feat(migration): phase 5 — root agent factory + entry point

Three new modules that wire Phases 0-4 into a runnable Strix scan:

- strix/agents/sdk_prompt.py: standalone Jinja-based system prompt
  renderer. Reuses the existing strix/agents/StrixAgent/system_prompt.
  jinja template (508 lines, the actual production prompt) so behavior
  parity with the legacy LLM._load_system_prompt is byte-identical.
  Skill resolution mirrors LLM._get_skills_to_load (caller skills →
  scan_modes/<mode> → whitebox pair, deduped). Fail-soft: template
  errors return empty string and log; agent construction must never
  blow up on prompt load.

- strix/agents/sdk_factory.py: build_strix_agent(name, skills, is_root)
  assembles an agents.Agent. Root carries finish_scan and stops there;
  child carries agent_finish and stops there (C4). Caido tools come
  from CaidoCapability automatically — we don't include them in
  _BASE_TOOLS to avoid double-registration when the SDK runtime merges
  capability tools. model=None so RunConfig drives the model alias
  through MultiProvider rather than the SDK default. make_child_factory
  returns a closure over scan-level config (scan_mode, is_whitebox,
  interactive, scope context) for ctx.context['agent_factory'] — the
  Phase 3 create_agent tool calls it with (name, skills) per child.

- strix/sdk_entry.py: run_strix_scan() — the top-level coroutine.
  Builds the bus, brings up (or reuses) a sandbox session via
  session_manager, builds the root Agent and the child factory, builds
  the per-agent context dict, registers the root in the bus, builds
  the RunConfig, calls Runner.run, and cleans up the session in a
  finally. Cancels descendants before re-raising any exception (C9).
  cleanup_on_exit toggle preserves the cached session for resume
  scenarios. _build_root_task and _build_scope_context preserve the
  legacy StrixAgent.execute_scan task formatting + scope context shape
  so the prompt template sees identical inputs.

Tests: 21 new tests (10 for factory + prompt, 11 for entry point).
Factory: root vs child tool list parity, finish_scan/agent_finish
placement, tool_use_behavior dict shape, Caido absence (capability-
provided), make_child_factory closure semantics. Entry point (all
mocked, no real Docker/LLM): wiring shape verification — context dict
carries every field downstream consumers read, session manager called
with correct scan_id, cleanup runs even on Runner.run failure,
cleanup skipped when disabled, scan_id auto-generation, scan-level
config (scan_mode, is_whitebox) flows into the factory. Task and scope
builders verified against the same shape as legacy.

Per-file ruff ignores added: TC002 on sdk_factory (Tool used at
runtime in _BASE_TOOLS tuple), TC003 + PLR0912 on sdk_entry (Path
runtime-imported; _build_root_task's per-target-type branches are
intentional and well-bounded).

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

pyproject.toml

@@ -303,6 +303,15 @@ ignore = [
 # CaidoCapability uses agents.tool.Tool at runtime — pydantic Field
 # annotations and the cached _CAIDO_TOOLS tuple need it eagerly.
 "strix/sandbox/caido_capability.py" = ["TC002"]
+# Agent factory: agents.tool.Tool is used at runtime in the _BASE_TOOLS
+# tuple type, not just for annotations.
+"strix/agents/sdk_factory.py" = ["TC002"]
+# Entry point: ``Path`` is used at runtime by the typing of the
+# session_manager call; importing under TYPE_CHECKING would defer
+# resolution past where mypy needs it. ``_build_root_task`` legitimately
+# walks every supported target type — splitting it into per-type
+# helpers would add indirection without simplifying anything.
+"strix/sdk_entry.py" = ["TC003", "PLR0912"]
 # Sandbox dispatch helper has many short-circuit error returns (auth fail,
 # size cap, decode fail, etc). Each is a distinct, documented failure mode
 # the model needs to see verbatim — collapsing them harms readability.