Garry's Opinionated OpenClaw/Hermes Agent Brain
TypeScript
tokenmax mode switch: point the banner and prompt at gbrain reindex --synopsis (#8744)
garrytan9b2348995d12
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 09d2b157c4..a420e35ec6 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -21,6 +21,7 @@ identifiers and attribution are available in the pre-removal Git revision| `gbrain doctor` on a brain whose configured tier is `per_chunk_synopsis` | nothing about it | `synopsis_tier_coverage` gives chunk and page coverage, the large pages left on the title tier and the last sweep job; it warns below 50% of chunks and names `gbrain reindex --synopsis`. The remote doctor runs it too, confined to the caller's sources || `gbrain search modes` | the configured tier only | one line with the synopsis-tier coverage (local only; the `search_modes` op leaves it out) || `gbrain reindex --synopsis` | did not exist | previews pages, chunks, synopsis tokens and dollars on the configured synopsis model plus the re-embed, and spends nothing |+| `gbrain config set search.mode tokenmax` | the banner named `gbrain reindex --markdown` (which embeds at the title tier) and, on a TTY with a live worker, offered to queue it | the banner names `gbrain reindex --synopsis`; on a TTY it shows the sweep's preview and runs the sweep in that terminal only when you answer yes. Without a TTY it prints the preview command || `gbrain reindex --synopsis --yes [--max-usd <usd>]` | did not exist | queues one `contextual_reindex_per_chunk` job per page under one spend cap the worker enforces across them, runs them in-process and reports the new coverage. Running it again resumes: finished pages are skipped and queued jobs are picked up |Nothing is scheduled automatically and no default changes. Inline pages over 1 MiB keep the title tier, as before. Repo-less brains work the same way: the sweep reads and writes the database only.diff --git a/skills/migrations/v0.40.3.0.md b/skills/migrations/v0.40.3.0.mdindex 363b0e741e..17cadee7ea 100644--- a/skills/migrations/v0.40.3.0.md+++ b/skills/migrations/v0.40.3.0.md@@ -69,9 +69,9 @@ Anthropic's published research, document-heavy benchmarks see agbrain config set search.mode tokenmax```-The mode-switch banner explains the cost and (on TTY + active Minion-worker) offers to submit `gbrain reindex --markdown` as a Minion job.-Non-TTY callers get a paste-ready hint to stderr. Suppress entirely+The mode-switch banner explains the cost and, on a TTY, previews the+synopsis sweep and asks before running `gbrain reindex --synopsis --yes`.+Non-TTY callers get the preview command on stderr. Suppress entirelywith `GBRAIN_NO_MODE_SWITCH_UX=1`.Import, sync and `gbrain reindex --markdown` embed tokenmax pages at the titlediff --git a/skills/skills.lock.json b/skills/skills.lock.jsonindex f4dea0a255..af8a638097 100644--- a/skills/skills.lock.json+++ b/skills/skills.lock.json@@ -131,7 +131,7 @@"migrations/v0.35.7.0.md": "c6d4454bd39e2aa243b3b3d9bc72fe5a4fd25d097be7be2bb14b25604b5c2cc5","migrations/v0.36.2.0.md": "18f72475a0c0de1489c518219128d331d8ed6b0cdcacfb329e18fbcc643d9c6e","migrations/v0.36.5.0.md": "889f42508c28835c99242ec20b610ab002f20cda821cb99039589a212cac2ce0",- "migrations/v0.40.3.0.md": "345621da8da253008947128a49ffdf1e170736a4b05b282c808d62ce641196e9",+ "migrations/v0.40.3.0.md": "8353087813055bb5dd5f176eb242e1169fbe17c58c727168d8bc3e884cce85d8","migrations/v0.40.5.md": "92f0fce78502356c0ac5b50d043070b4002455026237004dd3ef7f05584e95b6","migrations/v0.41.11.0.md": "75c9741617de4c163052609e64734b4696a1105d3d015ed451097eaf6ea1eb3c","migrations/v0.46.3.0.md": "add5bdace741f8f0a75a114e354aa8ea3bcadf4cb54e1823338fdc69a5ae3f5d",diff --git a/src/commands/config.ts b/src/commands/config.tsindex ade7bb21ad..d3982d8ca0 100644--- a/src/commands/config.ts+++ b/src/commands/config.ts@@ -1471,8 +1471,8 @@ export async function runConfig(engine: BrainEngine, args: string[]) {newMode: value,engine,isTty: Boolean(process.stdout.isTTY && process.stdin.isTTY),- // CLI doesn't thread --yes here today; reserved for /ship-style- // automation paths that can opt into auto-submit.