@cerefox/memory 1.16.1 → 1.17.1

package/dist/bin/cerefox.js

@@ -5318,7 +5318,7 @@ var init_cli_core = __esm(() => {
 });
 
 // src/meta.ts
-var PKG_VERSION = "1.16.1";
+var PKG_VERSION = "1.17.1";
 var init_meta = () => {};
 
 // ../../_shared/config/paths.ts
@@ -23719,24 +23719,6 @@ function getMaxResponseBytes() {
   const n = Number.parseInt(raw, 10);
   return Number.isNaN(n) || n <= 0 ? MAX_RESPONSE_BYTES : n;
 }
-function readEnv(name) {
-  const g = globalThis;
-  const fromProcess = g.process?.env?.[name];
-  if (fromProcess !== undefined && fromProcess !== "")
-    return fromProcess;
-  try {
-    const fromDeno = g.Deno?.env?.get(name);
-    return fromDeno === "" ? undefined : fromDeno;
-  } catch {
-    return;
-  }
-}
-function getSearchAlpha() {
-  return DEFAULT_SEARCH_ALPHA;
-}
-function getMinSearchScore() {
-  return readEnv("CEREFOX_EMBEDDER") === "local" ? DEFAULT_MIN_SEARCH_SCORE_LOCAL : DEFAULT_MIN_SEARCH_SCORE;
-}
 function getConfiguredMinSearchScore() {
   return;
 }
@@ -23793,7 +23775,7 @@ function resolveByteBudget(requested, ceiling) {
     return ceiling;
   return Math.min(Math.max(n, 1), ceiling);
 }
-var MAX_RESPONSE_BYTES = 200000, DEFAULT_MIN_SEARCH_SCORE = 0.5, DEFAULT_MIN_SEARCH_SCORE_LOCAL = 0.6, DEFAULT_SEARCH_ALPHA = 0.7;
+var MAX_RESPONSE_BYTES = 200000;
 var init__utils = __esm(() => {
   init_audit_ops();
 });
@@ -26248,7 +26230,7 @@ var init_bundled_docs = __esm(() => {
 });
 
 // ../../_shared/ef-meta/index.ts
-var EF_VERSION = "1.16.1", CEREFOX_VERSION = "1.16.1", EF_LAST_CHANGED = "1.16.1";
+var EF_VERSION = "1.17.1", CEREFOX_VERSION = "1.17.1", EF_LAST_CHANGED = "1.17.1";
 var init_ef_meta = () => {};
 
 // ../../_shared/compatibility/index.ts
@@ -26387,20 +26369,22 @@ var init_compatibility = __esm(() => {
 // ../../_shared/embeddings/onnx-embedder.ts
 var exports_onnx_embedder = {};
 __export(exports_onnx_embedder, {
+  EmbedderDownloadError: () => EmbedderDownloadError,
   ONNX_MODEL_APPROX_MB: () => ONNX_MODEL_APPROX_MB,
   ONNX_MODEL_DIM: () => ONNX_MODEL_DIM,
   ONNX_MODEL_DTYPE: () => ONNX_MODEL_DTYPE,
   ONNX_MODEL_ID: () => ONNX_MODEL_ID,
   ONNX_MODEL_NAME: () => ONNX_MODEL_NAME,
   buildPrefixedInputs: () => buildPrefixedInputs,
+  downloadModelFiles: () => downloadModelFiles,
   isModelCached: () => isModelCached,
   nomicPrefix: () => nomicPrefix,
   onnxEmbed: () => onnxEmbed,
   warmup: () => warmup
 });
-import { existsSync as existsSync10, mkdirSync as mkdirSync4 } from "node:fs";
+import { existsSync as existsSync10, mkdirSync as mkdirSync4, renameSync, statSync as statSync2, writeFileSync as writeFileSync5, appendFileSync } from "node:fs";
 import { homedir as homedir6 } from "node:os";
-import { join as join9 } from "node:path";
+import { dirname as dirname4, join as join9 } from "node:path";
 function nomicPrefix(role) {
   return role === "query" ? "search_query: " : "search_document: ";
 }
@@ -26408,6 +26392,86 @@ function buildPrefixedInputs(texts, role) {
   const p = nomicPrefix(role);
   return texts.map((t) => p + t);
 }
+async function fetchRange(url, start, end, timeoutMs) {
+  const res = await fetch(url, { headers: { Range: `bytes=${start}-${end}` }, signal: AbortSignal.timeout(timeoutMs) });
+  if (res.status === 200) {
+    await res.body?.cancel();
+    return "no-range";
+  }
+  const total = Number(/\/(\d+)\s*$/.exec(res.headers.get("content-range") ?? "")?.[1] ?? 0);
+  if (res.status === 416 && total > 0) {
+    await res.body?.cancel();
+    return { bytes: new Uint8Array(0), total };
+  }
+  if (res.status !== 206)
+    throw new Error(`HTTP ${res.status}`);
+  if (total === 0)
+    throw new Error("partial response without a total size (Content-Range)");
+  const bytes = new Uint8Array(await res.arrayBuffer());
+  const want = Math.min(end, total > 0 ? total - 1 : end) - start + 1;
+  if (bytes.byteLength !== want)
+    throw new Error(`segment ${start}-${end}: got ${bytes.byteLength} bytes, expected ${want}`);
+  return { bytes, total };
+}
+async function downloadModelFiles(remoteHost, onProgress, onDone, opts = {}) {
+  const attempts = opts.attempts ?? DOWNLOAD_ATTEMPTS;
+  const backoffMs = opts.backoffMs ?? ((attempt) => Math.min(30, 2 ** attempt) * 1000);
+  const segment = opts.segmentBytes ?? SEGMENT_BYTES;
+  const timeoutMs = opts.timeoutMs ?? REQUEST_TIMEOUT_MS;
+  const dir = getCacheDir();
+  const base = remoteHost.endsWith("/") ? remoteHost : `${remoteHost}/`;
+  for (const rel of MODEL_REPO_FILES) {
+    const dest = join9(dir, ONNX_MODEL_ID, rel);
+    if (existsSync10(dest))
+      continue;
+    mkdirSync4(dirname4(dest), { recursive: true });
+    const part = `${dest}.part`;
+    const url = `${base}${ONNX_MODEL_ID}/resolve/main/${rel}`;
+    let failures = 0;
+    let lastError = "";
+    let total = 0;
+    for (;; ) {
+      const have = existsSync10(part) ? statSync2(part).size : 0;
+      if (total > 0 && have >= total)
+        break;
+      try {
+        const got = await fetchRange(url, have, have + segment - 1, timeoutMs);
+        if (got === "no-range") {
+          const res = await fetch(url, { signal: AbortSignal.timeout(Math.max(timeoutMs, ONNX_MODEL_APPROX_MB * 1e5)) });
+          if (!res.ok)
+            throw new Error(`HTTP ${res.status}`);
+          const declared = Number(res.headers.get("content-length") ?? 0);
+          const bytes = new Uint8Array(await res.arrayBuffer());
+          if (declared > 0 && bytes.byteLength !== declared) {
+            throw new Error(`got ${bytes.byteLength} bytes, expected ${declared}`);
+          }
+          writeFileSync5(part, bytes);
+          total = bytes.byteLength;
+        } else {
+          total = got.total;
+          if (have > total) {
+            writeFileSync5(part, new Uint8Array(0));
+            continue;
+          }
+          appendFileSync(part, got.bytes);
+        }
+        failures = 0;
+        onProgress(rel, statSync2(part).size, total);
+      } catch (err) {
+        lastError = err instanceof Error ? err.message : String(err);
+        failures++;
+        if (failures >= attempts)
+          throw new EmbedderDownloadError(`${rel}: ${lastError}`);
+        const wait = backoffMs(failures);
+        process.stderr.write(`[cerefox-embed] ${rel}: ${lastError}; retrying in ${Math.round(wait / 1000)}s (${failures}/${attempts - 1})
+`);
+        await new Promise((r) => setTimeout(r, wait));
+      }
+    }
+    renameSync(part, dest);
+    onDone(rel, statSync2(dest).size);
+  }
+}
 function isModelCached(dir = getCacheDir()) {
   return MODEL_FILES.every((f) => existsSync10(join9(dir, f)));
 }
@@ -26536,9 +26600,9 @@ async function ensurePipeline() {
           progressState.set(file, { ...prior, done: true });
       }
     };
+    await downloadModelFiles(String(transformers.env.remoteHost ?? "https://huggingface.co/"), (file, loaded, total) => progressCallback({ status: "progress", file, loaded, total }), (file, size) => progressCallback({ status: "done", file, total: size }));
     const pipe = await transformers.pipeline("feature-extraction", ONNX_MODEL_ID, {
-      dtype: ONNX_MODEL_DTYPE,
-      progress_callback: progressCallback
+      dtype: ONNX_MODEL_DTYPE
     });
     process.stderr.write(`[cerefox-embed] embedder ready.
 `);
@@ -26582,14 +26646,23 @@ async function onnxEmbed(texts, role) {
   }
   return vectors;
 }
-var ONNX_MODEL_ID = "nomic-ai/nomic-embed-text-v1.5", ONNX_MODEL_NAME = "nomic-embed-text-v1.5", ONNX_MODEL_DTYPE = "q8", ONNX_MODEL_DIM = 768, ONNX_MODEL_APPROX_MB = 130, MODEL_FILES, transformersModule = null, pipelinePromise = null, DEFAULT_ONNX_BATCH = 4;
+var ONNX_MODEL_ID = "nomic-ai/nomic-embed-text-v1.5", ONNX_MODEL_NAME = "nomic-embed-text-v1.5", ONNX_MODEL_DTYPE = "q8", ONNX_MODEL_DIM = 768, ONNX_MODEL_APPROX_MB = 130, MODEL_REPO_FILES, MODEL_FILES, EmbedderDownloadError, DOWNLOAD_ATTEMPTS = 6, SEGMENT_BYTES, REQUEST_TIMEOUT_MS = 120000, transformersModule = null, pipelinePromise = null, DEFAULT_ONNX_BATCH = 4;
 var init_onnx_embedder = __esm(() => {
-  MODEL_FILES = [
+  MODEL_REPO_FILES = [
     "config.json",
     "tokenizer.json",
     "tokenizer_config.json",
     `onnx/model_quantized.onnx`
-  ].map((f) => join9(ONNX_MODEL_ID, f));
+  ];
+  MODEL_FILES = MODEL_REPO_FILES.map((f) => join9(ONNX_MODEL_ID, f));
+  EmbedderDownloadError = class EmbedderDownloadError extends Error {
+    status = 503;
+    constructor(detail) {
+      super(`The local embedding model (${ONNX_MODEL_NAME}, ~${ONNX_MODEL_APPROX_MB} MB) could not be downloaded: ${detail}. ` + "What was downloaded is kept, and the next request resumes it. Check the network and try again.");
+      this.name = "EmbedderDownloadError";
+    }
+  };
+  SEGMENT_BYTES = 4 * 1024 * 1024;
 });
 
 // ../../_shared/embeddings/index.ts
@@ -27138,6 +27211,16 @@ function escapedContentNote(content, channel = "mcp") {
   const remedy = channel === "cli" ? `fix the escaping in the source and re-ingest.` : `re-send with actual characters. For long content, prefer ` + `ingesting from a file or building the document incrementally with ` + `cerefox_insert/cerefox_edit.`;
   return ` Note: content contains ${parts.join(" and ")} sequence(s) against ` + `${m.realNewlines} real newline(s) — if line breaks or quotes were ` + `intended, ` + remedy;
 }
+function escapedTitleNote(title) {
+  const found = [...new Set((title.match(HTML_ENTITY) ?? []).map((e) => e.toLowerCase()))];
+  if (found.length === 0)
+    return "";
+  return ` Note: the title contains HTML entities (${found.join(", ")}), stored literally. ` + `If you meant the characters themselves (e.g. "&" for "&amp;", "<>" for "&lt;&gt;"), ` + `update the title with the actual characters.`;
+}
+var HTML_ENTITY;
+var init_escape_heuristic = __esm(() => {
+  HTML_ENTITY = /&(?:amp|lt|gt|quot|apos|nbsp|#\d{1,6}|#x[0-9a-f]{1,6});/gi;
+});
 
