Merge branch 'main' into pr-18

.gitignore

@@ -3,6 +3,7 @@
 *.pyc
 dist/
 build/
+docs/
 *.egg-info/
 *.egg
 *.pyc

README.md

@@ -60,6 +60,12 @@
 
 ## 📦 Install
 
+**Install with [uv](https://github.com/astral-sh/uv)** (recommended for speed)
+
+```bash
+uv tool install nanobot-ai
+```
+
 **Install from PyPi**
 
 ```bash
@@ -74,6 +80,14 @@ cd nanobot
 pip install -e .
 ```
 
+**Install with uv**
+
+```bash
+uv venv
+source .venv/bin/activate
+uv pip install nanobot-ai
+```
+
 ## 🚀 Quick Start
 
 > [!TIP]
@@ -331,22 +345,29 @@ nanobot/
 └── cli/            # 🖥️ Commands
 ```
 
-## 🗺️ Roadmap
+## 🤝 Contribute & Roadmap
 
+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
 - [ ] **More integrations** — Discord, Slack, email, calendar
 - [ ] **Self-improvement** — Learn from feedback and mistakes
 
-**Want to help?** Pick an item and [open a PR](https://github.com/HKUDS/nanobot/pulls)!
+### Contributors
+
+<a href="https://github.com/HKUDS/nanobot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=HKUDS/nanobot" />
+</a>
 
 ---
 
 ## ⭐ Star History
 
-*Community Growth Trajectory*
-
 <div align="center">
   <a href="https://star-history.com/#HKUDS/nanobot&Date">
     <picture>
@@ -357,12 +378,6 @@ nanobot/
   </a>
 </div>
 
----
-
-## 🤝 Contribute
-
-PRs welcome! The codebase is intentionally small and readable. 🤗
-
 <p align="center">
   <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">

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
 
@@ -114,7 +116,8 @@ 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.
@@ -123,6 +126,7 @@ When remembering something, write to {workspace_path}/memory/MEMORY.md"""
             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.
@@ -136,11 +140,30 @@ When remembering something, write to {workspace_path}/memory/MEMORY.md"""
         # 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,
         messages: list[dict[str, Any]],

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
@@ -189,7 +190,8 @@ class AgentLoop:
                 
                 # Execute tools
                 for tool_call in response.tool_calls:
-                    logger.debug(f"Executing tool: {tool_call.name}")
+                    args_str = json.dumps(tool_call.arguments)
+                    logger.debug(f"Executing tool: {tool_call.name} with arguments: {args_str}")
                     result = await self.tools.execute(tool_call.name, tool_call.arguments)
                     messages = self.context.add_tool_result(
                         messages, tool_call.id, tool_call.name, result
@@ -281,7 +283,8 @@ class AgentLoop:
                 )
                 
                 for tool_call in response.tool_calls:
-                    logger.debug(f"Executing tool: {tool_call.name}")
+                    args_str = json.dumps(tool_call.arguments)
+                    logger.debug(f"Executing tool: {tool_call.name} with arguments: {args_str}")
                     result = await self.tools.execute(tool_call.name, tool_call.arguments)
                     messages = self.context.add_tool_result(
                         messages, tool_call.id, tool_call.name, result

nanobot/channels/base.py

@@ -72,7 +72,14 @@ class BaseChannel(ABC):
         if not allow_list:
             return True
         
-        return str(sender_id) in allow_list
+        sender_str = str(sender_id)
+        if sender_str in allow_list:
+            return True
+        if "|" in sender_str:
+            for part in sender_str.split("|"):
+                if part and part in allow_list:
+                    return True
+        return False
     
     async def _handle_message(
         self,

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
     
@@ -199,8 +200,10 @@ class TelegramChannel(BaseChannel):
         user = update.effective_user
         chat_id = message.chat_id
         
-        # Get sender identifier (prefer username, fallback to user_id)
+        # Use stable numeric ID, but keep username for allowlist compatibility
-        sender_id = str(user.username or user.id)
+        sender_id = str(user.id)
+        if user.username:
+            sender_id = f"{sender_id}|{user.username}"
         
         # Store chat_id for replies
         self._chat_ids[sender_id] = chat_id
@@ -247,7 +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

@@ -506,6 +506,7 @@ 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
@@ -534,6 +535,7 @@ def cron_add(
         message=message,
         deliver=deliver,
         to=to,
+        channel=channel,
     )
     
     console.print(f"[green]✓[/green] Added job '{job.name}' ({job.id})")
@@ -624,11 +626,13 @@ def status():
         has_openrouter = bool(config.providers.openrouter.api_key)
         has_anthropic = bool(config.providers.anthropic.api_key)
         has_openai = bool(config.providers.openai.api_key)
+        has_gemini = bool(config.providers.gemini.api_key)
         has_vllm = bool(config.providers.vllm.api_base)
         
         console.print(f"OpenRouter API: {'[green]✓[/green]' if has_openrouter else '[dim]not set[/dim]'}")
         console.print(f"Anthropic API: {'[green]✓[/green]' if has_anthropic else '[dim]not set[/dim]'}")
         console.print(f"OpenAI API: {'[green]✓[/green]' if has_openai else '[dim]not set[/dim]'}")
+        console.print(f"Gemini API: {'[green]✓[/green]' if has_gemini else '[dim]not set[/dim]'}")
         vllm_status = f"[green]✓ {config.providers.vllm.api_base}[/green]" if has_vllm else "[dim]not set[/dim]"
         console.print(f"vLLM/Local: {vllm_status}")
 

nanobot/config/schema.py

@@ -50,7 +50,10 @@ 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)
 
 
 class GatewayConfig(BaseModel):
@@ -89,19 +92,24 @@ 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 > vLLM."""
+        """Get API key in priority order: OpenRouter > Anthropic > OpenAI > Gemini > Zhipu > Groq > 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
         )
     
     def get_api_base(self) -> str | None:
-        """Get API base URL if using OpenRouter or vLLM."""
+        """Get API base URL if using OpenRouter, Zhipu or vLLM."""
         if self.providers.openrouter.api_key:
             return self.providers.openrouter.api_base or "https://openrouter.ai/api/v1"
+        if self.providers.zhipu.api_key:
+            return self.providers.zhipu.api_base
         if self.providers.vllm.api_base:
             return self.providers.vllm.api_base
         return None

nanobot/providers/litellm_provider.py

@@ -13,7 +13,7 @@ class LiteLLMProvider(LLMProvider):
     """
     LLM provider using LiteLLM for multi-provider support.
     
-    Supports OpenRouter, Anthropic, OpenAI, and many other providers through
+    Supports OpenRouter, Anthropic, OpenAI, Gemini, and many other providers through
     a unified interface.
     """
     
@@ -47,6 +47,12 @@ class LiteLLMProvider(LLMProvider):
                 os.environ.setdefault("ANTHROPIC_API_KEY", api_key)
             elif "openai" in default_model or "gpt" in default_model:
                 os.environ.setdefault("OPENAI_API_KEY", api_key)
+            elif "gemini" in default_model.lower():
+                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
@@ -81,11 +87,24 @@ class LiteLLMProvider(LLMProvider):
         if self.is_openrouter and not model.startswith("openrouter/"):
             model = f"openrouter/{model}"
         
+        # For Zhipu/Z.ai, ensure prefix is present
+        # Handle cases like "glm-4.7-flash" -> "zhipu/glm-4.7-flash"
+        if ("glm" in model.lower() or "zhipu" in model.lower()) and not (
+            model.startswith("zhipu/") or 
+            model.startswith("zai/") or 
+            model.startswith("openrouter/")
+        ):
+            model = f"zhipu/{model}"
+        
         # For vLLM, use hosted_vllm/ prefix per LiteLLM docs
         # Convert openai/ prefix to hosted_vllm/ if user specified it
         if self.is_vllm:
             model = f"hosted_vllm/{model}"
         
+        # For Gemini, ensure gemini/ prefix if not already present
+        if "gemini" in model.lower() and not model.startswith("gemini/"):
+            model = f"gemini/{model}"
+        
         kwargs: dict[str, Any] = {
             "model": model,
             "messages": messages,

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 ""

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: