqD,gBAAgB,OAAOC,QAAUA,MAAMC,GAAG,CAACjB;QAAMkB,YAAY,OAAOjB,OAASD,IAAIC;IAAM;AAC/J"}

package/dist/esm/embed/store.d.ts

@@ -0,0 +1,8 @@
+import type { Config } from '../config/index.js';
+import { embedConfig } from '../config/index.js';
+export { hasModelFiles, isDownloadable, MODEL_FILENAMES, MODEL_FILES, modelDir, readLanguages, refsMainPath, snapshotDir, writeLanguages, writeRef } from './identity.js';
+export declare function modelPresent(cfg: Config): boolean;
+type ResolvedEmbedConfig = NonNullable<ReturnType<typeof embedConfig>>;
+export declare function localModelMissing(e: ResolvedEmbedConfig | null): e is ResolvedEmbedConfig;
+export declare function downloadModelRevision(model: string, sha: string, onFile?: (file: string, dir: string) => void): Promise<string>;
+export declare function downloadModel(model: string, onFile?: (file: string, dir: string) => void): Promise<string>;

package/dist/esm/embed/store.js

@@ -0,0 +1,123 @@
+import { existsSync, mkdirSync, renameSync, writeFileSync } from 'node:fs';
+import { join } from 'node:path';
+import { embedConfig } from '../config/index.js';
+import { SenseError } from '../errors.js';
+import { fetchWithRetry } from './http.js';
+import { hasModelFiles, isDownloadable, languagesPath, MODEL_FILES, readRef, snapshotDir, writeLanguages, writeRef } from './identity.js';
+import { isKnownLanguageTag, MEASURED_MODEL_LANGUAGES } from './languages.js';
+// identity.ts holds paths and cache identity, no network; store.ts holds the network fetches
+// (downloads, sha resolution, language metadata). Re-exported here for callers that otherwise
+// only need store.ts's network surface.
+export { hasModelFiles, isDownloadable, MODEL_FILENAMES, MODEL_FILES, modelDir, readLanguages, refsMainPath, snapshotDir, writeLanguages, writeRef } from './identity.js';
+// A non-static provider has nothing to download here; an unreachable endpoint surfaces as an
+// EMBED_MODEL error at call time instead.
+export function modelPresent(cfg) {
+    const e = embedConfig(cfg);
+    if (!e) return false;
+    return e.provider !== 'static' || hasModelFiles(e.model);
+}
+// True when embed.model names a local path (not a Hugging Face id) that is missing its model
+// files -- nothing will ever fetch it for itself, unlike a downloadable id.
+export function localModelMissing(e) {
+    return e !== null && e.provider === 'static' && !isDownloadable(e.model) && !hasModelFiles(e.model);
+}
+// `main` resolves to a sha once per model: a recorded ref pins until its snapshot is
+// removed, so only the first need for an id ever costs this HEAD request.
+async function resolveSha(model) {
+    const existing = readRef(model);
+    if (existing) return existing;
+    const url = `https://huggingface.co/${model}/resolve/main/model.safetensors`;
+    // redirect: manual -- the header rides the Hub's own response; following the LFS/CDN
+    // redirect would read the CDN's headers instead, which do not carry it.
+    let res;
+    try {
+        res = await fetchWithRetry(url, {
+            method: 'HEAD',
+            redirect: 'manual'
+        });
+    } catch (err) {
+        throw new SenseError('EMBED_MODEL', `could not reach ${url}: ${err.message}`);
+    }
+    const sha = res.headers.get('x-repo-commit');
+    if (!sha) throw new SenseError('EMBED_MODEL', `${url}: response carried no x-repo-commit header`);
+    writeRef(model, sha);
+    return sha;
+}
+// cardData.language is the structured field (verified live: minishlab/potion-retrieval-32M has
+// neither this nor any language tag, so it stays silent; potion-multilingual-128M carries an
+// array here). Tags are a fallback for cards that only tag languages, filtered to recognized
+// codes so an unrelated short tag (format markers etc.) is never mistaken for one.
+function languagesFromCard(info) {
+    var _info_tags;
+    var _info_cardData;
+    const lang = (_info_cardData = info.cardData) === null || _info_cardData === void 0 ? void 0 : _info_cardData.language;
+    if (typeof lang === 'string') return [
+        lang
+    ];
+    if (Array.isArray(lang) && lang.length > 0) return lang;
+    const tagLangs = ((_info_tags = info.tags) !== null && _info_tags !== void 0 ? _info_tags : []).filter(isKnownLanguageTag);
+    return tagLangs.length > 0 ? tagLangs : undefined;
+}
+// Best-effort, cached forever once resolved (even to "none"): unlike model weights, missing or
+// unreachable metadata is not an error -- it just means the language-fit check stays off.
+async function ensureLanguages(model) {
+    var _languagesFromCard;
+    if (existsSync(languagesPath(model))) return;
+    // A measured entry needs no card and no network, and stays deterministic offline.
+    const measured = MEASURED_MODEL_LANGUAGES[model];
+    if (measured) {
+        writeLanguages(model, measured);
+        return;
+    }
+    let res;
+    try {
+        res = await fetchWithRetry(`https://huggingface.co/api/models/${model}`, {});
+    } catch  {
+        return;
+    }
+    if (!res.ok) return;
+    let info;
+    try {
+        info = await res.json();
+    } catch  {
+        return;
+    }
+    writeLanguages(model, (_languagesFromCard = languagesFromCard(info)) !== null && _languagesFromCard !== void 0 ? _languagesFromCard : []);
+}
+async function fetchToFile(url, dest) {
+    let res;
+    try {
+        res = await fetchWithRetry(url, {});
+    } catch (err) {
+        throw new SenseError('EMBED_MODEL', `could not reach ${url}: ${err.message}`);
+    }
+    if (!res.ok) throw new SenseError('EMBED_MODEL', `${url} -> HTTP ${res.status}`);
+    writeFileSync(`${dest}.part`, Buffer.from(await res.arrayBuffer()));
+    renameSync(`${dest}.part`, dest);
+}
+// Fetches an already-known sha straight into its snapshot dir, without touching refs/main --
+// for downloadModel below, and for callers pinning an exact revision (the parity suite).
+export async function downloadModelRevision(model, sha, onFile) {
+    const dir = snapshotDir(model, sha);
+    mkdirSync(dir, {
+        recursive: true
+    });
+    for (const file of MODEL_FILES){
+        if (existsSync(join(dir, file))) continue;
+        onFile === null || onFile === void 0 ? void 0 : onFile(file, dir);
+        await fetchToFile(`https://huggingface.co/${model}/resolve/${sha}/${file}`, join(dir, file));
+    }
+    return dir;
+}
+// The only code path that resolves `main`: a static provider's first construction calls it
+// lazily, `sense download` as an explicit prefetch. Idempotent either way.
+export async function downloadModel(model, onFile) {
+    if (!isDownloadable(model)) {
+        throw new SenseError('EMBED_MODEL', `embed.model "${model}" is a local path, not a Hugging Face model id, so there is nothing to download; put model.safetensors and tokenizer.json in that directory, or name a model id like "minishlab/potion-retrieval-32M"`);
+    }
+    const sha = await resolveSha(model);
+    // Independent of the weights above: a fresh HEAD/GET pair either way, so a lazy first
+    // construction and an explicit prefetch both end up with a cached language verdict.
+    await ensureLanguages(model);
+    return downloadModelRevision(model, sha, onFile);
+}

package/dist/esm/embed/store.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/embed/store.ts"],"sourcesContent":["import { existsSync, mkdirSync, renameSync, writeFileSync } from 'node:fs';\nimport { join } from 'node:path';\nimport type { Config } from '../config/index.ts';\nimport { embedConfig } from '../config/index.ts';\nimport { SenseError } from '../errors.ts';\nimport { fetchWithRetry } from './http.ts';\nimport { hasModelFiles, isDownloadable, languagesPath, MODEL_FILES, readRef, snapshotDir, writeLanguages, writeRef } from './identity.ts';\nimport { isKnownLanguageTag, MEASURED_MODEL_LANGUAGES } from './languages.ts';\n\n// identity.ts holds paths and cache identity, no network; store.ts holds the network fetches\n// (downloads, sha resolution, language metadata). Re-exported here for callers that otherwise\n// only need store.ts's network surface.\nexport { hasModelFiles, isDownloadable, MODEL_FILENAMES, MODEL_FILES, modelDir, readLanguages, refsMainPath, snapshotDir, writeLanguages, writeRef } from './identity.ts';\n\n// A non-static provider has nothing to download here; an unreachable endpoint surfaces as an\n// EMBED_MODEL error at call time instead.\nexport function modelPresent(cfg: Config): boolean {\n  const e = embedConfig(cfg);\n  if (!e) return false;\n  return e.provider !== 'static' || hasModelFiles(e.model);\n}\n\ntype ResolvedEmbedConfig = NonNullable<ReturnType<typeof embedConfig>>;\n\n// True when embed.model names a local path (not a Hugging Face id) that is missing its model\n// files -- nothing will ever fetch it for itself, unlike a downloadable id.\nexport function localModelMissing(e: ResolvedEmbedConfig | null): e is ResolvedEmbedConfig {\n  return e !== null && e.provider === 'static' && !isDownloadable(e.model) && !hasModelFiles(e.model);\n}\n\n// `main` resolves to a sha once per model: a recorded ref pins until its snapshot is\n// removed, so only the first need for an id ever costs this HEAD request.\nasync function resolveSha(model: string): Promise<string> {\n  const existing = readRef(model);\n  if (existing) return existing;\n  const url = `https://huggingface.co/${model}/resolve/main/model.safetensors`;\n  // redirect: manual -- the header rides the Hub's own response; following the LFS/CDN\n  // redirect would read the CDN's headers instead, which do not carry it.\n  let res: Response;\n  try {\n    res = await fetchWithRetry(url, { method: 'HEAD', redirect: 'manual' });\n  } catch (err) {\n    throw new SenseError('EMBED_MODEL', `could not reach ${url}: ${(err as Error).message}`);\n  }\n  const sha = res.headers.get('x-repo-commit');\n  if (!sha) throw new SenseError('EMBED_MODEL', `${url}: response carried no x-repo-commit header`);\n  writeRef(model, sha);\n  return sha;\n}\n\ninterface HfModelInfo {\n  cardData?: { language?: string | string[] };\n  tags?: string[];\n}\n\n// cardData.language is the structured field (verified live: minishlab/potion-retrieval-32M has\n// neither this nor any language tag, so it stays silent; potion-multilingual-128M carries an\n// array here). Tags are a fallback for cards that only tag languages, filtered to recognized\n// codes so an unrelated short tag (format markers etc.) is never mistaken for one.