 // ../../_shared/ingest/chunker.ts
 function cpLen(s) {
@@ -51310,6 +51393,7 @@ async function editHandler(supabase, args, ctx) {
 }
 var AUDIT_OP, insertTool, editTool;
 var init_partial_edits2 = __esm(() => {
+  init_escape_heuristic();
   init_partial_edits();
   init__chunker();
   init__utils();
@@ -51436,12 +51520,12 @@ var init_partial_edits2 = __esm(() => {
 });
 
 // ../../_shared/mcp-tools/get-help-content.ts
-var HELP_FULL = '# Cerefox Knowledge Base -- Agent Quick Reference\n\nCerefox is a persistent, shared knowledge base. You have **15 core MCP tools** (14 with CLI equivalents — `cerefox_get_help` is MCP-only), plus 4 dormant relation tools that appear only when `relations_enabled` is on. For the full guide, search Cerefox for "How AI Agents Use Cerefox" or call `cerefox_get_help` to retrieve this content over MCP.\n\n## Tools\n\n| Tool | Purpose | Key params |\n|------|---------|------------|\n| `cerefox_search` | Find documents (hybrid FTS + semantic) | `query` (required), `project_name`, `metadata_filter`, `author` |\n| `cerefox_ingest` | Save or update a document | `title`, `content` (required), `document_id` (update by ID), `expected_content_hash` (**required on content updates** — see rule 10), `last_write_wins`, `update_if_exists`, `project_name` (single, non-destructive add on update), `project_names` (list, destructive replace on update), `metadata` (omit on update to keep existing tags; `{}` clears), `author` |\n| `cerefox_insert` | **Add** to a document without resending it. Cannot destroy content. | `document_id`, `text`, `position` (`end_of_document`/`end_of_section`/`after_heading`/`before_heading`), `expected_content_hash` (required), `anchor_heading` (unless `end_of_document`), `section_part`, `author` |\n| `cerefox_edit` | **Change** parts of a document: 1..n operations applied atomically | `document_id`, `operations` (`insert`/`replace_section`/`delete_section`/`rename_section`), `expected_content_hash` (required), `author` |\n| `cerefox_delete_document` | **Soft**-delete a document (to trash; excluded from search; permanent purge is human-only) | `document_id`, `expected_content_hash` (**required** — a delete must follow a read), `reason` (recorded in the audit log — give one), `author` |\n| `cerefox_restore_document` | Restore a soft-deleted document from the trash (audited inverse of delete; no-op if not deleted) | `document_id` (required), `reason` (recorded in the audit log), `author` |\n| `cerefox_get_document` | Get full document by ID (header includes `content_hash` — the update token), or with `outline: true` just its heading paths, sizes and hash, or with `section: "## Heading"` one section\'s text | `document_id` (required), `outline`, `section`, `section_part`, `author` |\n| `cerefox_list_versions` | Version history of a document | `document_id` (required), `author` |\n| `cerefox_set_relation` ⚑ | Link two documents (`source --rel_type--> target`) | `source_id`, `target_id`, `rel_type` (required), `metadata`, `author` |\n| `cerefox_delete_relation` ⚑ | Remove a relation | `source_id`, `target_id`, `rel_type`, `author` |\n| `cerefox_get_relations` ⚑ | All relations touching a document, both directions | `document_id` |\n| `cerefox_get_neighbors` ⚑ | Walk the graph along ONE relation type | `document_id`, `rel_type` (required), `depth`, `from_time`, `to_time`, `limit` |\n| `cerefox_metadata_search` | Find or list docs by metadata, project, or time (no text query) | `metadata_filter`, `project_name` (list a project\'s docs), `updated_since`, `include_content` — **at least one** of metadata_filter/project_name/updated_since/created_since |\n| `cerefox_list_metadata_keys` | Discover available metadata keys | (none required) |\n| `cerefox_list_projects` | List all projects | (none required) |\n| `cerefox_set_document_metadata` | Change tags WITHOUT resending content. **Merges** by default; a `null` value removes a key | `document_id`, `metadata` (required), `replace` (rare: set exactly this object), `author` |\n| `cerefox_set_document_projects` | Set doc\'s project memberships to exactly the given list (destructive replace; metadata-only, no content change) | `document_id`, `project_names` (required), `author` |\n| `cerefox_get_audit_log` | Query write operation history | `document_id`, `by_author` (filter), `operation`, `since`, `author` |\n| `cerefox_get_help` | Retrieve Cerefox conventions (this reference) over MCP. **Call this whenever uncertain.** | `topic` (optional, case-insensitive H2 substring match) |\n\n⚑ **Opt-in — usually absent.** The four relation tools are hidden unless the\noperator enables them (`relations_enabled`). **Trust your own tool list**: if\nthey are not in it, the feature is switched off for this deployment. That is\nnormal, not an error, and not something to work around.\n\n## Editing part of a document (prefer this over re-sending)\n\n**Re-sending a whole document to change part of it is the main way agents lose\ndata.** You have to reproduce the untouched remainder verbatim, and any drift\nsilently rewrites content nobody asked you to touch — which the caller cannot\ndiff. Use the partial-edit tools instead:\n\n1. **Learn the anchors** — `cerefox_get_document(document_id, outline: true)`.\n   Returns heading paths, per-section sizes and the `content_hash`, without the\n   body. The paths it returns are exactly what `anchor_heading` accepts.\n2. **Add** → `cerefox_insert`. `end_of_document` is a plain append;\n   `end_of_section` adds inside a named section. It is structurally incapable of\n   removing anything, so "I meant to append" cannot become "I replaced the file".\n3. **Look before you overwrite** — `cerefox_get_document(document_id,\n   section: "## Heading")` returns exactly the text a `replace_section` on that\n   anchor would destroy. The outline gives you a section\'s *size*, never its\n   *text*, so on a document you did not write yourself this is the difference\n   between a replace and a blind overwrite.\n4. **Change or remove** → `cerefox_edit`. Put changes that belong together in\n   ONE call: they apply atomically, so a table row and the total it feeds cannot\n   end up disagreeing. To change a single line, `replace_section` on its\n   smallest enclosing heading — that is the intended granularity, not a\n   workaround. To fix a stale heading (`## OPEN TODOs (as of ...)`), use\n   `rename_section`: it changes the heading text and leaves the body and\n   position alone.\n5. All of them require `expected_content_hash` and **have no last-write-wins**. A\n   conflict means someone else changed the document; re-read and decide, do not\n   force it.\n\n**A section runs to the next same-or-higher heading, or to the end of the\ndocument.** So `end_of_document` inserts land inside the *last* section, and\nreplacing or deleting that section removes them too. A large shrink in the\nresponse is your warning; `cerefox_list_versions` has the previous content.\n\n**When an anchor is ambiguous the tool refuses and hands you the options** — a\nrepeated heading returns the qualifying paths, and a section with both its own\ncontent and sub-sections returns both `section_part` choices. That is a\nrecoverable answer, not a failure: retry with what it gave you.\n\n## Essential Rules\n\n1. **Search before ingesting** -- check if the document exists first.\n2. **Prefer ID-based updates** -- pass `document_id` from search results for deterministic updates. Falls back to title-matching with `update_if_exists: true`.\n3. **Set `author`** to your name on every call, reads and writes alike (e.g., "Claude Code", "archiver"). Same parameter on every tool. (`requestor` is still accepted everywhere as the pre-1.13.1 alias.) On the CLI it is `--author` on every command too (plus `--author-type` on writes); or rely on `CEREFOX_AUTHOR_NAME`/`CEREFOX_AUTHOR_TYPE` env vars set in the user\'s `.env`.\n4. **Use `document_id` from search results** `[id: uuid]` for get_document and list_versions.\n5. **`max_bytes` has to fit a whole document.** Search returns COMPLETE documents, so a budget smaller than the top hit fits nothing. You get a header-only list saying so (never "No results found." — that means the store really has nothing). Raise `max_bytes`, or read one document with `cerefox_get_document` using `outline: true` or `section`.\n6. **Add metadata** -- at minimum `type` ("decision-log", "research", "design-doc") and `status` ("active", "draft").\n7. **Write for retrieval: the title does real work.** The document title is indexed at the **highest weight** *and* prepended to every chunk before it is embedded, so it steers both halves of hybrid search (keyword and semantic) for every chunk in the document. Name the document with the distinctive terms someone would actually search for -- "Cerefox Response Size Limits", not "Notes" or "Update 3". Renaming re-indexes and re-embeds, so correcting a vague title is cheap and takes effect immediately. Inside the content, write structured Markdown with H1/H2/H3 headings: the chunker follows them, and a chunk\'s own heading carries the same weight as the title.\n8. **Deletes are soft (recoverable); permanent purge is web-UI-only.** `cerefox_delete_document` requires the document\'s `content_hash` as you read it (read before you delete) and takes a `reason` — give one; it is what the human reviewing the trash sees. `cerefox_restore_document` undoes a mistaken delete (also audited, also takes a `reason`). Always surface deletes AND restores to the user. Once a human purges from the web UI, the document is gone for good; so is one auto-purged after `trash_retention_days`, if the operator has turned trash auto-purge on.\n9. **Cross-doc links inside content**: **always use `[Text](document-uuid)`.** UUIDs are the only fully reliable link form — stable across title changes, never ambiguous, no encoding gotchas. Every `cerefox_search` result shows `[id: <uuid>]` after the title; grab it and use it. Title-based linking (`[Text](<Title With Spaces>)`) is fragile (breaks on colons, parens, ampersands, brackets — silently navigates to wrong page) — **don\'t write title-based links**; do an extra search to get the UUID instead. Repo-path forms (`[Text](docs/path.md)`) exist for repo-ingested files; don\'t construct manually. **The server validates `](uuid)` links on every write** (v1.7.0): a link to a nonexistent id rejects the write, naming the offender — that means you mangled the UUID; re-read the source and correct it, do not retry unchanged. Example ids go in backticks (code is not validated). `[[Wikilinks]]` may dangle. See `AGENT_GUIDE.md → Writing linkable content` for the full rule.\n10. **Concurrency: content updates require `expected_content_hash`.** Pass the `content_hash` you last saw — every read shows one (`cerefox_get_document` incl. outline mode, `cerefox_search`, `cerefox_metadata_search`) and **every write returns the new one, including create** (v1.3.0, #189), so after writing you already hold the token for your next edit; no re-read needed. If it\'s stale you get a **conflict** — re-read the document, merge your changes into the latest content, retry with the new hash. **Never resolve a conflict by overwriting blindly** — the current content includes another writer\'s work. `last_write_wins: true` skips the check; use it ONLY when an external source of truth makes conflicts meaningless (file re-sync), never to silence a conflict.\n11. **Search: prefer a few distinctive terms; heed `below confidence`.** When nothing clears the relevance threshold, `cerefox_search` returns the closest candidates prefixed with a `below confidence` warning instead of an empty set — that flag means **weak signal, not absent knowledge**: check the candidates\' scores and titles before concluding the KB lacks the content. A truly empty response means nothing even weakly related exists.\n12. **Relations express how documents relate; lifecycle tells you if knowledge is still good.** Use `cerefox_set_relation` when one document supersedes, contradicts, references, or continues another. `supersedes` marks the target **superseded**; `contradicts` marks **both** stale; `related_to`/`duplicates`/`contradicts` are symmetric (both directions written). Any other type string is accepted without special behaviour. When a search result or `cerefox_get_relations` shows a neighbour marked `[superseded]` or `[stale]`, say so rather than presenting it as current.\n13. **Project memberships — non-destructive by default**: on `cerefox_ingest` updates, **`project_name` (singular) is a non-destructive add** (ensures membership, preserves others). Use **`project_names` (list)** when you want to set the doc\'s full project set in one call (destructive replace). For metadata-only project changes without writing content, use **`cerefox_set_document_projects(document_id, project_names)`** — that tool is the destructive-replace contract made explicit. Never call `cerefox_set_document_projects` with a single name when you mean "add" — that would REMOVE the doc from all other projects. When in doubt, use `cerefox_ingest` with singular `project_name`.\n\n## Update Workflow (ID-based -- preferred)\n\n```\nsearch("topic") -> find doc [id: abc123] -> get_document(abc123) -> note its content_hash -> modify ->\ningest(title="Same Title", content="...", document_id="abc123",\n       expected_content_hash="<the hash you read>", author="my-agent")\n```\n\nOn a **conflict** error: get_document again (fresh content + fresh hash) -> merge your changes -> retry with the new hash.\n\n## Update Workflow (title-based -- fallback)\n\n```\nsearch("topic") -> find doc (note its hash) -> modify ->\ningest(title="Same Title", content="...", update_if_exists=true,\n       expected_content_hash="<the hash you read>", author="my-agent")\n```\n\n## Catch-Up Workflow\n\n```\nmetadata_search(metadata_filter={"type": "decision-log"}, updated_since="2026-03-28T00:00:00Z")\n```\n\n## CLI fallback (when MCP is unavailable)\n\nIf `cerefox_search` is not in your tool list, your user has likely installed the Cerefox CLI. The canonical invocation is plain **`cerefox <subcommand>`** (the TypeScript CLI, installed via `npm install -g @cerefox/memory`). It uses a resource-verb shape (`cerefox document get`, `cerefox project list`, …).\n\nSame operations, same conventions. Full reference: [`docs/guides/cli.md`](docs/guides/cli.md). CLI flag names match MCP parameter names exactly (e.g. `metadata_filter` ↔ `--metadata-filter`); common flags also have single-letter short forms (`-f`, `-p`, `-c`, `-m`, `-u`, `-a`). Use the canonical long name (what `--help` shows) or its short form — there are no long-form aliases like `--filter` or `--count`.\n\n| MCP tool | CLI |\n|---|---|\n| `cerefox_search` | `cerefox search "<q>" --author "<your-name>"` |\n| `cerefox_ingest` (paste) | `printf \'...\' \\| cerefox document ingest --paste --title "<t>" --author "<your-name>" --author-type agent` |\n| `cerefox_ingest` (update by ID) | `printf \'...\' \\| cerefox document ingest --paste --title "<t>" --document-id "<uuid>" --expected-content-hash "<hash>" --author "<your-name>" --author-type agent` |\n| `cerefox_get_document` | `cerefox document get <id> --version-id <vid> --author "<your-name>"` |\n| `cerefox_list_versions` | `cerefox document version list <id> --author "<your-name>"` |\n| `cerefox_list_projects` | `cerefox project list --author "<your-name>"` |\n| `cerefox_list_metadata_keys` | `cerefox metadata keys` |\n| `cerefox_insert` | `cerefox document insert <id> -t "<text>" -p <position> -a "<anchor-heading>" -e "<hash>" --author "<your-name>" --author-type agent` |\n| `cerefox_edit` | `cerefox document edit-parts <id> --operations \'<json>\' -e "<hash>" --author "<your-name>" --author-type agent` |\n| `cerefox_delete_document` | `cerefox document delete <id> --reason "<why>" --author "<your-name>" --author-type agent --yes` (confirms interactively instead of requiring the hash) |\n| `cerefox_restore_document` | `cerefox document restore <id> --reason "<why>" --author "<your-name>" --author-type agent` |\n| `cerefox_metadata_search` | `cerefox metadata search --metadata-filter \'<json>\' --author "<your-name>"` (list a project: `cerefox document list --project <name>`) |\n| `cerefox_set_document_metadata` | `cerefox document set-metadata <id> --set key=value` (also `--remove key`, `--json \'{...