feat(langchain): forward provider-native modelSettings to chat models [PC-4672] - #119
Draft
tudormatei1 wants to merge 1 commit into
Draft
feat(langchain): forward provider-native modelSettings to chat models [PC-4672]#119tudormatei1 wants to merge 1 commit into
tudormatei1 wants to merge 1 commit into
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds model_settings to the langchain chat-model layer so agent.json's settings.modelSettings reaches the actual LLM call. UiPathBaseChatModel gets a model_settings field; get_chat_model gets a matching param that passes it into the client constructor.
Applied verbatim, no per-provider mapping. A validator walks each key: native fields on the vendor class (reasoning_effort on OpenAI, thinking/output_config on Anthropic, additional_model_request_fields on Bedrock) are set directly; anything else goes to model_kwargs; keys in disabled_params are skipped. Discovery owns the shape.
Langchain-only — core (src/uipath/llm_client/) is untouched, so the existing uipath-llm-client>=1.17.1 floor covers it. Bumped uipath-langchain-client to 1.18.0.
Tests build real OpenAI/Anthropic/Bedrock clients so the validator actually fires, and check native keys land as fields, unknowns go to model_kwargs, and disabled keys are skipped.