fix(core): Implement Boundary-First Tag Resolution (#943)

* refactor(context): Standardize tag and projectRoot handling across all task tools This commit unifies context management by adopting a boundary-first resolution strategy. All task-scoped tools now resolve `tag` and `projectRoot` at their entry point and forward these values to the underlying direct functions. This approach centralizes context logic, ensuring consistent behavior and enhanced flexibility in multi-tag environments. * fix(tag): Clean up tag handling in task functions and sync process This commit refines the handling of the `tag` parameter across multiple functions, ensuring consistent context management. The `tag` is now passed more efficiently in `listTasksDirect`, `setTaskStatusDirect`, and `syncTasksToReadme`, improving clarity and reducing redundancy. Additionally, a TODO comment has been added in `sync-readme.js` to address future tag support enhancements. * feat(tag): Implement Boundary-First Tag Resolution for consistent tag handling This commit introduces Boundary-First Tag Resolution in the task manager, ensuring consistent and deterministic tag handling across CLI and MCP. This change resolves potential race conditions and improves the reliability of tag-specific operations. Additionally, the `expandTask` function has been updated to use the resolved tag when writing JSON, enhancing data integrity during task updates. * chore(biome): formatting * fix(expand-task): Update writeJSON call to use tag instead of resolvedTag * fix(commands): Enhance complexity report path resolution and task initialization `resolveComplexityReportPath` function to streamline output path generation based on tag context and user-defined output. - Improved clarity and maintainability of command handling by centralizing path resolution logic. * Fix: unknown currentTag * fix(task-manager): Update generateTaskFiles calls to include tag and projectRoot parameters This commit modifies the `moveTask` and `updateSubtaskById` functions to pass the `tag` and `projectRoot` parameters to the `generateTaskFiles` function. This ensures that task files are generated with the correct context when requested, enhancing consistency in task management operations. * fix(commands): Refactor tag handling and complexity report path resolution This commit updates the `registerCommands` function to utilize `taskMaster.getCurrentTag()` for consistent tag retrieval across command actions. It also enhances the initialization of `TaskMaster` by passing the tag directly, improving clarity and maintainability. The complexity report path resolution is streamlined to ensure correct file naming based on the current tag context. * fix(task-master): Update complexity report path expectations in tests This commit modifies the `initTaskMaster` test to expect a valid string for the complexity report path, ensuring it matches the expected file naming convention. This change enhances test reliability by verifying the correct output format when the path is generated. * fix(set-task-status): Enhance logging and tag resolution in task status updates This commit improves the logging output in the `registerSetTaskStatusTool` function to include the tag context when setting task statuses. It also updates the tag handling by resolving the tag using the `resolveTag` utility, ensuring that the correct tag is used when updating task statuses. Additionally, the `setTaskStatus` function is modified to remove the tag parameter from the `readJSON` and `writeJSON` calls, streamlining the data handling process. * fix(commands, expand-task, task-manager): Add complexity report option and enhance path handling This commit introduces a new `--complexity-report` option in the `registerCommands` function, allowing users to specify a custom path for the complexity report. The `expandTask` function is updated to accept the `complexityReportPath` from the context, ensuring it is utilized correctly during task expansion. Additionally, the `setTaskStatus` function now includes the `tag` parameter in the `readJSON` and `writeJSON` calls, improving task status updates with proper context. The `initTaskMaster` function is also modified to create parent directories for output paths, enhancing file handling robustness. * fix(expand-task): Add complexityReportPath to context for task expansion tests This commit updates the test for the `expandTask` function by adding the `complexityReportPath` to the context object. This change ensures that the complexity report path is correctly utilized in the test, aligning with recent enhancements to complexity report handling in the task manager. * chore: implement suggested changes * fix(parse-prd): Clarify tag parameter description for task organization Updated the documentation for the `tag` parameter in the `parse-prd.js` file to provide a clearer context on its purpose for organizing tasks into separate task lists. * Fix Inconsistent tag resolution pattern. * fix: Enhance complexity report path handling with tag support This commit updates various functions to incorporate the `tag` parameter when resolving complexity report paths. The `expandTaskDirect`, `resolveComplexityReportPath`, and related tools now utilize the current tag context, improving consistency in task management. Additionally, the complexity report path is now correctly passed through the context in the `expand-task` and `set-task-status` tools, ensuring accurate report retrieval based on the active tag. * Updated the JSDoc for the `tag` parameter in the `show-task.js` file. * Remove redundant comment on tag parameter in readJSON call * Remove unused import for getTagAwareFilePath * Add missed complexityReportPath to args for task expansion * fix(tests): Enhance research tests with tag-aware functionality This commit updates the `research.test.js` file to improve the testing of the `performResearch` function by incorporating tag-aware functionality. Key changes include mocking the `findProjectRoot` to return a valid path, enhancing the `ContextGatherer` and `FuzzyTaskSearch` mocks, and adding comprehensive tests for tag parameter handling in various scenarios. The tests now cover passing different tag values, ensuring correct behavior when tags are provided, undefined, or null, and validating the integration of tags in task discovery and context gathering processes. * Remove unused import for * fix: Refactor complexity report path handling and improve argument destructuring This commit enhances the `expandTaskDirect` function by improving the destructuring of arguments for better readability. It also updates the `analyze.js` and `analyze-task-complexity.js` files to utilize the new `resolveComplexityReportOutputPath` function, ensuring tag-aware resolution of output paths. Additionally, logging has been added to provide clarity on the report path being used. * test: Add complexity report tag isolation tests and improve path handling This commit introduces a new test file for complexity report tag isolation, ensuring that different tags maintain separate complexity reports. It enhances the existing tests in `analyze-task-complexity.test.js` by updating expectations to use `expect.stringContaining` for file paths, improving robustness against path changes. The new tests cover various scenarios, including path resolution and report generation for both master and feature tags, ensuring no cross-tag contamination occurs. * Update scripts/modules/task-manager/list-tasks.js Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * Update scripts/modules/task-manager/list-tasks.js Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * test(complexity-report): Fix tag slugification in filename expectations - Update mocks to use slugifyTagForFilePath for cross-platform compatibility - Replace raw tag values with slugified versions in expected filenames - Fix test expecting 'feature/user-auth-v2' to expect 'feature-user-auth-v2' - Align test with actual filename generation logic that sanitizes special chars --------- Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2025-07-18 19:05:04 +02:00
parent 0451ebcc32
commit fd005c4c54
95 changed files with 3899 additions and 590 deletions
--- a/scripts/modules/task-manager/add-subtask.js
+++ b/scripts/modules/task-manager/add-subtask.js
@@ -12,6 +12,8 @@ import generateTaskFiles from './generate-task-files.js';
 * @param {Object} newSubtaskData - Data for creating a new subtask (used if existingTaskId is null)
 * @param {boolean} generateFiles - Whether to regenerate task files after adding the subtask
 * @param {Object} context - Context object containing projectRoot and tag information
+ * @param {string} context.projectRoot - Project root path
+ * @param {string} context.tag - Tag for the task
 * @returns {Object} The newly created or converted subtask
 */
 async function addSubtask(
@@ -22,13 +24,12 @@ async function addSubtask(
 	generateFiles = true,
 	context = {}
 ) {
+	const { projectRoot, tag } = context;
 	try {
 		log('info', `Adding subtask to parent task ${parentId}...`);

