ouroboros/docs
Anton Razzhigaev 1fcb1d32c3 feat(v6.74.4): workspace-tree freeze directives (mitigation) + truthful ProgramBench submission contract
Root cause (PB cmatsuoka__figlet smoke): the agent committed a compiling state, then broke the tree with one last uncommitted edit as the acceptance improvement loop hit its pass cap; the harness ships the LIVE tree, so the verified commit protected nothing — all salvage machinery guards the answer TEXT only. Prompt-only fix (P5) over existing channels (P7): the acceptance rails line marks the last admitted improvement pass (passes_done+1 >= cap, cap>0) as FINAL and, for workspace deliveries (canonical is_workspace_mode() with an attribute fallback), EVERY workspace improvement capsule carries the tree directive — a deadline or cost rail can end the loop between capsules (triad r1) — keeping the tree at a VERIFIED state (rebuild, verify, and commit if the task calls for a commit; revert unverified edits); the 10% deadline flush AND the cost wrap-up note gain one shared commit-NEUTRAL tree sentence (acting self_worktree subagents cannot commit; a moved HEAD fails patch capture closed), byte-identical for non-workspace tasks; the ProgramBench instruction now states the exporter's true submission contract (SOURCE tarball from the CURRENT tree state; .git, root binaries, .ouroboros/ and named build/cache noise excluded at any depth; run ./compile.sh one final time), replacing the false fresh-checkout framing. Tests pin the pacing/rails seam, the workspace gating on both axes, byte-identical non-workspace texts, the real tarball contract, and the instruction truth phrases. P9 carriers bumped to 6.74.4; changelog row added. Disclosed residual (this is a MITIGATION of the incident class, not a closure): a forced tool-less exit — deadline grace or budget stop crossed inside one long round with no pacing note or capsule in the terminal stretch — can still ship an unverified last edit; the structural verification-freshness seam is a filed follow-up pending an owner decision (triad r1-r3, codex full-access review concur).
2026-07-22 00:37:27 +00:00
..
ARCHITECTURE.md feat(v6.74.4): workspace-tree freeze directives (mitigation) + truthful ProgramBench submission contract 2026-07-22 00:37:27 +00:00
CHECKLISTS.md feat(v6.74.0): acceptance review becomes a reviewer-authored terminating dialogue 2026-07-21 19:57:55 +00:00
CREATING_SKILLS.md feat(v6.71.0): UI polish — a shared rich-content contract, one composer dock, calm charts, and whole-row disclosures 2026-07-17 11:49:01 +00:00
DEPLOYMENT.md v5.8.3-rc.2: centralize state helpers 2026-05-08 02:12:09 +03:00
DEVELOPMENT.md ci(skills): skill_smoke Tier 6 — production review→grant→enable flow on a cheap reviewer slot (#72) 2026-07-22 01:11:54 +03:00