+ // CLI doesn't thread --yes here today; --yes would skip the+ // prompt and print the preview command (it never spends).yesFlag: false,});} catch (err) {diff --git a/src/core/search/mode-switch-ux.ts b/src/core/search/mode-switch-ux.tsindex 9eddf37878..6845b78179 100644--- a/src/core/search/mode-switch-ux.ts+++ b/src/core/search/mode-switch-ux.ts@@ -5,36 +5,24 @@* surfaces a banner explaining the consequences and offers follow-up* actions.*- * Three concerns separated:- ** 1. summarizeTransition(old, new) — PURE function that classifies the* transition (no_change / narrowing / broadening / tokenmax_opt_in)- * and returns banner lines, reindex requirement, and cost estimate.- *- * 2. probeWorkerAvailable(engine) — checks Minion worker heartbeat- * (mirrors `gbrain doctor`'s queue_health check). Returns active /- * stale / never_seen with a paste-ready start command.+ * and returns banner lines, the backfill requirement and cost estimate.*- * 3. runModeSwitchUx(opts) — the orchestrator. Calls summarizeTransition,- * prints the banner, and for tokenmax_opt_in + TTY: prompts to run- * reindex, calls probeWorkerAvailable, and either submits the- * reindex job or prints the loud-fail "start a worker first" hint- * per D3.+ * 2. runModeSwitchUx(opts) — the orchestrator. Prints the banner, and for+ * tokenmax_opt_in on a TTY previews the per-chunk synopsis sweep+ * (`gbrain reindex --synopsis`, #8744: import, sync and+ * `reindex --markdown` embed at the title tier, so only that sweep+ * writes synopses) and runs it in this process when the user answers+ * yes. The yes is the consent; the sweep's spend cap applies.** Suppression: GBRAIN_NO_MODE_SWITCH_UX=1 skips the entire UX for* scripted operators (CI fixtures, automation). Non-TTY also skips* interactive prompts; prints paste-ready hints to stderr.- *- * The reindex idempotency key is content-stable per codex D12 Bug 1:- * cr-backfill:<source_id>:<chunker_version>:<corpus_generation_or_mode>- * NOT timestamp-based. Two retries against the same brain state dedupe- * via the Minion idempotency_key contract (v0.13.1).*/import type { BrainEngine } from '../engine.ts';import { readLineSafe } from '../../commands/init.ts';-import { MinionQueue } from '../minions/queue.ts';-import type { SpendAuthorization } from '../minions/spend-record.ts';import { isSearchMode, type SearchMode } from './mode.ts';export type TransitionKind =@@ -52,34 +40,16 @@ export interface TransitionSummary {callout_lines: string[];}-export type WorkerStatus = 'active' | 'stale' | 'never_seen';--export interface WorkerProbeResult {- status: WorkerStatus;- last_heartbeat_iso?: string;- paste_ready_start_command: string;-}-export interface ModeSwitchOpts {oldMode: SearchMode | null;newMode: string;engine: BrainEngine;isTty: boolean;yesFlag?: boolean;- /** Test seam: injectable worker probe. */- probeFn?: (engine: BrainEngine) => Promise<WorkerProbeResult>;- /** Test seam: injectable Minion submitter (avoids real queue in unit tests). */- submitFn?: (jobName: string, params: Record<string, unknown>, idempotencyKey: string, spendAuthorization?: SpendAuthorization) => Promise<number>;- /** Test seam: the TTY answer to the reindex prompt. */+ /** Test seam: the TTY answer to the sweep prompt. */answerFn?: (prompt: string) => Promise<string>;}-/**- * Worker stale threshold: 2 minutes (matches gbrain doctor's- * queue_health check semantics for "alive Minion worker").- */-export const WORKER_STALE_THRESHOLD_MS = 120_000;-/*** Classify the transition + build banner content. Pure: no engine, no* file I/O. Test surface for the 5-cell decision matrix below.@@ -117,19 +87,19 @@ export function summarizeTransition(};}- // tokenmax opt-in wins regardless of old mode. Triggers reindex prompt- // because per-chunk Haiku synopsis backfill is needed for full quality.+ // tokenmax opt-in wins regardless of old mode. Offers the synopsis sweep:+ // existing pages stay on the title tier until it runs (#8744).if (newMode === 'tokenmax') {return {kind: 'tokenmax_opt_in',reindex_required: true,- reindex_command: 'gbrain reindex --markdown',+ reindex_command: 'gbrain reindex --synopsis',cost_estimate_per_query_cents: 0.06, // ~$0.0006: rerank-3-lite at 50 candidates (gbrain-evals #148)callout_lines: [`Switched to tokenmax. Per-chunk Haiku synopsis enabled.`,`Backfill cost (one-time): ~$1-5 per 10K pages via Anthropic Haiku.`,`Per-query overhead: ~$0.0006 (reranker + slightly larger payload).`,- `Run \`gbrain reindex --markdown\` to backfill existing pages.`,+ `Existing pages stay on the title tier until the synopsis sweep runs: preview it with \`gbrain reindex --synopsis\`, run it with --yes.`,],};}@@ -175,79 +145,10 @@ function narrowness(mode: SearchMode): number {}}-/**- * Probe Minion worker heartbeat. Mirrors the queue_health doctor check- * semantics: a worker that pushed a heartbeat within- * WORKER_STALE_THRESHOLD_MS is considered active.- *- * Best-effort: any error returns `never_seen` so the caller can decide- * what to do. The paste-ready start command is always populated so the- * banner can offer a recovery path.- *- * The PGLite inline path (`gbrain agent run` with `--follow`) doesn't- * require a worker; this probe is for the production "spawn a real- * Minion worker" path.- */-export async function probeWorkerAvailable(engine: BrainEngine): Promise<WorkerProbeResult> {- const startCmd = 'gbrain jobs work';- try {- // gbrain doesn't have a minion_workers heartbeat table yet (B7 follow-up- // from v0.19.1 — see CLAUDE.md). Use a proxy: any minion_jobs row- // started or finished within WORKER_STALE_THRESHOLD_MS means a worker- // is doing real work. If only OLDER activity exists, treat as stale- // (worker likely died). If no activity at all, never_seen.- const rows = await engine.executeRaw<{ ts: string | null }>(- `SELECT MAX(GREATEST(- COALESCE(started_at, '-infinity'::timestamptz),- COALESCE(finished_at, '-infinity'::timestamptz)- ))::text AS ts- FROM minion_jobs- WHERE COALESCE(started_at, finished_at) > now() - INTERVAL '10 minutes'`,- );- const ts = rows[0]?.ts;- if (!ts) {- return { status: 'never_seen', paste_ready_start_command: startCmd };- }- const ageMs = Date.now() - new Date(ts).getTime();- if (ageMs <= WORKER_STALE_THRESHOLD_MS) {- return {- status: 'active',- last_heartbeat_iso: ts,- paste_ready_start_command: startCmd,- };- }- return {- status: 'stale',- last_heartbeat_iso: ts,- paste_ready_start_command: startCmd,- };- } catch {- // Table may not exist on a fresh brain. Treat as never_seen.- return { status: 'never_seen', paste_ready_start_command: startCmd };- }-}--/**- * Build the content-stable idempotency key for the reindex submission- * per codex D12 Bug 1. NOT timestamp-based — two retries against the- * same brain state must produce the SAME key so the Minion dedupes.- */-export function buildReindexIdempotencyKey(- sourceId: string,- chunkerVersion: number,- modeOrCorpusGen: string,-): string {- return `cr-backfill:${sourceId}:${chunkerVersion}:${modeOrCorpusGen}`;-}-/*** Orchestrator. Called by `gbrain config set search.mode <X>` after the- * config write lands. Honors GBRAIN_NO_MODE_SWITCH_UX=1 (full skip),- * non-TTY (skip prompt, print paste-ready hints), --yes (auto-submit- * reindex on tokenmax_opt_in transitions).- *- * Idempotent: invoking with the same (old, new) twice is harmless; the- * Minion idempotency_key ensures the reindex doesn't submit twice.+ * config write lands. Honors GBRAIN_NO_MODE_SWITCH_UX=1 (full skip) and+ * non-TTY / --yes (no prompt; prints the paste-ready preview command).