}\'`, `--replace`) |\n| `cerefox_set_document_projects` | `cerefox document set-projects <id> <name...> --author "<your-name>" --author-type agent` (or `--clear` to remove all) |\n| `cerefox_get_audit_log` | `cerefox audit list --author "<your-name>"` (add `--json` for scripted access) |\n| `cerefox_get_help` | `cerefox guides show agent-quick-reference` (or `cerefox guides list` for the full bundled-docs index) |\n\n**Set identity on every call**, exactly as you would on MCP:\n- Writes (`document ingest`, `document ingest-dir`): `--author "<your-name>" --author-type agent`\n- Reads: `--author "<your-name>"` (the same flag; `--requestor` still works as a hidden alias)\n\nOr have your user set `CEREFOX_AUTHOR_NAME` / `CEREFOX_AUTHOR_TYPE` / `CEREFOX_REQUESTOR_NAME` in their `.env` to apply defaults once.\n\n## Timestamps are UTC\n\nEvery timestamp Cerefox returns — `created_at` on audit entries, version\nhistory, document metadata — is **UTC**, and now carries its `Z` marker so it\ncannot be mistaken for local time.\n\n**When you write a date into a document\'s CONTENT, use your own clock, not a\nCerefox timestamp.** These are different things: a timestamp records when the\nserver stored something; a date in a log entry or a heading is authored content\nand belongs to your timezone. An agent working a Pacific afternoon read\n`2026-08-11` from version history, wrote "8/11" into its entries, and put a\nday\'s work in the future — the timestamp was correct, and copying it into\ncontent was not.\n\nCerefox deliberately does not convert to local time on the API or MCP paths.\n"Local" has no server-side meaning: the remote MCP server runs in a cloud\nfunction whose local time *is* UTC, while a local MCP server runs in yours, so\nthe same document would report two different times depending on transport. The\nweb UI converts because a browser knows the viewer\'s timezone; nothing\nserver-side does.\n\n## Mistakes that have actually happened\n\nEach of these comes from a real agent session, and each is easy to make.\n\n- **`cerefox_ingest` always replaces the ENTIRE document.** Never a section.\n  Before sending, check that the tool name matches the intent: if the intent is\n  "change one section", the call is `cerefox_edit` with `replace_section`. A\n  section-sized edit sent as a full ingest truncated a 13,000-character index to\n  a single word. It was recovered from version history within the minute, but\n  only because it was noticed immediately.\n\n- **Do not include the anchor\'s own heading in your text.** `replace_section`\n  keeps the heading and `insert` places your text inside the section, so\n  including it produces two. This is now refused rather than silently applied,\n  but the shape is worth knowing: it happened twice in one session, the second\n  time while trying to repair the first. A *deeper* sub-heading inside your text\n  is fine.\n\n- **Content between sections belongs to the section ABOVE it.** A section runs\n  to the next heading of the same or higher level, so a `---` rule, a note, or\n  any trailing text sitting just above the next heading is part of the section\n  before it — even when it visually reads as belonging below. Replacing that\n  section takes it too. An agent hit exactly this: a `---` that separated two\n  major sections disappeared when the section above it was replaced. The write\n  was correct by the addressing rules; the surprise is that "the end of this\n  section" is further down the page than it looks. Note the loss warning will\n  not catch it if your replacement text is longer than what it replaced, since\n  there is then no net loss to report.\n\n- **To change only tags, use `cerefox_set_document_metadata`, never `cerefox_ingest`.**\n  Ingest replaces the whole document, so re-sending it to set one tag carries the\n  full transcription risk for no reason. The metadata tool merges: the keys you\n  pass are set, everything else is left alone, so you do not need to read the\n  document first and cannot drop a tag another agent set. Pass `null` as a value\n  to remove a key.\n\n- **Never partial-edit to fix a partial edit.** If a write leaves unexpected\n  structure, stop. Use `cerefox_list_versions`, retrieve the last good version,\n  and re-ingest cleanly. Repairing edits with more edits compounds the damage.\n\n- **A rejected batch is safe.** Operations in one `cerefox_edit` are\n  all-or-nothing: if any is invalid, nothing is written. A refusal costs you a\n  retry, not data — so prefer one call for changes that belong together, and do\n  not split a batch to "make it more likely to succeed".\n\n- **Read before replacing.** `cerefox_get_document(section: "## Heading")`\n  returns exactly what a `replace_section` on that anchor would overwrite. Use it\n  for any section you did not write in this session. The outline gives a\n  section\'s *size*, never its *text*.\n\n- **Verify after writing** — read the result back before reporting success, and\n  report what the read actually shows.\n\n- **Partial edits cannot change a document\'s stored TITLE.** `rename_section`\n  changes a heading inside the content; the title is a separate field and still\n  needs `cerefox_ingest`.\n\n- **If a capability seems missing from one server, suspect your client first.**\n  Local and remote run the same code. **Every `cerefox_get_help()` response\n  begins with the server\'s version and the operations it registers** — you do\n  not need a special topic, and the *absence* of that block is itself an answer:\n  a server that does not print it predates v1.5.0. If that\n  disagrees with your tool list, the client is holding a list it fetched before\n  an upgrade — clients cache it at connect time. Ask the user to restart the\n  client. Do not record a capability difference between servers as a fact; every\n  such report so far has been a stale client.\n- Long inline bodies can arrive with literal `\\n`/`\\"` (the author over-escaped; Cerefox stores bytes faithfully). For long or quote-dense content, ingest from a file or build incrementally with `cerefox_insert`; read back multi-line writes.\n', HELP_SECTIONS, HELP_SECTION_HEADINGS;
+var HELP_FULL = '# Cerefox Knowledge Base -- Agent Quick Reference\n\nCerefox is a persistent, shared knowledge base. You have **15 core MCP tools** (14 with CLI equivalents — `cerefox_get_help` is MCP-only), plus 4 dormant relation tools that appear only when `relations_enabled` is on. For the full guide, search Cerefox for "How AI Agents Use Cerefox" or call `cerefox_get_help` to retrieve this content over MCP.\n\n## Tools\n\n| Tool | Purpose | Key params |\n|------|---------|------------|\n| `cerefox_search` | Find documents (hybrid FTS + semantic) | `query` (required), `project_name`, `metadata_filter`, `author` |\n| `cerefox_ingest` | Save or update a document | `title`, `content` (required), `document_id` (update by ID), `expected_content_hash` (**required on content updates** — see rule 10), `last_write_wins`, `update_if_exists`, `project_name` (single, non-destructive add on update), `project_names` (list, destructive replace on update), `metadata` (omit on update to keep existing tags; `{}` clears), `author` |\n| `cerefox_insert` | **Add** to a document without resending it. Cannot destroy content. | `document_id`, `text`, `position` (`end_of_document`/`end_of_section`/`after_heading`/`before_heading`), `expected_content_hash` (required), `anchor_heading` (unless `end_of_document`), `section_part`, `author` |\n| `cerefox_edit` | **Change** parts of a document: 1..n operations applied atomically | `document_id`, `operations` (`insert`/`replace_section`/`delete_section`/`rename_section`), `expected_content_hash` (required), `author` |\n| `cerefox_delete_document` | **Soft**-delete a document (to trash; excluded from search; permanent purge is human-only) | `document_id`, `expected_content_hash` (**required** — a delete must follow a read), `reason` (recorded in the audit log — give one), `author` |\n| `cerefox_restore_document` | Restore a soft-deleted document from the trash (audited inverse of delete; no-op if not deleted) | `document_id` (required), `reason` (recorded in the audit log), `author` |\n| `cerefox_get_document` | Get full document by ID (header includes `content_hash` — the update token), or with `outline: true` just its heading paths, sizes and hash, or with `section: "## Heading"` one section\'s text | `document_id` (required), `outline`, `section`, `section_part`, `author` |\n| `cerefox_list_versions` | Version history of a document | `document_id` (required), `author` |\n| `cerefox_set_relation` ⚑ | Link two documents (`source --rel_type--> target`) | `source_id`, `target_id`, `rel_type` (required), `metadata`, `author` |\n| `cerefox_delete_relation` ⚑ | Remove a relation | `source_id`, `target_id`, `rel_type`, `author` |\n| `cerefox_get_relations` ⚑ | All relations touching a document, both directions | `document_id` |\n| `cerefox_get_neighbors` ⚑ | Walk the graph along ONE relation type | `document_id`, `rel_type` (required), `depth`, `from_time`, `to_time`, `limit` |\n| `cerefox_metadata_search` | Find or list docs by metadata, project, or time (no text query) | `metadata_filter`, `project_name` (list a project\'s docs), `updated_since`, `include_content` — **at least one** of metadata_filter/project_name/updated_since/created_since |\n| `cerefox_list_metadata_keys` | Discover available metadata keys | (none required) |\n| `cerefox_list_projects` | List all projects | (none required) |\n| `cerefox_set_document_metadata` | Change tags WITHOUT resending content. **Merges** by default; a `null` value removes a key | `document_id`, `metadata` (required), `replace` (rare: set exactly this object), `author` |\n| `cerefox_set_document_projects` | Set doc\'s project memberships to exactly the given list (destructive replace; metadata-only, no content change) | `document_id`, `project_names` (required), `author` |\n| `cerefox_get_audit_log` | Query write operation history | `document_id`, `by_author` (filter), `operation`, `since`, `author` |\n| `cerefox_get_help` | Retrieve Cerefox conventions (this reference) over MCP. **Call this whenever uncertain.** | `topic` (optional, case-insensitive H2 substring match) |\n\n⚑ **Opt-in — usually absent.** The four relation tools are hidden unless the\noperator enables them (`relations_enabled`). **Trust your own tool list**: if\nthey are not in it, the feature is switched off for this deployment. That is\nnormal, not an error, and not something to work around.\n\n## Editing part of a document (prefer this over re-sending)\n\n**Re-sending a whole document to change part of it is the main way agents lose\ndata.** You have to reproduce the untouched remainder verbatim, and any drift\nsilently rewrites content nobody asked you to touch — which the caller cannot\ndiff. Use the partial-edit tools instead:\n\n1. **Learn the anchors** — `cerefox_get_document(document_id, outline: true)`.\n   Returns heading paths, per-section sizes and the `content_hash`, without the\n   body. The paths it returns are exactly what `anchor_heading` accepts.\n2. **Add** → `cerefox_insert`. `end_of_document` is a plain append;\n   `end_of_section` adds inside a named section. It is structurally incapable of\n   removing anything, so "I meant to append" cannot become "I replaced the file".\n3. **Look before you overwrite** — `cerefox_get_document(document_id,\n   section: "## Heading")` returns exactly the text a `replace_section` on that\n   anchor would destroy. The outline gives you a section\'s *size*, never its\n   *text*, so on a document you did not write yourself this is the difference\n   between a replace and a blind overwrite.\n4. **Change or remove** → `cerefox_edit`. Put changes that belong together in\n   ONE call: they apply atomically, so a table row and the total it feeds cannot\n   end up disagreeing. To change a single line, `replace_section` on its\n   smallest enclosing heading — that is the intended granularity, not a\n   workaround. To fix a stale heading (`## OPEN TODOs (as of ...)`), use\n   `rename_section`: it changes the heading text and leaves the body and\n   position alone.\n5. All of them require `expected_content_hash` and **have no last-write-wins**. A\n   conflict means someone else changed the document; re-read and decide, do not\n   force it.\n\n**A section runs to the next same-or-higher heading, or to the end of the\ndocument.** So `end_of_document` inserts land inside the *last* section, and\nreplacing or deleting that section removes them too. A large shrink in the\nresponse is your warning; `cerefox_list_versions` has the previous content.\n\n**When an anchor is ambiguous the tool refuses and hands you the options** — a\nrepeated heading returns the qualifying paths, and a section with both its own\ncontent and sub-sections returns both `section_part` choices. That is a\nrecoverable answer, not a failure: retry with what it gave you.\n\n## Essential Rules\n\n1. **Search before ingesting** -- check if the document exists first.\n2. **Prefer ID-based updates** -- pass `document_id` from search results for deterministic updates. Falls back to title-matching with `update_if_exists: true`.\n3. **Set `author`** to your name on every call, reads and writes alike (e.g., "Claude Code", "archiver"). Same parameter on every tool. (`requestor` is still accepted everywhere as the pre-1.13.1 alias.) On the CLI it is `--author` on every command too (plus `--author-type` on writes); or rely on `CEREFOX_AUTHOR_NAME`/`CEREFOX_AUTHOR_TYPE` env vars set in the user\'s `.env`.\n4. **Use `document_id` from search results** `[id: uuid]` for get_document and list_versions.\n5. **`max_bytes` has to fit a whole document.** Search returns COMPLETE documents, so a budget smaller than the top hit fits nothing. You get a header-only list saying so (never "No results found." — that means the store really has nothing). Raise `max_bytes`, or read one document with `cerefox_get_document` using `outline: true` or `section`.\n6. **Add metadata** -- at minimum `type` ("decision-log", "research", "design-doc") and `status` ("active", "draft").\n7. **Write for retrieval: the title does real work.** The document title is indexed at the **highest weight** *and* prepended to every chunk before it is embedded, so it steers both halves of hybrid search (keyword and semantic) for every chunk in the document. Name the document with the distinctive terms someone would actually search for -- "Cerefox Response Size Limits", not "Notes" or "Update 3". Renaming re-indexes and re-embeds, so correcting a vague title is cheap and takes effect immediately. Write the characters themselves: `&` and `<>`, never `&amp;` or `&lt;&gt;` (entities are stored literally and the write reply will say so). Inside the content, write structured Markdown with H1/H2/H3 headings: the chunker follows them, and a chunk\'s own heading carries the same weight as the title.\n8. **Deletes are soft (recoverable); permanent purge is web-UI-only.** `cerefox_delete_document` requires the document\'s `content_hash` as you read it (read before you delete) and takes a `reason` — give one; it is what the human reviewing the trash sees. `cerefox_restore_document` undoes a mistaken delete (also audited, also takes a `reason`). Always surface deletes AND restores to the user. Once a human purges from the web UI, the document is gone for good; so is one auto-purged after `trash_retention_days`, if the operator has turned trash auto-purge on.