feat(sdk): support max output tokens

python/sdk/src/deepseek_harness/api.py

@@ -20,6 +20,7 @@ class DeepSeekHarnessConfig:
 
     provider: str = "deepseek"
     model: str = "deepseek-v4-flash"
+    max_tokens: int | None = None
     cwd: str | None = None
     runtime_cwd: str | None = None
     session_root: str | None = None
@@ -100,6 +101,7 @@ class DeepSeekHarness:
             cwd=self._cwd,
             provider=self.config.provider,
             model=self.config.model,
+            max_tokens=self.config.max_tokens,
         )
         self._initialized = True
 

python/sdk/src/deepseek_harness/client.py

@@ -120,12 +120,15 @@ class HarnessClient:
         cwd: str,
         provider: str,
         model: str,
+        max_tokens: int | None = None,
     ) -> InitializeResponse:
         payload: JsonObject = {
             "cwd": str(Path(cwd).resolve()),
             "provider": provider,
             "model": model,
         }
+        if max_tokens is not None:
+            payload["maxTokens"] = max_tokens
         try:
             return self.request("initialize", payload, response_model=InitializeResponse)
         except BaseException: