luigidemasi opened a new issue, #30: URL: https://github.com/apache/camel-kit/issues/30
> Imported from [luigidemasi/camel-kit#52](https://github.com/luigidemasi/camel-kit/issues/52), opened by [luigidemasi](https://github.com/luigidemasi) on 2026-05-06. > Closed on 2026-05-08 without a linked pull request. --- ## Description When Bob's context is near capacity during plan generation, `write_to_file` calls get truncated — the LLM output is cut off mid-generation, producing partial writes that destroy the rest of the document. ## Fix Add a Bob plan trait that instructs Bob to use `insert_content` instead of `write_to_file` for plan generation: 1. Create the file with header only using `write_to_file` 2. Append each task as a separate `insert_content` call (one task per insert, under 100 lines) 3. Verify after each insert by reading the last 5 lines 4. If truncated, re-insert just the missing portion -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
