Cairn
NousResearch/hermes-agent

Classifying 429 quota-exhaustion errors for fallback instead of retry

Cluster 36276 · agent. Data as of

1 open item. Fix merged in #93455 on 24 Aug 2026. Check it covers your case.

The short answer

0open issues
1open PR
6items grouped
Known?
Yes. 6 related items grouped here, 2 issues already closed.
Fix event
A fix was merged to main in PR #93455. 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
0 issues and 1 PR.

These issues and pull requests all concern HTTP 429 quota or usage-limit errors from providers (e.g. Kimi monthly limit, Ollama Cloud session limit) being retried rather than treated as billing or non-retryable errors that trigger fallback. The members share one theme; one title mentions consolidating three earlier items, and another notes that reset signals should stay retryable.

Open issues0

No open issues.

Open PRs1

  • PR#36280fix(agent): trigger fallback on quota-exhaustion 429s (e.g. Kimi monthly limit)

Fixes on record

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

  • #93455 fix(classifier): 429 quota walls route to billing across providers; reset signals stay retryable (consolidates #39441, #63021, #74785)

    merged to main

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

2 PRs closed without merging

From the close comments: superseded by another PR 2

  • #39441 fix(agent): classify quota-exhaustion 429s as billing · superseded by another PR → 0c3a507, #93455
  • #65633 fix: classify 429 quota-exhaustion errors as non-retryable for fallback · superseded by another PR → 0c3a507, #93455, #39441
Closed issues · 2
  • Closed#36276fix(agent): HTTP 429 quota-exhaustion errors retried 3 times instead of failing fast
  • Closed#65563Ollama Cloud "session usage limit" 429 error not triggering fallback_providers chain
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 0.36: 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

Subsystem
agent
Merged PRs
#93455
Closed issues
2
Attempts
2 PRs closed without merging
Fix link checked
24 Aug 2026

For your agent

The same facts, typed.

cluster/36276.json
cluster/36276.md