eric/notarius
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add structured output repair configuration

Browse Source
This commit is contained in:
Eric Rakestraw
2026-08-25 19:47:42 +00:00
parent 0ef8931697
commit 9a92212632
6 changed files with 326 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
internal/core/config/config.go
View File

@@ -116,6 +116,10 @@ func (c *ConcurrencyConfig) recomputeStageWorkerDefaults() {
func clonePipelineProfile(in pipeline.PipelineProfile) pipeline.PipelineProfile {
out := in
if in.StructuredOutputRepairAttempts != nil {
value := *in.StructuredOutputRepairAttempts
out.StructuredOutputRepairAttempts = &value
}
out.Input = cloneModuleBinding(in.Input)
out.Chunk = cloneModuleBinding(in.Chunk)
out.Output = cloneModuleBinding(in.Output)
@@ -196,6 +200,10 @@ func cloneReferenceSource(in pipeline.ReferenceSource) pipeline.ReferenceSource
func cloneModuleBinding(in pipeline.ModuleBinding) pipeline.ModuleBinding {
out := in
if in.StructuredOutputRepairAttempts != nil {
value := *in.StructuredOutputRepairAttempts
out.StructuredOutputRepairAttempts = &value
}
if len(in.Options) > 0 {
out.Options = cloneOptions(in.Options)
}

109
internal/core/config/file_config.go
View File

@@ -35,23 +35,27 @@ type FilePromptKitLocalBackendConfig struct {
}
type FilePipelineProfile struct {
LLMProfile *string `yaml:"llm_profile,omitempty"`
Input fileModuleBinding `yaml:"input"`
Chunk *fileModuleBinding `yaml:"chunk,omitempty"`
Artifacts map[string]FileArtifactLaneProfile `yaml:"artifacts,omitempty"`
Steps []FilePipelineStepProfile `yaml:"steps,omitempty"`
Output *fileModuleBinding `yaml:"output,omitempty"`
References map[string]fileReferenceSource `yaml:"references,omitempty"`
artifactsSet bool `yaml:"-"`
stepsSet bool `yaml:"-"`
llmProfileSet bool `yaml:"-"`
LLMProfile *string `yaml:"llm_profile,omitempty"`
StructuredOutputRepairAttempts *int `yaml:"structured_output_repair_attempts,omitempty"`
Input fileModuleBinding `yaml:"input"`
Chunk *fileModuleBinding `yaml:"chunk,omitempty"`
Artifacts map[string]FileArtifactLaneProfile `yaml:"artifacts,omitempty"`
Steps []FilePipelineStepProfile `yaml:"steps,omitempty"`
Output *fileModuleBinding `yaml:"output,omitempty"`
References map[string]fileReferenceSource `yaml:"references,omitempty"`
artifactsSet bool `yaml:"-"`
stepsSet bool `yaml:"-"`
llmProfileSet bool `yaml:"-"`
}
func (p *FilePipelineProfile) UnmarshalYAML(node *yaml.Node) error {
if err := validateStructuredOutputRepairAttemptsNode(node, "pipeline profile"); err != nil {
return err
}
type plainFilePipelineProfile FilePipelineProfile
var decoded plainFilePipelineProfile
seen, err := decodeKnownMapping(node, &decoded, map[string]struct{}{
"llm_profile": {}, "input": {}, "chunk": {}, "artifacts": {}, "steps": {}, "output": {}, "references": {},
"llm_profile": {}, "structured_output_repair_attempts": {}, "input": {}, "chunk": {}, "artifacts": {}, "steps": {}, "output": {}, "references": {},
}, "pipeline profile")
if err != nil {
return err
@@ -147,12 +151,13 @@ type FileDebugConfig struct {
}
type fileModuleBinding struct {
Module string
LLMProfile string
Retries int
Options map[string]any
References map[string]fileReferenceSource
Validators pipeline.ValidatorOverride
Module string
LLMProfile string
StructuredOutputRepairAttempts *int
Retries int
Options map[string]any
References map[string]fileReferenceSource
Validators pipeline.ValidatorOverride
}
type fileReferenceSource struct {
@@ -264,6 +269,12 @@ func (b *fileModuleBinding) UnmarshalYAML(node *yaml.Node) error {
if b.LLMProfile == "" {
return fmt.Errorf("llm_profile must not be empty when set")
}
case "structured_output_repair_attempts":
attempts, err := parseStructuredOutputRepairAttempts(valueNode, "module binding")
if err != nil {
return err
}
b.StructuredOutputRepairAttempts = attempts
case "retries":
var retries int
if err := valueNode.Decode(&retries); err != nil {
@@ -304,15 +315,56 @@ func (b *fileModuleBinding) UnmarshalYAML(node *yaml.Node) error {
func (b fileModuleBinding) toPipelineBinding() pipeline.ModuleBinding {
return pipeline.ModuleBinding{
Module: strings.TrimSpace(b.Module),
LLMProfile: strings.TrimSpace(b.LLMProfile),
Retries: b.Retries,
Options: cloneOptions(b.Options),
References: fileReferenceSourcesToPipeline(b.References),
Validators: b.Validators,
Module: strings.TrimSpace(b.Module),
LLMProfile: strings.TrimSpace(b.LLMProfile),
StructuredOutputRepairAttempts: cloneStructuredOutputRepairAttempts(b.StructuredOutputRepairAttempts),
Retries: b.Retries,
Options: cloneOptions(b.Options),
References: fileReferenceSourcesToPipeline(b.References),
Validators: cloneValidatorOverride(b.Validators),
}
}
func validateStructuredOutputRepairAttemptsNode(node *yaml.Node, context string) error {
if node.Kind != yaml.MappingNode {
return fmt.Errorf("%s must be an object", context)
}
for i := 0; i < len(node.Content); i += 2 {
if node.Content[i].Value != "structured_output_repair_attempts" {
continue
}
if _, err := parseStructuredOutputRepairAttempts(node.Content[i+1], context); err != nil {
return err
}
}
return nil
}
func parseStructuredOutputRepairAttempts(node *yaml.Node, context string) (*int, error) {
if node.Tag == "!!null" {
return nil, fmt.Errorf("%s structured_output_repair_attempts must not be null", context)
}
if node.Kind != yaml.ScalarNode || node.Tag != "!!int" {
return nil, fmt.Errorf("%s structured_output_repair_attempts must be an integer", context)
}
var attempts int
if err := node.Decode(&attempts); err != nil {
return nil, fmt.Errorf("%s structured_output_repair_attempts must be an integer: %w", context, err)
}
if attempts < 0 || attempts > 3 {
return nil, fmt.Errorf("%s structured_output_repair_attempts must be between zero and three", context)
}
return &attempts, nil
}
func cloneStructuredOutputRepairAttempts(attempts *int) *int {
if attempts == nil {
return nil
}
value := *attempts
return &value
}
func LoadFileConfig(path string) (FileConfig, error) {
data, err := os.ReadFile(path)
if err != nil {
@@ -518,11 +570,12 @@ func (c *Config) applyFileConfigWithLookup(fileCfg FileConfig, lookup func(strin
return err
}
profile := pipeline.PipelineProfile{
ID: pipelineID,
LLMProfile: llmProfile,
Input: filePipeline.Input.toPipelineBinding(),
Artifacts: make(map[string]pipeline.ArtifactLaneProfile, len(filePipeline.Artifacts)),
References: fileReferenceSourcesToPipeline(filePipeline.References),
ID: pipelineID,
LLMProfile: llmProfile,
StructuredOutputRepairAttempts: cloneStructuredOutputRepairAttempts(filePipeline.StructuredOutputRepairAttempts),
Input: filePipeline.Input.toPipelineBinding(),
Artifacts: make(map[string]pipeline.ArtifactLaneProfile, len(filePipeline.Artifacts)),
References: fileReferenceSourcesToPipeline(filePipeline.References),
}
if filePipeline.Chunk != nil {
profile.Chunk = filePipeline.Chunk.toPipelineBinding()

