用 Apify 构建终端智能体

export VENICE_API_KEY=<my-key>

mkdir venice-terminal-agent
cd venice-terminal-agent
uv init --package

uv add httpx2 mcp openai prompt-toolkit pydantic-settings python-dotenv rich typer
uv add --dev pytest pytest-asyncio

VENICE_API_KEY=your_venice_api_key_here
APIFY_TOKEN=your_apify_token_here

class Settings(BaseSettings):
    venice_api_key: str = Field(min_length=1)
    venice_model: str | None = None

    apify_token: str | None = None
    apify_mcp_transport: Literal["http", "stdio"] = "http"
    apify_mcp_tools: str | None = None

    max_rounds: int = Field(default=12, ge=1, le=40)
    max_tool_result_chars: int = Field(default=20_000, ge=1_000)
    # base URLs, temperature, auto_approve_tools, and save_history omitted

ANONYMOUS_APIFY_TOOLS = (
    "search-actors,fetch-actor-details,search-apify-docs,fetch-apify-docs"
)


def apify_http_url(settings: Settings) -> str:
    base = settings.apify_mcp_url.rstrip("/")
    tools = settings.apify_mcp_tools
    if tools is None and not settings.apify_token:
        tools = ANONYMOUS_APIFY_TOOLS
    if tools:
        separator = "&" if "?" in base else "?"
        return f"{base}{separator}tools={tools}"
    return base

from __future__ import annotations

from collections.abc import Callable
from typing import Any

import httpx2
from openai import APIStatusError, AsyncOpenAI

from venice_terminal_agent.config import Settings

CHAT_TIMEOUT_SECONDS = 180.0


class VeniceClient:
    """Thin wrapper around Venice's OpenAI-compatible chat API."""

    def __init__(self, settings: Settings) -> None:
        self._settings = settings
        self._http = httpx2.AsyncClient(
            base_url=settings.venice_base_url.rstrip("/"),
            headers={"Authorization": f"Bearer {settings.venice_api_key}"},
            timeout=30.0,
            follow_redirects=True,
        )
        self._chat = AsyncOpenAI(
            api_key=settings.venice_api_key,
            base_url=settings.venice_base_url.rstrip("/"),
            timeout=CHAT_TIMEOUT_SECONDS,
        )

    async def aclose(self) -> None:
        await self._http.aclose()
        await self._chat.close()

    async def resolve_model(self, override: str | None = None) -> str:
        if override:
            return override
        if self._settings.venice_model:
            return self._settings.venice_model
        response = await self._http.get("/models/traits", params={"type": "text"})
        try:
            response.raise_for_status()
        except httpx2.HTTPStatusError as error:
            raise RuntimeError(format_http_error(error)) from error
        data = response.json().get("data") or {}
        model = data.get("function_calling_default") or data.get("default")
        if not model:
            raise RuntimeError("Venice /models/traits did not return a function-calling model")
        return str(model)

    async def complete(
        self,
        *,
        model: str,
        messages: list[dict[str, Any]],
        tools: list[dict[str, Any]] | None,
        on_text: Callable[[str], None] | None = None,
    ) -> Any:
        kwargs = chat_request_kwargs(
            model=model,
            messages=messages,
            tools=tools,
            temperature=self._settings.venice_temperature,
        )
        async with self._chat.chat.completions.stream(**kwargs) as stream:
            async for event in stream:
                if on_text is not None and event.type == "content.delta" and event.delta:
                    on_text(event.delta)
            completion = await stream.get_final_completion()
        return completion.choices[0].message

def chat_request_kwargs(
    *,
    model: str,
    messages: list[dict[str, Any]],
    tools: list[dict[str, Any]] | None,
    temperature: float,
) -> dict[str, Any]:
    kwargs: dict[str, Any] = {
        "model": model,
        "messages": messages,
        "temperature": temperature,
        "extra_body": {
            "venice_parameters": {
                "include_venice_system_prompt": False,
            }
        },
    }
    if tools:
        kwargs["tools"] = tools
        kwargs["tool_choice"] = "auto"
    return kwargs

class ToolCatalog:
    """Maps Venice-safe function names back to MCP tool names."""