\nfunction languagesFromCard(info: HfModelInfo): string[] | undefined {\n  const lang = info.cardData?.language;\n  if (typeof lang === 'string') return [lang];\n  if (Array.isArray(lang) && lang.length > 0) return lang;\n  const tagLangs = (info.tags ?? []).filter(isKnownLanguageTag);\n  return tagLangs.length > 0 ? tagLangs : undefined;\n}\n\n// Best-effort, cached forever once resolved (even to \"none\"): unlike model weights, missing or\n// unreachable metadata is not an error -- it just means the language-fit check stays off.\nasync function ensureLanguages(model: string): Promise<void> {\n  if (existsSync(languagesPath(model))) return;\n  // A measured entry needs no card and no network, and stays deterministic offline.\n  const measured = MEASURED_MODEL_LANGUAGES[model];\n  if (measured) {\n    writeLanguages(model, measured);\n    return;\n  }\n  let res: Response;\n  try {\n    res = await fetchWithRetry(`https://huggingface.co/api/models/${model}`, {});\n  } catch {\n    return;\n  }\n  if (!res.ok) return;\n  let info: HfModelInfo;\n  try {\n    info = (await res.json()) as HfModelInfo;\n  } catch {\n    return;\n  }\n  writeLanguages(model, languagesFromCard(info) ?? []);\n}\n\nasync function fetchToFile(url: string, dest: string): Promise<void> {\n  let res: Response;\n  try {\n    res = await fetchWithRetry(url, {});\n  } catch (err) {\n    throw new SenseError('EMBED_MODEL', `could not reach ${url}: ${(err as Error).message}`);\n  }\n  if (!res.ok) throw new SenseError('EMBED_MODEL', `${url} -> HTTP ${res.status}`);\n  writeFileSync(`${dest}.part`, Buffer.from(await res.arrayBuffer()));\n  renameSync(`${dest}.part`, dest);\n}\n\n// Fetches an already-known sha straight into its snapshot dir, without touching refs/main --\n// for downloadModel below, and for callers pinning an exact revision (the parity suite).\nexport async function downloadModelRevision(model: string, sha: string, onFile?: (file: string, dir: string) => void): Promise<string> {\n  const dir = snapshotDir(model, sha);\n  mkdirSync(dir, { recursive: true });\n  for (const file of MODEL_FILES) {\n    if (existsSync(join(dir, file))) continue;\n    onFile?.(file, dir);\n    await fetchToFile(`https://huggingface.co/${model}/resolve/${sha}/${file}`, join(dir, file));\n  }\n  return dir;\n}\n\n// The only code path that resolves `main`: a static provider's first construction calls it\n// lazily, `sense download` as an explicit prefetch. Idempotent either way.\nexport async function downloadModel(model: string, onFile?: (file: string, dir: string) => void): Promise<string> {\n  if (!isDownloadable(model)) {\n    throw new SenseError('EMBED_MODEL', `embed.model \"${model}\" is a local path, not a Hugging Face model id, so there is nothing to download; put model.safetensors and tokenizer.json in that directory, or name a model id like \"minishlab/potion-retrieval-32M\"`);\n  }\n  const sha = await resolveSha(model);\n  // Independent of the weights above: a fresh HEAD/GET pair either way, so a lazy first\n  // construction and an explicit prefetch both end up with a cached language verdict.\n  await ensureLanguages(model);\n  return downloadModelRevision(model, sha, onFile);\n}\n"],"names":["existsSync","mkdirSync","renameSync","writeFileSync","join","embedConfig","SenseError","fetchWithRetry","hasModelFiles","isDownloadable","languagesPath","MODEL_FILES","readRef","snapshotDir","writeLanguages","writeRef","isKnownLanguageTag","MEASURED_MODEL_LANGUAGES","MODEL_FILENAMES","modelDir","readLanguages","refsMainPath","modelPresent","cfg","e","provider","model","localModelMissing","resolveSha","existing","url","res","method","redirect","err","message","sha","headers","get","languagesFromCard","info","lang","cardData","language