Add bounded structured-output repair
This commit is contained in:
71
internal/usecase/repairer.go
Normal file
71
internal/usecase/repairer.go
Normal file
@@ -0,0 +1,71 @@
|
||||
package usecase
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"strings"
|
||||
|
||||
"gitea.maximumdirect.net/eric/scriptorium/internal/domain"
|
||||
"gitea.maximumdirect.net/eric/scriptorium/internal/llm"
|
||||
)
|
||||
|
||||
type OutputRepairer interface {
|
||||
Repair(ctx context.Context, req RepairRequest) (*domain.GenerateResponse, error)
|
||||
}
|
||||
|
||||
type RepairRequest struct {
|
||||
PreviousOutput string
|
||||
ValidationErrors []string
|
||||
Target domain.ModelTarget
|
||||
Attempt int
|
||||
MaxAttempts int
|
||||
Mode domain.ValidationMode
|
||||
}
|
||||
|
||||
type defaultOutputRepairer struct {
|
||||
llm llm.Client
|
||||
}
|
||||
|
||||
func NewDefaultOutputRepairer(llmClient llm.Client) OutputRepairer {
|
||||
return &defaultOutputRepairer{llm: llmClient}
|
||||
}
|
||||
|
||||
func (r *defaultOutputRepairer) Repair(ctx context.Context, req RepairRequest) (*domain.GenerateResponse, error) {
|
||||
if r.llm == nil {
|
||||
return nil, errors.New("llm client is required for repair")
|
||||
}
|
||||
|
||||
errs := "(none provided)"
|
||||
if len(req.ValidationErrors) > 0 {
|
||||
errs = strings.Join(req.ValidationErrors, "\n")
|
||||
}
|
||||
|
||||
prompt := domain.RenderedPrompt{Messages: []domain.RenderedMessage{
|
||||
{
|
||||
Role: "system",
|
||||
Content: "You repair invalid JSON output. Return only corrected JSON. Do not include explanations or markdown code fences.",
|
||||
},
|
||||
{
|
||||
Role: "user",
|
||||
Content: fmt.Sprintf(
|
||||
"Repair attempt %d of %d for validation mode %s.\n\nValidation errors:\n%s\n\nPrevious output:\n%s\n\nReturn only corrected JSON.",
|
||||
req.Attempt,
|
||||
req.MaxAttempts,
|
||||
req.Mode,
|
||||
errs,
|
||||
req.PreviousOutput,
|
||||
),
|
||||
},
|
||||
}}
|
||||
|
||||
resp, err := r.llm.Generate(ctx, domain.GenerateRequest{Prompt: prompt, Target: req.Target})
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if resp == nil {
|
||||
return nil, errors.New("repair llm returned nil response")
|
||||
}
|
||||
|
||||
return resp, nil
|
||||
}
|
||||
@@ -33,6 +33,7 @@ type Runner struct {
|
||||
renderer prompt.Renderer
|
||||
llm llm.Client
|
||||
validator validate.Validator
|
||||
repairer OutputRepairer
|
||||
}
|
||||
|
||||
func NewRunner(
|
||||
@@ -41,6 +42,17 @@ func NewRunner(
|
||||
renderer prompt.Renderer,
|
||||
llmClient llm.Client,
|
||||
validator validate.Validator,
|
||||
) *Runner {
|
||||
return NewRunnerWithRepairer(profiles, artifacts, renderer, llmClient, validator, nil)
|
||||
}
|
||||
|
||||
func NewRunnerWithRepairer(
|
||||
profiles profile.Repository,
|
||||
artifacts artifact.Reader,
|
||||
renderer prompt.Renderer,
|
||||
llmClient llm.Client,
|
||||
validator validate.Validator,
|
||||
repairer OutputRepairer,
|
||||
) *Runner {
|
||||
return &Runner{
|
||||
profiles: profiles,
|
||||
@@ -48,6 +60,7 @@ func NewRunner(
|
||||
renderer: renderer,
|
||||
llm: llmClient,
|
||||
validator: validator,
|
||||
repairer: repairer,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -96,18 +109,38 @@ func (r *Runner) Run(ctx context.Context, req domain.RunRequest) (*domain.RunRes
|
||||
}
|
||||
|
||||
outputArtifact := buildOutputArtifact(genResp.Content, effectiveContract.Format)
|
||||
|
||||
validationResult := domain.ValidationResult{
|
||||
