diff --git a/README.md b/README.md index d788e5e..45779e7 100644 --- a/README.md +++ b/README.md @@ -16,16 +16,24 @@ ⚑️ Delivers core agent functionality in just **~4,000** lines of code β€” **99% smaller** than Clawdbot's 430k+ lines. -πŸ“ Real-time line count: **3,922 lines** (run `bash core_agent_lines.sh` to verify anytime) +πŸ“ Real-time line count: **3,935 lines** (run `bash core_agent_lines.sh` to verify anytime) ## πŸ“’ News +- **2026-02-28** πŸš€ Released **v0.1.4.post3** β€” cleaner context, hardened session history, and smarter agent. Please see [release notes](https://github.com/HKUDS/nanobot/releases/tag/v0.1.4.post3) for details. +- **2026-02-27** 🧠 Experimental thinking mode support, DingTalk media messages, Feishu and QQ channel fixes. +- **2026-02-26** πŸ›‘οΈ Session poisoning fix, WhatsApp dedup, Windows path guard, Mistral compatibility. +- **2026-02-25** 🧹 New Matrix channel, cleaner session context, auto workspace template sync. - **2026-02-24** πŸš€ Released **v0.1.4.post2** β€” a reliability-focused release with a redesigned heartbeat, prompt cache optimization, and hardened provider & channel stability. See [release notes](https://github.com/HKUDS/nanobot/releases/tag/v0.1.4.post2) for details. - **2026-02-23** πŸ”§ Virtual tool-call heartbeat, prompt cache optimization, Slack mrkdwn fixes. - **2026-02-22** πŸ›‘οΈ Slack thread isolation, Discord typing fix, agent reliability improvements. - **2026-02-21** πŸŽ‰ Released **v0.1.4.post1** β€” new providers, media support across channels, and major stability improvements. See [release notes](https://github.com/HKUDS/nanobot/releases/tag/v0.1.4.post1) for details. - **2026-02-20** 🐦 Feishu now receives multimodal files from users. More reliable memory under the hood. - **2026-02-19** ✨ Slack now sends files, Discord splits long messages, and subagents work in CLI mode. + +
+Earlier news + - **2026-02-18** ⚑️ nanobot now supports VolcEngine, MCP custom auth headers, and Anthropic prompt caching. - **2026-02-17** πŸŽ‰ Released **v0.1.4** β€” MCP support, progress streaming, new providers, and multiple channel improvements. Please see [release notes](https://github.com/HKUDS/nanobot/releases/tag/v0.1.4) for details. - **2026-02-16** 🦞 nanobot now integrates a [ClawHub](https://clawhub.ai) skill β€” search and install public agent skills. @@ -34,10 +42,6 @@ - **2026-02-13** πŸŽ‰ Released **v0.1.3.post7** β€” includes security hardening and multiple improvements. **Please upgrade to the latest version to address security issues**. See [release notes](https://github.com/HKUDS/nanobot/releases/tag/v0.1.3.post7) for more details. - **2026-02-12** 🧠 Redesigned memory system β€” Less code, more reliable. Join the [discussion](https://github.com/HKUDS/nanobot/discussions/566) about it! - **2026-02-11** ✨ Enhanced CLI experience and added MiniMax support! - -
-Earlier news - - **2026-02-10** πŸŽ‰ Released **v0.1.3.post6** with improvements! Check the updates [notes](https://github.com/HKUDS/nanobot/releases/tag/v0.1.3.post6) and our [roadmap](https://github.com/HKUDS/nanobot/discussions/431). - **2026-02-09** πŸ’¬ Added Slack, Email, and QQ support β€” nanobot now supports multiple chat platforms! - **2026-02-08** πŸ”§ Refactored Providersβ€”adding a new LLM provider now takes just 2 simple steps! Check [here](#providers). diff --git a/nanobot/__init__.py b/nanobot/__init__.py index bb9bfb6..4dba5f4 100644 --- a/nanobot/__init__.py +++ b/nanobot/__init__.py @@ -2,5 +2,5 @@ nanobot - A lightweight AI agent framework """ -__version__ = "0.1.4.post2" +__version__ = "0.1.4.post3" __logo__ = "🐈" diff --git a/nanobot/agent/context.py b/nanobot/agent/context.py index a39ee75..010b126 100644 --- a/nanobot/agent/context.py +++ b/nanobot/agent/context.py @@ -150,6 +150,7 @@ Reply directly with text for conversations. Only use the 'message' tool to send content: str | None, tool_calls: list[dict[str, Any]] | None = None, reasoning_content: str | None = None, + 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} @@ -157,5 +158,7 @@ Reply directly with text for conversations. Only use the 'message' tool to send msg["tool_calls"] = tool_calls if reasoning_content is not None: msg["reasoning_content"] = reasoning_content + if thinking_blocks: + msg["thinking_blocks"] = thinking_blocks messages.append(msg) return messages diff --git a/nanobot/agent/loop.py b/nanobot/agent/loop.py index d8e5cad..8da9fcb 100644 --- a/nanobot/agent/loop.py +++ b/nanobot/agent/loop.py @@ -56,6 +56,7 @@ class AgentLoop: temperature: float = 0.1, max_tokens: int = 4096, memory_window: int = 100, + reasoning_effort: str | None = None, brave_api_key: str | None = None, exec_config: ExecToolConfig | None = None, cron_service: CronService | None = None, @@ -74,6 +75,7 @@ class AgentLoop: self.temperature = temperature self.max_tokens = max_tokens self.memory_window = memory_window + self.reasoning_effort = reasoning_effort self.brave_api_key = brave_api_key self.exec_config = exec_config or ExecToolConfig() self.cron_service = cron_service @@ -89,6 +91,7 @@ class AgentLoop: model=self.model, temperature=self.temperature, max_tokens=self.max_tokens, + reasoning_effort=reasoning_effort, brave_api_key=brave_api_key, exec_config=self.exec_config, restrict_to_workspace=restrict_to_workspace, @@ -191,6 +194,7 @@ class AgentLoop: model=self.model, temperature=self.temperature, max_tokens=self.max_tokens, + reasoning_effort=self.reasoning_effort, ) if response.has_tool_calls: @@ -214,6 +218,7 @@ class AgentLoop: messages = self.context.add_assistant_message( messages, response.content, tool_call_dicts, reasoning_content=response.reasoning_content, + thinking_blocks=response.thinking_blocks, ) for tool_call in response.tool_calls: @@ -234,6 +239,7 @@ class AgentLoop: break messages = self.context.add_assistant_message( messages, clean, reasoning_content=response.reasoning_content, + thinking_blocks=response.thinking_blocks, ) final_content = clean break @@ -447,7 +453,7 @@ class AgentLoop: """Save new-turn messages into session, truncating large tool results.""" from datetime import datetime for m in messages[skip:]: - entry = {k: v for k, v in m.items() if k != "reasoning_content"} + 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 β€” they poison session context diff --git a/nanobot/agent/subagent.py b/nanobot/agent/subagent.py index 5aff25c..9b543dc 100644 --- a/nanobot/agent/subagent.py +++ b/nanobot/agent/subagent.py @@ -29,6 +29,7 @@ class SubagentManager: model: str | None = None, temperature: float = 0.7, max_tokens: int = 4096, + reasoning_effort: str | None = None, brave_api_key: str | None = None, exec_config: "ExecToolConfig | None" = None, restrict_to_workspace: bool = False, @@ -40,6 +41,7 @@ class SubagentManager: self.model = model or provider.get_default_model() self.temperature = temperature self.max_tokens = max_tokens + self.reasoning_effort = reasoning_effort self.brave_api_key = brave_api_key self.exec_config = exec_config or ExecToolConfig() self.restrict_to_workspace = restrict_to_workspace @@ -104,9 +106,8 @@ class SubagentManager: )) tools.register(WebSearchTool(api_key=self.brave_api_key)) tools.register(WebFetchTool()) - - # Build messages with subagent-specific prompt - system_prompt = self._build_subagent_prompt(task) + + system_prompt = self._build_subagent_prompt() messages: list[dict[str, Any]] = [ {"role": "system", "content": system_prompt}, {"role": "user", "content": task}, @@ -126,6 +127,7 @@ class SubagentManager: model=self.model, temperature=self.temperature, max_tokens=self.max_tokens, + reasoning_effort=self.reasoning_effort, ) if response.has_tool_calls: @@ -204,44 +206,29 @@ Summarize this naturally for the user. Keep it brief (1-2 sentences). Do not men await self.bus.publish_inbound(msg) logger.debug("Subagent [{}] announced result to {}:{}", task_id, origin['channel'], origin['chat_id']) - - def _build_subagent_prompt(self, task: str) -> str: + + def _build_subagent_prompt(self) -> str: """Build a focused system prompt for the subagent.""" - import time as _time - from datetime import datetime - now = datetime.now().strftime("%Y-%m-%d %H:%M (%A)") - tz = _time.strftime("%Z") or "UTC" + from nanobot.agent.context import ContextBuilder + from nanobot.agent.skills import SkillsLoader - return f"""# Subagent + time_ctx = ContextBuilder._build_runtime_context(None, None) + parts = [f"""# Subagent -## Current Time -{now} ({tz}) +{time_ctx} You are a subagent spawned by the main agent to complete a specific task. - -## Rules -1. Stay focused - complete only the assigned task, nothing else -2. Your final response will be reported back to the main agent -3. Do not initiate conversations or take on side tasks -4. Be concise but informative in your findings - -## What You Can Do -- Read and write files in the workspace -- Execute shell commands -- Search the web and fetch web pages -- Complete the task thoroughly - -## What You Cannot Do -- Send messages directly to users (no message tool available) -- Spawn other subagents -- Access the main agent's conversation history +Stay focused on the assigned task. Your final response will be reported back to the main agent. ## Workspace -Your workspace is at: {self.workspace} -Skills are available at: {self.workspace}/skills/ (read SKILL.md files as needed) +{self.workspace}"""] -When you have completed the task, provide a clear summary of your findings or actions.""" + skills_summary = SkillsLoader(self.workspace).build_skills_summary() + if skills_summary: + parts.append(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 = [self._running_tasks[tid] for tid in self._session_tasks.get(session_key, []) diff --git a/nanobot/channels/dingtalk.py b/nanobot/channels/dingtalk.py index 371c45b..8d02fa6 100644 --- a/nanobot/channels/dingtalk.py +++ b/nanobot/channels/dingtalk.py @@ -2,8 +2,12 @@ import asyncio import json +import mimetypes +import os import time +from pathlib import Path from typing import Any +from urllib.parse import unquote, urlparse import httpx from loguru import logger @@ -96,6 +100,9 @@ class DingTalkChannel(BaseChannel): """ 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"} def __init__(self, config: DingTalkConfig, bus: MessageBus): super().__init__(config, bus) @@ -191,40 +198,224 @@ class DingTalkChannel(BaseChannel): logger.error("Failed to get DingTalk access token: {}", e) return None + @staticmethod + def _is_http_url(value: str) -> bool: + return urlparse(value).scheme in ("http", "https") + + def _guess_upload_type(self, media_ref: str) -> str: + ext = Path(urlparse(media_ref).path).suffix.lower() + if ext in self._IMAGE_EXTS: return "image" + if ext in self._AUDIO_EXTS: return "voice" + if ext in self._VIDEO_EXTS: return "video" + return "file" + + def _guess_filename(self, media_ref: str, upload_type: str) -> str: + name = os.path.basename(urlparse(media_ref).path) + return name or {"image": "image.jpg", "voice": "audio.amr", "video": "video.mp4"}.get(upload_type, "file.bin") + + async