Centralize D&D extraction request preparation

This commit is contained in:
2026-07-24 14:38:42 +00:00
parent 8e0b029f5f
commit e2cb0d901a
15 changed files with 144 additions and 185 deletions

View File

@@ -144,22 +144,7 @@ func (e *Extractor) Extract(ctx context.Context, req contracts.TypedExtractionRe
if e.llm == nil { if e.llm == nil {
return contracts.TypedExtractionResult[dnd.CombatTurnList]{}, extractorErrorf("LLM client must not be nil") return contracts.TypedExtractionResult[dnd.CombatTurnList]{}, extractorErrorf("LLM client must not be nil")
} }
if ctx == nil { sourceInput, err := shared.PrepareChunkExtraction(ctx, req)
return contracts.TypedExtractionResult[dnd.CombatTurnList]{}, extractorErrorf("context must not be nil")
}
if err := ctx.Err(); err != nil {
return contracts.TypedExtractionResult[dnd.CombatTurnList]{}, extractorErrorf("context error before extraction: %w", err)
}
if req.Source == nil {
return contracts.TypedExtractionResult[dnd.CombatTurnList]{}, extractorErrorf("source must not be nil")
}
if req.Chunk == nil {
return contracts.TypedExtractionResult[dnd.CombatTurnList]{}, extractorErrorf("chunk must not be nil")
}
if len(req.Chunk.Units) == 0 {
return contracts.TypedExtractionResult[dnd.CombatTurnList]{}, extractorErrorf("chunk %q units must not be empty", req.Chunk.ID)
}
sourceInput, err := shared.ChunkPromptMaterial(req)
if err != nil { if err != nil {
return contracts.TypedExtractionResult[dnd.CombatTurnList]{}, extractorErrorf("%w", err) return contracts.TypedExtractionResult[dnd.CombatTurnList]{}, extractorErrorf("%w", err)
} }

View File

@@ -222,9 +222,8 @@ func TestNewRejectsMalformedNPCRegistryBeforeLLMCallWithoutContent(t *testing.T)
func TestExtractRejectsInvalidRequestsAndWrapsProviderFailures(t *testing.T) { func TestExtractRejectsInvalidRequestsAndWrapsProviderFailures(t *testing.T) {
validReq := extractionRequest() validReq := extractionRequest()
canceledCtx, cancel := context.WithCancel(context.Background())
cancel()
validExtractor := newExtractor(t, &fakeCombatTurnsLLMClient{response: extractionResponse{CombatTurns: []combatTurnResponse{}}}) validExtractor := newExtractor(t, &fakeCombatTurnsLLMClient{response: extractionResponse{CombatTurns: []combatTurnResponse{}}})
var nilExtractor *Extractor
tests := []struct { tests := []struct {
name string name string
extractor *Extractor extractor *Extractor
@@ -232,13 +231,9 @@ func TestExtractRejectsInvalidRequestsAndWrapsProviderFailures(t *testing.T) {
req contracts.TypedExtractionRequest req contracts.TypedExtractionRequest
want string want string
}{ }{
{name: "nil extractor", ctx: context.Background(), req: validReq, want: "extractor"}, {name: "nil extractor", extractor: nilExtractor, ctx: context.Background(), req: validReq, want: "extractor"},
{name: "nil context", extractor: validExtractor, req: validReq, want: "context"}, {name: "nil LLM client", extractor: &Extractor{}, ctx: context.Background(), req: validReq, want: "LLM client"},
{name: "canceled context", extractor: validExtractor, ctx: canceledCtx, req: validReq, want: "context"}, {name: "wrapped preflight failure", extractor: validExtractor, ctx: context.Background(), req: mismatchedSourceInputRequest(validReq), want: "must match chunk"},
{name: "nil source", extractor: validExtractor, ctx: context.Background(), req: contracts.TypedExtractionRequest{Chunk: validReq.Chunk}, want: "source"},
{name: "nil chunk", extractor: validExtractor, ctx: context.Background(), req: contracts.TypedExtractionRequest{Source: validReq.Source}, want: "chunk"},
{name: "empty chunk units", extractor: validExtractor, ctx: context.Background(), req: emptyChunkRequest(validReq), want: "units"},
{name: "source input mismatch", extractor: validExtractor, ctx: context.Background(), req: mismatchedSourceInputRequest(validReq), want: "must match chunk"},
} }
for _, test := range tests { for _, test := range tests {
t.Run(test.name, func(t *testing.T) { t.Run(test.name, func(t *testing.T) {
@@ -339,11 +334,6 @@ func combatSourceDocument() *source.SourceDocument {
} }
} }
func emptyChunkRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest {
req.Chunk = &source.Chunk{ID: req.Chunk.ID, SourceID: req.Chunk.SourceID, Index: req.Chunk.Index}
return req
}
func mismatchedSourceInputRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest { func mismatchedSourceInputRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest {
req.SourceInput = contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"other":true}`), "sha256:other", "") req.SourceInput = contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"other":true}`), "sha256:other", "")
return req return req

