From e9d023f52cbc7fb8eab37ab5aa4a501b0b5bdc81 Mon Sep 17 00:00:00 2001 From: Joel Chan Date: Thu, 12 Feb 2026 17:10:50 +0800 Subject: [PATCH 01/17] feat(discord): add group policy to control group respond behaviour --- README.md | 8 +++++++- nanobot/channels/discord.py | 36 +++++++++++++++++++++++++++++++++++- nanobot/config/schema.py | 1 + 3 files changed, 43 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 45779e7..f141a1c 100644 --- a/README.md +++ b/README.md @@ -293,12 +293,18 @@ If you prefer to configure manually, add the following to `~/.nanobot/config.jso "discord": { "enabled": true, "token": "YOUR_BOT_TOKEN", - "allowFrom": ["YOUR_USER_ID"] + "allowFrom": ["YOUR_USER_ID"], + "groupPolicy": "mention" } } } ``` +> `groupPolicy` controls how the bot responds in group channels: +> - `"mention"` (default) — Only respond when @mentioned +> - `"open"` — Respond to all messages +> DMs always respond when the sender is in `allowFrom`. + **5. Invite the bot** - OAuth2 → URL Generator - Scopes: `bot` diff --git a/nanobot/channels/discord.py b/nanobot/channels/discord.py index 57e5922..85ff28a 100644 --- a/nanobot/channels/discord.py +++ b/nanobot/channels/discord.py @@ -54,6 +54,7 @@ class DiscordChannel(BaseChannel): self._heartbeat_task: asyncio.Task | None = None self._typing_tasks: dict[str, asyncio.Task] = {} self._http: httpx.AsyncClient | None = None + self._bot_user_id: str | None = None async def start(self) -> None: """Start the Discord gateway connection.""" @@ -170,6 +171,10 @@ class DiscordChannel(BaseChannel): await self._identify() elif op == 0 and event_type == "READY": logger.info("Discord gateway READY") + # Capture bot user ID for mention detection + user_data = payload.get("user") or {} + self._bot_user_id = user_data.get("id") + logger.info(f"Discord bot connected as user {self._bot_user_id}") elif op == 0 and event_type == "MESSAGE_CREATE": await self._handle_message_create(payload) elif op == 7: @@ -226,6 +231,7 @@ class DiscordChannel(BaseChannel): sender_id = str(author.get("id", "")) channel_id = str(payload.get("channel_id", "")) content = payload.get("content") or "" + guild_id = payload.get("guild_id") if not sender_id or not channel_id: return @@ -233,6 +239,11 @@ class DiscordChannel(BaseChannel): if not self.is_allowed(sender_id): return + # Check group channel policy (DMs always respond if is_allowed passes) + if guild_id is not None: + if not self._should_respond_in_group(payload, content): + return + content_parts = [content] if content else [] media_paths: list[str] = [] media_dir = Path.home() / ".nanobot" / "media" @@ -269,11 +280,34 @@ class DiscordChannel(BaseChannel): media=media_paths, metadata={ "message_id": str(payload.get("id", "")), - "guild_id": payload.get("guild_id"), + "guild_id": guild_id, "reply_to": reply_to, }, ) + def _should_respond_in_group(self, payload: dict[str, Any], content: str) -> bool: + """Check if bot should respond in a group channel based on policy.""" + channel_id = str(payload.get("channel_id", "")) + + if self.config.group_policy == "open": + return True + + if self.config.group_policy == "mention": + # Check if bot was mentioned in the message + if self._bot_user_id: + # Check mentions array + mentions = payload.get("mentions") or [] + for mention in mentions: + if str(mention.get("id")) == self._bot_user_id: + return True + # Also check content for mention format <@USER_ID> + if f"<@{self._bot_user_id}>" in content or f"<@!{self._bot_user_id}>" in content: + return True + logger.debug(f"Discord message in {channel_id} ignored (bot not mentioned)") + return False + + return True + async def _start_typing(self, channel_id: str) -> None: """Start periodic typing indicator for a channel.""" await self._stop_typing(channel_id) diff --git a/nanobot/config/schema.py b/nanobot/config/schema.py index 6b80c81..e3d3d23 100644 --- a/nanobot/config/schema.py +++ b/nanobot/config/schema.py @@ -62,6 +62,7 @@ class DiscordConfig(Base): allow_from: list[str] = Field(default_factory=list) # Allowed user IDs gateway_url: str = "wss://gateway.discord.gg/?v=10&encoding=json" intents: int = 37377 # GUILDS + GUILD_MESSAGES + DIRECT_MESSAGES + MESSAGE_CONTENT + group_policy: str = "open" # "mention" or "open" class MatrixConfig(Base): From ecdfaf0a5a00b0772719aa306d4cb36d8512f9c7 Mon Sep 17 00:00:00 2001 From: David Markey Date: Sun, 1 Mar 2026 20:49:00 +0000 Subject: [PATCH 02/17] feat(custom-provider): add x-session-affinity header for prompt caching --- nanobot/providers/custom_provider.