Skip to content

Refresh stale Codex/Gemini model lists to current CLI lineup#155

Open
ryuhaneul wants to merge 1 commit into
PleasePrompto:mainfrom
ryuhaneul:feat/refresh-model-lists
Open

Refresh stale Codex/Gemini model lists to current CLI lineup#155
ryuhaneul wants to merge 1 commit into
PleasePrompto:mainfrom
ryuhaneul:feat/refresh-model-lists

Conversation

@ryuhaneul

Copy link
Copy Markdown
Contributor

What

The RULES templates deployed as CLAUDE.md / AGENTS.md / GEMINI.md
(under config, cron_tasks, cron_tools, webhook_tools, agent_tools),
the tool --help text, and the hardcoded discovery fallbacks
(_FALLBACK_CODEX_MODELS, _FALLBACK_GEMINI_MODELS) all list Codex and
Gemini models that no longer exist in the current CLIs — e.g.
gpt-5.2-codex, gpt-5.3-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini,
gemini-2.5-flash-lite, gemini-3-flash-preview.

Changes

Update them to the current lineup (as exposed by the Codex/Gemini CLIs via
model discovery):

  • Codex: gpt-5.5, gpt-5.4, gpt-5.4-mini, gpt-5.3-codex-spark
  • Gemini: gemini-2.5-pro, gemini-2.5-flash, gemini-3-pro-preview, gemini-3.1-pro-preview, gemini-3.1-flash-lite, gemini-3.5-flash

Also:

  • Remove the obsolete per-model reasoning-effort caveat
    (gpt-5.1-codex-mini "medium/high only") — all current Codex models
    support low/medium/high/xhigh.
  • Map the old "cheapest" gemini-2.5-flash-lite examples to its lite-tier
    successor gemini-3.1-flash-lite.
  • Refresh _FALLBACK_CODEX_MODELS / _FALLBACK_GEMINI_MODELS so the
    discovery fallback no longer offers nonexistent models.

Already-valid example values (e.g. gpt-5.4, gemini-2.5-pro) are left
unchanged; only stale references are updated. Documentation + fallback
contents only — no logic changes.

The RULES templates (deployed as CLAUDE.md/AGENTS.md/GEMINI.md), the
cron/webhook/agent tool help text, and the hardcoded discovery
fallbacks all listed Codex and Gemini models that no longer exist in
the current CLIs (e.g. gpt-5.2-codex, gpt-5.1-codex-mini,
gpt-5.1-codex-max, gemini-2.5-flash-lite, gemini-3-flash-preview).

Update them to the current lineup:

- Codex: gpt-5.5, gpt-5.4, gpt-5.4-mini, gpt-5.3-codex-spark
- Gemini: gemini-2.5-pro, gemini-2.5-flash, gemini-3-pro-preview,
  gemini-3.1-pro-preview, gemini-3.1-flash-lite, gemini-3.5-flash

Also:

- Remove the obsolete per-model reasoning-effort caveat
  ("gpt-5.1-codex-mini only supports medium/high") since all current
  Codex models support low/medium/high/xhigh.
- Refresh the _FALLBACK_CODEX_MODELS / _FALLBACK_GEMINI_MODELS lists in
  codex_cache.py / gemini_cache.py so the discovery fallback no longer
  offers nonexistent models.

Already-valid example values (e.g. gpt-5.4, gemini-2.5-pro) are left
unchanged; only stale references are updated.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant