bueller-wheel 0.1.0 → 0.3.0

package/README.md

@@ -1,6 +1,8 @@
 # Bueller Wheel
 
-A headless Claude Code issue processor that runs in a loop and resolves issues or tickets written in markdown
+> Life moves pretty fast. If you don't stop and look around once in a while, you could miss it.
+
+This is a headless issue processor that runs in a loop and uses Claude to resolve issues or ticket files written in markdown. It plays nicely with Claude Code and uses the sames settings config.
 
 ## Quick Start
 
@@ -10,28 +12,26 @@ mkdir -p issues/open
 echo "@user: Please create a test file with 'Hello World'" > issues/open/p0-100-my-task.md
 
 # Run bueller-wheel to complete the task
-npx bueller-wheel
+npx bueller-wheel --run
 ```
 
 ## Why?
 
-Claude Code agents work better when they focus on one thing at a time. Bueller Wheel helps defer context until it's needed through two mechanisms:
-
-**Issues as directory-based threads** - Each task becomes a reviewable conversation stored as markdown that gets moved along a file-based "kanban" board. This solves a few problems:
-- **Code review**: When Claude burns through multiple tasks, it's hard to know what happened. The issues structure creates discrete, reviewable units of work.
-- **Iteration without re-prompting**: Markdown files are structured as a back-and-forth between you and Claude, which lets you append follow-ups naturally without starting over.
-- **Human-editable prompts**: Storing issues as simple markdown (not JSON or a database) makes it easy to edit, append, or retroactively clean up conversations to improve prompting.
+You want Claude to autonomously work on a large pile of issues while you go on a day trip into the city. Bueller Wheel helps tackle several issues you might encounter:
 
-**FAQ system** - Common mistakes get documented once, then referenced automatically. Instead of repeating corrections or watching Claude make the same errors over and over, capture solutions in FAQ files that the agent checks when stuck.
+- **Claude stops processing after a few issues**: Claude tends to stop processing after completing a few tasks. Bueller Wheel keeps prompting Claude to work until all of the issues have been resolved.
+- **Claude forgets what it's doing**: As Claude uses up its context window, it tends to forget what it was working on. Bueller Wheel runs Claude with a fresh context window and prompt for each issue.
+- **You forget what Claude was doing**: If you successfully get Claude to work on a large number of tasks, you end up with a pile of code to review. Bueller Wheel structures each issue as a discrete reviewable chunk of work, in a format amenable to multiple iterations of feedback between you and Claude.
+- **Claude keeps making the same mistakes**: An agent that forgets its history is doomed to repeat it. Bueller Wheel sets up an FAQ directory for Claude to speed up resolution of frequent pitfalls.
 
-**Note:** Bueller Wheel is not a full-fledged task management system. It has no concept of assignment or dependency apart from linear file ordering. The sweet spot for this tool is **solo developers working on a single branch**, but you can make [parallel branches and agents](#working-with-multiple-branches) work.
+**Note**: Bueller Wheel is not a full-fledged task management system. It has no concept of assignment or dependency apart from linear file ordering. The sweet spot for this tool is **solo developers working on a single branch**. That said, you can make [parallel branches and agents](#working-with-multiple-branches) work.
 
 ## How It Works
 
 **The Processing Loop**
 
 1. Bueller Wheel finds the next issue in `issues/open/` (sorted alphabetically by filename)
-2. Claude Code reads the issue and works on the task
+2. Claude reads the issue and works on the task
 3. Claude appends its work summary to the issue file
 4. Claude decides the outcome:
    - **CONTINUE**: Keep working (stays in `open/`)
@@ -45,7 +45,7 @@ Claude Code agents work better when they focus on one thing at a time. Bueller W
 - Move issues from `review/` or `stuck/` back to `open/` if more work is required
 - Delete issues from `review/` when done reviewing, or archive them however you want
 
-**Each iteration is a fresh Claude Code session** - no memory between iterations, which keeps context focused.
+**Each iteration is a fresh Claude session** - no memory between iterations, which keeps context focused.
 
 **Inherits your project's Claude Code setup** - `bueller-wheel` uses the Anthropic API credential from whichever user you're logged in as. It inherits the same `.claude/settings.json` or `.claude/settings.local.json` as the Claude Code project it's used in. Whatever permissions apply to your regular `claude` CLI should also apply to `bueller-wheel`, with the exception that `bueller-wheel` starts in "accept edits" mode.
 
@@ -139,18 +139,37 @@ The `open/` directory acts as an inbox for the agent on the current branch. The
 ## CLI Options
 
 ```bash
-npx bueller-wheel --issues-dir ./my-issues --faq-dir ./my-faq --max-iterations 50 --git-commit --prompt ./my-prompt.md
+# Start the agent loop with various options
+npx bueller-wheel --run
+npx bueller-wheel --git
+npx bueller-wheel --max 50
+npx bueller-wheel --continue "fix the bug"
+
+# Summarize issues
+npx bueller-wheel --summarize p1-003-task.md
+npx bueller-wheel --summarize p1-003.md p2-005.md --index 1
+
+# Combine with other options
+npx bueller-wheel --run --issues-dir ./my-issues --faq-dir ./my-faq
+npx bueller-wheel --max 50 --git --prompt ./my-prompt.md
 
 # Or if installed globally
-bueller-wheel --issues-dir ./my-issues --faq-dir ./my-faq --max-iterations 50 --git-commit --prompt ./my-prompt.md
+bueller-wheel --run
+bueller-wheel --git
 ```
 
+**Run Commands** (one required):
+- `--run`: Explicitly start the agent loop with defaults
+- `--git`: Enable automatic git commits and start the loop
+- `--max <number>`: Start with maximum N iterations (default: `25`)
+- `--continue [prompt]`: Continue from previous session. Optional prompt defaults to "continue" if not provided
+- `--summarize <issue...>`: Display abbreviated summaries of issue conversation history
+
+**Configuration Options**:
 - `--issues-dir <path>`: Issues directory (default: `./issues`)
 - `--faq-dir <path>`: FAQ directory (default: `./faq`)
-- `--max-iterations <number>`: Maximum iterations (default: `25`)
-- `--git-commit`: Enable automatic git commits after each iteration (default: disabled)
 - `--prompt <path>`: Path to custom prompt template file (default: `<issues-dir>/prompt.md`)
-- `--continue [prompt]`: Continue from previous session. Optional prompt defaults to "continue" if not provided
+- `--index <N>` or `--index <M,N>`: Expand specific messages when using `--summarize` (see below)
 
 ### Custom Prompt Templates
 
@@ -212,7 +231,7 @@ Note that only the immediate prior iteration is continued. The next iteration wi
 
 ### Git Auto-Commit
 
-When `--git-commit` is enabled, Bueller Wheel will automatically create a git commit after each iteration where work was done on an issue.
+When `--git` is enabled, Bueller Wheel will automatically create a git commit after each iteration where work was done on an issue.
 
 The commit message format includes the issue ID (the filename minus the `.md`) and status:
 ```
@@ -221,13 +240,68 @@ p0-002-git in progress
 p0-002-git stuck
 p0-002-git unknown
 ```
+
+### Issue Summarization
+
+The `--summarize` command provides a quick way to review issue conversation history without opening files. This is especially useful for:
+- Quickly understanding what happened in an issue
+- Reviewing multiple issues at once
+- Checking the status and progress of work
+
+**Basic Usage:**
+
+```bash
+# Summarize a single issue (by filename - searches across open/, review/, stuck/)
+npx bueller-wheel --summarize p1-003-task.md
+
+# Summarize by partial filename
+npx bueller-wheel --summarize p1-003.md
+
+# Summarize with full path
+npx bueller-wheel --summarize /path/to/issues/open/p1-003-task.md
+
+# Summarize multiple issues
+npx bueller-wheel --summarize p1-003.md p1-004.md p2-001.md
+```
+
+**Summary Format:**
+
+By default, summaries show:
+- Issue filename and status (open/review/stuck)
+- First message: up to 300 characters
+- Middle messages: up to 80 characters each (abbreviated)
+- Last message: up to 300 characters
+
+**Expanding Messages:**
+
+Use `--index` to expand specific messages to their full content:
+
+```bash
+# Expand a single message at index 2
+npx bueller-wheel --summarize p1-003.md --index 2
+
+# Expand a range of messages (indices 1 through 3)
+npx bueller-wheel --summarize p1-003.md --index 1,3
+
+# Works with multiple issues (expands same indices for all)
+npx bueller-wheel --summarize p1-003.md p1-004.md --index 0,2
+```
+
+**Note:** Message indices are 0-based (first message is index 0).
+
 ## Development
 
-`pnpm run dev` will execute the current `src/index.ts` script file with whatever args you pass to it.
+`pnpm run dev` will execute the current `src/index.ts` script file with whatever args you pass to it. For example:
+
+```bash
+pnpm run dev -- --run
+pnpm run dev -- --git
+pnpm run dev -- --max 10
+```
 
 ## End-to-End Testing
 
-**These tests use your actual live instance of Claude Code!**
+**These tests use your actual Anthropic / Claude credentials!**
 
 ```bash
 # Run all tests

package/dist/index.js

@@ -3,24 +3,42 @@ import { execSync } from 'node:child_process';
 import * as fs from 'node:fs/promises';
 import * as path from 'node:path';
 import { query } from '@anthropic-ai/claude-agent-sdk';
+import { expandMessages, formatIssueSummary, resolveIssueReference, summarizeIssue, } from './issue-summarize.js';
+// Colors for output
+const colors = {
+    red: '\x1b[0;31m',
+    green: '\x1b[0;32m',
+    yellow: '\x1b[1;33m',
+    blue: '\x1b[0;34m',
+    cyan: '\x1b[0;36m',
+    reset: '\x1b[0m',
+};
 const ISSUE_DIR_OPEN = 'open';
 const ISSUE_DIR_REVIEW = 'review';
 const ISSUE_DIR_STUCK = 'stuck';
 function showHelp() {
     console.log(`
-Bueller - Headless Claude Code Issue Processor
+Bueller Wheel - Headless Claude Code Issue Processor
 
 USAGE:
-  bueller [OPTIONS]
+  bueller-wheel run [OPTIONS]               Start the agent loop
+  bueller-wheel issue ISSUE... [OPTIONS]    View issue summaries
+
+COMMANDS:
+  run                 Start the agent loop to process issues
+  issue ISSUE...      Summarize one or more issues (accepts file paths or filenames)
 
 OPTIONS:
   --help              Show this help message and exit
+  --git               Enable automatic git commits (on by default, run command only)
+  --no-git            Disable automatic git commits (run command only)
+  --max N             Maximum number of iterations to run (default: 25, run command only)
+  --continue [PROMPT] Continue from previous session (default prompt: "continue", run command only)
+  --index N           Expand message at index N (issue command only)
+  --index M,N         Expand message range from M to N (issue command only)
   --issues-dir DIR    Directory containing issue queue (default: ./issues)
   --faq-dir DIR       Directory containing FAQ/troubleshooting guides (default: ./faq)
-  --max-iterations N  Maximum number of iterations to run (default: 25)
-  --git, --git-commit Enable automatic git commits after each iteration
-  --prompt FILE       Custom prompt template file (default: ./issues/prompt.md)
-  --continue [PROMPT] Continue from previous session (default prompt: "continue")
+  --prompt FILE       Custom prompt template file (default: ./issues/prompt.md, run command only)
 
 DIRECTORY STRUCTURE:
   issues/
@@ -39,10 +57,14 @@ ISSUE FILE FORMAT:
     p2: Non-blocking follow-up
 
 EXAMPLES:
-  bueller
-  bueller --issues-dir ./my-issues --faq-dir ./my-faq
-  bueller --max-iterations 50 --git-commit
-  bueller --prompt ./custom-prompt.md
+  bueller-wheel run
+  bueller-wheel run --no-git
+  bueller-wheel run --max 50
+  bueller-wheel run --continue "fix the bug"
+  bueller-wheel run --issues-dir ./my-issues --faq-dir ./my-faq
+  bueller-wheel issue p1-003-read-helper-002.md
+  bueller-wheel issue p1-003 p2-005 --index 1
+  bueller-wheel issue /path/to/issue.md --index 0,2
 
