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.

src/plyngent/cli/editor.py

@@ -57,7 +57,7 @@ _MINIMAL_CONFIG = """\
 # [providers.deepseek]
 # preset = "deepseek"
 # access_key_or_token = "sk-..."
-# # models default to deepseek-v4-flash and deepseek-v4-pro if omitted
+# # models default to deepseek-flash and deepseek-v4-pro if omitted
 """
 
 

src/plyngent/config/models.py

@@ -366,7 +366,7 @@ class AnthropicProvider(ProviderConfig, tag="anthropic"):
 def _default_deepseek_models() -> dict[str, ModelConfig]:
     """Current DeepSeek text catalog when TOML omits ``models``."""
     return {
-        "deepseek-v4-flash": ModelConfig(text=True),
+        "deepseek-flash": ModelConfig(text=True),
         "deepseek-v4-pro": ModelConfig(text=True),
     }
 

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

@@ -17,8 +17,8 @@ class DeepseekAnthropicClient(AnthropicClient):
     (see https://api-docs.deepseek.com/guides/anthropic_api). ``x-api-key`` is fully
     supported; ``anthropic-version`` / ``anthropic-beta`` headers are ignored by the
     server but harmless. Model ids map server-side: ``claude-opus*`` → ``deepseek-v4-pro``,
-    ``claude-haiku*`` / ``claude-sonnet*`` → ``deepseek-v4-flash``, unknown names →
+    ``claude-haiku*`` / ``claude-sonnet*`` → ``deepseek-flash``, unknown names →
-    ``deepseek-v4-flash``; real DeepSeek ids pass through as-is.
+    ``deepseek-flash``; real DeepSeek ids pass through as-is.
 
     ``GET /models`` is not documented on the ``/anthropic`` base, so ``models()``
     returns an empty list and model selection stays config-driven.

tests/test_agent/test_responses_bridge.py

@@ -167,7 +167,7 @@ def _reasoning_response(
     return Response(
         id="resp_r",
         created_at=1,
-        model="deepseek-v4-flash",
+        model="deepseek-flash",
         output=output,
         reasoning=top_level,
     )

tests/test_agent/test_responses_dispatch.py

@@ -430,7 +430,7 @@ async def test_dispatch_stream_failed_raises_with_error_detail() -> None:
                 "id": "resp_1",
                 "object": "response",
                 "created_at": 1,
-                "model": "deepseek-v4-flash",
+                "model": "deepseek-flash",
                 "status": "failed",
                 "output": [],
                 "error": {"code": "rate_limit_exceeded", "message": "slow down"},

tests/test_config/test_config.py

@@ -46,8 +46,8 @@ def test_read_valid_config() -> None:
     assert isinstance(providers["test3"], AnthropicProvider)
     assert isinstance(providers["foo1"], DeepseekProvider)
     # TOML omitted models → DeepSeek defaults.
-    assert set(providers["foo1"].models) == {"deepseek-v4-flash", "deepseek-v4-pro"}
+    assert set(providers["foo1"].models) == {"deepseek-flash", "deepseek-v4-pro"}
-    assert providers["foo1"].models["deepseek-v4-flash"].text is True
+    assert providers["foo1"].models["deepseek-flash"].text is True
     db = config.database
     assert db["implementation"] == "sqlite"
     assert db["url"] == ":memory:"
@@ -57,7 +57,7 @@ def test_read_valid_config() -> None:
 
 def test_deepseek_default_models_on_construct() -> None:
     provider = DeepseekProvider(access_key_or_token="sk-test")
-    assert set(provider.models) == {"deepseek-v4-flash", "deepseek-v4-pro"}
+    assert set(provider.models) == {"deepseek-flash", "deepseek-v4-pro"}
 
 
 def test_openai_default_models_on_construct() -> None:
@@ -179,7 +179,7 @@ preset = "deepseek"
 access_key_or_token = "sk-test"
 
 [providers.ds.models]
-"deepseek-v4-flash" = { text = true, convention = "responses" }
+"deepseek-flash" = { text = true, convention = "responses" }
 "deepseek-v4-pro" = { text = true }
 """,
         encoding="utf-8",
@@ -187,7 +187,7 @@ access_key_or_token = "sk-test"
     config = plyngent.config.load(path)
     provider = config.providers["ds"]
     assert isinstance(provider, DeepseekProvider)
-    assert provider.models["deepseek-v4-flash"].convention == "responses"
+    assert provider.models["deepseek-flash"].convention == "responses"
     assert provider.models["deepseek-v4-pro"].convention == ""
 
 
@@ -314,7 +314,7 @@ reasoning_effort = "high"
 
 [providers.ds.models]
 "deepseek-v4-pro" = { text = true, reasoning_effort = "max", thinking_budget_tokens = 32000 }
-"deepseek-v4-flash" = { text = true }
+"deepseek-flash" = { text = true }
 """,
         encoding="utf-8",
     )
@@ -327,8 +327,8 @@ reasoning_effort = "high"
     assert provider.thinking_budget_tokens == 0
     assert provider.models["deepseek-v4-pro"].reasoning_effort == "max"
     assert provider.models["deepseek-v4-pro"].thinking_budget_tokens == 32000
-    assert provider.models["deepseek-v4-flash"].reasoning_effort == ""
+    assert provider.models["deepseek-flash"].reasoning_effort == ""
-    assert provider.models["deepseek-v4-flash"].thinking_budget_tokens == 0
+    assert provider.models["deepseek-flash"].thinking_budget_tokens == 0
 
 
 def test_reasoning_effort_defaults_are_unset(tmp_path: Path) -> None:

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]

tests/test_memory/test_store.py

@@ -169,12 +169,12 @@ async def test_session_llm_remembered(store: MemoryStore) -> None:
     session = await store.create_session(
         name="llm",
         provider_name="deepseek",
-        model="deepseek-v4-flash",
+        model="deepseek-flash",
     )
     row = await store.get_session(session.sid)
     assert row is not None
     assert row.provider_name == "deepseek"
-    assert row.model == "deepseek-v4-flash"
+    assert row.model == "deepseek-flash"
     updated = await store.update_session_llm(session.sid, model="deepseek-v4-pro")
     assert updated.provider_name == "deepseek"
     assert updated.model == "deepseek-v4-pro"

tests/test_runtime/test_client_factory.py

@@ -60,7 +60,7 @@ def test_deepseek_openai_convention() -> None:
     client = create_client(provider)
     assert isinstance(client, DeepseekOpenAIClient)
     assert provider_to_openai_config(provider).base_url == "https://api.deepseek.com"
-    assert "deepseek-v4-flash" in provider.models
+    assert "deepseek-flash" in provider.models
     assert "deepseek-v4-pro" in provider.models
 
 
@@ -129,13 +129,13 @@ def test_deepseek_model_level_anthropic_convention() -> None:
         access_key_or_token="sk-test",
         models={
             "claude-proxy": ModelConfig(convention="anthropic"),
-            "deepseek-v4-flash": ModelConfig(),
+            "deepseek-flash": ModelConfig(),
         },
     )
     proxy = create_client(provider, model="claude-proxy")
     assert isinstance(proxy, DeepseekAnthropicClient)
     assert proxy.session.base_url == "https://api.deepseek.com/anthropic"
-    flash = create_client(provider, model="deepseek-v4-flash")
+    flash = create_client(provider, model="deepseek-flash")
     assert isinstance(flash, DeepseekOpenAIClient)
 
 
@@ -145,11 +145,11 @@ def test_deepseek_model_level_convention_override() -> None:
     provider = DeepseekProvider(
         access_key_or_token="sk-test",
         models={
-            "deepseek-v4-flash": ModelConfig(convention="responses"),
+            "deepseek-flash": ModelConfig(convention="responses"),
             "deepseek-v4-pro": ModelConfig(),
         },
     )
-    flash = create_client(provider, model="deepseek-v4-flash")
+    flash = create_client(provider, model="deepseek-flash")
     assert isinstance(flash, DeepseekResponsesClient)
     assert flash.kind == "responses"
     pro = create_client(provider, model="deepseek-v4-pro")