docs(models): document the reasoning-only stream limit - #94
Merged
Merged
Conversation
Publishes the platform-side limit that closes reasoning-only streams (issue #90 follow-up, alongside the estimated usage chunk shipped in nan-devops#550): 60,000 reasoning characters or 420 seconds with no visible output, closed with finish_reason=length plus an estimated, not-billed usage chunk when include_usage was requested. Sits in the same section as the reasoning_effort contract, EN + ES mirrors, with the disarm-on-first-output behavior and the mitigation levers members can act on.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Documents the platform-side reasoning-only stream limit in the public
model docs (EN + ES mirrors), in the same section as the
reasoning_effortcontract:no visible
content/ tool calls → the platform closes the turn withfinish_reason: "length".stream_options.include_usageis set:estimated: true, billed: false+nan_truncationmarker (shipped in nan-devops#550,deployed 2026-09-21).
levers (
reasoning_effort, early-content prompt design).Why
Issue #90: the limit was enforced but undeclared — the exact class of
published-vs-enforced disagreement tracked in #53. Members bisecting
long-reasoning prompts had no way to know the ceiling was ours, and the
missing usage block made attempts unaccountable.
Evidence
npm run buildgreen (Astro/Vite, both locales).chars, no env overrides in the cluster) and the live trip verified
2026-09-21 (glm5.3-flash, 164s, estimated usage chunk observed).