mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 09:52:22 +00:00
Compare commits
3
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
bcdb435d73 | ||
|
|
093d693502 | ||
|
|
9268552d70 |
@@ -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) {
|
||||
|
||||
@@ -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;
|
||||
|
||||
+101
-20
@@ -428,8 +428,13 @@ export async function runPhaseSynthesize(
|
||||
|
||||
const queue = new MinionQueue(engine);
|
||||
const childIds: number[] = [];
|
||||
/** Map child job_id → chunk metadata for D6 orchestrator-side slug rewrite. */
|
||||
const chunkInfo = new Map<number, { idx: number; hash6: string }>();
|
||||
/**
|
||||
* Map child job_id → transcript metadata. Drives D6 orchestrator-side
|
||||
* slug rewrite for chunked transcripts AND the deterministic frontmatter
|
||||
* stampDreamProvenance merges into each written page. Populated for
|
||||
* every child (single-chunk children carry chunkTotal=1).
|
||||
*/
|
||||
const childMeta = new Map<number, ChildMeta>();
|
||||
/** Skip reasons for the cycle report (D5 cap hits, D8 legacy-key skips). */
|
||||
const skipReports: Array<{ filePath: string; reason: string }> = [];
|
||||
|
||||
@@ -513,9 +518,14 @@ export async function runPhaseSynthesize(
|
||||
{ allowProtectedSubmit: true },
|
||||
);
|
||||
childIds.push(child.id);
|
||||
if (isChunked) {
|
||||
chunkInfo.set(child.id, { idx: i, hash6 });
|
||||
}
|
||||
childMeta.set(child.id, {
|
||||
idx: i,
|
||||
hash6,
|
||||
chunkTotal: chunks.length,
|
||||
transcriptSource: t.transcriptSource,
|
||||
transcriptId: stripContentVersionSuffix(t.basename),
|
||||
inferredDate: t.inferredDate,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
@@ -544,14 +554,14 @@ export async function runPhaseSynthesize(
|
||||
|
||||
// Collect slugs from put_page tool executions across the children
|
||||
// (codex finding #2: deterministic provenance, NOT pages.updated_at).
|
||||
// D6 orchestrator slug rewrite: chunkInfo drives post-hoc rewrite of
|
||||
// D6 orchestrator slug rewrite: childMeta drives post-hoc rewrite of
|
||||
// bare-hash slugs to `<hash6>-c<idx>` so chunked siblings can't collide
|
||||
// even if Sonnet drops the chunk suffix.
|
||||
// v0.32.8: refs carry source_id so reverseWriteRefs picks the correct
|
||||
// (source, slug) row. #1586: refs are stamped with the cycle's resolved
|
||||
// source (children write there via SubagentHandlerData.source_id).
|
||||
const cycleSourceId = opts.sourceId ?? 'default';
|
||||
const writtenRefs = await collectChildPutPageSlugs(engine, childIds, chunkInfo, cycleSourceId);
|
||||
const writtenRefs = await collectChildPutPageSlugs(engine, childIds, childMeta, cycleSourceId);
|
||||
|
||||
const summaryDate = opts.date ?? today();
|
||||
|
||||
@@ -559,7 +569,12 @@ export async function runPhaseSynthesize(
|
||||
// of every child-written page BEFORE reverse-rendering, so generated pages
|
||||
// are queryable (`frontmatter->>'dream_generated'`) and a later put_page
|
||||
// write-through (which re-renders from the DB row) can't erase the stamp.
|
||||
await stampDreamProvenance(engine, writtenRefs, summaryDate);
|
||||
// #2285: the stamp also carries the orchestrator-owned deterministic
|
||||
// frontmatter (transcript_id, transcript_source, transcript_hash, date,
|
||||
// chunk) derived from childMeta — subagent drift on those fields can't
|
||||
// leak, and reverseWriteRefs below re-reads the row so the same fields
|
||||
// land in the on-disk markdown.
|
||||
await stampDreamProvenance(engine, writtenRefs, summaryDate, childMeta);
|
||||
|
||||
// Dual-write: reverse-render each DB row → markdown file.
|
||||
const reverseWriteCount = await reverseWriteRefs(engine, opts.brainDir, writtenRefs, cycleSourceId);
|
||||
@@ -1095,15 +1110,17 @@ function sanitizeForSlug(s: string): string {
|
||||
* fake"): we no longer need detection because the rewrite enforces
|
||||
* uniqueness at slug-write time.
|
||||
*
|
||||
* `chunkInfo` maps child job_id → { chunk_index, hash6 }. Single-chunk
|
||||
* children are absent from the map and pass through unchanged.
|
||||
* `childMeta` maps child job_id → per-child transcript metadata. Chunked
|
||||
* children (chunkTotal > 1) get the slug rewrite; single-chunk children
|
||||
* pass through unchanged. Each returned ref carries the job_id that wrote
|
||||
* it so stampDreamProvenance can pair the slug back to its childMeta entry.
|
||||
*/
|
||||
async function collectChildPutPageSlugs(
|
||||
engine: BrainEngine,
|
||||
childIds: number[],
|
||||
chunkInfo: Map<number, { idx: number; hash6: string }>,
|
||||
childMeta: Map<number, ChildMeta>,
|
||||
sourceId = 'default',
|
||||
): Promise<Array<{ slug: string; source_id: string }>> {
|
||||
): Promise<Array<{ slug: string; source_id: string; jobId: number }>> {
|
||||
if (childIds.length === 0) return [];
|
||||
// Raw fetch — NO SELECT DISTINCT. Preserves per-child slug duplicates so
|
||||
// the orchestrator sees what each child wrote. COALESCE handles both
|
||||
@@ -1122,16 +1139,73 @@ async function collectChildPutPageSlugs(
|
||||
FROM subagent_tool_executions
|
||||
WHERE job_id = ANY($1::int[])
|
||||
AND tool_name = 'brain_put_page'
|
||||
AND status = 'complete'`,
|
||||
AND status = 'complete'
|
||||
ORDER BY id`,
|
||||
[childIds],
|
||||
);
|
||||
const rewritten = new Set<string>();
|
||||
const rewritten = new Map<string, number>();
|
||||
for (const r of rows) {
|
||||
if (typeof r.slug !== 'string' || r.slug.length === 0) continue;
|
||||
const ci = chunkInfo.get(r.job_id);
|
||||
rewritten.add(ci ? rewriteChunkedSlug(r.slug, ci.hash6, ci.idx) : r.slug);
|
||||
const meta = childMeta.get(r.job_id);
|
||||
const finalSlug = meta && meta.chunkTotal > 1
|
||||
? rewriteChunkedSlug(r.slug, meta.hash6, meta.idx)
|
||||
: r.slug;
|
||||
// Last writer wins, in execution-row order (ORDER BY id): if two children
|
||||
// collide on a final slug, the pages row holds the LAST put_page write, so
|
||||
// the stamp must attribute that child's transcript — not an arbitrary one.
|
||||
rewritten.set(finalSlug, r.job_id);
|
||||
}
|
||||
return Array.from(rewritten).sort().map(slug => ({ slug, source_id: sourceId }));
|
||||
return [...rewritten.entries()]
|
||||
.sort(([a], [b]) => a.localeCompare(b))
|
||||
.map(([slug, jobId]) => ({ slug, source_id: sourceId, jobId }));
|
||||
}
|
||||
|
||||
/**
|
||||
* Per-child orchestrator state. Drives D6 chunked-slug rewrite (idx + hash6)
|
||||
* AND the deterministic frontmatter stampDreamProvenance merges into each
|
||||
* written page. Populated for every child, not just chunked ones.
|
||||
*/
|
||||
interface ChildMeta {
|
||||
idx: number;
|
||||
hash6: string;
|
||||
chunkTotal: number;
|
||||
transcriptSource: string | null;
|
||||
transcriptId: string;
|
||||
inferredDate: string | null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Strip the content-version suffix that claude-code-archive appends when a
|
||||
* conversation is edited (`<uuid>--<contentHash>.md`). The session UUID is
|
||||
* the stable transcript identifier; the suffix changes with content. Used to
|
||||
* populate `transcript_id` so edits of the same session collapse to one id.
