nex-code 0.3.14 → 0.3.19

package/README.md

@@ -22,7 +22,7 @@
   <img src="https://img.shields.io/badge/Ollama_Cloud-supported-brightgreen.svg" alt="Ollama Cloud: supported">
   <img src="https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg" alt="Node >= 18">
   <img src="https://img.shields.io/badge/dependencies-2-green.svg" alt="Dependencies: 2">
-  <img src="https://img.shields.io/badge/tests-1752-blue.svg" alt="Tests: 1752">
+  <img src="https://img.shields.io/badge/tests-1825-blue.svg" alt="Tests: 1825">
 </p>
 
 ---
@@ -78,10 +78,13 @@ npm update -g nex-code
 | **Undo / Redo** | ✅ | ❌ | ❌ | ❌ |
 | **Cost tracking + budgets** | ✅ | ❌ | ❌ | ❌ |
 | **Pre-push secret detection** | ✅ | ❌ | ❌ | ❌ |
+| **Browser agent (headless)** | ✅ Playwright-based | ❌ | ⚠️ Experimental | ❌ |
+| **Grounded web search** | ✅ Perplexity/DDG | ❌ | ✅ Google grounded | ❌ |
+| **GitHub Actions tools** | ✅ native | ❌ | ❌ | ❌ |
 | **Open-source** | ✅ MIT | ❌ | ✅ Apache 2.0 | ✅ |
 | **Runtime dependencies** | **2** (axios, dotenv) | Many | Many | Heavy (Python) |
 | **Startup time** | **~100ms** | ~400ms | ~300ms | Slow |
-| **Test coverage** | 1752 tests, 85% | — | — | — |
+| **Test coverage** | 1825 tests, 84% | — | — | — |
 
 ---
 
@@ -142,6 +145,7 @@ OLLAMA_API_KEY=your-key       # Ollama Cloud (Qwen3 Coder, Qwen3.5, DeepSeek R1,
 OPENAI_API_KEY=your-key       # OpenAI (GPT-4o, GPT-4.1, o1, o3, o4-mini)
 ANTHROPIC_API_KEY=your-key    # Anthropic (Claude Sonnet 4.6, Opus 4.6, Haiku 4.5)
 GEMINI_API_KEY=your-key       # Google Gemini (3.1 Pro Preview, 2.5 Pro/Flash, 2.0 Flash)
+PERPLEXITY_API_KEY=your-key   # Perplexity (optional — enables grounded web search)
 # No key needed for local Ollama — just have it running
 ```
 
@@ -225,6 +229,36 @@ Supported formats: PNG, JPG, GIF, WebP, BMP. Works with Anthropic, OpenAI, Gemin
 
 Skip all confirmation prompts — file changes, dangerous commands, and tool permissions are auto-approved. The banner shows a `⚡ YOLO` indicator. Toggle at runtime with `/autoconfirm`.
 
+### Headless / Programmatic Mode
+
+Run nex-code non-interactively from scripts, CI pipelines, or other processes:
+
+```bash
+# Inline prompt
+nex-code --task "refactor src/index.js to use async/await" --yolo
+
+# Prompt from file (avoids shell-escaping issues with special characters)
+nex-code --prompt-file /tmp/task.txt --yolo
+
+# Delete the file after reading
+nex-code --prompt-file /tmp/task.txt --delete-prompt-file --yolo
+
+# JSON output for programmatic parsing
+nex-code --prompt-file /tmp/task.txt --yolo --json
+# → {"success":true,"response":"..."}
+```
+
+| Flag | Description |
+|------|-------------|
+| `--task <prompt>` | Run a single prompt and exit |
+| `--prompt-file <path>` | Read prompt from a UTF-8 file and run headless |
+| `--delete-prompt-file` | Delete the prompt file after reading (use with `--prompt-file`) |
+| `--auto` | Skip confirmations (non-interactive, no REPL banner) |
+| `--yolo` | Skip all confirmations including dangerous commands |
+| `--json` | Output `{"success":true,"response":"..."}` to stdout |
+| `--max-turns <n>` | Override the agentic loop iteration limit |
+| `--model <spec>` | Use a specific model (e.g. `anthropic:claude-sonnet-4-6`) |
+
 ---
 
 ## Providers & Models
@@ -317,13 +351,22 @@ The agent has 17 built-in tools:
 | `git_diff` | Git diff with optional path filter |
 | `git_log` | Git commit history with configurable count |
 | `web_fetch` | Fetch content from a URL |
-| `web_search` | Search the web via DuckDuckGo |
+| `web_search` | Grounded search via Perplexity (if `PERPLEXITY_API_KEY` set) or DuckDuckGo |
 | `ask_user` | Ask the user a question and wait for input |
 | `task_list` | Create and manage task lists for multi-step operations |
 | `spawn_agents` | Run parallel sub-agents with auto model routing |
+| `browser_open` | Open URL in headless browser, return text + links (JS-heavy pages) |
+| `browser_screenshot` | Screenshot a URL → saved file + vision-ready path |
+| `browser_click` | Click element by CSS selector or visible text |
+| `browser_fill` | Fill form field and optionally submit |
+| `gh_run_list` | List GitHub Actions workflow runs |
+| `gh_run_view` | View run details and step logs |
+| `gh_workflow_trigger` | Trigger a workflow dispatch event |
 
 **Interactive commands** (vim, top, htop, ssh, tmux, fzf, etc.) are automatically detected and spawned with full TTY passthrough — no separate handling required.
 
+**Browser tools** require Playwright (`npm install playwright && npx playwright install chromium`). nex-code works without it — browser tools return a helpful install message if missing.
+
 Additional tools can be added via [MCP servers](#mcp) or [Skills](#skills).
 
 ---
@@ -782,7 +825,7 @@ npm test              # Run all tests with coverage
 npm run test:watch    # Watch mode
 ```
 
-44 test suites, 1752 tests, 85% statement / 79% branch coverage.
+47 test suites, 1825 tests, 84% statement / 77% branch coverage.
 
 CI runs on GitHub Actions (Node 18/20/22).