NousResearch/hermes-agent

Classify masked Codex replay rejections correctly

Cluster 92353. Data as of 2026-10-25 11:21 UTC

Nothing open on GitHub. Fix merged in #104228 on 6 Sep 2026. Check it covers your case.

open issues

open PRs

items grouped

Known?: Yes. 4 related items grouped here, 1 issue already closed.
Fix event: A fix was merged to main in PR #104228. Check it covers your case. No release data is tracked.
Tracker: The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open: Nothing open on GitHub.

Next step: read #104228, then check it covers your case.

Read #104228 Pick up a Lab task

These issues and PRs concern a specific Codex replay rejection—where an 'invalid_prompt: Request blocked.' response masks the real cause—being misclassified into the wrong error bucket. The work focuses on correctly identifying and classifying these masked rejections as invalid_encrypted_content rather than a generic format error.

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.

#104228 Codex masked 'invalid_prompt: Request blocked.' replay rejection runs the replay-strip recovery (salvage #92357/#94077, closes #92353)

merged to main

files: agent/error_classifier.py, evals/codex_masked_replay_review.py, tests/agent/test_error_classifier.py

2 PRs closed without merging

From the close comments: done elsewhere 2

#92357 fix(codex): classify masked replay rejections behind the invalid_prompt envelope · done elsewhere → e0592b6, #104228, #104154
#94077 fix(agent): classify masked Codex replay rejection as invalid_encrypted_content · done elsewhere → e0592b6, #104228, #104154

Closed issues · 1

Closed#92353codex: masked replay rejection behind invalid_prompt falls into generic format-error bucket

How this cluster was grouped

Link evidence (structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
Pairwise link density 0.50: 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: #104228
Closed issues: 1
Attempts: 2 PRs closed without merging
Fix link checked: 6 Sep 2026

For your agent

The same facts, typed.

cluster/92353.json
cluster/92353.md