fix(tasks): Enable removing multiple tasks/subtasks via comma-separated IDs

- Refactors the core `removeTask` function (`task-manager/remove-task.js`) to accept and iterate over comma-separated task/subtask IDs.

- Updates dependency cleanup and file regeneration logic to run once after processing all specified IDs.

- Adjusts the `remove-task` CLI command (`commands.js`) description and confirmation prompt to handle multiple IDs correctly.

- Fixes a bug in the CLI confirmation prompt where task/subtask titles were not being displayed correctly.

- Updates the `remove_task` MCP tool description to reflect the new multi-ID capability.

This addresses the previously known issue where only the first ID in a comma-separated list was processed.

Closes #140

tasks/task_036.txt

@@ -1,6 +1,6 @@
 # Task ID: 36
 # Title: Add Ollama Support for AI Services as Claude Alternative
-# Status: pending
+# Status: deferred
 # Dependencies: None
 # Priority: medium
 # Description: Implement Ollama integration as an alternative to Claude for all main AI services, allowing users to run local language models instead of relying on cloud-based Claude API.

tasks/task_061.txt

@@ -1009,7 +1009,7 @@ When refactoring `sendChatWithContext` and related functions, ensure they align
 </info added on 2025-04-20T03:53:03.709Z>
 
 ## 18. Refactor Callers of AI Parsing Utilities [deferred]
-### Dependencies: 61.11,61.12,61.13,61.14,61.15,61.16,61.17,61.19
+### Dependencies: None
 ### Description: Update the code that calls `parseSubtasksFromText`, `parseTaskJsonResponse`, and `parseTasksFromCompletion` to instead directly handle the structured JSON output provided by `generateObjectService` (as the refactored AI calls will now use it).
 ### Details:
 
@@ -1588,7 +1588,7 @@ export async function streamOpenAITextSimplified(params) {
 </info added on 2025-04-27T05:39:31.942Z>
 
 ## 23. Implement Conditional Provider Logic in `ai-services-unified.js` [done]
-### Dependencies: 61.20,61.21,61.22,61.24,61.25,61.26,61.27,61.28,61.29,61.30,61.34
+### Dependencies: None
 ### Description: Implement logic within the functions of `ai-services-unified.js` (e.g., `generateTextService`, `generateObjectService`, `streamChatService`) to dynamically select and call the appropriate provider module (`anthropic.js`, `perplexity.js`, etc.) based on configuration (e.g., environment variables like `AI_PROVIDER` and `AI_MODEL` from `process.env` or `session.env`).
 ### Details:
 