162
internal/core/config/file_config_contract_test.go
View File

@@ -138,6 +138,168 @@ pipelines:
}
}
func TestStructuredOutputRepairAttemptsFileConfigurationPreservesPresenceAndOwnership(t *testing.T) {
const pipelineYAML = `version: 4
pipelines:
main:
%s
input: input
artifacts:
lane:
extract:
module: extract
structured_output_repair_attempts: 2
validators:
- module: validator
structured_output_repair_attempts: 3
`
t.Run("omitted pipeline value remains absent", func(t *testing.T) {
file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, ""))
if got := file.Pipelines["main"].StructuredOutputRepairAttempts; got != nil {
t.Fatalf("file pipeline repair attempts = %v, want nil", *got)
}
cfg := Default()
if err := cfg.ApplyFileConfig(file); err != nil {
t.Fatal(err)
}
if got := cfg.Pipelines["main"].StructuredOutputRepairAttempts; got != nil {
t.Fatalf("pipeline repair attempts = %v, want nil", *got)
}
if got := cfg.Pipelines["main"].Input.StructuredOutputRepairAttempts; got != nil {
t.Fatalf("scalar input binding repair attempts = %v, want nil", *got)
}
})
t.Run("zero is explicit and survives configuration boundaries", func(t *testing.T) {
file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, "structured_output_repair_attempts: 0"))
cfg := Default()
if err := cfg.ApplyFileConfig(file); err != nil {
t.Fatal(err)
}
profile := cfg.Pipelines["main"]
if profile.StructuredOutputRepairAttempts == nil || *profile.StructuredOutputRepairAttempts != 0 {
t.Fatalf("pipeline repair attempts = %v, want explicit zero", profile.StructuredOutputRepairAttempts)
}
lane := profile.Artifacts["lane"]
if lane.Extract.StructuredOutputRepairAttempts == nil || *lane.Extract.StructuredOutputRepairAttempts != 2 {
t.Fatalf("extract repair attempts = %v, want 2", lane.Extract.StructuredOutputRepairAttempts)
}
if lane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts == nil || *lane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts != 3 {
t.Fatalf("validator repair attempts = %v, want 3", lane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts)
}
*file.Pipelines["main"].StructuredOutputRepairAttempts = 1
if got := *cfg.Pipelines["main"].StructuredOutputRepairAttempts; got != 0 {
t.Fatalf("applied config aliased file configuration: got %d, want 0", got)
}
fileProfile := file.Pipelines["main"]
fileLane := fileProfile.Artifacts["lane"]
*fileLane.Extract.StructuredOutputRepairAttempts = 1
*fileLane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts = 1
fileProfile.Artifacts["lane"] = fileLane
file.Pipelines["main"] = fileProfile
configuredLane := cfg.Pipelines["main"].Artifacts["lane"]
if got := *configuredLane.Extract.StructuredOutputRepairAttempts; got != 2 {
t.Fatalf("configured extract aliased file configuration: got %d, want 2", got)
}
if got := *configuredLane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts; got != 3 {
t.Fatalf("configured validator aliased file configuration: got %d, want 3", got)
}
cloned := cloneConfig(cfg)
*cloned.Pipelines["main"].StructuredOutputRepairAttempts = 1
if got := *cfg.Pipelines["main"].StructuredOutputRepairAttempts; got != 0 {
t.Fatalf("cloned config aliased source configuration: got %d, want 0", got)
}
redacted := cfg.Redacted()
*redacted.Pipelines["main"].StructuredOutputRepairAttempts = 1
if got := *cfg.Pipelines["main"].StructuredOutputRepairAttempts; got != 0 {
t.Fatalf("redacted config aliased source configuration: got %d, want 0", got)
}
summary := cfg.RedactedSummaryPayload().(Config)
if summary.Pipelines["main"].StructuredOutputRepairAttempts == nil || *summary.Pipelines["main"].StructuredOutputRepairAttempts != 0 {
t.Fatalf("redacted summary pipeline repair attempts = %v, want explicit zero", summary.Pipelines["main"].StructuredOutputRepairAttempts)
}
data, err := json.Marshal(cfg)
if err != nil {
t.Fatal(err)
}
var roundTripped Config
if err := json.Unmarshal(data, &roundTripped); err != nil {
t.Fatal(err)
}
roundTrippedProfile := roundTripped.Pipelines["main"]
if roundTrippedProfile.StructuredOutputRepairAttempts == nil || *roundTrippedProfile.StructuredOutputRepairAttempts != 0 {
t.Fatalf("round-tripped pipeline repair attempts = %v, want explicit zero", roundTrippedProfile.StructuredOutputRepairAttempts)
}
roundTrippedLane := roundTrippedProfile.Artifacts["lane"]
if roundTrippedLane.Extract.StructuredOutputRepairAttempts == nil || *roundTrippedLane.Extract.StructuredOutputRepairAttempts != 2 {
t.Fatalf("round-tripped extract repair attempts = %v, want 2", roundTrippedLane.Extract.StructuredOutputRepairAttempts)
}
if roundTrippedLane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts == nil || *roundTrippedLane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts != 3 {
t.Fatalf("round-tripped validator repair attempts = %v, want 3", roundTrippedLane.Extract.Validators.Validators[0].StructuredOutputRepairAttempts)
}
})
}
func TestStructuredOutputRepairAttemptsFileConfigurationRejectsInvalidValues(t *testing.T) {
const pipelineYAML = `version: 4
pipelines:
main:
input: input
artifacts:
lane:
extract: extract
%s
`
const bindingYAML = `version: 4
pipelines:
main:
input:
module: input
%s
artifacts:
lane:
extract: extract
`
for _, tt := range []struct {
name string
source string
want string
}{
{name: "null pipeline value", source: "structured_output_repair_attempts: null", want: "pipeline profile structured_output_repair_attempts must not be null"},
{name: "fractional pipeline value", source: "structured_output_repair_attempts: 1.5", want: "pipeline profile structured_output_repair_attempts must be an integer"},
{name: "quoted pipeline value", source: "structured_output_repair_attempts: '1'", want: "pipeline profile structured_output_repair_attempts must be an integer"},
{name: "out of range pipeline value", source: "structured_output_repair_attempts: 4", want: "pipeline profile structured_output_repair_attempts must be between zero and three"},
} {
t.Run(tt.name, func(t *testing.T) {
_, err := ParseFileConfigYAML([]byte(fmt.Sprintf(pipelineYAML, tt.source)))
if err == nil || !strings.Contains(err.Error(), tt.want) {
t.Fatalf("ParseFileConfigYAML() error = %v, want %q", err, tt.want)
}
})
}
for _, tt := range []struct {
name string
source string
want string
}{
{name: "null binding value", source: "structured_output_repair_attempts: null", want: "module binding structured_output_repair_attempts must not be null"},
{name: "noninteger binding value", source: "structured_output_repair_attempts: true", want: "module binding structured_output_repair_attempts must be an integer"},
{name: "out of range binding value", source: "structured_output_repair_attempts: -1", want: "module binding structured_output_repair_attempts must be between zero and three"},
} {
t.Run(tt.name, func(t *testing.T) {
_, err := ParseFileConfigYAML([]byte(fmt.Sprintf(bindingYAML, tt.source)))
if err == nil || !strings.Contains(err.Error(), tt.want) {
t.Fatalf("ParseFileConfigYAML() error = %v, want %q", err, tt.want)
}
})
}
}
func TestFileModuleBindingRejectsExplicitEmptyLLMProfile(t *testing.T) {
const configYAML = `version: 4
pipelines:

16
internal/core/config/validation.go
View File

@@ -116,6 +116,9 @@ func validatePipelineProfiles(profiles map[string]pipeline.PipelineProfile) erro
if profile.ID != "" && strings.TrimSpace(profile.ID) != id {
return fmt.Errorf("pipeline %q profile id %q does not match map key", id, profile.ID)
}
if err := validateStructuredOutputRepairAttempts(fmt.Sprintf("pipeline %q", id), profile.StructuredOutputRepairAttempts); err != nil {
return err
}
if err := validateBinding(id, "", "input", profile.Input, false); err != nil {
return err
}
@@ -195,6 +198,9 @@ func validateBinding(
binding pipeline.ModuleBinding,
referencesAllowed bool,
) error {
if err := validateStructuredOutputRepairAttempts(referenceContext(pipelineID, laneID, slot), binding.StructuredOutputRepairAttempts); err != nil {
return err
}
if err := validateBindingLLMProfile(pipelineID, laneID, slot, binding); err != nil {
return err
}
@@ -219,6 +225,13 @@ func validateBinding(
return validateReferenceMapForContext(pipelineID, laneID, slot, binding.References, true)
}
func validateStructuredOutputRepairAttempts(context string, attempts *int) error {
if attempts != nil && (*attempts < 0 || *attempts > 3) {
return fmt.Errorf("%s structured_output_repair_attempts must be between zero and three", context)
}
return nil
}
func validateValidatorOverride(pipelineID string, laneID string, slot string, override pipeline.ValidatorOverride) error {
if !override.Set {
return nil
@@ -230,6 +243,9 @@ func validateValidatorOverride(pipelineID string, laneID string, slot string, ov
}
for i, validator := range override.Validators {
context := fmt.Sprintf("%s validators[%d]", referenceContext(pipelineID, laneID, slot), i)
if err := validateStructuredOutputRepairAttempts(context, validator.StructuredOutputRepairAttempts); err != nil {
return err
}
if strings.TrimSpace(validator.Module) == "" {
return fmt.Errorf("%s module must not be empty", context)
}

