Merge branch 'main' into fix/skills-yaml-frontmatter

nanobot/__init__.py

@@ -21,7 +21,7 @@ def _resolve_version() -> str:
         return _pkg_version("nanobot-ai")
     except PackageNotFoundError:
         # Source checkouts often import nanobot without installed dist-info.
-        return _read_pyproject_version() or "0.1.5"
+        return _read_pyproject_version() or "0.1.5.post1"
 
 
 __version__ = _resolve_version()

nanobot/agent/context.py

@@ -3,15 +3,14 @@
 import base64
 import mimetypes
 import platform
+from importlib.resources import files as pkg_files
 from pathlib import Path
 from typing import Any
 
-from nanobot.utils.helpers import current_time_str
-
 from nanobot.agent.memory import MemoryStore
-from nanobot.utils.prompt_templates import render_template
 from nanobot.agent.skills import SkillsLoader
-from nanobot.utils.helpers import build_assistant_message, detect_image_mime
+from nanobot.utils.helpers import build_assistant_message, current_time_str, detect_image_mime
+from nanobot.utils.prompt_templates import render_template
 
 
 class ContextBuilder:
@@ -41,7 +40,7 @@ class ContextBuilder:
             parts.append(bootstrap)
 
         memory = self.memory.get_memory_context()
-        if memory:
+        if memory and not self._is_template_content(self.memory.read_memory(), "memory/MEMORY.md"):
             parts.append(f"# Memory\n\n{memory}")
 
         always_skills = self.skills.get_always_skills()
@@ -50,7 +49,7 @@ class ContextBuilder:
             if always_content:
                 parts.append(f"# Active Skills\n\n{always_content}")
 
-        skills_summary = self.skills.build_skills_summary()
+        skills_summary = self.skills.build_skills_summary(exclude=set(always_skills))
         if skills_summary:
             parts.append(render_template("agent/skills_section.md", skills_summary=skills_summary))
 
@@ -116,6 +115,17 @@ class ContextBuilder:
 
         return "\n\n".join(parts) if parts else ""
 
+    @staticmethod
+    def _is_template_content(content: str, template_path: str) -> bool:
+        """Check if *content* is identical to the bundled template (user hasn't customized it)."""
+        try:
+            tpl = pkg_files("nanobot") / "templates" / template_path
+            if tpl.is_file():
+                return content.strip() == tpl.read_text(encoding="utf-8").strip()
+        except Exception:
+            pass
+        return False
+
     def build_messages(
         self,
         history: list[dict[str, Any]],
@@ -160,7 +170,6 @@ class ContextBuilder:
             if not p.is_file():
                 continue
             raw = p.read_bytes()
-            # Detect real MIME type from magic bytes; fallback to filename guess
             mime = detect_image_mime(raw) or mimetypes.guess_type(path)[0]
             if not mime or not mime.startswith("image/"):
                 continue

nanobot/agent/loop.py

@@ -17,10 +17,10 @@ from nanobot.agent.autocompact import AutoCompact
 from nanobot.agent.context import ContextBuilder
 from nanobot.agent.hook import AgentHook, AgentHookContext, CompositeHook
 from nanobot.agent.memory import Consolidator, Dream
-from nanobot.agent.runner import _MAX_INJECTIONS_PER_TURN, AgentRunSpec, AgentRunner
+from nanobot.agent.runner import _MAX_INJECTIONS_PER_TURN, AgentRunner, AgentRunSpec
+from nanobot.agent.skills import BUILTIN_SKILLS_DIR
 from nanobot.agent.subagent import SubagentManager
 from nanobot.agent.tools.cron import CronTool
-from nanobot.agent.skills import BUILTIN_SKILLS_DIR
 from nanobot.agent.tools.filesystem import EditFileTool, ListDirTool, ReadFileTool, WriteFileTool
 from nanobot.agent.tools.message import MessageTool
 from nanobot.agent.tools.notebook import NotebookEditTool
@@ -30,12 +30,14 @@ from nanobot.agent.tools.shell import ExecTool
 from nanobot.agent.tools.spawn import SpawnTool
 from nanobot.agent.tools.web import WebFetchTool, WebSearchTool
 from nanobot.bus.events import InboundMessage, OutboundMessage
-from nanobot.command import CommandContext, CommandRouter, register_builtin_commands
 from nanobot.bus.queue import MessageBus
+from nanobot.command import CommandContext, CommandRouter, register_builtin_commands
 from nanobot.config.schema import AgentDefaults
 from nanobot.providers.base import LLMProvider
 from nanobot.session.manager import Session, SessionManager
-from nanobot.utils.helpers import image_placeholder_text, truncate_text as truncate_text_fn
+from nanobot.utils.document import extract_documents
+from nanobot.utils.helpers import image_placeholder_text
+from nanobot.utils.helpers import truncate_text as truncate_text_fn
 from nanobot.utils.runtime import EMPTY_FINAL_RESPONSE_MESSAGE
 
 if TYPE_CHECKING:
@@ -383,10 +385,12 @@ class AgentLoop:
                     pending_msg = pending_queue.get_nowait()
                 except asyncio.QueueEmpty:
                     break
-                user_content = self.context._build_user_content(
-                    pending_msg.content,
-                    pending_msg.media if pending_msg.media else None,
-                )
+                content = pending_msg.content
+                media = pending_msg.media if pending_msg.media else None
+                if media:
+                    content, media = extract_documents(content, media)
+                    media = media or None
+                user_content = self.context._build_user_content(content, media)
                 runtime_ctx = self.context._build_runtime_context(
                     pending_msg.channel,
                     pending_msg.chat_id,
@@ -652,6 +656,12 @@ class AgentLoop:
                 content=final_content or "Background task completed.",
             )
 
+        # Extract document text from media at the processing boundary so all
+        # channels benefit without format-specific logic in ContextBuilder.
+        if msg.media:
+            new_content, image_only = extract_documents(msg.content, msg.media)
+            msg = dataclasses.replace(msg, content=new_content, media=image_only)
+
         preview = msg.content[:80] + "..." if len(msg.content) > 80 else msg.content
         logger.info("Processing message from {}:{}: {}", msg.channel, msg.sender_id, preview)
 
@@ -952,13 +962,17 @@ class AgentLoop:
         session_key: str = "cli:direct",
         channel: str = "cli",
         chat_id: str = "direct",
+        media: list[str] | None = None,
         on_progress: Callable[[str], Awaitable[None]] | None = None,
         on_stream: Callable[[str], Awaitable[None]] | None = None,
         on_stream_end: Callable[..., Awaitable[None]] | None = None,
     ) -> OutboundMessage | None:
         """Process a message directly and return the outbound payload."""
         await self._connect_mcp()
-        msg = InboundMessage(channel=channel, sender_id="user", chat_id=chat_id, content=content)
+        msg = InboundMessage(
+            channel=channel, sender_id="user", chat_id=chat_id,
+            content=content, media=media or [],
+        )
         return await self._process_message(
             msg,
             session_key=session_key,

nanobot/agent/runner.py

@@ -134,6 +134,50 @@ class AgentRunner:
                 continue
             messages.append(injection)
 
+    async def _try_drain_injections(
+        self,
+        spec: AgentRunSpec,
+        messages: list[dict[str, Any]],
+        assistant_message: dict[str, Any] | None,
+        injection_cycles: int,
+        *,
+        phase: str = "after error",
+        iteration: int | None = None,
+    ) -> tuple[bool, int]:
+        """Drain pending injections. Returns (should_continue, updated_cycles).
+
+        If injections are found and we haven't exceeded _MAX_INJECTION_CYCLES,
+        append them to *messages* (and emit a checkpoint if *assistant_message*
+        and *iteration* are both provided) and return (True, cycles+1) so the
+        caller continues the iteration loop.  Otherwise return (False, cycles).
+        """
+        if injection_cycles >= _MAX_INJECTION_CYCLES:
+            return False, injection_cycles
+        injections = await self._drain_injections(spec)
+        if not injections:
+            return False, injection_cycles
+        injection_cycles += 1
+        if assistant_message is not None:
+            messages.append(assistant_message)
+            if iteration is not None:
+                await self._emit_checkpoint(
+                    spec,
+                    {
+                        "phase": "final_response",
+                        "iteration": iteration,
+                        "model": spec.model,
+                        "assistant_message": assistant_message,
+                        "completed_tool_results": [],
+                        "pending_tool_calls": [],
+                    },
+                )
+        self._append_injected_messages(messages, injections)
+        logger.info(
+            "Injected {} follow-up message(s) {} ({}/{})",
+            len(injections), phase, injection_cycles, _MAX_INJECTION_CYCLES,
+        )
+        return True, injection_cycles
+
     async def _drain_injections(self, spec: AgentRunSpec) -> list[dict[str, Any]]:
         """Drain pending user messages via the injection callback.
 
