mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 02:12:40 +00:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
89579780e0 | ||
|
|
cf2deedfc6 |
@@ -457,7 +457,6 @@ 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.
|
||||
|
||||
@@ -91,18 +91,3 @@ 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.
|
||||
|
||||
@@ -23,7 +23,6 @@ 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
|
||||
@@ -168,10 +167,7 @@ export async function runCalibration(
|
||||
config: GBrainConfig,
|
||||
): Promise<void> {
|
||||
const { opts } = parseArgs(args);
|
||||
const holder = resolveOwnerHolder({
|
||||
override: opts.holder,
|
||||
configValue: await engine.getConfig('emotional_weight.user_holder'),
|
||||
});
|
||||
const holder = opts.holder ?? 'garry';
|
||||
// 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).
|
||||
@@ -257,15 +253,12 @@ export async function getCalibrationProfileOp(
|
||||
ctx: OperationContext,
|
||||
params: { holder?: string },
|
||||
): Promise<CalibrationProfileRow | null> {
|
||||
const holder = resolveOwnerHolder({
|
||||
override: params.holder,
|
||||
configValue: await ctx.engine.getConfig('emotional_weight.user_holder'),
|
||||
});
|
||||
const holder = params.holder ?? 'garry';
|
||||
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 the owner holder (config emotional_weight.user_holder, else "self")',
|
||||
'pass holder="<slug>" or omit to default to "garry"',
|
||||
);
|
||||
}
|
||||
const scope = sourceScopeOpts(ctx);
|
||||
|
||||
@@ -28,7 +28,6 @@ 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';
|
||||
@@ -1288,19 +1287,14 @@ export async function checkAbandonedThreads(engine: BrainEngine): Promise<Check>
|
||||
|
||||
/**
|
||||
* calibration_freshness: warns when the active calibration profile is
|
||||
* older than 7 days (configurable). Default holder resolves via resolveOwnerHolder
|
||||
* (config emotional_weight.user_holder, else 'self'). Multi-source
|
||||
* older than 7 days (configurable). Default holder 'garry'. 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 = $1`,
|
||||
[ownerHolder],
|
||||
`SELECT MAX(generated_at) AS generated_at FROM calibration_profiles WHERE holder = 'garry'`,
|
||||
);
|
||||
const generated = rows[0]?.generated_at;
|
||||
if (!generated) {
|
||||
|
||||
+14
-1
@@ -1,5 +1,5 @@
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { embedBatch, currentEmbeddingSignature } from '../core/embedding.ts';
|
||||
import { embedBatch, currentEmbeddingSignature, resolveEmbeddingModelLabel } from '../core/embedding.ts';
|
||||
import type { ChunkInput } from '../core/types.ts';
|
||||
import { chunkText } from '../core/chunkers/recursive.ts';
|
||||
import { createProgress, type ProgressReporter } from '../core/progress.ts';
|
||||
@@ -581,11 +581,16 @@ async function embedPage(
|
||||
for (let j = 0; j < toEmbed.length; j++) {
|
||||
embeddingMap.set(toEmbed[j].chunk_index, embeddings[j]);
|
||||
}
|
||||
// #1717: label each (re)embedded chunk with the model that actually
|
||||
// produced its vector. Preserved chunks (not re-embedded this pass) keep
|
||||
// their existing model so a mixed-model page isn't relabeled wholesale.
|
||||
const embedModelLabel = resolveEmbeddingModelLabel();
|
||||
const updated: ChunkInput[] = chunks.map(c => ({
|
||||
chunk_index: c.chunk_index,
|
||||
chunk_text: c.chunk_text,
|
||||
chunk_source: c.chunk_source,
|
||||
embedding: embeddingMap.get(c.chunk_index),
|
||||
model: embeddingMap.has(c.chunk_index) && embedModelLabel ? embedModelLabel : c.model,
|
||||
token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
|
||||
}));
|
||||
|
||||
@@ -717,12 +722,16 @@ async function embedAll(
|
||||
for (let j = 0; j < toEmbed.length; j++) {
|
||||
embeddingMap.set(toEmbed[j].chunk_index, embeddings[j]);
|
||||
}
|
||||
// #1717: stamp the resolved embedding model on (re)embedded chunks;
|
||||
// preserve the existing model on chunks left untouched.
