fix(agent): keep MCP connection failures from cancelling gateway

[guix4ever]

Summary

• Isolate a bare asyncio.CancelledError leaked by an MCP transport or session during connection setup.
• Keep a failed MCP server from terminating gateway startup while logging the affected server.
• Re-raise cancellation when Raven's own connection task has an active cancellation request.
• Add deterministic regression coverage for both SDK-side and external cancellation paths.

Type

• Fix
• Feature
• Docs
• CI / tooling
• Refactor
• Other

Verification

• uv run pytest tests/test_sandbox_unit.py tests/test_tool_registry_timeout.py -x -q - 76 passed.

• uv run --extra dev ruff check raven/agent/tools/mcp.py tests/test_sandbox_unit.py - passed.

• uv run --extra dev ruff format --check raven/agent/tools/mcp.py tests/test_sandbox_unit.py - passed.

• git diff --check - passed.

• Relevant tests pass locally

• Relevant lint / type checks pass locally

• User-facing docs or screenshots are updated when needed

No user-facing documentation or screenshots are required because this change only corrects connection failure isolation.

Risk

• Security impact considered
• Backward compatibility considered
• Rollback path is clear for risky changes

External gateway or task cancellation still propagates when Task.cancelling() reports an active cancellation request. Only a bare cancellation with no pending task cancellation is treated as an MCP server failure. Existing handling for ordinary exceptions and exception groups is unchanged. The change can be rolled back by reverting this commit.

Related Issues

Closes #231