-		const currentTag =
-			context.tag || getCurrentTag(context.projectRoot) || 'master';
 		// Read the existing tasks with proper context
-		const data = readJSON(tasksPath, context.projectRoot, currentTag);
+		const data = readJSON(tasksPath, projectRoot, tag);
 		if (!data || !data.tasks) {
 			throw new Error(`Invalid or missing tasks file at ${tasksPath}`);
 		}
@@ -139,7 +140,7 @@ async function addSubtask(
 		}

 		// Write the updated tasks back to the file with proper context
-		writeJSON(tasksPath, data, context.projectRoot, currentTag);
+		writeJSON(tasksPath, data, projectRoot, tag);

 		// Generate task files if requested
 		if (generateFiles) {
--- a/scripts/modules/task-manager/add-task.js
+++ b/scripts/modules/task-manager/add-task.js
@@ -22,8 +22,7 @@ import {
 	truncate,
 	ensureTagMetadata,
 	performCompleteTagMigration,
-	markMigrationForNotice,
-	getCurrentTag
+	markMigrationForNotice
 } from '../utils.js';
 import { generateObjectService } from '../ai-services-unified.js';
 import { getDefaultPriority } from '../config-manager.js';
@@ -93,7 +92,7 @@ function getAllTasks(rawData) {
 * @param {string} [context.projectRoot] - Project root path (for MCP/env fallback)
 * @param {string} [context.commandName] - The name of the command being executed (for telemetry)
 * @param {string} [context.outputType] - The output type ('cli' or 'mcp', for telemetry)
- * @param {string} [tag] - Tag for the task (optional)
+ * @param {string} [context.tag] - Tag for the task (optional)
 * @returns {Promise<object>} An object containing newTaskId and telemetryData
 */
 async function addTask(
@@ -104,10 +103,10 @@ async function addTask(
 	context = {},
 	outputFormat = 'text', // Default to text for CLI
 	manualTaskData = null,
-	useResearch = false,
-	tag = null
+	useResearch = false
 ) {
-	const { session, mcpLog, projectRoot, commandName, outputType } = context;
+	const { session, mcpLog, projectRoot, commandName, outputType, tag } =
+		context;
 	const isMCP = !!mcpLog;

 	// Create a consistent logFn object regardless of context
@@ -224,7 +223,7 @@ async function addTask(

 	try {
 		// Read the existing tasks - IMPORTANT: Read the raw data without tag resolution
-		let rawData = readJSON(tasksPath, projectRoot); // No tag parameter
+		let rawData = readJSON(tasksPath, projectRoot, tag); // No tag parameter

 		// Handle the case where readJSON returns resolved data with _rawTaggedData
 		if (rawData && rawData._rawTaggedData) {
@@ -279,8 +278,7 @@ async function addTask(
 		}

 		// Use the provided tag, or the current active tag, or default to 'master'
-		const targetTag =
-			tag || context.tag || getCurrentTag(projectRoot) || 'master';
+		const targetTag = tag;

 		// Ensure the target tag exists
 		if (!rawData[targetTag]) {
@@ -389,7 +387,7 @@ async function addTask(
 			report(`Generating task data with AI with prompt:\n${prompt}`, 'info');

 			// --- Use the new ContextGatherer ---
-			const contextGatherer = new ContextGatherer(projectRoot);
+			const contextGatherer = new ContextGatherer(projectRoot, tag);
 			const gatherResult = await contextGatherer.gather({
 				semanticQuery: prompt,
 				dependencyTasks: numericDependencies,
--- a/scripts/modules/task-manager/analyze-task-complexity.js
+++ b/scripts/modules/task-manager/analyze-task-complexity.js
@@ -19,6 +19,7 @@ import {
 	COMPLEXITY_REPORT_FILE,
 	LEGACY_TASKS_FILE
 } from '../../../src/constants/paths.js';
+import { resolveComplexityReportOutputPath } from '../../../src/utils/path-utils.js';
 import { ContextGatherer } from '../utils/contextGatherer.js';
 import { FuzzyTaskSearch } from '../utils/fuzzyTaskSearch.js';
 import { flattenTasksWithSubtasks } from '../utils.js';
@@ -71,6 +72,7 @@ Do not include any explanatory text, markdown formatting, or code block markers
 * @param {string|number} [options.threshold] - Complexity threshold
 * @param {boolean} [options.research] - Use research role
 * @param {string} [options.projectRoot] - Project root path (for MCP/env fallback).
+ * @param {string} [options.tag] - Tag for the task
 * @param {string} [options.id] - Comma-separated list of task IDs to analyze specifically
 * @param {number} [options.from] - Starting task ID in a range to analyze
 * @param {number} [options.to] - Ending task ID in a range to analyze
@@ -84,7 +86,6 @@ Do not include any explanatory text, markdown formatting, or code block markers
 async function analyzeTaskComplexity(options, context = {}) {
 	const { session, mcpLog } = context;
 	const tasksPath = options.file || LEGACY_TASKS_FILE;
-	const outputPath = options.output || COMPLEXITY_REPORT_FILE;
 	const thresholdScore = parseFloat(options.threshold || '5');
 	const useResearch = options.research || false;
 	const projectRoot = options.projectRoot;
@@ -109,6 +110,13 @@ async function analyzeTaskComplexity(options, context = {}) {
 		}
 	};

