pi-tuck 1.0.6 → 1.0.7

package/CHANGELOG.md

@@ -3,6 +3,16 @@
 All notable changes to pi-tuck. The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and versions follow
 [Semantic Versioning](https://semver.org/).
 
+## [1.0.7] - 2026-11-01
+
+### Changed
+
+- Semantic recall runs on Metal only, so only on Apple silicon. The CPU fallback is gone. Where the embedding server cannot start on Metal (a
+  VM, a Mac without a GPU), semantic recall goes off with "Semantic recall needs Metal; word recall still works", and word recall keeps
+  answering.
+- Off Apple silicon (Linux, Intel Macs), pi-tuck compacts and offers word recall only: `tuck_search` is no longer registered, `tuck_recall`'s
+  description no longer points to it, and nothing is downloaded. On Apple silicon both tools are as before.
+
 ## [1.0.6] - 2026-11-01
 
 ### Changed

package/README.md

@@ -58,8 +58,8 @@ Then start a new Pi session. That is all. pi-tuck takes over Pi's compaction, bo
 
 - Needs Pi 1.1 or later (tested on 1.1.0 and 1.4.0), on macOS or Linux.
 - On macOS with Apple silicon, the first session also downloads a local search model in the background (about 390 MB, once). Until it is ready, search works by keyword. See [Semantic search](#semantic-search).
-- Prefer GitHub? `pi install git:github.com/galyavin/pi-tuck@v1.0.6`.
-- To pin a version, add it: `pi install npm:pi-tuck@1.0.6`.
+- Prefer GitHub? `pi install git:github.com/galyavin/pi-tuck@v1.0.7`.
+- To pin a version, add it: `pi install npm:pi-tuck@1.0.7`.
 
 ## How it works
 
@@ -161,7 +161,7 @@ If you reach the model through OpenRouter, you can also pin one upstream, so tha
 
 ## Semantic search
 
-Semantic search is on by default on macOS with Apple silicon. It runs entirely on your Mac: an embedding model, [EmbeddingGemma-2](https://huggingface.co/google/embeddinggemma-2), served by [llama.cpp](https://github.com/ggml-org/llama.cpp) on the CPU. No text leaves your machine. Elsewhere, `tuck_search` uses keywords, and everything else works.
+Semantic search is on by default on macOS with Apple silicon. It runs entirely on your Mac: an embedding model, [EmbeddingGemma-2](https://huggingface.co/google/embeddinggemma-2), served by [llama.cpp](https://github.com/ggml-org/llama.cpp) on your Mac's GPU (Metal), or on the CPU where Metal cannot start. No text leaves your machine. Elsewhere, `tuck_search` uses keywords, and everything else works.
 
 The first time a session starts, pi-tuck downloads what it needs, once, about 390 MB, in the background. Keyword search works meanwhile:
 

package/dist/index.js

@@ -18,7 +18,9 @@ export default async function (pi) {
     // `/tuck-semantic off` holds for the rest of the session, including over a setup that finishes later.
     let off = false;
     const settings = readSettings(join(getAgentDir(), "pi-tuck.json"));
-    const handle = await installCompaction(pi, { semanticRecall, cutAt: settings.cutAt, onSemanticSetting: async (enabled) => { off = !enabled; } });
+    // Semantic recall runs on Metal, so only on Apple silicon; elsewhere the model is not offered tuck_search at all.
+    const appleSilicon = process.platform === "darwin" && process.arch === "arm64";
+    const handle = await installCompaction(pi, { semanticRecall, search: appleSilicon, cutAt: settings.cutAt, onSemanticSetting: async (enabled) => { off = !enabled; } });
     if (settings.semanticRecall === false)
         return;
     let session = 0, said = "", setup;
@@ -37,8 +39,8 @@ export default async function (pi) {
         off = false;
         if (settings.error)
             once(ctx, `pi-tuck: ${settings.error}; using the defaults.`, "warning");
-        if (process.platform !== "darwin" || process.arch !== "arm64")
-            return once(ctx, "pi-tuck: semantic recall needs macOS on Apple silicon for now; compaction and word recall work.", "info");
+        if (!appleSilicon)
+            return once(ctx, "pi-tuck: semantic recall needs macOS on Apple silicon; compaction and word recall work.", "info");
         // Semantic recall keeps its runtime and indexes outside the project it serves, so not when Pi runs in a folder that holds its
         // agent folder, such as the home folder.
         if (within(real(getAgentDir()), real(ctx.cwd)))