 For more information, visit: https://github.com/anthropics/bueller
 `);
@@ -50,18 +72,52 @@ For more information, visit: https://github.com/anthropics/bueller
 function parseArgs() {
     const args = process.argv.slice(2);
     // Check for help flag first
-    if (args.includes('--help') || args.includes('-h')) {
+    if (args.includes('--help') || args.includes('-h') || args.length === 0) {
         showHelp();
         process.exit(0);
     }
+    // First argument should be the command
+    const command = args[0];
+    if (command !== 'run' && command !== 'issue') {
+        console.error(`${colors.red}Error: Unknown command "${command}". Use "run" or "issue".${colors.reset}\n`);
+        showHelp();
+        process.exit(1);
+    }
+    // Define recognized flags
+    const recognizedFlags = new Set([
+        '--issues-dir',
+        '--faq-dir',
+        '--max',
+        '--git',
+        '--no-git',
+        '--prompt',
+        '--continue',
+        '--index',
+        '--help',
+        '-h',
+    ]);
+    // Check for unrecognized flags
+    for (const arg of args.slice(1)) {
+        // Check if this looks like a flag (starts with -)
+        if (arg.startsWith('-')) {
+            if (!recognizedFlags.has(arg)) {
+                console.error(`${colors.red}Error: Unrecognized flag: ${arg}${colors.reset}\n`);
+                showHelp();
+                process.exit(1);
+            }
+        }
+    }
     let issuesDir = './issues';
     let faqDir = './faq';
     let maxIterations = 25;
-    let gitCommit = false;
+    let gitCommit = true;
     let promptFile = path.join('./issues', 'prompt.md');
     let continueMode = false;
     let continuePrompt = 'continue';
-    for (let i = 0; i < args.length; i++) {
+    const issueReferences = [];
+    let issueIndex;
+    // Parse arguments starting from index 1 (skip the command)
+    for (let i = 1; i < args.length; i++) {
         if (args[i] === '--issues-dir' && i + 1 < args.length) {
             issuesDir = args[++i];
             // Update default prompt file location if issues-dir is changed
@@ -72,12 +128,15 @@ function parseArgs() {
         else if (args[i] === '--faq-dir' && i + 1 < args.length) {
             faqDir = args[++i];
         }
-        else if (args[i] === '--max-iterations' && i + 1 < args.length) {
+        else if (args[i] === '--max' && i + 1 < args.length) {
             maxIterations = parseInt(args[++i], 10);
         }
-        else if (args[i] === '--git' || args[i] === '--git-commit') {
+        else if (args[i] === '--git') {
             gitCommit = true;
         }
+        else if (args[i] === '--no-git') {
+            gitCommit = false;
+        }
         else if (args[i] === '--prompt' && i + 1 < args.length) {
             promptFile = args[++i];
         }
@@ -88,6 +147,21 @@ function parseArgs() {
                 continuePrompt = args[++i];
             }
         }
+        else if (args[i] === '--index' && i + 1 < args.length) {
+            issueIndex = args[++i];
+        }
+        else if (!args[i].startsWith('--')) {
+            // Non-flag argument - collect as issue reference for issue command
+            if (command === 'issue') {
+                issueReferences.push(args[i]);
+            }
+        }
+    }
+    // Validate issue command
+    if (command === 'issue' && issueReferences.length === 0) {
+        console.error(`${colors.red}Error: "issue" command requires at least one issue reference.${colors.reset}\n`);
+        showHelp();
+        process.exit(1);
     }
     return {
         issuesDir,
@@ -97,6 +171,9 @@ function parseArgs() {
         promptFile,
         continueMode,
         continuePrompt,
+        command: command,
+        issueReferences,
+        issueIndex,
     };
 }
 async function ensureDirectories(issuesDir, faqDir) {
@@ -136,7 +213,7 @@ function gitCommit(issueFile, status) {
                 encoding: 'utf-8',
             }).trim();
             if (!untrackedFiles) {
-                console.log('No changes to commit');
+                console.log(`${colors.cyan}No changes to commit${colors.reset}`);
                 return;
             }
         }
@@ -150,10 +227,10 @@ function gitCommit(issueFile, status) {
         execSync(`git commit -m "${commitMessage.replace(/"/g, '\\"')}"`, {
             stdio: 'inherit',
         });
-        console.log(`\nGit commit created: ${commitMessage}`);
+        console.log(`${colors.green}\nGit commit created: ${commitMessage}${colors.reset}`);
     }
     catch (error) {
-        console.error(`Failed to create git commit: ${String(error)}`);
+        console.error(`${colors.red}Failed to create git commit: ${String(error)}${colors.reset}`);
     }
 }
 function getDefaultPromptTemplate() {
@@ -205,9 +282,16 @@ Here is a summary of the work I have done:
 
 Your issue file: [ISSUE_FILE_PATH]
 
+Issue files may be long. Use CLI commands to read:
+- To summarize: \`npx bueller-wheel issue [ISSUE_FILE_PATH]\`
+- To expand: \`npx bueller-wheel issue [ISSUE_FILE_PATH] --index <start>,<end>\`
+
 1. **Read the issue**: Parse the conversation history in [ISSUE_FILE_PATH] to understand the task
 2. **Work on the task**: Do what the issue requests. When encountering issues, always check for a relevant guide in [FAQ_DIR]/ first.
-3. **Append your response**: Add your summary to [ISSUE_FILE_PATH] using this format:
+3. **Verify**: Verify the following pass:
+   - [ ] \`pnpm run lint:fix\`
+   - [ ] \`pnpm run typecheck\`
+4. **Append your response**: Add your summary to [ISSUE_FILE_PATH] using this format:
    \`\`\`
    ---
 
@@ -219,7 +303,7 @@ Your issue file: [ISSUE_FILE_PATH]
    - Item 3
    \`\`\`
 
-4. **Decide the outcome**: Choose ONE of the following actions:
+5. **Decide the outcome**: Choose ONE of the following actions:
 
    a. **CONTINUE** - You made progress but the task isn't complete yet
       - Leave the issue in \`[ISSUES_DIR]/[ISSUE_DIR_OPEN]/\` for the next iteration
@@ -250,18 +334,22 @@ Your issue file: [ISSUE_FILE_PATH]
 
 **Critical:** ALWAYS check the FAQ directory ([FAQ_DIR]/) to see if there is a guide when you encounter a problem.
 
+## Adding to the FAQ
+
+Consider adding a **CONCISE** FAQ in [FAQ_DIR]/ for non-obvious solutions, recurring issues, or multi-step troubleshooting that would help future agents. Skip trivial/one-off problems or topics already documented.
+
 Now, please process the issue at [ISSUE_FILE_PATH].`;
 }
 async function loadOrCreatePromptTemplate(promptFile) {
     // If prompt file exists, load it
     try {
         await fs.access(promptFile);
-        console.log(`Loading prompt template from: ${promptFile}`);
+        console.log(`${colors.cyan}Loading prompt template from: ${promptFile}${colors.reset}`);
         return await fs.readFile(promptFile, 'utf-8');
     }
     catch {
         // Otherwise, create the default prompt template
-        console.log(`Prompt file not found. Creating default template at: ${promptFile}`);
+        console.log(`${colors.yellow}Prompt file not found. Creating default template at: ${promptFile}${colors.reset}`);
         const defaultTemplate = getDefaultPromptTemplate();
         // Ensure the directory exists
         const promptDir = path.dirname(promptFile);
@@ -289,7 +377,7 @@ function buildSystemPrompt(template, issuesDir, faqDir, issueFile) {
 }
 function logToolUse(block) {
     process.stdout.write('\n');
-    process.stdout.write(`[${block.name}] `);
+    process.stdout.write(`${colors.cyan}[${block.name}]${colors.reset} `);
     switch (block.name.toLowerCase()) {
         case 'read':
         case 'write':
@@ -302,18 +390,33 @@ function logToolUse(block) {
         case 'glob':
             process.stdout.write(`${block.input?.pattern}`);
             break;
+        case 'grep': {
+            const pattern = block.input?.pattern;
+            const glob = block.input?.glob;
+            const path = block.input?.path;
+            if (pattern) {
+                process.stdout.write(`${pattern}`);
+            }
+            if (glob) {
+                process.stdout.write(` (${glob})`);
+            }
+            if (path) {
+                process.stdout.write(` (${path})`);
+            }
+            break;
+        }
         case 'todowrite': {
             for (const todo of block.input?.todos ?? []) {
                 process.stdout.write('\n');
                 switch (todo.status) {
                     case 'in_progress':
-                        process.stdout.write('⧖');
+                        process.stdout.write(`${colors.yellow}⧖${colors.reset}`);
                         break;
                     case 'pending':
                         process.stdout.write('☐');
                         break;
                     case 'completed':
-                        process.stdout.write('✓');
+                        process.stdout.write(`${colors.green}✓${colors.reset}`);
                         break;
                     default:
                         process.stdout.write(todo.status);
@@ -361,24 +464,62 @@ function logSDKMessage(item) {
 async function runAgent(options) {
     const { template, issuesDir, faqDir, issueFile, continueMode, continuePrompt } = options;
     const systemPrompt = buildSystemPrompt(template, issuesDir, faqDir, issueFile);
-    console.log('\n--- Starting agent ---');
+    console.log(`${colors.blue}\n--- Starting agent ---${colors.reset}`);
     const stream = query({
         prompt: continueMode ? continuePrompt : systemPrompt,
         options: {
             settingSources: ['local', 'project', 'user'],
             permissionMode: 'acceptEdits',
             continue: continueMode,
+            canUseTool: async (toolName, input) => {
+                console.log(`${colors.red}Auto-denied tool:${colors.reset} ${toolName} ${String(input?.['command'] ?? input?.['file_path'] ?? '')}`);
+                return {
+                    behavior: 'deny',
+                    message: `You are running autonomously. The user cannot grant permission. Find a workaround or mark the issue as stuck. Check ${faqDir}/ to see if this is covered.`,
+                };
+            },
         },
     });
     for await (const item of stream) {
         logSDKMessage(item);
     }
-    console.log('\n--- Agent finished ---');
+    console.log(`${colors.blue}\n--- Agent finished ---${colors.reset}`);
+}
+async function runIssue(config) {
+    for (const issueRef of config.issueReferences) {
+        // Normalize issue reference - add .md extension if missing
+        let normalizedRef = issueRef;
+        if (!issueRef.endsWith('.md')) {
+            normalizedRef = `${issueRef}.md`;
+        }
+        const located = await resolveIssueReference(normalizedRef, config.issuesDir);
+        if (!located) {
+            console.error(`${colors.red}Error: Could not find issue: ${issueRef}${colors.reset}\n`);
+            continue;
+        }
+        try {
+            let summary = await summarizeIssue(located);
+            // Apply index expansion if specified
+            if (config.issueIndex) {
+                summary = expandMessages(summary, config.issueIndex);
+            }
+            const formatted = formatIssueSummary(summary, config.issueIndex);
+            console.log(formatted);
+        }
+        catch (error) {
+            console.error(`${colors.red}Error summarizing ${issueRef}: ${String(error)}${colors.reset}\n`);
+        }
+    }
 }
 async function main() {
     const config = parseArgs();
-    console.log('Bueller? Bueller?');
-    console.log('-----------------');
+    // Handle issue command
+    if (config.command === 'issue') {
+        await runIssue(config);
+        return;
+    }
+    console.log(`${colors.cyan}Bueller? Bueller?${colors.reset}`);
+    console.log(`${colors.cyan}-----------------${colors.reset}`);
     console.log(`Issues directory: ${config.issuesDir}`);
     console.log(`FAQ directory: ${config.faqDir}`);
     console.log(`Max iterations: ${config.maxIterations}`);
@@ -393,21 +534,23 @@ async function main() {
     let iteration = 0;
     while (iteration < config.maxIterations) {
         iteration++;
-        console.log(`\n### Iteration ${iteration} ###\n`);
+        console.log(`${colors.yellow}\n### Iteration ${iteration} ###${colors.reset}\n`);
         const openIssues = await getOpenIssues(config.issuesDir);
         if (openIssues.length === 0) {
-            console.log('No more issues in open/. Exiting.');
+            console.log(`${colors.green}No more issues in open/. Exiting.${colors.reset}`);
             break;
         }
         console.log(`Found ${openIssues.length} open issue(s)`);
         console.log(`Next issue: ${openIssues[0]}`);
         const currentIssue = openIssues[0];
+        // Only use continue mode on the first iteration
+        const isFirstIteration = iteration === 1;
         await runAgent({
             template: promptTemplate,
             issuesDir: config.issuesDir,
             faqDir: config.faqDir,
             issueFile: currentIssue,
-            continueMode: config.continueMode,
+            continueMode: config.continueMode && isFirstIteration,
             continuePrompt: config.continuePrompt,
         });
         // Auto-commit if enabled and there's a current issue
@@ -451,12 +594,12 @@ async function main() {
         }
     }
     if (iteration >= config.maxIterations) {
-        console.log(`\nReached maximum iterations (${config.maxIterations}). Exiting.`);
+        console.log(`${colors.yellow}\nReached maximum iterations (${config.maxIterations}). Exiting.${colors.reset}`);
     }
-    console.log('\nDone!');
+    console.log(`${colors.green}\nDone!${colors.reset}`);
 }
 main().catch((error) => {
-    console.error('Error:', error);
+    console.error(`${colors.red}Error:${colors.reset}`, error);
     process.exit(1);
 });
 //# sourceMappingURL=index.js.map

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "bueller-wheel",
-	"version": "0.1.0",
+	"version": "0.3.0",
 	"description": "Headless Claude Code issue processor - A wrapper that runs Claude Code in a loop to process issues from a directory queue",
 	"type": "module",
 	"main": "dist/index.js",