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/config/config.py

@@ -5,9 +5,6 @@ from pathlib import Path
 from typing import Any, ClassVar
 
 
-STRIX_API_BASE = "https://models.strix.ai/api/v1"
-
-
 class Config:
     """Configuration Manager for Strix."""
 
@@ -197,28 +194,23 @@ def save_current_config() -> bool:
 
 
 def resolve_llm_config() -> tuple[str | None, str | None, str | None]:
-    """Resolve LLM model, api_key, and api_base based on STRIX_LLM prefix.
+    """Resolve LLM model, api_key, and api_base.
 
-    Returns:
-        tuple: (model_name, api_key, api_base)
-        - model_name: Original model name (strix/ prefix preserved for display)
-        - api_key: LLM API key
-        - api_base: API base URL (auto-set to STRIX_API_BASE for strix/ models)
+    Returns ``(model_name, api_key, api_base)``. ``api_base`` falls back
+    through the ``LLM_API_BASE`` / ``OPENAI_API_BASE`` /
+    ``LITELLM_BASE_URL`` / ``OLLAMA_API_BASE`` env chain so the user can
+    point at any OpenAI-compatible endpoint without changing the code.
     """
     model = Config.get("strix_llm")
     if not model:
         return None, None, None
 
     api_key = Config.get("llm_api_key")
-
-    if model.startswith("strix/"):
-        api_base: str | None = STRIX_API_BASE
-    else:
-        api_base = (
-            Config.get("llm_api_base")
-            or Config.get("openai_api_base")
-            or Config.get("litellm_base_url")
-            or Config.get("ollama_api_base")
-        )
+    api_base: str | None = (
+        Config.get("llm_api_base")
+        or Config.get("openai_api_base")
+        or Config.get("litellm_base_url")
+        or Config.get("ollama_api_base")
+    )
 
     return model, api_key, api_base