Merge branch 'main' into pr-1920

nanobot/agent/loop.py

@@ -139,7 +139,7 @@ class AgentLoop:
             await self._mcp_stack.__aenter__()
             await connect_mcp_servers(self._mcp_servers, self.tools, self._mcp_stack)
             self._mcp_connected = True
-        except Exception as e:
+        except BaseException as e:
             logger.error("Failed to connect MCP servers (will retry next message): {}", e)
             if self._mcp_stack:
                 try:
@@ -292,7 +292,9 @@ class AgentLoop:
 
         async def _do_restart():
             await asyncio.sleep(1)
-            os.execv(sys.executable, [sys.executable] + sys.argv)
+            # Use -m nanobot instead of sys.argv[0] for Windows compatibility
+            # (sys.argv[0] may be just "nanobot" without full path on Windows)
+            os.execv(sys.executable, [sys.executable, "-m", "nanobot"] + sys.argv[1:])
 
         asyncio.create_task(_do_restart())
 

nanobot/agent/memory.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 import asyncio
 import json
 import weakref
+from datetime import datetime
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Callable
 
@@ -57,13 +58,30 @@ def _normalize_save_memory_args(args: Any) -> dict[str, Any] | None:
         return args[0] if args and isinstance(args[0], dict) else None
     return args if isinstance(args, dict) else None
 
+_TOOL_CHOICE_ERROR_MARKERS = (
+    "tool_choice",
+    "toolchoice",
+    "does not support",
+    'should be ["none", "auto"]',
+)
+
+
+def _is_tool_choice_unsupported(content: str | None) -> bool:
+    """Detect provider errors caused by forced tool_choice being unsupported."""
+    text = (content or "").lower()
+    return any(m in text for m in _TOOL_CHOICE_ERROR_MARKERS)
+
+
 class MemoryStore:
     """Two-layer memory: MEMORY.md (long-term facts) + HISTORY.md (grep-searchable log)."""
 
+    _MAX_FAILURES_BEFORE_RAW_ARCHIVE = 3
+
     def __init__(self, workspace: Path):
         self.memory_dir = ensure_dir(workspace / "memory")
         self.memory_file = self.memory_dir / "MEMORY.md"
         self.history_file = self.memory_dir / "HISTORY.md"
+        self._consecutive_failures = 0
 
     def read_long_term(self) -> str:
         if self.memory_file.exists():
@@ -112,38 +130,93 @@ class MemoryStore:
 ## Conversation to Process
 {self._format_messages(messages)}"""
 
+        chat_messages = [
+            {"role": "system", "content": "You are a memory consolidation agent. Call the save_memory tool with your consolidation of the conversation."},
+            {"role": "user", "content": prompt},
+        ]
+
         try:
+            forced = {"type": "function", "function": {"name": "save_memory"}}
             response = await provider.chat_with_retry(
-                messages=[
-                    {"role": "system", "content": "You are a memory consolidation agent. Call the save_memory tool with your consolidation of the conversation."},
-                    {"role": "user", "content": prompt},
-                ],
+                messages=chat_messages,
                 tools=_SAVE_MEMORY_TOOL,
                 model=model,
-                tool_choice="required",
+                tool_choice=forced,
             )
 
+            if response.finish_reason == "error" and _is_tool_choice_unsupported(
+                response.content
+            ):
+                logger.warning("Forced tool_choice unsupported, retrying with auto")
+                response = await provider.chat_with_retry(
+                    messages=chat_messages,
+                    tools=_SAVE_MEMORY_TOOL,
+                    model=model,
+                    tool_choice="auto",
+                )
+
             if not response.has_tool_calls:
-                logger.warning("Memory consolidation: LLM did not call save_memory, skipping")
-                return False
+                logger.warning(
+                    "Memory consolidation: LLM did not call save_memory "
+                    "(finish_reason={}, content_len={}, content_preview={})",
+                    response.finish_reason,
+                    len(response.content or ""),
+                    (response.content or "")[:200],
+                )
+                return self._fail_or_raw_archive(messages)
 
             args = _normalize_save_memory_args(response.tool_calls[0].arguments)
             if args is None:
                 logger.warning("Memory consolidation: unexpected save_memory arguments")
-                return False
+                return self._fail_or_raw_archive(messages)
 
-            if entry := args.get("history_entry"):
-                self.append_history(_ensure_text(entry))
-            if update := args.get("memory_update"):
-                update = _ensure_text(update)
-                if update != current_memory:
-                    self.write_long_term(update)
+            if "history_entry" not in args or "memory_update" not in args:
+                logger.warning("Memory consolidation: save_memory payload missing required fields")
+                return self._fail_or_raw_archive(messages)
 
+            entry = args["history_entry"]
+            update = args["memory_update"]
+
+            if entry is None or update is None:
+                logger.warning("Memory consolidation: save_memory payload contains null required fields")
+                return self._fail_or_raw_archive(messages)
+
+            entry = _ensure_text(entry).strip()
+            if not entry:
+                logger.warning("Memory consolidation: history_entry is empty after normalization")
+                return self._fail_or_raw_archive(messages)
+
+            self.append_history(entry)
+            update = _ensure_text(update)
+            if update != current_memory:
+                self.write_long_term(update)
+
+            self._consecutive_failures = 0
             logger.info("Memory consolidation done for {} messages", len(messages))
             return True
         except Exception:
             logger.exception("Memory consolidation failed")
+            return self._fail_or_raw_archive(messages)
+
+    def _fail_or_raw_archive(self, messages: list[dict]) -> bool:
+        """Increment failure count; after threshold, raw-archive messages and return True."""
+        self._consecutive_failures += 1
+        if self._consecutive_failures < self._MAX_FAILURES_BEFORE_RAW_ARCHIVE:
             return False
+        self._raw_archive(messages)
+        self._consecutive_failures = 0
+        return True
+
+    def _raw_archive(self, messages: list[dict]) -> None:
+        """Fallback: dump raw messages to HISTORY.md without LLM summarization."""
+        ts = datetime.now().strftime("%Y-%m-%d %H:%M")
+        self.append_history(
+            f"[{ts}] [RAW] {len(messages)} messages\n"
+            f"{self._format_messages(messages)}"
+        )
+        logger.warning(
+            "Memory consolidation degraded: raw-archived {} messages", len(messages)
+        )
 
 
 class MemoryConsolidator:

nanobot/channels/matrix.py

@@ -149,13 +149,22 @@ class MatrixChannel(BaseChannel):
     name = "matrix"
     display_name = "Matrix"
 
-    def __init__(self, config: Any, bus: MessageBus):
+    def __init__(
+        self,
+        config: Any,
+        bus: MessageBus,
+        *,
+        restrict_to_workspace: bool = False,
+        workspace: str | Path | None = None,
+    ):
         super().__init__(config, bus)
         self.client: AsyncClient | None = None
         self._sync_task: asyncio.Task | None = None
         self._typing_tasks: dict[str, asyncio.Task] = {}
-        self._restrict_to_workspace = False
-        self._workspace: Path | None = None
+        self._restrict_to_workspace = bool(restrict_to_workspace)
+        self._workspace = (
+            Path(workspace).expanduser().resolve(strict=False) if workspace is not None else None
+        )
         self._server_upload_limit_bytes: int | None = None
         self._server_upload_limit_checked = False
 

nanobot/channels/qq.py

@@ -114,16 +114,16 @@ class QQChannel(BaseChannel):
             if msg_type == "group":
                 await self._client.api.post_group_message(
                     group_openid=msg.chat_id,
-                    msg_type=2,
-                    markdown={"content": msg.content},
+                    msg_type=0,
+                    content=msg.content,
                     msg_id=msg_id,
                     msg_seq=self._msg_seq,
                 )
             else:
                 await self._client.api.post_c2c_message(
                     openid=msg.chat_id,
-                    msg_type=2,
-                    markdown={"content": msg.content},
+                    msg_type=0,
+                    content=msg.content,
                     msg_id=msg_id,
                     msg_seq=self._msg_seq,
                 )

nanobot/cli/commands.py

@@ -19,10 +19,12 @@ if sys.platform == "win32":
             pass
 
 import typer
+from prompt_toolkit import print_formatted_text
 from prompt_toolkit import PromptSession
-from prompt_toolkit.formatted_text import HTML
+from prompt_toolkit.formatted_text import ANSI, HTML
 from prompt_toolkit.history import FileHistory
 from prompt_toolkit.patch_stdout import patch_stdout
+from prompt_toolkit.application import run_in_terminal
 from rich.console import Console
 from rich.markdown import Markdown
 from rich.table import Table
@@ -111,8 +113,25 @@ def _init_prompt_session() -> None:
     )
 
 
+def _make_console() -> Console:
+    return Console(file=sys.stdout)
+
+
+def _render_interactive_ansi(render_fn) -> str:
+    """Render Rich output to ANSI so prompt_toolkit can print it safely."""
+    ansi_console = Console(
+        force_terminal=True,
+        color_system=console.color_system or "standard",
+        width=console.width,
+    )
+    with ansi_console.capture() as capture:
+        render_fn(ansi_console)
+    return capture.get()
+
+
 def _print_agent_response(response: str, render_markdown: bool) -> None:
     """Render assistant response with consistent terminal styling."""
+    console = _make_console()
     content = response or ""
     body = Markdown(content) if render_markdown else Text(content)
     console.print()
@@ -121,6 +140,34 @@ def _print_agent_response(response: str, render_markdown: bool) -> None:
     console.print()
 
 
+async def _print_interactive_line(text: str) -> None:
+    """Print async interactive updates with prompt_toolkit-safe Rich styling."""
+    def _write() -> None:
+        ansi = _render_interactive_ansi(
+            lambda c: c.print(f"  [dim]↳ {text}[/dim]")
+        )
+        print_formatted_text(ANSI(ansi), end="")
+
+    await run_in_terminal(_write)
+
+
+async def _print_interactive_response(response: str, render_markdown: bool) -> None:
+    """Print async interactive replies with prompt_toolkit-safe Rich styling."""
+    def _write() -> None:
+        content = response or ""
+        ansi = _render_interactive_ansi(
+            lambda c: (
+                c.print(),
+                c.print(f"[cyan]{__logo__} nanobot[/cyan]"),
+                c.print(Markdown(content) if render_markdown else Text(content)),
+                c.print(),
+            )
+        )
+        print_formatted_text(ANSI(ansi), end="")
+
+    await run_in_terminal(_write)
+
+
 def _is_exit_command(command: str) -> bool:
     """Return True when input should end interactive chat."""
     return command.lower() in EXIT_COMMANDS
@@ -610,14 +657,15 @@ def agent(
                             elif ch and not is_tool_hint and not ch.send_progress:
                                 pass
                             else:
-                                console.print(f"  [dim]↳ {msg.content}[/dim]")
+                                await _print_interactive_line(msg.content)
+
                         elif not turn_done.is_set():
                             if msg.content:
                                 turn_response.append(msg.content)
                             turn_done.set()
                         elif msg.content:
-                            console.print()
-                            _print_agent_response(msg.content, render_markdown=markdown)
+                            await _print_interactive_response(msg.content, render_markdown=markdown)
+
                     except asyncio.TimeoutError:
                         continue
                     except asyncio.CancelledError:

nanobot/config/schema.py

@@ -276,15 +276,18 @@ class ProvidersConfig(Base):
     deepseek: ProviderConfig = Field(default_factory=ProviderConfig)
     groq: ProviderConfig = Field(default_factory=ProviderConfig)
     zhipu: ProviderConfig = Field(default_factory=ProviderConfig)
-    dashscope: ProviderConfig = Field(default_factory=ProviderConfig)  # 阿里云通义千问
+    dashscope: ProviderConfig = Field(default_factory=ProviderConfig)
     vllm: ProviderConfig = Field(default_factory=ProviderConfig)
+    ollama: ProviderConfig = Field(default_factory=ProviderConfig)  # Ollama local models
     gemini: ProviderConfig = Field(default_factory=ProviderConfig)
     moonshot: ProviderConfig = Field(default_factory=ProviderConfig)
     minimax: ProviderConfig = Field(default_factory=ProviderConfig)
     aihubmix: ProviderConfig = Field(default_factory=ProviderConfig)  # AiHubMix API gateway
-    ollama: ProviderConfig = Field(default_factory=ProviderConfig)  # Ollama local models
     siliconflow: ProviderConfig = Field(default_factory=ProviderConfig)  # SiliconFlow (硅基流动)
     volcengine: ProviderConfig = Field(default_factory=ProviderConfig)  # VolcEngine (火山引擎)
+    volcengine_coding_plan: ProviderConfig = Field(default_factory=ProviderConfig)  # VolcEngine Coding Plan
+    byteplus: ProviderConfig = Field(default_factory=ProviderConfig)  # BytePlus (VolcEngine international)
+    byteplus_coding_plan: ProviderConfig = Field(default_factory=ProviderConfig)  # BytePlus Coding Plan
     openai_codex: ProviderConfig = Field(default_factory=ProviderConfig)  # OpenAI Codex (OAuth)
     github_copilot: ProviderConfig = Field(default_factory=ProviderConfig)  # Github Copilot (OAuth)
 
@@ -398,12 +401,21 @@ class Config(BaseSettings):
 
         # Fallback: configured local providers can route models without
         # provider-specific keywords (for example plain "llama3.2" on Ollama).
+        # Prefer providers whose detect_by_base_keyword matches the configured api_base
+        # (e.g. Ollama's "11434" in "http://localhost:11434") over plain registry order.
+        local_fallback: tuple[ProviderConfig, str] | None = None
         for spec in PROVIDERS:
             if not spec.is_local:
                 continue
             p = getattr(self.providers, spec.name, None)
-            if p and p.api_base:
+            if not (p and p.api_base):
+                continue
+            if spec.detect_by_base_keyword and spec.detect_by_base_keyword in p.api_base:
                 return p, spec.name
+            if local_fallback is None:
+                local_fallback = (p, spec.name)
+        if local_fallback:
+            return local_fallback
 
         # Fallback: gateways first, then others (follows registry order)
         # OAuth providers are NOT valid fallbacks — they require explicit model selection

nanobot/providers/registry.py

@@ -145,7 +145,8 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         strip_model_prefix=False,
         model_overrides=(),
     ),
-    # VolcEngine (火山引擎): OpenAI-compatible gateway
+
+    # VolcEngine (火山引擎): OpenAI-compatible gateway, pay-per-use models
     ProviderSpec(
         name="volcengine",
         keywords=("volcengine", "volces", "ark"),
@@ -162,6 +163,62 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         strip_model_prefix=False,
         model_overrides=(),
     ),
+
+    # VolcEngine Coding Plan (火山引擎 Coding Plan): same key as volcengine
+    ProviderSpec(
+        name="volcengine_coding_plan",
+        keywords=("volcengine-plan",),
+        env_key="OPENAI_API_KEY",
+        display_name="VolcEngine Coding Plan",
+        litellm_prefix="volcengine",
+        skip_prefixes=(),
+        env_extras=(),
+        is_gateway=True,
+        is_local=False,
+        detect_by_key_prefix="",
+        detect_by_base_keyword="",
+        default_api_base="https://ark.cn-beijing.volces.com/api/coding/v3",
+        strip_model_prefix=True,
+        model_overrides=(),
+    ),
+
+    # BytePlus: VolcEngine international, pay-per-use models
+    ProviderSpec(
+        name="byteplus",
+        keywords=("byteplus",),
+        env_key="OPENAI_API_KEY",
+        display_name="BytePlus",
+        litellm_prefix="volcengine",
+        skip_prefixes=(),
+        env_extras=(),
+        is_gateway=True,
+        is_local=False,
+        detect_by_key_prefix="",
+        detect_by_base_keyword="bytepluses",
+        default_api_base="https://ark.ap-southeast.bytepluses.com/api/v3",
+        strip_model_prefix=True,
+        model_overrides=(),
+    ),
+
+    # BytePlus Coding Plan: same key as byteplus
+    ProviderSpec(
+        name="byteplus_coding_plan",
+        keywords=("byteplus-plan",),
+        env_key="OPENAI_API_KEY",
+        display_name="BytePlus Coding Plan",
+        litellm_prefix="volcengine",
+        skip_prefixes=(),
+        env_extras=(),
+        is_gateway=True,
+        is_local=False,
+        detect_by_key_prefix="",
+        detect_by_base_keyword="",
+        default_api_base="https://ark.ap-southeast.bytepluses.com/api/coding/v3",
+        strip_model_prefix=True,
+        model_overrides=(),
+    ),
+
+
     # === Standard providers (matched by model-name keywords) ===============
     # Anthropic: LiteLLM recognizes "claude-*" natively, no prefix needed.
     ProviderSpec(