|
||||
*/
|
||||
function stripContentVersionSuffix(basename: string): string {
|
||||
return basename.replace(/--[a-f0-9]+$/i, '');
|
||||
}
|
||||
|
||||
/**
|
||||
* Deterministic frontmatter for one synthesized page (#2285). Every field
|
||||
* here is owned by the orchestrator — the subagent's value for any of these
|
||||
* is overwritten. The subagent retains authority over type / title / tags /
|
||||
* body. `date` feeds the effective-date precedence chain
|
||||
* (src/core/effective-date.ts) so re-imports keep the conversation date even
|
||||
* when sync tools re-stamp file mtimes.
|
||||
*/
|
||||
function buildDeterministicFrontmatter(
|
||||
meta: ChildMeta,
|
||||
cycleDate: string,
|
||||
): Record<string, unknown> {
|
||||
const overrides: Record<string, unknown> = {
|
||||
dream_generated: true,
|
||||
dream_cycle_date: cycleDate,
|
||||
transcript_id: meta.transcriptId,
|
||||
transcript_hash: meta.hash6,
|
||||
};
|
||||
if (meta.transcriptSource) overrides.transcript_source = meta.transcriptSource;
|
||||
if (meta.chunkTotal > 1) overrides.chunk = `${meta.idx + 1}/${meta.chunkTotal}`;
|
||||
if (meta.inferredDate) overrides.date = meta.inferredDate;
|
||||
return overrides;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -1177,12 +1251,19 @@ async function hasLegacySingleChunkCompletion(
|
||||
*/
|
||||
async function stampDreamProvenance(
|
||||
engine: BrainEngine,
|
||||
refs: Array<{ slug: string; source_id: string }>,
|
||||
refs: Array<{ slug: string; source_id: string; jobId?: number }>,
|
||||
cycleDate: string,
|
||||
childMeta?: Map<number, ChildMeta>,
|
||||
): Promise<void> {
|
||||
if (refs.length === 0) return;
|
||||
const { executeRawJsonb } = await import('../sql-query.ts');
|
||||
for (const { slug, source_id } of refs) {
|
||||
for (const { slug, source_id, jobId } of refs) {
|
||||
// #2285: when the ref pairs back to a child, the stamp also carries the
|
||||
// orchestrator-owned deterministic frontmatter for that transcript.
|
||||
const meta = jobId !== undefined ? childMeta?.get(jobId) : undefined;
|
||||
const stamp = meta
|
||||
? buildDeterministicFrontmatter(meta, cycleDate)
|
||||
: { dream_generated: true, dream_cycle_date: cycleDate };
|
||||
try {
|
||||
await executeRawJsonb(
|
||||
engine,
|
||||
@@ -1190,7 +1271,7 @@ async function stampDreamProvenance(
|
||||
SET frontmatter = COALESCE(frontmatter, '{}'::jsonb) || $3::jsonb
|
||||
WHERE slug = $1 AND source_id = $2`,
|
||||
[slug, source_id],
|
||||
[{ dream_generated: true, dream_cycle_date: cycleDate }],
|
||||
[stamp],
|
||||
);
|
||||
} catch (e) {
|
||||
const msg = e instanceof Error ? e.message : String(e);
|
||||
|
||||
@@ -10,7 +10,7 @@
|
||||
*/
|
||||
|
||||
import { readFileSync, readdirSync, statSync } from 'node:fs';
|
||||
import { join, basename } from 'node:path';
|
||||
import { join, basename, dirname } from 'node:path';
|
||||
import { createHash } from 'node:crypto';
|
||||
import { pruneDir } from '../sync.ts';
|
||||
|
||||
@@ -23,8 +23,22 @@ export interface DiscoveredTranscript {
|
||||
content: string;
|
||||
/** Filename basename without extension; used as a topic-slug seed. */
|
||||
basename: string;
|
||||
/** Inferred date if the basename matches `YYYY-MM-DD...` (or null). */
|
||||
/**
|
||||
* Inferred conversation date (YYYY-MM-DD) or null. Precedence: the
|
||||
* `| First message | <ISO> |` row in the transcript's `## Metadata`
|
||||
* table (stable across mtime-restamping re-syncs) wins; a leading
|
||||
* `YYYY-MM-DD` in the basename is the fallback.
|
||||
*/
|
||||
inferredDate: string | null;
|
||||
/**
|
||||
* Transcript source archive name, derived from the path's grandparent
|
||||
* directory (the immediate parent of the date directory). For the
|
||||
* canonical layout `<corpus>/<source>/<date>/<id>.md` this yields the
|
||||
* source-name segment — e.g. `claude-code` for the claude-code-archive
|
||||
* output, `meetings` for meeting recordings. Null when the file does
|
||||
* not live under a `<source>/<date>/` pair (ad-hoc inputs).
|
||||
*/
|
||||
transcriptSource: string | null;
|
||||
}
|
||||
|
||||
export interface DiscoverOpts {
|
||||
@@ -161,6 +175,36 @@ function matchesAnyExclude(text: string, patterns: RegExp[]): boolean {
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* Content-based conversation date: the `| First message | <ISO timestamp> |`
|
||||
* row claude-code-archive writes into the transcript's `## Metadata` table.
|
||||
* Stable across rsync/Dropbox/Syncthing/B2 re-syncs that re-stamp mtime,
|
||||
* unlike anything derived from file metadata. Returns YYYY-MM-DD or null.
|
||||
*/
|
||||
const FIRST_MESSAGE_RE = /^\|\s*First message\s*\|\s*(\d{4}-\d{2}-\d{2})/im;
|
||||
|
||||
export function inferContentDate(content: string): string | null {
|
||||
const m = FIRST_MESSAGE_RE.exec(content);
|
||||
return m ? m[1] : null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Derive the archive source name from a transcript path. Returns the basename
|
||||
* of the directory two levels above the file when the immediate parent is a
|
||||
* date directory and the grandparent looks like a source-name slug (lowercase
|
||||
* alphanumeric segments separated by hyphens); otherwise null. This pins the
|
||||
* canonical claude-code-archive layout `<corpus>/<source>/<date>/<id>.md`
|
||||
* without claiming a source for ad-hoc inputs that don't match.
|
||||
*/
|
||||
export function deriveTranscriptSource(filePath: string): string | null {
|
||||
const parentName = basename(dirname(filePath));
|
||||
if (!/^\d{4}-\d{2}-\d{2}/.test(parentName)) return null;
|
||||
const grandparentName = basename(dirname(dirname(filePath)));
|
||||
if (!grandparentName) return null;
|
||||
if (!/^[a-z0-9]+(-[a-z0-9]+)*$/.test(grandparentName)) return null;
|
||||
return grandparentName;
|
||||
}
|
||||
|
||||
function listTextFiles(dir: string): string[] {
|
||||
// Recursive walk with descent-time pruning (closes codex C12/C13 spec gap).
|
||||
// Accepts BOTH .txt and .md per transcript-discovery's domain rules — does
|
||||
@@ -225,8 +269,11 @@ export function discoverTranscripts(opts: DiscoverOpts): DiscoveredTranscript[]
|
||||
const ext = filePath.endsWith('.md') ? '.md' : '.txt';
|
||||
const baseName = basename(filePath, ext);
|
||||
const dateMatch = DATE_RE.exec(baseName);
|
||||
const inferredDate = dateMatch ? dateMatch[1] : null;
|
||||
if (!isInDateRange(inferredDate, opts)) continue;
|
||||
const filenameDate = dateMatch ? dateMatch[1] : null;
|
||||
// Fast path: date-named files outside the window skip before the read.
|
||||
// ponytail: a date-named file whose content date differs is filtered on
|
||||
// its filename date — acceptable; archive layouts use UUID basenames.
