feat: define AI plugin communication interface standard #825
+124
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Define standard interfaces for AI plugin communication: - AIRequest: model + prompt + config (following langchaingo pattern) - AIResponse: content + metadata - AICapabilities: plugin capability discovery - Standard plugin message format using existing ExtManager system - AI plugins identified via StoreKind.Categories: ["ai"]
- Add AI plugin detection in startPlugins() function - logs when AI plugins are started - Implement GetAIPlugins() method to filter stores by 'ai' category - Add SendAIRequest() and GetAICapabilities() methods with TODO for plugin communication - Add AI plugin example in extension.yaml with OpenAI configuration - Use existing ExtManager and StoreKind architecture - AI plugins follow same patterns as other plugins - Compatible with existing protobuf Categories field for plugin classification This provides the complete AI plugin integration foundation while maintaining unified plugin architecture.
AI plugins should be treated exactly like other plugins in the startup process. The ExtManager.Start() method handles all plugins uniformly - AI plugins are only distinguished by their Categories field, not by special startup logic. This maintains the unified plugin architecture principle.
- Change plugin name from 'atest-ai-openai' to 'atest-ext-ai' following naming convention - Remove specific OpenAI parameters and implementation details - Keep only the essential configuration matching other plugins format - AI plugin now follows exact same structure as atest-store-database - Only difference is the categories: ['ai'] field for classification
LinuxSuRen
requested changes
Sep 12, 2025
Signed-off-by: Zhiyuan Zhao(赵志远) <[email protected]>
|
LinuxSuRen
approved these changes
Sep 14, 2025
LinuxSuRen
added
enhancement
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What this PR does / why we need it:
This PR defines a standard communication interface for AI plugins within the existing unified plugin architecture. Instead of treating AI
plugins as special cases, they now use the same extension system as other plugins with category-based identification.