mirror of
https://github.com/usestrix/strix.git
synced 2026-08-20 10:33:34 +02:00
0xallamandClaude Opus 4.7
d8881498ee
The SDK harness is the only path now; legacy host-side code is gone. File names no longer carry the ``sdk_`` distinction. Deleted legacy host-side modules: - strix/agents/StrixAgent/ (template moved to strix/agents/prompts/) - strix/agents/base_agent.py, state.py - strix/llm/llm.py, config.py - strix/runtime/docker_runtime.py, runtime.py - strix/tools/executor.py, agents_graph/agents_graph_actions.py - strix/interface/sdk_dispatch.py + the env-flag dispatch in cli.py Renamed (drop ``sdk_`` prefix): - strix/sdk_entry.py → strix/entry.py - strix/agents/sdk_factory.py → strix/agents/factory.py - strix/agents/sdk_prompt.py → strix/agents/prompt.py - strix/tools/<x>/<x>_sdk_tool[s].py → strix/tools/<x>/tool[s].py - strix/tools/_legacy_adapter.py → strix/tools/_state_adapter.py - ``_legacy`` aliases inside the wrappers → ``_impl`` CLI + TUI now call ``run_strix_scan`` directly — they build the sandbox image / sources_path locally and rely on ``session_manager.cleanup`` (called inside ``run_strix_scan``'s finally) for teardown. Three TUI handlers that reached into legacy multi-agent globals (``_agent_instances``, ``send_user_message_to_agent``, ``stop_agent``) are now no-ops with a TODO; reconnecting them to the ``AgentMessageBus`` is a follow-up. Tracer.get_total_llm_stats no longer reaches into the deleted ``agents_graph_actions`` globals — the orchestration hooks now feed the tracer via ``Tracer.record_llm_usage`` (live + completed buckets). finish_scan's ``_check_active_agents`` and load_skill's runtime ``_agent_instances`` reach-in are no-op stubs; the ``AgentMessageBus`` is the source of truth post-migration. llm/utils.py rewritten to keep only the streaming-parser helpers (``normalize_tool_format``, ``parse_tool_invocations``, ``fix_incomplete_tool_call``, ``format_tool_call``, ``clean_content``). ``STRIX_MODEL_MAP`` moved to ``llm/multi_provider_setup.py`` (its only remaining caller). Per-file ruff ignores added for legacy interface modules (TUI / main / CLI / utils / streaming_parser / tool_components) and tracer.py — pre-existing PLC0415/BLE001/PLR0915 patterns are out of scope. Tests: 287/287 passing. Renamed test files to drop ``sdk_`` prefix. ``test_tracer.py::test_get_total_llm_stats_aggregates_live_and_completed`` rewritten to feed ``Tracer.record_llm_usage`` instead of legacy globals. Test file annotations added so pre-commit's strict mypy passes. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
103 lines
2.9 KiB
Python
103 lines
2.9 KiB
Python
"""SDK function-tool wrapper for the legacy ``browser_action`` tool.
|
|
|
|
The browser is fully sandbox-bound — the legacy implementation runs
|
|
inside the container against a Playwright instance the tool server
|
|
manages. We delegate every action verbatim to ``post_to_sandbox``.
|
|
|
|
The legacy ``browser_action`` is a single mega-tool dispatching 21
|
|
discrete actions (launch, goto, click, scroll_*, new_tab, etc.). We
|
|
preserve that shape for parity rather than fanning out into 21
|
|
separate tools — that would balloon the system prompt and surprise
|
|
the model.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from typing import Any, Literal
|
|
|
|
from agents import RunContextWrapper
|
|
|
|
from strix.tools._decorator import strix_tool
|
|
from strix.tools._sandbox_dispatch import post_to_sandbox
|
|
|
|
|
|
def _dump(result: dict[str, Any]) -> str:
|
|
return json.dumps(result, ensure_ascii=False, default=str)
|
|
|
|
|
|
BrowserAction = Literal[
|
|
"launch",
|
|
"goto",
|
|
"click",
|
|
"type",
|
|
"scroll_down",
|
|
"scroll_up",
|
|
"back",
|
|
"forward",
|
|
"new_tab",
|
|
"switch_tab",
|
|
"close_tab",
|
|
"wait",
|
|
"execute_js",
|
|
"double_click",
|
|
"hover",
|
|
"press_key",
|
|
"save_pdf",
|
|
"get_console_logs",
|
|
"view_source",
|
|
"close",
|
|
"list_tabs",
|
|
]
|
|
|
|
|
|
# Browser actions can take time (page loads, navigation timeouts), so
|
|
# match the sandbox dispatch read budget rather than capping shorter.
|
|
@strix_tool(timeout=180)
|
|
async def browser_action(
|
|
ctx: RunContextWrapper,
|
|
action: BrowserAction,
|
|
url: str | None = None,
|
|
coordinate: str | None = None,
|
|
text: str | None = None,
|
|
tab_id: str | None = None,
|
|
js_code: str | None = None,
|
|
duration: float | None = None,
|
|
key: str | None = None,
|
|
file_path: str | None = None,
|
|
clear: bool = False,
|
|
) -> str:
|
|
"""Drive the sandboxed Playwright browser.
|
|
|
|
Args:
|
|
action: The browser action to dispatch — see ``BrowserAction``
|
|
literal for the full set.
|
|
url: Required for ``launch`` / ``goto`` / ``new_tab`` (with URL).
|
|
coordinate: ``"x,y"`` pixel target for click/hover/double_click.
|
|
text: Required for ``type``.
|
|
tab_id: Optional explicit tab targeting; defaults to the active tab.
|
|
js_code: Required for ``execute_js``.
|
|
duration: Seconds to wait for ``wait`` action.
|
|
key: Required for ``press_key`` (e.g. ``"Enter"``, ``"Escape"``).
|
|
file_path: Required for ``save_pdf``.
|
|
clear: For ``type``, clears the field first.
|
|
"""
|
|
return _dump(
|
|
await post_to_sandbox(
|
|
ctx,
|
|
"browser_action",
|
|
{
|
|
"action": action,
|
|
"url": url,
|
|
"coordinate": coordinate,
|
|
"text": text,
|
|
"tab_id": tab_id,
|
|
"js_code": js_code,
|
|
"duration": duration,
|
|
"key": key,
|
|
"file_path": file_path,
|
|
"clear": clear,
|
|
},
|
|
),
|
|
)
|