refactor: Standardize configuration and environment variable access

This commit centralizes configuration and environment variable access across various modules by consistently utilizing getters from scripts/modules/config-manager.js. This replaces direct access to process.env and the global CONFIG object, leading to improved consistency, maintainability, testability, and better handling of session-specific configurations within the MCP context.

Key changes include:

- Centralized Getters: Replaced numerous instances of process.env.* and CONFIG.* with corresponding getter functions (e.g., getLogLevel, getMainModelId, getResearchMaxTokens, getMainTemperature, isApiKeySet, getDebugFlag, getDefaultSubtasks).

- Session Awareness: Ensured that the session object is passed to config getters where necessary, particularly within AI service calls (ai-services.js, add-task.js) and error handling (ai-services.js), allowing for session-specific environment overrides.

- API Key Checks: Standardized API key availability checks using isApiKeySet() instead of directly checking process.env.* (e.g., for Perplexity in commands.js and ai-services.js).

- Client Instantiation Cleanup: Removed now-redundant/obsolete local client instantiation functions (getAnthropicClient, getPerplexityClient) from ai-services.js and the global Anthropic client initialization from dependency-manager.js. Client creation should now rely on the config manager and factory patterns.

- Consistent Debug Flag Usage: Standardized calls to getDebugFlag() in commands.js, removing potentially unnecessary null arguments.

- Accurate Progress Calculation: Updated AI stream progress reporting (ai-services.js, add-task.js) to use getMainMaxTokens(session) for more accurate calculations.

- Minor Cleanup: Removed unused  import from scripts/modules/commands.js.

Specific module updates:

- :

  - Uses getLogLevel() instead of process.env.LOG_LEVEL.

- :

  - Replaced direct env/config access for model IDs, tokens, temperature, API keys, and default subtasks with appropriate getters.

  - Passed session to handleClaudeError.

  - Removed local getPerplexityClient and getAnthropicClient functions.

  - Updated progress calculations to use getMainMaxTokens(session).

- :

  - Uses isApiKeySet('perplexity') for API key checks.

  - Uses getDebugFlag() consistently for debug checks.

  - Removed unused  import.

- :

  - Removed global Anthropic client initialization.

- :

  - Uses config getters (getResearch..., getMain...) for Perplexity and Claude API call parameters, preserving customEnv override logic.

This refactoring also resolves a potential SyntaxError: Identifier 'getPerplexityClient' has already been declared by removing the duplicated/obsolete function definition previously present in ai-services.js.

scripts/modules/task-manager/get-subtasks-from-ai.js

@@ -6,6 +6,16 @@ import {
 	parseSubtasksFromText
 } from '../ai-services.js';
 
+// Import necessary config getters
+import {
+	getMainModelId,
+	getMainMaxTokens,
+	getMainTemperature,
+	getResearchModelId,
+	getResearchMaxTokens,
+	getResearchTemperature
+} from '../config-manager.js';
+
 /**
  * Call AI to generate subtasks based on a prompt
  * @param {string} prompt - The prompt to send to the AI
@@ -26,9 +36,9 @@ async function getSubtasksFromAI(
 
 		// Prepare API parameters
 		const apiParams = {
-			model: session?.env?.ANTHROPIC_MODEL || CONFIG.model,
-			max_tokens: session?.env?.MAX_TOKENS || CONFIG.maxTokens,
-			temperature: session?.env?.TEMPERATURE || CONFIG.temperature,
+			model: getMainModelId(session),
+			max_tokens: getMainMaxTokens(session),
+			temperature: getMainTemperature(session),
 			system:
 				'You are an AI assistant helping with task breakdown for software development.',
 			messages: [{ role: 'user', content: prompt }]
@@ -46,10 +56,7 @@ async function getSubtasksFromAI(
 				mcpLog.info('Using Perplexity AI for research-backed subtasks');
 			}
 
-			const perplexityModel =
-				process.env.PERPLEXITY_MODEL ||
-				session?.env?.PERPLEXITY_MODEL ||
-				'sonar-pro';
+			const perplexityModel = getResearchModelId(session);
 			const result = await perplexity.chat.completions.create({
 				model: perplexityModel,
 				messages: [
@@ -60,8 +67,8 @@ async function getSubtasksFromAI(
 					},
 					{ role: 'user', content: prompt }
 				],
-				temperature: session?.env?.TEMPERATURE || CONFIG.temperature,
-				max_tokens: session?.env?.MAX_TOKENS || CONFIG.maxTokens
+				temperature: getResearchTemperature(session),
+				max_tokens: getResearchMaxTokens(session)
 			});
 
 			responseText = result.choices[0].message.content;