package/dist/src/build-id.d.ts

@@ -1 +1 @@
-export declare const BUILD_ID = "d2b2e6b0e594b5dd41e9771c43f4ed0355d8fd048c4e247541199f3b812751d3";
+export declare const BUILD_ID = "3ef35608c93cc69dbe42be20019d79b65f1a1e047e532fcd5efab4ab939b9150";

package/dist/src/build-id.js

@@ -1 +1 @@
-export const BUILD_ID = "d2b2e6b0e594b5dd41e9771c43f4ed0355d8fd048c4e247541199f3b812751d3";
+export const BUILD_ID = "3ef35608c93cc69dbe42be20019d79b65f1a1e047e532fcd5efab4ab939b9150";

package/dist/src/compaction.d.ts

@@ -23,6 +23,8 @@ export declare const MEASURED_CALIBRATION: Readonly<Record<string, number>>;
 export declare function seedWindow(branch: readonly SessionEntry[], key: string): number[];
 export interface CompactionOptions {
     semanticRecall?: SemanticRecallController;
+    /** Whether `tuck_search` exists: false where semantic recall cannot run (off Apple silicon), so the model is offered word recall only. */
+    search?: boolean;
     /** Optional host-owned transient operator preference; handle operations never call back. */
     onSemanticSetting?: (enabled: boolean) => Promise<unknown>;
     semanticStatus?: () => unknown;

package/dist/src/compaction.js

@@ -97,7 +97,7 @@ export async function installCompaction(pi, options = {}) {
     const cutAt = options.cutAt ?? DEFAULT_CUT_AT;
     if (!validCutAt(cutAt))
         throw new Error("Invalid cut point: cutAt must be a number above 0 and at most 1");
-    const semantic = options.semanticRecall ?? createSemanticRecall();
+    const semantic = options.semanticRecall ?? createSemanticRecall(), search = options.search ?? true;
     const hostAccess = () => {
         if (!active())
             throw new Error("Compaction host is inactive");
@@ -364,7 +364,7 @@ export async function installCompaction(pi, options = {}) {
     });
     pi.registerTool({
         name: "tuck_recall", label: "pi-tuck history", parameters: RecallInput,
-        description: "Keyword lookup locates particular text in your current branch. {query} returns ranked passages with read coordinates; punctuation separates words. Pass the returned next as {continuation} unchanged. Use tuck_search for historical information relevant to a question, including different wording and qualifications. Knowing an identifier does not itself justify narrowing discovery. {entryId} or {index} (a summary sourceIndex or #N) reads one source, optionally with query, offset and limit in UTF-16 characters (limit defaults to 8000). {} browses history; {around} expands neighbors; {entryId,image} reads an image; outputPath writes an original to a file with the native write tool. Hidden reasoning and system records are excluded.",
+        description: "Keyword lookup locates particular text in your current branch. {query} returns ranked passages with read coordinates; punctuation separates words. Pass the returned next as {continuation} unchanged. " + (search ? "Use tuck_search for historical information relevant to a question, including different wording and qualifications. " : "") + "Knowing an identifier does not itself justify narrowing discovery. {entryId} or {index} (a summary sourceIndex or #N) reads one source, optionally with query, offset and limit in UTF-16 characters (limit defaults to 8000). {} browses history; {around} expands neighbors; {entryId,image} reads an image; outputPath writes an original to a file with the native write tool. Hidden reasoning and system records are excluded.",
         async execute(_id, raw, signal, _update, ctx) {
             access();
             const input = checkedInput(raw);
@@ -391,31 +391,32 @@ export async function installCompaction(pi, options = {}) {
             return reply(tuckRecall(tuck, ctx.sessionManager.getEntries(), branch, input, options.recallPolicy));
         },
     });
-    pi.registerTool({ name: "tuck_search", label: "History search", parameters: SearchInput,
-        description: "Find historical information relevant to a question, including different wording and related qualifications. Combines keyword and local embedding search. Knowing a name or identifier does not imply keyword-only lookup is sufficient. Returns original evidence up to 20000 characters; not exhaustive. Semantic search may be off or incomplete, which is not the same as no matches. Read exact originals and their context with tuck_recall at the returned locators. priorResults lists source ranges already read.",
-        async execute(_id, raw, signal, _update, ctx) {
-            access();
-            if (!Check(SearchInput, raw))
-                throw new Error("Invalid broad search input");
-            const input = structuredClone(raw);
-            recorder.capture("recall-action", "authorized-native-tool-invocation-no-result-copy", input);
-            // Bind the actual independent lexical offer, including attribution derived
-            // from custom markers and receipts excluded from semantic indexing. Rebuild
-            // under current caller policy after await, when the session moved; never send this block to the encoder.
-            const wordOffer = () => tuckRecall(tuck, ctx.sessionManager.getEntries(), ctx.sessionManager.getBranch(), { query: input.query }, options.recallPolicy);
-            // The key is taken in the same synchronous step as the first lexical pass. After the await the second pass runs only if it moved (see eligibilityKey); a moved key alone invalidates nothing.
-            // The snapshot id check covers every in-contract change (any branch change moves the id); the key-gated second pass is defence in depth for out-of-contract callers.
-            const provider = semanticProvider(ctx), initialSnapshot = provider(), initialKey = eligibilityKey(ctx), words = wordOffer(), wordText = JSON.stringify(words);
-            const related = await semantic.search(input.query, provider, signal, input.priorResults ?? [], words);
-            access();
-            if (signal?.aborted)
-                throw Object.assign(new Error('Semantic recall cancelled'), { name: 'AbortError' });
-            const now = provider();
-            if (initialSnapshot.id !== now.id || (eligibilityKeyMoved(ctx, initialKey) && wordText !== JSON.stringify(wordOffer())))
-                return { ...reply({ status: "snapshot_invalidated", notice: "Search source eligibility or version changed; no earlier evidence delivered. Request a fresh query." }), isError: true };
-            const page = budgetSemantic(related, 20000 - wordText.length - 1);
-            return { content: [{ type: "text", text: wordText }, { type: "text", text: JSON.stringify(page) }], details: { semantic: { status: page.status, snapshotId: page.coverage.snapshotId } } };
-        } });
+    if (search)
+        pi.registerTool({ name: "tuck_search", label: "History search", parameters: SearchInput,
+            description: "Find historical information relevant to a question, including different wording and related qualifications. Combines keyword and local embedding search. Knowing a name or identifier does not imply keyword-only lookup is sufficient. Returns original evidence up to 20000 characters; not exhaustive. Semantic search may be off or incomplete, which is not the same as no matches. Read exact originals and their context with tuck_recall at the returned locators. priorResults lists source ranges already read.",
+            async execute(_id, raw, signal, _update, ctx) {
+                access();
+                if (!Check(SearchInput, raw))
+                    throw new Error("Invalid broad search input");
+                const input = structuredClone(raw);
+                recorder.capture("recall-action", "authorized-native-tool-invocation-no-result-copy", input);
+                // Bind the actual independent lexical offer, including attribution derived
+                // from custom markers and receipts excluded from semantic indexing. Rebuild
+                // under current caller policy after await, when the session moved; never send this block to the encoder.
+                const wordOffer = () => tuckRecall(tuck, ctx.sessionManager.getEntries(), ctx.sessionManager.getBranch(), { query: input.query }, options.recallPolicy);
+                // The key is taken in the same synchronous step as the first lexical pass. After the await the second pass runs only if it moved (see eligibilityKey); a moved key alone invalidates nothing.
+                // The snapshot id check covers every in-contract change (any branch change moves the id); the key-gated second pass is defence in depth for out-of-contract callers.
+                const provider = semanticProvider(ctx), initialSnapshot = provider(), initialKey = eligibilityKey(ctx), words = wordOffer(), wordText = JSON.stringify(words);
+                const related = await semantic.search(input.query, provider, signal, input.priorResults ?? [], words);
+                access();
+                if (signal?.aborted)
+                    throw Object.assign(new Error('Semantic recall cancelled'), { name: 'AbortError' });
+                const now = provider();
+                if (initialSnapshot.id !== now.id || (eligibilityKeyMoved(ctx, initialKey) && wordText !== JSON.stringify(wordOffer())))
+                    return { ...reply({ status: "snapshot_invalidated", notice: "Search source eligibility or version changed; no earlier evidence delivered. Request a fresh query." }), isError: true };
+                const page = budgetSemantic(related, 20000 - wordText.length - 1);
+                return { content: [{ type: "text", text: wordText }, { type: "text", text: JSON.stringify(page) }], details: { semantic: { status: page.status, snapshotId: page.coverage.snapshotId } } };
+            } });
     pi.on("session_before_compact", (event, ctx) => {
         try {
             if (!active())

