@link-assistant/hive-mind 0.46.1 → 0.47.1

package/CHANGELOG.md

@@ -1,11 +1,30 @@
 # @link-assistant/hive-mind
 
+## 0.47.1
+
+### Patch Changes
+
+- 68c0417: Fix Rocq installation verification by sourcing opam environment
+  - Source opam environment before verifying Rocq in installation summary
+  - Use `rocq -v` for verification as recommended by official documentation
+  - Update CI workflow to require Rocq to be accessible (not optional)
+  - Add case study documenting the issue and solution
+
+## 0.47.0
+
+### Minor Changes
+
+- 1351ffe: Add Prettier for automatic code formatting with ESLint integration
+  - Added Prettier configuration with project code style settings
+  - Created format and format:check npm scripts for code formatting
+  - Integrated Prettier with ESLint to warn about formatting issues
+  - Added eslint-config-prettier and eslint-plugin-prettier dependencies
+
 ## 0.46.1
 
 ### Patch Changes
 
 - 3707189: Implement fail-fast CI strategy for release.yml workflow
-
   - Added dependency ordering so long-running checks wait for all fast checks to pass
   - Fast checks (test-compilation, lint, check-file-line-limits) run first (~7-21s each)
   - Long-running checks (test-suites, test-execution, memory-check-linux, docker-pr-check) only run after fast checks pass
@@ -13,7 +32,6 @@
   - Added section markers to clearly document FAST vs LONG-RUNNING checks in the workflow
 
   Benefits:
-
   - Time savings: If fast checks fail, ~4+ minutes of long-running tests are skipped
   - Faster feedback: Developers get quick feedback on common issues
   - Resource efficiency: Reduces unnecessary GitHub Actions minutes consumption
@@ -41,7 +59,6 @@
 - b72136f: Add /version command to hive-telegram-bot
 
   Implements a new /version command that displays comprehensive version information including:
-
   - Bot version (package version with git commit SHA in development)
   - solve and hive command versions
   - Node.js runtime version
@@ -56,7 +73,6 @@
   The `perlbrew available` command output was not being parsed correctly, causing the installation script to skip Perl installation with the message "Could not determine latest Perl version."
 
   **Changes:**
-
   - Use `grep -oE` to robustly extract Perl version strings regardless of line formatting
   - Capture stderr from `perlbrew available` for better debugging
   - Add debug output showing `perlbrew available` response when version detection fails
@@ -75,7 +91,6 @@
   This release introduces a new opt-in feature that enables the AI to automatically create GitHub issues when it spots bugs, errors, or minor issues during working sessions that are not related to the main task.
 
   **New Features:**
-
   - Added `--prompt-issue-reporting` CLI flag (disabled by default)
   - Issues include reproducible examples, workarounds, and fix suggestions
   - Supports creating issues in both current and third-party repositories
@@ -89,7 +104,6 @@
   ```
 
   **Implementation:**
-
   - New guideline in system prompt (conditional on flag)
   - Flag added to both `hive` and `solve` commands
   - Uses `gh` CLI for authenticated issue creation (works with private repos)
@@ -101,7 +115,6 @@
 ### Patch Changes
 
 - 64d6cf8: Add experimental /top command to Telegram bot
-
   - Added /top command to show live system monitor in Telegram
   - Displays auto-updating `top` output in a single message (updates every 2 seconds)
   - Owner-only access with chat authorization checks
@@ -118,7 +131,6 @@
 ### Patch Changes
 
 - dca5bed: Make --auto-continue enabled by default
-
   - Changed default value from false to true for --auto-continue in both hive and solve commands
   - Smart handling of -s (--skip-issues-with-prs) flag interaction:
     - When -s is used, auto-continue is automatically disabled to avoid conflicts
@@ -133,7 +145,6 @@
 ### Patch Changes
 
 - acd70a9: Add Lean runtime preinstallation support via elan
-
   - Install elan (Lean version manager) with stable toolchain in all deployment environments
   - Add Lean/elan to PATH in Dockerfile, .gitpod.Dockerfile, coolify/Dockerfile
   - Add installation verification for elan, lean, and lake commands
@@ -144,7 +155,6 @@
 ### Minor Changes
 
 - d98d9c9: Add Java (OpenJDK) runtime installation support via SDKMAN in Ubuntu 24 server installation script
-
   - Install SDKMAN as Java version manager (following pattern of pyenv for Python, nvm for Node.js)
   - Install Java 21 LTS (Eclipse Temurin distribution) by default with fallback to OpenJDK
   - Add SDKMAN configuration to .bashrc for persistence
@@ -163,7 +173,6 @@
 
 - f77fdf8: Add Golang runtime installation support to Ubuntu 24 server installation script with proper success verification
 - ca4d83d: Add preinstalled Rocq (formerly Coq) theorem prover runtime support
-
   - Install opam (OCaml package manager) as prerequisite
   - Configure Rocq-released repository for package installation
   - Add Rocq prover with fallback to classic Coq package if unavailable
@@ -198,7 +207,6 @@
   When users provide URLs with backslashes (e.g., `https://github.com/owner/repo/issues/123\`), the system now properly validates them and provides helpful error messages with auto-corrected URL suggestions. According to RFC 3986, backslash is not a valid character in URL paths.
 
   **Changes:**
-
   - Enhanced `parseGitHubUrl()` function to detect backslashes in URL paths
   - Updated all validation points (Telegram bot `/solve` and `/hive` commands, CLI `hive` and `solve` commands)
   - Provides user-friendly error messages with corrected URL suggestions
@@ -215,7 +223,6 @@
   When a work session completes successfully but the CLAUDE.md commit hash was lost between sessions (e.g., due to session interruption), the system now attempts to detect the CLAUDE.md commit from the branch structure instead of silently skipping cleanup.
 
   **Safety Checks (Preventing Issue #617 Recurrence):**
-
   1. CLAUDE.md must exist in current branch
   2. Find merge base to isolate PR-only commits
   3. Must have at least 2 commits (CLAUDE.md + actual work)
@@ -241,7 +248,6 @@
 ### Patch Changes
 
 - f8ebd99: Make Playwright MCP usage guidelines conditional based on MCP availability
-
   - Add `checkPlaywrightMcpAvailability()` function to detect if Playwright MCP is installed
   - Conditionally include Playwright MCP section in Claude system prompt only when MCP is detected
   - Integration in both main execution (solve.mjs) and watch mode (solve.watch.lib.mjs)
@@ -272,7 +278,6 @@
 ### Patch Changes
 
 - 40545f6: Consolidate CI/CD workflows to single release.yml following js-ai-driven-development-pipeline-template best practices
-
   - Removed verify-version-bump job (replaced by changeset-check)
   - Consolidated main.yml, ci.yml, and helm-pr-check.yml into release.yml
   - Added template scripts for release automation (validate-changeset, version-and-commit, publish-to-npm, etc.)

package/README.md

@@ -47,6 +47,7 @@ There are infinite ways to extract tokens from a virtual machine connected to th
 **USE THIS SOFTWARE ENTIRELY AT YOUR OWN RISK AND RESPONSIBILITY.**
 
 We strongly recommend:
+
 - Using dedicated, isolated virtual machines
 - Rotating tokens regularly
 - Monitoring token usage for suspicious activity
@@ -54,6 +55,7 @@ We strongly recommend:
 - Being prepared to revoke and replace all tokens used with this system
 
 Minimum system requirements to run `hive.mjs`:
+
 ```
 1 CPU Core
 1 GB RAM
@@ -66,11 +68,13 @@ Minimum system requirements to run `hive.mjs`:
 ### Global Installation
 
 #### Using Bun (Recommended)
+
 ```bash
 bun install -g @link-assistant/hive-mind
 ```
 
 #### Using Node.js
+
 ```bash
 npm install -g @link-assistant/hive-mind
 ```
@@ -113,6 +117,7 @@ solve https://github.com/owner/repo/issues/123
 ```
 
 **Benefits of Docker:**
+
 - ✅ Pre-configured Ubuntu 24.04 environment
 - ✅ All dependencies pre-installed
 - ✅ Isolated from your host system
@@ -138,6 +143,7 @@ helm install hive-mind link-assistant/hive-mind -f values.yaml
 ```
 
