package itemoccurrences import ( "context" "encoding/json" "errors" "testing" "gitea.maximumdirect.net/eric/notarius/internal/core/source" "gitea.maximumdirect.net/eric/notarius/internal/framework/contracts" ) func extractionRequest() contracts.TypedExtractionRequest { doc := sourceDocument() chunk := &source.Chunk{ ID: "session-alpha:chunk:0", SourceID: doc.ID, Index: 0, Ref: source.SourceRef{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 5}, Content: []byte(`{"segments":[1,2,3,4,5]}`), MediaType: "application/json", Units: append([]source.SourceUnit(nil), doc.Units...), } return contracts.TypedExtractionRequest{ Source: doc, Chunk: chunk, SourceInput: contracts.NewLLMInputMaterial("source", chunk.MediaType, chunk.Content, "sha256:chunk", "file:///session-alpha.json"), SessionID: "session-123", LLMProfile: "profile-item-occurrences", } } func sourceDocument() *source.SourceDocument { return &source.SourceDocument{ ID: "session-alpha", Kind: "transcript", Format: "application/vnd.seriatim.minimal+json", Digest: "sha256:test", Units: []source.SourceUnit{ {ID: 1, Kind: "transcript_segment", Text: "The party discovers a hidden cache."}, {ID: 2, Kind: "transcript_segment", Text: "They acquire 20 gold pieces."}, {ID: 3, Kind: "transcript_segment", Text: "Aria gives Borin the moonblade."}, {ID: 4, Kind: "transcript_segment", Text: "The party consumes a healing potion."}, {ID: 5, Kind: "transcript_segment", Text: "The party loses a torch."}, }, } } func responseRefs(start, end int) []itemOccurrenceSourceRefResponse { return []itemOccurrenceSourceRefResponse{{StartSegment: start, EndSegment: end}} } func newExtractor(t *testing.T, client contracts.StructuredLLMClient, references ...contracts.ReferenceSet) *Extractor { t.Helper() extractor, err := New(client, Options{}, references...) if err != nil { t.Fatalf("New() error = %v", err) } return extractor } func cloneStructuredCompletionRequest(req contracts.StructuredCompletionRequest) contracts.StructuredCompletionRequest { req.Inputs = req.Inputs.Clone() return req } type fakeItemOccurrencesLLMClient struct { response extractionResponse content []byte err error requests []contracts.StructuredCompletionRequest } func (client *fakeItemOccurrencesLLMClient) CompleteStructured(_ context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) { client.requests = append(client.requests, cloneStructuredCompletionRequest(req)) if client.err != nil { return contracts.StructuredCompletionResponse{}, client.err } target, ok := out.(*extractionResponse) if !ok { return contracts.StructuredCompletionResponse{}, errors.New("unexpected output target") } content := append([]byte(nil), client.content...) if len(content) == 0 { var err error content, err = json.Marshal(client.response) if err != nil { return contracts.StructuredCompletionResponse{}, err } } if err := json.Unmarshal(content, target); err != nil { return contracts.StructuredCompletionResponse{}, err } return contracts.StructuredCompletionResponse{Content: content}, nil }