package/dist/src/diagnostics.d.ts

@@ -1,6 +1,6 @@
 import { type RecallPolicy } from './recall.js';
 import type { SessionEntry } from '@earendil-works/pi-coding-agent';
-export declare const DIAGNOSTIC_BUILD = "d2b2e6b0e594b5dd41e9771c43f4ed0355d8fd048c4e247541199f3b812751d3";
+export declare const DIAGNOSTIC_BUILD = "3ef35608c93cc69dbe42be20019d79b65f1a1e047e532fcd5efab4ab939b9150";
 export interface Receipt {
     id: string;
     build: string;

package/dist/src/semantic-recall.d.ts

@@ -112,13 +112,15 @@ export declare const HEAL_STEADY_MS = 600000;
 export declare const IDLE_STOP_MS = 600000;
 /** A worker call's deadline once the worker has answered a call after `ready`: index, embed and tokenize on a loaded model. */
 export declare const CALL_DEADLINE_MS = 60000;
+/** Why semantic recall is off where the embedding server cannot start on Metal (a VM, a Mac without a GPU): it runs on Metal only. */
+export declare const METAL_UNAVAILABLE = "Semantic recall needs Metal; word recall still works";
 /** What an `embed` call adds to its deadline for each text it carries. A batch of 8 passages on a starved CPU took longer than the per-call
  * deadline, and the worker failed when it should have slowed down; a query (one text) still fails fast when the server hangs. The worker
  * scales its native request timeout by the same amount (semantic-worker.py), so that limit is not reached first. */
 export declare const EMBED_TEXT_MS = 30000;
 /** The deadline for a worker's start: Python start, `ready` (which verifies every runtime file) and the first call after it, which loads the
  * model and starts its native server. On a busy machine that takes minutes; held to the per-call deadline, the worker never started and
- * semantic recall went unavailable. It stays above the worker's own native start limits (120 s on Metal, then 400 s on the CPU, in semantic-worker.py). */
+ * semantic recall went unavailable. It stays above the worker's own native start limit (540 s, in semantic-worker.py). */
 export declare const START_DEADLINE_MS = 600000;
 /** The most units one index window holds. The worker's SQLite store stops at 8,008 rows (`PRAGMA max_page_count=8192` in scripts/semantic-worker.py), so a cap below that keeps a window of short units from filling the store and sticking in `unavailable`. Raise it only together with the store. */
 export declare const MAX_INDEX_UNITS = 8000;

