Codex Work That Scales to the Task
LazyCodex now selects low-, medium-, or high-difficulty workers from the actual change size and risk instead of routing every implementation through one general executor. New installs default to GPT-5.6 Sol with a 372K context window, while exploration and deep-analysis categories use the new Luna and Terra routes. The result is cheaper handling for narrow work and stronger reasoning where a change genuinely needs it.
ULW Loops Recover and Prove the Right Revision
Interrupted ULW runs can now resume automatically through a bounded Stop hook. Evidence is isolated by attempt, tied to the commit that produced it, and checked before the final reviewer starts. Spawn guards and reviewer preflight checks prevent runaway fan-out and stop stale evidence from being relabeled as proof for a newer HEAD.
More Useful, Safer Task Output
The Senpi task TUI now shows resolved model details and contextual status, control, and output excerpts. Rows are width-bounded and terminal control sequences are sanitized, so narrow terminals and untrusted task output no longer distort the interface.
Cleaner Plugin Installs and Honest Prompt QA
Codex bundles no longer ship nested component MCP manifests with invalid relative daemon paths. Prompt and skill changes are now tested at behavioral seams—parsed values, runtime sentinels, and shipped-artifact equality—rather than fragile sentence matching or word-count tests that block legitimate prose improvements.
Minor Compatibility and Stability Release
This release carries compatibility-facing behavior changes and operational hardening. Read the summary below before upgrading or publishing.
- Rename transition updates across package detection, plugin/config compatibility, and install surfaces.
- Task and tool behavior updates, including delegate-task contract and runtime registration behavior.
- Install and publish workflow hardening, including safer release sequencing and package/install fixes.
Commit Summary
- b4673bf Merge pull request #6050 from code-yeongyu/fix/ulw-size-tier-guidance
- 9741e99 feat(omo-codex): size-drive the ulw worker-tier selection
- d6a4631 Merge pull request #6049 from code-yeongyu/fix/ulw-agent-tier-config
- cdc710a feat(omo-codex): emphasize code-mode parallel fan-out in hephaestus gpt-5.6 discovery
- 339e85b refactor(omo-codex): remove redundant lazycodex-executor agent; gate the workers
- e0734a8 fix(ultrawork): add answer-when-answerable stop rule to codex directive
- 7e26cae Merge pull request #6047 from code-yeongyu/fix/ulw-loop-evidence-commit-identity
- be7ea8f fix(ulw-loop): make the tool surface V2-native for GPT-5.6 (sol/terra)
- 9408493 Merge pull request #6048 from code-yeongyu/fix/codex-ulw-explore-first-plan-gate
- 1cc0be6 fix(ulw-loop): bind QA evidence to its capture commit to stop stale-HEAD relabeling
- 1a07908 test(ultrawork): pin explore-first scope-gated planning invariants
- 647cf1f fix(ultrawork): gather context before scope-gated planning in codex directive
- 09514c2 Merge pull request #6046 from code-yeongyu/fix/omo-codex-drop-nested-mcp-manifest
- 367d3b0 chore(package): ship git-bash-mcp package.json for vendored-MCP parity
- 661f9a3 fix(lazycodex-sync): drop nested component .mcp.json from the marketplace bundle
- 740f034 fix(codex-install): drop nested component .mcp.json from the plugin cache
- 28024d9 Merge pull request #6045 from code-yeongyu/fix/team-mode-deflake-windows-ci
- 7baf2bd test(team-mode): give concurrency cases an explicit 30s per-test timeout
- 860e01c test(team-mode): make launch-concurrency probe waits event-driven
- 1a2c5dc Merge pull request #6044 from code-yeongyu/feat/lazycodex-gate-reviewer-high
- e278bc7 Merge pull request #6041 from code-yeongyu/feat/lazycodex-default-model-gpt-5.6-sol
- b70edfc feat(lazycodex): drop gate-reviewer reasoning effort to high
- 13addbf Merge pull request #6040 from code-yeongyu/feat/lazycodex-worker-medium-qa-plan-retune
- 8d610cf test(omo-codex): pin gpt-5.6-sol default; keep v1 legacy paths covered
- 81c0d8f feat(omo-codex): default install model to gpt-5.6-sol/372k/high
- eda430f Merge pull request #6039 from code-yeongyu/fix/stop-continuation-session-suppression
- 45ac7be feat(lazycodex): retune worker-medium, qa-executor, and plan model tiers
- c611246 fix(stop-continuation): stop continuation from every /stop-continuation entry point
