multi-llm-orchestrationlisted

# Multi-LLM Orchestration Use the llm-gateway MCP server tools to orchestrate work across Claude, Codex, Gemini, Grok (xAI), and Mistral Vibe. ## 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 uses `bypassPermissions`, Gemini uses `yolo`, and Codex still needs `fullAuto:true` for autonomous file/shell work. 3. **No wallclock timeout; poll every 60 s** — `idleTimeoutMs` is a separate no-output safeguard. 4. **Iterate until unconditional APPROVED** (review dispatches only) — every review prompt must end with "End with APPROVED or NOT APPROVED with findings." Loop: dispatch → parse verdict → on `NOT APPROVED` or conditional, fix + re-review → repeat. Escalate after 3 rounds. This rule does **not** apply to pure implementation or non-review analysis dispatches. ## Available Tools - `claude_request` / `claude_request_async` — Send prompts to Claude Code CLI - `codex_request` / `codex_request_async` — Delegate tasks to Codex CLI (pass `sessionId:<UUID>` or `resumeLatest:true` to use `codex exec resume`) - `gemini_request` / `gemini_request_async` — Delegate tasks to Gemini C