Jeffrey Morgan d98dda4676 model: fix qwen3 tool calling in thinking (#14477) ...

Align Qwen parser behavior with Transformers serve by allowing <tool_call> parsing while still in thinking collection.

Changes:

- qwen3vl: detect <tool_call> before </think> in thinking state and transition to tool parsing

- qwen3: same thinking-state tool detection and partial-tag overlap handling

- tests: update qwen3vl thinking/tool interleaving expectations

- tests: add qwen3 cases for tool call before </think> and split <tool_call> streaming

2026-02-26 16:13:18 -08:00

..

cogito_test.go

preserve tool definition and call JSON ordering (#13525)

2026-01-05 18:03:36 -08:00

cogito.go

Parser for Cogito v2 (#13145)

2025-11-19 17:21:07 -08:00

deepseek3_test.go

preserve tool definition and call JSON ordering (#13525)

2026-01-05 18:03:36 -08:00

deepseek3.go

DeepseekV3 Family Parser (#13484)

2025-12-16 18:56:30 -08:00

functiongemma_test.go

preserve tool definition and call JSON ordering (#13525)

2026-01-05 18:03:36 -08:00

functiongemma.go

preserve tool definition and call JSON ordering (#13525)

2026-01-05 18:03:36 -08:00

glm46_test.go

model: add Glm4MoeLiteForCausalLM architecture to support GLM-4.7-Flash (#13779)

2026-01-19 12:47:17 -08:00

glm46.go

model: add Glm4MoeLiteForCausalLM architecture to support GLM-4.7-Flash (#13779)

2026-01-19 12:47:17 -08:00

glm47_test.go

model: add Glm4MoeLiteForCausalLM architecture to support GLM-4.7-Flash (#13779)

2026-01-19 12:47:17 -08:00

glm47.go

model: add Glm4MoeLiteForCausalLM architecture to support GLM-4.7-Flash (#13779)

2026-01-19 12:47:17 -08:00

glmocr.go

Add GLM-OCR vision model support (#14024)

2026-02-02 15:39:18 -08:00

lfm2_test.go

model: improvements to LFM architectures (#14368)

2026-02-23 14:38:10 -08:00

lfm2.go

model: improvements to LFM architectures (#14368)

2026-02-23 14:38:10 -08:00

ministral_test.go

parsers/ministral: fix nested tool call parsing by counting brace nesting (#13905)

2026-01-26 15:03:43 -08:00

ministral.go

parsers/ministral: fix nested tool call parsing by counting brace nesting (#13905)

2026-01-26 15:03:43 -08:00

nemotron3nano_test.go

parsers: refactor Nemotron parser to reuse Qwen3Coder for tool calls (#13764)

2026-01-17 18:28:52 -08:00

nemotron3nano.go

parsers: refactor Nemotron parser to reuse Qwen3Coder for tool calls (#13764)

2026-01-17 18:28:52 -08:00

olmo3_test.go

preserve tool definition and call JSON ordering (#13525)

2026-01-05 18:03:36 -08:00

olmo3_think_test.go

parsers/renderers: olmo3 think (#13290)

2025-12-09 10:41:47 -08:00

olmo3_think.go

parsers/renderers: olmo3 think (#13290)

2025-12-09 10:41:47 -08:00

olmo3.go

preserve tool definition and call JSON ordering (#13525)

2026-01-05 18:03:36 -08:00

parsers_test.go

model: support for qwen3.5 architecture (#14378)

2026-02-24 20:08:05 -08:00

parsers.go

model: support for qwen3.5 architecture (#14378)

2026-02-24 20:08:05 -08:00

qwen3_test.go

model: fix qwen3 tool calling in thinking (#14477)

2026-02-26 16:13:18 -08:00

qwen3.go

model: fix qwen3 tool calling in thinking (#14477)

2026-02-26 16:13:18 -08:00

qwen3coder_test.go

parsers: refactor Nemotron parser to reuse Qwen3Coder for tool calls (#13764)

2026-01-17 18:28:52 -08:00

qwen3coder.go

parsers/ministral: fix nested tool call parsing by counting brace nesting (#13905)

2026-01-26 15:03:43 -08:00

qwen3vl_nonthinking_test.go

preserve tool definition and call JSON ordering (#13525)

2026-01-05 18:03:36 -08:00

qwen3vl_thinking_test.go

model: fix qwen3 tool calling in thinking (#14477)

2026-02-26 16:13:18 -08:00

qwen3vl.go

model: fix qwen3 tool calling in thinking (#14477)

2026-02-26 16:13:18 -08:00

testhelpers_test.go

model: add Glm4MoeLiteForCausalLM architecture to support GLM-4.7-Flash (#13779)

2026-01-19 12:47:17 -08:00