GPT-5.6 Orchestration, Hardened End to End

This patch makes GPT-5.6 the first-class path for OMO's deepest work while tightening the handoffs that keep long-running agent workflows alive.

GPT-5.6 for Deep Work and Review

Hephaestus, Momus, deep, and ultrabrain now prefer GPT-5.6 Sol with role-appropriate reasoning levels, while GPT-5.5 remains the compatibility fallback. OpenCode and LazyCodex also select GPT-5.6-aware prompts and rule variants, so the model gets guidance tuned to its actual tool surface instead of inheriting older assumptions. GLM fallback chains move to GLM 5.2.

Native MultiAgentV2 Teams in LazyCodex

Codex team mode can now run on native MultiAgentV2 agents when that complete tool surface is available, with Codex App threads retained as the fallback transport. Team state records one immutable transport, validates agent and thread identities accordingly, and preserves the existing durable worktree, messaging, integration, and archive workflow across both paths.

Safer Codex Installation and Rule Switching

LazyCodex now resolves multi-agent behavior from the same custom model_catalog_json that Codex uses, including relative catalog paths beside config.toml. GPT-5.6/V2 installs remove stale V2 disables and incompatible agents.max_threads settings, while unknown root models no longer receive a risky thread-limit key. Managed Explorer, Librarian, and Momus defaults advance to their new model-appropriate efforts without overwriting custom model or effort choices. Symlinked plugin-cache entrypoints execute correctly, optional lifecycle tools are no longer assumed to exist, and dynamic bundled rules are reinjected when a session changes model.

Background Agents Stop Waiting Forever

OpenCode background tasks now finalize and notify their parent when provider, model, or credential errors are terminal even if the failed session shell still exists. Live-listener routing also verifies that the listener actually owns the target session before sending a parent wake, preventing completed work from disappearing into the wrong server instance.

No manual configuration migration is required. Explicit GPT-5.5 selections, custom LazyCodex agent efforts, and Codex App thread teams remain supported.

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

• 46a55ad Merge pull request #6022 from code-yeongyu/fix/codex-v2-catalog-guards-qa
• 7e45232 chore(codex): regenerate installer bundle
• cb11103 test(codex): pin bundled agent model matrix
• 60a8c55 fix(codex): advance managed agent efforts
• 6d69dc0 fix(codex): clean stale V2 installer guards
• 5eb7610 fix(codex): resolve V2 runtime catalog paths
• 9169161 Merge pull request #6021 from code-yeongyu/fix/preserve-explicit-gpt55-pins
• bdf7bb4 fix(config): preserve explicit GPT-5.5 pins
• 5c795d2 chore(skills): pin pre-publish review to Sol
• f33957d Merge pull request #6018 from code-yeongyu/fix/release-model-default-docs
• 3af2587 Merge pull request #6020 from code-yeongyu/fix/release-bg-terminal-errors
• 0eb507b Merge pull request #6019 from code-yeongyu/fix/release-rules-dynamic-model
• 7beada4 Merge pull request #6017 from code-yeongyu/fix/release-rules-hephaestus-truncation
• cf9cc74 docs: align root model defaults
• 8054bae docs: fix ultrabrain release model claim
• 39692c9 test(background): cover alive terminal cleanup
• effa699 fix(background): classify terminal provider errors
• f12a6b6 Merge pull request #6016 from code-yeongyu/fix/release-codex-installer-bundle
• 4f957b3 fix(omo-codex): invalidate dynamic rules on model switch
• 882c228 fix(rules): limit Hephaestus truncation exemption
• 7386266 docs: refresh GPT-native routing guidance
• 9de07f9 docs: complete current model fallback chains
• c3d4166 docs: align release model default tables
• 0a1fdfa fix(codex): regenerate installer bundle guards
• 0744e08 Merge pull request #6015 from code-yeongyu/fix/codex-sync-skills-optional-lifecycle
• a2e7f6a Merge pull request #6014 from code-yeongyu/fix/codex-multi-agent-unknown-model-safety
• a33ad74 fix(codex): guard optional subagent lifecycle tools in generated Codex guidance
• 9fb3110 fix(codex): resolve multi-agent version from model_catalog_json
• 33e204c fix(codex): installer never introduces agents.max_threads without a root model
• c5565df fix(codex): skip v2 disable and agents.max_threads when effective model is unknown
• 33b8055 Merge pull request #6013 from code-yeongyu/fix/live-route-session-affinity
• bcb1e09 fix(omo-opencode): verify live listener owns the session before routing parent wakes
• 7719ac3 fix(utils): allow affinity as a prompt dispatch route reason
• f1a8df1 Merge pull request #6012 from code-yeongyu/feature/omo-codex-gpt-5-6-prompt-rewrite
• b15f2c0 chore(omo-codex): trim lazycodex-executor worktree preamble
• de24514 feat(omo-codex): rewrite planner-support subagent prompts for gpt-5.6
• cf41382 feat(omo-codex): align hephaestus gpt-5.6 rule with opencode structure
• 14d6b2e Merge pull request #5998 from EvangelosMoschou/fix/5971-bg-task-death-notifies-parent
• ae3ca83 Merge pull request #6011 from code-yeongyu/feature/codex-teammode-v2-fallback
• 6a3b09a Merge pull request #6010 from code-yeongyu/feat/momus-gpt-5-6-xhigh
• 0348fd9 docs(codex): document teammode transports and V2-aware research routing
• 773706e feat(codex): route teammode through MultiAgentV2 with codex_app fallback
• dd22ebe docs: reflect momus gpt-5.6-sol xhigh default in model guides
• a6e5abf feat(utils): migrate momus configs pinned to old gpt-5.5 default
• 2dfbc26 feat(agents): add GPT-5.6 momus prompt with xhigh reasoning
• ac933d0 feat(model-core): route momus to gpt-5.6-sol xhigh as primary
• d81aed4 chore(omo-codex): set QA executor model to gpt-5.6-terra medium
• e1edf91 feat(omo-codex): route verification agents to gpt-5.6 series
• 9d10958 feat(omo-codex): run Momus reviews at ultra
• 1b8bc2d raise omo-codex gate reviewer reasoning effort to ultra
• 7124986 feat(omo-codex): model-gate Hephaestus bundled rule into gpt-5.5/gpt-5.6 variants
• 7ef8db1 docs: update model matching guide, examples, and references for gpt-5.6-sol and glm-5.2
• be29e0d test(omo-opencode): pin gpt-5.6-sol defaults for hephaestus, deep, and ultrabrain
• 6dd171c feat(model-core): replace glm-5.1 with glm-5.2 in agent and category fallback chains
• 38c703d docs(omo-codex): document V2-aware installer and symlink-safe entry guards
• ddac08f gpt-5.6 model migration across agents/categories/config; symlink-safe codex CLI entry-guard
• b765b54 lazycodex: set explorer/librarian to gpt-5.6-terra medium, plan to gpt-5.6-sol xhigh
• e4de69f fix(bg-agent): terminate task + notify parent on terminal session errors (#5971)

Thank you to 1 community contributor:

• @EvangelosMoschou:
  • fix(bg-agent): terminate task + notify parent on terminal session errors (#5971)