diff --git a/e2e/browser-v3/arena/llm_policy.py b/e2e/browser-v3/arena/llm_policy.py index 80db3f03..c9d799f7 100644 --- a/e2e/browser-v3/arena/llm_policy.py +++ b/e2e/browser-v3/arena/llm_policy.py @@ -704,6 +704,12 @@ def build(name: str, model: str = "", endpoint: str = "", **_: Any) -> Any: scripted_drag=True, auto_complete=True, som=False, native_pickers=True, verify_terminal=True, post_mouse_vision=True, multi_cap=6, fill_verify=True, **v17) + if name == "osw-llm-v20": # v19 + strict-retry on unparseable replies + 800-token headroom + v20 = dict(v7, system=OSW_SYSTEM_V8 + OSW_SYSTEM_V9_WIDGETS + OSW_SYSTEM_V16, max_tokens=800) + return OpenSwarmLlmPolicy(name=name, multi=True, vision="progressive", fastpath=True, + scripted_drag=True, auto_complete=True, som=False, + native_pickers=True, verify_terminal=True, post_mouse_vision=True, + multi_cap=6, fill_verify=True, dispatch=True, offscreen=True, **v20) if name in ("osw-llm-v18", "osw-llm-v19"): # v18 + (v19) off-screen rows and group ordinals v18 = dict(v7, system=OSW_SYSTEM_V8 + OSW_SYSTEM_V9_WIDGETS + OSW_SYSTEM_V16, max_tokens=500) return OpenSwarmLlmPolicy(name=name, multi=True, vision="progressive", fastpath=True,