Merge branch 'main' into pr-398

.github/workflows/ci.yml

@@ -0,0 +1,33 @@
+name: Test Suite
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.11", "3.12", "3.13"]
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install system dependencies
+      run: sudo apt-get update && sudo apt-get install -y libolm-dev build-essential
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install .[dev]
+
+    - name: Run tests
+      run: python -m pytest tests/ -v

.gitignore

@@ -1,5 +1,6 @@
 .worktrees/
 .assets
+.docs
 .env
 *.pyc
 dist/
@@ -7,7 +8,7 @@ build/
 docs/
 *.egg-info/
 *.egg
-*.pyc
+*.pycs
 *.pyo
 *.pyd
 *.pyw
@@ -20,4 +21,5 @@ __pycache__/
 poetry.lock
 .pytest_cache/
 botpy.log
+nano.*.save
 

README.md

@@ -64,7 +64,7 @@
 
 ## Key Features of nanobot:
 
-🪶 **Ultra-Lightweight**: Just ~4,000 lines of core agent code — 99% smaller than Clawdbot.
+🪶 **Ultra-Lightweight**: A super lightweight implementation of OpenClaw — 99% smaller, significantly faster.
 
 🔬 **Research-Ready**: Clean, readable code that's easy to understand, modify, and extend for research.
 
@@ -78,6 +78,25 @@
   <img src="nanobot_arch.png" alt="nanobot architecture" width="800">
 </p>
 
+## Table of Contents
+
+- [News](#-news)
+- [Key Features](#key-features-of-nanobot)
+- [Architecture](#️-architecture)
+- [Features](#-features)
+- [Install](#-install)
+- [Quick Start](#-quick-start)
+- [Chat Apps](#-chat-apps)
+- [Agent Social Network](#-agent-social-network)
+- [Configuration](#️-configuration)
+- [Multiple Instances](#-multiple-instances)
+- [CLI Reference](#-cli-reference)
+- [Docker](#-docker)
+- [Linux Service](#-linux-service)
+- [Project Structure](#-project-structure)
+- [Contribute & Roadmap](#-contribute--roadmap)
+- [Star History](#-star-history)
+
 ## ✨ Features
 
 <table align="center">
@@ -150,7 +169,7 @@ nanobot channels login
 
 > [!TIP]
 > Set your API key in `~/.nanobot/config.json`.
-> Get API keys: [OpenRouter](https://openrouter.ai/keys) (Global) · [DashScope](https://dashscope.console.aliyun.com) (Qwen) · [Brave Search](https://brave.com/search/api/) or [Tavily](https://tavily.com/) (optional, for web search). SearXNG is supported via a base URL.
+> Get API keys: [OpenRouter](https://openrouter.ai/keys) (Global) · [Brave Search](https://brave.com/search/api/) (optional, for web search)
 
 **1. Initialize**
 
@@ -185,21 +204,6 @@ Add or merge these **two parts** into your config (other options have defaults).
 }
 ```
 
-**Optional: Web search provider** — set `tools.web.search.provider` to `brave` (default), `duckduckgo`, `tavily`, or `searxng`. See [docs/web-search.md](docs/web-search.md) for full configuration.
-
-```json
-{
-  "tools": {
-    "web": {
-      "search": {
-        "provider": "tavily",
-        "apiKey": "tvly-..."
-      }
-    }
-  }
-}
-```
-
 **3. Chat**
 
 ```bash
@@ -223,6 +227,7 @@ Connect nanobot to your favorite chat platform.
 | **Slack** | Bot token + App-Level token |
 | **Email** | IMAP/SMTP credentials |
 | **QQ** | App ID + App Secret |
+| **Wecom** | Bot ID + Bot Secret |
 
 <details>
 <summary><b>Telegram</b> (Recommended)</summary>
@@ -497,7 +502,8 @@ Uses **WebSocket** long connection — no public IP required.
       "appSecret": "xxx",
       "encryptKey": "",
       "verificationToken": "",
-      "allowFrom": ["ou_YOUR_OPEN_ID"]
+      "allowFrom": ["ou_YOUR_OPEN_ID"],
+      "groupPolicy": "mention"
     }
   }
 }
@@ -505,6 +511,7 @@ Uses **WebSocket** long connection — no public IP required.
 
 > `encryptKey` and `verificationToken` are optional for Long Connection mode.
 > `allowFrom`: Add your open_id (find it in nanobot logs when you message the bot). Use `["*"]` to allow all users.
+> `groupPolicy`: `"mention"` (default — respond only when @mentioned), `"open"` (respond to all group messages). Private chats always respond.
 
 **3. Run**
 
@@ -692,6 +699,46 @@ nanobot gateway
 
 </details>
 
+<details>
+<summary><b>Wecom (企业微信)</b></summary>
+
+> Here we use [wecom-aibot-sdk-python](https://github.com/chengyongru/wecom_aibot_sdk) (community Python version of the official [@wecom/aibot-node-sdk](https://www.npmjs.com/package/@wecom/aibot-node-sdk)).
+>
+> Uses **WebSocket** long connection — no public IP required.
+
+**1. Install the optional dependency**
+
+```bash
+pip install nanobot-ai[wecom]
+```
+
+**2. Create a WeCom AI Bot**
+
+Go to the WeCom admin console → Intelligent Robot → Create Robot → select **API mode** with **long connection**. Copy the Bot ID and Secret.
+
+**3. Configure**
+
+```json
+{
+  "channels": {
+    "wecom": {
+      "enabled": true,
+      "botId": "your_bot_id",
+      "secret": "your_bot_secret",
+      "allowFrom": ["your_id"]
+    }
+  }
+}
+```
+
+**4. Run**
+
+```bash
+nanobot gateway
+```
+
+</details>
+
 ## 🌐 Agent Social Network
 
 🐈 nanobot is capable of linking to the agent social network (agent community). **Just send one message and your nanobot joins automatically!**
@@ -711,15 +758,17 @@ Config file: `~/.nanobot/config.json`
 
 > [!TIP]
 > - **Groq** provides free voice transcription via Whisper. If configured, Telegram voice messages will be automatically transcribed.
+> - **VolcEngine / BytePlus Coding Plan**: Use dedicated providers `volcengineCodingPlan` or `byteplusCodingPlan` instead of the pay-per-use `volcengine` / `byteplus` providers.
 > - **Zhipu Coding Plan**: If you're on Zhipu's coding plan, set `"apiBase": "https://open.bigmodel.cn/api/coding/paas/v4"` in your zhipu provider config.
 > - **MiniMax (Mainland China)**: If your API key is from MiniMax's mainland China platform (minimaxi.com), set `"apiBase": "https://api.minimaxi.com/v1"` in your minimax provider config.
-> - **VolcEngine Coding Plan**: If you're on VolcEngine's coding plan, set `"apiBase": "https://ark.cn-beijing.volces.com/api/coding/v3"` in your volcengine provider config.
+> - **Alibaba Cloud BaiLian**: If you're using Alibaba Cloud BaiLian's OpenAI-compatible endpoint, set `"apiBase": "https://dashscope.aliyuncs.com/compatible-mode/v1"` in your dashscope provider config.
-> - **Alibaba Cloud Coding Plan**: If you're on the Alibaba Cloud Coding Plan (BaiLian), set `"apiBase": "https://coding.dashscope.aliyuncs.com/v1"` in your dashscope provider config.
 
 | Provider | Purpose | Get API Key |
 |----------|---------|-------------|
 | `custom` | Any OpenAI-compatible endpoint (direct, no LiteLLM) | — |
 | `openrouter` | LLM (recommended, access to all models) | [openrouter.ai](https://openrouter.ai) |
+| `volcengine` | LLM (VolcEngine, pay-per-use) | [Coding Plan](https://www.volcengine.com/activity/codingplan?utm_campaign=nanobot&utm_content=nanobot&utm_medium=devrel&utm_source=OWO&utm_term=nanobot) · [volcengine.com](https://www.volcengine.com) |
+| `byteplus` | LLM (VolcEngine international, pay-per-use) | [Coding Plan](https://www.byteplus.com/en/activity/codingplan?utm_campaign=nanobot&utm_content=nanobot&utm_medium=devrel&utm_source=OWO&utm_term=nanobot) · [byteplus.com](https://www.byteplus.com) |
 | `anthropic` | LLM (Claude direct) | [console.anthropic.com](https://console.anthropic.com) |
 | `azure_openai` | LLM (Azure OpenAI) | [portal.azure.com](https://portal.azure.com) |
 | `openai` | LLM (GPT direct) | [platform.openai.com](https://platform.openai.com) |
@@ -729,10 +778,10 @@ Config file: `~/.nanobot/config.json`
 | `minimax` | LLM (MiniMax direct) | [platform.minimaxi.com](https://platform.minimaxi.com) |
 | `aihubmix` | LLM (API gateway, access to all models) | [aihubmix.com](https://aihubmix.com) |
 | `siliconflow` | LLM (SiliconFlow/硅基流动) | [siliconflow.cn](https://siliconflow.cn) |
-| `volcengine` | LLM (VolcEngine/火山引擎) | [volcengine.com](https://www.volcengine.com) |
 | `dashscope` | LLM (Qwen) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
 | `moonshot` | LLM (Moonshot/Kimi) | [platform.moonshot.cn](https://platform.moonshot.cn) |
 | `zhipu` | LLM (Zhipu GLM) | [open.bigmodel.cn](https://open.bigmodel.cn) |
+| `ollama` | LLM (local, Ollama) | — |
 | `vllm` | LLM (local, any OpenAI-compatible server) | — |
 | `openai_codex` | LLM (Codex, OAuth) | `nanobot provider login openai-codex` |
 | `github_copilot` | LLM (GitHub Copilot, OAuth) | `nanobot provider login github-copilot` |
@@ -798,6 +847,37 @@ Connects directly to any OpenAI-compatible endpoint — LM Studio, llama.cpp, To
 
 </details>
 
+<details>
+<summary><b>Ollama (local)</b></summary>
+
+Run a local model with Ollama, then add to config:
+
+**1. Start Ollama** (example):
+```bash
+ollama run llama3.2
+```
+
+**2. Add to config** (partial — merge into `~/.nanobot/config.json`):
+```json
+{
+  "providers": {
+    "ollama": {
+      "apiBase": "http://localhost:11434"
+    }
+  },
+  "agents": {
+    "defaults": {
+      "provider": "ollama",
+      "model": "llama3.2"
+    }
+  }
+}
+```
+
+> `provider: "auto"` also works when `providers.ollama.apiBase` is configured, but setting `"provider": "ollama"` is the clearest option.
+
+</details>
+
 <details>
 <summary><b>vLLM (local / OpenAI-compatible)</b></summary>
 

core_agent_lines.sh

@@ -15,7 +15,7 @@ root=$(cat nanobot/__init__.py nanobot/__main__.py | wc -l)
 printf "  %-16s %5s lines\n" "(root)" "$root"
 
 echo ""
-total=$(find nanobot -name "*.py" ! -path "*/channels/*" ! -path "*/cli/*" ! -path "*/providers/*" | xargs cat | wc -l)
+total=$(find nanobot -name "*.py" ! -path "*/channels/*" ! -path "*/cli/*" ! -path "*/providers/*" ! -path "*/skills/*" | xargs cat | wc -l)
 echo "  Core total:     $total lines"
 echo ""
-echo "  (excludes: channels/, cli/, providers/)"
+echo "  (excludes: channels/, cli/, providers/, skills/)"

docs/web-search.md

@@ -1,95 +0,0 @@
-# Web Search Providers
-
-NanoBot supports multiple web search providers. Configure in `~/.nanobot/config.json` under `tools.web.search`.
-
-| Provider | Key | Env var |
-|----------|-----|---------|
-| `brave` (default) | `apiKey` | `BRAVE_API_KEY` |
-| `tavily` | `apiKey` | `TAVILY_API_KEY` |
-| `searxng` | `baseUrl` | `SEARXNG_BASE_URL` |
-| `duckduckgo` | — | — |
-
-Each provider uses the same `apiKey` field — set the provider and key together. If no provider is specified but `apiKey` is given, Brave is assumed.
-
-When credentials are missing and `fallbackToDuckduckgo` is `true` (the default), searches fall back to DuckDuckGo automatically.
-
-## Examples
-
-**Brave** (default — just set the key):
-
-```json
-{
-  "tools": {
-    "web": {
-      "search": {
-        "apiKey": "BSA..."
-      }
-    }
-  }
-}
-```
-
-**Tavily:**
-
-```json
-{
-  "tools": {
-    "web": {
-      "search": {
-        "provider": "tavily",
-        "apiKey": "tvly-..."
-      }
-    }
-  }
-}
-```
-
-**SearXNG** (self-hosted, no API key needed):
-
-```json
-{
-  "tools": {
-    "web": {
-      "search": {
-        "provider": "searxng",
-        "baseUrl": "https://searx.example"
-      }
-    }
-  }
-}
-```
-
-**DuckDuckGo** (no credentials required):
-
-```json
-{
-  "tools": {
-    "web": {
-      "search": {
-        "provider": "duckduckgo"
-      }
-    }
-  }
-}
-```
-
-## Options
-
-| Key | Type | Default | Description |
-|-----|------|---------|-------------|
-| `provider` | string | `"brave"` | Search backend |
-| `apiKey` | string | `""` | API key for the selected provider |
-| `baseUrl` | string | `""` | Base URL for SearXNG (appends `/search`) |
-| `maxResults` | integer | `5` | Default results per search |
-| `fallbackToDuckduckgo` | boolean | `true` | Fall back to DuckDuckGo when credentials are missing |
-
-## Custom providers
-
-Plugins can register additional providers at runtime via the dispatch dict:
-
-```python
-async def my_search(query: str, n: int) -> str:
-    ...
-
-tool._provider_dispatch["my-engine"] = my_search
-```

nanobot/agent/context.py

@@ -10,7 +10,7 @@ from typing import Any
 
 from nanobot.agent.memory import MemoryStore
 from nanobot.agent.skills import SkillsLoader
-from nanobot.utils.helpers import detect_image_mime
+from nanobot.utils.helpers import build_assistant_message, detect_image_mime
 
 
 class ContextBuilder:
@@ -182,12 +182,10 @@ Reply directly with text for conversations. Only use the 'message' tool to send
         thinking_blocks: list[dict] | None = None,
     ) -> list[dict[str, Any]]:
         """Add an assistant message to the message list."""
-        msg: dict[str, Any] = {"role": "assistant", "content": content}
+        messages.append(build_assistant_message(
-        if tool_calls:
+            content,
-            msg["tool_calls"] = tool_calls
+            tool_calls=tool_calls,
-        if reasoning_content is not None:
+            reasoning_content=reasoning_content,
-            msg["reasoning_content"] = reasoning_content
+            thinking_blocks=thinking_blocks,
-        if thinking_blocks:
+        ))
-            msg["thinking_blocks"] = thinking_blocks
-        messages.append(msg)
         return messages

nanobot/agent/loop.py

@@ -4,8 +4,9 @@ from __future__ import annotations
 
 import asyncio
 import json
+import os
 import re
-import weakref
+import sys
 from contextlib import AsyncExitStack
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Awaitable, Callable
@@ -13,7 +14,7 @@ from typing import TYPE_CHECKING, Any, Awaitable, Callable
 from loguru import logger
 
 from nanobot.agent.context import ContextBuilder
-from nanobot.agent.memory import MemoryStore
+from nanobot.agent.memory import MemoryConsolidator
 from nanobot.agent.subagent import SubagentManager
 from nanobot.agent.tools.cron import CronTool
 from nanobot.agent.tools.filesystem import EditFileTool, ListDirTool, ReadFileTool, WriteFileTool
@@ -28,7 +29,7 @@ from nanobot.providers.base import LLMProvider
 from nanobot.session.manager import Session, SessionManager
 
 if TYPE_CHECKING:
-    from nanobot.config.schema import ChannelsConfig, ExecToolConfig, WebSearchConfig
+    from nanobot.config.schema import ChannelsConfig, ExecToolConfig
     from nanobot.cron.service import CronService
 
 
@@ -44,7 +45,7 @@ class AgentLoop:
     5. Sends responses back
     """
 
-    _TOOL_RESULT_MAX_CHARS = 500
+    _TOOL_RESULT_MAX_CHARS = 16_000
 
     def __init__(
         self,
@@ -53,11 +54,8 @@ class AgentLoop:
         workspace: Path,
         model: str | None = None,
         max_iterations: int = 40,
-        temperature: float = 0.1,
+        context_window_tokens: int = 65_536,
-        max_tokens: int = 4096,
+        brave_api_key: str | None = None,
-        memory_window: int = 100,
-        reasoning_effort: str | None = None,
-        web_search_config: "WebSearchConfig | None" = None,
         web_proxy: str | None = None,
         exec_config: ExecToolConfig | None = None,
         cron_service: CronService | None = None,
@@ -66,21 +64,16 @@ class AgentLoop:
         mcp_servers: dict | None = None,
         channels_config: ChannelsConfig | None = None,
     ):
-        from nanobot.config.schema import ExecToolConfig, WebSearchConfig
+        from nanobot.config.schema import ExecToolConfig
-        from nanobot.cron.service import CronService
-
         self.bus = bus
         self.channels_config = channels_config
         self.provider = provider
         self.workspace = workspace
         self.model = model or provider.get_default_model()
         self.max_iterations = max_iterations
-        self.temperature = temperature
+        self.context_window_tokens = context_window_tokens
-        self.max_tokens = max_tokens
+        self.brave_api_key = brave_api_key
-        self.memory_window = memory_window
-        self.reasoning_effort = reasoning_effort
         self.web_proxy = web_proxy
-        self.web_search_config = web_search_config or WebSearchConfig()
         self.exec_config = exec_config or ExecToolConfig()
         self.cron_service = cron_service
         self.restrict_to_workspace = restrict_to_workspace
@@ -93,10 +86,7 @@ class AgentLoop:
             workspace=workspace,
             bus=bus,
             model=self.model,
-            temperature=self.temperature,
+            brave_api_key=brave_api_key,
-            max_tokens=self.max_tokens,
-            reasoning_effort=reasoning_effort,
-            web_search_config=self.web_search_config,
             web_proxy=web_proxy,
             exec_config=self.exec_config,
             restrict_to_workspace=restrict_to_workspace,
@@ -107,13 +97,17 @@ class AgentLoop:
         self._mcp_stack: AsyncExitStack | None = None
         self._mcp_connected = False
         self._mcp_connecting = False
-        self._consolidating: set[str] = set()  # Session keys with consolidation in progress
-        self._consolidation_tasks: set[asyncio.Task] = set()  # Strong refs to in-flight tasks
-        self._consolidation_locks: weakref.WeakValueDictionary[str, asyncio.Lock] = (
-            weakref.WeakValueDictionary()
-        )
         self._active_tasks: dict[str, list[asyncio.Task]] = {}  # session_key -> tasks
         self._processing_lock = asyncio.Lock()
+        self.memory_consolidator = MemoryConsolidator(
+            workspace=workspace,
+            provider=provider,
+            model=self.model,
+            sessions=self.sessions,
+            context_window_tokens=context_window_tokens,
+            build_messages=self.context.build_messages,
+            get_tool_definitions=self.tools.get_definitions,
+        )
         self._register_default_tools()
 
     def _register_default_tools(self) -> None:
@@ -121,15 +115,13 @@ class AgentLoop:
         allowed_dir = self.workspace if self.restrict_to_workspace else None
         for cls in (ReadFileTool, WriteFileTool, EditFileTool, ListDirTool):
             self.tools.register(cls(workspace=self.workspace, allowed_dir=allowed_dir))
-        self.tools.register(
+        self.tools.register(ExecTool(
-            ExecTool(
+            working_dir=str(self.workspace),
-                working_dir=str(self.workspace),
+            timeout=self.exec_config.timeout,
-                timeout=self.exec_config.timeout,
+            restrict_to_workspace=self.restrict_to_workspace,
-                restrict_to_workspace=self.restrict_to_workspace,
+            path_append=self.exec_config.path_append,
-                path_append=self.exec_config.path_append,
+        ))
-            )
+        self.tools.register(WebSearchTool(api_key=self.brave_api_key, proxy=self.web_proxy))
-        )
-        self.tools.register(WebSearchTool(config=self.web_search_config, proxy=self.web_proxy))
         self.tools.register(WebFetchTool(proxy=self.web_proxy))
         self.tools.register(MessageTool(send_callback=self.bus.publish_outbound))
         self.tools.register(SpawnTool(manager=self.subagents))
@@ -142,13 +134,12 @@ class AgentLoop:
             return
         self._mcp_connecting = True
         from nanobot.agent.tools.mcp import connect_mcp_servers
-
         try:
             self._mcp_stack = AsyncExitStack()
             await self._mcp_stack.__aenter__()
             await connect_mcp_servers(self._mcp_servers, self.tools, self._mcp_stack)
             self._mcp_connected = True
-        except Exception as e:
+        except BaseException as e:
             logger.error("Failed to connect MCP servers (will retry next message): {}", e)
             if self._mcp_stack:
                 try:
@@ -176,14 +167,12 @@ class AgentLoop:
     @staticmethod
     def _tool_hint(tool_calls: list) -> str:
         """Format tool calls as concise hint, e.g. 'web_search("query")'."""
-
         def _fmt(tc):
             args = (tc.arguments[0] if isinstance(tc.arguments, list) else tc.arguments) or {}
             val = next(iter(args.values()), None) if isinstance(args, dict) else None
             if not isinstance(val, str):
                 return tc.name
             return f'{tc.name}("{val[:40]}…")' if len(val) > 40 else f'{tc.name}("{val}")'
-
         return ", ".join(_fmt(tc) for tc in tool_calls)
 
     async def _run_agent_loop(
@@ -191,7 +180,7 @@ class AgentLoop:
         initial_messages: list[dict],
         on_progress: Callable[..., Awaitable[None]] | None = None,
     ) -> tuple[str | None, list[str], list[dict]]:
-        """Run the agent iteration loop. Returns (final_content, tools_used, messages)."""
+        """Run the agent iteration loop."""
         messages = initial_messages
         iteration = 0
         final_content = None
@@ -200,13 +189,12 @@ class AgentLoop:
         while iteration < self.max_iterations:
             iteration += 1
 
-            response = await self.provider.chat(
+            tool_defs = self.tools.get_definitions()
+
+            response = await self.provider.chat_with_retry(
                 messages=messages,
-                tools=self.tools.get_definitions(),
+                tools=tool_defs,
                 model=self.model,
-                temperature=self.temperature,
-                max_tokens=self.max_tokens,
-                reasoning_effort=self.reasoning_effort,
             )
 
             if response.has_tool_calls:
@@ -217,20 +205,11 @@ class AgentLoop:
                     await on_progress(self._tool_hint(response.tool_calls), tool_hint=True)
 
                 tool_call_dicts = [
-                    {
+                    tc.to_openai_tool_call()
-                        "id": tc.id,
-                        "type": "function",
-                        "function": {
-                            "name": tc.name,
-                            "arguments": json.dumps(tc.arguments, ensure_ascii=False),
-                        },
-                    }
                     for tc in response.tool_calls
                 ]
                 messages = self.context.add_assistant_message(
-                    messages,
+                    messages, response.content, tool_call_dicts,
-                    response.content,
-                    tool_call_dicts,
                     reasoning_content=response.reasoning_content,
                     thinking_blocks=response.thinking_blocks,
                 )
@@ -252,9 +231,7 @@ class AgentLoop:
                     final_content = clean or "Sorry, I encountered an error calling the AI model."
                     break
                 messages = self.context.add_assistant_message(
-                    messages,
+                    messages, clean, reasoning_content=response.reasoning_content,
-                    clean,
-                    reasoning_content=response.reasoning_content,
                     thinking_blocks=response.thinking_blocks,
                 )
                 final_content = clean
@@ -281,17 +258,15 @@ class AgentLoop:
             except asyncio.TimeoutError:
                 continue
 
-            if msg.content.strip().lower() == "/stop":
+            cmd = msg.content.strip().lower()
+            if cmd == "/stop":
                 await self._handle_stop(msg)
+            elif cmd == "/restart":
+                await self._handle_restart(msg)
             else:
                 task = asyncio.create_task(self._dispatch(msg))
                 self._active_tasks.setdefault(msg.session_key, []).append(task)
-                task.add_done_callback(
+                task.add_done_callback(lambda t, k=msg.session_key: self._active_tasks.get(k, []) and self._active_tasks[k].remove(t) if t in self._active_tasks.get(k, []) else None)
-                    lambda t, k=msg.session_key: self._active_tasks.get(k, [])
-                    and self._active_tasks[k].remove(t)
-                    if t in self._active_tasks.get(k, [])
-                    else None
-                )
 
     async def _handle_stop(self, msg: InboundMessage) -> None:
         """Cancel all active tasks and subagents for the session."""
@@ -304,14 +279,24 @@ class AgentLoop:
                 pass
         sub_cancelled = await self.subagents.cancel_by_session(msg.session_key)
         total = cancelled + sub_cancelled
-        content = f"⏹ Stopped {total} task(s)." if total else "No active task to stop."
+        content = f"Stopped {total} task(s)." if total else "No active task to stop."
-        await self.bus.publish_outbound(
+        await self.bus.publish_outbound(OutboundMessage(
-            OutboundMessage(
+            channel=msg.channel, chat_id=msg.chat_id, content=content,
-                channel=msg.channel,
+        ))
-                chat_id=msg.chat_id,
+
-                content=content,
+    async def _handle_restart(self, msg: InboundMessage) -> None:
-            )
+        """Restart the process in-place via os.execv."""
-        )
+        await self.bus.publish_outbound(OutboundMessage(
+            channel=msg.channel, chat_id=msg.chat_id, content="Restarting...",
+        ))
+
+        async def _do_restart():
+            await asyncio.sleep(1)
+            # Use -m nanobot instead of sys.argv[0] for Windows compatibility
+            # (sys.argv[0] may be just "nanobot" without full path on Windows)
+            os.execv(sys.executable, [sys.executable, "-m", "nanobot"] + sys.argv[1:])
+
+        asyncio.create_task(_do_restart())
 
     async def _dispatch(self, msg: InboundMessage) -> None:
         """Process a message under the global lock."""
@@ -321,26 +306,19 @@ class AgentLoop:
                 if response is not None:
                     await self.bus.publish_outbound(response)
                 elif msg.channel == "cli":
-                    await self.bus.publish_outbound(
+                    await self.bus.publish_outbound(OutboundMessage(
-                        OutboundMessage(
+                        channel=msg.channel, chat_id=msg.chat_id,
-                            channel=msg.channel,
+                        content="", metadata=msg.metadata or {},
-                            chat_id=msg.chat_id,
+                    ))
-                            content="",
-                            metadata=msg.metadata or {},
-                        )
-                    )
             except asyncio.CancelledError:
                 logger.info("Task cancelled for session {}", msg.session_key)
                 raise
             except Exception:
                 logger.exception("Error processing message for session {}", msg.session_key)
-                await self.bus.publish_outbound(
+                await self.bus.publish_outbound(OutboundMessage(
-                    OutboundMessage(
+                    channel=msg.channel, chat_id=msg.chat_id,
-                        channel=msg.channel,
+                    content="Sorry, I encountered an error.",
-                        chat_id=msg.chat_id,
+                ))
-                        content="Sorry, I encountered an error.",
-                    )
-                )
 
     async def close_mcp(self) -> None:
         """Close MCP connections."""
@@ -365,28 +343,24 @@ class AgentLoop:
         """Process a single inbound message and return the response."""
         # System messages: parse origin from chat_id ("channel:chat_id")
         if msg.channel == "system":
-            channel, chat_id = (
+            channel, chat_id = (msg.chat_id.split(":", 1) if ":" in msg.chat_id
-                msg.chat_id.split(":", 1) if ":" in msg.chat_id else ("cli", msg.chat_id)
+                                else ("cli", msg.chat_id))
-            )
             logger.info("Processing system message from {}", msg.sender_id)
             key = f"{channel}:{chat_id}"
             session = self.sessions.get_or_create(key)
+            await self.memory_consolidator.maybe_consolidate_by_tokens(session)
             self._set_tool_context(channel, chat_id, msg.metadata.get("message_id"))
-            history = session.get_history(max_messages=self.memory_window)
+            history = session.get_history(max_messages=0)
             messages = self.context.build_messages(
                 history=history,
-                current_message=msg.content,
+                current_message=msg.content, channel=channel, chat_id=chat_id,
-                channel=channel,
-                chat_id=chat_id,
             )
             final_content, _, all_msgs = await self._run_agent_loop(messages)
             self._save_turn(session, all_msgs, 1 + len(history))
             self.sessions.save(session)
-            return OutboundMessage(
+            await self.memory_consolidator.maybe_consolidate_by_tokens(session)
-                channel=channel,
+            return OutboundMessage(channel=channel, chat_id=chat_id,
-                chat_id=chat_id,
+                                  content=final_content or "Background task completed.")
-                content=final_content or "Background task completed.",
-            )
 
         preview = msg.content[:80] + "..." if len(msg.content) > 80 else msg.content
         logger.info("Processing message from {}:{}: {}", msg.channel, msg.sender_id, preview)
@@ -397,20 +371,13 @@ class AgentLoop:
         # Slash commands
         cmd = msg.content.strip().lower()
         if cmd == "/new":
-            lock = self._consolidation_locks.setdefault(session.key, asyncio.Lock())
-            self._consolidating.add(session.key)
             try:
-                async with lock:
+                if not await self.memory_consolidator.archive_unconsolidated(session):
-                    snapshot = session.messages[session.last_consolidated :]
+                    return OutboundMessage(
-                    if snapshot:
+                        channel=msg.channel,
-                        temp = Session(key=session.key)
+                        chat_id=msg.chat_id,
-                        temp.messages = list(snapshot)
+                        content="Memory archival failed, session not cleared. Please try again.",
-                        if not await self._consolidate_memory(temp, archive_all=True):
+                    )
-                            return OutboundMessage(
-                                channel=msg.channel,
-                                chat_id=msg.chat_id,
-                                content="Memory archival failed, session not cleared. Please try again.",
-                            )
             except Exception:
                 logger.exception("/new archival failed for {}", session.key)
                 return OutboundMessage(
@@ -418,70 +385,48 @@ class AgentLoop:
                     chat_id=msg.chat_id,
                     content="Memory archival failed, session not cleared. Please try again.",
                 )
-            finally:
-                self._consolidating.discard(session.key)
 
             session.clear()
             self.sessions.save(session)
             self.sessions.invalidate(session.key)
-            return OutboundMessage(
+            return OutboundMessage(channel=msg.channel, chat_id=msg.chat_id,
-                channel=msg.channel, chat_id=msg.chat_id, content="New session started."
+                                  content="New session started.")
-            )
         if cmd == "/help":
+            lines = [
+                "🐈 nanobot commands:",
+                "/new — Start a new conversation",
+                "/stop — Stop the current task",
+                "/restart — Restart the bot",
+                "/help — Show available commands",
+            ]
             return OutboundMessage(
-                channel=msg.channel,
+                channel=msg.channel, chat_id=msg.chat_id, content="\n".join(lines),
-                chat_id=msg.chat_id,
-                content="🐈 nanobot commands:\n/new — Start a new conversation\n/stop — Stop the current task\n/help — Show available commands",
             )
-
+        await self.memory_consolidator.maybe_consolidate_by_tokens(session)
-        unconsolidated = len(session.messages) - session.last_consolidated
-        if unconsolidated >= self.memory_window and session.key not in self._consolidating:
-            self._consolidating.add(session.key)
-            lock = self._consolidation_locks.setdefault(session.key, asyncio.Lock())
-
-            async def _consolidate_and_unlock():
-                try:
-                    async with lock:
-                        await self._consolidate_memory(session)
-                finally:
-                    self._consolidating.discard(session.key)
-                    _task = asyncio.current_task()
-                    if _task is not None:
-                        self._consolidation_tasks.discard(_task)
-
-            _task = asyncio.create_task(_consolidate_and_unlock())
-            self._consolidation_tasks.add(_task)
 
         self._set_tool_context(msg.channel, msg.chat_id, msg.metadata.get("message_id"))
         if message_tool := self.tools.get("message"):
             if isinstance(message_tool, MessageTool):
                 message_tool.start_turn()
 
-        history = session.get_history(max_messages=self.memory_window)
+        history = session.get_history(max_messages=0)
         initial_messages = self.context.build_messages(
             history=history,
             current_message=msg.content,
             media=msg.media if msg.media else None,
-            channel=msg.channel,
+            channel=msg.channel, chat_id=msg.chat_id,
-            chat_id=msg.chat_id,
         )
 
         async def _bus_progress(content: str, *, tool_hint: bool = False) -> None:
             meta = dict(msg.metadata or {})
             meta["_progress"] = True
             meta["_tool_hint"] = tool_hint
-            await self.bus.publish_outbound(
+            await self.bus.publish_outbound(OutboundMessage(
-                OutboundMessage(
+                channel=msg.channel, chat_id=msg.chat_id, content=content, metadata=meta,
-                    channel=msg.channel,
+            ))
-                    chat_id=msg.chat_id,
-                    content=content,
-                    metadata=meta,
-                )
-            )
 
         final_content, _, all_msgs = await self._run_agent_loop(
-            initial_messages,
+            initial_messages, on_progress=on_progress or _bus_progress,
-            on_progress=on_progress or _bus_progress,
         )
 
         if final_content is None:
@@ -489,6 +434,7 @@ class AgentLoop:
 
         self._save_turn(session, all_msgs, 1 + len(history))
         self.sessions.save(session)
+        await self.memory_consolidator.maybe_consolidate_by_tokens(session)
 
         if (mt := self.tools.get("message")) and isinstance(mt, MessageTool) and mt._sent_in_turn:
             return None
@@ -496,31 +442,22 @@ class AgentLoop:
         preview = final_content[:120] + "..." if len(final_content) > 120 else final_content
         logger.info("Response to {}:{}: {}", msg.channel, msg.sender_id, preview)
         return OutboundMessage(
-            channel=msg.channel,
+            channel=msg.channel, chat_id=msg.chat_id, content=final_content,
-            chat_id=msg.chat_id,
-            content=final_content,
             metadata=msg.metadata or {},
         )
 
     def _save_turn(self, session: Session, messages: list[dict], skip: int) -> None:
         """Save new-turn messages into session, truncating large tool results."""
         from datetime import datetime
-
         for m in messages[skip:]:
             entry = dict(m)
             role, content = entry.get("role"), entry.get("content")
             if role == "assistant" and not content and not entry.get("tool_calls"):
                 continue  # skip empty assistant messages — they poison session context
-            if (
+            if role == "tool" and isinstance(content, str) and len(content) > self._TOOL_RESULT_MAX_CHARS:
-                role == "tool"
+                entry["content"] = content[:self._TOOL_RESULT_MAX_CHARS] + "\n... (truncated)"
-                and isinstance(content, str)
-                and len(content) > self._TOOL_RESULT_MAX_CHARS
-            ):
-                entry["content"] = content[: self._TOOL_RESULT_MAX_CHARS] + "\n... (truncated)"
             elif role == "user":
-                if isinstance(content, str) and content.startswith(
+                if isinstance(content, str) and content.startswith(ContextBuilder._RUNTIME_CONTEXT_TAG):
-                    ContextBuilder._RUNTIME_CONTEXT_TAG
-                ):
                     # Strip the runtime-context prefix, keep only the user text.
                     parts = content.split("\n\n", 1)
                     if len(parts) > 1 and parts[1].strip():
@@ -530,15 +467,10 @@ class AgentLoop:
                 if isinstance(content, list):
                     filtered = []
                     for c in content:
-                        if (
+                        if c.get("type") == "text" and isinstance(c.get("text"), str) and c["text"].startswith(ContextBuilder._RUNTIME_CONTEXT_TAG):
-                            c.get("type") == "text"
-                            and isinstance(c.get("text"), str)
-                            and c["text"].startswith(ContextBuilder._RUNTIME_CONTEXT_TAG)
-                        ):
                             continue  # Strip runtime context from multimodal messages
-                        if c.get("type") == "image_url" and c.get("image_url", {}).get(
+                        if (c.get("type") == "image_url"
-                            "url", ""
+                                and c.get("image_url", {}).get("url", "").startswith("data:image/")):
-                        ).startswith("data:image/"):
                             filtered.append({"type": "text", "text": "[image]"})
                         else:
                             filtered.append(c)
@@ -549,16 +481,6 @@ class AgentLoop:
             session.messages.append(entry)
         session.updated_at = datetime.now()
 
-    async def _consolidate_memory(self, session, archive_all: bool = False) -> bool:
-        """Delegate to MemoryStore.consolidate(). Returns True on success."""
-        return await MemoryStore(self.workspace).consolidate(
-            session,
-            self.provider,
-            self.model,
-            archive_all=archive_all,
-            memory_window=self.memory_window,
-        )
-
     async def process_direct(
         self,
         content: str,
@@ -570,7 +492,5 @@ class AgentLoop:
         """Process a message directly (for CLI or cron usage)."""
         await self._connect_mcp()
         msg = InboundMessage(channel=channel, sender_id="user", chat_id=chat_id, content=content)
-        response = await self._process_message(
+        response = await self._process_message(msg, session_key=session_key, on_progress=on_progress)
-            msg, session_key=session_key, on_progress=on_progress
-        )
         return response.content if response else ""

nanobot/agent/memory.py

@@ -2,17 +2,20 @@
 
 from __future__ import annotations
 
+import asyncio
 import json
+import weakref
+from datetime import datetime
 from pathlib import Path
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Any, Callable
 
 from loguru import logger
 
-from nanobot.utils.helpers import ensure_dir
+from nanobot.utils.helpers import ensure_dir, estimate_message_tokens, estimate_prompt_tokens_chain
 
 if TYPE_CHECKING:
     from nanobot.providers.base import LLMProvider
-    from nanobot.session.manager import Session
+    from nanobot.session.manager import Session, SessionManager
 
 
 _SAVE_MEMORY_TOOL = [
@@ -26,7 +29,7 @@ _SAVE_MEMORY_TOOL = [
                 "properties": {
                     "history_entry": {
                         "type": "string",
-                        "description": "A paragraph (2-5 sentences) summarizing key events/decisions/topics. "
+                        "description": "A paragraph summarizing key events/decisions/topics. "
                         "Start with [YYYY-MM-DD HH:MM]. Include detail useful for grep search.",
                     },
                     "memory_update": {
@@ -42,13 +45,43 @@ _SAVE_MEMORY_TOOL = [
 ]
 
 
+def _ensure_text(value: Any) -> str:
+    """Normalize tool-call payload values to text for file storage."""
+    return value if isinstance(value, str) else json.dumps(value, ensure_ascii=False)
+
+
+def _normalize_save_memory_args(args: Any) -> dict[str, Any] | None:
+    """Normalize provider tool-call arguments to the expected dict shape."""
+    if isinstance(args, str):
+        args = json.loads(args)
+    if isinstance(args, list):
+        return args[0] if args and isinstance(args[0], dict) else None
+    return args if isinstance(args, dict) else None
+
+_TOOL_CHOICE_ERROR_MARKERS = (
+    "tool_choice",
+    "toolchoice",
+    "does not support",
+    'should be ["none", "auto"]',
+)
+
+
+def _is_tool_choice_unsupported(content: str | None) -> bool:
+    """Detect provider errors caused by forced tool_choice being unsupported."""
+    text = (content or "").lower()
+    return any(m in text for m in _TOOL_CHOICE_ERROR_MARKERS)
+
+
 class MemoryStore:
     """Two-layer memory: MEMORY.md (long-term facts) + HISTORY.md (grep-searchable log)."""
 
+    _MAX_FAILURES_BEFORE_RAW_ARCHIVE = 3
+
     def __init__(self, workspace: Path):
         self.memory_dir = ensure_dir(workspace / "memory")
         self.memory_file = self.memory_dir / "MEMORY.md"
         self.history_file = self.memory_dir / "HISTORY.md"
+        self._consecutive_failures = 0
 
     def read_long_term(self) -> str:
         if self.memory_file.exists():
@@ -66,40 +99,27 @@ class MemoryStore:
         long_term = self.read_long_term()
         return f"## Long-term Memory\n{long_term}" if long_term else ""
 
+    @staticmethod
+    def _format_messages(messages: list[dict]) -> str:
+        lines = []
+        for message in messages:
+            if not message.get("content"):
+                continue
+            tools = f" [tools: {', '.join(message['tools_used'])}]" if message.get("tools_used") else ""
+            lines.append(
+                f"[{message.get('timestamp', '?')[:16]}] {message['role'].upper()}{tools}: {message['content']}"
+            )
+        return "\n".join(lines)
+
     async def consolidate(
         self,
-        session: Session,
+        messages: list[dict],
         provider: LLMProvider,
         model: str,
-        *,
-        archive_all: bool = False,
-        memory_window: int = 50,
     ) -> bool:
-        """Consolidate old messages into MEMORY.md + HISTORY.md via LLM tool call.
+        """Consolidate the provided message chunk into MEMORY.md + HISTORY.md."""
-
+        if not messages:
-        Returns True on success (including no-op), False on failure.
+            return True
-        """
-        if archive_all:
-            old_messages = session.messages
-            keep_count = 0
-            logger.info("Memory consolidation (archive_all): {} messages", len(session.messages))
-        else:
-            keep_count = memory_window // 2
-            if len(session.messages) <= keep_count:
-                return True
-            if len(session.messages) - session.last_consolidated <= 0:
-                return True
-            old_messages = session.messages[session.last_consolidated:-keep_count]
-            if not old_messages:
-                return True
-            logger.info("Memory consolidation: {} to consolidate, {} keep", len(old_messages), keep_count)
-
-        lines = []
-        for m in old_messages:
-            if not m.get("content"):
-                continue
-            tools = f" [tools: {', '.join(m['tools_used'])}]" if m.get("tools_used") else ""
-            lines.append(f"[{m.get('timestamp', '?')[:16]}] {m['role'].upper()}{tools}: {m['content']}")
 
         current_memory = self.read_long_term()
         prompt = f"""Process this conversation and call the save_memory tool with your consolidation.
@@ -108,50 +128,230 @@ class MemoryStore:
 {current_memory or "(empty)"}
 
 ## Conversation to Process
-{chr(10).join(lines)}"""
+{self._format_messages(messages)}"""
+
+        chat_messages = [
+            {"role": "system", "content": "You are a memory consolidation agent. Call the save_memory tool with your consolidation of the conversation."},
+            {"role": "user", "content": prompt},
+        ]
 
         try:
-            response = await provider.chat(
+            forced = {"type": "function", "function": {"name": "save_memory"}}
-                messages=[
+            response = await provider.chat_with_retry(
-                    {"role": "system", "content": "You are a memory consolidation agent. Call the save_memory tool with your consolidation of the conversation."},
+                messages=chat_messages,
-                    {"role": "user", "content": prompt},
-                ],
                 tools=_SAVE_MEMORY_TOOL,
                 model=model,
+                tool_choice=forced,
             )
 
+            if response.finish_reason == "error" and _is_tool_choice_unsupported(
+                response.content
+            ):
+                logger.warning("Forced tool_choice unsupported, retrying with auto")
+                response = await provider.chat_with_retry(
+                    messages=chat_messages,
+                    tools=_SAVE_MEMORY_TOOL,
+                    model=model,
+                    tool_choice="auto",
+                )
+
             if not response.has_tool_calls:
-                logger.warning("Memory consolidation: LLM did not call save_memory, skipping")
+                logger.warning(
-                return False
+                    "Memory consolidation: LLM did not call save_memory "
+                    "(finish_reason={}, content_len={}, content_preview={})",
+                    response.finish_reason,
+                    len(response.content or ""),
+                    (response.content or "")[:200],
+                )
+                return self._fail_or_raw_archive(messages)
 
-            args = response.tool_calls[0].arguments
+            args = _normalize_save_memory_args(response.tool_calls[0].arguments)
-            # Some providers return arguments as a JSON string instead of dict
+            if args is None:
-            if isinstance(args, str):
+                logger.warning("Memory consolidation: unexpected save_memory arguments")
-                args = json.loads(args)
+                return self._fail_or_raw_archive(messages)
-            # Some providers return arguments as a list (handle edge case)
-            if isinstance(args, list):
-                if args and isinstance(args[0], dict):
-                    args = args[0]
-                else:
-                    logger.warning("Memory consolidation: unexpected arguments as empty or non-dict list")
-                    return False
-            if not isinstance(args, dict):
-                logger.warning("Memory consolidation: unexpected arguments type {}", type(args).__name__)
-                return False
 
-            if entry := args.get("history_entry"):
+            if "history_entry" not in args or "memory_update" not in args:
-                if not isinstance(entry, str):
+                logger.warning("Memory consolidation: save_memory payload missing required fields")
-                    entry = json.dumps(entry, ensure_ascii=False)
+                return self._fail_or_raw_archive(messages)
-                self.append_history(entry)
-            if update := args.get("memory_update"):
-                if not isinstance(update, str):
-                    update = json.dumps(update, ensure_ascii=False)
-                if update != current_memory:
-                    self.write_long_term(update)
 
-            session.last_consolidated = 0 if archive_all else len(session.messages) - keep_count
+            entry = args["history_entry"]
-            logger.info("Memory consolidation done: {} messages, last_consolidated={}", len(session.messages), session.last_consolidated)
+            update = args["memory_update"]
+
+            if entry is None or update is None:
+                logger.warning("Memory consolidation: save_memory payload contains null required fields")
+                return self._fail_or_raw_archive(messages)
+
+            entry = _ensure_text(entry).strip()
+            if not entry:
+                logger.warning("Memory consolidation: history_entry is empty after normalization")
+                return self._fail_or_raw_archive(messages)
+
+            self.append_history(entry)
+            update = _ensure_text(update)
+            if update != current_memory:
+                self.write_long_term(update)
+
+            self._consecutive_failures = 0
+            logger.info("Memory consolidation done for {} messages", len(messages))
             return True
         except Exception:
             logger.exception("Memory consolidation failed")
+            return self._fail_or_raw_archive(messages)
+
+    def _fail_or_raw_archive(self, messages: list[dict]) -> bool:
+        """Increment failure count; after threshold, raw-archive messages and return True."""
+        self._consecutive_failures += 1
+        if self._consecutive_failures < self._MAX_FAILURES_BEFORE_RAW_ARCHIVE:
             return False
+        self._raw_archive(messages)
+        self._consecutive_failures = 0
+        return True
+
+    def _raw_archive(self, messages: list[dict]) -> None:
+        """Fallback: dump raw messages to HISTORY.md without LLM summarization."""
+        ts = datetime.now().strftime("%Y-%m-%d %H:%M")
+        self.append_history(
+            f"[{ts}] [RAW] {len(messages)} messages\n"
+            f"{self._format_messages(messages)}"
+        )
+        logger.warning(
+            "Memory consolidation degraded: raw-archived {} messages", len(messages)
+        )
+
+
+class MemoryConsolidator:
+    """Owns consolidation policy, locking, and session offset updates."""
+
+    _MAX_CONSOLIDATION_ROUNDS = 5
+
+    def __init__(
+        self,
+        workspace: Path,
+        provider: LLMProvider,
+        model: str,
+        sessions: SessionManager,
+        context_window_tokens: int,
+        build_messages: Callable[..., list[dict[str, Any]]],
+        get_tool_definitions: Callable[[], list[dict[str, Any]]],
+    ):
+        self.store = MemoryStore(workspace)
+        self.provider = provider
+        self.model = model
+        self.sessions = sessions
+        self.context_window_tokens = context_window_tokens
+        self._build_messages = build_messages
+        self._get_tool_definitions = get_tool_definitions
+        self._locks: weakref.WeakValueDictionary[str, asyncio.Lock] = weakref.WeakValueDictionary()
+
+    def get_lock(self, session_key: str) -> asyncio.Lock:
+        """Return the shared consolidation lock for one session."""
+        return self._locks.setdefault(session_key, asyncio.Lock())
+
+    async def consolidate_messages(self, messages: list[dict[str, object]]) -> bool:
+        """Archive a selected message chunk into persistent memory."""
+        return await self.store.consolidate(messages, self.provider, self.model)
+
+    def pick_consolidation_boundary(
+        self,
+        session: Session,
+        tokens_to_remove: int,
+    ) -> tuple[int, int] | None:
+        """Pick a user-turn boundary that removes enough old prompt tokens."""
+        start = session.last_consolidated
+        if start >= len(session.messages) or tokens_to_remove <= 0:
+            return None
+
+        removed_tokens = 0
+        last_boundary: tuple[int, int] | None = None
+        for idx in range(start, len(session.messages)):
+            message = session.messages[idx]
+            if idx > start and message.get("role") == "user":
+                last_boundary = (idx, removed_tokens)
+                if removed_tokens >= tokens_to_remove:
+                    return last_boundary
+            removed_tokens += estimate_message_tokens(message)
+
+        return last_boundary
+
+    def estimate_session_prompt_tokens(self, session: Session) -> tuple[int, str]:
+        """Estimate current prompt size for the normal session history view."""
+        history = session.get_history(max_messages=0)
+        channel, chat_id = (session.key.split(":", 1) if ":" in session.key else (None, None))
+        probe_messages = self._build_messages(
+            history=history,
+            current_message="[token-probe]",
+            channel=channel,
+            chat_id=chat_id,
+        )
+        return estimate_prompt_tokens_chain(
+            self.provider,
+            self.model,
+            probe_messages,
+            self._get_tool_definitions(),
+        )
+
+    async def archive_unconsolidated(self, session: Session) -> bool:
+        """Archive the full unconsolidated tail for /new-style session rollover."""
+        lock = self.get_lock(session.key)
+        async with lock:
+            snapshot = session.messages[session.last_consolidated:]
+            if not snapshot:
+                return True
+            return await self.consolidate_messages(snapshot)
+
+    async def maybe_consolidate_by_tokens(self, session: Session) -> None:
+        """Loop: archive old messages until prompt fits within half the context window."""
+        if not session.messages or self.context_window_tokens <= 0:
+            return
+
+        lock = self.get_lock(session.key)
+        async with lock:
+            target = self.context_window_tokens // 2
+            estimated, source = self.estimate_session_prompt_tokens(session)
+            if estimated <= 0:
+                return
+            if estimated < self.context_window_tokens:
+                logger.debug(
+                    "Token consolidation idle {}: {}/{} via {}",
+                    session.key,
+                    estimated,
+                    self.context_window_tokens,
+                    source,
+                )
+                return
+
+            for round_num in range(self._MAX_CONSOLIDATION_ROUNDS):
+                if estimated <= target:
+                    return
+
+                boundary = self.pick_consolidation_boundary(session, max(1, estimated - target))
+                if boundary is None:
+                    logger.debug(
+                        "Token consolidation: no safe boundary for {} (round {})",
+                        session.key,
+                        round_num,
+                    )
+                    return
+
+                end_idx = boundary[0]
+                chunk = session.messages[session.last_consolidated:end_idx]
+                if not chunk:
+                    return
+
+                logger.info(
+                    "Token consolidation round {} for {}: {}/{} via {}, chunk={} msgs",
+                    round_num,
+                    session.key,
+                    estimated,
+                    self.context_window_tokens,
+                    source,
+                    len(chunk),
+                )
+                if not await self.consolidate_messages(chunk):
+                    return
+                session.last_consolidated = end_idx
+                self.sessions.save(session)
+
+                estimated, source = self.estimate_session_prompt_tokens(session)
+                if estimated <= 0:
+                    return

nanobot/agent/subagent.py

@@ -16,6 +16,7 @@ from nanobot.bus.events import InboundMessage
 from nanobot.bus.queue import MessageBus
 from nanobot.config.schema import ExecToolConfig
 from nanobot.providers.base import LLMProvider
+from nanobot.utils.helpers import build_assistant_message
 
 
 class SubagentManager:
@@ -27,25 +28,18 @@ class SubagentManager:
         workspace: Path,
         bus: MessageBus,
         model: str | None = None,
-        temperature: float = 0.7,
+        brave_api_key: str | None = None,
-        max_tokens: int = 4096,
-        reasoning_effort: str | None = None,
-        web_search_config: "WebSearchConfig | None" = None,
         web_proxy: str | None = None,
         exec_config: "ExecToolConfig | None" = None,
         restrict_to_workspace: bool = False,
     ):
-        from nanobot.config.schema import ExecToolConfig, WebSearchConfig
+        from nanobot.config.schema import ExecToolConfig
-
         self.provider = provider
         self.workspace = workspace
         self.bus = bus
         self.model = model or provider.get_default_model()
-        self.temperature = temperature
+        self.brave_api_key = brave_api_key
-        self.max_tokens = max_tokens
-        self.reasoning_effort = reasoning_effort
         self.web_proxy = web_proxy
-        self.web_search_config = web_search_config or WebSearchConfig()
         self.exec_config = exec_config or ExecToolConfig()
         self.restrict_to_workspace = restrict_to_workspace
         self._running_tasks: dict[str, asyncio.Task[None]] = {}
@@ -64,7 +58,9 @@ class SubagentManager:
         display_label = label or task[:30] + ("..." if len(task) > 30 else "")
         origin = {"channel": origin_channel, "chat_id": origin_chat_id}
 
-        bg_task = asyncio.create_task(self._run_subagent(task_id, task, display_label, origin))
+        bg_task = asyncio.create_task(
+            self._run_subagent(task_id, task, display_label, origin)
+        )
         self._running_tasks[task_id] = bg_task
         if session_key:
             self._session_tasks.setdefault(session_key, set()).add(task_id)
@@ -99,17 +95,15 @@ class SubagentManager:
             tools.register(WriteFileTool(workspace=self.workspace, allowed_dir=allowed_dir))
             tools.register(EditFileTool(workspace=self.workspace, allowed_dir=allowed_dir))
             tools.register(ListDirTool(workspace=self.workspace, allowed_dir=allowed_dir))
-            tools.register(
+            tools.register(ExecTool(
-                ExecTool(
+                working_dir=str(self.workspace),
-                    working_dir=str(self.workspace),
+                timeout=self.exec_config.timeout,
-                    timeout=self.exec_config.timeout,
+                restrict_to_workspace=self.restrict_to_workspace,
-                    restrict_to_workspace=self.restrict_to_workspace,
+                path_append=self.exec_config.path_append,
-                    path_append=self.exec_config.path_append,
+            ))
-                )
+            tools.register(WebSearchTool(api_key=self.brave_api_key, proxy=self.web_proxy))
-            )
-            tools.register(WebSearchTool(config=self.web_search_config, proxy=self.web_proxy))
             tools.register(WebFetchTool(proxy=self.web_proxy))
-
+            
             system_prompt = self._build_subagent_prompt()
             messages: list[dict[str, Any]] = [
                 {"role": "system", "content": system_prompt},
@@ -124,54 +118,35 @@ class SubagentManager:
             while iteration < max_iterations:
                 iteration += 1
 
-                response = await self.provider.chat(
+                response = await self.provider.chat_with_retry(
                     messages=messages,
                     tools=tools.get_definitions(),
                     model=self.model,
-                    temperature=self.temperature,
-                    max_tokens=self.max_tokens,
-                    reasoning_effort=self.reasoning_effort,
                 )
 
                 if response.has_tool_calls:
-                    # Add assistant message with tool calls
                     tool_call_dicts = [
-                        {
+                        tc.to_openai_tool_call()
-                            "id": tc.id,
-                            "type": "function",
-                            "function": {
-                                "name": tc.name,
-                                "arguments": json.dumps(tc.arguments, ensure_ascii=False),
-                            },
-                        }
                         for tc in response.tool_calls
                     ]
-                    messages.append(
+                    messages.append(build_assistant_message(
-                        {
+                        response.content or "",
-                            "role": "assistant",
+                        tool_calls=tool_call_dicts,
-                            "content": response.content or "",
+                        reasoning_content=response.reasoning_content,
-                            "tool_calls": tool_call_dicts,
+                        thinking_blocks=response.thinking_blocks,
-                        }
+                    ))
-                    )
 
                     # Execute tools
                     for tool_call in response.tool_calls:
                         args_str = json.dumps(tool_call.arguments, ensure_ascii=False)
-                        logger.debug(
+                        logger.debug("Subagent [{}] executing: {} with arguments: {}", task_id, tool_call.name, args_str)
-                            "Subagent [{}] executing: {} with arguments: {}",
-                            task_id,
-                            tool_call.name,
-                            args_str,
-                        )
                         result = await tools.execute(tool_call.name, tool_call.arguments)
-                        messages.append(
+                        messages.append({
-                            {
+                            "role": "tool",
-                                "role": "tool",
+                            "tool_call_id": tool_call.id,
-                                "tool_call_id": tool_call.id,
+                            "name": tool_call.name,
-                                "name": tool_call.name,
+                            "content": result,
-                                "content": result,
+                        })
-                            }
-                        )
                 else:
                     final_result = response.content
                     break
@@ -217,18 +192,15 @@ Summarize this naturally for the user. Keep it brief (1-2 sentences). Do not men
         )
 
         await self.bus.publish_inbound(msg)
-        logger.debug(
+        logger.debug("Subagent [{}] announced result to {}:{}", task_id, origin['channel'], origin['chat_id'])
-            "Subagent [{}] announced result to {}:{}", task_id, origin["channel"], origin["chat_id"]
+    
-        )
-
     def _build_subagent_prompt(self) -> str:
         """Build a focused system prompt for the subagent."""
         from nanobot.agent.context import ContextBuilder
         from nanobot.agent.skills import SkillsLoader
 
         time_ctx = ContextBuilder._build_runtime_context(None, None)
-        parts = [
+        parts = [f"""# Subagent
-            f"""# Subagent
 
 {time_ctx}
 
@@ -236,24 +208,18 @@ You are a subagent spawned by the main agent to complete a specific task.
 Stay focused on the assigned task. Your final response will be reported back to the main agent.
 
 ## Workspace
-{self.workspace}"""
+{self.workspace}"""]
-        ]
 
         skills_summary = SkillsLoader(self.workspace).build_skills_summary()
         if skills_summary:
-            parts.append(
+            parts.append(f"## Skills\n\nRead SKILL.md with read_file to use a skill.\n\n{skills_summary}")
-                f"## Skills\n\nRead SKILL.md with read_file to use a skill.\n\n{skills_summary}"
-            )
 
         return "\n\n".join(parts)
 
     async def cancel_by_session(self, session_key: str) -> int:
         """Cancel all subagents for the given session. Returns count cancelled."""
-        tasks = [
+        tasks = [self._running_tasks[tid] for tid in self._session_tasks.get(session_key, [])
-            self._running_tasks[tid]
+                 if tid in self._running_tasks and not self._running_tasks[tid].done()]
-            for tid in self._session_tasks.get(session_key, [])
-            if tid in self._running_tasks and not self._running_tasks[tid].done()
-        ]
         for t in tasks:
             t.cancel()
         if tasks:

nanobot/agent/tools/filesystem.py

@@ -1,4 +1,4 @@
-"""File system tools: read, write, edit."""
+"""File system tools: read, write, edit, list."""
 
 import difflib
 from pathlib import Path
@@ -23,62 +23,108 @@ def _resolve_path(
     return resolved
 
 
-class ReadFileTool(Tool):
+class _FsTool(Tool):
-    """Tool to read file contents."""
+    """Shared base for filesystem tools — common init and path resolution."""
-
-    _MAX_CHARS = 128_000  # ~128 KB — prevents OOM from reading huge files into LLM context
 
     def __init__(self, workspace: Path | None = None, allowed_dir: Path | None = None):
         self._workspace = workspace
         self._allowed_dir = allowed_dir
 
+    def _resolve(self, path: str) -> Path:
+        return _resolve_path(path, self._workspace, self._allowed_dir)
+
+
+# ---------------------------------------------------------------------------
+# read_file
+# ---------------------------------------------------------------------------
+
+class ReadFileTool(_FsTool):
+    """Read file contents with optional line-based pagination."""
+
+    _MAX_CHARS = 128_000
+    _DEFAULT_LIMIT = 2000
+
     @property
     def name(self) -> str:
         return "read_file"
 
     @property
     def description(self) -> str:
-        return "Read the contents of a file at the given path."
+        return (
+            "Read the contents of a file. Returns numbered lines. "
+            "Use offset and limit to paginate through large files."
+        )
 
     @property
     def parameters(self) -> dict[str, Any]:
         return {
             "type": "object",
-            "properties": {"path": {"type": "string", "description": "The file path to read"}},
+            "properties": {
+                "path": {"type": "string", "description": "The file path to read"},
+                "offset": {
+                    "type": "integer",
+                    "description": "Line number to start reading from (1-indexed, default 1)",
+                    "minimum": 1,
+                },
+                "limit": {
+                    "type": "integer",
+                    "description": "Maximum number of lines to read (default 2000)",
+                    "minimum": 1,
+                },
+            },
             "required": ["path"],
         }
 
-    async def execute(self, path: str, **kwargs: Any) -> str:
+    async def execute(self, path: str, offset: int = 1, limit: int | None = None, **kwargs: Any) -> str:
         try:
-            file_path = _resolve_path(path, self._workspace, self._allowed_dir)
+            fp = self._resolve(path)
-            if not file_path.exists():
+            if not fp.exists():
                 return f"Error: File not found: {path}"
-            if not file_path.is_file():
+            if not fp.is_file():
                 return f"Error: Not a file: {path}"
 
-            size = file_path.stat().st_size
+            all_lines = fp.read_text(encoding="utf-8").splitlines()
-            if size > self._MAX_CHARS * 4:  # rough upper bound (UTF-8 chars ≤ 4 bytes)
+            total = len(all_lines)
-                return (
-                    f"Error: File too large ({size:,} bytes). "
-                    f"Use exec tool with head/tail/grep to read portions."
-                )
 
-            content = file_path.read_text(encoding="utf-8")
+            if offset < 1:
-            if len(content) > self._MAX_CHARS:
+                offset = 1
-                return content[: self._MAX_CHARS] + f"\n\n... (truncated — file is {len(content):,} chars, limit {self._MAX_CHARS:,})"
+            if total == 0:
-            return content
+                return f"(Empty file: {path})"
+            if offset > total:
+                return f"Error: offset {offset} is beyond end of file ({total} lines)"
+
+            start = offset - 1
+            end = min(start + (limit or self._DEFAULT_LIMIT), total)
+            numbered = [f"{start + i + 1}| {line}" for i, line in enumerate(all_lines[start:end])]
+            result = "\n".join(numbered)
+
+            if len(result) > self._MAX_CHARS:
+                trimmed, chars = [], 0
+                for line in numbered:
+                    chars += len(line) + 1
+                    if chars > self._MAX_CHARS:
+                        break
+                    trimmed.append(line)
+                end = start + len(trimmed)
+                result = "\n".join(trimmed)
+
+            if end < total:
+                result += f"\n\n(Showing lines {offset}-{end} of {total}. Use offset={end + 1} to continue.)"
+            else:
+                result += f"\n\n(End of file — {total} lines total)"
+            return result
         except PermissionError as e:
             return f"Error: {e}"
         except Exception as e:
-            return f"Error reading file: {str(e)}"
+            return f"Error reading file: {e}"
 
 
-class WriteFileTool(Tool):
+# ---------------------------------------------------------------------------
-    """Tool to write content to a file."""
+# write_file
+# ---------------------------------------------------------------------------
 
-    def __init__(self, workspace: Path | None = None, allowed_dir: Path | None = None):
+class WriteFileTool(_FsTool):
-        self._workspace = workspace
+    """Write content to a file."""
-        self._allowed_dir = allowed_dir
 
     @property
     def name(self) -> str:
@@ -101,22 +147,48 @@ class WriteFileTool(Tool):
 
     async def execute(self, path: str, content: str, **kwargs: Any) -> str:
         try:
-            file_path = _resolve_path(path, self._workspace, self._allowed_dir)
+            fp = self._resolve(path)
-            file_path.parent.mkdir(parents=True, exist_ok=True)
+            fp.parent.mkdir(parents=True, exist_ok=True)
-            file_path.write_text(content, encoding="utf-8")
+            fp.write_text(content, encoding="utf-8")
-            return f"Successfully wrote {len(content)} bytes to {file_path}"
+            return f"Successfully wrote {len(content)} bytes to {fp}"
         except PermissionError as e:
             return f"Error: {e}"
         except Exception as e:
-            return f"Error writing file: {str(e)}"
+            return f"Error writing file: {e}"
 
 
-class EditFileTool(Tool):
+# ---------------------------------------------------------------------------
-    """Tool to edit a file by replacing text."""
+# edit_file
+# ---------------------------------------------------------------------------
 
-    def __init__(self, workspace: Path | None = None, allowed_dir: Path | None = None):
+def _find_match(content: str, old_text: str) -> tuple[str | None, int]:
-        self._workspace = workspace
+    """Locate old_text in content: exact first, then line-trimmed sliding window.
-        self._allowed_dir = allowed_dir
+
+    Both inputs should use LF line endings (caller normalises CRLF).
+    Returns (matched_fragment, count) or (None, 0).
+    """
+    if old_text in content:
+        return old_text, content.count(old_text)
+
+    old_lines = old_text.splitlines()
+    if not old_lines:
+        return None, 0
+    stripped_old = [l.strip() for l in old_lines]
+    content_lines = content.splitlines()
+
+    candidates = []
+    for i in range(len(content_lines) - len(stripped_old) + 1):
+        window = content_lines[i : i + len(stripped_old)]
+        if [l.strip() for l in window] == stripped_old:
+            candidates.append("\n".join(window))
+
+    if candidates:
+        return candidates[0], len(candidates)
+    return None, 0
+
+
+class EditFileTool(_FsTool):
+    """Edit a file by replacing text with fallback matching."""
 
     @property
     def name(self) -> str:
@@ -124,7 +196,11 @@ class EditFileTool(Tool):
 
     @property
     def description(self) -> str:
-        return "Edit a file by replacing old_text with new_text. The old_text must exist exactly in the file."
+        return (
+            "Edit a file by replacing old_text with new_text. "
+            "Supports minor whitespace/line-ending differences. "
+            "Set replace_all=true to replace every occurrence."
+        )
 
     @property
     def parameters(self) -> dict[str, Any]:
@@ -132,40 +208,52 @@ class EditFileTool(Tool):
             "type": "object",
             "properties": {
                 "path": {"type": "string", "description": "The file path to edit"},
-                "old_text": {"type": "string", "description": "The exact text to find and replace"},
+                "old_text": {"type": "string", "description": "The text to find and replace"},
                 "new_text": {"type": "string", "description": "The text to replace with"},
+                "replace_all": {
+                    "type": "boolean",
+                    "description": "Replace all occurrences (default false)",
+                },
             },
             "required": ["path", "old_text", "new_text"],
         }
 
-    async def execute(self, path: str, old_text: str, new_text: str, **kwargs: Any) -> str:
+    async def execute(
+        self, path: str, old_text: str, new_text: str,
+        replace_all: bool = False, **kwargs: Any,
+    ) -> str:
         try:
-            file_path = _resolve_path(path, self._workspace, self._allowed_dir)
+            fp = self._resolve(path)
-            if not file_path.exists():
+            if not fp.exists():
                 return f"Error: File not found: {path}"
 
-            content = file_path.read_text(encoding="utf-8")
+            raw = fp.read_bytes()
+            uses_crlf = b"\r\n" in raw
+            content = raw.decode("utf-8").replace("\r\n", "\n")
+            match, count = _find_match(content, old_text.replace("\r\n", "\n"))
 
-            if old_text not in content:
+            if match is None:
-                return self._not_found_message(old_text, content, path)
+                return self._not_found_msg(old_text, content, path)
+            if count > 1 and not replace_all:
+                return (
+                    f"Warning: old_text appears {count} times. "
+                    "Provide more context to make it unique, or set replace_all=true."
+                )
 
-            # Count occurrences
+            norm_new = new_text.replace("\r\n", "\n")
-            count = content.count(old_text)
+            new_content = content.replace(match, norm_new) if replace_all else content.replace(match, norm_new, 1)
-            if count > 1:
+            if uses_crlf:
-                return f"Warning: old_text appears {count} times. Please provide more context to make it unique."
+                new_content = new_content.replace("\n", "\r\n")
 
-            new_content = content.replace(old_text, new_text, 1)
+            fp.write_bytes(new_content.encode("utf-8"))
-            file_path.write_text(new_content, encoding="utf-8")
+            return f"Successfully edited {fp}"
-
-            return f"Successfully edited {file_path}"
         except PermissionError as e:
             return f"Error: {e}"
         except Exception as e:
-            return f"Error editing file: {str(e)}"
+            return f"Error editing file: {e}"
 
     @staticmethod
-    def _not_found_message(old_text: str, content: str, path: str) -> str:
+    def _not_found_msg(old_text: str, content: str, path: str) -> str:
-        """Build a helpful error when old_text is not found."""
         lines = content.splitlines(keepends=True)
         old_lines = old_text.splitlines(keepends=True)
         window = len(old_lines)
@@ -177,27 +265,29 @@ class EditFileTool(Tool):
                 best_ratio, best_start = ratio, i
 
         if best_ratio > 0.5:
-            diff = "\n".join(
+            diff = "\n".join(difflib.unified_diff(
-                difflib.unified_diff(
+                old_lines, lines[best_start : best_start + window],
-                    old_lines,
+                fromfile="old_text (provided)",
-                    lines[best_start : best_start + window],
+                tofile=f"{path} (actual, line {best_start + 1})",
-                    fromfile="old_text (provided)",
+                lineterm="",
-                    tofile=f"{path} (actual, line {best_start + 1})",
+            ))
-                    lineterm="",
-                )
-            )
             return f"Error: old_text not found in {path}.\nBest match ({best_ratio:.0%} similar) at line {best_start + 1}:\n{diff}"
-        return (
+        return f"Error: old_text not found in {path}. No similar text found. Verify the file content."
-            f"Error: old_text not found in {path}. No similar text found. Verify the file content."
-        )
 
 
-class ListDirTool(Tool):
+# ---------------------------------------------------------------------------
-    """Tool to list directory contents."""
+# list_dir
+# ---------------------------------------------------------------------------
 
-    def __init__(self, workspace: Path | None = None, allowed_dir: Path | None = None):
+class ListDirTool(_FsTool):
-        self._workspace = workspace
+    """List directory contents with optional recursion."""
-        self._allowed_dir = allowed_dir
+
+    _DEFAULT_MAX = 200
+    _IGNORE_DIRS = {
+        ".git", "node_modules", "__pycache__", ".venv", "venv",
+        "dist", "build", ".tox", ".mypy_cache", ".pytest_cache",
+        ".ruff_cache", ".coverage", "htmlcov",
+    }
 
     @property
     def name(self) -> str:
@@ -205,34 +295,71 @@ class ListDirTool(Tool):
 
     @property
     def description(self) -> str:
-        return "List the contents of a directory."
+        return (
+            "List the contents of a directory. "
+            "Set recursive=true to explore nested structure. "
+            "Common noise directories (.git, node_modules, __pycache__, etc.) are auto-ignored."
+        )
 
     @property
     def parameters(self) -> dict[str, Any]:
         return {
             "type": "object",
-            "properties": {"path": {"type": "string", "description": "The directory path to list"}},
+            "properties": {
+                "path": {"type": "string", "description": "The directory path to list"},
+                "recursive": {
+                    "type": "boolean",
+                    "description": "Recursively list all files (default false)",
+                },
+                "max_entries": {
+                    "type": "integer",
+                    "description": "Maximum entries to return (default 200)",
+                    "minimum": 1,
+                },
+            },
             "required": ["path"],
         }
 
-    async def execute(self, path: str, **kwargs: Any) -> str:
+    async def execute(
+        self, path: str, recursive: bool = False,
+        max_entries: int | None = None, **kwargs: Any,
+    ) -> str:
         try:
-            dir_path = _resolve_path(path, self._workspace, self._allowed_dir)
+            dp = self._resolve(path)
-            if not dir_path.exists():
+            if not dp.exists():
                 return f"Error: Directory not found: {path}"
-            if not dir_path.is_dir():
+            if not dp.is_dir():
                 return f"Error: Not a directory: {path}"
 
-            items = []
+            cap = max_entries or self._DEFAULT_MAX
-            for item in sorted(dir_path.iterdir()):
+            items: list[str] = []
-                prefix = "📁 " if item.is_dir() else "📄 "
+            total = 0
-                items.append(f"{prefix}{item.name}")
 
-            if not items:
+            if recursive:
+                for item in sorted(dp.rglob("*")):
+                    if any(p in self._IGNORE_DIRS for p in item.parts):
+                        continue
+                    total += 1
+                    if len(items) < cap:
+                        rel = item.relative_to(dp)
+                        items.append(f"{rel}/" if item.is_dir() else str(rel))
+            else:
+                for item in sorted(dp.iterdir()):
+                    if item.name in self._IGNORE_DIRS:
+                        continue
+                    total += 1
+                    if len(items) < cap:
+                        pfx = "📁 " if item.is_dir() else "📄 "
+                        items.append(f"{pfx}{item.name}")
+
+            if not items and total == 0:
                 return f"Directory {path} is empty"
 
-            return "\n".join(items)
+            result = "\n".join(items)
+            if total > cap:
+                result += f"\n\n(truncated, showing first {cap} of {total} entries)"
+            return result
         except PermissionError as e:
             return f"Error: {e}"
         except Exception as e:
-            return f"Error listing directory: {str(e)}"
+            return f"Error listing directory: {e}"

nanobot/agent/tools/shell.py

@@ -42,6 +42,9 @@ class ExecTool(Tool):
     def name(self) -> str:
         return "exec"
 
+    _MAX_TIMEOUT = 600
+    _MAX_OUTPUT = 10_000
+
     @property
     def description(self) -> str:
         return "Execute a shell command and return its output. Use with caution."
@@ -53,22 +56,36 @@ class ExecTool(Tool):
             "properties": {
                 "command": {
                     "type": "string",
-                    "description": "The shell command to execute"
+                    "description": "The shell command to execute",
                 },
                 "working_dir": {
                     "type": "string",
-                    "description": "Optional working directory for the command"
+                    "description": "Optional working directory for the command",
-                }
+                },
+                "timeout": {
+                    "type": "integer",
+                    "description": (
+                        "Timeout in seconds. Increase for long-running commands "
+                        "like compilation or installation (default 60, max 600)."
+                    ),
+                    "minimum": 1,
+                    "maximum": 600,
+                },
             },
-            "required": ["command"]
+            "required": ["command"],
         }
-    
+
-    async def execute(self, command: str, working_dir: str | None = None, **kwargs: Any) -> str:
+    async def execute(
+        self, command: str, working_dir: str | None = None,
+        timeout: int | None = None, **kwargs: Any,
+    ) -> str:
         cwd = working_dir or self.working_dir or os.getcwd()
         guard_error = self._guard_command(command, cwd)
         if guard_error:
             return guard_error
-        
+
+        effective_timeout = min(timeout or self.timeout, self._MAX_TIMEOUT)
+
         env = os.environ.copy()
         if self.path_append:
             env["PATH"] = env.get("PATH", "") + os.pathsep + self.path_append
@@ -81,44 +98,46 @@ class ExecTool(Tool):
                 cwd=cwd,
                 env=env,
             )
-            
+
             try:
                 stdout, stderr = await asyncio.wait_for(
                     process.communicate(),
-                    timeout=self.timeout
+                    timeout=effective_timeout,
                 )
             except asyncio.TimeoutError:
                 process.kill()
-                # Wait for the process to fully terminate so pipes are
-                # drained and file descriptors are released.
                 try:
                     await asyncio.wait_for(process.wait(), timeout=5.0)
                 except asyncio.TimeoutError:
                     pass
-                return f"Error: Command timed out after {self.timeout} seconds"
+                return f"Error: Command timed out after {effective_timeout} seconds"
-            
+
             output_parts = []
-            
+
             if stdout:
                 output_parts.append(stdout.decode("utf-8", errors="replace"))
-            
+
             if stderr:
                 stderr_text = stderr.decode("utf-8", errors="replace")
                 if stderr_text.strip():
                     output_parts.append(f"STDERR:\n{stderr_text}")
-            
+
-            if process.returncode != 0:
+            output_parts.append(f"\nExit code: {process.returncode}")
-                output_parts.append(f"\nExit code: {process.returncode}")
+
-            
             result = "\n".join(output_parts) if output_parts else "(no output)"
-            
+
-            # Truncate very long output
+            # Head + tail truncation to preserve both start and end of output
-            max_len = 10000
+            max_len = self._MAX_OUTPUT
             if len(result) > max_len:
-                result = result[:max_len] + f"\n... (truncated, {len(result) - max_len} more chars)"
+                half = max_len // 2
-            
+                result = (
+                    result[:half]
+                    + f"\n\n... ({len(result) - max_len:,} chars truncated) ...\n\n"
+                    + result[-half:]
+                )
+
             return result
-            
+
         except Exception as e:
             return f"Error executing command: {str(e)}"
 
@@ -143,7 +162,8 @@ class ExecTool(Tool):
 
             for raw in self._extract_absolute_paths(cmd):
                 try:
-                    p = Path(raw.strip()).resolve()
+                    expanded = os.path.expandvars(raw.strip())
+                    p = Path(expanded).expanduser().resolve()
                 except Exception:
                     continue
                 if p.is_absolute() and cwd_path not in p.parents and p != cwd_path:
@@ -154,5 +174,6 @@ class ExecTool(Tool):
     @staticmethod
     def _extract_absolute_paths(command: str) -> list[str]:
         win_paths = re.findall(r"[A-Za-z]:\\[^\s\"'|><;]+", command)   # Windows: C:\...
-        posix_paths = re.findall(r"(?:^|[\s|>])(/[^\s\"'>]+)", command) # POSIX: /absolute only
+        posix_paths = re.findall(r"(?:^|[\s|>'\"])(/[^\s\"'>;|<]+)", command) # POSIX: /absolute only
-        return win_paths + posix_paths
+        home_paths = re.findall(r"(?:^|[\s|>'\"])(~[^\s\"'>;|<]*)", command) # POSIX/Windows home shortcut: ~
+        return win_paths + posix_paths + home_paths

nanobot/agent/tools/web.py

@@ -1,16 +1,13 @@
 """Web tools: web_search and web_fetch."""
 
-import asyncio
 import html
 import json
 import os
 import re
-from collections.abc import Awaitable, Callable
 from typing import Any
 from urllib.parse import urlparse
 
 import httpx
-from ddgs import DDGS
 from loguru import logger
 
 from nanobot.agent.tools.base import Tool
@@ -47,22 +44,8 @@ def _validate_url(url: str) -> tuple[bool, str]:
         return False, str(e)
 
 
-def _format_results(query: str, items: list[dict[str, Any]], n: int) -> str:
-    """Format provider results into a shared plaintext output."""
-    if not items:
-        return f"No results for: {query}"
-    lines = [f"Results for: {query}\n"]
-    for i, item in enumerate(items[:n], 1):
-        title = _normalize(_strip_tags(item.get('title', '')))
-        snippet = _normalize(_strip_tags(item.get('content', '')))
-        lines.append(f"{i}. {title}\n   {item.get('url', '')}")
-        if snippet:
-            lines.append(f"   {snippet}")
-    return "\n".join(lines)
-
-
 class WebSearchTool(Tool):
-    """Search the web using configured provider."""
+    """Search the web using Brave Search API."""
 
     name = "web_search"
     description = "Search the web. Returns titles, URLs, and snippets."
@@ -75,133 +58,49 @@ class WebSearchTool(Tool):
         "required": ["query"]
     }
 
-    def __init__(
+    def __init__(self, api_key: str | None = None, max_results: int = 5, proxy: str | None = None):
-        self,
+        self._init_api_key = api_key
-        config: "WebSearchConfig | None" = None,
+        self.max_results = max_results
-        transport: httpx.AsyncBaseTransport | None = None,
-        ddgs_factory: Callable[[], DDGS] | None = None,
-        proxy: str | None = None,
-    ):
-        from nanobot.config.schema import WebSearchConfig
-
-        self.config = config if config is not None else WebSearchConfig()
-        self._transport = transport
-        self._ddgs_factory = ddgs_factory or (lambda: DDGS(timeout=10))
         self.proxy = proxy
-        self._provider_dispatch: dict[str, Callable[[str, int], Awaitable[str]]] = {
+
-            "duckduckgo": self._search_duckduckgo,
+    @property
-            "tavily": self._search_tavily,
+    def api_key(self) -> str:
-            "searxng": self._search_searxng,
+        """Resolve API key at call time so env/config changes are picked up."""
-            "brave": self._search_brave,
+        return self._init_api_key or os.environ.get("BRAVE_API_KEY", "")
-        }
 
     async def execute(self, query: str, count: int | None = None, **kwargs: Any) -> str:
-        provider = (self.config.provider or "brave").strip().lower()
+        if not self.api_key:
-        n = min(max(count or self.config.max_results, 1), 10)
+            return (
-
+                "Error: Brave Search API key not configured. Set it in "
-        search = self._provider_dispatch.get(provider)
+                "~/.nanobot/config.json under tools.web.search.apiKey "
-        if search is None:
+                "(or export BRAVE_API_KEY), then restart the gateway."
-            return f"Error: unknown search provider '{provider}'"
+            )
-        return await search(query, n)
-
-    async def _fallback_to_duckduckgo(self, missing_key: str, query: str, n: int) -> str:
-        logger.warning("Falling back to DuckDuckGo: {} not configured", missing_key)
-        ddg = await self._search_duckduckgo(query=query, n=n)
-        if ddg.startswith('Error:'):
-            return ddg
-        return f'Using DuckDuckGo fallback ({missing_key} missing).\n\n{ddg}'
-
-    async def _search_brave(self, query: str, n: int) -> str:
-        api_key = self.config.api_key or os.environ.get("BRAVE_API_KEY", "")
-        if not api_key:
-            if self.config.fallback_to_duckduckgo:
-                return await self._fallback_to_duckduckgo('BRAVE_API_KEY', query, n)
-            return "Error: BRAVE_API_KEY not configured"
 
         try:
-            async with httpx.AsyncClient(transport=self._transport, proxy=self.proxy) as client:
+            n = min(max(count or self.max_results, 1), 10)
+            logger.debug("WebSearch: {}", "proxy enabled" if self.proxy else "direct connection")
+            async with httpx.AsyncClient(proxy=self.proxy) as client:
                 r = await client.get(
                     "https://api.search.brave.com/res/v1/web/search",
                     params={"q": query, "count": n},
-                    headers={"Accept": "application/json", "X-Subscription-Token": api_key},
+                    headers={"Accept": "application/json", "X-Subscription-Token": self.api_key},
-                    timeout=10.0,
+                    timeout=10.0
                 )
                 r.raise_for_status()
 
-            items = [{"title": x.get("title", ""), "url": x.get("url", ""),
+            results = r.json().get("web", {}).get("results", [])[:n]
-                      "content": x.get("description", "")}
+            if not results:
-                     for x in r.json().get("web", {}).get("results", [])]
-            return _format_results(query, items, n)
-        except Exception as e:
-            return f"Error: {e}"
-
-    async def _search_tavily(self, query: str, n: int) -> str:
-        api_key = self.config.api_key or os.environ.get("TAVILY_API_KEY", "")
-        if not api_key:
-            if self.config.fallback_to_duckduckgo:
-                return await self._fallback_to_duckduckgo('TAVILY_API_KEY', query, n)
-            return "Error: TAVILY_API_KEY not configured"
-
-        try:
-            async with httpx.AsyncClient(transport=self._transport, proxy=self.proxy) as client:
-                r = await client.post(
-                    "https://api.tavily.com/search",
-                    headers={"Authorization": f"Bearer {api_key}"},
-                    json={"query": query, "max_results": n},
-                    timeout=15.0,
-                )
-                r.raise_for_status()
-
-            results = r.json().get("results", [])
-            return _format_results(query, results, n)
-        except Exception as e:
-            return f"Error: {e}"
-
-    async def _search_duckduckgo(self, query: str, n: int) -> str:
-        try:
-            ddgs = self._ddgs_factory()
-            raw_results = await asyncio.to_thread(ddgs.text, query, max_results=n)
-
-            if not raw_results:
                 return f"No results for: {query}"
 
-            items = [
+            lines = [f"Results for: {query}\n"]
-                {
+            for i, item in enumerate(results, 1):
-                    "title": result.get("title", ""),
+                lines.append(f"{i}. {item.get('title', '')}\n   {item.get('url', '')}")
-                    "url": result.get("href", ""),
+                if desc := item.get("description"):
-                    "content": result.get("body", ""),
+                    lines.append(f"   {desc}")
-                }
+            return "\n".join(lines)
-                for result in raw_results
+        except httpx.ProxyError as e:
-            ]
+            logger.error("WebSearch proxy error: {}", e)
-            return _format_results(query, items, n)
+            return f"Proxy error: {e}"
-        except Exception as e:
-            logger.warning("DuckDuckGo search failed: {}", e)
-            return f"Error: DuckDuckGo search failed ({e})"
-
-    async def _search_searxng(self, query: str, n: int) -> str:
-        base_url = (self.config.base_url or os.environ.get("SEARXNG_BASE_URL", "")).strip()
-        if not base_url:
-            if self.config.fallback_to_duckduckgo:
-                return await self._fallback_to_duckduckgo('SEARXNG_BASE_URL', query, n)
-            return "Error: SEARXNG_BASE_URL not configured"
-
-        endpoint = f"{base_url.rstrip('/')}/search"
-        is_valid, error_msg = _validate_url(endpoint)
-        if not is_valid:
-            return f"Error: invalid SearXNG URL: {error_msg}"
-
-        try:
-            async with httpx.AsyncClient(transport=self._transport, proxy=self.proxy) as client:
-                r = await client.get(
-                    endpoint,
-                    params={"q": query, "format": "json"},
-                    headers={"User-Agent": USER_AGENT},
-                    timeout=10.0,
-                )
-                r.raise_for_status()
-
-            results = r.json().get("results", [])
-            return _format_results(query, results, n)
         except Exception as e:
             logger.error("WebSearch error: {}", e)
             return f"Error: {e}"
@@ -258,8 +157,7 @@ class WebFetchTool(Tool):
                 text, extractor = r.text, "raw"
 
             truncated = len(text) > max_chars
-            if truncated:
+            if truncated: text = text[:max_chars]
-                text = text[:max_chars]
 
             return json.dumps({"url": url, "finalUrl": str(r.url), "status": r.status_code,
                               "extractor": extractor, "truncated": truncated, "length": len(text), "text": text}, ensure_ascii=False)

nanobot/channels/base.py

@@ -1,6 +1,9 @@
 """Base channel interface for chat platforms."""
 
+from __future__ import annotations
+
 from abc import ABC, abstractmethod
+from pathlib import Path
 from typing import Any
 
 from loguru import logger
@@ -18,6 +21,8 @@ class BaseChannel(ABC):
     """
 
     name: str = "base"
+    display_name: str = "Base"
+    transcription_api_key: str = ""
 
     def __init__(self, config: Any, bus: MessageBus):
         """
@@ -31,6 +36,19 @@ class BaseChannel(ABC):
         self.bus = bus
         self._running = False
 
+    async def transcribe_audio(self, file_path: str | Path) -> str:
+        """Transcribe an audio file via Groq Whisper. Returns empty string on failure."""
+        if not self.transcription_api_key:
+            return ""
+        try:
+            from nanobot.providers.transcription import GroqTranscriptionProvider
+
+            provider = GroqTranscriptionProvider(api_key=self.transcription_api_key)
+            return await provider.transcribe(file_path)
+        except Exception as e:
+            logger.warning("{}: audio transcription failed: {}", self.name, e)
+            return ""
+
     @abstractmethod
     async def start(self) -> None:
         """

nanobot/channels/dingtalk.py

@@ -57,6 +57,8 @@ class NanobotDingTalkHandler(CallbackHandler):
             content = ""
             if chatbot_msg.text:
                 content = chatbot_msg.text.content.strip()
+            elif chatbot_msg.extensions.get("content", {}).get("recognition"):
+                content = chatbot_msg.extensions["content"]["recognition"].strip()
             if not content:
                 content = message.data.get("text", {}).get("content", "").strip()
 
@@ -112,6 +114,7 @@ class DingTalkChannel(BaseChannel):
     """
 
     name = "dingtalk"
+    display_name = "DingTalk"
     _IMAGE_EXTS = {".jpg", ".jpeg", ".png", ".gif", ".bmp", ".webp"}
     _AUDIO_EXTS = {".amr", ".mp3", ".wav", ".ogg", ".m4a", ".aac"}
     _VIDEO_EXTS = {".mp4", ".mov", ".avi", ".mkv", ".webm"}

nanobot/channels/discord.py

@@ -25,6 +25,7 @@ class DiscordChannel(BaseChannel):
     """Discord channel using Gateway websocket."""
 
     name = "discord"
+    display_name = "Discord"
 
     def __init__(self, config: DiscordConfig, bus: MessageBus):
         super().__init__(config, bus)

nanobot/channels/email.py

@@ -35,6 +35,7 @@ class EmailChannel(BaseChannel):
     """
 
     name = "email"
+    display_name = "Email"
     _IMAP_MONTHS = (
         "Jan",
         "Feb",

nanobot/channels/feishu.py

@@ -244,11 +244,11 @@ class FeishuChannel(BaseChannel):
     """
 
     name = "feishu"
+    display_name = "Feishu"
 
-    def __init__(self, config: FeishuConfig, bus: MessageBus, groq_api_key: str = ""):
+    def __init__(self, config: FeishuConfig, bus: MessageBus):
         super().__init__(config, bus)
         self.config: FeishuConfig = config
-        self.groq_api_key = groq_api_key
         self._client: Any = None
         self._ws_client: Any = None
         self._ws_thread: threading.Thread | None = None
@@ -352,6 +352,27 @@ class FeishuChannel(BaseChannel):
         self._running = False
         logger.info("Feishu bot stopped")
 
+    def _is_bot_mentioned(self, message: Any) -> bool:
+        """Check if the bot is @mentioned in the message."""
+        raw_content = message.content or ""
+        if "@_all" in raw_content:
+            return True
+
+        for mention in getattr(message, "mentions", None) or []:
+            mid = getattr(mention, "id", None)
+            if not mid:
+                continue
+            # Bot mentions have no user_id (None or "") but a valid open_id
+            if not getattr(mid, "user_id", None) and (getattr(mid, "open_id", None) or "").startswith("ou_"):
+                return True
+        return False
+
+    def _is_group_message_for_bot(self, message: Any) -> bool:
+        """Allow group messages when policy is open or bot is @mentioned."""
+        if self.config.group_policy == "open":
+            return True
+        return self._is_bot_mentioned(message)
+
     def _add_reaction_sync(self, message_id: str, emoji_type: str) -> None:
         """Sync helper for adding reaction (runs in thread pool)."""
         from lark_oapi.api.im.v1 import CreateMessageReactionRequest, CreateMessageReactionRequestBody, Emoji
@@ -893,6 +914,10 @@ class FeishuChannel(BaseChannel):
             chat_type = message.chat_type
             msg_type = message.message_type
 
+            if chat_type == "group" and not self._is_group_message_for_bot(message):
+                logger.debug("Feishu: skipping group message (not mentioned)")
+                return
+
             # Add reaction
             await self._add_reaction(message_id, self.config.react_emoji)
 
@@ -928,16 +953,10 @@ class FeishuChannel(BaseChannel):
                 if file_path:
                     media_paths.append(file_path)
 
-                # Transcribe audio using Groq Whisper
+                if msg_type == "audio" and file_path:
-                if msg_type == "audio" and file_path and self.groq_api_key:
+                    transcription = await self.transcribe_audio(file_path)
-                    try:
+                    if transcription:
-                        from nanobot.providers.transcription import GroqTranscriptionProvider
+                        content_text = f"[transcription: {transcription}]"
-                        transcriber = GroqTranscriptionProvider(api_key=self.groq_api_key)
-                        transcription = await transcriber.transcribe(file_path)
-                        if transcription:
-                            content_text = f"[transcription: {transcription}]"
-                    except Exception as e:
-                        logger.warning("Failed to transcribe audio: {}", e)
 
                 content_parts.append(content_text)
 

nanobot/channels/manager.py

@@ -7,7 +7,6 @@ from typing import Any
 
 from loguru import logger
 
-from nanobot.bus.events import OutboundMessage
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.schema import Config
@@ -32,123 +31,23 @@ class ChannelManager:
         self._init_channels()
 
     def _init_channels(self) -> None:
-        """Initialize channels based on config."""
+        """Initialize channels discovered via pkgutil scan."""
+        from nanobot.channels.registry import discover_channel_names, load_channel_class
 
-        # Telegram channel
+        groq_key = self.config.providers.groq.api_key
-        if self.config.channels.telegram.enabled:
+
+        for modname in discover_channel_names():
+            section = getattr(self.config.channels, modname, None)
+            if not section or not getattr(section, "enabled", False):
+                continue
             try:
-                from nanobot.channels.telegram import TelegramChannel
+                cls = load_channel_class(modname)
-                self.channels["telegram"] = TelegramChannel(
+                channel = cls(section, self.bus)
-                    self.config.channels.telegram,
+                channel.transcription_api_key = groq_key
-                    self.bus,
+                self.channels[modname] = channel
-                    groq_api_key=self.config.providers.groq.api_key,
+                logger.info("{} channel enabled", cls.display_name)
-                )
-                logger.info("Telegram channel enabled")
             except ImportError as e:
-                logger.warning("Telegram channel not available: {}", e)
+                logger.warning("{} channel not available: {}", modname, e)
-
-        # WhatsApp channel
-        if self.config.channels.whatsapp.enabled:
-            try:
-                from nanobot.channels.whatsapp import WhatsAppChannel
-                self.channels["whatsapp"] = WhatsAppChannel(
-                    self.config.channels.whatsapp, self.bus
-                )
-                logger.info("WhatsApp channel enabled")
-            except ImportError as e:
-                logger.warning("WhatsApp channel not available: {}", e)
-
-        # Discord channel
-        if self.config.channels.discord.enabled:
-            try:
-                from nanobot.channels.discord import DiscordChannel
-                self.channels["discord"] = DiscordChannel(
-                    self.config.channels.discord, self.bus
-                )
-                logger.info("Discord channel enabled")
-            except ImportError as e:
-                logger.warning("Discord channel not available: {}", e)
-
-        # Feishu channel
-        if self.config.channels.feishu.enabled:
-            try:
-                from nanobot.channels.feishu import FeishuChannel
-                self.channels["feishu"] = FeishuChannel(
-                    self.config.channels.feishu, self.bus,
-                    groq_api_key=self.config.providers.groq.api_key,
-                )
-                logger.info("Feishu channel enabled")
-            except ImportError as e:
-                logger.warning("Feishu channel not available: {}", e)
-
-        # Mochat channel
-        if self.config.channels.mochat.enabled:
-            try:
-                from nanobot.channels.mochat import MochatChannel
-
-                self.channels["mochat"] = MochatChannel(
-                    self.config.channels.mochat, self.bus
-                )
-                logger.info("Mochat channel enabled")
-            except ImportError as e:
-                logger.warning("Mochat channel not available: {}", e)
-
-        # DingTalk channel
-        if self.config.channels.dingtalk.enabled:
-            try:
-                from nanobot.channels.dingtalk import DingTalkChannel
-                self.channels["dingtalk"] = DingTalkChannel(
-                    self.config.channels.dingtalk, self.bus
-                )
-                logger.info("DingTalk channel enabled")
-            except ImportError as e:
-                logger.warning("DingTalk channel not available: {}", e)
-
-        # Email channel
-        if self.config.channels.email.enabled:
-            try:
-                from nanobot.channels.email import EmailChannel
-                self.channels["email"] = EmailChannel(
-                    self.config.channels.email, self.bus
-                )
-                logger.info("Email channel enabled")
-            except ImportError as e:
-                logger.warning("Email channel not available: {}", e)
-
-        # Slack channel
-        if self.config.channels.slack.enabled:
-            try:
-                from nanobot.channels.slack import SlackChannel
-                self.channels["slack"] = SlackChannel(
-                    self.config.channels.slack, self.bus
-                )
-                logger.info("Slack channel enabled")
-            except ImportError as e:
-                logger.warning("Slack channel not available: {}", e)
-
-        # QQ channel
-        if self.config.channels.qq.enabled:
-            try:
-                from nanobot.channels.qq import QQChannel
-                self.channels["qq"] = QQChannel(
-                    self.config.channels.qq,
-                    self.bus,
-                )
-                logger.info("QQ channel enabled")
-            except ImportError as e:
-                logger.warning("QQ channel not available: {}", e)
-
-        # Matrix channel
-        if self.config.channels.matrix.enabled:
-            try:
-                from nanobot.channels.matrix import MatrixChannel
-                self.channels["matrix"] = MatrixChannel(
-                    self.config.channels.matrix,
-                    self.bus,
-                )
-                logger.info("Matrix channel enabled")
-            except ImportError as e:
-                logger.warning("Matrix channel not available: {}", e)
 
         self._validate_allow_from()
 

nanobot/channels/matrix.py

@@ -37,6 +37,7 @@ except ImportError as e:
     ) from e
 
 from nanobot.bus.events import OutboundMessage
+from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.paths import get_data_dir, get_media_dir
 from nanobot.utils.helpers import safe_filename
@@ -146,15 +147,24 @@ class MatrixChannel(BaseChannel):
     """Matrix (Element) channel using long-polling sync."""
 
     name = "matrix"
+    display_name = "Matrix"
 
-    def __init__(self, config: Any, bus, *, restrict_to_workspace: bool = False,
+    def __init__(
-                 workspace: Path | None = None):
+        self,
+        config: Any,
+        bus: MessageBus,
+        *,
+        restrict_to_workspace: bool = False,
+        workspace: str | Path | None = None,
+    ):
         super().__init__(config, bus)
         self.client: AsyncClient | None = None
         self._sync_task: asyncio.Task | None = None
         self._typing_tasks: dict[str, asyncio.Task] = {}
-        self._restrict_to_workspace = restrict_to_workspace
+        self._restrict_to_workspace = bool(restrict_to_workspace)
-        self._workspace = workspace.expanduser().resolve() if workspace else None
+        self._workspace = (
+            Path(workspace).expanduser().resolve(strict=False) if workspace is not None else None
+        )
         self._server_upload_limit_bytes: int | None = None
         self._server_upload_limit_checked = False
 
@@ -677,7 +687,14 @@ class MatrixChannel(BaseChannel):
         parts: list[str] = []
         if isinstance(body := getattr(event, "body", None), str) and body.strip():
             parts.append(body.strip())
-        if marker:
+
+        if attachment and attachment.get("type") == "audio":
+            transcription = await self.transcribe_audio(attachment["path"])
+            if transcription:
+                parts.append(f"[transcription: {transcription}]")
+            else:
+                parts.append(marker)
+        elif marker:
             parts.append(marker)
 
         await self._start_typing_keepalive(room.room_id)

nanobot/channels/mochat.py

@@ -216,6 +216,7 @@ class MochatChannel(BaseChannel):
     """Mochat channel using socket.io with fallback polling workers."""
 
     name = "mochat"
+    display_name = "Mochat"
 
     def __init__(self, config: MochatConfig, bus: MessageBus):
         super().__init__(config, bus)

nanobot/channels/qq.py

@@ -54,6 +54,7 @@ class QQChannel(BaseChannel):
     """QQ channel using botpy SDK with WebSocket connection."""
 
     name = "qq"
+    display_name = "QQ"
 
     def __init__(self, config: QQConfig, bus: MessageBus):
         super().__init__(config, bus)
@@ -113,16 +114,16 @@ class QQChannel(BaseChannel):
             if msg_type == "group":
                 await self._client.api.post_group_message(
                     group_openid=msg.chat_id,
-                    msg_type=2,
+                    msg_type=0,
-                    markdown={"content": msg.content},
+                    content=msg.content,
                     msg_id=msg_id,
                     msg_seq=self._msg_seq,
                 )
             else:
                 await self._client.api.post_c2c_message(
                     openid=msg.chat_id,
-                    msg_type=2,
+                    msg_type=0,
-                    markdown={"content": msg.content},
+                    content=msg.content,
                     msg_id=msg_id,
                     msg_seq=self._msg_seq,
                 )

nanobot/channels/registry.py

@@ -0,0 +1,35 @@
+"""Auto-discovery for channel modules — no hardcoded registry."""
+
+from __future__ import annotations
+
+import importlib
+import pkgutil
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from nanobot.channels.base import BaseChannel
+
+_INTERNAL = frozenset({"base", "manager", "registry"})
+
+
+def discover_channel_names() -> list[str]:
+    """Return all channel module names by scanning the package (zero imports)."""
+    import nanobot.channels as pkg
+
+    return [
+        name
+        for _, name, ispkg in pkgutil.iter_modules(pkg.__path__)
+        if name not in _INTERNAL and not ispkg
+    ]
+
+
+def load_channel_class(module_name: str) -> type[BaseChannel]:
+    """Import *module_name* and return the first BaseChannel subclass found."""
+    from nanobot.channels.base import BaseChannel as _Base
+
+    mod = importlib.import_module(f"nanobot.channels.{module_name}")
+    for attr in dir(mod):
+        obj = getattr(mod, attr)
+        if isinstance(obj, type) and issubclass(obj, _Base) and obj is not _Base:
+            return obj
+    raise ImportError(f"No BaseChannel subclass in nanobot.channels.{module_name}")

nanobot/channels/slack.py

@@ -21,6 +21,7 @@ class SlackChannel(BaseChannel):
     """Slack channel using Socket Mode."""
 
     name = "slack"
+    display_name = "Slack"
 
     def __init__(self, config: SlackConfig, bus: MessageBus):
         super().__init__(config, bus)

nanobot/channels/telegram.py

@@ -20,6 +20,7 @@ from nanobot.config.schema import TelegramConfig
 from nanobot.utils.helpers import split_message
 
 TELEGRAM_MAX_MESSAGE_LEN = 4000  # Telegram message character limit
+TELEGRAM_REPLY_CONTEXT_MAX_LEN = TELEGRAM_MAX_MESSAGE_LEN  # Max length for reply context in user message
 
 
 def _strip_md(s: str) -> str:
@@ -155,6 +156,7 @@ class TelegramChannel(BaseChannel):
     """
 
     name = "telegram"
+    display_name = "Telegram"
 
     # Commands registered with Telegram's command menu
     BOT_COMMANDS = [
@@ -162,23 +164,20 @@ class TelegramChannel(BaseChannel):
         BotCommand("new", "Start a new conversation"),
         BotCommand("stop", "Stop the current task"),
         BotCommand("help", "Show available commands"),
+        BotCommand("restart", "Restart the bot"),
     ]
 
-    def __init__(
+    def __init__(self, config: TelegramConfig, bus: MessageBus):
-        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
         self._typing_tasks: dict[str, asyncio.Task] = {}  # chat_id -> typing loop task
         self._media_group_buffers: dict[str, dict] = {}
         self._media_group_tasks: dict[str, asyncio.Task] = {}
         self._message_threads: dict[tuple[str, int], int] = {}
+        self._bot_user_id: int | None = None
+        self._bot_username: str | None = None
 
     def is_allowed(self, sender_id: str) -> bool:
         """Preserve Telegram's legacy id|username allowlist matching."""
@@ -223,6 +222,7 @@ class TelegramChannel(BaseChannel):
         self._app.add_handler(CommandHandler("start", self._on_start))
         self._app.add_handler(CommandHandler("new", self._forward_command))
         self._app.add_handler(CommandHandler("stop", self._forward_command))
+        self._app.add_handler(CommandHandler("restart", self._forward_command))
         self._app.add_handler(CommandHandler("help", self._on_help))
 
         # Add message handler for text, photos, voice, documents
@@ -242,6 +242,8 @@ class TelegramChannel(BaseChannel):
 
         # Get bot info and register command menu
         bot_info = await self._app.bot.get_me()
+        self._bot_user_id = getattr(bot_info, "id", None)
+        self._bot_username = getattr(bot_info, "username", None)
         logger.info("Telegram bot @{} connected", bot_info.username)
 
         try:
@@ -452,6 +454,7 @@ class TelegramChannel(BaseChannel):
     @staticmethod
     def _build_message_metadata(message, user) -> dict:
         """Build common Telegram inbound metadata payload."""
+        reply_to = getattr(message, "reply_to_message", None)
         return {
             "message_id": message.message_id,
             "user_id": user.id,
@@ -460,8 +463,137 @@ class TelegramChannel(BaseChannel):
             "is_group": message.chat.type != "private",
             "message_thread_id": getattr(message, "message_thread_id", None),
             "is_forum": bool(getattr(message.chat, "is_forum", False)),
+            "reply_to_message_id": getattr(reply_to, "message_id", None) if reply_to else None,
         }
 
+    @staticmethod
+    def _extract_reply_context(message) -> str | None:
+        """Extract text from the message being replied to, if any."""
+        reply = getattr(message, "reply_to_message", None)
+        if not reply:
+            return None
+        text = getattr(reply, "text", None) or getattr(reply, "caption", None) or ""
+        if len(text) > TELEGRAM_REPLY_CONTEXT_MAX_LEN:
+            text = text[:TELEGRAM_REPLY_CONTEXT_MAX_LEN] + "..."
+        return f"[Reply to: {text}]" if text else None
+
+    async def _download_message_media(
+        self, msg, *, add_failure_content: bool = False
+    ) -> tuple[list[str], list[str]]:
+        """Download media from a message (current or reply). Returns (media_paths, content_parts)."""
+        media_file = None
+        media_type = None
+        if getattr(msg, "photo", None):
+            media_file = msg.photo[-1]
+            media_type = "image"
+        elif getattr(msg, "voice", None):
+            media_file = msg.voice
+            media_type = "voice"
+        elif getattr(msg, "audio", None):
+            media_file = msg.audio
+            media_type = "audio"
+        elif getattr(msg, "document", None):
+            media_file = msg.document
+            media_type = "file"
+        elif getattr(msg, "video", None):
+            media_file = msg.video
+            media_type = "video"
+        elif getattr(msg, "video_note", None):
+            media_file = msg.video_note
+            media_type = "video"
+        elif getattr(msg, "animation", None):
+            media_file = msg.animation
+            media_type = "animation"
+        if not media_file or not self._app:
+            return [], []
+        try:
+            file = await self._app.bot.get_file(media_file.file_id)
+            ext = self._get_extension(
+                media_type,
+                getattr(media_file, "mime_type", None),
+                getattr(media_file, "file_name", None),
+            )
+            media_dir = get_media_dir("telegram")
+            file_path = media_dir / f"{media_file.file_id[:16]}{ext}"
+            await file.download_to_drive(str(file_path))
+            path_str = str(file_path)
+            if media_type in ("voice", "audio"):
+                transcription = await self.transcribe_audio(file_path)
+                if transcription:
+                    logger.info("Transcribed {}: {}...", media_type, transcription[:50])
+                    return [path_str], [f"[transcription: {transcription}]"]
+                return [path_str], [f"[{media_type}: {path_str}]"]
+            return [path_str], [f"[{media_type}: {path_str}]"]
+        except Exception as e:
+            logger.warning("Failed to download message media: {}", e)
+            if add_failure_content:
+                return [], [f"[{media_type}: download failed]"]
+            return [], []
+
+    async def _ensure_bot_identity(self) -> tuple[int | None, str | None]:
+        """Load bot identity once and reuse it for mention/reply checks."""
+        if self._bot_user_id is not None or self._bot_username is not None:
+            return self._bot_user_id, self._bot_username
+        if not self._app:
+            return None, None
+        bot_info = await self._app.bot.get_me()
+        self._bot_user_id = getattr(bot_info, "id", None)
+        self._bot_username = getattr(bot_info, "username", None)
+        return self._bot_user_id, self._bot_username
+
+    @staticmethod
+    def _has_mention_entity(
+        text: str,
+        entities,
+        bot_username: str,
+        bot_id: int | None,
+    ) -> bool:
+        """Check Telegram mention entities against the bot username."""
+        handle = f"@{bot_username}".lower()
+        for entity in entities or []:
+            entity_type = getattr(entity, "type", None)
+            if entity_type == "text_mention":
+                user = getattr(entity, "user", None)
+                if user is not None and bot_id is not None and getattr(user, "id", None) == bot_id:
+                    return True
+                continue
+            if entity_type != "mention":
+                continue
+            offset = getattr(entity, "offset", None)
+            length = getattr(entity, "length", None)
+            if offset is None or length is None:
+                continue
+            if text[offset : offset + length].lower() == handle:
+                return True
+        return handle in text.lower()
+
+    async def _is_group_message_for_bot(self, message) -> bool:
+        """Allow group messages when policy is open, @mentioned, or replying to the bot."""
+        if message.chat.type == "private" or self.config.group_policy == "open":
+            return True
+
+        bot_id, bot_username = await self._ensure_bot_identity()
+        if bot_username:
+            text = message.text or ""
+            caption = message.caption or ""
+            if self._has_mention_entity(
+                text,
+                getattr(message, "entities", None),
+                bot_username,
+                bot_id,
+            ):
+                return True
+            if self._has_mention_entity(
+                caption,
+                getattr(message, "caption_entities", None),
+                bot_username,
+                bot_id,
+            ):
+                return True
+
+        reply_user = getattr(getattr(message, "reply_to_message", None), "from_user", None)
+        return bool(bot_id and reply_user and reply_user.id == bot_id)
+
     def _remember_thread_context(self, message) -> None:
         """Cache topic thread id by chat/message id for follow-up replies."""
         message_thread_id = getattr(message, "message_thread_id", None)
@@ -482,7 +614,7 @@ class TelegramChannel(BaseChannel):
         await self._handle_message(
             sender_id=self._sender_id(user),
             chat_id=str(message.chat_id),
-            content=message.text,
+            content=message.text or "",
             metadata=self._build_message_metadata(message, user),
             session_key=self._derive_topic_session_key(message),
         )
@@ -501,6 +633,9 @@ class TelegramChannel(BaseChannel):
         # Store chat_id for replies
         self._chat_ids[sender_id] = chat_id
 
+        if not await self._is_group_message_for_bot(message):
+            return
+
         # Build content from text and/or media
         content_parts = []
         media_paths = []
@@ -511,57 +646,26 @@ class TelegramChannel(BaseChannel):
         if message.caption:
             content_parts.append(message.caption)
 