+	// Resolve output path using tag-aware resolution
+	const outputPath = resolveComplexityReportOutputPath(
+		options.output,
+		{ projectRoot, tag },
+		reportLog
+	);
+
 	if (outputFormat === 'text') {
 		console.log(
 			chalk.blue(
@@ -220,7 +228,7 @@ async function analyzeTaskComplexity(options, context = {}) {
 		let gatheredContext = '';
 		if (originalData && originalData.tasks.length > 0) {
 			try {
-				const contextGatherer = new ContextGatherer(projectRoot);
+				const contextGatherer = new ContextGatherer(projectRoot, tag);
 				const allTasksFlat = flattenTasksWithSubtasks(originalData.tasks);
 				const fuzzySearch = new FuzzyTaskSearch(
 					allTasksFlat,
@@ -535,7 +543,7 @@ async function analyzeTaskComplexity(options, context = {}) {
 				}
 			}

-			// Merge with existing report
+			// Merge with existing report - only keep entries from the current tag
 			let finalComplexityAnalysis = [];

 			if (existingReport && Array.isArray(existingReport.complexityAnalysis)) {
@@ -544,10 +552,14 @@ async function analyzeTaskComplexity(options, context = {}) {
 					complexityAnalysis.map((item) => item.taskId)
 				);

-				// Keep existing entries that weren't in this analysis run
+				// Keep existing entries that weren't in this analysis run AND belong to the current tag
+				// We determine tag membership by checking if the task ID exists in the current tag's tasks
+				const currentTagTaskIds = new Set(tasksData.tasks.map((t) => t.id));
 				const existingEntriesNotAnalyzed =
 					existingReport.complexityAnalysis.filter(
-						(item) => !analyzedTaskIds.has(item.taskId)
+						(item) =>
+							!analyzedTaskIds.has(item.taskId) &&
+							currentTagTaskIds.has(item.taskId) // Only keep entries for tasks in current tag
 					);

 				// Combine with new analysis
@@ -557,7 +569,7 @@ async function analyzeTaskComplexity(options, context = {}) {
 				];

 				reportLog(
-					`Merged ${complexityAnalysis.length} new analyses with ${existingEntriesNotAnalyzed.length} existing entries`,
+					`Merged ${complexityAnalysis.length} new analyses with ${existingEntriesNotAnalyzed.length} existing entries from current tag`,
 					'info'
 				);
 			} else {
--- a/scripts/modules/task-manager/clear-subtasks.js
+++ b/scripts/modules/task-manager/clear-subtasks.js
@@ -11,6 +11,8 @@ import { displayBanner } from '../ui.js';
 * @param {string} tasksPath - Path to the tasks.json file
 * @param {string} taskIds - Task IDs to clear subtasks from
 * @param {Object} context - Context object containing projectRoot and tag
+ * @param {string} [context.projectRoot] - Project root path
+ * @param {string} [context.tag] - Tag for the task
 */
 function clearSubtasks(tasksPath, taskIds, context = {}) {
 	const { projectRoot, tag } = context;
--- a/scripts/modules/task-manager/expand-all-tasks.js
+++ b/scripts/modules/task-manager/expand-all-tasks.js
@@ -20,6 +20,8 @@ import boxen from 'boxen';
 * @param {Object} context - Context object containing session and mcpLog.
 * @param {Object} [context.session] - Session object from MCP.
 * @param {Object} [context.mcpLog] - MCP logger object.
+ * @param {string} [context.projectRoot] - Project root path
+ * @param {string} [context.tag] - Tag for the task
 * @param {string} [outputFormat='text'] - Output format ('text' or 'json'). MCP calls should use 'json'.
 * @returns {Promise<{success: boolean, expandedCount: number, failedCount: number, skippedCount: number, tasksToExpand: number, telemetryData: Array<Object>}>} - Result summary.
 */
@@ -32,12 +34,7 @@ async function expandAllTasks(
 	context = {},
 	outputFormat = 'text' // Assume text default for CLI
 ) {
-	const {
-		session,
-		mcpLog,
-		projectRoot: providedProjectRoot,
-		tag: contextTag
-	} = context;
+	const { session, mcpLog, projectRoot: providedProjectRoot, tag } = context;
 	const isMCPCall = !!mcpLog; // Determine if called from MCP

 	const projectRoot = providedProjectRoot || findProjectRoot();
@@ -79,7 +76,7 @@ async function expandAllTasks(

 	try {
 		logger.info(`Reading tasks from ${tasksPath}`);
-		const data = readJSON(tasksPath, projectRoot, contextTag);
+		const data = readJSON(tasksPath, projectRoot, tag);
 		if (!data || !data.tasks) {
 			throw new Error(`Invalid tasks data in ${tasksPath}`);
 		}
@@ -129,7 +126,7 @@ async function expandAllTasks(
 					numSubtasks,
 					useResearch,
 					additionalContext,
-					{ ...context, projectRoot, tag: data.tag || contextTag }, // Pass the whole context object with projectRoot and resolved tag
+					{ ...context, projectRoot, tag: data.tag || tag }, // Pass the whole context object with projectRoot and resolved tag
 					force
 				);
 				expandedCount++;
--- a/scripts/modules/task-manager/expand-task.js
+++ b/scripts/modules/task-manager/expand-task.js
@@ -290,6 +290,8 @@ function parseSubtasksFromText(
 * @param {Object} context - Context object containing session and mcpLog.
 * @param {Object} [context.session] - Session object from MCP.
 * @param {Object} [context.mcpLog] - MCP logger object.
+ * @param {string} [context.projectRoot] - Project root path
+ * @param {string} [context.tag] - Tag for the task
 * @param {boolean} [force=false] - If true, replace existing subtasks; otherwise, append.
 * @returns {Promise<Object>} The updated parent task object with new subtasks.
 * @throws {Error} If task not found, AI service fails, or parsing fails.
@@ -303,7 +305,13 @@ async function expandTask(
 	context = {},
 	force = false
 ) {
-	const { session, mcpLog, projectRoot: contextProjectRoot, tag } = context;
+	const {
+		session,
+		mcpLog,
+		projectRoot: contextProjectRoot,
+		tag,
+		complexityReportPath
+	} = context;
 	const outputFormat = mcpLog ? 'json' : 'text';