|
||||
const embedModelLabel = resolveEmbeddingModelLabel();
|
||||
// Preserve ALL chunks, only update embeddings for stale ones
|
||||
const updated: ChunkInput[] = chunks.map(c => ({
|
||||
chunk_index: c.chunk_index,
|
||||
chunk_text: c.chunk_text,
|
||||
chunk_source: c.chunk_source,
|
||||
embedding: embeddingMap.get(c.chunk_index) ?? undefined,
|
||||
model: embeddingMap.has(c.chunk_index) && embedModelLabel ? embedModelLabel : c.model,
|
||||
token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
|
||||
}));
|
||||
await observed(pacer, () => engine.upsertChunks(page.slug, updated, pageOpts));
|
||||
@@ -1012,11 +1021,15 @@ async function embedAllStale(
|
||||
for (let j = 0; j < stale.length; j++) {
|
||||
staleIdxToEmbedding.set(stale[j].chunk_index, embeddings[j]);
|
||||
}
|
||||
// #1717: label the re-embedded (stale) chunks with the resolved
|
||||
// model; preserve the existing model on the non-stale chunks.
|
||||
const embedModelLabel = resolveEmbeddingModelLabel();
|
||||
const merged: ChunkInput[] = existing.map(c => ({
|
||||
chunk_index: c.chunk_index,
|
||||
chunk_text: c.chunk_text,
|
||||
chunk_source: c.chunk_source,
|
||||
embedding: staleIdxToEmbedding.get(c.chunk_index) ?? undefined,
|
||||
model: staleIdxToEmbedding.has(c.chunk_index) && embedModelLabel ? embedModelLabel : c.model,
|
||||
token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
|
||||
}));
|
||||
await observed(pacer, () => engine.upsertChunks(slug, merged, { sourceId: keySourceId }));
|
||||
|
||||
@@ -45,7 +45,6 @@ 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
|
||||
@@ -1191,7 +1190,7 @@ 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 = resolveOwnerHolder({ override: (req.query.holder as string) || undefined, configValue: await engine.getConfig('emotional_weight.user_holder') });
|
||||
const holder = (req.query.holder as string) || 'garry';
|
||||
const profile = await getLatestProfile(engine, { holder });
|
||||
if (!profile) {
|
||||
res.status(404).json({ error: 'no_profile' });
|
||||
@@ -1241,7 +1240,7 @@ 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 = resolveOwnerHolder({ override: (req.query.holder as string) || undefined, configValue: await engine.getConfig('emotional_weight.user_holder') });
|
||||
const holder = (req.query.holder as string) || 'garry';
|
||||
const profile = await getLatestProfile(engine, { holder });
|
||||
res.json(profile);
|
||||
} catch (err) {
|
||||
@@ -1258,7 +1257,7 @@ export async function runServeHttp(engine: BrainEngine, options: ServeHttpOption
|
||||
renderAbandonedThreadsCard,
|
||||
renderPatternStatementsCard,
|
||||
} = await import('../core/calibration/svg-renderer.ts');
|
||||
const holder = resolveOwnerHolder({ override: (req.query.holder as string) || undefined, configValue: await engine.getConfig('emotional_weight.user_holder') });
|
||||
const holder = (req.query.holder as string) || 'garry';
|
||||
const type = req.params.type;
|
||||
const profile = await getLatestProfile(engine, { holder });
|
||||
|
||||
|
||||
@@ -29,7 +29,6 @@ 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 ---
|
||||
|
||||
@@ -365,7 +364,7 @@ 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') ?? resolveOwnerHolder({ configValue: await engine.getConfig('emotional_weight.user_holder') });
|
||||
const resolvedBy = flagValue(args, '--by') ?? 'garry';
|
||||
const dirArg = flagValue(args, '--dir');
|
||||
|
||||
const pageId = await getPageId(engine, slug, sourceId);
|
||||
|
||||
@@ -68,7 +68,6 @@ import {
|
||||
type BrainstormCheckpoint,
|
||||
type CheckpointCross,
|
||||
} from './checkpoint.ts';
|
||||
import { resolveOwnerHolder } from '../owner-holder.ts';
|
||||
|
||||
export { BudgetExhausted };
|
||||
|
||||
@@ -140,7 +139,7 @@ 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 `'self'`. */
|
||||
/** When set, force the user holder for calibration profile lookup. Falls back to config (`emotional_weight.user_holder`) then `'garry'`. */
|
||||
holderOverride?: string;
|
||||
/** Source scope. */
|
||||
sourceId?: string;
|
||||
@@ -624,7 +623,7 @@ async function _runBrainstormInner(
|
||||
}
|
||||
|
||||
// ---- Phase 3: calibration context (cold-start fallback) ----
|
||||
const holder = resolveOwnerHolder({ override: opts.holderOverride, configValue: config.emotional_weight?.user_holder });
|
||||
const holder = opts.holderOverride ?? config.emotional_weight?.user_holder ?? 'garry';
|
||||
const calibContext = await loadCalibrationContext(engine, {
|
||||
holder,
|
||||
sourceId: opts.sourceId,
|
||||
|
||||
@@ -25,7 +25,7 @@ import type { BrainEngine } from '../engine.ts';
|
||||
|
||||
export interface ABRunInput {
|
||||
question: string;
|
||||
/** Holder context for calibration. Resolves via resolveOwnerHolder (config emotional_weight.user_holder, else 'self'). */
|
||||
/** Holder context for calibration. Default 'garry'. */
|
||||
holder?: string;
|
||||
/** Engine for DB write. */
|
||||
engine: BrainEngine;
|
||||
|
||||
@@ -26,7 +26,6 @@
|
||||
*/
|
||||
|
||||
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';
|
||||
@@ -97,7 +96,7 @@ export type PatternStatementsGenerator = (input: {
|
||||
export type BiasTagsGenerator = (patterns: string[]) => Promise<string[]>;
|
||||
|
||||
export interface CalibrationProfileOpts extends BasePhaseOpts {
|
||||
/** Holder to generate the profile for. Default resolves via resolveOwnerHolder (config emotional_weight.user_holder, else 'self'). */
|
||||
/** Holder to generate the profile for. Default 'garry'. */
|
||||
holder?: string;
|
||||
/** Inject the patterns generator (tests). */
|
||||
patternsGenerator?: PatternStatementsGenerator;
|
||||
@@ -228,10 +227,7 @@ class CalibrationProfilePhase extends BaseCyclePhase {
|
||||
_ctx: OperationContext,
|
||||
opts: CalibrationProfileOpts,
|
||||
): Promise<{ summary: string; details: Record<string, unknown>; status?: PhaseStatus }> {
|
||||
const holder = resolveOwnerHolder({
|
||||
override: opts.holder,
|
||||
configValue: await engine.getConfig('emotional_weight.user_holder'),
|
||||
});
|
||||
const holder = opts.holder ?? 'garry';
|
||||
const promptVersion = opts.promptVersion ?? CALIBRATION_PROFILE_PROMPT_VERSION;
|
||||
const modelId = opts.model ?? TIER_DEFAULTS.reasoning;
|
||||
const gradeCompletion = opts.gradeCompletion ?? 1.0;
|
||||
|
||||
@@ -14,8 +14,6 @@
|
||||
* 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
|
||||
@@ -45,12 +43,11 @@ export const HIGH_EMOTION_TAGS: ReadonlySet<string> = new Set([
|
||||
]);
|
||||
|
||||
/**
|
||||
* 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
|
||||
* facts→takes writer instead of a hardcoded name.
