Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 5350bbc796 test(calibration): replace real-name holder fixture with charlie-example placeholder
Privacy iron rule: no real people's names in checked-in code. The sanctioned
placeholder mapping uses people/charlie-example.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 11:21:06 -07:00
8c27339c5c fix(calibration): resolve owner holder via config (default 'self'), fixes #2464
Takeover of #2467 (rebased onto master). consolidate writes owner takes
with holder='self' while calibration-profile, calibration CLI/op, think's
calibration block, emotional-weight, and doctor's calibration_freshness
all defaulted to a hardcoded 'garry' — so getScorecard returned 0
resolved and the calibration profile never built on non-upstream brains.

New src/core/owner-holder.ts is the single source of truth:
resolveOwnerHolder({override, configValue}) = override >
emotional_weight.user_holder config > 'self'. All six call sites route
through it; doctor's freshness SQL is parameterized ().

Upgrade note: upstream-owner brains with historical holder='garry'
profiles should `gbrain config set emotional_weight.user_holder garry`
to keep reading them.

Co-authored-by: devty <devty@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:19:58 -07:00
26 changed files with 187 additions and 254 deletions
+1
View File
@@ -457,6 +457,7 @@ unresolvable+true|false, pre-v80 NULL/NULL rows survive).
- `src/core/think/prompt.ts` extension — anti-bias rewrite. `withCalibration` option on `buildThinkSystemPrompt` adds anti-bias rules. `buildCalibrationBlock()` emits the `<calibration>` XML. `buildThinkUserMessage` has TWO shapes: default (question first), and with-calibration (retrieval → calibration → question) when opt-in. Wired into `runThink` via `opts.withCalibration` + `opts.calibrationHolder`.
- `src/commands/calibration.ts` — CLI: `gbrain calibration` (read + print), `--regenerate`, `--undo-wave <ver>`, `ab-report`. MCP op `get_calibration_profile` (scope: read) backs the same data path. Source-scoped via `sourceScopeOpts(ctx)`.
- `src/commands/serve-http.ts` extension — three admin routes: `/admin/api/calibration/profile`, `/admin/api/calibration/charts/:type` (image/svg+xml; type in {brier-trend, domain-bars, pattern-statements, abandoned-threads}), `/admin/api/calibration/pattern/:id` (drill-down).
- `src/core/owner-holder.ts` — single source of truth for "the brain owner" holder string. `DEFAULT_OWNER_HOLDER = 'self'` (matches the consolidate facts→takes writer + `docs/takes-vs-facts.md`); `resolveOwnerHolder({override, configValue})` returns override > `emotional_weight.user_holder` config > `'self'`. Consumed by the calibration_profile cycle phase, `gbrain calibration` CLI, the `get_calibration_profile` op, `think`'s calibration block, `emotional-weight`'s `DEFAULT_USER_HOLDER`, and doctor's `calibration_freshness`. Pure; unit-tested in `test/owner-holder.test.ts`. Does NOT unify owner-identity fragmentation (`self`/`brain`/`people-<owner>`) — tracked separately.
- `src/commands/takes.ts` extension — `gbrain takes revisit <slug>` opens $EDITOR on the source page with a `<!-- gbrain:revisit -->` cursor marker.
- `src/commands/doctor.ts` extension — 4 checks: `abandoned_threads`, `calibration_freshness`, `grade_confidence_drift` (mitigation surface; math ships later), `voice_gate_health`.
- `admin/src/pages/Calibration.tsx` — Calibration tab. Single-column layout. `<TrustedSVG>` wrapper handles `dangerouslySetInnerHTML` for the server-rendered SVG.
+15
View File
@@ -91,3 +91,18 @@ First full takes extraction run on a ~100K-page brain:
4. **Self-reported ≠ verified.** "Reports 7 figures" → holder=person, weight=0.75, NOT world/1.0
5. **No false precision.** Use 0.05 increments (0.35, 0.55, 0.75), not 0.74 or 0.82
6. **"So what" test.** Skip Twitter handles, follower counts, obvious metadata
## Owner-holder canonicalization
"The brain owner" is, by convention, the holder string **`self`** — the value the
dream `consolidate` phase stamps when it promotes the owner's hot facts into cold
takes. Calibration, `think`, and the `doctor` calibration check resolve the owner
holder through `resolveOwnerHolder` (`src/core/owner-holder.ts`): explicit override
> `emotional_weight.user_holder` config > `self`.
Known limitation (tracked in garrytan/gbrain#2465): the owner can also
appear under `brain` (a take the owner asserts, via `propose_takes`) and
`people/<owner>` (extraction that names the owner). The resolver selects the
*default* canonical owner string for reads; it does not merge those other
strings. Per-take attribution for other people (e.g. `people/george`) is
unaffected and correct.
