vikingowl c2214aef96 feat(tools): graceful truncation for fetch_url with LLM retry hints ...

- Remove curl --max-filesize to avoid hard failures on large pages
- Add Truncated/OriginalSize fields to FetchResult for all fetch methods
- Return truncation info in proxy response (truncated, originalSize, returnedSize)
- Add timeout parameter to fetch_url tool (default 30s, max 120s)
- Increase default maxLength from 5KB to 50KB, allow up to 2MB
- Include _hint in response guiding LLM to retry with larger maxLength

Instead of failing when content exceeds limits, the tool now returns
truncated content with guidance for the LLM to request more if needed.

2026-01-02 19:14:35 +01:00

2.7 KiB

Raw Blame History

View Raw