* feat(facts): typed-claim substrate + cycle correctness fixes (v0.35.6 wave 1/3) Schema (migration v67): - Add four optional typed-claim columns to facts: claim_metric TEXT, claim_value DOUBLE PRECISION, claim_unit TEXT, claim_period TEXT - Partial index facts_typed_claim_idx ON (entity_slug, claim_metric, valid_from) WHERE claim_metric IS NOT NULL - All nullable, metadata-only on both engines Fence layer: - ParsedFact (facts-fence.ts) gains optional claimMetric/Value/Unit/Period - Parser tolerates both 10-cell (legacy) and 14-cell (widened) rows - Renderer emits 14 cells iff any row has typed data; otherwise stays 10-cell so existing fences don't widen on unrelated edits - Numeric value cell tolerates comma thousand separators (50,000 -> 50000) Extract pipeline (D-CDX-2, D-ENG-1): - src/core/facts/extract.ts (the actual Haiku call site, NOT extract-facts.ts cycle phase) extends its system prompt to emit typed fields for metric-shaped claims - extractFactsFromFenceText gains optional pageEffectiveDate. Precedence: fence-row validFrom > pageEffectiveDate > undefined (engine defaults to now) - normalizeMetricLabel: 15-entry seed map for common founder metrics (mrr, arr, runway, headcount, team_size, cac, ltv, gross_margin, burn_rate, cash, users, mau, dau, churn_rate, revenue); unknown labels lowercase + space->_ Engine extensions: - NewFact + insertFact + insertFacts in both engines accept the four typed columns (all nullable) - Cycle phase extract-facts.ts threads page.effective_date through AND batch-embeds via gateway.embed() before insertFacts (D-CDX-3 fix for cycle-inserted facts arriving with embedding=NULL) Consolidate fix (D-CDX-4 — Codex F4): - Replace MAX(row_num)+1 INSERT with semantic upsert on (page_id, claim, since_date). Re-running the full cycle on stable input produces zero new takes — fixes the pre-existing duplicate-takes bug after extract_facts wipes consolidated_at - Chronological valid_until writeback per cluster: sort by (valid_from ASC, id ASC), walk pairs, set older.valid_until = newer.valid_from Tests: - test/migrate.test.ts +6 cases for v67 shape + materialization + nullable backward compat - test/facts-fence-typed.test.ts (new, 17 cases): parser+renderer round-trip, normalization seed map coverage, valid_from precedence three-branch - test/consolidate-valid-until.test.ts (new, 4 cases): chronological writeback (R4a), same-day id tiebreaker, cycle re-run zero duplicates (R4b/R7), valid_until idempotency - test/schema-bootstrap-coverage.test.ts: add four typed-claim columns to COLUMN_EXEMPTIONS (migration co-defines the partial index, no forward reference to bootstrap) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(trajectory): find_trajectory MCP op + eval/founder CLIs (v0.35.6 wave 2/3) Engine method (D-CDX-1, D-CDX-6): - BrainEngine.findTrajectory(opts) on both Postgres and PGLite - TrajectoryOpts: scalar sourceId fast path + sourceIds federated array (mirrors v0.34.1.0 search* dual pattern) - opts.remote: when true, SQL adds AND visibility='world' so OAuth read clients see only world-visibility facts (mirrors recall's posture — closes the F7 privacy regression Codex caught in plan review) - Single SQL query, ORDER BY valid_from ASC, id ASC for deterministic output (R3 pin). Returns TrajectoryPoint[] including raw embedding so the caller can compute drift without a second round-trip Pure function library (src/core/trajectory.ts, new): - detectRegressions(points, threshold): walks consecutive (metric, value) pairs per metric; emits when newer drops >= threshold below older. 10% default, override via GBRAIN_TRAJECTORY_REGRESSION_THRESHOLD - computeDriftScore(points): 1 - mean(cosine(emb[i], emb[i-1])) over embedded points; clamped [0,1]; null when <3 embedded points (D-ENG-3 graceful degradation) - computeTrajectoryStats(points): composed shape returning both - TRAJECTORY_SCHEMA_VERSION = 1 — additive-only across releases (R5) MCP op (src/core/operations.ts): - find_trajectory: scope read, NOT localOnly. Routes through sourceScopeOpts(ctx) for federated isolation AND threads ctx.remote for visibility filtering. Strips raw Float32Array embeddings from the wire shape; converts valid_from to YYYY-MM-DD string - Registered in operations array after find_experts - FIND_TRAJECTORY_DESCRIPTION in operations-descriptions.ts CLIs: - gbrain eval trajectory <entity> [--metric M] [--since D] [--until D] [--limit