jay77721 e4c658c046 Refactor(go-models): add token usage for groq (#17574) ...

### Summary
Add token usage reporting for the Groq model provider. Related to
#17284.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-07-31 11:37:51 +08:00

..

302ai_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

302ai.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

aliyun_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

aliyun.go

fix(go-models): record provider token usage (#17423)

2026-07-27 17:16:50 +08:00

anthropic_test.go

fix(go): implement Anthropic streaming (ChatStreamlyWithSender) (#17380)

2026-07-28 21:10:28 +08:00

anthropic.go

fix(go): implement Anthropic streaming (ChatStreamlyWithSender) (#17380)

2026-07-28 21:10:28 +08:00

astraflow_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

astraflow.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

avian_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

avian.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

azure_openai.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

baichuan.go

Go: add token usage for orcarouter, baichuan, cohere and novita (#17455)

2026-07-28 19:14:05 +08:00

baidu.go

Go: add token usage for baidu, minimax, moonshot and mistral (#17413)

2026-07-27 18:04:36 +08:00

base_model.go

Go: add token usage for baidu, minimax, moonshot and mistral (#17413)

2026-07-27 18:04:36 +08:00

bedrock_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

bedrock.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

builtin.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

chat_tools.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

chat_usage_test.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

cohere_test.go

Go: add token usage for orcarouter, baichuan, cohere and novita (#17455)

2026-07-28 19:14:05 +08:00

cohere.go

Go: add token usage for orcarouter, baichuan, cohere and novita (#17455)

2026-07-28 19:14:05 +08:00

cometapi_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

cometapi.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

common_test.go

fix(go-models): normalize Qwen reasoning families (#15735)

2026-06-08 19:32:19 +08:00

common.go

fix(go-models): normalize Qwen reasoning families (#15735)

2026-06-08 19:32:19 +08:00

deepinfra_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

deepinfra.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

deepseek_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

deepseek.go

refactor(go-models): share chat response handling (#17289)

2026-07-24 10:51:37 +08:00

dummy.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

factory.go

feat: add GreenPT model provider (#17447)

2026-07-28 19:19:00 +08:00

fishaudio_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

fishaudio.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

funasr_test.go

fix: allow local FunASR without API key (#17388)

2026-07-27 10:09:31 +08:00

funasr.go

fix: allow local FunASR without API key (#17388)

2026-07-27 10:09:31 +08:00

futurmix.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

get_driver_test.go

fix: docx/email parsing, extractor LLM driver, and chunker alignment (#17144)

2026-07-21 13:51:17 +08:00

get_driver.go

fix: docx/email parsing, extractor LLM driver, and chunker alignment (#17144)

2026-07-21 13:51:17 +08:00

gitee_test.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

gitee.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

google_test.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

google.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

gpustack_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

gpustack.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

greenpt_test.go

feat: add GreenPT model provider (#17447)

2026-07-28 19:19:00 +08:00

greenpt.go

feat: add GreenPT model provider (#17447)

2026-07-28 19:19:00 +08:00

groq_test.go

Refactor(go-models): add token usage for groq (#17574)

2026-07-31 11:37:51 +08:00

groq.go

Refactor(go-models): add token usage for groq (#17574)

2026-07-31 11:37:51 +08:00

huaweicloud_test.go

feat(go-models): expand providers (SiliconFlow, Qiniu, Huawei Cloud, Jina) tool call support (#17241)

2026-07-22 21:27:58 +08:00

huaweicloud.go

fix(go-models): record provider token usage (#17423)

2026-07-27 17:16:50 +08:00

huggingface.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

hunyuan_test.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

hunyuan.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

jiekouai_test.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

jiekouai.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

jina_test.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

jina.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

llm_test.go

fix(go-agent): message double (#17353)

2026-07-24 19:23:51 +08:00

llm.go

fix(go-agent): message double (#17353)

2026-07-24 19:23:51 +08:00

lmstudio.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

localai_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

localai.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

longcat_test.go

Refactor(go-models)/llm token usage for longcat (#17480)

2026-07-28 21:08:51 +08:00

longcat.go

Refactor(go-models)/llm token usage for longcat (#17480)

2026-07-28 21:08:51 +08:00

mineru_local.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

mineru.go

Fix: simplify verify go (#17397)

2026-07-27 13:54:36 +08:00

minimax_test.go

fix(models): surface MiniMax rate-limit and API errors instead of generic messages (#17292)

2026-07-24 09:54:08 +08:00

minimax.go

Go: add token usage for baidu, minimax, moonshot and mistral (#17413)

