You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
[LLM-Wiki-v2][F1] Build real and formal wiki verification skills; close safety and schema gaps #874
Apply canonical skills/create-verification-skill/SKILL.md to generate a host-native project-local verify-llm-wiki CLI drive with Launch/Doctor/Drive/Evidence/Cleanup/Helpers and deterministic isolated scratch instances. Apply skills/create-formal-verification-skill/SKILL.md to model source immutability, page promotion/admission, and concurrent writer/linearizable update properties; pin code spans and sync SHA. Check a deliberate broken variant causes failure (negative control). Add Python tests for no overwrite, basename collision, symlink/path confinement, invalid page type/frontmatter, unindexed/deeply nested page, link resolution, conflicting concurrent ingests, torn log/index, stale digest and CLI exit codes. Repair defects only when independently verified. Formal TLC/SMT unavailable => BLOCKED, not proof. Keep functional vs formal verdicts distinct.
Evidence policy
Acceptance requires a reviewable PR and exact-head reproducible receipts. Planning is not implementation; no claimed Swarm/Arena/Interrogate model execution without actual independent work.
Partial implementation and exact-head evidence (2026-10-31)
Stacked draft PR #879 on docs(wiki): audit reference engines and propose governed migration (#871) #878 adds scripts/llm_wiki.py raw write-once/exclusive creation, link confinement and atomic index replacement, 11 new negative safety tests, 39-history bounded real-code checker + failing overwrite mutant, native Codex verify-llm-wiki and verify-llm-wiki-formal skills, optional NOT_EXECUTED TLA+ model, and offline CI wiring.
Earlier implementation head 674b2bfb354f71e8674c4cf5fa33e10dd9868262: Actions 41214985678SUCCESS. Inspected job log: original wiki tests 9 passed, new safety negatives 11 passed, bounded model tests 3 passed; standalone model reports 39 bounded actual-code traces PASS and deliberate conflicting overwrite mutant detected at two-step trace A→B. Skill scaffold check PASS. This is offline functional evidence only.
Current successor head 0029b35fad97aa19fd67c42f35bd0ff3ec6f15ce includes schema/wiki documentation changes; Actions 41215096803 was IN_PROGRESS at this inspection. Do not treat prior-head CI as exact-head proof of later changes.
Remaining OPEN: actual TLC execution/negative TLA check, independent Swarm/Arena/Interrogate and Thermos reviews, crash-safe source+human-log transaction, adversarial directory-swap confinement (beyond simple preflight), independent source/rights review, multi-host observed-live coverage. Source+log writes are not atomic and not claimed as such. This child remains OPEN until acceptance gates are met.
Activity
fix(wiki): write-once raw ingestion, confine links and atomically rep…
test(wiki): negative controls for immutable source capture and local …
verify(wiki): bounded actual-code state exploration and optional TLC …
verify(wiki): bounded actual-code state exploration and optional TLC …
verify(wiki): bounded actual-code state exploration and optional TLC …
verify(wiki): bounded actual-code state exploration and optional TLC …
skills(wiki): host-native functional and bounded formal verification …
skills(wiki): host-native functional and bounded formal verification …
skills(wiki): host-native functional and bounded formal verification …
skills(wiki): host-native functional and bounded formal verification …
skills(wiki): host-native functional and bounded formal verification …
skills(wiki): host-native functional and bounded formal verification …
skills(wiki): host-native functional and bounded formal verification …
fix(wiki-skill): conform ordered feature-map scaffold contract (#874)
ci(wiki): execute real CLI skill and bounded mutation controls offline (
docs(wiki): align project knowledge and ownership schema with real ve…
docs(wiki): align project knowledge and ownership schema with real ve…
fix(wiki): rebase tested write-once capture and verification skills o…
fix(wiki, worktree): enforce write-once capture, link confinement, an…
verify(wiki): bind formal spec negative fixtures to maintained skill …
verify(wiki): bind formal spec negative fixtures to maintained skill …
verify(wiki): bind formal spec negative fixtures to maintained skill …
verify(wiki): bind formal spec negative fixtures to maintained skill …
verify(wiki): bind formal spec negative fixtures to maintained skill …
verify(wiki): bind formal spec negative fixtures to maintained skill …
verify(wiki): bind formal spec negative fixtures to maintained skill …
verify(wiki): bind formal spec negative fixtures to maintained skill …
spec(wiki): source-pinned OpenSpec, semantic contracts, schema and wi…