Status: domain.ValidationSkipped,
|
||||
Mode: effectiveContract.ValidationMode,
|
||||
SchemaPath: effectiveContract.SchemaPath,
|
||||
RepairAttempts: effectiveContract.RepairAttempts,
|
||||
IsValid: true,
|
||||
validationResult, err := r.validateOutput(ctx, &outputArtifact, effectiveContract, 0)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("%w: %w", ErrValidation, err)
|
||||
}
|
||||
if r.validator != nil && effectiveContract.ValidationMode != domain.ValidationNone {
|
||||
validationResult, err = r.validator.Validate(ctx, &outputArtifact, effectiveContract)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("%w: %w", ErrValidation, err)
|
||||
|
||||
if r.shouldAttemptRepair(effectiveContract, validationResult) {
|
||||
attemptsUsed := 0
|
||||
for attemptsUsed < effectiveContract.RepairAttempts && validationResult.Status == domain.ValidationFailed {
|
||||
attemptsUsed++
|
||||
|
||||
repairResp, repairErr := r.repairer.Repair(ctx, RepairRequest{
|
||||
PreviousOutput: genResp.Content,
|
||||
ValidationErrors: validationResult.Errors,
|
||||
Target: effectiveModel,
|
||||
Attempt: attemptsUsed,
|
||||
MaxAttempts: effectiveContract.RepairAttempts,
|
||||
Mode: effectiveContract.ValidationMode,
|
||||
})
|
||||
if repairErr != nil {
|
||||
return nil, fmt.Errorf("%w: %w", ErrValidation, repairErr)
|
||||
}
|
||||
if repairResp == nil {
|
||||
return nil, fmt.Errorf("%w: repairer returned nil response", ErrValidation)
|
||||
}
|
||||
|
||||
genResp = repairResp
|
||||
outputArtifact = buildOutputArtifact(genResp.Content, effectiveContract.Format)
|
||||
|
||||
validationResult, err = r.validateOutput(ctx, &outputArtifact, effectiveContract, attemptsUsed)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("%w: %w", ErrValidation, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -129,6 +162,38 @@ func (r *Runner) Run(ctx context.Context, req domain.RunRequest) (*domain.RunRes
|
||||
}, nil
|
||||
}
|
||||
|
||||
func (r *Runner) validateOutput(ctx context.Context, artifact *domain.Artifact, contract domain.OutputContract, attemptsUsed int) (domain.ValidationResult, error) {
|
||||
if r.validator == nil || contract.ValidationMode == domain.ValidationNone {
|
||||
return domain.ValidationResult{
|
||||
Status: domain.ValidationSkipped,
|
||||
Mode: contract.ValidationMode,
|
||||
SchemaPath: contract.SchemaPath,
|
||||
RepairAttempts: attemptsUsed,
|
||||
IsValid: true,
|
||||
}, nil
|
||||
}
|
||||
|
||||
res, err := r.validator.Validate(ctx, artifact, contract)
|
||||
if err != nil {
|
||||
return domain.ValidationResult{}, err
|
||||
}
|
||||
res.RepairAttempts = attemptsUsed
|
||||
return res, nil
|
||||
}
|
||||
|
||||
func (r *Runner) shouldAttemptRepair(contract domain.OutputContract, validationResult domain.ValidationResult) bool {
|
||||
if r.repairer == nil {
|
||||
return false
|
||||
}
|
||||
if contract.RepairAttempts <= 0 {
|
||||
return false
|
||||
}
|
||||
if validationResult.Status != domain.ValidationFailed {
|
||||
return false
|
||||
}
|
||||
return contract.ValidationMode == domain.ValidationJSON || contract.ValidationMode == domain.ValidationJSONSchema
|
||||
}
|
||||
|
||||
func mergeModelTarget(base domain.ModelTarget, override *domain.ModelTarget) domain.ModelTarget {
|
||||
if override == nil {
|
||||
return base
|
||||
|
||||
@@ -87,6 +87,29 @@ func (f *fakeValidator) Validate(ctx context.Context, artifact *domain.Artifact,
|
||||
return f.result, nil
|
||||
}
|
||||
|
||||
