# NousResearch/hermes-agent · Upstream capacity 429/503 errors hitting paid users

## Open now

- 2 issues, 1 PR open on GitHub.
- #38929: Paid subscription: HTTP 503 upstream capacity limits on qwen/qwen3.7-max
- #38933: \[Bug\]: Getting failed message requests to models on PAID subscription due to "upstream quota limits"?
- PR #102395: fix(agent): retry 503/529 capacity overloads over a bounded window, then fall back
- _Broad area: open items may be separate problems._

Reports and a code change related to upstream capacity limit errors (429/503) from model providers incorrectly triggering rate limiting or disrupting requests for paid subscribers. At least one proposed code change addresses handling these errors differently.

## TL;DR

- 3 member(s): 2 open issue(s), 0 closed issue(s), 1 open PR(s), 0 merged PR(s), 0 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. 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evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.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 `0.45`: 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.

## Open related issues

- #38929: Paid subscription: HTTP 503 upstream capacity limits on qwen/qwen3.7-max
- #38933: \[Bug\]: Getting failed message requests to models on PAID subscription due to "upstream quota limits"?

## Prior & competing PRs

- **#102395: fix(agent): retry 503/529 capacity overloads over a bounded window, then fall back**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`; refs `#83754`, `#33729`, `#68886`, `#68771`, `#55540`
  - files: `agent/conversation_loop.py`, `agent/retry_utils.py`, `tests/agent/test_capacity_overload_retry.py`

## Fix status

- No merged fix on record.
- Subsystem: `agent`