 **Benefits of Helm:**
+
 - ✅ Easy deployment to Kubernetes clusters
 - ✅ Declarative configuration management
 - ✅ Simple upgrades and rollbacks
@@ -153,17 +159,21 @@ See [docs/HELM.md](./docs/HELM.md) for detailed Helm configuration options.
 1. Reset/install VPS/VDS server with fresh Ubuntu 24.04
 2. Login to `root` user.
 3. Execute main installation script
+
    ```bash
    curl -fsSL -o- https://github.com/link-assistant/hive-mind/raw/refs/heads/main/scripts/ubuntu-24-server-install.sh | bash
    ```
+
    **Note:** The installation script will NOT run `gh auth login` automatically. This is intentional to support Docker builds without timeouts. Authentication is performed in the next steps.
 
 4. Login to `hive` user
+
    ```bash
    su - hive
    ```
 
 5. **IMPORTANT:** Authenticate with GitHub CLI AFTER installation is complete
+
    ```bash
    gh auth login -h github.com -s repo,workflow,user,read:org,gist
 
@@ -177,9 +187,11 @@ See [docs/HELM.md](./docs/HELM.md) for detailed Helm configuration options.
    git config --global user.name
    git config --global user.email
    ```
+
    Note: Follow the prompts to authenticate with your GitHub account. This is required for the gh tool to work, and the system will perform all actions using this GitHub account. This step must be done AFTER the installation script completes to avoid build timeouts in Docker environments.
 
 6. Claude Code CLI, OpenCode AI CLI, and @link-assistant/agent are preinstalled with the previous script. Now you need to make sure claude is authorized. Execute claude command, and follow all steps to authorize the local claude
+
    ```bash
    claude
    ```
@@ -189,6 +201,7 @@ See [docs/HELM.md](./docs/HELM.md) for detailed Helm configuration options.
 7. Launch the Hive Mind telegram bot:
 
    **Using Links Notation (recommended):**
+
    ```
    screen -S bot # Enter new screen for bot
 
@@ -215,6 +228,7 @@ See [docs/HELM.md](./docs/HELM.md) for detailed Helm configuration options.
    ```
 
    **Using individual command-line options:**
+
    ```
    screen -S bot # Enter new screen for bot
 
@@ -239,10 +253,10 @@ See [docs/HELM.md](./docs/HELM.md) for detailed Helm configuration options.
 
    Note: You may need to register you own bot with https://t.me/BotFather to get the bot token.
 
-
 #### Codex sign-in
 
 1. Connect to your instance of VPS with Hive Mind installed, using SSH with tunnel opened
+
 ```bash
 ssh -L 1455:localhost:1455 root@123.123.123.123
 ```
@@ -252,11 +266,13 @@ ssh -L 1455:localhost:1455 root@123.123.123.123
 ```bash
 codex login
 ```
+
 The oAuth callback server on 1455 port will be started, and the link to oAuth will be printed, copy the link.
 
 3. Use your browser on machine where you started the tunnel from, paste there the link from `codex login` command, and go there using your browser. Once redirected to localhost:1455 you will see successful login page, and in `codex login` you will see `Successfully logged in`. After that `codex login` command will complete, and you can use `codex` command as usual to verify. It should also be working with `--tool codex` in `solve` and `hive` commands.
 
 ### Core Operations
+
 ```bash
 # Solve using maximum power
 solve https://github.com/Veronika89-lang/index.html/issues/1 --auto-continue --attach-logs --verbose --model opus --auto-fork --think max
@@ -288,17 +304,18 @@ review --repo owner/repo --pr 456
 
 ## 📋 Core Components
 
-| Script | Purpose | Key Features |
-|--------|---------|--------------|
-| `solve.mjs` (stable) | GitHub issue solver | Auto fork, branch creation, PR generation, resume sessions, fork support |
-| `hive.mjs` (stable) | AI orchestration & monitoring | Multi-repo monitoring, concurrent workers, issue queue management |
-| `review.mjs` (alpha) | Code review automation | Collaborative AI reviews, automated feedback |
-| `reviewers-hive.mjs` (alpha / experimental) | Review team management | Multi-agent consensus, reviewer assignment |
-| `telegram-bot.mjs` (stable) | Telegram bot interface | Remote command execution, group chat support, diagnostic tools |
+| Script                                      | Purpose                       | Key Features                                                             |
+| ------------------------------------------- | ----------------------------- | ------------------------------------------------------------------------ |
+| `solve.mjs` (stable)                        | GitHub issue solver           | Auto fork, branch creation, PR generation, resume sessions, fork support |
+| `hive.mjs` (stable)                         | AI orchestration & monitoring | Multi-repo monitoring, concurrent workers, issue queue management        |
+| `review.mjs` (alpha)                        | Code review automation        | Collaborative AI reviews, automated feedback                             |
+| `reviewers-hive.mjs` (alpha / experimental) | Review team management        | Multi-agent consensus, reviewer assignment                               |
+| `telegram-bot.mjs` (stable)                 | Telegram bot interface        | Remote command execution, group chat support, diagnostic tools           |
 
 > **Note**: For a comprehensive analysis of the "Could not process image" error in AI issue solvers, see the [Case Study: Issue #597](docs/case-studies/issue-597/README.md). The case study includes root cause analysis, timeline reconstruction, and evidence of GitHub's time-limited S3 URLs causing image processing failures. Separate tools for downloading GitHub issues and PRs with embedded images are being developed at [gh-download-issue](https://github.com/link-foundation/gh-download-issue) and [gh-download-pull-request](https://github.com/link-foundation/gh-download-pull-request).
 
 ## 🔧 solve Options
+
 ```bash
 solve <issue-url> [options]
 
@@ -350,6 +367,7 @@ solve <issue-url> [options]
 ```
 
 ## 🔧 hive Options
+
 ```bash
 hive <github-url> [options]
 
@@ -412,6 +430,7 @@ Want to see the Hive Mind in action? Join our Telegram channel where you can exe
    - Add the bot to your group chat and make it an admin
 
 2. **Configure Environment**
+
    ```bash
    # Copy the example configuration
    cp .env.example .env
@@ -434,6 +453,7 @@ Want to see the Hive Mind in action? Join our Telegram channel where you can exe
 All commands work in **group chats only** (not in private messages with the bot):
 
 #### `/solve` - Solve GitHub Issues
+
 ```
 /solve <github-url> [options]
 
@@ -444,6 +464,7 @@ Examples:
 ```
 
 #### `/hive` - Run Hive Orchestration
+
 ```
 /hive <github-url> [options]
 
@@ -454,6 +475,7 @@ Examples:
 ```
 
 #### `/help` - Get Help and Diagnostic Info
+
 ```
 /help
 
@@ -490,6 +512,7 @@ The Hive Mind operates on three layers:
 ### Data Flow
 
 #### Mode 1: Issue → Pull Request Flow
+
 ```mermaid
 sequenceDiagram
     participant H as Human
@@ -526,6 +549,7 @@ sequenceDiagram
 ```
 
 #### Mode 2: Pull Request → Comments Flow
+
 ```mermaid
 sequenceDiagram
     participant H as Human
@@ -565,6 +589,7 @@ sequenceDiagram
 ## 📊 Usage Examples
 
 ### Automated Issue Resolution
+
 ```bash
 # Auto-fork and solve issue (automatic fork detection for public repos)
 solve https://github.com/owner/repo/issues/123 --auto-fork --model opus
@@ -583,6 +608,7 @@ solve https://github.com/owner/repo/issues/123 --dry-run
 ```
 
 ### Multi-Repository Orchestration
+
 ```bash
 # Monitor single repository with specific label
 hive https://github.com/owner/repo --monitor-tag "bug" --concurrency 4
@@ -601,6 +627,7 @@ hive https://github.com/org/repo --auto-cleanup --auto-fork --concurrency 5
 ```
 
 ### Session Management
+
 ```bash
 # Resume when Claude hits limit
 solve https://github.com/owner/repo/issues/123 --resume 657e6db1-6eb3-4a8d
@@ -612,6 +639,7 @@ solve https://github.com/owner/repo/issues/123 --resume 657e6db1-6eb3-4a8d
 ## 🔍 Monitoring & Logging
 
