UN-3136 [FIX] Skip thinking config for Vertex AI pro models when disabled #1775
+47
−29
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
Contributor
Summary by CodeRabbitRelease Notes
WalkthroughBumps tool image tags and toolVersion values for classifier, structure, and text_extractor across configs and registry; updates backend sample.env structure image tag; adds VertexAILLMParameters._get_thinking_config and changes thinking emission logic in the Vertex AI adapter. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes 🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
🧪 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
Test ResultsSummary
Runner Tests - Full Report
SDK1 Tests - Full Report
|
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In `@unstract/sdk1/src/unstract/sdk1/adapters/base1.py`:
- Around line 443-445: The current logic copies metadata into result_metadata
and then checks "thinking" in result_metadata which can reintroduce a stale
value; instead, use the thinking_config variable (the actual computed value)
when populating validated_data: only set validated_data["thinking"] =
thinking_config if thinking_config is not None (or if you want to allow falsy
values, test explicitly for the enabled/disabled condition), and remove reliance
on the presence of "thinking" in result_metadata so stale keys from
metadata_copy cannot leak through.
harini-venkataraman
approved these changes
Feb 3, 2026
Contributor
harini-venkataraman
left a comment
harini-venkataraman
left a comment
There was a problem hiding this comment.
Added a minor comment, LGTM otherwise
|
|
||
| # Pro models don't allow disabling thinking with budget_tokens=0 | ||
| model_name = metadata.get("model", "").lower() | ||
| if "pro" in model_name: |
Contributor
There was a problem hiding this comment.
@pk-zipstack Is this way of detection is reliable ?
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
Why
promodels because the thinking feature cannot be turned off forpromodelsHow
thinking_budgetwas sent to thelitellm.completion()by default when thinking config was not present.Can this PR break any existing features. If yes, please list possible items. If no, please explain why. (PS: Admins do not merge the PR without this section filled)
Database Migrations
Env Config
Relevant Docs
Related Issues or PRs
Dependencies Versions
Notes on Testing
Screenshots
Checklist
I have read and understood the Contribution Guidelines.