|
||||
* 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).
|
||||
*/
|
||||
export const DEFAULT_USER_HOLDER = DEFAULT_OWNER_HOLDER;
|
||||
export const DEFAULT_USER_HOLDER = 'garry';
|
||||
|
||||
export interface EmotionalWeightTake {
|
||||
holder: string;
|
||||
|
||||
@@ -20,6 +20,7 @@
|
||||
import type { BrainEngine } from './engine.ts';
|
||||
import type { ChunkInput } from './types.ts';
|
||||
import { embedBatchWithBackoff } from '../commands/embed.ts';
|
||||
import { resolveEmbeddingModelLabel } from './embedding.ts';
|
||||
import { type DbPacer, createNoopPacer, observed } from './db-pacer.ts';
|
||||
import { AbortError } from './abort-check.ts';
|
||||
|
||||
@@ -200,11 +201,17 @@ export async function embedStaleForSource(
|
||||
for (let j = 0; j < stale.length; j++) {
|
||||
staleIdxToEmbedding.set(stale[j].chunk_index, embeddings[j]);
|
||||
}
|
||||
// #1717: label re-embedded chunks with the model that produced the
|
||||
// vector; preserved chunks keep their existing model. Without this,
|
||||
// upsertChunks falls back to DEFAULT_EMBEDDING_MODEL for every chunk
|
||||
// (the same mislabel the embed.ts paths fixed).
|
||||
const embedModelLabel = resolveEmbeddingModelLabel();
|
||||
const merged: ChunkInput[] = existing.map((c) => ({
|
||||
chunk_index: c.chunk_index,
|
||||
chunk_text: c.chunk_text,
|
||||
chunk_source: c.chunk_source,
|
||||
embedding: staleIdxToEmbedding.get(c.chunk_index) ?? undefined,
|
||||
model: staleIdxToEmbedding.has(c.chunk_index) && embedModelLabel ? embedModelLabel : c.model,
|
||||
token_count: c.token_count || Math.ceil(c.chunk_text.length / 4),
|
||||
// Carry through per-chunk metadata. upsertChunks writes these as
|
||||
// EXCLUDED.<col> (not COALESCE), so omitting them here resets image
|
||||
|
||||
@@ -113,6 +113,21 @@ export async function embedBatch(
|
||||
return results;
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolve the embedding model label (`provider:model`) to stamp onto
|
||||
* `content_chunks.model`, so each chunk records the model that actually
|
||||
* produced its vector instead of the engine's hardcoded default (#1717).
|
||||
* Returns undefined if the gateway is unconfigured; callers then fall back
|
||||
* to the chunk's existing model rather than mislabeling it.
|
||||
*/
|
||||
export function resolveEmbeddingModelLabel(): string | undefined {
|
||||
try {
|
||||
return gatewayGetModel();
|
||||
} catch {
|
||||
return undefined;
|
||||
}
|
||||
}
|
||||
|
||||
/** Currently-configured embedding model (short form without provider prefix). */
|
||||
export function getEmbeddingModelName(): string {
|
||||
return gatewayGetModel().split(':').slice(1).join(':') || 'text-embedding-3-large';
|
||||
|
||||
+11
-1
@@ -8,7 +8,7 @@ import { chunkText } from './chunkers/recursive.ts';
|
||||
import { chunkCodeText, chunkCodeTextFull, detectCodeLanguage, CHUNKER_VERSION } from './chunkers/code.ts';
|
||||
import { findChunkForOffset } from './chunkers/edge-extractor.ts';
|
||||
import { extractCodeRefs, imageOfCandidates } from './link-extraction.ts';
|
||||
import { embedBatch, embedMultimodal, currentEmbeddingSignature } from './embedding.ts';
|
||||
import { embedBatch, embedMultimodal, currentEmbeddingSignature, resolveEmbeddingModelLabel } from './embedding.ts';
|
||||
import { slugifyPath, slugifyCodePath, isCodeFilePath } from './sync.ts';
|
||||
import type { ChunkInput, PageInput, PageType } from './types.ts';
|
||||
import { computeEffectiveDate } from './effective-date.ts';
|
||||
@@ -716,8 +716,12 @@ export async function importFromContent(
|
||||
? chunks.map((c) => wrapChunkForEmbedding(c.chunk_text, prefix, c.chunk_source))
|
||||
: chunks.map((c) => c.chunk_text);
|
||||
const embeddings = await embedBatch(wrappedTexts);
|
||||
// #1717: label each chunk with the model that actually produced its
|
||||
// vector, not the engine's hardcoded default.
