feat: add Groq and Mistral providers and System Info sfn example#1202
feat: add Groq and Mistral providers and System Info sfn example#1202J926L wants to merge 1 commit intoyomorun:masterfrom
Conversation
|
|
Summary of ChangesHello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly expands the YoMo ecosystem by integrating two new large language model providers, Groq and Mistral, which broadens the range of AI models available for use. Concurrently, it introduces a practical serverless function example designed to monitor system resources on edge nodes, showcasing how YoMo can facilitate real-time infrastructure health monitoring through AI agents in distributed environments. Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces support for Groq and Mistral LLM providers and adds a new serverless function example for retrieving system information. The implementation of the new providers and their configuration is well-done and includes relevant tests. However, the new sfn-system-info example has some areas for improvement, particularly around handling default arguments and error logging. I've provided specific suggestions to enhance the robustness and clarity of the example code.
| var p LLMArguments | ||
| // deserialize the arguments from llm tool_call response | ||
| ctx.ReadLLMArguments(&p) |
There was a problem hiding this comment.
The LLMArguments struct is initialized with zero values, resulting in IncludeCPU and IncludeMemory being false by default. This contradicts the jsonschema description, which specifies default=true. If ctx.ReadLLMArguments is called without arguments, it will return an error, and the handler will proceed with the false values. To align with the documented behavior, you should initialize LLMArguments with the desired default values before reading arguments from the context.
| var p LLMArguments | |
| // deserialize the arguments from llm tool_call response | |
| ctx.ReadLLMArguments(&p) | |
| p := LLMArguments{ | |
| IncludeCPU: true, | |
| IncludeMemory: true, | |
| } | |
| // deserialize the arguments from llm tool_call response | |
| _ = ctx.ReadLLMArguments(&p) |
| if p.IncludeCPU { | ||
| percent, err := cpu.Percent(time.Second, false) | ||
| if err == nil && len(percent) > 0 { | ||
| res += fmt.Sprintf("- CPU Usage: %.2f%%\n", percent[0]) | ||
| } | ||
| } |
There was a problem hiding this comment.
Errors from cpu.Percent are silently ignored. While this is an example, it's good practice to demonstrate proper error handling. Consider logging the error if retrieving CPU usage fails, which provides better visibility for debugging.
if p.IncludeCPU {
percent, err := cpu.Percent(time.Second, false)
if err != nil {
slog.Warn("could not get CPU usage", "err", err)
} else if len(percent) > 0 {
res += fmt.Sprintf("- CPU Usage: %.2f%%\n", percent[0])
}
}| if p.IncludeMemory { | ||
| v, err := mem.VirtualMemory() | ||
| if err == nil { | ||
| res += fmt.Sprintf("- Memory Usage: %.2f%% (Used: %v MB, Total: %v MB)\n", | ||
| v.UsedPercent, v.Used/1024/1024, v.Total/1024/1024) | ||
| } | ||
| } |
There was a problem hiding this comment.
The error returned by mem.VirtualMemory is silently ignored. It's a good practice, even in examples, to handle or at least log errors. This makes the function more robust and easier to debug.
if p.IncludeMemory {
v, err := mem.VirtualMemory()
if err != nil {
slog.Warn("could not get memory usage", "err", err)
} else {
res += fmt.Sprintf("- Memory Usage: %.2f%% (Used: %v MB, Total: %v MB)\n",
v.UsedPercent, v.Used/1024/1024, v.Total/1024/1024)
}
}
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## master #1202 +/- ##
==========================================
- Coverage 48.09% 47.91% -0.19%
==========================================
Files 93 95 +2
Lines 5510 5552 +42
==========================================
+ Hits 2650 2660 +10
- Misses 2664 2696 +32
Partials 196 196 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
There was a problem hiding this comment.
