Free profile: when every router model refuses mid-step, the step fails instead of waiting for quota #196
Loading…
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Seen in run 76 (production
97242c8, Free profile),openspec.apply[5], 2026-10-18 ~06:41Z. The step's session hopped between models turn by turn (Gemini 3.5 and 3.1 Flash-Lite, OVH Qwen3.5) until every model the router could reach refused at once:reflection/beam-free: its 200 requests an hour (per IP) were used, back at 07:00Z.429 You exceeded your current quota … Quota exceeded for metric: …, limit: 250000, model: gemini-3.5-flash-lite. That is a 250,000-tokens-per-minute limit, at about 45K input tokens a turn. The catalog has no token-per-minute limit for Gemini (operator task 1.6 of free-profile is still open), so the quota view showed the model asbreaker_open, not spent.429 … used up your daily free allocation of 10,000 neurons(code 4006). Most of that day had gone to the probes earlier the same night. Braid's ledger counts only what Braid sends, so it believed most of the day was left.GoModel returned the last refusal to opencode. Opencode treats a quota 429 (
provider.quota) as final, so the turn ended. The attempt closedcompletedwith 0 of 6 tasks done, and the step failed its predicate (group 5: 0/6 done (from tasks.md)). Braid's mediation then retried it (1 of 2). Braid holds a step for spent quota before it starts, but nothing waits when the chain runs dry part way through one. A longer crunch would use up both retries and fail the run.To do
limit: 250000per model per minute in tokens. Record it as a learned window so the ledger stops sending into it.cf-ai-neuronsheader andusage.neurons, or its refusal code 4006/3036 read as "spent until 00:00 UTC".Shipped in
ead9f7e(changefree-steps-ride-out-refusals). Seen on production in run 78: when every router model refused (Gemini's "exceeded your current quota"), the step parked (osf.free.parked,free_quota, "every model refused the step's turn") until OVH's minute reset, and continued the same session, with no failed attempt. Gemini's 250,000-token-per-minute limit is learned from its refusal. Run 78's failed attempts came from #202, not from this.Left open: the OpenSpec change is not archived yet, and its tasks are not ticked against production. Deferred when the session wrapped up (2026-10-18).
Closing: verified on production (run 78,
c1228b4): a dry chain parked the step and it continued the same session, with no failed attempt (see above). The OpenSpec changefree-steps-ride-out-refusals(shared with #195) archives afterfree-profile(#164), whose requirements it modifies.Archived in OpenSpec as
free-steps-ride-out-refusals(5a953a0).