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/src/nisse_dev/agent.py

@@ -19,7 +19,11 @@ from nisse_dev.executor import LLMExecutor
 from nisse_dev.expert import ExpertDesk
 from nisse_dev.git import GitRepo, authenticated_url
 from nisse_dev.gitea import Comment, GiteaClient
-from nisse_dev.llm import AnthropicPassthroughClient, LiteLLMClient
+from nisse_dev.llm import (
+    AnthropicPassthroughClient,
+    LiteLLMClient,
+    select_client,
+)
 from nisse_dev.matrix import MatrixTransport
 from nisse_dev.oplog import OpLog
 from nisse_dev.planner import LLMPlanningAgent
@@ -98,19 +102,22 @@ def build_agent(
     workspace = Workspace(config.workspace)
 
     normalized = LiteLLMClient(config.llm_base_url, config.llm_token)
-    # Delegations take the passthrough route; fidelity is cheap elsewhere (A5).
+    # Delegations prefer the vendor-native route; fidelity is cheap
+    # elsewhere (A5). Which route a given model gets is decided by
+    # select_client, not by where the caller happens to sit.
     passthrough = AnthropicPassthroughClient(config.llm_base_url, config.llm_token)
 
     transport = MatrixTransport(config.matrix)
     announce = notify or transport.send_message
 
     expert = ExpertDesk(normalized, store, config.roles)
+    delegate_model = config.roles.resolve("delegate")
     delegation = Delegation(
-        passthrough,
+        select_client(delegate_model, normalized, passthrough),
         store,
         workspace,
         git_repo,
-        model=config.roles.resolve("delegate"),
+        model=delegate_model,
     )
     executor = LLMExecutor(
         normalized,