Hi, thanks for your PR, Please don't commit this _example
3 participants
Description
This PR adds two new LLM providers and a practical Serverless LLM Function (sfn) example to the YoMo ecosystem:
New LLM Providers:
New Serverless LLM Function (sfn) Example:
Changes
Verification
=== RUN TestParseZipperAddr/Valid_address
=== RUN TestParseZipperAddr/Valid_address_of_localhost
�[2m3:12PM�[0m �[91mERR�[0m invalid zipper address, return default �[2maddr=�[0mlocalhost �[2mdefault=�[0mlocalhost:9000 �[2merr=�[0m"address localhost: missing port in address"
=== RUN TestParseZipperAddr/Invalid_address
�[2m3:12PM�[0m �[91mERR�[0m invalid zipper address, return default �[2maddr=�[0minvalid �[2mdefault=�[0mlocalhost:9000 �[2merr=�[0m"address invalid: missing port in address"
=== RUN TestParseZipperAddr/Localhost
=== RUN TestParseZipperAddr/Unspecified_IP
--- PASS: TestParseZipperAddr (0.00s)
--- PASS: TestParseZipperAddr/Valid_address (0.00s)
--- PASS: TestParseZipperAddr/Valid_address_of_localhost (0.00s)
--- PASS: TestParseZipperAddr/Invalid_address (0.00s)
--- PASS: TestParseZipperAddr/Localhost (0.00s)
--- PASS: TestParseZipperAddr/Unspecified_IP (0.00s)
=== RUN TestParseConfig
=== RUN TestParseConfig/Config_not_found
=== RUN TestParseConfig/Config_format_error
=== RUN TestParseConfig/Valid_config
=== RUN TestParseConfig/Default_server_address
=== RUN TestParseConfig/malformaled_config
--- PASS: TestParseConfig (0.00s)
--- PASS: TestParseConfig/Config_not_found (0.00s)
--- PASS: TestParseConfig/Config_format_error (0.00s)
--- PASS: TestParseConfig/Valid_config (0.00s)
--- PASS: TestParseConfig/Default_server_address (0.00s)
--- PASS: TestParseConfig/malformaled_config (0.00s)
=== RUN TestNewProviderFromConfig
=== RUN TestNewProviderFromConfig/openai
=== RUN TestNewProviderFromConfig/groq
=== RUN TestNewProviderFromConfig/mistral
--- PASS: TestNewProviderFromConfig (0.00s)
--- PASS: TestNewProviderFromConfig/openai (0.00s)
--- PASS: TestNewProviderFromConfig/groq (0.00s)
--- PASS: TestNewProviderFromConfig/mistral (0.00s)
=== RUN TestResponseWriter
--- PASS: TestResponseWriter (0.00s)
=== RUN TestOpSystemPrompt
=== RUN TestOpSystemPrompt/disabled
=== RUN TestOpSystemPrompt/overwrite_with_empty_system_prompt
=== RUN TestOpSystemPrompt/empty_system_prompt_should_not_overwrite
=== RUN TestOpSystemPrompt/overwrite_with_not_empty_system_prompt
=== RUN TestOpSystemPrompt/prefix_with_empty_system_prompt
=== RUN TestOpSystemPrompt/prefix_with_not_empty_system_prompt
=== RUN TestOpSystemPrompt/client_preferred_with_client_system_prompt
=== RUN TestOpSystemPrompt/client_preferred_without_client_system_prompt
=== RUN TestOpSystemPrompt/client_preferred_with_empty_system_prompt
--- PASS: TestOpSystemPrompt (0.00s)
--- PASS: TestOpSystemPrompt/disabled (0.00s)
--- PASS: TestOpSystemPrompt/overwrite_with_empty_system_prompt (0.00s)
--- PASS: TestOpSystemPrompt/empty_system_prompt_should_not_overwrite (0.00s)
--- PASS: TestOpSystemPrompt/overwrite_with_not_empty_system_prompt (0.00s)
--- PASS: TestOpSystemPrompt/prefix_with_empty_system_prompt (0.00s)
--- PASS: TestOpSystemPrompt/prefix_with_not_empty_system_prompt (0.00s)
--- PASS: TestOpSystemPrompt/client_preferred_with_client_system_prompt (0.00s)
--- PASS: TestOpSystemPrompt/client_preferred_without_client_system_prompt (0.00s)
--- PASS: TestOpSystemPrompt/client_preferred_with_empty_system_prompt (0.00s)
=== RUN TestServiceInvoke
=== RUN TestServiceInvoke/invoke_with_tool_call
