refactor: remove all strix/ model alias machinery

The Strix proxy / ``strix/`` model namespace is gone. Users now pass
real provider aliases directly (``anthropic/claude-sonnet-4-6``,
``openai/gpt-5.4``, ``gemini/...``, ``openrouter/...``).

Deleted:
- ``STRIX_API_BASE`` constant in ``strix/config/config.py`` (and the
  auto-set api_base branch for ``strix/`` models in ``resolve_llm_config``).
- ``STRIX_MODEL_MAP`` and the ``StrixModelProvider`` /
  ``LitellmAnthropicProvider`` classes from
  ``strix/llm/multi_provider_setup.py``.
- ``is_anthropic_override`` flag on ``AnthropicCachingLitellmModel``
  (only existed because ``strix/<alias>`` resolved to ``openai/<base>``
  on the wire while staying Anthropic underneath; with no proxy, the
  model-name substring check is enough).
- ``startswith("strix/")`` branches in ``cli.py`` / ``main.py`` /
  ``dedupe.py`` and the ``uses_strix_models`` env-validation flag.

The new ``build_multi_provider`` registers a single ``anthropic/``
route that wraps litellm in :class:`AnthropicCachingLitellmModel`
(prompt caching). Every other prefix falls through to the SDK's
built-in routing.

Defaults flipped from ``strix/claude-sonnet-4.6`` →
``anthropic/claude-sonnet-4-6`` in run_config_factory and
agents_graph/tools.py + corresponding tests.

Tests updated:
- ``test_anthropic_cache_wrapper.py``: drop the override-flag tests.
- ``test_multi_provider_setup.py``: rewrite around the new single
  ``_AnthropicCachingProvider`` route.
- ``test_tool_registration_modes.py::test_load_skill_import_...``:
  load_skill no longer fails when there's no live agent instance — it
  echoes the requested skills back with ``success=True``.

Tests: 281/281 passing.

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

strix/interface/main.py

@@ -20,7 +20,6 @@ from rich.text import Text
 
 from strix.config import Config, apply_saved_config, save_current_config
 from strix.config.config import resolve_llm_config
-from strix.llm.multi_provider_setup import STRIX_MODEL_MAP
 
 
 apply_saved_config()
@@ -58,12 +57,10 @@ def validate_environment() -> None:
     missing_optional_vars = []
 
     strix_llm = Config.get("strix_llm")
-    uses_strix_models = strix_llm and strix_llm.startswith("strix/")
-
     if not strix_llm:
         missing_required_vars.append("STRIX_LLM")
 
-    has_base_url = uses_strix_models or any(
+    has_base_url = any(
         [
             Config.get("llm_api_base"),
             Config.get("openai_api_base"),
@@ -211,13 +208,7 @@ async def warm_up_llm() -> None:
 
     try:
         model_name, api_key, api_base = resolve_llm_config()
-        # ``strix/<alias>`` is routed through the Strix proxy (OpenAI-compatible);
-        # everything else is sent as-is.
         litellm_model: str | None = model_name
-        if model_name and model_name.startswith("strix/"):
-            base = model_name[len("strix/") :]
-            if base in STRIX_MODEL_MAP:
-                litellm_model = f"openai/{base}"
 
         test_messages = [
             {"role": "system", "content": "You are a helpful assistant."},