yolo/arr
3
0
Fork 0
Code Issues 12 Pull Requests Actions Packages Projects Releases Wiki Activity

docs: pair two models per difficulty tier

Browse Source
This commit is contained in:
Claude
2026-08-22 18:52:35 +01:00
parent dfd8440e10
commit 18fc1d1d44
1 changed files with 22 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CLAUDE.md
+22 -15
View File
@@ -131,35 +131,42 @@ alone. The loop:
### Model selection ### Model selection
Sessions are spawned with `aoe`. **Four models, and only these four** — Opus 5 Sessions are spawned with `aoe`. Each difficulty tier has **two models**, and
and Fable 5 through the `claude` tool, Sol and Terra through `codex`. issues at that tier are distributed between them — not run twice. Splitting
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
entire codebase.
| Difficulty | Model | Spawn | | Difficulty | Models | Spawn |
|---|---|---| |---|---|---|
| `difficulty/hard` | Fable 5 | `aoe add <path> --tool claude --extra-args "--model claude-fable-5" -l` | | `difficulty/hard` | Fable 5 | `aoe add <path> --tool claude --extra-args "--model claude-fable-5" -l` |
| | Sol | `aoe add <path> --tool codex --extra-args "-m gpt-5.6-sol" -l` |
| `difficulty/moderate` | Opus 5 | `aoe add <path> --tool claude --extra-args "--model claude-opus-5" -l` | | `difficulty/moderate` | Opus 5 | `aoe add <path> --tool claude --extra-args "--model claude-opus-5" -l` |
| `difficulty/easy` | Sol | `aoe add <path> --tool codex --extra-args "-m gpt-5.6-sol" -l` | | | Sol, low effort | `aoe add <path> --tool codex --extra-args "-m gpt-5.6-sol -c model_reasoning_effort=low" -l` |
| `difficulty/easy` | Sonnet 5 | `aoe add <path> --tool claude --extra-args "--model claude-sonnet-5" -l` |
| | Terra | `aoe add <path> --tool codex --extra-args "-m gpt-5.6-terra" -l` |
| `difficulty/trivial` | Terra | `aoe add <path> --tool codex --extra-args "-m gpt-5.6-terra" -l` | | `difficulty/trivial` | Terra | `aoe add <path> --tool codex --extra-args "-m gpt-5.6-terra" -l` |
Alternate within a tier rather than draining one model first, so a bad run is
visible early instead of after ten issues.
Use `-w <branch> -b` to put each session in its own git worktree, which is what Use `-w <branch> -b` to put each session in its own git worktree, which is what
makes parallel issues safe. makes parallel issues safe.
Two caveats on the table above, both cheap to fix and worth fixing before a long Caveats worth resolving before a long unattended run:
unattended run:
- `gpt-5.6-terra` is confirmed — it is the default in `~/.codex/config.toml`. - `gpt-5.6-terra` is confirmed — it is the default in `~/.codex/config.toml`.
`gpt-5.6-sol` is inferred from the sibling naming and unverified. `gpt-5.6-sol` is inferred from the sibling naming and unverified.
- Opus 5 and Fable 5 are both frontier models; the split between them at hard - `-c model_reasoning_effort=low` is the documented codex config-override form
and moderate is about reasoning depth, not capability tier. Sol above Terra is but has not been exercised here.
an assumption — swap the rows if it is backwards.
- `area/web` issues run on Fable 5 regardless of their difficulty label, since
they go through the `impeccable` skill.
Escalate one tier if a session fails CI twice on the same issue. Never **`area/web` issues run on Fable 5 regardless of their difficulty label**, since
de-escalate mid-issue. they go through the `impeccable` skill and the UI is the reason this project
has a frontend at all (see the design section above).
`area/web` issues ignore this table's lower tiers — see the design section Escalate one tier if a session fails CI twice on the same issue — and escalate
above. They go through the `impeccable` skill regardless of difficulty label. to the *other* model at that tier first, before going up. Never de-escalate
mid-issue.
### What a driver must not do ### What a driver must not do