package/dist/src/semantic-recall.js

@@ -171,13 +171,15 @@ export const HEAL_STEADY_MS = 600000;
 export const IDLE_STOP_MS = 600000;
 /** A worker call's deadline once the worker has answered a call after `ready`: index, embed and tokenize on a loaded model. */
 export const CALL_DEADLINE_MS = 60000;
+/** Why semantic recall is off where the embedding server cannot start on Metal (a VM, a Mac without a GPU): it runs on Metal only. */
+export const METAL_UNAVAILABLE = 'Semantic recall needs Metal; word recall still works';
 /** What an `embed` call adds to its deadline for each text it carries. A batch of 8 passages on a starved CPU took longer than the per-call
  * deadline, and the worker failed when it should have slowed down; a query (one text) still fails fast when the server hangs. The worker
  * scales its native request timeout by the same amount (semantic-worker.py), so that limit is not reached first. */
 export const EMBED_TEXT_MS = 30000;
 /** The deadline for a worker's start: Python start, `ready` (which verifies every runtime file) and the first call after it, which loads the
  * model and starts its native server. On a busy machine that takes minutes; held to the per-call deadline, the worker never started and
- * semantic recall went unavailable. It stays above the worker's own native start limits (120 s on Metal, then 400 s on the CPU, in semantic-worker.py). */
+ * semantic recall went unavailable. It stays above the worker's own native start limit (540 s, in semantic-worker.py). */
 export const START_DEADLINE_MS = 600000;
 /** The most units one index window holds. The worker's SQLite store stops at 8,008 rows (`PRAGMA max_page_count=8192` in scripts/semantic-worker.py), so a cap below that keeps a window of short units from filling the store and sticking in `unavailable`. Raise it only together with the store. */
 export const MAX_INDEX_UNITS = 8000;
@@ -274,7 +276,7 @@ class LocalWorker {
                     if (pending) {
                         clearTimeout(pending.timer);
                         this.pending.delete(reply.id);
-                        reply.ok ? pending.resolve(reply.result) : pending.reject(new WorkerFailure('Local semantic runtime: ' + reply.error?.code, reply.error?.code ?? null));
+                        reply.ok ? pending.resolve(reply.result) : pending.reject(new WorkerFailure(reply.error?.code === 'metal_unavailable' ? METAL_UNAVAILABLE : 'Local semantic runtime: ' + reply.error?.code, reply.error?.code ?? null));
                         if (this.nativeHelper && this.nativeInputId === reply.id) {
                             this.nativeInputId = undefined;
                             this.pumpNativeInput();

package/index.ts

@@ -22,7 +22,9 @@ export default async function (pi: ExtensionAPI) {
 	// `/tuck-semantic off` holds for the rest of the session, including over a setup that finishes later.
 	let off = false;
 	const settings = readSettings(join(getAgentDir(), "pi-tuck.json"));
-	const handle = await installCompaction(pi, { semanticRecall, cutAt: settings.cutAt, onSemanticSetting: async enabled => { off = !enabled; } });
+	// Semantic recall runs on Metal, so only on Apple silicon; elsewhere the model is not offered tuck_search at all.
+	const appleSilicon = process.platform === "darwin" && process.arch === "arm64";
+	const handle = await installCompaction(pi, { semanticRecall, search: appleSilicon, cutAt: settings.cutAt, onSemanticSetting: async enabled => { off = !enabled; } });
 	if (settings.semanticRecall === false) return;
 	let session = 0, said = "", setup: Promise<unknown> | undefined;
 	// A context outlives its session (a setup can finish after /new); a notice to an ended session is dropped.
@@ -33,8 +35,8 @@ export default async function (pi: ExtensionAPI) {
 		const current = ++session;
 		off = false;
 		if (settings.error) once(ctx, `pi-tuck: ${settings.error}; using the defaults.`, "warning");
-		if (process.platform !== "darwin" || process.arch !== "arm64")
-			return once(ctx, "pi-tuck: semantic recall needs macOS on Apple silicon for now; compaction and word recall work.", "info");
+		if (!appleSilicon)
+			return once(ctx, "pi-tuck: semantic recall needs macOS on Apple silicon; compaction and word recall work.", "info");
 		// Semantic recall keeps its runtime and indexes outside the project it serves, so not when Pi runs in a folder that holds its
 		// agent folder, such as the home folder.
 		if (within(real(getAgentDir()), real(ctx.cwd)))