*/export async function runModeSwitchUx(opts: ModeSwitchOpts): Promise<void> {if (process.env.GBRAIN_NO_MODE_SWITCH_UX === '1') return;@@ -270,99 +171,21 @@ export async function runModeSwitchUx(opts: ModeSwitchOpts): Promise<void> {if (!summary.reindex_required) return;- // Reindex offered only for tokenmax_opt_in (today). Honor --yes /- // non-TTY by NOT prompting; just print the paste-ready command.if (!opts.isTty || opts.yesFlag) {- console.error(`[mode-switch] To backfill now: ${summary.reindex_command}`);+ console.error(`[mode-switch] Preview the backfill (spends nothing): ${summary.reindex_command}`);return;}- // TTY + interactive: prompt, naming what the reindex re-embeds and costs (W4.5: the yes is stored on the job as its spend authorization).- const { countPending } = await import('../../commands/reindex.ts');- const { estimateReindexSpend } = await import('../reindex-consent.ts');- const plan = await estimateReindexSpend(opts.engine, { type: null, target: await countPending(opts.engine, null, false) });- const cost = plan.est_usd === null ? 'embedding cost unknown in advance' : `embedding about $${plan.est_usd.toFixed(2)}`;- const prompt = `Run '${summary.reindex_command}' now? It re-embeds ${plan.pages} page(s) (${cost}, plus a chat call per chunk under tokenmax). [y/N]: `;+ // TTY: show the sweep's preview (pages, chunks, tokens, dollars), then ask before any spend.+ const { runReindexSynopsis } = await import('../../commands/reindex-synopsis.ts');+ const preview = await runReindexSynopsis(opts.engine, ['--synopsis']);+ if (preview.mode !== 'preview' || !preview.plan || preview.plan.pages.length === 0) return;+ const cost = preview.plan.est_usd === null ? 'cost unknown in advance' : `up to $${preview.plan.est_usd.toFixed(2)}`;+ const prompt = `Run '${summary.reindex_command} --yes' now? It writes per-chunk synopses for ${preview.plan.pages.length} page(s) (${cost}) in this terminal; Ctrl-C stops it and the same command resumes. [y/N]: `;const answer = opts.answerFn ? await opts.answerFn(prompt) : await readLineSafe(prompt, 'n', 60_000);if (answer.toLowerCase() !== 'y' && answer.toLowerCase() !== 'yes') {- console.error(`[mode-switch] Skipped. Run \`${summary.reindex_command}\` when ready.`);- return;- }-- // User opted in. Probe worker availability before submitting.- const probeFn = opts.probeFn ?? probeWorkerAvailable;- const worker = await probeFn(opts.engine);-- if (worker.status !== 'active') {- // Loud-fail per D3 to avoid the silent-stall footgun. Caller can- // still invoke reindex inline (`gbrain reindex --markdown` runs- // synchronously without a worker on the PGLite inline path).- console.error(`[mode-switch] No active worker (${worker.status}).`);- console.error(`[mode-switch] Either run inline: ${summary.reindex_command}`);- console.error(`[mode-switch] Or start a worker first: ${worker.paste_ready_start_command}`);+ console.error(`[mode-switch] Skipped. Run \`${summary.reindex_command}\` to preview it again when ready.`);return;}-- // Submit via Minion queue with content-stable idempotency key.- const sourceId = await resolveDefaultSourceId(opts.engine);- const chunkerVersion = await resolveChunkerVersion(opts.engine);- const idempotencyKey = buildReindexIdempotencyKey(sourceId, chunkerVersion, opts.newMode);-- const submitFn = opts.submitFn ?? defaultSubmit;- const { DEFAULT_PAID_CAP_USD, derivedCapUsd } = await import('../consent.ts');- const { jobSpendAuthorization } = await import('../minions/spend-authorization.ts');- const capUsd = Math.max(DEFAULT_PAID_CAP_USD, plan.est_usd === null ? 0 : derivedCapUsd(plan.est_usd));- const spend = jobSpendAuthorization({ consented_effects: ['paid'], cap_usd: capUsd, cap_source: 'default', via: 'tty_prompt' },- { command: `config set search.mode ${opts.newMode}`, of: 1, argv: ['gbrain', 'reindex', '--markdown'], ...(plan.est_usd !== null ? { est_usd: plan.est_usd } : {}) });- try {- const jobId = await submitFn(- 'reindex',- { markdown: true, source_id: sourceId },- idempotencyKey,- spend,- );- console.error(`[mode-switch] Submitted as job ${jobId}. Watch with: gbrain jobs follow ${jobId}`);- } catch (err) {- console.error(`[mode-switch] Submit failed: ${(err as Error).message}`);- console.error(`[mode-switch] Run inline: ${summary.reindex_command}`);- }-- async function defaultSubmit(- jobName: string,- params: Record<string, unknown>,- idemKey: string,- spendAuthorization?: SpendAuthorization,- ): Promise<number> {- const queue = new MinionQueue(opts.engine);- const job = await queue.add(- jobName,- params,- { idempotency_key: idemKey },- { allowProtectedSubmit: true, ...(spendAuthorization ? { spendAuthorization } : {}) },- );- return job.id;- }-}--async function resolveDefaultSourceId(engine: BrainEngine): Promise<string> {- try {- const rows = await engine.executeRaw<{ id: string }>(- `SELECT id FROM sources WHERE id = 'default' LIMIT 1`,- );- return rows[0]?.id ?? 'default';- } catch {- return 'default';- }-}--async function resolveChunkerVersion(engine: BrainEngine): Promise<number> {- try {- const rows = await engine.executeRaw<{ v: string | null }>(- `SELECT value AS v FROM config WHERE key = 'chunker_version'`,- );- const v = Number(rows[0]?.v ?? 0);- return Number.isFinite(v) ? v : 0;- } catch {- return 0;- }+ await runReindexSynopsis(opts.engine, ['--synopsis', '--yes']);}diff --git a/test/mode-switch-ux.test.ts b/test/mode-switch-ux.test.tsindex d3d96931bd..e0d83b4049 100644--- a/test/mode-switch-ux.test.ts+++ b/test/mode-switch-ux.test.ts@@ -1,30 +1,27 @@/*** v0.40.3.0 — mode-switch UX (D3)*- * Pure unit tests for the 3 exports:* - summarizeTransition: 5-cell matrix + invalid fallthrough- * - probeWorkerAvailable: active / stale / never_seen branches via DI- * - buildReindexIdempotencyKey: content-stable invariance (codex D12 #1)+ * - runModeSwitchUx without a TTY: the banner names the synopsis sweep+ * preview (#8744) and prompts for nothing. The TTY preview-and-ask path+ * runs against a real brain in test/synopsis-sweep-8744.serial.test.ts.*/-import { afterAll, beforeAll, beforeEach, describe, expect, test } from 'bun:test';-import { PGLiteEngine } from '../src/core/pglite-engine.ts';-import { resetPgliteState } from './helpers/reset-pglite.ts';-import {- summarizeTransition,- probeWorkerAvailable,- buildReindexIdempotencyKey,- WORKER_STALE_THRESHOLD_MS,-} from '../src/core/search/mode-switch-ux.ts';+import { describe, expect, test } from 'bun:test';+import { runModeSwitchUx, summarizeTransition } from '../src/core/search/mode-switch-ux.ts';+import { withEnv } from './helpers/with-env.ts';describe('summarizeTransition (5-cell matrix + invalid fallthrough)', () => {test('any → tokenmax: tokenmax_opt_in with reindex required', () => {const s = summarizeTransition('balanced', 'tokenmax');expect(s.kind).toBe('tokenmax_opt_in');expect(s.reindex_required).toBe(true);- expect(s.reindex_command).toBe('gbrain reindex --markdown');+ expect(s.reindex_command).toBe('gbrain reindex --synopsis');expect(s.cost_estimate_per_query_cents).toBeGreaterThan(0);expect(s.callout_lines.some((l) => l.includes('tokenmax'))).toBe(true);+ // #8744: import and reindex --markdown embed at the title tier; only the synopsis sweep backfills.+ expect(s.callout_lines.some((l) => l.includes('`gbrain reindex --synopsis`'))).toBe(true);+ expect(s.callout_lines.join('\n')).not.toContain('reindex --markdown');});test('first-time any → tokenmax (null → tokenmax)', () => {@@ -75,92 +72,30 @@ describe('summarizeTransition (5-cell matrix + invalid fallthrough)', () => {});});-describe('probeWorkerAvailable (DI for active/stale/never_seen)', () => {- let engine: PGLiteEngine;-- beforeAll(async () => {- engine = new PGLiteEngine();- await engine.connect({});- await engine.initSchema();- });-- afterAll(async () => {- await engine.disconnect();- });-- beforeEach(async () => {- await resetPgliteState(engine);- });-- test('never_seen when minion_jobs has no recent activity', async () => {- const result = await probeWorkerAvailable(engine);- expect(result.status).toBe('never_seen');- expect(result.paste_ready_start_command).toBe('gbrain jobs work');- expect(result.last_heartbeat_iso).toBeUndefined();- });-- test('active when minion_jobs activity is fresh (<2 min)', async () => {- // Seed a recently-started job.