2026-07-27 18:04:36 +08:00

mistral_test.go

Go: add token usage for baidu, minimax, moonshot and mistral (#17413)

2026-07-27 18:04:36 +08:00

mistral.go

Go: add token usage for baidu, minimax, moonshot and mistral (#17413)

2026-07-27 18:04:36 +08:00

model_test_helpers_test.go

refactor(go-models): add unsupported model driver defaults (#15431)

2026-06-03 19:16:28 +08:00

model_test.go

Go: implement embed, rerank for PPIO provider (#17486)

2026-07-28 19:16:31 +08:00

model.go

Fix: align go provider apis with python apis (#16867)

2026-07-14 21:06:11 +08:00

modelscope_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

modelscope.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

moonshot_test.go

Go: add token usage for baidu, minimax, moonshot and mistral (#17413)

2026-07-27 18:04:36 +08:00

moonshot.go

Go: add token usage for baidu, minimax, moonshot and mistral (#17413)

2026-07-27 18:04:36 +08:00

n1n_test.go

fix(go-models): harden N1N default transport handling (#15351)

2026-06-02 13:40:10 +08:00

n1n.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

non_chat_usage_test.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

novita_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

novita.go

Go: add token usage for orcarouter, baichuan, cohere and novita (#17455)

2026-07-28 19:14:05 +08:00

nvidia_rerank_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

nvidia_test.go

fix: list model function for nvidia on python/go not returning current models (#17501)

2026-07-29 13:15:34 +08:00

nvidia.go

fix: list model function for nvidia on python/go not returning current models (#17501)

2026-07-29 13:15:34 +08:00

ollama_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

ollama.go

refactor: the request body build (#17286)

2026-07-23 19:12:58 +08:00

openai_api_compatible.go

Feat: OpenAI-API-Compatible (#17276)

2026-07-23 13:39:57 +08:00

openai_compatible_usage_test.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

openai_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

openai.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

openrouter_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

openrouter.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

orcarouter.go

Go: add token usage for orcarouter, baichuan, cohere and novita (#17455)

2026-07-28 19:14:05 +08:00

paddleocr_local.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

paddleocr.go

refactor: use the built-in max/min to simplify the code (#17059)

2026-07-24 15:33:02 +08:00

perplexity_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

perplexity.go

refactor: the request body build (#17286)

2026-07-23 19:12:58 +08:00

ppio_test.go

Go: implement embed, rerank for PPIO provider (#17486)

2026-07-28 19:16:31 +08:00

ppio.go

Go: implement embed, rerank for PPIO provider (#17486)

2026-07-28 19:16:31 +08:00

provider_response_usage_test.go

feat(go-llm): align provider responses and streaming usage (#17509)

2026-07-29 18:54:11 +08:00

qiniu_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

qiniu.go

fix(go-models): record provider token usage (#17423)

2026-07-27 17:16:50 +08:00

ragcon_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

ragcon.go

refactor: the request body build (#17286)

2026-07-23 19:12:58 +08:00

reasoning_family_provider_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

replicate_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

replicate.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

siliconflow_test.go

fix(go-models): record provider token usage (#17423)

2026-07-27 17:16:50 +08:00

siliconflow.go

fix(go-models): record provider token usage (#17423)

2026-07-27 17:16:50 +08:00

sse_scanner_buffer_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

stepfun.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

timeout_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

togetherai_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

togetherai.go

refactor: the request body build (#17286)

2026-07-23 19:12:58 +08:00

tokenhub_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

tokenhub.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

tokenpony_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

tokenpony.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

tool_call_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

types.go

Go: implement embed, rerank for PPIO provider (#17486)

2026-07-28 19:16:31 +08:00

upstage_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

upstage.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

vllm_rerank_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

vllm.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

volcengine_test.go

fix(go-models): record provider token usage (#17423)

2026-07-27 17:16:50 +08:00

volcengine.go

fix(go-models): record provider token usage (#17423)

2026-07-27 17:16:50 +08:00

voyage_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

voyage.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

xai_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

xai.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

xiaomi_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

xiaomi.go

refactor: the request body build (#17286)

2026-07-23 19:12:58 +08:00

xinference_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

xinference.go

refactor: the request body build (#17286)

2026-07-23 19:12:58 +08:00

xunfei_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

xunfei.go

Go: add tools for a lot of providers (#17341)

2026-07-24 19:33:38 +08:00

zhipu_ai_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

zhipu-ai_test.go

Go: add context to lots of interface (#17253)

2026-07-22 22:30:57 +08:00

zhipu-ai.go

refactor(go-models): share chat response handling (#17289)

2026-07-24 10:51:37 +08:00