feat(deepseek): use native Anthropic Messages transport
Browse files- Point DeepSeek at api.deepseek.com/anthropic with x-api-key headers
- Native request builder, DeepSeek-specific thinking/block sanitization
- Drop deepseek from OpenAI-chat server-tool preflight; update tests and docs
- Default smoke model deepseek-v4-pro; re-export dump_raw_messages_request
- .env.example +1 -1
- README.md +8 -6
- api/services.py +1 -1
- api/web_tools/request.py +1 -1
- config/provider_catalog.py +7 -4
- core/anthropic/native_messages_request.py +5 -0
- providers/deepseek/__init__.py +6 -2
- providers/deepseek/client.py +15 -8
- providers/deepseek/request.py +161 -27
- providers/defaults.py +2 -0
- providers/openai_compat.py +3 -3
- smoke/README.md +1 -1
- smoke/lib/config.py +1 -1
- tests/api/test_dependencies.py +2 -2
- tests/api/test_web_server_tools.py +1 -1
- tests/providers/test_deepseek.py +317 -243
.env.example
CHANGED
|
@@ -6,7 +6,7 @@ NVIDIA_NIM_API_KEY=""
|
|
| 6 |
OPENROUTER_API_KEY=""
|
| 7 |
|
| 8 |
|
| 9 |
-
# DeepSeek Config
|
| 10 |
DEEPSEEK_API_KEY=""
|
| 11 |
|
| 12 |
|
|
|
|
| 6 |
OPENROUTER_API_KEY=""
|
| 7 |
|
| 8 |
|
| 9 |
+
# DeepSeek Config (uses native Anthropic Messages at api.deepseek.com/anthropic)
|
| 10 |
DEEPSEEK_API_KEY=""
|
| 11 |
|
| 12 |
|
README.md
CHANGED
|
@@ -12,7 +12,7 @@
|
|
| 12 |
[](https://github.com/astral-sh/ruff)
|
| 13 |
[](https://github.com/Delgan/loguru)
|
| 14 |
|
| 15 |
-
A lightweight proxy that routes Claude Code's Anthropic API calls to **NVIDIA NIM** (40 req/min free), **OpenRouter** (hundreds of models), **DeepSeek** (direct API), **LM Studio** (fully local), **llama.cpp** (local with Anthropic endpoints), or **Ollama** (fully local, native Anthropic Messages).
|
| 16 |
|
| 17 |
[Quick Start](#quick-start) · [Providers](#providers) · [Discord Bot](#discord-bot) · [Configuration](#configuration) · [Development](#development) · [Contributing](#contributing)
|
| 18 |
|
|
@@ -375,7 +375,7 @@ The proxy also exposes Claude-compatible probe routes: `GET /v1/models`, `POST /
|
|
| 375 |
| -------------- | ------------ | ---------- | ------------------------------------ |
|
| 376 |
| **NVIDIA NIM** | Free | 40 req/min | Daily driver, generous free tier |
|
| 377 |
| **OpenRouter** | Free / Paid | Varies | Model variety, fallback options |
|
| 378 |
-
| **DeepSeek** | Usage-based | Varies |
|
| 379 |
| **LM Studio** | Free (local) | Unlimited | Privacy, offline use, no rate limits |
|
| 380 |
| **llama.cpp** | Free (local) | Unlimited | Lightweight local inference engine |
|
| 381 |
| **Ollama** | Free (local) | Unlimited | Easy local LLM runtime, native Anthropic API |
|
|
@@ -386,7 +386,7 @@ Models use a prefix format: `provider_prefix/model/name`. An invalid prefix caus
|
|
| 386 |
| ---------- | ----------------- | -------------------- | ----------------------------- |
|
| 387 |
| NVIDIA NIM | `nvidia_nim/...` | `NVIDIA_NIM_API_KEY` | `integrate.api.nvidia.com/v1` |
|
| 388 |
| OpenRouter | `open_router/...` | `OPENROUTER_API_KEY` | `openrouter.ai/api/v1` |
|
| 389 |
-
| DeepSeek | `deepseek/...` | `DEEPSEEK_API_KEY` | `api.deepseek.com`
|
| 390 |
| LM Studio | `lmstudio/...` | (none) | `localhost:1234/v1` |
|
| 391 |
| llama.cpp | `llamacpp/...` | (none) | `localhost:8080/v1` |
|
| 392 |
| Ollama | `ollama/...` | (none) | `localhost:11434` |
|
|
@@ -423,10 +423,12 @@ Browse: [openrouter.ai/models](https://openrouter.ai/models) · [Free models](ht
|
|
| 423 |
<details>
|
| 424 |
<summary><b>DeepSeek models</b></summary>
|
| 425 |
|
| 426 |
-
|
|
|
|
|
|
|
| 427 |
|
| 428 |
-
- `deepseek/deepseek-
|
| 429 |
-
- `deepseek/deepseek-reasoner`
|
| 430 |
|
| 431 |
Browse: [api-docs.deepseek.com](https://api-docs.deepseek.com)
|
| 432 |
|
|
|
|
| 12 |
[](https://github.com/astral-sh/ruff)
|
| 13 |
[](https://github.com/Delgan/loguru)
|
| 14 |
|
| 15 |
+
A lightweight proxy that routes Claude Code's Anthropic API calls to **NVIDIA NIM** (40 req/min free), **OpenRouter** (hundreds of models), **DeepSeek** (direct Anthropic-compatible API), **LM Studio** (fully local), **llama.cpp** (local with Anthropic endpoints), or **Ollama** (fully local, native Anthropic Messages).
|
| 16 |
|
| 17 |
[Quick Start](#quick-start) · [Providers](#providers) · [Discord Bot](#discord-bot) · [Configuration](#configuration) · [Development](#development) · [Contributing](#contributing)
|
| 18 |
|
|
|
|
| 375 |
| -------------- | ------------ | ---------- | ------------------------------------ |
|
| 376 |
| **NVIDIA NIM** | Free | 40 req/min | Daily driver, generous free tier |
|
| 377 |
| **OpenRouter** | Free / Paid | Varies | Model variety, fallback options |
|
| 378 |
+
| **DeepSeek** | Usage-based | Varies | Native Anthropic Messages on DeepSeek's API |
|
| 379 |
| **LM Studio** | Free (local) | Unlimited | Privacy, offline use, no rate limits |
|
| 380 |
| **llama.cpp** | Free (local) | Unlimited | Lightweight local inference engine |
|
| 381 |
| **Ollama** | Free (local) | Unlimited | Easy local LLM runtime, native Anthropic API |
|
|
|
|
| 386 |
| ---------- | ----------------- | -------------------- | ----------------------------- |
|
| 387 |
| NVIDIA NIM | `nvidia_nim/...` | `NVIDIA_NIM_API_KEY` | `integrate.api.nvidia.com/v1` |
|
| 388 |
| OpenRouter | `open_router/...` | `OPENROUTER_API_KEY` | `openrouter.ai/api/v1` |
|
| 389 |
+
| DeepSeek | `deepseek/...` | `DEEPSEEK_API_KEY` | `api.deepseek.com/anthropic` |
|
| 390 |
| LM Studio | `lmstudio/...` | (none) | `localhost:1234/v1` |
|
| 391 |
| llama.cpp | `llamacpp/...` | (none) | `localhost:8080/v1` |
|
| 392 |
| Ollama | `ollama/...` | (none) | `localhost:11434` |
|
|
|
|
| 423 |
<details>
|
| 424 |
<summary><b>DeepSeek models</b></summary>
|
| 425 |
|
| 426 |
+
The `deepseek` provider uses DeepSeek's **Anthropic-compatible** `POST /v1/messages` entrypoint
|
| 427 |
+
(HTTP base `https://api.deepseek.com/anthropic`), not the OpenAI `chat/completions` API. Some
|
| 428 |
+
Anthropic request features are unsupported; see the DeepSeek API docs for limits.