|
||||
const embedModelLabel = resolveEmbeddingModelLabel();
|
||||
for (let i = 0; i < chunks.length; i++) {
|
||||
chunks[i].embedding = embeddings[i];
|
||||
if (embedModelLabel) chunks[i].model = embedModelLabel;
|
||||
// token_count tracks the wrapped string length so cost reporting
|
||||
// reflects what we actually sent to the embedder.
|
||||
chunks[i].token_count = Math.ceil(wrappedTexts[i].length / 4);
|
||||
@@ -1141,7 +1145,10 @@ export async function importCodeFile(
|
||||
const matched = existingByKey.get(key);
|
||||
if (matched && matched.embedding) {
|
||||
// Reuse the existing embedding verbatim. No API call, no cost.
|
||||
// #1717: carry the existing model label along with the reused vector
|
||||
// so the upsert doesn't relabel it with the engine default.
|
||||
chunks[i]!.embedding = matched.embedding as Float32Array;
|
||||
chunks[i]!.model = matched.model ?? undefined;
|
||||
chunks[i]!.token_count = matched.token_count ?? undefined;
|
||||
} else {
|
||||
needsEmbedIndexes.push(i);
|
||||
@@ -1153,9 +1160,12 @@ export async function importCodeFile(
|
||||
try {
|
||||
const textsToEmbed = needsEmbedIndexes.map((i) => chunks[i]!.chunk_text);
|
||||
const embeddings = await embedBatch(textsToEmbed);
|
||||
// #1717: stamp the model that produced these vectors.
|
||||
const embedModelLabel = resolveEmbeddingModelLabel();
|
||||
for (let j = 0; j < needsEmbedIndexes.length; j++) {
|
||||
const i = needsEmbedIndexes[j]!;
|
||||
chunks[i]!.embedding = embeddings[j]!;
|
||||
if (embedModelLabel) chunks[i]!.model = embedModelLabel;
|
||||
chunks[i]!.token_count = Math.ceil(chunks[i]!.chunk_text.length / 4);
|
||||
}
|
||||
} catch (e: unknown) {
|
||||
|
||||
@@ -3289,7 +3289,7 @@ const get_calibration_profile: Operation = {
|
||||
holder: {
|
||||
type: 'string',
|
||||
description:
|
||||
"Holder slug, e.g. 'self' or 'people/charlie-example'. Defaults to config emotional_weight.user_holder, else 'self', when omitted.",
|
||||
"Holder slug, e.g. 'garry' or 'people/charlie-example'. Defaults to 'garry' when omitted.",
|
||||
},
|
||||
},
|
||||
handler: async (ctx, p) => {
|
||||
|
||||
@@ -1,24 +0,0 @@
|
||||
/**
|
||||
* 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 facts→takes 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;
|
||||
}
|
||||
@@ -23,7 +23,6 @@ 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';
|
||||
@@ -77,8 +76,8 @@ export interface RunThinkOpts {
|
||||
*/
|
||||
withCalibration?: boolean;
|
||||
/**
|
||||
* Holder to retrieve the calibration profile for. Resolves via resolveOwnerHolder
|
||||
* (config emotional_weight.user_holder, else 'self'). Only consulted when withCalibration=true.