- 17104e1 Merge pull request #6038 from code-yeongyu/fix/worker-toml-nickname-charset
- 7124b08 test(codex-plugin): pin the codex nickname charset for bundled agent TOMLs
- 37d9b83 fix(ultrawork-agents): worker nicknames violate codex role-loader charset
- 2ce3cae Merge pull request #6036 from code-yeongyu/feat/ulw-loop-infra-hooks
- 384cb0d fix(ulw-loop): harden Stop-hook deferral and resume directive per review
- f00b581 feat(ulw-loop): register the spawn-guard PreToolUse root manifest
- bfd32af feat(ulw-loop): spawn fan-out cap and gate-reviewer artifact preflight guard
- 067f34b Merge pull request #6035 from code-yeongyu/docs/omomomo-command-roster
- ee2958b feat(ulw-loop): register the Stop resume hook on the root manifest surface
- 68ea258 feat(ulw-loop): auto-resume interrupted runs via Stop hook with two-strike cap
- 235c0dc docs: fix stale agent roster in omomomo command copies
- bbdd080 Merge pull request #6034 from code-yeongyu/docs/model-claims-audit
- 2b25d64 Merge pull request #6031 from code-yeongyu/feat/ulw-loop-gate-middle-states
- c44d199 docs: fix omomomo agent roster, landing writing label, sync pre-publish-review skill
- 0b83b6a docs(reference): sync agent and category chain tables with model-core
- 80ef1c8 docs(guide): correct stale model claims in orchestration, installation, overview, matching
- d463a2c docs: fix stale agent chains in READMEs across all languages
- a88c7f1 fix(ulw-loop): make component tests pass on win32 CI
- 87b5205 fix(ci): run ulw-loop component suite before the plugin bundling build
- 2e40dbd style(ulw-loop): sort quality-gate imports per biome
- 1433f38 chore(omo-codex): regenerate bundled installer from current source
- aaf328f docs(ulw-plan): migrate scaffold evidence templates to the attempt directory
- fe552e6 fix(ulw-loop): make attempt containment separator-agnostic and CI-gate the component suite
- 683fe57 docs(ultrawork-agents): route evidence path templates through currentAttemptDir
- b250866 feat(ulw-loop): expose currentAttemptDir in status --json and goal handoff text
- b628995 feat(ulw-loop): enforce attempt-scoped evidence directories at the final quality gate
- bccf3fa feat(ulw-loop): accept WATCH and reasoned not_applicable at the quality gate
- d9f01f5 fix(ulw-loop): stage final gate spawn after reviewer artifacts exist and bound re-review
- a9d76d8 Merge pull request #6030 from code-yeongyu/feature/lazycodex-difficulty-tier-routing
- e6c0dc6 fix(start-work): keep the corrected v2 agent_type claim authoritative in the synced skill
- 6462494 test(lazycodex): pin the extended SubagentStop verifier matcher
- 29526d7 test(lazycodex-install): pin explorer/librarian effort chain to the luna/low target
- e5f959b feat(lazycodex): enforce evidence receipts for difficulty-tier workers
- 142e503 feat(start-work): delegate implementation by difficulty tier on Codex
- ec8d5ac fix(ultrawork): restore child-liveness guidance and compress tier rows under word budget
- 2b9d084 feat(lazycodex): difficulty-tier delegation guidance in ulw-loop workflow and directive
- 89766ee fix(lazycodex-install): chain explorer/librarian reasoning defaults to luna/low for upgraders
- bacfe64 feat(lazycodex): add difficulty-tier worker agents and route explorer/librarian to luna
- d759965 Merge pull request #6029 from code-yeongyu/fix/ulw-verifier-calibration
- 4851d18 chore(lazycodex): regenerate tracked init-deep skill with backoff prose
- a9e2e12 fix(review-work): inline-blocker reject contract and wait backoff
- dd06e34 fix(ultrawork): bound the verification gate loop and delta-scope re-reviews
- 72bb086 fix(lazycodex): rebalance reviewer burden-of-proof and inline REJECT blockers
- fb74d77 Merge pull request #6027 from code-yeongyu/docs/gpt-5-6-model-label-sync
- 47809d5 fix(web): correct model labels on landing page
- 511956e docs: sync localized README ultrabrain routing with gpt-5.6-sol default
- e001a91 Merge pull request #6026 from code-yeongyu/feat/gpt-5-6-category-defaults
- 54a375c test(omo-opencode): assert unspecified-low xhigh variant in delegate default test
- 1249bdd docs: reflect gpt-5.6 terra/luna category defaults in guides and examples
- 9a6036a feat(omo-opencode): adopt gpt-5.6 terra/luna builtin category defaults
- 9d51fb6 feat(model-core): route deep to gpt-5.6-terra xhigh, unspecified-low to gpt-5.6-luna xhigh