[mock provider] request: {"model":"","messages":[{"role":"system","content":"this is a system prompt"},{"role":"user","content":"hi"}],"tools":[{"type":"function","function":{"name":"get_current_weather","parameters":null}}]}
[mock provider] request: {"model":"","messages":[{"role":"system","content":"this is a system prompt"},{"role":"user","content":"hi"},{"role":"assistant","tool_calls":[{"id":"call_abc123","type":"function","function":{"name":"get_current_weather","arguments":"{\n"location": "Boston, MA"\n}"}}]},{"role":"tool","content":"temperature: 31°C","tool_call_id":"call_abc123"}],"tools":[{"type":"function","function":{"name":"get_current_weather","parameters":null}}]}
=== RUN TestServiceInvoke/invoke_without_tool_call
[mock provider] request: {"model":"","messages":[{"role":"system","content":"this is a system prompt"},{"role":"user","content":"hi"}]}
--- PASS: TestServiceInvoke (0.00s)
--- PASS: TestServiceInvoke/invoke_with_tool_call (0.00s)
--- PASS: TestServiceInvoke/invoke_without_tool_call (0.00s)
=== RUN TestServiceChatCompletion
=== RUN TestServiceChatCompletion/chat_with_tool_call
[mock provider] request: {"model":"","messages":[{"role":"system","content":"this is a system prompt"},{"role":"user","content":"How is the weather today in Boston, MA?"}],"tools":[{"type":"function","function":{"name":"get_current_weather","parameters":null}}]}
[mock provider] request: {"model":"","messages":[{"role":"system","content":"this is a system prompt"},{"role":"user","content":"How is the weather today in Boston, MA?"},{"role":"assistant","tool_calls":[{"id":"call_abc123","type":"function","function":{"name":"get_current_weather","arguments":"{\n"location": "Boston, MA"\n}"}}]},{"role":"tool","content":"temperature: 31°C","tool_call_id":"call_abc123"}],"tools":[{"type":"function","function":{"name":"get_current_weather","parameters":null}}]}
=== RUN TestServiceChatCompletion/chat_without_tool_call
[mock provider] request: {"model":"","messages":[{"role":"system","content":"You are an assistant."},{"role":"user","content":"How are you"}],"tools":[{"type":"function","function":{"name":"get_current_weather","parameters":null}}]}
=== RUN TestServiceChatCompletion/chat_with_tool_call_in_stream
[mock provider] stream request: {"model":"","messages":[{"role":"system","content":"You are a weather assistant"},{"role":"user","content":"How is the weather today in Boston, MA?"}],"stream":true,"tools":[{"type":"function","function":{"name":"get_current_weather","parameters":null}}]}
[mock provider] stream request: {"model":"","messages":[{"role":"system","content":"You are a weather assistant"},{"role":"user","content":"How is the weather today in Boston, MA?"},{"role":"assistant","tool_calls":[{"index":0,"id":"call_9ctHOJqO3bYrpm2A6S7nHd5k","type":"function","function":{"name":"get_current_weather","arguments":"{"location":"Boston, MA"}"}}]},{"role":"tool","content":"temperature: 31°C","tool_call_id":"call_9ctHOJqO3bYrpm2A6S7nHd5k"}],"stream":true,"tools":[{"type":"function","function":{"name":"get_current_weather","parameters":null}}]}
=== RUN TestServiceChatCompletion/chat_without_tool_call_in_stream
[mock provider] stream request: {"model":"","messages":[{"role":"system","content":"You are a weather assistant"},{"role":"user","content":"How is the weather today in Boston, MA?"}],"stream":true,"tools":[{"type":"function","function":{"name":"get_current_weather","parameters":null}}]}
=== RUN TestServiceChatCompletion/deepseek-v3.2_stream_with_tools
[mock provider] stream request: {"model":"","messages":[{"role":"system","content":"You are a weather assistant"},{"role":"user","content":"how is the weather in tokyo?"}],"stream":true,"tools":[{"type":"function","function":{"name":"market-get-weather","parameters":null}}]}