\n9. **Cross-doc links inside content**: **always use `[Text](document-uuid)`.** UUIDs are the only fully reliable link form — stable across title changes, never ambiguous, no encoding gotchas. Every `cerefox_search` result shows `[id: <uuid>]` after the title; grab it and use it. Title-based linking (`[Text](<Title With Spaces>)`) is fragile (breaks on colons, parens, ampersands, brackets — silently navigates to wrong page) — **don\'t write title-based links**; do an extra search to get the UUID instead. Repo-path forms (`[Text](docs/path.md)`) exist for repo-ingested files; don\'t construct manually. **The server validates `](uuid)` links on every write** (v1.7.0): a link to a nonexistent id rejects the write, naming the offender — that means you mangled the UUID; re-read the source and correct it, do not retry unchanged. Example ids go in backticks (code is not validated). `[[Wikilinks]]` may dangle. See `AGENT_GUIDE.md → Writing linkable content` for the full rule.\n10. **Concurrency: content updates require `expected_content_hash`.** Pass the `content_hash` you last saw — every read shows one (`cerefox_get_document` incl. outline mode, `cerefox_search`, `cerefox_metadata_search`) and **every write returns the new one, including create** (v1.3.0, #189), so after writing you already hold the token for your next edit; no re-read needed. If it\'s stale you get a **conflict** — re-read the document, merge your changes into the latest content, retry with the new hash. **Never resolve a conflict by overwriting blindly** — the current content includes another writer\'s work. `last_write_wins: true` skips the check; use it ONLY when an external source of truth makes conflicts meaningless (file re-sync), never to silence a conflict.\n11. **Search: prefer a few distinctive terms; heed `below confidence`.** When nothing clears the relevance threshold, `cerefox_search` returns the closest candidates prefixed with a `below confidence` warning instead of an empty set — that flag means **weak signal, not absent knowledge**: check the candidates\' scores and titles before concluding the KB lacks the content. A truly empty response means nothing even weakly related exists.\n12. **Relations express how documents relate; lifecycle tells you if knowledge is still good.** Use `cerefox_set_relation` when one document supersedes, contradicts, references, or continues another. `supersedes` marks the target **superseded**; `contradicts` marks **both** stale; `related_to`/`duplicates`/`contradicts` are symmetric (both directions written). Any other type string is accepted without special behaviour. When a search result or `cerefox_get_relations` shows a neighbour marked `[superseded]` or `[stale]`, say so rather than presenting it as current.\n13. **Project memberships — non-destructive by default**: on `cerefox_ingest` updates, **`project_name` (singular) is a non-destructive add** (ensures membership, preserves others). Use **`project_names` (list)** when you want to set the doc\'s full project set in one call (destructive replace). For metadata-only project changes without writing content, use **`cerefox_set_document_projects(document_id, project_names)`** — that tool is the destructive-replace contract made explicit. Never call `cerefox_set_document_projects` with a single name when you mean "add" — that would REMOVE the doc from all other projects. When in doubt, use `cerefox_ingest` with singular `project_name`.\n\n## Update Workflow (ID-based -- preferred)\n\n```\nsearch("topic") -> find doc [id: abc123] -> get_document(abc123) -> note its content_hash -> modify ->\ningest(title="Same Title", content="...", document_id="abc123",\n       expected_content_hash="<the hash you read>", author="my-agent")\n```\n\nOn a **conflict** error: get_document again (fresh content + fresh hash) -> merge your changes -> retry with the new hash.\n\n## Update Workflow (title-based -- fallback)\n\n```\nsearch("topic") -> find doc (note its hash) -> modify ->\ningest(title="Same Title", content="...", update_if_exists=true,\n       expected_content_hash="<the hash you read>", author="my-agent")\n```\n\n## Catch-Up Workflow\n\n```\nmetadata_search(metadata_filter={"type": "decision-log"}, updated_since="2026-03-28T00:00:00Z")\n```\n\n## CLI fallback (when MCP is unavailable)\n\nIf `cerefox_search` is not in your tool list, your user has likely installed the Cerefox CLI. The canonical invocation is plain **`cerefox <subcommand>`** (the TypeScript CLI, installed via `npm install -g @cerefox/memory`). It uses a resource-verb shape (`cerefox document get`, `cerefox project list`, …).\n\nSame operations, same conventions. Full reference: [`docs/guides/cli.md`](docs/guides/cli.md). CLI flag names match MCP parameter names exactly (e.g. `metadata_filter` ↔ `--metadata-filter`); common flags also have single-letter short forms (`-f`, `-p`, `-c`, `-m`, `-u`, `-a`). Use the canonical long name (what `--help` shows) or its short form — there are no long-form aliases like `--filter` or `--count`.\n\n| MCP tool | CLI |\n|---|---|\n| `cerefox_search` | `cerefox search "<q>" --author "<your-name>"` |\n| `cerefox_ingest` (paste) | `printf \'...\' \\| cerefox document ingest --paste --title "<t>" --author "<your-name>" --author-type agent` |\n| `cerefox_ingest` (update by ID) | `printf \'...\' \\| cerefox document ingest --paste --title "<t>" --document-id "<uuid>" --expected-content-hash "<hash>" --author "<your-name>" --author-type agent` |\n| `cerefox_get_document` | `cerefox document get <id> --version-id <vid> --author "<your-name>"` |\n| `cerefox_list_versions` | `cerefox document version list <id> --author "<your-name>"` |\n| `cerefox_list_projects` | `cerefox project list --author "<your-name>"` |\n| `cerefox_list_metadata_keys` | `cerefox metadata keys` |\n| `cerefox_insert` | `cerefox document insert <id> -t "<text>" -p <position> -a "<anchor-heading>" -e "<hash>" --author "<your-name>" --author-type agent` |\n| `cerefox_edit` | `cerefox document edit-parts <id> --operations \'<json>\' -e "<hash>" --author "<your-name>" --author-type agent` |\n| `cerefox_delete_document` | `cerefox document delete <id> --reason "<why>" --author "<your-name>" --author-type agent --yes` (confirms interactively instead of requiring the hash) |\n| `cerefox_restore_document` | `cerefox document restore <id> --reason "<why>" --author "<your-name>" --author-type agent` |\n| `cerefox_metadata_search` | `cerefox metadata search --metadata-filter \'<json>\' --author "<your-name>"` (list a project: `cerefox document list --project <name>`) |\n| `cerefox_set_document_metadata` | `cerefox document set-metadata <id> --set key=value` (also `--remove key`, `--json \'{...}\'`, `--replace`) |\n| `cerefox_set_document_projects` | `cerefox document set-projects <id> <name...> --author "<your-name>" --author-type agent` (or `--clear` to remove all) |\n| `cerefox_get_audit_log` | `cerefox audit list --author "<your-name>"` (add `--json` for scripted access) |\n| `cerefox_get_help` | `cerefox guides show agent-quick-reference` (or `cerefox guides list` for the full bundled-docs index) |\n\n**Set identity on every call**, exactly as you would on MCP:\n- Writes (`document ingest`, `document ingest-dir`): `--author "<your-name>" --author-type agent`\n- Reads: `--author "<your-name>"` (the same flag; `--requestor` still works as a hidden alias)\n\nOr have your user set `CEREFOX_AUTHOR_NAME` / `CEREFOX_AUTHOR_TYPE` / `CEREFOX_REQUESTOR_NAME` in their `.env` to apply defaults once.\n\n## Timestamps are UTC\n\nEvery timestamp Cerefox returns — `created_at` on audit entries, version\nhistory, document metadata — is **UTC**, and now carries its `Z` marker so it\ncannot be mistaken for local time.\n\n**When you write a date into a document\'s CONTENT, use your own clock, not a\nCerefox timestamp.** These are different things: a timestamp records when the\nserver stored something; a date in a log entry or a heading is authored content\nand belongs to your timezone. An agent working a Pacific afternoon read\n`2026-08-11` from version history, wrote "8/11" into its entries, and put a\nday\'s work in the future — the timestamp was correct, and copying it into\ncontent was not.\n\nCerefox deliberately does not convert to local time on the API or MCP paths.\n"Local" has no server-side meaning: the remote MCP server runs in a cloud\nfunction whose local time *is* UTC, while a local MCP server runs in yours, so\nthe same document would report two different times depending on transport. The\nweb UI converts because a browser knows the viewer\'s timezone; nothing\nserver-side does.\n\n## Mistakes that have actually happened\n\nEach of these comes from a real agent session, and each is easy to make.\n\n- **`cerefox_ingest` always replaces the ENTIRE document.** Never a section.\n  Before sending, check that the tool name matches the intent: if the intent is\n  "change one section", the call is `cerefox_edit` with `replace_section`. A\n  section-sized edit sent as a full ingest truncated a 13,000-character index to\n  a single word. It was recovered from version history within the minute, but\n  only because it was noticed immediately.\n\n- **Do not include the anchor\'s own heading in your text.** `replace_section`\n  keeps the heading and `insert` places your text inside the section, so\n  including it produces two. This is now refused rather than silently applied,\n  but the shape is worth knowing: it happened twice in one session, the second\n  time while trying to repair the first. A *deeper* sub-heading inside your text\n  is fine.\n\n- **Content between sections belongs to the section ABOVE it.** A section runs\n  to the next heading of the same or higher level, so a `---` rule, a note, or\n  any trailing text sitting just above the next heading is part of the section\n  before it — even when it visually reads as belonging below. Replacing that\n  section takes it too. An agent hit exactly this: a `---` that separated two\n  major sections disappeared when the section above it was replaced. The write\n  was correct by the addressing rules; the surprise is that "the end of this\n  section" is further down the page than it looks. Note the loss warning will\n  not catch it if your replacement text is longer than what it replaced, since\n  there is then no net loss to report.\n\n- **To change only tags, use `cerefox_set_document_metadata`, never `cerefox_ingest`.**\n  Ingest replaces the whole document, so re-sending it to set one tag carries the\n  full transcription risk for no reason. The metadata tool merges: the keys you\n  pass are set, everything else is left alone, so you do not need to read the\n  document first and cannot drop a tag another agent set. Pass `null` as a value\n  to remove a key.\n\n- **Never partial-edit to fix a partial edit.** If a write leaves unexpected\n  structure, stop. Use `cerefox_list_versions`, retrieve the last good version,\n  and re-ingest cleanly. Repairing edits with more edits compounds the damage.\n\n- **A rejected batch is safe.** Operations in one `cerefox_edit` are\n  all-or-nothing: if any is invalid, nothing is written. A refusal costs you a\n  retry, not data — so prefer one call for changes that belong together, and do\n  not split a batch to "make it more likely to succeed".\n\n- **Read before replacing.** `cerefox_get_document(section: "## Heading")`\n  returns exactly what a `replace_section` on that anchor would overwrite. Use it\n  for any section you did not write in this session. The outline gives a\n  section\'s *size*, never its *text*.\n\n- **Verify after writing** — read the result back before reporting success, and\n  report what the read actually shows.\n\n- **Partial edits cannot change a document\'s stored TITLE.** `rename_section`\n  changes a heading inside the content; the title is a separate field and still\n  needs `cerefox_ingest`.\n\n- **If a capability seems missing from one server, suspect your client first.**\n  Local and remote run the same code. **Every `cerefox_get_help()` response\n  begins with the server\'s version and the operations it registers** — you do\n  not need a special topic, and the *absence* of that block is itself an answer:\n  a server that does not print it predates v1.5.0. If that\n  disagrees with your tool list, the client is holding a list it fetched before\n  an upgrade — clients cache it at connect time. Ask the user to restart the\n  client. Do not record a capability difference between servers as a fact; every\n  such report so far has been a stale client.\n- Long inline bodies can arrive with literal `\\n`/`\\"` (the author over-escaped; Cerefox stores bytes faithfully). For long or quote-dense content, ingest from a file or build incrementally with `cerefox_insert`; read back multi-line writes.\n', HELP_SECTIONS, HELP_SECTION_HEADINGS;
 var init_get_help_content = __esm(() => {
   HELP_SECTIONS = {
     Tools: "## Tools\n\n| Tool | Purpose | Key params |\n|------|---------|------------|\n| `cerefox_search` | Find documents (hybrid FTS + semantic) | `query` (required), `project_name`, `metadata_filter`, `author` |\n| `cerefox_ingest` | Save or update a document | `title`, `content` (required), `document_id` (update by ID), `expected_content_hash` (**required on content updates** — see rule 10), `last_write_wins`, `update_if_exists`, `project_name` (single, non-destructive add on update), `project_names` (list, destructive replace on update), `metadata` (omit on update to keep existing tags; `{}` clears), `author` |\n| `cerefox_insert` | **Add** to a document without resending it. Cannot destroy content. | `document_id`, `text`, `position` (`end_of_document`/`end_of_section`/`after_heading`/`before_heading`), `expected_content_hash` (required), `anchor_heading` (unless `end_of_document`), `section_part`, `author` |\n| `cerefox_edit` | **Change** parts of a document: 1..n operations applied atomically | `document_id`, `operations` (`insert`/`replace_section`/`delete_section`/`rename_section`), `expected_content_hash` (required), `author` |\n| `cerefox_delete_document` | **Soft**-delete a document (to trash; excluded from search; permanent purge is human-only) | `document_id`, `expected_content_hash` (**required** — a delete must follow a read), `reason` (recorded in the audit log — give one), `author` |\n| `cerefox_restore_document` | Restore a soft-deleted document from the trash (audited inverse of delete; no-op if not deleted) | `document_id` (required), `reason` (recorded in the audit log), `author` |\n| `cerefox_get_document` | Get full document by ID (header includes `content_hash` — the update token), or with `outline: true` just its heading paths, sizes and hash, or with `section: \"## Heading\"` one section's text | `document_id` (required), `outline`, `section`, `section_part`, `author` |\n| `cerefox_list_versions` | Version history of a document | `document_id` (required), `author` |\n| `cerefox_set_relation` ⚑ | Link two documents (`source --rel_type--> target`) | `source_id`, `target_id`, `rel_type` (required), `metadata`, `author` |\n| `cerefox_delete_relation` ⚑ | Remove a relation | `source_id`, `target_id`, `rel_type`, `author` |\n| `cerefox_get_relations` ⚑ | All relations touching a document, both directions | `document_id` |\n| `cerefox_get_neighbors` ⚑ | Walk the graph along ONE relation type | `document_id`, `rel_type` (required), `depth`, `from_time`, `to_time`, `limit` |\n| `cerefox_metadata_search` | Find or list docs by metadata, project, or time (no text query) | `metadata_filter`, `project_name` (list a project's docs), `updated_since`, `include_content` — **at least one** of metadata_filter/project_name/updated_since/created_since |\n| `cerefox_list_metadata_keys` | Discover available metadata keys | (none required) |\n| `cerefox_list_projects` | List all projects | (none required) |\n| `cerefox_set_document_metadata` | Change tags WITHOUT resending content. **Merges** by default; a `null` value removes a key | `document_id`, `metadata` (required), `replace` (rare: set exactly this object), `author` |\n| `cerefox_set_document_projects` | Set doc's project memberships to exactly the given list (destructive replace; metadata-only, no content change) | `document_id`, `project_names` (required), `author` |\n| `cerefox_get_audit_log` | Query write operation history | `document_id`, `by_author` (filter), `operation`, `since`, `author` |\n| `cerefox_get_help` | Retrieve Cerefox conventions (this reference) over MCP. **Call this whenever uncertain.** | `topic` (optional, case-insensitive H2 substring match) |\n\n⚑ **Opt-in — usually absent.** The four relation tools are hidden unless the\noperator enables them (`relations_enabled`). **Trust your own tool list**: if\nthey are not in it, the feature is switched off for this deployment. That is\nnormal, not an error, and not something to work around.",
