Repository navigation
docs(models): document the reasoning token budget - #201
Merged
Merged
Conversation
…thinking_token_budget) Both names are accepted since nan-devops#895 and each model receives the one it reads. Values and behaviour measured on prod 2026-10-19: 64 caps reasoning at 64 tokens on qwen3.8-flash, 0 turns it off on qwen3.8-flash and qwen3.6, values above 32768 are lowered on NaN, and combining a budget with reasoning_effort behaves differently per model. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ontract wording, Responses) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
barckcode
added a commit
that referenced
this pull request
Oct 19, 2026
Resolved into one text per surface: - deepseek-v4-flash card (en + es): #200's wording (both ceilings, per-route signals, remedies) plus #202's non-streamed x-nan-truncated-in-reasoning header on the /chat/completions signal. #202's voseo phrasing and "raise the budget, or stream" are superseded. - Controlling reasoning: #200's paragraph keeps #202's three-field rule and header (scoped to non-streamed Chat Completions, per nan-devops#901, which reads `choices`); #201's token-budget subsection is linked from the "effort is a hint" sentence. - OpenAPI max_tokens: #200's text plus the header. max_output_tokens: #202 claimed finish_reason and the header on Responses; replaced by the Responses signal (status incomplete, incomplete_details) and the ceilings. - Tests: union of both suites, adjusted to the final text. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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
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
New subsection under Controlling reasoning (en + es):
thinking_token_budget/thinking_budgetonqwen3.6,gemma4andqwen3.8-flash(Chat Completions): the 1-32768 range, 0 = off, NaN lowers larger values to 32768, and use either a budget orreasoning_effort, not both.Why
helmcode/nan-devops#895 (in prod since 2026-10-19) accepts both names and sends each model the one it reads. Before that, only
thinking_token_budgetwas accepted and it did nothing on qwen3.8-flash.Evidence (prod, synthetic key, nonce to bypass the cache)
thinking_budget/thinking_token_budget64: 64 reasoning tokens; none: 899.none+ budget still reasons). Hence 'not both'.Tests
npm run buildOK;vitest run2496/2496 (the docs reasoning test that forbids upstream provider names passes).🤖 Generated with Claude Code