🤖 fix: avoid invalid requests from tool-only partials #1251
Conversation
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
ammar-agent
force-pushed
the
messages-vwm9
branch
2 times, most recently
from
5835eb2 to
aeda4c1
Compare
Add defensive filter after convertToModelMessages to catch any empty assistant messages that slip through. This is a final safety net - if corrupted history produces empty ModelMessages, they are filtered out before sending to the API. Also adds integration tests that seed corrupted history and verify the system self-heals.
ammar-agent
force-pushed
the
messages-vwm9
branch
2 times, most recently
from
6931bcd to
b373f93
Compare
Root cause: Anthropic's Extended Thinking API requires thinking blocks to include a signature for replay. The Vercel AI SDK silently drops reasoning parts without providerOptions.anthropic.signature, which can leave assistant messages empty and cause API rejection with 'all messages must have non-empty content'. Changes: - Add signature field to MuxReasoningPart and ReasoningDeltaEvent - Capture signatures from SDK stream events (signature_delta) - Store providerOptions.anthropic.signature for SDK compatibility - Add stripUnsendableReasoning() to remove reasoning without signatures before API calls, preventing empty messages - Add --workspace flag to CLI for debugging existing workspaces
ammar-agent
force-pushed
the
messages-vwm9
branch
from
b373f93 to
3b281cd
Compare
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Outdated suggestions cannot be applied.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.
Summary
Fixes Anthropic API validation error:
messages.X: all messages must have non-empty content except for the optional final assistant messageRoot Cause
Anthropic's Extended Thinking API requires thinking blocks to include a signature for replay. The Vercel AI SDK silently drops reasoning parts without
providerOptions.anthropic.signature. When all parts of an assistant message are unsigned reasoning, the SDK drops them all, leaving an empty message that Anthropic rejects.Changes
Core Fix
stripUnsendableReasoning()- Removes reasoning parts without signatures before API calls, preventing empty messages from reaching AnthropicSignature Capture (for future reasoning replay)
signatureandproviderOptionsfields toMuxReasoningPartsignaturetoReasoningDeltaEventSchemafor event transmissionsignature_delta)providerOptions.anthropic.signaturefor SDK compatibilityDebug Tooling
--workspace <id>flag to CLI for testing against existing workspacesTesting
Verified against a corrupted workspace (
e8dab40a78) with 286 empty assistant messages that previously caused consistent API failures. After fix:Generated with
mux• Model:anthropic:claude-opus-4-5• Thinking:high