     "Editing part of a document (prefer this over re-sending)": '## Editing part of a document (prefer this over re-sending)\n\n**Re-sending a whole document to change part of it is the main way agents lose\ndata.** You have to reproduce the untouched remainder verbatim, and any drift\nsilently rewrites content nobody asked you to touch — which the caller cannot\ndiff. Use the partial-edit tools instead:\n\n1. **Learn the anchors** — `cerefox_get_document(document_id, outline: true)`.\n   Returns heading paths, per-section sizes and the `content_hash`, without the\n   body. The paths it returns are exactly what `anchor_heading` accepts.\n2. **Add** → `cerefox_insert`. `end_of_document` is a plain append;\n   `end_of_section` adds inside a named section. It is structurally incapable of\n   removing anything, so "I meant to append" cannot become "I replaced the file".\n3. **Look before you overwrite** — `cerefox_get_document(document_id,\n   section: "## Heading")` returns exactly the text a `replace_section` on that\n   anchor would destroy. The outline gives you a section\'s *size*, never its\n   *text*, so on a document you did not write yourself this is the difference\n   between a replace and a blind overwrite.\n4. **Change or remove** → `cerefox_edit`. Put changes that belong together in\n   ONE call: they apply atomically, so a table row and the total it feeds cannot\n   end up disagreeing. To change a single line, `replace_section` on its\n   smallest enclosing heading — that is the intended granularity, not a\n   workaround. To fix a stale heading (`## OPEN TODOs (as of ...)`), use\n   `rename_section`: it changes the heading text and leaves the body and\n   position alone.\n5. All of them require `expected_content_hash` and **have no last-write-wins**. A\n   conflict means someone else changed the document; re-read and decide, do not\n   force it.\n\n**A section runs to the next same-or-higher heading, or to the end of the\ndocument.** So `end_of_document` inserts land inside the *last* section, and\nreplacing or deleting that section removes them too. A large shrink in the\nresponse is your warning; `cerefox_list_versions` has the previous content.\n\n**When an anchor is ambiguous the tool refuses and hands you the options** — a\nrepeated heading returns the qualifying paths, and a section with both its own\ncontent and sub-sections returns both `section_part` choices. That is a\nrecoverable answer, not a failure: retry with what it gave you.',
-    "Essential Rules": '## Essential Rules\n\n1. **Search before ingesting** -- check if the document exists first.\n2. **Prefer ID-based updates** -- pass `document_id` from search results for deterministic updates. Falls back to title-matching with `update_if_exists: true`.\n3. **Set `author`** to your name on every call, reads and writes alike (e.g., "Claude Code", "archiver"). Same parameter on every tool. (`requestor` is still accepted everywhere as the pre-1.13.1 alias.) On the CLI it is `--author` on every command too (plus `--author-type` on writes); or rely on `CEREFOX_AUTHOR_NAME`/`CEREFOX_AUTHOR_TYPE` env vars set in the user\'s `.env`.\n4. **Use `document_id` from search results** `[id: uuid]` for get_document and list_versions.\n5. **`max_bytes` has to fit a whole document.** Search returns COMPLETE documents, so a budget smaller than the top hit fits nothing. You get a header-only list saying so (never "No results found." — that means the store really has nothing). Raise `max_bytes`, or read one document with `cerefox_get_document` using `outline: true` or `section`.\n6. **Add metadata** -- at minimum `type` ("decision-log", "research", "design-doc") and `status` ("active", "draft").\n7. **Write for retrieval: the title does real work.** The document title is indexed at the **highest weight** *and* prepended to every chunk before it is embedded, so it steers both halves of hybrid search (keyword and semantic) for every chunk in the document. Name the document with the distinctive terms someone would actually search for -- "Cerefox Response Size Limits", not "Notes" or "Update 3". Renaming re-indexes and re-embeds, so correcting a vague title is cheap and takes effect immediately. Inside the content, write structured Markdown with H1/H2/H3 headings: the chunker follows them, and a chunk\'s own heading carries the same weight as the title.\n8. **Deletes are soft (recoverable); permanent purge is web-UI-only.** `cerefox_delete_document` requires the document\'s `content_hash` as you read it (read before you delete) and takes a `reason` — give one; it is what the human reviewing the trash sees. `cerefox_restore_document` undoes a mistaken delete (also audited, also takes a `reason`). Always surface deletes AND restores to the user. Once a human purges from the web UI, the document is gone for good; so is one auto-purged after `trash_retention_days`, if the operator has turned trash auto-purge on.\n9. **Cross-doc links inside content**: **always use `[Text](document-uuid)`.** UUIDs are the only fully reliable link form — stable across title changes, never ambiguous, no encoding gotchas. Every `cerefox_search` result shows `[id: <uuid>]` after the title; grab it and use it. Title-based linking (`[Text](<Title With Spaces>)`) is fragile (breaks on colons, parens, ampersands, brackets — silently navigates to wrong page) — **don\'t write title-based links**; do an extra search to get the UUID instead. Repo-path forms (`[Text](docs/path.md)`) exist for repo-ingested files; don\'t construct manually. **The server validates `](uuid)` links on every write** (v1.7.0): a link to a nonexistent id rejects the write, naming the offender — that means you mangled the UUID; re-read the source and correct it, do not retry unchanged. Example ids go in backticks (code is not validated). `[[Wikilinks]]` may dangle. See `AGENT_GUIDE.md → Writing linkable content` for the full rule.\n10. **Concurrency: content updates require `expected_content_hash`.** Pass the `content_hash` you last saw — every read shows one (`cerefox_get_document` incl. outline mode, `cerefox_search`, `cerefox_metadata_search`) and **every write returns the new one, including create** (v1.3.0, #189), so after writing you already hold the token for your next edit; no re-read needed. If it\'s stale you get a **conflict** — re-read the document, merge your changes into the latest content, retry with the new hash. **Never resolve a conflict by overwriting blindly** — the current content includes another writer\'s work. `last_write_wins: true` skips the check; use it ONLY when an external source of truth makes conflicts meaningless (file re-sync), never to silence a conflict.\n11. **Search: prefer a few distinctive terms; heed `below confidence`.** When nothing clears the relevance threshold, `cerefox_search` returns the closest candidates prefixed with a `below confidence` warning instead of an empty set — that flag means **weak signal, not absent knowledge**: check the candidates\' scores and titles before concluding the KB lacks the content. A truly empty response means nothing even weakly related exists.\n12. **Relations express how documents relate; lifecycle tells you if knowledge is still good.** Use `cerefox_set_relation` when one document supersedes, contradicts, references, or continues another. `supersedes` marks the target **superseded**; `contradicts` marks **both** stale; `related_to`/`duplicates`/`contradicts` are symmetric (both directions written). Any other type string is accepted without special behaviour. When a search result or `cerefox_get_relations` shows a neighbour marked `[superseded]` or `[stale]`, say so rather than presenting it as current.\n13. **Project memberships — non-destructive by default**: on `cerefox_ingest` updates, **`project_name` (singular) is a non-destructive add** (ensures membership, preserves others). Use **`project_names` (list)** when you want to set the doc\'s full project set in one call (destructive replace). For metadata-only project changes without writing content, use **`cerefox_set_document_projects(document_id, project_names)`** — that tool is the destructive-replace contract made explicit. Never call `cerefox_set_document_projects` with a single name when you mean "add" — that would REMOVE the doc from all other projects. When in doubt, use `cerefox_ingest` with singular `project_name`.',
+    "Essential Rules": '## Essential Rules\n\n1. **Search before ingesting** -- check if the document exists first.\n2. **Prefer ID-based updates** -- pass `document_id` from search results for deterministic updates. Falls back to title-matching with `update_if_exists: true`.\n3. **Set `author`** to your name on every call, reads and writes alike (e.g., "Claude Code", "archiver"). Same parameter on every tool. (`requestor` is still accepted everywhere as the pre-1.13.1 alias.) On the CLI it is `--author` on every command too (plus `--author-type` on writes); or rely on `CEREFOX_AUTHOR_NAME`/`CEREFOX_AUTHOR_TYPE` env vars set in the user\'s `.env`.\n4. **Use `document_id` from search results** `[id: uuid]` for get_document and list_versions.\n5. **`max_bytes` has to fit a whole document.** Search returns COMPLETE documents, so a budget smaller than the top hit fits nothing. You get a header-only list saying so (never "No results found." — that means the store really has nothing). Raise `max_bytes`, or read one document with `cerefox_get_document` using `outline: true` or `section`.\n6. **Add metadata** -- at minimum `type` ("decision-log", "research", "design-doc") and `status` ("active", "draft").\n7. **Write for retrieval: the title does real work.** The document title is indexed at the **highest weight** *and* prepended to every chunk before it is embedded, so it steers both halves of hybrid search (keyword and semantic) for every chunk in the document. Name the document with the distinctive terms someone would actually search for -- "Cerefox Response Size Limits", not "Notes" or "Update 3". Renaming re-indexes and re-embeds, so correcting a vague title is cheap and takes effect immediately. Write the characters themselves: `&` and `<>`, never `&amp;` or `&lt;&gt;` (entities are stored literally and the write reply will say so). Inside the content, write structured Markdown with H1/H2/H3 headings: the chunker follows them, and a chunk\'s own heading carries the same weight as the title.\n8. **Deletes are soft (recoverable); permanent purge is web-UI-only.** `cerefox_delete_document` requires the document\'s `content_hash` as you read it (read before you delete) and takes a `reason` — give one; it is what the human reviewing the trash sees. `cerefox_restore_document` undoes a mistaken delete (also audited, also takes a `reason`). Always surface deletes AND restores to the user. Once a human purges from the web UI, the document is gone for good; so is one auto-purged after `trash_retention_days`, if the operator has turned trash auto-purge on.\n9. **Cross-doc links inside content**: **always use `[Text](document-uuid)`.** UUIDs are the only fully reliable link form — stable across title changes, never ambiguous, no encoding gotchas. Every `cerefox_search` result shows `[id: <uuid>]` after the title; grab it and use it. Title-based linking (`[Text](<Title With Spaces>)`) is fragile (breaks on colons, parens, ampersands, brackets — silently navigates to wrong page) — **don\'t write title-based links**; do an extra search to get the UUID instead. Repo-path forms (`[Text](docs/path.md)`) exist for repo-ingested files; don\'t construct manually. **The server validates `](uuid)` links on every write** (v1.7.0): a link to a nonexistent id rejects the write, naming the offender — that means you mangled the UUID; re-read the source and correct it, do not retry unchanged. Example ids go in backticks (code is not validated). `[[Wikilinks]]` may dangle. See `AGENT_GUIDE.md → Writing linkable content` for the full rule.\n10. **Concurrency: content updates require `expected_content_hash`.** Pass the `content_hash` you last saw — every read shows one (`cerefox_get_document` incl. outline mode, `cerefox_search`, `cerefox_metadata_search`) and **every write returns the new one, including create** (v1.3.0, #189), so after writing you already hold the token for your next edit; no re-read needed. If it\'s stale you get a **conflict** — re-read the document, merge your changes into the latest content, retry with the new hash. **Never resolve a conflict by overwriting blindly** — the current content includes another writer\'s work. `last_write_wins: true` skips the check; use it ONLY when an external source of truth makes conflicts meaningless (file re-sync), never to silence a conflict.\n11. **Search: prefer a few distinctive terms; heed `below confidence`.** When nothing clears the relevance threshold, `cerefox_search` returns the closest candidates prefixed with a `below confidence` warning instead of an empty set — that flag means **weak signal, not absent knowledge**: check the candidates\' scores and titles before concluding the KB lacks the content. A truly empty response means nothing even weakly related exists.\n12. **Relations express how documents relate; lifecycle tells you if knowledge is still good.** Use `cerefox_set_relation` when one document supersedes, contradicts, references, or continues another. `supersedes` marks the target **superseded**; `contradicts` marks **both** stale; `related_to`/`duplicates`/`contradicts` are symmetric (both directions written). Any other type string is accepted without special behaviour. When a search result or `cerefox_get_relations` shows a neighbour marked `[superseded]` or `[stale]`, say so rather than presenting it as current.\n13. **Project memberships — non-destructive by default**: on `cerefox_ingest` updates, **`project_name` (singular) is a non-destructive add** (ensures membership, preserves others). Use **`project_names` (list)** when you want to set the doc\'s full project set in one call (destructive replace). For metadata-only project changes without writing content, use **`cerefox_set_document_projects(document_id, project_names)`** — that tool is the destructive-replace contract made explicit. Never call `cerefox_set_document_projects` with a single name when you mean "add" — that would REMOVE the doc from all other projects. When in doubt, use `cerefox_ingest` with singular `project_name`.',
     "Update Workflow (ID-based -- preferred)": `## Update Workflow (ID-based -- preferred)
 