 	// Determine projectRoot: Use from context if available, otherwise derive from tasksPath
@@ -350,7 +358,7 @@ async function expandTask(
 		// --- Context Gathering ---
 		let gatheredContext = '';
 		try {
-			const contextGatherer = new ContextGatherer(projectRoot);
+			const contextGatherer = new ContextGatherer(projectRoot, tag);
 			const allTasksFlat = flattenTasksWithSubtasks(data.tasks);
 			const fuzzySearch = new FuzzyTaskSearch(allTasksFlat, 'expand-task');
 			const searchQuery = `${task.title} ${task.description}`;
@@ -379,17 +387,10 @@ async function expandTask(
 		// --- Complexity Report Integration ---
 		let finalSubtaskCount;
 		let complexityReasoningContext = '';
-
-		// Use tag-aware complexity report path
-		const complexityReportPath = getTagAwareFilePath(
-			COMPLEXITY_REPORT_FILE,
-			tag,
-			projectRoot
-		);
 		let taskAnalysis = null;

 		logger.info(
-			`Looking for complexity report at: ${complexityReportPath}${tag && tag !== 'master' ? ` (tag-specific for '${tag}')` : ''}`
+			`Looking for complexity report at: ${complexityReportPath}${tag !== 'master' ? ` (tag-specific for '${tag}')` : ''}`
 		);

 		try {
--- a/scripts/modules/task-manager/generate-task-files.js
+++ b/scripts/modules/task-manager/generate-task-files.js
@@ -12,16 +12,20 @@ import { getDebugFlag } from '../config-manager.js';
 * @param {string} tasksPath - Path to the tasks.json file
 * @param {string} outputDir - Output directory for task files
 * @param {Object} options - Additional options (mcpLog for MCP mode, projectRoot, tag)
+ * @param {string} [options.projectRoot] - Project root path
+ * @param {string} [options.tag] - Tag for the task
+ * @param {Object} [options.mcpLog] - MCP logger object
 * @returns {Object|undefined} Result object in MCP mode, undefined in CLI mode
 */
 function generateTaskFiles(tasksPath, outputDir, options = {}) {
 	try {
 		const isMcpMode = !!options?.mcpLog;
+		const { projectRoot, tag } = options;

 		// 1. Read the raw data structure, ensuring we have all tags.
 		// We call readJSON without a specific tag to get the resolved default view,
 		// which correctly contains the full structure in `_rawTaggedData`.
-		const resolvedData = readJSON(tasksPath, options.projectRoot);
+		const resolvedData = readJSON(tasksPath, projectRoot, tag);
 		if (!resolvedData) {
 			throw new Error(`Could not read or parse tasks file: ${tasksPath}`);
 		}
@@ -29,13 +33,10 @@ function generateTaskFiles(tasksPath, outputDir, options = {}) {
 		const rawData = resolvedData._rawTaggedData || resolvedData;

 		// 2. Determine the target tag we need to generate files for.
-		const targetTag = options.tag || resolvedData.tag || 'master';
-		const tagData = rawData[targetTag];
+		const tagData = rawData[tag];

 		if (!tagData || !tagData.tasks) {
-			throw new Error(
-				`Tag '${targetTag}' not found or has no tasks in the data.`
-			);
+			throw new Error(`Tag '${tag}' not found or has no tasks in the data.`);
 		}
 		const tasksForGeneration = tagData.tasks;

@@ -46,15 +47,15 @@ function generateTaskFiles(tasksPath, outputDir, options = {}) {

 		log(
 			'info',
-			`Preparing to regenerate ${tasksForGeneration.length} task files for tag '${targetTag}'`
+			`Preparing to regenerate ${tasksForGeneration.length} task files for tag '${tag}'`
 		);

 		// 3. Validate dependencies using the FULL, raw data structure to prevent data loss.
 		validateAndFixDependencies(
 			rawData, // Pass the entire object with all tags
 			tasksPath,
-			options.projectRoot,
-			targetTag // Provide the current tag context for the operation
+			projectRoot,
+			tag // Provide the current tag context for the operation
 		);

 		const allTasksInTag = tagData.tasks;
@@ -66,14 +67,14 @@ function generateTaskFiles(tasksPath, outputDir, options = {}) {
 			const files = fs.readdirSync(outputDir);
 			// Tag-aware file patterns: master -> task_001.txt, other tags -> task_001_tagname.txt
 			const masterFilePattern = /^task_(\d+)\.txt$/;
-			const taggedFilePattern = new RegExp(`^task_(\\d+)_${targetTag}\\.txt$`);
+			const taggedFilePattern = new RegExp(`^task_(\\d+)_${tag}\\.txt$`);

 			const orphanedFiles = files.filter((file) => {
 				let match = null;
 				let fileTaskId = null;

 				// Check if file belongs to current tag
-				if (targetTag === 'master') {
+				if (tag === 'master') {
 					match = file.match(masterFilePattern);
 					if (match) {
 						fileTaskId = parseInt(match[1], 10);
@@ -94,7 +95,7 @@ function generateTaskFiles(tasksPath, outputDir, options = {}) {
 			if (orphanedFiles.length > 0) {
 				log(
 					'info',
-					`Found ${orphanedFiles.length} orphaned task files to remove for tag '${targetTag}'`
+					`Found ${orphanedFiles.length} orphaned task files to remove for tag '${tag}'`
 				);
 				orphanedFiles.forEach((file) => {
 					const filePath = path.join(outputDir, file);
@@ -108,13 +109,13 @@ function generateTaskFiles(tasksPath, outputDir, options = {}) {
 		}

 		// Generate task files for the target tag
-		log('info', `Generating individual task files for tag '${targetTag}'...`);
+		log('info', `Generating individual task files for tag '${tag}'...`);
 		tasksForGeneration.forEach((task) => {
 			// Tag-aware file naming: master -> task_001.txt, other tags -> task_001_tagname.txt
 			const taskFileName =
-				targetTag === 'master'
+				tag === 'master'
 					? `task_${task.id.toString().padStart(3, '0')}.txt`
-					: `task_${task.id.toString().padStart(3, '0')}_${targetTag}.txt`;
+					: `task_${task.id.toString().padStart(3, '0')}_${tag}.txt`;

 			const taskPath = path.join(outputDir, taskFileName);

@@ -174,7 +175,7 @@ function generateTaskFiles(tasksPath, outputDir, options = {}) {

 		log(
 			'success',
-			`All ${tasksForGeneration.length} tasks for tag '${targetTag}' have been generated into '${outputDir}'.`
+			`All ${tasksForGeneration.length} tasks for tag '${tag}' have been generated into '${outputDir}'.`
 		);

 		if (isMcpMode) {
--- a/scripts/modules/task-manager/list-tasks.js
+++ b/scripts/modules/task-manager/list-tasks.js
@@ -26,8 +26,9 @@ import {
 * @param {string} reportPath - Path to the complexity report
 * @param {boolean} withSubtasks - Whether to show subtasks
 * @param {string} outputFormat - Output format (text or json)
- * @param {string} tag - Optional tag to override current tag resolution
- * @param {Object} context - Optional context object containing projectRoot and other options
+ * @param {Object} context - Context object (required)
+ * @param {string} context.projectRoot - Project root path
+ * @param {string} context.tag - Tag for the task
 * @returns {Object} - Task list result for json format
 */
 function listTasks(
@@ -36,18 +37,18 @@ function listTasks(
 	reportPath = null,
 	withSubtasks = false,
 	outputFormat = 'text',
-	tag = null,
 	context = {}
 ) {
+	const { projectRoot, tag } = context;
 	try {
 		// Extract projectRoot from context if provided
-		const projectRoot = context.projectRoot || null;
 		const data = readJSON(tasksPath, projectRoot, tag); // Pass projectRoot to readJSON
 		if (!data || !data.tasks) {
 			throw new Error(`No valid tasks found in ${tasksPath}`);
 		}