","Array","isArray","length","tagLangs","tags","filter","undefined","ensureLanguages","measured","ok","json","fetchToFile","dest","status","Buffer","from","arrayBuffer","downloadModelRevision","onFile","dir","recursive","file","downloadModel"],"mappings":"AAAA,SAASA,UAAU,EAAEC,SAAS,EAAEC,UAAU,EAAEC,aAAa,QAAQ,UAAU;AAC3E,SAASC,IAAI,QAAQ,YAAY;AAEjC,SAASC,WAAW,QAAQ,qBAAqB;AACjD,SAASC,UAAU,QAAQ,eAAe;AAC1C,SAASC,cAAc,QAAQ,YAAY;AAC3C,SAASC,aAAa,EAAEC,cAAc,EAAEC,aAAa,EAAEC,WAAW,EAAEC,OAAO,EAAEC,WAAW,EAAEC,cAAc,EAAEC,QAAQ,QAAQ,gBAAgB;AAC1I,SAASC,kBAAkB,EAAEC,wBAAwB,QAAQ,iBAAiB;AAE9E,6FAA6F;AAC7F,8FAA8F;AAC9F,wCAAwC;AACxC,SAAST,aAAa,EAAEC,cAAc,EAAES,eAAe,EAAEP,WAAW,EAAEQ,QAAQ,EAAEC,aAAa,EAAEC,YAAY,EAAER,WAAW,EAAEC,cAAc,EAAEC,QAAQ,QAAQ,gBAAgB;AAE1K,6FAA6F;AAC7F,0CAA0C;AAC1C,OAAO,SAASO,aAAaC,GAAW;IACtC,MAAMC,IAAInB,YAAYkB;IACtB,IAAI,CAACC,GAAG,OAAO;IACf,OAAOA,EAAEC,QAAQ,KAAK,YAAYjB,cAAcgB,EAAEE,KAAK;AACzD;AAIA,6FAA6F;AAC7F,4EAA4E;AAC5E,OAAO,SAASC,kBAAkBH,CAA6B;IAC7D,OAAOA,MAAM,QAAQA,EAAEC,QAAQ,KAAK,YAAY,CAAChB,eAAee,EAAEE,KAAK,KAAK,CAAClB,cAAcgB,EAAEE,KAAK;AACpG;AAEA,qFAAqF;AACrF,0EAA0E;AAC1E,eAAeE,WAAWF,KAAa;IACrC,MAAMG,WAAWjB,QAAQc;IACzB,IAAIG,UAAU,OAAOA;IACrB,MAAMC,MAAM,CAAC,uBAAuB,EAAEJ,MAAM,+BAA+B,CAAC;IAC5E,qFAAqF;IACrF,wEAAwE;IACxE,IAAIK;IACJ,IAAI;QACFA,MAAM,MAAMxB,eAAeuB,KAAK;YAAEE,QAAQ;YAAQC,UAAU;QAAS;IACvE,EAAE,OAAOC,KAAK;QACZ,MAAM,IAAI5B,WAAW,eAAe,CAAC,gBAAgB,EAAEwB,IAAI,EAAE,EAAE,AAACI,IAAcC,OAAO,EAAE;IACzF;IACA,MAAMC,MAAML,IAAIM,OAAO,CAACC,GAAG,CAAC;IAC5B,IAAI,CAACF,KAAK,MAAM,IAAI9B,WAAW,eAAe,GAAGwB,IAAI,0CAA0C,CAAC;IAChGf,SAASW,OAAOU;IAChB,OAAOA;AACT;AAOA,+FAA+F;AAC/F,6FAA6F;AAC7F,6FAA6F;AAC7F,mFAAmF;AACnF,SAASG,kBAAkBC,IAAiB;QAIxBA;QAHLA;IAAb,MAAMC,QAAOD,iBAAAA,KAAKE,QAAQ,cAAbF,qCAAAA,eAAeG,QAAQ;IACpC,IAAI,OAAOF,SAAS,UAAU,OAAO;QAACA;KAAK;IAC3C,IAAIG,MAAMC,OAAO,CAACJ,SAASA,KAAKK,MAAM,GAAG,GAAG,OAAOL;IACnD,MAAMM,WAAW,EAACP,aAAAA,KAAKQ,IAAI,cAATR,wBAAAA,aAAa,EAAE,EAAES,MAAM,CAACjC;IAC1C,OAAO+B,SAASD,MAAM,GAAG,IAAIC,WAAWG;AAC1C;AAEA,+FAA+F;AAC/F,0FAA0F;AAC1F,eAAeC,gBAAgBzB,KAAa;QAqBpBa;IApBtB,IAAIvC,WAAWU,cAAcgB,SAAS;IACtC,kFAAkF;IAClF,MAAM0B,WAAWnC,wBAAwB,CAACS,MAAM;IAChD,IAAI0B,UAAU;QACZtC,eAAeY,OAAO0B;QACtB;IACF;IACA,IAAIrB;IACJ,IAAI;QACFA,MAAM,MAAMxB,eAAe,CAAC,kCAAkC,EAAEmB,OAAO,EAAE,CAAC;IAC5E,EAAE,OAAM;QACN;IACF;IACA,IAAI,CAACK,IAAIsB,EAAE,EAAE;IACb,IAAIb;IACJ,IAAI;QACFA,OAAQ,MAAMT,IAAIuB,IAAI;IACxB,EAAE,OAAM;QACN;IACF;IACAxC,eAAeY,QAAOa,qBAAAA,kBAAkBC,mBAAlBD,gCAAAA,qBAA2B,EAAE;AACrD;AAEA,eAAegB,YAAYzB,GAAW,EAAE0B,IAAY;IAClD,IAAIzB;IACJ,IAAI;QACFA,MAAM,MAAMxB,eAAeuB,KAAK,CAAC;IACnC,EAAE,OAAOI,KAAK;QACZ,MAAM,IAAI5B,WAAW,eAAe,CAAC,gBAAgB,EAAEwB,IAAI,EAAE,EAAE,AAACI,IAAcC,OAAO,EAAE;IACzF;IACA,IAAI,CAACJ,IAAIsB,EAAE,EAAE,MAAM,IAAI/C,WAAW,eAAe,GAAGwB,IAAI,SAAS,EAAEC,IAAI0B,MAAM,EAAE;IAC/EtD,cAAc,GAAGqD,KAAK,KAAK,CAAC,EAAEE,OAAOC,IAAI,CAAC,MAAM5B,IAAI6B,WAAW;IAC/D1D,WAAW,GAAGsD,KAAK,KAAK,CAAC,EAAEA;AAC7B;AAEA,6FAA6F;AAC7F,yFAAyF;AACzF,OAAO,eAAeK,sBAAsBnC,KAAa,EAAEU,GAAW,EAAE0B,MAA4C;IAClH,MAAMC,MAAMlD,YAAYa,OAAOU;IAC/BnC,UAAU8D,KAAK;QAAEC,WAAW;IAAK;IACjC,KAAK,MAAMC,QAAQtD,YAAa;QAC9B,IAAIX,WAAWI,KAAK2D,KAAKE,QAAQ;QACjCH,mBAAAA,6BAAAA,OAASG,MAAMF;QACf,MAAMR,YAAY,CAAC,uBAAuB,EAAE7B,MAAM,SAAS,EAAEU,IAAI,CAAC,EAAE6B,MAAM,EAAE7D,KAAK2D,KAAKE;IACxF;IACA,OAAOF;AACT;AAEA,2FAA2F;AAC3F,2EAA2E;AAC3E,OAAO,eAAeG,cAAcxC,KAAa,EAAEoC,MAA4C;IAC7F,IAAI,CAACrD,eAAeiB,QAAQ;QAC1B,MAAM,IAAIpB,WAAW,eAAe,CAAC,aAAa,EAAEoB,MAAM,qMAAqM,CAAC;IAClQ;IACA,MAAMU,MAAM,MAAMR,WAAWF;IAC7B,sFAAsF;IACtF,oFAAoF;IACpF,MAAMyB,gBAAgBzB;IACtB,OAAOmC,sBAAsBnC,OAAOU,KAAK0B;AAC3C"}

