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/update-task-by-id.js

@@ -13,7 +13,16 @@ import {
 } from '../ui.js';
 
 import { _handleAnthropicStream } from '../ai-services.js';
-import { getDebugFlag } from '../config-manager.js';
+import {
+	getDebugFlag,
+	getMainModelId,
+	getMainMaxTokens,
+	getMainTemperature,
+	getResearchModelId,
+	getResearchMaxTokens,
+	getResearchTemperature,
+	isApiKeySet
+} from '../config-manager.js';
 import generateTaskFiles from './generate-task-files.js';
 
 /**
@@ -64,15 +73,10 @@ async function updateTaskById(
 			);
 		}
 
-		// Validate research flag
-		if (
-			useResearch &&
-			(!perplexity ||
-				!process.env.PERPLEXITY_API_KEY ||
-				session?.env?.PERPLEXITY_API_KEY)
-		) {
+		// Validate research flag and API key
+		if (useResearch && !isApiKeySet('perplexity', session)) {
 			report(
-				'Perplexity AI is not available. Falling back to Claude AI.',
+				'Perplexity AI research requested but API key is not set. Falling back to main AI.',
 				'warn'
 			);
 
@@ -274,7 +278,7 @@ The changes described in the prompt should be thoughtfully applied to make the t
 							session?.env?.PERPLEXITY_MODEL ||
 							'sonar-pro';
 						const result = await client.chat.completions.create({
-							model: perplexityModel,
+							model: getResearchModelId(session),
 							messages: [
 								{
 									role: 'system',
@@ -293,12 +297,8 @@ IMPORTANT: In the task JSON above, any subtasks with "status": "done" or "status
 Return only the updated task as a valid JSON object.`
 								}
 							],
-							temperature: parseFloat(
-								process.env.TEMPERATURE ||
-									session?.env?.TEMPERATURE ||
-									CONFIG.temperature
-							),
-							max_tokens: 8700
+							temperature: getResearchTemperature(session),
+							max_tokens: getResearchMaxTokens(session)
 						});
 
 						const responseText = result.choices[0].message.content;
@@ -343,9 +343,9 @@ Return only the updated task as a valid JSON object.`
 
 							// Use streaming API call
 							const stream = await client.messages.create({
-								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: systemPrompt,
 								messages: [
 									{
@@ -371,12 +371,13 @@ Return only the updated task as a valid JSON object.`
 								}
 								if (reportProgress) {
 									await reportProgress({
-										progress: (responseText.length / CONFIG.maxTokens) * 100
+										progress:
+											(responseText.length / getMainMaxTokens(session)) * 100
 									});
 								}
 								if (mcpLog) {
 									mcpLog.info(
-										`Progress: ${(responseText.length / CONFIG.maxTokens) * 100}%`
+										`Progress: ${(responseText.length / getMainMaxTokens(session)) * 100}%`
 									);
 								}
 							}
@@ -667,7 +668,7 @@ Return only the updated task as a valid JSON object.`
 				console.log('  2. Use a valid task ID with the --id parameter');
 			}
 
-			if (getDebugFlag()) {
+			if (getDebugFlag(session)) {
 				// Use getter
 				console.error(error);
 			}