ros/claude-task-master
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(tasks): Align add-task with unified AI service and add research flag

Browse Source
This commit is contained in:
Eyal Toledano
2025-04-24 01:59:41 -04:00
parent 90c6c1e587
commit be3f68e777
10 changed files with 351 additions and 404 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
tasks/task_061.txt
View File

@@ -712,7 +712,7 @@ When implementing the refactored research processing logic, ensure the following
- How to verify configuration is correctly loaded
</info added on 2025-04-20T03:55:20.433Z>
## 11. Refactor PRD Parsing to use generateObjectService [in-progress]
## 11. Refactor PRD Parsing to use generateObjectService [done]
### Dependencies: 61.23
### Description: Update PRD processing logic (callClaude, processClaudeResponse, handleStreamingRequest in ai-services.js) to use the new `generateObjectService` from `ai-services-unified.js` with an appropriate Zod schema.
### Details:
@@ -747,7 +747,7 @@ const result = await generateObjectService({
5. Ensure any default values previously hardcoded are now retrieved from the configuration system.
</info added on 2025-04-20T03:55:01.707Z>
## 12. Refactor Basic Subtask Generation to use generateObjectService [pending]
## 12. Refactor Basic Subtask Generation to use generateObjectService [cancelled]
### Dependencies: 61.23
### Description: Update the `generateSubtasks` function in `ai-services.js` to use the new `generateObjectService` from `ai-services-unified.js` with a Zod schema for the subtask array.
### Details:
@@ -798,7 +798,7 @@ The refactoring should leverage the new configuration system:
```
</info added on 2025-04-20T03:54:45.542Z>
## 13. Refactor Research Subtask Generation to use generateObjectService [pending]
## 13. Refactor Research Subtask Generation to use generateObjectService [cancelled]
### Dependencies: 61.23
### Description: Update the `generateSubtasksWithPerplexity` function in `ai-services.js` to first perform research (potentially keeping the Perplexity call separate or adapting it) and then use `generateObjectService` from `ai-services-unified.js` with research results included in the prompt.
### Details:
@@ -828,7 +828,7 @@ const { verbose } = getLoggingConfig();
5. Ensure the transition to generateObjectService maintains all existing functionality while leveraging the new configuration system
</info added on 2025-04-20T03:54:26.882Z>
## 14. Refactor Research Task Description Generation to use generateObjectService [pending]
## 14. Refactor Research Task Description Generation to use generateObjectService [cancelled]
### Dependencies: 61.23
### Description: Update the `generateTaskDescriptionWithPerplexity` function in `ai-services.js` to first perform research and then use `generateObjectService` from `ai-services-unified.js` to generate the structured task description.
### Details:
@@ -869,7 +869,7 @@ return generateObjectService({
5. Remove any hardcoded configuration values, ensuring all settings are retrieved from the centralized configuration system.
</info added on 2025-04-20T03:54:04.420Z>
## 15. Refactor Complexity Analysis AI Call to use generateObjectService [pending]
## 15. Refactor Complexity Analysis AI Call to use generateObjectService [cancelled]
### Dependencies: 61.23
### Description: Update the logic that calls the AI after using `generateComplexityAnalysisPrompt` in `ai-services.js` to use the new `generateObjectService` from `ai-services-unified.js` with a Zod schema for the complexity report.
### Details:
@@ -916,7 +916,7 @@ The complexity analysis AI call should be updated to align with the new configur
```
</info added on 2025-04-20T03:53:46.120Z>
## 16. Refactor Task Addition AI Call to use generateObjectService [pending]
## 16. Refactor Task Addition AI Call to use generateObjectService [cancelled]
### Dependencies: 61.23
### Description: Update the logic that calls the AI after using `_buildAddTaskPrompt` in `ai-services.js` to use the new `generateObjectService` from `ai-services-unified.js` with a Zod schema for the single task object.
### Details:
@@ -1276,7 +1276,7 @@ When testing the non-streaming `generateTextService` call in `updateSubtaskById`
</info added on 2025-04-22T06:35:14.892Z>
</info added on 2025-04-22T06:23:23.247Z>
## 20. Implement `anthropic.js` Provider Module using Vercel AI SDK [in-progress]
## 20. Implement `anthropic.js` Provider Module using Vercel AI SDK [done]
### Dependencies: None
### Description: Create and implement the `anthropic.js` module within `src/ai-providers/`. This module should contain functions to interact with the Anthropic API (streaming and non-streaming) using the **Vercel AI SDK**, adhering to the standardized input/output format defined for `ai-services-unified.js`.