 \`\`\`
@@ -51760,7 +51844,7 @@ async function handler6(supabase, args, ctx) {
       await ensureDocumentInProject(supabase, existingDoc.id, project_name, { author, authorType: author_type });
     }
     const note = overrideNote;
-    return `Document updated: "${title}" (id: ${existingDoc.id}), ${chunks.length} chunk(s), ${totalChars} chars. New content_hash: ${contentHash}.${note}${escapedContentNote(content)}`;
+    return `Document updated: "${title}" (id: ${existingDoc.id}), ${chunks.length} chunk(s), ${totalChars} chars. New content_hash: ${contentHash}.${note}${escapedContentNote(content)}${escapedTitleNote(title)}`;
   }
   if (update_if_exists) {
     let { data: existing } = await supabase.from("cerefox_documents").select("id, title, content_hash, deleted_at").eq("title", title).is("deleted_at", null).order("updated_at", { ascending: false }).limit(1);
@@ -51822,7 +51906,7 @@ async function handler6(supabase, args, ctx) {
       } else if (project_name) {
         await ensureDocumentInProject(supabase, existingDoc.id, project_name, { author, authorType: author_type });
       }
-      return `Document updated: "${existingDoc.title}" (id: ${existingDoc.id}), ${chunks.length} chunk(s), ${totalChars} chars. New content_hash: ${contentHash}.${escapedContentNote(content)}`;
+      return `Document updated: "${existingDoc.title}" (id: ${existingDoc.id}), ${chunks.length} chunk(s), ${totalChars} chars. New content_hash: ${contentHash}.${escapedContentNote(content)}${escapedTitleNote(title)}`;
     }
   }
   const { data: hashMatch } = await supabase.from("cerefox_documents").select("id, title, deleted_at").eq("content_hash", contentHash).limit(1);
@@ -51876,10 +51960,11 @@ async function handler6(supabase, args, ctx) {
     result_count: chunks.length
   });
   const projectInfo = project_name ? `, project: "${project_name}"` : "";
-  return `Document saved: "${title}" (id: ${documentId}), ${chunks.length} chunk(s), ${totalChars} chars${projectInfo}. ` + `content_hash: ${contentHash} — pass it as expected_content_hash on your next edit.` + escapedContentNote(content);
+  return `Document saved: "${title}" (id: ${documentId}), ${chunks.length} chunk(s), ${totalChars} chars${projectInfo}. ` + `content_hash: ${contentHash} — pass it as expected_content_hash on your next edit.` + escapedContentNote(content) + escapedTitleNote(title);
 }
 var ingestTool;
 var init_ingest = __esm(() => {
+  init_escape_heuristic();
   init__chunker();
   init__projects();
   init__utils();
@@ -52525,7 +52610,7 @@ var init_search = __esm(() => {
         },
         min_term_coverage: {
           type: "number",
-          description: "Keyword OR-fallback confidence bar 0–1 (default 0.5): fraction of the query's meaningful terms a result must match to count as a confident hit; weaker matches return flagged below-confidence. 0 = any matching term. Needs schema ≥ 0.9.1."
+          description: "Keyword OR-fallback confidence bar 0–1 (default: server-configured, else 0.67): fraction of the query's meaningful terms a result must match to count as a confident hit; weaker matches return flagged below-confidence. 0 = any matching term. Needs schema ≥ 0.9.1."
         },
         max_bytes: {
           type: "integer",
@@ -65705,9 +65790,10 @@ var CONFIG_CATALOG = [
   },
   {
     key: "min_search_score",
-    description: "Minimum cosine similarity for vector-side results. Use 0.6 with the local embedder.",
+    description: "Minimum cosine similarity for vector-side results. Unset, it follows the store's embedder: 0.5 OpenAI, 0.6 local (nomic).",
     kind: "number",
     defaultValue: "0.5",
+    defaultRpc: "cerefox_default_min_search_score",
     min: 0,
     max: 1,
     group: "Retrieval"
@@ -65716,7 +65802,7 @@ var CONFIG_CATALOG = [
     key: "min_term_coverage",
     description: "Fraction of a query's meaningful terms a keyword OR-fallback match must cover to count as confident.",
     kind: "number",
-    defaultValue: "0.5",
+    defaultValue: "0.67",
     min: 0,
     max: 1,
     group: "Retrieval"
@@ -71778,7 +71864,7 @@ init_config();
 init_config();
 init_compatibility();
 init_server_assets();
-import { existsSync as existsSync11, readFileSync as readFileSync9, realpathSync, statSync as statSync2 } from "node:fs";
+import { existsSync as existsSync11, readFileSync as readFileSync9, realpathSync, statSync as statSync3 } from "node:fs";
 import { homedir as homedir7 } from "node:os";
 import { join as join10 } from "node:path";
 
