notarius/internal/modules/extract/dnd/spells/prompt_test.go

package spells

import (
	"encoding/json"
	"reflect"
	"strings"
	"testing"

	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
	"gitea.maximumdirect.net/eric/notarius/internal/framework/prompt"
)

func TestBuildPromptDataFromGenericSourceChunk(t *testing.T) {
	req := promptExtractionRequest()

	data, err := buildPromptData(req)
	if err != nil {
		t.Fatalf("buildPromptData() error = %v, want nil", err)
	}

	if data.SourceID != "session-alpha" {
		t.Fatalf("SourceID = %q, want session-alpha", data.SourceID)
	}
	if !data.HasChunk || data.ChunkID != "session-alpha:chunk:0" || data.ChunkIndex != 0 {
		t.Fatalf("chunk data = %#v, want fixture chunk", data)
	}
	if len(data.Units) != 2 {
		t.Fatalf("len(Units) = %d, want 2", len(data.Units))
	}
	first := data.Units[0]
	if first.ID != "seg-001" || first.Text != "Aria raises her hand and casts Cure Wounds." {
		t.Fatalf("first unit = %#v, want source unit data", first)
	}
	wantMetadata := []promptMetadata{
		{Key: "speaker", Value: "Alice"},
		{Key: "start", Value: "1.25"},
		{Key: "end", Value: "3.5"},
	}
	if !reflect.DeepEqual(first.Metadata, wantMetadata) {
		t.Fatalf("first.Metadata = %#v, want %#v", first.Metadata, wantMetadata)
	}
	if len(data.Units[1].Metadata) != 0 {
		t.Fatalf("second.Metadata = %#v, want no selected metadata", data.Units[1].Metadata)
	}
}

func TestBuildPromptDataDoesNotMutateRequest(t *testing.T) {
	req := promptExtractionRequest()
	beforeSource := mustJSON(t, req.Source)
	beforeChunk := mustJSON(t, req.Chunk)
	beforeRequest := mustJSON(t, req)

	if _, err := buildPromptData(req); err != nil {
		t.Fatalf("buildPromptData() error = %v, want nil", err)
	}
	afterSource := mustJSON(t, req.Source)
	afterChunk := mustJSON(t, req.Chunk)
	afterRequest := mustJSON(t, req)
	if beforeSource != afterSource || beforeChunk != afterChunk || beforeRequest != afterRequest {
		t.Fatalf(
			"request mutated:\nsource before: %s\nsource after:  %s\nchunk before: %s\nchunk after:  %s\nrequest before: %s\nrequest after:  %s",
			beforeSource,
			afterSource,
			beforeChunk,
			afterChunk,
			beforeRequest,
			afterRequest,
		)
	}
}

func TestRenderPromptIncludesSourceContext(t *testing.T) {
	system, user, metadata, err := renderPrompt(promptExtractionRequest())
	if err != nil {
		t.Fatalf("renderPrompt() error = %v, want nil", err)
	}

	if !strings.Contains(system, prompt.HardeningText()) {
		t.Fatalf("system prompt = %q, want hardening text", system)
	}
	for _, want := range []string{
		"session-alpha",
		"session-alpha:chunk:0",
		"seg-001",
		"Aria raises her hand and casts Cure Wounds.",
		"speaker: Alice",
		"start: 1.25",
		"end: 3.5",
	} {
		if !strings.Contains(user, want) {
			t.Fatalf("user prompt = %q, want substring %q", user, want)
		}
	}
	if metadata.PromptID != PromptID {
		t.Fatalf("metadata.PromptID = %q, want %q", metadata.PromptID, PromptID)
	}
	if metadata.PromptVersion != SchemaVersion {
		t.Fatalf("metadata.PromptVersion = %q, want %q", metadata.PromptVersion, SchemaVersion)
	}
	if metadata.EmbeddedPath != "assets/prompts" {
		t.Fatalf("metadata.EmbeddedPath = %q, want assets/prompts", metadata.EmbeddedPath)
	}
}

func TestBuildPromptDataRejectsMissingSourceContext(t *testing.T) {
	if _, err := buildPromptData(contracts.ExtractionRequest{}); err == nil || !strings.Contains(err.Error(), "source") {
		t.Fatalf("buildPromptData() error = %v, want source error", err)
	}
	if _, err := buildPromptData(contracts.ExtractionRequest{Source: promptSourceDocument()}); err == nil || !strings.Contains(err.Error(), "chunk") {
		t.Fatalf("buildPromptData() error = %v, want chunk error", err)
	}
}

func promptExtractionRequest() contracts.ExtractionRequest {
	doc := promptSourceDocument()
	chunk := &contracts.SourceChunk{
		ID:       "session-alpha:chunk:0",
		SourceID: doc.ID,
		Index:    0,
		Units:    append([]source.SourceUnit(nil), doc.Units...),
		Metadata: map[string]any{"ignored": "chunk metadata"},
	}
	return contracts.ExtractionRequest{
		Source: doc,
		Chunk:  chunk,
	}
}

func promptSourceDocument() *source.SourceDocument {
	return &source.SourceDocument{
		ID:     "session-alpha",
		Kind:   "transcript",
		Format: "application/vnd.seriatim.minimal+json",
		Digest: "sha256:test",
		Units: []source.SourceUnit{
			{
				ID:   "seg-001",
				Kind: "transcript_segment",
				Text: "Aria raises her hand and casts Cure Wounds.",
				Metadata: map[string]any{
					"speaker": "Alice",
					"start":   json.Number("1.25"),
					"end":     json.Number("3.5"),
					"ignored": "not rendered",
				},
			},
			{
				ID:       "seg-002",
				Kind:     "transcript_segment",
				Text:     "The fighter's wounds begin to close.",
				Metadata: map[string]any{"ignored": "not rendered"},
			},
		},
	}
}

func mustJSON(t *testing.T, value any) string {
	t.Helper()
	encoded, err := json.Marshal(value)
	if err != nil {
		t.Fatalf("Marshal() error = %v, want nil", err)
	}
	return string(encoded)
}