Cairn

Codex cache key exceeds 64-char limit causing 400 errors

NousResearch/hermes-agent · cluster 62063

Data as of

Nothing open on GitHub. Fix merged in #66330. Check it covers your case.

The short answer

0open issues
0open PRs
9items grouped
Known?
Yes. 9 related items grouped here, 2 issues already closed.
Fix event
A fix was merged to main in PR #66330. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this partially resolved, deciding PR #66330. That is separate from the fix event.
Still open
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.

Open issues0

No open issues.

Open PRs0

No open pull requests.

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

  • #66330 fix(codex): bound cache keys at provider boundaries

    merged to main

    files: agent/transports/codex.py, scripts/release.py, tests/agent/transports/test_codex_transport.py, tests/run_agent/test_run_agent_codex_responses.py

6 PRs closed without merging

From the close comments: duplicate 3 · superseded by another PR 2 · done elsewhere 1

  • #62266 fix(codex): clamp prompt_cache_key to 64 chars for Codex/ChatGPT backend · duplicate → #24273, #62063, #26468, #28307, #51037
  • #66050 fix: guard float infinity in stale timeout display and truncate codex cache key (#65746, #66045) · superseded by another PR → #66139, #66272
  • #66053 fix: cap prompt_cache_key at 64 chars to avoid OpenAI Codex 400 error (#66045) · duplicate → #24273
  • #66245 fix(codex): hash over-length prompt_cache_key to fit 64-char limit · done elsewhere → 61bbc39, #66330
  • #66272 fix: cap cache-scope headers at 64 chars to avoid Codex 400 error (#66045) · duplicate → #24273
Show 1 more
  • #66302 fix(runtime): recover stale model and cache state · superseded by another PR → #66330, #66331, #66332
Closed issues · 2
  • Closed#62063Codex/ChatGPT backend rejects requests when session_id > 64 chars (prompt_cache_key HTTP 400)
  • Closed#66045Codex transport emits an over-length `prompt_cache_key` (>64) → every openai-codex request 400s and silently falls back
How this cluster was grouped
  • Link evidence (partly structural links): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.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 item 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.

Pick up a Lab task

Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.

Open the Lab

At a glance

Merged PRs
#66330
Closed issues
2
Attempts
6 PRs closed without merging
Fix link checked
17 Jul 2026

For your agent

The same facts, typed.

cluster/62063.json
cluster/62063.md