View File

@@ -143,22 +143,7 @@ func (e *Extractor) Extract(ctx context.Context, req contracts.TypedExtractionRe
if e.llm == nil { if e.llm == nil {
return contracts.TypedExtractionResult[dnd.NPCInteractionList]{}, extractorErrorf("LLM client must not be nil") return contracts.TypedExtractionResult[dnd.NPCInteractionList]{}, extractorErrorf("LLM client must not be nil")
} }
if ctx == nil { sourceInput, err := shared.PrepareChunkExtraction(ctx, req)
return contracts.TypedExtractionResult[dnd.NPCInteractionList]{}, extractorErrorf("context must not be nil")
}
if err := ctx.Err(); err != nil {
return contracts.TypedExtractionResult[dnd.NPCInteractionList]{}, extractorErrorf("context error before extraction: %w", err)
}
if req.Source == nil {
return contracts.TypedExtractionResult[dnd.NPCInteractionList]{}, extractorErrorf("source must not be nil")
}
if req.Chunk == nil {
return contracts.TypedExtractionResult[dnd.NPCInteractionList]{}, extractorErrorf("chunk must not be nil")
}
if len(req.Chunk.Units) == 0 {
return contracts.TypedExtractionResult[dnd.NPCInteractionList]{}, extractorErrorf("chunk %q units must not be empty", req.Chunk.ID)
}
sourceInput, err := shared.ChunkPromptMaterial(req)
if err != nil { if err != nil {
return contracts.TypedExtractionResult[dnd.NPCInteractionList]{}, extractorErrorf("%w", err) return contracts.TypedExtractionResult[dnd.NPCInteractionList]{}, extractorErrorf("%w", err)
} }

View File

@@ -204,24 +204,21 @@ func TestExtractRejectsInvalidRequestsAndProviderFailures(t *testing.T) {
references := requiredRegistryReferences(t, "Mira Thorn") references := requiredRegistryReferences(t, "Mira Thorn")
valid := extractionRequest() valid := extractionRequest()
valid.References = references valid.References = references
canceled, cancel := context.WithCancel(context.Background())
cancel()
extractor := newExtractor(t, &fakeInteractionsLLMClient{}, references) extractor := newExtractor(t, &fakeInteractionsLLMClient{}, references)
var nilExtractor *Extractor
for _, test := range []struct { for _, test := range []struct {
name string name string
ctx context.Context extractor *Extractor
req contracts.TypedExtractionRequest ctx context.Context
want string req contracts.TypedExtractionRequest
want string
}{ }{
{"nil context", nil, valid, "context"}, {"nil extractor", nilExtractor, context.Background(), valid, "extractor"},
{"canceled context", canceled, valid, "context"}, {"nil LLM client", &Extractor{}, context.Background(), valid, "LLM client"},
{"nil source", context.Background(), contracts.TypedExtractionRequest{Chunk: valid.Chunk, References: references}, "source"}, {"wrapped preflight failure", extractor, context.Background(), mismatchedSourceInputRequest(valid), "must match chunk"},
{"nil chunk", context.Background(), contracts.TypedExtractionRequest{Source: valid.Source, References: references}, "chunk"},
{"empty chunk", context.Background(), emptyChunkRequest(valid), "units"},
{"source input mismatch", context.Background(), mismatchedSourceInputRequest(valid), "must match chunk"},
} { } {
t.Run(test.name, func(t *testing.T) { t.Run(test.name, func(t *testing.T) {
if _, err := extractor.Extract(test.ctx, test.req); err == nil || !strings.Contains(err.Error(), test.want) { if _, err := test.extractor.Extract(test.ctx, test.req); err == nil || !strings.Contains(err.Error(), test.want) {
t.Fatalf("Extract() error = %v, want %q", err, test.want) t.Fatalf("Extract() error = %v, want %q", err, test.want)
} }
}) })
@@ -361,11 +358,6 @@ func interactionKinds(value dnd.NPCInteractionList) []dnd.NPCInteractionKind {
return kinds return kinds
} }
func emptyChunkRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest {
req.Chunk = &source.Chunk{ID: req.Chunk.ID, SourceID: req.Chunk.SourceID, Index: req.Chunk.Index}
return req
}
func mismatchedSourceInputRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest { func mismatchedSourceInputRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest {
req.SourceInput = contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"different":true}`), "sha256:other", "") req.SourceInput = contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"different":true}`), "sha256:other", "")
return req return req

