Merge branch 'main' into feat/discord-support

.dockerignore

@@ -0,0 +1,13 @@
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+*.egg-info
+dist/
+build/
+.git
+.env
+.assets
+node_modules/
+bridge/dist/
+workspace/

Dockerfile

@@ -0,0 +1,40 @@
+FROM ghcr.io/astral-sh/uv:python3.12-bookworm-slim
+
+# Install Node.js 20 for the WhatsApp bridge
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends curl ca-certificates gnupg git && \
+    mkdir -p /etc/apt/keyrings && \
+    curl -fsSL https://deb.nodesource.com/gpgkey/nodesource-repo.gpg.key | gpg --dearmor -o /etc/apt/keyrings/nodesource.gpg && \
+    echo "deb [signed-by=/etc/apt/keyrings/nodesource.gpg] https://deb.nodesource.com/node_20.x nodistro main" > /etc/apt/sources.list.d/nodesource.list && \
+    apt-get update && \
+    apt-get install -y --no-install-recommends nodejs && \
+    apt-get purge -y gnupg && \
+    apt-get autoremove -y && \
+    rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Install Python dependencies first (cached layer)
+COPY pyproject.toml README.md LICENSE ./
+RUN mkdir -p nanobot bridge && touch nanobot/__init__.py && \
+    uv pip install --system --no-cache . && \
+    rm -rf nanobot bridge
+
+# Copy the full source and install
+COPY nanobot/ nanobot/
+COPY bridge/ bridge/
+RUN uv pip install --system --no-cache .
+
+# Build the WhatsApp bridge
+WORKDIR /app/bridge
+RUN npm install && npm run build
+WORKDIR /app
+
+# Create config directory
+RUN mkdir -p /root/.nanobot
+
+# Gateway default port
+EXPOSE 18790
+
+ENTRYPOINT ["nanobot"]
+CMD ["status"]

README.md

@@ -8,6 +8,7 @@
     <img src="https://img.shields.io/badge/license-MIT-green" alt="License">
     <a href="./COMMUNICATION.md"><img src="https://img.shields.io/badge/Feishu-Group-E9DBFC?style=flat&logo=feishu&logoColor=white" alt="Feishu"></a>
     <a href="./COMMUNICATION.md"><img src="https://img.shields.io/badge/WeChat-Group-C5EAB4?style=flat&logo=wechat&logoColor=white" alt="WeChat"></a>
+    <a href="https://discord.gg/MnCvHqpUGB"><img src="https://img.shields.io/badge/Discord-Community-5865F2?style=flat&logo=discord&logoColor=white" alt="Discord"></a>
   </p>
 </div>
 
@@ -17,7 +18,7 @@
 
 ## 📢 News
 
-- **2025-02-01** 🎉 nanobot launched! Welcome to try 🐈 nanobot!
+- **2026-02-01** 🎉 nanobot launched! Welcome to try 🐈 nanobot!
 
 ## Key Features of nanobot:
 
@@ -60,13 +61,7 @@
 
 ## 📦 Install
 
-**Install from PyPi**
+**Install from source** (latest features, recommended for development)
-
-```bash
-pip install nanobot-ai
-```
-
-**Install from source** (recommended for development)
 
 ```bash
 git clone https://github.com/HKUDS/nanobot.git
@@ -74,6 +69,18 @@ cd nanobot
 pip install -e .
 ```
 
+**Install with [uv](https://github.com/astral-sh/uv)** (stable, fast)
+
+```bash
+uv tool install nanobot-ai
+```
+
+**Install from PyPI** (stable)
+
+```bash
+pip install nanobot-ai
+```
+
 ## 🚀 Quick Start
 
 > [!TIP]
@@ -279,6 +286,22 @@ nanobot gateway
 
 ## ⚙️ Configuration
 
+Config file: `~/.nanobot/config.json`
+
+### Providers
+
+> [!NOTE]
+> Groq provides free voice transcription via Whisper. If configured, Telegram voice messages will be automatically transcribed.
+
+| Provider | Purpose | Get API Key |
+|----------|---------|-------------|
+| `openrouter` | LLM (recommended, access to all models) | [openrouter.ai](https://openrouter.ai) |
+| `anthropic` | LLM (Claude direct) | [console.anthropic.com](https://console.anthropic.com) |
+| `openai` | LLM (GPT direct) | [platform.openai.com](https://platform.openai.com) |
+| `groq` | LLM + **Voice transcription** (Whisper) | [console.groq.com](https://console.groq.com) |
+| `gemini` | LLM (Gemini direct) | [aistudio.google.com](https://aistudio.google.com) |
+
+
 <details>
 <summary><b>Full config example</b></summary>
 
@@ -292,6 +315,9 @@ nanobot gateway
   "providers": {
     "openrouter": {
       "apiKey": "sk-or-v1-xxx"
+    },
+    "groq": {
+      "apiKey": "gsk_xxx"
     }
   },
   "channels": {
@@ -350,6 +376,31 @@ nanobot cron remove <job_id>
 
 </details>
 
+## 🐳 Docker
+
+> [!TIP]
+> The `-v ~/.nanobot:/root/.nanobot` flag mounts your local config directory into the container, so your config and workspace persist across container restarts.
+
+Build and run nanobot in a container:
+
+```bash
+# Build the image
+docker build -t nanobot .
+
+# Initialize config (first time only)
+docker run -v ~/.nanobot:/root/.nanobot --rm nanobot onboard
+
+# Edit config on host to add API keys
+vim ~/.nanobot/config.json
+
+# Run gateway (connects to Telegram/WhatsApp)
+docker run -v ~/.nanobot:/root/.nanobot -p 18790:18790 nanobot gateway
+
+# Or run a single command
+docker run -v ~/.nanobot:/root/.nanobot --rm nanobot agent -m "Hello!"
+docker run -v ~/.nanobot:/root/.nanobot --rm nanobot status
+```
+
 ## 📁 Project Structure
 
 ```
@@ -378,6 +429,7 @@ PRs welcome! The codebase is intentionally small and readable. 🤗
 
 **Roadmap** — Pick an item and [open a PR](https://github.com/HKUDS/nanobot/pulls)!
 
+- [x] **Voice Transcription** — Support for Groq Whisper (Issue #13)
 - [ ] **Multi-modal** — See and hear (images, voice, video)
 - [ ] **Long-term memory** — Never forget important context
 - [ ] **Better reasoning** — Multi-step planning and reflection
@@ -390,7 +442,6 @@ PRs welcome! The codebase is intentionally small and readable. 🤗
   <img src="https://contrib.rocks/image?repo=HKUDS/nanobot" />
 </a>
 
----
 
 ## ⭐ Star History
 
@@ -408,3 +459,8 @@ PRs welcome! The codebase is intentionally small and readable. 🤗
   <em> Thanks for visiting ✨ nanobot!</em><br><br>
   <img src="https://visitor-badge.laobi.icu/badge?page_id=HKUDS.nanobot&style=for-the-badge&color=00d4ff" alt="Views">
 </p>
+
+
+<p align="center">
+  <sub>nanobot is for educational, research, and technical exchange purposes only</sub>
+</p>

bridge/src/whatsapp.ts

@@ -160,6 +160,11 @@ export class WhatsAppClient {
       return `[Document] ${message.documentMessage.caption}`;
     }
 
+    // Voice/Audio message
+    if (message.audioMessage) {
+      return `[Voice Message]`;
+    }
+
     return null;
   }
 

nanobot/agent/context.py

@@ -1,5 +1,7 @@
 """Context builder for assembling agent prompts."""
 
+import base64
+import mimetypes
 from pathlib import Path
 from typing import Any
 
@@ -114,32 +116,53 @@ When remembering something, write to {workspace_path}/memory/MEMORY.md"""
         self,
         history: list[dict[str, Any]],
         current_message: str,
-        skill_names: list[str] | None = None
+        skill_names: list[str] | None = None,
+        media: list[str] | None = None,
     ) -> list[dict[str, Any]]:
         """
         Build the complete message list for an LLM call.
-        
+
         Args:
             history: Previous conversation messages.
             current_message: The new user message.
             skill_names: Optional skills to include.
-        
+            media: Optional list of local file paths for images/media.
+
         Returns:
             List of messages including system prompt.
         """
         messages = []
-        
+
         # System prompt
         system_prompt = self.build_system_prompt(skill_names)
         messages.append({"role": "system", "content": system_prompt})
-        
+
         # History
         messages.extend(history)
-        
+
-        # Current message
+        # Current message (with optional image attachments)
-        messages.append({"role": "user", "content": current_message})
+        user_content = self._build_user_content(current_message, media)
-        
+        messages.append({"role": "user", "content": user_content})
+
         return messages
+
+    def _build_user_content(self, text: str, media: list[str] | None) -> str | list[dict[str, Any]]:
+        """Build user message content with optional base64-encoded images."""
+        if not media:
+            return text
+        
+        images = []
+        for path in media:
+            p = Path(path)
+            mime, _ = mimetypes.guess_type(path)
+            if not p.is_file() or not mime or not mime.startswith("image/"):
+                continue
+            b64 = base64.b64encode(p.read_bytes()).decode()
+            images.append({"type": "image_url", "image_url": {"url": f"data:{mime};base64,{b64}"}})
+        
+        if not images:
+            return text
+        return images + [{"type": "text", "text": text}]
     
     def add_tool_result(
         self,

nanobot/agent/loop.py

@@ -152,7 +152,8 @@ class AgentLoop:
         # Build initial messages (use get_history for LLM-formatted messages)
         messages = self.context.build_messages(
             history=session.get_history(),
-            current_message=msg.content
+            current_message=msg.content,
+            media=msg.media if msg.media else None,
         )
         
         # Agent loop

nanobot/channels/manager.py

@@ -37,7 +37,9 @@ class ChannelManager:
             try:
                 from nanobot.channels.telegram import TelegramChannel
                 self.channels["telegram"] = TelegramChannel(
-                    self.config.channels.telegram, self.bus
+                    self.config.channels.telegram,
+                    self.bus,
+                    groq_api_key=self.config.providers.groq.api_key,
                 )
                 logger.info("Telegram channel enabled")
             except ImportError as e:

nanobot/channels/telegram.py

@@ -85,9 +85,10 @@ class TelegramChannel(BaseChannel):
     
     name = "telegram"
     
-    def __init__(self, config: TelegramConfig, bus: MessageBus):
+    def __init__(self, config: TelegramConfig, bus: MessageBus, groq_api_key: str = ""):
         super().__init__(config, bus)
         self.config: TelegramConfig = config
+        self.groq_api_key = groq_api_key
         self._app: Application | None = None
         self._chat_ids: dict[str, int] = {}  # Map sender_id to chat_id for replies
     
@@ -249,7 +250,20 @@ class TelegramChannel(BaseChannel):
                 await file.download_to_drive(str(file_path))
                 
                 media_paths.append(str(file_path))
-                content_parts.append(f"[{media_type}: {file_path}]")
+                
+                # Handle voice transcription
+                if media_type == "voice" or media_type == "audio":
+                    from nanobot.providers.transcription import GroqTranscriptionProvider
+                    transcriber = GroqTranscriptionProvider(api_key=self.groq_api_key)
+                    transcription = await transcriber.transcribe(file_path)
+                    if transcription:
+                        logger.info(f"Transcribed {media_type}: {transcription[:50]}...")
+                        content_parts.append(f"[transcription: {transcription}]")
+                    else:
+                        content_parts.append(f"[{media_type}: {file_path}]")
+                else:
+                    content_parts.append(f"[{media_type}: {file_path}]")
+                    
                 logger.debug(f"Downloaded {media_type} to {file_path}")
             except Exception as e:
                 logger.error(f"Failed to download media: {e}")

nanobot/channels/whatsapp.py

@@ -107,6 +107,11 @@ class WhatsAppChannel(BaseChannel):
             # Extract just the phone number as chat_id
             chat_id = sender.split("@")[0] if "@" in sender else sender
             
+            # Handle voice transcription if it's a voice message
+            if content == "[Voice Message]":
+                logger.info(f"Voice message received from {chat_id}, but direct download from bridge is not yet supported.")
+                content = "[Voice Message: Transcription not available for WhatsApp yet]"
+            
             await self._handle_message(
                 sender_id=chat_id,
                 chat_id=sender,  # Use full JID for replies

nanobot/cli/commands.py

@@ -178,11 +178,13 @@ def gateway(
     # Create components
     bus = MessageBus()
     
-    # Create provider (supports OpenRouter, Anthropic, OpenAI)
+    # Create provider (supports OpenRouter, Anthropic, OpenAI, Bedrock)
     api_key = config.get_api_key()
     api_base = config.get_api_base()
-    
+    model = config.agents.defaults.model
-    if not api_key:
+    is_bedrock = model.startswith("bedrock/")
+