|
||||
if (filenameDate && !isInDateRange(filenameDate, opts)) continue;
|
||||
|
||||
let content: string;
|
||||
try {
|
||||
@@ -241,12 +288,17 @@ export function discoverTranscripts(opts: DiscoverOpts): DiscoveredTranscript[]
|
||||
}
|
||||
if (matchesAnyExclude(content, excludeRes)) continue;
|
||||
|
||||
// Content-metadata date wins (survives mtime restamps); filename next.
|
||||
const inferredDate = inferContentDate(content) ?? filenameDate;
|
||||
if (!isInDateRange(inferredDate, opts)) continue;
|
||||
|
||||
results.push({
|
||||
filePath,
|
||||
contentHash: hashContent(content),
|
||||
content,
|
||||
basename: baseName,
|
||||
inferredDate,
|
||||
transcriptSource: deriveTranscriptSource(filePath),
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -290,6 +342,7 @@ export function readSingleTranscript(
|
||||
contentHash: hashContent(content),
|
||||
content,
|
||||
basename: baseName,
|
||||
inferredDate: dateMatch ? dateMatch[1] : null,
|
||||
inferredDate: inferContentDate(content) ?? (dateMatch ? dateMatch[1] : null),
|
||||
transcriptSource: deriveTranscriptSource(filePath),
|
||||
};
|
||||
}
|
||||
|
||||
@@ -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');
|
||||
});
|
||||
});
|
||||
|
||||
@@ -26,6 +26,7 @@ const transcript: DiscoveredTranscript = {
|
||||
content: 'User: hello world',
|
||||
contentHash: 'abcdef0123456789',
|
||||
inferredDate: '2026-07-17',
|
||||
transcriptSource: null,
|
||||
} as DiscoveredTranscript;
|
||||
|
||||
describe('#2415: buildSynthesisPrompt output root', () => {
|
||||
|
||||
@@ -152,3 +152,94 @@ describe('#2569: stampDreamProvenance persists the marker into DB frontmatter',
|
||||
await stampDreamProvenance(engine as any, refs, '2026-07-17'); // idempotent
|
||||
});
|
||||
});
|
||||
|
||||
describe('#2285: orchestrator-owned deterministic transcript frontmatter', () => {
|
||||
const meta = {
|
||||
idx: 1,
|
||||
hash6: 'abc123',
|
||||
chunkTotal: 3,
|
||||
transcriptSource: 'claude-code',
|
||||
transcriptId: 'session-uuid',
|
||||
inferredDate: '2026-05-15',
|
||||
};
|
||||
|
||||
test('collectChildPutPageSlugs pairs each ref back to the writing job', async () => {
|
||||
const refs = await collectChildPutPageSlugs(
|
||||
engine as any, [1001], new Map([[1001, { ...meta, chunkTotal: 1 }]]), 'mybrain',
|
||||
);
|
||||
expect(refs.length).toBeGreaterThan(0);
|
||||
for (const r of refs) {
|
||||
expect(r.jobId).toBe(1001);
|
||||
expect(r.source_id).toBe('mybrain'); // #1586: cycle source, never hardcoded 'default'
|
||||
}
|
||||
});
|
||||
|
||||
test('slug collision across children attributes the LAST writer (matches surviving putPage)', async () => {
|
||||
const db = (engine as any).db;
|
||||
// Jobs 1001 then 1002 write the same slug; the pages row would hold
|
||||
// 1002's content (last put_page wins), so the ref must carry jobId 1002.