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/nanobot/providers/custom_provider.py b/nanobot/providers/custom_provider.py index 56e6270..02183f3 100644 --- a/nanobot/providers/custom_provider.py +++ b/nanobot/providers/custom_provider.py @@ -2,6 +2,7 @@ from __future__ import annotations +import uuid from typing import Any import json_repair @@ -15,7 +16,11 @@ class CustomProvider(LLMProvider): def __init__(self, api_key: str = "no-key", api_base: str = "http://localhost:8000/v1", default_model: str = "default"): super().__init__(api_key, api_base) self.default_model = default_model - self._client = AsyncOpenAI(api_key=api_key, base_url=api_base) + self._client = AsyncOpenAI( + api_key=api_key, + base_url=api_base, + default_headers={"x-session-affinity": uuid.uuid4().hex}, + ) 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, From d0a48ed23c7eb578702f9dd5e7d4dc009d022efa Mon Sep 17 00:00:00 2001 From: Liwx Date: Wed, 4 Mar 2026 14:00:40 +0800 Subject: [PATCH 03/17] Update qq.py --- nanobot/channels/qq.py | 1 + 1 file changed, 1 insertion(+) diff --git a/nanobot/channels/qq.py b/nanobot/channels/qq.py index 7b171bc..99a712b 100644 --- a/nanobot/channels/qq.py +++ b/nanobot/channels/qq.py @@ -56,6 +56,7 @@ class QQChannel(BaseChannel): self.config: QQConfig = config self._client: "botpy.Client | None" = None self._processed_ids: deque = deque(maxlen=1000) + self._msg_seq: int = 1 # Message sequence to avoid QQ API deduplication async def start(self) -> None: """Start the QQ bot.""" From 20bec3bc266ef84399d3170cef6b4b5de8627f67 Mon Sep 17 00:00:00 2001 From: Liwx Date: Wed, 4 Mar 2026 14:06:19 +0800 Subject: [PATCH 04/17] Update qq.py --- nanobot/channels/qq.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/nanobot/channels/qq.py b/nanobot/channels/qq.py index 99a712b..6c58049 100644 --- a/nanobot/channels/qq.py +++ b/nanobot/channels/qq.py @@ -56,7 +56,7 @@ class QQChannel(BaseChannel): self.config: QQConfig = config self._client: "botpy.Client | None" = None self._processed_ids: deque = deque(maxlen=1000) - self._msg_seq: int = 1 # Message sequence to avoid QQ API deduplication + self._msg_seq: int = 1 # 消息序列号，避免被 QQ API 去重 async def start(self) -> None: """Start the QQ bot.""" @@ -103,11 +103,13 @@ class QQChannel(BaseChannel): return try: msg_id = msg.metadata.get("message_id") + self._msg_seq += 1 # 递增序列号 await self._client.api.post_c2c_message( openid=msg.chat_id, msg_type=0, content=msg.content, msg_id=msg_id, + msg_seq=self._msg_seq, # 添加序列号避免去重 ) except Exception as e: logger.error("Error sending QQ message: {}", e) @@ -134,3 +136,4 @@ class QQChannel(BaseChannel): ) except Exception: logger.exception("Error handling QQ message") + From df8d09f2b6c0eb23298e41acbe139fad9d38f325 Mon Sep 17 00:00:00 2001 From: Kiplangatkorir Date: Wed, 4 Mar 2026 10:53:30 +0300 Subject: [PATCH 05/17] fix: guard validate_params against non-dict input When the LLM returns malformed tool arguments (e.g. a list or string instead of a dict), validate_params would crash with AttributeError in _validate() when calling val.items(). Now returns a clear validation error instead of crashing. --- nanobot/agent/tools/base.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/nanobot/agent/tools/base.py b/nanobot/agent/tools/base.py index 8dd82c7..051fc9a 100644 --- a/nanobot/agent/tools/base.py +++ b/nanobot/agent/tools/base.py @@ -54,6 +54,8 @@ class Tool(ABC): def validate_params(self, params: dict[str, Any]) -> list[str]: """Validate tool parameters against JSON schema. Returns error list (empty if valid).""" + if not isinstance(params, dict): + return [f"parameters must be an object, got {type(params).__name__}"] schema = self.parameters or {} if schema.get("type", "object") != "object": raise ValueError(f"Schema must be object type, got {schema.get('type')!r}") From edaf7a244a0d65395cab954fc768dc8031489b29 Mon Sep 17 00:00:00 2001 From: Kiplangatkorir Date: Wed, 4 Mar 2026 10:55:17 +0300 Subject: [PATCH 06/17] fix: handle invalid ISO datetime in CronTool gracefully datetime.fromisoformat(at) raises ValueError for malformed strings, which propagated uncaught and crashed the tool execution. Now catches ValueError and returns a user-friendly error message instead. --- nanobot/agent/tools/cron.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/nanobot/agent/tools/cron.py b/nanobot/agent/tools/cron.py index 13b1e12..f8e737b 100644 --- a/nanobot/agent/tools/cron.py +++ b/nanobot/agent/tools/cron.py @@ -122,7 +122,10 @@ class CronTool(Tool): elif at: from datetime import datetime - dt = datetime.fromisoformat(at) + try: + dt = datetime.fromisoformat(at) + except ValueError: + return f"Error: invalid ISO datetime format '{at}'. Expected format: YYYY-MM-DDTHH:MM:SS" at_ms = int(dt.timestamp() * 1000) schedule = CronSchedule(kind="at", at_ms=at_ms) delete_after = True From ce65f8c11be13b51f242890cabdf15f4e0d1b12a Mon Sep 17 00:00:00 2001 From: Kiplangatkorir Date: Wed, 4 Mar 2026 11:15:45 +0300 Subject: [PATCH 07/17] fix: add size limit to