Merge branch 'HKUDS:main' into feat/improve-tool-validation-tests

nanobot/agent/context.py

@@ -10,6 +10,7 @@ from typing import Any
 
 from nanobot.agent.memory import MemoryStore
 from nanobot.agent.skills import SkillsLoader
+from nanobot.utils.helpers import detect_image_mime
 
 
 class ContextBuilder:
@@ -136,10 +137,14 @@ Reply directly with text for conversations. Only use the 'message' tool to send
         images = []
         for path in media:
             p = Path(path)
-            mime, _ = mimetypes.guess_type(path)
-            if not p.is_file() or not mime or not mime.startswith("image/"):
+            if not p.is_file():
                 continue
-            b64 = base64.b64encode(p.read_bytes()).decode()
+            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
+            b64 = base64.b64encode(raw).decode()
             images.append({"type": "image_url", "image_url": {"url": f"data:{mime};base64,{b64}"}})
 
         if not images:

nanobot/agent/loop.py

@@ -202,9 +202,18 @@ class AgentLoop:
 
             if response.has_tool_calls:
                 if on_progress:
-                    clean = self._strip_think(response.content)
-                    if clean:
-                        await on_progress(clean)
+                    thoughts = [
+                        self._strip_think(response.content),
+                        response.reasoning_content,
+                        *(
+                            f"Thinking [{b.get('signature', '...')}]:\n{b.get('thought', '...')}"
+                            for b in (response.thinking_blocks or [])
+                            if isinstance(b, dict) and "signature" in b
+                        ),
+                    ]
+                    combined_thoughts = "\n\n".join(filter(None, thoughts))
+                    if combined_thoughts:
+                        await on_progress(combined_thoughts)
                     await on_progress(self._tool_hint(response.tool_calls), tool_hint=True)
 
                 tool_call_dicts = [

nanobot/agent/memory.py

@@ -128,6 +128,13 @@ class MemoryStore:
             # Some providers return arguments as a JSON string instead of dict
             if isinstance(args, str):
                 args = json.loads(args)
+            # Some providers return arguments as a list (handle edge case)
+            if isinstance(args, list):
+                if args and isinstance(args[0], dict):
+                    args = args[0]
+                else:
+                    logger.warning("Memory consolidation: unexpected arguments as empty or non-dict list")
+                    return False
             if not isinstance(args, dict):
                 logger.warning("Memory consolidation: unexpected arguments type {}", type(args).__name__)
                 return False

nanobot/agent/tools/mcp.py

@@ -58,17 +58,48 @@ async def connect_mcp_servers(
 ) -> None:
     """Connect to configured MCP servers and register their tools."""
     from mcp import ClientSession, StdioServerParameters
+    from mcp.client.sse import sse_client
     from mcp.client.stdio import stdio_client
+    from mcp.client.streamable_http import streamable_http_client
 
     for name, cfg in mcp_servers.items():
         try:
-            if cfg.command:
+            transport_type = cfg.type
+            if not transport_type:
+                if cfg.command:
+                    transport_type = "stdio"
+                elif cfg.url:
+                    # Convention: URLs ending with /sse use SSE transport; others use streamableHttp
+                    transport_type = (
+                        "sse" if cfg.url.rstrip("/").endswith("/sse") else "streamableHttp"
+                    )
+                else:
+                    logger.warning("MCP server '{}': no command or url configured, skipping", name)
+                    continue
+
+            if transport_type == "stdio":
                 params = StdioServerParameters(
                     command=cfg.command, args=cfg.args, env=cfg.env or None
                 )
                 read, write = await stack.enter_async_context(stdio_client(params))
-            elif cfg.url:
-                from mcp.client.streamable_http import streamable_http_client
+            elif transport_type == "sse":
+                def httpx_client_factory(
+                    headers: dict[str, str] | None = None,
+                    timeout: httpx.Timeout | None = None,
+                    auth: httpx.Auth | None = None,
+                ) -> httpx.AsyncClient:
+                    merged_headers = {**(cfg.headers or {}), **(headers or {})}
+                    return httpx.AsyncClient(
+                        headers=merged_headers or None,
+                        follow_redirects=True,
+                        timeout=timeout,
+                        auth=auth,
+                    )
+
+                read, write = await stack.enter_async_context(
+                    sse_client(cfg.url, httpx_client_factory=httpx_client_factory)
+                )
+            elif transport_type == "streamableHttp":
                 # Always provide an explicit httpx client so MCP HTTP transport does not
                 # inherit httpx's default 5s timeout and preempt the higher-level tool timeout.
                 http_client = await stack.enter_async_context(
@@ -82,7 +113,7 @@ async def connect_mcp_servers(
                     streamable_http_client(cfg.url, http_client=http_client)
                 )
             else:
-                logger.warning("MCP server '{}': no command or url configured, skipping", name)
+                logger.warning("MCP server '{}': unknown transport type '{}'", name, transport_type)
                 continue
 
             session = await stack.enter_async_context(ClientSession(read, write))