N] [--json] — chronological human view with [REGRESSION] inline annotation; thin-client routing via callRemoteTool(find_trajectory). Dispatched in src/commands/eval.ts sub-subcommand block - gbrain founder scorecard <entity> [--since D] [--until D] [--json] — pure aggregation over Phase 2's substrate. Four signals: claim_accuracy (over resolved takes), consistency, growth_trajectory, red_flags. computeFounderScorecard exported for tests. Registered as top-level command in cli.ts; added to CLI_ONLY set Tests (45 cases across 5 files): - test/engine-find-trajectory.test.ts: 18 cases — chronological order, source scoping (scalar + federated), visibility filter on remote=true, metric + since/until filters, regression detection at threshold boundaries, drift score with various embedding states - test/operations-find-trajectory.test.ts: 9 cases — op registration, param validation, JSON envelope shape, R5 schema_version: 1, embedding stripped from wire, R6 visibility filter, source scoping - test/eval-trajectory.test.ts: 7 cases — arg parsing, --help, --json envelope, regression annotation, --metric filter, empty entity - test/founder-scorecard.test.ts: 9 cases — empty inputs no-NaN (G2), claim_accuracy math, consistency math, growth_trajectory math, red_flags fire for regression / narrative_drift / missed_prediction - test/eval-contradictions/no-valid-until-write.test.ts: 4 cases — R1 (probe never writes valid_until under eval-contradictions/) + R8 (only allow-listed files write valid_until anywhere in src/) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: v0.35.6.0 — CHANGELOG + VERSION + docs + migration note Bumps to v0.35.6.0 (next-minor after master's v0.35.5.1 — typed-claim substrate + trajectory + founder scorecard is a new user-facing feature surface, not a fix). - VERSION + package.json synced - CHANGELOG.md release-summary block in the wave-style voice, lead with what the user can now DO. Sections: typed metric claims in the fence, chronological metric trajectories, founder scorecard, MCP find_trajectory op, cycle re-run idempotency fix, embedding-on-insert fix, valid_from precedence fix. To-take-advantage-of block with verification + opt-in fence syntax example - CLAUDE.md Key Files entry consolidating the wave across eval-trajectory.ts + founder-scorecard.ts + trajectory.ts. Names every D-ENG / D-CDX decision and the Codex outside-voice F-numbers - skills/migrations/v0.35.6.md agent-readable migration note. Includes fence-syntax example for typed-claim rows so downstream agents start emitting them. Iron-rule contracts called out (R1 + R8 + R7 + visibility) - llms-full.txt regenerated to reflect the new CLAUDE.md entry Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: post-ship sync for v0.35.7.0 — trajectory + founder scorecard - README.md: add `gbrain eval trajectory` to EVAL section, add new TEMPORAL block covering `gbrain founder scorecard` + the GBRAIN_TRAJECTORY_REGRESSION_THRESHOLD env override; add v0.35.7 "What's new" paragraph below the v0.28.8 LongMemEval blurb - AGENTS.md: new bullet under Common tasks teaching agents to reach for `gbrain eval trajectory` / `gbrain founder scorecard` / the `find_trajectory` MCP op when asked to evaluate a founder/company over time - docs/contradictions.md: append "Temporal axis follow-on (v0.35.3.1 + v0.35.7)" subsection under See also, cross-linking the trajectory substrate and naming the auto-supersession.ts:4 invariant preserved by both the verdict enum (probe side) and consolidate's valid_until writeback (cycle side) - CLAUDE.md: fix stale (v0.35.4) tag on the trajectory entry to (v0.35.7) — version got rebumped twice during the merge wave - skills/migrations/v0.35.7.md renamed to v0.35.7.0.md for consistency with the v0.35.0.0.md / v0.14.0.md / etc naming convention - llms-full.txt regenerated to reflect the CLAUDE.md edit Coverage map (Diataxis): /eval trajectory CLI ✅ ref (README, AGENTS) ✅ how-to (CHANGELOG) ❌ tutorial /founder scorecard CLI ✅ ref (README, AGENTS) ✅ how-to (CHANGELOG) ❌ tutorial find_trajectory MCP op ✅ ref (CLAUDE.md, AGENTS, contradictions.md) typed-claim fence cols ✅ ref (skills/migrations/v0.35.7.0.md, CHANGELOG) Migration v67 ✅ ref (CLAUDE.md, CHANGELOG) No tutorial / explanation gaps worth filling in this PR — the migration note's fence-syntax example already covers the "first typed claim" walkthrough. ARCHITECTURE diagrams not drifted (the trajectory work extends existing facts/takes infrastructure; no new component boxes). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