77
internal/framework/pipeline/profile.go
View File

@@ -81,19 +81,21 @@ type ValidatorOverride struct {
func (binding ModuleBinding) MarshalJSON() ([]byte, error) {
type moduleBindingJSON struct {
Module string `json:"module"`
LLMProfile string `json:"llm_profile,omitempty"`
Retries int `json:"retries,omitempty"`
Options map[string]any `json:"options,omitempty"`
References map[string]ReferenceSource `json:"references,omitempty"`
Validators *[]ModuleBinding `json:"validators,omitempty"`
Module string `json:"module"`
LLMProfile string `json:"llm_profile,omitempty"`
StructuredOutputRepairAttempts *int `json:"structured_output_repair_attempts,omitempty"`
Retries int `json:"retries,omitempty"`
Options map[string]any `json:"options,omitempty"`
References map[string]ReferenceSource `json:"references,omitempty"`
Validators *[]ModuleBinding `json:"validators,omitempty"`
}
out := moduleBindingJSON{
Module: binding.Module,
LLMProfile: binding.LLMProfile,
Retries: binding.Retries,
Options: binding.Options,
References: binding.References,
Module: binding.Module,
LLMProfile: binding.LLMProfile,
StructuredOutputRepairAttempts: binding.StructuredOutputRepairAttempts,
Retries: binding.Retries,
Options: binding.Options,
References: binding.References,
}
if binding.Validators.Set {
validators := cloneModuleBindings(binding.Validators.Validators)
@@ -102,6 +104,42 @@ func (binding ModuleBinding) MarshalJSON() ([]byte, error) {
return json.Marshal(out)
}
func (binding *ModuleBinding) UnmarshalJSON(data []byte) error {
if binding == nil {
return fmt.Errorf("module binding must not be nil")
}
type moduleBindingJSON struct {
Module string `json:"module"`
LLMProfile string `json:"llm_profile,omitempty"`
StructuredOutputRepairAttempts *int `json:"structured_output_repair_attempts,omitempty"`
Retries int `json:"retries,omitempty"`
Options map[string]any `json:"options,omitempty"`
References map[string]ReferenceSource `json:"references,omitempty"`
Validators json.RawMessage `json:"validators,omitempty"`
}
var decoded moduleBindingJSON
if err := json.Unmarshal(data, &decoded); err != nil {
return err
}
out := ModuleBinding{
Module: decoded.Module,
LLMProfile: decoded.LLMProfile,
StructuredOutputRepairAttempts: decoded.StructuredOutputRepairAttempts,
Retries: decoded.Retries,
Options: decoded.Options,
References: decoded.References,
}
if len(decoded.Validators) > 0 && string(decoded.Validators) != "null" {
var validators []ModuleBinding
if err := json.Unmarshal(decoded.Validators, &validators); err != nil {
return fmt.Errorf("decode module binding validators: %w", err)
}
out.Validators = ValidatorOverride{Set: true, Validators: validators}
}
*binding = cloneModuleBinding(out)
return nil
}
type ArtifactLaneProfile struct {
Extract ModuleBinding `json:"extract"`
Merge ModuleBinding `json:"merge,omitempty"`
@@ -117,14 +155,15 @@ type PipelineStepProfile struct {
}
type PipelineProfile struct {
ID string `json:"id"`
LLMProfile string `json:"llm_profile,omitempty"`
Input ModuleBinding `json:"input"`
Chunk ModuleBinding `json:"chunk,omitempty"`
Artifacts map[string]ArtifactLaneProfile `json:"artifacts"`
Steps []PipelineStepProfile `json:"steps,omitempty"`
Output ModuleBinding `json:"output,omitempty"`
References map[string]ReferenceSource `json:"references,omitempty"`
ID string `json:"id"`
LLMProfile string `json:"llm_profile,omitempty"`
StructuredOutputRepairAttempts *int `json:"structured_output_repair_attempts,omitempty"`
Input ModuleBinding `json:"input"`
Chunk ModuleBinding `json:"chunk,omitempty"`
Artifacts map[string]ArtifactLaneProfile `json:"artifacts"`
Steps []PipelineStepProfile `json:"steps,omitempty"`
Output ModuleBinding `json:"output,omitempty"`
References map[string]ReferenceSource `json:"references,omitempty"`
}
type ResolveOptions struct {