feat: add DeepSeek V4 Flash 0731 renderer

README.md

@@ -57,7 +57,7 @@ next_prompt_ids = r.bridge_to_next_turn(
 )
 ```
 
-Hand-coded renderers ship for `qwen3`, `qwen3-vl`, `qwen3.5`, `qwen3.6`, `qwen3.8`, `gemma4`, `glm-5`, `glm-5.1`, `glm-4.5`, `minimax-m2`, `deepseek-v3`, `deepseek-r1`, `kimi-k2`, `kimi-k2.5` / `kimi-k2.6`, `laguna-xs.2`, `laguna-xs-2.1`, `laguna-s-2.1`, `laguna-m.1`, `nemotron-3`, `nemotron-3-ultra`, `nemotron-3.5`, `llama-3`, `gpt-oss`, `hy3`, `inkling` / `inkling-small`, and `prime-qwen3`. Anything else falls back to `DefaultRenderer`, a generic `apply_chat_template` wrapper. `qwen3-vl`, `qwen3.5`, `qwen3.6`, `qwen3.8`, `gemma4`, `kimi-k2.5` / `kimi-k2.6`, and the Inkling checkpoints are multimodal (Inkling handles both image **and** audio).
+Hand-coded renderers ship for `qwen3`, `qwen3-vl`, `qwen3.5`, `qwen3.6`, `qwen3.8`, `gemma4`, `glm-5`, `glm-5.1`, `glm-4.5`, `minimax-m2`, `deepseek-v3`, `deepseek-r1`, `deepseek-v4` (V4 Flash 0731), `kimi-k2`, `kimi-k2.5` / `kimi-k2.6`, `laguna-xs.2`, `laguna-xs-2.1`, `laguna-s-2.1`, `laguna-m.1`, `nemotron-3`, `nemotron-3-ultra`, `nemotron-3.5`, `llama-3`, `gpt-oss`, `hy3`, `inkling` / `inkling-small`, and `prime-qwen3`. Anything else falls back to `DefaultRenderer`, a generic `apply_chat_template` wrapper. `qwen3-vl`, `qwen3.5`, `qwen3.6`, `qwen3.8`, `gemma4`, `kimi-k2.5` / `kimi-k2.6`, and the Inkling checkpoints are multimodal (Inkling handles both image **and** audio).
 
 ## API
 

docs/renderer-config.md

@@ -51,6 +51,7 @@ definition time. Template fields are covered by parity tests against
 | Nemotron-3.5 Lightning | `Nemotron35RendererConfig` | `enable_thinking`, `truncate_history_thinking` | - |
 | DeepSeek V3 | `DeepSeekV3RendererConfig` | - | - |
 | DeepSeek R1 | `DeepSeekR1RendererConfig` | - | - |
+| DeepSeek V4 Flash 0731 | `DeepSeekV4RendererConfig` | `enable_thinking`, `drop_thinking`, `reasoning_effort` | - |
 
 Configs are frozen value objects. To override a field, construct a new instance
 or call `config.model_copy(update={...})`.
@@ -145,6 +146,7 @@ the knobs its template actually exposes:
 | Kimi K2.5 / 2.6 | `thinking=False -> all`, else `tool_cycle` |
 | Nemotron-3 / 3.5 | `truncate_history_thinking=False -> all`; else `enable_thinking=False -> all`; else `tool_cycle` |
 | DeepSeek R1 | `template` |
+| DeepSeek V4 Flash 0731 | `enable_thinking=False` or `drop_thinking=False -> all`, else `tool_cycle` |
 | MiniMax M2 | `tool_cycle` |
 | DeepSeek V3, Qwen3-VL, Kimi K2, Laguna XS.2 / M.1 / XS-2.1 / S-2.1, Llama 3, Inkling | `all` |
 | PrimeIntellect Qwen3 | `all` |

renderers/__init__.py

@@ -48,6 +48,7 @@
     DefaultRendererConfig,
     DeepSeekR1RendererConfig,
     DeepSeekV3RendererConfig,
+    DeepSeekV4RendererConfig,
     GLM45RendererConfig,
     GLM51RendererConfig,
     GLM5RendererConfig,
@@ -85,6 +86,7 @@
 _LAZY_RENDERERS: dict[str, str] = {
     "DeepSeekR1Renderer": "renderers.deepseek_r1",
     "DeepSeekV3Renderer": "renderers.deepseek_v3",
+    "DeepSeekV4Renderer": "renderers.deepseek_v4",
     "DefaultRenderer": "renderers.default",
     "GLM45Renderer": "renderers.glm45",
     "GLM51Renderer": "renderers.glm5",
@@ -138,6 +140,8 @@ def __dir__() -> list[str]:
     "DeepSeekR1RendererConfig",
     "DeepSeekV3Renderer",
     "DeepSeekV3RendererConfig",
+    "DeepSeekV4Renderer",
+    "DeepSeekV4RendererConfig",
     "DefaultRenderer",
     "DefaultRendererConfig",
     "GLM45Renderer",

renderers/base.py

@@ -982,6 +982,9 @@ def is_multimodal(r: object) -> bool:
     # DeepSeek R1 (reasoning).
     "deepseek-ai/DeepSeek-R1": "deepseek-r1",
     "deepseek-ai/DeepSeek-R1-0528": "deepseek-r1",
+    # DeepSeek V4 Flash 0731 uses the repository's Python DSML encoder (the
+    # tokenizer intentionally ships no Jinja chat_template).
+    "deepseek-ai/DeepSeek-V4-Flash-0731": "deepseek-v4",
     # Kimi K2 (K2.5 and K2.6 share the K2.5 template, distinct from K2).
     "moonshotai/Kimi-K2-Instruct": "kimi-k2",
     "moonshotai/Kimi-K2.5": "kimi-k2.5",
@@ -1299,6 +1302,7 @@ def _populate_registry():
         return
     from renderers.deepseek_r1 import DeepSeekR1Renderer
     from renderers.deepseek_v3 import DeepSeekV3Renderer
+    from renderers.deepseek_v4 import DeepSeekV4Renderer
     from renderers.default import DefaultRenderer
     from renderers.glm5 import GLM5Renderer, GLM51Renderer
     from renderers.glm45 import GLM45Renderer
@@ -1344,6 +1348,7 @@ def _populate_registry():
             "minimax-m2": MiniMaxM2Renderer,
             "deepseek-v3": DeepSeekV3Renderer,
             "deepseek-r1": DeepSeekR1Renderer,
+            "deepseek-v4": DeepSeekV4Renderer,
             "hy3": Hy3Renderer,
             "inkling": InklingRenderer,
             "kimi-k2": KimiK2Renderer,

renderers/configs.py

@@ -930,6 +930,47 @@ class DeepSeekR1RendererConfig(BaseRendererConfig):
     _template_fields = frozenset()
 
 
+class DeepSeekV4RendererConfig(BaseRendererConfig):
+    """DeepSeek-V4-Flash-0731 reference-encoder configuration.
+
+    The checkpoint ships a Python encoder rather than a Jinja template.  These
+    fields mirror its public controls: chat vs thinking mode, historical
+    reasoning dropping, and the opt-in thinking-effort prefix.
+    """
+
+    name: Literal["deepseek-v4"] = "deepseek-v4"
+    _template_fields = frozenset(
+        {"enable_thinking", "drop_thinking", "reasoning_effort"}
+    )
+
+    enable_thinking: bool = False
+    """Select thinking mode.  ``False`` matches the official inference script."""
+
+    drop_thinking: bool = True
+    """Drop reasoning before the latest user query when no tools are present.
+
+    The reference encoder automatically preserves all reasoning whenever tools
+    are supplied, regardless of this value.
+    """
+
+    reasoning_effort: Literal["low", "high", "max"] = "low"
+    """Thinking-only effort prefix; ``low`` adds no text.
+
+    ``low`` is the checkpoint Python encoder's default. DeepSeek's hosted API
+    independently defaults its thinking effort to ``high``.
+    """
+
+    @model_validator(mode="after")
+    def _check_thinking_retention(self):
+        _reject_thinking_retention_conflict(
+            self,
+            "drop_thinking",
+            true_implies="tool_cycle",
+            false_implies="all",
+        )
+        return self
+
+
 RendererConfig = Annotated[
     Union[
         AutoRendererConfig,
@@ -960,6 +1001,7 @@ class DeepSeekR1RendererConfig(BaseRendererConfig):
         Nemotron35RendererConfig,
         DeepSeekV3RendererConfig,
         DeepSeekR1RendererConfig,
+        DeepSeekV4RendererConfig,
     ],
     Field(discriminator="name"),
 ]
@@ -1006,6 +1048,7 @@ class DeepSeekR1RendererConfig(BaseRendererConfig):
     "nemotron-3.5": Nemotron35RendererConfig,
     "deepseek-v3": DeepSeekV3RendererConfig,
     "deepseek-r1": DeepSeekR1RendererConfig,
+    "deepseek-v4": DeepSeekV4RendererConfig,
 }
 
 
@@ -1039,6 +1082,7 @@ def config_from_name(name: str) -> BaseRendererConfig | None:
     "DefaultRendererConfig",
     "DeepSeekR1RendererConfig",
     "DeepSeekV3RendererConfig",
+    "DeepSeekV4RendererConfig",
     "GLM45RendererConfig",
     "GLM51RendererConfig",
     "GLM5RendererConfig",