|
| 429 |
|
| 430 |
+
- `deepseek/deepseek-v4-pro` / `deepseek/deepseek-v4-flash` (recommended for smokes and tools+thinking)
|
| 431 |
+
- `deepseek/deepseek-chat` / `deepseek/deepseek-reasoner` (older model ids may still be available)
|
| 432 |
|
| 433 |
Browse: [api-docs.deepseek.com](https://api-docs.deepseek.com)
|
| 434 |
|
api/services.py
CHANGED
|
@@ -33,7 +33,7 @@ TokenCounter = Callable[[list[Any], str | list[Any] | None, list[Any] | None], i
|
|
| 33 |
ProviderGetter = Callable[[str], BaseProvider]
|
| 34 |
|
| 35 |
# Providers that use ``/chat/completions`` + Anthropic-to-OpenAI conversion (not native Messages).
|
| 36 |
-
_OPENAI_CHAT_UPSTREAM_IDS = frozenset({"nvidia_nim"
|
| 37 |
|
| 38 |
|
| 39 |
def anthropic_sse_streaming_response(
|
|
|
|
| 33 |
ProviderGetter = Callable[[str], BaseProvider]
|
| 34 |
|
| 35 |
# Providers that use ``/chat/completions`` + Anthropic-to-OpenAI conversion (not native Messages).
|
| 36 |
+
_OPENAI_CHAT_UPSTREAM_IDS = frozenset({"nvidia_nim"})
|
| 37 |
|
| 38 |
|
| 39 |
def anthropic_sse_streaming_response(
|
api/web_tools/request.py
CHANGED
|
@@ -79,7 +79,7 @@ def openai_chat_upstream_server_tool_error(
|
|
| 79 |
)
|
| 80 |
if not forced and has_listed_anthropic_server_tools(request):
|
| 81 |
return (
|
| 82 |
-
"OpenAI Chat upstreams (NVIDIA NIM
|
| 83 |
"(web_search / web_fetch) without the local web server tool handler. Use a native "
|
| 84 |
"Anthropic transport, set ENABLE_WEB_SERVER_TOOLS=true and force the tool with "
|
| 85 |
"tool_choice, or remove these tools from the request."
|
|
|
|
| 79 |
)
|
| 80 |
if not forced and has_listed_anthropic_server_tools(request):
|
| 81 |
return (
|
| 82 |
+
"OpenAI Chat upstreams (NVIDIA NIM) cannot use listed Anthropic server tools "
|
| 83 |
"(web_search / web_fetch) without the local web server tool handler. Use a native "
|
| 84 |
"Anthropic transport, set ENABLE_WEB_SERVER_TOOLS=true and force the tool with "
|
| 85 |
"tool_choice, or remove these tools from the request."
|
config/provider_catalog.py
CHANGED
|
@@ -13,7 +13,10 @@ TransportType = Literal["openai_chat", "anthropic_messages"]
|
|
| 13 |
|
| 14 |
# Default upstream base URLs (also re-exported via :mod:`providers.defaults`)
|
| 15 |
NVIDIA_NIM_DEFAULT_BASE = "https://integrate.api.nvidia.com/v1"
|
| 16 |
-
|
|
|
|
|
|
|
|
|
|
| 17 |
OPENROUTER_DEFAULT_BASE = "https://openrouter.ai/api/v1"
|
| 18 |
LMSTUDIO_DEFAULT_BASE = "http://localhost:1234/v1"
|
| 19 |
LLAMACPP_DEFAULT_BASE = "http://localhost:8080/v1"
|
|
@@ -59,12 +62,12 @@ PROVIDER_CATALOG: dict[str, ProviderDescriptor] = {
|
|
| 59 |
),
|
| 60 |
"deepseek": ProviderDescriptor(
|
| 61 |
provider_id="deepseek",
|
| 62 |
-
transport_type="
|
| 63 |
credential_env="DEEPSEEK_API_KEY",
|
| 64 |
credential_url="https://platform.deepseek.com/api_keys",
|
| 65 |
credential_attr="deepseek_api_key",
|
| 66 |
-
default_base_url=
|
| 67 |
-
capabilities=("chat", "streaming", "thinking"),
|
| 68 |
),
|
| 69 |
"lmstudio": ProviderDescriptor(
|
| 70 |
provider_id="lmstudio",
|
|
|
|
| 13 |
|
| 14 |
# Default upstream base URLs (also re-exported via :mod:`providers.defaults`)
|
| 15 |
NVIDIA_NIM_DEFAULT_BASE = "https://integrate.api.nvidia.com/v1"
|
| 16 |
+
# DeepSeek Anthropic-compatible Messages API (not OpenAI ``/v1`` chat completions).
|
| 17 |
+
DEEPSEEK_ANTHROPIC_DEFAULT_BASE = "https://api.deepseek.com/anthropic"
|
| 18 |
+
# Historical export name: DeepSeek upstream is the native Anthropic path above.
|
| 19 |
+
DEEPSEEK_DEFAULT_BASE = DEEPSEEK_ANTHROPIC_DEFAULT_BASE
|
| 20 |
OPENROUTER_DEFAULT_BASE = "https://openrouter.ai/api/v1"
|
| 21 |
LMSTUDIO_DEFAULT_BASE = "http://localhost:1234/v1"
|
| 22 |
LLAMACPP_DEFAULT_BASE = "http://localhost:8080/v1"
|
|
|
|
| 62 |
),
|
| 63 |
"deepseek": ProviderDescriptor(
|
| 64 |
provider_id="deepseek",
|
| 65 |
+
transport_type="anthropic_messages",
|
| 66 |
credential_env="DEEPSEEK_API_KEY",
|
| 67 |
credential_url="https://platform.deepseek.com/api_keys",
|
| 68 |
credential_attr="deepseek_api_key",
|
| 69 |
+
default_base_url=DEEPSEEK_ANTHROPIC_DEFAULT_BASE,
|
| 70 |
+
capabilities=("chat", "streaming", "tools", "thinking", "native_anthropic"),
|
| 71 |
),
|
| 72 |
"lmstudio": ProviderDescriptor(
|
| 73 |
provider_id="lmstudio",
|
core/anthropic/native_messages_request.py
CHANGED
|
@@ -109,6 +109,11 @@ def _dump_request_fields(request_data: Any) -> dict[str, Any]:
|
|
| 109 |
return dumped
|
| 110 |
|
| 111 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 112 |
def sanitize_native_messages_thinking_policy(
|
| 113 |
messages: Any, *, thinking_enabled: bool
|
| 114 |
) -> Any:
|
|
|
|
| 109 |
return dumped
|
| 110 |
|
| 111 |
|
| 112 |
+
def dump_raw_messages_request(request_data: Any) -> dict[str, Any]:
|
| 113 |
+
"""Public JSON-ready dict of Anthropic public request fields (for native adapters)."""
|
| 114 |
+
return _dump_request_fields(request_data)
|
| 115 |
+
|
| 116 |
+
|
| 117 |
def sanitize_native_messages_thinking_policy(
|
| 118 |
messages: Any, *, thinking_enabled: bool
|
| 119 |
) -> Any:
|
providers/deepseek/__init__.py
CHANGED
|
@@ -1,7 +1,11 @@
|
|
| 1 |
"""DeepSeek provider exports."""
|
| 2 |
|
| 3 |
-
from providers.defaults import DEEPSEEK_DEFAULT_BASE
|
| 4 |
|
| 5 |
from .client import DeepSeekProvider
|
| 6 |
|
| 7 |
-
__all__ = [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
"""DeepSeek provider exports."""
|
| 2 |
|
| 3 |
+
from providers.defaults import DEEPSEEK_ANTHROPIC_DEFAULT_BASE, DEEPSEEK_DEFAULT_BASE
|
| 4 |
|
| 5 |
from .client import DeepSeekProvider
|
| 6 |
|
| 7 |
+
__all__ = [
|
| 8 |
+
"DEEPSEEK_ANTHROPIC_DEFAULT_BASE",
|
| 9 |
+
"DEEPSEEK_DEFAULT_BASE",
|
| 10 |
+
"DeepSeekProvider",
|
| 11 |
+
]
|
providers/deepseek/client.py
CHANGED
|
@@ -1,30 +1,37 @@
|
|
| 1 |
-
"""DeepSeek provider implementation."""
|
|
|
|
|
|
|
| 2 |
|
| 3 |
from typing import Any
|
| 4 |
|
|
|
|
| 5 |
from providers.base import ProviderConfig
|
| 6 |
-
from providers.defaults import
|
| 7 |
-
from providers.openai_compat import OpenAIChatTransport
|
| 8 |
|
| 9 |
from .request import build_request_body
|
| 10 |
|
| 11 |
|
| 12 |
-
class DeepSeekProvider(
|
| 13 |
-
"""DeepSeek
|
| 14 |
|
| 15 |
def __init__(self, config: ProviderConfig):
|
| 16 |
super().__init__(
|
| 17 |
config,
|
| 18 |
provider_name="DEEPSEEK",
|
| 19 |
-
|
| 20 |
-
api_key=config.api_key,
|
| 21 |
)
|
| 22 |
|
| 23 |
def _build_request_body(
|
| 24 |
self, request: Any, thinking_enabled: bool | None = None
|
| 25 |
) -> dict:
|
| 26 |
-
"""Internal helper for tests and shared building."""
|
| 27 |
return build_request_body(
|
| 28 |
request,
|
| 29 |
thinking_enabled=self._is_thinking_enabled(request, thinking_enabled),
|
| 30 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""DeepSeek provider implementation (native Anthropic-compatible Messages)."""