+    if not api_key and not is_bedrock:
         console.print("[red]Error: No API key configured.[/red]")
         console.print("Set one in ~/.nanobot/config.json under providers.openrouter.apiKey")
         raise typer.Exit(1)
@@ -289,11 +291,13 @@ def agent(
     
     api_key = config.get_api_key()
     api_base = config.get_api_base()
-    
+    model = config.agents.defaults.model
-    if not api_key:
+    is_bedrock = model.startswith("bedrock/")
+
+    if not api_key and not is_bedrock:
         console.print("[red]Error: No API key configured.[/red]")
         raise typer.Exit(1)
-    
+
     bus = MessageBus()
     provider = LiteLLMProvider(
         api_key=api_key,
@@ -348,14 +352,15 @@ app.add_typer(channels_app, name="channels")
 def channels_status():
     """Show channel status."""
     from nanobot.config.loader import load_config
-    
+
     config = load_config()
-    
+
     table = Table(title="Channel Status")
     table.add_column("Channel", style="cyan")
     table.add_column("Enabled", style="green")
-    table.add_column("Bridge URL", style="yellow")
+    table.add_column("Configuration", style="yellow")
-    
+
+    # WhatsApp
     wa = config.channels.whatsapp
     table.add_row(
         "WhatsApp",
@@ -363,13 +368,6 @@ def channels_status():
         wa.bridge_url
     )
 
-    tg = config.channels.telegram
-    table.add_row(
-        "Telegram",
-        "✓" if tg.enabled else "✗",
-        "polling"
-    )
-
     dc = config.channels.discord
     table.add_row(
         "Discord",
@@ -377,6 +375,15 @@ def channels_status():
         dc.gateway_url
     )
     
+    # Telegram
+    tg = config.channels.telegram
+    tg_config = f"token: {tg.token[:10]}..." if tg.token else "[dim]not configured[/dim]"
+    table.add_row(
+        "Telegram",
+        "✓" if tg.enabled else "✗",
+        tg_config
+    )
+
     console.print(table)
 
 
@@ -520,6 +527,7 @@ def cron_add(
     at: str = typer.Option(None, "--at", help="Run once at time (ISO format)"),
     deliver: bool = typer.Option(False, "--deliver", "-d", help="Deliver response to channel"),
     to: str = typer.Option(None, "--to", help="Recipient for delivery"),
+    channel: str = typer.Option(None, "--channel", help="Channel for delivery (e.g. 'telegram', 'whatsapp')"),
 ):
     """Add a scheduled job."""
     from nanobot.config.loader import get_data_dir
@@ -548,6 +556,7 @@ def cron_add(
         message=message,
         deliver=deliver,
         to=to,
+        channel=channel,
     )
     
     console.print(f"[green]✓[/green] Added job '{job.name}' ({job.id})")

nanobot/config/schema.py

@@ -60,6 +60,7 @@ class ProvidersConfig(BaseModel):
     anthropic: ProviderConfig = Field(default_factory=ProviderConfig)
     openai: ProviderConfig = Field(default_factory=ProviderConfig)
     openrouter: ProviderConfig = Field(default_factory=ProviderConfig)
+    groq: ProviderConfig = Field(default_factory=ProviderConfig)
     zhipu: ProviderConfig = Field(default_factory=ProviderConfig)
     vllm: ProviderConfig = Field(default_factory=ProviderConfig)
     gemini: ProviderConfig = Field(default_factory=ProviderConfig)
@@ -101,14 +102,14 @@ class Config(BaseSettings):
         return Path(self.agents.defaults.workspace).expanduser()
     
     def get_api_key(self) -> str | None:
-        """Get API key in priority order: OpenRouter > Anthropic > OpenAI > Gemini > vLLM."""
+        """Get API key in priority order: OpenRouter > Anthropic > OpenAI > Gemini > Zhipu > Groq > vLLM."""
-        """Get API key in priority order: OpenRouter > Anthropic > OpenAI > Gemini > Zhipu > vLLM."""
         return (
             self.providers.openrouter.api_key or
             self.providers.anthropic.api_key or
             self.providers.openai.api_key or
             self.providers.gemini.api_key or
             self.providers.zhipu.api_key or
+            self.providers.groq.api_key or
             self.providers.vllm.api_key or
             None
         )

nanobot/providers/litellm_provider.py

@@ -51,6 +51,8 @@ class LiteLLMProvider(LLMProvider):
                 os.environ.setdefault("GEMINI_API_KEY", api_key)
             elif "zhipu" in default_model or "glm" in default_model or "zai" in default_model:
                 os.environ.setdefault("ZHIPUAI_API_KEY", api_key)