 		// Add complexity scores to tasks if report exists
+		// `reportPath` is already tag-aware (resolved at the CLI boundary).
 		const complexityReport = readComplexityReport(reportPath);
 		// Apply complexity scores to tasks
 		if (complexityReport && complexityReport.complexityAnalysis) {
--- a/scripts/modules/task-manager/move-task.js
+++ b/scripts/modules/task-manager/move-task.js
@@ -1,11 +1,5 @@
 import path from 'path';
-import {
-	log,
-	readJSON,
-	writeJSON,
-	getCurrentTag,
-	setTasksForTag
-} from '../utils.js';
+import { log, readJSON, writeJSON, setTasksForTag } from '../utils.js';
 import { isTaskDependentOn } from '../task-manager.js';
 import generateTaskFiles from './generate-task-files.js';

@@ -27,6 +21,7 @@ async function moveTask(
 	generateFiles = false,
 	options = {}
 ) {
+	const { projectRoot, tag } = options;
 	// Check if we have comma-separated IDs (batch move)
 	const sourceIds = sourceId.split(',').map((id) => id.trim());
 	const destinationIds = destinationId.split(',').map((id) => id.trim());
@@ -53,7 +48,10 @@ async function moveTask(

 		// Generate files once at the end if requested
 		if (generateFiles) {
-			await generateTaskFiles(tasksPath, path.dirname(tasksPath));
+			await generateTaskFiles(tasksPath, path.dirname(tasksPath), {
+				tag: tag,
+				projectRoot: projectRoot
+			});
 		}

 		return {
@@ -64,7 +62,7 @@ async function moveTask(

 	// Single move logic
 	// Read the raw data without tag resolution to preserve tagged structure
-	let rawData = readJSON(tasksPath, options.projectRoot); // No tag parameter
+	let rawData = readJSON(tasksPath, projectRoot, tag);

 	// Handle the case where readJSON returns resolved data with _rawTaggedData
 	if (rawData && rawData._rawTaggedData) {
@@ -72,27 +70,19 @@ async function moveTask(
 		rawData = rawData._rawTaggedData;
 	}

-	// Determine the current tag
-	const currentTag =
-		options.tag || getCurrentTag(options.projectRoot) || 'master';
-
 	// Ensure the tag exists in the raw data
-	if (
-		!rawData ||
-		!rawData[currentTag] ||
-		!Array.isArray(rawData[currentTag].tasks)
-	) {
+	if (!rawData || !rawData[tag] || !Array.isArray(rawData[tag].tasks)) {
 		throw new Error(
-			`Invalid tasks file or tag "${currentTag}" not found at ${tasksPath}`
+			`Invalid tasks file or tag "${tag}" not found at ${tasksPath}`
 		);
 	}

 	// Get the tasks for the current tag
-	const tasks = rawData[currentTag].tasks;
+	const tasks = rawData[tag].tasks;

 	log(
 		'info',
-		`Moving task/subtask ${sourceId} to ${destinationId} (tag: ${currentTag})`
+		`Moving task/subtask ${sourceId} to ${destinationId} (tag: ${tag})`
 	);

 	// Parse source and destination IDs
@@ -116,14 +106,17 @@ async function moveTask(
 	}

 	// Update the data structure with the modified tasks
-	rawData[currentTag].tasks = tasks;
+	rawData[tag].tasks = tasks;

 	// Always write the data object, never the _rawTaggedData directly
 	// The writeJSON function will filter out _rawTaggedData automatically
-	writeJSON(tasksPath, rawData, options.projectRoot, currentTag);
+	writeJSON(tasksPath, rawData, options.projectRoot, tag);

 	if (generateFiles) {
-		await generateTaskFiles(tasksPath, path.dirname(tasksPath));
+		await generateTaskFiles(tasksPath, path.dirname(tasksPath), {
+			tag: tag,
+			projectRoot: projectRoot
+		});
 	}

 	return result;
--- a/scripts/modules/task-manager/parse-prd.js
+++ b/scripts/modules/task-manager/parse-prd.js
@@ -76,7 +76,7 @@ async function parsePRD(prdPath, tasksPath, numTasks, options = {}) {
 	const outputFormat = isMCP ? 'json' : 'text';

 	// Use the provided tag, or the current active tag, or default to 'master'
-	const targetTag = tag || getCurrentTag(projectRoot) || 'master';
+	const targetTag = tag;

 	const logFn = mcpLog
 		? mcpLog
--- a/scripts/modules/task-manager/remove-subtask.js
+++ b/scripts/modules/task-manager/remove-subtask.js
@@ -9,6 +9,8 @@ import generateTaskFiles from './generate-task-files.js';
 * @param {boolean} convertToTask - Whether to convert the subtask to a standalone task
 * @param {boolean} generateFiles - Whether to regenerate task files after removing the subtask
 * @param {Object} context - Context object containing projectRoot and tag information
+ * @param {string} [context.projectRoot] - Project root path
+ * @param {string} [context.tag] - Tag for the task
 * @returns {Object|null} The removed subtask if convertToTask is true, otherwise null
 */
 async function removeSubtask(
@@ -18,11 +20,12 @@ async function removeSubtask(
 	generateFiles = true,
 	context = {}
 ) {
+	const { projectRoot, tag } = context;
 	try {
 		log('info', `Removing subtask ${subtaskId}...`);

 		// Read the existing tasks with proper context
-		const data = readJSON(tasksPath, context.projectRoot, context.tag);
+		const data = readJSON(tasksPath, projectRoot, tag);
 		if (!data || !data.tasks) {
 			throw new Error(`Invalid or missing tasks file at ${tasksPath}`);
 		}
@@ -103,7 +106,7 @@ async function removeSubtask(
 		}

 		// Write the updated tasks back to the file with proper context
-		writeJSON(tasksPath, data, context.projectRoot, context.tag);
+		writeJSON(tasksPath, data, projectRoot, tag);