@@ -72019,7 +72105,7 @@ function checkConfig() {
   let modeDetail = "";
   if (process.platform !== "win32") {
     try {
-      const mode = statSync2(envPath).mode & 511;
+      const mode = statSync3(envPath).mode & 511;
       if (mode & 63) {
         return {
           name: "config",
@@ -72376,6 +72462,17 @@ async function checkEmbedderMismatch() {
     const recorded = [...new Set(rows.map((r) => r.embedder_primary))];
     const stale = recorded.filter((r) => r !== active);
     if (stale.length === 0) {
+      if (resolveEmbedderKind() === "local") {
+        await Promise.resolve().then(() => init_onnx_embedder());
+        if (!isModelCached()) {
+          return {
+            name: EMBEDDER_CHECK_NAME,
+            status: "warn",
+            detail: `configured "${active}", but the model is not downloaded yet; the first search or write will fetch it (~130 MB).`,
+            hint: "Fetch it now with `cerefox embedder-warmup` (Cerefox Local: `cerefox-local embedder-warmup`); it resumes if the connection drops."
+          };
+        }
+      }
       return {
         name: EMBEDDER_CHECK_NAME,
         status: "ok",
@@ -73146,6 +73243,7 @@ function registerGetDoc(program) {
 
 // src/cli/commands/ingest.ts
 init_dist4();
+init_escape_heuristic();
 init_cli_core();
 init_config();
 import { readFileSync as readFileSync11 } from "node:fs";
@@ -74034,7 +74132,7 @@ init_dist4();
 init_cli_core();
 init_config();
 var import_cli_progress = __toESM(require_cli_progress(), 1);
-import { readdirSync as readdirSync4, statSync as statSync3 } from "node:fs";
+import { readdirSync as readdirSync4, statSync as statSync4 } from "node:fs";
 import { basename as basename3, extname as extname4, join as join11 } from "node:path";
 function walk(dir, extensions) {
   let entries;
@@ -74048,7 +74146,7 @@ function walk(dir, extensions) {
     const full = join11(dir, name);
     let stat;
     try {
-      stat = statSync3(full);
+      stat = statSync4(full);
     } catch {
       continue;
     }
@@ -74151,10 +74249,10 @@ import {
   existsSync as existsSync12,
   mkdirSync as mkdirSync5,
   readFileSync as readFileSync14,
-  writeFileSync as writeFileSync5
+  writeFileSync as writeFileSync6
 } from "node:fs";
 import { homedir as homedir8 } from "node:os";
-import { dirname as dirname4, join as join12 } from "node:path";
+import { dirname as dirname5, join as join12 } from "node:path";
 async function readConfigFile(path) {
   if (!existsSync12(path)) {
     throw userError(`--config file not found: ${path}`);
@@ -74458,8 +74556,8 @@ async function postWriteLifecycle(envPath, options) {
   println(c.dim(`  Config in effect: ${envPath}`));
 }
 function writeAnswersTo(target, answers) {
-  mkdirSync5(dirname4(target), { recursive: true });
-  writeFileSync5(target, buildEnvFile(answers), "utf8");
+  mkdirSync5(dirname5(target), { recursive: true });
+  writeFileSync6(target, buildEnvFile(answers), "utf8");
   if (process.platform !== "win32") {
     try {
       chmodSync(target, 384);
@@ -74522,7 +74620,7 @@ async function action23(options) {
     const ch = await promptMigrationChoice();
     println("");
     if (ch === "c") {
-      mkdirSync5(dirname4(homeEnv), { recursive: true });
+      mkdirSync5(dirname5(homeEnv), { recursive: true });
       copyFileSync2(cwdEnv, homeEnv);
       if (process.platform !== "win32") {
         try {
@@ -75139,7 +75237,7 @@ function registerMigrateFormat(program) {
 // src/cli/commands/restore.ts
 init_cli_core();
 init_client();
-import { existsSync as existsSync13, readFileSync as readFileSync15, readdirSync as readdirSync5, statSync as statSync4 } from "node:fs";
+import { existsSync as existsSync13, readFileSync as readFileSync15, readdirSync as readdirSync5, statSync as statSync5 } from "node:fs";
 import { homedir as homedir9 } from "node:os";
 import { join as join13, resolve as resolve4 } from "node:path";
 function expandHome2(path) {
@@ -75154,10 +75252,10 @@ function resolveBackupFile(target) {
   if (!existsSync13(path)) {
     throw userError(`Backup path not found: ${target}`);
   }
-  const stat = statSync4(path);
+  const stat = statSync5(path);
   if (stat.isFile())
     return path;
-  const candidates = readdirSync5(path).filter((n) => n.endsWith(".json") && n.startsWith("cerefox-")).map((n) => ({ name: n, mtime: statSync4(join13(path, n)).mtimeMs })).sort((a, b) => b.mtime - a.mtime);
+  const candidates = readdirSync5(path).filter((n) => n.endsWith(".json") && n.startsWith("cerefox-")).map((n) => ({ name: n, mtime: statSync5(join13(path, n)).mtimeMs })).sort((a, b) => b.mtime - a.mtime);
   if (candidates.length === 0) {
     throw userError(`No cerefox-*.json files in ${path}`);
   }
@@ -75491,7 +75589,7 @@ async function action32(query, options) {
   }
 }
 function registerSearch(program) {
-  program.command("search").description("Search the knowledge base (hybrid FTS + semantic).").argument("<query>", "Natural-language search query.").option("-c, --match-count <n>", "Maximum number of documents to return.", "5").option("-p, --project-name <name>", "Filter results to a specific project.").option("-f, --metadata-filter <json>", "JSON containment filter; only docs whose metadata contains ALL pairs are returned.").option("--mode <mode>", "Search mode: docs (default), hybrid, fts.", "docs").option("--alpha <float>", "Semantic weight 0..1 (default: CEREFOX_SEARCH_ALPHA; else 0.7).").option("--min-score <float>", "Minimum cosine similarity threshold (default: CEREFOX_MIN_SEARCH_SCORE; else 0.5, or 0.6 with the local embedder).").option("--min-term-coverage <float>", "OR-fallback keyword matches must cover at least this fraction of the query's meaningful terms to count as confident hits (default: CEREFOX_MIN_TERM_COVERAGE; else the server default 0.5; needs schema ≥ 0.9.1).").option("--max-bytes <n>", "Response size budget in bytes (default: CEREFOX_MAX_RESPONSE_BYTES or 200000).").addOption(authorOption("read")).addOption(requestorAliasOption()).option("--json", "Emit machine-readable JSON instead of the default text.").option("--only-metadata", "List matching docs (id, score, chunks, chars, partial/full) WITHOUT their content — like the web UI's collapsed result list. Grab a [id:…] then `cerefox document get <id>`.").action(action32);
+  program.command("search").description("Search the knowledge base (hybrid FTS + semantic).").argument("<query>", "Natural-language search query.").option("-c, --match-count <n>", "Maximum number of documents to return.", "5").option("-p, --project-name <name>", "Filter results to a specific project.").option("-f, --metadata-filter <json>", "JSON containment filter; only docs whose metadata contains ALL pairs are returned.").option("--mode <mode>", "Search mode: docs (default), hybrid, fts.", "docs").option("--alpha <float>", "Semantic weight 0..1 (default: CEREFOX_SEARCH_ALPHA; else 0.7).").option("--min-score <float>", "Minimum cosine similarity threshold (default: the store's min_search_score; else 0.5, or 0.6 on a local-embedder store).").option("--min-term-coverage <float>", "OR-fallback keyword matches must cover at least this fraction of the query's meaningful terms to count as confident hits (default: the store's min_term_coverage; else 0.67; needs schema ≥ 0.9.1).").option("--max-bytes <n>", "Response size budget in bytes (default: CEREFOX_MAX_RESPONSE_BYTES or 200000).").addOption(authorOption("read")).addOption(requestorAliasOption()).option("--json", "Emit machine-readable JSON instead of the default text.").option("--only-metadata", "List matching docs (id, score, chunks, chars, partial/full) WITHOUT their content — like the web UI's collapsed result list. Grab a [id:…] then `cerefox document get <id>`.").action(action32);
 }
 