-        # Handle media files
+        # Download current message media
-        media_file = None
+        current_media_paths, current_media_parts = await self._download_message_media(
-        media_type = None
+            message, add_failure_content=True
-
+        )
-        if message.photo:
+        media_paths.extend(current_media_paths)
-            media_file = message.photo[-1]  # Largest photo
+        content_parts.extend(current_media_parts)
-            media_type = "image"
+        if current_media_paths:
-        elif message.voice:
+            logger.debug("Downloaded message media to {}", current_media_paths[0])
-            media_file = message.voice
-            media_type = "voice"
-        elif message.audio:
-            media_file = message.audio
-            media_type = "audio"
-        elif message.document:
-            media_file = message.document
-            media_type = "file"
-
-        # Download media if present
-        if media_file and self._app:
-            try:
-                file = await self._app.bot.get_file(media_file.file_id)
-                ext = self._get_extension(
-                    media_type,
-                    getattr(media_file, 'mime_type', None),
-                    getattr(media_file, 'file_name', None),
-                )
-                media_dir = get_media_dir("telegram")
-
-                file_path = media_dir / f"{media_file.file_id[:16]}{ext}"
-                await file.download_to_drive(str(file_path))
-
-                media_paths.append(str(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("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("Downloaded {} to {}", media_type, file_path)
-            except Exception as e:
-                logger.error("Failed to download media: {}", e)
-                content_parts.append(f"[{media_type}: download failed]")
 
+        # Reply context: text and/or media from the replied-to message
+        reply = getattr(message, "reply_to_message", None)
+        if reply is not None:
+            reply_ctx = self._extract_reply_context(message)
+            reply_media, reply_media_parts = await self._download_message_media(reply)
+            if reply_media:
+                media_paths = reply_media + media_paths
+                logger.debug("Attached replied-to media: {}", reply_media[0])
+            tag = reply_ctx or (f"[Reply to: {reply_media_parts[0]}]" if reply_media_parts else None)
+            if tag:
+                content_parts.insert(0, tag)
         content = "\n".join(content_parts) if content_parts else "[empty message]"
 
         logger.debug("Telegram message from {}: {}...", sender_id, content[:50])

nanobot/channels/wecom.py

@@ -0,0 +1,353 @@
+"""WeCom (Enterprise WeChat) channel implementation using wecom_aibot_sdk."""
+
+import asyncio
+import importlib.util
+import os
+from collections import OrderedDict
+from typing import Any
+
+from loguru import logger
+
+from nanobot.bus.events import OutboundMessage
+from nanobot.bus.queue import MessageBus
+from nanobot.channels.base import BaseChannel
+from nanobot.config.paths import get_media_dir
+from nanobot.config.schema import WecomConfig
+
+WECOM_AVAILABLE = importlib.util.find_spec("wecom_aibot_sdk") is not None
+
+# Message type display mapping
+MSG_TYPE_MAP = {
+    "image": "[image]",
+    "voice": "[voice]",
+    "file": "[file]",
+    "mixed": "[mixed content]",
+}
+
+
+class WecomChannel(BaseChannel):
+    """
+    WeCom (Enterprise WeChat) channel using WebSocket long connection.
+
+    Uses WebSocket to receive events - no public IP or webhook required.
+
+    Requires:
+    - Bot ID and Secret from WeCom AI Bot platform
+    """
+
+    name = "wecom"
+    display_name = "WeCom"
+
+    def __init__(self, config: WecomConfig, bus: MessageBus):
+        super().__init__(config, bus)
+        self.config: WecomConfig = config
+        self._client: Any = None
+        self._processed_message_ids: OrderedDict[str, None] = OrderedDict()
+        self._loop: asyncio.AbstractEventLoop | None = None
+        self._generate_req_id = None
+        # Store frame headers for each chat to enable replies
+        self._chat_frames: dict[str, Any] = {}
+
+    async def start(self) -> None:
+        """Start the WeCom bot with WebSocket long connection."""
+        if not WECOM_AVAILABLE:
+            logger.error("WeCom SDK not installed. Run: pip install nanobot-ai[wecom]")
+            return
+
+        if not self.config.bot_id or not self.config.secret:
+            logger.error("WeCom bot_id and secret not configured")
+            return
+
+        from wecom_aibot_sdk import WSClient, generate_req_id
+
+        self._running = True
+        self._loop = asyncio.get_running_loop()
+        self._generate_req_id = generate_req_id
+
+        # Create WebSocket client
+        self._client = WSClient({
+            "bot_id": self.config.bot_id,
+            "secret": self.config.secret,
+            "reconnect_interval": 1000,
+            "max_reconnect_attempts": -1,  # Infinite reconnect
+            "heartbeat_interval": 30000,
+        })
+
+        # Register event handlers
+        self._client.on("connected", self._on_connected)
+        self._client.on("authenticated", self._on_authenticated)
+        self._client.on("disconnected", self._on_disconnected)
+        self._client.on("error", self._on_error)
+        self._client.on("message.text", self._on_text_message)
+        self._client.on("message.image", self._on_image_message)
+        self._client.on("message.voice", self._on_voice_message)
+        self._client.on("message.file", self._on_file_message)
+        self._client.on("message.mixed", self._on_mixed_message)
+        self._client.on("event.enter_chat", self._on_enter_chat)
+
+        logger.info("WeCom bot starting with WebSocket long connection")
+        logger.info("No public IP required - using WebSocket to receive events")
+
+        # Connect
+        await self._client.connect_async()
+
+        # Keep running until stopped
+        while self._running:
+            await asyncio.sleep(1)
+
+    async def stop(self) -> None:
+        """Stop the WeCom bot."""
+        self._running = False
+        if self._client:
+            await self._client.disconnect()
+        logger.info("WeCom bot stopped")
+
+    async def _on_connected(self, frame: Any) -> None:
+        """Handle WebSocket connected event."""
+        logger.info("WeCom WebSocket connected")
+
+    async def _on_authenticated(self, frame: Any) -> None:
+        """Handle authentication success event."""
+        logger.info("WeCom authenticated successfully")
+
+    async def _on_disconnected(self, frame: Any) -> None:
+        """Handle WebSocket disconnected event."""
+        reason = frame.body if hasattr(frame, 'body') else str(frame)
+        logger.warning("WeCom WebSocket disconnected: {}", reason)
+
+    async def _on_error(self, frame: Any) -> None:
+        """Handle error event."""
+        logger.error("WeCom error: {}", frame)
+
+    async def _on_text_message(self, frame: Any) -> None:
+        """Handle text message."""
+        await self._process_message(frame, "text")
+
+    async def _on_image_message(self, frame: Any) -> None:
+        """Handle image message."""
+        await self._process_message(frame, "image")
+
+    async def _on_voice_message(self, frame: Any) -> None:
+        """Handle voice message."""
+        await self._process_message(frame, "voice")
+
+    async def _on_file_message(self, frame: Any) -> None:
+        """Handle file message."""
+        await self._process_message(frame, "file")
+
+    async def _on_mixed_message(self, frame: Any) -> None:
+        """Handle mixed content message."""
+        await self._process_message(frame, "mixed")
+
+    async def _on_enter_chat(self, frame: Any) -> None:
+        """Handle enter_chat event (user opens chat with bot)."""
+        try:
+            # Extract body from WsFrame dataclass or dict
+            if hasattr(frame, 'body'):
+                body = frame.body or {}
+            elif isinstance(frame, dict):
+                body = frame.get("body", frame)
+            else:
+                body = {}
+
+            chat_id = body.get("chatid", "") if isinstance(body, dict) else ""
+
+            if chat_id and self.config.welcome_message:
+                await self._client.reply_welcome(frame, {
+                    "msgtype": "text",
+                    "text": {"content": self.config.welcome_message},
+                })
+        except Exception as e:
+            logger.error("Error handling enter_chat: {}", e)
+
+    async def _process_message(self, frame: Any, msg_type: str) -> None:
+        """Process incoming message and forward to bus."""
+        try:
+            # Extract body from WsFrame dataclass or dict
+            if hasattr(frame, 'body'):
+                body = frame.body or {}
+            elif isinstance(frame, dict):
+                body = frame.get("body", frame)
+            else:
+                body = {}
+
+            # Ensure body is a dict
+            if not isinstance(body, dict):
+                logger.warning("Invalid body type: {}", type(body))
+                return
+
+            # Extract message info
+            msg_id = body.get("msgid", "")
+            if not msg_id:
+                msg_id = f"{body.get('chatid', '')}_{body.get('sendertime', '')}"
+
+            # Deduplication check
+            if msg_id in self._processed_message_ids:
+                return
+            self._processed_message_ids[msg_id] = None
+
+            # Trim cache
+            while len(self._processed_message_ids) > 1000:
+                self._processed_message_ids.popitem(last=False)
+
+            # Extract sender info from "from" field (SDK format)
+            from_info = body.get("from", {})
+            sender_id = from_info.get("userid", "unknown") if isinstance(from_info, dict) else "unknown"
+
+            # For single chat, chatid is the sender's userid
+            # For group chat, chatid is provided in body
+            chat_type = body.get("chattype", "single")
+            chat_id = body.get("chatid", sender_id)
+
+            content_parts = []
+
+            if msg_type == "text":
+                text = body.get("text", {}).get("content", "")
+                if text:
+                    content_parts.append(text)
+
+            elif msg_type == "image":
+                image_info = body.get("image", {})
+                file_url = image_info.get("url", "")
+                aes_key = image_info.get("aeskey", "")
+
+                if file_url and aes_key:
+                    file_path = await self._download_and_save_media(file_url, aes_key, "image")
+                    if file_path:
+                        filename = os.path.basename(file_path)
+                        content_parts.append(f"[image: {filename}]\n[Image: source: {file_path}]")
+                    else:
+                        content_parts.append("[image: download failed]")
+                else:
+                    content_parts.append("[image: download failed]")
+
+            elif msg_type == "voice":
+                voice_info = body.get("voice", {})
+                # Voice message already contains transcribed content from WeCom
+                voice_content = voice_info.get("content", "")
+                if voice_content:
+                    content_parts.append(f"[voice] {voice_content}")
+                else:
+                    content_parts.append("[voice]")
+
+            elif msg_type == "file":
+                file_info = body.get("file", {})
+                file_url = file_info.get("url", "")
+                aes_key = file_info.get("aeskey", "")
+                file_name = file_info.get("name", "unknown")
+
+                if file_url and aes_key:
+                    file_path = await self._download_and_save_media(file_url, aes_key, "file", file_name)
+                    if file_path:
+                        content_parts.append(f"[file: {file_name}]\n[File: source: {file_path}]")
+                    else:
+                        content_parts.append(f"[file: {file_name}: download failed]")
+                else:
+                    content_parts.append(f"[file: {file_name}: download failed]")
+
+            elif msg_type == "mixed":
+                # Mixed content contains multiple message items
+                msg_items = body.get("mixed", {}).get("item", [])
+                for item in msg_items:
+                    item_type = item.get("type", "")
+                    if item_type == "text":
+                        text = item.get("text", {}).get("content", "")
+                        if text:
+                            content_parts.append(text)
+                    else:
+                        content_parts.append(MSG_TYPE_MAP.get(item_type, f"[{item_type}]"))
+
+            else:
+                content_parts.append(MSG_TYPE_MAP.get(msg_type, f"[{msg_type}]"))
+
+            content = "\n".join(content_parts) if content_parts else ""
+
+            if not content:
+                return
+
+            # Store frame for this chat to enable replies
+            self._chat_frames[chat_id] = frame
+
+            # Forward to message bus
+            # Note: media paths are included in content for broader model compatibility
+            await self._handle_message(
+                sender_id=sender_id,
+                chat_id=chat_id,
+                content=content,
+                media=None,
+                metadata={
+                    "message_id": msg_id,
+                    "msg_type": msg_type,
+                    "chat_type": chat_type,
+                }
+            )
+
+        except Exception as e:
+            logger.error("Error processing WeCom message: {}", e)
+
+    async def _download_and_save_media(
+        self,
+        file_url: str,
+        aes_key: str,
+        media_type: str,
+        filename: str | None = None,
+    ) -> str | None:
+        """
+        Download and decrypt media from WeCom.
+
+        Returns:
+            file_path or None if download failed
+        """
+        try:
+            data, fname = await self._client.download_file(file_url, aes_key)
+
+            if not data:
+                logger.warning("Failed to download media from WeCom")
+                return None
+
+            media_dir = get_media_dir("wecom")
+            if not filename:
+                filename = fname or f"{media_type}_{hash(file_url) % 100000}"
+            filename = os.path.basename(filename)
+
+            file_path = media_dir / filename
+            file_path.write_bytes(data)
+            logger.debug("Downloaded {} to {}", media_type, file_path)
+            return str(file_path)
+
+        except Exception as e:
+            logger.error("Error downloading media: {}", e)
+            return None
+
+    async def send(self, msg: OutboundMessage) -> None:
+        """Send a message through WeCom."""
+        if not self._client:
+            logger.warning("WeCom client not initialized")
+            return
+
+        try:
+            content = msg.content.strip()
+            if not content:
+                return
+
+            # Get the stored frame for this chat
+            frame = self._chat_frames.get(msg.chat_id)
+            if not frame:
+                logger.warning("No frame found for chat {}, cannot reply", msg.chat_id)
+                return
+
+            # Use streaming reply for better UX
+            stream_id = self._generate_req_id("stream")
+
+            # Send as streaming message with finish=True
+            await self._client.reply_stream(
+                frame,
+                stream_id,
+                content,
+                finish=True,
+            )
+
+            logger.debug("WeCom message sent to {}", msg.chat_id)
+
+        except Exception as e:
+            logger.error("Error sending WeCom message: {}", e)

nanobot/channels/whatsapp.py

@@ -22,6 +22,7 @@ class WhatsAppChannel(BaseChannel):
     """
 
     name = "whatsapp"
+    display_name = "WhatsApp"
 
     def __init__(self, config: WhatsAppConfig, bus: MessageBus):
         super().__init__(config, bus)

nanobot/cli/commands.py

@@ -19,10 +19,12 @@ if sys.platform == "win32":
             pass
 
 import typer
+from prompt_toolkit import print_formatted_text
 from prompt_toolkit import PromptSession
-from prompt_toolkit.formatted_text import HTML
+from prompt_toolkit.formatted_text import ANSI, HTML
 from prompt_toolkit.history import FileHistory
 from prompt_toolkit.patch_stdout import patch_stdout
+from prompt_toolkit.application import run_in_terminal
 from rich.console import Console
 from rich.markdown import Markdown
 from rich.table import Table
@@ -111,8 +113,25 @@ def _init_prompt_session() -> None:
     )
 
 
+def _make_console() -> Console:
+    return Console(file=sys.stdout)
+
+
+def _render_interactive_ansi(render_fn) -> str:
+    """Render Rich output to ANSI so prompt_toolkit can print it safely."""
+    ansi_console = Console(
+        force_terminal=True,
+        color_system=console.color_system or "standard",
+        width=console.width,
+    )
+    with ansi_console.capture() as capture:
+        render_fn(ansi_console)
+    return capture.get()
+
+
 def _print_agent_response(response: str, render_markdown: bool) -> None:
     """Render assistant response with consistent terminal styling."""
+    console = _make_console()
     content = response or ""
     body = Markdown(content) if render_markdown else Text(content)
     console.print()
@@ -121,6 +140,34 @@ def _print_agent_response(response: str, render_markdown: bool) -> None:
     console.print()
 
 
+async def _print_interactive_line(text: str) -> None:
+    """Print async interactive updates with prompt_toolkit-safe Rich styling."""
+    def _write() -> None:
+        ansi = _render_interactive_ansi(
+            lambda c: c.print(f"  [dim]↳ {text}[/dim]")
+        )
+        print_formatted_text(ANSI(ansi), end="")
+
+    await run_in_terminal(_write)
+
+
+async def _print_interactive_response(response: str, render_markdown: bool) -> None:
+    """Print async interactive replies with prompt_toolkit-safe Rich styling."""
+    def _write() -> None:
+        content = response or ""
+        ansi = _render_interactive_ansi(
+            lambda c: (
+                c.print(),
+                c.print(f"[cyan]{__logo__} nanobot[/cyan]"),
+                c.print(Markdown(content) if render_markdown else Text(content)),
+                c.print(),
+            )
+        )
+        print_formatted_text(ANSI(ansi), end="")
+
+    await run_in_terminal(_write)
+
+
 def _is_exit_command(command: str) -> bool:
     """Return True when input should end interactive chat."""
     return command.lower() in EXIT_COMMANDS
@@ -191,6 +238,8 @@ def onboard():
         save_config(Config())
         console.print(f"[green]✓[/green] Created config at {config_path}")
 
+    console.print("[dim]Config template now uses `maxTokens` + `contextWindowTokens`; `memoryWindow` is no longer a runtime setting.[/dim]")
+
     # Create workspace
     workspace = get_workspace_path()
 
@@ -213,6 +262,7 @@ def onboard():
 
 def _make_provider(config: Config):
     """Create the appropriate LLM provider from config."""
+    from nanobot.providers.base import GenerationSettings
     from nanobot.providers.openai_codex_provider import OpenAICodexProvider
     from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
 
@@ -222,46 +272,50 @@ def _make_provider(config: Config):
 
     # OpenAI Codex (OAuth)
     if provider_name == "openai_codex" or model.startswith("openai-codex/"):
-        return OpenAICodexProvider(default_model=model)
+        provider = OpenAICodexProvider(default_model=model)
-
     # Custom: direct OpenAI-compatible endpoint, bypasses LiteLLM
-    from nanobot.providers.custom_provider import CustomProvider
+    elif provider_name == "custom":
-    if provider_name == "custom":
+        from nanobot.providers.custom_provider import CustomProvider
-        return CustomProvider(
+        provider = CustomProvider(
             api_key=p.api_key if p else "no-key",
             api_base=config.get_api_base(model) or "http://localhost:8000/v1",
             default_model=model,
         )
-
     # Azure OpenAI: direct Azure OpenAI endpoint with deployment name
-    if provider_name == "azure_openai":
+    elif provider_name == "azure_openai":
         if not p or not p.api_key or not p.api_base:
             console.print("[red]Error: Azure OpenAI requires api_key and api_base.[/red]")
             console.print("Set them in ~/.nanobot/config.json under providers.azure_openai section")
             console.print("Use the model field to specify the deployment name.")
             raise typer.Exit(1)
-        
+        provider = AzureOpenAIProvider(
-        return AzureOpenAIProvider(
             api_key=p.api_key,
             api_base=p.api_base,
             default_model=model,
         )
+    else:
+        from nanobot.providers.litellm_provider import LiteLLMProvider
+        from nanobot.providers.registry import find_by_name
+        spec = find_by_name(provider_name)
+        if not model.startswith("bedrock/") and not (p and p.api_key) and not (spec and (spec.is_oauth or spec.is_local)):
+            console.print("[red]Error: No API key configured.[/red]")
+            console.print("Set one in ~/.nanobot/config.json under providers section")
+            raise typer.Exit(1)
+        provider = LiteLLMProvider(
+            api_key=p.api_key if p else None,
+            api_base=config.get_api_base(model),
+            default_model=model,
+            extra_headers=p.extra_headers if p else None,
+            provider_name=provider_name,
+        )
 
-    from nanobot.providers.litellm_provider import LiteLLMProvider
+    defaults = config.agents.defaults
-    from nanobot.providers.registry import find_by_name
+    provider.generation = GenerationSettings(
-    spec = find_by_name(provider_name)
+        temperature=defaults.temperature,
-    if not model.startswith("bedrock/") and not (p and p.api_key) and not (spec and spec.is_oauth):
+        max_tokens=defaults.max_tokens,
-        console.print("[red]Error: No API key configured.[/red]")
+        reasoning_effort=defaults.reasoning_effort,
-        console.print("Set one in ~/.nanobot/config.json under providers section")
-        raise typer.Exit(1)
-
-    return LiteLLMProvider(
-        api_key=p.api_key if p else None,
-        api_base=config.get_api_base(model),
-        default_model=model,
-        extra_headers=p.extra_headers if p else None,
-        provider_name=provider_name,
     )
+    return provider
 
 
 def _load_runtime_config(config: str | None = None, workspace: str | None = None) -> Config:
@@ -283,6 +337,16 @@ def _load_runtime_config(config: str | None = None, workspace: str | None = None
     return loaded
 
 
+def _print_deprecated_memory_window_notice(config: Config) -> None:
+    """Warn when running with old memoryWindow-only config."""
+    if config.agents.defaults.should_warn_deprecated_memory_window:
+        console.print(
+            "[yellow]Hint:[/yellow] Detected deprecated `memoryWindow` without "
+            "`contextWindowTokens`. `memoryWindow` is ignored; run "
+            "[cyan]nanobot onboard[/cyan] to refresh your config template."
+        )
+
+
 # ============================================================================
 # Gateway / Server
 # ============================================================================
@@ -290,7 +354,7 @@ def _load_runtime_config(config: str | None = None, workspace: str | None = None
 
 @app.command()
 def gateway(
-    port: int = typer.Option(18790, "--port", "-p", help="Gateway port"),
+    port: int | None = typer.Option(None, "--port", "-p", help="Gateway port"),
     workspace: str | None = typer.Option(None, "--workspace", "-w", help="Workspace directory"),
     verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
     config: str | None = typer.Option(None, "--config", "-c", help="Path to config file"),
@@ -310,6 +374,8 @@ def gateway(
         logging.basicConfig(level=logging.DEBUG)
 
     config = _load_runtime_config(config, workspace)
+    _print_deprecated_memory_window_notice(config)
+    port = port if port is not None else config.gateway.port
 
     console.print(f"{__logo__} Starting nanobot gateway on port {port}...")
     sync_workspace_templates(config.workspace_path)
@@ -327,12 +393,9 @@ def gateway(
         provider=provider,
         workspace=config.workspace_path,
         model=config.agents.defaults.model,
-        temperature=config.agents.defaults.temperature,
-        max_tokens=config.agents.defaults.max_tokens,
         max_iterations=config.agents.defaults.max_tool_iterations,
-        memory_window=config.agents.defaults.memory_window,
+        context_window_tokens=config.agents.defaults.context_window_tokens,
-        reasoning_effort=config.agents.defaults.reasoning_effort,
+        brave_api_key=config.tools.web.search.api_key or None,
-        web_search_config=config.tools.web.search,
         web_proxy=config.tools.web.proxy or None,
         exec_config=config.tools.exec,
         cron_service=cron,
@@ -493,6 +556,7 @@ def agent(
     from nanobot.cron.service import CronService
 
     config = _load_runtime_config(config, workspace)
+    _print_deprecated_memory_window_notice(config)
     sync_workspace_templates(config.workspace_path)
 
     bus = MessageBus()
@@ -512,12 +576,9 @@ def agent(
         provider=provider,
         workspace=config.workspace_path,
         model=config.agents.defaults.model,
-        temperature=config.agents.defaults.temperature,
-        max_tokens=config.agents.defaults.max_tokens,
         max_iterations=config.agents.defaults.max_tool_iterations,
-        memory_window=config.agents.defaults.memory_window,
+        context_window_tokens=config.agents.defaults.context_window_tokens,
-        reasoning_effort=config.agents.defaults.reasoning_effort,
+        brave_api_key=config.tools.web.search.api_key or None,
-        web_search_config=config.tools.web.search,
         web_proxy=config.tools.web.proxy or None,
         exec_config=config.tools.exec,
         cron_service=cron,
@@ -596,14 +657,15 @@ def agent(
                             elif ch and not is_tool_hint and not ch.send_progress:
                                 pass
                             else:
-                                console.print(f"  [dim]↳ {msg.content}[/dim]")
+                                await _print_interactive_line(msg.content)
+
                         elif not turn_done.is_set():
                             if msg.content:
                                 turn_response.append(msg.content)
                             turn_done.set()
                         elif msg.content:
-                            console.print()
+                            await _print_interactive_response(msg.content, render_markdown=markdown)
-                            _print_agent_response(msg.content, render_markdown=markdown)
+
                     except asyncio.TimeoutError:
                         continue
                     except asyncio.CancelledError:
@@ -669,6 +731,7 @@ app.add_typer(channels_app, name="channels")
 @channels_app.command("status")
 def channels_status():
     """Show channel status."""
+    from nanobot.channels.registry import discover_channel_names, load_channel_class
     from nanobot.config.loader import load_config
 
     config = load_config()
@@ -676,85 +739,19 @@ def channels_status():
     table = Table(title="Channel Status")
     table.add_column("Channel", style="cyan")
     table.add_column("Enabled", style="green")
-    table.add_column("Configuration", style="yellow")
 
-    # WhatsApp
+    for modname in sorted(discover_channel_names()):
-    wa = config.channels.whatsapp
+        section = getattr(config.channels, modname, None)
-    table.add_row(
+        enabled = section and getattr(section, "enabled", False)
-        "WhatsApp",
+        try:
-        "✓" if wa.enabled else "✗",
+            cls = load_channel_class(modname)
-        wa.bridge_url
+            display = cls.display_name
-    )
+        except ImportError:
-
+            display = modname.title()
-    dc = config.channels.discord
+        table.add_row(
-    table.add_row(
+            display,
-        "Discord",
+            "[green]\u2713[/green]" if enabled else "[dim]\u2717[/dim]",
-        "✓" if dc.enabled else "✗",
+        )
-        dc.gateway_url
-    )
-
-    # Feishu
-    fs = config.channels.feishu
-    fs_config = f"app_id: {fs.app_id[:10]}..." if fs.app_id else "[dim]not configured[/dim]"
-    table.add_row(
-        "Feishu",
-        "✓" if fs.enabled else "✗",
-        fs_config
-    )
-
-    # Mochat
-    mc = config.channels.mochat
-    mc_base = mc.base_url or "[dim]not configured[/dim]"
-    table.add_row(
-        "Mochat",
-        "✓" if mc.enabled else "✗",
-        mc_base
-    )
-
-    # 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
-    )
-
-    # Slack
-    slack = config.channels.slack
-    slack_config = "socket" if slack.app_token and slack.bot_token else "[dim]not configured[/dim]"
-    table.add_row(
-        "Slack",
-        "✓" if slack.enabled else "✗",
-        slack_config
-    )
-
-    # DingTalk
-    dt = config.channels.dingtalk
-    dt_config = f"client_id: {dt.client_id[:10]}..." if dt.client_id else "[dim]not configured[/dim]"
-    table.add_row(
-        "DingTalk",
-        "✓" if dt.enabled else "✗",
-        dt_config
-    )
-
-    # QQ
-    qq = config.channels.qq
-    qq_config = f"app_id: {qq.app_id[:10]}..." if qq.app_id else "[dim]not configured[/dim]"
-    table.add_row(
-        "QQ",
-        "✓" if qq.enabled else "✗",
-        qq_config
-    )
-
-    # Email
-    em = config.channels.email
-    em_config = em.imap_host if em.imap_host else "[dim]not configured[/dim]"
-    table.add_row(
-        "Email",
-        "✓" if em.enabled else "✗",
-        em_config
-    )
 
     console.print(table)
 

nanobot/config/schema.py

@@ -33,6 +33,7 @@ class TelegramConfig(Base):
         None  # HTTP/SOCKS5 proxy URL, e.g. "http://127.0.0.1:7890" or "socks5://127.0.0.1:1080"
     )
     reply_to_message: bool = False  # If true, bot replies quote the original message
+    group_policy: Literal["open", "mention"] = "mention"  # "mention" responds when @mentioned or replied to, "open" responds to all
 
 
 class FeishuConfig(Base):
@@ -47,6 +48,7 @@ class FeishuConfig(Base):
     react_emoji: str = (
         "THUMBSUP"  # Emoji type for message reactions (e.g. THUMBSUP, OK, DONE, SMILE)
     )
+    group_policy: Literal["open", "mention"] = "mention"  # "mention" responds when @mentioned, "open" responds to all
 
 
 class DingTalkConfig(Base):
@@ -199,6 +201,14 @@ class QQConfig(Base):
     )  # Allowed user openids (empty = public access)
 
 
+class WecomConfig(Base):
+    """WeCom (Enterprise WeChat) AI Bot channel configuration."""
+
+    enabled: bool = False
+    bot_id: str = ""  # Bot ID from WeCom AI Bot platform
+    secret: str = ""  # Bot Secret from WeCom AI Bot platform
+    allow_from: list[str] = Field(default_factory=list)  # Allowed user IDs
+    welcome_message: str = ""  # Welcome message for enter_chat event
 
 
 class ChannelsConfig(Base):
@@ -216,6 +226,7 @@ class ChannelsConfig(Base):
     slack: SlackConfig = Field(default_factory=SlackConfig)
     qq: QQConfig = Field(default_factory=QQConfig)
     matrix: MatrixConfig = Field(default_factory=MatrixConfig)
+    wecom: WecomConfig = Field(default_factory=WecomConfig)
 
 
 class AgentDefaults(Base):
@@ -227,11 +238,18 @@ class AgentDefaults(Base):
         "auto"  # Provider name (e.g. "anthropic", "openrouter") or "auto" for auto-detection
     )
     max_tokens: int = 8192
+    context_window_tokens: int = 65_536
     temperature: float = 0.1
     max_tool_iterations: int = 40
-    memory_window: int = 100
+    # Deprecated compatibility field: accepted from old configs but ignored at runtime.
+    memory_window: int | None = Field(default=None, exclude=True)
     reasoning_effort: str | None = None  # low / medium / high — enables LLM thinking mode
 
+    @property
+    def should_warn_deprecated_memory_window(self) -> bool:
+        """Return True when old memoryWindow is present without contextWindowTokens."""
+        return self.memory_window is not None and "context_window_tokens" not in self.model_fields_set
+
 
 class AgentsConfig(Base):
     """Agent configuration."""
@@ -258,14 +276,18 @@ class ProvidersConfig(Base):
     deepseek: ProviderConfig = Field(default_factory=ProviderConfig)
     groq: ProviderConfig = Field(default_factory=ProviderConfig)
     zhipu: ProviderConfig = Field(default_factory=ProviderConfig)
-    dashscope: ProviderConfig = Field(default_factory=ProviderConfig)  # 阿里云通义千问
+    dashscope: ProviderConfig = Field(default_factory=ProviderConfig)
     vllm: ProviderConfig = Field(default_factory=ProviderConfig)
+    ollama: ProviderConfig = Field(default_factory=ProviderConfig)  # Ollama local models
     gemini: ProviderConfig = Field(default_factory=ProviderConfig)
     moonshot: ProviderConfig = Field(default_factory=ProviderConfig)
     minimax: ProviderConfig = Field(default_factory=ProviderConfig)
     aihubmix: ProviderConfig = Field(default_factory=ProviderConfig)  # AiHubMix API gateway
     siliconflow: ProviderConfig = Field(default_factory=ProviderConfig)  # SiliconFlow (硅基流动)
     volcengine: ProviderConfig = Field(default_factory=ProviderConfig)  # VolcEngine (火山引擎)
+    volcengine_coding_plan: ProviderConfig = Field(default_factory=ProviderConfig)  # VolcEngine Coding Plan
+    byteplus: ProviderConfig = Field(default_factory=ProviderConfig)  # BytePlus (VolcEngine international)
+    byteplus_coding_plan: ProviderConfig = Field(default_factory=ProviderConfig)  # BytePlus Coding Plan
     openai_codex: ProviderConfig = Field(default_factory=ProviderConfig)  # OpenAI Codex (OAuth)
     github_copilot: ProviderConfig = Field(default_factory=ProviderConfig)  # Github Copilot (OAuth)
 
@@ -288,10 +310,7 @@ class GatewayConfig(Base):
 class WebSearchConfig(Base):
     """Web search tool configuration."""
 
-    provider: str = ""  # brave, tavily, searxng, duckduckgo (empty = brave)
+    api_key: str = ""  # Brave Search API key
-    api_key: str = ""  # API key for selected provider
-    base_url: str = ""  # Base URL (SearXNG)
-    fallback_to_duckduckgo: bool = True
     max_results: int = 5
 
 
@@ -370,16 +389,34 @@ class Config(BaseSettings):
         for spec in PROVIDERS:
             p = getattr(self.providers, spec.name, None)
             if p and model_prefix and normalized_prefix == spec.name:
-                if spec.is_oauth or p.api_key:
+                if spec.is_oauth or spec.is_local or p.api_key:
                     return p, spec.name
 
         # Match by keyword (order follows PROVIDERS registry)
         for spec in PROVIDERS:
             p = getattr(self.providers, spec.name, None)
             if p and any(_kw_matches(kw) for kw in spec.keywords):
-                if spec.is_oauth or p.api_key:
+                if spec.is_oauth or spec.is_local or p.api_key:
                     return p, spec.name
 
+        # Fallback: configured local providers can route models without
+        # provider-specific keywords (for example plain "llama3.2" on Ollama).
+        # Prefer providers whose detect_by_base_keyword matches the configured api_base
+        # (e.g. Ollama's "11434" in "http://localhost:11434") over plain registry order.
+        local_fallback: tuple[ProviderConfig, str] | None = None
+        for spec in PROVIDERS:
+            if not spec.is_local:
+                continue
+            p = getattr(self.providers, spec.name, None)
+            if not (p and p.api_base):
+                continue
+            if spec.detect_by_base_keyword and spec.detect_by_base_keyword in p.api_base:
+                return p, spec.name
+            if local_fallback is None:
+                local_fallback = (p, spec.name)
+        if local_fallback:
+            return local_fallback
+
         # Fallback: gateways first, then others (follows registry order)
         # OAuth providers are NOT valid fallbacks — they require explicit model selection
         for spec in PROVIDERS:
@@ -406,7 +443,7 @@ class Config(BaseSettings):
         return p.api_key if p else None
 
     def get_api_base(self, model: str | None = None) -> str | None:
-        """Get API base URL for the given model. Applies default URLs for known gateways."""
+        """Get API base URL for the given model. Applies default URLs for gateway/local providers."""
         from nanobot.providers.registry import find_by_name
 
         p, name = self._match_provider(model)
@@ -417,7 +454,7 @@ class Config(BaseSettings):
         # to avoid polluting the global litellm.api_base.
         if name:
             spec = find_by_name(name)
-            if spec and spec.is_gateway and spec.default_api_base:
+            if spec and (spec.is_gateway or spec.is_local) and spec.default_api_base:
                 return spec.default_api_base
         return None
 

nanobot/heartbeat/service.py

@@ -87,7 +87,7 @@ class HeartbeatService:
 
         Returns (action, tasks) where action is 'skip' or 'run'.
         """
-        response = await self.provider.chat(
+        response = await self.provider.chat_with_retry(
             messages=[
                 {"role": "system", "content": "You are a heartbeat agent. Call the heartbeat tool to report your decision."},
                 {"role": "user", "content": (

nanobot/providers/azure_openai_provider.py

@@ -88,6 +88,7 @@ class AzureOpenAIProvider(LLMProvider):
         max_tokens: int = 4096,
         temperature: float = 0.7,
         reasoning_effort: str | None = None,
+        tool_choice: str | dict[str, Any] | None = None,
     ) -> dict[str, Any]:
         """Prepare the request payload with Azure OpenAI 2024-10-21 compliance."""
         payload: dict[str, Any] = {
@@ -106,7 +107,7 @@ class AzureOpenAIProvider(LLMProvider):
 
         if tools:
             payload["tools"] = tools
-            payload["tool_choice"] = "auto"
+            payload["tool_choice"] = tool_choice or "auto"
 
         return payload
 
@@ -118,6 +119,7 @@ class AzureOpenAIProvider(LLMProvider):
         max_tokens: int = 4096,
         temperature: float = 0.7,
         reasoning_effort: str | None = None,
+        tool_choice: str | dict[str, Any] | None = None,
     ) -> LLMResponse:
         """
         Send a chat completion request to Azure OpenAI.
@@ -137,7 +139,8 @@ class AzureOpenAIProvider(LLMProvider):
         url = self._build_chat_url(deployment_name)
         headers = self._build_headers()
         payload = self._prepare_request_payload(
-            deployment_name, messages, tools, max_tokens, temperature, reasoning_effort
+            deployment_name, messages, tools, max_tokens, temperature, reasoning_effort,
+            tool_choice=tool_choice,
         )
 
         try:

nanobot/providers/base.py

@@ -1,9 +1,13 @@
 """Base LLM provider interface."""
 