|
| 2 |
+
|
| 3 |
+
from __future__ import annotations
|
| 4 |
|
| 5 |
from typing import Any
|
| 6 |
|
| 7 |
+
from providers.anthropic_messages import AnthropicMessagesTransport
|
| 8 |
from providers.base import ProviderConfig
|
| 9 |
+
from providers.defaults import DEEPSEEK_ANTHROPIC_DEFAULT_BASE
|
|
|
|
| 10 |
|
| 11 |
from .request import build_request_body
|
| 12 |
|
| 13 |
|
| 14 |
+
class DeepSeekProvider(AnthropicMessagesTransport):
|
| 15 |
+
"""DeepSeek using ``https://api.deepseek.com/anthropic`` (Anthropic Messages API)."""
|
| 16 |
|
| 17 |
def __init__(self, config: ProviderConfig):
|
| 18 |
super().__init__(
|
| 19 |
config,
|
| 20 |
provider_name="DEEPSEEK",
|
| 21 |
+
default_base_url=DEEPSEEK_ANTHROPIC_DEFAULT_BASE,
|
|
|
|
| 22 |
)
|
| 23 |
|
| 24 |
def _build_request_body(
|
| 25 |
self, request: Any, thinking_enabled: bool | None = None
|
| 26 |
) -> dict:
|
|
|
|
| 27 |
return build_request_body(
|
| 28 |
request,
|
| 29 |
thinking_enabled=self._is_thinking_enabled(request, thinking_enabled),
|
| 30 |
)
|
| 31 |
+
|
| 32 |
+
def _request_headers(self) -> dict[str, str]:
|
| 33 |
+
return {
|
| 34 |
+
"Accept": "text/event-stream",
|
| 35 |
+
"Content-Type": "application/json",
|
| 36 |
+
"x-api-key": self._api_key,
|
| 37 |
+
}
|
providers/deepseek/request.py
CHANGED
|
@@ -1,46 +1,180 @@
|
|
| 1 |
-
"""Request builder
|
| 2 |
|
|
|
|
|
|
|
|
|
|
| 3 |
from typing import Any
|
| 4 |
|
| 5 |
from loguru import logger
|
| 6 |
|
| 7 |
-
from
|
| 8 |
-
from core.anthropic.
|
| 9 |
from providers.exceptions import InvalidRequestError
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
def build_request_body(request_data: Any, *, thinking_enabled: bool) -> dict:
|
| 13 |
-
"""Build
|
| 14 |
logger.debug(
|
| 15 |
-
"DEEPSEEK_REQUEST:
|
| 16 |
getattr(request_data, "model", "?"),
|
| 17 |
len(getattr(request_data, "messages", [])),
|
| 18 |
)
|
| 19 |
-
try:
|
| 20 |
-
body = build_base_request_body(
|
| 21 |
-
request_data,
|
| 22 |
-
reasoning_replay=ReasoningReplayMode.REASONING_CONTENT
|
| 23 |
-
if thinking_enabled
|
| 24 |
-
else ReasoningReplayMode.DISABLED,
|
| 25 |
-
)
|
| 26 |
-
except OpenAIConversionError as exc:
|
| 27 |
-
raise InvalidRequestError(str(exc)) from exc
|
| 28 |
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
extra_body.update(request_extra)
|
| 33 |
|
| 34 |
-
|
| 35 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
|
| 37 |
-
|
| 38 |
-
body["extra_body"] = extra_body
|
| 39 |
|
| 40 |
logger.debug(
|
| 41 |
-
"DEEPSEEK_REQUEST:
|
| 42 |
-
|
| 43 |
-
len(
|
| 44 |
-
len(
|
| 45 |
)
|
| 46 |
-
return
|
|
|
|
| 1 |
+
"""Request builder and DeepSeek native Anthropic compatibility sanitizer."""
|
| 2 |
|
| 3 |
+
from __future__ import annotations
|
| 4 |
+
|
| 5 |
+
from collections.abc import Mapping
|
| 6 |
from typing import Any
|
| 7 |
|
| 8 |
from loguru import logger
|
| 9 |
|
| 10 |
+
from config.constants import ANTHROPIC_DEFAULT_MAX_OUTPUT_TOKENS
|
| 11 |
+
from core.anthropic.native_messages_request import dump_raw_messages_request
|
| 12 |
from providers.exceptions import InvalidRequestError
|
| 13 |
|
| 14 |
+
# Block types not supported on DeepSeek partial Anthropic-compatible API.
|
| 15 |
+
_UNSUPPORTED_MESSAGE_BLOCK_TYPES = frozenset(
|
| 16 |
+
{
|
| 17 |
+
"image",
|
| 18 |
+
"document",
|
| 19 |
+
"server_tool_use",
|
| 20 |
+
"web_search_tool_result",
|
| 21 |
+
"web_fetch_tool_result",
|
| 22 |
+
}
|
| 23 |
+
)
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
def _is_server_listed_tool(tool: Mapping[str, Any]) -> bool:
|
| 27 |
+
"""True for Anthropic web_search / web_fetch-style tool definitions (listed tools)."""
|
| 28 |
+
name = (tool.get("name") or "").strip()
|
| 29 |
+
if name in ("web_search", "web_fetch"):
|
| 30 |
+
return True
|
| 31 |
+
typ = tool.get("type")
|
| 32 |
+
if isinstance(typ, str):
|
| 33 |
+
return typ.startswith("web_search") or typ.startswith("web_fetch")
|
| 34 |
+
return False
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
def _walk_block_list_for_unsupported(blocks: Any, *, where: str) -> None:
|
| 38 |
+
if not isinstance(blocks, list):
|
| 39 |
+
return
|
| 40 |
+
for block in blocks:
|
| 41 |
+
if not isinstance(block, dict):
|
| 42 |
+
continue
|
| 43 |
+
btype = block.get("type")
|
| 44 |
+
if btype in _UNSUPPORTED_MESSAGE_BLOCK_TYPES:
|
| 45 |
+
raise InvalidRequestError(
|
| 46 |
+
f"DeepSeek native does not support {btype!r} blocks ({where})."
|
| 47 |
+
)
|
| 48 |
+
if btype == "tool_result" and "content" in block:
|
| 49 |
+
_walk_block_list_for_unsupported(
|
| 50 |
+
block["content"], where=f"{where} (tool_result content)"
|
| 51 |
+
)
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
def _validate_deepseek_native_request_dict(data: dict[str, Any]) -> None:
|
| 55 |
+
mcp = data.get("mcp_servers")
|
| 56 |
+
if mcp:
|
| 57 |
+
raise InvalidRequestError(
|
| 58 |
+
"DeepSeek native does not support mcp_servers on requests."
|
| 59 |
+
)
|
| 60 |
+
|
| 61 |
+
for tool in data.get("tools") or ():
|
| 62 |
+
if not isinstance(tool, dict):
|
| 63 |
+
continue
|
| 64 |
+
if _is_server_listed_tool(tool):
|
| 65 |
+
raise InvalidRequestError(
|
| 66 |
+
"DeepSeek native does not support listed Anthropic server tools "
|
| 67 |
+
"(web_search / web_fetch). Remove them or use a different provider."
|
| 68 |
+
)
|
| 69 |
+
|
| 70 |
+
for i, message in enumerate(data.get("messages") or ()):
|
| 71 |
+
if not isinstance(message, dict):
|
| 72 |
+
continue
|
| 73 |
+
c = message.get("content")
|
| 74 |
+
if isinstance(c, list):
|
| 75 |
+
_walk_block_list_for_unsupported(c, where=f"messages[{i}].content")
|
| 76 |
+
if isinstance(c, str) and "<think>" in c:
|
| 77 |
+
# Unusual, but block encoded redacted content — treat as unsafe for DeepSeek.
|
| 78 |
+
pass
|
| 79 |
+
|
| 80 |
+
system = data.get("system")
|
| 81 |
+
if isinstance(system, list):
|
| 82 |
+
_walk_block_list_for_unsupported(system, where="system")
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
def sanitize_deepseek_messages_for_native(
|
| 86 |
+
messages: Any, *, thinking_enabled: bool
|
| 87 |
+
) -> Any:
|
| 88 |
+
"""Filter assistant content for DeepSeek: unsigned ``thinking`` is allowed; no ``redacted_thinking``."""
