core/lmproto: add OpenAI Responses API models and client

POST/GET/DELETE /responses with stream events; helpers for output_text and function_call items.

CLAUDE.md

@@ -34,7 +34,8 @@ lmproto/deepseek/openai_compat/ ← Extends base via inheritance + extra fields
 ```
 
 - **`openai_compatible/model.py`** — tagged chat messages (`SystemChatMessage`, `UserChatMessage`, …), tools, request/response, streaming chunks.
-- **`openai_compatible/client.py`** — `BaseOpenAIClient` / `OpenAIClient` via `niquests` async + SSE.
+- **`openai_compatible/responses_model.py`** — OpenAI Responses API (`ResponsesCreateParam`, `Response`, function_call items, stream events).
+- **`openai_compatible/client.py`** — `BaseOpenAIClient` / `OpenAIClient` via `niquests` async + SSE; `chat_completions`, `models`, `responses` / `get_response` / `delete_response`.
 - **`openai_compatible/config.py`** — `OpenAIConfig` (token + base URL).
 - **DeepSeek** — `DeepseekOpenAIClient`; models add `reasoning_content`, `prefix`, `ThinkingOptions`. Config default model ids: `deepseek-v4-flash`, `deepseek-v4-pro`.
 

src/plyngent/lmproto/openai_compatible/__init__.py

@@ -40,3 +40,14 @@ from .model import ToolFunctionItem as ToolFunctionItem
 from .model import UserChatMessage as UserChatMessage
 from .model import Verbosity as Verbosity
 from .model import VoiceName as VoiceName
+from .responses_model import Response as Response
+from .responses_model import ResponseDeleted as ResponseDeleted
+from .responses_model import ResponseFunctionTool as ResponseFunctionTool
+from .responses_model import ResponseFunctionToolCall as ResponseFunctionToolCall
+from .responses_model import ResponseFunctionToolCallOutput as ResponseFunctionToolCallOutput
+from .responses_model import ResponseOutputMessage as ResponseOutputMessage
+from .responses_model import ResponseOutputText as ResponseOutputText
+from .responses_model import ResponsesCreateParam as ResponsesCreateParam
+from .responses_model import ResponseStreamEvent as ResponseStreamEvent
+from .responses_model import response_function_calls as response_function_calls
+from .responses_model import response_output_text as response_output_text

src/plyngent/lmproto/openai_compatible/client.py

@@ -18,6 +18,7 @@ from .model import (
     ModelsResponse,
     StreamToolCallDelta,
 )
+from .responses_model import Response, ResponseDeleted, ResponsesCreateParam, ResponseStreamEvent
 
 if TYPE_CHECKING:
     from collections.abc import AsyncIterator
@@ -77,11 +78,16 @@ def sse_data_payload(line: bytes) -> bytes | None | Literal[False]:
     return payload
 
 
-def http_error_message(status_code: int, body: bytes | str | None = None) -> str | None:
+def http_error_message(
+    status_code: int,
+    body: bytes | str | None = None,
+    *,
+    what: str = "request",
+) -> str | None:
     """Return an error string for HTTP ``status_code`` >= 400, else ``None``."""
     if status_code < _HTTP_ERROR:
         return None
-    msg = f"chat completions HTTP {status_code}"
+    msg = f"{what} HTTP {status_code}"
     if body is None:
         return msg
     if isinstance(body, (bytes, bytearray)):
@@ -97,6 +103,9 @@ class BaseOpenAIClient:
     decoder: msgspec.json.Decoder[ChatCompletionResponse]
     chunk_decoder: msgspec.json.Decoder[ChatCompletionChunk]
     models_decoder: msgspec.json.Decoder[ModelsResponse]
+    response_decoder: msgspec.json.Decoder[Response]
+    response_deleted_decoder: msgspec.json.Decoder[ResponseDeleted]
+    response_event_decoder: msgspec.json.Decoder[ResponseStreamEvent]
 
     def __init__(self, config: OpenAIConfig) -> None:
         self.session = niquests.AsyncSession(
@@ -107,6 +116,9 @@ class BaseOpenAIClient:
         self.decoder = msgspec.json.Decoder(ChatCompletionResponse)
         self.chunk_decoder = msgspec.json.Decoder(ChatCompletionChunk)
         self.models_decoder = msgspec.json.Decoder(ModelsResponse)
+        self.response_decoder = msgspec.json.Decoder(Response)
+        self.response_deleted_decoder = msgspec.json.Decoder(ResponseDeleted)
+        self.response_event_decoder = msgspec.json.Decoder(ResponseStreamEvent)
 
     async def models(self) -> list[str]:
         """List model ids via OpenAI-compatible ``GET /models``.
