This repository has been archived by the owner on Jan 7, 2025. It is now read-only.
Refactor ParseResult into separate Pydantic models for success and error #588
Conversation
This file contains 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
![mentatai[bot]](https://avatars.githubusercontent.com/in/850097?s=60&v=4){kind=small}
Add error handling for invalid JSON and format in model responses - Introduce `ParseError` class to represent parsing errors, which can be returned instead of `ParsedLLMResponse` when an error occurs. - Handle `JSONDecodeError` and `ValidationError` exceptions in the `JsonParser` class, returning a `ParseError` instance with the appropriate error message and partial response. - Modify the `Conversation` class to handle `ParseError` instances, displaying the error message to the user and not adding the error response to the conversation messages. - Update the `AgentHandler` class to handle `ParseError` instances returned from the parser, displaying the error message to the user and returning an empty list of commands. This change improves the robustness of the system by providing better error handling and feedback to the user when issues occur during the parsing of model responses.
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
ParsedEditfor successful parses andParseErrorfor error cases.ParsedLLMResponseto be a union ofParsedEditandParseError.agent_handler.py,conversation.py, andjson_parser.pyto handle the new models.Closes #587