[fix] Normalize chat workflow output to the canonical Message shape#4719
Open
jp-agenta wants to merge 1 commit into
Open
[fix] Normalize chat workflow output to the canonical Message shape#4719jp-agenta wants to merge 1 commit into
jp-agenta wants to merge 1 commit into
Conversation
chat_v0 returned the raw LiteLLM message, leaking provider-specific fields
(provider_specific_fields, annotations) into outputs. Validate through the SDK
Message model so the output is the canonical {role, content, name, tool_calls,
tool_call_id}, matching what a hook/custom workflow returns.
dosubot
Bot
added
the
size:XS
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
📝 WalkthroughSummary by CodeRabbit
WalkthroughIn ChangesMessage Canonicalization in chat_v0
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
Railway Preview Environment
|
mmabrouk
approved these changes
Jun 17, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Context
The
chat_v0workflow returned the raw LiteLLM message, leaking provider-specific fields intodata.outputs. So a basic chat call produced:{"content": "...", "role": "assistant", "provider_specific_fields": {"refusal": null}, "annotations": []}instead of the canonical message shape the rest of the platform uses.
Changes
chat_v0now validates its result through the SDKMessagemodel before dumping, sooutputsis the canonical{role, content, name, tool_calls, tool_call_id}(provider extras dropped). This matches what a custom/hook workflow returns after validating its own output throughMessage.Before:
{content, role, provider_specific_fields, annotations}After:
{role, content}(plus any of name/tool_calls/tool_call_id that are set)Tests / notes
Message.model_validatecleanly accepts a LiteLLM message dump with extras and yields the canonical fields.sdks/python/agenta/sdk/engines/running/handlers.py(chat_v0).🤖 Generated with Claude Code