### Details:
@@ -1813,9 +1813,45 @@ This separation ensures security best practices for credentials while centralizi
This piecemeal approach aims to establish the refactoring pattern before tackling the entire codebase.
</info added on 2025-04-20T06:58:36.731Z>
## 35. Review/Refactor MCP Direct Functions for Explicit Config Root Passing [done]
## 35. Refactor add-task.js for Unified AI Service & Config [done]
### Dependencies: None
### Description: Review all functions in mcp-server/src/core/direct-functions/*.js. Ensure that any calls made from these functions to getters in scripts/modules/config-manager.js (e.g., getMainProvider, getDefaultPriority, getLogLevel, etc.) explicitly pass the projectRoot (obtained from the args object, which is derived from the session context) as the first argument to the getter. This prevents the getters from incorrectly falling back to using findProjectRoot() based on the server's cwd when running in an MCP context. This is crucial for loading the correct .taskmasterconfig settings based on the user's project.
### Description: Replace direct AI calls (old `ai-services.js` helpers) with `generateObjectService` or `generateTextService` from `ai-services-unified.js`. Pass `role` and `session`. Remove direct config getter usage (from `config-manager.js`) for AI parameters; use unified service instead. Keep `getDefaultPriority` usage.
### Details:
## 36. Refactor analyze-task-complexity.js for Unified AI Service & Config [pending]
### Dependencies: None
### Description: Replace direct AI calls with `generateObjectService` from `ai-services-unified.js`. Pass `role` and `session`. Remove direct config getter usage (from `config-manager.js`) for AI parameters; use unified service instead. Keep config getters needed for report metadata (`getProjectName`, `getDefaultSubtasks`).
### Details:
## 37. Refactor expand-task.js for Unified AI Service & Config [pending]
### Dependencies: None
### Description: Replace direct AI calls (old `ai-services.js` helpers like `generateSubtasksWithPerplexity`) with `generateObjectService` from `ai-services-unified.js`. Pass `role` and `session`. Remove direct config getter usage (from `config-manager.js`) for AI parameters; use unified service instead. Keep `getDefaultSubtasks` usage.
### Details:
## 38. Refactor expand-all-tasks.js for Unified AI Helpers & Config [pending]
### Dependencies: None
### Description: Ensure this file correctly calls the refactored `getSubtasksFromAI` helper. Update config usage to only use `getDefaultSubtasks` from `config-manager.js` directly. AI interaction itself is handled by the helper.
### Details:
## 39. Refactor get-subtasks-from-ai.js for Unified AI Service & Config [pending]
### Dependencies: None
### Description: Replace direct AI calls (old `ai-services.js` helpers) with `generateObjectService` or `generateTextService` from `ai-services-unified.js`. Pass `role` and `session`. Remove direct config getter usage (from `config-manager.js`) for AI parameters; use unified service instead.
### Details:
## 40. Refactor update-task-by-id.js for Unified AI Service & Config [pending]
### Dependencies: None
### Description: Replace direct AI calls (old `ai-services.js` helpers) with `generateObjectService` or `generateTextService` from `ai-services-unified.js`. Pass `role` and `session`. Remove direct config getter usage (from `config-manager.js`) for AI parameters and fallback logic; use unified service instead. Keep `getDebugFlag`.
### Details:
## 41. Refactor update-tasks.js for Unified AI Service & Config [pending]
### Dependencies: None
### Description: Replace direct AI calls (old `ai-services.js` helpers) with `generateObjectService` or `generateTextService` from `ai-services-unified.js`. Pass `role` and `session`. Remove direct config getter usage (from `config-manager.js`) for AI parameters and fallback logic; use unified service instead. Keep `getDebugFlag`.
