fix: Tool Calling w/ Parsing#108
Merged
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Notes
In general attempting to make the mixed form behavior of tool calls (xml especially) with parsing logic.
Nonebehavior being used to indicate tool call stopping conditionsGenerated Summary
Stopexception inrigging.error.pyto indicate a stopping condition within the pipeline.rigging/chat.pyfor clarity:stop_on_tool_callstoadd_tool_stop_token.add_tool_stop_token.ChatPipeline.clonemethod to allow selective cloning of callbacks, thereby providing more control during pipeline instantiation._then_tools,_then_parse) to utilize the new stopping mechanism.Toolclass to return a stop condition instead of a boolean to streamline flow control.tests/test_tool.pyto reflect changes in method signatures and assert logic that checks the new stop return value instead of continuation.rigging/prompt.pyfor better user guidance.This summary was generated with ❤️ by rigging
Generated Summary
Stopclass to manage stopping conditions within pipelines.stop_on_tool_callswithadd_tool_stop_tokenfor improved clarity in theChatPipeline.clonemethod inChatPipelineto control callback cloning behavior, allowing conditional cloning of callbacks based on the newcallbacksparameter.ChatPipelinemethods to accommodate new naming and logic for stopping tool calls.ChatPipelineto reflect changes, ensuring backward compatibility while enhancing functionality.should_continuetostop, simplifying control flow during tool call executions.stopcondition instead ofshould_continue.These changes improve the overall robustness and readability of the code, making it easier to manage tool calls and stopping conditions.
This summary was generated with ❤️ by rigging