audita/internal/modules/glossary/module_test.go

package glossary

import (
	"context"
	"errors"
	"os"
	"path/filepath"
	"strings"
	"testing"

	"gitea.maximumdirect.net/eric/audita/internal/core/config"
	"gitea.maximumdirect.net/eric/audita/internal/core/schema"
	"gitea.maximumdirect.net/eric/audita/internal/framework/contracts"
	"gitea.maximumdirect.net/eric/audita/internal/framework/proposal_generation"
	"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
)

type fakeLLMClient struct {
	responses []proposal_generation.StructuredCorrectionSet
	err       error
	calls     []contracts.StructuredCompletionRequest
}

func (f *fakeLLMClient) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
	_ = ctx
	f.calls = append(f.calls, req)
	if f.err != nil {
		return contracts.StructuredCompletionResponse{}, f.err
	}
	target, ok := out.(*proposal_generation.StructuredCorrectionSet)
	if !ok {
		return contracts.StructuredCompletionResponse{}, errors.New("unexpected output type")
	}
	if len(f.responses) == 0 {
		return contracts.StructuredCompletionResponse{}, errors.New("unexpected call")
	}
	*target = f.responses[0]
	f.responses = f.responses[1:]
	return contracts.StructuredCompletionResponse{}, nil
}

type countingScheduler struct {
	runs int
}

func (s *countingScheduler) Run(ctx context.Context, fn func(context.Context) error) error {
	s.runs++
	return fn(ctx)
}

func tinyTranscript() *schema.Transcript {
	return &schema.Transcript{Segments: []schema.Segment{
		{ID: 1, Speaker: "A", Start: 0, End: 1, Text: "There were gestures in the hall.", Categories: []string{"session"}},
	}}
}

func tinyGlossary() *schema.Glossary {
	return &schema.Glossary{Entries: []schema.GlossaryEntry{
		{Name: "Jesters", Aliases: []string{"Jester"}, Category: "faction", Summary: "Guild members", Plural: "Jesters"},
	}}
}

func TestBuildProposalMessagesContainsGlossaryContextAndConstraints(t *testing.T) {
	msgs, err := BuildProposalMessages(tinyTranscript(), tinyGlossary(), 0, "")
	if err != nil {
		t.Fatalf("BuildProposalMessages error: %v", err)
	}
	if len(msgs) != 2 {
		t.Fatalf("expected 2 messages, got %d", len(msgs))
	}
	combined := msgs[0].Content + "\n" + msgs[1].Content
	for _, want := range []string{
		"Glossary:",
		"Transcript section:",
		`"section_index": 0`,
		`"Aliases":`,
		`"Jester"`,
		`"Category": "faction"`,
		`"Summary": "Guild members"`,
		`"Plural": "Jesters"`,
		"glossary-supported corrections",
		"acoustically similar",
		"Do not make generic grammar, spelling, capitalization, style, or filler-word edits",
	} {
		if !strings.Contains(combined, want) {
			t.Fatalf("expected prompt to contain %q", want)
		}
	}
	if strings.Contains(strings.ToLower(combined), "summarize the transcript") {
		t.Fatalf("prompt should not invite summarization")
	}
}

func TestBuildProposalMessagesIncludesTranscriptDescriptionGuidance(t *testing.T) {
	msgs, err := BuildProposalMessages(tinyTranscript(), tinyGlossary(), 0, "Campaign scene in a crowded harbor.")
	if err != nil {
		t.Fatalf("BuildProposalMessages error: %v", err)
	}
	combined := msgs[0].Content + "\n" + msgs[1].Content
	for _, want := range []string{
		"Transcript description (background context only):",
		"Campaign scene in a crowded harbor.",
		"must not override the transcript content",
		"Do not invent corrections, facts, names, events, motivations, or speaker intent based on this description.",
	} {
		if !strings.Contains(combined, want) {
			t.Fatalf("expected prompt to contain %q", want)
		}
	}
}

func TestGlossaryModuleReplacementPolicy(t *testing.T) {
	m, err := New()
	if err != nil {
		t.Fatalf("New error: %v", err)
	}
	if m.ReplacementPolicy() != proposals.ReplacementPolicyReplaceAll {
		t.Fatalf("unexpected replacement policy: %q", m.ReplacementPolicy())
	}
}

func TestGlossaryModuleValidatorChain(t *testing.T) {
	m, err := New()
	if err != nil {
		t.Fatalf("New error: %v", err)
	}
	got := make([]string, 0, len(m.Validators()))
	for _, v := range m.Validators() {
		got = append(got, v.Name())
	}
	want := []string{
		"no_effect",
		"original_text_presence",
		"confidence_threshold",
		"glossary_stage_protected_glossary_terms",
		"non_empty_correction",
		"spoken_form_plausibility_review",
		"meaning_reversal_review",
	}
	if strings.Join(got, ",") != strings.Join(want, ",") {
		t.Fatalf("unexpected validator chain\n got: %v\nwant: %v", got, want)
	}
}

func TestGlossaryModuleProposeMapsCorrectionsAndWritesDiagnostics(t *testing.T) {
	secret := "glossary-secret"
	client := &fakeLLMClient{
		responses: []proposal_generation.StructuredCorrectionSet{
			{
				Corrections: []proposal_generation.StructuredCorrectionProposal{
					{TargetSegmentID: 1, OriginalText: "gestures", CorrectedText: "Jesters", Confidence: 0.94},
				},
			},
		},
	}
	scheduler := &countingScheduler{}
	cfg := config.Default()
	cfg.PrimaryLLM.APIKey = secret
	m, err := New()
	if err != nil {
		t.Fatalf("New error: %v", err)
	}
	diagDir := t.TempDir()
	out, err := m.Propose(context.Background(), contracts.ProposalRequest{
		ExecutionContext: contracts.ExecutionContext{
			Config:            &cfg,
			WorkingTranscript: tinyTranscript(),
			Glossary:          tinyGlossary(),
			DiagnosticsDir:    diagDir,
		},
		RunSpec: contracts.ModuleRunSpec{
			ModuleKey:         "glossary",
			InstanceName:      "glossary",
			ReplacementPolicy: proposals.ReplacementPolicyReplaceAll,
		},
		LLMClient:    client,
		LLMScheduler: scheduler,
	})
	if err != nil {
		t.Fatalf("Propose error: %v", err)
	}
	if scheduler.runs != 1 {
		t.Fatalf("expected scheduler run count 1, got %d", scheduler.runs)
	}
	if len(client.calls) != 1 || client.calls[0].StageName != "glossary:proposal" {
		t.Fatalf("expected one glossary:proposal call, got %+v", client.calls)
	}
	if len(out) != 1 || out[0].CorrectedText != "Jesters" {
		t.Fatalf("unexpected proposals: %+v", out)
	}
	diagFiles, globErr := filepath.Glob(filepath.Join(diagDir, "glossary", "*proposal*response-payload.json"))
	if globErr != nil {
		t.Fatalf("glob error: %v", globErr)
	}
	if len(diagFiles) == 0 {
		t.Fatalf("expected diagnostics response payload under %s", filepath.Join(diagDir, "glossary"))
	}
	for _, f := range diagFiles {
		raw, readErr := os.ReadFile(f)
		if readErr != nil {
			t.Fatalf("read diag %q: %v", f, readErr)
		}
		if strings.Contains(string(raw), secret) {
			t.Fatalf("secret leaked in diagnostics: %s", string(raw))
		}
	}
}