Yoni Gozlan 2eaa3bc5ac [Frontend] Enrich chat_parsing streaming events (#58603) ...

Give serving adapters the delimiter spans and opener captures they need,
and keep streaming after a region that fails to parse.

Signed-off-by: Yoni Gozlan <yonigozlan@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Fix mypy index types in the event-stream test.

2026-10-01 11:13:13 +08:00

..

chat_parsing

[Frontend] Enrich chat_parsing streaming events (#58603)

2026-10-01 11:13:13 +08:00

engine

[Frontend] Support strict MiMo-V2.6 tool calling (#58019)

2026-09-29 12:47:47 +00:00

__init__.py

[Refactor] Chat Completions Harmony Refactor, non-streaming path. (#45171)

2026-06-11 21:18:30 +00:00

abstract_parser.py

[Bugfix][Frontend] Enforce parallel_tool_calls=false in the required-tool grammar (#50502)

2026-09-29 21:33:28 +00:00

AGENTS.md

[Agent] Add agent instructions for parser directories (#56883)

2026-09-16 06:55:26 -04:00

CLAUDE.md

[Agent] Add agent instructions for parser directories (#56883)

2026-09-16 06:55:26 -04:00

cohere_command.py

[Bugfix] Hoist $defs/definitions in Cohere parser tool schema composition (#49602)

2026-09-29 07:11:56 +00:00

deepseek_v4.py

[Frontend] Fix the parsing of missing string= in DeepSeek V4 (#56271)

2026-09-18 05:11:24 +00:00

deepseek_v32.py

[Refactor] Derive is_reasoning_end from the engine grammar (#56200)

2026-09-15 10:07:58 +00:00

deepseek_v41.py

[Frontend] Fix the parsing of missing string= in DeepSeek V4 (#56271)

2026-09-18 05:11:24 +00:00

gemma4.py

fix: perf: use startswith(x, i) instead of string slicing to avoid O(N^2) (#52580)

2026-09-25 23:22:13 +00:00

glm47_moe.py

[Bugfix][Frontend] Force reasoning mode for GLM-5.3 chat templates in the GLM MoE parser (#56994)

2026-09-29 21:26:34 +08:00

granite_thinking.py

[Feature][Frontend] Add granite_thinking_parser reasoning parser for Granite 4.2 (#55957)

2026-09-25 20:43:08 +00:00

granite.py

[Bugfix][Tool Parser] Migrate Granite to the streaming Parser Engine (#49648)

2026-09-23 10:37:40 +00:00

harmony.py

[Bugfix] Suppress HarmonyError Unexpected token while expecting start token 200006 (#59254)

2026-09-29 16:40:15 -04:00

inkling.py

[Bugfix][Frontend] Fix Inkling tool name leaking into content after reasoning (#58792)

2026-09-26 00:38:52 +00:00

kimi_k2.py

[Refactor] Derive is_reasoning_end from the engine grammar (#56200)

2026-09-15 10:07:58 +00:00

kimi_k3.py

[Frontend] Move engine/protocol.py out openai folder (#54492)

2026-08-31 10:13:50 +00:00

ling3.py

[Model] Add Bailing V3 VL support (#55921)

2026-09-10 02:46:56 -07:00

metrics.py

[Frontend][Metrics] Add vllm:tool_call_parser_invocations_total Prometheus metric (#44448)

2026-06-10 10:29:11 -04:00

mimo.py

[Frontend] Support strict MiMo-V2.6 tool calling (#58019)

2026-09-29 12:47:47 +00:00

minimax_m2.py

[Refactor] Derive is_reasoning_end from the engine grammar (#56200)

2026-09-15 10:07:58 +00:00

mistral.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

nemotron_v3.py

[Frontend] Move engine/protocol.py out openai folder (#54492)

2026-08-31 10:13:50 +00:00

parser_manager.py

[Frontend] Add --tool-strict-level for server-side control for structural tag activation (#56268)

2026-09-18 04:32:39 +00:00

plamo3.py

[Model] Engine based plamo3 parser (#56575)

2026-09-29 05:17:42 +00:00

qwen3.py

[Refactor] Derive is_reasoning_end from the engine grammar (#56200)

2026-09-15 10:07:58 +00:00

seed_oss.py

[Bugfix][Parser] Seed-OSS turn-boundary tokens + boundary-fallback tests (#54264)

2026-09-09 23:29:30 +00:00

utils.py

[Bugfix][Tool Parser] Migrate Granite to the streaming Parser Engine (#49648)

2026-09-23 10:37:40 +00:00