|
| 89 |
+
if not isinstance(messages, list):
|
| 90 |
+
return messages
|
| 91 |
+
|
| 92 |
+
sanitized: list[Any] = []
|
| 93 |
+
for message in messages:
|
| 94 |
+
if not isinstance(message, dict):
|
| 95 |
+
sanitized.append(message)
|
| 96 |
+
continue
|
| 97 |
+
if message.get("role") != "assistant":
|
| 98 |
+
sanitized.append(message)
|
| 99 |
+
continue
|
| 100 |
+
content = message.get("content")
|
| 101 |
+
if not isinstance(content, list):
|
| 102 |
+
sanitized.append(message)
|
| 103 |
+
continue
|
| 104 |
+
|
| 105 |
+
if not thinking_enabled:
|
| 106 |
+
filtered = [
|
| 107 |
+
block
|
| 108 |
+
for block in content
|
| 109 |
+
if not (
|
| 110 |
+
isinstance(block, dict)
|
| 111 |
+
and block.get("type") in ("thinking", "redacted_thinking")
|
| 112 |
+
)
|
| 113 |
+
]
|
| 114 |
+
else:
|
| 115 |
+
filtered = [
|
| 116 |
+
block
|
| 117 |
+
for block in content
|
| 118 |
+
if not (
|
| 119 |
+
isinstance(block, dict) and block.get("type") == "redacted_thinking"
|
| 120 |
+
)
|
| 121 |
+
]
|
| 122 |
+
new_msg = dict(message)
|
| 123 |
+
new_msg["content"] = filtered or ""
|
| 124 |
+
sanitized.append(new_msg)
|
| 125 |
+
return sanitized
|
| 126 |
+
|
| 127 |
+
|
| 128 |
+
def _strip_reasoning_content_when_native(messages: Any) -> Any:
|
| 129 |
+
"""``reasoning_content`` is OpenAI-helper metadata; not part of native Anthropic body."""
|
| 130 |
+
if not isinstance(messages, list):
|
| 131 |
+
return messages
|
| 132 |
+
out: list[Any] = []
|
| 133 |
+
for m in messages:
|
| 134 |
+
if not isinstance(m, dict):
|
| 135 |
+
out.append(m)
|
| 136 |
+
continue
|
| 137 |
+
msg = {k: v for k, v in m.items() if k != "reasoning_content"}
|
| 138 |
+
out.append(msg)
|
| 139 |
+
return out
|
| 140 |
+
|
| 141 |
|
| 142 |
def build_request_body(request_data: Any, *, thinking_enabled: bool) -> dict:
|
| 143 |
+
"""Build a DeepSeek ``/v1/messages`` JSON body (Anthropic format)."""
|
| 144 |
logger.debug(
|
| 145 |
+
"DEEPSEEK_REQUEST: native build model={} msgs={}",
|
| 146 |
getattr(request_data, "model", "?"),
|
| 147 |
len(getattr(request_data, "messages", [])),
|
| 148 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 149 |
|
| 150 |
+
data = dump_raw_messages_request(request_data)
|
| 151 |
+
_validate_deepseek_native_request_dict(data)
|
| 152 |
+
data.pop("extra_body", None)
|
|
|
|
| 153 |
|
| 154 |
+
thinking_cfg = data.pop("thinking", None)
|
| 155 |
+
if thinking_enabled and isinstance(thinking_cfg, dict):
|
| 156 |
+
thinking_payload: dict[str, Any] = {"type": "enabled"}
|
| 157 |
+
budget_tokens = thinking_cfg.get("budget_tokens")
|
| 158 |
+
if isinstance(budget_tokens, int):
|
| 159 |
+
thinking_payload["budget_tokens"] = budget_tokens
|
| 160 |
+
data["thinking"] = thinking_payload
|
| 161 |
+
|
| 162 |
+
if "messages" in data:
|
| 163 |
+
data["messages"] = _strip_reasoning_content_when_native(
|
| 164 |
+
sanitize_deepseek_messages_for_native(
|
| 165 |
+
data["messages"],
|
| 166 |
+
thinking_enabled=thinking_enabled,
|
| 167 |
+
)
|
| 168 |
+
)
|
| 169 |
+
if "max_tokens" not in data or data.get("max_tokens") is None:
|
| 170 |
+
data["max_tokens"] = ANTHROPIC_DEFAULT_MAX_OUTPUT_TOKENS
|
| 171 |
|
| 172 |
+
data["stream"] = True
|
|
|
|
| 173 |
|
| 174 |
logger.debug(
|
| 175 |
+
"DEEPSEEK_REQUEST: build done model={} msgs={} tools={}",
|
| 176 |
+
data.get("model"),
|
| 177 |
+
len(data.get("messages", [])),
|
| 178 |
+
len(data.get("tools", [])),
|
| 179 |
)
|
| 180 |
+
return data
|
providers/defaults.py
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
"""Re-exports default upstream base URLs from the config provider catalog."""
|
| 2 |
|
| 3 |
from config.provider_catalog import (
|
|
|
|
| 4 |
DEEPSEEK_DEFAULT_BASE,
|
| 5 |
LLAMACPP_DEFAULT_BASE,
|
| 6 |
LMSTUDIO_DEFAULT_BASE,
|
|
@@ -10,6 +11,7 @@ from config.provider_catalog import (
|
|
| 10 |
)
|
| 11 |
|
| 12 |
__all__ = (
|
|
|
|
| 13 |
"DEEPSEEK_DEFAULT_BASE",
|
| 14 |
"LLAMACPP_DEFAULT_BASE",
|
| 15 |
"LMSTUDIO_DEFAULT_BASE",
|
|
|
|
| 1 |
"""Re-exports default upstream base URLs from the config provider catalog."""
|
| 2 |
|
| 3 |
from config.provider_catalog import (
|
| 4 |
+
DEEPSEEK_ANTHROPIC_DEFAULT_BASE,
|
| 5 |
DEEPSEEK_DEFAULT_BASE,
|
| 6 |
LLAMACPP_DEFAULT_BASE,
|
| 7 |
LMSTUDIO_DEFAULT_BASE,
|
|
|
|
| 11 |
)
|
| 12 |
|
| 13 |
__all__ = (
|
| 14 |
+
"DEEPSEEK_ANTHROPIC_DEFAULT_BASE",
|
| 15 |
"DEEPSEEK_DEFAULT_BASE",
|
| 16 |
"LLAMACPP_DEFAULT_BASE",
|
| 17 |
"LMSTUDIO_DEFAULT_BASE",
|
providers/openai_compat.py
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
-
"""OpenAI-style chat base for :class:`OpenAIChatTransport` (NIM,
|
| 2 |
|
| 3 |
-
``AnthropicMessagesTransport``-based providers (OpenRouter, LM Studio, …) live
|
| 4 |
in separate modules; do not list them as subclasses of this class.
|
| 5 |
"""
|
| 6 |
|
|
@@ -56,7 +56,7 @@ def _iter_heuristic_tool_use_sse(
|
|
| 56 |
|
| 57 |
|
| 58 |
class OpenAIChatTransport(BaseProvider):
|
| 59 |
-
"""Base for OpenAI-compatible ``/chat/completions`` adapters (NIM,
|
| 60 |
|
| 61 |
def __init__(
|
| 62 |
self,
|
|
|
|
| 1 |
+
"""OpenAI-style chat base for :class:`OpenAIChatTransport` (NIM, etc.).
|
| 2 |
|
| 3 |
+
``AnthropicMessagesTransport``-based providers (OpenRouter, LM Studio, DeepSeek, …) live
|
| 4 |
in separate modules; do not list them as subclasses of this class.
|
| 5 |
"""
|
| 6 |
|
|
|
|
| 56 |
|
| 57 |
|
| 58 |
class OpenAIChatTransport(BaseProvider):
|
| 59 |
+
"""Base for OpenAI-compatible ``/chat/completions`` adapters (NIM, …)."""
|
| 60 |
|
| 61 |
def __init__(
|
| 62 |
self,
|
smoke/README.md
CHANGED
|
@@ -34,7 +34,7 @@ uv run pytest smoke -n 0 -s --tb=short
|
|
| 34 |
Provider product E2E runs once per configured provider, independent of `MODEL`,
|
| 35 |
`MODEL_OPUS`, `MODEL_SONNET`, and `MODEL_HAIKU`. Defaults come from the provider
|
| 36 |
catalog/docs and can be overridden with `FCC_SMOKE_MODEL_<PROVIDER>`, for example
|
| 37 |
-
`FCC_SMOKE_MODEL_DEEPSEEK=deepseek-
|
| 38 |
configured, live product smoke fails as `missing_env` unless you explicitly set
|
| 39 |
`FCC_ALLOW_NO_PROVIDER_SMOKE=1`.
|
| 40 |
|
|
|
|
| 34 |
Provider product E2E runs once per configured provider, independent of `MODEL`,
|
| 35 |
`MODEL_OPUS`, `MODEL_SONNET`, and `MODEL_HAIKU`. Defaults come from the provider
|
| 36 |
catalog/docs and can be overridden with `FCC_SMOKE_MODEL_<PROVIDER>`, for example
|
| 37 |
+
`FCC_SMOKE_MODEL_DEEPSEEK=deepseek-v4-pro` (or `deepseek-v4-flash`). If no provider smoke model is
|
| 38 |
configured, live product smoke fails as `missing_env` unless you explicitly set
|
| 39 |
`FCC_ALLOW_NO_PROVIDER_SMOKE=1`.