+import asyncio
+import json
 from abc import ABC, abstractmethod
 from dataclasses import dataclass, field
 from typing import Any
 
+from loguru import logger
+
 
 @dataclass
 class ToolCallRequest:
@@ -11,6 +15,24 @@ class ToolCallRequest:
     id: str
     name: str
     arguments: dict[str, Any]
+    provider_specific_fields: dict[str, Any] | None = None
+    function_provider_specific_fields: dict[str, Any] | None = None
+
+    def to_openai_tool_call(self) -> dict[str, Any]:
+        """Serialize to an OpenAI-style tool_call payload."""
+        tool_call = {
+            "id": self.id,
+            "type": "function",
+            "function": {
+                "name": self.name,
+                "arguments": json.dumps(self.arguments, ensure_ascii=False),
+            },
+        }
+        if self.provider_specific_fields:
+            tool_call["provider_specific_fields"] = self.provider_specific_fields
+        if self.function_provider_specific_fields:
+            tool_call["function"]["provider_specific_fields"] = self.function_provider_specific_fields
+        return tool_call
 
 
 @dataclass
@@ -29,6 +51,21 @@ class LLMResponse:
         return len(self.tool_calls) > 0
 
 
+@dataclass(frozen=True)
+class GenerationSettings:
+    """Default generation parameters for LLM calls.
+
+    Stored on the provider so every call site inherits the same defaults
+    without having to pass temperature / max_tokens / reasoning_effort
+    through every layer.  Individual call sites can still override by
+    passing explicit keyword arguments to chat() / chat_with_retry().
+    """
+
+    temperature: float = 0.7
+    max_tokens: int = 4096
+    reasoning_effort: str | None = None
+
+
 class LLMProvider(ABC):
     """
     Abstract base class for LLM providers.
@@ -37,9 +74,28 @@ class LLMProvider(ABC):
     while maintaining a consistent interface.
     """
 
+    _CHAT_RETRY_DELAYS = (1, 2, 4)
+    _TRANSIENT_ERROR_MARKERS = (
+        "429",
+        "rate limit",
+        "500",
+        "502",
+        "503",
+        "504",
+        "overloaded",
+        "timeout",
+        "timed out",
+        "connection",
+        "server error",
+        "temporarily unavailable",
+    )
+
+    _SENTINEL = object()
+
     def __init__(self, api_key: str | None = None, api_base: str | None = None):
         self.api_key = api_key
         self.api_base = api_base
+        self.generation: GenerationSettings = GenerationSettings()
 
     @staticmethod
     def _sanitize_empty_content(messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
@@ -110,6 +166,7 @@ class LLMProvider(ABC):
         max_tokens: int = 4096,
         temperature: float = 0.7,
         reasoning_effort: str | None = None,
+        tool_choice: str | dict[str, Any] | None = None,
     ) -> LLMResponse:
         """
         Send a chat completion request.
@@ -120,12 +177,93 @@ class LLMProvider(ABC):
             model: Model identifier (provider-specific).
             max_tokens: Maximum tokens in response.
             temperature: Sampling temperature.
+            tool_choice: Tool selection strategy ("auto", "required", or specific tool dict).
         
         Returns:
             LLMResponse with content and/or tool calls.
         """
         pass
 
+    @classmethod
+    def _is_transient_error(cls, content: str | None) -> bool:
+        err = (content or "").lower()
+        return any(marker in err for marker in cls._TRANSIENT_ERROR_MARKERS)
+
+    async def chat_with_retry(
+        self,
+        messages: list[dict[str, Any]],
+        tools: list[dict[str, Any]] | None = None,
+        model: str | None = None,
+        max_tokens: object = _SENTINEL,
+        temperature: object = _SENTINEL,
+        reasoning_effort: object = _SENTINEL,
+        tool_choice: str | dict[str, Any] | None = None,
+    ) -> LLMResponse:
+        """Call chat() with retry on transient provider failures.
+
+        Parameters default to ``self.generation`` when not explicitly passed,
+        so callers no longer need to thread temperature / max_tokens /
+        reasoning_effort through every layer.
+        """
+        if max_tokens is self._SENTINEL:
+            max_tokens = self.generation.max_tokens
+        if temperature is self._SENTINEL:
+            temperature = self.generation.temperature
+        if reasoning_effort is self._SENTINEL:
+            reasoning_effort = self.generation.reasoning_effort
+
+        for attempt, delay in enumerate(self._CHAT_RETRY_DELAYS, start=1):
+            try:
+                response = await self.chat(
+                    messages=messages,
+                    tools=tools,
+                    model=model,
+                    max_tokens=max_tokens,
+                    temperature=temperature,
+                    reasoning_effort=reasoning_effort,
+                    tool_choice=tool_choice,
+                )
+            except asyncio.CancelledError:
+                raise
+            except Exception as exc:
+                response = LLMResponse(
+                    content=f"Error calling LLM: {exc}",
+                    finish_reason="error",
+                )
+
+            if response.finish_reason != "error":
+                return response
+            if not self._is_transient_error(response.content):
+                return response
+
+            err = (response.content or "").lower()
+            logger.warning(
+                "LLM transient error (attempt {}/{}), retrying in {}s: {}",
+                attempt,
+                len(self._CHAT_RETRY_DELAYS),
+                delay,
+                err[:120],
+            )
+            await asyncio.sleep(delay)
+
+        try:
+            return await self.chat(
+                messages=messages,
+                tools=tools,
+                model=model,
+                max_tokens=max_tokens,
+                temperature=temperature,
+                reasoning_effort=reasoning_effort,
+                tool_choice=tool_choice,
+            )
+        except asyncio.CancelledError:
+            raise
+        except Exception as exc:
+            return LLMResponse(
+                content=f"Error calling LLM: {exc}",
+                finish_reason="error",
+            )
+
     @abstractmethod
     def get_default_model(self) -> str:
         """Get the default model for this provider."""

nanobot/providers/custom_provider.py

@@ -25,7 +25,8 @@ class CustomProvider(LLMProvider):
 
     async def chat(self, messages: list[dict[str, Any]], tools: list[dict[str, Any]] | None = None,
                    model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7,
-                   reasoning_effort: str | None = None) -> LLMResponse:
+                   reasoning_effort: str | None = None,
+                   tool_choice: str | dict[str, Any] | None = None) -> LLMResponse:
         kwargs: dict[str, Any] = {
             "model": model or self.default_model,
             "messages": self._sanitize_empty_content(messages),
@@ -35,7 +36,7 @@ class CustomProvider(LLMProvider):
         if reasoning_effort:
             kwargs["reasoning_effort"] = reasoning_effort
         if tools:
-            kwargs.update(tools=tools, tool_choice="auto")
+            kwargs.update(tools=tools, tool_choice=tool_choice or "auto")
         try:
             return self._parse(await self._client.chat.completions.create(**kwargs))
         except Exception as e:

nanobot/providers/litellm_provider.py

@@ -62,6 +62,8 @@ class LiteLLMProvider(LLMProvider):
         # Drop unsupported parameters for providers (e.g., gpt-5 rejects some params)
         litellm.drop_params = True
 
+        self._langsmith_enabled = bool(os.getenv("LANGSMITH_API_KEY"))
+
     def _setup_env(self, api_key: str, api_base: str | None, model: str) -> None:
         """Set environment variables based on detected provider."""
         spec = self._gateway or find_by_model(model)
@@ -214,6 +216,7 @@ class LiteLLMProvider(LLMProvider):
         max_tokens: int = 4096,
         temperature: float = 0.7,
         reasoning_effort: str | None = None,
+        tool_choice: str | dict[str, Any] | None = None,
     ) -> LLMResponse:
         """
         Send a chat completion request via LiteLLM.
@@ -249,6 +252,9 @@ class LiteLLMProvider(LLMProvider):
         # Apply model-specific overrides (e.g. kimi-k2.5 temperature)
         self._apply_model_overrides(model, kwargs)
 
+        if self._langsmith_enabled:
+            kwargs.setdefault("callbacks", []).append("langsmith")
+
         # Pass api_key directly — more reliable than env vars alone
         if self.api_key:
             kwargs["api_key"] = self.api_key
@@ -267,7 +273,7 @@ class LiteLLMProvider(LLMProvider):
         
         if tools:
             kwargs["tools"] = tools
-            kwargs["tool_choice"] = "auto"
+            kwargs["tool_choice"] = tool_choice or "auto"
 
         try:
             response = await acompletion(**kwargs)
@@ -309,10 +315,17 @@ class LiteLLMProvider(LLMProvider):
             if isinstance(args, str):
                 args = json_repair.loads(args)
 
+            provider_specific_fields = getattr(tc, "provider_specific_fields", None) or None
+            function_provider_specific_fields = (
+                getattr(tc.function, "provider_specific_fields", None) or None
+            )
+
             tool_calls.append(ToolCallRequest(
                 id=_short_tool_id(),
                 name=tc.function.name,
                 arguments=args,
+                provider_specific_fields=provider_specific_fields,
+                function_provider_specific_fields=function_provider_specific_fields,
             ))
 
         usage = {}

nanobot/providers/openai_codex_provider.py

@@ -32,6 +32,7 @@ class OpenAICodexProvider(LLMProvider):
         max_tokens: int = 4096,
         temperature: float = 0.7,
         reasoning_effort: str | None = None,
+        tool_choice: str | dict[str, Any] | None = None,
     ) -> LLMResponse:
         model = model or self.default_model
         system_prompt, input_items = _convert_messages(messages)
@@ -48,7 +49,7 @@ class OpenAICodexProvider(LLMProvider):
             "text": {"verbosity": "medium"},
             "include": ["reasoning.encrypted_content"],
             "prompt_cache_key": _prompt_cache_key(messages),
-            "tool_choice": "auto",
+            "tool_choice": tool_choice or "auto",
             "parallel_tool_calls": True,
         }
 

nanobot/providers/registry.py

@@ -145,7 +145,8 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         strip_model_prefix=False,
         model_overrides=(),
     ),
-    # VolcEngine (火山引擎): OpenAI-compatible gateway
+
+    # VolcEngine (火山引擎): OpenAI-compatible gateway, pay-per-use models
     ProviderSpec(
         name="volcengine",
         keywords=("volcengine", "volces", "ark"),
@@ -162,6 +163,62 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         strip_model_prefix=False,
         model_overrides=(),
     ),
+
+    # VolcEngine Coding Plan (火山引擎 Coding Plan): same key as volcengine
+    ProviderSpec(
+        name="volcengine_coding_plan",
+        keywords=("volcengine-plan",),
+        env_key="OPENAI_API_KEY",
+        display_name="VolcEngine Coding Plan",
+        litellm_prefix="volcengine",
+        skip_prefixes=(),
+        env_extras=(),
+        is_gateway=True,
+        is_local=False,
+        detect_by_key_prefix="",
+        detect_by_base_keyword="",
+        default_api_base="https://ark.cn-beijing.volces.com/api/coding/v3",
+        strip_model_prefix=True,
+        model_overrides=(),
+    ),
+
+    # BytePlus: VolcEngine international, pay-per-use models
+    ProviderSpec(
+        name="byteplus",
+        keywords=("byteplus",),
+        env_key="OPENAI_API_KEY",
+        display_name="BytePlus",
+        litellm_prefix="volcengine",
+        skip_prefixes=(),
+        env_extras=(),
+        is_gateway=True,
+        is_local=False,
+        detect_by_key_prefix="",
+        detect_by_base_keyword="bytepluses",
+        default_api_base="https://ark.ap-southeast.bytepluses.com/api/v3",
+        strip_model_prefix=True,
+        model_overrides=(),
+    ),
+
+    # BytePlus Coding Plan: same key as byteplus
+    ProviderSpec(
+        name="byteplus_coding_plan",
+        keywords=("byteplus-plan",),
+        env_key="OPENAI_API_KEY",
+        display_name="BytePlus Coding Plan",
+        litellm_prefix="volcengine",
+        skip_prefixes=(),
+        env_extras=(),
+        is_gateway=True,
+        is_local=False,
+        detect_by_key_prefix="",
+        detect_by_base_keyword="",
+        default_api_base="https://ark.ap-southeast.bytepluses.com/api/coding/v3",
+        strip_model_prefix=True,
+        model_overrides=(),
+    ),
+
+
     # === Standard providers (matched by model-name keywords) ===============
     # Anthropic: LiteLLM recognizes "claude-*" natively, no prefix needed.
     ProviderSpec(
@@ -360,6 +417,23 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         strip_model_prefix=False,
         model_overrides=(),
     ),
+    # === Ollama (local, OpenAI-compatible) ===================================
+    ProviderSpec(
+        name="ollama",
+        keywords=("ollama", "nemotron"),
+        env_key="OLLAMA_API_KEY",
+        display_name="Ollama",
+        litellm_prefix="ollama_chat",  # model → ollama_chat/model
+        skip_prefixes=("ollama/", "ollama_chat/"),
+        env_extras=(),
+        is_gateway=False,
+        is_local=True,
+        detect_by_key_prefix="",
+        detect_by_base_keyword="11434",
+        default_api_base="http://localhost:11434",
+        strip_model_prefix=False,
+        model_overrides=(),
+    ),
     # === Auxiliary (not a primary LLM provider) ============================
     # Groq: mainly used for Whisper voice transcription, also usable for LLM.
     # Needs "groq/" prefix for LiteLLM routing. Placed last — it rarely wins fallback.

nanobot/skills/skill-creator/SKILL.md

@@ -268,6 +268,8 @@ Skip this step only if the skill being developed already exists, and iteration o
 
 When creating a new skill from scratch, always run the `init_skill.py` script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable.
 
+For `nanobot`, custom skills should live under the active workspace `skills/` directory so they can be discovered automatically at runtime (for example, `<workspace>/skills/my-skill/SKILL.md`).
+
 Usage:
 
 ```bash
@@ -277,9 +279,9 @@ scripts/init_skill.py <skill-name> --path <output-directory> [--resources script
 Examples:
 
