github code-yeongyu/oh-my-openagent v4.17.1

3 hours ago

Safer Durable Task Recovery

Interrupted process-backed tasks now resume only from trusted current runtime state. Team members retain their scoped messaging runtime after recovery, corrupt team state fails closed, and independent team waits cannot consume one another’s messages.

Bounded, Observable Task Fan-Out

Batch task launches are capped before work is queued. A failed child start is reported per item instead of hiding already-started work, and the Senpi QA gate now requires real child completion and output.

Release and Routing Integrity

Publication is now pinned to the exact prepared source commit across npm, platform binaries, and LazyCodex, so provenance and payloads agree. Explicit GPT-5.6 Sol overrides also retain their intended reasoning level across gateway model IDs.


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.
  • Install and publish workflow hardening, including safer release sequencing and package/install fixes.

Commit Summary

  • ed0241d Merge pull request #6080 from code-yeongyu/release/v4.17.1-source-state
  • 616d30b Merge pull request #6079 from code-yeongyu/fix/publish-skill-fastpath
  • 9306641 Merge remote-tracking branch 'origin/dev' into fix/publish-skill-fastpath
  • e52cd8f test(ci): cover provenance dispatch summary
  • 298b743 fix(publish): make /publish ship-only, stop auto-triggering pre-publish review
  • 017d70c fix(release): pin publication provenance to source
  • c1a741d fix(codex): align model and team spawn contracts
  • 2331213 Merge pull request #6068 from code-yeongyu/code-yeongyu/cleanup-codex-toml-parser
  • 848ffce Merge origin/dev into code-yeongyu/cleanup-codex-toml-parser
  • 82864f8 Merge pull request #6070 from code-yeongyu/fix/visual-qa-tag-emission
  • 12e2637 Merge origin/dev into code-yeongyu/cleanup-codex-toml-parser
  • e47aa9b fix(skills): emit [product]/[evidence] tag reviewers and unify backoff dashes
  • c660246 Merge pull request #6069 from code-yeongyu/fix/qa-loop-contradictions
  • af27b97 fix(skills): resolve QA-loop contradictions and evidence-vs-product churn
  • 5cfa606 Merge remote-tracking branch 'origin/dev' into code-yeongyu/cleanup-codex-toml-parser
  • 734b1b4 refactor(omo-codex): reuse TOML string parser
  • 6e4c826 Merge pull request #6065 from code-yeongyu/code-yeongyu/cleanup-shared-skill-helpers
  • 955214b Merge remote-tracking branch 'origin/dev' into code-yeongyu/cleanup-shared-skill-helpers
  • e1e09ae feat(team-core): lead unread recipient + leadSessionId + consumed-ledger + consumer lease
  • 58000e2 Merge pull request #6064 from code-yeongyu/fix/ulw-loop-test-timeouts
  • 4ccba96 fix: increase bun:test timeout for load-sensitive async tests in ulw-loop
  • 5071a7c Merge pull request #6063 from code-yeongyu/fix/release-4-17-1-blockers
  • 20887c5 Merge pull request #6057 from code-yeongyu/code-yeongyu/cleanup-root-contract-tests
  • fbb5616 docs(skills): align review and Hephaestus guidance
  • d66fe09 fix(release): build from prepared installer version
  • 7c55a25 fix(skills): preserve full evidenced planning scope
  • 8bbabd6 fix(ulw-loop): route planning by uncertainty
  • e38bc3f fix(teammode): gate fallback on visible capabilities
  • b5040f9 Merge remote-tracking branch 'origin/dev' into code-yeongyu/cleanup-shared-skill-helpers
  • d8a71f0 refactor(skills): reuse path resolver
  • 99f1246 refactor(skills-loader): reuse initiator marker
  • e564bd4 refactor(utils): own skill path resolution
  • efc9928 Merge origin/dev into code-yeongyu/cleanup-root-contract-tests
  • f7eb7dd Merge pull request #6060 from code-yeongyu/fix/plan-prompts-scope-narrowing
  • 19aabe5 fix(skills): make full-request scope the ulw-plan default
  • d0e2e08 fix(agents): remove scope-narrowing MVP language from metis prompts
  • 412405b Merge origin/dev into code-yeongyu/cleanup-root-contract-tests
  • 0f69b09 Merge pull request #6059 from code-yeongyu/code-yeongyu/cleanup-lsp-record-predicate
  • 7a9a0d0 Merge remote-tracking branch 'origin/dev' into code-yeongyu/cleanup-lsp-record-predicate
  • 1136361 Merge remote-tracking branch 'origin/dev' into code-yeongyu/cleanup-root-contract-tests
  • 8ca9a88 Merge pull request #6058 from code-yeongyu/fix/hephaestus-review-gate-overtrigger
  • d5fa068 fix(codex-rules): scope review-work gate to PR handoffs instead of fuzzy 'significant work'
  • 76e7e76 Merge pull request #6056 from code-yeongyu/fix/hephaestus-sol-high-default
  • 14c892c Merge remote-tracking branch 'origin/dev' into code-yeongyu/cleanup-lsp-record-predicate
  • 7f648ca refactor(lsp-daemon): reuse record predicate
  • a67f3d1 test(root): remove source-shape sentinels
  • 2c4c7f0 test(agents): preserve hephaestus override coverage
  • dc253ff fix(model-core): raise hephaestus sol default
  • d269b23 Merge pull request #6052 from code-yeongyu/fix/teammode-transport-fallback
  • e101423 Merge pull request #6055 from code-yeongyu/chore/ultimate-browsing-dep-bump
  • 655f0f7 chore(ultimate-browsing): bump documented runtime dependency pins to latest
  • f261104 Merge pull request #6054 from code-yeongyu/fix/ultrawork-plan-routing
  • 1f58a54 fix(omo-codex): align plan agent and hephaestus routing with uncertainty-based planning
  • 22d66b0 fix(ultrawork): mirror uncertainty-based plan trigger in gpt variant
  • 691e76a fix(ultrawork): size planning by design uncertainty, not step count
  • 316e635 docs(omo-codex): sync teammode component AGENTS.md with transport fallback protocol
  • d49f5f8 fix(omo-codex): teammode transport chain with tool_search check and subagent fallback

Don't miss a new oh-my-openagent release

NewReleases is sending notifications on new releases.