 		// Generate task files if requested
 		if (generateFiles) {
--- a/scripts/modules/task-manager/remove-task.js
+++ b/scripts/modules/task-manager/remove-task.js
@@ -9,6 +9,8 @@ import taskExists from './task-exists.js';
 * @param {string} tasksPath - Path to the tasks file
 * @param {string} taskIds - Comma-separated string of task/subtask IDs to remove (e.g., '5,6.1,7')
 * @param {Object} context - Context object containing projectRoot and tag information
+ * @param {string} [context.projectRoot] - Project root path
+ * @param {string} [context.tag] - Tag for the task
 * @returns {Object} Result object with success status, messages, and removed task info
 */
 async function removeTask(tasksPath, taskIds, context = {}) {
@@ -32,7 +34,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {

 	try {
 		// Read the tasks file ONCE before the loop, preserving the full tagged structure
-		const rawData = readJSON(tasksPath, projectRoot); // Read raw data
+		const rawData = readJSON(tasksPath, projectRoot, tag); // Read raw data
 		if (!rawData) {
 			throw new Error(`Could not read tasks file at ${tasksPath}`);
 		}
@@ -40,19 +42,18 @@ async function removeTask(tasksPath, taskIds, context = {}) {
 		// Use the full tagged data if available, otherwise use the data as is
 		const fullTaggedData = rawData._rawTaggedData || rawData;

-		const currentTag = tag || rawData.tag || 'master';
-		if (!fullTaggedData[currentTag] || !fullTaggedData[currentTag].tasks) {
-			throw new Error(`Tag '${currentTag}' not found or has no tasks.`);
+		if (!fullTaggedData[tag] || !fullTaggedData[tag].tasks) {
+			throw new Error(`Tag '${tag}' not found or has no tasks.`);
 		}

-		const tasks = fullTaggedData[currentTag].tasks; // Work with tasks from the correct tag
+		const tasks = fullTaggedData[tag].tasks; // Work with tasks from the correct tag

 		const tasksToDeleteFiles = []; // Collect IDs of main tasks whose files should be deleted

 		for (const taskId of taskIdsToRemove) {
 			// Check if the task ID exists *before* attempting removal
 			if (!taskExists(tasks, taskId)) {
-				const errorMsg = `Task with ID ${taskId} in tag '${currentTag}' not found or already removed.`;
+				const errorMsg = `Task with ID ${taskId} in tag '${tag}' not found or already removed.`;
 				results.errors.push(errorMsg);
 				results.success = false; // Mark overall success as false if any error occurs
 				continue; // Skip to the next ID
@@ -94,7 +95,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
 					parentTask.subtasks.splice(subtaskIndex, 1);

 					results.messages.push(
-						`Successfully removed subtask ${taskId} from tag '${currentTag}'`
+						`Successfully removed subtask ${taskId} from tag '${tag}'`
 					);
 				}
 				// Handle main task removal
@@ -102,9 +103,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
 					const taskIdNum = parseInt(taskId, 10);
 					const taskIndex = tasks.findIndex((t) => t.id === taskIdNum);
 					if (taskIndex === -1) {
-						throw new Error(
-							`Task with ID ${taskId} not found in tag '${currentTag}'`
-						);
+						throw new Error(`Task with ID ${taskId} not found in tag '${tag}'`);
 					}

 					// Store the task info before removal
@@ -116,7 +115,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
 					tasks.splice(taskIndex, 1);

 					results.messages.push(
-						`Successfully removed task ${taskId} from tag '${currentTag}'`
+						`Successfully removed task ${taskId} from tag '${tag}'`
 					);
 				}
 			} catch (innerError) {
@@ -139,7 +138,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
 			);

 			// Update the tasks in the current tag of the full data structure
-			fullTaggedData[currentTag].tasks = tasks;
+			fullTaggedData[tag].tasks = tasks;

 			// Remove dependencies from all tags
 			for (const tagName in fullTaggedData) {
@@ -171,7 +170,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
 			}

 			// Save the updated raw data structure
-			writeJSON(tasksPath, fullTaggedData, projectRoot, currentTag);
+			writeJSON(tasksPath, fullTaggedData, projectRoot, tag);

 			// Delete task files AFTER saving tasks.json
 			for (const taskIdNum of tasksToDeleteFiles) {
@@ -196,7 +195,7 @@ async function removeTask(tasksPath, taskIds, context = {}) {
 			try {
 				await generateTaskFiles(tasksPath, path.dirname(tasksPath), {
 					projectRoot,
-					tag: currentTag
+					tag
 				});
 				results.messages.push('Task files regenerated successfully.');
 			} catch (genError) {
--- a/scripts/modules/task-manager/research.js
+++ b/scripts/modules/task-manager/research.js
@@ -35,6 +35,7 @@ import {
 * @param {boolean} [options.includeProjectTree] - Include project file tree
 * @param {string} [options.detailLevel] - Detail level: 'low', 'medium', 'high'
 * @param {string} [options.projectRoot] - Project root directory
+ * @param {string} [options.tag] - Tag for the task
 * @param {boolean} [options.saveToFile] - Whether to save results to file (MCP mode)
 * @param {Object} [context] - Execution context
 * @param {Object} [context.session] - MCP session object
@@ -59,6 +60,7 @@ async function performResearch(
 		includeProjectTree = false,
 		detailLevel = 'medium',
 		projectRoot: providedProjectRoot,
+		tag,
 		saveToFile = false
 	} = options;

@@ -101,7 +103,7 @@ async function performResearch(

 	try {
 		// Initialize context gatherer
-		const contextGatherer = new ContextGatherer(projectRoot);
+		const contextGatherer = new ContextGatherer(projectRoot, tag);

 		// Auto-discover relevant tasks using fuzzy search to supplement provided tasks
 		let finalTaskIds = [...taskIds]; // Start with explicitly provided tasks
@@ -114,7 +116,7 @@ async function performResearch(
 				'tasks',
 				'tasks.json'
 			);
-			const tasksData = await readJSON(tasksPath, projectRoot);
+			const tasksData = await readJSON(tasksPath, projectRoot, tag);

 			if (tasksData && tasksData.tasks && tasksData.tasks.length > 0) {
 				// Flatten tasks to include subtasks for fuzzy search
@@ -769,10 +771,7 @@ async function handleSaveToTask(
 			return;
 		}