def _read_media_bytes( + self, + media_ref: str, + ) -> tuple[bytes | None, str | None, str | None]: + if not media_ref: + return None, None, None + + if self._is_http_url(media_ref): + if not self._http: + return None, None, None + try: + resp = await self._http.get(media_ref, follow_redirects=True) + if resp.status_code >= 400: + logger.warning( + "DingTalk media download failed status={} ref={}", + resp.status_code, + media_ref, + ) + return None, None, None + content_type = (resp.headers.get("content-type") or "").split(";")[0].strip() + filename = self._guess_filename(media_ref, self._guess_upload_type(media_ref)) + return resp.content, filename, content_type or None + except Exception as e: + logger.error("DingTalk media download error ref={} err={}", media_ref, e) + return None, None, None + + try: + if media_ref.startswith("file://"): + parsed = urlparse(media_ref) + local_path = Path(unquote(parsed.path)) + else: + local_path = Path(os.path.expanduser(media_ref)) + if not local_path.is_file(): + logger.warning("DingTalk media file not found: {}", local_path) + return None, None, None + data = await asyncio.to_thread(local_path.read_bytes) + content_type = mimetypes.guess_type(local_path.name)[0] + return data, local_path.name, content_type + except Exception as e: + logger.error("DingTalk media read error ref={} err={}", media_ref, e) + return None, None, None + + async def _upload_media( + self, + token: str, + data: bytes, + media_type: str, + filename: str, + content_type: str | None, + ) -> str | None: + if not self._http: + return None + url = f"https://oapi.dingtalk.com/media/upload?access_token={token}&type={media_type}" + mime = content_type or mimetypes.guess_type(filename)[0] or "application/octet-stream" + files = {"media": (filename, data, mime)} + + try: + resp = await self._http.post(url, files=files) + text = resp.text + result = resp.json() if resp.headers.get("content-type", "").startswith("application/json") else {} + if resp.status_code >= 400: + logger.error("DingTalk media upload failed status={} type={} body={}", resp.status_code, media_type, text[:500]) + return None + errcode = result.get("errcode", 0) + if errcode != 0: + logger.error("DingTalk media upload api error type={} errcode={} body={}", media_type, errcode, text[:500]) + return None + sub = result.get("result") or {} + media_id = result.get("media_id") or result.get("mediaId") or sub.get("media_id") or sub.get("mediaId") + if not media_id: + logger.error("DingTalk media upload missing media_id body={}", text[:500]) + return None + return str(media_id) + except Exception as e: + logger.error("DingTalk media upload error type={} err={}", media_type, e) + return None + + async def _send_batch_message( + self, + token: str, + chat_id: str, + msg_key: str, + msg_param: dict[str, Any], + ) -> bool: + if not self._http: + logger.warning("DingTalk HTTP client not initialized, cannot send") + return False + + url = "https://api.dingtalk.com/v1.0/robot/oToMessages/batchSend" + headers = {"x-acs-dingtalk-access-token": token} + payload = { + "robotCode": self.config.client_id, + "userIds": [chat_id], + "msgKey": msg_key, + "msgParam": json.dumps(msg_param, ensure_ascii=False), + } + + try: + resp = await self._http.post(url, json=payload, headers=headers) + body = resp.text + if resp.status_code != 200: + logger.error("DingTalk send failed msgKey={} status={} body={}", msg_key, resp.status_code, body[:500]) + return False + try: result = resp.json() + except Exception: result = {} + errcode = result.get("errcode") + if errcode not in (None, 0): + logger.error("DingTalk send api error msgKey={} errcode={} body={}", msg_key, errcode, body[:500]) + return False + logger.debug("DingTalk message sent to {} with msgKey={}", chat_id, msg_key) + return True + except Exception as e: + logger.error("Error sending DingTalk message msgKey={} err={}", msg_key, e) + return False + + async def _send_markdown_text(self, token: str, chat_id: str, content: str) -> bool: + return await self._send_batch_message( + token, + chat_id, + "sampleMarkdown", + {"text": content, "title": "Nanobot Reply"}, + ) + + async def _send_media_ref(self, token: str, chat_id: str, media_ref: str) -> bool: + media_ref = (media_ref or "").strip() + if not media_ref: + return True + + upload_type = self._guess_upload_type(media_ref) + if upload_type == "image" and self._is_http_url(media_ref): + ok = await self._send_batch_message( + token, + chat_id, + "sampleImageMsg", + {"photoURL": media_ref}, + ) + if ok: + return True + logger.warning("DingTalk image url send failed, trying upload fallback: {}", media_ref) + + data, filename, content_type = await self._read_media_bytes(media_ref) + if not data: + logger.error("DingTalk media read failed: {}", media_ref) + return False + + filename = filename or self._guess_filename(media_ref, upload_type) + file_type = Path(filename).suffix.lower().lstrip(".") + if not file_type: + guessed = mimetypes.guess_extension(content_type or "") + file_type = (guessed or ".bin").lstrip(".") + if file_type == "jpeg": + file_type = "jpg" + + media_id = await self._upload_media( + token=token, + data=data, + media_type=upload_type, + filename=filename, + content_type=content_type, + ) + if not media_id: + return False + + if upload_type == "image": + # Verified in production: sampleImageMsg accepts media_id in photoURL. + ok = await self._send_batch_message( + token, + chat_id, + "sampleImageMsg", + {"photoURL": media_id}, + ) + if ok: + return True + logger.warning("DingTalk image media_id send failed, falling back to file: {}", media_ref) + + return await self._send_batch_message( + token, + chat_id, + "sampleFile", + {"mediaId": media_id, "fileName": filename, "fileType": file_type}, + ) + async def send(self, msg: OutboundMessage) -> None: """Send a message through DingTalk.""" token = await self._get_access_token() if not token: return - # oToMessages/batchSend: sends to individual users (private chat) - # https://open.dingtalk.com/document/orgapp/robot-batch-send-messages - url = "https://api.dingtalk.com/v1.0/robot/oToMessages/batchSend" + if msg.content and msg.content.strip(): + await self._send_markdown_text(token, msg.chat_id, msg.content.strip()) - headers = {"x-acs-dingtalk-access-token": token} - - data = { - "robotCode": self.config.client_id, - "userIds": [msg.chat_id], # chat_id is the user's staffId - "msgKey": "sampleMarkdown", - "msgParam": json.dumps({ - "text": msg.content, - "title": "Nanobot Reply", - }, ensure_ascii=False), - } - - if not self._http: - logger.warning("DingTalk HTTP client not initialized, cannot send") - return - - try: - resp = await self._http.post(url, json=data, headers=headers) - if resp.status_code != 200: - logger.error("DingTalk send failed: {}", resp.text) - else: - logger.debug("DingTalk message sent to {}", msg.chat_id) - except Exception as e: - logger.error("Error sending DingTalk message: {}", e) + for media_ref in msg.media or []: + ok = await self._send_media_ref(token, msg.chat_id, media_ref) + if ok: + continue + logger.error("DingTalk media send failed for {}", media_ref) + # Send visible fallback so failures are observable by the user. + filename = self._guess_filename(media_ref, self._guess_upload_type(media_ref)) + await self._send_markdown_text( + token, + msg.chat_id, + f"[Attachment send failed: {filename}]", + ) async def _on_message(self, content: str, sender_id: str, sender_name: str) -> None: """Handle incoming message (called by NanobotDingTalkHandler). diff --git a/nanobot/channels/feishu.py b/nanobot/channels/feishu.py index 9911d08..5a86e73 100644 --- a/nanobot/channels/feishu.py +++ b/nanobot/channels/feishu.py @@ -326,13 +326,14 @@ class FeishuChannel(BaseChannel): await asyncio.sleep(1) async def stop(self) -> None: - """Stop the Feishu bot.""" + """ + Stop the Feishu bot. + + Notice: lark.ws.Client does not expose stop method， simply exiting the program will close the client. + + Reference: https://github.com/larksuite/oapi-sdk-python/blob/v2_main/lark_oapi/ws/client.py#L86 + """ self._running = False - if self._ws_client: - try: - self._ws_client.stop() - except Exception as e: - logger.warning("Error stopping WebSocket client: {}", e) logger.info("Feishu bot stopped") def _add_reaction_sync(self, message_id: str, emoji_type: str) -> None: diff --git a/nanobot/channels/qq.py b/nanobot/channels/qq.py index 50dbbde..7b171bc 100644 --- a/nanobot/channels/qq.py +++ b/nanobot/channels/qq.py @@ -31,7 +31,8 @@ def _make_bot_class(channel: "QQChannel") -> "type[botpy.Client]": class _Bot(botpy.Client): def __init__(self): - super().__init__(intents=intents) + # Disable botpy's file log β€” nanobot uses loguru; default "botpy.log" fails on read-only fs + super().__init__(intents=intents, ext_handlers=False) async def on_ready(self): logger.info("QQ bot ready: {}", self.robot.name) diff --git a/nanobot/cli/commands.py b/nanobot/cli/commands.py index 15bee4c..4987c84 100644 --- a/nanobot/cli/commands.py +++ b/nanobot/cli/commands.py @@ -282,6 +282,7 @@ def gateway( max_tokens=config.agents.defaults.max_tokens, max_iterations=config.agents.defaults.max_tool_iterations, memory_window=config.agents.defaults.memory_window, + reasoning_effort=config.agents.defaults.reasoning_effort, brave_api_key=config.tools.web.search.api_key or None, exec_config=config.tools.exec, cron_service=cron, @@ -441,6 +442,7 @@ def agent( max_tokens=config.agents.defaults.max_tokens, max_iterations=config.agents.defaults.max_tool_iterations, memory_window=config.agents.defaults.memory_window, + reasoning_effort=config.agents.defaults.reasoning_effort, brave_api_key=config.tools.web.search.api_key or None, exec_config=config.tools.exec, cron_service=cron, @@ -934,6 +936,7 @@ def cron_run( max_tokens=config.agents.defaults.max_tokens, max_iterations=config.agents.defaults.max_tool_iterations, memory_window=config.agents.defaults.memory_window, + reasoning_effort=config.agents.defaults.reasoning_effort, brave_api_key=config.tools.web.search.api_key or None, exec_config=config.tools.exec, restrict_to_workspace=config.tools.restrict_to_workspace, diff --git a/nanobot/config/schema.py b/nanobot/config/schema.py index a908f3d..091a210 100644 --- a/nanobot/config/schema.py +++ b/nanobot/config/schema.py @@ -226,6 +226,7 @@ class AgentDefaults(Base): temperature: float = 0.1 max_tool_iterations: int = 40 memory_window: int = 100 + reasoning_effort: str | None = None # low / medium / high β€” enables LLM thinking mode class AgentsConfig(Base): diff --git a/nanobot/providers/base.py b/nanobot/providers/base.py index a46e68f..af23a4c 100644 --- a/nanobot/providers/base.py +++ b/nanobot/providers/base.py @@ -21,7 +21,8 @@ class LLMResponse: finish_reason: str = "stop" usage: dict[str, int] = field(default_factory=dict) reasoning_content: str | None = None # Kimi, DeepSeek-R1 etc. - + thinking_blocks: list[dict] | None = None # Anthropic extended thinking + @property def has_tool_calls(self) -> bool: """Check if response contains tool calls.""" @@ -88,6 +89,7 @@ class LLMProvider(ABC): model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7, + reasoning_effort: str | None = None, ) -> LLMResponse: """ Send a chat completion request. diff --git a/nanobot/providers/custom_provider.py b/nanobot/providers/custom_provider.py index a578d14..56e6270 100644 --- a/nanobot/providers/custom_provider.py +++ b/nanobot/providers/custom_provider.py @@ -18,13 +18,16 @@ class CustomProvider(LLMProvider): self._client = AsyncOpenAI(api_key=api_key, base_url=api_base) 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) -> LLMResponse: + model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7, + reasoning_effort: str | None = None) -> LLMResponse: kwargs: dict[str, Any] = { "model": model or self.default_model, "messages": self._sanitize_empty_content(messages), "max_tokens": max(1, max_tokens), "temperature": temperature, } + if reasoning_effort: + kwargs["reasoning_effort"] = reasoning_effort if tools: kwargs.update(tools=tools, tool_choice="auto") try: diff --git a/nanobot/providers/litellm_provider.py b/nanobot/providers/litellm_provider.py index 931e038..79277bc 100644 --- a/nanobot/providers/litellm_provider.py +++ b/nanobot/providers/litellm_provider.py @@ -14,7 +14,7 @@ from nanobot.providers.registry import find_by_model, find_gateway # Standard OpenAI chat-completion message keys plus reasoning_content for # thinking-enabled models (Kimi k2.5, DeepSeek-R1, etc.). -_ALLOWED_MSG_KEYS = frozenset({"role", "content", "tool_calls", "tool_call_id", "name", "reasoning_content"}) +_ALLOWED_MSG_KEYS = frozenset({"role", "content", "tool_calls", "tool_call_id", "name", "reasoning_content", "thinking_blocks"}) _ALNUM = string.ascii_letters + string.digits def _short_tool_id() -> str: @@ -176,6 +176,7 @@ class LiteLLMProvider(LLMProvider): model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7, + reasoning_effort: str | None = None, ) -> LLMResponse: """ Send a chat completion request via LiteLLM. @@ -221,7 +222,11 @@ class LiteLLMProvider(LLMProvider): # Pass extra headers (e.g. APP-Code for AiHubMix) if self.extra_headers: kwargs["extra_headers"] = self.extra_headers - + + if reasoning_effort: + kwargs["reasoning_effort"] = reasoning_effort + kwargs["drop_params"] = True + if tools: kwargs["tools"] = tools kwargs["tool_choice"] = "auto" @@ -264,13 +269,15 @@ class LiteLLMProvider(LLMProvider): } reasoning_content = getattr(message, "reasoning_content", None) or None - + thinking_blocks = getattr(message, "thinking_blocks", None) or None + return LLMResponse( content=message.content, tool_calls=tool_calls, finish_reason=choice.finish_reason or "stop", usage=usage, reasoning_content=reasoning_content, + thinking_blocks=thinking_blocks, ) def get_default_model(self) -> str: diff --git a/nanobot/providers/openai_codex_provider.py b/nanobot/providers/openai_codex_provider.py index 1e4dd8a..b6afa65 100644 --- a/nanobot/providers/openai_codex_provider.py +++ b/nanobot/providers/openai_codex_provider.py @@ -31,6 +31,7 @@ class OpenAICodexProvider(LLMProvider): model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7, + reasoning_effort: str | None = None, ) -> LLMResponse: model = model or self.default_model system_prompt, input_items = _convert_messages(messages) diff --git a/pyproject.toml b/pyproject.toml index 20dcb1e..a22053c 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "nanobot-ai" -version = "0.1.4.post2" +version = "0.1.4.post3" description = "A lightweight personal AI assistant framework" requires-python = ">=3.11" license = {text = "MIT"}