|
||||
await db.query(
|
||||
`INSERT INTO subagent_tool_executions (job_id, message_idx, tool_use_id, tool_name, status, input)
|
||||
VALUES (1001, 9, 'tool_dup_a', 'brain_put_page', 'complete', $1::jsonb)`,
|
||||
[JSON.stringify({ slug: 'wiki/agents/test/collision', body: 'first' })],
|
||||
);
|
||||
await db.query(
|
||||
`INSERT INTO subagent_tool_executions (job_id, message_idx, tool_use_id, tool_name, status, input)
|
||||
VALUES (1002, 9, 'tool_dup_b', 'brain_put_page', 'complete', $1::jsonb)`,
|
||||
[JSON.stringify({ slug: 'wiki/agents/test/collision', body: 'second' })],
|
||||
);
|
||||
const refs = await collectChildPutPageSlugs(engine as any, [1001, 1002], new Map());
|
||||
const hit = refs.find((r: { slug: string }) => r.slug === 'wiki/agents/test/collision');
|
||||
expect(hit?.jobId).toBe(1002);
|
||||
});
|
||||
|
||||
test('stampDreamProvenance merges the transcript metadata into DB frontmatter', async () => {
|
||||
const slug = 'wiki/originals/ideas/2026-07-17-transcript-meta-abc123';
|
||||
await engine.putPage(slug, {
|
||||
type: 'note',
|
||||
title: 'Meta stamp',
|
||||
compiled_truth: 'body',
|
||||
timeline: '',
|
||||
frontmatter: { keep_me: 'yes', transcript_id: 'subagent-drift' },
|
||||
});
|
||||
await stampDreamProvenance(
|
||||
engine as any,
|
||||
[{ slug, source_id: 'default', jobId: 42 }],
|
||||
'2026-07-17',
|
||||
new Map([[42, meta]]),
|
||||
);
|
||||
const rows = await engine.executeRaw<{ fm: Record<string, unknown> }>(
|
||||
`SELECT frontmatter AS fm FROM pages WHERE slug = $1`, [slug],
|
||||
);
|
||||
const fm = rows[0].fm as Record<string, unknown>;
|
||||
expect(fm.dream_generated).toBe(true);
|
||||
expect(fm.dream_cycle_date).toBe('2026-07-17');
|
||||
expect(fm.transcript_id).toBe('session-uuid'); // orchestrator wins over subagent drift
|
||||
expect(fm.transcript_hash).toBe('abc123');
|
||||
expect(fm.transcript_source).toBe('claude-code');
|
||||
expect(fm.chunk).toBe('2/3');
|
||||
expect(fm.date).toBe('2026-05-15');
|
||||
expect(fm.keep_me).toBe('yes'); // subagent-owned keys survive
|
||||
});
|
||||
|
||||
test('single-chunk children with no inferredDate stamp only the applicable fields', async () => {
|
||||
const slug = 'wiki/originals/ideas/2026-07-17-minimal-meta-abc123';
|
||||
await engine.putPage(slug, {
|
||||
type: 'note', title: 'Minimal', compiled_truth: 'b', timeline: '', frontmatter: {},
|
||||
});
|
||||
await stampDreamProvenance(
|
||||
engine as any,
|
||||
[{ slug, source_id: 'default', jobId: 43 }],
|
||||
'2026-07-17',
|
||||
new Map([[43, { ...meta, chunkTotal: 1, transcriptSource: null, inferredDate: null }]]),
|
||||
);
|
||||
const rows = await engine.executeRaw<{ fm: Record<string, unknown> }>(
|
||||
`SELECT frontmatter AS fm FROM pages WHERE slug = $1`, [slug],
|
||||
);
|
||||
const fm = rows[0].fm as Record<string, unknown>;
|
||||
expect(fm.transcript_id).toBe('session-uuid');
|
||||
expect(fm.chunk).toBeUndefined();
|
||||
expect(fm.transcript_source).toBeUndefined();
|
||||
expect(fm.date).toBeUndefined();
|
||||
});
|
||||
});
|
||||
|
||||
@@ -302,6 +302,7 @@ describe('judgeSignificance', () => {
|
||||
content: 'A short conversation about something interesting.',
|
||||
basename: 'x',
|
||||
inferredDate: null,
|
||||
transcriptSource: null,
|
||||
};
|
||||
}
|
||||
|
||||
@@ -415,6 +416,7 @@ describe('judgeSignificance — UTF-16 safety (v0.41.13)', () => {
|
||||
content,
|
||||
basename: 'long',
|
||||
inferredDate: null,
|
||||
transcriptSource: null,
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
@@ -45,6 +45,7 @@ const FIXTURE_TRANSCRIPT: DiscoveredTranscript = {
|
||||
content: 'Synthetic transcript content for gateway-adapter parity tests.',
|
||||
contentHash: 'sha-fixture-1',
|
||||
inferredDate: '2026-05-24',
|
||||
transcriptSource: null,
|
||||
};
|
||||
|
||||
describe('makeJudgeClient — construction-time provider probe', () => {
|
||||
|
||||
@@ -0,0 +1,109 @@
|
||||
/**
|
||||
* #2285 — transcript metadata discovery.