-		// Validate ID exists - use tag from context
-		const { getCurrentTag } = await import('../utils.js');
-		const tag = context.tag || getCurrentTag(projectRoot) || 'master';
-		const data = readJSON(tasksPath, projectRoot, tag);
+		const data = readJSON(tasksPath, projectRoot, context.tag);
 		if (!data || !data.tasks) {
 			console.log(chalk.red('❌ No valid tasks found.'));
 			return;
@@ -806,7 +805,7 @@ async function handleSaveToTask(
 				trimmedTaskId,
 				conversationThread,
 				false, // useResearch = false for simple append
-				{ ...context, tag },
+				context,
 				'text'
 			);

@@ -833,7 +832,7 @@ async function handleSaveToTask(
 				taskIdNum,
 				conversationThread,
 				false, // useResearch = false for simple append
-				{ ...context, tag },
+				context,
 				'text',
 				true // appendMode = true
 			);
--- a/scripts/modules/task-manager/set-task-status.js
+++ b/scripts/modules/task-manager/set-task-status.js
@@ -7,7 +7,6 @@ import {
 	readJSON,
 	writeJSON,
 	findTaskById,
-	getCurrentTag,
 	ensureTagMetadata
 } from '../utils.js';
 import { displayBanner } from '../ui.js';
@@ -26,16 +25,13 @@ import {
 * @param {string} taskIdInput - Task ID(s) to update
 * @param {string} newStatus - New status
 * @param {Object} options - Additional options (mcpLog for MCP mode, projectRoot for tag resolution)
- * @param {string} tag - Optional tag to override current tag resolution
+ * @param {string} [options.projectRoot] - Project root path
+ * @param {string} [options.tag] - Optional tag to override current tag resolution
+ * @param {string} [options.mcpLog] - MCP logger object
 * @returns {Object|undefined} Result object in MCP mode, undefined in CLI mode
 */
-async function setTaskStatus(
-	tasksPath,
-	taskIdInput,
-	newStatus,
-	options = {},
-	tag = null
-) {
+async function setTaskStatus(tasksPath, taskIdInput, newStatus, options = {}) {
+	const { projectRoot, tag } = options;
 	try {
 		if (!isValidTaskStatus(newStatus)) {
 			throw new Error(
@@ -59,7 +55,7 @@ async function setTaskStatus(
 		log('info', `Reading tasks from ${tasksPath}...`);

 		// Read the raw data without tag resolution to preserve tagged structure
-		let rawData = readJSON(tasksPath, options.projectRoot); // No tag parameter
+		let rawData = readJSON(tasksPath, projectRoot, tag); // No tag parameter

 		// Handle the case where readJSON returns resolved data with _rawTaggedData
 		if (rawData && rawData._rawTaggedData) {
@@ -67,24 +63,17 @@ async function setTaskStatus(
 			rawData = rawData._rawTaggedData;
 		}

-		// Determine the current tag
-		const currentTag = tag || getCurrentTag(options.projectRoot) || 'master';
-
 		// Ensure the tag exists in the raw data
-		if (
-			!rawData ||
-			!rawData[currentTag] ||
-			!Array.isArray(rawData[currentTag].tasks)
-		) {
+		if (!rawData || !rawData[tag] || !Array.isArray(rawData[tag].tasks)) {
 			throw new Error(
-				`Invalid tasks file or tag "${currentTag}" not found at ${tasksPath}`
+				`Invalid tasks file or tag "${tag}" not found at ${tasksPath}`
 			);
 		}

 		// Get the tasks for the current tag
 		const data = {
-			tasks: rawData[currentTag].tasks,
-			tag: currentTag,
+			tasks: rawData[tag].tasks,
+			tag,
 			_rawTaggedData: rawData
 		};

@@ -123,16 +112,16 @@ async function setTaskStatus(
 		}

 		// Update the raw data structure with the modified tasks
-		rawData[currentTag].tasks = data.tasks;
+		rawData[tag].tasks = data.tasks;

 		// Ensure the tag has proper metadata
-		ensureTagMetadata(rawData[currentTag], {
-			description: `Tasks for ${currentTag} context`
+		ensureTagMetadata(rawData[tag], {
+			description: `Tasks for ${tag} context`
 		});

 		// Write the updated raw data back to the file
 		// The writeJSON function will automatically filter out _rawTaggedData
-		writeJSON(tasksPath, rawData, options.projectRoot, currentTag);
+		writeJSON(tasksPath, rawData, projectRoot, tag);

 		// Validate dependencies after status update
 		log('info', 'Validating dependencies after status update...');
--- a/scripts/modules/task-manager/update-subtask-by-id.js
+++ b/scripts/modules/task-manager/update-subtask-by-id.js
@@ -17,8 +17,7 @@ import {
 	truncate,
 	isSilentMode,
 	findProjectRoot,
-	flattenTasksWithSubtasks,
-	getCurrentTag
+	flattenTasksWithSubtasks
 } from '../utils.js';
 import { generateTextService } from '../ai-services-unified.js';
 import { getDebugFlag } from '../config-manager.js';
@@ -37,6 +36,7 @@ import { FuzzyTaskSearch } from '../utils/fuzzyTaskSearch.js';
 * @param {Object} [context.session] - Session object from MCP server.
 * @param {Object} [context.mcpLog] - MCP logger object.
 * @param {string} [context.projectRoot] - Project root path (needed for AI service key resolution).
+ * @param {string} [context.tag] - Tag for the task
 * @param {string} [outputFormat='text'] - Output format ('text' or 'json'). Automatically 'json' if mcpLog is present.
 * @returns {Promise<Object|null>} - The updated subtask or null if update failed.
 */
@@ -92,10 +92,7 @@ async function updateSubtaskById(
 			throw new Error('Could not determine project root directory');
 		}