-4
View File
@@ -686,7 +686,6 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
try {
const { MinionQueue } = await import('../core/minions/queue.ts');
const { computeRecommendations, embeddingProviderConfigured, HOSTED_EMBED_KEY_CONFIG } = await import('../core/brain-score-recommendations.ts');
const { countExtractionLag } = await import('../core/remediation/context.ts');
const queue = new MinionQueue(engine);
const slotMs = Math.floor(Date.now() / (baseInterval * 1000)) * baseInterval * 1000;
const slot = new Date(slotMs).toISOString();
@@ -878,9 +877,6 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
return !!(process.env[envVar] || (cfgField ? embedKeyCfg[cfgField] : undefined));
}),
hasChatApiKey: !!(process.env.ANTHROPIC_API_KEY || await engine.getConfig('anthropic_api_key')),
// Real extraction-lag gate for sync.repo/extract.all — same counter
// loadRecommendationContext uses (replaces the health.stale_pages proxy).
extractionLagPages: await countExtractionLag(engine),
};
// v0.41.18.0 (A5 + A19 + A22, T15): consult onboard recommendations
// ALONGSIDE doctor's brain-score recommendations. Onboard's 4 new
+10 -3
View File
@@ -23,6 +23,7 @@ import { runPhaseCalibrationProfile } from '../core/cycle/calibration-profile.ts
import { sourceScopeOpts, type OperationContext } from '../core/operations.ts';
import type { GBrainConfig } from '../core/config.ts';
import { GBrainError } from '../core/types.ts';
import { resolveOwnerHolder } from '../core/owner-holder.ts';
export interface CalibrationProfileRow {
/** BIGSERIAL → string (postgres.js int8 wire shape; never Number() — int8
@@ -167,7 +168,10 @@ export async function runCalibration(
config: GBrainConfig,
): Promise<void> {
const { opts } = parseArgs(args);
const holder = opts.holder ?? 'garry';
const holder = resolveOwnerHolder({
override: opts.holder,
configValue: await engine.getConfig('emotional_weight.user_holder'),
});
// Resolve --source / GBRAIN_SOURCE / .gbrain-source so the (now reachable, #2035)
// calibration command targets the right source in a multi-source brain instead
// of always reading `default`. No signal → 'default' (prior behavior).
@@ -253,12 +257,15 @@ export async function getCalibrationProfileOp(
ctx: OperationContext,
params: { holder?: string },
): Promise<CalibrationProfileRow | null> {
const holder = params.holder ?? 'garry';
const holder = resolveOwnerHolder({
override: params.holder,
configValue: await ctx.engine.getConfig('emotional_weight.user_holder'),
});
if (typeof holder !== 'string' || holder.length === 0) {
throw new GBrainError(
'INVALID_HOLDER',
'get_calibration_profile.holder must be a non-empty string',
'pass holder="<slug>" or omit to default to "garry"',
'pass holder="<slug>" or omit to default to the owner holder (config emotional_weight.user_holder, else "self")',
);
}
const scope = sourceScopeOpts(ctx);
+8 -2
View File
@@ -28,6 +28,7 @@ import type { DbUrlSource } from '../core/config.ts';
import { gbrainPath, loadConfig } from '../core/config.ts';
import { reflexEnabled } from '../core/context/reflex.ts';
import { resolveSocketPath } from '../core/context/resolve-ipc.ts';
import { resolveOwnerHolder } from '../core/owner-holder.ts';
import { homedir } from 'os';
import { dirname, isAbsolute, join, resolve as resolvePath } from 'path';
import { fileURLToPath } from 'url';
@@ -1287,14 +1288,19 @@ export async function checkAbandonedThreads(engine: BrainEngine): Promise<Check>
/**
* calibration_freshness: warns when the active calibration profile is
* older than 7 days (configurable). Default holder 'garry'. Multi-source
* older than 7 days (configurable). Default holder resolves via resolveOwnerHolder
* (config emotional_weight.user_holder, else 'self'). Multi-source
* brains see one row per source; this check uses the most recent across
* all sources.
*/
export async function checkCalibrationFreshness(engine: BrainEngine): Promise<Check> {
try {
const ownerHolder = resolveOwnerHolder({
configValue: await engine.getConfig('emotional_weight.user_holder'),
});
const rows = await engine.executeRaw<{ generated_at: Date | null }>(
`SELECT MAX(generated_at) AS generated_at FROM calibration_profiles WHERE holder = 'garry'`,
`SELECT MAX(generated_at) AS generated_at FROM calibration_profiles WHERE holder = $1`,
[ownerHolder],
);
const generated = rows[0]?.generated_at;
if (!generated) {
+4 -3
View File
@@ -45,6 +45,7 @@ import {
type IngestionContentType,
type IngestionEvent,
} from '../core/ingestion/types.ts';
import { resolveOwnerHolder } from '../core/owner-holder.ts';
/**
* /health endpoint timeout. 3s rather than 5s: Fly.io's default
@@ -1190,7 +1191,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
app.get('/admin/api/calibration/pattern/:id', requireAdmin, async (req: Request, res: Response) => {
try {
const { getLatestProfile } = await import('./calibration.ts');
const holder = (req.query.holder as string) || 'garry';
const holder = resolveOwnerHolder({ override: (req.query.holder as string) || undefined, configValue: await engine.getConfig('emotional_weight.user_holder') });
const profile = await getLatestProfile(engine, { holder });
if (!profile) {
res.status(404).json({ error: 'no_profile' });
@@ -1240,7 +1241,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
app.get('/admin/api/calibration/profile', requireAdmin, async (req: Request, res: Response) => {
try {
const { getLatestProfile } = await import('./calibration.ts');
const holder = (req.query.holder as string) || 'garry';
const holder = resolveOwnerHolder({ override: (req.query.holder as string) || undefined, configValue: await engine.getConfig('emotional_weight.user_holder') });
const profile = await getLatestProfile(engine, { holder });
res.json(profile);
} catch (err) {
@@ -1257,7 +1258,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
renderAbandonedThreadsCard,
renderPatternStatementsCard,
} = await import('../core/calibration/svg-renderer.ts');
const holder = (req.query.holder as string) || 'garry';
const holder = resolveOwnerHolder({ override: (req.query.holder as string) || undefined, configValue: await engine.getConfig('emotional_weight.user_holder') });
const type = req.params.type;
const profile = await getLatestProfile(engine, { holder });
+2 -1
View File
@@ -29,6 +29,7 @@ import {
} from '../core/takes-fence.ts';
import { withPageLock } from '../core/page-lock.ts';
import { resolveSourceId } from '../core/source-resolver.ts';
import { resolveOwnerHolder } from '../core/owner-holder.ts';
// --- Helpers ---
@@ -364,7 +365,7 @@ async function cmdResolve(engine: BrainEngine, args: string[], sourceId?: string
// --evidence is the v0.30.0 alias for --source on the resolve subcommand
// (semantic clarity: "what evidence resolved this bet?").
const source = flagValue(args, '--evidence') ?? flagValue(args, '--source');
const resolvedBy = flagValue(args, '--by') ?? 'garry';
const resolvedBy = flagValue(args, '--by') ?? resolveOwnerHolder({ configValue: await engine.getConfig('emotional_weight.user_holder') });
const dirArg = flagValue(args, '--dir');
const pageId = await getPageId(engine, slug, sourceId);
+8 -26
View File
@@ -146,16 +146,6 @@ export interface RecommendationContext {
chatModel?: string;
/** Whether the chat provider has a usable API key. */
hasChatApiKey?: boolean;
/**
* Count of pages needing link/timeline extraction — the SAME staleness the
* `gbrain extract --stale` walk and doctor's `links_extraction_lag` check use
* (`engine.countStalePagesForExtraction`). Gates the sync→extract pipeline
* (sync.repo / extract.all). Replaces the old `health.stale_pages` gate, which
* counted "pages whose updated_at predates their newest timeline entry" — a
* proxy that broke when the updated_at-on-timeline-insert trigger was dropped
* (migration v10) and never reflected real extraction work.
*/
extractionLagPages?: number;
}
/** Triage result for one check. */
@@ -202,28 +192,20 @@ export function computeRecommendations(
const source = ctx.sourceId ?? 'default';
// ---------------------------------------------------------------------
// sync.repo + extract.all — the materialization pipeline, gated on the REAL
// extraction lag (pages whose link/timeline edges are stale), NOT on the
// legacy `health.stale_pages` proxy. `extractionLagPages` comes from the same
// counter the `extract --stale` walk + doctor's `links_extraction_lag` use, so
// the recommendation can only fire when running extract will actually reduce
// it (and clear the rec). See RecommendationContext.extractionLagPages.
// sync.repo is the prerequisite: re-sync so pages are current before extract
// materializes their edges.
// sync.repo — fires when sync hasn't run recently OR pages are stale
// ---------------------------------------------------------------------
const extractionLag = ctx.extractionLagPages ?? 0;
if (ctx.repoPath && extractionLag > 0) {
if (ctx.repoPath && health.stale_pages > 0) {
const params = { repoPath: ctx.repoPath, sourceId: ctx.sourceId, noEmbed: true };
out.push({
id: 'sync.repo',
job: 'sync',
params,
idempotency_key: idemKey(source, 'sync', params),
severity: extractionLag > 50 ? 'high' : 'medium',
est_seconds: Math.min(600, 30 + extractionLag * 0.5),
severity: health.stale_pages > 50 ? 'high' : 'medium',
est_seconds: Math.min(600, 30 + health.stale_pages * 0.5),
est_usd_cost: 0, // sync is fs+DB only
depends_on: [],
rationale: `Sync before extracting ${extractionLag} page${extractionLag === 1 ? '' : 's'} with stale link/timeline edges`,
rationale: `${health.stale_pages} stale page${health.stale_pages === 1 ? '' : 's'} on disk`,
status: 'remediable',
});
}
@@ -255,7 +237,7 @@ export function computeRecommendations(
est_seconds: Math.min(3600, 5 + health.missing_embeddings * 0.05),
est_usd_cost,
// sync should run first so embed sees fresh pages.
depends_on: ctx.repoPath && extractionLag > 0 ? ['sync.repo'] : [],
depends_on: ctx.repoPath && health.stale_pages > 0 ? ['sync.repo'] : [],
rationale: `${health.missing_embeddings} chunk${health.missing_embeddings === 1 ? '' : 's'} invisible to vector search`,
status: 'remediable',
});
@@ -285,7 +267,7 @@ export function computeRecommendations(
// Triggered when sync.repo fires (because sync was set to noEmbed:true,
// and noExtract:true after T5 lands → extract job is the materializer).