 // src/cli/commands/self-update.ts
@@ -75642,8 +75740,8 @@ init_config();
 import { randomBytes } from "node:crypto";
 
 // src/cli/util/env-file.ts
-import { copyFileSync as copyFileSync3, existsSync as existsSync14, readFileSync as readFileSync16, writeFileSync as writeFileSync6 } from "node:fs";
-import { dirname as dirname5 } from "node:path";
+import { copyFileSync as copyFileSync3, existsSync as existsSync14, readFileSync as readFileSync16, writeFileSync as writeFileSync7 } from "node:fs";
+import { dirname as dirname6 } from "node:path";
 import { spawnSync as spawnSync6 } from "node:child_process";
 function escapeRegExp(s) {
   return s.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
@@ -75653,7 +75751,7 @@ function upsertEnvVar(path, key, value, opts = {}) {
   const header = opts.comment ? `# ${opts.comment}
 ` : "";
   if (!existsSync14(path)) {
-    writeFileSync6(path, `${header}${line}
+    writeFileSync7(path, `${header}${line}
 `, { mode: 384 });
     return { path, action: "created" };
   }
@@ -75678,7 +75776,7 @@ ${header}${line}
 `;
     action = "added";
   }
-  writeFileSync6(path, next);
+  writeFileSync7(path, next);
   return { path, action, backupPath };
 }
 function readEnvVar(path, key) {
@@ -75689,7 +75787,7 @@ function readEnvVar(path, key) {
 }
 function envGitignoreWarning(path) {
   try {
-    const dir = dirname5(path);
+    const dir = dirname6(path);
     const inTree = spawnSync6("git", ["-C", dir, "rev-parse", "--is-inside-work-tree"], {
       encoding: "utf8"
     });
@@ -77649,7 +77747,7 @@ var _baseMimes = {
 var baseMimes = _baseMimes;
 
 // ../../node_modules/.bun/@hono+node-server@2.1.1+2ac783cc5e75a70c/node_modules/@hono/node-server/dist/serve-static.mjs
-import { createReadStream, existsSync as existsSync16, statSync as statSync5 } from "node:fs";
+import { createReadStream, existsSync as existsSync16, statSync as statSync6 } from "node:fs";
 import { join as join14 } from "node:path";
 var COMPRESSIBLE_CONTENT_TYPE_REGEX = /^\s*(?:text\/[^;\s]+|application\/(?:javascript|json|xml|xml-dtd|ecmascript|dart|postscript|rtf|tar|toml|vnd\.dart|vnd\.ms-fontobject|vnd\.ms-opentype|wasm|x-httpd-php|x-javascript|x-ns-proxy-autoconfig|x-sh|x-tar|x-virtualbox-hdd|x-virtualbox-ova|x-virtualbox-ovf|x-virtualbox-vbox|x-virtualbox-vdi|x-virtualbox-vhd|x-virtualbox-vmdk|x-www-form-urlencoded)|font\/(?:otf|ttf)|image\/(?:bmp|vnd\.adobe\.photoshop|vnd\.microsoft\.icon|vnd\.ms-dds|x-icon|x-ms-bmp)|message\/rfc822|model\/gltf-binary|x-shader\/x-fragment|x-shader\/x-vertex|[^;\s]+?\+(?:json|text|xml|yaml))(?:[;\s]|$)/i;
 var ENCODINGS = {
@@ -77661,7 +77759,7 @@ var ENCODINGS_ORDERED_KEYS = Object.keys(ENCODINGS);
 var getStats = (path) => {
   let stats;
   try {
-    stats = statSync5(path);
+    stats = statSync6(path);
   } catch {}
   return stats;
 };
@@ -77807,7 +77905,7 @@ var serveStatic = (options = { root: "" }) => {
 
 // src/web/server.ts
 import { existsSync as existsSync20 } from "node:fs";
-import { readFileSync as readFileSync19, statSync as statSync8 } from "node:fs";
+import { readFileSync as readFileSync19, statSync as statSync9 } from "node:fs";
 import { join as join18 } from "node:path";
 
 // ../../node_modules/.bun/hono@4.13.7/node_modules/hono/dist/compose.js
@@ -79584,15 +79682,22 @@ function registerConfigRoutes(app, ctx) {
         p_key: spec.key
       });
       const stored = error ? null : unwrapScalarRpc(data);
+      let builtIn = spec.defaultValue;
+      if (stored == null && spec.defaultRpc) {
+        const d = await ctx.supabase.rpc(spec.defaultRpc, {});
+        const v = d.error ? null : unwrapScalarRpc(d.data);
+        if (v != null)
+          builtIn = String(v);
+      }
       const envVar = RETIRED_ENV_VARS2[spec.key];
       const envValue = envVar ? (process.env[envVar] ?? "").trim() : "";
       return {
         key: spec.key,
         value: stored,
-        effective: stored ?? spec.defaultValue,
+        effective: stored ?? builtIn,
         description: spec.description,
         kind: spec.kind,
-        default: spec.defaultValue,
+        default: builtIn,
         min: spec.min ?? null,
         max: spec.max ?? null,
         group: spec.group,
@@ -79651,7 +79756,6 @@ function registerConfigRoutes(app, ctx) {
   });
 }
 // src/web/routes/discovery.ts
-init__utils();
 init_feature_flags();
 
 // src/web/usage.ts
@@ -79880,10 +79984,8 @@ async function runSearch(ctx, opts) {
       p_query_text: query,
       p_query_embedding: embedding,
       p_match_count: count,
-      p_alpha: getSearchAlpha(),
       p_use_upgrade: false,
-      p_project_id: projectId,
-      p_min_score: getMinSearchScore()
+      p_project_id: projectId
     };
     if (metadataFilter)
       params.p_metadata_filter = metadataFilter;
@@ -79898,9 +80000,7 @@ async function runSearch(ctx, opts) {
     p_query_text: query,
     p_query_embedding: embedding,
     p_match_count: Math.min(count, 5),
-    p_alpha: getSearchAlpha(),
-    p_project_id: projectId,
-    p_min_score: getMinSearchScore()
+    p_project_id: projectId
   };
   if (metadataFilter)
     params.p_metadata_filter = metadataFilter;
@@ -79995,6 +80095,9 @@ function registerDiscoveryRoutes(app, ctx) {
       if (err instanceof HttpError) {
         return c.json({ detail: err.message }, err.status);
       }
+      if (err instanceof Error && err.name === "EmbedderDownloadError") {
+        return c.json({ detail: err.message }, 503);
+      }
       throw err;
     }
     const who = resolveCallerIdentity(c);
@@ -80794,6 +80897,8 @@ function notReady(error) {
   return { success: false, error, detail: error };
 }
 function ingestFailure(err) {
+  if (err instanceof Error && err.name === "EmbedderDownloadError")
+    return [notReady(err.message), 503];
   if (err instanceof ConcurrencyConflictError) {
     return [
       {
@@ -81060,7 +81165,7 @@ function registerIngestRoutes(app, ctx) {
 init_server_assets();
 init_meta();
 import { execFileSync } from "node:child_process";
-import { dirname as dirname7 } from "node:path";
+import { dirname as dirname8 } from "node:path";
 import { fileURLToPath as fileURLToPath4 } from "node:url";
 
 // src/web/docs.ts
@@ -81068,9 +81173,9 @@ import {
   existsSync as existsSync17,
   readFileSync as readFileSync17,
   readdirSync as readdirSync6,
-  statSync as statSync6
+  statSync as statSync7
 } from "node:fs";
-import { basename as basename5, dirname as dirname6, join as join15, resolve as resolve5 } from "node:path";
+import { basename as basename5, dirname as dirname7, join as join15, resolve as resolve5 } from "node:path";
 import { fileURLToPath as fileURLToPath3 } from "node:url";
 var TOP_LEVEL_DOCS = [
   { filename: "README.md", path: "README.md", category: "readme" },
@@ -81086,7 +81191,7 @@ var TOP_LEVEL_DOCS = [
   }
 ];
 function moduleDir2() {
-  return dirname6(fileURLToPath3(import.meta.url));
+  return dirname7(fileURLToPath3(import.meta.url));
 }
 function resolveDocsRoots() {
   const here = moduleDir2();
@@ -81098,7 +81203,7 @@ function resolveDocsRoots() {
   let pkgTopLevel = null;
   for (const pkg of pkgRootCandidates) {
     const guides = join15(pkg, "docs", "guides");
-    if (existsSync17(guides) && statSync6(guides).isDirectory()) {
+    if (existsSync17(guides) && statSync7(guides).isDirectory()) {
       pkgGuides = guides;
       pkgTopLevel = pkg;
       break;
@@ -81164,7 +81269,7 @@ function readDoc(docPath) {
   if (!candidate.startsWith(rootResolved + "/") && candidate !== rootResolved) {
     return null;
   }
-  if (existsSync17(candidate) && statSync6(candidate).isFile()) {
+  if (existsSync17(candidate) && statSync7(candidate).isFile()) {
     try {
       return readFileSync17(candidate, "utf8");
     } catch {
@@ -81190,7 +81295,7 @@ function readOpenApiDocument() {
 
 // src/web/routes/meta.ts
 init_compatibility();
-function resolveGitCommitShort(dir = dirname7(fileURLToPath4(import.meta.url))) {
+function resolveGitCommitShort(dir = dirname8(fileURLToPath4(import.meta.url))) {
   const env = process.env.CEREFOX_GIT_COMMIT;
   if (env)
     return env.slice(0, 7);
@@ -81322,7 +81427,7 @@ function registerPostgrestProxy(app) {
 
 // src/web/routes/preferences.ts
 init_config();
-import { existsSync as existsSync18, mkdirSync as mkdirSync6, readFileSync as readFileSync18, writeFileSync as writeFileSync7 } from "node:fs";
+import { existsSync as existsSync18, mkdirSync as mkdirSync6, readFileSync as readFileSync18, writeFileSync as writeFileSync8 } from "node:fs";
 import { join as join16 } from "node:path";
 function isTheme(v) {
   return v === "auto" || v === "light" || v === "dark";
@@ -81350,7 +81455,7 @@ function registerPreferencesRoutes(app) {
       const dir = userStateDir();
       if (!existsSync18(dir))
         mkdirSync6(dir, { recursive: true });
-      writeFileSync7(prefsFile(), `${JSON.stringify(next, null, 2)}
+      writeFileSync8(prefsFile(), `${JSON.stringify(next, null, 2)}
 `);
     } catch (err) {
       return c.json({ detail: err instanceof Error ? err.message : String(err) }, 500);
@@ -81485,14 +81590,14 @@ function registerProjectsRoutes(app, ctx) {
 }
 
 // src/web/static.ts
-import { existsSync as existsSync19, statSync as statSync7 } from "node:fs";
-import { dirname as dirname8, join as join17 } from "node:path";
+import { existsSync as existsSync19, statSync as statSync8 } from "node:fs";
+import { dirname as dirname9, join as join17 } from "node:path";
 import { fileURLToPath as fileURLToPath5 } from "node:url";
 function moduleDir3() {
-  return dirname8(fileURLToPath5(import.meta.url));
+  return dirname9(fileURLToPath5(import.meta.url));
 }
 function isUsableSpaDir(dir) {
-  return existsSync19(dir) && statSync7(dir).isDirectory() && existsSync19(join17(dir, "index.html"));
+  return existsSync19(dir) && statSync8(dir).isDirectory() && existsSync19(join17(dir, "index.html"));
 }
 function resolveSpaDist() {
   const here = moduleDir3();
@@ -81514,7 +81619,7 @@ function resolveStaticDir() {
     join17(here, "..", "..", "..", "..", "web", "static")
   ];
   for (const c of candidates) {
-    if (existsSync19(c) && statSync7(c).isDirectory())
+    if (existsSync19(c) && statSync8(c).isDirectory())
       return c;
   }
   return null;
@@ -81615,7 +81720,7 @@ function buildApp(ctx = buildWebContext()) {
       let cached = null;
       const readIndex = () => {
         try {
-          const { mtimeMs, size } = statSync8(indexPath);
+          const { mtimeMs, size } = statSync9(indexPath);
           if (!cached || cached.mtimeMs !== mtimeMs || cached.size !== size) {
             cached = { mtimeMs, size, html: readFileSync19(indexPath, "utf8") };
           }