HAL9000
9c71c8fa3b
- Implemented OllamaChatProvider to enable local Ollama model support. - Implemented MistralChatProvider to integrate with the Mistral API. - Added Behave BDD tests for both providers. - Updated dependencies: langchain-mistralai and ollama. - Updated provider exports to include the new providers. ISSUES CLOSED: #5257
72 lines
4.3 KiB
Gherkin
72 lines
4.3 KiB
Gherkin
Feature: Mistral chat provider coverage
|
|
As a maintainer integrating Mistral API support
|
|
I want unit-level Behave scenarios for the Mistral chat provider
|
|
So that the Mistral adapter stays documented and regression tested
|
|
|
|
@unit @providers @mistral
|
|
Scenario: Mistral provider instantiates ChatMistralAI with provided credentials
|
|
Given I have sample provider domain inputs
|
|
When I create a Mistral chat provider with API key "test-key-123" and model "mistral-large-latest"
|
|
And I request plan generation from the Mistral provider
|
|
Then the Mistral provider should construct ChatMistralAI with api key "test-key-123" and model "mistral-large-latest"
|
|
And the Mistral provider metadata should report name "mistral" and model "mistral-large-latest"
|
|
|
|
@unit @providers @mistral
|
|
Scenario: Mistral provider stubbed response reports metadata
|
|
Given I have sample provider domain inputs
|
|
And I create a Mistral chat provider with API key "test-key-123" and model "mistral-large-latest"
|
|
When I request plan generation from the Mistral provider
|
|
Then the Mistral provider response should contain no generated changes
|
|
And the Mistral provider response should report the requested model without errors
|
|
|
|
@unit @providers @mistral
|
|
Scenario: Mistral provider rejects missing API key
|
|
Given I have sample provider domain inputs
|
|
When I attempt to create a Mistral chat provider without an API key
|
|
Then the Mistral provider creation should fail with error containing "Mistral API key is required"
|
|
|
|
@unit @providers @mistral
|
|
Scenario: Mistral provider reads API key from environment variable
|
|
Given I have sample provider domain inputs
|
|
And I set the MISTRAL_API_KEY environment variable to "env-key-456"
|
|
When I create a Mistral chat provider without explicit API key and model "mistral-large-latest"
|
|
And I request plan generation from the Mistral provider
|
|
Then the Mistral provider should construct ChatMistralAI with api key "env-key-456" and model "mistral-large-latest"
|
|
|
|
@unit @providers @mistral
|
|
Scenario: Mistral provider forwards extra kwargs
|
|
Given I have sample provider domain inputs
|
|
And I set the Mistral provider extra kwargs "temperature=0.5,max_tokens=512"
|
|
When I create a Mistral chat provider with API key "test-key-123" and model "mistral-large-latest"
|
|
And I request plan generation from the Mistral provider
|
|
Then the Mistral provider should construct ChatMistralAI with api key "test-key-123" and model "mistral-large-latest"
|
|
And the Mistral provider should include kwargs "temperature=0.5,max_tokens=512" in the ChatMistralAI call
|
|
|
|
@unit @providers @mistral
|
|
Scenario: Mistral provider reports runtime errors
|
|
Given I have sample provider domain inputs
|
|
And I create a Mistral chat provider with API key "test-key-123" and model "mistral-large-latest"
|
|
And the plan generation graph raises RuntimeError "API rate limit exceeded"
|
|
When I request plan generation from the Mistral provider
|
|
Then the Mistral provider response should report error "API rate limit exceeded"
|
|
And the Mistral provider response should contain no generated changes
|
|
|
|
@unit @providers @mistral
|
|
Scenario: Mistral provider streaming yields workflow events
|
|
Given I have sample provider domain inputs
|
|
And the plan generation graph returns a generated change for "app/mistral.py"
|
|
And the plan generation graph emits streaming nodes "load_context,analyze_requirements,generate_plan,validate"
|
|
And I create a Mistral chat provider with API key "test-key-123" and model "mistral-large-latest"
|
|
When I stream plan generation from the Mistral provider
|
|
Then the Mistral provider streaming events should include nodes "load_context,analyze_requirements,generate_plan,validate"
|
|
And the Mistral provider streaming result should finish with a response containing 1 generated change
|
|
|
|
@unit @providers @mistral
|
|
Scenario: Mistral provider surfaces plan generation errors
|
|
Given I have sample provider domain inputs
|
|
And the plan generation graph raises ValueError "invalid request"
|
|
And I create a Mistral chat provider with API key "test-key-123" and model "mistral-large-latest"
|
|
When I request plan generation from the Mistral provider
|
|
Then the Mistral provider response should report error "invalid request"
|
|
And the Mistral provider response should contain no generated changes
|