// ---------------------------------------------------------------------
if (ctx.repoPath && extractionLag > 0) {
if (ctx.repoPath && health.stale_pages > 0) {
const params = { mode: 'all', dir: ctx.repoPath };
out.push({
id: 'extract.all',
@@ -296,7 +278,7 @@ export function computeRecommendations(
est_seconds: Math.min(600, 30 + health.page_count * 0.01),
est_usd_cost: 0,
depends_on: ['sync.repo'],
rationale: `Materialize link + timeline edges for ${extractionLag} page${extractionLag === 1 ? '' : 's'} with stale extraction`,
rationale: 'Materialize link + timeline edges from fresh pages',
status: 'remediable',
});
}
+3 -2
View File
@@ -68,6 +68,7 @@ import {
type BrainstormCheckpoint,
type CheckpointCross,
} from './checkpoint.ts';
import { resolveOwnerHolder } from '../owner-holder.ts';
export { BudgetExhausted };
@@ -139,7 +140,7 @@ export interface BrainstormOptions {
modelOverride?: string;
/** Skip the cost-preview TTY grace window. Required for non-interactive callers. */
skipCostPreview?: boolean;
/** When set, force the user holder for calibration profile lookup. Falls back to config (`emotional_weight.user_holder`) then `'garry'`. */
/** When set, force the user holder for calibration profile lookup. Falls back to config (`emotional_weight.user_holder`) then `'self'`. */
holderOverride?: string;
/** Source scope. */
sourceId?: string;
@@ -623,7 +624,7 @@ async function _runBrainstormInner(
}
// ---- Phase 3: calibration context (cold-start fallback) ----
const holder = opts.holderOverride ?? config.emotional_weight?.user_holder ?? 'garry';
const holder = resolveOwnerHolder({ override: opts.holderOverride, configValue: config.emotional_weight?.user_holder });
const calibContext = await loadCalibrationContext(engine, {
holder,
sourceId: opts.sourceId,
+1 -1
View File
@@ -25,7 +25,7 @@ import type { BrainEngine } from '../engine.ts';
export interface ABRunInput {
question: string;
/** Holder context for calibration. Default 'garry'. */
/** Holder context for calibration. Resolves via resolveOwnerHolder (config emotional_weight.user_holder, else 'self'). */
holder?: string;
/** Engine for DB write. */
engine: BrainEngine;
+6 -2
View File
@@ -26,6 +26,7 @@
*/
import { BaseCyclePhase, type ScopedReadOpts, type BasePhaseOpts } from './base-phase.ts';
import { resolveOwnerHolder } from '../owner-holder.ts';
import { chat as gatewayChat } from '../ai/gateway.ts';
import { TIER_DEFAULTS } from '../model-config.ts';
import { gateVoice, type VoiceGateGenerator, type VoiceGateJudge } from '../calibration/voice-gate.ts';
@@ -96,7 +97,7 @@ export type PatternStatementsGenerator = (input: {
export type BiasTagsGenerator = (patterns: string[]) => Promise<string[]>;
export interface CalibrationProfileOpts extends BasePhaseOpts {
/** Holder to generate the profile for. Default 'garry'. */
/** Holder to generate the profile for. Default resolves via resolveOwnerHolder (config emotional_weight.user_holder, else 'self'). */
holder?: string;
/** Inject the patterns generator (tests). */
patternsGenerator?: PatternStatementsGenerator;
@@ -227,7 +228,10 @@ class CalibrationProfilePhase extends BaseCyclePhase {
_ctx: OperationContext,
opts: CalibrationProfileOpts,
): Promise<{ summary: string; details: Record<string, unknown>; status?: PhaseStatus }> {
const holder = opts.holder ?? 'garry';
const holder = resolveOwnerHolder({
override: opts.holder,
configValue: await engine.getConfig('emotional_weight.user_holder'),
});
const promptVersion = opts.promptVersion ?? CALIBRATION_PROFILE_PROMPT_VERSION;
const modelId = opts.model ?? TIER_DEFAULTS.reasoning;
const gradeCompletion = opts.gradeCompletion ?? 1.0;
+7 -4
View File
@@ -14,6 +14,8 @@
* See `loadHighEmotionTags` for the resolution path.
*/
import { DEFAULT_OWNER_HOLDER } from '../owner-holder.ts';
/**
* Default high-emotion tag seed list. Pages with any tag in this set get the
* tag-emotion boost in the formula below. Override via config key
@@ -43,11 +45,12 @@ export const HIGH_EMOTION_TAGS: ReadonlySet<string> = new Set([
]);
/**
* Holder name treated as "the user" for the Garry-as-holder ratio. Configurable
* via the `emotional_weight.user_holder` config key (defaults to 'garry' to
* match the v0.28 schema's takes table convention).
* Holder name treated as "the user" for the user-as-holder ratio. Configurable
* via the `emotional_weight.user_holder` config key; defaults to the canonical
* owner holder ('self', DEFAULT_OWNER_HOLDER) so it matches the consolidate
* factstakes writer instead of a hardcoded name.
*/
export const DEFAULT_USER_HOLDER = 'garry';
export const DEFAULT_USER_HOLDER = DEFAULT_OWNER_HOLDER;
export interface EmotionalWeightTake {
holder: string;
+1 -1
View File
@@ -3289,7 +3289,7 @@ const get_calibration_profile: Operation = {
holder: {
type: 'string',
description:
"Holder slug, e.g. 'garry' or 'people/charlie-example'. Defaults to 'garry' when omitted.",
"Holder slug, e.g. 'self' or 'people/charlie-example'. Defaults to config emotional_weight.user_holder, else 'self', when omitted.",
},
},
handler: async (ctx, p) => {
+24
View File
@@ -0,0 +1,24 @@
/**
* Canonical holder string for "the brain owner," resolved in ONE place so the
* calibration / think / doctor / emotional-weight defaults stop disagreeing.
*
* The default matches the consolidate factstakes writer
* (src/core/cycle/phases/consolidate.ts: holder:'self') and docs/takes-vs-facts.md.
* Do NOT introduce a fourth literal three already exist historically
* ('garry', 'system', 'self'); this is the source of truth.
*
* NORMALIZATION NOTE: the brain owner may also appear under other holder
* strings 'brain' (propose_takes when the author asserts a claim) and
* people/<owner> (extraction that names the owner). This resolver only selects
* the *default* canonical owner string for reads; it does NOT merge those other
* strings. Unifying them is owner-identity entity-resolution, tracked separately
* (see garrytan/gbrain#2465). Until then, historical owner takes
* under 'brain'/people-<owner> are not folded into the default profile.
*/
export const DEFAULT_OWNER_HOLDER = 'self';
export function resolveOwnerHolder(
opts: { override?: string | null; configValue?: string | null },
): string {
return opts.override ?? opts.configValue ?? DEFAULT_OWNER_HOLDER;
}
-25
View File
@@ -8,7 +8,6 @@
import type { BrainEngine } from '../engine.ts';
import type { RecommendationContext } from '../brain-score-recommendations.ts';
import { LINK_EXTRACTOR_VERSION_TS } from '../link-extraction.ts';
// Re-export so consumers can `import { RecommendationContext } from '../remediation'`
// — the canonical RecommendationContext type still lives in
@@ -69,29 +68,5 @@ export async function loadRecommendationContext(
embeddingDimensions,
embeddingProviderConfigured: embeddingConfigured,
hasChatApiKey: !!(process.env.ANTHROPIC_API_KEY || fileCfg?.anthropic_api_key),
extractionLagPages: await countExtractionLag(engine),
};
}
/**
* Real extraction-lag count the SAME staleness `gbrain extract --stale`
* processes (engine.countStalePagesForExtraction with
* versionTs=LINK_EXTRACTOR_VERSION_TS, matching doctor's links_extraction_lag
* check without versionTs, pages stamped before an extractor version bump
* would lag for doctor/extract but never trip this gate). Drives the
* syncextract recommendation pipeline; replaces the legacy
* `health.stale_pages` proxy that no longer reflected real extraction work
* after the v10 trigger drop.
*
* Shared by loadRecommendationContext AND the D7 per-step recheck in
* runRemediation the recheck MUST refresh this gate alongside getHealth,
* or a completed extract step keeps re-firing off the frozen initial count.
*/
export async function countExtractionLag(engine: BrainEngine): Promise<number> {
try {
return await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS });
} catch {
/* counter unavailable (very old brain / mid-migration) — treat as 0 */
return 0;
}
}
+2 -7
View File
@@ -16,7 +16,7 @@ import {
computeRecommendations,
} from '../brain-score-recommendations.ts';
import type { RemediationStep } from '../remediation-step.ts';
import { countExtractionLag, loadRecommendationContext } from './context.ts';
import { loadRecommendationContext } from './context.ts';
import { computeRemediationPlan } from './plan.ts';
import type {
RemediationHooks,
@@ -65,7 +65,7 @@ export async function runRemediation(
clearRemediationCheckpoint,
} = await import('../remediation-checkpoint.ts');
let ctx = await loadRecommendationContext(engine);
const ctx = await loadRecommendationContext(engine);
// Pre-flight ceiling check via the shared plan computation.
const initialPlan = await computeRemediationPlan(engine, { targetScore });
@@ -305,11 +305,6 @@ export async function runRemediation(
// steps with bumped retry suffix (D1).
if (recs.length === 0 || stepCount >= maxJobs) break;
const freshHealth = await engine.getHealth();
// Refresh the extraction-lag gate alongside health: ctx was loaded once
// before the loop, and a completed sync/extract step is exactly what
// drives the count down. Reusing the frozen initial count would re-fire
// sync.repo/extract.all every recheck until maxJobs.
ctx = { ...ctx, extractionLagPages: await countExtractionLag(engine) };
recs = computeRecommendations(freshHealth, ctx).filter((r) => r.status === 'remediable');
}
};
+7 -3
View File
@@ -23,6 +23,7 @@ import { runGather, renderPagesBlock, takesHitToTakeForPrompt } from './gather.t
import { renderTakesBlock } from './sanitize.ts';
import { buildThinkSystemPrompt, buildThinkUserMessage } from './prompt.ts';
import { resolveCitations, type ParsedCitation } from './cite-render.ts';
import { resolveOwnerHolder } from '../owner-holder.ts';
import { resolveModel } from '../model-config.ts';
import { chat as gatewayChat, probeChatModel, type ChatResult } from '../ai/gateway.ts';
import { AIConfigError } from '../ai/errors.ts';
@@ -76,8 +77,8 @@ export interface RunThinkOpts {
*/
withCalibration?: boolean;
/**
* Holder to retrieve the calibration profile for. Default 'garry'. Only
* consulted when withCalibration=true.
* Holder to retrieve the calibration profile for. Resolves via resolveOwnerHolder
* (config emotional_weight.user_holder, else 'self'). Only consulted when withCalibration=true.
*/
calibrationHolder?: string;
/**
@@ -308,7 +309,10 @@ export async function runThink(
try {
const { getLatestProfile } = await import('../../commands/calibration.ts');
const profile = await getLatestProfile(engine, {
holder: opts.calibrationHolder ?? 'garry',
holder: resolveOwnerHolder({
override: opts.calibrationHolder,
configValue: await engine.getConfig('emotional_weight.user_holder'),
}),
});
if (profile) {
calibrationBlockOpts = {
-9
View File
@@ -1423,15 +1423,6 @@ export interface BrainStats {
export interface BrainHealth {
page_count: number;
embed_coverage: number;
/**
* LEGACY proxy: count of pages whose `updated_at` predates their newest
* timeline entry. This bumped meaningfully only while a trigger updated
* `pages.updated_at` on timeline insert; that trigger was dropped in
* migration v10, so the metric no longer reflects real "needs work" state.
* NO LONGER gates remediations the syncextract pipeline now gates on
* `RecommendationContext.extractionLagPages` (the real extraction-lag from
* `countStalePagesForExtraction`). Retained for the CLI health line + back-compat.
*/
stale_pages: number;
/**
* Islanded pages zero inbound AND zero outbound links. A hub page
+12 -9
View File
@@ -119,12 +119,13 @@ describe('computeRecommendations', () => {
expect(recs.find((r) => r.id === 'embed.stale')).toBeUndefined();
});
test('extraction lag + dead links produce sync + backlinks + extract', () => {
test('stale pages + dead links produce sync + backlinks + extract', () => {
const health = makeHealth({
stale_pages: 25,
dead_links: 8,
brain_score: 70,
});
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 25 });
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
const ids = recs.map((r) => r.id);
expect(ids).toContain('sync.repo');
expect(ids).toContain('backlinks.fix');
@@ -132,17 +133,18 @@ describe('computeRecommendations', () => {
});
test('extract.all depends on sync.repo (D14: stable ids)', () => {
const health = makeHealth();
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 10 });
const health = makeHealth({ stale_pages: 10 });
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
const extract = recs.find((r) => r.id === 'extract.all');
expect(extract?.depends_on).toContain('sync.repo');
});
test('embed.stale depends on sync.repo when extraction also needed', () => {
test('embed.stale depends on sync.repo when sync also needed', () => {
const health = makeHealth({
stale_pages: 10,
missing_embeddings: 100,
});
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 10 });
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
const embed = recs.find((r) => r.id === 'embed.stale');
expect(embed?.depends_on).toContain('sync.repo');
});
@@ -157,9 +159,9 @@ describe('computeRecommendations', () => {
test('severity ordering: critical before high before medium', () => {
const health = makeHealth({
missing_embeddings: 100, // critical
stale_pages: 80, // high
});
// extractionLagPages > 50 → sync.repo fires at 'high' severity.
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 80 });
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
const critIdx = recs.findIndex((r) => r.severity === 'critical');
const highIdx = recs.findIndex((r) => r.severity === 'high');
expect(critIdx).toBeLessThan(highIdx);
@@ -168,10 +170,11 @@ describe('computeRecommendations', () => {
// D6 #5 — THE critical regression test for the agent contract.
test('D6 #5: determinism — same input twice produces identical output', () => {
const health = makeHealth({
stale_pages: 10,
missing_embeddings: 50,
dead_links: 3,
});
const ctx = { repoPath: '/brain', embeddingProviderConfigured: true, sourceId: 'default', extractionLagPages: 10 };
const ctx = { repoPath: '/brain', embeddingProviderConfigured: true, sourceId: 'default' };
const run1 = computeRecommendations(health, ctx);
const run2 = computeRecommendations(health, ctx);
expect(JSON.stringify(run1)).toBe(JSON.stringify(run2));
+13 -7
View File
@@ -27,6 +27,12 @@ function buildMockEngine(opts: { rows: CalibrationProfileRow[] }): {
const capturedParams: unknown[][] = [];
const engine = {
kind: 'pglite',
// #2464: getCalibrationProfileOp resolves the owner holder via
// resolveOwnerHolder(config emotional_weight.user_holder, else 'self'), so the
// mock must implement getConfig. null = key unset → resolver falls back to 'self'.
async getConfig(): Promise<string | null> {
return null;
},
async executeRaw<T>(sql: string, params?: unknown[]): Promise<T[]> {
capturedSql.push(sql);
capturedParams.push(params ?? []);
@@ -211,17 +217,17 @@ describe('formatProfileText', () => {
// ─── getCalibrationProfileOp ────────────────────────────────────────
describe('getCalibrationProfileOp (MCP)', () => {
test('defaults holder to "garry" when omitted', async () => {
const { engine } = buildMockEngine({ rows: [buildProfile({ holder: 'garry' })] });
test('defaults holder to "self" when omitted (config emotional_weight.user_holder unset)', async () => {
const { engine } = buildMockEngine({ rows: [buildProfile({ holder: 'self' })] });
const ctx = buildCtx(engine);
const result = await getCalibrationProfileOp(ctx, {});
expect(result?.holder).toBe('garry');
expect(result?.holder).toBe('self');
});
test('routes through sourceScopeOpts: scalar source-bound client gets source-scoped result', async () => {
const rows = [
buildProfile({ holder: 'garry', source_id: 'default' }),
buildProfile({ holder: 'garry', source_id: 'tenant-b' }),
buildProfile({ holder: 'self', source_id: 'default' }),
buildProfile({ holder: 'self', source_id: 'tenant-b' }),
];
const { engine } = buildMockEngine({ rows });
const ctx = buildCtx(engine, { sourceId: 'tenant-b' });
@@ -231,8 +237,8 @@ describe('getCalibrationProfileOp (MCP)', () => {
test('federated read scope sees the union of allowed sources', async () => {
const rows = [
buildProfile({ holder: 'garry', source_id: 'tenant-a' }),
buildProfile({ holder: 'garry', source_id: 'tenant-z' }),
