Marvin 253cf76f59 feat(server): strip executed Bailing blocks from reasoning_content ... vLLM Ling3 parity: reasoning ends where the executed call begins, so downstream panels never render converted calls as thinking text. Only complete blocks are removed; truncated fragments and narration survive. Separate commit on top of the rescue so each reverts independently.		2026-09-07 21:44:54 -03:00
..
bailing_parser.hpp	feat(server): strip executed Bailing blocks from reasoning_content	2026-09-07 21:44:54 -03:00
kimi_k2_parser.hpp	Function calling support for Kimi-K2 (#628)	2025-07-23 18:11:42 +02:00
qwen3_parser.hpp	Fix Qwen3 content extraction breaking code formatting (#661)	2025-08-07 08:22:01 +03:00