7 people d706dec904 fix: Correct reasoning-end detection for prompt history (#44551) ...

Signed-off-by: jwzheng96 <jianweizheng@pku.edu.cn>
Signed-off-by: JianweiZheng <32029023+jwzheng96@users.noreply.github.com>
Signed-off-by: Jason Ozuzu <jasonozuzu@cohere.com>
Signed-off-by: walterbm <walter.beller.morales@gmail.com>
Co-authored-by: JianweiZheng <32029023+jwzheng96@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: walterbm <walter.beller.morales@gmail.com>
Co-authored-by: Walter Beller-Morales <walterbm@users.noreply.github.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>

2026-06-26 22:15:06 -07:00

..

__init__.py

[Refactor][Frontend] Keep all logic about reasoning into one class (#14428)

2025-03-28 00:23:30 -07:00

test_base_thinking_reasoning_parser.py

[Frontend] Fix reasoning_tokens for text-based parsers in Responses API (#33513)

2026-02-18 23:16:41 -08:00

test_cohere_command_reasoning_parser.py

fix: Correct reasoning-end detection for prompt history (#44551)

2026-06-26 22:15:06 -07:00

test_deepseekr1_reasoning_parser.py

reasoning_content -> reasoning (#27752)

2025-11-08 12:15:08 +00:00

test_deepseekv3_reasoning_parser.py

[Feat] DeepSeek V4 Rebased (#40860)

2026-04-26 18:31:08 -07:00

test_ernie45_reasoning_parser.py

reasoning_content -> reasoning (#27752)

2025-11-08 12:15:08 +00:00

test_gemma4_reasoning_parser.py

[Bugfix][Gemma4] Fix offline parser truncation, adjust_request token leak, and chat template sync (#45553)

2026-06-16 04:31:53 +00:00

test_glm4_moe_reasoning_parser.py

[Frontend] Add Streaming Parser Engine and new GLM4.7/GLM5.1/GLM5.2 Parser (#45915)

2026-06-19 00:42:10 +08:00

test_gptoss_reasoning_parser.py

[Performance] Add is_reasoning_end_streaming() override to GptOssReasoningParser (#35745)

2026-04-21 18:31:27 +00:00

test_granite_reasoning_parser.py

reasoning_content -> reasoning (#27752)

2025-11-08 12:15:08 +00:00

test_holo2_reasoning_parser.py

[Misc] Provide a DeepSeek ReasoningParser with thinking enabled by default (#33221)

2026-01-28 21:16:53 +08:00

test_hunyuan_reasoning_parser.py

Fix spelling errors (#33978)

2026-02-06 23:58:50 -08:00

test_hy_v3_reasoning_parser.py

[Bugfix] Avoid mutating chat_template_kwargs in HYV3ReasoningParser initialization (#40713)

2026-04-24 13:08:58 +08:00

test_kimi_k2_reasoning_parser.py

[Bugfix] KimiK2ReasoningParser: guard against buffered end-token in streaming (#41068)

2026-05-04 17:42:05 +00:00

test_minimax_m2_append_reasoning_parser.py

[bugfix] fix MiniMaxM2ReasoningParser streaming output not separating reasoning_content. (#29882)

2025-12-11 09:05:08 +00:00

test_minimax_m2_reasoning_parser.py

[Frontend] Add Streaming Parser Engine and new MinimaxM2 Parser (#45701)

2026-06-16 13:38:17 -04:00

test_minimax_m3_reasoning_parser.py

[Bugfix] Parse MiniMax M3 streaming reasoning by text markers (#45718)

2026-06-23 14:43:58 -04:00

test_mistral_reasoning_parser.py

[Chore] Adjust tokenizer import to avoid circular imports (#30601)

2025-12-13 04:42:39 -08:00

test_nemotron_v3_reasoning_parser.py

[Frontend] [Parser] Migrate Nemotron V3 to streaming parser engine (#45755)

2026-06-16 05:31:21 +00:00

test_olmo3_reasoning_parser.py

[Bugfix] Remove tokenizer encode/decode calls from Olmo3 reasoning parser (#40855)

2026-04-27 19:36:54 -07:00

test_qwen3_reasoning_parser.py

[Bugfix] Treat <tool_call> as implicit reasoning end in Qwen3 parser (#35687)

2026-04-24 09:10:04 +08:00

test_step3p5_reasoning_parser.py

Update to transformers v5 (#30566)

2026-04-15 16:29:15 -07:00

utils.py

[Feature] Lazy import for the "mistral" tokenizer module. (#34651)

2026-02-23 00:43:01 -08:00