config: rename the DeepSeek flash model to deepseek-flash

DeepSeek dropped the `v4` prefix from its flash model, and the old id stays
valid only as a compatibility alias. Seed the default catalog with the current
name so a provider that omits `models` no longer offers a deprecated id, and
follow the rename in the wire fixtures and the minimal config template. An
explicit `deepseek-v4-flash` in TOML still passes through unchanged.

tests/test_lmproto/test_deepseek_anthropic.py

@@ -17,7 +17,7 @@ def _sample_message_body() -> bytes:
     return msgspec.json.encode(
         AnthropicMessageResponse(
             id="msg_1",
-            model="deepseek-v4-flash",
+            model="deepseek-flash",
             content=[AnthropicResponseText(text="hello world")],
             stop_reason="end_turn",
             usage=AnthropicUsage(input_tokens=9, output_tokens=3),
@@ -52,7 +52,7 @@ async def test_client_messages_create(monkeypatch: pytest.MonkeyPatch) -> None:
         return _Resp()
 
     monkeypatch.setattr(client.session, "post", fake_post)
-    result = await client.messages(AnthropicMessagesParam(model="deepseek-v4-flash", messages=[]))
+    result = await client.messages(AnthropicMessagesParam(model="deepseek-flash", messages=[]))
     assert isinstance(result, AnthropicMessageResponse)
     assert result.content[0].text == "hello world"
     assert result.usage.output_tokens == 3
@@ -78,7 +78,7 @@ async def test_client_messages_stream(monkeypatch: pytest.MonkeyPatch) -> None:
         return _Resp()
 
     monkeypatch.setattr(client.session, "post", fake_post)
-    stream = await client.messages(AnthropicMessagesParam(model="deepseek-v4-flash", messages=[]), stream=True)
+    stream = await client.messages(AnthropicMessagesParam(model="deepseek-flash", messages=[]), stream=True)
     events = [event async for event in stream]
     assert len(events) == 2
 

tests/test_lmproto/test_deepseek_responses.py

@@ -9,7 +9,7 @@ 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'{"id":"resp_1","object":"response","created_at":1,"model":"deepseek-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":[]}]}'
@@ -40,7 +40,7 @@ async def test_client_responses_create(monkeypatch: pytest.MonkeyPatch) -> None:
         return _Resp()
 
     monkeypatch.setattr(client.session, "post", fake_post)
-    result = await client.responses(ResponsesCreateParam(model="deepseek-v4-flash", input="hi"))
+    result = await client.responses(ResponsesCreateParam(model="deepseek-flash", input="hi"))
     assert isinstance(result, Response)
     assert response_output_text(result) == "hello from deepseek"
 
@@ -62,7 +62,7 @@ async def test_client_responses_stream_stops_at_terminal(monkeypatch: pytest.Mon
             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":[]}}'
+                b'"model":"deepseek-flash","status":"completed","output":[]}}'
             )
             # Anything after the terminal event must not be consumed.
             yield b'data: {"type":"response.output_text.delta","delta":"ignored"}'
@@ -77,7 +77,7 @@ async def test_client_responses_stream_stops_at_terminal(monkeypatch: pytest.Mon
 
     monkeypatch.setattr(client.session, "post", fake_post)
     stream = await client.responses(
-        ResponsesCreateParam(model="deepseek-v4-flash", input="hi"),
+        ResponsesCreateParam(model="deepseek-flash", input="hi"),
         stream=True,
     )
     events = [event async for event in stream]