docs: verify model ids and worktree launch

This commit is contained in:
Claude
2026-08-22 18:57:38 +01:00
parent 18fc1d1d44
commit 5cf4eecdc3
2 changed files with 52 additions and 16 deletions
+1
View File
@@ -7,3 +7,4 @@
*.db-wal *.db-wal
result result
result-* result-*
/worktrees
+51 -16
View File
@@ -137,28 +137,63 @@ across two providers keeps a single provider's rate limits or an outage from
stalling the whole queue, and keeps one model's blind spots from shaping the stalling the whole queue, and keeps one model's blind spots from shaping the
entire codebase. entire codebase.
| Difficulty | Models | Spawn | | Difficulty | Models | `--tool` | `--extra-args` |
|---|---|---| |---|---|---|---|
| `difficulty/hard` | Fable 5 | `aoe add <path> --tool claude --extra-args "--model claude-fable-5" -l` | | `difficulty/hard` | Fable 5 | `claude` | `--model claude-fable-5` |
| | Sol | `aoe add <path> --tool codex --extra-args "-m gpt-5.6-sol" -l` | | | Sol | `codex` | `-m gpt-5.6-sol` |
| `difficulty/moderate` | Opus 5 | `aoe add <path> --tool claude --extra-args "--model claude-opus-5" -l` | | `difficulty/moderate` | Opus 5 | `claude` | `--model claude-opus-5` |
| | Sol, low effort | `aoe add <path> --tool codex --extra-args "-m gpt-5.6-sol -c model_reasoning_effort=low" -l` | | | Sol, low effort | `codex` | `-m gpt-5.6-sol -c model_reasoning_effort="low"` |
| `difficulty/easy` | Sonnet 5 | `aoe add <path> --tool claude --extra-args "--model claude-sonnet-5" -l` | | `difficulty/easy` | Sonnet 5 | `claude` | `--model claude-sonnet-5` |
| | Terra | `aoe add <path> --tool codex --extra-args "-m gpt-5.6-terra" -l` | | | Terra | `codex` | `-m gpt-5.6-terra` |
| `difficulty/trivial` | Terra | `aoe add <path> --tool codex --extra-args "-m gpt-5.6-terra" -l` | | `difficulty/trivial` | Terra | `codex` | `-m gpt-5.6-terra` |
Alternate within a tier rather than draining one model first, so a bad run is Alternate within a tier rather than draining one model first, so a bad run is
visible early instead of after ten issues. visible early instead of after ten issues.
Use `-w <branch> -b` to put each session in its own git worktree, which is what ### Launching a session
makes parallel issues safe.
Caveats worth resolving before a long unattended run: Verified working against this repo:
- `gpt-5.6-terra` is confirmed — it is the default in `~/.codex/config.toml`. ```sh
`gpt-5.6-sol` is inferred from the sibling naming and unverified. aoe add /home/naps62/tea/arr \
- `-c model_reasoning_effort=low` is the documented codex config-override form --title "arr-42-torznab" \
but has not been exercised here. --worktree issue/42-torznab --new-branch \
--tool codex --extra-args "-m gpt-5.6-sol" \
--launch
```
Things that are easy to get wrong:
- **The worktree path comes from `--title`, not from the branch.** That command
creates `/home/naps62/tea/arr/worktrees/arr-42-torznab` on branch
`issue/42-torznab`. Give every session a distinct title or the second one
collides.
- `--new-branch` is required alongside `--worktree` for a branch that does not
exist yet. Without it, `aoe` expects the branch to be there already.
- The base branch defaults to the repo default (`main`). Pass `--base-branch`
only when stacking on an in-flight branch.
- YOLO mode came out enabled without passing `-y`, from profile config. Check
that is what you want before an unattended run.
- `aoe remove <title>` keeps the worktree. Use `--delete-worktree`, or clean up
with `git worktree remove --force` — and note `aoe` leaves the worktree
*locked*, so `git worktree unlock` comes first.
### Model IDs, verified
All five were checked against the live CLIs on 2026-08-22, with a deliberately
bogus ID as a control to prove the check discriminates:
| ID | Tool | Result |
|---|---|---|
| `claude-fable-5` | claude | accepted |
| `claude-opus-5` | claude | accepted |
| `claude-sonnet-5` | claude | accepted |
| `gpt-5.6-sol` | codex | accepted |
| `gpt-5.6-terra` | codex | accepted, and the default in `~/.codex/config.toml` |
`-c model_reasoning_effort="low"` was exercised on a real `codex exec` run and
accepted. The bogus control (`gpt-5.6-nonesuch`) failed with HTTP 400, and
`claude-bogus-9` was rejected by the CLI.
**`area/web` issues run on Fable 5 regardless of their difficulty label**, since **`area/web` issues run on Fable 5 regardless of their difficulty label**, since
they go through the `impeccable` skill and the UI is the reason this project they go through the `impeccable` skill and the UI is the reason this project