chore: run format to resolve CI issues

- Normalize all tags' data when creating _rawTaggedData in readJSON
- Add support for handling malformed dotted subtask IDs (e.g., "5.1" -> 1)
- Remove redundant normalizeTaskIds calls from set-task-status, add-task, and move-task
- Add comprehensive test for mixed ID formats (string IDs and dotted notation)
- Cleaner, more maintainable solution that normalizes IDs at load time

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

.changeset/eleven-horses-shop.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Fix for tasks not found when using string IDs

.changeset/fix-gemini-cli-dependency.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix compatibility with @google/gemini-cli-core v0.1.12+ by updating ai-sdk-provider-gemini-cli to v0.1.1.

.changeset/fix-tag-complexity-detection.md

@@ -0,0 +1,7 @@
+---
+"task-master-ai": patch
+---
+
+Fix tag-specific complexity report detection in expand command
+
+The expand command now correctly finds and uses tag-specific complexity reports (e.g., `task-complexity-report_feature-xyz.json`) when operating in a tag context. Previously, it would always look for the generic `task-complexity-report.json` file due to a default value in the CLI option definition.

.changeset/fresh-bugs-squashed.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix 'expand --all' and 'show' commands to correctly handle tag contexts for complexity reports and task display.

.changeset/happy-sites-stay.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Clean up remaining automatic task file generation calls

.changeset/orange-pots-add.md

@@ -1,24 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add comprehensive Kiro IDE integration with autonomous task management hooks
-
-- **Kiro Profile**: Added full support for Kiro IDE with automatic installation of 7 Taskmaster agent hooks
-- **Hook-Driven Workflow**: Introduced natural language automation hooks that eliminate manual task status updates
-- **Automatic Hook Installation**: Hooks are now automatically copied to `.kiro/hooks/` when running `task-master rules add kiro`
-- **Language-Agnostic Support**: All hooks support multiple programming languages (JS, Python, Go, Rust, Java, etc.)
-- **Frontmatter Transformation**: Kiro rules use simplified `inclusion: always` format instead of Cursor's complex frontmatter
-- **Special Rule**: Added `taskmaster_hooks_workflow.md` that guides AI assistants to prefer hook-driven completion
-
-Key hooks included:
-
-- Task Dependency Auto-Progression: Automatically starts tasks when dependencies complete
-- Code Change Task Tracker: Updates task progress as you save files
-- Test Success Task Completer: Marks tasks done when tests pass
-- Daily Standup Assistant: Provides personalized task status summaries
-- PR Readiness Checker: Validates task completion before creating pull requests
-- Complexity Analyzer: Auto-expands complex tasks into manageable subtasks
-- Git Commit Task Linker: Links commits to tasks for better traceability
-
-This creates a truly autonomous development workflow where task management happens naturally as you code!

.changeset/quiet-rabbits-bathe.md

@@ -1,10 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix max_tokens limits for OpenRouter and Groq models
-
-- Add special handling in config-manager.js for custom OpenRouter models to use a conservative default of 32,768 max_tokens
-- Update qwen/qwen-turbo model max_tokens from 1,000,000 to 32,768 to match OpenRouter's actual limits
-- Fix moonshotai/kimi-k2-instruct max_tokens to 16,384 to match Groq's actual limit (fixes #1028)
-- This prevents "maximum context length exceeded" errors when using OpenRouter models not in our supported models list

.changeset/swift-otters-argue.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix VSCode profile generation to use correct rule file names (using `.instructions.md` extension instead of `.md`) and front-matter properties (removing the unsupported `alwaysApply` property from instructions files' front-matter).

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,45 @@
+# What type of PR is this?
+<!-- Check one -->
+
+ - [ ] 🐛 Bug fix
+ - [ ] ✨ Feature
+ - [ ] 🔌 Integration
+ - [ ] 📝 Docs
+ - [ ] 🧹 Refactor
+ - [ ] Other:
+## Description
+<!-- What does this PR do? -->
+
+## Related Issues
+<!-- Link issues: Fixes #123 -->
+
+## How to Test This
+<!-- Quick steps to verify the changes work -->
+```bash
+# Example commands or steps
+```
+
+**Expected result:**
+<!-- What should happen? -->
+
+## Contributor Checklist
+
+- [ ] Created changeset: `npm run changeset`
+- [ ] Tests pass: `npm test`
+- [ ] Format check passes: `npm run format-check` (or `npm run format` to fix)
+- [ ] Addressed CodeRabbit comments (if any)
+- [ ] Linked related issues (if any)
+- [ ] Manually tested the changes
+
+## Changelog Entry
+<!-- One line describing the change for users -->
+<!-- Example: "Added Kiro IDE integration with automatic task status updates" -->
+
+---
+
+### For Maintainers
+
+- [ ] PR title follows conventional commits
+- [ ] Target branch correct
+- [ ] Labels added
+- [ ] Milestone assigned (if applicable)

.github/PULL_REQUEST_TEMPLATE/bugfix.md

@@ -0,0 +1,39 @@
+## 🐛 Bug Fix
+
+### 🔍 Bug Description
+<!-- Describe the bug -->
+
+### 🔗 Related Issues
+<!-- Fixes #123 -->
+
+### ✨ Solution
+<!-- How does this PR fix the bug? -->
+
+## How to Test
+
+### Steps that caused the bug:
+1. 
+2. 
+
+**Before fix:** 
+**After fix:** 
+
+### Quick verification:
+```bash
+# Commands to verify the fix
+```
+
+## Contributor Checklist
+- [ ] Created changeset: `npm run changeset`
+- [ ] Tests pass: `npm test`
+- [ ] Format check passes: `npm run format-check`
+- [ ] Addressed CodeRabbit comments
+- [ ] Added unit tests (if applicable)
+- [ ] Manually verified the fix works
+
+---
+
+### For Maintainers
+- [ ] Root cause identified
+- [ ] Fix doesn't introduce new issues
+- [ ] CI passes

.github/PULL_REQUEST_TEMPLATE/config.yml

@@ -0,0 +1,11 @@
+blank_issues_enabled: false
+contact_links:
+  - name: 🐛 Bug Fix
+    url: https://github.com/eyaltoledano/claude-task-master/compare/next...HEAD?template=bugfix.md
+    about: Fix a bug in Task Master
+  - name: ✨ New Feature
+    url: https://github.com/eyaltoledano/claude-task-master/compare/next...HEAD?template=feature.md
+    about: Add a new feature to Task Master
+  - name: 🔌 New Integration
+    url: https://github.com/eyaltoledano/claude-task-master/compare/next...HEAD?template=integration.md
+    about: Add support for a new tool, IDE, or platform

.github/PULL_REQUEST_TEMPLATE/feature.md

@@ -0,0 +1,49 @@
+## ✨ New Feature
+
+### 📋 Feature Description
+<!-- Brief description -->
+
+### 🎯 Problem Statement
+<!-- What problem does this feature solve? Why is it needed? -->
+
+### 💡 Solution
+<!-- How does this feature solve the problem? What's the approach? -->
+
+### 🔗 Related Issues
+<!-- Link related issues: Fixes #123, Part of #456 -->
+
+## How to Use It
+
+### Quick Start
+```bash
+# Basic usage example
+```
+
+### Example
+<!-- Show a real use case -->
+```bash
+# Practical example
+```
+
+**What you should see:**
+<!-- Expected behavior -->
+
+## Contributor Checklist
+- [ ] Created changeset: `npm run changeset`
+- [ ] Tests pass: `npm test`
+- [ ] Format check passes: `npm run format-check`
+- [ ] Addressed CodeRabbit comments
+- [ ] Added tests for new functionality
+- [ ] Manually tested in CLI mode
+- [ ] Manually tested in MCP mode (if applicable)
+
+## Changelog Entry
+<!-- One-liner for release notes -->
+
+---
+
+### For Maintainers
+
+- [ ] Feature aligns with project vision
+- [ ] CIs pass
+- [ ] Changeset file exists

.github/PULL_REQUEST_TEMPLATE/integration.md

@@ -0,0 +1,53 @@
+# 🔌 New Integration
+
+## What tool/IDE is being integrated?
+
+<!-- Name and brief description -->
+
+## What can users do with it?
+
+<!-- Key benefits -->
+
+## How to Enable
+
+### Setup
+
+```bash
+task-master rules add [name]
+# Any other setup steps
+```
+
+### Example Usage
+
+<!-- Show it in action -->
+
+```bash
+# Real example
+```
+
+### Natural Language Hooks (if applicable)
+
+```
+"When tests pass, mark task as done"
+# Other examples
+```
+
+## Contributor Checklist
+
+- [ ] Created changeset: `npm run changeset`
+- [ ] Tests pass: `npm test`
+- [ ] Format check passes: `npm run format-check`
+- [ ] Addressed CodeRabbit comments
+- [ ] Integration fully tested with target tool/IDE
+- [ ] Error scenarios tested
+- [ ] Added integration tests
+- [ ] Documentation includes setup guide
+- [ ] Examples are working and clear
+
+---
+
+## For Maintainers
+
+- [ ] Integration stability verified
+- [ ] Documentation comprehensive
+- [ ] Examples working

CHANGELOG.md

@@ -1,5 +1,91 @@
 # task-master-ai
 
+## 0.22.0
+
+### Minor Changes
+
+- [#1043](https://github.com/eyaltoledano/claude-task-master/pull/1043) [`dc44ed9`](https://github.com/eyaltoledano/claude-task-master/commit/dc44ed9de8a57aca5d39d3a87565568bd0a82068) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Prompt to generate a complexity report when it is missing
+
+- [#1032](https://github.com/eyaltoledano/claude-task-master/pull/1032) [`4423119`](https://github.com/eyaltoledano/claude-task-master/commit/4423119a5ec53958c9dffa8bf564da8be7a2827d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add comprehensive Kiro IDE integration with autonomous task management hooks
+  - **Kiro Profile**: Added full support for Kiro IDE with automatic installation of 7 Taskmaster agent hooks
+  - **Hook-Driven Workflow**: Introduced natural language automation hooks that eliminate manual task status updates
+  - **Automatic Hook Installation**: Hooks are now automatically copied to `.kiro/hooks/` when running `task-master rules add kiro`
+  - **Language-Agnostic Support**: All hooks support multiple programming languages (JS, Python, Go, Rust, Java, etc.)
+  - **Frontmatter Transformation**: Kiro rules use simplified `inclusion: always` format instead of Cursor's complex frontmatter
+  - **Special Rule**: Added `taskmaster_hooks_workflow.md` that guides AI assistants to prefer hook-driven completion
+
+  Key hooks included:
+  - Task Dependency Auto-Progression: Automatically starts tasks when dependencies complete
+  - Code Change Task Tracker: Updates task progress as you save files
+  - Test Success Task Completer: Marks tasks done when tests pass
+  - Daily Standup Assistant: Provides personalized task status summaries
+  - PR Readiness Checker: Validates task completion before creating pull requests
+  - Complexity Analyzer: Auto-expands complex tasks into manageable subtasks
+  - Git Commit Task Linker: Links commits to tasks for better traceability
+
+  This creates a truly autonomous development workflow where task management happens naturally as you code!
+
+### Patch Changes
+
+- [#1033](https://github.com/eyaltoledano/claude-task-master/pull/1033) [`7b90568`](https://github.com/eyaltoledano/claude-task-master/commit/7b9056832653464f934c91c22997077065d738c4) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Fix compatibility with @google/gemini-cli-core v0.1.12+ by updating ai-sdk-provider-gemini-cli to v0.1.1.
+
+- [#1038](https://github.com/eyaltoledano/claude-task-master/pull/1038) [`77cc5e4`](https://github.com/eyaltoledano/claude-task-master/commit/77cc5e4537397642f2664f61940a101433ee6fb4) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix 'expand --all' and 'show' commands to correctly handle tag contexts for complexity reports and task display.
+
+- [#1025](https://github.com/eyaltoledano/claude-task-master/pull/1025) [`8781794`](https://github.com/eyaltoledano/claude-task-master/commit/8781794c56d454697fc92c88a3925982d6b81205) Thanks [@joedanz](https://github.com/joedanz)! - Clean up remaining automatic task file generation calls
+
+- [#1035](https://github.com/eyaltoledano/claude-task-master/pull/1035) [`fb7d588`](https://github.com/eyaltoledano/claude-task-master/commit/fb7d588137e8c53b0d0f54bd1dd8d387648583ee) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix max_tokens limits for OpenRouter and Groq models
+  - Add special handling in config-manager.js for custom OpenRouter models to use a conservative default of 32,768 max_tokens
+  - Update qwen/qwen-turbo model max_tokens from 1,000,000 to 32,768 to match OpenRouter's actual limits
+  - Fix moonshotai/kimi-k2-instruct max_tokens to 16,384 to match Groq's actual limit (fixes #1028)
+  - This prevents "maximum context length exceeded" errors when using OpenRouter models not in our supported models list
