Choose the LLM route by model, and add a capability matrix

The arrival of non-Anthropic models made a latent bug observable: the
delegate's client was hardcoded to the Anthropic passthrough, so
pointing NISSE_ROLE_DELEGATE at gpt-6-astra or a local model would
have sent Anthropic-shaped /v1/messages bodies to something that does
not speak them. A5 promises the frontier tier is swappable "as a
configuration change, not a refactor", and it was not.

select_client now picks the route from the model: the vendor-native
adapter where one exists, LiteLLM's normalization otherwise — which is
exactly what A13 prescribes for a vendor whose renderer adapter has
not been written, pending validation against the A16 eval set.

Also adds the capability matrix Part H asks for. It says the
thresholds that depend on local capability — A12's failure count,
A14's consult budget, A15's manifest size — must be tuned "on the real
hardware", and that needs measurement rather than reputation. The
harness probes each model for the things that actually break: whether
it calls a tool at all, whether the plan it submits has substance
(llama3.2 emitted "{"), whether it can consume its own tool result,
and whether prompt-level JSON holds. Opt in with
NISSE_CAPABILITY_MODELS; it spends real tokens across several models.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

nisse-dev/tests/test_llm.py

@@ -11,7 +11,14 @@ from nisse_dev.canonical import (
     UserMessage,
 )
 from nisse_dev.envfile import load_env_file
-from nisse_dev.llm import RATE_LIMIT_RETRY_S, LiteLLMClient, LLMError, RoleMap
+from nisse_dev.llm import (
+    RATE_LIMIT_RETRY_S,
+    LiteLLMClient,
+    LLMError,
+    RoleMap,
+    has_native_adapter,
+    select_client,
+)
 
 EVENTS = [StoredEvent(id=1, ts="t", event=UserMessage(text="hi", source="m:1"))]
 
@@ -203,3 +210,28 @@ def test_load_env_file_missing_is_noop(tmp_path: Path) -> None:
     env: dict[str, str] = {}
     load_env_file(tmp_path / "nope.env", env)
     assert env == {}
+
+
+# --- route selection (A5 vendor fluidity) --------------------------------
+
+
+def test_anthropic_models_take_the_native_route() -> None:
+    normalized, passthrough = object(), object()
+    for model in ("claude-haiku-4-5", "claude-opus-5", "anthropic/claude-sonnet-5"):
+        assert select_client(model, normalized, passthrough) is passthrough
+
+
+def test_other_vendors_take_the_normalized_route() -> None:
+    # A13: provisionally accept LiteLLM's normalization for a vendor whose
+    # renderer adapter does not exist yet, rather than sending it request
+    # bodies shaped for someone else.
+    normalized, passthrough = object(), object()
+    for model in ("gpt-6-astra", "local-coder", "local-fast", "llama3.2"):
+        assert select_client(model, normalized, passthrough) is normalized
+
+
+def test_native_adapter_detection_is_explicit() -> None:
+    assert has_native_adapter("claude-opus-5")
+    assert not has_native_adapter("gpt-6-astra")
+    # A model merely mentioning the vendor is not the vendor.
+    assert not has_native_adapter("my-claude-clone")