implement-review-fixlisted

# Implement-Review-Fix Cycle Structured workflow: multiple LLMs implement, review, iterate until quality met. ## Cycle ``` 1. Implement (Codex) → 2. Review (Claude+Gemini) → 3. Fix (Codex) → 4. Verify └──────────────── loop until unconditional APPROVED ────────────────┘ ``` Single-level orchestration only — parent agent coordinates all steps. Child LLMs cannot call other LLMs through gateway. ## Dispatch Defaults Apply these on every dispatch unless the caller has explicitly overridden a rule in the current turn: 1. **Omit `model`** — let the gateway use its configured default per CLI. Nominating a model risks deprecated IDs (`o3`, `o3-pro`, `gpt-4o`, …) and capability mismatches. Use `list_models` only if the caller has asked for a specific variant. 2. **`approvalStrategy:"mcp_managed"`** is the skill dispatch default (the gateway schema default is `"legacy"`). It gates the request before execution; Claude then runs with `--permission-mode bypassPermissions`, Gemini with `--approval-mode yolo`, and Codex still needs `fullAuto:true` for autonomous file/shell work. Prefer this over raw bypass flags. 3. **No wallclock timeout; poll every 60 s** — let sync auto-defer at 45 s or use `*_request_async`. Poll `llm_job_status` once every 60 seconds. Do **not** cancel jobs for taking too long; cancel only on explicit instruction or hard failure. `idleTimeoutMs` (no-output safeguard) is separate. 4. **Iterate until unconditional APPROVED** (review dispatches only) — every rev