tasks/tasks.json

@@ -2298,7 +2298,7 @@
       "id": 36,
       "title": "Add Ollama Support for AI Services as Claude Alternative",
       "description": "Implement Ollama integration as an alternative to Claude for all main AI services, allowing users to run local language models instead of relying on cloud-based Claude API.",
-      "status": "pending",
+      "status": "deferred",
       "dependencies": [],
       "priority": "medium",
       "details": "This task involves creating a comprehensive Ollama integration that can replace Claude across all main AI services in the application. Implementation should include:\n\n1. Create an OllamaService class that implements the same interface as the ClaudeService to ensure compatibility\n2. Add configuration options to specify Ollama endpoint URL (default: http://localhost:11434)\n3. Implement model selection functionality to allow users to choose which Ollama model to use (e.g., llama3, mistral, etc.)\n4. Handle prompt formatting specific to Ollama models, ensuring proper system/user message separation\n5. Implement proper error handling for cases where Ollama server is unavailable or returns errors\n6. Add fallback mechanism to Claude when Ollama fails or isn't configured\n7. Update the AI service factory to conditionally create either Claude or Ollama service based on configuration\n8. Ensure token counting and rate limiting are appropriately handled for Ollama models\n9. Add documentation for users explaining how to set up and use Ollama with the application\n10. Optimize prompt templates specifically for Ollama models if needed\n\nThe implementation should be toggled through a configuration option (useOllama: true/false) and should maintain all existing functionality currently provided by Claude.",
@@ -3193,9 +3193,7 @@
           "description": "Update the code that calls `parseSubtasksFromText`, `parseTaskJsonResponse`, and `parseTasksFromCompletion` to instead directly handle the structured JSON output provided by `generateObjectService` (as the refactored AI calls will now use it).",
           "details": "\n\n<info added on 2025-04-20T03:52:45.518Z>\nThe refactoring of callers to AI parsing utilities should align with the new configuration system. When updating these callers:\n\n1. Replace direct API key references with calls to the configuration system using `resolveEnvVariable` for sensitive credentials.\n\n2. Update model selection logic to use the centralized configuration from `.taskmasterconfig` via the getter functions in `config-manager.js`. For example:\n   ```javascript\n   // Old approach\n   const model = \"gpt-4\";\n   \n   // New approach\n   import { getModelForRole } from './config-manager';\n   const model = getModelForRole('parsing'); // or appropriate role\n   ```\n\n3. Similarly, replace hardcoded parameters with configuration-based values:\n   ```javascript\n   // Old approach\n   const maxTokens = 2000;\n   const temperature = 0.2;\n   \n   // New approach\n   import { getAIParameterValue } from './config-manager';\n   const maxTokens = getAIParameterValue('maxTokens', 'parsing');\n   const temperature = getAIParameterValue('temperature', 'parsing');\n   ```\n\n4. Ensure logging behavior respects the centralized logging configuration settings.\n\n5. When calling `generateObjectService`, pass the appropriate configuration context to ensure it uses the correct settings from the centralized configuration system.\n</info added on 2025-04-20T03:52:45.518Z>",
           "status": "deferred",
-          "dependencies": [
-            "61.11,61.12,61.13,61.14,61.15,61.16,61.17,61.19"
-          ],
+          "dependencies": [],
           "parentTaskId": 61
         },
         {
@@ -3242,9 +3240,7 @@
           "description": "Implement logic within the functions of `ai-services-unified.js` (e.g., `generateTextService`, `generateObjectService`, `streamChatService`) to dynamically select and call the appropriate provider module (`anthropic.js`, `perplexity.js`, etc.) based on configuration (e.g., environment variables like `AI_PROVIDER` and `AI_MODEL` from `process.env` or `session.env`).",
           "details": "\n\n<info added on 2025-04-20T03:52:13.065Z>\nThe unified service should now use the configuration manager for provider selection rather than directly accessing environment variables. Here's the implementation approach:\n\n1. Import the config-manager functions:\n```javascript\nconst { \n  getMainProvider, \n  getResearchProvider, \n  getFallbackProvider,\n  getModelForRole,\n  getProviderParameters\n} = require('./config-manager');\n```\n\n2. Implement provider selection based on context/role:\n```javascript\nfunction selectProvider(role = 'default', context = {}) {\n  // Try to get provider based on role or context\n  let provider;\n  \n  if (role === 'research') {\n    provider = getResearchProvider();\n  } else if (context.fallback) {\n    provider = getFallbackProvider();\n  } else {\n    provider = getMainProvider();\n  }\n  \n  // Dynamically import the provider module\n  return require(`./${provider}.js`);\n}\n```\n\n3. Update service functions to use this selection logic:\n```javascript\nasync function generateTextService(prompt, options = {}) {\n  const { role = 'default', ...otherOptions } = options;\n  const provider = selectProvider(role, options);\n  const model = getModelForRole(role);\n  const parameters = getProviderParameters(provider.name);\n  \n  return provider.generateText(prompt, { \n    model, \n    ...parameters,\n    ...otherOptions \n  });\n}\n```\n\n4. Implement fallback logic for service resilience:\n```javascript\nasync function executeWithFallback(serviceFunction, ...args) {\n  try {\n    return await serviceFunction(...args);\n  } catch (error) {\n    console.error(`Primary provider failed: ${error.message}`);\n    const fallbackProvider = require(`./${getFallbackProvider()}.js`);\n    return fallbackProvider[serviceFunction.name](...args);\n  }\n}\n```\n\n5. Add provider capability checking to prevent calling unsupported features:\n```javascript\nfunction checkProviderCapability(provider, capability) {\n  const capabilities = {\n    'anthropic': ['text', 'chat', 'stream'],\n    'perplexity': ['text', 'chat', 'stream', 'research'],\n    'openai': ['text', 'chat', 'stream', 'embedding', 'vision']\n    // Add other providers as needed\n  };\n  \n  return capabilities[provider]?.includes(capability) || false;\n}\n```\n</info added on 2025-04-20T03:52:13.065Z>",
           "status": "done",
-          "dependencies": [
-            "61.20,61.21,61.22,61.24,61.25,61.26,61.27,61.28,61.29,61.30,61.34"
-          ],
+          "dependencies": [],
           "parentTaskId": 61
         },
         {