mirror of
https://github.com/merlinhu1/codex-game-studio.git
synced 2026-08-25 07:54:34 +02:00
* feat: add deterministic model tier routing Define Sol, Terra, and Luna policies with fixed fallbacks, explicit surface assignments, runtime precedence, and Luna escalation. Validate generated metadata and expose tier overrides across role, task, and orchestration commands. * fix: infer model tiers from surface models * fix: rebalance prompt model routing * fix: decouple prompt effort routing --------- Co-authored-by: MerlinH <merlinh221@gmail.com>
2.4 KiB
2.4 KiB
model, model_reasoning_effort, primary-agent, linked-skills, phase, risk, argument-hint, source-reference, source-hash, output-artifacts
| model | model_reasoning_effort | primary-agent | linked-skills | phase | risk | argument-hint | source-reference | source-hash | output-artifacts | ||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| gpt-5.6-terra | low | producer |
|
plan | high | Provide a team polish request with milestone state, polish candidates, discipline owners, risks, owner or handoff needs, and required verification evidence. | .codex/workflows/team-polish.md | 9999999999999999999999999999999999999999999999999999999999999999 |
|
Team Polish Workflow
Purpose
Coordinate polish work across design, art, audio, UI, QA, and engineering with owners, cutlines, risks, and verification gates.
Inputs
- AGENTS.md
- .codex/studio.json
- .codex/workflows/team-polish.md
- Production timeline, bug list, playtest findings, and discipline status
Role
Producer (producer) owns this workflow.
Taxonomy
Category: team-coordination CCGS adaptation coverage:
- team polish planning
- multi-role polish coordination CLI aliases:
- team-polish
Outputs
- Polish plan with owners, priorities, cutlines, and dependencies.
- Risks and release impact.
- Verification checklist and handoff routes.
Validation
- Polish items are bounded to milestone goals.
- Each item has one owner and validation signal.
- Cut or defer decisions are recorded.
Phase Gates
- Confirm project state, owner role, write policy, and selected context.
- Name required artifacts and acceptance criteria before implementation or review work.
- Do not advance to handoff until evidence is recorded or a blocker is explicit.
Required Artifacts
- Summary of the workflow result.
- Files, assets, tasks, docs, release notes, or tests changed or proposed.
- Verification evidence and unresolved risks.
Context Contract
- Load AGENTS.md, .codex/studio.json, this workflow, the primary agent, linked skills, and only task-relevant project files.
- Avoid broad context unless the user explicitly approves it.
Output Contract
- Decision or change summary.
- Step-by-step work performed or planned.
- Evidence, blockers, warnings, and next owner.
Stop Conditions
- Required project state, approval, target files, or verification path is missing.
- The task crosses into another role without an explicit handoff.
- The workflow would require generated prompt mirrors or hidden automation.
Handoff
Report changed files, validation evidence, residual risks, and the next owner only when ownership changes.