docs(queue): record cheap-worker launch config (#356)

Merge the reviewed, green documentation update. Fixes #355.
2026-07-14 19:00:01 +00:00
parent 1e0eaca35e b37924545c
commit ecde59be32
1 changed files with 9 additions and 0 deletions
@@ -184,6 +184,15 @@ HARD CONSTRAINTS:

 - READ docs/README.md → the convention docs FIRST; point recon/implementer agents at specific
  doc sections. Only recon the task-specific delta.
+- **Codex cheap-worker launch (tested 2026-07-14)**: the native `spawn_agent` interface currently
+  has no model/effort selector, so it provides parallelism but not cost savings. For bounded,
+  tool-bearing selector/recon work, launch a separate worker with
+  `codex exec --ephemeral --color never -m gpt-5.4-mini -c model_reasoning_effort=low -s read-only
+  -C <repo> "<hard-capped scope contract>"`. GPT-5.4-Mini is the current supported small/cost-efficient
+  profile on this ChatGPT-authenticated host; the older `gpt-5.1-codex-mini` guess fails with HTTP 400.
+  Keep `low` whenever any shell/MCP/web tool is exposed; reserve `minimal` for explicitly tool-free
+  synthesis over already-supplied bounded evidence. If the model rolls over, inspect the visible entries
+  in `~/.codex/models_cache.json` instead of guessing names, then update this dated note once verified.
 - Keep the MAIN checkout's `web/node_modules` fresh (`npm install` after pulling a PR that
  adds a dep) — worktrees copy it, and a stale copy broke typecheck in a #198 worktree.
 - **Playwright-MCP E2E: never open tabs/window.open for file-download endpoints** — curl them.