|
| 40 |
|
smoke/lib/config.py
CHANGED
|
@@ -40,7 +40,7 @@ SECRET_KEY_PARTS = ("KEY", "TOKEN", "SECRET", "WEBHOOK", "AUTH")
|
|
| 40 |
PROVIDER_SMOKE_DEFAULT_MODELS: dict[str, str] = {
|
| 41 |
"nvidia_nim": "nvidia_nim/z-ai/glm4.7",
|
| 42 |
"open_router": "open_router/stepfun/step-3.5-flash:free",
|
| 43 |
-
"deepseek": "deepseek/deepseek-
|
| 44 |
"lmstudio": "lmstudio/local-model",
|
| 45 |
"llamacpp": "llamacpp/local-model",
|
| 46 |
"ollama": "ollama/llama3.1",
|
|
|
|
| 40 |
PROVIDER_SMOKE_DEFAULT_MODELS: dict[str, str] = {
|
| 41 |
"nvidia_nim": "nvidia_nim/z-ai/glm4.7",
|
| 42 |
"open_router": "open_router/stepfun/step-3.5-flash:free",
|
| 43 |
+
"deepseek": "deepseek/deepseek-v4-pro",
|
| 44 |
"lmstudio": "lmstudio/local-model",
|
| 45 |
"llamacpp": "llamacpp/local-model",
|
| 46 |
"ollama": "ollama/llama3.1",
|
tests/api/test_dependencies.py
CHANGED
|
@@ -154,7 +154,7 @@ async def test_get_provider_deepseek():
|
|
| 154 |
provider = get_provider()
|
| 155 |
|
| 156 |
assert isinstance(provider, DeepSeekProvider)
|
| 157 |
-
assert provider._base_url == "https://api.deepseek.com"
|
| 158 |
assert provider._api_key == "test_deepseek_key"
|
| 159 |
assert provider._config.enable_thinking is True
|
| 160 |
|
|
@@ -170,7 +170,7 @@ async def test_get_provider_deepseek_uses_fixed_base_url():
|
|
| 170 |
provider = get_provider()
|
| 171 |
|
| 172 |
assert isinstance(provider, DeepSeekProvider)
|
| 173 |
-
assert provider._base_url == "https://api.deepseek.com"
|
| 174 |
|
| 175 |
|
| 176 |
@pytest.mark.asyncio
|
|
|
|
| 154 |
provider = get_provider()
|
| 155 |
|
| 156 |
assert isinstance(provider, DeepSeekProvider)
|
| 157 |
+
assert provider._base_url == "https://api.deepseek.com/anthropic"
|
| 158 |
assert provider._api_key == "test_deepseek_key"
|
| 159 |
assert provider._config.enable_thinking is True
|
| 160 |
|
|
|
|
| 170 |
provider = get_provider()
|
| 171 |
|
| 172 |
assert isinstance(provider, DeepSeekProvider)
|
| 173 |
+
assert provider._base_url == "https://api.deepseek.com/anthropic"
|
| 174 |
|
| 175 |
|
| 176 |
@pytest.mark.asyncio
|
tests/api/test_web_server_tools.py
CHANGED
|
@@ -584,7 +584,7 @@ def test_service_rejects_listed_server_tools_on_openai_chat() -> None:
|
|
| 584 |
service = ClaudeProxyService(
|
| 585 |
settings,
|
| 586 |
provider_getter=lambda _: MagicMock(),
|
| 587 |
-
model_router=FixedProviderModelRouter(settings, "
|
| 588 |
)
|
| 589 |
request = MessagesRequest(
|
| 590 |
model="m",
|
|
|
|
| 584 |
service = ClaudeProxyService(
|
| 585 |
settings,
|
| 586 |
provider_getter=lambda _: MagicMock(),
|
| 587 |
+
model_router=FixedProviderModelRouter(settings, "nvidia_nim"),
|
| 588 |
)
|
| 589 |
request = MessagesRequest(
|
| 590 |
model="m",
|
tests/providers/test_deepseek.py
CHANGED
|
@@ -1,50 +1,31 @@
|
|
| 1 |
-
"""Tests for DeepSeek provider."""
|
| 2 |
|
|
|
|
| 3 |
from unittest.mock import AsyncMock, MagicMock, patch
|
| 4 |
|
| 5 |
import pytest
|
| 6 |
|
| 7 |
-
from api.models.anthropic import
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
from providers.base import ProviderConfig
|
| 9 |
-
from providers.deepseek import
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
from providers.exceptions import InvalidRequestError
|
| 11 |
|
| 12 |
|
| 13 |
-
class MockMessage:
|
| 14 |
-
def __init__(self, role, content, reasoning_content=None):
|
| 15 |
-
self.role = role
|
| 16 |
-
self.content = content
|
| 17 |
-
self.reasoning_content = reasoning_content
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
class MockBlock:
|
| 21 |
-
def __init__(self, **kwargs):
|
| 22 |
-
for key, value in kwargs.items():
|
| 23 |
-
setattr(self, key, value)
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
class MockRequest:
|
| 27 |
-
def __init__(self, **kwargs):
|
| 28 |
-
self.model = "deepseek-chat"
|
| 29 |
-
self.messages = [MockMessage("user", "Hello")]
|
| 30 |
-
self.max_tokens = 100
|
| 31 |
-
self.temperature = 0.5
|
| 32 |
-
self.top_p = 0.9
|
| 33 |
-
self.system = "System prompt"
|
| 34 |
-
self.stop_sequences = None
|
| 35 |
-
self.tools = []
|
| 36 |
-
self.extra_body = {}
|
| 37 |
-
self.thinking = MagicMock()
|
| 38 |
-
self.thinking.enabled = True
|
| 39 |
-
for key, value in kwargs.items():
|
| 40 |
-
setattr(self, key, value)
|
| 41 |
-
|
| 42 |
-
|
| 43 |
@pytest.fixture
|
| 44 |
def deepseek_config():
|
| 45 |
return ProviderConfig(
|
| 46 |
api_key="test_deepseek_key",
|
| 47 |
-
base_url=
|
| 48 |
rate_limit=10,
|
| 49 |
rate_window=60,
|
| 50 |
enable_thinking=True,
|
|
@@ -53,15 +34,18 @@ def deepseek_config():
|
|
| 53 |
|
| 54 |
@pytest.fixture(autouse=True)
|
| 55 |
def mock_rate_limiter():
|
| 56 |
-
|
| 57 |
-
|
|
|
|
|
|
|
|
|
|
| 58 |
instance = mock.get_scoped_instance.return_value
|
| 59 |
-
instance.wait_if_blocked = AsyncMock(return_value=False)
|
| 60 |
|
| 61 |
async def _passthrough(fn, *args, **kwargs):
|
| 62 |
return await fn(*args, **kwargs)
|
| 63 |
|
| 64 |
instance.execute_with_retry = AsyncMock(side_effect=_passthrough)
|
|
|
|
| 65 |
yield instance
|
| 66 |
|
| 67 |
|
|
@@ -70,240 +54,202 @@ def deepseek_provider(deepseek_config):
|
|
| 70 |
return DeepSeekProvider(deepseek_config)
|
| 71 |
|
| 72 |
|
| 73 |
-
def
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
provider = DeepSeekProvider(deepseek_config)
|
| 77 |
-
assert provider._api_key == "test_deepseek_key"
|
| 78 |
-
assert provider._base_url == DEEPSEEK_DEFAULT_BASE
|
| 79 |
-
mock_openai.assert_called_once()
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
def test_build_request_body_enables_thinking_for_chat_model(deepseek_provider):
|
| 83 |
-
"""Thinking-enabled requests add DeepSeek's thinking payload for chat model."""
|
| 84 |
-
req = MockRequest(model="deepseek-chat")
|
| 85 |
-
body = deepseek_provider._build_request_body(req)
|
| 86 |
-
|
| 87 |
-
assert body["model"] == "deepseek-chat"
|
| 88 |
-
assert body["extra_body"]["thinking"] == {"type": "enabled"}
|
| 89 |
-
assert body["messages"][0]["role"] == "system"
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
def test_build_request_body_global_disable_blocks_request_thinking():
|
| 93 |
-
"""Global disable suppresses provider-side thinking even if the request enables it."""
|
| 94 |
-
provider = DeepSeekProvider(
|
| 95 |
-
ProviderConfig(
|
| 96 |
-
api_key="test_deepseek_key",
|
| 97 |
-
base_url=DEEPSEEK_DEFAULT_BASE,
|
| 98 |
-
rate_limit=10,
|
| 99 |
-
rate_window=60,
|
| 100 |
-
enable_thinking=False,
|
| 101 |
-
)
|
| 102 |
-
)
|
| 103 |
-
req = MockRequest(model="deepseek-chat")
|
| 104 |
-
body = provider._build_request_body(req)
|
| 105 |
-
|
| 106 |
-
assert "extra_body" not in body or "thinking" not in body["extra_body"]
|
| 107 |
-
|
| 108 |
|
| 109 |
-
def test_build_request_body_request_disable_blocks_global_thinking(deepseek_provider):
|
| 110 |
-
"""Request-level disable suppresses provider-side thinking when global is enabled."""