4.4 KiB
version, date, feature_pitch
| version | date | feature_pitch |
|---|---|---|
| v0.35.7.0 | 2026-05-17 | Typed metric claims, chronological trajectory queries, and a founder scorecard CLI. The temporal axis the v0.35.3.1 contradiction probe needed in order to be useful, finally landed. |
v0.35.7.0 — Temporal trajectory + founder scorecard
What changed
- Migration v67 (
facts_typed_claim_columns) adds four optional columns tofacts:claim_metric,claim_value,claim_unit,claim_period. All nullable — existing facts persist identically. - The
## Factsfence widens from 10 to 14 columns when a row carries typed-claim data. Backward compat: fences without typed data stay at 10 cells. - New MCP op:
find_trajectory(read scope, not localOnly). Federated source-scoped, visibility-filtered for remote callers. - New CLI commands:
gbrain eval trajectory <entity>andgbrain founder scorecard <entity>. - The
extract_factscycle phase now batch-embeds facts before insert AND threadspages.effective_dateas the fallbackvalid_from. - The
consolidatecycle phase now uses semantic upsert on(page_id, claim, since_date)so re-running the full cycle on stable input produces zero duplicate takes. Also writes chronologicalvalid_untilon each cluster's older facts.
What agents need to do
Most of this is automatic on upgrade. Three things worth knowing:
1. Author typed-claim rows in ## Facts fences
When you write facts about a company or person that include metric assertions, add the four typed columns to the fence row:
| # | claim | kind | confidence | visibility | notability | valid_from | valid_until | source | context | claim_metric | claim_value | claim_unit | claim_period |
|---|-------|------|------------|------------|------------|------------|-------------|--------|---------|--------------|-------------|------------|--------------|
| 1 | MRR hit $50K (Jan 2026) | fact | 1.0 | private | high | 2026-01-15 | | OH transcript | | mrr | 50000 | USD | monthly |
| 2 | ARR target | commitment | 0.6 | private | high | 2026-01-15 | 2026-12-31 | OH transcript | predicted $1M ARR by Q4 | arr | 1000000 | USD | annual |
The claim_metric column normalizes to lowercase snake_case (mrr, arr,
team_size, runway, burn_rate, cac, ltv, mau, dau, churn_rate, revenue,
fundraise, headcount, gross_margin, users). Unknown labels lowercase +
underscore-collapse and pass through verbatim.
2. When the user asks "how has X trended"
Use gbrain eval trajectory:
gbrain eval trajectory companies/acme-example
gbrain eval trajectory companies/acme-example --metric mrr
gbrain eval trajectory companies/acme-example --since 2026-01-01 --json
Or the MCP op find_trajectory with {entity_slug, metric?, since?, until?, limit?}.
Regressions are auto-flagged at 10% drops by default. Drift score indicates narrative stability (0 = stable, 1 = every claim is unrelated; null when <3 embedded points).
3. When the user asks "is this founder consistent / reliable"
Use gbrain founder scorecard:
gbrain founder scorecard companies/acme-example --json
Returns four signals: claim_accuracy (over resolved takes),
consistency (1 minus the fraction of metric value-changes),
growth_trajectory (direction + delta per metric), red_flags
(regressions + high drift + missed predictions).
JSON schema is schema_version: 1, additive-only across releases.
Iron-rule contracts to preserve
- The contradiction probe MUST NOT write
valid_untilon facts.consolidatewrites it; the probe emits paste-ready commands instead. This invariant is pinned bytest/eval-contradictions/no-valid-until-write.test.ts(R1 + R8 grep guards). find_trajectoryMUST visibility-filter remote callers (ctx.remote === true→ SQL addsAND visibility = 'world'). Mirrorsrecall's posture.consolidate's semantic upsert MUST be keyed on(page_id, claim, since_date), NOTMAX(row_num)+1. Pinned bytest/consolidate-valid-until.test.ts(R4b/R7).
Where to look
- Cycle phase:
src/core/cycle/extract-facts.ts,src/core/cycle/phases/consolidate.ts - Engine method:
BrainEngine.findTrajectoryinsrc/core/engine.ts,src/core/postgres-engine.ts,src/core/pglite-engine.ts - Trajectory math:
src/core/trajectory.ts - MCP op:
src/core/operations.ts(search forfind_trajectory) - CLIs:
src/commands/eval-trajectory.ts,src/commands/founder-scorecard.ts - Schema:
src/core/migrate.ts(migration v67)