refactor(config): Standardize env var access and config getters

This commit focuses on standardizing configuration and API key access patterns across key modules as part of subtask 61.34.

Key changes include:

- Refactored `ai-services.js` to remove global AI clients and use `resolveEnvVariable` for API key checks. Client instantiation now relies on `getAnthropicClient`/`getPerplexityClient` accepting a session object.

- Refactored `task-manager.js` (`analyzeTaskComplexity` function) to use the unified `generateTextService` from `ai-services-unified.js`, removing direct AI client calls.

- Replaced direct `process.env` access for model parameters and other configurations (`PERPLEXITY_MODEL`, `CONFIG.*`) in `task-manager.js` with calls to the appropriate getters from `config-manager.js` (e.g., `getResearchModelId(session)`, `getMainMaxTokens(session)`).

- Ensured `utils.js` (`resolveEnvVariable`) correctly handles potentially undefined session objects.

- Updated function signatures where necessary to propagate the `session` object for correct context-aware configuration/key retrieval.

This moves towards the goal of using `ai-client-factory.js` and `ai-services-unified.js` as the standard pattern for AI interactions and centralizing configuration management through `config-manager.js`.

scripts/modules/task-manager/generate-subtask-prompt.js

@@ -0,0 +1,51 @@
+/**
+ * Generate a prompt for creating subtasks from a task
+ * @param {Object} task - The task to generate subtasks for
+ * @param {number} numSubtasks - Number of subtasks to generate
+ * @param {string} additionalContext - Additional context to include in the prompt
+ * @param {Object} taskAnalysis - Optional complexity analysis for the task
+ * @returns {string} - The generated prompt
+ */
+function generateSubtaskPrompt(
+	task,
+	numSubtasks,
+	additionalContext = '',
+	taskAnalysis = null
+) {
+	// Build the system prompt
+	const basePrompt = `You need to break down the following task into ${numSubtasks} specific subtasks that can be implemented one by one.
+
+Task ID: ${task.id}
+Title: ${task.title}
+Description: ${task.description || 'No description provided'}
+Current details: ${task.details || 'No details provided'}
+${additionalContext ? `\nAdditional context to consider: ${additionalContext}` : ''}
+${taskAnalysis ? `\nComplexity analysis: This task has a complexity score of ${taskAnalysis.complexityScore}/10.` : ''}
+${taskAnalysis && taskAnalysis.reasoning ? `\nReasoning for complexity: ${taskAnalysis.reasoning}` : ''}
+
+Subtasks should:
+1. Be specific and actionable implementation steps
+2. Follow a logical sequence
+3. Each handle a distinct part of the parent task
+4. Include clear guidance on implementation approach
+5. Have appropriate dependency chains between subtasks
+6. Collectively cover all aspects of the parent task
+
+Return exactly ${numSubtasks} subtasks with the following JSON structure:
+[
+  {
+    "id": 1,
+    "title": "First subtask title",
+    "description": "Detailed description",
+    "dependencies": [], 
+    "details": "Implementation details"
+  },
+  ...more subtasks...
+]
+
+Note on dependencies: Subtasks can depend on other subtasks with lower IDs. Use an empty array if there are no dependencies.`;
+
+	return basePrompt;
+}
+
+export default generateSubtaskPrompt;