View File

@@ -110,22 +110,7 @@ func (e *Extractor) Extract(ctx context.Context, req contracts.TypedExtractionRe
if e.llm == nil { if e.llm == nil {
return contracts.TypedExtractionResult[dnd.NPCList]{}, extractorErrorf("LLM client must not be nil") return contracts.TypedExtractionResult[dnd.NPCList]{}, extractorErrorf("LLM client must not be nil")
} }
if ctx == nil { sourceInput, err := shared.PrepareChunkExtraction(ctx, req)
return contracts.TypedExtractionResult[dnd.NPCList]{}, extractorErrorf("context must not be nil")
}
if err := ctx.Err(); err != nil {
return contracts.TypedExtractionResult[dnd.NPCList]{}, extractorErrorf("context error before extraction: %w", err)
}
if req.Source == nil {
return contracts.TypedExtractionResult[dnd.NPCList]{}, extractorErrorf("source must not be nil")
}
if req.Chunk == nil {
return contracts.TypedExtractionResult[dnd.NPCList]{}, extractorErrorf("chunk must not be nil")
}
if len(req.Chunk.Units) == 0 {
return contracts.TypedExtractionResult[dnd.NPCList]{}, extractorErrorf("chunk %q units must not be empty", req.Chunk.ID)
}
sourceInput, err := shared.ChunkPromptMaterial(req)
if err != nil { if err != nil {
return contracts.TypedExtractionResult[dnd.NPCList]{}, extractorErrorf("%w", err) return contracts.TypedExtractionResult[dnd.NPCList]{}, extractorErrorf("%w", err)
} }

View File

@@ -173,19 +173,27 @@ func TestExtractMapsRawSemanticCandidatesWithoutRepair(t *testing.T) {
} }
} }
func TestExtractHandlesCancellationAndProviderErrors(t *testing.T) { func TestExtractRetainsLocalErrorContextAndProviderFailures(t *testing.T) {
request := extractionRequest() request := extractionRequest()
extractor := newExtractor(t, &fakeNPCsLLMClient{response: extractionResponse{NPCs: []npcResponse{}}}) extractor := newExtractor(t, &fakeNPCsLLMClient{response: extractionResponse{NPCs: []npcResponse{}}})
canceled, cancel := context.WithCancel(context.Background()) var nilExtractor *Extractor
cancel() for _, test := range []struct {
if _, err := extractor.Extract(canceled, request); err == nil || !strings.Contains(err.Error(), "context") { name string
t.Fatalf("canceled Extract() error = %v, want context error", err) extractor *Extractor
req contracts.TypedExtractionRequest
want string
}{
{name: "nil extractor", extractor: nilExtractor, req: request, want: "extractor"},
{name: "nil LLM client", extractor: &Extractor{}, req: request, want: "LLM client"},
{name: "wrapped preflight failure", extractor: extractor, req: mismatchedSourceInputRequest(request), want: "must match chunk"},
} {
t.Run(test.name, func(t *testing.T) {
if _, err := test.extractor.Extract(context.Background(), test.req); err == nil || !strings.Contains(err.Error(), "dnd npcs") || !strings.Contains(err.Error(), test.want) {
t.Fatalf("Extract() error = %v, want contextual local error", err)
}
})
} }
_, err := extractor.Extract(context.Background(), mismatchedSourceInputRequest(request)) _, err := newExtractor(t, &fakeNPCsLLMClient{err: errors.New("provider unavailable")}).Extract(context.Background(), request)
if err == nil || !strings.Contains(err.Error(), "dnd npcs") || !strings.Contains(err.Error(), "must match chunk") {
t.Fatalf("source input error = %v, want contextual source input error", err)
}
_, err = newExtractor(t, &fakeNPCsLLMClient{err: errors.New("provider unavailable")}).Extract(context.Background(), request)
if err == nil || !strings.Contains(err.Error(), "dnd npcs") || !strings.Contains(err.Error(), "provider unavailable") { if err == nil || !strings.Contains(err.Error(), "dnd npcs") || !strings.Contains(err.Error(), "provider unavailable") {
t.Fatalf("provider Extract() error = %v, want contextual provider error", err) t.Fatalf("provider Extract() error = %v, want contextual provider error", err)
} }