@@ -287,6 +331,13 @@ class AgentRunner:
                     context.error = error
                     context.stop_reason = stop_reason
                     await hook.after_iteration(context)
+                    should_continue, injection_cycles = await self._try_drain_injections(
+                        spec, messages, None, injection_cycles,
+                        phase="after tool error",
+                    )
+                    if should_continue:
+                        had_injections = True
+                        continue
                     break
                 await self._emit_checkpoint(
                     spec,
@@ -302,16 +353,12 @@ class AgentRunner:
                 empty_content_retries = 0
                 length_recovery_count = 0
                 # Checkpoint 1: drain injections after tools, before next LLM call
-                if injection_cycles < _MAX_INJECTION_CYCLES:
-                    injections = await self._drain_injections(spec)
-                    if injections:
-                        had_injections = True
-                        injection_cycles += 1
-                        self._append_injected_messages(messages, injections)
-                        logger.info(
-                            "Injected {} follow-up message(s) after tool execution ({}/{})",
-                            len(injections), injection_cycles, _MAX_INJECTION_CYCLES,
-                        )
+                _drained, injection_cycles = await self._try_drain_injections(
+                    spec, messages, None, injection_cycles,
+                    phase="after tool execution",
+                )
+                if _drained:
+                    had_injections = True
                 await hook.after_iteration(context)
                 continue
 
@@ -379,36 +426,18 @@ class AgentRunner:
             # Check for mid-turn injections BEFORE signaling stream end.
             # If injections are found we keep the stream alive (resuming=True)
             # so streaming channels don't prematurely finalize the card.
-            _injected_after_final = False
-            if injection_cycles < _MAX_INJECTION_CYCLES:
-                injections = await self._drain_injections(spec)
-                if injections:
-                    had_injections = True
-                    injection_cycles += 1
-                    _injected_after_final = True
-                    if assistant_message is not None:
-                        messages.append(assistant_message)
-                        await self._emit_checkpoint(
-                            spec,
-                            {
-                                "phase": "final_response",
-                                "iteration": iteration,
-                                "model": spec.model,
-                                "assistant_message": assistant_message,
-                                "completed_tool_results": [],
-                                "pending_tool_calls": [],
-                            },
-                        )
-                    self._append_injected_messages(messages, injections)
-                    logger.info(
-                        "Injected {} follow-up message(s) after final response ({}/{})",
-                        len(injections), injection_cycles, _MAX_INJECTION_CYCLES,
-                    )
+            should_continue, injection_cycles = await self._try_drain_injections(
+                spec, messages, assistant_message, injection_cycles,
+                phase="after final response",
+                iteration=iteration,
+            )
+            if should_continue:
+                had_injections = True
 
             if hook.wants_streaming():
-                await hook.on_stream_end(context, resuming=_injected_after_final)
+                await hook.on_stream_end(context, resuming=should_continue)
 
-            if _injected_after_final:
+            if should_continue:
                 await hook.after_iteration(context)
                 continue
 
@@ -421,6 +450,13 @@ class AgentRunner:
                 context.error = error
                 context.stop_reason = stop_reason
                 await hook.after_iteration(context)
+                should_continue, injection_cycles = await self._try_drain_injections(
+                    spec, messages, None, injection_cycles,
+                    phase="after LLM error",
+                )
+                if should_continue:
+                    had_injections = True
+                    continue
                 break
             if is_blank_text(clean):
                 final_content = EMPTY_FINAL_RESPONSE_MESSAGE
@@ -431,6 +467,13 @@ class AgentRunner:
                 context.error = error
                 context.stop_reason = stop_reason
                 await hook.after_iteration(context)
+                should_continue, injection_cycles = await self._try_drain_injections(
+                    spec, messages, None, injection_cycles,
+                    phase="after empty response",
+                )
+                if should_continue:
+                    had_injections = True
+                    continue
                 break
 
             messages.append(assistant_message or build_assistant_message(
@@ -467,6 +510,17 @@ class AgentRunner:
                     max_iterations=spec.max_iterations,
                 )
             self._append_final_message(messages, final_content)
+            # Drain any remaining injections so they are appended to the
+            # conversation history instead of being re-published as
+            # independent inbound messages by _dispatch's finally block.
+            # We ignore should_continue here because the for-loop has already
+            # exhausted all iterations.
+            drained_after_max_iterations, injection_cycles = await self._try_drain_injections(
+                spec, messages, None, injection_cycles,
+                phase="after max_iterations",
+            )
+            if drained_after_max_iterations:
+                had_injections = True
 
         return AgentRunResult(
             final_content=final_content,

nanobot/agent/skills.py

@@ -18,10 +18,6 @@ _STRIP_SKILL_FRONTMATTER = re.compile(
 )
 
 
-def _escape_xml(text: str) -> str:
-    return text.replace("&", "&amp;").replace("<", "&lt;").replace(">", "&gt;")
-
-
 class SkillsLoader:
     """
     Loader for agent skills.
@@ -112,39 +108,37 @@ class SkillsLoader:
         ]
         return "\n\n---\n\n".join(parts)
 
-    def build_skills_summary(self) -> str:
+    def build_skills_summary(self, exclude: set[str] | None = None) -> str:
         """
         Build a summary of all skills (name, description, path, availability).
 
         This is used for progressive loading - the agent can read the full
         skill content using read_file when needed.
 
+        Args:
+            exclude: Set of skill names to omit from the summary.
+
         Returns:
-            XML-formatted skills summary.
+            Markdown-formatted skills summary.
         """
         all_skills = self.list_skills(filter_unavailable=False)
         if not all_skills:
             return ""
 
-        lines: list[str] = ["<skills>"]
+        lines: list[str] = []
         for entry in all_skills:
             skill_name = entry["name"]
+            if exclude and skill_name in exclude:
+                continue
             meta = self._get_skill_meta(skill_name)
             available = self._check_requirements(meta)
-            lines.extend(
-                [
-                    f'  <skill available="{str(available).lower()}">',
-                    f"    <name>{_escape_xml(skill_name)}</name>",
-                    f"    <description>{_escape_xml(self._get_skill_description(skill_name))}</description>",
-                    f"    <location>{entry['path']}</location>",
-                ]
-            )
-            if not available:
+            desc = self._get_skill_description(skill_name)
+            if available:
+                lines.append(f"- **{skill_name}** — {desc}  `{entry['path']}`")
+            else:
                 missing = self._get_missing_requirements(meta)
-                if missing:
-                    lines.append(f"    <requires>{_escape_xml(missing)}</requires>")
-            lines.append("  </skill>")
-        lines.append("</skills>")
+                suffix = f" (unavailable: {missing})" if missing else " (unavailable)"
+                lines.append(f"- **{skill_name}** — {desc}{suffix}  `{entry['path']}`")
         return "\n".join(lines)
 
     def _get_missing_requirements(self, skill_meta: dict) -> str:

nanobot/agent/subagent.py

@@ -262,3 +262,11 @@ class SubagentManager:
     def get_running_count(self) -> int:
         """Return the number of currently running subagents."""
         return len(self._running_tasks)
+
+    def get_running_count_by_session(self, session_key: str) -> int:
+        """Return the number of currently running subagents for a session."""
+        tids = self._session_tasks.get(session_key, set())
+        return sum(
+            1 for tid in tids
+            if tid in self._running_tasks and not self._running_tasks[tid].done()
+        )

nanobot/agent/tools/web.py

@@ -96,10 +96,37 @@ class WebSearchTool(Tool):
         self.config = config if config is not None else WebSearchConfig()
         self.proxy = proxy
 
+    def _effective_provider(self) -> str:
+        """Resolve the backend that execute() will actually use."""
+        provider = self.config.provider.strip().lower() or "brave"
+        if provider == "duckduckgo":
+            return "duckduckgo"
+        if provider == "brave":
+            api_key = self.config.api_key or os.environ.get("BRAVE_API_KEY", "")
+            return "brave" if api_key else "duckduckgo"
+        if provider == "tavily":
+            api_key = self.config.api_key or os.environ.get("TAVILY_API_KEY", "")
+            return "tavily" if api_key else "duckduckgo"
+        if provider == "searxng":
+            base_url = (self.config.base_url or os.environ.get("SEARXNG_BASE_URL", "")).strip()
+            return "searxng" if base_url else "duckduckgo"
+        if provider == "jina":
+            api_key = self.config.api_key or os.environ.get("JINA_API_KEY", "")
+            return "jina" if api_key else "duckduckgo"
+        if provider == "kagi":
+            api_key = self.config.api_key or os.environ.get("KAGI_API_KEY", "")
+            return "kagi" if api_key else "duckduckgo"
+        return provider
+
     @property
     def read_only(self) -> bool:
         return True
 
+    @property
+    def exclusive(self) -> bool:
+        """DuckDuckGo searches are serialized because ddgs is not concurrency-safe."""
+        return self._effective_provider() == "duckduckgo"
+
     async def execute(self, query: str, count: int | None = None, **kwargs: Any) -> str:
         provider = self.config.provider.strip().lower() or "brave"
         n = min(max(count or self.config.max_results, 1), 10)

nanobot/api/server.py

@@ -7,15 +7,28 @@ All requests route to a single persistent API session.
 from __future__ import annotations
 
 import asyncio
+import base64
+import mimetypes
+import re
 import time
 import uuid
+from pathlib import Path
 from typing import Any
 
 from aiohttp import web
 from loguru import logger
 
+from nanobot.config.paths import get_media_dir
+from nanobot.utils.helpers import safe_filename
 from nanobot.utils.runtime import EMPTY_FINAL_RESPONSE_MESSAGE
 
+MAX_FILE_SIZE = 10 * 1024 * 1024  # 10 MB
+_DATA_URL_RE = re.compile(r"^data:([^;]+);base64,(.+)$", re.DOTALL)
+
+
+class _FileSizeExceeded(Exception):
+    """Raised when an uploaded file exceeds the size limit."""
+
 API_SESSION_KEY = "api:default"
 API_CHAT_ID = "default"
 
@@ -57,48 +70,138 @@ def _response_text(value: Any) -> str:
     return str(value)
 
 
+# ---------------------------------------------------------------------------
+# Upload helpers
+# ---------------------------------------------------------------------------
+
+def _save_base64_data_url(data_url: str, media_dir: Path) -> str | None:
+    """Decode a data:...;base64,... URL and save to disk."""
+    m = _DATA_URL_RE.match(data_url)
+    if not m:
+        return None
+    mime_type, b64_payload = m.group(1), m.group(2)
+    try:
+        raw = base64.b64decode(b64_payload)
+    except Exception:
+        return None
+    if len(raw) > MAX_FILE_SIZE:
+        raise _FileSizeExceeded(
+            f"File exceeds {MAX_FILE_SIZE // (1024 * 1024)}MB limit"
+        )
+    ext = mimetypes.guess_extension(mime_type) or ".bin"
+    filename = f"{uuid.uuid4().hex[:12]}{ext}"
+    dest = media_dir / safe_filename(filename)
+    dest.write_bytes(raw)
+    return str(dest)
+
+
+def _parse_json_content(body: dict) -> tuple[str, list[str]]:
+    """Parse JSON request body. Returns (text, media_paths)."""
+    messages = body.get("messages")
+    if not isinstance(messages, list) or len(messages) != 1:
+        raise ValueError("Only a single user message is supported")
+    message = messages[0]
+    if not isinstance(message, dict) or message.get("role") != "user":
+        raise ValueError("Only a single user message is supported")
+
+    user_content = message.get("content", "")
+    media_dir = get_media_dir("api")
+    media_paths: list[str] = []
+
+    if isinstance(user_content, list):
+        text_parts: list[str] = []
+        for part in user_content:
+            if not isinstance(part, dict):
+                continue
+            if part.get("type") == "text":
+                text_parts.append(part.get("text", ""))
+            elif part.get("type") == "image_url":
+                url = part.get("image_url", {}).get("url", "")
+                if url.startswith("data:"):
+                    saved = _save_base64_data_url(url, media_dir)
+                    if saved:
+                        media_paths.append(saved)
+        text = " ".join(text_parts)
+    elif isinstance(user_content, str):
+        text = user_content
+    else:
+        raise ValueError("Invalid content format")
+
+    return text, media_paths
+
+
+async def _parse_multipart(request: web.Request) -> tuple[str, list[str], str | None]:
+    """Parse multipart/form-data. Returns (text, media_paths, session_id)."""
+    media_dir = get_media_dir("api")
+    reader = await request.multipart()
+    text = ""
+    session_id = None
+    media_paths: list[str] = []
+
+    while True:
+        part = await reader.next()
+        if part is None:
+            break
+        if part.name == "message":
+            text = (await part.read()).decode("utf-8")
+        elif part.name == "session_id":
+            session_id = (await part.read()).decode("utf-8").strip()
+        elif part.name == "files":
+            raw = await part.read()
+            if len(raw) > MAX_FILE_SIZE:
+                raise _FileSizeExceeded(f"File '{part.filename}' exceeds {MAX_FILE_SIZE // (1024*1024)}MB limit")
+            filename = safe_filename(part.filename or f"{uuid.uuid4().hex[:12]}.bin")
+            dest = media_dir / filename
+            dest.write_bytes(raw)
+            media_paths.append(str(dest))
+
+    if not text:
+        text = "请分析上传的文件"
+
+    return text, media_paths, session_id
+
+
 # ---------------------------------------------------------------------------
 # Route handlers
 # ---------------------------------------------------------------------------
 
 async def handle_chat_completions(request: web.Request) -> web.Response:
-    """POST /v1/chat/completions"""
-
-    # --- Parse body ---
-    try:
-        body = await request.json()
-    except Exception:
-        return _error_json(400, "Invalid JSON body")
-
-    messages = body.get("messages")
-    if not isinstance(messages, list) or len(messages) != 1:
-        return _error_json(400, "Only a single user message is supported")
-
-    # Stream not yet supported
-    if body.get("stream", False):
-        return _error_json(400, "stream=true is not supported yet. Set stream=false or omit it.")
-
-    message = messages[0]
-    if not isinstance(message, dict) or message.get("role") != "user":
-        return _error_json(400, "Only a single user message is supported")
-    user_content = message.get("content", "")
-    if isinstance(user_content, list):
-        # Multi-modal content array — extract text parts
-        user_content = " ".join(
-            part.get("text", "") for part in user_content if part.get("type") == "text"
-        )
+    """POST /v1/chat/completions — supports JSON and multipart/form-data."""
+    content_type = request.content_type or ""
+    if not isinstance(content_type, str):
+        content_type = ""
 
     agent_loop = request.app["agent_loop"]
     timeout_s: float = request.app.get("request_timeout", 120.0)
     model_name: str = request.app.get("model_name", "nanobot")
-    if (requested_model := body.get("model")) and requested_model != model_name:
-        return _error_json(400, f"Only configured model '{model_name}' is available")
 
-    session_key = f"api:{body['session_id']}" if body.get("session_id") else API_SESSION_KEY
+    try:
+        if content_type.startswith("multipart/"):
+            text, media_paths, session_id = await _parse_multipart(request)
+        else:
+            try:
+                body = await request.json()
+            except Exception:
+                return _error_json(400, "Invalid JSON body")
+            if body.get("stream", False):
+                return _error_json(400, "stream=true is not supported yet. Set stream=false or omit it.")
+            if (requested_model := body.get("model")) and requested_model != model_name:
+                return _error_json(400, f"Only configured model '{model_name}' is available")
+            text, media_paths = _parse_json_content(body)
+            session_id = body.get("session_id")
+    except ValueError as e:
+        return _error_json(400, str(e))
+    except _FileSizeExceeded as e:
+        return _error_json(413, str(e), err_type="invalid_request_error")
+    except Exception:
+        logger.exception("Error parsing upload")
+        return _error_json(413, "File too large or invalid upload")
+
+    session_key = f"api:{session_id}" if session_id else API_SESSION_KEY
     session_locks: dict[str, asyncio.Lock] = request.app["session_locks"]
     session_lock = session_locks.setdefault(session_key, asyncio.Lock())
 
-    logger.info("API request session_key={} content={}", session_key, user_content[:80])
+    logger.info("API request session_key={} media={} text={}", session_key, len(media_paths), text[:80])
 
     _FALLBACK = EMPTY_FINAL_RESPONSE_MESSAGE
 
@@ -107,7 +210,8 @@ async def handle_chat_completions(request: web.Request) -> web.Response:
             try:
                 response = await asyncio.wait_for(
                     agent_loop.process_direct(
-                        content=user_content,
+                        content=text,
+                        media=media_paths if media_paths else None,
                         session_key=session_key,
                         channel="api",
                         chat_id=API_CHAT_ID,
@@ -117,13 +221,11 @@ async def handle_chat_completions(request: web.Request) -> web.Response:
                 response_text = _response_text(response)
 
                 if not response_text or not response_text.strip():
-                    logger.warning(
-                        "Empty response for session {}, retrying",
-                        session_key,
-                    )
+                    logger.warning("Empty response for session {}, retrying", session_key)
                     retry_response = await asyncio.wait_for(
                         agent_loop.process_direct(
-                            content=user_content,
+                            content=text,
+                            media=media_paths if media_paths else None,
                             session_key=session_key,
                             channel="api",
                             chat_id=API_CHAT_ID,
@@ -132,10 +234,7 @@ async def handle_chat_completions(request: web.Request) -> web.Response:
                     )
                     response_text = _response_text(retry_response)
                     if not response_text or not response_text.strip():
-                        logger.warning(
-                            "Empty response after retry for session {}, using fallback",
-                            session_key,
-                        )
+                        logger.warning("Empty response after retry, using fallback")
                         response_text = _FALLBACK
 
             except asyncio.TimeoutError:
@@ -183,7 +282,7 @@ def create_app(agent_loop, model_name: str = "nanobot", request_timeout: float =
         model_name: Model name reported in responses.
         request_timeout: Per-request timeout in seconds.
     """
-    app = web.Application()
+    app = web.Application(client_max_size=20 * 1024 * 1024)  # 20MB for base64 images
     app["agent_loop"] = agent_loop
     app["model_name"] = model_name
     app["request_timeout"] = request_timeout

nanobot/channels/base.py

@@ -116,7 +116,13 @@ class BaseChannel(ABC):
 
     def is_allowed(self, sender_id: str) -> bool:
         """Check if *sender_id* is permitted.  Empty list → deny all; ``"*"`` → allow all."""
-        allow_list = getattr(self.config, "allow_from", [])
+        if isinstance(self.config, dict):
+            if "allow_from" in self.config:
+                allow_list = self.config.get("allow_from")
+            else:
+                allow_list = self.config.get("allowFrom", [])
+        else:
+            allow_list = getattr(self.config, "allow_from", [])
         if not allow_list:
             logger.warning("{}: allow_from is empty — all access denied", self.name)
             return False

nanobot/channels/feishu.py

@@ -1290,7 +1290,6 @@ class FeishuChannel(BaseChannel):
 
         Supported metadata keys:
             _stream_end: Finalize the streaming card.
-            _resuming:   Mid-turn pause – flush but keep the buffer alive.
             _tool_hint:  Delta is a formatted tool hint (for display only).
             message_id:  Original message id (used with _stream_end for reaction cleanup).
             reaction_id: Reaction id to remove on stream end.
@@ -1309,50 +1308,44 @@ class FeishuChannel(BaseChannel):
                 if self.config.done_emoji and message_id:
                     await self._add_reaction(message_id, self.config.done_emoji)
 
-            resuming = meta.get("_resuming", False)
-            if resuming:
-                # Mid-turn pause (e.g. tool call between streaming segments).
-                # Flush current text to card but keep the buffer alive so the
-                # next segment appends to the same card.
-                buf = self._stream_bufs.get(chat_id)
-                if buf and buf.card_id and buf.text:
-                    buf.sequence += 1
-                    await loop.run_in_executor(
-                        None, self._stream_update_text_sync, buf.card_id, buf.text, buf.sequence,
-                    )
-                return
-
             buf = self._stream_bufs.pop(chat_id, None)
             if not buf or not buf.text:
                 return
+            # Try to finalize via streaming card; if that fails (e.g.
+            # streaming mode was closed by Feishu due to timeout), fall
+            # back to sending a regular interactive card.
             if buf.card_id:
                 buf.sequence += 1
-                await loop.run_in_executor(
+                ok = await loop.run_in_executor(
                     None,
                     self._stream_update_text_sync,
                     buf.card_id,
                     buf.text,
                     buf.sequence,
                 )
-                # Required so the chat list preview exits the streaming placeholder (Feishu streaming card docs).
-                buf.sequence += 1
-                await loop.run_in_executor(
-                    None,
-                    self._close_streaming_mode_sync,
-                    buf.card_id,
-                    buf.sequence,
-                )
-            else:
-                for chunk in self._split_elements_by_table_limit(
-                    self._build_card_elements(buf.text)
-                ):
-                    card = json.dumps(
-                        {"config": {"wide_screen_mode": True}, "elements": chunk},
-                        ensure_ascii=False,
-                    )
+                if ok:
+                    buf.sequence += 1
                     await loop.run_in_executor(
-                        None, self._send_message_sync, rid_type, chat_id, "interactive", card
+                        None,
+                        self._close_streaming_mode_sync,
+                        buf.card_id,
+                        buf.sequence,
                     )
+                    return
+                logger.warning(
+                    "Streaming card {} final update failed, falling back to regular card",
+                    buf.card_id,
+                )
+            for chunk in self._split_elements_by_table_limit(
+                self._build_card_elements(buf.text)
+            ):
+                card = json.dumps(
+                    {"config": {"wide_screen_mode": True}, "elements": chunk},
+                    ensure_ascii=False,
+                )
+                await loop.run_in_executor(
+                    None, self._send_message_sync, rid_type, chat_id, "interactive", card
+                )
             return
 
         # --- accumulate delta ---
@@ -1404,14 +1397,21 @@ class FeishuChannel(BaseChannel):
                 if buf and buf.card_id:
                     # Delegate to send_delta so tool hints get the same
                     # throttling (and card creation) as regular text deltas.
-                    lines = self.__class__._format_tool_hint_lines(hint).split("\n")
-                    delta = "\n\n" + "\n".join(
-                        f"{self.config.tool_hint_prefix} {ln}" for ln in lines if ln.strip()
-                    ) + "\n\n"
-                    await self.send_delta(msg.chat_id, delta)
+                    await self.send_delta(
+                        msg.chat_id,
+                        "\n\n" + self._format_tool_hint_delta(hint) + "\n\n",
+                    )
                     return
-                await self._send_tool_hint_card(
-                    receive_id_type, msg.chat_id, hint
+                # No active streaming card — send as a regular
+                # interactive card with the same 🔧 prefix style.
+                card = json.dumps(
+                    {"config": {"wide_screen_mode": True}, "elements": [
+                        {"tag": "markdown", "content": self._format_tool_hint_delta(hint)},
+                    ]},
+                    ensure_ascii=False,
+                )
+                await loop.run_in_executor(
+                    None, self._send_message_sync, receive_id_type, msg.chat_id, "interactive", card
                 )
                 return
 
@@ -1708,33 +1708,9 @@ class FeishuChannel(BaseChannel):
 
         return "\n".join(part for part in parts if part)
 
-    async def _send_tool_hint_card(
-        self, receive_id_type: str, receive_id: str, tool_hint: str
-    ) -> None:
-        """Send tool hint as an interactive card with formatted code block.
-
-        Args:
-            receive_id_type: "chat_id" or "open_id"
-            receive_id: The target chat or user ID
-            tool_hint: Formatted tool hint string (e.g., 'web_search("q"), read_file("path")')
-        """
-        loop = asyncio.get_running_loop()
-
-        # Put each top-level tool call on its own line without altering commas inside arguments.
-        formatted_code = self.__class__._format_tool_hint_lines(tool_hint)
-
-        card = {
-            "config": {"wide_screen_mode": True},
-            "elements": [
-                {"tag": "markdown", "content": f"**Tool Calls**\n\n```text\n{formatted_code}\n```"}
-            ],
-        }
-
-        await loop.run_in_executor(
-            None,
-            self._send_message_sync,
-            receive_id_type,
-            receive_id,
-            "interactive",
-            json.dumps(card, ensure_ascii=False),
+    def _format_tool_hint_delta(self, tool_hint: str) -> str:
+        """Format a tool hint string with the 🔧 prefix for each line."""
+        lines = self.__class__._format_tool_hint_lines(tool_hint).split("\n")
+        return "\n".join(
+            f"{self.config.tool_hint_prefix} {ln}" for ln in lines if ln.strip()
         )

nanobot/channels/manager.py

@@ -75,7 +75,15 @@ class ChannelManager:
 
     def _validate_allow_from(self) -> None:
         for name, ch in self.channels.items():
-            if getattr(ch.config, "allow_from", None) == []:
+            cfg = ch.config
+            if isinstance(cfg, dict):
+                if "allow_from" in cfg:
+                    allow = cfg.get("allow_from")
+                else:
+                    allow = cfg.get("allowFrom")
+            else:
+                allow = getattr(cfg, "allow_from", None)
+            if allow == []:
                 raise SystemExit(
                     f'Error: "{name}" has empty allowFrom (denies all). '
                     f'Set ["*"] to allow everyone, or add specific user IDs.'

nanobot/channels/slack.py

@@ -5,6 +5,7 @@ import re
 from typing import Any
 
 from loguru import logger
+from pydantic import Field
 from slack_sdk.socket_mode.request import SocketModeRequest
 from slack_sdk.socket_mode.response import SocketModeResponse
 from slack_sdk.socket_mode.websockets import SocketModeClient
@@ -13,8 +14,6 @@ from slackify_markdown import slackify_markdown
 
 from nanobot.bus.events import OutboundMessage
 from nanobot.bus.queue import MessageBus
-from pydantic import Field
-
 from nanobot.channels.base import BaseChannel
 from nanobot.config.schema import Base
 
@@ -50,6 +49,9 @@ class SlackChannel(BaseChannel):
 
     name = "slack"
     display_name = "Slack"
+    _SLACK_ID_RE = re.compile(r"^[CDGUW][A-Z0-9]{2,}$")
+    _SLACK_CHANNEL_REF_RE = re.compile(r"^<#([A-Z0-9]+)(?:\|[^>]+)?>$")
+    _SLACK_USER_REF_RE = re.compile(r"^<@([A-Z0-9]+)(?:\|[^>]+)?>$")
 
     @classmethod
     def default_config(cls) -> dict[str, Any]:
@@ -63,6 +65,7 @@ class SlackChannel(BaseChannel):
         self._web_client: AsyncWebClient | None = None
         self._socket_client: SocketModeClient | None = None
         self._bot_user_id: str | None = None
+        self._target_cache: dict[str, str] = {}
 
     async def start(self) -> None:
         """Start the Slack Socket Mode client."""
@@ -113,17 +116,23 @@ class SlackChannel(BaseChannel):
             logger.warning("Slack client not running")
             return
         try:
+            target_chat_id = await self._resolve_target_chat_id(msg.chat_id)
             slack_meta = msg.metadata.get("slack", {}) if msg.metadata else {}
             thread_ts = slack_meta.get("thread_ts")
             channel_type = slack_meta.get("channel_type")
+            origin_chat_id = str((slack_meta.get("event", {}) or {}).get("channel") or msg.chat_id)
             # Slack DMs don't use threads; channel/group replies may keep thread_ts.
-            thread_ts_param = thread_ts if thread_ts and channel_type != "im" else None
+            thread_ts_param = (
+                thread_ts
+                if thread_ts and channel_type != "im" and target_chat_id == origin_chat_id
+                else None
+            )
 
             # Slack rejects empty text payloads. Keep media-only messages media-only,
             # but send a single blank message when the bot has no text or files to send.
             if msg.content or not (msg.media or []):
                 await self._web_client.chat_postMessage(
-                    channel=msg.chat_id,
+                    channel=target_chat_id,
                     text=self._to_mrkdwn(msg.content) if msg.content else " ",
                     thread_ts=thread_ts_param,
                 )
@@ -131,7 +140,7 @@ class SlackChannel(BaseChannel):
             for media_path in msg.media or []:
                 try:
                     await self._web_client.files_upload_v2(
-                        channel=msg.chat_id,
+                        channel=target_chat_id,
                         file=media_path,
                         thread_ts=thread_ts_param,
                     )
@@ -141,12 +150,123 @@ class SlackChannel(BaseChannel):
             # Update reaction emoji when the final (non-progress) response is sent
             if not (msg.metadata or {}).get("_progress"):
                 event = slack_meta.get("event", {})
-                await self._update_react_emoji(msg.chat_id, event.get("ts"))
+                await self._update_react_emoji(origin_chat_id, event.get("ts"))
 
         except Exception as e:
             logger.error("Error sending Slack message: {}", e)
             raise
 
+    async def _resolve_target_chat_id(self, target: str) -> str:
+        """Resolve human-friendly Slack targets to concrete IDs when needed."""
+        if not self._web_client:
+            return target
+
+        target = target.strip()
+        if not target:
+            return target
+
+        if match := self._SLACK_CHANNEL_REF_RE.fullmatch(target):
+            return match.group(1)
+        if match := self._SLACK_USER_REF_RE.fullmatch(target):
+            return await self._open_dm_for_user(match.group(1))
+        if self._SLACK_ID_RE.fullmatch(target):
+            if target.startswith(("U", "W")):
+                return await self._open_dm_for_user(target)
+            return target
+
+        if target.startswith("#"):
+            return await self._resolve_channel_name(target[1:])
+        if target.startswith("@"):
+            return await self._resolve_user_handle(target[1:])
+
+        try:
+            return await self._resolve_channel_name(target)
+        except ValueError:
+            return await self._resolve_user_handle(target)
+
+    async def _resolve_channel_name(self, name: str) -> str:
+        normalized = self._normalize_target_name(name)
+        if not normalized:
+            raise ValueError("Slack target channel name is empty")
+
+        cache_key = f"channel:{normalized}"
+        if cache_key in self._target_cache:
+            return self._target_cache[cache_key]
+
+        cursor: str | None = None
+        while True:
+            response = await self._web_client.conversations_list(
+                types="public_channel,private_channel",
+                exclude_archived=True,
+                limit=200,
+                cursor=cursor,
+            )
+            for channel in response.get("channels", []):
+                if self._normalize_target_name(str(channel.get("name") or "")) == normalized:
+                    channel_id = str(channel.get("id") or "")
+                    if channel_id:
+                        self._target_cache[cache_key] = channel_id
+                        return channel_id
+            cursor = ((response.get("response_metadata") or {}).get("next_cursor") or "").strip()
+            if not cursor:
+                break
+
+        raise ValueError(
+            f"Slack channel '{name}' was not found. Use a joined channel name like "
+            f"'#general' or a concrete channel ID."
+        )
+
+    async def _resolve_user_handle(self, handle: str) -> str:
+        normalized = self._normalize_target_name(handle)
+        if not normalized:
+            raise ValueError("Slack target user handle is empty")
+
+        cache_key = f"user:{normalized}"
+        if cache_key in self._target_cache:
+            return self._target_cache[cache_key]
+
+        cursor: str | None = None
+        while True:
+            response = await self._web_client.users_list(limit=200, cursor=cursor)
+            for member in response.get("members", []):
+                if self._member_matches_handle(member, normalized):
+                    user_id = str(member.get("id") or "")
+                    if not user_id:
+                        continue
+                    dm_id = await self._open_dm_for_user(user_id)
+                    self._target_cache[cache_key] = dm_id
+                    return dm_id
+            cursor = ((response.get("response_metadata") or {}).get("next_cursor") or "").strip()
+            if not cursor:
+                break
+
+        raise ValueError(
+            f"Slack user '{handle}' was not found. Use '@name' or a concrete DM/channel ID."
+        )
+
+    async def _open_dm_for_user(self, user_id: str) -> str:
+        response = await self._web_client.conversations_open(users=user_id)
+        channel_id = str(((response.get("channel") or {}).get("id")) or "")
+        if not channel_id:
+            raise ValueError(f"Slack DM target for user '{user_id}' could not be opened.")
+        return channel_id
+
+    @staticmethod
+    def _normalize_target_name(value: str) -> str:
+        return value.strip().lstrip("#@").lower()
+
+    @classmethod
+    def _member_matches_handle(cls, member: dict[str, Any], normalized: str) -> bool:
+        profile = member.get("profile") or {}
+        candidates = {
+            str(member.get("name") or ""),
+            str(profile.get("display_name") or ""),
+            str(profile.get("display_name_normalized") or ""),
+            str(profile.get("real_name") or ""),
+            str(profile.get("real_name_normalized") or ""),
+        }
+        return normalized in {cls._normalize_target_name(candidate) for candidate in candidates if candidate}
+
     async def _on_socket_request(
         self,
         client: SocketModeClient,

nanobot/channels/wecom.py

@@ -302,13 +302,22 @@ class WecomChannel(BaseChannel):
 
             elif msg_type == "mixed":
                 # Mixed content contains multiple message items
-                msg_items = body.get("mixed", {}).get("item", [])
+                msg_items = body.get("mixed", {}).get("msg_item", [])
                 for item in msg_items:
-                    item_type = item.get("type", "")
+                    item_type = item.get("msgtype", "")
                     if item_type == "text":
                         text = item.get("text", {}).get("content", "")
                         if text:
                             content_parts.append(text)
+                    elif item_type == "image":
+                        file_url = item.get("image", {}).get("url", "")
+                        aes_key = item.get("image", {}).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}]")
+                                media_paths.append(file_path)
                     else:
                         content_parts.append(MSG_TYPE_MAP.get(item_type, f"[{item_type}]"))
 

nanobot/cli/commands.py

@@ -821,6 +821,48 @@ def gateway(
 
     console.print(f"[green]✓[/green] Heartbeat: every {hb_cfg.interval_s}s")
 
+    async def _health_server(host: str, health_port: int):
+        """Lightweight HTTP health endpoint on the gateway port."""
+        import json as _json
+
+        async def handle(reader, writer):
+            try:
+                data = await asyncio.wait_for(reader.read(4096), timeout=5)
+            except (asyncio.TimeoutError, ConnectionError):
+                writer.close()
+                return
+
+            request_line = data.split(b"\r\n", 1)[0].decode("utf-8", errors="replace")
+            method, path = "", ""
+            parts = request_line.split(" ")
+            if len(parts) >= 2:
+                method, path = parts[0], parts[1]
+
+            if method == "GET" and path == "/health":
+                body = _json.dumps({"status": "ok"})
+                resp = (
+                    f"HTTP/1.0 200 OK\r\n"
+                    f"Content-Type: application/json\r\n"
+                    f"Content-Length: {len(body)}\r\n"
+                    f"\r\n{body}"
+                )
+            else:
+                body = "Not Found"
+                resp = (
+                    f"HTTP/1.0 404 Not Found\r\n"
+                    f"Content-Type: text/plain\r\n"
+                    f"Content-Length: {len(body)}\r\n"
+                    f"\r\n{body}"
+                )
+
+            writer.write(resp.encode())
+            await writer.drain()
+            writer.close()
+
+        server = await asyncio.start_server(handle, host, health_port)
+        console.print(f"[green]✓[/green] Health endpoint: http://{host}:{health_port}/health")
+        async with server:
+            await server.serve_forever()
     # Register Dream system job (always-on, idempotent on restart)
     dream_cfg = config.agents.defaults.dream
     if dream_cfg.model_override:
@@ -843,6 +885,7 @@ def gateway(
             await asyncio.gather(
                 agent.run(),
                 channels.start_all(),
+                _health_server(config.gateway.host, port),
             )
         except KeyboardInterrupt:
             console.print("\nShutting down...")
@@ -964,7 +1007,7 @@ def agent(
         # Interactive mode — route through bus like other channels
         from nanobot.bus.events import InboundMessage
         _init_prompt_session()
-        console.print(f"{__logo__} Interactive mode (type [bold]exit[/bold] or [bold]Ctrl+C[/bold] to quit)\n")
+        console.print(f"{__logo__} Interactive mode [bold blue]({config.agents.defaults.model})[/bold blue] — type [bold]exit[/bold] or [bold]Ctrl+C[/bold] to quit\n")
 
         if ":" in session_id:
             cli_channel, cli_chat_id = session_id.split(":", 1)

nanobot/cli/stream.py

@@ -102,7 +102,7 @@ class StreamRenderer:
             self._live = Live(self._render(), console=c, auto_refresh=False)
             self._live.start()
         now = time.monotonic()
-        if "\n" in delta or (now - self._t) > 0.05:
+        if (now - self._t) > 0.15:
             self._live.update(self._render())
             self._live.refresh()
             self._t = now

nanobot/command/builtin.py

@@ -74,6 +74,12 @@ async def cmd_status(ctx: CommandContext) -> OutboundMessage:
             search_usage_text = usage.format()
     except Exception:
         pass  # Never let usage fetch break /status
+    active_tasks = loop._active_tasks.get(ctx.key, [])
+    task_count = sum(1 for t in active_tasks if not t.done())
+    try:
+        task_count += loop.subagents.get_running_count_by_session(ctx.key)
+    except Exception:
+        pass
     return OutboundMessage(
         channel=ctx.msg.channel,
         chat_id=ctx.msg.chat_id,
@@ -84,6 +90,7 @@ async def cmd_status(ctx: CommandContext) -> OutboundMessage:
             session_msg_count=len(session.get_history(max_messages=0)),
             context_tokens_estimate=ctx_est,
             search_usage_text=search_usage_text,
+            active_task_count=task_count,
         ),
         metadata={**dict(ctx.msg.metadata or {}), "render_as": "text"},
     )

nanobot/config/schema.py

@@ -152,7 +152,7 @@ class ApiConfig(Base):
 class GatewayConfig(Base):
     """Gateway/server configuration."""
 
-    host: str = "0.0.0.0"
+    host: str = "127.0.0.1"  # Safer default: local-only bind.
     port: int = 18790
     heartbeat: HeartbeatConfig = Field(default_factory=HeartbeatConfig)
 

nanobot/providers/base.py

@@ -718,9 +718,22 @@ class LLMProvider(ABC):
                     identical_error_count,
                     (response.content or "")[:120].lower(),
                 )
+                if on_retry_wait:
+                    await on_retry_wait(
+                        f"Persistent retry stopped after {identical_error_count} identical errors."
+                    )
                 return response
 
             if not persistent and attempt > len(delays):
+                logger.warning(
+                    "LLM request failed after {} retries, giving up: {}",
+                    attempt,
+                    (response.content or "")[:120].lower(),
+                )
+                if on_retry_wait:
+                    await on_retry_wait(
+                        f"Model request failed after {attempt} retries, giving up."
+                    )
                 break
 
             base_delay = delays[min(attempt - 1, len(delays) - 1)]

nanobot/providers/openai_compat_provider.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import asyncio
+import json
 import hashlib
 import importlib.util
 import os
@@ -49,6 +50,29 @@ _DEFAULT_OPENROUTER_HEADERS = {
     "X-OpenRouter-Title": "nanobot",
     "X-OpenRouter-Categories": "cli-agent,personal-agent",
 }
+_KIMI_THINKING_MODELS: frozenset[str] = frozenset({
+    "kimi-k2.5",
+    "k2.6-code-preview",
+})
+
+
+def _is_kimi_thinking_model(model_name: str) -> bool:
+    """Return True if model_name refers to a Kimi thinking-capable model.
+
+    Supports two forms:
+    - Exact match: kimi-k2.5 in _KIMI_THINKING_MODELS
+    - Slug match:  moonshotai/kimi-k2.5 -> the part after the last "/"
+                   is checked against _KIMI_THINKING_MODELS
+
+    This covers both the native Moonshot provider (bare slug) and
+    OpenRouter-style names (``"publisher/slug"``).
+    """
+    name = model_name.lower()
+    if name in _KIMI_THINKING_MODELS:
+        return True
+    if "/" in name and name.rsplit("/", 1)[1] in _KIMI_THINKING_MODELS:
+        return True
+    return False
 
 
 def _short_tool_id() -> str:
@@ -222,6 +246,24 @@ class OpenAICompatProvider(LLMProvider):
             return tool_call_id
         return hashlib.sha1(tool_call_id.encode()).hexdigest()[:9]
 
+    @staticmethod
+    def _normalize_tool_call_arguments(arguments: Any) -> str:
+        """Force function.arguments into a valid JSON object string."""
+        if isinstance(arguments, str):
+            stripped = arguments.strip()
+            if not stripped:
+                return "{}"
+            try:
+                parsed = json_repair.loads(stripped)
+            except Exception:
+                return "{}"
+            if isinstance(parsed, dict):
+                return json.dumps(parsed, ensure_ascii=False)
+            return "{}"
+        if isinstance(arguments, dict):
+            return json.dumps(arguments, ensure_ascii=False)
+        return "{}"
+
     def _sanitize_messages(self, messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
         """Strip non-standard keys, normalize tool_call IDs."""
         sanitized = LLMProvider._sanitize_request_messages(messages, _ALLOWED_MSG_KEYS)
@@ -241,6 +283,16 @@ class OpenAICompatProvider(LLMProvider):
                         continue
                     tc_clean = dict(tc)
                     tc_clean["id"] = map_id(tc_clean.get("id"))
+                    function = tc_clean.get("function")
+                    if isinstance(function, dict):
+                        function_clean = dict(function)
+                        if "arguments" in function_clean:
+                            function_clean["arguments"] = self._normalize_tool_call_arguments(
+                                function_clean.get("arguments")
+                            )
+                        else:
+                            function_clean["arguments"] = "{}"
+                        tc_clean["function"] = function_clean
                     normalized.append(tc_clean)
                 clean["tool_calls"] = normalized
                 if clean.get("role") == "assistant":
@@ -334,6 +386,16 @@ class OpenAICompatProvider(LLMProvider):
             if extra:
                 kwargs.setdefault("extra_body", {}).update(extra)
 
+        # Model-level thinking injection for Kimi thinking-capable models.
+        # Strip any provider prefix (e.g. "moonshotai/") before the set lookup
+        # so that OpenRouter-style names like "moonshotai/kimi-k2.5" are handled
+        # identically to bare names like "kimi-k2.5".
+        if reasoning_effort is not None and _is_kimi_thinking_model(model_name):
+            thinking_enabled = reasoning_effort.lower() != "minimal"
+            kwargs.setdefault("extra_body", {}).update(
+                {"thinking": {"type": "enabled" if thinking_enabled else "disabled"}}
+            )
+
         if tools:
             kwargs["tools"] = tools
             kwargs["tool_choice"] = tool_choice or "auto"

nanobot/templates/agent/skills_section.md

@@ -1,6 +1,6 @@
 # Skills
 
 The following skills extend your capabilities. To use a skill, read its SKILL.md file using the read_file tool.
-Skills with available="false" need dependencies installed first - you can try installing them with apt/brew.
+Unavailable skills need dependencies installed first — you can try installing them with apt/brew.
 
 {{ skills_summary }}

nanobot/utils/document.py

@@ -0,0 +1,267 @@
+"""Document text extraction utilities for nanobot."""
+
+import mimetypes
+from pathlib import Path
+
+from loguru import logger
+
+from nanobot.utils.helpers import detect_image_mime
+
+try:
+    from pypdf import PdfReader
+except ImportError:
+    PdfReader = None  # type: ignore
+
+try:
+    from docx import Document as DocxDocument
+except ImportError:
+    DocxDocument = None  # type: ignore
+
+try:
+    from openpyxl import load_workbook
+except ImportError:
+    load_workbook = None  # type: ignore
+
+try:
+    from pptx import Presentation as PptxPresentation
+except ImportError:
+    PptxPresentation = None  # type: ignore
+
+
+# Supported file extensions for text extraction
+SUPPORTED_EXTENSIONS: set[str] = {
+    # Document formats
+    ".pdf",
+    ".docx",
+    ".xlsx",
+    ".pptx",
+    # Text formats
+    ".txt",
+    ".md",
+    ".csv",
+    ".json",
+    ".xml",
+    ".html",
+    ".htm",
+    ".log",
+    ".yaml",
+    ".yml",
+    ".toml",
+    ".ini",
+    ".cfg",
+    # Image formats (for future OCR support)
+    ".png",
+    ".jpg",
+    ".jpeg",
+    ".gif",
+    ".webp",
+}
+
+_MAX_TEXT_LENGTH = 200_000
+
+
+def extract_text(path: Path) -> str | None:
+    """Extract text from a file.
+
+    Args:
+        path: Path to the file.
+
+    Returns:
+        Extracted text as string, None for unsupported types,
+        or error string for failures.
+    """
+    if not isinstance(path, Path):
+        path = Path(path)
+
+    if not path.exists():
+        return f"[error: file not found: {path}]"
+
+    ext = path.suffix.lower()
+
+    # Document formats
+    if ext == ".pdf":
+        if PdfReader is None:
+            return "[error: pypdf not installed]"
+        return _extract_pdf(path)
+    elif ext == ".docx":
+        if DocxDocument is None:
+            return "[error: python-docx not installed]"
+        return _extract_docx(path)
+    elif ext == ".xlsx":
+        if load_workbook is None:
+            return "[error: openpyxl not installed]"
+        return _extract_xlsx(path)
+    elif ext == ".pptx":
+        if PptxPresentation is None:
+            return "[error: python-pptx not installed]"
+        return _extract_pptx(path)
+    elif _is_text_extension(ext):
+        return _extract_text_file(path)
+    elif ext in {".png", ".jpg", ".jpeg", ".gif", ".webp"}:
+        # Image files - for future OCR support
+        return f"[image: {path.name}]"
+    else:
+        # Unsupported extension
+        return None
+
+
+def _extract_pdf(path: Path) -> str:
+    """Extract text from PDF using pypdf."""
+    try:
+        reader = PdfReader(path)
+        pages: list[str] = []
+        for i, page in enumerate(reader.pages, 1):
+            text = page.extract_text() or ""
+            pages.append(f"--- Page {i} ---\n{text}")
+        return _truncate("\n\n".join(pages), _MAX_TEXT_LENGTH)
+    except Exception as e:
+        logger.error("Failed to extract PDF {}: {}", path, e)
+        return f"[error: failed to extract PDF: {e!s}]"
+
+
+def _extract_docx(path: Path) -> str:
+    """Extract text from DOCX using python-docx."""
+    try:
+        doc = DocxDocument(path)
+        paragraphs: list[str] = [p.text for p in doc.paragraphs if p.text.strip()]
+        return _truncate("\n\n".join(paragraphs), _MAX_TEXT_LENGTH)
+    except Exception as e:
+        logger.error("Failed to extract DOCX {}: {}", path, e)
+        return f"[error: failed to extract DOCX: {e!s}]"
+
+
+def _extract_xlsx(path: Path) -> str:
+    """Extract text from XLSX using openpyxl."""
+    try:
+        wb = load_workbook(path, read_only=True, data_only=True)
+        sheets: list[str] = []
+        for sheet_name in wb.sheetnames:
+            ws = wb[sheet_name]
+            rows: list[str] = []
+            for row in ws.iter_rows(values_only=True):
+                row_text = "\t".join(str(cell) if cell is not None else "" for cell in row)
+                if row_text.strip():
+                    rows.append(row_text)
+            if rows:
+                sheets.append(f"--- Sheet: {sheet_name} ---\n" + "\n".join(rows))
+        wb.close()
+        return _truncate("\n\n".join(sheets), _MAX_TEXT_LENGTH)
+    except Exception as e:
+        logger.error("Failed to extract XLSX {}: {}", path, e)
+        return f"[error: failed to extract XLSX: {e!s}]"
+
+
+def _extract_pptx(path: Path) -> str:
+    """Extract text from PPTX using python-pptx."""
+    try:
+        prs = PptxPresentation(path)
+        slides: list[str] = []
+        for i, slide in enumerate(prs.slides, 1):
+            slide_text: list[str] = []
+            for shape in slide.shapes:
+                if hasattr(shape, "text") and shape.text:
+                    slide_text.append(shape.text)
+            if slide_text:
+                slides.append(f"--- Slide {i} ---\n" + "\n".join(slide_text))
+        return _truncate("\n\n".join(slides), _MAX_TEXT_LENGTH)
+    except Exception as e:
+        logger.error("Failed to extract PPTX {}: {}", path, e)
+        return f"[error: failed to extract PPTX: {e!s}]"
+
+
+def _extract_text_file(path: Path) -> str:
+    """Extract text from a plain text file."""
+    try:
+        # Try UTF-8 first, then latin-1 fallback
+        try:
+            content = path.read_text(encoding="utf-8")
+        except UnicodeDecodeError:
+            content = path.read_text(encoding="latin-1")
+        return _truncate(content, _MAX_TEXT_LENGTH)
+    except Exception as e:
+        logger.error("Failed to read text file {}: {}", path, e)
+        return f"[error: failed to read file: {e!s}]"
+
+
+def _truncate(text: str, max_length: int) -> str:
+    """Truncate text with a suffix indicating truncation."""
+    if len(text) <= max_length:
+        return text
+    return text[:max_length] + f"... (truncated, {len(text)} chars total)"
+
+
+def _is_text_extension(ext: str) -> bool:
+    """Check if extension is a text format."""
+    return ext in {
+        ".txt",
+        ".md",
+        ".csv",
+        ".json",
+        ".xml",
+        ".html",
+        ".htm",
+        ".log",
+        ".yaml",
+        ".yml",
+        ".toml",
+        ".ini",
+        ".cfg",
+    }
+
+
+# ---------------------------------------------------------------------------
+# High-level helper: split media into images + extracted document text
+# ---------------------------------------------------------------------------
+
+_MAX_EXTRACT_FILE_SIZE = 50 * 1024 * 1024  # 50 MB
+
+
+def extract_documents(
+    text: str,
+    media_paths: list[str],
+    *,
+    max_file_size: int = _MAX_EXTRACT_FILE_SIZE,
+) -> tuple[str, list[str]]:
+    """Separate images from documents in *media_paths*.
+
+    Documents (PDF, DOCX, XLSX, PPTX, plain-text, …) have their text
+    extracted and appended to *text*.  Only image paths are kept in the
+    returned list so that downstream layers only need to handle vision
+    blocks.
+
+    Files larger than *max_file_size* bytes are skipped with a warning
+    to avoid unbounded memory / CPU usage.
+    """
+    image_paths: list[str] = []
+    doc_texts: list[str] = []
+
+    for path_str in media_paths:
+        p = Path(path_str)
+        if not p.is_file():
+            continue
+
+        try:
+            size = p.stat().st_size
+        except OSError:
+            continue
+        if size > max_file_size:
+            logger.warning(
+                "Skipping oversized file for extraction: {} ({:.1f} MB > {} MB limit)",
+                p.name, size / (1024 * 1024), max_file_size // (1024 * 1024),
+            )
+            continue
+
+        with open(p, "rb") as f:
+            header = f.read(16)
+        mime = detect_image_mime(header) or mimetypes.guess_type(path_str)[0]
+        if mime and mime.startswith("image/"):
+            image_paths.append(path_str)
+        else:
+            extracted = extract_text(p)
+            if extracted and not extracted.startswith("[error:"):
+                doc_texts.append(f"[File: {p.name}]\n{extracted}")
+
+    if doc_texts:
+        text = text + "\n\n" + "\n\n".join(doc_texts)
+
+    return text, image_paths

nanobot/utils/helpers.py

@@ -400,6 +400,7 @@ def build_status_content(
     session_msg_count: int,
     context_tokens_estimate: int,
     search_usage_text: str | None = None,
+    active_task_count: int = 0,
 ) -> str:
     """Build a human-readable runtime status snapshot.
     
@@ -431,6 +432,7 @@ def build_status_content(
         f"\U0001f4da Context: {ctx_used_str}/{ctx_total_str} ({ctx_pct}%)",
         f"\U0001f4ac Session: {session_msg_count} messages",
         f"\u23f1 Uptime: {uptime}",
+        f"\u26a1 Tasks: {active_task_count} active",
     ]
     if search_usage_text:
         lines.append(search_usage_text)