[mock provider] stream request: {"model":"","messages":[{"role":"system","content":"You are a weather assistant"},{"role":"user","content":"how is the weather in tokyo?"},{"role":"assistant","tool_calls":[{"index":0,"id":"call_a6dea19b4490485bbdad7047","type":"function","function":{"name":"market-get-weather","arguments":"{"city": "Tokyo", "latitude": 35.6762, "longitude": 139.6503}"}}]},{"role":"tool","content":"temperature: 31°C","tool_call_id":"call_a6dea19b4490485bbdad7047"}],"stream":true,"tools":[{"type":"function","function":{"name":"market-get-weather","parameters":null}}]}
--- PASS: TestServiceChatCompletion (0.00s)
--- PASS: TestServiceChatCompletion/chat_with_tool_call (0.00s)
--- PASS: TestServiceChatCompletion/chat_without_tool_call (0.00s)
--- PASS: TestServiceChatCompletion/chat_with_tool_call_in_stream (0.00s)
--- PASS: TestServiceChatCompletion/chat_without_tool_call_in_stream (0.00s)
--- PASS: TestServiceChatCompletion/deepseek-v3.2_stream_with_tools (0.00s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai (cached)
=== RUN TestTimeoutCallSyncer
--- PASS: TestTimeoutCallSyncer (0.00s)
=== RUN TestCallSyncer
--- PASS: TestCallSyncer (0.00s)
=== RUN TestCaller
--- PASS: TestCaller (0.00s)
=== RUN TestMockCaller
--- PASS: TestMockCaller (0.00s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/caller (cached)
=== RUN TestMockProviderRequest
[mock provider] request: {"model":"","messages":[{"role":"user","content":"hi, llm bridge"}]}
[mock provider] stream request: {"model":"","messages":[{"role":"user","content":"hi, yomo"}]}
--- PASS: TestMockProviderRequest (0.00s)
=== RUN TestMockProvider
=== RUN TestMockProvider/Name()
=== RUN TestMockProvider/GetChatCompletions()
[mock provider] request: {"model":"gpt-4o-2024-05-13","messages":null}
=== RUN TestMockProvider/GetChatCompletionsStream()
[mock provider] stream request: {"model":"","messages":null}
--- PASS: TestMockProvider (0.00s)
--- PASS: TestMockProvider/Name() (0.00s)
--- PASS: TestMockProvider/GetChatCompletions() (0.00s)
--- PASS: TestMockProvider/GetChatCompletionsStream() (0.00s)
=== RUN TestProviders
=== RUN TestProviders/ListProviders
=== RUN TestProviders/GetProvider
=== RUN TestProviders/GetProvider/ok
=== RUN TestProviders/GetProvider/name_is_empty
=== RUN TestProviders/GetProvider/not_found
--- PASS: TestProviders (0.00s)
--- PASS: TestProviders/ListProviders (0.00s)
--- PASS: TestProviders/GetProvider (0.00s)
--- PASS: TestProviders/GetProvider/ok (0.00s)
--- PASS: TestProviders/GetProvider/name_is_empty (0.00s)
--- PASS: TestProviders/GetProvider/not_found (0.00s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/provider (cached)
? github.com/yomorun/yomo/pkg/bridge/ai/provider/anthropic [no test files]
=== RUN TestNewProvider
--- PASS: TestNewProvider (0.00s)
=== RUN TestAzureOpenAIProvider_Name
--- PASS: TestAzureOpenAIProvider_Name (0.00s)
=== RUN TestAzureOpenAIProvider_GetChatCompletions
provider_test.go:63: Post "https://yomo.openai.azure.com/openai/deployments/test/chat/completions?api-version=test-version": context deadline exceeded (Client.Timeout exceeded while awaiting headers)
provider_test.go:66: Post "https://yomo.openai.azure.com/openai/deployments/test/chat/completions?api-version=test-version": context deadline exceeded (Client.Timeout exceeded while awaiting headers)
--- PASS: TestAzureOpenAIProvider_GetChatCompletions (0.00s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/provider/azopenai (cached)
