Free profile: a model whose streams stall or time out keeps being chosen, and the router cuts slow streams at 10 minutes #195
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, the first production run on the Free profile (
97242c8), inopenspec.propose.design. Every turn went to the strong chain's head, NVIDIA'sz-ai/glm-5.3. Opencode showedprovider.unknown: provider stream ended before completionand retried with "The previous response was interrupted. Continue from where you left off…", four times and counting, and the console sat idle for minutes between tries.The router's log (GoModel 0.1.103), 2026-10-18:
provider stream ended before completion: context deadline exceeded (Client.Timeout …). That is the router's ownhttp.timeout: 600, a flat ten-minute cap per request. Braid's served rows for the design step showduration_ms600006.[nvidia] provider_error: provider stream stalled: no data for 5m0s. That isstream_idle_timeout: 300. The served row shows 460053 ms.failovers: [].Why it keeps happening
stream_error.To do
stream_errorattempts (provider stream stalled,context deadline exceeded,stream ended before completion) as a failure of that model. Put it behind the other models of its tiers for a cool-down, so the next try is served by the next model. Say so in the quota view and Settings, e.g. "stalled: 3 streams cut in 20 min, back at 06:40".Workaround used now: take NVIDIA out (
OSF_FREE_OPT_INcleared in the stack).Another stream fault of the same class, run 76,
openspec.apply[7], 06:57:51Z:provider.invalid-output: OpenAI Chat received content after the finish reason. The error body is a stream chunk with areadtool call andfinish_reason: "tool_calls", so a model sent a tool-call delta after its finish reason. It is most likely Gemini through GoModel's translation: the probes saw Gemini 3.5's stream break opencode's first turn the same way. Like a stalled or cut stream, it ends the turn with an error after a 200. It belongs in point 1: count it against the model (cool-down), and continue the step on the next model.Another output defect of the same class, run 78 (
c1228b4),openspec.apply[5], 14:15:57Z to 14:16:18Z: opencode retried three times on status 200Provider finish_reason: malformed_function_call(Gemini's MALFORMED_FUNCTION_CALL finish reason, passed through GoModel), on the same model. Likeinvalid_output, a retry on the same model tends to repeat it. Count it against the model (cool-down) so the retry goes to the next model.Shipped in
ead9f7e(changefree-steps-ride-out-refusals, with #196), plusc1228b4: a client's cancel is not a cut (750de96), and the router fails over on unrenderable requests (#200). Seen on production in run 78: Gemini 3.5 Flash-Lite's malformed stream put it behind for 30 min (osf.free.stalled, causeinvalid_output); a busy Zen model stalled (causebusy) and the step moved back to the router, announced before Braid's abort. Not yet seen live: a cut at 10 minutes under the new 3,600 s cap. Still open from the comments:malformed_function_callcounted against the model.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).
Archived in OpenSpec as
free-steps-ride-out-refusals(5a953a0, with #196). Verified on production in run 78: malformed streams and busy Zen models put behind, a client's cancel no longer counted, the router failing over on unrenderable requests (#200). Not yet seen live: a 10-minute cut under the 3,600 s cap, andmalformed_function_call, which still needs counting; both are in #205. Closing.