|
||||
*
|
||||
* Pins the two discovery-side additions:
|
||||
* 1. `transcriptSource` — derived from the `<source>/<date>/<file>` path
|
||||
* layout; null for ad-hoc inputs that don't match.
|
||||
* 2. Content-based date inference — the `| First message | <ISO> |` row in
|
||||
* the transcript's `## Metadata` table wins over the filename-regex
|
||||
* date (stable across mtime-restamping re-syncs); filename is the
|
||||
* fallback.
|
||||
*
|
||||
* Pure filesystem; no engine, no LLM.
|
||||
*/
|
||||
|
||||
import { describe, test, expect, beforeEach, afterEach } from 'bun:test';
|
||||
import { mkdtempSync, rmSync, writeFileSync, mkdirSync } from 'node:fs';
|
||||
import { tmpdir } from 'node:os';
|
||||
import { join, dirname } from 'node:path';
|
||||
import {
|
||||
discoverTranscripts,
|
||||
readSingleTranscript,
|
||||
deriveTranscriptSource,
|
||||
inferContentDate,
|
||||
} from '../../src/core/cycle/transcript-discovery.ts';
|
||||
|
||||
let tmpDir: string;
|
||||
|
||||
beforeEach(() => {
|
||||
tmpDir = mkdtempSync(join(tmpdir(), 'gbrain-transcript-meta-'));
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
rmSync(tmpDir, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
function write(relPath: string, body: string): string {
|
||||
const full = join(tmpDir, relPath);
|
||||
mkdirSync(dirname(full), { recursive: true });
|
||||
writeFileSync(full, body);
|
||||
return full;
|
||||
}
|
||||
|
||||
const FILLER = 'User: hello world. '.repeat(200);
|
||||
const METADATA_BLOCK =
|
||||
'## Metadata\n\n| Key | Value |\n| --- | --- |\n| First message | 2026-05-15T03:51:11.584Z |\n\n';
|
||||
|
||||
describe('deriveTranscriptSource', () => {
|
||||
test('extracts the source slug from <source>/<date>/<file> layout', () => {
|
||||
expect(deriveTranscriptSource('/corpus/claude-code/2026-06-12/abc.md')).toBe('claude-code');
|
||||
expect(deriveTranscriptSource('/corpus/voice-notes/2026-06-12/xyz.md')).toBe('voice-notes');
|
||||
});
|
||||
|
||||
test('null when the parent dir is not a date dir or grandparent is not a slug', () => {
|
||||
expect(deriveTranscriptSource('/corpus/flat-file.md')).toBeNull();
|
||||
expect(deriveTranscriptSource('/corpus/claude-code/not-a-date/abc.md')).toBeNull();
|
||||
expect(deriveTranscriptSource('/corpus/Not A Slug/2026-06-12/abc.md')).toBeNull();
|
||||
});
|
||||
});
|
||||
|
||||
describe('inferContentDate', () => {
|
||||
test('parses the | First message | row', () => {
|
||||
expect(inferContentDate(METADATA_BLOCK)).toBe('2026-05-15');
|
||||
});
|
||||
test('null when absent', () => {
|
||||
expect(inferContentDate(FILLER)).toBeNull();
|
||||
});
|
||||
});
|
||||
|
||||
describe('discoverTranscripts — transcriptSource + date cascade', () => {
|
||||
test('populates transcriptSource per file; null for flat files', () => {
|
||||
write('claude-code/2026-06-12/aaaa.md', FILLER);
|
||||
write('2026-06-12-flat.md', FILLER);
|
||||
const out = discoverTranscripts({ corpusDir: tmpDir, minChars: 100 });
|
||||
const byBase = new Map(out.map(t => [t.basename, t.transcriptSource]));
|
||||
expect(byBase.get('aaaa')).toBe('claude-code');
|
||||
expect(byBase.get('2026-06-12-flat')).toBeNull();
|
||||
});
|
||||
|
||||