### Details:

72
tasks/tasks.json
View File

@@ -2874,7 +2874,7 @@
"title": "Refactor PRD Parsing to use generateObjectService",
"description": "Update PRD processing logic (callClaude, processClaudeResponse, handleStreamingRequest in ai-services.js) to use the new `generateObjectService` from `ai-services-unified.js` with an appropriate Zod schema.",
"details": "\n\n<info added on 2025-04-20T03:55:01.707Z>\nThe PRD parsing refactoring should align with the new configuration system architecture. When implementing this change:\n\n1. Replace direct environment variable access with `resolveEnvVariable` calls for API keys.\n\n2. Remove any hardcoded model names or parameters in the PRD processing functions. Instead, use the config-manager.js getters:\n - `getModelForRole('prd')` to determine the appropriate model\n - `getModelParameters('prd')` to retrieve temperature, maxTokens, etc.\n\n3. When constructing the generateObjectService call, ensure parameters are sourced from config:\n```javascript\nconst modelConfig = getModelParameters('prd');\nconst model = getModelForRole('prd');\n\nconst result = await generateObjectService({\n model,\n temperature: modelConfig.temperature,\n maxTokens: modelConfig.maxTokens,\n // other parameters as needed\n schema: prdSchema,\n // existing prompt/context parameters\n});\n```\n\n4. Update any logging to respect the logging configuration from config-manager (e.g., `isLoggingEnabled('ai')`)\n\n5. Ensure any default values previously hardcoded are now retrieved from the configuration system.\n</info added on 2025-04-20T03:55:01.707Z>",
"status": "in-progress",
"status": "done",
"dependencies": [
"61.23"
],
@@ -2885,7 +2885,7 @@
"title": "Refactor Basic Subtask Generation to use generateObjectService",
"description": "Update the `generateSubtasks` function in `ai-services.js` to use the new `generateObjectService` from `ai-services-unified.js` with a Zod schema for the subtask array.",
"details": "\n\n<info added on 2025-04-20T03:54:45.542Z>\nThe refactoring should leverage the new configuration system:\n\n1. Replace direct model references with calls to config-manager.js getters:\n ```javascript\n const { getModelForRole, getModelParams } = require('./config-manager');\n \n // Instead of hardcoded models/parameters:\n const model = getModelForRole('subtask-generator');\n const modelParams = getModelParams('subtask-generator');\n ```\n\n2. Update API key handling to use the resolveEnvVariable pattern:\n ```javascript\n const { resolveEnvVariable } = require('./utils');\n const apiKey = resolveEnvVariable('OPENAI_API_KEY');\n ```\n\n3. When calling generateObjectService, pass the configuration parameters:\n ```javascript\n const result = await generateObjectService({\n schema: subtasksArraySchema,\n prompt: subtaskPrompt,\n model: model,\n temperature: modelParams.temperature,\n maxTokens: modelParams.maxTokens,\n // Other parameters from config\n });\n ```\n\n4. Add error handling that respects logging configuration:\n ```javascript\n const { isLoggingEnabled } = require('./config-manager');\n \n try {\n // Generation code\n } catch (error) {\n if (isLoggingEnabled('errors')) {\n console.error('Subtask generation error:', error);\n }\n throw error;\n }\n ```\n</info added on 2025-04-20T03:54:45.542Z>",
"status": "pending",
"status": "cancelled",
"dependencies": [
"61.23"
],
@@ -2896,7 +2896,7 @@
"title": "Refactor Research Subtask Generation to use generateObjectService",
"description": "Update the `generateSubtasksWithPerplexity` function in `ai-services.js` to first perform research (potentially keeping the Perplexity call separate or adapting it) and then use `generateObjectService` from `ai-services-unified.js` with research results included in the prompt.",
"details": "\n\n<info added on 2025-04-20T03:54:26.882Z>\nThe refactoring should align with the new configuration system by:\n\n1. Replace direct environment variable access with `resolveEnvVariable` for API keys\n2. Use the config-manager.js getters to retrieve model parameters:\n - Replace hardcoded model names with `getModelForRole('research')`\n - Use `getParametersForRole('research')` to get temperature, maxTokens, etc.\n3. Implement proper error handling that respects the `getLoggingConfig()` settings\n4. Example implementation pattern:\n```javascript\nconst { getModelForRole, getParametersForRole, getLoggingConfig } = require('./config-manager');\nconst { resolveEnvVariable } = require('./environment-utils');\n\n// In the refactored function:\nconst researchModel = getModelForRole('research');\nconst { temperature, maxTokens } = getParametersForRole('research');\nconst apiKey = resolveEnvVariable('PERPLEXITY_API_KEY');\nconst { verbose } = getLoggingConfig();\n\n// Then use these variables in the API call configuration\n```\n5. Ensure the transition to generateObjectService maintains all existing functionality while leveraging the new configuration system\n</info added on 2025-04-20T03:54:26.882Z>",
"status": "pending",
"status": "cancelled",
"dependencies": [
"61.23"
],
@@ -2907,7 +2907,7 @@
"title": "Refactor Research Task Description Generation to use generateObjectService",
"description": "Update the `generateTaskDescriptionWithPerplexity` function in `ai-services.js` to first perform research and then use `generateObjectService` from `ai-services-unified.js` to generate the structured task description.",
"details": "\n\n<info added on 2025-04-20T03:54:04.420Z>\nThe refactoring should incorporate the new configuration management system:\n\n1. Update imports to include the config-manager:\n```javascript\nconst { getModelForRole, getParametersForRole } = require('./config-manager');\n```\n\n2. Replace any hardcoded model selections or parameters with config-manager calls:\n```javascript\n// Replace direct model references like:\n// const model = \"perplexity-model-7b-online\" \n// With:\nconst model = getModelForRole('research');\nconst parameters = getParametersForRole('research');\n```\n\n3. For API key handling, use the resolveEnvVariable pattern:\n```javascript\nconst apiKey = resolveEnvVariable('PERPLEXITY_API_KEY');\n```\n\n4. When calling generateObjectService, pass the configuration-derived parameters:\n```javascript\nreturn generateObjectService({\n prompt: researchResults,\n schema: taskDescriptionSchema,\n role: 'taskDescription',\n // Config-driven parameters will be applied within generateObjectService\n});\n```\n\n5. Remove any hardcoded configuration values, ensuring all settings are retrieved from the centralized configuration system.\n</info added on 2025-04-20T03:54:04.420Z>",
"status": "pending",
"status": "cancelled",
"dependencies": [
"61.23"
],
@@ -2918,7 +2918,7 @@
"title": "Refactor Complexity Analysis AI Call to use generateObjectService",
"description": "Update the logic that calls the AI after using `generateComplexityAnalysisPrompt` in `ai-services.js` to use the new `generateObjectService` from `ai-services-unified.js` with a Zod schema for the complexity report.",
"details": "\n\n<info added on 2025-04-20T03:53:46.120Z>\nThe complexity analysis AI call should be updated to align with the new configuration system architecture. When refactoring to use `generateObjectService`, implement the following changes:\n\n1. Replace direct model references with calls to the appropriate config getter:\n ```javascript\n const modelName = getComplexityAnalysisModel(); // Use the specific getter from config-manager.js\n ```\n\n2. Retrieve AI parameters from the config system:\n ```javascript\n const temperature = getAITemperature('complexityAnalysis');\n const maxTokens = getAIMaxTokens('complexityAnalysis');\n ```\n\n3. When constructing the call to `generateObjectService`, pass these configuration values:\n ```javascript\n const result = await generateObjectService({\n prompt,\n schema: complexityReportSchema,\n modelName,\n temperature,\n maxTokens,\n sessionEnv: session?.env\n });\n ```\n\n4. Ensure API key resolution uses the `resolveEnvVariable` helper:\n ```javascript\n // Don't hardcode API keys or directly access process.env\n // The generateObjectService should handle this internally with resolveEnvVariable\n ```\n\n5. Add logging configuration based on settings:\n ```javascript\n const enableLogging = getAILoggingEnabled('complexityAnalysis');\n if (enableLogging) {\n // Use the logging mechanism defined in the configuration\n }\n ```\n</info added on 2025-04-20T03:53:46.120Z>",
"status": "pending",
"status": "cancelled",
"dependencies": [
"61.23"
],
@@ -2929,7 +2929,7 @@
"title": "Refactor Task Addition AI Call to use generateObjectService",