package/dist/esm/embed/types.d.ts

@@ -0,0 +1,8 @@
+export interface EmbedProvider {
+    id: string;
+    dims: number;
+    batchCap: number;
+    languages?: string[];
+    embedDocuments(texts: string[]): Promise<Float32Array[]>;
+    embedQuery(text: string): Promise<Float32Array>;
+}

package/dist/esm/embed/types.js

@@ -0,0 +1,3 @@
+// The provider contract every wire protocol implements: a Liskov-substitutable
+// surface so query/search code never branches on provider identity.
+export { };

package/dist/esm/embed/types.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/embed/types.ts"],"sourcesContent":["// The provider contract every wire protocol implements: a Liskov-substitutable\n// surface so query/search code never branches on provider identity.\nexport interface EmbedProvider {\n  id: string; // model identity; participates in the cache key, change -> re-embed\n  dims: number;\n  batchCap: number; // max texts per embedDocuments call\n  languages?: string[]; // declared model languages, for the language-fit check\n  embedDocuments(texts: string[]): Promise<Float32Array[]>;\n  embedQuery(text: string): Promise<Float32Array>;\n}\n"],"names":[],"mappings":"AAAA,+EAA+E;AAC/E,oEAAoE;AACpE,WAOC"}

package/dist/esm/errors.d.ts

@@ -1,4 +1,4 @@
-export type SenseErrorCode = 'CONFIG_NOT_FOUND' | 'CONFIG_EXISTS' | 'CONFIG_INVALID' | 'CONFIG_VERSION_UNSUPPORTED' | 'WATCH_ACTIVE' | 'NOTE_NOT_FOUND' | 'NOTE_AMBIGUOUS' | 'EMBED_DISABLED' | 'EMBED_MODEL' | 'EMBED_MODEL_MISSING' | 'SEARCH_SYNTAX' | 'COLUMN_LIMIT' | 'PRESET_UNKNOWN' | 'PRESET_NOT_SEMANTIC' | 'NOTE_NOT_EMBEDDED';
+export type SenseErrorCode = 'CONFIG_NOT_FOUND' | 'CONFIG_EXISTS' | 'CONFIG_INVALID' | 'CONFIG_VERSION_UNSUPPORTED' | 'WATCH_ACTIVE' | 'NOTE_NOT_FOUND' | 'NOTE_AMBIGUOUS' | 'EMBED_DISABLED' | 'EMBED_MODEL' | 'EMBED_MODEL_MISSING' | 'EMBED_MODEL_MISMATCH' | 'SEARCH_SYNTAX' | 'COLUMN_LIMIT' | 'PRESET_UNKNOWN' | 'PRESET_NOT_SEMANTIC' | 'NOTE_NOT_EMBEDDED';
 export declare class SenseError extends Error {
     code: SenseErrorCode;
     constructor(code: SenseErrorCode, message: string);

package/dist/esm/errors.js.map

@@ -1 +1 @@
-{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/errors.ts"],"sourcesContent":["// Library code throws; only cli.ts prints and exits.\nexport type SenseErrorCode =\n  | 'CONFIG_NOT_FOUND'\n  | 'CONFIG_EXISTS'\n  | 'CONFIG_INVALID'\n  | 'CONFIG_VERSION_UNSUPPORTED'\n  | 'WATCH_ACTIVE'\n  | 'NOTE_NOT_FOUND'\n  | 'NOTE_AMBIGUOUS'\n  | 'EMBED_DISABLED'\n  | 'EMBED_MODEL'\n  | 'EMBED_MODEL_MISSING'\n  | 'SEARCH_SYNTAX'\n  | 'COLUMN_LIMIT'\n  | 'PRESET_UNKNOWN'\n  | 'PRESET_NOT_SEMANTIC'\n  | 'NOTE_NOT_EMBEDDED';\n\nexport class SenseError extends Error {\n  code: SenseErrorCode;\n\n  constructor(code: SenseErrorCode, message: string) {\n    super(message);\n    this.name = 'SenseError';\n    this.code = code;\n  }\n}\n"],"names":["SenseError","Error","code","message","name"],"mappings":"AAAA,qDAAqD;AAkBrD,OAAO,MAAMA,mBAAmBC;IAG9B,YAAYC,IAAoB,EAAEC,OAAe,CAAE;QACjD,KAAK,CAACA;QACN,IAAI,CAACC,IAAI,GAAG;QACZ,IAAI,CAACF,IAAI,GAAGA;IACd;AACF"}
+{"version":3,"sources":["/Users/kevin/Dev/OpenSource/ai/sensemaking/src/errors.ts"],"sourcesContent":["// Library code throws; only cli.ts prints and exits.\nexport type SenseErrorCode =\n  | 'CONFIG_NOT_FOUND'\n  | 'CONFIG_EXISTS'\n  | 'CONFIG_INVALID'\n  | 'CONFIG_VERSION_UNSUPPORTED'\n  | 'WATCH_ACTIVE'\n  | 'NOTE_NOT_FOUND'\n  | 'NOTE_AMBIGUOUS'\n  | 'EMBED_DISABLED'\n  | 'EMBED_MODEL'\n  | 'EMBED_MODEL_MISSING'\n  | 'EMBED_MODEL_MISMATCH'\n  | 'SEARCH_SYNTAX'\n  | 'COLUMN_LIMIT'\n  | 'PRESET_UNKNOWN'\n  | 'PRESET_NOT_SEMANTIC'\n  | 'NOTE_NOT_EMBEDDED';\n\nexport class SenseError extends Error {\n  code: SenseErrorCode;\n\n  constructor(code: SenseErrorCode, message: string) {\n    super(message);\n    this.name = 'SenseError';\n    this.code = code;\n  }\n}\n"],"names":["SenseError","Error","code","message","name"],"mappings":"AAAA,qDAAqD;AAmBrD,OAAO,MAAMA,mBAAmBC;IAG9B,YAAYC,IAAoB,EAAEC,OAAe,CAAE;QACjD,KAAK,CAACA;QACN,IAAI,CAACC,IAAI,GAAG;QACZ,IAAI,CAACF,IAAI,GAAGA;IACd;AACF"}

package/dist/esm/features/embed.d.ts

@@ -1,30 +1,7 @@
-import type { DatabaseSync } from 'node:sqlite';
-import type { Config } from '../config/index.js';
 import type { Feature } from './types.js';
-export interface EmbedProvider {
-    id: string;
-    dims: number;
-    embed(texts: string[]): Promise<Float32Array[]>;
+export interface Chunk {
+    startLine: number;
+    endLine: number;
+    text: string;
 }
 export declare const embed: Feature;
-export declare const MODEL_FILENAMES: string;
-export declare function isDownloadable(model: string): boolean;
-export declare function modelDir(model: string): string;
-export declare function hasModelFiles(model: string): boolean;
-export declare function modelPresent(cfg: Config): boolean;
-export declare function downloadModel(model: string, onFile?: (file: string, dir: string) => void): Promise<string>;
-export declare function embedPending(db: DatabaseSync, cfg: Config, baseDir: string): Promise<void>;
-export declare function semanticCandidates(db: DatabaseSync, cfg: Config, terms: string, fetch: number, allowed?: Set<string>): Promise<Array<{
-    path: string;
-    lines: string;
-    similarity: number;
-}>>;
-export declare function hasEmbedding(db: DatabaseSync, path: string): boolean;
-export declare function similarNotes(db: DatabaseSync, _cfg: Config, path: string, opts: {
-    exclude: Set<string>;
-    allowed?: Set<string>;
-    k: number;
-}): Array<{
-    path: string;
-    similarity: number;
-}>;

