refactor(dedupe): route through MultiProvider + cache wrapper + retry policy

``check_duplicate`` was calling ``litellm.completion(...)`` directly
via ``resolve_llm_config()``, bypassing every layer the main agent
loop runs through:

- :class:`MultiProvider` (so ``anthropic/...`` aliases never went
  through :class:`AnthropicCachingLitellmModel` and missed the
  ``cache_control`` patching on the system prompt — 4x cost on
  repeated dedupe calls within the same scan).
- :data:`DEFAULT_RETRY` (no retry on 429s / network blips — the
  caller's broad except-and-fallback was hiding this).

Switch to the SDK's :meth:`Model.get_response` directly: same model
selection, same retry policy, same cache wrapper. Extract assistant
text from ``ModelResponse.output`` via the canonical
``ResponseOutputMessage`` walk.

``check_duplicate`` is now async — drops the ``asyncio.to_thread``
indirection in ``_do_create``. Validation logic is fast-sync; running
it on the event loop is fine.

Drive-by: rename ``_DEFAULT_RETRY`` → ``DEFAULT_RETRY`` in
``run_config_factory`` so the dedupe path can reuse the same constant
without reaching into a private name.

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

strix/tools/reporting/tool.py

@@ -2,7 +2,6 @@
 
 from __future__ import annotations
 
-import asyncio
 import json
 import logging
 import re
@@ -152,7 +151,7 @@ _REQUIRED_FIELDS = {
 }
 
 
-def _do_create(  # noqa: PLR0912
+async def _do_create(  # noqa: PLR0912
     *,
     title: str,
     description: str,
@@ -238,7 +237,7 @@ def _do_create(  # noqa: PLR0912
             "endpoint": endpoint,
             "method": method,
         }
-        dedupe = check_duplicate(candidate, existing)
+        dedupe = await check_duplicate(candidate, existing)
         if dedupe.get("is_duplicate"):
             duplicate_id = dedupe.get("duplicate_id", "")
             duplicate_title = next(
@@ -397,8 +396,7 @@ async def create_vulnerability_report(
             ``fix_before`` (verbatim source), ``fix_after`` (suggested
             replacement).
     """
-    result = await asyncio.to_thread(
-        _do_create,
+    result = await _do_create(
         title=title,
         description=description,
         impact=impact,