Register configured local PromptKit backend

internal/cli/production_contract_test.go

@@ -6,6 +6,8 @@ import (
 	"errors"
 	"fmt"
 	"io/fs"
+	"net/http"
+	"net/http/httptest"
 	"os"
 	"path/filepath"
 	"reflect"
@@ -13,7 +15,9 @@ import (
 	"sort"
 	"strings"
 	"sync"
+	"sync/atomic"
 	"testing"
+	"testing/fstest"
 	"time"
 
 	"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
@@ -34,6 +38,7 @@ import (
 	itemeventnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/itemevents"
 	spellnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/spells"
 	"gitea.maximumdirect.net/eric/notarius/internal/modules/generic/normalize/noop"
+	"gitea.maximumdirect.net/eric/promptkit"
 )
 
 func TestProductionCatalogCoversMaintainedConfigurations(t *testing.T) {
@@ -406,6 +411,89 @@ func TestProductionLLMClientFactoriesBuildOfflineRuntime(t *testing.T) {
 	}
 }
 
+func TestProductionLLMClientFactoryUsesConfiguredLocalBackend(t *testing.T) {
+	var providerCalls atomic.Int32
+	server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		providerCalls.Add(1)
+		if r.URL.Path != "/v1/chat/completions" {
+			t.Errorf("provider path = %q, want /v1/chat/completions", r.URL.Path)
+		}
+		w.Header().Set("Content-Type", "application/json")
+		_, _ = w.Write([]byte(`{
+			"choices": [{"message": {"role": "assistant", "content": "{\"ok\":true}"}}],
+			"usage": {"prompt_tokens": 3, "completion_tokens": 4, "total_tokens": 7}
+		}`))
+	}))
+	defer server.Close()
+
+	profilePath := filepath.Join(t.TempDir(), "profiles.yml")
+	if err := os.WriteFile(profilePath, []byte(`id: local-profile
+backend: local
+model: local-model
+`), 0o600); err != nil {
+		t.Fatal(err)
+	}
+	assets := llm.NewAssetRegistry()
+	if err := assets.RegisterPromptFS(fstest.MapFS{
+		"production.local.yaml": {Data: []byte(`id: production.local
+version: "v1"
+inputs:
+  - name: transcript
+    required: true
+messages:
+  - role: user
+    content: '{{ input "transcript" }}'
+output:
+  format: json
+  validation_mode: json
+`)},
+	}, "."); err != nil {
+		t.Fatalf("register prompt assets: %v", err)
+	}
+
+	cfg := config.Default()
+	cfg.PromptKit.ProfileFile = profilePath
+	cfg.PromptKit.LocalBackend = &config.PromptKitLocalBackendConfig{
+		Endpoint:         server.URL + "/v1",
+		ConcurrencyLimit: 2,
+	}
+	client, manifests, err := productionLLMClientFactoryWithAssets(assets)(
+		context.Background(),
+		cfg,
+		"local-profile",
+		LLMRuntimeOverrides{},
+	)
+	if err != nil {
+		t.Fatalf("build production LLM runtime: %v", err)
+	}
+	if len(manifests) != 0 {
+		t.Fatalf("eager profile manifests = %#v, want none", manifests)
+	}
+
+	var out map[string]any
+	_, err = client.CompleteStructured(context.Background(), contracts.StructuredCompletionRequest{
+		PromptID:  "production.local",
+		ProfileID: "local-profile",
+		Inputs: contracts.LLMInputSet{
+			"transcript": contracts.NewLLMInputMaterial("transcript", "text/plain", []byte("local request"), "", ""),
+		},
+	}, &out)
+	if err != nil {
+		t.Fatalf("CompleteStructured() error = %v, want nil", err)
+	}
+	if providerCalls.Load() != 1 {
+		t.Fatalf("provider calls = %d, want 1", providerCalls.Load())
+	}
+	provider, ok := client.(contracts.LLMProfileManifestProvider)
+	if !ok {
+		t.Fatalf("production client %T does not provide profile manifests", client)
+	}
+	recorded := provider.LLMProfileManifests()
+	if len(recorded) != 1 || recorded[0].BackendID != promptkit.BackendLocal {
+		t.Fatalf("production profile manifests = %#v, want local backend", recorded)
+	}
+}
+
 func TestProductionLLMClientFactoriesRejectInvalidConstruction(t *testing.T) {
 	t.Run("canceled context", func(t *testing.T) {
 		ctx, cancel := context.WithCancel(context.Background())