release: bump version to 0.74.5

backend/app/services/llm_model_catalog.py

@@ -0,0 +1,186 @@
+"""Authenticated model discovery shared by refresh and connection checks."""
+
+from __future__ import annotations
+
+import asyncio
+from dataclasses import dataclass
+from datetime import datetime
+from urllib.parse import urlsplit, urlunsplit
+
+import httpx
+
+CATALOG_TIMEOUT_SECONDS = 30
+CATALOG_MAX_PAGES = 100
+CATALOG_PAGE_SIZE = 100
+CATALOG_REQUEST_ATTEMPTS = 2
+CATALOG_RETRY_DELAY_SECONDS = 0.2
+SUPPORTED_PROVIDER_APIS = {
+    "openai-completions",
+    "openai-responses",
+    "anthropic-messages",
+    "ollama-generate",
+}
+
+
+class LLMProviderCatalogError(RuntimeError):
+    """A safe, user-facing catalog failure with no upstream response or credentials."""
+
+
+@dataclass(frozen=True)
+class ModelCatalog:
+    url: str
+    models: list[str]
+
+
+def model_catalog_url(provider: str, base_url: str, provider_api: str) -> str:
+    parts = urlsplit(base_url.strip())
+    if parts.scheme not in {"http", "https"} or not parts.hostname:
+        raise LLMProviderCatalogError("请填写有效的 HTTP(S) 模型基础地址。")
+    if parts.username or parts.password or parts.query or parts.fragment:
+        raise LLMProviderCatalogError("模型基础地址不能包含账号、密码、查询参数或片段。")
+    if provider_api not in SUPPORTED_PROVIDER_APIS:
+        raise LLMProviderCatalogError("当前接口协议不支持模型目录查询。")
+    path = parts.path.rstrip("/")
+    if provider_api == "ollama-generate":
+        path = path.removesuffix("/api").removesuffix("/v1") + "/api/tags"
+    elif provider == "alibaba" and parts.hostname.endswith(".aliyuncs.com"):
+        path = "/api/v1/models"
+    else:
+        if not path or (provider_api == "anthropic-messages" and path.endswith("/anthropic")):
+            path += "/v1"
+        path += "/models"
+    return urlunsplit((parts.scheme, parts.netloc, path, "", ""))
+
+
+def catalog_error_message(exc: Exception) -> str:
+    if isinstance(exc, LLMProviderCatalogError):
+        return str(exc)
+    if isinstance(exc, (httpx.TimeoutException, TimeoutError)):
+        return "模型目录请求超时，请检查网络后重试。"
+    if isinstance(exc, httpx.HTTPStatusError):
+        code = exc.response.status_code
+        messages = {
+            401: "API Key 验证失败，请检查当前供应商的凭证。",
+            403: "当前 API Key 无权访问该模型目录，请检查账号权限和服务地域。",
+            404: "模型目录接口不存在，请检查基础地址、地域和接口协议。",
+            429: "供应商请求限流，请稍后重试。",
+        }
+        return messages.get(code, f"供应商模型目录返回 HTTP {code}，请稍后重试。")
+    if isinstance(exc, httpx.RequestError):
+        return "无法连接模型目录，请检查基础地址和网络。"
+    return "模型目录响应无效，请稍后重试。"
+
+
+def _model_rows(payload: object) -> tuple[list[dict[str, object]], dict[str, object]]:
+    if not isinstance(payload, dict):
+        raise LLMProviderCatalogError("供应商返回了无效的模型目录。")
+    envelope = payload.get("output", payload)
+    if not isinstance(envelope, dict):
+        raise LLMProviderCatalogError("供应商返回了无效的模型目录。")
+    rows = envelope.get("data", envelope.get("models"))
+    if not isinstance(rows, list):
+        raise LLMProviderCatalogError("供应商响应中没有模型列表。")
+    if any(not isinstance(row, dict) for row in rows):
+        raise LLMProviderCatalogError("供应商返回了无效的模型条目。")
+    return rows, envelope
+
+
+def _model_id(row: dict[str, object]) -> str:
+    value = row.get("id") or row.get("model") or row.get("name")
+    if not isinstance(value, str) or not value.strip():
+        raise LLMProviderCatalogError("供应商返回了缺少 ID 的模型条目。")
+    return value.strip()
+
+
+def _model_date(row: dict[str, object]) -> float:
+    value = row.get("created_at") or row.get("published_time") or row.get("created")
+    if isinstance(value, (int, float)):
+        return float(value)
+    if isinstance(value, str):
+        try:
+            return datetime.fromisoformat(value.replace("Z", "+00:00")).timestamp()
+        except ValueError:
+            pass
+    return 0
+
+
+async def _get_catalog_page(
+    client: httpx.AsyncClient,
+    url: str,
+    headers: dict[str, str],
+    params: dict[str, str | int],
+) -> object:
+    for attempt in range(CATALOG_REQUEST_ATTEMPTS):
+        try:
+            response = await client.get(url, headers=headers, params=params)
+            response.raise_for_status()
+            return response.json()
+        except httpx.HTTPStatusError as exc:
+            if attempt or exc.response.status_code not in {502, 503, 504}:
+                raise
+        except httpx.TransportError:
+            if attempt:
+                raise
+        await asyncio.sleep(CATALOG_RETRY_DELAY_SECONDS)
+    raise LLMProviderCatalogError("模型目录请求失败。")
+
+
+async def fetch_model_catalog(
+    provider: str,
+    base_url: str,
+    provider_api: str,
+    api_key: str = "",
+    anthropic_version: str = "2023-06-01",
+    timeout_seconds: int = CATALOG_TIMEOUT_SECONDS,
+) -> ModelCatalog:
+    url = model_catalog_url(provider, base_url, provider_api)
+    public_catalog = provider in {"opencode-go", "openrouter"}
+    if not api_key and provider_api != "ollama-generate" and not public_catalog:
+        raise LLMProviderCatalogError("请先配置当前供应商的 API Key，再刷新模型列表。")
+    headers = {"User-Agent": "Planet/1.0", "Accept": "application/json"}
+    if provider_api == "anthropic-messages" and provider not in {
+        "opencode-go",
+        "openrouter",
+        "alibaba",
+        "moonshotai",
+    }:
+        headers.update({"x-api-key": api_key, "anthropic-version": anthropic_version})
+    elif api_key:
+        headers["Authorization"] = f"Bearer {api_key}"
+    native_dashscope = provider == "alibaba" and urlsplit(url).hostname.endswith(".aliyuncs.com")
+    params: dict[str, str | int] = {}
+    if native_dashscope:
+        params = {"page_no": 1, "page_size": CATALOG_PAGE_SIZE, "capabilities": "TG"}
+    rows_by_id: dict[str, dict[str, object]] = {}
+    timeout = max(1, min(timeout_seconds, CATALOG_TIMEOUT_SECONDS))
+    # Bound the complete pagination/retry cycle, not just each individual request.
+    async with asyncio.timeout(timeout), httpx.AsyncClient(timeout=timeout) as client:
+        for page in range(CATALOG_MAX_PAGES):
+            payload = await _get_catalog_page(client, url, headers, params)
+            rows, envelope = _model_rows(payload)
+            previous_count = len(rows_by_id)
+            for row in rows:
+                rows_by_id[_model_id(row)] = row
+            has_more = envelope.get("has_more") is True
+            if native_dashscope:
+                total = envelope.get("total")
+                if not isinstance(total, int) or total < 0:
+                    raise LLMProviderCatalogError("供应商返回了无效的模型目录分页信息。")
+                has_more = len(rows_by_id) < total
+                params["page_no"] = page + 2
+            elif has_more:
+                cursor = envelope.get("last_id")
+                if not isinstance(cursor, str) or not cursor or cursor == params.get("after_id"):
+                    raise LLMProviderCatalogError("供应商返回了无效的模型目录分页信息。")
+                params["after_id"] = cursor
+            if not has_more:
+                models = sorted(
+                    rows_by_id, key=lambda key: _model_date(rows_by_id[key]), reverse=True
+                )
+                # An empty Ollama catalog is valid: no models have been installed yet.
+                if not models and provider_api != "ollama-generate":
+                    raise LLMProviderCatalogError("供应商返回了空模型目录，已保留上次模型列表。")
+                return ModelCatalog(url=url, models=models)
+            if len(rows_by_id) == previous_count:
+                raise LLMProviderCatalogError("供应商模型目录分页没有进展，已保留上次模型列表。")
+    raise LLMProviderCatalogError("供应商模型目录分页超过限制，已保留上次模型列表。")