View File

@@ -58,11 +58,6 @@ func newExtractor(t *testing.T, client contracts.StructuredLLMClient, references
return extractor return extractor
} }
func emptyChunkRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest {
req.Chunk = &source.Chunk{ID: req.Chunk.ID, SourceID: req.Chunk.SourceID, Index: req.Chunk.Index}
return req
}
func mismatchedSourceInputRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest { func mismatchedSourceInputRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest {
req.SourceInput = contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"different":true}`), "sha256:other", "file:///other.json") req.SourceInput = contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"different":true}`), "sha256:other", "file:///other.json")
return req return req

View File

@@ -113,22 +113,7 @@ func (e *Extractor) Extract(ctx context.Context, req contracts.TypedExtractionRe
if e.llm == nil { if e.llm == nil {
return contracts.TypedExtractionResult[dnd.SceneDescriptionList]{}, extractorErrorf("LLM client must not be nil") return contracts.TypedExtractionResult[dnd.SceneDescriptionList]{}, extractorErrorf("LLM client must not be nil")
} }
if ctx == nil { sourceInput, err := shared.PrepareChunkExtraction(ctx, req)
return contracts.TypedExtractionResult[dnd.SceneDescriptionList]{}, extractorErrorf("context must not be nil")
}
if err := ctx.Err(); err != nil {
return contracts.TypedExtractionResult[dnd.SceneDescriptionList]{}, extractorErrorf("context error before extraction: %w", err)
}
if req.Source == nil {
return contracts.TypedExtractionResult[dnd.SceneDescriptionList]{}, extractorErrorf("source must not be nil")
}
if req.Chunk == nil {
return contracts.TypedExtractionResult[dnd.SceneDescriptionList]{}, extractorErrorf("chunk must not be nil")
}
if len(req.Chunk.Units) == 0 {
return contracts.TypedExtractionResult[dnd.SceneDescriptionList]{}, extractorErrorf("chunk %q units must not be empty", req.Chunk.ID)
}
sourceInput, err := shared.ChunkPromptMaterial(req)
if err != nil { if err != nil {
return contracts.TypedExtractionResult[dnd.SceneDescriptionList]{}, extractorErrorf("%w", err) return contracts.TypedExtractionResult[dnd.SceneDescriptionList]{}, extractorErrorf("%w", err)
} }

View File

@@ -87,26 +87,23 @@ func TestExtractPreservesTheModelKindWithoutRepair(t *testing.T) {
func TestExtractValidatesRequestsAndSurfacesProviderFailures(t *testing.T) { func TestExtractValidatesRequestsAndSurfacesProviderFailures(t *testing.T) {
request := extractionRequest() request := extractionRequest()
extractor := newExtractor(t, &fakeSceneDescriptionsLLMClient{response: extractionResponse{Kind: dnd.SceneKindMeta, Title: "Table talk", Summary: "The group discusses rules."}}) extractor := newExtractor(t, &fakeSceneDescriptionsLLMClient{response: extractionResponse{Kind: dnd.SceneKindMeta, Title: "Table talk", Summary: "The group discusses rules."}})
var nilExtractor *Extractor
for _, test := range []struct { for _, test := range []struct {
name string name string
req contracts.TypedExtractionRequest extractor *Extractor
req contracts.TypedExtractionRequest
want string
}{ }{
{name: "nil source", req: func() contracts.TypedExtractionRequest { r := request; r.Source = nil; return r }()}, {name: "nil extractor", extractor: nilExtractor, req: request, want: "extractor"},
{name: "nil chunk", req: func() contracts.TypedExtractionRequest { r := request; r.Chunk = nil; return r }()}, {name: "nil LLM client", extractor: &Extractor{}, req: request, want: "LLM client"},
{name: "empty chunk", req: emptyChunkRequest(request)}, {name: "wrapped preflight failure", extractor: extractor, req: mismatchedSourceInputRequest(request), want: "must match chunk"},
{name: "mismatched source input", req: mismatchedSourceInputRequest(request)},
} { } {
t.Run(test.name, func(t *testing.T) { t.Run(test.name, func(t *testing.T) {
if _, err := extractor.Extract(context.Background(), test.req); err == nil || !strings.Contains(err.Error(), "dnd scene descriptions") { if _, err := test.extractor.Extract(context.Background(), test.req); err == nil || !strings.Contains(err.Error(), "dnd scene descriptions") || !strings.Contains(err.Error(), test.want) {
t.Fatalf("Extract() error = %v, want contextual validation error", err) t.Fatalf("Extract() error = %v, want contextual validation error", err)
} }
}) })
} }
canceled, cancel := context.WithCancel(context.Background())
cancel()
if _, err := extractor.Extract(canceled, request); err == nil || !strings.Contains(err.Error(), "context") {
t.Fatalf("canceled Extract() error = %v, want context error", err)
}
_, err := newExtractor(t, &fakeSceneDescriptionsLLMClient{err: errors.New("provider unavailable")}).Extract(context.Background(), request) _, err := newExtractor(t, &fakeSceneDescriptionsLLMClient{err: errors.New("provider unavailable")}).Extract(context.Background(), request)
if err == nil || !strings.Contains(err.Error(), "dnd scene descriptions") || !strings.Contains(err.Error(), "provider unavailable") { if err == nil || !strings.Contains(err.Error(), "dnd scene descriptions") || !strings.Contains(err.Error(), "provider unavailable") {
t.Fatalf("provider Extract() error = %v, want contextual provider error", err) t.Fatalf("provider Extract() error = %v, want contextual provider error", err)

View File

@@ -54,11 +54,6 @@ func newExtractor(t *testing.T, client contracts.StructuredLLMClient, references
return extractor return extractor
} }
func emptyChunkRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest {
req.Chunk = &source.Chunk{ID: req.Chunk.ID, SourceID: req.Chunk.SourceID, Index: req.Chunk.Index}
return req
}
func mismatchedSourceInputRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest { func mismatchedSourceInputRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest {
req.SourceInput = contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"different":true}`), "sha256:other", "file:///other.json") req.SourceInput = contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"different":true}`), "sha256:other", "file:///other.json")
return req return req

View File

@@ -166,22 +166,7 @@ func (e *Extractor) Extract(ctx context.Context, req contracts.TypedExtractionRe
if e.llm == nil { if e.llm == nil {
return contracts.TypedExtractionResult[dnd.SpellList]{}, extractorErrorf("LLM client must not be nil") return contracts.TypedExtractionResult[dnd.SpellList]{}, extractorErrorf("LLM client must not be nil")
} }
if ctx == nil { sourceInput, err := shared.PrepareChunkExtraction(ctx, req)
return contracts.TypedExtractionResult[dnd.SpellList]{}, extractorErrorf("context must not be nil")
}
if err := ctx.Err(); err != nil {
return contracts.TypedExtractionResult[dnd.SpellList]{}, extractorErrorf("context error before extraction: %w", err)
}
if req.Source == nil {
return contracts.TypedExtractionResult[dnd.SpellList]{}, extractorErrorf("source must not be nil")
}
if req.Chunk == nil {
return contracts.TypedExtractionResult[dnd.SpellList]{}, extractorErrorf("chunk must not be nil")
}
if len(req.Chunk.Units) == 0 {
return contracts.TypedExtractionResult[dnd.SpellList]{}, extractorErrorf("chunk %q units must not be empty", req.Chunk.ID)
}
sourceInput, err := shared.ChunkPromptMaterial(req)
if err != nil { if err != nil {
return contracts.TypedExtractionResult[dnd.SpellList]{}, extractorErrorf("%w", err) return contracts.TypedExtractionResult[dnd.SpellList]{}, extractorErrorf("%w", err)
} }

