lmproto: add DeepSeek Responses client

src/plyngent/agent/types.py

@@ -3,8 +3,10 @@
 from __future__ import annotations
 
 from plyngent.lmproto.anthropic.client import AnthropicClient
-from plyngent.lmproto.deepseek.openai_compat.client import DeepseekOpenAIClient
+from plyngent.lmproto.deepseek import DeepseekOpenAIClient, DeepseekResponsesClient
 from plyngent.lmproto.openai.client import OpenAIClient
 from plyngent.lmproto.openai_compatible.client import OpenAICompatibleClient
 
-type AnyLLMClient = OpenAICompatibleClient | DeepseekOpenAIClient | OpenAIClient | AnthropicClient
+type AnyLLMClient = (
+    OpenAICompatibleClient | DeepseekOpenAIClient | DeepseekResponsesClient | OpenAIClient | AnthropicClient
+)

src/plyngent/lmproto/deepseek/__init__.py

@@ -6,3 +6,4 @@ from .openai_compat.model import DeepSeekReasoningEffort as DeepSeekReasoningEff
 from .openai_compat.model import NamedChatMessage as NamedChatMessage
 from .openai_compat.model import ThinkingOptions as ThinkingOptions
 from .openai_compat.model import ToolChatMessage as ToolChatMessage
+from .responses.client import DeepseekResponsesClient as DeepseekResponsesClient

src/plyngent/lmproto/deepseek/responses/__init__.py

@@ -0,0 +1 @@
+from .client import DeepseekResponsesClient as DeepseekResponsesClient

src/plyngent/lmproto/deepseek/responses/client.py

@@ -0,0 +1,58 @@
+"""DeepSeek Responses API client (``POST /responses`` on the DeepSeek endpoint)."""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any, cast, override
+
+from plyngent.lmproto.openai.client import OpenAIClient
+
+# DeepSeek Responses SSE streams end with a terminal event instead of
+# ``data: [DONE]`` (see https://api-docs.deepseek.com/guides/responses_api).
+_RESPONSES_TERMINAL_EVENTS = frozenset({"response.completed", "response.incomplete", "response.failed"})
+
+if TYPE_CHECKING:
+    from collections.abc import AsyncIterator
+
+    from plyngent.lmproto.openai.model import ResponseStreamEvent
+    from plyngent.lmproto.openai_compatible.config import OpenAIConfig
+
+
+class DeepseekResponsesClient(OpenAIClient):
+    """DeepSeek Responses client: OpenAI Responses format on DeepSeek's endpoint.
+
+    Differs from :class:`~plyngent.lmproto.openai.OpenAIClient` only in
+    streaming: DeepSeek sends no ``data: [DONE]``, so the SSE loop stops at a
+    terminal event (``response.completed`` / ``response.incomplete`` /
+    ``response.failed``) instead of waiting for ``[DONE]``.
+    """
+
+    kind: str = "responses"
+
+    def __init__(self, config: OpenAIConfig) -> None:
+        super().__init__(config)
+
+    @override
+    async def _parse_response_sse(self, resp: object) -> AsyncIterator[ResponseStreamEvent]:
+        """Yield Responses API SSE events; stop at terminal events (no ``[DONE]``)."""
+        from plyngent.lmproto.openai_compatible.client import (
+            close_async_response,
+            sse_data_payload,
+        )
+
+        typed = cast("Any", resp)
+        try:
+            await self._ensure_ok(typed, what="responses")
+            async for raw in typed.iter_lines():
+                if not raw:
+                    continue
+                parsed = sse_data_payload(bytes(raw))
+                if parsed is None:
+                    continue
+                if parsed is False:
+                    break
+                event = self.response_event_decoder.decode(parsed)
+                yield event
+                if event.type in _RESPONSES_TERMINAL_EVENTS:
+                    break
+        finally:
+            await close_async_response(typed)

tests/test_lmproto/test_deepseek_responses.py

@@ -0,0 +1,89 @@
+from __future__ import annotations
+
+import pytest
+
+from plyngent.lmproto.deepseek import DeepseekResponsesClient
+from plyngent.lmproto.openai import Response, ResponsesCreateParam, response_output_text
+from plyngent.lmproto.openai_compatible.config import OpenAIConfig
+
+
+def _sample_response_body() -> bytes:
+    return (
+        b'{"id":"resp_1","object":"response","created_at":1,"model":"deepseek-v4-flash",'
+        b'"status":"completed","output":['
+        b'{"id":"msg_1","type":"message","role":"assistant","status":"completed",'
+        b'"content":[{"type":"output_text","text":"hello from deepseek","annotations":[]}]}'
+        b"]}"
+    )
+
+
+def test_client_kind_and_base_url() -> None:
+    client = DeepseekResponsesClient(OpenAIConfig(access_key_or_token="sk", base_url="https://api.deepseek.com"))
+    assert client.kind == "responses"
+    assert client.session.base_url == "https://api.deepseek.com"
+
+
+@pytest.mark.asyncio
+async def test_client_responses_create(monkeypatch: pytest.MonkeyPatch) -> None:
+    client = DeepseekResponsesClient(OpenAIConfig(access_key_or_token="sk", base_url="https://api.deepseek.com"))
+
+    class _Resp:
+        status_code = 200
+
+        @property
+        def content(self) -> bytes:
+            return _sample_response_body()
+
+    async def fake_post(path: str, **kwargs: object) -> _Resp:
+        assert path == "/responses"
+        assert kwargs.get("stream") is False
+        return _Resp()
+
+    monkeypatch.setattr(client.session, "post", fake_post)
+    result = await client.responses(ResponsesCreateParam(model="deepseek-v4-flash", input="hi"))
+    assert isinstance(result, Response)
+    assert response_output_text(result) == "hello from deepseek"
+
+
+@pytest.mark.asyncio
+async def test_client_responses_stream_stops_at_terminal(monkeypatch: pytest.MonkeyPatch) -> None:
+    """DeepSeek sends no ``[DONE]``: the stream must stop at a terminal event."""
+    client = DeepseekResponsesClient(OpenAIConfig(access_key_or_token="sk", base_url="https://api.deepseek.com"))
+
+    class _Resp:
+        status_code = 200
+
+        async def iter_lines(self):
+            yield (
+                b'data: {"type":"response.output_text.delta","delta":"hel",'
+                b'"item_id":"m","output_index":0,"content_index":0,"sequence_number":1}'
+            )
+            # Terminal event carries the full response (no [DONE] follows).
+            yield (
+                b'data: {"type":"response.completed","sequence_number":2,'
+                b'"response":{"id":"resp_1","object":"response","created_at":1,'
+                b'"model":"deepseek-v4-flash","status":"completed","output":[]}}'
+            )
+            # Anything after the terminal event must not be consumed.
+            yield b'data: {"type":"response.output_text.delta","delta":"ignored"}'
+
+        def close(self) -> None:
+            return None
+
+    async def fake_post(path: str, **kwargs: object) -> _Resp:
+        assert path == "/responses"
+        assert kwargs.get("stream") is True
+        return _Resp()
+
+    monkeypatch.setattr(client.session, "post", fake_post)
+    stream = await client.responses(
+        ResponsesCreateParam(model="deepseek-v4-flash", input="hi"),
+        stream=True,
+    )
+    events = [event async for event in stream]
+    assert [event.type for event in events] == [
+        "response.output_text.delta",
+        "response.completed",
+    ]
+    assert isinstance(events[1].response, dict)
+    assert events[1].response["status"] == "completed"