|
||||
* Holder to retrieve the calibration profile for. Default 'garry'. Only
|
||||
* consulted when withCalibration=true.
|
||||
*/
|
||||
calibrationHolder?: string;
|
||||
/**
|
||||
@@ -309,10 +308,7 @@ export async function runThink(
|
||||
try {
|
||||
const { getLatestProfile } = await import('../../commands/calibration.ts');
|
||||
const profile = await getLatestProfile(engine, {
|
||||
holder: resolveOwnerHolder({
|
||||
override: opts.calibrationHolder,
|
||||
configValue: await engine.getConfig('emotional_weight.user_holder'),
|
||||
}),
|
||||
holder: opts.calibrationHolder ?? 'garry',
|
||||
});
|
||||
if (profile) {
|
||||
calibrationBlockOpts = {
|
||||
|
||||
@@ -27,12 +27,6 @@ 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 ?? []);
|
||||
@@ -217,17 +211,17 @@ describe('formatProfileText', () => {
|
||||
// ─── getCalibrationProfileOp ────────────────────────────────────────
|
||||
|
||||
describe('getCalibrationProfileOp (MCP)', () => {
|
||||
test('defaults holder to "self" when omitted (config emotional_weight.user_holder unset)', async () => {
|
||||
const { engine } = buildMockEngine({ rows: [buildProfile({ holder: 'self' })] });
|
||||
test('defaults holder to "garry" when omitted', async () => {
|
||||
const { engine } = buildMockEngine({ rows: [buildProfile({ holder: 'garry' })] });
|
||||
const ctx = buildCtx(engine);
|
||||
const result = await getCalibrationProfileOp(ctx, {});
|
||||
expect(result?.holder).toBe('self');
|
||||
expect(result?.holder).toBe('garry');
|
||||
});
|
||||
|
||||
test('routes through sourceScopeOpts: scalar source-bound client gets source-scoped result', async () => {
|
||||
const rows = [
|
||||
buildProfile({ holder: 'self', source_id: 'default' }),
|
||||
buildProfile({ holder: 'self', source_id: 'tenant-b' }),
|
||||
buildProfile({ holder: 'garry', source_id: 'default' }),
|
||||
buildProfile({ holder: 'garry', source_id: 'tenant-b' }),
|
||||
];
|
||||
const { engine } = buildMockEngine({ rows });
|
||||
const ctx = buildCtx(engine, { sourceId: 'tenant-b' });
|
||||
@@ -237,8 +231,8 @@ describe('getCalibrationProfileOp (MCP)', () => {
|
||||
|
||||
test('federated read scope sees the union of allowed sources', async () => {
|
||||
const rows = [
|
||||
buildProfile({ holder: 'self', source_id: 'tenant-a' }),
|
||||
buildProfile({ holder: 'self', source_id: 'tenant-z' }),
|
||||
buildProfile({ holder: 'garry', source_id: 'tenant-a' }),
|
||||
buildProfile({ holder: 'garry', source_id: 'tenant-z' }),
|
||||
];
|
||||
const { engine } = buildMockEngine({ rows });
|
||||
const ctx = buildCtx(engine, { allowedSources: ['tenant-a', 'tenant-b'] });
|
||||
|
||||
@@ -32,7 +32,7 @@ interface CapturedSql {
|
||||
params: unknown[];
|
||||
}
|
||||
|
||||
function buildMockEngine(opts: { scorecard: TakesScorecard; userHolder?: string | null }): {
|
||||
function buildMockEngine(opts: { scorecard: TakesScorecard }): {
|
||||
engine: BrainEngine;
|
||||
captured: CapturedSql[];
|
||||
} {
|
||||
@@ -42,10 +42,6 @@ function buildMockEngine(opts: { scorecard: TakesScorecard; userHolder?: string
|
||||
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 [];
|
||||
@@ -238,7 +234,7 @@ 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('self'); // holder (resolved via resolveOwnerHolder, no override)
|
||||
expect(insert!.params[1]).toBe('garry'); // holder
|
||||
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
|
||||
@@ -334,24 +330,4 @@ 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');
|
||||
});
|
||||
});
|
||||
|
||||
@@ -32,12 +32,6 @@ 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));
|
||||
|
||||
@@ -15,6 +15,7 @@ import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:tes
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
import { resetPgliteState } from './helpers/reset-pglite.ts';
|
||||
import { embedStaleForSource } from '../src/core/embed-stale.ts';
|
||||
import { configureGateway, resetGateway } from '../src/core/ai/gateway.ts';
|
||||
import type { ChunkInput } from '../src/core/types.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
@@ -276,4 +277,49 @@ describe('embedStaleForSource', () => {
|
||||
// The stale text row actually got its embedding.