"description": "Update the logic that calls the AI after using `_buildAddTaskPrompt` in `ai-services.js` to use the new `generateObjectService` from `ai-services-unified.js` with a Zod schema for the single task object.",
"details": "\n\n<info added on 2025-04-20T03:53:27.455Z>\nTo implement this refactoring, you'll need to:\n\n1. Replace direct AI calls with the new `generateObjectService` approach:\n ```javascript\n // OLD approach\n const aiResponse = await callLLM(prompt, modelName, temperature, maxTokens);\n const task = parseAIResponseToTask(aiResponse);\n \n // NEW approach using generateObjectService with config-manager\n import { generateObjectService } from '../services/ai-services-unified.js';\n import { getAIModelForRole, getAITemperature, getAIMaxTokens } from '../config/config-manager.js';\n import { taskSchema } from '../schemas/task-schema.js'; // Create this Zod schema for a single task\n \n const modelName = getAIModelForRole('taskCreation');\n const temperature = getAITemperature('taskCreation');\n const maxTokens = getAIMaxTokens('taskCreation');\n \n const task = await generateObjectService({\n prompt: _buildAddTaskPrompt(...),\n schema: taskSchema,\n modelName,\n temperature,\n maxTokens\n });\n ```\n\n2. Create a Zod schema for the task object in a new file `schemas/task-schema.js` that defines the expected structure.\n\n3. Ensure API key resolution uses the new pattern:\n ```javascript\n // This happens inside generateObjectService, but verify it uses:\n import { resolveEnvVariable } from '../config/config-manager.js';\n // Instead of direct process.env access\n ```\n\n4. Update any error handling to match the new service's error patterns.\n</info added on 2025-04-20T03:53:27.455Z>",
"status": "pending",
"status": "cancelled",
"dependencies": [
"61.23"
],
@@ -2973,7 +2973,7 @@
"title": "Implement `anthropic.js` Provider Module using Vercel AI SDK",
"description": "Create and implement the `anthropic.js` module within `src/ai-providers/`. This module should contain functions to interact with the Anthropic API (streaming and non-streaming) using the **Vercel AI SDK**, adhering to the standardized input/output format defined for `ai-services-unified.js`.",
"details": "\n\n<info added on 2025-04-24T02:54:40.326Z>\n- Use the `@ai-sdk/anthropic` package to implement the provider module. You can import the default provider instance with `import { anthropic } from '@ai-sdk/anthropic'`, or create a custom instance using `createAnthropic` if you need to specify custom headers, API key, or base URL (such as for beta features or proxying)[1][4].\n\n- To address persistent 'Not Found' errors, ensure the model name matches the latest Anthropic model IDs (e.g., `claude-3-haiku-20240307`, `claude-3-5-sonnet-20241022`). Model naming is case-sensitive and must match Anthropic's published versions[4][5].\n\n- If you require custom headers (such as for beta features), use the `createAnthropic` function and pass a `headers` object. For example:\n ```js\n import { createAnthropic } from '@ai-sdk/anthropic';\n const anthropic = createAnthropic({\n apiKey: process.env.ANTHROPIC_API_KEY,\n headers: { 'anthropic-beta': 'tools-2024-04-04' }\n });\n ```\n\n- For streaming and non-streaming support, the Vercel AI SDK provides both `generateText` (non-streaming) and `streamText` (streaming) functions. Use these with the Anthropic provider instance as the `model` parameter[5].\n\n- Example usage for non-streaming:\n ```js\n import { generateText } from 'ai';\n import { anthropic } from '@ai-sdk/anthropic';\n\n const result = await generateText({\n model: anthropic('claude-3-haiku-20240307'),\n messages: [{ role: 'user', content: [{ type: 'text', text: 'Hello!' }] }]\n });\n ```\n\n- Example usage for streaming:\n ```js\n import { streamText } from 'ai';\n import { anthropic } from '@ai-sdk/anthropic';\n\n const stream = await streamText({\n model: anthropic('claude-3-haiku-20240307'),\n messages: [{ role: 'user', content: [{ type: 'text', text: 'Hello!' }] }]\n });\n ```\n\n- Ensure that your implementation adheres to the standardized input/output format defined for `ai-services-unified.js`, mapping the SDK's response structure to your unified format.\n\n- If you continue to encounter 'Not Found' errors, verify:\n - The API key is valid and has access to the requested models.\n - The model name is correct and available to your Anthropic account.\n - Any required beta headers are included if using beta features or models[1].\n\n- Prefer direct provider instantiation with explicit headers and API key configuration for maximum compatibility and to avoid SDK-level abstraction issues[1].\n</info added on 2025-04-24T02:54:40.326Z>",