-		// Determine the tag to use
-		const currentTag = tag || getCurrentTag(projectRoot) || 'master';
-
-		const data = readJSON(tasksPath, projectRoot, currentTag);
+		const data = readJSON(tasksPath, projectRoot, tag);
 		if (!data || !data.tasks) {
 			throw new Error(
 				`No valid tasks found in ${tasksPath}. The file may be corrupted or have an invalid format.`
@@ -142,7 +139,7 @@ async function updateSubtaskById(
 		// --- Context Gathering ---
 		let gatheredContext = '';
 		try {
-			const contextGatherer = new ContextGatherer(projectRoot);
+			const contextGatherer = new ContextGatherer(projectRoot, tag);
 			const allTasksFlat = flattenTasksWithSubtasks(data.tasks);
 			const fuzzySearch = new FuzzyTaskSearch(allTasksFlat, 'update-subtask');
 			const searchQuery = `${parentTask.title} ${subtask.title} ${prompt}`;
@@ -331,13 +328,17 @@ async function updateSubtaskById(
 		if (outputFormat === 'text' && getDebugFlag(session)) {
 			console.log('>>> DEBUG: About to call writeJSON with updated data...');
 		}
-		writeJSON(tasksPath, data, projectRoot, currentTag);
+		writeJSON(tasksPath, data, projectRoot, tag);
 		if (outputFormat === 'text' && getDebugFlag(session)) {
 			console.log('>>> DEBUG: writeJSON call completed.');
 		}

 		report('success', `Successfully updated subtask ${subtaskId}`);
-		// await generateTaskFiles(tasksPath, path.dirname(tasksPath));
+		// Updated  function call to make sure if uncommented it will generate the task files for the updated subtask based on the tag
+		// await generateTaskFiles(tasksPath, path.dirname(tasksPath), {
+		// 	tag: tag,
+		// 	projectRoot: projectRoot
+		// });

 		if (outputFormat === 'text') {
 			if (loadingIndicator) {
--- a/scripts/modules/task-manager/update-task-by-id.js
+++ b/scripts/modules/task-manager/update-task-by-id.js
@@ -12,8 +12,7 @@ import {
 	truncate,
 	isSilentMode,
 	flattenTasksWithSubtasks,
-	findProjectRoot,
-	getCurrentTag
+	findProjectRoot
 } from '../utils.js';

 import {
@@ -262,6 +261,7 @@ function parseUpdatedTaskFromText(text, expectedTaskId, logFn, isMCP) {
 * @param {Object} [context.session] - Session object from MCP server.
 * @param {Object} [context.mcpLog] - MCP logger object.
 * @param {string} [context.projectRoot] - Project root path.
+ * @param {string} [context.tag] - Tag for the task
 * @param {string} [outputFormat='text'] - Output format ('text' or 'json').
 * @param {boolean} [appendMode=false] - If true, append to details instead of full update.
 * @returns {Promise<Object|null>} - The updated task or null if update failed.
@@ -320,11 +320,8 @@ async function updateTaskById(
 			throw new Error('Could not determine project root directory');
 		}

-		// Determine the tag to use
-		const currentTag = tag || getCurrentTag(projectRoot) || 'master';
-
 		// --- Task Loading and Status Check (Keep existing) ---
-		const data = readJSON(tasksPath, projectRoot, currentTag);
+		const data = readJSON(tasksPath, projectRoot, tag);
 		if (!data || !data.tasks)
 			throw new Error(`No valid tasks found in ${tasksPath}.`);
 		const taskIndex = data.tasks.findIndex((task) => task.id === taskId);
@@ -364,7 +361,7 @@ async function updateTaskById(
 		// --- Context Gathering ---
 		let gatheredContext = '';
 		try {
-			const contextGatherer = new ContextGatherer(projectRoot);
+			const contextGatherer = new ContextGatherer(projectRoot, tag);
 			const allTasksFlat = flattenTasksWithSubtasks(data.tasks);
 			const fuzzySearch = new FuzzyTaskSearch(allTasksFlat, 'update-task');
 			const searchQuery = `${taskToUpdate.title} ${taskToUpdate.description} ${prompt}`;
@@ -559,7 +556,7 @@ async function updateTaskById(

 				// Write the updated task back to file
 				data.tasks[taskIndex] = taskToUpdate;
-				writeJSON(tasksPath, data, projectRoot, currentTag);
+				writeJSON(tasksPath, data, projectRoot, tag);
 				report('success', `Successfully appended to task ${taskId}`);

 				// Display success message for CLI
@@ -704,7 +701,7 @@ async function updateTaskById(
 			// --- End Update Task Data ---

 			// --- Write File and Generate (Unchanged) ---
-			writeJSON(tasksPath, data, projectRoot, currentTag);
+			writeJSON(tasksPath, data, projectRoot, tag);
 			report('success', `Successfully updated task ${taskId}`);
 			// await generateTaskFiles(tasksPath, path.dirname(tasksPath));
 			// --- End Write File ---
--- a/scripts/modules/task-manager/update-tasks.js
+++ b/scripts/modules/task-manager/update-tasks.js
@@ -9,8 +9,7 @@ import {
 	readJSON,
 	writeJSON,
 	truncate,
-	isSilentMode,
-	getCurrentTag
+	isSilentMode
 } from '../utils.js';

 import {
@@ -234,8 +233,8 @@ function parseUpdatedTasksFromText(text, expectedCount, logFn, isMCP) {
 * @param {Object} context - Context object containing session and mcpLog.
 * @param {Object} [context.session] - Session object from MCP server.
 * @param {Object} [context.mcpLog] - MCP logger object.
+ * @param {string} [context.tag] - Tag for the task
 * @param {string} [outputFormat='text'] - Output format ('text' or 'json').
- * @param {string} [tag=null] - Tag associated with the tasks.
 */
 async function updateTasks(
 	tasksPath,
@@ -269,11 +268,8 @@ async function updateTasks(
 			throw new Error('Could not determine project root directory');
 		}

-		// Determine the current tag - prioritize explicit tag, then context.tag, then current tag
-		const currentTag = tag || getCurrentTag(projectRoot) || 'master';
-
 		// --- Task Loading/Filtering (Updated to pass projectRoot and tag) ---
-		const data = readJSON(tasksPath, projectRoot, currentTag);
+		const data = readJSON(tasksPath, projectRoot, tag);
 		if (!data || !data.tasks)
 			throw new Error(`No valid tasks found in ${tasksPath}`);
 		const tasksToUpdate = data.tasks.filter(
@@ -292,7 +288,7 @@ async function updateTasks(
 		// --- Context Gathering ---
 		let gatheredContext = '';
 		try {
-			const contextGatherer = new ContextGatherer(projectRoot);
+			const contextGatherer = new ContextGatherer(projectRoot, tag);
 			const allTasksFlat = flattenTasksWithSubtasks(data.tasks);
 			const fuzzySearch = new FuzzyTaskSearch(allTasksFlat, 'update');
 			const searchResults = fuzzySearch.findRelevantTasks(prompt, {
@@ -478,7 +474,7 @@ async function updateTasks(
 				);

 			// Fix: Pass projectRoot and currentTag to writeJSON
-			writeJSON(tasksPath, data, projectRoot, currentTag);
+			writeJSON(tasksPath, data, projectRoot, tag);
 			if (isMCP)
 				logFn.info(
 					`Successfully updated ${actualUpdateCount} tasks in ${tasksPath}`