=== RUN TestAzureAIFoundryProvider_Name
--- PASS: TestAzureAIFoundryProvider_Name (0.00s)
=== RUN TestAzureOpenAIProvider_GetChatCompletions
--- PASS: TestAzureOpenAIProvider_GetChatCompletions (0.00s)
=== RUN TestNewProvider
--- PASS: TestNewProvider (0.00s)
=== RUN TestNewConfigFunction
--- PASS: TestNewConfigFunction (0.00s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/provider/azure-ai-foundry (cached)
=== RUN TestNewProvider
--- PASS: TestNewProvider (0.00s)
=== RUN TestCerebrasProvider_Name
--- PASS: TestCerebrasProvider_Name (0.00s)
=== RUN TestCerebrasProvider_GetChatCompletions
provider_test.go:48: error, status code: 401, status: 401 Unauthorized, message: %!s(), body: {"message":"Wrong API Key","type":"invalid_request_error","param":"api_key","code":"wrong_api_key"}
provider_test.go:52: error, status code: 401, status: 401 Unauthorized, message: %!s(), body: {"message":"Wrong API Key","type":"invalid_request_error","param":"api_key","code":"wrong_api_key"}
--- PASS: TestCerebrasProvider_GetChatCompletions (1.79s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/provider/cerebras (cached)
=== RUN TestNewProvider
�[2m3:12PM�[0m �[91mERR�[0m parameters are required �[2mcfEndpoint=�[0m"" �[2mapiKey=�[0m"" �[2mresource=�[0m"" �[2mdeploymentID=�[0m""
--- PASS: TestNewProvider (0.00s)
=== RUN TestName
--- PASS: TestName (0.00s)
=== RUN TestCloudflareAzureProvider_GetChatCompletions
provider_test.go:65: Post "https://facker.gateway.ai.cloudflare.com/v1/111111111111111111/ai-cc-test/azure-openai/test/test/chat/completions?api-version=test-version": EOF
provider_test.go:68: Post "https://facker.gateway.ai.cloudflare.com/v1/111111111111111111/ai-cc-test/azure-openai/test/test/chat/completions?api-version=test-version": EOF
--- PASS: TestCloudflareAzureProvider_GetChatCompletions (3.54s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/provider/cfazure (cached)
=== RUN TestCloudflareOpenAIProvider_Name
--- PASS: TestCloudflareOpenAIProvider_Name (0.00s)
=== RUN TestNewProvider
=== RUN TestNewProvider/with_parameters
=== RUN TestNewProvider/with_environment_variables
--- PASS: TestNewProvider (0.00s)
--- PASS: TestNewProvider/with_parameters (0.00s)
--- PASS: TestNewProvider/with_environment_variables (0.00s)
=== RUN TestCloudflareOpenAIProvider_GetChatCompletions
provider_test.go:70: Post "https://faker.gateway.ai.cloudflare.com/v1/111111111111111111/ai-cc-test/openai/chat/completions": EOF
provider_test.go:73: Post "https://faker.gateway.ai.cloudflare.com/v1/111111111111111111/ai-cc-test/openai/chat/completions": EOF
--- PASS: TestCloudflareOpenAIProvider_GetChatCompletions (3.44s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/provider/cfopenai (cached)
=== RUN TestDeepSeekProvider_Name
--- PASS: TestDeepSeekProvider_Name (0.00s)
=== RUN TestDeepSeekProvider_GetChatCompletions
provider_test.go:37: error, status code: 401, status: 401 Unauthorized, message: invalid character 'A' looking for beginning of value, body: Authentication Fails (governor)
provider_test.go:41: error, status code: 401, status: 401 Unauthorized, message: invalid character 'A' looking for beginning of value, body: Authentication Fails (governor)
--- PASS: TestDeepSeekProvider_GetChatCompletions (0.37s)
=== RUN TestDeepSeekProvider_GetChatCompletionsWithoutModel
provider_test.go:62: error, status code: 401, status: 401 Unauthorized, message: invalid character 'A' looking for beginning of value, body: Authentication Fails (governor)