+
+- [#1027](https://github.com/eyaltoledano/claude-task-master/pull/1027) [`6ae66b2`](https://github.com/eyaltoledano/claude-task-master/commit/6ae66b2afbfe911340fa25e0236c3db83deaa7eb) Thanks [@andreswebs](https://github.com/andreswebs)! - Fix VSCode profile generation to use correct rule file names (using `.instructions.md` extension instead of `.md`) and front-matter properties (removing the unsupported `alwaysApply` property from instructions files' front-matter).
+
+## 0.22.0-rc.1
+
+### Minor Changes
+
+- [#1043](https://github.com/eyaltoledano/claude-task-master/pull/1043) [`dc44ed9`](https://github.com/eyaltoledano/claude-task-master/commit/dc44ed9de8a57aca5d39d3a87565568bd0a82068) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Prompt to generate a complexity report when it is missing
+
+## 0.22.0-rc.0
+
+### Minor Changes
+
+- [#1032](https://github.com/eyaltoledano/claude-task-master/pull/1032) [`4423119`](https://github.com/eyaltoledano/claude-task-master/commit/4423119a5ec53958c9dffa8bf564da8be7a2827d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add comprehensive Kiro IDE integration with autonomous task management hooks
+  - **Kiro Profile**: Added full support for Kiro IDE with automatic installation of 7 Taskmaster agent hooks
+  - **Hook-Driven Workflow**: Introduced natural language automation hooks that eliminate manual task status updates
+  - **Automatic Hook Installation**: Hooks are now automatically copied to `.kiro/hooks/` when running `task-master rules add kiro`
+  - **Language-Agnostic Support**: All hooks support multiple programming languages (JS, Python, Go, Rust, Java, etc.)
+  - **Frontmatter Transformation**: Kiro rules use simplified `inclusion: always` format instead of Cursor's complex frontmatter
+  - **Special Rule**: Added `taskmaster_hooks_workflow.md` that guides AI assistants to prefer hook-driven completion
+
+  Key hooks included:
+  - Task Dependency Auto-Progression: Automatically starts tasks when dependencies complete
+  - Code Change Task Tracker: Updates task progress as you save files
+  - Test Success Task Completer: Marks tasks done when tests pass
+  - Daily Standup Assistant: Provides personalized task status summaries
+  - PR Readiness Checker: Validates task completion before creating pull requests
+  - Complexity Analyzer: Auto-expands complex tasks into manageable subtasks
+  - Git Commit Task Linker: Links commits to tasks for better traceability
+
+  This creates a truly autonomous development workflow where task management happens naturally as you code!
+
+### Patch Changes
+
+- [#1033](https://github.com/eyaltoledano/claude-task-master/pull/1033) [`7b90568`](https://github.com/eyaltoledano/claude-task-master/commit/7b9056832653464f934c91c22997077065d738c4) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Fix compatibility with @google/gemini-cli-core v0.1.12+ by updating ai-sdk-provider-gemini-cli to v0.1.1.
+
+- [#1038](https://github.com/eyaltoledano/claude-task-master/pull/1038) [`77cc5e4`](https://github.com/eyaltoledano/claude-task-master/commit/77cc5e4537397642f2664f61940a101433ee6fb4) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix 'expand --all' and 'show' commands to correctly handle tag contexts for complexity reports and task display.
+
+- [#1025](https://github.com/eyaltoledano/claude-task-master/pull/1025) [`8781794`](https://github.com/eyaltoledano/claude-task-master/commit/8781794c56d454697fc92c88a3925982d6b81205) Thanks [@joedanz](https://github.com/joedanz)! - Clean up remaining automatic task file generation calls
+
+- [#1035](https://github.com/eyaltoledano/claude-task-master/pull/1035) [`fb7d588`](https://github.com/eyaltoledano/claude-task-master/commit/fb7d588137e8c53b0d0f54bd1dd8d387648583ee) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix max_tokens limits for OpenRouter and Groq models
+  - Add special handling in config-manager.js for custom OpenRouter models to use a conservative default of 32,768 max_tokens
+  - Update qwen/qwen-turbo model max_tokens from 1,000,000 to 32,768 to match OpenRouter's actual limits
+  - Fix moonshotai/kimi-k2-instruct max_tokens to 16,384 to match Groq's actual limit (fixes #1028)
+  - This prevents "maximum context length exceeded" errors when using OpenRouter models not in our supported models list
+
+- [#1027](https://github.com/eyaltoledano/claude-task-master/pull/1027) [`6ae66b2`](https://github.com/eyaltoledano/claude-task-master/commit/6ae66b2afbfe911340fa25e0236c3db83deaa7eb) Thanks [@andreswebs](https://github.com/andreswebs)! - Fix VSCode profile generation to use correct rule file names (using `.instructions.md` extension instead of `.md`) and front-matter properties (removing the unsupported `alwaysApply` property from instructions files' front-matter).
+
 ## 0.21.0
 
 ### Minor Changes

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "task-master-ai",
-	"version": "0.21.0",
+	"version": "0.22.0",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "task-master-ai",
-			"version": "0.21.0",
+			"version": "0.22.0",
 			"license": "MIT WITH Commons-Clause",
 			"workspaces": [
 				"apps/*",

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "task-master-ai",
-	"version": "0.21.0",
+	"version": "0.22.0",
 	"description": "A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.",
 	"main": "index.js",
 	"type": "module",

scripts/modules/commands.js

@@ -1564,8 +1564,8 @@ function registerCommands(programInstance) {
 		) // Allow file override
 		.option(
 			'-cr, --complexity-report <file>',
-			'Path to the report file',
-			COMPLEXITY_REPORT_FILE
+			'Path to the complexity report file (use this to specify the complexity report, not --file)'
+			// Removed default value to allow tag-specific auto-detection
 		)
 		.option('--tag <tag>', 'Specify tag context for task operations')
 		.action(async (options) => {

scripts/modules/ui.js

@@ -9,6 +9,7 @@ import boxen from 'boxen';
 import ora from 'ora';
 import Table from 'cli-table3';
 import gradient from 'gradient-string';
+import readline from 'readline';
 import {
 	log,
 	findTaskById,
@@ -1682,18 +1683,15 @@ async function displayComplexityReport(reportPath) {
 			)
 		);
 
-		const readline = require('readline').createInterface({
+		const rl = readline.createInterface({
 			input: process.stdin,
 			output: process.stdout
 		});
 
 		const answer = await new Promise((resolve) => {
-			readline.question(
-				chalk.cyan('Generate complexity report? (y/n): '),
-				resolve
-			);
+			rl.question(chalk.cyan('Generate complexity report? (y/n): '), resolve);
 		});
-		readline.close();
+		rl.close();
 
 		if (answer.toLowerCase() === 'y' || answer.toLowerCase() === 'yes') {
 			// Call the analyze-complexity command
@@ -1974,8 +1972,6 @@ async function confirmTaskOverwrite(tasksPath) {
 		)
 	);
 
-	// Use dynamic import to get the readline module
-	const readline = await import('readline');
 	const rl = readline.createInterface({
 		input: process.stdin,
 		output: process.stdout
@@ -2463,8 +2459,6 @@ async function displayMultipleTasksSummary(
 			)
 		);
 
-		// Use dynamic import for readline
-		const readline = await import('readline');
 		const rl = readline.createInterface({
 			input: process.stdin,
 			output: process.stdout

scripts/modules/utils.js

@@ -262,6 +262,43 @@ function hasTaggedStructure(data) {
 	return false;
 }
 
+/**
+ * Normalizes task IDs to ensure they are numbers instead of strings
+ * @param {Array} tasks - Array of tasks to normalize
+ */
+function normalizeTaskIds(tasks) {
+	if (!Array.isArray(tasks)) return;
+
+	tasks.forEach((task) => {
+		// Convert task ID to number with validation
+		if (task.id !== undefined) {
+			const parsedId = parseInt(task.id, 10);
+			if (!isNaN(parsedId) && parsedId > 0) {
+				task.id = parsedId;
+			}
+		}
+
+		// Convert subtask IDs to numbers with validation
+		if (Array.isArray(task.subtasks)) {
+			task.subtasks.forEach((subtask) => {
+				if (subtask.id !== undefined) {
+					// Check for dot notation (which shouldn't exist in storage)
+					if (typeof subtask.id === 'string' && subtask.id.includes('.')) {
+						// Extract the subtask part after the dot
+						const parts = subtask.id.split('.');
+						subtask.id = parseInt(parts[parts.length - 1], 10);
+					} else {
+						const parsedSubtaskId = parseInt(subtask.id, 10);
+						if (!isNaN(parsedSubtaskId) && parsedSubtaskId > 0) {
+							subtask.id = parsedSubtaskId;
+						}
+					}
+				}
+			});
+		}
+	});
+}
+
 /**
  * Reads and parses a JSON file
  * @param {string} filepath - Path to the JSON file
@@ -322,6 +359,8 @@ function readJSON(filepath, projectRoot = null, tag = null) {
 			console.log(`File is in legacy format, performing migration...`);
 		}
 
+		normalizeTaskIds(data.tasks);
+
 		// This is legacy format - migrate it to tagged format
 		const migratedData = {
 			master: {
@@ -401,6 +440,16 @@ function readJSON(filepath, projectRoot = null, tag = null) {
 		// Store reference to the raw tagged data for functions that need it
 		const originalTaggedData = JSON.parse(JSON.stringify(data));
 
+		// Normalize IDs in all tags before storing as originalTaggedData
+		for (const tagName in originalTaggedData) {
+			if (
+				originalTaggedData[tagName] &&
+				Array.isArray(originalTaggedData[tagName].tasks)
+			) {
+				normalizeTaskIds(originalTaggedData[tagName].tasks);
+			}
+		}
+
 		// Check and auto-switch git tags if enabled (for existing tagged format)
 		// This needs to run synchronously BEFORE tag resolution
 		if (projectRoot) {
@@ -448,6 +497,8 @@ function readJSON(filepath, projectRoot = null, tag = null) {
 			// Get the data for the resolved tag
 			const tagData = data[resolvedTag];
 			if (tagData && tagData.tasks) {
+				normalizeTaskIds(tagData.tasks);
+
 				// Add the _rawTaggedData property and the resolved tag to the returned data
 				const result = {
 					...tagData,
@@ -464,6 +515,8 @@ function readJSON(filepath, projectRoot = null, tag = null) {
 				// If the resolved tag doesn't exist, fall back to master
 				const masterData = data.master;
 				if (masterData && masterData.tasks) {
+					normalizeTaskIds(masterData.tasks);
+
 					if (isDebug) {
 						console.log(
 							`Tag '${resolvedTag}' not found, falling back to master with ${masterData.tasks.length} tasks`
@@ -493,6 +546,7 @@ function readJSON(filepath, projectRoot = null, tag = null) {
 			// If anything goes wrong, try to return master or empty
 			const masterData = data.master;
 			if (masterData && masterData.tasks) {
+				normalizeTaskIds(masterData.tasks);
 				return {
 					...masterData,
 					_rawTaggedData: originalTaggedData
@@ -1412,5 +1466,6 @@ export {
 	createStateJson,
 	markMigrationForNotice,
 	flattenTasksWithSubtasks,
-	ensureTagMetadata
+	ensureTagMetadata,
+	normalizeTaskIds
 };

