fix: address audit findings — SDK plumbing, TUI bus, dead code

Critical fixes:

- ``StrixOrchestrationHooks.on_agent_start`` now finds the
  ``CaidoCapability`` via ``ctx.context['caido_capability']`` instead
  of ``agent.capabilities`` (we use plain ``Agent``, not
  ``SandboxAgent``, so the latter never existed). The session
  manager's bundle already exposes the capability; ``run_strix_scan``
  threads it through ``make_agent_context`` and ``create_agent``
  forwards it to children.

- ``run_strix_scan`` registers the ``StrixTracingProcessor`` with the
  SDK's tracing provider via ``add_trace_processor`` so SDK trace
  spans hit ``run_dir/events.jsonl`` (was previously a parallel stream
  the SDK ignored).

- ``on_llm_end`` now writes to ``Tracer.record_llm_usage`` in
  addition to ``bus.record_usage`` so the CLI/TUI stats panel sees
  real numbers instead of zeros.

- ``run_strix_scan`` accepts an externally-built ``AgentMessageBus``
  + an explicit ``model`` arg. The TUI pre-creates the bus so its
  stop and chat-input handlers can submit ``bus.send`` /
  ``bus.cancel_descendants`` coroutines onto the scan thread's loop
  via ``asyncio.run_coroutine_threadsafe`` — replacing the
  TODO-stub no-ops.

- ``model`` config now propagates root → context → child agents in
  ``create_agent`` (was hardcoded fallback).

Dead-code removal:

- Deleted the ``load_skill`` tool entirely (host module, sandbox
  module, TUI renderer, tests). The legacy implementation reached
  into a global ``_agent_instances`` registry that no longer exists;
  the post-migration stub returned ``success=True`` without
  injecting anything — pure theater. Skills are still preloaded via
  the system prompt at scan-bring-up.

- Dropped ``tenacity`` and ``xmltodict`` from
  ``[project.dependencies]`` — neither is imported anywhere
  post-migration.

- Stripped the system prompt's "use the load_skill tool" lines.

Tests: 278/278 passing. Removed two ``load_skill`` test cases and a
``test_tool_registration_modes::test_load_skill_import_...`` assertion
that exercised the deleted module.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

tests/agents/test_factory.py

@@ -115,7 +115,6 @@ def test_agent_includes_graph_and_sandbox_tools() -> None:
         "web_search",
         "str_replace_editor",
         "create_vulnerability_report",
-        "load_skill",
         "browser_action",
         "terminal_execute",
         "python_action",

tests/tools/test_remaining_local_tools.py

@@ -1,12 +1,7 @@
-"""Phase 2.4 smoke tests for the remaining local SDK tool wrappers.
+"""Smoke tests for the remaining local SDK tool wrappers.
 
 Covers: web_search, file_edit (str_replace_editor + list_files +
-search_files), reporting (create_vulnerability_report), load_skill,
-finish_scan.
-
-Pattern matches test_sdk_local_tools.py — confirm registration as
-``FunctionTool``, exercise the legacy delegation path, verify that
-sandbox-bound tools route through ``post_to_sandbox``.
+search_files), reporting (create_vulnerability_report), finish_scan.
 """
 
 from __future__ import annotations
@@ -25,7 +20,6 @@ from strix.tools.file_edit.tools import (
     str_replace_editor,
 )
 from strix.tools.finish.tool import finish_scan
-from strix.tools.load_skill.tool import load_skill
 from strix.tools.reporting.tool import create_vulnerability_report
 from strix.tools.web_search.tool import web_search
 
@@ -69,7 +63,6 @@ def test_all_remaining_tools_are_function_tools() -> None:
         list_files,
         search_files,
         create_vulnerability_report,
-        load_skill,
         finish_scan,
     ):
         assert isinstance(tool, FunctionTool)
@@ -240,38 +233,6 @@ async def test_create_vulnerability_report_delegates_to_impl() -> None:
     assert kwargs["method"] is None
 
 
-# --- load_skill ----------------------------------------------------------
-
-
-@pytest.mark.asyncio
-async def test_load_skill_passes_adapter_with_agent_id() -> None:
-    """The wrapper must build the legacy-shaped adapter from ctx.context."""
-    captured: dict[str, Any] = {}
-
-    def fake_legacy(*, agent_state: Any, skills: str) -> dict[str, Any]:
-        captured["agent_id"] = agent_state.agent_id
-        captured["skills"] = skills
-        return {"success": True, "loaded_skills": ["recon"]}
-
-    with patch(
-        "strix.tools.load_skill.tool._impl.load_skill",
-        side_effect=fake_legacy,
-    ):
-        out = await _invoke(load_skill, _ctx_for("agent-XYZ"), skills="recon")
-
-    assert out["success"] is True
-    assert captured["agent_id"] == "agent-XYZ"
-    assert captured["skills"] == "recon"
-
-
-@pytest.mark.asyncio
-async def test_load_skill_with_empty_input() -> None:
-    """End-to-end: empty skills string yields the legacy validation error."""
-    out = await _invoke(load_skill, _ctx_for(), skills="")
-    assert out["success"] is False
-    assert "No skills" in out["error"]
-
-
 # --- finish_scan ---------------------------------------------------------
 
 

tests/tools/test_tool_registration_modes.py

@@ -58,45 +58,5 @@ def test_sandbox_registers_sandbox_tools_but_not_non_sandbox_tools(
     assert "list_requests" in names
     assert "create_agent" not in names
     assert "finish_scan" not in names
-    assert "load_skill" not in names
     assert "browser_action" not in names
     assert "web_search" not in names
-
-
-def test_load_skill_import_does_not_register_create_agent_in_sandbox(
-    monkeypatch: Any,
-) -> None:
-    monkeypatch.setenv("STRIX_SANDBOX_MODE", "true")
-    monkeypatch.setenv("STRIX_DISABLE_BROWSER", "true")
-    monkeypatch.delenv("PERPLEXITY_API_KEY", raising=False)
-    monkeypatch.setattr(Config, "load", classmethod(_empty_config_load))
-
-    clear_registry()
-    for name in list(sys.modules):
-        if name == "strix.tools" or name.startswith("strix.tools."):
-            sys.modules.pop(name, None)
-
-    load_skill_module = importlib.import_module("strix.tools.load_skill.load_skill_actions")
-    registry = importlib.import_module("strix.tools.registry")
-
-    names_before = set(registry.get_tool_names())
-    assert "load_skill" not in names_before
-    assert "create_agent" not in names_before
-
-    state_type = type(
-        "DummyState",
-        (),
-        {
-            "agent_id": "agent_test",
-            "context": {},
-            "update_context": lambda self, key, value: self.context.__setitem__(key, value),
-        },
-    )
-    result = load_skill_module.load_skill(state_type(), "nmap")
-
-    names_after = set(registry.get_tool_names())
-    assert "create_agent" not in names_after
-    # load_skill no longer reaches into the legacy _agent_instances global —
-    # it returns ``success=True`` with the requested skills echoed back.
-    assert result["success"] is True
-    assert result["loaded_skills"] == ["nmap"]