Merge remote-tracking branch 'origin/main'

2026-03-13 09:39:01 +08:00
parent cf3c88014f 774452795b
commit f4018dcce5
6 changed files with 164 additions and 15 deletions
--- a/README.md
+++ b/README.md
@@ -794,15 +794,17 @@ Config file: `~/.nanobot/config.json`

 > [!TIP]
 > - **Groq** provides free voice transcription via Whisper. If configured, Telegram voice messages will be automatically transcribed.
+> - **VolcEngine / BytePlus Coding Plan**: Use dedicated providers `volcengineCodingPlan` or `byteplusCodingPlan` instead of the pay-per-use `volcengine` / `byteplus` providers.
 > - **Zhipu Coding Plan**: If you're on Zhipu's coding plan, set `"apiBase": "https://open.bigmodel.cn/api/coding/paas/v4"` in your zhipu provider config.
 > - **MiniMax (Mainland China)**: If your API key is from MiniMax's mainland China platform (minimaxi.com), set `"apiBase": "https://api.minimaxi.com/v1"` in your minimax provider config.
-> - **VolcEngine Coding Plan**: If you're on VolcEngine's coding plan, set `"apiBase": "https://ark.cn-beijing.volces.com/api/coding/v3"` in your volcengine provider config.
 > - **Alibaba Cloud Coding Plan**: If you're on the Alibaba Cloud Coding Plan (BaiLian), set `"apiBase": "https://coding.dashscope.aliyuncs.com/v1"` in your dashscope provider config.

 | Provider | Purpose | Get API Key |
 |----------|---------|-------------|
 | `custom` | Any OpenAI-compatible endpoint (direct, no LiteLLM) | — |
 | `openrouter` | LLM (recommended, access to all models) | [openrouter.ai](https://openrouter.ai) |
+| `volcengine` | LLM (VolcEngine, pay-per-use) | [Coding Plan](https://www.volcengine.com/activity/codingplan?utm_campaign=nanobot&utm_content=nanobot&utm_medium=devrel&utm_source=OWO&utm_term=nanobot) · [volcengine.com](https://www.volcengine.com) |
+| `byteplus` | LLM (VolcEngine international, pay-per-use) | [Coding Plan](https://www.byteplus.com/en/activity/codingplan?utm_campaign=nanobot&utm_content=nanobot&utm_medium=devrel&utm_source=OWO&utm_term=nanobot) · [byteplus.com](https://www.byteplus.com) |
 | `anthropic` | LLM (Claude direct) | [console.anthropic.com](https://console.anthropic.com) |
 | `azure_openai` | LLM (Azure OpenAI) | [portal.azure.com](https://portal.azure.com) |
 | `openai` | LLM (GPT direct) | [platform.openai.com](https://platform.openai.com) |
@@ -812,7 +814,6 @@ Config file: `~/.nanobot/config.json`
 | `minimax` | LLM (MiniMax direct) | [platform.minimaxi.com](https://platform.minimaxi.com) |
 | `aihubmix` | LLM (API gateway, access to all models) | [aihubmix.com](https://aihubmix.com) |
 | `siliconflow` | LLM (SiliconFlow/硅基流动) | [siliconflow.cn](https://siliconflow.cn) |
-| `volcengine` | LLM (VolcEngine/火山引擎) | [volcengine.com](https://www.volcengine.com) |
 | `dashscope` | LLM (Qwen) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
 | `moonshot` | LLM (Moonshot/Kimi) | [platform.moonshot.cn](https://platform.moonshot.cn) |
 | `zhipu` | LLM (Zhipu GLM) | [open.bigmodel.cn](https://open.bigmodel.cn) |
--- a/nanobot/agent/memory.py
+++ b/nanobot/agent/memory.py
@@ -112,15 +112,17 @@ 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:
            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={"type": "function", "function": {"name": "save_memory"}},
            )

            if not response.has_tool_calls:
--- a/nanobot/cli/commands.py
+++ b/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
@@ -616,14 +663,15 @@ 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:
--- a/nanobot/config/schema.py
+++ b/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)

@@ -400,12 +403,21 @@ 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
--- a/nanobot/providers/registry.py
+++ b/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(
--- a/tests/test_commands.py
+++ b/tests/test_commands.py
@@ -143,6 +143,35 @@ def test_config_auto_detects_ollama_from_local_api_base():
    assert config.get_api_base() == "http://localhost:11434"


+def test_config_prefers_ollama_over_vllm_when_both_local_providers_configured():
+    config = Config.model_validate(
+        {
+            "agents": {"defaults": {"provider": "auto", "model": "llama3.2"}},
+            "providers": {
+                "vllm": {"apiBase": "http://localhost:8000"},
+                "ollama": {"apiBase": "http://localhost:11434"},
+            },
+        }
+    )
+
+    assert config.get_provider_name() == "ollama"
+    assert config.get_api_base() == "http://localhost:11434"
+
+
+def test_config_falls_back_to_vllm_when_ollama_not_configured():
+    config = Config.model_validate(
+        {
+            "agents": {"defaults": {"provider": "auto", "model": "llama3.2"}},
+            "providers": {
+                "vllm": {"apiBase": "http://localhost:8000"},
+            },
+        }
+    )
+
+    assert config.get_provider_name() == "vllm"
+    assert config.get_api_base() == "http://localhost:8000"
+
+
 def test_find_by_model_prefers_explicit_prefix_over_generic_codex_keyword():
    spec = find_by_model("github-copilot/gpt-5.3-codex")