Attempt to decode tool_input as a JSON #1167
Open
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
We currently evaluate tool_input as a Python object. However, self._validate_tool_input may return a JSON string instead. This causes an error when tool_input contains lowercase true/false, which are valid JSON values but not valid Python (True/False).
As a result, the agent could enter an infinite loop if tool_input keeps resolving to a JSON string like:
```
{"timeMin": "2024-08-12T00:00:00Z", "timeMax": "2024-08-13T00:00:00Z", "single_events": true, "order_by": "startTime", "calendar_id": "primary"}
```
This commit addresses the issue by ensuring that tool_input is correctly parsed as JSON when necessary, preventing the infinite loop.
pythonbyte
reviewed
Aug 20, 2024
There was a problem hiding this comment.
Nice work @meetwudi
Can you provide a test case for this issue?
And fix the conflict?
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Outdated suggestions cannot be applied.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.
We currently evaluate tool_input as a Python object. However, self._validate_tool_input may return a JSON string instead. This causes an error when tool_input contains lowercase true/false, which are valid JSON values but not valid Python (True/False).
As a result, the agent could enter an infinite loop if tool_input keeps resolving to a JSON string like:
This commit addresses the issue by ensuring that tool_input is correctly parsed as JSON when necessary, preventing the infinite loop.