tests/unit/task-finder.test.js

@@ -23,6 +23,82 @@ describe('Task Finder', () => {
 			expect(result.originalSubtaskCount).toBeNull();
 		});
 
+		test('should find tasks when JSON contains string IDs (normalized to numbers)', () => {
+			// Simulate tasks loaded from JSON with string IDs and mixed subtask notations
+			const tasksWithStringIds = [
+				{ id: '1', title: 'First Task' },
+				{
+					id: '2',
+					title: 'Second Task',
+					subtasks: [
+						{ id: '1', title: 'Subtask One' },
+						{ id: '2.2', title: 'Subtask Two (with dotted notation)' } // Testing dotted notation
+					]
+				},
+				{
+					id: '5',
+					title: 'Fifth Task',
+					subtasks: [
+						{ id: '5.1', title: 'Subtask with dotted ID' }, // Should normalize to 1
+						{ id: '3', title: 'Subtask with simple ID' } // Should stay as 3
+					]
+				}
+			];
+
+			// The readJSON function should normalize these IDs to numbers
+			// For this test, we'll manually normalize them to simulate what happens
+			tasksWithStringIds.forEach((task) => {
+				task.id = parseInt(task.id, 10);
+				if (task.subtasks) {
+					task.subtasks.forEach((subtask) => {
+						// Handle dotted notation like "5.1" -> extract the subtask part
+						if (typeof subtask.id === 'string' && subtask.id.includes('.')) {
+							const parts = subtask.id.split('.');
+							subtask.id = parseInt(parts[parts.length - 1], 10);
+						} else {
+							subtask.id = parseInt(subtask.id, 10);
+						}
+					});
+				}
+			});
+
+			// Test finding tasks by numeric ID
+			const result1 = findTaskById(tasksWithStringIds, 5);
+			expect(result1.task).toBeDefined();
+			expect(result1.task.id).toBe(5);
+			expect(result1.task.title).toBe('Fifth Task');
+
+			// Test finding tasks by string ID
+			const result2 = findTaskById(tasksWithStringIds, '5');
+			expect(result2.task).toBeDefined();
+			expect(result2.task.id).toBe(5);
+
+			// Test finding subtasks with normalized IDs
+			const result3 = findTaskById(tasksWithStringIds, '2.1');
+			expect(result3.task).toBeDefined();
+			expect(result3.task.id).toBe(1);
+			expect(result3.task.title).toBe('Subtask One');
+			expect(result3.task.isSubtask).toBe(true);
+
+			// Test subtask that was originally "2.2" (should be normalized to 2)
+			const result4 = findTaskById(tasksWithStringIds, '2.2');
+			expect(result4.task).toBeDefined();
+			expect(result4.task.id).toBe(2);
+			expect(result4.task.title).toBe('Subtask Two (with dotted notation)');
+
+			// Test subtask that was originally "5.1" (should be normalized to 1)
+			const result5 = findTaskById(tasksWithStringIds, '5.1');
+			expect(result5.task).toBeDefined();
+			expect(result5.task.id).toBe(1);
+			expect(result5.task.title).toBe('Subtask with dotted ID');
+
+			// Test subtask that was originally "3" (should stay as 3)
+			const result6 = findTaskById(tasksWithStringIds, '5.3');
+			expect(result6.task).toBeDefined();
+			expect(result6.task.id).toBe(3);
+			expect(result6.task.title).toBe('Subtask with simple ID');
+		});
+
 		test('should find a subtask using dot notation', () => {
 			const result = findTaskById(sampleTasks.tasks, '3.1');
 			expect(result.task).toBeDefined();