# NousResearch/hermes-agent · Codex cache key exceeds 64-char limit causing 400 errors

## Open now

- Nothing open on GitHub.

Multiple fixes and a bug report address an over-length prompt_cache_key being sent to the OpenAI Codex/ChatGPT backend, triggering HTTP 400 rejections. The cluster centers on capping or hashing the cache key to fit within the 64-character limit.

## TL;DR

- 9 member(s): 0 open issue(s), 2 closed issue(s), 0 open PR(s), 1 merged PR(s), 6 PR(s) closed without merging.
- A fix was merged to main in PR #66330. Verify it addresses your case.
- **Recommended:** read PR #66330 (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: `partially_resolved` · deciding PR(s): `pr-66330`. 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evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.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 `0.20`: 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

- #62063: Codex/ChatGPT backend rejects requests when session_id > 64 chars (prompt_cache_key HTTP 400)
- #66045: Codex transport emits an over-length \`prompt_cache_key\` (>64) → every openai-codex request 400s and silently falls back

## Prior & competing PRs

- **#66330: fix(codex): bound cache keys at provider boundaries**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`; implication `superseded`
  - files: `agent/transports/codex.py`, `scripts/release.py`, `tests/agent/transports/test_codex_transport.py`, `tests/run_agent/test_run_agent_codex_responses.py`
- **#62266: fix(codex): clamp prompt_cache_key to 64 chars for Codex/ChatGPT backend**. closed without merge
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#24273`, `#24273`, `#62063`, `#26468`, `#28307`, `#51037`
- **#66050: fix: guard float infinity in stale timeout display and truncate codex cache key (#65746, #66045)**. closed without merge
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#66139`, `#66272`
- **#66053: fix: cap prompt_cache_key at 64 chars to avoid OpenAI Codex 400 error (#66045)**. closed without merge
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#24273`
- **#66245: fix(codex): hash over-length prompt_cache_key to fit 64-char limit**. closed without merge
  - maintainer direction: category `implemented_elsewhere`; implication `superseded`; refs `61bbc3933`, `#66330`
- **#66272: fix: cap cache-scope headers at 64 chars to avoid Codex 400 error (#66045)**. closed without merge
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#24273`
- **#66302: fix(runtime): recover stale model and cache state**. closed without merge
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#66330`, `#66331`, `#66332`

## Fix status

- Merged to main in PR #66330 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-07-17`.