 ```bash
-scripts/init_skill.py my-skill --path skills/public
+scripts/init_skill.py my-skill --path ./workspace/skills
-scripts/init_skill.py my-skill --path skills/public --resources scripts,references
+scripts/init_skill.py my-skill --path ./workspace/skills --resources scripts,references
-scripts/init_skill.py my-skill --path skills/public --resources scripts --examples
+scripts/init_skill.py my-skill --path ./workspace/skills --resources scripts --examples
 ```
 
 The script:
@@ -326,7 +328,7 @@ Write the YAML frontmatter with `name` and `description`:
   - Include all "when to use" information here - Not in the body. The body is only loaded after triggering, so "When to Use This Skill" sections in the body are not helpful to the agent.
   - Example description for a `docx` skill: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when the agent needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks"
 
-Do not include any other fields in YAML frontmatter.
+Keep frontmatter minimal. In `nanobot`, `metadata` and `always` are also supported when needed, but avoid adding extra fields unless they are actually required.
 
 ##### Body
 
@@ -349,7 +351,6 @@ scripts/package_skill.py <path/to/skill-folder> ./dist
 The packaging script will:
 
 1. **Validate** the skill automatically, checking:
-
    - YAML frontmatter format and required fields
    - Skill naming conventions and directory structure
    - Description completeness and quality
@@ -357,6 +358,8 @@ The packaging script will:
 
 2. **Package** the skill if validation passes, creating a .skill file named after the skill (e.g., `my-skill.skill`) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension.
 
+   Security restriction: symlinks are rejected and packaging fails when any symlink is present.
+
 If validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again.
 
 ### Step 6: Iterate

nanobot/skills/skill-creator/scripts/init_skill.py

@@ -0,0 +1,378 @@
+#!/usr/bin/env python3
+"""
+Skill Initializer - Creates a new skill from template
+
+Usage:
+    init_skill.py <skill-name> --path <path> [--resources scripts,references,assets] [--examples]
+
+Examples:
+    init_skill.py my-new-skill --path skills/public
+    init_skill.py my-new-skill --path skills/public --resources scripts,references
+    init_skill.py my-api-helper --path skills/private --resources scripts --examples
+    init_skill.py custom-skill --path /custom/location
+"""
+
+import argparse
+import re
+import sys
+from pathlib import Path
+
+MAX_SKILL_NAME_LENGTH = 64
+ALLOWED_RESOURCES = {"scripts", "references", "assets"}
+
+SKILL_TEMPLATE = """---
+name: {skill_name}
+description: [TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
+---
+
+# {skill_title}
+
+## Overview
+
+[TODO: 1-2 sentences explaining what this skill enables]
+
+## Structuring This Skill
+
+[TODO: Choose the structure that best fits this skill's purpose. Common patterns:
+
+**1. Workflow-Based** (best for sequential processes)
+- Works well when there are clear step-by-step procedures
+- Example: DOCX skill with "Workflow Decision Tree" -> "Reading" -> "Creating" -> "Editing"
+- Structure: ## Overview -> ## Workflow Decision Tree -> ## Step 1 -> ## Step 2...
+
+**2. Task-Based** (best for tool collections)
+- Works well when the skill offers different operations/capabilities
+- Example: PDF skill with "Quick Start" -> "Merge PDFs" -> "Split PDFs" -> "Extract Text"
+- Structure: ## Overview -> ## Quick Start -> ## Task Category 1 -> ## Task Category 2...
+
+**3. Reference/Guidelines** (best for standards or specifications)
+- Works well for brand guidelines, coding standards, or requirements
+- Example: Brand styling with "Brand Guidelines" -> "Colors" -> "Typography" -> "Features"
+- Structure: ## Overview -> ## Guidelines -> ## Specifications -> ## Usage...
+
+**4. Capabilities-Based** (best for integrated systems)
+- Works well when the skill provides multiple interrelated features
+- Example: Product Management with "Core Capabilities" -> numbered capability list
+- Structure: ## Overview -> ## Core Capabilities -> ### 1. Feature -> ### 2. Feature...
+
+Patterns can be mixed and matched as needed. Most skills combine patterns (e.g., start with task-based, add workflow for complex operations).
+
+Delete this entire "Structuring This Skill" section when done - it's just guidance.]
+
+## [TODO: Replace with the first main section based on chosen structure]
+
+[TODO: Add content here. See examples in existing skills:
+- Code samples for technical skills
+- Decision trees for complex workflows
+- Concrete examples with realistic user requests
+- References to scripts/templates/references as needed]
+
+## Resources (optional)
+
+Create only the resource directories this skill actually needs. Delete this section if no resources are required.
+
+### scripts/
+Executable code (Python/Bash/etc.) that can be run directly to perform specific operations.
+
+**Examples from other skills:**
+- PDF skill: `fill_fillable_fields.py`, `extract_form_field_info.py` - utilities for PDF manipulation
+- DOCX skill: `document.py`, `utilities.py` - Python modules for document processing
+
+**Appropriate for:** Python scripts, shell scripts, or any executable code that performs automation, data processing, or specific operations.
+
+**Note:** Scripts may be executed without loading into context, but can still be read by Codex for patching or environment adjustments.
+
+### references/
+Documentation and reference material intended to be loaded into context to inform Codex's process and thinking.
+
+**Examples from other skills:**
+- Product management: `communication.md`, `context_building.md` - detailed workflow guides
+- BigQuery: API reference documentation and query examples
+- Finance: Schema documentation, company policies
+
+**Appropriate for:** In-depth documentation, API references, database schemas, comprehensive guides, or any detailed information that Codex should reference while working.
+
+### assets/
+Files not intended to be loaded into context, but rather used within the output Codex produces.
+
+**Examples from other skills:**
+- Brand styling: PowerPoint template files (.pptx), logo files
+- Frontend builder: HTML/React boilerplate project directories
+- Typography: Font files (.ttf, .woff2)
+
+**Appropriate for:** Templates, boilerplate code, document templates, images, icons, fonts, or any files meant to be copied or used in the final output.
+
+---
+
+**Not every skill requires all three types of resources.**
+"""
+
+EXAMPLE_SCRIPT = '''#!/usr/bin/env python3
+"""
+Example helper script for {skill_name}
+
+This is a placeholder script that can be executed directly.
+Replace with actual implementation or delete if not needed.
+
+Example real scripts from other skills:
+- pdf/scripts/fill_fillable_fields.py - Fills PDF form fields
+- pdf/scripts/convert_pdf_to_images.py - Converts PDF pages to images
+"""
+
+def main():
+    print("This is an example script for {skill_name}")
+    # TODO: Add actual script logic here
+    # This could be data processing, file conversion, API calls, etc.
+
+if __name__ == "__main__":
+    main()
+'''
+
+EXAMPLE_REFERENCE = """# Reference Documentation for {skill_title}
+
+This is a placeholder for detailed reference documentation.
+Replace with actual reference content or delete if not needed.
+
+Example real reference docs from other skills:
+- product-management/references/communication.md - Comprehensive guide for status updates
+- product-management/references/context_building.md - Deep-dive on gathering context
+- bigquery/references/ - API references and query examples
+
+## When Reference Docs Are Useful
+
+Reference docs are ideal for:
+- Comprehensive API documentation
+- Detailed workflow guides
+- Complex multi-step processes
+- Information too lengthy for main SKILL.md
+- Content that's only needed for specific use cases
+
+## Structure Suggestions
+
+### API Reference Example
+- Overview
+- Authentication
+- Endpoints with examples
+- Error codes
+- Rate limits
+
+### Workflow Guide Example
+- Prerequisites
+- Step-by-step instructions
+- Common patterns
+- Troubleshooting
+- Best practices
+"""
+
+EXAMPLE_ASSET = """# Example Asset File
+
+This placeholder represents where asset files would be stored.
+Replace with actual asset files (templates, images, fonts, etc.) or delete if not needed.
+
+Asset files are NOT intended to be loaded into context, but rather used within
+the output Codex produces.
+
+Example asset files from other skills:
+- Brand guidelines: logo.png, slides_template.pptx
+- Frontend builder: hello-world/ directory with HTML/React boilerplate
+- Typography: custom-font.ttf, font-family.woff2
+- Data: sample_data.csv, test_dataset.json
+
+## Common Asset Types
+
+- Templates: .pptx, .docx, boilerplate directories
+- Images: .png, .jpg, .svg, .gif
+- Fonts: .ttf, .otf, .woff, .woff2
+- Boilerplate code: Project directories, starter files
+- Icons: .ico, .svg
+- Data files: .csv, .json, .xml, .yaml
+
+Note: This is a text placeholder. Actual assets can be any file type.
+"""
+
+
+def normalize_skill_name(skill_name):
+    """Normalize a skill name to lowercase hyphen-case."""
+    normalized = skill_name.strip().lower()
+    normalized = re.sub(r"[^a-z0-9]+", "-", normalized)
+    normalized = normalized.strip("-")
+    normalized = re.sub(r"-{2,}", "-", normalized)
+    return normalized
+
+
+def title_case_skill_name(skill_name):
+    """Convert hyphenated skill name to Title Case for display."""
+    return " ".join(word.capitalize() for word in skill_name.split("-"))
+
+
+def parse_resources(raw_resources):
+    if not raw_resources:
+        return []
+    resources = [item.strip() for item in raw_resources.split(",") if item.strip()]
+    invalid = sorted({item for item in resources if item not in ALLOWED_RESOURCES})
+    if invalid:
+        allowed = ", ".join(sorted(ALLOWED_RESOURCES))
+        print(f"[ERROR] Unknown resource type(s): {', '.join(invalid)}")
+        print(f"   Allowed: {allowed}")
+        sys.exit(1)
+    deduped = []
+    seen = set()
+    for resource in resources:
+        if resource not in seen:
+            deduped.append(resource)
+            seen.add(resource)
+    return deduped
+
+
+def create_resource_dirs(skill_dir, skill_name, skill_title, resources, include_examples):
+    for resource in resources:
+        resource_dir = skill_dir / resource
+        resource_dir.mkdir(exist_ok=True)
+        if resource == "scripts":
+            if include_examples:
+                example_script = resource_dir / "example.py"
+                example_script.write_text(EXAMPLE_SCRIPT.format(skill_name=skill_name))
+                example_script.chmod(0o755)
+                print("[OK] Created scripts/example.py")
+            else:
+                print("[OK] Created scripts/")
+        elif resource == "references":
+            if include_examples:
+                example_reference = resource_dir / "api_reference.md"
+                example_reference.write_text(EXAMPLE_REFERENCE.format(skill_title=skill_title))
+                print("[OK] Created references/api_reference.md")
+            else:
+                print("[OK] Created references/")
+        elif resource == "assets":
+            if include_examples:
+                example_asset = resource_dir / "example_asset.txt"
+                example_asset.write_text(EXAMPLE_ASSET)
+                print("[OK] Created assets/example_asset.txt")
+            else:
+                print("[OK] Created assets/")
+
+
+def init_skill(skill_name, path, resources, include_examples):
+    """
+    Initialize a new skill directory with template SKILL.md.
+
+    Args:
+        skill_name: Name of the skill
+        path: Path where the skill directory should be created
+        resources: Resource directories to create
+        include_examples: Whether to create example files in resource directories
+
+    Returns:
+        Path to created skill directory, or None if error
+    """
+    # Determine skill directory path
+    skill_dir = Path(path).resolve() / skill_name
+
+    # Check if directory already exists
+    if skill_dir.exists():
+        print(f"[ERROR] Skill directory already exists: {skill_dir}")
+        return None
+
+    # Create skill directory
+    try:
+        skill_dir.mkdir(parents=True, exist_ok=False)
+        print(f"[OK] Created skill directory: {skill_dir}")
+    except Exception as e:
+        print(f"[ERROR] Error creating directory: {e}")
+        return None
+
+    # Create SKILL.md from template
+    skill_title = title_case_skill_name(skill_name)
+    skill_content = SKILL_TEMPLATE.format(skill_name=skill_name, skill_title=skill_title)
+
+    skill_md_path = skill_dir / "SKILL.md"
+    try:
+        skill_md_path.write_text(skill_content)
+        print("[OK] Created SKILL.md")
+    except Exception as e:
+        print(f"[ERROR] Error creating SKILL.md: {e}")
+        return None
+
+    # Create resource directories if requested
+    if resources:
+        try:
+            create_resource_dirs(skill_dir, skill_name, skill_title, resources, include_examples)
+        except Exception as e:
+            print(f"[ERROR] Error creating resource directories: {e}")
+            return None
+
+    # Print next steps
+    print(f"\n[OK] Skill '{skill_name}' initialized successfully at {skill_dir}")
+    print("\nNext steps:")
+    print("1. Edit SKILL.md to complete the TODO items and update the description")
+    if resources:
+        if include_examples:
+            print("2. Customize or delete the example files in scripts/, references/, and assets/")
+        else:
+            print("2. Add resources to scripts/, references/, and assets/ as needed")
+    else:
+        print("2. Create resource directories only if needed (scripts/, references/, assets/)")
+    print("3. Run the validator when ready to check the skill structure")
+
+    return skill_dir
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Create a new skill directory with a SKILL.md template.",
+    )
+    parser.add_argument("skill_name", help="Skill name (normalized to hyphen-case)")
+    parser.add_argument("--path", required=True, help="Output directory for the skill")
+    parser.add_argument(
+        "--resources",
+        default="",
+        help="Comma-separated list: scripts,references,assets",
+    )
+    parser.add_argument(
+        "--examples",
+        action="store_true",
+        help="Create example files inside the selected resource directories",
+    )
+    args = parser.parse_args()
+
+    raw_skill_name = args.skill_name
+    skill_name = normalize_skill_name(raw_skill_name)
+    if not skill_name:
+        print("[ERROR] Skill name must include at least one letter or digit.")
+        sys.exit(1)
+    if len(skill_name) > MAX_SKILL_NAME_LENGTH:
+        print(
+            f"[ERROR] Skill name '{skill_name}' is too long ({len(skill_name)} characters). "
+            f"Maximum is {MAX_SKILL_NAME_LENGTH} characters."
+        )
+        sys.exit(1)
+    if skill_name != raw_skill_name:
+        print(f"Note: Normalized skill name from '{raw_skill_name}' to '{skill_name}'.")
+
+    resources = parse_resources(args.resources)
+    if args.examples and not resources:
+        print("[ERROR] --examples requires --resources to be set.")
+        sys.exit(1)
+
+    path = args.path
+
+    print(f"Initializing skill: {skill_name}")
+    print(f"   Location: {path}")
+    if resources:
+        print(f"   Resources: {', '.join(resources)}")
+        if args.examples:
+            print("   Examples: enabled")
+    else:
+        print("   Resources: none (create as needed)")
+    print()
+
+    result = init_skill(skill_name, path, resources, args.examples)
+
+    if result:
+        sys.exit(0)
+    else:
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

nanobot/skills/skill-creator/scripts/package_skill.py

@@ -0,0 +1,154 @@
+#!/usr/bin/env python3
+"""
+Skill Packager - Creates a distributable .skill file of a skill folder
+
+Usage:
+    python package_skill.py <path/to/skill-folder> [output-directory]
+
+Example:
+    python package_skill.py skills/public/my-skill
+    python package_skill.py skills/public/my-skill ./dist
+"""
+
+import sys
+import zipfile
+from pathlib import Path
+
+from quick_validate import validate_skill
+
+
+def _is_within(path: Path, root: Path) -> bool:
+    try:
+        path.relative_to(root)
+        return True
+    except ValueError:
+        return False
+
+
+def _cleanup_partial_archive(skill_filename: Path) -> None:
+    try:
+        if skill_filename.exists():
+            skill_filename.unlink()
+    except OSError:
+        pass
+
+
+def package_skill(skill_path, output_dir=None):
+    """
+    Package a skill folder into a .skill file.
+
+    Args:
+        skill_path: Path to the skill folder
+        output_dir: Optional output directory for the .skill file (defaults to current directory)
+
+    Returns:
+        Path to the created .skill file, or None if error
+    """
+    skill_path = Path(skill_path).resolve()
+
+    # Validate skill folder exists
+    if not skill_path.exists():
+        print(f"[ERROR] Skill folder not found: {skill_path}")
+        return None
+
+    if not skill_path.is_dir():
+        print(f"[ERROR] Path is not a directory: {skill_path}")
+        return None
+
+    # Validate SKILL.md exists
+    skill_md = skill_path / "SKILL.md"
+    if not skill_md.exists():
+        print(f"[ERROR] SKILL.md not found in {skill_path}")
+        return None
+
+    # Run validation before packaging
+    print("Validating skill...")
+    valid, message = validate_skill(skill_path)
+    if not valid:
+        print(f"[ERROR] Validation failed: {message}")
+        print("   Please fix the validation errors before packaging.")
+        return None
+    print(f"[OK] {message}\n")
+
+    # Determine output location
+    skill_name = skill_path.name
+    if output_dir:
+        output_path = Path(output_dir).resolve()
+        output_path.mkdir(parents=True, exist_ok=True)
+    else:
+        output_path = Path.cwd()
+
+    skill_filename = output_path / f"{skill_name}.skill"
+
+    EXCLUDED_DIRS = {".git", ".svn", ".hg", "__pycache__", "node_modules"}
+
+    files_to_package = []
+    resolved_archive = skill_filename.resolve()
+
+    for file_path in skill_path.rglob("*"):
+        # Fail closed on symlinks so the packaged contents are explicit and predictable.
+        if file_path.is_symlink():
+            print(f"[ERROR] Symlink not allowed in packaged skill: {file_path}")
+            _cleanup_partial_archive(skill_filename)
+            return None
+
+        rel_parts = file_path.relative_to(skill_path).parts
+        if any(part in EXCLUDED_DIRS for part in rel_parts):
+            continue
+
+        if file_path.is_file():
+            resolved_file = file_path.resolve()
+            if not _is_within(resolved_file, skill_path):
+                print(f"[ERROR] File escapes skill root: {file_path}")
+                _cleanup_partial_archive(skill_filename)
+                return None
+            # If output lives under skill_path, avoid writing archive into itself.
+            if resolved_file == resolved_archive:
+                print(f"[WARN] Skipping output archive: {file_path}")
+                continue
+            files_to_package.append(file_path)
+
+    # Create the .skill file (zip format)
+    try:
+        with zipfile.ZipFile(skill_filename, "w", zipfile.ZIP_DEFLATED) as zipf:
+            for file_path in files_to_package:
+                # Calculate the relative path within the zip.
+                arcname = Path(skill_name) / file_path.relative_to(skill_path)
+                zipf.write(file_path, arcname)
+                print(f"  Added: {arcname}")
+
+        print(f"\n[OK] Successfully packaged skill to: {skill_filename}")
+        return skill_filename
+
+    except Exception as e:
+        _cleanup_partial_archive(skill_filename)
+        print(f"[ERROR] Error creating .skill file: {e}")
+        return None
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: python package_skill.py <path/to/skill-folder> [output-directory]")
+        print("\nExample:")
+        print("  python package_skill.py skills/public/my-skill")
+        print("  python package_skill.py skills/public/my-skill ./dist")
+        sys.exit(1)
+
+    skill_path = sys.argv[1]
+    output_dir = sys.argv[2] if len(sys.argv) > 2 else None
+
+    print(f"Packaging skill: {skill_path}")
+    if output_dir:
+        print(f"   Output directory: {output_dir}")
+    print()
+
+    result = package_skill(skill_path, output_dir)
+
+    if result:
+        sys.exit(0)
+    else:
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

nanobot/skills/skill-creator/scripts/quick_validate.py

@@ -0,0 +1,213 @@
+#!/usr/bin/env python3
+"""
+Minimal validator for nanobot skill folders.
+"""
+
+import re
+import sys
+from pathlib import Path
+from typing import Optional
+
+try:
+    import yaml
+except ModuleNotFoundError:
+    yaml = None
+
+MAX_SKILL_NAME_LENGTH = 64
+ALLOWED_FRONTMATTER_KEYS = {
+    "name",
+    "description",
+    "metadata",
+    "always",
+    "license",
+    "allowed-tools",
+}
+ALLOWED_RESOURCE_DIRS = {"scripts", "references", "assets"}
+PLACEHOLDER_MARKERS = ("[todo", "todo:")
+
+
+def _extract_frontmatter(content: str) -> Optional[str]:
+    lines = content.splitlines()
+    if not lines or lines[0].strip() != "---":
+        return None
+    for i in range(1, len(lines)):
+        if lines[i].strip() == "---":
+            return "\n".join(lines[1:i])
+    return None
+
+
+def _parse_simple_frontmatter(frontmatter_text: str) -> Optional[dict[str, str]]:
+    """Fallback parser for simple frontmatter when PyYAML is unavailable."""
+    parsed: dict[str, str] = {}
+    current_key: Optional[str] = None
+    multiline_key: Optional[str] = None
+
+    for raw_line in frontmatter_text.splitlines():
+        stripped = raw_line.strip()
+        if not stripped or stripped.startswith("#"):
+            continue
+
+        is_indented = raw_line[:1].isspace()
+        if is_indented:
+            if current_key is None:
+                return None
+            current_value = parsed[current_key]
+            parsed[current_key] = f"{current_value}\n{stripped}" if current_value else stripped
+            continue
+
+        if ":" not in stripped:
+            return None
+
+        key, value = stripped.split(":", 1)
+        key = key.strip()
+        value = value.strip()
+        if not key:
+            return None
+
+        if value in {"|", ">"}:
+            parsed[key] = ""
+            current_key = key
+            multiline_key = key
+            continue
+
+        if (value.startswith('"') and value.endswith('"')) or (
+            value.startswith("'") and value.endswith("'")
+        ):
+            value = value[1:-1]
+        parsed[key] = value
+        current_key = key
+        multiline_key = None
+
+    if multiline_key is not None and multiline_key not in parsed:
+        return None
+    return parsed
+
+
+def _load_frontmatter(frontmatter_text: str) -> tuple[Optional[dict], Optional[str]]:
+    if yaml is not None:
+        try:
+            frontmatter = yaml.safe_load(frontmatter_text)
+        except yaml.YAMLError as exc:
+            return None, f"Invalid YAML in frontmatter: {exc}"
+        if not isinstance(frontmatter, dict):
+            return None, "Frontmatter must be a YAML dictionary"
+        return frontmatter, None
+
+    frontmatter = _parse_simple_frontmatter(frontmatter_text)
+    if frontmatter is None:
+        return None, "Invalid YAML in frontmatter: unsupported syntax without PyYAML installed"
+    return frontmatter, None
+
+
+def _validate_skill_name(name: str, folder_name: str) -> Optional[str]:
+    if not re.fullmatch(r"[a-z0-9]+(?:-[a-z0-9]+)*", name):
+        return (
+            f"Name '{name}' should be hyphen-case "
+            "(lowercase letters, digits, and single hyphens only)"
+        )
+    if len(name) > MAX_SKILL_NAME_LENGTH:
+        return (
+            f"Name is too long ({len(name)} characters). "
+            f"Maximum is {MAX_SKILL_NAME_LENGTH} characters."
+        )
+    if name != folder_name:
+        return f"Skill name '{name}' must match directory name '{folder_name}'"
+    return None
+
+
+def _validate_description(description: str) -> Optional[str]:
+    trimmed = description.strip()
+    if not trimmed:
+        return "Description cannot be empty"
+    lowered = trimmed.lower()
+    if any(marker in lowered for marker in PLACEHOLDER_MARKERS):
+        return "Description still contains TODO placeholder text"
+    if "<" in trimmed or ">" in trimmed:
+        return "Description cannot contain angle brackets (< or >)"
+    if len(trimmed) > 1024:
+        return f"Description is too long ({len(trimmed)} characters). Maximum is 1024 characters."
+    return None
+
+
+def validate_skill(skill_path):
+    """Validate a skill folder structure and required frontmatter."""
+    skill_path = Path(skill_path).resolve()
+
+    if not skill_path.exists():
+        return False, f"Skill folder not found: {skill_path}"
+    if not skill_path.is_dir():
+        return False, f"Path is not a directory: {skill_path}"
+
+    skill_md = skill_path / "SKILL.md"
+    if not skill_md.exists():
+        return False, "SKILL.md not found"
+
+    try:
+        content = skill_md.read_text(encoding="utf-8")
+    except OSError as exc:
+        return False, f"Could not read SKILL.md: {exc}"
+
+    frontmatter_text = _extract_frontmatter(content)
+    if frontmatter_text is None:
+        return False, "Invalid frontmatter format"
+
+    frontmatter, error = _load_frontmatter(frontmatter_text)
+    if error:
+        return False, error
+
+    unexpected_keys = sorted(set(frontmatter.keys()) - ALLOWED_FRONTMATTER_KEYS)
+    if unexpected_keys:
+        allowed = ", ".join(sorted(ALLOWED_FRONTMATTER_KEYS))
+        unexpected = ", ".join(unexpected_keys)
+        return (
+            False,
+            f"Unexpected key(s) in SKILL.md frontmatter: {unexpected}. Allowed properties are: {allowed}",
+        )
+
+    if "name" not in frontmatter:
+        return False, "Missing 'name' in frontmatter"
+    if "description" not in frontmatter:
+        return False, "Missing 'description' in frontmatter"
+
+    name = frontmatter["name"]
+    if not isinstance(name, str):
+        return False, f"Name must be a string, got {type(name).__name__}"
+    name_error = _validate_skill_name(name.strip(), skill_path.name)
+    if name_error:
+        return False, name_error
+
+    description = frontmatter["description"]
+    if not isinstance(description, str):
+        return False, f"Description must be a string, got {type(description).__name__}"
+    description_error = _validate_description(description)
+    if description_error:
+        return False, description_error
+
+    always = frontmatter.get("always")
+    if always is not None and not isinstance(always, bool):
+        return False, f"'always' must be a boolean, got {type(always).__name__}"
+
+    for child in skill_path.iterdir():
+        if child.name == "SKILL.md":
+            continue
+        if child.is_dir() and child.name in ALLOWED_RESOURCE_DIRS:
+            continue
+        if child.is_symlink():
+            continue
+        return (
+            False,
+            f"Unexpected file or directory in skill root: {child.name}. "
+            "Only SKILL.md, scripts/, references/, and assets/ are allowed.",
+        )
+
+    return True, "Skill is valid!"
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: python quick_validate.py <skill_directory>")
+        sys.exit(1)
+
+    valid, message = validate_skill(sys.argv[1])
+    print(message)
+    sys.exit(0 if valid else 1)

nanobot/utils/helpers.py

@@ -1,8 +1,12 @@
 """Utility functions for nanobot."""
 
+import json
 import re
 from datetime import datetime
 from pathlib import Path
+from typing import Any
+
+import tiktoken
 
 
 def detect_image_mime(data: bytes) -> str | None:
@@ -68,6 +72,104 @@ def split_message(content: str, max_len: int = 2000) -> list[str]:
     return chunks
 
 
+def build_assistant_message(
+    content: str | None,
+    tool_calls: list[dict[str, Any]] | None = None,
+    reasoning_content: str | None = None,
+    thinking_blocks: list[dict] | None = None,
+) -> dict[str, Any]:
+    """Build a provider-safe assistant message with optional reasoning fields."""
+    msg: dict[str, Any] = {"role": "assistant", "content": content}
+    if tool_calls:
+        msg["tool_calls"] = tool_calls
+    if reasoning_content is not None:
+        msg["reasoning_content"] = reasoning_content
+    if thinking_blocks:
+        msg["thinking_blocks"] = thinking_blocks
+    return msg
+
+
+def estimate_prompt_tokens(
+    messages: list[dict[str, Any]],
+    tools: list[dict[str, Any]] | None = None,
+) -> int:
+    """Estimate prompt tokens with tiktoken."""
+    try:
+        enc = tiktoken.get_encoding("cl100k_base")
+        parts: list[str] = []
+        for msg in messages:
+            content = msg.get("content")
+            if isinstance(content, str):
+                parts.append(content)
+            elif isinstance(content, list):
+                for part in content:
+                    if isinstance(part, dict) and part.get("type") == "text":
+                        txt = part.get("text", "")
+                        if txt:
+                            parts.append(txt)
+        if tools:
+            parts.append(json.dumps(tools, ensure_ascii=False))
+        return len(enc.encode("\n".join(parts)))
+    except Exception:
+        return 0
+
+
+def estimate_message_tokens(message: dict[str, Any]) -> int:
+    """Estimate prompt tokens contributed by one persisted message."""
+    content = message.get("content")
+    parts: list[str] = []
+    if isinstance(content, str):
+        parts.append(content)
+    elif isinstance(content, list):
+        for part in content:
+            if isinstance(part, dict) and part.get("type") == "text":
+                text = part.get("text", "")
+                if text:
+                    parts.append(text)
+            else:
+                parts.append(json.dumps(part, ensure_ascii=False))
+    elif content is not None:
+        parts.append(json.dumps(content, ensure_ascii=False))
+
+    for key in ("name", "tool_call_id"):
+        value = message.get(key)
+        if isinstance(value, str) and value:
+            parts.append(value)
+    if message.get("tool_calls"):
+        parts.append(json.dumps(message["tool_calls"], ensure_ascii=False))
+
+    payload = "\n".join(parts)
+    if not payload:
+        return 1
+    try:
+        enc = tiktoken.get_encoding("cl100k_base")
+        return max(1, len(enc.encode(payload)))
+    except Exception:
+        return max(1, len(payload) // 4)
+
+
+def estimate_prompt_tokens_chain(
+    provider: Any,
+    model: str | None,
+    messages: list[dict[str, Any]],
+    tools: list[dict[str, Any]] | None = None,
+) -> tuple[int, str]:
+    """Estimate prompt tokens via provider counter first, then tiktoken fallback."""
+    provider_counter = getattr(provider, "estimate_prompt_tokens", None)
+    if callable(provider_counter):
+        try:
+            tokens, source = provider_counter(messages, tools, model)
+            if isinstance(tokens, (int, float)) and tokens > 0:
+                return int(tokens), str(source or "provider_counter")
+        except Exception:
+            pass
+
+    estimated = estimate_prompt_tokens(messages, tools)
+    if estimated > 0:
+        return int(estimated), "tiktoken"
+    return 0, "none"
+
+
 def sync_workspace_templates(workspace: Path, silent: bool = False) -> list[str]:
     """Sync bundled templates to workspace. Only creates missing files."""
     from importlib.resources import files as pkg_files
@@ -88,7 +190,7 @@ def sync_workspace_templates(workspace: Path, silent: bool = False) -> list[str]
         added.append(str(dest.relative_to(workspace)))
 
     for item in tpl.iterdir():
-        if item.name.endswith(".md"):
+        if item.name.endswith(".md") and not item.name.startswith("."):
             _write(item, workspace / item.name)
     _write(tpl / "memory" / "MEMORY.md", workspace / "memory" / "MEMORY.md")
     _write(None, workspace / "memory" / "HISTORY.md")

pyproject.toml

@@ -18,13 +18,12 @@ classifiers = [
 
 dependencies = [
     "typer>=0.20.0,<1.0.0",
-    "litellm>=1.81.5,<2.0.0",
+    "litellm>=1.82.1,<2.0.0",
     "pydantic>=2.12.0,<3.0.0",
     "pydantic-settings>=2.12.0,<3.0.0",
     "websockets>=16.0,<17.0",
     "websocket-client>=1.9.0,<2.0.0",
     "httpx>=0.28.0,<1.0.0",
-    "ddgs>=9.5.5,<10.0.0",
     "oauth-cli-kit>=0.1.3,<1.0.0",
     "loguru>=0.7.3,<1.0.0",
     "readability-lxml>=0.8.4,<1.0.0",
@@ -45,14 +44,21 @@ dependencies = [
     "json-repair>=0.57.0,<1.0.0",
     "chardet>=3.0.2,<6.0.0",
     "openai>=2.8.0",
+    "tiktoken>=0.12.0,<1.0.0",
 ]
 
 [project.optional-dependencies]
+wecom = [
+    "wecom-aibot-sdk-python>=0.1.2",
+]
 matrix = [
     "matrix-nio[e2e]>=0.25.2",
     "mistune>=3.0.0,<4.0.0",
     "nh3>=0.2.17,<1.0.0",
 ]
+langsmith = [
+    "langsmith>=0.1.0",
+]
 dev = [
     "pytest>=9.0.0,<10.0.0",
     "pytest-asyncio>=1.3.0,<2.0.0",
@@ -69,13 +75,9 @@ nanobot = "nanobot.cli.commands:app"
 requires = ["hatchling"]
 build-backend = "hatchling.build"
 
-[tool.hatch.build.targets.wheel]
+[tool.hatch.metadata]
-packages = ["nanobot"]
+allow-direct-references = true
 
-[tool.hatch.build.targets.wheel.sources]
-"nanobot" = "nanobot"
-
-# Include non-Python files in skills and templates
 [tool.hatch.build]
 include = [
     "nanobot/**/*.py",
@@ -84,6 +86,15 @@ include = [
     "nanobot/skills/**/*.sh",
 ]
 
+[tool.hatch.build.targets.wheel]
+packages = ["nanobot"]
+
+[tool.hatch.build.targets.wheel.sources]
+"nanobot" = "nanobot"
+
+[tool.hatch.build.targets.wheel.force-include]
+"bridge" = "nanobot/bridge"
+
 [tool.hatch.build.targets.sdist]
 include = [
     "nanobot/",
@@ -92,9 +103,6 @@ include = [
     "LICENSE",
 ]
 
-[tool.hatch.build.targets.wheel.force-include]
-"bridge" = "nanobot/bridge"
-
 [tool.ruff]
 line-length = 100
 target-version = "py311"

tests/test_commands.py

@@ -1,3 +1,4 @@
+import re
 import shutil
 from pathlib import Path
 from unittest.mock import AsyncMock, MagicMock, patch
@@ -11,6 +12,12 @@ from nanobot.providers.litellm_provider import LiteLLMProvider
 from nanobot.providers.openai_codex_provider import _strip_model_prefix
 from nanobot.providers.registry import find_by_model
 
+
+def _strip_ansi(text):
+    """Remove ANSI escape codes from text."""
+    ansi_escape = re.compile(r'\x1b\[[0-9;]*m')
+    return ansi_escape.sub('', text)
+
 runner = CliRunner()
 
 
@@ -114,6 +121,64 @@ def test_config_matches_openai_codex_with_hyphen_prefix():
     assert config.get_provider_name() == "openai_codex"
 
 
+def test_config_matches_explicit_ollama_prefix_without_api_key():
+    config = Config()
+    config.agents.defaults.model = "ollama/llama3.2"
+
+    assert config.get_provider_name() == "ollama"
+    assert config.get_api_base() == "http://localhost:11434"
+
+
+def test_config_explicit_ollama_provider_uses_default_localhost_api_base():
+    config = Config()
+    config.agents.defaults.provider = "ollama"
+    config.agents.defaults.model = "llama3.2"
+
+    assert config.get_provider_name() == "ollama"
+    assert config.get_api_base() == "http://localhost:11434"
+
+
+def test_config_auto_detects_ollama_from_local_api_base():
+    config = Config.model_validate(
+        {
+            "agents": {"defaults": {"provider": "auto", "model": "llama3.2"}},
+            "providers": {"ollama": {"apiBase": "http://localhost:11434"}},
+        }
+    )
+
+    assert config.get_provider_name() == "ollama"
+    assert config.get_api_base() == "http://localhost:11434"
+
+
+def test_config_prefers_ollama_over_vllm_when_both_local_providers_configured():
+    config = Config.model_validate(
+        {
+            "agents": {"defaults": {"provider": "auto", "model": "llama3.2"}},
+            "providers": {
+                "vllm": {"apiBase": "http://localhost:8000"},
+                "ollama": {"apiBase": "http://localhost:11434"},
+            },
+        }
+    )
+
+    assert config.get_provider_name() == "ollama"
+    assert config.get_api_base() == "http://localhost:11434"
+
+
+def test_config_falls_back_to_vllm_when_ollama_not_configured():
+    config = Config.model_validate(
+        {
+            "agents": {"defaults": {"provider": "auto", "model": "llama3.2"}},
+            "providers": {
+                "vllm": {"apiBase": "http://localhost:8000"},
+            },
+        }
+    )
+
+    assert config.get_provider_name() == "vllm"
+    assert config.get_api_base() == "http://localhost:8000"
+
+
 def test_find_by_model_prefers_explicit_prefix_over_generic_codex_keyword():
     spec = find_by_model("github-copilot/gpt-5.3-codex")
 
@@ -170,10 +235,11 @@ def test_agent_help_shows_workspace_and_config_options():
     result = runner.invoke(app, ["agent", "--help"])
 
     assert result.exit_code == 0
-    assert "--workspace" in result.stdout
+    stripped_output = _strip_ansi(result.stdout)
-    assert "-w" in result.stdout
+    assert "--workspace" in stripped_output
-    assert "--config" in result.stdout
+    assert "-w" in stripped_output
-    assert "-c" in result.stdout
+    assert "--config" in stripped_output
+    assert "-c" in stripped_output
 
 
 def test_agent_uses_default_config_when_no_workspace_or_config_flags(mock_agent_runtime):
@@ -267,6 +333,16 @@ def test_agent_workspace_override_wins_over_config_workspace(mock_agent_runtime,
     assert mock_agent_runtime["agent_loop_cls"].call_args.kwargs["workspace"] == workspace_path
 
 
+def test_agent_warns_about_deprecated_memory_window(mock_agent_runtime):
+    mock_agent_runtime["config"].agents.defaults.memory_window = 100
+
+    result = runner.invoke(app, ["agent", "-m", "hello"])
+
+    assert result.exit_code == 0
+    assert "memoryWindow" in result.stdout
+    assert "contextWindowTokens" in result.stdout
+
+
 def test_gateway_uses_workspace_from_config_by_default(monkeypatch, tmp_path: Path) -> None:
     config_file = tmp_path / "instance" / "config.json"
     config_file.parent.mkdir(parents=True)
@@ -328,6 +404,28 @@ def test_gateway_workspace_option_overrides_config(monkeypatch, tmp_path: Path)
     assert config.workspace_path == override
 
 
+def test_gateway_warns_about_deprecated_memory_window(monkeypatch, tmp_path: Path) -> None:
+    config_file = tmp_path / "instance" / "config.json"
+    config_file.parent.mkdir(parents=True)
+    config_file.write_text("{}")
+
+    config = Config()
+    config.agents.defaults.memory_window = 100
+
+    monkeypatch.setattr("nanobot.config.loader.set_config_path", lambda _path: None)
+    monkeypatch.setattr("nanobot.config.loader.load_config", lambda _path=None: config)
+    monkeypatch.setattr("nanobot.cli.commands.sync_workspace_templates", lambda _path: None)
+    monkeypatch.setattr(
+        "nanobot.cli.commands._make_provider",
+        lambda _config: (_ for _ in ()).throw(_StopGateway("stop")),
+    )
+
+    result = runner.invoke(app, ["gateway", "--config", str(config_file)])
+
+    assert isinstance(result.exception, _StopGateway)
+    assert "memoryWindow" in result.stdout
+    assert "contextWindowTokens" in result.stdout
+
 def test_gateway_uses_config_directory_for_cron_store(monkeypatch, tmp_path: Path) -> None:
     config_file = tmp_path / "instance" / "config.json"
     config_file.parent.mkdir(parents=True)
@@ -356,3 +454,47 @@ def test_gateway_uses_config_directory_for_cron_store(monkeypatch, tmp_path: Pat
 
     assert isinstance(result.exception, _StopGateway)
     assert seen["cron_store"] == config_file.parent / "cron" / "jobs.json"
+
+
+def test_gateway_uses_configured_port_when_cli_flag_is_missing(monkeypatch, tmp_path: Path) -> None:
+    config_file = tmp_path / "instance" / "config.json"
+    config_file.parent.mkdir(parents=True)
+    config_file.write_text("{}")
+
+    config = Config()
+    config.gateway.port = 18791
+
+    monkeypatch.setattr("nanobot.config.loader.set_config_path", lambda _path: None)
+    monkeypatch.setattr("nanobot.config.loader.load_config", lambda _path=None: config)
+    monkeypatch.setattr("nanobot.cli.commands.sync_workspace_templates", lambda _path: None)
+    monkeypatch.setattr(
+        "nanobot.cli.commands._make_provider",
+        lambda _config: (_ for _ in ()).throw(_StopGateway("stop")),
+    )
+
+    result = runner.invoke(app, ["gateway", "--config", str(config_file)])
+
+    assert isinstance(result.exception, _StopGateway)
+    assert "port 18791" in result.stdout
+
+
+def test_gateway_cli_port_overrides_configured_port(monkeypatch, tmp_path: Path) -> None:
+    config_file = tmp_path / "instance" / "config.json"
+    config_file.parent.mkdir(parents=True)
+    config_file.write_text("{}")
+
+    config = Config()
+    config.gateway.port = 18791
+
+    monkeypatch.setattr("nanobot.config.loader.set_config_path", lambda _path: None)
+    monkeypatch.setattr("nanobot.config.loader.load_config", lambda _path=None: config)
+    monkeypatch.setattr("nanobot.cli.commands.sync_workspace_templates", lambda _path: None)
+    monkeypatch.setattr(
+        "nanobot.cli.commands._make_provider",
+        lambda _config: (_ for _ in ()).throw(_StopGateway("stop")),
+    )
+
+    result = runner.invoke(app, ["gateway", "--config", str(config_file), "--port", "18792"])
+
+    assert isinstance(result.exception, _StopGateway)
+    assert "port 18792" in result.stdout

tests/test_config_migration.py

@@ -0,0 +1,88 @@
+import json
+
+from typer.testing import CliRunner
+
+from nanobot.cli.commands import app
+from nanobot.config.loader import load_config, save_config
+
+runner = CliRunner()
+
+
+def test_load_config_keeps_max_tokens_and_warns_on_legacy_memory_window(tmp_path) -> None:
+    config_path = tmp_path / "config.json"
+    config_path.write_text(
+        json.dumps(
+            {
+                "agents": {
+                    "defaults": {
+                        "maxTokens": 1234,
+                        "memoryWindow": 42,
+                    }
+                }
+            }
+        ),
+        encoding="utf-8",
+    )
+
+    config = load_config(config_path)
+
+    assert config.agents.defaults.max_tokens == 1234
+    assert config.agents.defaults.context_window_tokens == 65_536
+    assert config.agents.defaults.should_warn_deprecated_memory_window is True
+
+
+def test_save_config_writes_context_window_tokens_but_not_memory_window(tmp_path) -> None:
+    config_path = tmp_path / "config.json"
+    config_path.write_text(
+        json.dumps(
+            {
+                "agents": {
+                    "defaults": {
+                        "maxTokens": 2222,
+                        "memoryWindow": 30,
+                    }
+                }
+            }
+        ),
+        encoding="utf-8",
+    )
+
+    config = load_config(config_path)
+    save_config(config, config_path)
+    saved = json.loads(config_path.read_text(encoding="utf-8"))
+    defaults = saved["agents"]["defaults"]
+
+    assert defaults["maxTokens"] == 2222
+    assert defaults["contextWindowTokens"] == 65_536
+    assert "memoryWindow" not in defaults
+
+
+def test_onboard_refresh_rewrites_legacy_config_template(tmp_path, monkeypatch) -> None:
+    config_path = tmp_path / "config.json"
+    workspace = tmp_path / "workspace"
+    config_path.write_text(
+        json.dumps(
+            {
+                "agents": {
+                    "defaults": {
+                        "maxTokens": 3333,
+                        "memoryWindow": 50,
+                    }
+                }
+            }
+        ),
+        encoding="utf-8",
+    )
+
+    monkeypatch.setattr("nanobot.config.loader.get_config_path", lambda: config_path)
+    monkeypatch.setattr("nanobot.cli.commands.get_workspace_path", lambda: workspace)
+
+    result = runner.invoke(app, ["onboard"], input="n\n")
+
+    assert result.exit_code == 0
+    assert "contextWindowTokens" in result.stdout
+    saved = json.loads(config_path.read_text(encoding="utf-8"))
+    defaults = saved["agents"]["defaults"]
+    assert defaults["maxTokens"] == 3333
+    assert defaults["contextWindowTokens"] == 65_536
+    assert "memoryWindow" not in defaults

tests/test_consolidate_offset.py

@@ -480,226 +480,35 @@ class TestEmptyAndBoundarySessions:
         assert_messages_content(old_messages, 10, 34)
 
 
-class TestConsolidationDeduplicationGuard:
+class TestNewCommandArchival:
-    """Test that consolidation tasks are deduplicated and serialized."""
+    """Test /new archival behavior with the simplified consolidation flow."""
 
-    @pytest.mark.asyncio
+    @staticmethod
-    async def test_consolidation_guard_prevents_duplicate_tasks(self, tmp_path: Path) -> None:
+    def _make_loop(tmp_path: Path):
-        """Concurrent messages above memory_window spawn only one consolidation task."""
         from nanobot.agent.loop import AgentLoop
-        from nanobot.bus.events import InboundMessage
         from nanobot.bus.queue import MessageBus
         from nanobot.providers.base import LLMResponse
 
         bus = MessageBus()
         provider = MagicMock()
         provider.get_default_model.return_value = "test-model"
+        provider.estimate_prompt_tokens.return_value = (10_000, "test")
         loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
+            bus=bus,
+            provider=provider,
+            workspace=tmp_path,
+            model="test-model",
+            context_window_tokens=1,
         )
-
+        loop.provider.chat_with_retry = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
         loop.tools.get_definitions = MagicMock(return_value=[])
-
+        return loop
-        session = loop.sessions.get_or_create("cli:test")
-        for i in range(15):
-            session.add_message("user", f"msg{i}")
-            session.add_message("assistant", f"resp{i}")
-        loop.sessions.save(session)
-
-        consolidation_calls = 0
-
-        async def _fake_consolidate(_session, archive_all: bool = False) -> None:
-            nonlocal consolidation_calls
-            consolidation_calls += 1
-            await asyncio.sleep(0.05)
-
-        loop._consolidate_memory = _fake_consolidate  # type: ignore[method-assign]
-
-        msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="hello")
-        await loop._process_message(msg)
-        await loop._process_message(msg)
-        await asyncio.sleep(0.1)
-
-        assert consolidation_calls == 1, (
-            f"Expected exactly 1 consolidation, got {consolidation_calls}"
-        )
-
-    @pytest.mark.asyncio
-    async def test_new_command_guard_prevents_concurrent_consolidation(
-        self, tmp_path: Path
-    ) -> None:
-        """/new command does not run consolidation concurrently with in-flight consolidation."""
-        from nanobot.agent.loop import AgentLoop
-        from nanobot.bus.events import InboundMessage
-        from nanobot.bus.queue import MessageBus
-        from nanobot.providers.base import LLMResponse
-
-        bus = MessageBus()
-        provider = MagicMock()
-        provider.get_default_model.return_value = "test-model"
-        loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
-        )
-
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.tools.get_definitions = MagicMock(return_value=[])
-
-        session = loop.sessions.get_or_create("cli:test")
-        for i in range(15):
-            session.add_message("user", f"msg{i}")
-            session.add_message("assistant", f"resp{i}")
-        loop.sessions.save(session)
-
-        consolidation_calls = 0
-        active = 0
-        max_active = 0
-
-        async def _fake_consolidate(_session, archive_all: bool = False) -> None:
-            nonlocal consolidation_calls, active, max_active
-            consolidation_calls += 1
-            active += 1
-            max_active = max(max_active, active)
-            await asyncio.sleep(0.05)
-            active -= 1
-
-        loop._consolidate_memory = _fake_consolidate  # type: ignore[method-assign]
-
-        msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="hello")
-        await loop._process_message(msg)
-
-        new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
-        await loop._process_message(new_msg)
-        await asyncio.sleep(0.1)
-
-        assert consolidation_calls == 2, (
-            f"Expected normal + /new consolidations, got {consolidation_calls}"
-        )
-        assert max_active == 1, (
-            f"Expected serialized consolidation, observed concurrency={max_active}"
-        )
-
-    @pytest.mark.asyncio
-    async def test_consolidation_tasks_are_referenced(self, tmp_path: Path) -> None:
-        """create_task results are tracked in _consolidation_tasks while in flight."""
-        from nanobot.agent.loop import AgentLoop
-        from nanobot.bus.events import InboundMessage
-        from nanobot.bus.queue import MessageBus
-        from nanobot.providers.base import LLMResponse
-
-        bus = MessageBus()
-        provider = MagicMock()
-        provider.get_default_model.return_value = "test-model"
-        loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
-        )
-
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.tools.get_definitions = MagicMock(return_value=[])
-
-        session = loop.sessions.get_or_create("cli:test")
-        for i in range(15):
-            session.add_message("user", f"msg{i}")
-            session.add_message("assistant", f"resp{i}")
-        loop.sessions.save(session)
-
-        started = asyncio.Event()
-
-        async def _slow_consolidate(_session, archive_all: bool = False) -> None:
-            started.set()
-            await asyncio.sleep(0.1)
-
-        loop._consolidate_memory = _slow_consolidate  # type: ignore[method-assign]
-
-        msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="hello")
-        await loop._process_message(msg)
-
-        await started.wait()
-        assert len(loop._consolidation_tasks) == 1, "Task must be referenced while in-flight"
-
-        await asyncio.sleep(0.15)
-        assert len(loop._consolidation_tasks) == 0, (
-            "Task reference must be removed after completion"
-        )
-
-    @pytest.mark.asyncio
-    async def test_new_waits_for_inflight_consolidation_and_preserves_messages(
-        self, tmp_path: Path
-    ) -> None:
-        """/new waits for in-flight consolidation and archives before clear."""
-        from nanobot.agent.loop import AgentLoop
-        from nanobot.bus.events import InboundMessage
-        from nanobot.bus.queue import MessageBus
-        from nanobot.providers.base import LLMResponse
-
-        bus = MessageBus()
-        provider = MagicMock()
-        provider.get_default_model.return_value = "test-model"
-        loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
-        )
-
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.tools.get_definitions = MagicMock(return_value=[])
-
-        session = loop.sessions.get_or_create("cli:test")
-        for i in range(15):
-            session.add_message("user", f"msg{i}")
-            session.add_message("assistant", f"resp{i}")
-        loop.sessions.save(session)
-
-        started = asyncio.Event()
-        release = asyncio.Event()
-        archived_count = 0
-
-        async def _fake_consolidate(sess, archive_all: bool = False) -> bool:
-            nonlocal archived_count
-            if archive_all:
-                archived_count = len(sess.messages)
-                return True
-            started.set()
-            await release.wait()
-            return True
-
-        loop._consolidate_memory = _fake_consolidate  # type: ignore[method-assign]
-
-        msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="hello")
-        await loop._process_message(msg)
-        await started.wait()
-
-        new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
-        pending_new = asyncio.create_task(loop._process_message(new_msg))
-
-        await asyncio.sleep(0.02)
-        assert not pending_new.done(), "/new should wait while consolidation is in-flight"
-
-        release.set()
-        response = await pending_new
-        assert response is not None
-        assert "new session started" in response.content.lower()
-        assert archived_count > 0, "Expected /new archival to process a non-empty snapshot"
-
-        session_after = loop.sessions.get_or_create("cli:test")
-        assert session_after.messages == [], "Session should be cleared after successful archival"
 
     @pytest.mark.asyncio
     async def test_new_does_not_clear_session_when_archive_fails(self, tmp_path: Path) -> None:
-        """/new must keep session data if archive step reports failure."""
-        from nanobot.agent.loop import AgentLoop
         from nanobot.bus.events import InboundMessage
-        from nanobot.bus.queue import MessageBus
-        from nanobot.providers.base import LLMResponse
-
-        bus = MessageBus()
-        provider = MagicMock()
-        provider.get_default_model.return_value = "test-model"
-        loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
-        )
-
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.tools.get_definitions = MagicMock(return_value=[])
 
+        loop = self._make_loop(tmp_path)
         session = loop.sessions.get_or_create("cli:test")
         for i in range(5):
             session.add_message("user", f"msg{i}")
@@ -707,111 +516,61 @@ class TestConsolidationDeduplicationGuard:
         loop.sessions.save(session)
         before_count = len(session.messages)
 
-        async def _failing_consolidate(sess, archive_all: bool = False) -> bool:
+        async def _failing_consolidate(_messages) -> bool:
-            if archive_all:
+            return False
-                return False
-            return True
 
-        loop._consolidate_memory = _failing_consolidate  # type: ignore[method-assign]
+        loop.memory_consolidator.consolidate_messages = _failing_consolidate  # type: ignore[method-assign]
 
         new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
         response = await loop._process_message(new_msg)
 
         assert response is not None
         assert "failed" in response.content.lower()
-        session_after = loop.sessions.get_or_create("cli:test")
+        assert len(loop.sessions.get_or_create("cli:test").messages) == before_count
-        assert len(session_after.messages) == before_count, (
-            "Session must remain intact when /new archival fails"
-        )
 
     @pytest.mark.asyncio
-    async def test_new_archives_only_unconsolidated_messages_after_inflight_task(
+    async def test_new_archives_only_unconsolidated_messages(self, tmp_path: Path) -> None:
-        self, tmp_path: Path
-    ) -> None:
-        """/new should archive only messages not yet consolidated by prior task."""
-        from nanobot.agent.loop import AgentLoop
         from nanobot.bus.events import InboundMessage
-        from nanobot.bus.queue import MessageBus
-        from nanobot.providers.base import LLMResponse
-
-        bus = MessageBus()
-        provider = MagicMock()
-        provider.get_default_model.return_value = "test-model"
-        loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
-        )
-
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.tools.get_definitions = MagicMock(return_value=[])
 
+        loop = self._make_loop(tmp_path)
         session = loop.sessions.get_or_create("cli:test")
         for i in range(15):
             session.add_message("user", f"msg{i}")
             session.add_message("assistant", f"resp{i}")
+        session.last_consolidated = len(session.messages) - 3
         loop.sessions.save(session)
 
-        started = asyncio.Event()
-        release = asyncio.Event()
         archived_count = -1
 
-        async def _fake_consolidate(sess, archive_all: bool = False) -> bool:
+        async def _fake_consolidate(messages) -> bool:
             nonlocal archived_count
-            if archive_all:
+            archived_count = len(messages)
-                archived_count = len(sess.messages)
-                return True
-
-            started.set()
-            await release.wait()
-            sess.last_consolidated = len(sess.messages) - 3
             return True
 
-        loop._consolidate_memory = _fake_consolidate  # type: ignore[method-assign]
+        loop.memory_consolidator.consolidate_messages = _fake_consolidate  # type: ignore[method-assign]
-
-        msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="hello")
-        await loop._process_message(msg)
-        await started.wait()
 
         new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
-        pending_new = asyncio.create_task(loop._process_message(new_msg))
+        response = await loop._process_message(new_msg)
-        await asyncio.sleep(0.02)
-        assert not pending_new.done()
-
-        release.set()
-        response = await pending_new
 
         assert response is not None
         assert "new session started" in response.content.lower()
-        assert archived_count == 3, (
+        assert archived_count == 3
-            f"Expected only unconsolidated tail to archive, got {archived_count}"
-        )
 
     @pytest.mark.asyncio
     async def test_new_clears_session_and_responds(self, tmp_path: Path) -> None:
-        """/new clears session and returns confirmation."""
-        from nanobot.agent.loop import AgentLoop
         from nanobot.bus.events import InboundMessage
-        from nanobot.bus.queue import MessageBus
-        from nanobot.providers.base import LLMResponse
-
-        bus = MessageBus()
-        provider = MagicMock()
-        provider.get_default_model.return_value = "test-model"
-        loop = AgentLoop(
-            bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10
-        )
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
-        loop.tools.get_definitions = MagicMock(return_value=[])
 
+        loop = self._make_loop(tmp_path)
         session = loop.sessions.get_or_create("cli:test")
         for i in range(3):
             session.add_message("user", f"msg{i}")
             session.add_message("assistant", f"resp{i}")
         loop.sessions.save(session)
 
-        async def _ok_consolidate(sess, archive_all: bool = False) -> bool:
+        async def _ok_consolidate(_messages) -> bool:
             return True
 
-        loop._consolidate_memory = _ok_consolidate  # type: ignore[method-assign]
+        loop.memory_consolidator.consolidate_messages = _ok_consolidate  # type: ignore[method-assign]
 
         new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
         response = await loop._process_message(new_msg)

tests/test_dingtalk_channel.py

@@ -1,9 +1,11 @@
+import asyncio
 from types import SimpleNamespace
 
 import pytest
 
 from nanobot.bus.queue import MessageBus
-from nanobot.channels.dingtalk import DingTalkChannel
+import nanobot.channels.dingtalk as dingtalk_module
+from nanobot.channels.dingtalk import DingTalkChannel, NanobotDingTalkHandler
 from nanobot.config.schema import DingTalkConfig
 
 
@@ -64,3 +66,46 @@ async def test_group_send_uses_group_messages_api() -> None:
     assert call["url"] == "https://api.dingtalk.com/v1.0/robot/groupMessages/send"
     assert call["json"]["openConversationId"] == "conv123"
     assert call["json"]["msgKey"] == "sampleMarkdown"
+
+
+@pytest.mark.asyncio
+async def test_handler_uses_voice_recognition_text_when_text_is_empty(monkeypatch) -> None:
+    bus = MessageBus()
+    channel = DingTalkChannel(
+        DingTalkConfig(client_id="app", client_secret="secret", allow_from=["user1"]),
+        bus,
+    )
+    handler = NanobotDingTalkHandler(channel)
+
+    class _FakeChatbotMessage:
+        text = None
+        extensions = {"content": {"recognition": "voice transcript"}}
+        sender_staff_id = "user1"
+        sender_id = "fallback-user"
+        sender_nick = "Alice"
+        message_type = "audio"
+
+        @staticmethod
+        def from_dict(_data):
+            return _FakeChatbotMessage()
+
+    monkeypatch.setattr(dingtalk_module, "ChatbotMessage", _FakeChatbotMessage)
+    monkeypatch.setattr(dingtalk_module, "AckMessage", SimpleNamespace(STATUS_OK="OK"))
+
+    status, body = await handler.process(
+        SimpleNamespace(
+            data={
+                "conversationType": "2",
+                "conversationId": "conv123",
+                "text": {"content": ""},
+            }
+        )
+    )
+
+    await asyncio.gather(*list(channel._background_tasks))
+    msg = await bus.consume_inbound()
+
+    assert (status, body) == ("OK", "OK")
+    assert msg.content == "voice transcript"
+    assert msg.sender_id == "user1"
+    assert msg.chat_id == "group:conv123"

tests/test_filesystem_tools.py

@@ -0,0 +1,251 @@
+"""Tests for enhanced filesystem tools: ReadFileTool, EditFileTool, ListDirTool."""
+
+import pytest
+
+from nanobot.agent.tools.filesystem import (
+    EditFileTool,
+    ListDirTool,
+    ReadFileTool,
+    _find_match,
+)
+
+
+# ---------------------------------------------------------------------------
+# ReadFileTool
+# ---------------------------------------------------------------------------
+
+class TestReadFileTool:
+
+    @pytest.fixture()
+    def tool(self, tmp_path):
+        return ReadFileTool(workspace=tmp_path)
+
+    @pytest.fixture()
+    def sample_file(self, tmp_path):
+        f = tmp_path / "sample.txt"
+        f.write_text("\n".join(f"line {i}" for i in range(1, 21)), encoding="utf-8")
+        return f
+
+    @pytest.mark.asyncio
+    async def test_basic_read_has_line_numbers(self, tool, sample_file):
+        result = await tool.execute(path=str(sample_file))
+        assert "1| line 1" in result
+        assert "20| line 20" in result
+
+    @pytest.mark.asyncio
+    async def test_offset_and_limit(self, tool, sample_file):
+        result = await tool.execute(path=str(sample_file), offset=5, limit=3)
+        assert "5| line 5" in result
+        assert "7| line 7" in result
+        assert "8| line 8" not in result
+        assert "Use offset=8 to continue" in result
+
+    @pytest.mark.asyncio
+    async def test_offset_beyond_end(self, tool, sample_file):
+        result = await tool.execute(path=str(sample_file), offset=999)
+        assert "Error" in result
+        assert "beyond end" in result
+
+    @pytest.mark.asyncio
+    async def test_end_of_file_marker(self, tool, sample_file):
+        result = await tool.execute(path=str(sample_file), offset=1, limit=9999)
+        assert "End of file" in result
+
+    @pytest.mark.asyncio
+    async def test_empty_file(self, tool, tmp_path):
+        f = tmp_path / "empty.txt"
+        f.write_text("", encoding="utf-8")
+        result = await tool.execute(path=str(f))
+        assert "Empty file" in result
+
+    @pytest.mark.asyncio
+    async def test_file_not_found(self, tool, tmp_path):
+        result = await tool.execute(path=str(tmp_path / "nope.txt"))
+        assert "Error" in result
+        assert "not found" in result
+
+    @pytest.mark.asyncio
+    async def test_char_budget_trims(self, tool, tmp_path):
+        """When the selected slice exceeds _MAX_CHARS the output is trimmed."""
+        f = tmp_path / "big.txt"
+        # Each line is ~110 chars, 2000 lines ≈ 220 KB > 128 KB limit
+        f.write_text("\n".join("x" * 110 for _ in range(2000)), encoding="utf-8")
+        result = await tool.execute(path=str(f))
+        assert len(result) <= ReadFileTool._MAX_CHARS + 500  # small margin for footer
+        assert "Use offset=" in result
+
+
+# ---------------------------------------------------------------------------
+# _find_match  (unit tests for the helper)
+# ---------------------------------------------------------------------------
+
+class TestFindMatch:
+
+    def test_exact_match(self):
+        match, count = _find_match("hello world", "world")
+        assert match == "world"
+        assert count == 1
+
+    def test_exact_no_match(self):
+        match, count = _find_match("hello world", "xyz")
+        assert match is None
+        assert count == 0
+
+    def test_crlf_normalisation(self):
+        # Caller normalises CRLF before calling _find_match, so test with
+        # pre-normalised content to verify exact match still works.
+        content = "line1\nline2\nline3"
+        old_text = "line1\nline2\nline3"
+        match, count = _find_match(content, old_text)
+        assert match is not None
+        assert count == 1
+
+    def test_line_trim_fallback(self):
+        content = "    def foo():\n        pass\n"
+        old_text = "def foo():\n    pass"
+        match, count = _find_match(content, old_text)
+        assert match is not None
+        assert count == 1
+        # The returned match should be the *original* indented text
+        assert "    def foo():" in match
+
+    def test_line_trim_multiple_candidates(self):
+        content = "  a\n  b\n  a\n  b\n"
+        old_text = "a\nb"
+        match, count = _find_match(content, old_text)
+        assert count == 2
+
+    def test_empty_old_text(self):
+        match, count = _find_match("hello", "")
+        # Empty string is always "in" any string via exact match
+        assert match == ""
+
+
+# ---------------------------------------------------------------------------
+# EditFileTool
+# ---------------------------------------------------------------------------
+
+class TestEditFileTool:
+
+    @pytest.fixture()
+    def tool(self, tmp_path):
+        return EditFileTool(workspace=tmp_path)
+
+    @pytest.mark.asyncio
+    async def test_exact_match(self, tool, tmp_path):
+        f = tmp_path / "a.py"
+        f.write_text("hello world", encoding="utf-8")
+        result = await tool.execute(path=str(f), old_text="world", new_text="earth")
+        assert "Successfully" in result
+        assert f.read_text() == "hello earth"
+
+    @pytest.mark.asyncio
+    async def test_crlf_normalisation(self, tool, tmp_path):
+        f = tmp_path / "crlf.py"
+        f.write_bytes(b"line1\r\nline2\r\nline3")
+        result = await tool.execute(
+            path=str(f), old_text="line1\nline2", new_text="LINE1\nLINE2",
+        )
+        assert "Successfully" in result
+        raw = f.read_bytes()
+        assert b"LINE1" in raw
+        # CRLF line endings should be preserved throughout the file
+        assert b"\r\n" in raw
+
+    @pytest.mark.asyncio
+    async def test_trim_fallback(self, tool, tmp_path):
+        f = tmp_path / "indent.py"
+        f.write_text("    def foo():\n        pass\n", encoding="utf-8")
+        result = await tool.execute(
+            path=str(f), old_text="def foo():\n    pass", new_text="def bar():\n    return 1",
+        )
+        assert "Successfully" in result
+        assert "bar" in f.read_text()
+
+    @pytest.mark.asyncio
+    async def test_ambiguous_match(self, tool, tmp_path):
+        f = tmp_path / "dup.py"
+        f.write_text("aaa\nbbb\naaa\nbbb\n", encoding="utf-8")
+        result = await tool.execute(path=str(f), old_text="aaa\nbbb", new_text="xxx")
+        assert "appears" in result.lower() or "Warning" in result
+
+    @pytest.mark.asyncio
+    async def test_replace_all(self, tool, tmp_path):
+        f = tmp_path / "multi.py"
+        f.write_text("foo bar foo bar foo", encoding="utf-8")
+        result = await tool.execute(
+            path=str(f), old_text="foo", new_text="baz", replace_all=True,
+        )
+        assert "Successfully" in result
+        assert f.read_text() == "baz bar baz bar baz"
+
+    @pytest.mark.asyncio
+    async def test_not_found(self, tool, tmp_path):
+        f = tmp_path / "nf.py"
+        f.write_text("hello", encoding="utf-8")
+        result = await tool.execute(path=str(f), old_text="xyz", new_text="abc")
+        assert "Error" in result
+        assert "not found" in result
+
+
+# ---------------------------------------------------------------------------
+# ListDirTool
+# ---------------------------------------------------------------------------
+
+class TestListDirTool:
+
+    @pytest.fixture()
+    def tool(self, tmp_path):
+        return ListDirTool(workspace=tmp_path)
+
+    @pytest.fixture()
+    def populated_dir(self, tmp_path):
+        (tmp_path / "src").mkdir()
+        (tmp_path / "src" / "main.py").write_text("pass")
+        (tmp_path / "src" / "utils.py").write_text("pass")
+        (tmp_path / "README.md").write_text("hi")
+        (tmp_path / ".git").mkdir()
+        (tmp_path / ".git" / "config").write_text("x")
+        (tmp_path / "node_modules").mkdir()
+        (tmp_path / "node_modules" / "pkg").mkdir()
+        return tmp_path
+
+    @pytest.mark.asyncio
+    async def test_basic_list(self, tool, populated_dir):
+        result = await tool.execute(path=str(populated_dir))
+        assert "README.md" in result
+        assert "src" in result
+        # .git and node_modules should be ignored
+        assert ".git" not in result
+        assert "node_modules" not in result
+
+    @pytest.mark.asyncio
+    async def test_recursive(self, tool, populated_dir):
+        result = await tool.execute(path=str(populated_dir), recursive=True)
+        assert "src/main.py" in result
+        assert "src/utils.py" in result
+        assert "README.md" in result
+        # Ignored dirs should not appear
+        assert ".git" not in result
+        assert "node_modules" not in result
+
+    @pytest.mark.asyncio
+    async def test_max_entries_truncation(self, tool, tmp_path):
+        for i in range(10):
+            (tmp_path / f"file_{i}.txt").write_text("x")
+        result = await tool.execute(path=str(tmp_path), max_entries=3)
+        assert "truncated" in result
+        assert "3 of 10" in result
+
+    @pytest.mark.asyncio
+    async def test_empty_dir(self, tool, tmp_path):
+        d = tmp_path / "empty"
+        d.mkdir()
+        result = await tool.execute(path=str(d))
+        assert "empty" in result.lower()
+
+    @pytest.mark.asyncio
+    async def test_not_found(self, tool, tmp_path):
+        result = await tool.execute(path=str(tmp_path / "nope"))
+        assert "Error" in result
+        assert "not found" in result

tests/test_gemini_thought_signature.py

@@ -0,0 +1,53 @@
+from types import SimpleNamespace
+
+from nanobot.providers.base import ToolCallRequest
+from nanobot.providers.litellm_provider import LiteLLMProvider
+
+
+def test_litellm_parse_response_preserves_tool_call_provider_fields() -> None:
+    provider = LiteLLMProvider(default_model="gemini/gemini-3-flash")
+
+    response = SimpleNamespace(
+        choices=[
+            SimpleNamespace(
+                finish_reason="tool_calls",
+                message=SimpleNamespace(
+                    content=None,
+                    tool_calls=[
+                        SimpleNamespace(
+                            id="call_123",
+                            function=SimpleNamespace(
+                                name="read_file",
+                                arguments='{"path":"todo.md"}',
+                                provider_specific_fields={"inner": "value"},
+                            ),
+                            provider_specific_fields={"thought_signature": "signed-token"},
+                        )
+                    ],
+                ),
+            )
+        ],
+        usage=None,
+    )
+
+    parsed = provider._parse_response(response)
+
+    assert len(parsed.tool_calls) == 1
+    assert parsed.tool_calls[0].provider_specific_fields == {"thought_signature": "signed-token"}
+    assert parsed.tool_calls[0].function_provider_specific_fields == {"inner": "value"}
+
+
+def test_tool_call_request_serializes_provider_fields() -> None:
+    tool_call = ToolCallRequest(
+        id="abc123xyz",
+        name="read_file",
+        arguments={"path": "todo.md"},
+        provider_specific_fields={"thought_signature": "signed-token"},
+        function_provider_specific_fields={"inner": "value"},
+    )
+
+    message = tool_call.to_openai_tool_call()
+
+    assert message["provider_specific_fields"] == {"thought_signature": "signed-token"}
+    assert message["function"]["provider_specific_fields"] == {"inner": "value"}
+    assert message["function"]["arguments"] == '{"path": "todo.md"}'

tests/test_heartbeat_service.py

@@ -3,18 +3,24 @@ import asyncio
 import pytest
 
 from nanobot.heartbeat.service import HeartbeatService
-from nanobot.providers.base import LLMResponse, ToolCallRequest
+from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
 
 
-class DummyProvider:
+class DummyProvider(LLMProvider):
     def __init__(self, responses: list[LLMResponse]):
+        super().__init__()
         self._responses = list(responses)
+        self.calls = 0
 
     async def chat(self, *args, **kwargs) -> LLMResponse:
+        self.calls += 1
         if self._responses:
             return self._responses.pop(0)
         return LLMResponse(content="", tool_calls=[])
 
+    def get_default_model(self) -> str:
+        return "test-model"
+
 
 @pytest.mark.asyncio
 async def test_start_is_idempotent(tmp_path) -> None:
@@ -115,3 +121,40 @@ async def test_trigger_now_returns_none_when_decision_is_skip(tmp_path) -> None:
     )
 
     assert await service.trigger_now() is None
+
+
+@pytest.mark.asyncio
+async def test_decide_retries_transient_error_then_succeeds(tmp_path, monkeypatch) -> None:
+    provider = DummyProvider([
+        LLMResponse(content="429 rate limit", finish_reason="error"),
+        LLMResponse(
+            content="",
+            tool_calls=[
+                ToolCallRequest(
+                    id="hb_1",
+                    name="heartbeat",
+                    arguments={"action": "run", "tasks": "check open tasks"},
+                )
+            ],
+        ),
+    ])
+
+    delays: list[int] = []
+
+    async def _fake_sleep(delay: int) -> None:
+        delays.append(delay)
+
+    monkeypatch.setattr(asyncio, "sleep", _fake_sleep)
+
+    service = HeartbeatService(
+        workspace=tmp_path,
+        provider=provider,
+        model="openai/gpt-4o-mini",
+    )
+
+    action, tasks = await service._decide("heartbeat content")
+
+    assert action == "run"
+    assert tasks == "check open tasks"
+    assert provider.calls == 2
+    assert delays == [1]

tests/test_loop_consolidation_tokens.py

@@ -0,0 +1,190 @@
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from nanobot.agent.loop import AgentLoop
+import nanobot.agent.memory as memory_module
+from nanobot.bus.queue import MessageBus
+from nanobot.providers.base import LLMResponse
+
+
+def _make_loop(tmp_path, *, estimated_tokens: int, context_window_tokens: int) -> AgentLoop:
+    provider = MagicMock()
+    provider.get_default_model.return_value = "test-model"
+    provider.estimate_prompt_tokens.return_value = (estimated_tokens, "test-counter")
+    provider.chat_with_retry = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
+
+    loop = AgentLoop(
+        bus=MessageBus(),
+        provider=provider,
+        workspace=tmp_path,
+        model="test-model",
+        context_window_tokens=context_window_tokens,
+    )
+    loop.tools.get_definitions = MagicMock(return_value=[])
+    return loop
+
+
+@pytest.mark.asyncio
+async def test_prompt_below_threshold_does_not_consolidate(tmp_path) -> None:
+    loop = _make_loop(tmp_path, estimated_tokens=100, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+
+    await loop.process_direct("hello", session_key="cli:test")
+
+    loop.memory_consolidator.consolidate_messages.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_prompt_above_threshold_triggers_consolidation(tmp_path, monkeypatch) -> None:
+    loop = _make_loop(tmp_path, estimated_tokens=1000, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+    ]
+    loop.sessions.save(session)
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda _message: 500)
+
+    await loop.process_direct("hello", session_key="cli:test")
+
+    assert loop.memory_consolidator.consolidate_messages.await_count >= 1
+
+
+@pytest.mark.asyncio
+async def test_prompt_above_threshold_archives_until_next_user_boundary(tmp_path, monkeypatch) -> None:
+    loop = _make_loop(tmp_path, estimated_tokens=1000, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+        {"role": "assistant", "content": "a2", "timestamp": "2026-01-01T00:00:03"},
+        {"role": "user", "content": "u3", "timestamp": "2026-01-01T00:00:04"},
+    ]
+    loop.sessions.save(session)
+
+    token_map = {"u1": 120, "a1": 120, "u2": 120, "a2": 120, "u3": 120}
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda message: token_map[message["content"]])
+
+    await loop.memory_consolidator.maybe_consolidate_by_tokens(session)
+
+    archived_chunk = loop.memory_consolidator.consolidate_messages.await_args.args[0]
+    assert [message["content"] for message in archived_chunk] == ["u1", "a1", "u2", "a2"]
+    assert session.last_consolidated == 4
+
+
+@pytest.mark.asyncio
+async def test_consolidation_loops_until_target_met(tmp_path, monkeypatch) -> None:
+    """Verify maybe_consolidate_by_tokens keeps looping until under threshold."""
+    loop = _make_loop(tmp_path, estimated_tokens=0, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+        {"role": "assistant", "content": "a2", "timestamp": "2026-01-01T00:00:03"},
+        {"role": "user", "content": "u3", "timestamp": "2026-01-01T00:00:04"},
+        {"role": "assistant", "content": "a3", "timestamp": "2026-01-01T00:00:05"},
+        {"role": "user", "content": "u4", "timestamp": "2026-01-01T00:00:06"},
+    ]
+    loop.sessions.save(session)
+
+    call_count = [0]
+    def mock_estimate(_session):
+        call_count[0] += 1
+        if call_count[0] == 1:
+            return (500, "test")
+        if call_count[0] == 2:
+            return (300, "test")
+        return (80, "test")
+
+    loop.memory_consolidator.estimate_session_prompt_tokens = mock_estimate  # type: ignore[method-assign]
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda _m: 100)
+
+    await loop.memory_consolidator.maybe_consolidate_by_tokens(session)
+
+    assert loop.memory_consolidator.consolidate_messages.await_count == 2
+    assert session.last_consolidated == 6
+
+
+@pytest.mark.asyncio
+async def test_consolidation_continues_below_trigger_until_half_target(tmp_path, monkeypatch) -> None:
+    """Once triggered, consolidation should continue until it drops below half threshold."""
+    loop = _make_loop(tmp_path, estimated_tokens=0, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+        {"role": "assistant", "content": "a2", "timestamp": "2026-01-01T00:00:03"},
+        {"role": "user", "content": "u3", "timestamp": "2026-01-01T00:00:04"},
+        {"role": "assistant", "content": "a3", "timestamp": "2026-01-01T00:00:05"},
+        {"role": "user", "content": "u4", "timestamp": "2026-01-01T00:00:06"},
+    ]
+    loop.sessions.save(session)
+
+    call_count = [0]
+
+    def mock_estimate(_session):
+        call_count[0] += 1
+        if call_count[0] == 1:
+            return (500, "test")
+        if call_count[0] == 2:
+            return (150, "test")
+        return (80, "test")
+
+    loop.memory_consolidator.estimate_session_prompt_tokens = mock_estimate  # type: ignore[method-assign]
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda _m: 100)
+
+    await loop.memory_consolidator.maybe_consolidate_by_tokens(session)
+
+    assert loop.memory_consolidator.consolidate_messages.await_count == 2
+    assert session.last_consolidated == 6
+
+
+@pytest.mark.asyncio
+async def test_preflight_consolidation_before_llm_call(tmp_path, monkeypatch) -> None:
+    """Verify preflight consolidation runs before the LLM call in process_direct."""
+    order: list[str] = []
+
+    loop = _make_loop(tmp_path, estimated_tokens=0, context_window_tokens=200)
+
+    async def track_consolidate(messages):
+        order.append("consolidate")
+        return True
+    loop.memory_consolidator.consolidate_messages = track_consolidate  # type: ignore[method-assign]
+
+    async def track_llm(*args, **kwargs):
+        order.append("llm")
+        return LLMResponse(content="ok", tool_calls=[])
+    loop.provider.chat_with_retry = track_llm
+
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+    ]
+    loop.sessions.save(session)
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda _m: 500)
+
+    call_count = [0]
+    def mock_estimate(_session):
+        call_count[0] += 1
+        return (1000 if call_count[0] <= 1 else 80, "test")
+    loop.memory_consolidator.estimate_session_prompt_tokens = mock_estimate  # type: ignore[method-assign]
+
+    await loop.process_direct("hello", session_key="cli:test")
+
+    assert "consolidate" in order
+    assert "llm" in order
+    assert order.index("consolidate") < order.index("llm")

tests/test_loop_save_turn.py

@@ -5,7 +5,7 @@ from nanobot.session.manager import Session
 
 def _mk_loop() -> AgentLoop:
     loop = AgentLoop.__new__(AgentLoop)
-    loop._TOOL_RESULT_MAX_CHARS = 500
+    loop._TOOL_RESULT_MAX_CHARS = AgentLoop._TOOL_RESULT_MAX_CHARS
     return loop
 
 
@@ -39,3 +39,17 @@ def test_save_turn_keeps_image_placeholder_after_runtime_strip() -> None:
         skip=0,
     )
     assert session.messages[0]["content"] == [{"type": "text", "text": "[image]"}]
+
+
+def test_save_turn_keeps_tool_results_under_16k() -> None:
+    loop = _mk_loop()
+    session = Session(key="test:tool-result")
+    content = "x" * 12_000
+
+    loop._save_turn(
+        session,
+        [{"role": "tool", "tool_call_id": "call_1", "name": "read_file", "content": content}],
+        skip=0,
+    )
+
+    assert session.messages[0]["content"] == content

tests/test_memory_consolidation_types.py

@@ -7,23 +7,20 @@ tool call response, it should serialize them to JSON instead of raising TypeErro
 
 import json
 from pathlib import Path
-from unittest.mock import AsyncMock, MagicMock
+from unittest.mock import AsyncMock
 
 import pytest
 
 from nanobot.agent.memory import MemoryStore
-from nanobot.providers.base import LLMResponse, ToolCallRequest
+from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
 
 
-def _make_session(message_count: int = 30, memory_window: int = 50):
+def _make_messages(message_count: int = 30):
-    """Create a mock session with messages."""
+    """Create a list of mock messages."""
-    session = MagicMock()
+    return [
-    session.messages = [
         {"role": "user", "content": f"msg{i}", "timestamp": "2026-01-01 00:00"}
         for i in range(message_count)
     ]
-    session.last_consolidated = 0
-    return session
 
 
 def _make_tool_response(history_entry, memory_update):
@@ -43,6 +40,22 @@ def _make_tool_response(history_entry, memory_update):
     )
 
 
+class ScriptedProvider(LLMProvider):
+    def __init__(self, responses: list[LLMResponse]):
+        super().__init__()
+        self._responses = list(responses)
+        self.calls = 0
+
+    async def chat(self, *args, **kwargs) -> LLMResponse:
+        self.calls += 1
+        if self._responses:
+            return self._responses.pop(0)
+        return LLMResponse(content="", tool_calls=[])
+
+    def get_default_model(self) -> str:
+        return "test-model"
+
+
 class TestMemoryConsolidationTypeHandling:
     """Test that consolidation handles various argument types correctly."""
 
@@ -57,9 +70,10 @@ class TestMemoryConsolidationTypeHandling:
                 memory_update="# Memory\nUser likes testing.",
             )
         )
-        session = _make_session(message_count=60)
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is True
         assert store.history_file.exists()
@@ -77,9 +91,10 @@ class TestMemoryConsolidationTypeHandling:
                 memory_update={"facts": ["User likes testing"], "topics": ["testing"]},
             )
         )
-        session = _make_session(message_count=60)
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is True
         assert store.history_file.exists()
@@ -97,7 +112,6 @@ class TestMemoryConsolidationTypeHandling:
         store = MemoryStore(tmp_path)
         provider = AsyncMock()
 
-        # Simulate arguments being a JSON string (not yet parsed)
         response = LLMResponse(
             content=None,
             tool_calls=[
@@ -112,9 +126,10 @@ class TestMemoryConsolidationTypeHandling:
             ],
         )
         provider.chat = AsyncMock(return_value=response)
-        session = _make_session(message_count=60)
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is True
         assert "User discussed testing." in store.history_file.read_text()
@@ -127,21 +142,23 @@ class TestMemoryConsolidationTypeHandling:
         provider.chat = AsyncMock(
             return_value=LLMResponse(content="I summarized the conversation.", tool_calls=[])
         )
-        session = _make_session(message_count=60)
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is False
         assert not store.history_file.exists()
 
     @pytest.mark.asyncio
-    async def test_skips_when_few_messages(self, tmp_path: Path) -> None:
+    async def test_skips_when_message_chunk_is_empty(self, tmp_path: Path) -> None:
-        """Consolidation should be a no-op when messages < keep_count."""
+        """Consolidation should be a no-op when the selected chunk is empty."""
         store = MemoryStore(tmp_path)
         provider = AsyncMock()
-        session = _make_session(message_count=10)
+        provider.chat_with_retry = provider.chat
+        messages: list[dict] = []
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is True
         provider.chat.assert_not_called()
@@ -152,7 +169,6 @@ class TestMemoryConsolidationTypeHandling:
         store = MemoryStore(tmp_path)
         provider = AsyncMock()
 
-        # Simulate arguments being a list containing a dict
         response = LLMResponse(
             content=None,
             tool_calls=[
@@ -167,9 +183,10 @@ class TestMemoryConsolidationTypeHandling:
             ],
         )
         provider.chat = AsyncMock(return_value=response)
-        session = _make_session(message_count=60)
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is True
         assert "User discussed testing." in store.history_file.read_text()
@@ -192,9 +209,10 @@ class TestMemoryConsolidationTypeHandling:
             ],
         )
         provider.chat = AsyncMock(return_value=response)
-        session = _make_session(message_count=60)
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is False
 
@@ -215,8 +233,246 @@ class TestMemoryConsolidationTypeHandling:
             ],
         )
         provider.chat = AsyncMock(return_value=response)
-        session = _make_session(message_count=60)
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
 
-        result = await store.consolidate(session, provider, "test-model", memory_window=50)
+        result = await store.consolidate(messages, provider, "test-model")
 
         assert result is False
+
+    @pytest.mark.asyncio
+    async def test_missing_history_entry_returns_false_without_writing(self, tmp_path: Path) -> None:
+        """Do not persist partial results when required fields are missing."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(
+            return_value=LLMResponse(
+                content=None,
+                tool_calls=[
+                    ToolCallRequest(
+                        id="call_1",
+                        name="save_memory",
+                        arguments={"memory_update": "# Memory\nOnly memory update"},
+                    )
+                ],
+            )
+        )
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+        assert not store.history_file.exists()
+        assert not store.memory_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_missing_memory_update_returns_false_without_writing(self, tmp_path: Path) -> None:
+        """Do not append history if memory_update is missing."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(
+            return_value=LLMResponse(
+                content=None,
+                tool_calls=[
+                    ToolCallRequest(
+                        id="call_1",
+                        name="save_memory",
+                        arguments={"history_entry": "[2026-01-01] Partial output."},
+                    )
+                ],
+            )
+        )
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+        assert not store.history_file.exists()
+        assert not store.memory_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_null_required_field_returns_false_without_writing(self, tmp_path: Path) -> None:
+        """Null required fields should be rejected before persistence."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(
+            return_value=_make_tool_response(
+                history_entry=None,
+                memory_update="# Memory\nUser likes testing.",
+            )
+        )
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+        assert not store.history_file.exists()
+        assert not store.memory_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_empty_history_entry_returns_false_without_writing(self, tmp_path: Path) -> None:
+        """Empty history entries should be rejected to avoid blank archival records."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(
+            return_value=_make_tool_response(
+                history_entry="   ",
+                memory_update="# Memory\nUser likes testing.",
+            )
+        )
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+        assert not store.history_file.exists()
+        assert not store.memory_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_retries_transient_error_then_succeeds(self, tmp_path: Path, monkeypatch) -> None:
+        store = MemoryStore(tmp_path)
+        provider = ScriptedProvider([
+            LLMResponse(content="503 server error", finish_reason="error"),
+            _make_tool_response(
+                history_entry="[2026-01-01] User discussed testing.",
+                memory_update="# Memory\nUser likes testing.",
+            ),
+        ])
+        messages = _make_messages(message_count=60)
+        delays: list[int] = []
+
+        async def _fake_sleep(delay: int) -> None:
+            delays.append(delay)
+
+        monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is True
+        assert provider.calls == 2
+        assert delays == [1]
+
+    @pytest.mark.asyncio
+    async def test_consolidation_delegates_to_provider_defaults(self, tmp_path: Path) -> None:
+        """Consolidation no longer passes generation params — the provider owns them."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(
+            return_value=_make_tool_response(
+                history_entry="[2026-01-01] User discussed testing.",
+                memory_update="# Memory\nUser likes testing.",
+            )
+        )
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is True
+        provider.chat_with_retry.assert_awaited_once()
+        _, kwargs = provider.chat_with_retry.await_args
+        assert kwargs["model"] == "test-model"
+        assert "temperature" not in kwargs
+        assert "max_tokens" not in kwargs
+        assert "reasoning_effort" not in kwargs
+
+    @pytest.mark.asyncio
+    async def test_tool_choice_fallback_on_unsupported_error(self, tmp_path: Path) -> None:
+        """Forced tool_choice rejected by provider -> retry with auto and succeed."""
+        store = MemoryStore(tmp_path)
+        error_resp = LLMResponse(
+            content="Error calling LLM: litellm.BadRequestError: "
+            "The tool_choice parameter does not support being set to required or object",
+            finish_reason="error",
+            tool_calls=[],
+        )
+        ok_resp = _make_tool_response(
+            history_entry="[2026-01-01] Fallback worked.",
+            memory_update="# Memory\nFallback OK.",
+        )
+
+        call_log: list[dict] = []
+
+        async def _tracking_chat(**kwargs):
+            call_log.append(kwargs)
+            return error_resp if len(call_log) == 1 else ok_resp
+
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(side_effect=_tracking_chat)
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is True
+        assert len(call_log) == 2
+        assert isinstance(call_log[0]["tool_choice"], dict)
+        assert call_log[1]["tool_choice"] == "auto"
+        assert "Fallback worked." in store.history_file.read_text()
+
+    @pytest.mark.asyncio
+    async def test_tool_choice_fallback_auto_no_tool_call(self, tmp_path: Path) -> None:
+        """Forced rejected, auto retry also produces no tool call -> return False."""
+        store = MemoryStore(tmp_path)
+        error_resp = LLMResponse(
+            content="Error: tool_choice must be none or auto",
+            finish_reason="error",
+            tool_calls=[],
+        )
+        no_tool_resp = LLMResponse(
+            content="Here is a summary.",
+            finish_reason="stop",
+            tool_calls=[],
+        )
+
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(side_effect=[error_resp, no_tool_resp])
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+        assert not store.history_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_raw_archive_after_consecutive_failures(self, tmp_path: Path) -> None:
+        """After 3 consecutive failures, raw-archive messages and return True."""
+        store = MemoryStore(tmp_path)
+        no_tool = LLMResponse(content="No tool call.", finish_reason="stop", tool_calls=[])
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(return_value=no_tool)
+        messages = _make_messages(message_count=10)
+
+        assert await store.consolidate(messages, provider, "m") is False
+        assert await store.consolidate(messages, provider, "m") is False
+        assert await store.consolidate(messages, provider, "m") is True
+
+        assert store.history_file.exists()
+        content = store.history_file.read_text()
+        assert "[RAW]" in content
