async-job-orchestrationlisted

# Async Job Orchestration Async execution for Claude, Codex, Gemini, Grok, and Mistral. Non-blocking jobs with polling lifecycle. Job state is **durable** — results survive gateway restarts and polling timeouts (see [Durability & Dedup](#durability--dedup)). > **Mistral Vibe**: the gateway always emits `--agent <mode>` and defaults to `auto-approve` for programmatic callers. Current Vibe defaults session logging on; `doctor --json` flags an explicit `[session_logging] enabled = false` before session-continuity use. ## 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. 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 `bypassPermissions`, Gemini with `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** — see [Polling Strategy](#polling-strategy) below. 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) — end every review prompt with "End with APPRO