- await engine.executeRaw(- `INSERT INTO minion_jobs (submission_authority, queue, name, data, status, started_at)- VALUES ('{"version":1,"kind":"application"}'::jsonb, 'default', 'test-job', '{}'::jsonb, 'active', now())`,- );- const result = await probeWorkerAvailable(engine);- expect(result.status).toBe('active');- expect(result.last_heartbeat_iso).toBeDefined();- });-- test('stale when activity is older than 2 min but within 10-min window', async () => {- // Seed a 5-minute-old started_at (within 10-min query window, > 2-min stale).- await engine.executeRaw(- `INSERT INTO minion_jobs (submission_authority, queue, name, data, status, started_at)- VALUES ('{"version":1,"kind":"application"}'::jsonb, 'default', 'test-stale-job', '{}'::jsonb, 'completed',- now() - INTERVAL '5 minutes')`,- );- const result = await probeWorkerAvailable(engine);- expect(result.status).toBe('stale');- expect(result.last_heartbeat_iso).toBeDefined();- });-- test('threshold constant is 2 minutes (120_000 ms)', () => {- expect(WORKER_STALE_THRESHOLD_MS).toBe(120_000);- });-});--describe('buildReindexIdempotencyKey (codex D12 Bug 1 content-stable invariance)', () => {- test('same inputs produce identical key', () => {- const k1 = buildReindexIdempotencyKey('default', 2, 'tokenmax');- const k2 = buildReindexIdempotencyKey('default', 2, 'tokenmax');- expect(k1).toBe(k2);- });-- test('key shape matches the canonical pattern', () => {- const k = buildReindexIdempotencyKey('default', 2, 'tokenmax');- expect(k).toBe('cr-backfill:default:2:tokenmax');- });-- test('different source_id produces different key', () => {- const k1 = buildReindexIdempotencyKey('default', 2, 'tokenmax');- const k2 = buildReindexIdempotencyKey('other-source', 2, 'tokenmax');- expect(k1).not.toBe(k2);- });-- test('different chunker_version produces different key (re-chunk = new key)', () => {- const k1 = buildReindexIdempotencyKey('default', 2, 'tokenmax');- const k2 = buildReindexIdempotencyKey('default', 3, 'tokenmax');- expect(k1).not.toBe(k2);- });-- test('different mode produces different key', () => {- const k1 = buildReindexIdempotencyKey('default', 2, 'tokenmax');- const k2 = buildReindexIdempotencyKey('default', 2, 'balanced');- expect(k1).not.toBe(k2);- });-- test('NOT timestamp-based: two consecutive runs with same state produce same key', async () => {- const k1 = buildReindexIdempotencyKey('default', 2, 'tokenmax');- await new Promise((r) => setTimeout(r, 10));- const k2 = buildReindexIdempotencyKey('default', 2, 'tokenmax');- expect(k1).toBe(k2);+describe('runModeSwitchUx without a TTY', () => {+ const capture = async (newMode: string) => {+ const lines: string[] = [];+ const error = console.error;+ console.error = (...args: unknown[]) => { lines.push(args.join(' ')); };+ try {+ await withEnv({ GBRAIN_NO_MODE_SWITCH_UX: undefined }, () => runModeSwitchUx({ oldMode: 'balanced', newMode, engine: {} as never, isTty: false,+ answerFn: async () => { throw new Error('no prompt without a TTY'); } }));+ } finally {+ console.error = error;+ }+ return lines;+ };++ test('balanced → tokenmax: the banner names the free synopsis sweep preview, not reindex --markdown', async () => {+ const lines = await capture('tokenmax');+ expect(lines[0]).toBe('[mode-switch] Switched to tokenmax. Per-chunk Haiku synopsis enabled.');+ expect(lines.some((l) => l.includes('`gbrain reindex --synopsis`'))).toBe(true);+ expect(lines.at(-1)).toBe('[mode-switch] Preview the backfill (spends nothing): gbrain reindex --synopsis');+ expect(lines.join('\n')).not.toContain('reindex --markdown');+ });++ test('balanced → conservative: no backfill hint', async () => {+ const lines = await capture('conservative');+ expect(lines.join('\n')).not.toContain('reindex');});});diff --git a/test/synopsis-sweep-8744.serial.test.ts b/test/synopsis-sweep-8744.serial.test.tsindex 50d7e1c80c..96ecaa8eee 100644--- a/test/synopsis-sweep-8744.serial.test.ts+++ b/test/synopsis-sweep-8744.serial.test.ts@@ -7,6 +7,8 @@* is not applicable on a balanced brain;* - the preview's pages, chunks, tokens and dollars on the configured* synopsis model, and that it queues and spends nothing;+ * - switching to tokenmax on a TTY previews the sweep and asks before+ * running `gbrain reindex --synopsis --yes`; a no queues nothing;* - a --yes run under a cap below one synopsis call is refused by the* shared spend group and stamps nothing; a later run resumes;* - --yes queues one contextual_reindex_per_chunk job per page under one@@ -30,6 +32,7 @@ import { importFromContent } from '../src/core/import-file.ts';import { __setChatTransportForTests, __setEmbedTransportForTests, configureGateway, resetGateway } from '../src/core/ai/gateway.ts';import { checkSynopsisTierCoverage } from '../src/commands/doctor/checks/synopsis-coverage.ts';import { runReindexSynopsis } from '../src/commands/reindex-synopsis.ts';+import { runModeSwitchUx } from '../src/core/search/mode-switch-ux.ts';import { estimateSynopsisCallUsd, SYNOPSIS_MAX_TOKENS } from '../src/core/page-summary.ts';import { reservationCostUsd } from '../src/core/budget/reservation-cost.ts';import { lookupEmbeddingPrice } from '../src/core/embedding-pricing.ts';@@ -73,10 +76,12 @@ beforeEach(() => { chatCalls = 0; _resetCliExitVerdictForTests(); });const body = (title: string, paragraphs: number) => `---\ntype: note\ntitle: ${title}\n---\n\n${Array.from({ length: paragraphs }, (_, i) => `Paragraph ${i} about ${title}. `.repeat(30)).join('\n\n')}\n`;const quiet = async <T>(fn: () => Promise<T>): Promise<T> => {const log = console.log;+ const error = console.error;const write = process.stderr.write.bind(process.stderr);console.log = () => {};+ console.error = () => {};process.stderr.write = (() => true) as typeof process.stderr.write;- try { return await fn(); } finally { console.log = log; process.stderr.write = write; }+ try { return await fn(); } finally { console.log = log; console.error = error; process.stderr.write = write; }};for (const kind of testBackends()) describe(`#8744 synopsis sweep (${kind})`, () => {@@ -159,6 +164,25 @@ for (const kind of testBackends()) describe(`#8744 synopsis sweep (${kind})`, ()expect(chatCalls).toBe(0);});+ test('mode switch to tokenmax on a TTY: previews the sweep and asks before running it; a no queues and spends nothing', async () => {+ const prompts: string[] = [];+ const saved = process.env.GBRAIN_NO_MODE_SWITCH_UX;+ delete process.env.GBRAIN_NO_MODE_SWITCH_UX;+ try {+ await quiet(() => runModeSwitchUx({ oldMode: 'balanced', newMode: 'tokenmax', engine, isTty: true,+ answerFn: async (prompt) => { prompts.push(prompt); return 'n'; } }));+ } finally {+ if (saved === undefined) delete process.env.GBRAIN_NO_MODE_SWITCH_UX; else process.env.GBRAIN_NO_MODE_SWITCH_UX = saved;+ }+ expect(prompts).toHaveLength(1);+ expect(prompts[0]).toContain("Run 'gbrain reindex --synopsis --yes' now?");+ expect(prompts[0]).toContain('for 2 page(s)');+ expect(prompts[0]).not.toContain('reindex --markdown');+ const jobs = await engine.executeRaw<{ n: number | string }>(`SELECT count(*)::int AS n FROM minion_jobs`);+ expect(Number(jobs[0]!.n)).toBe(0);+ expect(chatCalls).toBe(0);+ });+test('--yes under a cap below one synopsis call: the shared spend cap refuses the work, nothing is stamped, and the run says so', async () => {const result = await quiet(() => runReindexSynopsis(engine, ['--synopsis', '--yes', '--max-usd', '0.0001'], { pollMs: 100 }));expect(result.mode).toBe('run');