# NousResearch/hermes-agent · Codex model picker compatibility and slug fixes

## Open now

- 0 issues, 1 PR open on GitHub.
- PR #23189: fix(codex): trust live ChatGPT picker catalog

These issues and PRs center on problems with model name validity, filtering, and selection in the Codex/OpenAI-Codex provider, particularly around which model slugs are accepted or rejected by ChatGPT accounts versus Codex backends. Several entries address adding, removing, or correcting specific model identifiers like gpt-5.3-codex-spark and pro-tier slugs that return HTTP 400 errors.

## TL;DR

- 7 member(s): 0 open issue(s), 2 closed issue(s), 1 open PR(s), 1 merged PR(s), 3 PR(s) closed without merging.
- A fix was merged to main in PR #115760. Verify it addresses your case.
- **Recommended:** read PR #115760 (and any competing PRs below) before filing. Confirm the merged change covers your symptom.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.
- Members outside that structural core may belong to a different underlying problem.
- Pairwise link density `0.26`: the share of member pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. `1.00` means every pair is linked.

## Closed / duplicate issues

- #23097: \[Bug\]: OpenAI Codex picker allows ChatGPT-account unsupported models
- #61660: codex_models.py: \`*-pro\` slugs in DEFAULT_CODEX_MODELS return HTTP 400 for ChatGPT accounts

## Prior & competing PRs

- **#115760: fix(agent): Codex pool rotates to the next account on a ChatGPT-account model entitlement 400 (#71970, salvage #71973)**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`
  - files: `agent/agent_runtime_helpers.py`, `agent/credential_pool.py`, `agent/credential_pool_model_cooldowns.py`, `agent/error_classifier.py`, `agent/fallback_cooldown.py`, `contributors/emails/[redacted:email]`, `tests/agent/test_codex_model_entitlement_rotation.py`, `tests/agent/test_entitlement_fail_closed.py`, `tests/agent/test_error_classifier.py`, `website/docs/user-guide/features/credential-pools.md`
- **#23175: fix(cli): drop ChatGPT-account-rejected models from openai-codex picker**. closed without merge
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#23189`
- **#23189: fix(codex): trust live ChatGPT picker catalog**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `e8955f222`
  - files: `hermes_cli/codex_models.py`, `tests/hermes_cli/test_codex_models.py`
- **#61665: fix(codex): drop unsupported pro defaults**. closed without merge
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#89194`
- **#71973: fix(agent): rotate Codex credentials on model entitlement rejection**. closed without merge
  - maintainer direction: category `merged_via`; implication `superseded`; refs `f07afac38bc8`, `#115760`, `#71970`, `#71973`

## Fix status

- Merged to main in PR #115760 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-09-19`.
- Subsystem: `agent/secret_sources`