⚡ Bolt: Replace DirtyJson.parse_string with dirty_json.try_parse#14
⚡ Bolt: Replace DirtyJson.parse_string with dirty_json.try_parse#14thirdeyenation wants to merge 1 commit intomainfrom
Conversation
Co-authored-by: thirdeyenation <133812267+thirdeyenation@users.noreply.github.com>
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
💡 What: Replaced direct calls to
DirtyJson.parse_stringwithdirty_json.try_parse.🎯 Why:
dirty_json.try_parsetriesjson.loadsfirst, which is heavily optimized C code, and falls back toDirtyJson.parse_stringonly when the JSON is malformed. CallingDirtyJson.parse_stringdirectly uses a slower python-based parser even for well-formed JSON strings. This was identified as a bottleneck in the Bolt journal.📊 Impact: Considerably faster parsing for all JSON strings generated by LLM that are well-formed. This directly improves the execution speed of MCP handlers, memory consolidation loops, browser agent processing, and general streaming JSON processing in the agent.
🔬 Measurement: Run unit tests and benchmark the execution loop duration with well-formed JSON strings to observe the performance difference.
PR created automatically by Jules for task 14067371454696352230 started by @thirdeyenation