+            elif "groq" in default_model:
+                os.environ.setdefault("GROQ_API_KEY", api_key)
         
         if api_base:
             litellm.api_base = api_base

nanobot/providers/transcription.py

@@ -0,0 +1,65 @@
+"""Voice transcription provider using Groq."""
+
+import os
+from pathlib import Path
+from typing import Any
+
+import httpx
+from loguru import logger
+
+
+class GroqTranscriptionProvider:
+    """
+    Voice transcription provider using Groq's Whisper API.
+    
+    Groq offers extremely fast transcription with a generous free tier.
+    """
+    
+    def __init__(self, api_key: str | None = None):
+        self.api_key = api_key or os.environ.get("GROQ_API_KEY")
+        self.api_url = "https://api.groq.com/openai/v1/audio/transcriptions"
+    
+    async def transcribe(self, file_path: str | Path) -> str:
+        """
+        Transcribe an audio file using Groq.
+        
+        Args:
+            file_path: Path to the audio file.
+            
+        Returns:
+            Transcribed text.
+        """
+        if not self.api_key:
+            logger.warning("Groq API key not configured for transcription")
+            return ""
+        
+        path = Path(file_path)
+        if not path.exists():
+            logger.error(f"Audio file not found: {file_path}")
+            return ""
+        
+        try:
+            async with httpx.AsyncClient() as client:
+                with open(path, "rb") as f:
+                    files = {
+                        "file": (path.name, f),
+                        "model": (None, "whisper-large-v3"),
+                    }
+                    headers = {
+                        "Authorization": f"Bearer {self.api_key}",
+                    }
+                    
+                    response = await client.post(
+                        self.api_url,
+                        headers=headers,
+                        files=files,
+                        timeout=60.0
+                    )
+                    
+                    response.raise_for_status()
+                    data = response.json()
+                    return data.get("text", "")
+                    
+        except Exception as e:
+            logger.error(f"Groq transcription error: {e}")
+            return ""

test_docker.sh

@@ -0,0 +1,55 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+IMAGE_NAME="nanobot-test"
+
+echo "=== Building Docker image ==="
+docker build -t "$IMAGE_NAME" .
+
+echo ""
+echo "=== Running 'nanobot onboard' ==="
+docker run --name nanobot-test-run "$IMAGE_NAME" onboard
+
+echo ""
+echo "=== Running 'nanobot status' ==="
+STATUS_OUTPUT=$(docker commit nanobot-test-run nanobot-test-onboarded > /dev/null && \
+    docker run --rm nanobot-test-onboarded status 2>&1) || true
+
+echo "$STATUS_OUTPUT"
+
+echo ""
+echo "=== Validating output ==="
+PASS=true
+
+check() {
+    if echo "$STATUS_OUTPUT" | grep -q "$1"; then
+        echo "  PASS: found '$1'"
+    else
+        echo "  FAIL: missing '$1'"
+        PASS=false
+    fi
+}
+
+check "nanobot Status"
+check "Config:"
+check "Workspace:"
+check "Model:"
+check "OpenRouter API:"
+check "Anthropic API:"
+check "OpenAI API:"
+
+echo ""
+if $PASS; then
+    echo "=== All checks passed ==="
+else
+    echo "=== Some checks FAILED ==="
+    exit 1
+fi
+
+# Cleanup
+echo ""
+echo "=== Cleanup ==="
+docker rm -f nanobot-test-run 2>/dev/null || true
+docker rmi -f nanobot-test-onboarded 2>/dev/null || true
+docker rmi -f "$IMAGE_NAME" 2>/dev/null || true
+echo "Done."

workspace/AGENTS.md

@@ -22,6 +22,16 @@ You have access to:
 - Use `memory/` directory for daily notes
 - Use `MEMORY.md` for long-term information
 
+## Scheduled Reminders
+
+When user asks for a reminder at a specific time, use `exec` to run:
+```
+nanobot cron add --name "reminder" --message "Your message" --at "YYYY-MM-DDTHH:MM:SS" --deliver --to "USER_ID" --channel "CHANNEL"
+```
+Get USER_ID and CHANNEL from the current session (e.g., `8281248569` and `telegram` from `telegram:8281248569`).
+
+**Do NOT just write reminders to MEMORY.md** — that won't trigger actual notifications.
+
 ## Heartbeat Tasks
 
 `HEARTBEAT.md` is checked every 30 minutes. You can manage periodic tasks by editing this file: