Ettore Di Giacinto 53deeb1107 fix(reasoning): suppress partial tag tokens during autoparser warm-up ... The C++ PEG parser needs a few tokens to identify the reasoning format (e.g. "<|channel>thought\n" for Gemma 4). During this warm-up, the gRPC layer was sending raw partial tag tokens to Go, which leaked into the reasoning field. - Clear reply.message in gRPC when autoparser is active but has no diffs yet, matching llama.cpp server behavior of only emitting classified output - Prefer C++ autoparser chat deltas for reasoning/content in all streaming paths, falling back to Go-side extraction for backends without autoparser (e.g. vLLM) - Override non-streaming no-tools result with chat delta content when available - Guard PrependThinkingTokenIfNeeded against partial tag prefixes during streaming accumulation - Reorder default thinking tokens so <|channel>thought is checked before <|think|> (Gemma 4 templates contain both)		2026-04-04 20:45:57 +00:00
..
config.go	feat(openresponses): Support reasoning blocks (#8133)	2026-01-21 00:11:45 +01:00
extractor.go	fix(reasoning): accumulate and strip reasoning tags from autoparser results (#9227)	2026-04-04 18:15:32 +02:00
extractor_test.go	fix(reasoning): accumulate and strip reasoning tags from autoparser results (#9227)	2026-04-04 18:15:32 +02:00
reasoning.go	fix(reasoning): suppress partial tag tokens during autoparser warm-up	2026-04-04 20:45:57 +00:00
reasoning_suite_test.go	fix(reasoning): support models with reasoning without starting thinking tag (#8132)	2026-01-20 21:07:59 +01:00
reasoning_test.go	feat(gemma4): add thinking support (#9221)	2026-04-04 12:11:38 +02:00