fix: use strict=False for JSON parsing of tool calls and session data#1460
Open
Br1an67 wants to merge 1 commit intoMoonshotAI:mainfrom
Open
fix: use strict=False for JSON parsing of tool calls and session data#1460Br1an67 wants to merge 1 commit intoMoonshotAI:mainfrom
Br1an67 wants to merge 1 commit intoMoonshotAI:mainfrom
Conversation
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
LLM responses sometimes contain raw control characters (newlines, tabs) inside JSON string values in tool call arguments. With the default strict=True, json.loads() rejects these, causing tool call failures and corrupting the session context file so it can never be restored. Use strict=False in all critical JSON parsing paths: - Tool call argument parsing (toolset.py) - Session context restore and checkpoint revert (context.py) - Tool argument extraction for display (tools/__init__.py) - Debug tool call formatting (debug.py) Fixes MoonshotAI#1378
Br1an67
force-pushed
the
fix/json-control-chars
branch
from
efc6868 to
fcb799c
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
LLM responses sometimes contain raw control characters (newlines, tabs) inside JSON string values in tool call arguments. With the default
strict=True,json.loads()rejects these, causing:context.jsonllines that prevent session restorationFix
Use
json.loads(..., strict=False)in all critical JSON parsing paths:soul/toolset.py— tool call argument parsingsoul/context.py— session restore and checkpoint reverttools/__init__.py— tool argument extraction for displayui/shell/debug.py— debug tool call formattingTesting
Verified that
json.loads('{"key": "value\nwith newline"}', strict=False)correctly parses control characters that would fail withstrict=True.Fixes #1378