@@ -114,19 +126,12 @@ class BaseOpenAIClient:
         Returns sorted unique ``id`` values from the response ``data`` array.
         """
         resp = await self.session.get("/models", stream=False)
-        await self._ensure_ok(resp)
-        body = await read_response_body(resp)
-        if body is None:
-            msg = "models response body is empty"
-            raise RuntimeError(msg)
-        if not isinstance(body, (bytes, bytearray)):
-            msg = f"models response body has unexpected type {type(body)!r}"
-            raise TypeError(msg)
-        parsed = self.models_decoder.decode(bytes(body))
+        body = await self._read_json_body(resp, what="models")
+        parsed = self.models_decoder.decode(body)
         ids = {item.id for item in parsed.data if item.id}
         return sorted(ids)
 
-    async def _ensure_ok(self, resp: object) -> None:
+    async def _ensure_ok(self, resp: object, *, what: str = "request") -> None:
         """Raise if the HTTP response is an error (stream or non-stream)."""
         status = getattr(resp, "status_code", None)
         if not isinstance(status, int):
@@ -136,7 +141,7 @@ class BaseOpenAIClient:
         body: bytes | str | None = None
         if status >= _HTTP_ERROR:
             body = await read_response_body(resp)
-        msg = http_error_message(status, body)
+        msg = http_error_message(status, body, what=what)
         if msg is None:
             return
         if hasattr(resp, "close") or hasattr(resp, "aclose"):
@@ -146,7 +151,7 @@ class BaseOpenAIClient:
     async def _parse_sse(self, resp: AsyncResponse) -> AsyncIterator[ChatCompletionChunk]:
         """Yield SSE chunks; stop at ``data: [DONE]`` so we do not hang on keep-alive."""
         try:
-            await self._ensure_ok(resp)
+            await self._ensure_ok(resp, what="chat completions")
             async for raw in resp.iter_lines():
                 if not raw:
                     continue
@@ -159,6 +164,33 @@ class BaseOpenAIClient:
         finally:
             await _close_async_response(resp)
 
+    async def _parse_response_sse(self, resp: AsyncResponse) -> AsyncIterator[ResponseStreamEvent]:
+        """Yield Responses API SSE events; stop at ``data: [DONE]``."""
+        try:
+            await self._ensure_ok(resp, what="responses")
+            async for raw in resp.iter_lines():
+                if not raw:
+                    continue
+                parsed = sse_data_payload(bytes(raw))
+                if parsed is None:
+                    continue
+                if parsed is False:
+                    break
+                yield self.response_event_decoder.decode(parsed)
+        finally:
+            await _close_async_response(resp)
+
+    async def _read_json_body(self, resp: object, *, what: str) -> bytes:
+        await self._ensure_ok(resp, what=what)
+        body = await read_response_body(resp)
+        if body is None:
+            msg = f"{what} response body is empty"
+            raise RuntimeError(msg)
+        if not isinstance(body, (bytes, bytearray)):
+            msg = f"{what} response body has unexpected type {type(body)!r}"
+            raise TypeError(msg)
+        return bytes(body)
+
 
 class OpenAIClient(BaseOpenAIClient):
     def __init__(self, config: OpenAIConfig) -> None:
@@ -194,15 +226,53 @@ class OpenAIClient(BaseOpenAIClient):
             headers={"Content-Type": "application/json"},
             stream=False,
         )
-        await self._ensure_ok(resp)
-        body = await read_response_body(resp)
-        if body is None:
-            msg = "chat completions response body is empty"
-            raise RuntimeError(msg)
-        if not isinstance(body, (bytes, bytearray)):
-            msg = f"chat completions response body has unexpected type {type(body)!r}"
-            raise TypeError(msg)
-        return self.decoder.decode(bytes(body))
+        body = await self._read_json_body(resp, what="chat completions")
+        return self.decoder.decode(body)
+
+    @overload
+    async def responses(
+        self, param: ResponsesCreateParam, *, stream: Literal[False] = False
+    ) -> Response: ...
+
+    @overload
+    async def responses(
+        self, param: ResponsesCreateParam, *, stream: Literal[True]
+    ) -> AsyncIterator[ResponseStreamEvent]: ...
+
+    async def responses(
+        self, param: ResponsesCreateParam, *, stream: bool = False
+    ) -> Response | AsyncIterator[ResponseStreamEvent]:
+        """Create a model response via OpenAI ``POST /responses``."""
+        param = msgspec.structs.replace(param, stream=stream)
+        data = self.encoder.encode(param)
+        if stream:
+            resp = await self.session.post(
+                "/responses",
+                data=data,
+                headers={"Content-Type": "application/json"},
+                stream=True,
+            )
+            return self._parse_response_sse(resp)
+        resp = await self.session.post(
+            "/responses",
+            data=data,
+            headers={"Content-Type": "application/json"},
+            stream=False,
+        )
+        body = await self._read_json_body(resp, what="responses")
+        return self.response_decoder.decode(body)
+
+    async def get_response(self, response_id: str) -> Response:
+        """Retrieve a stored response via ``GET /responses/{id}``."""
+        resp = await self.session.get(f"/responses/{response_id}", stream=False)
+        body = await self._read_json_body(resp, what="responses")
+        return self.response_decoder.decode(body)
+
+    async def delete_response(self, response_id: str) -> ResponseDeleted:
+        """Delete a stored response via ``DELETE /responses/{id}``."""
+        resp = await self.session.delete(f"/responses/{response_id}", stream=False)
+        body = await self._read_json_body(resp, what="responses")
+        return self.response_deleted_decoder.decode(body)
 
 
 def merge_stream_tool_calls(deltas: list[StreamToolCallDelta]) -> list[AssistantFunctionToolCall]:

src/plyngent/lmproto/openai_compatible/responses_model.py

@@ -0,0 +1,326 @@
+"""OpenAI Responses API (``POST /responses``) msgspec models.
+
+Covers the common text + function-calling surface used by agents. Built-in
+tools (web_search, file_search, …) may appear as extra fields on decode when
+``omit_defaults`` / unknown fields allow; request construction for those is
+left to callers via generic dicts where needed.
+"""
+
+from __future__ import annotations
+
+from typing import Any, Literal, cast
+
+import msgspec
+from msgspec import UNSET, Struct, field
+
+from plyngent.typedef import JSONSchema, Unset  # noqa: TC001
+
+from .model import ServiceTier  # noqa: TC001
+
+type ResponseStatus = Literal[
+    "completed",
+    "failed",
+    "in_progress",
+    "cancelled",
+    "queued",
+    "incomplete",
+]
+type ResponseItemStatus = Literal["in_progress", "completed", "incomplete"]
+type ReasoningEffort = Literal["none", "minimal", "low", "medium", "high", "xhigh"]
+type TruncationMode = Literal["auto", "disabled"]
+type PromptCacheRetention = Literal["in_memory", "24h"]
+
+
+# --- Input / output content blocks -------------------------------------------------
+
+
+class ResponseInputText(Struct, tag_field="type", tag="input_text"):
+    text: str
+
+
+class ResponseOutputText(Struct, tag_field="type", tag="output_text"):
+    text: str
+    annotations: list[dict[str, Any]] = field(default_factory=list)
+    logprobs: list[dict[str, Any]] | Unset = UNSET
+
+
+class ResponseOutputRefusal(Struct, tag_field="type", tag="refusal"):
+    refusal: str
+
+
+type ResponseMessageContent = ResponseOutputText | ResponseOutputRefusal | ResponseInputText
+
+
+# --- Message-shaped items (input or output) ----------------------------------------
+
+
+class ResponseEasyInputMessage(Struct, tag_field="type", tag="message"):
+    """Message item used in ``input`` (role + content string or parts)."""
