Merge commit '94eb92f' into overnight-jul31

# Conflicts:
#	Makefile

Makefile

@@ -16,7 +16,7 @@ PIPER_BIN     := $(shell pwd)/deps/piper/piper
 PIPER_MODEL   := $(shell pwd)/models/tts/ru_RU-irina-medium.onnx
 PIPER_ESPEAK  := $(shell pwd)/deps/piper/espeak-ng-data
 
-.PHONY: all build build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav clean test fmt-check vet run-stt run-tts run-web download-embedder deps-go eval-router eval-recall eval-phrasing
+.PHONY: all build build-stt build-tts build-daemon build-client build-waked build-web build-poll build-caldav clean test fmt-check vet run-stt run-tts run-web download-embedder deps-go eval-router eval-recall eval-phrasing eval-models
 
 all: build
 
@@ -112,6 +112,21 @@ eval-recall:
 eval-phrasing:
 	$(GO) test -v -count=1 -timeout 40m ./internal/phraser/eval/
 
+# eval-models — score ONE llama-server against the same fixture, for the
+# resident-model bake-off (#278, #250). Start a server with the gguf you want,
+# then:
+#
+#   make eval-models MAVEN_LLM_URL=http://127.0.0.1:18100
+#
+# The report names carry the model llama-server reports, so runs from two
+# checkpoints stay apart. Only the LLM test runs — the classifier baselines do
+# not depend on the model and take the ONNX runtime with them.
+MAVEN_LLM_URL ?= http://127.0.0.1:18099
+
+eval-models:
+	MAVEN_LLM_URL="$(MAVEN_LLM_URL)" $(GO) test -v -count=1 -timeout 60m \
+		-run TestLLMRouterBaseline ./internal/router/eval/
+
 run-stt: build-stt
 	LD_LIBRARY_PATH="$(shell pwd)/deps/lib" \
 		./mavsttd -socket /tmp/maven/stt.sock -model $(WHISPER_MODEL)