provider_test.go:66: error, status code: 401, status: 401 Unauthorized, message: invalid character 'A' looking for beginning of value, body: Authentication Fails (governor)
--- PASS: TestDeepSeekProvider_GetChatCompletionsWithoutModel (0.05s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/provider/deepseek (cached)
? github.com/yomorun/yomo/pkg/bridge/ai/provider/gemini [no test files]
=== RUN TestGithubModelsProvider_Name
--- PASS: TestGithubModelsProvider_Name (0.00s)
=== RUN TestNewProvider
=== RUN TestNewProvider/with_parameters
=== RUN TestNewProvider/with_environment_variables
--- PASS: TestNewProvider (0.00s)
--- PASS: TestNewProvider/with_parameters (0.00s)
--- PASS: TestNewProvider/with_environment_variables (0.00s)
=== RUN TestGithubModelsProvider_GetChatCompletions
--- PASS: TestGithubModelsProvider_GetChatCompletions (2.53s)
=== RUN TestGithubModelsProvider_GetChatCompletionsStream
--- PASS: TestGithubModelsProvider_GetChatCompletionsStream (0.43s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/provider/githubmodels (cached)
? github.com/yomorun/yomo/pkg/bridge/ai/provider/groq [no test files]
? github.com/yomorun/yomo/pkg/bridge/ai/provider/mistral [no test files]
? github.com/yomorun/yomo/pkg/bridge/ai/provider/ollama [no test files]
=== RUN TestNewProvider
--- PASS: TestNewProvider (0.00s)
=== RUN TestOpenAIProvider_Name
--- PASS: TestOpenAIProvider_Name (0.00s)
=== RUN TestCloudflareOpenAIProvider_GetChatCompletions
provider_test.go:60: Post "https://api.openai.com/v1/chat/completions": context deadline exceeded (Client.Timeout exceeded while awaiting headers)
provider_test.go:63: Post "https://api.openai.com/v1/chat/completions": context deadline exceeded (Client.Timeout exceeded while awaiting headers)
--- PASS: TestCloudflareOpenAIProvider_GetChatCompletions (0.00s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/provider/openai (cached)
? github.com/yomorun/yomo/pkg/bridge/ai/provider/vertexai [no test files]
=== RUN TestVLlmProvider_Name
--- PASS: TestVLlmProvider_Name (0.00s)
=== RUN TestVLlmProvider_GetChatCompletions
provider_test.go:37: Post "http://127.0.0.1:8000/chat/completions": dial tcp 127.0.0.1:8000: connect: connection refused
provider_test.go:41: Post "http://127.0.0.1:8000/chat/completions": dial tcp 127.0.0.1:8000: connect: connection refused
--- PASS: TestVLlmProvider_GetChatCompletions (0.00s)
=== RUN TestVLlmProvider_GetChatCompletionsWithoutModel
provider_test.go:62: Post "http://127.0.0.1:8000/chat/completions": dial tcp 127.0.0.1:8000: connect: connection refused
provider_test.go:66: Post "http://127.0.0.1:8000/chat/completions": dial tcp 127.0.0.1:8000: connect: connection refused
--- PASS: TestVLlmProvider_GetChatCompletionsWithoutModel (0.00s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/provider/vllm (cached)
=== RUN TestXAIProvider_Name
--- PASS: TestXAIProvider_Name (0.00s)
=== RUN TestXAIProvider_GetChatCompletions
provider_test.go:41: Post "https://api.x.ai/v1/chat/completions": context deadline exceeded
provider_test.go:45: Post "https://api.x.ai/v1/chat/completions": context deadline exceeded
provider_test.go:53: Post "https://api.x.ai/v1/chat/completions": context deadline exceeded
provider_test.go:57: Post "https://api.x.ai/v1/chat/completions": context deadline exceeded
--- PASS: TestXAIProvider_GetChatCompletions (1.00s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/provider/xai (cached)
=== RUN TestRegister
--- PASS: TestRegister (0.00s)
PASS
ok github.com/yomorun/yomo/pkg/bridge/ai/register (cached) and all tests passed (including the new provider tests).