ReadFileTool to prevent OOM MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ReadFileTool had no file size check — reading a multi-GB file would load everything into memory and crash the process. Now: - Rejects files over ~512KB at the byte level (fast stat check) - Truncates at 128K chars with a notice if content is too long - Guides the agent to use exec with head/tail/grep for large files This matches the protection already in ExecTool (10KB) and WebFetchTool (50KB). --- nanobot/agent/tools/filesystem.py | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/nanobot/agent/tools/filesystem.py b/nanobot/agent/tools/filesystem.py index bbdd49c..7b0b867 100644 --- a/nanobot/agent/tools/filesystem.py +++ b/nanobot/agent/tools/filesystem.py @@ -26,6 +26,8 @@ def _resolve_path( class ReadFileTool(Tool): """Tool to read file contents.""" + _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 @@ -54,7 +56,16 @@ class ReadFileTool(Tool): if not file_path.is_file(): return f"Error: Not a file: {path}" + size = file_path.stat().st_size + if size > self._MAX_CHARS * 4: # rough upper bound (UTF-8 chars ≤ 4 bytes) + 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 len(content) > self._MAX_CHARS: + return content[: self._MAX_CHARS] + f"\n\n... (truncated — file is {len(content):,} chars, limit {self._MAX_CHARS:,})" return content except PermissionError as e: return f"Error: {e}" From bb8512ca842fc3b14c6dee01c5aaf9e241f8344e Mon Sep 17 00:00:00 2001 From: chengyongru <2755839590@qq.com> Date: Wed, 4 Mar 2026 20:42:49 +0800 Subject: [PATCH 08/17] test: fix test failures from refactored cron and context builder - test_context_prompt_cache: Update test to reflect merged runtime context and user message (commit ad99d5a merged them into one) - Remove test_cron_commands.py: cron add CLI command was removed in commit c05cb2e (unified scheduling via cron tool) --- tests/test_context_prompt_cache.py | 19 +++++++++---------- tests/test_cron_commands.py | 29 ----------------------------- 2 files changed, 9 insertions(+), 39 deletions(-) delete mode 100644 tests/test_cron_commands.py diff --git a/tests/test_context_prompt_cache.py b/tests/test_context_prompt_cache.py index 9afcc7d..ce796e2 100644 --- a/tests/test_context_prompt_cache.py +++ b/tests/test_context_prompt_cache.py @@ -40,7 +40,7 @@ def test_system_prompt_stays_stable_when_clock_changes(tmp_path, monkeypatch) -> def test_runtime_context_is_separate_untrusted_user_message(tmp_path) -> None: - """Runtime metadata should be a separate user message before the actual user message.""" + """Runtime metadata should be merged with the user message.""" workspace = _make_workspace(tmp_path) builder = ContextBuilder(workspace) @@ -54,13 +54,12 @@ def test_runtime_context_is_separate_untrusted_user_message(tmp_path) -> None: assert messages[0]["role"] == "system" assert "## Current Session" not in messages[0]["content"] - assert messages[-2]["role"] == "user" - runtime_content = messages[-2]["content"] - assert isinstance(runtime_content, str) - assert ContextBuilder._RUNTIME_CONTEXT_TAG in runtime_content - assert "Current Time:" in runtime_content - assert "Channel: cli" in runtime_content - assert "Chat ID: direct" in runtime_content - + # Runtime context is now merged with user message into a single message assert messages[-1]["role"] == "user" - assert messages[-1]["content"] == "Return exactly: OK" + user_content = messages[-1]["content"] + assert isinstance(user_content, str) + assert ContextBuilder._RUNTIME_CONTEXT_TAG in user_content + assert "Current Time:" in user_content + assert "Channel: cli" in user_content + assert "Chat ID: direct" in user_content + assert "Return exactly: OK" in user_content diff --git a/tests/test_cron_commands.py b/tests/test_cron_commands.py deleted file mode 100644 index bce1ef5..0000000 --- a/tests/test_cron_commands.py +++ /dev/null @@ -1,29 +0,0 @@ -from typer.testing import CliRunner - -from nanobot.cli.commands import app - -runner = CliRunner() - - -def test_cron_add_rejects_invalid_timezone(monkeypatch, tmp_path) -> None: - monkeypatch.setattr("nanobot.config.loader.get_data_dir", lambda: tmp_path) - - result = runner.invoke( - app, - [ - "cron", - "add", - "--name", - "demo", - "--message", - "hello", - "--cron", - "0 9 * * *", - "--tz", - "America/Vancovuer", - ], - ) - - assert result.exit_code == 1 - assert "Error: unknown timezone 'America/Vancovuer'" in result.stdout - assert not (tmp_path / "cron" / "jobs.json").exists() From ecdf30940459a27311855a97cfdb7599cb3f89a2 Mon Sep 17 00:00:00 2001 From: Daniel Emden Date: Wed, 4 Mar 2026 15:31:56 +0100 Subject: [PATCH 09/17] fix(codex): pass reasoning_effort to Codex API The OpenAI Codex provider accepts reasoning_effort but silently discards it. Wire it through as {"reasoning": {"effort": ...}} in the request body so the config option actually takes effect. --- nanobot/providers/openai_codex_provider.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/nanobot/providers/openai_codex_provider.py b/nanobot/providers/openai_codex_provider.py index b6afa65..d04e210 100644 --- a/nanobot/providers/openai_codex_provider.py +++ b/nanobot/providers/openai_codex_provider.py @@ -52,6 +52,9 @@ class OpenAICodexProvider(LLMProvider): "parallel_tool_calls": True, } + if reasoning_effort: + body["reasoning"] = {"effort": reasoning_effort} + if tools: body["tools"] = _convert_tools(tools) From c64fe0afd8cfcbfe0c26569140db33b473f87854 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergio=20S=C3=A1nchez=20Vall=C3=A9s?= Date: Wed, 4 Mar 2026 16:53:07 +0100 Subject: [PATCH 10/17] fix(tests): resolve failing tests on main branch - Unskip matrix logic by adding missing deps (matrix-nio, nh3, mistune) - Update matrix tests for 'allow_from' default deny security change - Fix asyncio typing keepalive leak in matrix tests - Update context prompt cache assert after runtime message merge - Fix flaky cron service test with mtime sleep - Remove obsolete test_cron_commands.py testing deleted CLI commands --- pyproject.toml | 3 +++ tests/test_context_prompt_cache.py | 9 ++++----- tests/test_cron_commands.py | 29 ----------------------------- tests/test_cron_service.py | 2 ++ tests/test_matrix_channel.py | 20 ++++++++++++++++++-- 5 files changed, 27 insertions(+), 36 deletions(-) delete mode 100644 tests/test_cron_commands.py diff --git a/pyproject.toml b/pyproject.toml index a22053c..0546523 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -54,6 +54,9 @@ dev = [ "pytest>=9.0.0,<10.0.0", "pytest-asyncio>=1.3.0,<2.0.0", "ruff>=0.1.0", + "matrix-nio[e2e]>=0.25.2", + "mistune>=3.0.0,<4.0.0", + "nh3>=0.2.17,<1.0.0", ] [project.scripts] diff --git a/tests/test_context_prompt_cache.py b/tests/test_context_prompt_cache.py index 9afcc7d..38b8d35 100644 --- a/tests/test_context_prompt_cache.py +++ b/tests/test_context_prompt_cache.py @@ -54,13 +54,12 @@ def test_runtime_context_is_separate_untrusted_user_message(tmp_path) -> None: assert messages[0]["role"] == "system" assert "## Current Session" not in messages[0]["content"] - assert messages[-2]["role"] == "user" - runtime_content = messages[-2]["content"] + assert len(messages) == 2 + assert messages[-1]["role"] == "user" + runtime_content = messages[-1]["content"] assert isinstance(runtime_content, str) assert ContextBuilder._RUNTIME_CONTEXT_TAG in runtime_content assert "Current Time:" in runtime_content assert "Channel: cli" in runtime_content assert "Chat ID: direct" in runtime_content - - assert messages[-1]["role"] == "user" - assert messages[-1]["content"] == "Return exactly: OK" + assert "Return exactly: OK" in runtime_content diff --git a/tests/test_cron_commands.py b/tests/test_cron_commands.py deleted file mode 100644 index bce1ef5..0000000 --- a/tests/test_cron_commands.py +++ /dev/null @@ -1,29 +0,0 @@ -from typer.testing import CliRunner - -from nanobot.cli.commands import app - -runner = CliRunner() - - -def test_cron_add_rejects_invalid_timezone(monkeypatch, tmp_path) -> None: - monkeypatch.setattr("nanobot.config.loader.get_data_dir", lambda: tmp_path) - - result = runner.invoke( - app, - [ - "cron", - "add", - "--name", - "demo", - "--message", - "hello", - "--cron", - "0 9 * * *", - "--tz", - "America/Vancovuer", - ], - ) - - assert result.exit_code == 1 - assert "Error: unknown timezone 'America/Vancovuer'" in result.stdout - assert not (tmp_path / "cron" / "jobs.json").exists() diff --git a/tests/test_cron_service.py b/tests/test_cron_service.py index 2a36f4c..9631da5 100644 --- a/tests/test_cron_service.py +++ b/tests/test_cron_service.py @@ -48,6 +48,8 @@ async def test_running_service_honors_external_disable(tmp_path) -> None: ) await service.start() try: + # Wait slightly to ensure file mtime is definitively different + await asyncio.sleep(0.05) external = CronService(store_path) updated = external.enable_job(job.id, enabled=False) assert updated is not None diff --git a/tests/test_matrix_channel.py b/tests/test_matrix_channel.py index c6714c2..c25b95a 100644 --- a/tests/test_matrix_channel.py +++ b/tests/test_matrix_channel.py @@ -159,6 +159,7 @@ class _FakeAsyncClient: def _make_config(**kwargs) -> MatrixConfig: + kwargs.setdefault("allow_from", ["*"]) return MatrixConfig( enabled=True, homeserver="https://matrix.org", @@ -274,7 +275,7 @@ async def test_stop_stops_sync_forever_before_close(monkeypatch) -> None: @pytest.mark.asyncio -async def test_room_invite_joins_when_allow_list_is_empty() -> None: +async def test_room_invite_ignores_when_allow_list_is_empty() -> None: channel = MatrixChannel(_make_config(allow_from=[]), MessageBus()) client = _FakeAsyncClient("", "", "", None) channel.client = client @@ -284,9 +285,22 @@ async def test_room_invite_joins_when_allow_list_is_empty() -> None: await channel._on_room_invite(room, event) - assert client.join_calls == ["!room:matrix.org"] + assert client.join_calls == [] +@pytest.mark.asyncio +async def test_room_invite_joins_when_sender_allowed() -> None: + channel = MatrixChannel(_make_config(allow_from=["@alice:matrix.org"]), MessageBus()) + client = _FakeAsyncClient("", "", "", None) + channel.client = client + + room = SimpleNamespace(room_id="!room:matrix.org") + event = SimpleNamespace(sender="@alice:matrix.org") + + await channel._on_room_invite(room, event) + + assert client.join_calls == ["!room:matrix.org"] + @pytest.mark.asyncio async def test_room_invite_respects_allow_list_when_configured() -> None: channel = MatrixChannel(_make_config(allow_from=["@bob:matrix.org"]), MessageBus()) @@ -1163,6 +1177,8 @@ async def test_send_progress_keeps_typing_keepalive_running() -> None: assert "!room:matrix.org" in channel._typing_tasks assert client.typing_calls[-1] == ("!room:matrix.org", True, TYPING_NOTICE_TIMEOUT_MS) + await channel.stop() + @pytest.mark.asyncio async def test_send_clears_typing_when_send_fails() -> None: From 88d7642c1ec570e07eef473f47d1d637b38b9b07 Mon Sep 17 00:00:00 2001 From: chengyongru <2755839590@qq.com> Date: Wed, 4 Mar 2026 20:42:49 +0800 Subject: [PATCH 11/17] test: fix test failures from refactored cron and context builder - test_context_prompt_cache: Update test to reflect merged runtime context and user message (commit ad99d5a merged them into one) - Remove test_cron_commands.py: cron add CLI command was removed in commit c05cb2e (unified scheduling via cron tool) --- tests/test_context_prompt_cache.py | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/tests/test_context_prompt_cache.py b/tests/test_context_prompt_cache.py index 38b8d35..fa7f02d 100644 --- a/tests/test_context_prompt_cache.py +++ b/tests/test_context_prompt_cache.py @@ -40,7 +40,7 @@ def test_system_prompt_stays_stable_when_clock_changes(tmp_path, monkeypatch) -> def test_runtime_context_is_separate_untrusted_user_message(tmp_path) -> None: - """Runtime metadata should be a separate user message before the actual user message.""" + """Runtime metadata should be merged with the user message.""" workspace = _make_workspace(tmp_path) builder = ContextBuilder(workspace) @@ -55,11 +55,12 @@ def test_runtime_context_is_separate_untrusted_user_message(tmp_path) -> None: assert "## Current Session" not in messages[0]["content"] assert len(messages) == 2 + # Runtime context is now merged with user message into a single message assert messages[-1]["role"] == "user" - runtime_content = messages[-1]["content"] - assert isinstance(runtime_content, str) - assert ContextBuilder._RUNTIME_CONTEXT_TAG in runtime_content - assert "Current Time:" in runtime_content - assert "Channel: cli" in runtime_content - assert "Chat ID: direct" in runtime_content - assert "Return exactly: OK" in runtime_content + user_content = messages[-1]["content"] + assert isinstance(user_content, str) + assert ContextBuilder._RUNTIME_CONTEXT_TAG in user_content + assert "Current Time:" in user_content + assert "Channel: cli" in user_content + assert "Chat ID: direct" in user_content + assert "Return exactly: OK" in user_content From bdfe7d6449dab772f681b857ad76796c92b63d05 Mon Sep 17 00:00:00 2001 From: Ben Date: Thu, 5 Mar 2026 00:16:31 +0800 Subject: [PATCH 12/17] fix(feishu): convert audio type to file for API compatibility Feishu's GetMessageResource API only accepts 'image' or 'file' as the type parameter. When downloading voice messages, nanobot was passing 'audio' which caused the API to reject the request with an error. This fix converts 'audio' to 'file' in _download_file_sync method before making the API call, allowing voice messages to be downloaded and transcribed successfully. Fixes voice message download failure in Feishu channel. --- nanobot/channels/feishu.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/nanobot/channels/feishu.py b/nanobot/channels/feishu.py index 0a0a5e4..a9a32b2 100644 --- a/nanobot/channels/feishu.py +++ b/nanobot/channels/feishu.py @@ -530,6 +530,10 @@ class FeishuChannel(BaseChannel): self, message_id: str, file_key: str, resource_type: str = "file" ) -> tuple[bytes | None, str | None]: """Download a file/audio/media from a Feishu message by message_id and file_key.""" + # Feishu API only accepts 'image' or 'file' as type parameter + # Convert 'audio' to 'file' for API compatibility + if resource_type == "audio": + resource_type = "file" try: request = ( GetMessageResourceRequest.builder() From 0209ad57d9655d8fea5f5e551a4bb89bd0f1691c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergio=20S=C3=A1nchez=20Vall=C3=A9s?= Date: Wed, 4 Mar 2026 19:31:39 +0100 Subject: [PATCH 13/17] fix(tests): resolve RequestsDependencyWarning and lark-oapi asyncio/websockets DeprecationWarnings --- nanobot/channels/feishu.py | 32 +++++++++++--------------------- pyproject.toml | 1 + 2 files changed, 12 insertions(+), 21 deletions(-) diff --git a/nanobot/channels/feishu.py b/nanobot/channels/feishu.py index 0a0a5e4..7d26fa8 100644 --- a/nanobot/channels/feishu.py +++ b/nanobot/channels/feishu.py @@ -16,26 +16,9 @@ from nanobot.bus.queue import MessageBus from nanobot.channels.base import BaseChannel from nanobot.config.schema import FeishuConfig -try: - import lark_oapi as lark - from lark_oapi.api.im.v1 import ( - CreateFileRequest, - CreateFileRequestBody, - CreateImageRequest, - CreateImageRequestBody, - CreateMessageReactionRequest, - CreateMessageReactionRequestBody, - CreateMessageRequest, - CreateMessageRequestBody, - Emoji, - GetMessageResourceRequest, - P2ImMessageReceiveV1, - ) - FEISHU_AVAILABLE = True -except ImportError: - FEISHU_AVAILABLE = False - lark = None - Emoji = None +import importlib.util + +FEISHU_AVAILABLE = importlib.util.find_spec("lark_oapi") is not None # Message type display mapping MSG_TYPE_MAP = { @@ -280,6 +263,7 @@ class FeishuChannel(BaseChannel): logger.error("Feishu app_id and app_secret not configured") return + import lark_oapi as lark self._running = True self._loop = asyncio.get_running_loop() @@ -340,6 +324,7 @@ class FeishuChannel(BaseChannel): 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 try: request = CreateMessageReactionRequest.builder() \ .message_id(message_id) \ @@ -364,7 +349,7 @@ class FeishuChannel(BaseChannel): Common emoji types: THUMBSUP, OK, EYES, DONE, OnIt, HEART """ - if not self._client or not Emoji: + if not self._client: return loop = asyncio.get_running_loop() @@ -456,6 +441,7 @@ class FeishuChannel(BaseChannel): def _upload_image_sync(self, file_path: str) -> str | None: """Upload an image to Feishu and return the image_key.""" + from lark_oapi.api.im.v1 import CreateImageRequest, CreateImageRequestBody try: with open(file_path, "rb") as f: request = CreateImageRequest.builder() \ @@ -479,6 +465,7 @@ class FeishuChannel(BaseChannel): def _upload_file_sync(self, file_path: str) -> str | None: """Upload a file to Feishu and return the file_key.""" + from lark_oapi.api.im.v1 import CreateFileRequest, CreateFileRequestBody ext = os.path.splitext(file_path)[1].lower() file_type = self._FILE_TYPE_MAP.get(ext, "stream") file_name = os.path.basename(file_path) @@ -506,6 +493,7 @@ class FeishuChannel(BaseChannel): def _download_image_sync(self, message_id: str, image_key: str) -> tuple[bytes | None, str | None]: """Download an image from Feishu message by message_id and image_key.""" + from lark_oapi.api.im.v1 import GetMessageResourceRequest try: request = GetMessageResourceRequest.builder() \ .message_id(message_id) \ @@ -530,6 +518,7 @@ class FeishuChannel(BaseChannel): self, message_id: str, file_key: str, resource_type: str = "file" ) -> tuple[bytes | None, str | None]: """Download a file/audio/media from a Feishu message by message_id and file_key.""" + from lark_oapi.api.im.v1 import GetMessageResourceRequest try: request = ( GetMessageResourceRequest.builder() @@ -598,6 +587,7 @@ class FeishuChannel(BaseChannel): def _send_message_sync(self, receive_id_type: str, receive_id: str, msg_type: str, content: str) -> bool: """Send a single message (text/image/file/interactive) synchronously.""" + from lark_oapi.api.im.v1 import CreateMessageRequest, CreateMessageRequestBody try: request = CreateMessageRequest.builder() \ .receive_id_type(receive_id_type) \ diff --git a/pyproject.toml b/pyproject.toml index 0546523..d384f3f 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -42,6 +42,7 @@ dependencies = [ "prompt-toolkit>=3.0.50,<4.0.0", "mcp>=1.26.0,<2.0.0", "json-repair>=0.57.0,<1.0.0", + "chardet>=3.0.2,<6.0.0", ] [project.optional-dependencies] From e032faaeff81d7e4fa39659badbacc7b4004dc05 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergio=20S=C3=A1nchez=20Vall=C3=A9s?= Date: Wed, 4 Mar 2026 20:04:00 +0100 Subject: [PATCH 14/17] Merge branch 'main' of upstream/main into fix/test-failures --- .gitignore | 2 +- nanobot/agent/tools/base.py | 2 ++ nanobot/agent/tools/cron.py | 5 ++++- nanobot/agent/tools/filesystem.py | 11 +++++++++++ nanobot/channels/feishu.py | 6 ++++++ nanobot/providers/openai_codex_provider.py | 3 +++ pyproject.toml | 2 ++ tests/test_context_prompt_cache.py | 1 + 8 files changed, 30 insertions(+), 2 deletions(-) diff --git a/.gitignore b/.gitignore index d7b930d..742d593 100644 --- a/.gitignore +++ b/.gitignore @@ -19,4 +19,4 @@ __pycache__/ poetry.lock .pytest_cache/ botpy.log -tests/ + diff --git a/nanobot/agent/tools/base.py b/nanobot/agent/tools/base.py index 8dd82c7..051fc9a 100644 --- a/nanobot/agent/tools/base.py +++ b/nanobot/agent/tools/base.py @@ -54,6 +54,8 @@ class Tool(ABC): def validate_params(self, params: dict[str, Any]) -> list[str]: """Validate tool parameters against JSON schema. Returns error list (empty if valid).""" + if not isinstance(params, dict): + return [f"parameters must be an object, got {type(params).__name__}"] schema = self.parameters or {} if schema.get("type", "object") != "object": raise ValueError(f"Schema must be object type, got {schema.get('type')!r}") diff --git a/nanobot/agent/tools/cron.py b/nanobot/agent/tools/cron.py index 13b1e12..f8e737b 100644 --- a/nanobot/agent/tools/cron.py +++ b/nanobot/agent/tools/cron.py @@ -122,7 +122,10 @@ class CronTool(Tool): elif at: from datetime import datetime - dt = datetime.fromisoformat(at) + try: + dt = datetime.fromisoformat(at) + except ValueError: + return f"Error: invalid ISO datetime format '{at}'. Expected format: YYYY-MM-DDTHH:MM:SS" at_ms = int(dt.timestamp() * 1000) schedule = CronSchedule(kind="at", at_ms=at_ms) delete_after = True diff --git a/nanobot/agent/tools/filesystem.py b/nanobot/agent/tools/filesystem.py index bbdd49c..7b0b867 100644 --- a/nanobot/agent/tools/filesystem.py +++ b/nanobot/agent/tools/filesystem.py @@ -26,6 +26,8 @@ def _resolve_path( class ReadFileTool(Tool): """Tool to read file contents.""" + _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 @@ -54,7 +56,16 @@ class ReadFileTool(Tool): if not file_path.is_file(): return f"Error: Not a file: {path}" + size = file_path.stat().st_size + if size > self._MAX_CHARS * 4: # rough upper bound (UTF-8 chars ≤ 4 bytes) + 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 len(content) > self._MAX_CHARS: + return content[: self._MAX_CHARS] + f"\n\n... (truncated — file is {len(content):,} chars, limit {self._MAX_CHARS:,})" return content except PermissionError as e: return f"Error: {e}" diff --git a/nanobot/channels/feishu.py b/nanobot/channels/feishu.py index 7d26fa8..0cd84c3 100644 --- a/nanobot/channels/feishu.py +++ b/nanobot/channels/feishu.py @@ -519,6 +519,12 @@ class FeishuChannel(BaseChannel): ) -> tuple[bytes | None, str | None]: """Download a file/audio/media from a Feishu message by message_id and file_key.""" from lark_oapi.api.im.v1 import GetMessageResourceRequest + + # Feishu API only accepts 'image' or 'file' as type parameter + # Convert 'audio' to 'file' for API compatibility + if resource_type == "audio": + resource_type = "file" + try: request = ( GetMessageResourceRequest.builder() diff --git a/nanobot/providers/openai_codex_provider.py b/nanobot/providers/openai_codex_provider.py index b6afa65..d04e210 100644 --- a/nanobot/providers/openai_codex_provider.py +++ b/nanobot/providers/openai_codex_provider.py @@ -52,6 +52,9 @@ class OpenAICodexProvider(LLMProvider): "parallel_tool_calls": True, } + if reasoning_effort: + body["reasoning"] = {"effort": reasoning_effort} + if tools: body["tools"] = _convert_tools(tools) diff --git a/pyproject.toml b/pyproject.toml index d384f3f..e5214bd 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -43,6 +43,8 @@ dependencies = [ "mcp>=1.26.0,<2.0.0", "json-repair>=0.57.0,<1.0.0", "chardet>=3.0.2,<6.0.0", + "openai>=2.8.0", + ] [project.optional-dependencies] diff --git a/tests/test_context_prompt_cache.py b/tests/test_context_prompt_cache.py index fa7f02d..d347e53 100644 --- a/tests/test_context_prompt_cache.py +++ b/tests/test_context_prompt_cache.py @@ -55,6 +55,7 @@ def test_runtime_context_is_separate_untrusted_user_message(tmp_path) -> None: assert "## Current Session" not in messages[0]["content"] assert len(messages) == 2 + # Runtime context is now merged with user message into a single message assert messages[-1]["role"] == "user" user_content = messages[-1]["content"] From 97522bfa0309931e53782ed7a4e2cfdc470853c4 Mon Sep 17 00:00:00 2001 From: coldxiangyu Date: Thu, 5 Mar 2026 17:27:17 +0800 Subject: [PATCH 15/17] fix(feishu): isolate lark ws Client event loop from main asyncio loop Commit 0209ad5 moved `import lark_oapi as lark` inside the start() method (lazy import) to suppress DeprecationWarnings. This had an unintended side effect: the import now happens after the main asyncio loop is already running, so lark_oapi's module-level loop = asyncio.get_event_loop() captures the running main loop. When the WebSocket thread then calls loop.run_until_complete() inside Client.start(), Python raises: RuntimeError: This event loop is already running and the _connect/_disconnect coroutines are never awaited. Fix: in run_ws(), create a fresh event loop with asyncio.new_event_loop(), set it as the thread's current loop, and patch lark_oapi.ws.client.loop to point to this dedicated loop before calling Client.start(). The loop is closed on thread exit. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> --- nanobot/channels/feishu.py | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) diff --git a/nanobot/channels/feishu.py b/nanobot/channels/feishu.py index 0cd84c3..fcb70a8 100644 --- a/nanobot/channels/feishu.py +++ b/nanobot/channels/feishu.py @@ -290,16 +290,28 @@ class FeishuChannel(BaseChannel): log_level=lark.LogLevel.INFO ) - # Start WebSocket client in a separate thread with reconnect loop + # Start WebSocket client in a separate thread with reconnect loop. + # A dedicated event loop is created for this thread so that lark_oapi's + # module-level `loop = asyncio.get_event_loop()` picks up an idle loop + # instead of the already-running main asyncio loop, which would cause + # "This event loop is already running" errors. def run_ws(): - while self._running: - try: - self._ws_client.start() - except Exception as e: - logger.warning("Feishu WebSocket error: {}", e) - if self._running: - import time - time.sleep(5) + import time + import lark_oapi.ws.client as _lark_ws_client + ws_loop = asyncio.new_event_loop() + asyncio.set_event_loop(ws_loop) + # Patch the module-level loop used by lark's ws Client.start() + _lark_ws_client.loop = ws_loop + try: + while self._running: + try: + self._ws_client.start() + except Exception as e: + logger.warning("Feishu WebSocket error: {}", e) + if self._running: + time.sleep(5) + finally: + ws_loop.close() self._ws_thread = threading.Thread(target=run_ws, daemon=True) self._ws_thread.start() From fb77176cfd41b50b3495ffa99cfc22bb6cbd4ed1 Mon Sep 17 00:00:00 2001 From: Re-bin Date: Thu, 5 Mar 2026 14:25:46 +0000 Subject: [PATCH 16/17] feat(custom-provider): keep instance-level session affinity header for cache locality --- nanobot/providers/custom_provider.py | 1 + 1 file changed, 1 insertion(+) diff --git a/nanobot/providers/custom_provider.py b/nanobot/providers/custom_provider.py index 02183f3..66df734 100644 --- a/nanobot/providers/custom_provider.py +++ b/nanobot/providers/custom_provider.py @@ -16,6 +16,7 @@ class CustomProvider(LLMProvider): def __init__(self, api_key: str = "no-key", api_base: str = "http://localhost:8000/v1", default_model: str = "default"): super().__init__(api_key, api_base) self.default_model = default_model + # Keep affinity stable for this provider instance to improve backend cache locality. self._client = AsyncOpenAI( api_key=api_key, base_url=api_base, From 06fcd2cc3fed18667672f638a6c7cc54f8d5f736 Mon Sep 17 00:00:00 2001 From: Re-bin Date: Thu, 5 Mar 2026 14:33:14 +0000 Subject: [PATCH 17/17] fix(discord): correct group_policy default to mention and style cleanup --- nanobot/channels/discord.py | 6 ++---- nanobot/config/schema.py | 2 +- 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/nanobot/channels/discord.py b/nanobot/channels/discord.py index 85ff28a..900c17b 100644 --- a/nanobot/channels/discord.py +++ b/nanobot/channels/discord.py @@ -174,7 +174,7 @@ class DiscordChannel(BaseChannel): # Capture bot user ID for mention detection user_data = payload.get("user") or {} self._bot_user_id = user_data.get("id") - logger.info(f"Discord bot connected as user {self._bot_user_id}") + logger.info("Discord bot connected as user {}", self._bot_user_id) elif op == 0 and event_type == "MESSAGE_CREATE": await self._handle_message_create(payload) elif op == 7: @@ -287,8 +287,6 @@ class DiscordChannel(BaseChannel): def _should_respond_in_group(self, payload: dict[str, Any], content: str) -> bool: """Check if bot should respond in a group channel based on policy.""" - channel_id = str(payload.get("channel_id", "")) - if self.config.group_policy == "open": return True @@ -303,7 +301,7 @@ class DiscordChannel(BaseChannel): # Also check content for mention format <@USER_ID> if f"<@{self._bot_user_id}>" in content or f"<@!{self._bot_user_id}>" in content: return True - logger.debug(f"Discord message in {channel_id} ignored (bot not mentioned)") + logger.debug("Discord message in {} ignored (bot not mentioned)", payload.get("channel_id")) return False return True diff --git a/nanobot/config/schema.py b/nanobot/config/schema.py index a6b609b..9d7da3b 100644 --- a/nanobot/config/schema.py +++ b/nanobot/config/schema.py @@ -62,7 +62,7 @@ class DiscordConfig(Base): allow_from: list[str] = Field(default_factory=list) # Allowed user IDs gateway_url: str = "wss://gateway.discord.gg/?v=10&encoding=json" intents: int = 37377 # GUILDS + GUILD_MESSAGES + DIRECT_MESSAGES + MESSAGE_CONTENT - group_policy: str = "open" # "mention" or "open" + group_policy: Literal["mention", "open"] = "mention" class MatrixConfig(Base):