|
| 111 |
-
req = MockRequest(model="deepseek-chat")
|
| 112 |
-
req.thinking.enabled = False
|
| 113 |
-
body = deepseek_provider._build_request_body(req)
|
| 114 |
-
|
| 115 |
-
assert "extra_body" not in body or "thinking" not in body["extra_body"]
|
| 116 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
|
| 118 |
-
def test_build_request_body_reasoner_skips_thinking_extra(deepseek_provider):
|
| 119 |
-
"""deepseek-reasoner does not need an extra thinking payload."""
|
| 120 |
-
req = MockRequest(model="deepseek-reasoner")
|
| 121 |
-
body = deepseek_provider._build_request_body(req)
|
| 122 |
|
| 123 |
-
|
| 124 |
-
|
|
|
|
|
|
|
|
|
|
| 125 |
|
| 126 |
|
| 127 |
-
def
|
| 128 |
-
|
| 129 |
-
|
| 130 |
-
|
| 131 |
-
|
|
|
|
| 132 |
)
|
| 133 |
-
body = deepseek_provider._build_request_body(
|
| 134 |
-
|
| 135 |
-
assert body["
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
req = MockRequest(
|
| 141 |
-
system=None,
|
| 142 |
-
messages=[
|
| 143 |
-
MockMessage(
|
| 144 |
-
"assistant",
|
| 145 |
-
[
|
| 146 |
-
MockBlock(type="thinking", thinking="First think"),
|
| 147 |
-
MockBlock(type="text", text="Then answer"),
|
| 148 |
-
],
|
| 149 |
-
)
|
| 150 |
-
],
|
| 151 |
)
|
| 152 |
-
|
| 153 |
-
body =
|
| 154 |
-
|
| 155 |
-
assistant = body["messages"][0]
|
| 156 |
-
assert assistant["reasoning_content"] == "First think"
|
| 157 |
-
assert "<think>" not in assistant["content"]
|
| 158 |
-
assert assistant["content"] == "Then answer"
|
| 159 |
|
| 160 |
|
| 161 |
-
def
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
messages=[
|
| 166 |
-
MockMessage(
|
| 167 |
-
"assistant",
|
| 168 |
-
"Then answer",
|
| 169 |
-
reasoning_content="First think",
|
| 170 |
-
)
|
| 171 |
-
],
|
| 172 |
)
|
|
|
|
|
|
|
| 173 |
|
| 174 |
-
body = deepseek_provider._build_request_body(req)
|
| 175 |
|
| 176 |
-
|
| 177 |
-
|
| 178 |
-
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
):
|
| 184 |
-
"""Thinking plus tool_use history is replayed in DeepSeek's top-level shape."""
|
| 185 |
-
req = MockRequest(
|
| 186 |
-
system=None,
|
| 187 |
-
messages=[
|
| 188 |
-
MockMessage(
|
| 189 |
-
"assistant",
|
| 190 |
-
[
|
| 191 |
-
MockBlock(type="thinking", thinking="Need the tool."),
|
| 192 |
-
MockBlock(
|
| 193 |
-
type="tool_use",
|
| 194 |
-
id="call_reasoning",
|
| 195 |
-
name="echo",
|
| 196 |
-
input={"value": "x"},
|
| 197 |
-
),
|
| 198 |
-
],
|
| 199 |
-
)
|
| 200 |
-
],
|
| 201 |
)
|
|
|
|
|
|
|
|
|
|
| 202 |
|
| 203 |
-
body = deepseek_provider._build_request_body(req)
|
| 204 |
-
|
| 205 |
-
assistant = body["messages"][0]
|
| 206 |
-
assert assistant["content"] == ""
|
| 207 |
-
assert assistant["reasoning_content"] == "Need the tool."
|
| 208 |
-
assert assistant["tool_calls"][0]["id"] == "call_reasoning"
|
| 209 |
-
assert "<think>" not in assistant["content"]
|
| 210 |
|
| 211 |
-
|
| 212 |
-
def test_build_request_body_disabled_thinking_omits_reasoning_and_thinking_tags():
|
| 213 |
-
"""Resolved thinking policy must strip assistant thinking from OpenAI history."""
|
| 214 |
provider = DeepSeekProvider(
|
| 215 |
ProviderConfig(
|
| 216 |
-
api_key="
|
| 217 |
-
base_url=
|
| 218 |
-
rate_limit=
|
| 219 |
-
rate_window=
|
| 220 |
enable_thinking=False,
|
| 221 |
)
|
| 222 |
)
|
| 223 |
-
|
| 224 |
-
|
| 225 |
-
|
| 226 |
-
|
| 227 |
-
|
| 228 |
-
|
| 229 |
-
[
|
| 230 |
-
MockBlock(type="thinking", thinking="secret"),
|
| 231 |
-
MockBlock(type="text", text="hi"),
|
| 232 |
-
],
|
| 233 |
-
)
|
| 234 |
-
],
|
| 235 |
)
|
| 236 |
-
|
| 237 |
-
|
| 238 |
-
|
| 239 |
-
|
| 240 |
-
|
| 241 |
-
|
| 242 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 243 |
|
| 244 |
|
| 245 |
-
def
|
| 246 |
-
"""redacted_thinking is not sent as OpenAI text when thinking is disabled."""
|
| 247 |
provider = DeepSeekProvider(
|
| 248 |
ProviderConfig(
|
| 249 |
-
api_key="
|
| 250 |
-
base_url=
|
| 251 |
-
rate_limit=
|
| 252 |
-
rate_window=
|
| 253 |
enable_thinking=False,
|
| 254 |
)
|
| 255 |
)
|
| 256 |
-
|
| 257 |
-
|
| 258 |
-
|
| 259 |
-
|
| 260 |
-
|
| 261 |
-
|
| 262 |
-
|
| 263 |
-
|
| 264 |
-
|
| 265 |
-
|
| 266 |
-
|
| 267 |
-
|
|
|
|
| 268 |
)
|
| 269 |
-
body = provider._build_request_body(
|
| 270 |
-
|
| 271 |
-
|
| 272 |
-
|
| 273 |
-
|
| 274 |
-
|
| 275 |
-
|
| 276 |
-
|
| 277 |
-
|
| 278 |
-
|
| 279 |
-
|
| 280 |
-
|
| 281 |
-
|
| 282 |
-
|
| 283 |
-
|
| 284 |
-
|
| 285 |
-
|
| 286 |
-
|
| 287 |
-
|
| 288 |
-
|
| 289 |
-
|
| 290 |
-
|
| 291 |
-
|
| 292 |
-
|
| 293 |
-
|
| 294 |
-
|
| 295 |
-
|
| 296 |
-
|
| 297 |
-
|
| 298 |
-
|
| 299 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 300 |
|
| 301 |
|
| 302 |
-
def
|
| 303 |
-
"""Eager preflight: image block fails before a stream would be opened."""
|
| 304 |
request = MessagesRequest(
|
| 305 |
-
model="
|
| 306 |
-
max_tokens=100,
|
| 307 |
messages=[
|
| 308 |
Message(
|
| 309 |
role="user",
|
|
@@ -323,11 +269,139 @@ def test_preflight_stream_rejects_unsupported_user_image_for_openai_conversion()
|
|
| 323 |
provider = DeepSeekProvider(
|
| 324 |
ProviderConfig(
|
| 325 |
api_key="k",
|
| 326 |
-
base_url=
|
| 327 |
-
rate_limit=
|
| 328 |
-
rate_window=
|
| 329 |
)
|
| 330 |
)
|
| 331 |
-
with pytest.raises(InvalidRequestError
|
| 332 |
provider.preflight_stream(request, thinking_enabled=True)
|
| 333 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""Tests for DeepSeek native Anthropic Messages provider."""
