nas/MoviePilot
1
0
Fork 0
mirror of https://github.com/jxxghp/MoviePilot.git synced 2026-11-02 21:34:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(agent): preserve WebAgent event timeline

Browse Source
This commit is contained in:
jxxghp
2026-09-11 16:44:05 +08:00
parent d6bcedd3e0
commit 643efea1aa
21 changed files with 489 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
scripts/evaluation/codex.py
View File

@@ -76,7 +76,7 @@ def _configuration(settings: ModelSettings, proxy: EvaluationModelProxy, server:
"skill_mcp_dependency_install", "workspace_dependencies", "goals", "sleep_tool", "code_mode",
"code_mode_host", "enable_request_compression", "unbounded_connection_retries", "tool_suggest",
]
if scenario_id not in {"command_execution", "terminal_session"}:
if scenario_id not in {"command_execution", "terminal_session", "terminal_pty_session"}:
disabled.extend(("shell_tool", "unified_exec", "shell_snapshot"))
if scenario_id == "browser_navigation":
for feature in ("browser_use", "browser_use_external", "browser_use_full_cdp_access", "computer_use", "in_app_browser"):
@@ -104,7 +104,7 @@ def _configuration(settings: ModelSettings, proxy: EvaluationModelProxy, server:
"tools": {name: {"approval_mode": "approve"} for name in ("moviepilot_api", "read_skill", "read_tool_result")},
}},
}
if scenario_id in {"command_execution", "terminal_session"}:
if scenario_id in {"command_execution", "terminal_session", "terminal_pty_session"}:
# 命令场景只开放 CLI 已核对的两个终端动作；仍使用只读沙箱和 never 审批。
configuration.update({f"features.{name}": True for name in ("shell_tool", "unified_exec", "shell_snapshot")})
elif scenario_id == "browser_navigation":
@@ -257,7 +257,9 @@ async def _run_codex(scenario_id: str, settings: ModelSettings, executable: str,
raise RuntimeError("无法读取当前原生客户端自带模型目录")
catalog, catalog_metadata = _catalog(json.loads(catalog_result["stdout"]), settings.model)
(control_dir / "models.json").write_text(json.dumps(catalog), encoding="utf-8")
extra_native_tools = NATIVE_SHELL_TOOLS if scenario_id in {"command_execution", "terminal_session"} else frozenset()
extra_native_tools = NATIVE_SHELL_TOOLS if scenario_id in {
"command_execution", "terminal_session", "terminal_pty_session",
} else frozenset()
async with EvaluationMcpServer(world) as server, EvaluationModelProxy(
settings, probe_only=probe_only, extra_native_tools=extra_native_tools,
) as proxy:
@@ -283,7 +285,7 @@ async def _run_codex(scenario_id: str, settings: ModelSettings, executable: str,
server_stats = server.stats
skill_sha256 = server.skill_sha256
events, final_text, completed = _events(result.get("stdout", ""))
if scenario_id in {"command_execution", "terminal_session"}:
if scenario_id in {"command_execution", "terminal_session", "terminal_pty_session"}:
_record_native_command_events(world, events)
if any(event.get("type") == "evaluation.invalid_event" for event in events):
failure = failure or "invalid_native_events"