buildProfile({ holder: 'self', source_id: 'tenant-a' }),
buildProfile({ holder: 'self', source_id: 'tenant-z' }),
];
const { engine } = buildMockEngine({ rows });
const ctx = buildCtx(engine, { allowedSources: ['tenant-a', 'tenant-b'] });
+26 -2
View File
@@ -32,7 +32,7 @@ interface CapturedSql {
params: unknown[];
}
function buildMockEngine(opts: { scorecard: TakesScorecard }): {
function buildMockEngine(opts: { scorecard: TakesScorecard; userHolder?: string | null }): {
engine: BrainEngine;
captured: CapturedSql[];
} {
@@ -42,6 +42,10 @@ function buildMockEngine(opts: { scorecard: TakesScorecard }): {
async getScorecard() {
return opts.scorecard;
},
async getConfig(key: string): Promise<string | null> {
if (key === 'emotional_weight.user_holder') return opts.userHolder ?? null;
return null;
},
async executeRaw<T>(sql: string, params?: unknown[]): Promise<T[]> {
captured.push({ sql, params: params ?? [] });
return [];
@@ -234,7 +238,7 @@ describe('runPhaseCalibrationProfile — phase integration', () => {
// grade_completion, domain_scorecards_json, patterns[], voice_passed, voice_attempts,
// bias_tags[], model_id
expect(insert!.params[0]).toBe('default'); // source_id
expect(insert!.params[1]).toBe('garry'); // holder
expect(insert!.params[1]).toBe('self'); // holder (resolved via resolveOwnerHolder, no override)
expect(insert!.params[2]).toBe(12); // total_resolved
expect(insert!.params[9]).toBe(true); // voice_gate_passed
expect(insert!.params[10]).toBe(1); // voice_gate_attempts
@@ -330,4 +334,24 @@ describe('runPhaseCalibrationProfile — phase integration', () => {
const insert = captured.find(c => c.sql.includes('INSERT INTO calibration_profiles'));
expect(insert!.params[0]).toBe('tenant-b');
});
test('cold-brain summary uses resolved owner holder self when user_holder unset', async () => {
const { engine } = buildMockEngine({
scorecard: { total_bets: 0, resolved: 0, correct: 0, incorrect: 0, partial: 0,
accuracy: null, brier: null, partial_rate: null, unresolvable_count: 0, unresolvable_rate: null },
});
const result = await runPhaseCalibrationProfile(buildCtx(engine), {});
expect(result.summary).toContain('holder=self');
expect(result.summary).not.toContain('holder=garry');
});
test('configured user_holder overrides the default in the cold-brain summary', async () => {
const { engine } = buildMockEngine({
scorecard: { total_bets: 0, resolved: 0, correct: 0, incorrect: 0, partial: 0,
accuracy: null, brier: null, partial_rate: null, unresolvable_count: 0, unresolvable_rate: null },
userHolder: 'people/charlie-example',
});
const result = await runPhaseCalibrationProfile(buildCtx(engine), {});
expect(result.summary).toContain('holder=people/charlie-example');
});
});
+6
View File
@@ -32,6 +32,12 @@ function buildMockEngine(opts: {
}): BrainEngine {
return {
kind: 'pglite',
// #2464: checkCalibrationFreshness resolves the owner holder via
// resolveOwnerHolder(config emotional_weight.user_holder, else 'self'), so the
// mock must implement getConfig. null = key unset → resolver falls back to 'self'.
async getConfig(): Promise<string | null> {
return null;
},
async executeRaw<T>(sql: string): Promise<T[]> {
if (opts.throwOn && opts.throwOn.test(sql)) {
throw new Error('mock engine error: ' + sql.slice(0, 50));
+4
View File
@@ -112,3 +112,7 @@ describe('computeEmotionalWeight', () => {
expect(HIGH_EMOTION_TAGS.has('mental-health')).toBe(true);
});
});
test('DEFAULT_USER_HOLDER is the canonical owner holder self', () => {
expect(DEFAULT_USER_HOLDER).toBe('self');
});
+27
View File
@@ -0,0 +1,27 @@
import { describe, test, expect } from 'bun:test';
import { resolveOwnerHolder, DEFAULT_OWNER_HOLDER } from '../src/core/owner-holder.ts';
describe('owner-holder', () => {
test('DEFAULT_OWNER_HOLDER is self', () => {
expect(DEFAULT_OWNER_HOLDER).toBe('self');
});
test('defaults to self when nothing provided', () => {
expect(resolveOwnerHolder({})).toBe('self');
});
test('null/undefined config falls back to self', () => {
expect(resolveOwnerHolder({ configValue: null })).toBe('self');
expect(resolveOwnerHolder({ configValue: undefined })).toBe('self');
});
test('uses config value when set and no override', () => {
expect(resolveOwnerHolder({ configValue: 'people/charlie-example' }))
.toBe('people/charlie-example');
});
test('override beats config and default', () => {
expect(resolveOwnerHolder({ override: 'world', configValue: 'people/charlie-example' }))
.toBe('world');
});
});
@@ -1,62 +0,0 @@
// test/remediation-context-extraction-lag.test.ts
//
// Pins the v-next fix: the sync→extract remediation pipeline gates on REAL
// extraction lag, not the legacy `health.stale_pages` proxy (which counted
// "updated_at predates newest timeline entry" — meaningless after the v10
// trigger drop). loadRecommendationContext now populates `extractionLagPages`
// from `engine.countStalePagesForExtraction` — the SAME counter the
// `gbrain extract --stale` walk and doctor's `links_extraction_lag` use — so a
// recommendation can only fire when running extract will actually reduce it.