type fakeRepairer struct {
|
||||
responses []*domain.GenerateResponse
|
||||
err error
|
||||
calls int
|
||||
lastReq RepairRequest
|
||||
}
|
||||
|
||||
func (f *fakeRepairer) Repair(ctx context.Context, req RepairRequest) (*domain.GenerateResponse, error) {
|
||||
f.calls++
|
||||
f.lastReq = req
|
||||
if f.err != nil {
|
||||
return nil, f.err
|
||||
}
|
||||
if len(f.responses) == 0 {
|
||||
return nil, errors.New("no repair response configured")
|
||||
}
|
||||
idx := f.calls - 1
|
||||
if idx >= len(f.responses) {
|
||||
idx = len(f.responses) - 1
|
||||
}
|
||||
return f.responses[idx], nil
|
||||
}
|
||||
|
||||
func TestRunnerRunSuccessful(t *testing.T) {
|
||||
repo := &fakeProfileRepo{
|
||||
profile: &domain.PromptProfile{
|
||||
@@ -377,6 +400,267 @@ func TestRunnerRunValidationFailureWithRealValidatorPreservesRawOutput(t *testin
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunnerRunNoRepairWhenDisabled(t *testing.T) {
|
||||
repairer := &fakeRepairer{
|
||||
responses: []*domain.GenerateResponse{{Content: `{"ok":true}`}},
|
||||
}
|
||||
|
||||
runner := NewRunnerWithRepairer(
|
||||
&fakeProfileRepo{profile: &domain.PromptProfile{
|
||||
ID: "p-json",
|
||||
Version: "1",
|
||||
OutputFormat: domain.FormatJSON,
|
||||
ModelDefaults: domain.ModelTarget{
|
||||
Endpoint: "ep",
|
||||
Model: "m",
|
||||
},
|
||||
Validation: domain.OutputContract{
|
||||
ValidationMode: domain.ValidationJSON,
|
||||
Format: domain.FormatJSON,
|
||||
RepairAttempts: 0,
|
||||
},
|
||||
}},
|
||||
&fakeArtifactReader{artifactsByURI: map[string]*domain.Artifact{"a://ok": {Body: []byte("x"), Hash: hashString("x")}}},
|
||||
&fakeRenderer{rendered: &domain.RenderedPrompt{}},
|
||||
&fakeLLM{resp: &domain.GenerateResponse{Content: `{"broken":`}},
|
||||
validate.NewStandardValidator(t.TempDir()),
|
||||
repairer,
|
||||
)
|
||||
|
||||
res, err := runner.Run(context.Background(), domain.RunRequest{
|
||||
ProfileID: "p-json",
|
||||
Inputs: map[string]domain.ArtifactRef{
|
||||
"transcript": {Type: domain.ArtifactRefFile, URI: "a://ok"},
|
||||
},
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("expected no error, got %v", err)
|
||||
}
|
||||
if repairer.calls != 0 {
|
||||
t.Fatalf("expected no repair calls, got %d", repairer.calls)
|
||||
}
|
||||
if res.Validation.Status != domain.ValidationFailed {
|
||||
t.Fatalf("expected failed validation, got %q", res.Validation.Status)
|
||||
}
|
||||
if res.RawOutput != `{"broken":` {
|
||||
t.Fatalf("expected original output preserved, got %q", res.RawOutput)
|
||||
}
|
||||
if res.Validation.RepairAttempts != 0 {
|
||||
t.Fatalf("expected repair attempts 0, got %d", res.Validation.RepairAttempts)
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunnerRunSuccessfulRepairAfterInvalidJSON(t *testing.T) {
|
||||
repairer := &fakeRepairer{
|
||||
responses: []*domain.GenerateResponse{{Content: `{"ok":true}`, Usage: domain.TokenUsage{TotalTokens: 5}}},
|
||||
}
|
||||
|
||||
runner := NewRunnerWithRepairer(
|
||||
&fakeProfileRepo{profile: &domain.PromptProfile{
|
||||
ID: "p-json",
|
||||
Version: "1",
|
||||
OutputFormat: domain.FormatJSON,
|
||||
ModelDefaults: domain.ModelTarget{
|
||||
Endpoint: "ep",
|
||||
Model: "m",
|
||||
},
|
||||
Validation: domain.OutputContract{
|
||||
ValidationMode: domain.ValidationJSON,
|
||||
Format: domain.FormatJSON,
|
||||
RepairAttempts: 1,
|
||||
},
|
||||
}},
|
||||
&fakeArtifactReader{artifactsByURI: map[string]*domain.Artifact{"a://ok": {Body: []byte("x"), Hash: hashString("x")}}},
|
||||
&fakeRenderer{rendered: &domain.RenderedPrompt{}},
|
||||
&fakeLLM{resp: &domain.GenerateResponse{Content: `{"broken":`, Usage: domain.TokenUsage{TotalTokens: 3}}},
|
||||
validate.NewStandardValidator(t.TempDir()),
|
||||
repairer,
|
||||
)
|
||||
|
||||
res, err := runner.Run(context.Background(), domain.RunRequest{
|
||||
ProfileID: "p-json",
|
||||
Inputs: map[string]domain.ArtifactRef{
|
||||
"transcript": {Type: domain.ArtifactRefFile, URI: "a://ok"},
|
||||
},
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("expected no error, got %v", err)
|
||||
}
|
||||
if repairer.calls != 1 {
|
||||
t.Fatalf("expected one repair call, got %d", repairer.calls)
|
||||
}
|
||||
if res.Validation.Status != domain.ValidationPassed {
|
||||
t.Fatalf("expected passed validation, got %q", res.Validation.Status)
|
||||
}
|
||||
if res.Validation.RepairAttempts != 1 {
|
||||
t.Fatalf("expected repair attempts 1, got %d", res.Validation.RepairAttempts)
|
||||
}
|
||||
if res.RawOutput != `{"ok":true}` {
|
||||
t.Fatalf("expected repaired output, got %q", res.RawOutput)
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunnerRunSuccessfulRepairAfterSchemaFailure(t *testing.T) {
|
||||
tmp := t.TempDir()
|
||||
if err := os.WriteFile(filepath.Join(tmp, "schema.json"), []byte(`{
|
||||
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
||||
"type": "object",
|
||||
"required": ["name"],
|
||||
"properties": {
|
||||
"name": {"type": "string"}
|
||||
}
|
||||
}`), 0644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
repairer := &fakeRepairer{
|
||||
responses: []*domain.GenerateResponse{{Content: `{"name":"eris"}`}},
|
||||
}
|
||||
|
||||
runner := NewRunnerWithRepairer(
|
||||
&fakeProfileRepo{profile: &domain.PromptProfile{
|
||||
ID: "p-json",
|
||||
Version: "1",
|
||||
OutputFormat: domain.FormatJSON,
|
||||
ModelDefaults: domain.ModelTarget{
|
||||
Endpoint: "ep",
|
||||
Model: "m",
|
||||
},
|
||||
Validation: domain.OutputContract{
|
||||
ValidationMode: domain.ValidationJSONSchema,
|
||||
SchemaPath: "schema.json",
|
||||
Format: domain.FormatJSON,
|
||||
RepairAttempts: 1,
|
||||
},
|
||||
}},
|
||||
&fakeArtifactReader{artifactsByURI: map[string]*domain.Artifact{"a://ok": {Body: []byte("x"), Hash: hashString("x")}}},
|
||||
&fakeRenderer{rendered: &domain.RenderedPrompt{}},
|
||||
&fakeLLM{resp: &domain.GenerateResponse{Content: `{"count":1}`}},
|
||||
validate.NewStandardValidator(tmp),
|
||||
repairer,
|
||||
)
|
||||
|
||||
res, err := runner.Run(context.Background(), domain.RunRequest{
|
||||
ProfileID: "p-json",
|
||||
Inputs: map[string]domain.ArtifactRef{
|
||||
"transcript": {Type: domain.ArtifactRefFile, URI: "a://ok"},
|
||||
},
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("expected no error, got %v", err)
|
||||
}
|
||||
if res.Validation.Status != domain.ValidationPassed {
|
||||
t.Fatalf("expected passed validation, got %q", res.Validation.Status)
|
||||
}
|
||||
if res.Validation.RepairAttempts != 1 {
|
||||
t.Fatalf("expected repair attempts 1, got %d", res.Validation.RepairAttempts)
|
||||
}
|
||||
if res.RawOutput != `{"name":"eris"}` {
|
||||
t.Fatalf("expected repaired output, got %q", res.RawOutput)
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunnerRunFailedRepairPreservesRawOutputAndErrors(t *testing.T) {
|
||||
repairer := &fakeRepairer{
|
||||
responses: []*domain.GenerateResponse{
|
||||
{Content: `{"repair1":`},
|
||||
{Content: `{"repair2":`},
|
||||
},
|
||||
}
|
||||
|
||||
runner := NewRunnerWithRepairer(
|
||||
&fakeProfileRepo{profile: &domain.PromptProfile{
|
||||
ID: "p-json",
|
||||
Version: "1",
|
||||
OutputFormat: domain.FormatJSON,
|
||||
ModelDefaults: domain.ModelTarget{
|
||||
Endpoint: "ep",
|
||||
Model: "m",
|
||||
},
|
||||
Validation: domain.OutputContract{
|
||||
ValidationMode: domain.ValidationJSON,
|
||||
Format: domain.FormatJSON,
|
||||
RepairAttempts: 2,
|
||||
},
|
||||
}},
|
||||
&fakeArtifactReader{artifactsByURI: map[string]*domain.Artifact{"a://ok": {Body: []byte("x"), Hash: hashString("x")}}},
|
||||
&fakeRenderer{rendered: &domain.RenderedPrompt{}},
|
||||
&fakeLLM{resp: &domain.GenerateResponse{Content: `{"initial":`}},
|
||||
validate.NewStandardValidator(t.TempDir()),
|
||||
repairer,
|
||||
)
|
||||
|
||||
res, err := runner.Run(context.Background(), domain.RunRequest{
|
||||
ProfileID: "p-json",
|
||||
Inputs: map[string]domain.ArtifactRef{
|
||||
"transcript": {Type: domain.ArtifactRefFile, URI: "a://ok"},
|
||||
},
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("expected no error, got %v", err)
|
||||
}
|
||||
if res.Validation.Status != domain.ValidationFailed {
|
||||
t.Fatalf("expected failed validation, got %q", res.Validation.Status)
|
||||
}
|
||||
if len(res.Validation.Errors) == 0 {
|
||||
t.Fatal("expected validation errors after failed repair")
|
||||
}
|
||||
if res.Validation.RepairAttempts != 2 {
|
||||
t.Fatalf("expected repair attempts 2, got %d", res.Validation.RepairAttempts)
|
||||
}
|
||||
if res.RawOutput != `{"repair2":` {
|
||||
t.Fatalf("expected final repaired output preserved, got %q", res.RawOutput)
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunnerRunRepairAttemptsBounded(t *testing.T) {
|
||||
repairer := &fakeRepairer{
|
||||
responses: []*domain.GenerateResponse{
|
||||
{Content: `{"repair1":`},
|
||||
{Content: `{"repair2":`},
|
||||
{Content: `{"repair3":`},
|
||||
},
|
||||
}
|
||||
|
||||
runner := NewRunnerWithRepairer(
|
||||
&fakeProfileRepo{profile: &domain.PromptProfile{
|
||||
ID: "p-json",
|
||||
Version: "1",
|
||||
OutputFormat: domain.FormatJSON,
|
||||
ModelDefaults: domain.ModelTarget{
|
||||
Endpoint: "ep",
|
||||
Model: "m",
|
||||
},
|
||||
Validation: domain.OutputContract{
|
||||
ValidationMode: domain.ValidationJSON,
|
||||
Format: domain.FormatJSON,
|
||||
RepairAttempts: 1,
|
||||
},
|
||||
}},
|
||||
&fakeArtifactReader{artifactsByURI: map[string]*domain.Artifact{"a://ok": {Body: []byte("x"), Hash: hashString("x")}}},
|
||||
&fakeRenderer{rendered: &domain.RenderedPrompt{}},
|
||||
&fakeLLM{resp: &domain.GenerateResponse{Content: `{"initial":`}},
|
||||
validate.NewStandardValidator(t.TempDir()),
|
||||
repairer,
|
||||
)
|
||||
|
||||
res, err := runner.Run(context.Background(), domain.RunRequest{
|
||||
ProfileID: "p-json",
|
||||
Inputs: map[string]domain.ArtifactRef{
|
||||
"transcript": {Type: domain.ArtifactRefFile, URI: "a://ok"},
|
||||
},
|
||||
})
|
||||
if err != nil {
|
||||
t.Fatalf("expected no error, got %v", err)
|
||||
}
|
||||
if repairer.calls != 1 {
|
||||
t.Fatalf("expected repair calls bounded to 1, got %d", repairer.calls)
|
||||
}
|
||||
if res.Validation.RepairAttempts != 1 {
|
||||
t.Fatalf("expected repair attempts 1, got %d", res.Validation.RepairAttempts)
|
||||
}
|
||||
}
|
||||
|
||||
func minimalProfile() *domain.PromptProfile {
|
||||
return &domain.PromptProfile{
|
||||
ID: "p",
|
||||
|
||||
Reference in New Issue
Block a user