Default model reasoning effort to medium

src/agent.py

@@ -628,6 +628,9 @@ class ScreenJobAgent:
             return {"_raw": raw}
 
     def _call_model(self, input_items: list[dict[str, Any]]) -> Any:
+        effort = str(self.options.reasoning_effort or "medium").strip().lower()
+        if effort not in {"low", "medium", "high"}:
+            effort = "medium"
         return self.client.responses.create(
             model=self.options.model,
             instructions=SYSTEM_PROMPT,
@@ -636,6 +639,7 @@ class ScreenJobAgent:
             previous_response_id=self.previous_response_id,
             parallel_tool_calls=True,
             max_tool_calls=8,
+            reasoning={"effort": effort},
         )
 
     def run(self, job: str) -> AgentResult:
@@ -648,6 +652,7 @@ class ScreenJobAgent:
             {
                 "run_id": self.artifacts.run_id,
                 "model": self.options.model,
+                "reasoning_effort": self.options.reasoning_effort,
                 "objective": job,
                 "disabled_tools": sorted(self.disabled_tools),
             },

src/cli.py

@@ -28,6 +28,12 @@ def build_parser() -> argparse.ArgumentParser:
     parser.add_argument("--command-timeout", type=int, default=45, help="Timeout in seconds for execute_command.")
     parser.add_argument("--type-interval", type=float, default=0.02, help="Seconds between typed characters.")
     parser.add_argument("--click-pause", type=float, default=0.10, help="Mouse move duration before click.")
+    parser.add_argument(
+        "--reasoning-effort",
+        choices=["low", "medium", "high"],
+        default="medium",
+        help="Reasoning effort passed to the model.",
+    )
     parser.add_argument("--disable-tool", action="append", default=[], help="Disable a tool by name.")
     parser.add_argument("--skip-safety-check", action="store_true", help="Bypass pre-flight safety check.")
     parser.add_argument("--no-failsafe", action="store_true", help="Disable PyAutoGUI fail-safe.")
@@ -78,6 +84,7 @@ def main(argv: list[str] | None = None) -> int:
         command_timeout=args.command_timeout,
         type_interval=args.type_interval,
         click_pause=args.click_pause,
+        reasoning_effort=args.reasoning_effort,
         disable_tools=set(disabled_tools),
     )
     try:

src/models.py

@@ -58,4 +58,5 @@ class RuntimeOptions:
     command_timeout: int = 45
     type_interval: float = 0.02
     click_pause: float = 0.10
+    reasoning_effort: str = "medium"
     disable_tools: set[str] | None = None

src/server.py

@@ -25,6 +25,7 @@ class CreateJobRequest(BaseModel):
     command_timeout: int = Field(45, ge=1, le=600)
     type_interval: float = Field(0.02, ge=0.0, le=1.0)
     click_pause: float = Field(0.10, ge=0.0, le=2.0)
+    reasoning_effort: str = Field("medium", pattern="^(low|medium|high)$")
     disabled_tools: list[str] = Field(default_factory=list)
     safety_override: bool = False
     no_failsafe: bool = False
@@ -301,6 +302,7 @@ def create_app(config: AppConfig | None = None) -> FastAPI:
             command_timeout=payload.command_timeout,
             type_interval=payload.type_interval,
             click_pause=payload.click_pause,
+            reasoning_effort=payload.reasoning_effort,
             disabled_tools=payload.disabled_tools,
             safety_override=payload.safety_override,
             no_failsafe=payload.no_failsafe,

src/task_manager.py

@@ -48,6 +48,7 @@ class JobManager:
         command_timeout: int = 45,
         type_interval: float = 0.02,
         click_pause: float = 0.10,
+        reasoning_effort: str = "medium",
         disabled_tools: list[str] | None = None,
         safety_override: bool = False,
         no_failsafe: bool = False,
@@ -93,6 +94,7 @@ class JobManager:
                 "command_timeout": command_timeout,
                 "type_interval": type_interval,
                 "click_pause": click_pause,
+                "reasoning_effort": reasoning_effort,
                 "no_failsafe": no_failsafe,
                 "cancel_event": cancel_event,
             },
@@ -121,6 +123,7 @@ class JobManager:
         command_timeout: int,
         type_interval: float,
         click_pause: float,
+        reasoning_effort: str,
         no_failsafe: bool,
         cancel_event: threading.Event,
     ) -> None:
@@ -218,6 +221,7 @@ class JobManager:
             command_timeout=command_timeout,
             type_interval=type_interval,
             click_pause=click_pause,
+            reasoning_effort=reasoning_effort,
             disable_tools=set(disabled_tools),
         )
         try:

tests/test_cli.py

@@ -29,7 +29,10 @@ def test_cli_emits_structured_return_and_data(monkeypatch: Any, capsys, tmp_path
     def fake_assess_task_safety(*_args, **_kwargs):
         return True, "safe", {"safe": True}
 
+    captured_kwargs: dict[str, Any] = {}
+
     def fake_run_job(*_args, **_kwargs):
+        captured_kwargs.update(_kwargs)
         result = AgentResult(
             completed=True,
             result="Done",
@@ -66,3 +69,4 @@ def test_cli_emits_structured_return_and_data(monkeypatch: Any, capsys, tmp_path
     assert payload["response"]["data"] == "file1.txt\nfile2.txt"
     assert payload["return"] == "Task completed successfully"
     assert payload["data"] == "file1.txt\nfile2.txt"
+    assert captured_kwargs["options"].reasoning_effort == "medium"

tests/test_server_api.py

@@ -26,6 +26,7 @@ class FakeJobManager:
         command_timeout: int = 45,
         type_interval: float = 0.02,
         click_pause: float = 0.10,
+        reasoning_effort: str = "medium",
         disabled_tools: list[str] | None = None,
         safety_override: bool = False,
         no_failsafe: bool = False,
@@ -46,6 +47,7 @@ class FakeJobManager:
             "command_timeout": command_timeout,
             "type_interval": type_interval,
             "click_pause": click_pause,
+            "reasoning_effort": reasoning_effort,
             "no_failsafe": no_failsafe,
         }
         self._jobs[job_id] = {
@@ -189,6 +191,7 @@ def test_create_job_returns_only_job_id_and_defaults_model(tmp_path: Path, monke
     manager = app.state.manager
     assert manager.last_submit_payload["model"] == "gpt-5.4-mini"
     assert manager.last_submit_payload["disabled_tools"] == ["click"]
+    assert manager.last_submit_payload["reasoning_effort"] == "medium"
 
     status_res = client.get(f"/api/jobs/{job_id}/status", headers=headers)
     assert status_res.status_code == 200