feat: extract sandbox runtimes from core

[zouyonghe]

Summary

• Add generic sandbox provider registration, registry, manager, and dashboard sandbox APIs.
• Remove built-in CUA, Shipyard, Shipyard Neo, Boxlite, and Bay runtime implementations from core.
• Keep core sandbox tool mounting provider-driven and remove runtime-specific dashboard/config coupling.

Verification

• uv run ruff format ... reported 20 files left unchanged
• uv run ruff check ... reported All checks passed!
• uv run pytest tests/unit/test_cua_extracted_from_core.py tests/unit/test_sandbox_computer_client.py tests/unit/test_sandbox_manager.py tests/unit/test_sandbox_provider.py tests/unit/test_sandbox_registry.py tests/unit/test_sandbox_models.py tests/unit/test_computer.py tests/unit/test_astr_main_agent.py tests/test_computer_config.py tests/test_dashboard.py -q reported 174 passed, 1 warning

[sourcery-ai]

Sorry @zouyonghe, your pull request is larger than the review limit of 150000 diff characters

[gemini-code-assist]

Code Review

This pull request transitions the sandbox management system to a provider-based architecture, removing hardcoded implementations for Shipyard and CUA from the core. It introduces a SandboxManager, SandboxRegistry, and a SandboxProvider protocol to handle sandbox lifecycles, leases, and persistence generically. The dashboard is updated with new sandbox routes, and tool registration is refactored to be dynamically driven by providers. Review feedback highlights the need to restore provider-specific system prompts lost during extraction, improve resilience when sandboxes are busy, ensure compatibility with different booter implementations of the available check, and avoid blocking the event loop with synchronous file I/O in the registry.

[gemini-code-assist]

The generic sandbox tool mounting logic should also include provider-specific system prompt instructions if available. The extraction of runtimes removed important guidance (e.g., file path rules for Shipyard Neo or GUI instructions for CUA) that the LLM needs to use the tools effectively. The SandboxProvider protocol should be updated to provide these instructions. Please ensure this new functionality is accompanied by corresponding unit tests and that the logic for extracting provider info is shared to avoid duplication.

Suggested change

	provider_info = get_sandbox_provider_info(booter)
	if provider_info:
	for tool_name in provider_info.get("tool_names", []):
	tool = tool_mgr.get_func(tool_name)
	if tool and getattr(tool, "active", True):
	req.func_tool.add_tool(tool)
	provider_info = get_sandbox_provider_info(booter)
	if provider_info:
	if prompt := provider_info.get("system_prompt"):
	req.system_prompt = f"{req.system_prompt or ''}\n{prompt}\n"
	for tool_name in provider_info.get("tool_names", []):
	tool = tool_mgr.get_func(tool_name)
	if tool and getattr(tool, "active", True):
	req.func_tool.add_tool(tool)

References

1. When implementing similar functionality for different cases (e.g., direct vs. quoted attachments), refactor the logic into a shared helper function to avoid code duplication.
2. New functionality, such as handling attachments, should be accompanied by corresponding unit tests.

[gemini-code-assist]

Include the system_prompt from the provider in the info dictionary so it can be utilized by the agent during tool registration. Refactor the logic into a shared helper function to avoid code duplication. Also, ensure this new functionality is accompanied by unit tests.

Suggested change

	def _sandbox_provider_info(provider_id: str, provider: SandboxProvider) -> dict:
	return {
	"provider_id": provider_id,
	"capabilities": sorted(getattr(provider, "capabilities", set())),
	"tool_names": sorted(getattr(provider, "tool_names", set())),
	}
	def _sandbox_provider_info(provider_id: str, provider: SandboxProvider) -> dict:
	return {
	"provider_id": provider_id,
	"capabilities": sorted(getattr(provider, "capabilities", set())),
	"tool_names": sorted(getattr(provider, "tool_names", set())),
	"system_prompt": getattr(provider, "system_prompt", ""),
	}

References

1. When implementing similar functionality for different cases (e.g., direct vs. quoted attachments), refactor the logic into a shared helper function to avoid code duplication.
2. New functionality, such as handling attachments, should be accompanied by corresponding unit tests.

[gemini-code-assist]

The available attribute might be a property or a synchronous method in some implementations. It's safer to check if it's callable before awaiting it to avoid a TypeError.

        if callable(available):
            return await available()
        return bool(available)

[gemini-code-assist]

If the current sandbox is busy (e.g., taken over by another session), raising a RuntimeError here will cause the agent to fail. Instead of crashing, it would be more resilient to clear the current sandbox assignment for this session and fall through to the logic that finds the default sandbox or creates a new one.

Suggested change

	if not self.acquire_lease(current_sandbox_id, session_id):
	raise RuntimeError(f"Sandbox {current_sandbox_id} is busy")
	booter = self.session_booter[current_sandbox_id]
	if await self.booter_available(booter):
	self.registry.touch_sandbox(current_sandbox_id)
	self.save_registry()
	self.schedule_idle_cleanup(current_sandbox_id, idle_timeout)
	return booter
	self.session_booter.pop(current_sandbox_id, None)
	if self.acquire_lease(current_sandbox_id, session_id):
	booter = self.session_booter[current_sandbox_id]
	if await self.booter_available(booter):
	self.registry.touch_sandbox(current_sandbox_id)
	self.save_registry()
	self.schedule_idle_cleanup(current_sandbox_id, idle_timeout)
	return booter
	self.session_booter.pop(current_sandbox_id, None)
	else:
	self.registry.set_current_sandbox_id(session_id, None)
	self.save_registry()

[gemini-code-assist]

The SandboxProvider protocol should include a system_prompt field to allow runtimes to provide necessary instructions to the LLM (e.g., path conventions or specific tool usage workflows). New functionality should be accompanied by corresponding unit tests.

Suggested change

	class SandboxProvider(Protocol):
	provider_id: str
	capabilities: set[str]
	tool_names: set[str]
	class SandboxProvider(Protocol):
	provider_id: str
	capabilities: set[str]
	tool_names: set[str]
	system_prompt: str = ""

References

1. New functionality, such as handling attachments, should be accompanied by corresponding unit tests.

[gemini-code-assist]

Performing synchronous file I/O with write_text inside the event loop can block other coroutines, especially if the registry grows large. Consider using an executor or an asynchronous file library for persistence.