|
| 2 |
|
| 3 |
+
from contextlib import asynccontextmanager
|
| 4 |
from unittest.mock import AsyncMock, MagicMock, patch
|
| 5 |
|
| 6 |
import pytest
|
| 7 |
|
| 8 |
+
from api.models.anthropic import (
|
| 9 |
+
ContentBlockImage,
|
| 10 |
+
Message,
|
| 11 |
+
MessagesRequest,
|
| 12 |
+
Tool,
|
| 13 |
+
)
|
| 14 |
+
from config.constants import ANTHROPIC_DEFAULT_MAX_OUTPUT_TOKENS
|
| 15 |
from providers.base import ProviderConfig
|
| 16 |
+
from providers.deepseek import (
|
| 17 |
+
DEEPSEEK_ANTHROPIC_DEFAULT_BASE,
|
| 18 |
+
DEEPSEEK_DEFAULT_BASE,
|
| 19 |
+
DeepSeekProvider,
|
| 20 |
+
)
|
| 21 |
from providers.exceptions import InvalidRequestError
|
| 22 |
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
@pytest.fixture
|
| 25 |
def deepseek_config():
|
| 26 |
return ProviderConfig(
|
| 27 |
api_key="test_deepseek_key",
|
| 28 |
+
base_url=DEEPSEEK_ANTHROPIC_DEFAULT_BASE,
|
| 29 |
rate_limit=10,
|
| 30 |
rate_window=60,
|
| 31 |
enable_thinking=True,
|
|
|
|
| 34 |
|
| 35 |
@pytest.fixture(autouse=True)
|
| 36 |
def mock_rate_limiter():
|
| 37 |
+
@asynccontextmanager
|
| 38 |
+
async def _slot():
|
| 39 |
+
yield
|
| 40 |
+
|
| 41 |
+
with patch("providers.anthropic_messages.GlobalRateLimiter") as mock:
|
| 42 |
instance = mock.get_scoped_instance.return_value
|
|
|
|
| 43 |
|
| 44 |
async def _passthrough(fn, *args, **kwargs):
|
| 45 |
return await fn(*args, **kwargs)
|
| 46 |
|
| 47 |
instance.execute_with_retry = AsyncMock(side_effect=_passthrough)
|
| 48 |
+
instance.concurrency_slot.side_effect = _slot
|
| 49 |
yield instance
|
| 50 |
|
| 51 |
|
|
|
|
| 54 |
return DeepSeekProvider(deepseek_config)
|
| 55 |
|
| 56 |
|
| 57 |
+
def test_default_base_url_alias():
|
| 58 |
+
assert DEEPSEEK_DEFAULT_BASE == DEEPSEEK_ANTHROPIC_DEFAULT_BASE
|
| 59 |
+
assert DEEPSEEK_ANTHROPIC_DEFAULT_BASE == "https://api.deepseek.com/anthropic"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
+
def test_init(deepseek_config):
|
| 63 |
+
with patch("httpx.AsyncClient") as mock_client:
|
| 64 |
+
provider = DeepSeekProvider(deepseek_config)
|
| 65 |
+
assert provider._api_key == "test_deepseek_key"
|
| 66 |
+
assert provider._base_url == "https://api.deepseek.com/anthropic"
|
| 67 |
+
assert mock_client.called
|
| 68 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
|
| 70 |
+
def test_request_headers_includes_x_api_key(deepseek_provider):
|
| 71 |
+
h = deepseek_provider._request_headers()
|
| 72 |
+
assert h["x-api-key"] == "test_deepseek_key"
|
| 73 |
+
assert h["Content-Type"] == "application/json"
|
| 74 |
+
assert h["Accept"] == "text/event-stream"
|
| 75 |
|
| 76 |
|
| 77 |
+
def test_build_request_body_native_shape(deepseek_provider):
|
| 78 |
+
request = MessagesRequest(
|
| 79 |
+
model="deepseek-v4-pro",
|
| 80 |
+
max_tokens=100,
|
| 81 |
+
messages=[Message(role="user", content="Hello")],
|
| 82 |
+
system="S",
|
| 83 |
)
|
| 84 |
+
body = deepseek_provider._build_request_body(request)
|
| 85 |
+
assert body["model"] == "deepseek-v4-pro"
|
| 86 |
+
assert body["stream"] is True
|
| 87 |
+
assert body["messages"][0]["role"] == "user"
|
| 88 |
+
assert body["messages"][0]["content"] in (
|
| 89 |
+
"Hello",
|
| 90 |
+
[{"type": "text", "text": "Hello"}],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
)
|
| 92 |
+
assert body["system"] == "S"
|
| 93 |
+
assert body["max_tokens"] == 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
|
| 95 |
|
| 96 |
+
def test_build_request_body_default_max_tokens(deepseek_provider):
|
| 97 |
+
request = MessagesRequest(
|
| 98 |
+
model="m",
|
| 99 |
+
messages=[Message(role="user", content="x")],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
)
|
| 101 |
+
body = deepseek_provider._build_request_body(request)
|
| 102 |
+
assert body["max_tokens"] == ANTHROPIC_DEFAULT_MAX_OUTPUT_TOKENS
|
| 103 |
|
|
|
|
| 104 |
|
| 105 |
+
def test_build_request_body_thinking_enabled(deepseek_provider):
|
| 106 |
+
request = MessagesRequest.model_validate(
|
| 107 |
+
{
|
| 108 |
+
"model": "m",
|
| 109 |
+
"messages": [{"role": "user", "content": "x"}],
|
| 110 |
+
"thinking": {"type": "enabled", "budget_tokens": 2000},
|
| 111 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 112 |
)
|
| 113 |
+
body = deepseek_provider._build_request_body(request)
|
| 114 |
+
assert body["thinking"] == {"type": "enabled", "budget_tokens": 2000}
|
| 115 |
+
assert "extra_body" not in body
|
| 116 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
|
| 118 |
+
def test_build_request_body_respects_global_thinking_disable():
|
|
|
|
|
|
|
| 119 |
provider = DeepSeekProvider(
|
| 120 |
ProviderConfig(
|
| 121 |
+
api_key="k",
|
| 122 |
+
base_url=DEEPSEEK_ANTHROPIC_DEFAULT_BASE,
|
| 123 |
+
rate_limit=1,
|
| 124 |
+
rate_window=1,
|
| 125 |
enable_thinking=False,
|
| 126 |
)
|
| 127 |
)
|
| 128 |
+
request = MessagesRequest.model_validate(
|
| 129 |
+
{
|
| 130 |
+
"model": "m",
|
| 131 |
+
"messages": [{"role": "user", "content": "x"}],
|
| 132 |
+
"thinking": {"type": "enabled", "budget_tokens": 1},
|
| 133 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 134 |
)
|
| 135 |
+
body = provider._build_request_body(request)
|
| 136 |
+
assert "thinking" not in body
|
| 137 |
+
|
| 138 |
+
|
| 139 |
+
def test_preserve_unsigned_thinking_when_thinking_on(deepseek_provider):
|
| 140 |
+
request = MessagesRequest.model_validate(
|
| 141 |
+
{
|
| 142 |
+
"model": "m",
|
| 143 |
+
"messages": [
|
| 144 |
+
{
|
| 145 |
+
"role": "assistant",
|
| 146 |
+
"content": [
|
| 147 |
+
{
|
| 148 |
+
"type": "thinking",
|
| 149 |
+
"thinking": "plain",
|
| 150 |
+
"signature": None,
|
| 151 |
+
},
|
| 152 |
+
{"type": "text", "text": "out"},
|
| 153 |
+
],
|
| 154 |
+
}
|
| 155 |
+
],
|
| 156 |
+
}
|
| 157 |
+
)
|
| 158 |
+
body = deepseek_provider._build_request_body(request)
|
| 159 |
+
blocks = body["messages"][0]["content"]
|
| 160 |
+
assert len(blocks) == 2
|
| 161 |
+
assert blocks[0]["type"] == "thinking"
|
| 162 |
+
assert blocks[0]["thinking"] == "plain"
|
| 163 |
+
|
| 164 |
+
|
| 165 |
+
def test_strip_redacted_thinking_when_thinking_on(deepseek_provider):
|
| 166 |
+
request = MessagesRequest.model_validate(
|
| 167 |
+
{
|
| 168 |
+
"model": "m",
|
| 169 |
+
"messages": [
|
| 170 |
+
{
|
| 171 |
+
"role": "assistant",
|
| 172 |
+
"content": [
|
| 173 |
+
{"type": "redacted_thinking", "data": "opaque"},
|
| 174 |
+
{"type": "text", "text": "out"},
|
| 175 |
+
],
|
| 176 |
+
}
|
| 177 |
+
],
|
| 178 |
+
}
|
| 179 |
+
)
|
| 180 |
+
body = deepseek_provider._build_request_body(request)
|
| 181 |
+
types = {b["type"] for b in body["messages"][0]["content"]}
|
| 182 |
+
assert "redacted_thinking" not in types
|
| 183 |
+
assert "text" in types
|
| 184 |
|
| 185 |
|
| 186 |
+
def test_thinking_off_strips_thinking_history():
