Repository navigation
fix(ai): require thinking signature with provider-aware fallback - #44713
Merged
Merged
Conversation
rekram1-node
force-pushed
the
thinking-signature
branch
7 times, most recently
from
August 24, 2026 17:49
32aca2a to
3ff1f21
Compare
rekram1-node
force-pushed
the
thinking-signature
branch
from
August 24, 2026 17:52
3ff1f21 to
dad1392
Compare
24 of 30 tasks
jinhuang712
pushed a commit
to jinhuang712/opencode
that referenced
this pull request
Sep 26, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Anthropic requires
ThinkingBlockParam.signature, but some Anthropic-compatible APIs accept unsigned thinking only when it is sent with an empty signature.This keeps the behavior entirely in
packages/ai:signaturein the Anthropic request schemarequireSignaturesignature: ""for compatible APIs; otherwise demote it to text instead of sending an invalid thinking blockFocused Anthropic Messages tests cover the strict default, Kimi coding and Moonshot inference, and explicit override precedence.