+
+    role: Literal["system", "developer", "user", "assistant"]
+    content: str | list[dict[str, Any]]
+    # Output messages from the API also use type=message with id/status.
+    id: str | Unset = UNSET
+    status: ResponseItemStatus | Unset = UNSET
+    phase: Literal["commentary", "final_answer"] | Unset = UNSET
+
+
+class ResponseOutputMessage(Struct, tag_field="type", tag="message"):
+    """Assistant message item in ``response.output``."""
+
+    id: str
+    content: list[ResponseMessageContent]
+    role: Literal["assistant"] = "assistant"
+    status: ResponseItemStatus = "completed"
+    phase: Literal["commentary", "final_answer"] | Unset = UNSET
+
+
+# --- Function calling (Responses shape: flat, not nested under ``function``) -------
+
+
+class ResponseFunctionTool(Struct, tag_field="type", tag="function"):
+    """Function tool definition for Responses ``tools`` array."""
+
+    name: str
+    description: str | Unset = UNSET
+    parameters: JSONSchema | Unset = UNSET
+    strict: bool | Unset = UNSET
+
+
+class ResponseFunctionToolCall(Struct, tag_field="type", tag="function_call"):
+    """Model-emitted function call item."""
+
+    call_id: str
+    name: str
+    arguments: str
+    id: str | Unset = UNSET
+    status: ResponseItemStatus | Unset = UNSET
+    namespace: str | Unset = UNSET
+
+
+class ResponseFunctionToolCallOutput(Struct, tag_field="type", tag="function_call_output"):
+    """Tool result item passed back in subsequent ``input``."""
+
+    call_id: str
+    output: str
+    id: str | Unset = UNSET
+    status: ResponseItemStatus | Unset = UNSET
+
+
+# --- Reasoning item ----------------------------------------------------------------
+
+
+class ResponseReasoningItem(Struct, tag_field="type", tag="reasoning"):
+    id: str
+    content: list[dict[str, Any]] = field(default_factory=list)
+    summary: list[dict[str, Any]] = field(default_factory=list)
+    status: ResponseItemStatus | Unset = UNSET
+    encrypted_content: str | Unset = UNSET
+
+
+# --- Catch-all for other output item types (web_search_call, …) ---------------------
+
+
+class ResponseUnknownItem(Struct):
+    """Fallback for output/input items we do not model in full yet."""
+
+    type: str
+    id: str | Unset = UNSET
+
+
+type ResponseOutputItem = (
+    ResponseOutputMessage
+    | ResponseFunctionToolCall
+    | ResponseReasoningItem
+    | ResponseFunctionToolCallOutput
+    | ResponseEasyInputMessage
+)
+
+
+# --- Request -----------------------------------------------------------------------
+
+
+class ResponseReasoningConfig(Struct, omit_defaults=True):
+    effort: ReasoningEffort | Unset = UNSET
+    summary: Literal["auto", "concise", "detailed"] | Unset = UNSET
+
+
+class ResponseTextFormatJsonSchema(Struct, tag_field="type", tag="json_schema"):
+    name: str
+    schema: JSONSchema
+    strict: bool | Unset = UNSET
+    description: str | Unset = UNSET
+
+
+class ResponseTextFormatText(Struct, tag_field="type", tag="text"):
+    pass
+
+
+class ResponseTextFormatJsonObject(Struct, tag_field="type", tag="json_object"):
+    pass
+
+
+type ResponseTextFormat = ResponseTextFormatText | ResponseTextFormatJsonObject | ResponseTextFormatJsonSchema
+
+
+class ResponseTextConfig(Struct, omit_defaults=True):
+    format: ResponseTextFormat | Unset = UNSET
+    verbosity: Literal["low", "medium", "high"] | Unset = UNSET
+
+
+class ResponseStreamOptions(Struct, omit_defaults=True):
+    include_obfuscation: bool | Unset = UNSET
+
+
+class ResponsesCreateParam(Struct, omit_defaults=True):
+    """Body for ``POST /responses``."""
+
+    model: str
+    # string, or list of message / function_call_output / … items
+    input: str | list[dict[str, Any] | ResponseEasyInputMessage | ResponseFunctionToolCallOutput]
+    instructions: str | Unset = UNSET
+    tools: list[ResponseFunctionTool | dict[str, Any]] | Unset = UNSET
+    tool_choice: str | dict[str, Any] | Unset = UNSET
+    parallel_tool_calls: bool | Unset = UNSET
+    previous_response_id: str | Unset = UNSET
+    store: bool | Unset = UNSET
+    stream: bool = False
+    stream_options: ResponseStreamOptions | Unset = UNSET
+    temperature: float | Unset = UNSET
+    top_p: float | Unset = UNSET
+    max_output_tokens: int | Unset = UNSET
+    max_tool_calls: int | Unset = UNSET
+    metadata: dict[str, str] | Unset = UNSET
+    reasoning: ResponseReasoningConfig | Unset = UNSET
+    text: ResponseTextConfig | Unset = UNSET
+    truncation: TruncationMode | Unset = UNSET
+    service_tier: ServiceTier | Unset = UNSET
+    user: str | Unset = UNSET
+    safety_identifier: str | Unset = UNSET
+    prompt_cache_key: str | Unset = UNSET
+    prompt_cache_retention: PromptCacheRetention | Unset = UNSET
+    include: list[str] | Unset = UNSET
+    background: bool | Unset = UNSET
+
+
+# --- Response object ---------------------------------------------------------------
+
+
+class ResponseIncompleteDetails(Struct, omit_defaults=True):
+    reason: Literal["max_output_tokens", "content_filter"] | Unset = UNSET
+
+
+class ResponseError(Struct, omit_defaults=True):
+    code: str | Unset = UNSET
+    message: str | Unset = UNSET
+
+
+class ResponseUsage(Struct, omit_defaults=True):
+    input_tokens: int | Unset = UNSET
+    output_tokens: int | Unset = UNSET
+    total_tokens: int | Unset = UNSET
+    input_tokens_details: dict[str, Any] | Unset = UNSET
+    output_tokens_details: dict[str, Any] | Unset = UNSET
+
+
+class Response(Struct, omit_defaults=True):
+    """``object: response`` from create/retrieve."""
+
+    id: str
+    created_at: float | int
+    model: str
+    # Keep items as dicts so unknown built-in tool item types still decode.
+    output: list[dict[str, Any]]
+    object: Literal["response"] = "response"
+    status: ResponseStatus | Unset = UNSET
+    error: ResponseError | None | Unset = UNSET
+    incomplete_details: ResponseIncompleteDetails | None | Unset = UNSET
+    instructions: str | list[dict[str, Any]] | None | Unset = UNSET
+    metadata: dict[str, str] | None | Unset = UNSET
+    parallel_tool_calls: bool | Unset = UNSET
+    temperature: float | None | Unset = UNSET
+    top_p: float | None | Unset = UNSET
+    tools: list[dict[str, Any]] | Unset = UNSET
+    tool_choice: str | dict[str, Any] | Unset = UNSET
+    # Prefer loose dict — nested usage details vary by model/API version.
+    usage: dict[str, Any] | None | Unset = UNSET
+    previous_response_id: str | None | Unset = UNSET
+    service_tier: ServiceTier | None | Unset = UNSET
+    truncation: TruncationMode | None | Unset = UNSET
+    text: dict[str, Any] | Unset = UNSET
+    reasoning: dict[str, Any] | None | Unset = UNSET
+    store: bool | Unset = UNSET
+    user: str | None | Unset = UNSET
+
+
+class ResponseDeleted(Struct):
+    id: str
+    object: Literal["response.deleted"] = "response.deleted"
+    deleted: bool = True
+
+
+# --- Streaming events (subset) -----------------------------------------------------
+
+
+class ResponseStreamEvent(Struct, omit_defaults=True):
+    """Generic SSE event for Responses streaming.
+
+    OpenAI emits many event types; we keep common fields optional and let
+    callers branch on ``type``. Nested ``response`` is a dict so unknown
+    fields and evolving shapes still decode.
+    """
+
+    type: str
+    response: dict[str, Any] | Unset = UNSET
+    item_id: str | Unset = UNSET
+    output_index: int | Unset = UNSET
+    content_index: int | Unset = UNSET
+    delta: str | Unset = UNSET
+    text: str | Unset = UNSET
+    item: dict[str, Any] | Unset = UNSET
+    sequence_number: int | Unset = UNSET
+    # function call argument streaming
+    name: str | Unset = UNSET
+    arguments: str | Unset = UNSET
+    call_id: str | Unset = UNSET
+
+
+# --- Helpers -----------------------------------------------------------------------
+
+
+def response_output_text(response: Response) -> str:
+    """Concatenate all ``output_text`` blocks from message items (SDK-style helper)."""
+    parts: list[str] = []
+    for raw in response.output:
+        if raw.get("type") != "message":
+            continue
+        content = raw.get("content")
+        if not isinstance(content, list):
+            continue
+        for block_obj in content:
+            if not isinstance(block_obj, dict):
+                continue
+            block_map = cast("dict[str, object]", block_obj)
+            if block_map.get("type") != "output_text":
+                continue
+            text = block_map.get("text")
+            if isinstance(text, str):
+                parts.append(text)
+    return "".join(parts)
+
+
+def response_function_calls(response: Response) -> list[ResponseFunctionToolCall]:
+    """Decode ``function_call`` items from ``response.output``."""
+    result: list[ResponseFunctionToolCall] = []
+    for raw in response.output:
+        if raw.get("type") != "function_call":
+            continue
+        try:
+            result.append(msgspec_convert_function_call(raw))
+        except (TypeError, ValueError, KeyError, msgspec.ValidationError):
+            continue
+    return result
+
+
+def msgspec_convert_function_call(raw: dict[str, Any]) -> ResponseFunctionToolCall:
+    return msgspec.convert(raw, ResponseFunctionToolCall)

tests/test_lmproto/test_responses.py

@@ -0,0 +1,158 @@
+from __future__ import annotations
+
+import msgspec
+import pytest
+
+from plyngent.lmproto.openai_compatible.client import OpenAIClient
+from plyngent.lmproto.openai_compatible.config import OpenAIConfig
+from plyngent.lmproto.openai_compatible.responses_model import (
+    Response,
+    ResponseDeleted,
+    ResponseFunctionTool,
+    ResponseFunctionToolCall,
+    ResponsesCreateParam,
+    ResponseStreamEvent,
+    response_function_calls,
+    response_output_text,
+)
+
+
+def _sample_response_body() -> bytes:
+    return (
+        b'{"id":"resp_1","object":"response","created_at":1,"model":"gpt-test",'
+        b'"status":"completed","output":['
+        b'{"id":"rs_1","type":"reasoning","content":[],"summary":[]},'
+        b'{"id":"msg_1","type":"message","role":"assistant","status":"completed",'
+        b'"content":[{"type":"output_text","text":"hello world","annotations":[]}]},'