 Find resume commands in logs:
+
 ```bash
 grep -E '\(cd /tmp/gh-issue-solver-[0-9]+ && claude --resume [0-9a-f-]{36}\)' hive-*.log
 ```
@@ -619,6 +647,7 @@ grep -E '\(cd /tmp/gh-issue-solver-[0-9]+ && claude --resume [0-9a-f-]{36}\)' hi
 ## 🔧 Configuration
 
 Authentication is handled through:
+
 - `gh auth login` - GitHub CLI authentication
 - `claude-profiles` - Claude authentication profile migration to server
 
@@ -627,18 +656,23 @@ No environment variable configuration is currently supported.
 ## 🐛 Reporting Issues
 
 ### Hive Mind Issues
+
 If you encounter issues with **Hive Mind** (this project), please report them on our GitHub Issues page:
+
 - **Repository**: https://github.com/link-assistant/hive-mind
 - **Issues**: https://github.com/link-assistant/hive-mind/issues
 
 ### Claude Code CLI Issues
+
 If you encounter issues with the **Claude Code CLI** itself (e.g., `claude` command errors, installation problems, or CLI bugs), please report them to the official Claude Code repository:
+
 - **Repository**: https://github.com/anthropics/claude-code
 - **Issues**: https://github.com/anthropics/claude-code/issues
 
 ## 🛡️ File Size Enforcement
 
 All documentation files are automatically checked:
+
 ```bash
 find docs/ -name "*.md" -exec wc -l {} + | awk '$1 > 1000 {print "ERROR: " $2 " has " $1 " lines (max 1000)"}'
 ```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@link-assistant/hive-mind",
-  "version": "0.46.1",
+  "version": "0.47.1",
   "description": "AI-powered issue solver and hive mind for collaborative problem solving",
   "main": "src/hive.mjs",
   "type": "module",
@@ -16,10 +16,13 @@
     "test": "echo \"Error: no test specified\" && exit 1",
     "lint": "eslint 'src/**/*.{js,mjs,cjs}'",
     "lint:fix": "eslint 'src/**/*.{js,mjs,cjs}' --fix",
+    "format": "prettier --write \"**/*.{js,mjs,json,md}\"",
+    "format:check": "prettier --check \"**/*.{js,mjs,json,md}\"",
     "changeset": "changeset",
     "changeset:version": "changeset version",
     "changeset:publish": "npm run build:pre && changeset publish",
-    "build:pre": "chmod +x src/hive.mjs && chmod +x src/solve.mjs"
+    "build:pre": "chmod +x src/hive.mjs && chmod +x src/solve.mjs",
+    "prepare": "husky"
   },
   "repository": {
     "type": "git",
@@ -49,10 +52,20 @@
   "devDependencies": {
     "@changesets/cli": "^2.27.0",
     "@eslint/js": "^9.35.0",
-    "eslint": "^9.35.0"
+    "eslint": "^9.35.0",
+    "eslint-config-prettier": "^10.1.8",
+    "eslint-plugin-prettier": "^5.5.4",
+    "husky": "^9.1.7",
+    "lint-staged": "^16.2.7",
+    "prettier": "^3.6.2"
   },
   "dependencies": {
     "@sentry/node": "^10.15.0",
     "@sentry/profiling-node": "^10.15.0"
+  },
+  "lint-staged": {
+    "*.{js,mjs,json,md}": [
+      "prettier --write"
+    ]
   }
 }