Cairn

Provider overload errors triggering fallback chain

NousResearch/hermes-agent · cluster 10210 · agent

Data as of

5 open items. Fix attempted, not merged.

The short answer

2open issues
3open PRs
11items grouped
Known?
Yes. 11 related items grouped here, 2 issues already closed.
Fix event
No fix has been merged to main. 3 PRs closed without merging; see the attempts below.
Tracker
The maintainers' tracker marks this partially resolved, deciding PR #15120. That is separate from the fix event.
Still open
2 issues and 3 PRs.

These issues and PRs concern making 5xx/529/503 provider overload and rate-limit errors trigger the fallback model chain rather than retrying or failing in place. Related concerns include fallback suppression bugs, credential pool rotation, and surfacing error details to users.

Open issues2

  • Issue#60761Fallback chain never activates for 529 overloaded errors; once a fallback entry fails, it is permanently suppressed for the rest of the session
  • Issue#68771[Feature]: Treat provider 5xx (503 capacity/overload) as fallback-chain trigger, not just retry-then-fail

Open PRs3

  • PR#11034fix(run-agent): fail over on provider overload
  • PR#60785fix(agent): fix two fallback chain bugs (overloaded immediate fallback + TTL-based suppression)
  • PR#68886fix(agent): treat retryable 5xx as fallback-chain trigger

Fixes on record

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

  • #15120 fix(credential-pool): correctness + rotation + cross-process sync

    merged to mainSuggested link · files and diff not shown

3 PRs closed without merging

From the close comments: done elsewhere 3

  • #12554 fix(agent): fall back on rate limit when pool has no rotation room · done elsewhere → 1fc77f9
  • #15666 fix(fallback): trigger eager fallback on 503/529 provider overload · done elsewhere → #10210, #14038, #11314, #13636
  • #68926 fix(agent): treat retryable 5xx (overloaded/server_error) as fallback-chain trigger · done elsewhere → #68886
Closed issues · 2
  • Closed#10210[Bug]: Persistent HTTP 529 / “server cluster is currently under high load” errors in Hermes when using MiniMax M2.7
  • Closed#11314[Feature]: 遇到http 529错误的时候，应该尝试切换成fallback的模型
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(partly structural links): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.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 0.15: 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
#15120
Closed issues
2
Attempts
3 PRs closed without merging

For your agent

The same facts, typed.

cluster/10210.json
cluster/10210.md