"status": "in-progress",
"status": "done",
"dependencies": [],
"parentTaskId": 61
},
@@ -3114,12 +3114,66 @@
},
{
"id": 35,
"title": "Review/Refactor MCP Direct Functions for Explicit Config Root Passing",
"description": "Review all functions in mcp-server/src/core/direct-functions/*.js. Ensure that any calls made from these functions to getters in scripts/modules/config-manager.js (e.g., getMainProvider, getDefaultPriority, getLogLevel, etc.) explicitly pass the projectRoot (obtained from the args object, which is derived from the session context) as the first argument to the getter. This prevents the getters from incorrectly falling back to using findProjectRoot() based on the server's cwd when running in an MCP context. This is crucial for loading the correct .taskmasterconfig settings based on the user's project.",
"title": "Refactor add-task.js for Unified AI Service & Config",
"description": "Replace direct AI calls (old `ai-services.js` helpers) with `generateObjectService` or `generateTextService` from `ai-services-unified.js`. Pass `role` and `session`. Remove direct config getter usage (from `config-manager.js`) for AI parameters; use unified service instead. Keep `getDefaultPriority` usage.",
"details": "",
"status": "done",
"dependencies": [],
"parentTaskId": 61
},
{
"id": 36,
"title": "Refactor analyze-task-complexity.js for Unified AI Service & Config",
"description": "Replace direct AI calls with `generateObjectService` from `ai-services-unified.js`. Pass `role` and `session`. Remove direct config getter usage (from `config-manager.js`) for AI parameters; use unified service instead. Keep config getters needed for report metadata (`getProjectName`, `getDefaultSubtasks`).",
"details": "",
"status": "pending",
"dependencies": [],
"parentTaskId": 61
},
{
"id": 37,
"title": "Refactor expand-task.js for Unified AI Service & Config",
"description": "Replace direct AI calls (old `ai-services.js` helpers like `generateSubtasksWithPerplexity`) with `generateObjectService` from `ai-services-unified.js`. Pass `role` and `session`. Remove direct config getter usage (from `config-manager.js`) for AI parameters; use unified service instead. Keep `getDefaultSubtasks` usage.",
"details": "",
"status": "pending",
"dependencies": [],
"parentTaskId": 61
},
{
"id": 38,
"title": "Refactor expand-all-tasks.js for Unified AI Helpers & Config",
"description": "Ensure this file correctly calls the refactored `getSubtasksFromAI` helper. Update config usage to only use `getDefaultSubtasks` from `config-manager.js` directly. AI interaction itself is handled by the helper.",
"details": "",
"status": "pending",
"dependencies": [],
"parentTaskId": 61
},
{
"id": 39,
"title": "Refactor get-subtasks-from-ai.js for Unified AI Service & Config",
"description": "Replace direct AI calls (old `ai-services.js` helpers) with `generateObjectService` or `generateTextService` from `ai-services-unified.js`. Pass `role` and `session`. Remove direct config getter usage (from `config-manager.js`) for AI parameters; use unified service instead.",
"details": "",
"status": "pending",
"dependencies": [],
"parentTaskId": 61
},
{
"id": 40,
"title": "Refactor update-task-by-id.js for Unified AI Service & Config",
"description": "Replace direct AI calls (old `ai-services.js` helpers) with `generateObjectService` or `generateTextService` from `ai-services-unified.js`. Pass `role` and `session`. Remove direct config getter usage (from `config-manager.js`) for AI parameters and fallback logic; use unified service instead. Keep `getDebugFlag`.",
"details": "",
"status": "pending",
"dependencies": [],
"parentTaskId": 61
},
{
"id": 41,
"title": "Refactor update-tasks.js for Unified AI Service & Config",
"description": "Replace direct AI calls (old `ai-services.js` helpers) with `generateObjectService` or `generateTextService` from `ai-services-unified.js`. Pass `role` and `session`. Remove direct config getter usage (from `config-manager.js`) for AI parameters and fallback logic; use unified service instead. Keep `getDebugFlag`.",
"details": "",
"status": "pending",
"dependencies": [],
"parentTaskId": 61
}
]
}