Improve message history pruning strategy in LLM Executor #4
Conversation
- Add `pruneMessages` function to `llm-executor.ts` - Update `executeLlmStep` to use robust pruning instead of naive slicing - Ensure orphaned tool results are re-attached to their parent assistant message - Fallback to naive slicing if parent is not found or history is malformed
|
👋 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. |
Improved the message history pruning strategy in
LLMExecutor. Previously, the code naively sliced the last N messages, which could leave 'tool' result messages orphaned without their corresponding 'assistant' tool call message. This change implements a smarterpruneMessagesfunction that backtracks from the cut point to ensure tool call/result pairs remain intact in the context window.PR created automatically by Jules for task 2138557981897317126 started by @mhingston