Garry TanandClaude Opus 4.8 b38d3a071b feat(eval): relational benchmark + recall@k harness metrics ...

NamedThingBench harness gains recall@k / recall@10 (the relational headline
metric) on QuestionResult + FamilyReport, plus typed seed/linkTypes/kind on
NamedThingQuestion so the graph-relationship family is machine-checkable.

Adds the relational benchmark corpus (test/fixtures/retrieval-quality/
relational/): a small entity graph whose answers are LEXICALLY UNRECOVERABLE
— every page body is generic and never names the entity it relates to, so
only the typed edge connects query to answer. corpus.ts is the canonical
source for both the seed loader and the 38-question gold set; relational.jsonl
is generated from it (a drift test pins them equal).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-07 18:16:45 -07:00

..

brain-first-skills

v0.37.3.0 feat: skill_brain_first doctor check + auto-fix + declarative opt-out (supersedes #1206) (#1215)

2026-05-20 13:55:12 -07:00

calibration

v0.36.1.0 Hindsight calibration wave: brain learns how you tend to be wrong (#1139)

2026-05-18 19:34:44 -07:00

claw-test-scenarios

v0.40.0.0 feat: agent-voice (Mars + Venus) + copy-into-host-repo skillpack paradigm (#1128)

2026-05-22 21:54:13 -07:00

conversation-formats

v0.41.29.0 feat(conversation-parser): bold-name-no-time builtin + fix(orphans): source-scoped orphan_ratio (supersedes #1613) (#1620)

2026-05-29 07:06:08 -07:00

e5-lease-cap-ab

v0.41.0.0 feat(minions): fleet you supervise (4 field bugs + cathedral) (#1367)

2026-05-24 11:37:03 -07:00

eval-baselines

v0.40.1.0 Track D — eval infrastructure (catch retrieval regressions, prove answer-quality wins) (#1298)

2026-05-22 22:16:25 -07:00

images

v0.28.9 feat: Voyage multimodal embeddings (v0.27.1 catch-up + v0.28.6 master merge) (#706)

2026-05-07 10:03:38 -07:00

openclaw-compact-resolver/skills

v0.41.7.0 feat: compact list-format resolver + 300-skill scaling tutorial (#1407)

2026-05-25 13:58:26 -07:00

openclaw-mixed-merge

v0.41.7.0 feat: compact list-format resolver + 300-skill scaling tutorial (#1407)

2026-05-25 13:58:26 -07:00

openclaw-plugin-real

v0.32.5 feat: gbrain-context OpenClaw context engine — deterministic temporal/spatial injection (#880)

2026-05-11 21:49:57 -07:00

openclaw-reference-minimal

v0.19.0 check-resolvable: add OpenClaw skills-dir fallback + docs/tests (#326)

2026-04-23 19:34:27 -07:00

retrieval-quality

feat(eval): relational benchmark + recall@k harness metrics

2026-06-07 18:16:45 -07:00

skill-catalog/skills

v0.41.36.0 feat(mcp): publish agent skills (list_skills / get_skill) for thin clients (#1661)

2026-05-30 13:11:25 -07:00

brainstorm-eval.jsonl

v0.37.1.0 feat: brainstorm + lsd — bisociation idea generator grounded in your own brain (#1214)

2026-05-19 22:32:52 -07:00

contradictions-mini.jsonl

v0.32.6 feat: brain-consistency probe + doctor + MCP + dream-cycle wire-up (#901)

2026-05-11 22:42:54 -07:00

dream-budget-schema-v1.jsonl

v0.39.0.0 feat: brainstorm cost cathedral (P1-P7) + page_links schema fix (#1283)

2026-05-22 11:53:11 -07:00

longmemeval-mini.jsonl

v0.28.12 feat: LongMemEval benchmark harness (#606)

2026-05-07 19:49:46 -07:00

longmemeval-nightly.jsonl

v0.40.1.0 Track D — eval infrastructure (catch retrieval regressions, prove answer-quality wins) (#1298)

2026-05-22 22:16:25 -07:00

notability-eval-public.jsonl

v0.31.6 feat: extract facts during sync (real-time hot memory) (#796)

2026-05-10 12:49:14 -07:00

supervisor-runner.ts

v0.42.5.0 fix(minions): RSS watchdog opacity + pooler-reap self-heal + silent lens backlog + cycle lint DB-disconnect (#1678) (#1735)

2026-06-01 22:01:14 -07:00

watchdog-harness.ts

v0.42.18.0 fix: sync orphan-pileup watchdog (#1633) + links-lag µs stamp (#1768) (#1807)

2026-06-03 08:00:57 -07:00

whoknows-eval.jsonl

v0.33.1.0 feat: eval-gated whoknows — expertise + relationship-proximity routing (#881)

2026-05-12 14:33:29 -07:00