+        assert "10 messages" in content
+        assert "msg0" in content
+        assert not store.memory_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_raw_archive_counter_resets_on_success(self, tmp_path: Path) -> None:
+        """A successful consolidation resets the failure counter."""
+        store = MemoryStore(tmp_path)
+        no_tool = LLMResponse(content="Nope.", finish_reason="stop", tool_calls=[])
+        ok_resp = _make_tool_response(
+            history_entry="[2026-01-01] OK.",
+            memory_update="# Memory\nOK.",
+        )
+        messages = _make_messages(message_count=10)
+
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(return_value=no_tool)
+        assert await store.consolidate(messages, provider, "m") is False
+        assert await store.consolidate(messages, provider, "m") is False
+        assert store._consecutive_failures == 2
+
+        provider.chat_with_retry = AsyncMock(return_value=ok_resp)
+        assert await store.consolidate(messages, provider, "m") is True
+        assert store._consecutive_failures == 0
+
+        provider.chat_with_retry = AsyncMock(return_value=no_tool)
+        assert await store.consolidate(messages, provider, "m") is False
+        assert store._consecutive_failures == 1

tests/test_message_tool_suppress.py

@@ -16,7 +16,7 @@ def _make_loop(tmp_path: Path) -> AgentLoop:
     bus = MessageBus()
     provider = MagicMock()
     provider.get_default_model.return_value = "test-model"
-    return AgentLoop(bus=bus, provider=provider, workspace=tmp_path, model="test-model", memory_window=10)
+    return AgentLoop(bus=bus, provider=provider, workspace=tmp_path, model="test-model")
 
 
 class TestMessageToolSuppressLogic:
@@ -33,7 +33,7 @@ class TestMessageToolSuppressLogic:
             LLMResponse(content="", tool_calls=[tool_call]),
             LLMResponse(content="Done", tool_calls=[]),
         ])
-        loop.provider.chat = AsyncMock(side_effect=lambda *a, **kw: next(calls))
+        loop.provider.chat_with_retry = AsyncMock(side_effect=lambda *a, **kw: next(calls))
         loop.tools.get_definitions = MagicMock(return_value=[])
 
         sent: list[OutboundMessage] = []
@@ -58,7 +58,7 @@ class TestMessageToolSuppressLogic:
             LLMResponse(content="", tool_calls=[tool_call]),
             LLMResponse(content="I've sent the email.", tool_calls=[]),
         ])
-        loop.provider.chat = AsyncMock(side_effect=lambda *a, **kw: next(calls))
+        loop.provider.chat_with_retry = AsyncMock(side_effect=lambda *a, **kw: next(calls))
         loop.tools.get_definitions = MagicMock(return_value=[])
 
         sent: list[OutboundMessage] = []
@@ -77,7 +77,7 @@ class TestMessageToolSuppressLogic:
     @pytest.mark.asyncio
     async def test_not_suppress_when_no_message_tool_used(self, tmp_path: Path) -> None:
         loop = _make_loop(tmp_path)
-        loop.provider.chat = AsyncMock(return_value=LLMResponse(content="Hello!", tool_calls=[]))
+        loop.provider.chat_with_retry = AsyncMock(return_value=LLMResponse(content="Hello!", tool_calls=[]))
         loop.tools.get_definitions = MagicMock(return_value=[])
 
         msg = InboundMessage(channel="feishu", sender_id="user1", chat_id="chat123", content="Hi")
@@ -98,7 +98,7 @@ class TestMessageToolSuppressLogic:
             ),
             LLMResponse(content="Done", tool_calls=[]),
         ])
-        loop.provider.chat = AsyncMock(side_effect=lambda *a, **kw: next(calls))
+        loop.provider.chat_with_retry = AsyncMock(side_effect=lambda *a, **kw: next(calls))
         loop.tools.get_definitions = MagicMock(return_value=[])
         loop.tools.execute = AsyncMock(return_value="ok")
 

tests/test_provider_retry.py

@@ -0,0 +1,125 @@
+import asyncio
+
+import pytest
+
+from nanobot.providers.base import GenerationSettings, LLMProvider, LLMResponse
+
+
+class ScriptedProvider(LLMProvider):
+    def __init__(self, responses):
+        super().__init__()
+        self._responses = list(responses)
+        self.calls = 0
+        self.last_kwargs: dict = {}
+
+    async def chat(self, *args, **kwargs) -> LLMResponse:
+        self.calls += 1
+        self.last_kwargs = kwargs
+        response = self._responses.pop(0)
+        if isinstance(response, BaseException):
+            raise response
+        return response
+
+    def get_default_model(self) -> str:
+        return "test-model"
+
+
+@pytest.mark.asyncio
+async def test_chat_with_retry_retries_transient_error_then_succeeds(monkeypatch) -> None:
+    provider = ScriptedProvider([
+        LLMResponse(content="429 rate limit", finish_reason="error"),
+        LLMResponse(content="ok"),
+    ])
+    delays: list[int] = []
+
+    async def _fake_sleep(delay: int) -> None:
+        delays.append(delay)
+
+    monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
+
+    response = await provider.chat_with_retry(messages=[{"role": "user", "content": "hello"}])
+
+    assert response.finish_reason == "stop"
+    assert response.content == "ok"
+    assert provider.calls == 2
+    assert delays == [1]
+
+
+@pytest.mark.asyncio
+async def test_chat_with_retry_does_not_retry_non_transient_error(monkeypatch) -> None:
+    provider = ScriptedProvider([
+        LLMResponse(content="401 unauthorized", finish_reason="error"),
+    ])
+    delays: list[int] = []
+
+    async def _fake_sleep(delay: int) -> None:
+        delays.append(delay)
+
+    monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
+
+    response = await provider.chat_with_retry(messages=[{"role": "user", "content": "hello"}])
+
+    assert response.content == "401 unauthorized"
+    assert provider.calls == 1
+    assert delays == []
+
+
+@pytest.mark.asyncio
+async def test_chat_with_retry_returns_final_error_after_retries(monkeypatch) -> None:
+    provider = ScriptedProvider([
+        LLMResponse(content="429 rate limit a", finish_reason="error"),
+        LLMResponse(content="429 rate limit b", finish_reason="error"),
+        LLMResponse(content="429 rate limit c", finish_reason="error"),
+        LLMResponse(content="503 final server error", finish_reason="error"),
+    ])
+    delays: list[int] = []
+
+    async def _fake_sleep(delay: int) -> None:
+        delays.append(delay)
+
+    monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
+
+    response = await provider.chat_with_retry(messages=[{"role": "user", "content": "hello"}])
+
+    assert response.content == "503 final server error"
+    assert provider.calls == 4
+    assert delays == [1, 2, 4]
+
+
+@pytest.mark.asyncio
+async def test_chat_with_retry_preserves_cancelled_error() -> None:
+    provider = ScriptedProvider([asyncio.CancelledError()])
+
+    with pytest.raises(asyncio.CancelledError):
+        await provider.chat_with_retry(messages=[{"role": "user", "content": "hello"}])
+
+
+@pytest.mark.asyncio
+async def test_chat_with_retry_uses_provider_generation_defaults() -> None:
+    """When callers omit generation params, provider.generation defaults are used."""
+    provider = ScriptedProvider([LLMResponse(content="ok")])
+    provider.generation = GenerationSettings(temperature=0.2, max_tokens=321, reasoning_effort="high")
+
+    await provider.chat_with_retry(messages=[{"role": "user", "content": "hello"}])
+
+    assert provider.last_kwargs["temperature"] == 0.2
+    assert provider.last_kwargs["max_tokens"] == 321
+    assert provider.last_kwargs["reasoning_effort"] == "high"
+
+
+@pytest.mark.asyncio
+async def test_chat_with_retry_explicit_override_beats_defaults() -> None:
+    """Explicit kwargs should override provider.generation defaults."""
+    provider = ScriptedProvider([LLMResponse(content="ok")])
+    provider.generation = GenerationSettings(temperature=0.2, max_tokens=321, reasoning_effort="high")
+
+    await provider.chat_with_retry(
+        messages=[{"role": "user", "content": "hello"}],
+        temperature=0.9,
+        max_tokens=9999,
+        reasoning_effort="low",
+    )
+
+    assert provider.last_kwargs["temperature"] == 0.9
+    assert provider.last_kwargs["max_tokens"] == 9999
+    assert provider.last_kwargs["reasoning_effort"] == "low"

tests/test_qq_channel.py

@@ -44,7 +44,7 @@ async def test_on_group_message_routes_to_group_chat_id() -> None:
 
 
 @pytest.mark.asyncio
-async def test_send_group_message_uses_group_api_with_msg_seq() -> None:
+async def test_send_group_message_uses_plain_text_group_api_with_msg_seq() -> None:
     channel = QQChannel(QQConfig(app_id="app", secret="secret", allow_from=["*"]), MessageBus())
     channel._client = _FakeClient()
     channel._chat_type_cache["group123"] = "group"
@@ -60,7 +60,37 @@ async def test_send_group_message_uses_group_api_with_msg_seq() -> None:
 
     assert len(channel._client.api.group_calls) == 1
     call = channel._client.api.group_calls[0]
-    assert call["group_openid"] == "group123"
+    assert call == {
-    assert call["msg_id"] == "msg1"
+        "group_openid": "group123",
-    assert call["msg_seq"] == 2
+        "msg_type": 0,
+        "content": "hello",
+        "msg_id": "msg1",
+        "msg_seq": 2,
+    }
     assert not channel._client.api.c2c_calls
+
+
+@pytest.mark.asyncio
+async def test_send_c2c_message_uses_plain_text_c2c_api_with_msg_seq() -> None:
+    channel = QQChannel(QQConfig(app_id="app", secret="secret", allow_from=["*"]), MessageBus())
+    channel._client = _FakeClient()
+
+    await channel.send(
+        OutboundMessage(
+            channel="qq",
+            chat_id="user123",
+            content="hello",
+            metadata={"message_id": "msg1"},
+        )
+    )
+
+    assert len(channel._client.api.c2c_calls) == 1
+    call = channel._client.api.c2c_calls[0]
+    assert call == {
+        "openid": "user123",
+        "msg_type": 0,
+        "content": "hello",
+        "msg_id": "msg1",
+        "msg_seq": 2,
+    }
+    assert not channel._client.api.group_calls

tests/test_restart_command.py

@@ -0,0 +1,76 @@
+"""Tests for /restart slash command."""
+
+from __future__ import annotations
+
+import asyncio
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from nanobot.bus.events import InboundMessage
+
+
+def _make_loop():
+    """Create a minimal AgentLoop with mocked dependencies."""
+    from nanobot.agent.loop import AgentLoop
+    from nanobot.bus.queue import MessageBus
+
+    bus = MessageBus()
+    provider = MagicMock()
+    provider.get_default_model.return_value = "test-model"
+    workspace = MagicMock()
+    workspace.__truediv__ = MagicMock(return_value=MagicMock())
+
+    with patch("nanobot.agent.loop.ContextBuilder"), \
+         patch("nanobot.agent.loop.SessionManager"), \
+         patch("nanobot.agent.loop.SubagentManager"):
+        loop = AgentLoop(bus=bus, provider=provider, workspace=workspace)
+    return loop, bus
+
+
+class TestRestartCommand:
+
+    @pytest.mark.asyncio
+    async def test_restart_sends_message_and_calls_execv(self):
+        loop, bus = _make_loop()
+        msg = InboundMessage(channel="cli", sender_id="user", chat_id="direct", content="/restart")
+
+        with patch("nanobot.agent.loop.os.execv") as mock_execv:
+            await loop._handle_restart(msg)
+            out = await asyncio.wait_for(bus.consume_outbound(), timeout=1.0)
+            assert "Restarting" in out.content
+
+            await asyncio.sleep(1.5)
+            mock_execv.assert_called_once()
+
+    @pytest.mark.asyncio
+    async def test_restart_intercepted_in_run_loop(self):
+        """Verify /restart is handled at the run-loop level, not inside _dispatch."""
+        loop, bus = _make_loop()
+        msg = InboundMessage(channel="telegram", sender_id="u1", chat_id="c1", content="/restart")
+
+        with patch.object(loop, "_handle_restart") as mock_handle:
+            mock_handle.return_value = None
+            await bus.publish_inbound(msg)
+
+            loop._running = True
+            run_task = asyncio.create_task(loop.run())
+            await asyncio.sleep(0.1)
+            loop._running = False
+            run_task.cancel()
+            try:
+                await run_task
+            except asyncio.CancelledError:
+                pass
+
+            mock_handle.assert_called_once()
+
+    @pytest.mark.asyncio
+    async def test_help_includes_restart(self):
+        loop, bus = _make_loop()
+        msg = InboundMessage(channel="telegram", sender_id="u1", chat_id="c1", content="/help")
+
+        response = await loop._process_message(msg)
+
+        assert response is not None
+        assert "/restart" in response.content

tests/test_skill_creator_scripts.py

@@ -0,0 +1,127 @@
+import importlib
+import shutil
+import sys
+import zipfile
+from pathlib import Path
+
+
+SCRIPT_DIR = Path("nanobot/skills/skill-creator/scripts").resolve()
+if str(SCRIPT_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPT_DIR))
+
+init_skill = importlib.import_module("init_skill")
+package_skill = importlib.import_module("package_skill")
+quick_validate = importlib.import_module("quick_validate")
+
+
+def test_init_skill_creates_expected_files(tmp_path: Path) -> None:
+    skill_dir = init_skill.init_skill(
+        "demo-skill",
+        tmp_path,
+        ["scripts", "references", "assets"],
+        include_examples=True,
+    )
+
+    assert skill_dir == tmp_path / "demo-skill"
+    assert (skill_dir / "SKILL.md").exists()
+    assert (skill_dir / "scripts" / "example.py").exists()
+    assert (skill_dir / "references" / "api_reference.md").exists()
+    assert (skill_dir / "assets" / "example_asset.txt").exists()
+
+
+def test_validate_skill_accepts_existing_skill_creator() -> None:
+    valid, message = quick_validate.validate_skill(
+        Path("nanobot/skills/skill-creator").resolve()
+    )
+
+    assert valid, message
+
+
+def test_validate_skill_rejects_placeholder_description(tmp_path: Path) -> None:
+    skill_dir = tmp_path / "placeholder-skill"
+    skill_dir.mkdir()
+    (skill_dir / "SKILL.md").write_text(
+        "---\n"
+        "name: placeholder-skill\n"
+        'description: "[TODO: fill me in]"\n'
+        "---\n"
+        "# Placeholder\n",
+        encoding="utf-8",
+    )
+
+    valid, message = quick_validate.validate_skill(skill_dir)
+
+    assert not valid
+    assert "TODO placeholder" in message
+
+
+def test_validate_skill_rejects_root_files_outside_allowed_dirs(tmp_path: Path) -> None:
+    skill_dir = tmp_path / "bad-root-skill"
+    skill_dir.mkdir()
+    (skill_dir / "SKILL.md").write_text(
+        "---\n"
+        "name: bad-root-skill\n"
+        "description: Valid description\n"
+        "---\n"
+        "# Skill\n",
+        encoding="utf-8",
+    )
+    (skill_dir / "README.md").write_text("extra\n", encoding="utf-8")
+
+    valid, message = quick_validate.validate_skill(skill_dir)
+
+    assert not valid
+    assert "Unexpected file or directory in skill root" in message
+
+
+def test_package_skill_creates_archive(tmp_path: Path) -> None:
+    skill_dir = tmp_path / "package-me"
+    skill_dir.mkdir()
+    (skill_dir / "SKILL.md").write_text(
+        "---\n"
+        "name: package-me\n"
+        "description: Package this skill.\n"
+        "---\n"
+        "# Skill\n",
+        encoding="utf-8",
+    )
+    scripts_dir = skill_dir / "scripts"
+    scripts_dir.mkdir()
+    (scripts_dir / "helper.py").write_text("print('ok')\n", encoding="utf-8")
+
+    archive_path = package_skill.package_skill(skill_dir, tmp_path / "dist")
+
+    assert archive_path == (tmp_path / "dist" / "package-me.skill")
+    assert archive_path.exists()
+    with zipfile.ZipFile(archive_path, "r") as archive:
+        names = set(archive.namelist())
+    assert "package-me/SKILL.md" in names
+    assert "package-me/scripts/helper.py" in names
+
+
+def test_package_skill_rejects_symlink(tmp_path: Path) -> None:
+    skill_dir = tmp_path / "symlink-skill"
+    skill_dir.mkdir()
+    (skill_dir / "SKILL.md").write_text(
+        "---\n"
+        "name: symlink-skill\n"
+        "description: Reject symlinks during packaging.\n"
+        "---\n"
+        "# Skill\n",
+        encoding="utf-8",
+    )
+    scripts_dir = skill_dir / "scripts"
+    scripts_dir.mkdir()
+    target = tmp_path / "outside.txt"
+    target.write_text("secret\n", encoding="utf-8")
+    link = scripts_dir / "outside.txt"
+
+    try:
+        link.symlink_to(target)
+    except (OSError, NotImplementedError):
+        return
+
+    archive_path = package_skill.package_skill(skill_dir, tmp_path / "dist")
+
+    assert archive_path is None
+    assert not (tmp_path / "dist" / "symlink-skill.skill").exists()

tests/test_task_cancel.py

@@ -165,3 +165,46 @@ class TestSubagentCancellation:
         provider.get_default_model.return_value = "test-model"
         mgr = SubagentManager(provider=provider, workspace=MagicMock(), bus=bus)
         assert await mgr.cancel_by_session("nonexistent") == 0
+
+    @pytest.mark.asyncio
+    async def test_subagent_preserves_reasoning_fields_in_tool_turn(self, monkeypatch, tmp_path):
+        from nanobot.agent.subagent import SubagentManager
+        from nanobot.bus.queue import MessageBus
+        from nanobot.providers.base import LLMResponse, ToolCallRequest
+
+        bus = MessageBus()
+        provider = MagicMock()
+        provider.get_default_model.return_value = "test-model"
+
+        captured_second_call: list[dict] = []
+
+        call_count = {"n": 0}
+
+        async def scripted_chat_with_retry(*, messages, **kwargs):
+            call_count["n"] += 1
+            if call_count["n"] == 1:
+                return LLMResponse(
+                    content="thinking",
+                    tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
+                    reasoning_content="hidden reasoning",
+                    thinking_blocks=[{"type": "thinking", "thinking": "step"}],
+                )
+            captured_second_call[:] = messages
+            return LLMResponse(content="done", tool_calls=[])
+        provider.chat_with_retry = scripted_chat_with_retry
+        mgr = SubagentManager(provider=provider, workspace=tmp_path, bus=bus)
+
+        async def fake_execute(self, name, arguments):
+            return "tool result"
+
+        monkeypatch.setattr("nanobot.agent.tools.registry.ToolRegistry.execute", fake_execute)
+
+        await mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
+
+        assistant_messages = [
+            msg for msg in captured_second_call
+            if msg.get("role") == "assistant" and msg.get("tool_calls")
+        ]
+        assert len(assistant_messages) == 1
+        assert assistant_messages[0]["reasoning_content"] == "hidden reasoning"
+        assert assistant_messages[0]["thinking_blocks"] == [{"type": "thinking", "thinking": "step"}]

tests/test_telegram_channel.py

@@ -1,10 +1,13 @@
+import asyncio
+from pathlib import Path
 from types import SimpleNamespace
+from unittest.mock import AsyncMock
 
 import pytest
 
 from nanobot.bus.events import OutboundMessage
 from nanobot.bus.queue import MessageBus
-from nanobot.channels.telegram import TelegramChannel
+from nanobot.channels.telegram import TELEGRAM_REPLY_CONTEXT_MAX_LEN, TelegramChannel
 from nanobot.config.schema import TelegramConfig
 
 
@@ -27,9 +30,11 @@ class _FakeUpdater:
 class _FakeBot:
     def __init__(self) -> None:
         self.sent_messages: list[dict] = []
+        self.get_me_calls = 0
 
     async def get_me(self):
-        return SimpleNamespace(username="nanobot_test")
+        self.get_me_calls += 1
+        return SimpleNamespace(id=999, username="nanobot_test")
 
     async def set_my_commands(self, commands) -> None:
         self.commands = commands
@@ -37,6 +42,15 @@ class _FakeBot:
     async def send_message(self, **kwargs) -> None:
         self.sent_messages.append(kwargs)
 
+    async def send_chat_action(self, **kwargs) -> None:
+        pass
+
+    async def get_file(self, file_id: str):
+        """Return a fake file that 'downloads' to a path (for reply-to-media tests)."""
+        async def _fake_download(path) -> None:
+            pass
+        return SimpleNamespace(download_to_drive=_fake_download)
+
 
 class _FakeApp:
     def __init__(self, on_start_polling) -> None:
@@ -87,6 +101,35 @@ class _FakeBuilder:
         return self.app
 
 
+def _make_telegram_update(
+    *,
+    chat_type: str = "group",
+    text: str | None = None,
+    caption: str | None = None,
+    entities=None,
+    caption_entities=None,
+    reply_to_message=None,
+):
+    user = SimpleNamespace(id=12345, username="alice", first_name="Alice")
+    message = SimpleNamespace(
+        chat=SimpleNamespace(type=chat_type, is_forum=False),
+        chat_id=-100123,
+        text=text,
+        caption=caption,
+        entities=entities or [],
+        caption_entities=caption_entities or [],
+        reply_to_message=reply_to_message,
+        photo=None,
+        voice=None,
+        audio=None,
+        document=None,
+        media_group_id=None,
+        message_thread_id=None,
+        message_id=1,
+    )
+    return SimpleNamespace(message=message, effective_user=user)
+
+
 @pytest.mark.asyncio
 async def test_start_uses_request_proxy_without_builder_proxy(monkeypatch) -> None:
     config = TelegramConfig(
@@ -131,6 +174,10 @@ def test_get_extension_falls_back_to_original_filename() -> None:
     assert channel._get_extension("file", None, "archive.tar.gz") == ".tar.gz"
 
 
+def test_telegram_group_policy_defaults_to_mention() -> None:
+    assert TelegramConfig().group_policy == "mention"
+
+
 def test_is_allowed_accepts_legacy_telegram_id_username_formats() -> None:
     channel = TelegramChannel(TelegramConfig(allow_from=["12345", "alice", "67890|bob"]), MessageBus())
 
@@ -182,3 +229,371 @@ async def test_send_reply_infers_topic_from_message_id_cache() -> None:
 
     assert channel._app.bot.sent_messages[0]["message_thread_id"] == 42
     assert channel._app.bot.sent_messages[0]["reply_parameters"].message_id == 10
+
+
+@pytest.mark.asyncio
+async def test_group_policy_mention_ignores_unmentioned_group_message() -> None:
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="mention"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+
+    handled = []
+
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    await channel._on_message(_make_telegram_update(text="hello everyone"), None)
+
+    assert handled == []
+    assert channel._app.bot.get_me_calls == 1
+
+
+@pytest.mark.asyncio
+async def test_group_policy_mention_accepts_text_mention_and_caches_bot_identity() -> None:
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="mention"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+
+    handled = []
+
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    mention = SimpleNamespace(type="mention", offset=0, length=13)
+    await channel._on_message(_make_telegram_update(text="@nanobot_test hi", entities=[mention]), None)
+    await channel._on_message(_make_telegram_update(text="@nanobot_test again", entities=[mention]), None)
+
+    assert len(handled) == 2
+    assert channel._app.bot.get_me_calls == 1
+
+
+@pytest.mark.asyncio
+async def test_group_policy_mention_accepts_caption_mention() -> None:
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="mention"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+
+    handled = []
+
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    mention = SimpleNamespace(type="mention", offset=0, length=13)
+    await channel._on_message(
+        _make_telegram_update(caption="@nanobot_test photo", caption_entities=[mention]),
+        None,
+    )
+
+    assert len(handled) == 1
+    assert handled[0]["content"] == "@nanobot_test photo"
+
+
+@pytest.mark.asyncio
+async def test_group_policy_mention_accepts_reply_to_bot() -> None:
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="mention"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+
+    handled = []
+
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    reply = SimpleNamespace(from_user=SimpleNamespace(id=999))
+    await channel._on_message(_make_telegram_update(text="reply", reply_to_message=reply), None)
+
+    assert len(handled) == 1
+
+
+@pytest.mark.asyncio
+async def test_group_policy_open_accepts_plain_group_message() -> None:
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+
+    handled = []
+
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    await channel._on_message(_make_telegram_update(text="hello group"), None)
+
+    assert len(handled) == 1
+    assert channel._app.bot.get_me_calls == 0
+
+
+def test_extract_reply_context_no_reply() -> None:
+    """When there is no reply_to_message, _extract_reply_context returns None."""
+    message = SimpleNamespace(reply_to_message=None)
+    assert TelegramChannel._extract_reply_context(message) is None
+
+
+def test_extract_reply_context_with_text() -> None:
+    """When reply has text, return prefixed string."""
+    reply = SimpleNamespace(text="Hello world", caption=None)
+    message = SimpleNamespace(reply_to_message=reply)
+    assert TelegramChannel._extract_reply_context(message) == "[Reply to: Hello world]"
+
+
+def test_extract_reply_context_with_caption_only() -> None:
+    """When reply has only caption (no text), caption is used."""
+    reply = SimpleNamespace(text=None, caption="Photo caption")
+    message = SimpleNamespace(reply_to_message=reply)
+    assert TelegramChannel._extract_reply_context(message) == "[Reply to: Photo caption]"
+
+
+def test_extract_reply_context_truncation() -> None:
+    """Reply text is truncated at TELEGRAM_REPLY_CONTEXT_MAX_LEN."""
+    long_text = "x" * (TELEGRAM_REPLY_CONTEXT_MAX_LEN + 100)
+    reply = SimpleNamespace(text=long_text, caption=None)
+    message = SimpleNamespace(reply_to_message=reply)
+    result = TelegramChannel._extract_reply_context(message)
+    assert result is not None
+    assert result.startswith("[Reply to: ")
+    assert result.endswith("...]")
+    assert len(result) == len("[Reply to: ]") + TELEGRAM_REPLY_CONTEXT_MAX_LEN + len("...")
+
+
+def test_extract_reply_context_no_text_returns_none() -> None:
+    """When reply has no text/caption, _extract_reply_context returns None (media handled separately)."""
+    reply = SimpleNamespace(text=None, caption=None)
+    message = SimpleNamespace(reply_to_message=reply)
+    assert TelegramChannel._extract_reply_context(message) is None
+
+
+@pytest.mark.asyncio
+async def test_on_message_includes_reply_context() -> None:
+    """When user replies to a message, content passed to bus starts with reply context."""
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+    handled = []
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    reply = SimpleNamespace(text="Hello", message_id=2, from_user=SimpleNamespace(id=1))
+    update = _make_telegram_update(text="translate this", reply_to_message=reply)
+    await channel._on_message(update, None)
+
+    assert len(handled) == 1
+    assert handled[0]["content"].startswith("[Reply to: Hello]")
+    assert "translate this" in handled[0]["content"]
+
+
+@pytest.mark.asyncio
+async def test_download_message_media_returns_path_when_download_succeeds(
+    monkeypatch, tmp_path
+) -> None:
+    """_download_message_media returns (paths, content_parts) when bot.get_file and download succeed."""
+    media_dir = tmp_path / "media" / "telegram"
+    media_dir.mkdir(parents=True)
+    monkeypatch.setattr(
+        "nanobot.channels.telegram.get_media_dir",
+        lambda channel=None: media_dir if channel else tmp_path / "media",
+    )
+
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"]),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+    channel._app.bot.get_file = AsyncMock(
+        return_value=SimpleNamespace(download_to_drive=AsyncMock(return_value=None))
+    )
+
+    msg = SimpleNamespace(
+        photo=[SimpleNamespace(file_id="fid123", mime_type="image/jpeg")],
+        voice=None,
+        audio=None,
+        document=None,
+        video=None,
+        video_note=None,
+        animation=None,
+    )
+    paths, parts = await channel._download_message_media(msg)
+    assert len(paths) == 1
+    assert len(parts) == 1
+    assert "fid123" in paths[0]
+    assert "[image:" in parts[0]
+
+
+@pytest.mark.asyncio
+async def test_on_message_attaches_reply_to_media_when_available(monkeypatch, tmp_path) -> None:
+    """When user replies to a message with media, that media is downloaded and attached to the turn."""
+    media_dir = tmp_path / "media" / "telegram"
+    media_dir.mkdir(parents=True)
+    monkeypatch.setattr(
+        "nanobot.channels.telegram.get_media_dir",
+        lambda channel=None: media_dir if channel else tmp_path / "media",
+    )
+
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    app = _FakeApp(lambda: None)
+    app.bot.get_file = AsyncMock(
+        return_value=SimpleNamespace(download_to_drive=AsyncMock(return_value=None))
+    )
+    channel._app = app
+    handled = []
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    reply_with_photo = SimpleNamespace(
+        text=None,
+        caption=None,
+        photo=[SimpleNamespace(file_id="reply_photo_fid", mime_type="image/jpeg")],
+        document=None,
+        voice=None,
+        audio=None,
+        video=None,
+        video_note=None,
+        animation=None,
+    )
+    update = _make_telegram_update(
+        text="what is the image?",
+        reply_to_message=reply_with_photo,
+    )
+    await channel._on_message(update, None)
+
+    assert len(handled) == 1
+    assert handled[0]["content"].startswith("[Reply to: [image:")
+    assert "what is the image?" in handled[0]["content"]
+    assert len(handled[0]["media"]) == 1
+    assert "reply_photo_fid" in handled[0]["media"][0]
+
+
+@pytest.mark.asyncio
+async def test_on_message_reply_to_media_fallback_when_download_fails() -> None:
+    """When reply has media but download fails, no media attached and no reply tag."""
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+    channel._app.bot.get_file = None
+    handled = []
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    reply_with_photo = SimpleNamespace(
+        text=None,
+        caption=None,
+        photo=[SimpleNamespace(file_id="x", mime_type="image/jpeg")],
+        document=None,
+        voice=None,
+        audio=None,
+        video=None,
+        video_note=None,
+        animation=None,
+    )
+    update = _make_telegram_update(text="what is this?", reply_to_message=reply_with_photo)
+    await channel._on_message(update, None)
+
+    assert len(handled) == 1
+    assert "what is this?" in handled[0]["content"]
+    assert handled[0]["media"] == []
+
+
+@pytest.mark.asyncio
+async def test_on_message_reply_to_caption_and_media(monkeypatch, tmp_path) -> None:
+    """When replying to a message with caption + photo, both text context and media are included."""
+    media_dir = tmp_path / "media" / "telegram"
+    media_dir.mkdir(parents=True)
+    monkeypatch.setattr(
+        "nanobot.channels.telegram.get_media_dir",
+        lambda channel=None: media_dir if channel else tmp_path / "media",
+    )
+
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    app = _FakeApp(lambda: None)
+    app.bot.get_file = AsyncMock(
+        return_value=SimpleNamespace(download_to_drive=AsyncMock(return_value=None))
+    )
+    channel._app = app
+    handled = []
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    reply_with_caption_and_photo = SimpleNamespace(
+        text=None,
+        caption="A cute cat",
+        photo=[SimpleNamespace(file_id="cat_fid", mime_type="image/jpeg")],
+        document=None,
+        voice=None,
+        audio=None,
+        video=None,
+        video_note=None,
+        animation=None,
+    )
+    update = _make_telegram_update(
+        text="what breed is this?",
+        reply_to_message=reply_with_caption_and_photo,
+    )
+    await channel._on_message(update, None)
+
+    assert len(handled) == 1
+    assert "[Reply to: A cute cat]" in handled[0]["content"]
+    assert "what breed is this?" in handled[0]["content"]
+    assert len(handled[0]["media"]) == 1
+    assert "cat_fid" in handled[0]["media"][0]
+
+
+@pytest.mark.asyncio
+async def test_forward_command_does_not_inject_reply_context() -> None:
+    """Slash commands forwarded via _forward_command must not include reply context."""
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+    handled = []
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+    channel._handle_message = capture_handle
+
+    reply = SimpleNamespace(text="some old message", message_id=2, from_user=SimpleNamespace(id=1))
+    update = _make_telegram_update(text="/new", reply_to_message=reply)
+    await channel._forward_command(update, None)
+
+    assert len(handled) == 1
+    assert handled[0]["content"] == "/new"

tests/test_tool_validation.py

@@ -1,10 +1,8 @@
 from typing import Any
 
-from nanobot.agent.tools.web import WebSearchTool
 from nanobot.agent.tools.base import Tool
 from nanobot.agent.tools.registry import ToolRegistry
 from nanobot.agent.tools.shell import ExecTool
-from nanobot.config.schema import WebSearchConfig
 
 
 class SampleTool(Tool):
@@ -110,6 +108,32 @@ def test_exec_extract_absolute_paths_captures_posix_absolute_paths() -> None:
     assert "/tmp/out.txt" in paths
 
 
+def test_exec_extract_absolute_paths_captures_home_paths() -> None:
+    cmd = "cat ~/.nanobot/config.json > ~/out.txt"
+    paths = ExecTool._extract_absolute_paths(cmd)
+    assert "~/.nanobot/config.json" in paths
+    assert "~/out.txt" in paths
+
+
+def test_exec_extract_absolute_paths_captures_quoted_paths() -> None:
+    cmd = 'cat "/tmp/data.txt" "~/.nanobot/config.json"'
+    paths = ExecTool._extract_absolute_paths(cmd)
+    assert "/tmp/data.txt" in paths
+    assert "~/.nanobot/config.json" in paths
+
+
+def test_exec_guard_blocks_home_path_outside_workspace(tmp_path) -> None:
+    tool = ExecTool(restrict_to_workspace=True)
+    error = tool._guard_command("cat ~/.nanobot/config.json", str(tmp_path))
+    assert error == "Error: Command blocked by safety guard (path outside working dir)"
+
+
+def test_exec_guard_blocks_quoted_home_path_outside_workspace(tmp_path) -> None:
+    tool = ExecTool(restrict_to_workspace=True)
+    error = tool._guard_command('cat "~/.nanobot/config.json"', str(tmp_path))
+    assert error == "Error: Command blocked by safety guard (path outside working dir)"
+
+
 # --- cast_params tests ---
 
 
@@ -341,14 +365,42 @@ def test_cast_params_single_value_not_auto_wrapped_to_array() -> None:
     assert result["items"] == "text"  # Not wrapped to ["text"]
 
 
-async def test_web_search_no_fallback_returns_provider_error() -> None:
+# --- ExecTool enhancement tests ---
-    tool = WebSearchTool(
-        config=WebSearchConfig(
-            provider="brave",
-            api_key="",
-            fallback_to_duckduckgo=False,
-        )
-    )
 
-    result = await tool.execute(query="fallback", count=1)
+
-    assert result == "Error: BRAVE_API_KEY not configured"
+async def test_exec_always_returns_exit_code() -> None:
+    """Exit code should appear in output even on success (exit 0)."""
+    tool = ExecTool()
+    result = await tool.execute(command="echo hello")
+    assert "Exit code: 0" in result
+    assert "hello" in result
+
+
+async def test_exec_head_tail_truncation() -> None:
+    """Long output should preserve both head and tail."""
+    tool = ExecTool()
+    # Generate output that exceeds _MAX_OUTPUT
+    big = "A" * 6000 + "\n" + "B" * 6000
+    result = await tool.execute(command=f"echo '{big}'")
+    assert "chars truncated" in result
+    # Head portion should start with As
+    assert result.startswith("A")
+    # Tail portion should end with the exit code which comes after Bs
+    assert "Exit code:" in result
+
+
+async def test_exec_timeout_parameter() -> None:
+    """LLM-supplied timeout should override the constructor default."""
+    tool = ExecTool(timeout=60)
+    # A very short timeout should cause the command to be killed
+    result = await tool.execute(command="sleep 10", timeout=1)
+    assert "timed out" in result
+    assert "1 seconds" in result
+
+
+async def test_exec_timeout_capped_at_max() -> None:
+    """Timeout values above _MAX_TIMEOUT should be clamped."""
+    tool = ExecTool()
+    # Should not raise — just clamp to 600
+    result = await tool.execute(command="echo ok", timeout=9999)
+    assert "Exit code: 0" in result

tests/test_web_search_tool.py

@@ -1,327 +0,0 @@
-import httpx
-import pytest
-from collections.abc import Callable
-from typing import Literal
-
-from nanobot.agent.tools.web import WebSearchTool
-from nanobot.config.schema import WebSearchConfig
-
-
-def _tool(config: WebSearchConfig, handler) -> WebSearchTool:
-    return WebSearchTool(config=config, transport=httpx.MockTransport(handler))
-
-
-def _assert_tavily_request(request: httpx.Request) -> bool:
-    return (
-        request.method == "POST"
-        and str(request.url) == "https://api.tavily.com/search"
-        and request.headers.get("authorization") == "Bearer tavily-key"
-        and '"query":"openclaw"' in request.read().decode("utf-8")
-    )
-
-
-@pytest.mark.asyncio
-@pytest.mark.parametrize(
-    ("provider", "config_kwargs", "query", "count", "assert_request", "response", "assert_text"),
-    [
-        (
-            "brave",
-            {"api_key": "brave-key"},
-            "nanobot",
-            1,
-            lambda request: (
-                request.method == "GET"
-                and str(request.url)
-                == "https://api.search.brave.com/res/v1/web/search?q=nanobot&count=1"
-                and request.headers["X-Subscription-Token"] == "brave-key"
-            ),
-            httpx.Response(
-                200,
-                json={
-                    "web": {
-                        "results": [
-                            {
-                                "title": "NanoBot",
-                                "url": "https://example.com/nanobot",
-                                "description": "Ultra-lightweight assistant",
-                            }
-                        ]
-                    }
-                },
-            ),
-            ["Results for: nanobot", "1. NanoBot", "https://example.com/nanobot"],
-        ),
-        (
-            "tavily",
-            {"api_key": "tavily-key"},
-            "openclaw",
-            2,
-            _assert_tavily_request,
-            httpx.Response(
-                200,
-                json={
-                    "results": [
-                        {
-                            "title": "OpenClaw",
-                            "url": "https://example.com/openclaw",
-                            "content": "Plugin-based assistant framework",
-                        }
-                    ]
-                },
-            ),
-            ["Results for: openclaw", "1. OpenClaw", "https://example.com/openclaw"],
-        ),
-        (
-            "searxng",
-            {"base_url": "https://searx.example"},
-            "nanobot",
-            1,
-            lambda request: (
-                request.method == "GET"
-                and str(request.url) == "https://searx.example/search?q=nanobot&format=json"
-            ),
-            httpx.Response(
-                200,
-                json={
-                    "results": [
-                        {
-                            "title": "nanobot docs",
-                            "url": "https://example.com/nanobot",
-                            "content": "Lightweight assistant docs",
-                        }
-                    ]
-                },
-            ),
-            ["Results for: nanobot", "1. nanobot docs", "https://example.com/nanobot"],
-        ),
-    ],
-)
-async def test_web_search_provider_formats_results(
-    provider: Literal["brave", "tavily", "searxng"],
-    config_kwargs: dict,
-    query: str,
-    count: int,
-    assert_request: Callable[[httpx.Request], bool],
-    response: httpx.Response,
-    assert_text: list[str],
-) -> None:
-    def handler(request: httpx.Request) -> httpx.Response:
-        assert assert_request(request)
-        return response
-
-    tool = _tool(WebSearchConfig(provider=provider, max_results=5, **config_kwargs), handler)
-    result = await tool.execute(query=query, count=count)
-    for text in assert_text:
-        assert text in result
-
-
-@pytest.mark.asyncio
-async def test_web_search_from_legacy_config_works() -> None:
-    def handler(request: httpx.Request) -> httpx.Response:
-        return httpx.Response(
-            200,
-            json={
-                "web": {
-                    "results": [
-                        {"title": "Legacy", "url": "https://example.com", "description": "ok"}
-                    ]
-                }
-            },
-        )
-
-    config = WebSearchConfig(api_key="legacy-key", max_results=3)
-    tool = WebSearchTool(config=config, transport=httpx.MockTransport(handler))
-    result = await tool.execute(query="constructor", count=1)
-    assert "1. Legacy" in result
-
-
-@pytest.mark.asyncio
-@pytest.mark.parametrize(
-    ("provider", "config", "missing_env", "expected_title"),
-    [
-        (
-            "brave",
-            WebSearchConfig(provider="brave", api_key="", max_results=5),
-            "BRAVE_API_KEY",
-            "Fallback Result",
-        ),
-        (
-            "tavily",
-            WebSearchConfig(provider="tavily", api_key="", max_results=5),
-            "TAVILY_API_KEY",
-            "Tavily Fallback",
-        ),
-    ],
-)
-async def test_web_search_missing_key_falls_back_to_duckduckgo(
-    monkeypatch: pytest.MonkeyPatch,
-    provider: str,
-    config: WebSearchConfig,
-    missing_env: str,
-    expected_title: str,
-) -> None:
-    monkeypatch.delenv(missing_env, raising=False)
-
-    called = False
-
-    class FakeDDGS:
-        def __init__(self, *args, **kwargs):
-            pass
-
-        def text(self, keywords: str, max_results: int):
-            nonlocal called
-            called = True
-            return [
-                {
-                    "title": expected_title,
-                    "href": f"https://example.com/{provider}-fallback",
-                    "body": "Fallback snippet",
-                }
-            ]
-
-    monkeypatch.setattr("nanobot.agent.tools.web.DDGS", FakeDDGS, raising=False)
-
-    result = await WebSearchTool(config=config).execute(query="fallback", count=1)
-    assert called
-    assert "Using DuckDuckGo fallback" in result
-    assert f"1. {expected_title}" in result
-
-
-@pytest.mark.asyncio
-async def test_web_search_brave_missing_key_without_fallback_returns_error(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    monkeypatch.delenv("BRAVE_API_KEY", raising=False)
-    tool = WebSearchTool(
-        config=WebSearchConfig(
-            provider="brave",
-            api_key="",
-            fallback_to_duckduckgo=False,
-        )
-    )
-
-    result = await tool.execute(query="fallback", count=1)
-    assert result == "Error: BRAVE_API_KEY not configured"
-
-
-@pytest.mark.asyncio
-async def test_web_search_searxng_missing_base_url_falls_back_to_duckduckgo() -> None:
-    tool = WebSearchTool(
-        config=WebSearchConfig(provider="searxng", base_url="", max_results=5)
-    )
-
-    result = await tool.execute(query="nanobot", count=1)
-    assert "DuckDuckGo fallback" in result
-    assert "SEARXNG_BASE_URL" in result
-
-
-@pytest.mark.asyncio
-async def test_web_search_searxng_missing_base_url_no_fallback_returns_error() -> None:
-    tool = WebSearchTool(
-        config=WebSearchConfig(
-            provider="searxng", base_url="",
-            fallback_to_duckduckgo=False, max_results=5,
-        )
-    )
-
-    result = await tool.execute(query="nanobot", count=1)
-    assert result == "Error: SEARXNG_BASE_URL not configured"
-
-
-@pytest.mark.asyncio
-async def test_web_search_searxng_uses_env_base_url(
-    monkeypatch: pytest.MonkeyPatch,
-) -> None:
-    monkeypatch.setenv("SEARXNG_BASE_URL", "https://searx.env")
-
-    def handler(request: httpx.Request) -> httpx.Response:
-        assert request.method == "GET"
-        assert str(request.url) == "https://searx.env/search?q=nanobot&format=json"
-        return httpx.Response(
-            200,
-            json={
-                "results": [
-                    {
-                        "title": "env result",
-                        "url": "https://example.com/env",
-                        "content": "from env",
-                    }
-                ]
-            },
-        )
-
-    config = WebSearchConfig(provider="searxng", base_url="", max_results=5)
-    result = await _tool(config, handler).execute(query="nanobot", count=1)
-    assert "1. env result" in result
-
-
-@pytest.mark.asyncio
-async def test_web_search_register_custom_provider() -> None:
-    config = WebSearchConfig(provider="custom", max_results=5)
-    tool = WebSearchTool(config=config)
-
-    async def _custom_provider(query: str, n: int) -> str:
-        return f"custom:{query}:{n}"
-
-    tool._provider_dispatch["custom"] = _custom_provider
-
-    result = await tool.execute(query="nanobot", count=2)
-    assert result == "custom:nanobot:2"
-
-
-@pytest.mark.asyncio
-async def test_web_search_duckduckgo_uses_injected_ddgs_factory() -> None:
-    class FakeDDGS:
-        def text(self, keywords: str, max_results: int):
-            assert keywords == "nanobot"
-            assert max_results == 1
-            return [
-                {
-                    "title": "NanoBot result",
-                    "href": "https://example.com/nanobot",
-                    "body": "Search content",
-                }
-            ]
-
-    tool = WebSearchTool(
-        config=WebSearchConfig(provider="duckduckgo", max_results=5),
-        ddgs_factory=lambda: FakeDDGS(),
-    )
-
-    result = await tool.execute(query="nanobot", count=1)
-    assert "1. NanoBot result" in result
-
-
-@pytest.mark.asyncio
-async def test_web_search_unknown_provider_returns_error() -> None:
-    tool = WebSearchTool(
-        config=WebSearchConfig(provider="google", max_results=5),
-    )
-    result = await tool.execute(query="nanobot", count=1)
-    assert result == "Error: unknown search provider 'google'"
-
-
-@pytest.mark.asyncio
-async def test_web_search_dispatch_dict_overwrites_builtin() -> None:
-    async def _custom_brave(query: str, n: int) -> str:
-        return f"custom-brave:{query}:{n}"
-
-    tool = WebSearchTool(
-        config=WebSearchConfig(provider="brave", api_key="key", max_results=5),
-    )
-    tool._provider_dispatch["brave"] = _custom_brave
-    result = await tool.execute(query="nanobot", count=2)
-    assert result == "custom-brave:nanobot:2"
-
-
-@pytest.mark.asyncio
-async def test_web_search_searxng_rejects_invalid_url() -> None:
-    tool = WebSearchTool(
-        config=WebSearchConfig(
-            provider="searxng",
-            base_url="ftp://internal.host",
-            max_results=5,
-        ),
-    )
-    result = await tool.execute(query="nanobot", count=1)
-    assert "Error: invalid SearXNG URL" in result