mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-10-27 13:40:37 +00:00
27aa05f54e
* feat(community): add Jsonify dataset rows tool Adds deerflow.community.jsonify.tools:dataset_rows_tool, a read-only tool that returns rows from maintained Jsonify datasets. Jsonify pipelines run on a schedule and repair themselves when a source changes, so the agent reads a current table instead of scraping. - operator configures a named map of dataset -> serve URL; the model picks by name and never sees the URL - serve URLs must be https without userinfo and pass validate_public_http_url before any request; the URL is redacted from error text - paging with has_more/next_offset, version pinned after the first page, limit clamped to the configured max_rows, system columns stripped - config.example.yaml entry under tools; unit tests cover paging, clamping, unknown dataset, unconfigured tool, http/userinfo rejection, private address block and error redaction Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QrmeK98ZKoxZNiUiz8kVeX * fix(community): harden Jsonify tool paging, logging and error handling - Stop paging on an empty page or a next_offset that does not advance - Log config validation failures by field location and error type only - Validate page shape; malformed or non-JSON pages return a clean error - Transport errors report the exception type, never the URL - Add truncated flag when rows were clipped or more rows remain - Tests for each case Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QrmeK98ZKoxZNiUiz8kVeX --------- Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>