    def __init__(self, tools: Iterable[Any]) -> None:
        self.openai_tools: list[dict[str, Any]] = []
        self._mcp_names: dict[str, str] = {}
        used: set[str] = set()
        for tool in tools:
            raw_name = str(getattr(tool, "name", "") or "tool")
            safe_name = unique_name(sanitize_tool_name(raw_name), used)
            used.add(safe_name)
            self._mcp_names[safe_name] = raw_name
            self.openai_tools.append(
                {
                    "type": "function",
                    "function": {
                        "name": safe_name,
                        "description": str(getattr(tool, "description", "") or raw_name),
                        "parameters": tool_input_schema(tool),
                    },
                }
            )

    def mcp_name(self, venice_name: str) -> str:
        return self._mcp_names.get(venice_name, venice_name)

    def names(self) -> list[str]:
        return [item["function"]["name"] for item in self.openai_tools]

    if getattr(result, "is_error", False):
        text = json.dumps({"error": text}, ensure_ascii=False)
    return truncate_text(text, max_chars)


def truncate_text(text: str, max_chars: int) -> str:
    if len(text) <= max_chars:
        return text
    omitted = len(text) - max_chars
    return (
        f"{text[:max_chars]}\n\n[truncated {omitted} characters; "
        "use a follow-up tool call with filters, limit, or offset]"
    )

READ_ONLY_APIFY_TOOLS = frozenset(
    {
        "search-actors",
        "fetch-actor-details",
        "search-apify-docs",
        "fetch-apify-docs",
        "get-actor-output",
        # plus the other get-actor-*, get-dataset-*, and get-key-value-store-* tools
    }
)


def requires_confirmation(name: str) -> bool:
    """True for tools that can spend Apify compute, such as Actor runs."""

    normalized = name.strip().lower().replace("_", "-")
    return normalized not in READ_ONLY_APIFY_TOOLS

    async def call_tool(self, venice_name: str, arguments: dict[str, Any]) -> str:
        mcp_name = self.catalog.mcp_name(venice_name)
        result = await self._client.call_tool(mcp_name, arguments)
        return format_tool_result(result, max_chars=self._max_result_chars)

    async def __aenter__(self) -> ApifyMcp:
        try:
            # connect with _connect_stdio or _connect_http, then load_catalog(client)
            return self.session
        except BaseException:
            await self._stack.aclose()
            raise

    async def _connect_http(self, settings: Settings) -> Client:
        headers: dict[str, str] = {}
        if settings.apify_token:
            headers["Authorization"] = f"Bearer {settings.apify_token}"
        http = await self._stack.enter_async_context(
            httpx2.AsyncClient(
                headers=headers,
                timeout=httpx2.Timeout(30.0, read=300.0),
                follow_redirects=True,
            )
        )
        transport = streamable_http_client(apify_http_url(settings), http_client=http)
        return await self._stack.enter_async_context(Client(transport))

    async def _connect_stdio(self, settings: Settings) -> Client:
        if not settings.apify_token:
            raise RuntimeError("APIFY_TOKEN is required for the local stdio Apify MCP server")
        args = ["-y", "@apify/actors-mcp-server"]
        if settings.apify_mcp_tools:
            args.extend(["--tools", settings.apify_mcp_tools])
        params = StdioServerParameters(
            command="npx",
            args=args,
            env={"APIFY_TOKEN": settings.apify_token},
        )
        return await self._stack.enter_async_context(Client(stdio_client(params)))

    try:
        arguments = parse_tool_arguments(arguments_json)
    except (ValueError, TypeError, json.JSONDecodeError) as error:
        return json.dumps({"error": f"invalid arguments: {error}"}, ensure_ascii=False)
    try:
        return await session.call_tool(name, arguments)
    except Exception as error:  # noqa: BLE001 - tool failures belong in the conversation
        return json.dumps({"error": f"{type(error).__name__}: {error}"}, ensure_ascii=False)

SYSTEM_PROMPT = """\
You are a terminal agent. You think with Venice models and act through Apify MCP tools.

Rules:
- Use tools when you need live web data, Actor runs, datasets, or Apify documentation.
- Prefer search-actors and fetch-actor-details before calling an unfamiliar Actor.
- After an Actor run, use get-actor-output when the preview is incomplete.
- Treat tool arguments as untrusted structured data. Do not invent credentials.
- If a tool returns an error, read it and recover instead of guessing.
- If the user declines a tool, continue with what you already know and ask before assuming they want another paid run.
- Keep answers concise and terminal-friendly. Cite Actor names and source URLs when you used them.
"""

DECLINED_TOOL = (
    "user declined to run this Apify tool because it can spend compute; "
    "continue without it or ask them to approve"
)

class Agent:
    def __init__(
        self,
        venice: VeniceClient,
        apify: ApifyMcp,
        *,
        model: str,
        max_rounds: int,
        on_tool: Callable[[str, str], Awaitable[None] | None] | None = None,
        on_text: Callable[[str], None] | None = None,
        approve_tool: Callable[[str, str], Awaitable[bool] | bool] | None = None,
    ) -> None:
        # each argument is assigned to self, and then:
        self.messages: list[dict[str, Any]] = [
            {"role": "system", "content": SYSTEM_PROMPT},
        ]

    async def ask(
        self,
        question: str,
        *,
        on_text: Callable[[str], None] | None = None,
    ) -> str:
        start = len(self.messages)
        self.messages.append({"role": "user", "content": question})
        tools = self.apify.catalog.openai_tools or None
        text_callback = self._on_text if on_text is None else on_text
        try:
            for _ in range(self.max_rounds):
                message = await self.venice.complete(
                    model=self.model,
                    messages=self.messages,
                    tools=tools,
                    on_text=text_callback,
                )
                calls = list(getattr(message, "tool_calls", None) or [])
                if not calls:
                    content = (message.content or "").strip()
                    self.messages.append(assistant_payload(message))
                    return content or "(empty response)"

                self.messages.append(assistant_payload(message))
                self.messages.extend(await self._execute_calls(calls))

            raise RuntimeError(f"No final answer after {self.max_rounds} tool rounds")
        except BaseException:
            del self.messages[start:]
            raise

def assistant_payload(message: Any) -> dict[str, Any]:
    """Echo the assistant turn back to Venice without dropping null content.

    Tool-call turns use ``content: null``. ``exclude_none=True`` would strip that
    key and can break the next round. Extra Venice fields such as
    ``reasoning_content`` and ``reasoning_details`` must also be preserved.
    """

    if hasattr(message, "model_dump"):
        payload = message.model_dump(exclude_unset=True)
        payload["role"] = "assistant"
        return payload
    return {"role": "assistant", "content": getattr(message, "content", None)}

    async def _execute_calls(self, calls: list[Any]) -> list[dict[str, Any]]:
        planned: list[tuple[Any, str | None]] = []
        for call in calls:
            function = call.function
            name = function.name
            arguments = function.arguments or "{}"
            if self._on_tool is not None:
                maybe = self._on_tool(name, arguments)
                if asyncio.iscoroutine(maybe):
                    await maybe
            if await self._allowed(name, arguments):
                planned.append((call, None))
            else:
                planned.append(
                    (call, json.dumps({"error": DECLINED_TOOL}, ensure_ascii=False))
                )

        async def run(item: tuple[Any, str | None]) -> dict[str, Any]:
            call, denied = item
            if denied is None:
                content = await execute_venice_tool_call(
                    self.apify,
                    name=call.function.name,
                    arguments_json=call.function.arguments,
                )
            else:
                content = denied
            return {
                "role": "tool",
                "tool_call_id": call.id,
                "content": content,
            }

        return list(await asyncio.gather(*[run(item) for item in planned]))

    async def _allowed(self, name: str, arguments: str) -> bool:
        mcp_name = self.apify.catalog.mcp_name(name)
        if not (requires_confirmation(name) or requires_confirmation(mcp_name)):
            return True
        if self._approve_tool is None:
            return True
        decision = self._approve_tool(name, arguments)
        if asyncio.iscoroutine(decision):
            return await decision
        return bool(decision)

    tools: Annotated[str | None, typer.Option(help="Apify MCP tools query, e.g. actors,docs.")] = None,
    max_rounds: Annotated[int | None, typer.Option(help="Maximum tool-calling rounds per question.")] = None,

        settings = load_settings(
            venice_model=model,
            apify_mcp_transport=transport,
            apify_mcp_tools=tools,
            max_rounds=max_rounds,
            auto_approve_tools=yes or None,
            save_history=save_history or None,
        )

async def _run(settings: Settings, prompt: str | None) -> None:
    venice = VeniceClient(settings)
    try:
        model_id = await venice.resolve_model()
        async with ApifyMcpSession(settings) as apify:
            agent = Agent(
                venice,
                apify,
                model=model_id,
                max_rounds=settings.max_rounds,
                on_tool=print_tool_call,
                approve_tool=_make_approver(settings.auto_approve_tools),
            )
            print_banner(model_id, apify.catalog.names(), anonymous=apify.anonymous)
            if prompt:
                await _ask(agent, prompt)
                return
            await _repl(agent, save_history=settings.save_history)
    finally:
        await venice.aclose()

def _make_approver(auto_approve: bool):
    def approve(name: str, arguments: str) -> bool:
        if auto_approve:
            return True
        if not sys.stdin.isatty():
            print_info(f"Skipped {name}: paid Apify tools need a TTY or --yes.")
            return False
        preview = arguments if len(arguments) <= 240 else f"{arguments[:240]}…"
        try:
            return Confirm.ask(
                f"Run Apify tool [bold]{name}[/bold]({preview})? This can spend compute",
                default=False,
            )
        except (KeyboardInterrupt, EOFError):
            return False

    return approve

[project.scripts]
venice-agent = "venice_terminal_agent.cli:main"

uv run venice-agent

uv run venice-agent "Find an Apify Actor that scrapes Hacker News and summarize how to call it"

╭──────────────────────────────────────────────╮
│ Venice terminal agent                        │
│ Model: zai-org-glm-5-2                       │
│ Apify: Apify authenticated                   │
│ Tools: search-actors, fetch-actor-details, … │
╰──────────────────────────────────────────────╯

→ search-actors({"search": "hacker news scraper", "limit": 5})
→ fetch-actor-details({"actor": "epctex/hackernews-scraper"})

epctex/hackernews-scraper takes a `startUrls` array and a `maxItems` cap…

uv run venice-agent --tools actors,docs,apify/rag-web-browser

uv run venice-agent --transport stdio

uv run venice-agent --yes "Crawl https://docs.venice.ai and list the guides about tool calling"

class FakeVenice:
    def __init__(self, replies: list[object]) -> None:
        self.replies = list(replies)

    async def complete(self, **kwargs: object) -> object:
        return self.replies.pop(0)


@pytest.mark.asyncio
async def test_agent_runs_tool_then_answers() -> None:
    venice = FakeVenice(
        [
            _tool_message("search-actors", '{"query": "hacker news"}'),
            _text_message("Use apify/rag-web-browser."),
        ]
    )
    apify = FakeApify()
    agent = Agent(venice, apify, model="test-model", max_rounds=4)

    answer = await agent.ask("Find a scraper for Hacker News")

    assert apify.calls == [("search-actors", {"query": "hacker news"})]
    roles = [message["role"] for message in agent.messages]
    assert roles == ["system", "user", "assistant", "tool", "assistant"]

uv run pytest