+        b'{"type":"function_call","call_id":"call_1","name":"add",'
+        b'"arguments":"{\\"a\\":1}","status":"completed"}'
+        b"]}"
+    )
+
+
+def test_response_decode_and_helpers() -> None:
+    parsed = msgspec.json.decode(_sample_response_body(), type=Response)
+    assert parsed.id == "resp_1"
+    assert parsed.object == "response"
+    assert response_output_text(parsed) == "hello world"
+    calls = response_function_calls(parsed)
+    assert len(calls) == 1
+    assert isinstance(calls[0], ResponseFunctionToolCall)
+    assert calls[0].name == "add"
+    assert calls[0].call_id == "call_1"
+
+
+def test_create_param_encode_omits_defaults() -> None:
+    param = ResponsesCreateParam(
+        model="gpt-test",
+        input="hi",
+        tools=[ResponseFunctionTool(name="add", parameters={"type": "object"})],
+    )
+    raw = msgspec.json.encode(param)
+    data = msgspec.json.decode(raw)
+    assert data["model"] == "gpt-test"
+    assert data["input"] == "hi"
+    # omit_defaults: default stream=False is not encoded until client sets stream
+    assert "stream" not in data
+    assert data["tools"][0]["type"] == "function"
+    assert data["tools"][0]["name"] == "add"
+
+
+def test_stream_event_decode() -> None:
+    raw = (
+        b'{"type":"response.output_text.delta","item_id":"msg_1",'
+        b'"output_index":0,"content_index":0,"delta":"hel"}'
+    )
+    event = msgspec.json.decode(raw, type=ResponseStreamEvent)
+    assert event.type == "response.output_text.delta"
+    assert event.delta == "hel"
+
+
+@pytest.mark.asyncio
+async def test_client_responses_create(monkeypatch: pytest.MonkeyPatch) -> None:
+    client = OpenAIClient(OpenAIConfig(access_key_or_token="sk", base_url="https://example/v1"))
+
+    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="gpt-test", input="hi"))
+    assert isinstance(result, Response)
+    assert response_output_text(result) == "hello world"
+
+
+@pytest.mark.asyncio
+async def test_client_responses_stream(monkeypatch: pytest.MonkeyPatch) -> None:
+    client = OpenAIClient(OpenAIConfig(access_key_or_token="sk", base_url="https://example/v1"))
+
+    class _Resp:
+        status_code = 200
+
+        async def iter_lines(self):
+            yield (
+                b'data: {"type":"response.output_text.delta","delta":"a",'
+                b'"item_id":"m","output_index":0,"content_index":0}'
+            )
+            yield b"data: [DONE]"
+
+        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="gpt-test", input="hi"),
+        stream=True,
+    )
+    events = [event async for event in stream]
+    assert len(events) == 1
+    assert events[0].type == "response.output_text.delta"
+    assert events[0].delta == "a"
+
+
+@pytest.mark.asyncio
+async def test_client_get_delete_response(monkeypatch: pytest.MonkeyPatch) -> None:
+    client = OpenAIClient(OpenAIConfig(access_key_or_token="sk", base_url="https://example/v1"))
+
+    class _Get:
+        status_code = 200
+
+        @property
+        def content(self) -> bytes:
+            return _sample_response_body()
+
+    class _Del:
+        status_code = 200
+
+        @property
+        def content(self) -> bytes:
+            return b'{"id":"resp_1","object":"response.deleted","deleted":true}'
+
+    async def fake_get(path: str, **kwargs: object) -> _Get:
+        assert path == "/responses/resp_1"
+        return _Get()
+
+    async def fake_delete(path: str, **kwargs: object) -> _Del:
+        assert path == "/responses/resp_1"
+        return _Del()
+
+    monkeypatch.setattr(client.session, "get", fake_get)
+    monkeypatch.setattr(client.session, "delete", fake_delete)
+    got = await client.get_response("resp_1")
+    assert got.id == "resp_1"
+    deleted = await client.delete_response("resp_1")
+    assert isinstance(deleted, ResponseDeleted)
+    assert deleted.deleted is True