th-c127d1: send temperature 1.0 — 0 is rejected by many frontier models - #334
Merged
Conversation
Forward-port of the fix already shipped on the pinned lineage (b8acb3b, PR #333, branched from e9ce68c so smooth could consume it without a 1.23 -> 1.36 jump). This is the same change on main so future releases carry it. A growing set of frontier models accept only their default temperature and 400 the entire request: Unsupported value: 'temperature' does not support 0 with this model. Only the default (1) value is supported. The symptom does not look like a config error. The server boots, accepts the turn, every LLM call 400s, and the user sees an assistant that silently says nothing. Downstream this made Big Smooth's entire model picker a no-op — every model except the default returned an empty reply. A per-model allowlist was the obvious fix and is provably wrong; the behaviour does not follow the names. Measured against llm.smoo.ai: rejects temperature 0 : gpt-5.1, gpt-5.4-pro, gpt-5.5, claude-opus-4-7, claude-opus-4-8, claude-sonnet-5, claude-fable-5 accepts it : gpt-5, gpt-5.2, gpt-5.4, claude-haiku-4-5, claude-sonnet-4-5/4-6, claude-opus-4-6, gemini-3.5-flash, deepseek-v4-flash/pro, glm-5.1, minimax-m2.7, groq-gpt-oss-20b gpt-5.1 rejects while gpt-5.2 accepts; gpt-5.4 accepts while gpt-5.4-pro rejects. 1.0 was accepted by all 12 models tested across 6 families. Verified end-to-end on the pinned lineage against a real gateway: gpt-5.5 went from producing nothing at all to passing Big Smooth conversation scenarios 5/5/5/5 with zero LLM errors. 112 server tests pass. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01P83HrAKaqp2ehxQcW7m6QU
🦋 Changeset detectedLatest commit: f819ddf The changes in this PR will be included in the next version bump. This PR includes changesets to release 2 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
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
1 participant
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.
Forward-port of the fix already shipped on the pinned lineage (
b8acb3b, #333 — branched frome9ce68cso smooth could consume it without a 1.23 → 1.36 jump). Same change onmainso future releases carry it.The bug
A growing set of frontier models accept only their default temperature and 400 the entire request:
The symptom doesn't look like a config error. The server boots, accepts the turn, every LLM call 400s, and the user sees an assistant that silently says nothing. Downstream this made Big Smooth's entire model picker a no-op — every model except the default returned an empty reply.
Why not a per-model allowlist
Provably wrong; the behaviour doesn't follow the names. Measured by calling each model against llm.smoo.ai on 2026-08-07:
temperature: 0gpt-5.1,gpt-5.4-pro,gpt-5.5gpt-5,gpt-5.2,gpt-5.4claude-opus-4-7,claude-opus-4-8,claude-sonnet-5,claude-fable-5claude-haiku-4-5,claude-sonnet-4-5/4-6,claude-opus-4-6gemini-3.5-flash,deepseek-v4-flash/pro,glm-5.1,minimax-m2.7,groq-gpt-oss-20bgpt-5.1rejects whilegpt-5.2accepts.gpt-5.4accepts whilegpt-5.4-prorejects.1.0was accepted by all 12 models tested across 6 families.Verification
Verified end-to-end on the pinned lineage against a real gateway:
gpt-5.5went from producing nothing at all to passing Big Smooth conversation scenarios at 5/5/5/5 with zero LLM errors.claude-sonnet-5likewise runs.112 server tests pass.
Follow-up worth doing
The cleaner shape is
Option<f32>onLlmConfig— omit the field entirely and take each provider's own default, so there's no constant to maintain as the strict set moves.🤖 Generated with Claude Code
https://claude.ai/code/session_01P83HrAKaqp2ehxQcW7m6QU