View File

@@ -238,9 +238,8 @@ func TestExtractWrapsLLMClientError(t *testing.T) {
func TestExtractRejectsInvalidRequests(t *testing.T) { func TestExtractRejectsInvalidRequests(t *testing.T) {
validReq := extractionRequest() validReq := extractionRequest()
canceledCtx, cancel := context.WithCancel(context.Background())
cancel()
validExtractor := newExtractor(t, &fakeSpellsLLMClient{response: extractionResponse{SpellCasts: []spellCastResponse{}}}) validExtractor := newExtractor(t, &fakeSpellsLLMClient{response: extractionResponse{SpellCasts: []spellCastResponse{}}})
var nilExtractor *Extractor
tests := []struct { tests := []struct {
name string name string
extractor *Extractor extractor *Extractor
@@ -248,13 +247,9 @@ func TestExtractRejectsInvalidRequests(t *testing.T) {
req contracts.TypedExtractionRequest req contracts.TypedExtractionRequest
want string want string
}{ }{
{name: "nil extractor", ctx: context.Background(), req: validReq, want: "extractor"}, {name: "nil extractor", extractor: nilExtractor, ctx: context.Background(), req: validReq, want: "extractor"},
{name: "nil context", extractor: validExtractor, req: validReq, want: "context"}, {name: "nil LLM client", extractor: &Extractor{}, ctx: context.Background(), req: validReq, want: "LLM client"},
{name: "canceled context", extractor: validExtractor, ctx: canceledCtx, req: validReq, want: "context"}, {name: "wrapped preflight failure", extractor: validExtractor, ctx: context.Background(), req: mismatchedSourceInputRequest(validReq), want: "must match chunk"},
{name: "nil source", extractor: validExtractor, ctx: context.Background(), req: contracts.TypedExtractionRequest{Chunk: validReq.Chunk}, want: "source"},
{name: "nil chunk", extractor: validExtractor, ctx: context.Background(), req: contracts.TypedExtractionRequest{Source: validReq.Source}, want: "chunk"},
{name: "empty chunk units", extractor: validExtractor, ctx: context.Background(), req: emptyChunkRequest(validReq), want: "units"},
{name: "source input mismatches chunk", extractor: validExtractor, ctx: context.Background(), req: mismatchedSourceInputRequest(validReq), want: "must match chunk"},
} }
for _, test := range tests { for _, test := range tests {
t.Run(test.name, func(t *testing.T) { t.Run(test.name, func(t *testing.T) {

View File

@@ -99,11 +99,6 @@ func extractionRequest() contracts.TypedExtractionRequest {
return req return req
} }
func emptyChunkRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest {
req.Chunk = &source.Chunk{ID: req.Chunk.ID, SourceID: req.Chunk.SourceID, Index: req.Chunk.Index}
return req
}
func mismatchedSourceInputRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest { func mismatchedSourceInputRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest {
req.SourceInput = spellSourceInput() req.SourceInput = spellSourceInput()
return req return req

