Client-side rate limiting and RPM throttling proposals

NousResearch/hermes-agent · cluster 5449 · agent

Data as of

6 open items. Fix attempted, not merged.

The short answer

5open issues
1open PR
7items grouped
Known?
Yes. 7 related items grouped here, 0 issues already closed.
Fix event
No fix has been merged to main. 1 PR closed without merging; see the attempts below.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
5 issues and 1 PR.

These issues and pull requests discuss adding configurable, client-side rate limiting features—including RPM caps and use of x-ratelimit response headers—to proactively throttle requests and avoid hitting provider rate limits. The members cover both feature requests and proposed implementations around the same theme.

Open issues5

  • Issue#5449Track rate limit headers for proactive throttling
  • Issue#7489feat(agent): RPM-based pre-emptive throttling using x-ratelimit response headers
  • Issue#31802Feature Request: Configurable per-minute rate limiting (RPM) for models to prevent 429 errors
  • Issue#56419[Feature]: Configurable Client-Side API Rate Limit Management and Smart Request Scheduling
  • Issue#58061Feature request: provider-level rate limiter / throttle for fragile free endpoints

Open PRs1

  • PR#128816feat(agent): per-provider max_in_flight and requests_per_minute request admission

1 PR closed without merging

From the close comments: done elsewhere 1

  • #7490 feat(agent): pre-emptive RPM throttling using x-ratelimit response headers · done elsewhere → #7479
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(partly structural links): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.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 0.23: 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
Closed issues
0
Attempts
1 PR closed without merging

For your agent

The same facts, typed.