package/dist/esm/features/embed.js

@@ -1,19 +1,4 @@
-import { existsSync, mkdirSync, readFileSync, renameSync, writeFileSync } from 'node:fs';
-import { homedir } from 'node:os';
-import { join } from 'node:path';
-import { embedConfig } from '../config/index.js';
-import { SenseError } from '../errors.js';
 import { fenceTracker } from '../fences.js';
-import { progress } from '../progress.js';
-import { parseFile } from '../scan.js';
-// Heading-based chunks, int8 vectors with a per-vector scale, NULL vector = not yet embedded.
-// Reconcile writes dirty rows; embedding tops up on the next search, so staleness costs recall.
-// Storage lever fixed by the bake-off (BENCHMARKING.md): int8 at 256 dims is
-// quality-free vs f32-512 when fused. Queries stay f32 at the same dims.
-const STORE_DIMS = 256;
-// Seed chunks that participate in a `related` scan; see similarNotes for the measurement.
-const TARGET_CHUNK_CAP = 16;
-const BATCH = 64;
 // Deterministic, so embed time can re-derive text from stored line ranges. Heading-delimited,
 // preamble kept, whole body when no headings; the title/summary prefix mirrors bm25 weighting.
 //
@@ -77,334 +62,3 @@ export const embed = {
         return file.embed;
     }
 };
-// --- static type: Model2Vec safetensors + pure-JS tokenizer, model cached in ~/.cache ---
-// Encode convention from model2vec/model.py: no special tokens, drop unk ids, mean-pool,
-// L2-normalize.
-const MODEL_FILES = [
-    'model.safetensors',
-    'tokenizer.json'
-];
-// The pair, for messages that name what a local model directory must contain.
-export const MODEL_FILENAMES = MODEL_FILES.join(' and ');
-// A Hugging Face repo id: one slash, HF's charset. Anything else is a path, used as one rather
-// than flattened into a cache key Windows would reject.
-const HF_MODEL_ID = /^[A-Za-z0-9][\w.-]*\/[A-Za-z0-9][\w.-]*$/;
-// Downloadable iff it names a Hugging Face repo; a local path is the caller's to populate.
-export function isDownloadable(model) {
-    return HF_MODEL_ID.test(model);
-}
-// Machine-wide, not per-tree: `.sense/` is the index a rebuild throws away, while a 124 MB
-// model is shared by every tree on the machine. Honors XDG_CACHE_HOME where it is set;
-// elsewhere ~/.cache, which is also where Hugging Face's own libraries keep theirs.
-function cacheRoot() {
-    const xdg = process.env.XDG_CACHE_HOME;
-    return join(xdg && xdg.length > 0 ? xdg : join(homedir(), '.cache'), 'sensemaking', 'models');
-}
-// A model is either a local directory the caller pointed at, or the cache `sense download`
-// fills. Nothing here fetches: an absent model degrades search to its other signals rather
-// than pulling 124 MB out of a command that reads like a query.
-export function modelDir(model) {
-    if (!HF_MODEL_ID.test(model)) return model;
-    return join(cacheRoot(), model.replace(/\//g, '--'));
-}
-// Both files, so an interrupted download reads as absent and the next one resumes it.
-export function hasModelFiles(model) {
-    const dir = modelDir(model);
-    return MODEL_FILES.every((file)=>existsSync(join(dir, file)));
-}
-// api providers have nothing to download, so they are never "missing" here; an unreachable
-// endpoint surfaces as an EMBED_MODEL error at call time instead.
-export function modelPresent(cfg) {
-    const e = embedConfig(cfg);
-    if (!e) return false;
-    return e.type === 'api' || hasModelFiles(e.model);
-}
-function fetchToFile(url, dest) {
-    return fetch(url).then(async (res)=>{
-        if (!res.ok) throw new SenseError('EMBED_MODEL', `model download failed: ${url} -> HTTP ${res.status}`);
-        writeFileSync(`${dest}.part`, Buffer.from(await res.arrayBuffer()));
-        renameSync(`${dest}.part`, dest);
-    });
-}
-// The only code path that touches the network for weights. `sense download` calls it; no
-// query ever does. Idempotent: a file already on disk is left alone.
-export async function downloadModel(model, onFile) {
-    if (!isDownloadable(model)) {
-        throw new SenseError('EMBED_MODEL', `embed.model "${model}" is a local path, not a Hugging Face model id, so there is nothing to download; put model.safetensors and tokenizer.json in that directory, or name a model id like "minishlab/potion-retrieval-32M"`);
-    }
-    const dir = modelDir(model);
-    mkdirSync(dir, {
-        recursive: true
-    });
-    for (const file of MODEL_FILES){
-        if (existsSync(join(dir, file))) continue;
-        onFile === null || onFile === void 0 ? void 0 : onFile(file, dir);
-        await fetchToFile(`https://huggingface.co/${model}/resolve/main/${file}`, join(dir, file));
-    }
-    return dir;
-}
-async function staticProvider(model) {
-    var _ref;
-    var _tokenizerJson_model, _tokenizerJson_model_vocab, _tokenizerJson_model1;
-    const dir = modelDir(model);
-    for (const file of MODEL_FILES){
-        if (!existsSync(join(dir, file))) {
-            // A local path the caller controls gets told what is missing where; only a repo id can
-            // be fixed by downloading.
-            const fix = isDownloadable(model) ? 'run `sense download`' : `expected ${MODEL_FILENAMES} in that directory`;
-            throw new SenseError('EMBED_MODEL_MISSING', `embed model ${model} is not available (looked in ${dir}); ${fix}`);
-        }
-    }
-    const raw = readFileSync(join(dir, 'model.safetensors'));
-    const headerLen = Number(raw.readBigUInt64LE(0));
-    const header = JSON.parse(raw.subarray(8, 8 + headerLen).toString('utf8'));
-    const entry = Object.entries(header).find(([k])=>k !== '__metadata__');
-    if (!entry || entry[1].dtype !== 'F32') throw new SenseError('EMBED_MODEL', `${model}: expected an F32 safetensors matrix`);
-    const spec = entry[1];
-    const dims = spec.shape[1];