View File

@@ -2,14 +2,30 @@ package shared
import ( import (
"bytes" "bytes"
"context"
"fmt" "fmt"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts" "gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
) )
// ChunkPromptMaterial prepares the chunk-scoped source material used by D&D // PrepareChunkExtraction validates common D&D extraction prerequisites and
// extractors when constructing their prompt inputs. // prepares owned chunk-scoped source material for prompt inputs.
func ChunkPromptMaterial(req contracts.TypedExtractionRequest) (contracts.LLMInputMaterial, error) { func PrepareChunkExtraction(ctx context.Context, req contracts.TypedExtractionRequest) (contracts.LLMInputMaterial, error) {
if ctx == nil {
return contracts.LLMInputMaterial{}, fmt.Errorf("context must not be nil")
}
if err := ctx.Err(); err != nil {
return contracts.LLMInputMaterial{}, fmt.Errorf("context error before extraction: %w", err)
}
if req.Source == nil {
return contracts.LLMInputMaterial{}, fmt.Errorf("source must not be nil")
}
if req.Chunk == nil {
return contracts.LLMInputMaterial{}, fmt.Errorf("chunk must not be nil")
}
if len(req.Chunk.Units) == 0 {
return contracts.LLMInputMaterial{}, fmt.Errorf("chunk %q units must not be empty", req.Chunk.ID)
}
material := req.SourceInput.Clone() material := req.SourceInput.Clone()
if len(material.Content) == 0 { if len(material.Content) == 0 {
material = contracts.NewLLMInputMaterial("source", req.Chunk.MediaType, req.Chunk.Content, "", "") material = contracts.NewLLMInputMaterial("source", req.Chunk.MediaType, req.Chunk.Content, "", "")

View File

@@ -1,6 +1,7 @@
package shared package shared
import ( import (
"context"
"reflect" "reflect"
"strings" "strings"
"testing" "testing"
@@ -9,48 +10,78 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts" "gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
) )
func TestChunkPromptMaterial(t *testing.T) { func TestPrepareChunkExtraction(t *testing.T) {
chunk := &source.Chunk{ canceled, cancel := context.WithCancel(context.Background())
ID: "session-alpha:chunk:0", cancel()
Content: []byte(`{"units":[1,2]}`),
MediaType: "application/json",
}
tests := []struct { tests := []struct {
name string name string
ctx context.Context
configure func(*contracts.TypedExtractionRequest)
sourceInput contracts.LLMInputMaterial sourceInput contracts.LLMInputMaterial
want contracts.LLMInputMaterial want contracts.LLMInputMaterial
wantErr string wantErr string
mutateOutput bool mutateOutput bool
}{ }{
{ {
name: "fallback to chunk content", name: "nil context",
want: contracts.NewLLMInputMaterial("source", chunk.MediaType, chunk.Content, "", ""), wantErr: "context must not be nil",
},
{
name: "canceled context",
ctx: canceled,
wantErr: "context error before extraction",
},
{
name: "nil source",
configure: func(req *contracts.TypedExtractionRequest) {
req.Source = nil
},
wantErr: "source must not be nil",
},
{
name: "nil chunk",
configure: func(req *contracts.TypedExtractionRequest) {
req.Chunk = nil
},
wantErr: "chunk must not be nil",
},
{
name: "empty chunk units",
configure: func(req *contracts.TypedExtractionRequest) {
req.Chunk = &source.Chunk{ID: req.Chunk.ID}
},
wantErr: "units must not be empty",
},
{
name: "fallback to chunk content",
want: contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"units":[1,2]}`), "", ""),
mutateOutput: true,
}, },
{ {
name: "clone isolation", name: "clone isolation",
sourceInput: contracts.NewLLMInputMaterial("source", chunk.MediaType, chunk.Content, "sha256:source", "file:///source.json"), sourceInput: contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"units":[1,2]}`), "sha256:source", "file:///source.json"),
want: contracts.NewLLMInputMaterial("source", chunk.MediaType, chunk.Content, "sha256:source", "file:///source.json"), want: contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"units":[1,2]}`), "sha256:source", "file:///source.json"),
mutateOutput: true, mutateOutput: true,
}, },
{ {
name: "mismatched content", name: "mismatched content",
sourceInput: contracts.NewLLMInputMaterial("source", chunk.MediaType, []byte(`{"units":[9]}`), "sha256:other", "file:///other.json"), sourceInput: contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"units":[9]}`), "sha256:other", "file:///other.json"),
wantErr: "source input must match chunk", wantErr: "source input must match chunk",
}, },
{ {
name: "default fields", name: "default fields",
sourceInput: contracts.LLMInputMaterial{ sourceInput: contracts.LLMInputMaterial{
Content: append([]byte(nil), chunk.Content...), Content: []byte(`{"units":[1,2]}`),
Digest: "sha256:source", Digest: "sha256:source",
OriginURI: "file:///source.json", OriginURI: "file:///source.json",
}, },
want: contracts.LLMInputMaterial{ want: contracts.LLMInputMaterial{
Name: "source", Name: "source",
MediaType: chunk.MediaType, MediaType: "application/json",
Content: append([]byte(nil), chunk.Content...), Content: []byte(`{"units":[1,2]}`),
Digest: "sha256:source", Digest: "sha256:source",
OriginURI: "file:///source.json", OriginURI: "file:///source.json",
SizeBytes: int64(len(chunk.Content)), SizeBytes: int64(len(`{"units":[1,2]}`)),
}, },
}, },
{ {
@@ -58,7 +89,7 @@ func TestChunkPromptMaterial(t *testing.T) {
sourceInput: contracts.LLMInputMaterial{ sourceInput: contracts.LLMInputMaterial{
Name: "transcript", Name: "transcript",
MediaType: "text/plain", MediaType: "text/plain",
Content: append([]byte(nil), chunk.Content...), Content: []byte(`{"units":[1,2]}`),
Digest: "sha256:explicit", Digest: "sha256:explicit",
OriginURI: "file:///explicit.txt", OriginURI: "file:///explicit.txt",
SizeBytes: 42, SizeBytes: 42,
@@ -66,7 +97,7 @@ func TestChunkPromptMaterial(t *testing.T) {
want: contracts.LLMInputMaterial{ want: contracts.LLMInputMaterial{
Name: "transcript", Name: "transcript",
MediaType: "text/plain", MediaType: "text/plain",
Content: append([]byte(nil), chunk.Content...), Content: []byte(`{"units":[1,2]}`),
Digest: "sha256:explicit", Digest: "sha256:explicit",
OriginURI: "file:///explicit.txt", OriginURI: "file:///explicit.txt",
SizeBytes: 42, SizeBytes: 42,
@@ -76,26 +107,46 @@ func TestChunkPromptMaterial(t *testing.T) {
for _, test := range tests { for _, test := range tests {
t.Run(test.name, func(t *testing.T) { t.Run(test.name, func(t *testing.T) {
req := contracts.TypedExtractionRequest{Chunk: chunk, SourceInput: test.sourceInput} req := extractionRequest()
got, err := ChunkPromptMaterial(req) req.SourceInput = test.sourceInput
if test.configure != nil {
test.configure(&req)
}
ctx := test.ctx
if ctx == nil && test.wantErr != "context must not be nil" {
ctx = context.Background()
}
got, err := PrepareChunkExtraction(ctx, req)
if test.wantErr != "" { if test.wantErr != "" {
if err == nil || !strings.Contains(err.Error(), test.wantErr) { if err == nil || !strings.Contains(err.Error(), test.wantErr) {
t.Fatalf("ChunkPromptMaterial() error = %v, want %q", err, test.wantErr) t.Fatalf("PrepareChunkExtraction() error = %v, want %q", err, test.wantErr)
} }
return return
} }
if err != nil { if err != nil {
t.Fatalf("ChunkPromptMaterial() error = %v, want nil", err) t.Fatalf("PrepareChunkExtraction() error = %v, want nil", err)
} }
if !reflect.DeepEqual(got, test.want) { if !reflect.DeepEqual(got, test.want) {
t.Fatalf("ChunkPromptMaterial() = %#v, want %#v", got, test.want) t.Fatalf("PrepareChunkExtraction() = %#v, want %#v", got, test.want)
} }
if test.mutateOutput { if test.mutateOutput {
got.Content[0] = 'x' got.Content[0] = 'x'
if string(test.sourceInput.Content) != string(chunk.Content) { if string(req.SourceInput.Content) != string(test.sourceInput.Content) || string(req.Chunk.Content) != `{"units":[1,2]}` {
t.Fatalf("ChunkPromptMaterial() output shares content with source input") t.Fatal("PrepareChunkExtraction() output shares request content")
} }
} }
}) })
} }
} }
func extractionRequest() contracts.TypedExtractionRequest {
doc := &source.SourceDocument{ID: "session-alpha"}
chunk := &source.Chunk{
ID: "session-alpha:chunk:0",
SourceID: doc.ID,
Content: []byte(`{"units":[1,2]}`),
MediaType: "application/json",
Units: []source.SourceUnit{{ID: 1}},
}
return contracts.TypedExtractionRequest{Source: doc, Chunk: chunk}
}