import { afterAll, beforeAll, describe, expect, it } from 'bun:test';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { loadRecommendationContext } from '../src/core/remediation/context.ts';
let engine: PGLiteEngine;
beforeAll(async () => {
engine = new PGLiteEngine();
await engine.connect({});
await engine.initSchema();
});
afterAll(async () => {
await engine.disconnect();
});
describe('loadRecommendationContext — extractionLagPages wiring', () => {
it('is 0 on an empty brain (nothing to extract)', async () => {
const ctx = await loadRecommendationContext(engine);
expect(ctx.extractionLagPages).toBe(0);
});
it('reflects the real extraction-lag count once a page needs extraction', async () => {
// A freshly-imported page has links_extracted_at = NULL, which the canonical
// countStalePagesForExtraction predicate counts as stale-for-extraction.
await engine.putPage('p0', {
title: 'p0',
type: 'note' as never,
compiled_truth: 'body that is long enough to pass any minimum-length guards in the codebase',
timeline: '',
frontmatter: {},
source_path: 'p0.md',
});
const ctx = await loadRecommendationContext(engine);
expect(ctx.extractionLagPages).toBeGreaterThan(0);
});
it('counts pages stamped before LINK_EXTRACTOR_VERSION_TS (version-bump arm)', async () => {
// Backdate p0 so BOTH the NULL arm and the updated_at arm are quiet:
// updated_at < links_extracted_at, but links_extracted_at predates the
// extractor version stamp. doctor's links_extraction_lag and
// `extract --stale` both count this page; the remediation gate must too.
await engine.executeRaw(
`UPDATE pages SET updated_at = '2020-01-01T00:00:00Z'::timestamptz,
links_extracted_at = '2020-01-02T00:00:00Z'::timestamptz
WHERE slug = 'p0'`,
[],
);
const ctx = await loadRecommendationContext(engine);
expect(ctx.extractionLagPages).toBeGreaterThan(0);
});
});
@@ -1,81 +0,0 @@
// test/remediation-run-d7-refresh.serial.test.ts
//
// Pins the D7-recheck half of the extraction-lag gate fix: runRemediation
// loads RecommendationContext ONCE before the step loop, and the per-step
// recheck (D7) must REFRESH ctx.extractionLagPages alongside getHealth.
// Without the refresh, a completed sync/extract step keeps re-firing off
// the frozen initial count — the plan never converges and the loop burns
// steps until maxJobs.
//
// SERIAL (R2): uses top-level mock.module for the minion queue +
// wait-for-completion so no real worker is needed — mocks leak across
// files in a shard process, so this file must run in its own process.
import { describe, expect, mock, test } from 'bun:test';
// The fake brain: sync.repo clears the extraction lag when it "runs"
// (today's sync materializes link/timeline edges; extract.all is the
// explicit re-materializer). The frozen-ctx bug makes runRemediation
// ignore that and resubmit sync.repo on every D7 recheck.
let extractionLag = 25;
const submittedJobs: string[] = [];
mock.module('../src/core/minions/queue.ts', () => ({
MinionQueue: class {
constructor(_engine: unknown) {}
async add(job: string): Promise<{ id: number }> {
submittedJobs.push(job);
if (job === 'sync' || job === 'extract') extractionLag = 0;
return { id: submittedJobs.length };
}
},
}));
mock.module('../src/core/minions/wait-for-completion.ts', () => ({
waitForCompletion: async () => ({ status: 'completed' }),
}));
const health = () => ({
page_count: 100,
embed_coverage: 1.0,
stale_pages: 0, // legacy proxy stays 0 — the real counter drives the gate
orphan_pages: 0,
missing_embeddings: 0,
brain_score: 70,
dead_links: 0,
link_coverage: 1.0,
timeline_coverage: 1.0,
most_connected: [],
embed_coverage_score: 35,
link_density_score: 25,
timeline_coverage_score: 15,
no_orphans_score: 15,
no_dead_links_score: 10,
});
const fakeEngine = {
kind: 'pglite' as const,
getHealth: async () => health(),
getConfig: async (key: string) =>
key === 'sync.repo_path' ? '/tmp/brain-example' : null,
countStalePagesForExtraction: async () => extractionLag,
};
describe('runRemediation D7 recheck — extraction-lag gate refresh', () => {
test('a completed materializer step clears the gate; the pipeline is not resubmitted', async () => {
const { runRemediation } = await import('../src/core/remediation/run.ts');
const result = await runRemediation(
// Only the methods the orchestrator touches are needed.
fakeEngine as never,
{ targetScore: 0, maxJobs: 6 },
);
// Frozen-ctx bug: extractionLagPages stays 25 forever, so every D7
// recheck re-introduces the sync/extract pipeline and the loop burns
// all 6 maxJobs. With the refresh, the plan converges after the first
// completed step: no step id is ever submitted twice.
const ids = result.submitted.map((s) => s.id);
expect(new Set(ids).size).toBe(ids.length);
expect(submittedJobs.length).toBeLessThan(3);
expect(extractionLag).toBe(0);
});
});