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-tuck",
-  "version": "1.0.6",
+  "version": "1.0.7",
   "description": "Deterministic compaction for Pi: compact summaries that keep the dialogue and the files touched, plus history recall by keyword and by meaning, all local.",
   "keywords": [
     "pi-package",

package/scripts/semantic-worker.py

@@ -92,9 +92,9 @@ def load():
    # Pinned common/arg.cpp supports LLAMA_API_KEY; server-http.cpp requires Bearer
    # on /props and embeddings, but /health is public. No token in process argv.
    env['LLAMA_API_KEY']=encoder_token
-  def launch(gpu_layers,limit):
+  def launch(limit):
    """The server, or None when it exits or is not healthy within `limit` seconds (it is then stopped)."""
-   child=subprocess.Popen([str(executable),'-m',str(ROOT/'model.gguf'),'--embedding','--pooling','mean','--embd-normalize','2','--ctx-size','8192','--batch-size','8192','--ubatch-size','8192','--parallel','1','--n-gpu-layers',str(gpu_layers),'--cache-type-k','f32','--cache-type-v','f32','--flash-attn','off','--threads','4',*transport,'--no-webui','--log-disable'],stdin=subprocess.DEVNULL,stdout=subprocess.DEVNULL,stderr=subprocess.DEVNULL,env=env)
+   child=subprocess.Popen([str(executable),'-m',str(ROOT/'model.gguf'),'--embedding','--pooling','mean','--embd-normalize','2','--ctx-size','8192','--batch-size','8192','--ubatch-size','8192','--parallel','1','--n-gpu-layers','99','--cache-type-k','f32','--cache-type-v','f32','--flash-attn','off','--threads','4',*transport,'--no-webui','--log-disable'],stdin=subprocess.DEVNULL,stdout=subprocess.DEVNULL,stderr=subprocess.DEVNULL,env=env)
    started=time.monotonic()
    while child.poll() is None and time.monotonic()-started<=limit:
     try:
@@ -106,13 +106,12 @@ def load():
    if child.poll() is None:
     child.kill();child.wait()
    return None
-  # Metal first: on Apple silicon it embeds a batch about 56 times faster than the CPU (0.7 s against 39 s for 8 passages at load 44-76),
-  # with vectors of cosine 0.9998 or more to the CPU's. Where Metal cannot start (a VM, CI, no GPU) the server exits or never becomes
-  # healthy, and the same server starts on the CPU. A busy machine can take minutes to start it; both limits stay under the host's start
-  # deadline (START_DEADLINE_MS, 600 s). Windows has no Metal.
-  server=None if WINDOWS else launch(99,120)
-  if server is None:server=launch(0,400)
-  if server is None:raise Refusal('native_start_failure')
+  # Semantic recall runs on Metal only (the project's platform choice): on Apple silicon it embeds a batch about 56 times faster than the
+  # CPU did (0.7 s against 39 s for 8 passages at load 44-76). Where Metal cannot start (a VM, no GPU) the server exits or never becomes
+  # healthy, and semantic recall goes off with that reason; word recall keeps working. A busy machine can take minutes to start it; the
+  # limit stays under the host's start deadline (START_DEADLINE_MS, 600 s).
+  server=launch(540)
+  if server is None:raise Refusal('metal_unavailable')
  return server
 def run(req):
  op=req['op']

package/src/build-id.ts

@@ -1 +1 @@
-export const BUILD_ID = "d2b2e6b0e594b5dd41e9771c43f4ed0355d8fd048c4e247541199f3b812751d3";
+export const BUILD_ID = "3ef35608c93cc69dbe42be20019d79b65f1a1e047e532fcd5efab4ab939b9150";