|
||||
expect(txtRow.embedded_at).not.toBeNull();
|
||||
});
|
||||
|
||||
// #1717: the backfill path must label re-embedded chunks with the model
|
||||
// that produced the vector, and preserve the existing label on chunks it
|
||||
// did not touch (before the fix, both were reset to the engine default).
|
||||
test('labels re-embedded chunks with the gateway model, preserves untouched labels (#1717)', async () => {
|
||||
configureGateway({
|
||||
embedding_model: 'openai:text-embedding-3-large',
|
||||
env: { OPENAI_API_KEY: 'sk-test-embed-stale-1717' },
|
||||
});
|
||||
try {
|
||||
await engine.putPage('notes/model-label', {
|
||||
type: 'note',
|
||||
title: 'model-label',
|
||||
compiled_truth: '# model-label\n\nseeded',
|
||||
});
|
||||
await engine.upsertChunks('notes/model-label', [
|
||||
{
|
||||
chunk_index: 0,
|
||||
chunk_text: 'already embedded elsewhere',
|
||||
chunk_source: 'compiled_truth',
|
||||
embedding: new Float32Array(1536).fill(0.01),
|
||||
model: 'voyage:voyage-3',
|
||||
token_count: 4,
|
||||
},
|
||||
{
|
||||
chunk_index: 1,
|
||||
chunk_text: 'stale chunk needing embed',
|
||||
chunk_source: 'compiled_truth',
|
||||
token_count: 5,
|
||||
embedding: undefined, // stale
|
||||
},
|
||||
]);
|
||||
|
||||
const result = await embedStaleForSource(engine, 'default', { embedFn: fakeEmbedFn });
|
||||
expect(result.embedded).toBe(1);
|
||||
|
||||
const after = await engine.getChunks('notes/model-label');
|
||||
const preserved = after.find((c) => c.chunk_index === 0)!;
|
||||
const reembedded = after.find((c) => c.chunk_index === 1)!;
|
||||
expect(reembedded.model).toBe('openai:text-embedding-3-large');
|
||||
expect(preserved.model).toBe('voyage:voyage-3');
|
||||
} finally {
|
||||
resetGateway();
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
@@ -37,6 +37,8 @@ mock.module('../src/core/embedding.ts', () => ({
|
||||
// setPageEmbeddingSignature / invalidateStaleSignatureEmbeddings resolve to
|
||||
// null via the Proxy default, so the signature value is inert here.
|
||||
currentEmbeddingSignature: () => 'test:model:1536',
|
||||
// #1717: embed paths stamp this label on (re)embedded chunks.
|
||||
resolveEmbeddingModelLabel: () => 'openai:text-embedding-3-large',
|
||||
}));
|
||||
|
||||
// Import AFTER mocking.
|
||||
@@ -803,3 +805,34 @@ describe('embedAllStale --source threading (D7)', () => {
|
||||
expect((firstCallOpts as { sourceId?: string }).sourceId).toBe('media-corpus');
|
||||
});
|
||||
});
|
||||
|
||||
// #1717: content_chunks.model must record the model that actually produced
|
||||
// each vector, not the gateway/engine default.
|
||||
describe('content_chunks.model labeling (#1717)', () => {
|
||||
test('stamps the resolved embedding model on re-embedded chunks, preserves it on untouched chunks', async () => {
|
||||
let upserted: any[] | undefined;
|
||||
// Chunk 0 is stale (no embedded_at) → gets re-embedded this pass.
|
||||
// Chunk 1 is already embedded with a DIFFERENT model → must be preserved,
|
||||
// not relabeled to the current model.
|
||||
const chunks = [
|
||||
{ chunk_index: 0, chunk_text: 'a', chunk_source: 'compiled_truth', embedded_at: null, model: 'zeroentropyai:zembed-1', token_count: 1 },
|
||||
{ chunk_index: 1, chunk_text: 'b', chunk_source: 'compiled_truth', embedded_at: '2026-01-01', embedding: new Float32Array(1536), model: 'voyage:voyage-3', token_count: 1 },
|
||||
];
|
||||
const engine = mockEngine({
|
||||
getPage: async () => ({ slug: 'notes/x', compiled_truth: 'a', timeline: '', source_id: 'default' }),
|
||||
getChunks: async () => chunks,
|
||||
upsertChunks: async (_slug: string, c: any[]) => { upserted = c; },
|
||||
setPageEmbeddingSignature: async () => null,
|
||||
});
|
||||
|
||||
await runEmbedCore(engine, { slugs: ['notes/x'] });
|
||||
|
||||
expect(upserted).toBeDefined();
|
||||
const byIdx = Object.fromEntries(upserted!.map(c => [c.chunk_index, c]));
|
||||
// Re-embedded chunk carries the model that produced its vector (was
|
||||
// mislabeled with the default before the fix).
|
||||
expect(byIdx[0].model).toBe('openai:text-embedding-3-large');
|
||||
// Untouched chunk keeps its original model — no wholesale relabel.
|
||||
expect(byIdx[1].model).toBe('voyage:voyage-3');
|
||||
});
|
||||
});
|
||||
|
||||
@@ -112,7 +112,3 @@ 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');
|
||||
});
|
||||
|
||||
@@ -73,4 +73,21 @@ describe('importFromContent embedding_signature stamping (F1)', () => {
|
||||
await importFromContent(engine, 'concepts/unstamped', '# Unstamped\n\nbody content.', { noEmbed: true });
|
||||
expect(await signatureOf('concepts/unstamped')).toBeNull();
|
||||
});
|
||||
|
||||
// #1717: content_chunks.model must record the model that produced the
|
||||
// vector (the configured gateway model), not the engine's hardcoded
|
||||
// default. The gateway here is configured to openai:text-embedding-3-large,
|
||||
// which differs from DEFAULT_EMBEDDING_MODEL — so this fails without the
|
||||
// import-path model stamping.
|
||||
test('inline embed labels content_chunks.model with the configured model (#1717)', async () => {
|
||||
await importFromContent(engine, 'concepts/labeled', '# Labeled\n\nsome body content to chunk and embed.', {});
|
||||
const rows = await engine.executeRaw<{ model: string }>(
|
||||
`SELECT cc.model FROM content_chunks cc
|
||||
JOIN pages p ON p.id = cc.page_id
|
||||
WHERE p.slug = $1 AND p.source_id = 'default'`,
|
||||
['concepts/labeled'],
|
||||
);
|
||||
expect(rows.length).toBeGreaterThan(0);
|
||||
for (const r of rows) expect(r.model).toBe('openai:text-embedding-3-large');
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,27 +0,0 @@
|
||||
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');
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user