Add prompt input materials and session IDs

internal/framework/pipeline/runner_test.go

@@ -476,6 +476,84 @@ func TestRunExecutesChunksAndPassesChunkAndLLMClient(t *testing.T) {
 	}
 }
 
+func TestRunPassesSourceInputAndSessionIDToPromptCapableStages(t *testing.T) {
+	modules := defaultRunnerModules()
+	rawInput := []byte("{\"source\":\"exact bytes\"}")
+
+	output, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{
+		Pipeline:  resolvedPipeline(),
+		Path:      "session.json",
+		RawInput:  rawInput,
+		SessionID: " explicit-session ",
+	})
+	if err != nil {
+		t.Fatalf("Run() error = %v, want nil", err)
+	}
+
+	if got := output.Manifest.Metadata["session_id"]; got != "explicit-session" {
+		t.Fatalf("manifest metadata = %#v, want session_id", output.Manifest.Metadata)
+	}
+
+	requests := []struct {
+		name      string
+		material  contracts.LLMInputMaterial
+		sessionID string
+	}{
+		{name: "chunk", material: modules.chunker.requests[0].SourceInput, sessionID: modules.chunker.requests[0].SessionID},
+		{name: "extract first", material: modules.extractors["extract-alpha"].requests[0].SourceInput, sessionID: modules.extractors["extract-alpha"].requests[0].SessionID},
+		{name: "extract second", material: modules.extractors["extract-alpha"].requests[1].SourceInput, sessionID: modules.extractors["extract-alpha"].requests[1].SessionID},
+		{name: "normalize", material: modules.normalizers["normalize"].requests[0].SourceInput, sessionID: modules.normalizers["normalize"].requests[0].SessionID},
+	}
+	for _, req := range requests {
+		if req.sessionID != "explicit-session" {
+			t.Fatalf("%s session ID = %q, want explicit-session", req.name, req.sessionID)
+		}
+		if got := string(req.material.Content); got != string(rawInput) {
+			t.Fatalf("%s source input content = %q, want exact raw input", req.name, got)
+		}
+		if req.material.Name != "source" || req.material.MediaType != "application/json" || req.material.SizeBytes != int64(len(rawInput)) {
+			t.Fatalf("%s source input = %#v, want source metadata", req.name, req.material)
+		}
+		if req.material.Digest != sourceInputDigest(rawInput) {
+			t.Fatalf("%s digest = %q, want %q", req.name, req.material.Digest, sourceInputDigest(rawInput))
+		}
+		if !strings.HasPrefix(req.material.OriginURI, "file://") || !strings.HasSuffix(req.material.OriginURI, "/session.json") {
+			t.Fatalf("%s origin URI = %q, want file URI ending in session.json", req.name, req.material.OriginURI)
+		}
+	}
+
+	modules.chunker.requests[0].SourceInput.Content[0] = 'X'
+	if got := string(modules.extractors["extract-alpha"].requests[0].SourceInput.Content); got != string(rawInput) {
+		t.Fatalf("source input content aliased across requests: %q", got)
+	}
+	if got := string(rawInput); got != "{\"source\":\"exact bytes\"}" {
+		t.Fatalf("raw input mutated through request material: %q", got)
+	}
+}
+
+func TestRunDefaultsSessionIDFromParsedSourceDocumentID(t *testing.T) {
+	modules := defaultRunnerModules()
+
+	output, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{
+		Pipeline: resolvedPipeline(),
+		Path:     "notes.unknown",
+		RawInput: []byte("notes"),
+	})
+	if err != nil {
+		t.Fatalf("Run() error = %v, want nil", err)
+	}
+
+	if got := modules.chunker.requests[0].SessionID; got != "source-1" {
+		t.Fatalf("chunk session ID = %q, want parsed source document ID", got)
+	}
+	if got := output.Manifest.Metadata["session_id"]; got != "source-1" {
+		t.Fatalf("manifest metadata = %#v, want default session id", output.Manifest.Metadata)
+	}
+	if got := modules.chunker.requests[0].SourceInput.MediaType; got != unknownMediaType {
+		t.Fatalf("source input media type = %q, want fallback %q", got, unknownMediaType)
+	}
+}
+
 func TestRunPassesInputRequestFields(t *testing.T) {
 	modules := defaultRunnerModules()
 	metadata := map[string]any{"request": "test"}