package/src/compaction.ts

@@ -88,6 +88,8 @@ export function seedWindow(branch: readonly SessionEntry[], key: string): number
 }
 export interface CompactionOptions {
  semanticRecall?: SemanticRecallController;
+ /** Whether `tuck_search` exists: false where semantic recall cannot run (off Apple silicon), so the model is offered word recall only. */
+ search?: boolean;
  /** Optional host-owned transient operator preference; handle operations never call back. */
  onSemanticSetting?: (enabled: boolean) => Promise<unknown>;
  semanticStatus?: () => unknown;
@@ -119,7 +121,7 @@ export interface CompactionOptions {
 export async function installCompaction(pi: ExtensionAPI, options: CompactionOptions = {}) {
     const cutAt = options.cutAt ?? DEFAULT_CUT_AT;
     if (!validCutAt(cutAt)) throw new Error("Invalid cut point: cutAt must be a number above 0 and at most 1");
-    const semantic = options.semanticRecall ?? createSemanticRecall();
+    const semantic = options.semanticRecall ?? createSemanticRecall(), search = options.search ?? true;
     const hostAccess = () => {
         if (!active()) throw new Error("Compaction host is inactive");
         options.assertAccess?.();
@@ -318,7 +320,7 @@ export async function installCompaction(pi: ExtensionAPI, options: CompactionOpt
     });
 	pi.registerTool({
 		name: "tuck_recall", label: "pi-tuck history", parameters: RecallInput,
-        description: "Keyword lookup locates particular text in your current branch. {query} returns ranked passages with read coordinates; punctuation separates words. Pass the returned next as {continuation} unchanged. Use tuck_search for historical information relevant to a question, including different wording and qualifications. Knowing an identifier does not itself justify narrowing discovery. {entryId} or {index} (a summary sourceIndex or #N) reads one source, optionally with query, offset and limit in UTF-16 characters (limit defaults to 8000). {} browses history; {around} expands neighbors; {entryId,image} reads an image; outputPath writes an original to a file with the native write tool. Hidden reasoning and system records are excluded.",
+        description: "Keyword lookup locates particular text in your current branch. {query} returns ranked passages with read coordinates; punctuation separates words. Pass the returned next as {continuation} unchanged. " + (search ? "Use tuck_search for historical information relevant to a question, including different wording and qualifications. " : "") + "Knowing an identifier does not itself justify narrowing discovery. {entryId} or {index} (a summary sourceIndex or #N) reads one source, optionally with query, offset and limit in UTF-16 characters (limit defaults to 8000). {} browses history; {around} expands neighbors; {entryId,image} reads an image; outputPath writes an original to a file with the native write tool. Hidden reasoning and system records are excluded.",
 		async execute(_id, raw, signal, _update, ctx) {
 			access();
             const input = checkedInput(raw);
@@ -341,7 +343,7 @@ export async function installCompaction(pi: ExtensionAPI, options: CompactionOpt
             return reply(tuckRecall(tuck, ctx.sessionManager.getEntries(), branch, input, options.recallPolicy));
 		},
 	});
-    pi.registerTool({name:"tuck_search",label:"History search",parameters:SearchInput,
+    if (search) pi.registerTool({name:"tuck_search",label:"History search",parameters:SearchInput,
         description:"Find historical information relevant to a question, including different wording and related qualifications. Combines keyword and local embedding search. Knowing a name or identifier does not imply keyword-only lookup is sufficient. Returns original evidence up to 20000 characters; not exhaustive. Semantic search may be off or incomplete, which is not the same as no matches. Read exact originals and their context with tuck_recall at the returned locators. priorResults lists source ranges already read.",
         async execute(_id,raw,signal,_update,ctx){
             access();if(!Check(SearchInput,raw))throw new Error("Invalid broad search input");const input=structuredClone(raw);

package/src/semantic-recall.ts

@@ -104,13 +104,15 @@ export const HEAL_STEADY_MS=600000;
 export const IDLE_STOP_MS=600000;
 /** A worker call's deadline once the worker has answered a call after `ready`: index, embed and tokenize on a loaded model. */
 export const CALL_DEADLINE_MS=60000;
+/** Why semantic recall is off where the embedding server cannot start on Metal (a VM, a Mac without a GPU): it runs on Metal only. */
+export const METAL_UNAVAILABLE='Semantic recall needs Metal; word recall still works';
 /** What an `embed` call adds to its deadline for each text it carries. A batch of 8 passages on a starved CPU took longer than the per-call
  * deadline, and the worker failed when it should have slowed down; a query (one text) still fails fast when the server hangs. The worker
  * scales its native request timeout by the same amount (semantic-worker.py), so that limit is not reached first. */
 export const EMBED_TEXT_MS=30000;
 /** The deadline for a worker's start: Python start, `ready` (which verifies every runtime file) and the first call after it, which loads the
  * model and starts its native server. On a busy machine that takes minutes; held to the per-call deadline, the worker never started and
- * semantic recall went unavailable. It stays above the worker's own native start limits (120 s on Metal, then 400 s on the CPU, in semantic-worker.py). */
+ * semantic recall went unavailable. It stays above the worker's own native start limit (540 s, in semantic-worker.py). */
 export const START_DEADLINE_MS=600000;
 /** The most units one index window holds. The worker's SQLite store stops at 8,008 rows (`PRAGMA max_page_count=8192` in scripts/semantic-worker.py), so a cap below that keeps a window of short units from filling the store and sticking in `unavailable`. Raise it only together with the store. */
 export const MAX_INDEX_UNITS=8000;
@@ -149,7 +151,7 @@ class LocalWorker {
    const launchLine=JSON.stringify(launch)+'\n';if(this.nativeHelper&&Buffer.byteLength(launchLine)>2*1048576)throw new Error('Native owner launch bound');
    const child=spawn(this.nativeHelper?this.config.nativeOwnerHelperPath!:this.config.pythonPath,this.nativeHelper?['--run']:args,{cwd:this.scratch,env:this.nativeHelper?osEnvironment:env,stdio:'pipe',detached:!this.nativeHelper});
    this.child=child;this.exited=new Promise<void>(done=>child.once('close',(code,signal)=>{this.nativeExit={code,signal};this.rejectAll(new WorkerFailure('Local worker stopped'));done();this.lose('Local worker stopped');}));
-   child.stdout.on('data',data=>{this.buffer+=data.toString();if(this.buffer.length>16*1024*1024){this.lose('Local worker output bound');return;}let end;while((end=this.buffer.indexOf('\n'))>=0){const line=this.buffer.slice(0,end);this.buffer=this.buffer.slice(end+1);try{const reply=JSON.parse(line),pending=this.pending.get(reply.id);if(pending){clearTimeout(pending.timer);this.pending.delete(reply.id);reply.ok?pending.resolve(reply.result):pending.reject(new WorkerFailure('Local semantic runtime: '+reply.error?.code,reply.error?.code??null));if(this.nativeHelper&&this.nativeInputId===reply.id){this.nativeInputId=undefined;this.pumpNativeInput();}}}catch{this.lose('Local worker framing');}}});
+   child.stdout.on('data',data=>{this.buffer+=data.toString();if(this.buffer.length>16*1024*1024){this.lose('Local worker output bound');return;}let end;while((end=this.buffer.indexOf('\n'))>=0){const line=this.buffer.slice(0,end);this.buffer=this.buffer.slice(end+1);try{const reply=JSON.parse(line),pending=this.pending.get(reply.id);if(pending){clearTimeout(pending.timer);this.pending.delete(reply.id);reply.ok?pending.resolve(reply.result):pending.reject(new WorkerFailure(reply.error?.code==='metal_unavailable'?METAL_UNAVAILABLE:'Local semantic runtime: '+reply.error?.code,reply.error?.code??null));if(this.nativeHelper&&this.nativeInputId===reply.id){this.nativeInputId=undefined;this.pumpNativeInput();}}}catch{this.lose('Local worker framing');}}});
    child.stdout.on('error',()=>this.lose('Local worker output'));
    if(this.nativeHelper)this.helperReceipt=observeNativeFrames(child.stderr,()=>{},()=>this.closeInBackground());
    else child.stderr.resume();