test('content First-message date wins over the filename date', () => {
|
||||
write('2026-01-01-named.md', METADATA_BLOCK + FILLER);
|
||||
const out = discoverTranscripts({ corpusDir: tmpDir, minChars: 100 });
|
||||
expect(out).toHaveLength(1);
|
||||
expect(out[0].inferredDate).toBe('2026-05-15');
|
||||
});
|
||||
|
||||
test('filename date remains the fallback when content has no metadata row', () => {
|
||||
write('2026-01-01-named.md', FILLER);
|
||||
const out = discoverTranscripts({ corpusDir: tmpDir, minChars: 100 });
|
||||
expect(out[0].inferredDate).toBe('2026-01-01');
|
||||
});
|
||||
|
||||
test('date filter matches on the content date for UUID-named transcripts', () => {
|
||||
write('claude-code/2026-05-15/uuid-basename.md', METADATA_BLOCK + FILLER);
|
||||
const hit = discoverTranscripts({ corpusDir: tmpDir, minChars: 100, date: '2026-05-15' });
|
||||
expect(hit).toHaveLength(1);
|
||||
const miss = discoverTranscripts({ corpusDir: tmpDir, minChars: 100, date: '2026-05-16' });
|
||||
expect(miss).toHaveLength(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe('readSingleTranscript — same metadata surface', () => {
|
||||
test('carries transcriptSource and prefers the content date', () => {
|
||||
const p = write('claude-code/2026-05-15/2026-01-01-single.md', METADATA_BLOCK + FILLER);
|
||||
const t = readSingleTranscript(p, { minChars: 100 });
|
||||
expect(t).not.toBeNull();
|
||||
expect(t!.transcriptSource).toBe('claude-code');
|
||||
expect(t!.inferredDate).toBe('2026-05-15');
|
||||
});
|
||||
});
|
||||
@@ -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));
|
||||
|
||||
@@ -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');
|
||||
});
|
||||
|
||||
@@ -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');
|
||||
});
|
||||
});
|
||||
@@ -216,17 +216,21 @@ describe('progress reporter', () => {
|
||||
});
|
||||
|
||||
test('only one process-level signal handler installed across many reporters', () => {
|
||||
// Baseline: one handler already installed by prior tests in this file.
|
||||
// Baseline: one handler already installed by prior tests in this file, and
|
||||
// possibly live reporters from OTHER test files sharing this bun process
|
||||
// (shard composition is not this test's invariant — assert the delta, not
|
||||
// an absolute zero, or shard reshuffles make this fail spuriously).
|
||||
const installedBefore = __signalHandlerInstalledForTest();
|
||||
const liveBefore = __liveReporterCountForTest();
|
||||
const { stream } = sink(false);
|
||||
for (let i = 0; i < 50; i++) {
|
||||
const p = createProgress({ mode: 'json', stream, minIntervalMs: 0, minItems: 1 });
|
||||
p.start(`phase_${i}`, 1);
|
||||
p.finish();
|
||||
}
|
||||
// After 50 reporter lifecycles, still exactly one handler and zero leaked live entries.
|
||||
// After 50 reporter lifecycles, still exactly one handler and zero NET leaked live entries.
|
||||
expect(__signalHandlerInstalledForTest()).toBe(installedBefore || true);
|
||||
expect(__liveReporterCountForTest()).toBe(0);
|
||||
expect(__liveReporterCountForTest()).toBe(liveBefore);
|
||||
});
|
||||
|
||||
test('startHeartbeat() fires heartbeats and stop() clears', async () => {
|
||||
|
||||
Reference in New Issue
Block a user