-    const dataStart = raw.byteOffset + 8 + headerLen + spec.data_offsets[0];
-    const matrix = dataStart % 4 === 0 ? new Float32Array(raw.buffer, dataStart, spec.shape[0] * dims) : new Float32Array(raw.buffer.slice(dataStart, dataStart + spec.shape[0] * dims * 4));
-    const tokenizerJson = JSON.parse(readFileSync(join(dir, 'tokenizer.json'), 'utf8'));
-    // Lazy import: the tokenizer loads only on the semantic path, never at CLI startup.
-    const { Tokenizer } = await import('@huggingface/tokenizers');
-    const tok = new Tokenizer(tokenizerJson, {});
-    const unkId = (_ref = (_tokenizerJson_model1 = tokenizerJson.model) === null || _tokenizerJson_model1 === void 0 ? void 0 : (_tokenizerJson_model_vocab = _tokenizerJson_model1.vocab) === null || _tokenizerJson_model_vocab === void 0 ? void 0 : _tokenizerJson_model_vocab[(_tokenizerJson_model = tokenizerJson.model) === null || _tokenizerJson_model === void 0 ? void 0 : _tokenizerJson_model.unk_token]) !== null && _ref !== void 0 ? _ref : -1;
-    function one(text) {
-        // The tokenizer yields undefined (not the unk id) for tokens outside the vocab; an
-        // undefined id would index the matrix at NaN and poison the whole mean-pool -- and the
-        // int8 conversion then stores the NaN vector as all zeros, silently. Keep integers only.
-        const ids = tok.encode(text, {
-            add_special_tokens: false
-        }).ids.filter((id)=>Number.isInteger(id) && id !== unkId);
-        const v = new Float32Array(dims);
-        if (ids.length === 0) return v;
-        for (const id of ids){
-            const off = id * dims;
-            for(let d = 0; d < dims; d++)v[d] += matrix[off + d];
-        }
-        let norm = 0;
-        for(let d = 0; d < dims; d++){
-            v[d] /= ids.length;
-            norm += v[d] * v[d];
-        }
-        norm = Math.sqrt(norm) + 1e-32;
-        for(let d = 0; d < dims; d++)v[d] /= norm;
-        return v;
-    }
-    return {
-        id: `static:${model}`,
-        dims,
-        embed: async (texts)=>texts.map(one)
-    };
-}
-// --- api type: one POST against any OpenAI-compatible /embeddings endpoint ---
-async function apiProvider(model, url, keyEnv) {
-    if (!url) throw new SenseError('EMBED_MODEL', 'features.embed.type "api" requires a url');
-    const base = url.replace(/\/+$/, '');
-    const headers = {
-        'content-type': 'application/json'
-    };
-    const key = keyEnv ? process.env[keyEnv] : undefined;
-    if (key) headers.authorization = `Bearer ${key}`;
-    async function post(texts) {
-        const res = await fetch(`${base}/embeddings`, {
-            method: 'POST',
-            headers,
-            body: JSON.stringify({
-                model,
-                input: texts
-            })
-        });
-        if (!res.ok) throw new SenseError('EMBED_MODEL', `${base}/embeddings -> HTTP ${res.status}`);
-        const body = await res.json();
-        return body.data.map((d)=>Float32Array.from(d.embedding));
-    }
-    const dims = (await post([
-        'dimension probe'
-    ]))[0].length;
-    return {
-        id: `api:${base}:${model}`,
-        dims,
-        embed: post
-    };
-}
-const providers = new Map();
-function getProvider(cfg) {
-    var _e_url;
-    const e = embedConfig(cfg);
-    if (!e) throw new SenseError('EMBED_DISABLED', 'this tree has no embedding model: add an "embed" block naming one to sense.config.json, then run `sense download`');
-    const sig = `${e.type}:${e.model}:${(_e_url = e.url) !== null && _e_url !== void 0 ? _e_url : ''}`;
-    let p = providers.get(sig);
-    if (!p) {
-        p = e.type === 'api' ? apiProvider(e.model, e.url, e.key) : staticProvider(e.model);
-        providers.set(sig, p);
-    }
-    return p;
-}
-// Slice + re-normalize (Matryoshka); optionally round through int8 storage.
-function toStore(full, dims, int8) {
-    const v = new Float32Array(dims);
-    let norm = 0;
-    for(let d = 0; d < dims; d++)norm += full[d] * full[d];
-    norm = Math.sqrt(norm) + 1e-32;
-    for(let d = 0; d < dims; d++)v[d] = full[d] / norm;
-    if (!int8) return {
-        v,
-        scale: 1
-    };
-    let max = 0;
-    for(let d = 0; d < dims; d++)max = Math.max(max, Math.abs(v[d]));
-    return {
-        v,
-        scale: max / 127 || 1
-    };
-}
-// Embed rows whose vector is NULL, re-deriving chunk text from the files through the
-// same parse + chunker that stored the rows.
-export async function embedPending(db, cfg, baseDir) {
-    const provider = await getProvider(cfg); // throws EMBED_DISABLED before touching the table
-    const dirty = db.prepare('SELECT "path", chunk FROM embeddings WHERE vector IS NULL ORDER BY "path", chunk').all();
-    if (dirty.length === 0) return;
-    const storeDims = Math.min(STORE_DIMS, provider.dims);
-    const byPath = new Map();
-    for (const row of dirty){
-        var _byPath_get;
-        const list = (_byPath_get = byPath.get(row.path)) !== null && _byPath_get !== void 0 ? _byPath_get : [];
-        list.push(row.chunk);
-        byPath.set(row.path, list);
-    }
-    const jobs = [];
-    for (const [path, chunkIdxs] of byPath){
-        let chunks;
-        try {
-            // presets/embed are irrelevant here -- re-deriving chunk text for a doc that already
-            // has embeddings rows means the tree had an embedding model at reconcile time.
-            chunks = parseFile({
-                relPath: path,
-                absPath: join(baseDir, path),
-                mtimeMs: 0,
-                ctimeMs: 0,
-                size: 0,
-                presets: [],
-                embed: true
-            }, [
-                embed
-            ]).doc.extracted.embed;
-        } catch  {
-            continue; // vanished since reconcile; the next reconcile removes its rows
-        }
-        for (const idx of chunkIdxs)if (chunks[idx]) jobs.push({
-            path,
-            chunk: idx,
-            text: chunks[idx].text
-        });
-    }
-    const update = db.prepare('UPDATE embeddings SET scale = ?, vector = ? WHERE "path" = ? AND chunk = ?');
-    // The lazy build is the one long silence a first search hits (measured 23s at
-    // 26k notes); progress makes it distinguishable from a hang.
-    const report = progress('embedding chunks', jobs.length);
-    for(let i = 0; i < jobs.length; i += BATCH){
-        const batch = jobs.slice(i, i + BATCH);
-        const vectors = await provider.embed(batch.map((j)=>j.text));
-        db.exec('BEGIN');
-        try {
-            batch.forEach((job, j)=>{
-                const { v, scale } = toStore(vectors[j], storeDims, true);
-                const q = new Int8Array(storeDims);
-                for(let d = 0; d < storeDims; d++)q[d] = Math.round(v[d] / scale);
-                update.run(scale, Buffer.from(q.buffer), job.path, job.chunk);
-            });
-            db.exec('COMMIT');
-        } catch (err) {
-            db.exec('ROLLBACK');
-            throw err;
-        }
-        report.tick(Math.min(i + BATCH, jobs.length));
-    }
-    report.finish();
-}
-// Dequantised int8 dot products land a little either side of a true cosine, so an identical
-// pair prints 1.001 and undermines a column whose whole job is being a bounded number.
-function asCosine(score) {
-    return Math.round(Math.min(1, Math.max(-1, score)) * 1000) / 1000;
-}
-// Best chunk per file by cosine, its line range riding along; FTS5 operators are stripped as
-// lexical syntax. Similarity comes back because the fused score cannot express match quality,
-// and nearest-neighbour search always returns a neighbour however far away.
-export async function semanticCandidates(db, cfg, terms, fetch1, allowed) {
-    var _terms_match;
-    const baseDir = cfg.baseDir;
-    if (!baseDir) throw new SenseError('EMBED_MODEL', 'semantic expansion needs a config with baseDir (use loadConfig/open)');
-    await embedPending(db, cfg, baseDir);
-    const provider = await getProvider(cfg);
-    const storeDims = Math.min(STORE_DIMS, provider.dims);
-    const text = ((_terms_match = terms.match(/[\p{L}\p{N}]+/gu)) !== null && _terms_match !== void 0 ? _terms_match : []).filter((t)=>![
-            'AND',
-            'OR',
-            'NOT',
-            'NEAR'
-        ].includes(t)).join(' ');
-    const { v: qv } = toStore((await provider.embed([
-        text
-    ]))[0], storeDims, false);
-    const rows = db.prepare('SELECT "path", start_line, end_line, scale, vector FROM embeddings WHERE vector IS NOT NULL').all();
-    const best = new Map();
-    for (const row of rows){
-        if (allowed && !allowed.has(row.path)) continue;
-        const q = new Int8Array(row.vector.buffer, row.vector.byteOffset, Math.min(storeDims, row.vector.byteLength));
-        let dot = 0;
-        for(let d = 0; d < q.length; d++)dot += q[d] * qv[d];
-        const score = dot * row.scale;
-        const existing = best.get(row.path);
-        if (!existing || score > existing.score) best.set(row.path, {
-            score,
-            lines: `L${row.start_line}-${row.end_line}`
-        });
-    }
-    return [
-        ...best.entries()
-    ].sort((a, b)=>b[1].score - a[1].score).slice(0, fetch1).map(([path, b])=>({
-            path,
-            lines: b.lines,
-            similarity: asCosine(b.score)
-        }));
-}
-// Whether a note has any chunk with a vector. Distinguishes "nothing is near this note" from
-// "this note has no text", which look the same in an empty result.
-export function hasEmbedding(db, path) {
-    const row = db.prepare('SELECT 1 AS ok FROM embeddings WHERE "path" = ? AND vector IS NOT NULL LIMIT 1').get(path);
-    return row !== undefined;
-}
-// Note-to-note similarity is the max cosine over (target chunk, other chunk) pairs, one linear
-// scan of stored vectors. Reads only what is stored, so it stays sync.
-export function similarNotes(db, _cfg, path, opts) {
-    // Cost is target_chunks x stored_chunks, so a heading-dense seed multiplies a full-corpus
-    // scan (12.7s at 201 chunks/note). Sample evenly, so late sections still get a vote.
-    const targetRows = db.prepare('SELECT scale, vector FROM embeddings WHERE "path" = ? AND vector IS NOT NULL ORDER BY chunk').all(path);
-    if (targetRows.length === 0) return [];
-    const step = Math.max(1, Math.ceil(targetRows.length / TARGET_CHUNK_CAP));
-    const target = targetRows.filter((_, i)=>i % step === 0).map((row)=>({
-            v: new Int8Array(row.vector.buffer, row.vector.byteOffset, row.vector.byteLength),
-            scale: row.scale
-        }));
-    const rows = db.prepare('SELECT "path", scale, vector FROM embeddings WHERE vector IS NOT NULL').all();
-    const best = new Map();
-    for (const row of rows){
-        if (row.path === path || opts.exclude.has(row.path) || opts.allowed && !opts.allowed.has(row.path)) continue;
-        const other = new Int8Array(row.vector.buffer, row.vector.byteOffset, row.vector.byteLength);
-        for (const t of target){
-            let dot = 0;
-            const len = Math.min(t.v.length, other.length);
-            for(let d = 0; d < len; d++)dot += t.v[d] * other[d];
-            const score = dot * t.scale * row.scale;
-            const existing = best.get(row.path);
-            if (existing === undefined || score > existing) best.set(row.path, score);
-        }
-    }
-    return [
-        ...best.entries()
-    ].sort((a, b)=>b[1] - a[1]).slice(0, opts.k).map(([p, score])=>({
-            path: p,
-            similarity: asCosine(score)
-        }));
-}