Hua/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' into feat/discord-support

Browse Source
This commit is contained in:
Anunay Aatipamula
2026-02-03 21:15:15 +05:30
committed by GitHub
parent bab464df5f d9d744d536
commit 7d2bebcfa3
15 changed files with 342 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
nanobot/agent/context.py
View File

@@ -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
messages.append({"role": "user", "content": current_message})
# Current message (with optional image attachments)
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,

3
nanobot/agent/loop.py
View File

@@ -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

4
nanobot/channels/manager.py
View File

@@ -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:

18
nanobot/channels/telegram.py
View File

@@ -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}")

5
nanobot/channels/whatsapp.py
View File

@@ -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

43
nanobot/cli/commands.py
View File

@@ -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()
if not api_key:
model = config.agents.defaults.model
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()
if not api_key:
model = config.agents.defaults.model
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})")

5
nanobot/config/schema.py
View File

@@ -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 > 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
)

2
nanobot/providers/litellm_provider.py
View File

@@ -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

65
nanobot/providers/transcription.py Normal file
View File

@@ -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 ""