|
|
|
|
| 187 |
provider = DeepSeekProvider(
|
| 188 |
ProviderConfig(
|
| 189 |
+
api_key="k",
|
| 190 |
+
base_url=DEEPSEEK_ANTHROPIC_DEFAULT_BASE,
|
| 191 |
+
rate_limit=1,
|
| 192 |
+
rate_window=1,
|
| 193 |
enable_thinking=False,
|
| 194 |
)
|
| 195 |
)
|
| 196 |
+
request = MessagesRequest.model_validate(
|
| 197 |
+
{
|
| 198 |
+
"model": "m",
|
| 199 |
+
"messages": [
|
| 200 |
+
{
|
| 201 |
+
"role": "assistant",
|
| 202 |
+
"content": [
|
| 203 |
+
{"type": "thinking", "thinking": "sec"},
|
| 204 |
+
{"type": "text", "text": "hi"},
|
| 205 |
+
],
|
| 206 |
+
}
|
| 207 |
+
],
|
| 208 |
+
}
|
| 209 |
)
|
| 210 |
+
body = provider._build_request_body(request)
|
| 211 |
+
for b in body["messages"][0]["content"]:
|
| 212 |
+
assert b["type"] != "thinking"
|
| 213 |
+
assert "sec" not in str(body["messages"])
|
| 214 |
+
|
| 215 |
+
|
| 216 |
+
def test_passthrough_tool_use_and_result(deepseek_provider):
|
| 217 |
+
request = MessagesRequest.model_validate(
|
| 218 |
+
{
|
| 219 |
+
"model": "m",
|
| 220 |
+
"messages": [
|
| 221 |
+
{
|
| 222 |
+
"role": "assistant",
|
| 223 |
+
"content": [
|
| 224 |
+
{
|
| 225 |
+
"type": "tool_use",
|
| 226 |
+
"id": "t1",
|
| 227 |
+
"name": "n",
|
| 228 |
+
"input": {"a": 1},
|
| 229 |
+
}
|
| 230 |
+
],
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"role": "user",
|
| 234 |
+
"content": [
|
| 235 |
+
{
|
| 236 |
+
"type": "tool_result",
|
| 237 |
+
"tool_use_id": "t1",
|
| 238 |
+
"content": "ok",
|
| 239 |
+
}
|
| 240 |
+
],
|
| 241 |
+
},
|
| 242 |
+
],
|
| 243 |
+
}
|
| 244 |
+
)
|
| 245 |
+
body = deepseek_provider._build_request_body(request)
|
| 246 |
+
assert body["messages"][0]["content"][0]["type"] == "tool_use"
|
| 247 |
+
assert body["messages"][1]["content"][0]["type"] == "tool_result"
|
| 248 |
|
| 249 |
|
| 250 |
+
def test_preflight_rejects_user_image():
|
|
|
|
| 251 |
request = MessagesRequest(
|
| 252 |
+
model="m",
|
|
|
|
| 253 |
messages=[
|
| 254 |
Message(
|
| 255 |
role="user",
|
|
|
|
| 269 |
provider = DeepSeekProvider(
|
| 270 |
ProviderConfig(
|
| 271 |
api_key="k",
|
| 272 |
+
base_url=DEEPSEEK_ANTHROPIC_DEFAULT_BASE,
|
| 273 |
+
rate_limit=1,
|
| 274 |
+
rate_window=1,
|
| 275 |
)
|
| 276 |
)
|
| 277 |
+
with pytest.raises(InvalidRequestError, match="image"):
|
| 278 |
provider.preflight_stream(request, thinking_enabled=True)
|
| 279 |
+
|
| 280 |
+
|
| 281 |
+
def test_preflight_rejects_mcp_servers():
|
| 282 |
+
request = MessagesRequest(
|
| 283 |
+
model="m",
|
| 284 |
+
messages=[Message(role="user", content="x")],
|
| 285 |
+
mcp_servers=[{"type": "url", "url": "https://x"}],
|
| 286 |
+
)
|
| 287 |
+
provider = DeepSeekProvider(
|
| 288 |
+
ProviderConfig(
|
| 289 |
+
api_key="k",
|
| 290 |
+
base_url=DEEPSEEK_ANTHROPIC_DEFAULT_BASE,
|
| 291 |
+
rate_limit=1,
|
| 292 |
+
rate_window=1,
|
| 293 |
+
)
|
| 294 |
+
)
|
| 295 |
+
with pytest.raises(InvalidRequestError, match="mcp_servers"):
|
| 296 |
+
provider.preflight_stream(request)
|
| 297 |
+
|
| 298 |
+
|
| 299 |
+
def test_preflight_rejects_listed_server_tools_in_tools_list():
|
| 300 |
+
request = MessagesRequest(
|
| 301 |
+
model="m",
|
| 302 |
+
messages=[Message(role="user", content="x")],
|
| 303 |
+
tools=[Tool(name="web_search", type="web_search_20250305", input_schema={})],
|
| 304 |
+
)
|
| 305 |
+
provider = DeepSeekProvider(
|
| 306 |
+
ProviderConfig(
|
| 307 |
+
api_key="k",
|
| 308 |
+
base_url=DEEPSEEK_ANTHROPIC_DEFAULT_BASE,
|
| 309 |
+
rate_limit=1,
|
| 310 |
+
rate_window=1,
|
| 311 |
+
)
|
| 312 |
+
)
|
| 313 |
+
with pytest.raises(InvalidRequestError, match="web_search"):
|
| 314 |
+
provider.preflight_stream(request)
|
| 315 |
+
|
| 316 |
+
|
| 317 |
+
def test_preflight_rejects_server_tool_result_blocks():
|
| 318 |
+
request = MessagesRequest.model_validate(
|
| 319 |
+
{
|
| 320 |
+
"model": "m",
|
| 321 |
+
"messages": [
|
| 322 |
+
{
|
| 323 |
+
"role": "assistant",
|
| 324 |
+
"content": [
|
| 325 |
+
{
|
| 326 |
+
"type": "server_tool_use",
|
| 327 |
+
"id": "s1",
|
| 328 |
+
"name": "web_search",
|
| 329 |
+
"input": {"q": "a"},
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"type": "web_search_tool_result",
|
| 333 |
+
"tool_use_id": "s1",
|
| 334 |
+
"content": [],
|
| 335 |
+
},
|
| 336 |
+
],
|
| 337 |
+
}
|
| 338 |
+
],
|
| 339 |
+
}
|
| 340 |
+
)
|
| 341 |
+
provider = DeepSeekProvider(
|
| 342 |
+
ProviderConfig(
|
| 343 |
+
api_key="k",
|
| 344 |
+
base_url=DEEPSEEK_ANTHROPIC_DEFAULT_BASE,
|
| 345 |
+
rate_limit=1,
|
| 346 |
+
rate_window=1,
|
| 347 |
+
)
|
| 348 |
+
)
|
| 349 |
+
with pytest.raises(InvalidRequestError, match=r"web_search_tool_result|server"):
|
| 350 |
+
provider.preflight_stream(request)
|
| 351 |
+
|
| 352 |
+
|
| 353 |
+
def test_strip_reasoning_content_not_forwarded(deepseek_provider):
|
| 354 |
+
# ``reasoning_content`` is for OpenAI helpers only, not in native body.
|
| 355 |
+
request = MessagesRequest(
|
| 356 |
+
model="m",
|
| 357 |
+
messages=[
|
| 358 |
+
Message(
|
| 359 |
+
role="assistant",
|
| 360 |
+
content="hi",
|
| 361 |
+
reasoning_content="r",
|
| 362 |
+
)
|
| 363 |
+
],
|
| 364 |
+
)
|
| 365 |
+
body = deepseek_provider._build_request_body(request)
|
| 366 |
+
assert "reasoning_content" not in body["messages"][0]
|
| 367 |
+
|
| 368 |
+
|
| 369 |
+
@pytest.mark.asyncio
|
| 370 |
+
async def test_stream_uses_post_messages_path(deepseek_provider):
|
| 371 |
+
request = MessagesRequest(
|
| 372 |
+
model="m",
|
| 373 |
+
messages=[Message(role="user", content="hi")],
|
| 374 |
+
)
|
| 375 |
+
called: dict[str, str] = {}
|
| 376 |
+
|
| 377 |
+
async def fake_send(request, *args, **kwargs):
|
| 378 |
+
called["path"] = request.url.path
|
| 379 |
+
mock_resp = MagicMock()
|
| 380 |
+
mock_resp.status_code = 200
|
| 381 |
+
mock_resp.is_closed = False
|
| 382 |
+
mock_resp.raise_for_status = lambda: None
|
| 383 |
+
|
| 384 |
+
async def aiter():
|
| 385 |
+
if False: # pragma: no cover
|
| 386 |
+
yield ""
|
| 387 |
+
|
| 388 |
+
mock_resp.aiter_lines = aiter
|
| 389 |
+
mock_resp.aclose = AsyncMock()
|
| 390 |
+
return mock_resp
|
| 391 |
+
|
| 392 |
+
deepseek_provider._client.send = fake_send
|
| 393 |
+
_ = [x async for x in deepseek_provider.stream_response(request, request_id="r1")]
|
| 394 |
+
|
| 395 |
+
assert called["path"] == "/anthropic/messages"
|
| 396 |
+
|
| 397 |
+
|
| 398 |
+
def test_drops_extra_body_from_canonical_request(deepseek_provider):
|
| 399 |
+
raw = {
|
| 400 |
+
"model": "m",
|
| 401 |
+
"max_tokens": 3,
|
| 402 |
+
"messages": [{"role": "user", "content": "x"}],
|
| 403 |
+
"extra_body": {"note": 1},
|
| 404 |
+
}
|
| 405 |
+
r = MessagesRequest.model_validate(raw)
|
| 406 |
+
body = deepseek_provider._build_request_body(r)
|
| 407 |
+
assert "extra_body" not in body
|