Add validation policy configuration

This commit is contained in:
2026-08-26 23:34:06 +00:00
parent 1c3da3e869
commit 9d0faabf61
14 changed files with 628 additions and 57 deletions

View File

@@ -116,6 +116,7 @@ func (c *ConcurrencyConfig) recomputeStageWorkerDefaults() {
func clonePipelineProfile(in pipeline.PipelineProfile) pipeline.PipelineProfile {
out := in
out.ValidationPolicy = cloneValidationPolicyOverride(in.ValidationPolicy)
if in.StructuredOutputRepairAttempts != nil {
value := *in.StructuredOutputRepairAttempts
out.StructuredOutputRepairAttempts = &value
@@ -200,6 +201,7 @@ func cloneReferenceSource(in pipeline.ReferenceSource) pipeline.ReferenceSource
func cloneModuleBinding(in pipeline.ModuleBinding) pipeline.ModuleBinding {
out := in
out.ValidationPolicy = cloneValidationPolicyOverride(in.ValidationPolicy)
if in.StructuredOutputRepairAttempts != nil {
value := *in.StructuredOutputRepairAttempts
out.StructuredOutputRepairAttempts = &value
@@ -212,6 +214,26 @@ func cloneModuleBinding(in pipeline.ModuleBinding) pipeline.ModuleBinding {
return out
}
func cloneValidationPolicyOverride(in *pipeline.ValidationPolicyOverride) *pipeline.ValidationPolicyOverride {
if in == nil {
return nil
}
out := *in
if in.ProducerStructuralFailure != nil {
value := *in.ProducerStructuralFailure
out.ProducerStructuralFailure = &value
}
if in.SemanticRejection != nil {
value := *in.SemanticRejection
out.SemanticRejection = &value
}
if in.ValidatorFailure != nil {
value := *in.ValidatorFailure
out.ValidatorFailure = &value
}
return &out
}
func cloneValidatorOverride(in pipeline.ValidatorOverride) pipeline.ValidatorOverride {
out := pipeline.ValidatorOverride{Set: in.Set}
if len(in.Validators) > 0 {

View File

@@ -37,6 +37,7 @@ type FilePromptKitLocalBackendConfig struct {
type FilePipelineProfile struct {
LLMProfile *string `yaml:"llm_profile,omitempty"`
StructuredOutputRepairAttempts *int `yaml:"structured_output_repair_attempts,omitempty"`
ValidationPolicy *pipeline.ValidationPolicyOverride `yaml:"validation_policy,omitempty"`
Input fileModuleBinding `yaml:"input"`
Chunk *fileModuleBinding `yaml:"chunk,omitempty"`
Artifacts map[string]FileArtifactLaneProfile `yaml:"artifacts,omitempty"`
@@ -55,12 +56,19 @@ func (p *FilePipelineProfile) UnmarshalYAML(node *yaml.Node) error {
type plainFilePipelineProfile FilePipelineProfile
var decoded plainFilePipelineProfile
seen, err := decodeKnownMapping(node, &decoded, map[string]struct{}{
"llm_profile": {}, "structured_output_repair_attempts": {}, "input": {}, "chunk": {}, "artifacts": {}, "steps": {}, "output": {}, "references": {},
"llm_profile": {}, "structured_output_repair_attempts": {}, "validation_policy": {}, "input": {}, "chunk": {}, "artifacts": {}, "steps": {}, "output": {}, "references": {},
}, "pipeline profile")
if err != nil {
return err
}
*p = FilePipelineProfile(decoded)
if validationPolicyNode, ok := mappingValue(node, "validation_policy"); ok {
policy, err := parseValidationPolicy(validationPolicyNode, "pipeline profile")
if err != nil {
return err
}
p.ValidationPolicy = policy
}
_, p.artifactsSet = seen["artifacts"]
_, p.stepsSet = seen["steps"]
_, p.llmProfileSet = seen["llm_profile"]
@@ -154,6 +162,7 @@ type fileModuleBinding struct {
Module string
LLMProfile string
StructuredOutputRepairAttempts *int
ValidationPolicy *pipeline.ValidationPolicyOverride
Retries int
Options map[string]any
References map[string]fileReferenceSource
@@ -250,9 +259,14 @@ func (b *fileModuleBinding) UnmarshalYAML(node *yaml.Node) error {
b.Module = strings.TrimSpace(module)
return nil
case yaml.MappingNode:
seen := make(map[string]struct{}, len(node.Content)/2)
for i := 0; i < len(node.Content); i += 2 {
keyNode := node.Content[i]
valueNode := node.Content[i+1]
if _, exists := seen[keyNode.Value]; exists {
return fmt.Errorf("module binding field %q is duplicated", keyNode.Value)
}
seen[keyNode.Value] = struct{}{}
switch keyNode.Value {
case "module":
var module string
@@ -275,6 +289,12 @@ func (b *fileModuleBinding) UnmarshalYAML(node *yaml.Node) error {
return err
}
b.StructuredOutputRepairAttempts = attempts
case "validation_policy":
policy, err := parseValidationPolicy(valueNode, "module binding")
if err != nil {
return err
}
b.ValidationPolicy = policy
case "retries":
var retries int
if err := valueNode.Decode(&retries); err != nil {
@@ -318,6 +338,7 @@ func (b fileModuleBinding) toPipelineBinding() pipeline.ModuleBinding {
Module: strings.TrimSpace(b.Module),
LLMProfile: strings.TrimSpace(b.LLMProfile),
StructuredOutputRepairAttempts: cloneStructuredOutputRepairAttempts(b.StructuredOutputRepairAttempts),
ValidationPolicy: cloneValidationPolicyOverride(b.ValidationPolicy),
Retries: b.Retries,
Options: cloneOptions(b.Options),
References: fileReferenceSourcesToPipeline(b.References),
@@ -325,6 +346,51 @@ func (b fileModuleBinding) toPipelineBinding() pipeline.ModuleBinding {
}
}
func mappingValue(node *yaml.Node, key string) (*yaml.Node, bool) {
for i := 0; i < len(node.Content); i += 2 {
if node.Content[i].Value == key {
return node.Content[i+1], true
}
}
return nil, false
}
func parseValidationPolicy(node *yaml.Node, context string) (*pipeline.ValidationPolicyOverride, error) {
if node == nil || node.Tag == "!!null" || node.Kind != yaml.MappingNode {
return nil, fmt.Errorf("%s validation_policy must be an object", context)
}
policy := &pipeline.ValidationPolicyOverride{}
seen := make(map[string]struct{}, len(node.Content)/2)
for i := 0; i < len(node.Content); i += 2 {
key := node.Content[i].Value
value := node.Content[i+1]
if _, exists := seen[key]; exists {
return nil, fmt.Errorf("%s validation_policy field %q is duplicated", context, key)
}
seen[key] = struct{}{}
if value.Tag == "!!null" || value.Kind != yaml.ScalarNode || value.Tag != "!!str" {
return nil, fmt.Errorf("%s validation_policy.%s must be a string", context, key)
}
switch key {
case "producer_structural_failure":
value := pipeline.ProducerStructuralFailureAction(value.Value)
policy.ProducerStructuralFailure = &value
case "semantic_rejection":
value := pipeline.SemanticRejectionAction(value.Value)
policy.SemanticRejection = &value
case "validator_failure":
value := pipeline.ValidatorFailureAction(value.Value)
policy.ValidatorFailure = &value
default:
return nil, fmt.Errorf("field %s not found in %s validation_policy", key, context)
}
}
if err := policy.Validate(); err != nil {
return nil, fmt.Errorf("%s validation_policy: %w", context, err)
}
return policy, nil
}
func validateStructuredOutputRepairAttemptsNode(node *yaml.Node, context string) error {
if node.Kind != yaml.MappingNode {
return fmt.Errorf("%s must be an object", context)
@@ -573,6 +639,7 @@ func (c *Config) applyFileConfigWithLookup(fileCfg FileConfig, lookup func(strin
ID: pipelineID,
LLMProfile: llmProfile,
StructuredOutputRepairAttempts: cloneStructuredOutputRepairAttempts(filePipeline.StructuredOutputRepairAttempts),
ValidationPolicy: cloneValidationPolicyOverride(filePipeline.ValidationPolicy),
Input: filePipeline.Input.toPipelineBinding(),
Artifacts: make(map[string]pipeline.ArtifactLaneProfile, len(filePipeline.Artifacts)),
References: fileReferenceSourcesToPipeline(filePipeline.References),

View File

@@ -32,6 +32,7 @@ func (e EffectiveConfig) RedactedResolvedPipelinePayload() pipeline.ResolvedPipe
func cloneResolvedPipeline(in pipeline.ResolvedPipeline) pipeline.ResolvedPipeline {
out := in
out.ConfiguredValidationPolicy = cloneValidationPolicyOverride(in.ConfiguredValidationPolicy)
out.Input = redactBinding(cloneModuleBinding(in.Input))
out.Chunk = redactBinding(cloneModuleBinding(in.Chunk))
out.ChunkReferences = pipeline.CloneReferenceTarget(in.ChunkReferences)

View File

@@ -225,6 +225,39 @@ func TestRedactedResolvedPipelinePayloadHandlesTypedOptionContainers(t *testing.
}
}
func TestRedactedEffectiveConfigPayloadOwnsValidationPolicies(t *testing.T) {
semantic := pipeline.SemanticRejectionRejectOutput
validator := pipeline.ValidatorFailureFailRun
configured := &pipeline.ValidationPolicyOverride{SemanticRejection: &semantic, ValidatorFailure: &validator}
effective := EffectiveConfig{
Config: Config{Pipelines: map[string]pipeline.PipelineProfile{
"main": {ValidationPolicy: configured},
}},
ResolvedPipeline: pipeline.ResolvedPipeline{
ConfiguredValidationPolicy: configured,
ChunkValidationPolicy: pipeline.ValidationPolicy{
ProducerStructuralFailure: pipeline.ProducerStructuralFailureFailRun,
SemanticRejection: pipeline.SemanticRejectionRejectOutput,
ValidatorFailure: pipeline.ValidatorFailureFailRun,
},
},
}
payload := effective.RedactedSummaryPayload().(EffectiveConfig)
encoded, err := json.Marshal(payload)
if err != nil {
t.Fatal(err)
}
if !strings.Contains(string(encoded), `"configured_validation_policy":{"semantic_rejection":"reject_output","validator_failure":"fail_run"}`) || !strings.Contains(string(encoded), `"chunk_validation_policy":{"producer_structural_failure":"fail_run","semantic_rejection":"reject_output","validator_failure":"fail_run"}`) {
t.Fatalf("redacted payload omitted validation policy: %s", encoded)
}
*payload.Config.Pipelines["main"].ValidationPolicy.SemanticRejection = pipeline.SemanticRejectionFailRun
*payload.ResolvedPipeline.ConfiguredValidationPolicy.ValidatorFailure = pipeline.ValidatorFailureWarnContinue
if *effective.Config.Pipelines["main"].ValidationPolicy.SemanticRejection != pipeline.SemanticRejectionRejectOutput || *effective.ResolvedPipeline.ConfiguredValidationPolicy.ValidatorFailure != pipeline.ValidatorFailureFailRun {
t.Fatal("redacted payload aliases validation policy")
}
}
func redactionTestBinding(name string) pipeline.ModuleBinding {
return pipeline.ModuleBinding{
Module: "safe-" + name,

View File

@@ -119,6 +119,11 @@ func validatePipelineProfiles(profiles map[string]pipeline.PipelineProfile) erro
if err := validateStructuredOutputRepairAttempts(fmt.Sprintf("pipeline %q", id), profile.StructuredOutputRepairAttempts); err != nil {
return err
}
if profile.ValidationPolicy != nil {
if err := profile.ValidationPolicy.Validate(); err != nil {
return fmt.Errorf("pipeline %q validation_policy: %w", id, err)
}
}
if err := validateBinding(id, "", "input", profile.Input, false); err != nil {
return err
}
@@ -198,6 +203,16 @@ func validateBinding(
binding pipeline.ModuleBinding,
referencesAllowed bool,
) error {
if binding.ValidationPolicy != nil {
switch slot {
case "chunk", "extract", "merge", "normalize":
default:
return fmt.Errorf("%s validation_policy is not supported", referenceContext(pipelineID, laneID, slot))
}
if err := binding.ValidationPolicy.Validate(); err != nil {
return fmt.Errorf("%s validation_policy: %w", referenceContext(pipelineID, laneID, slot), err)
}
}
if err := validateStructuredOutputRepairAttempts(referenceContext(pipelineID, laneID, slot), binding.StructuredOutputRepairAttempts); err != nil {
return err
}
@@ -255,6 +270,9 @@ func validateValidatorOverride(pipelineID string, laneID string, slot string, ov
if validator.Validators.Set {
return fmt.Errorf("%s nested validators are not supported", context)
}
if validator.ValidationPolicy != nil {
return fmt.Errorf("%s validation_policy is not supported", context)
}
if validator.Retries != 0 {
return fmt.Errorf("%s retries are not supported", context)
}

View File

@@ -0,0 +1,97 @@
package config
import (
"strings"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
func TestValidationPolicyFileConfigurationIsStrictAndPresenceAware(t *testing.T) {
const valid = `version: 4
pipelines:
main:
validation_policy:
producer_structural_failure: reject_output
semantic_rejection: fail_run
input: seriatim
chunk:
module: generic
validation_policy:
validator_failure: fail_run
artifacts:
lane:
extract:
module: extract
validation_policy:
semantic_rejection: reject_output
`
cfg := applyFileConfig(t, valid)
profile := cfg.Pipelines["main"]
if profile.ValidationPolicy == nil || profile.ValidationPolicy.ProducerStructuralFailure == nil || *profile.ValidationPolicy.ProducerStructuralFailure != pipeline.ProducerStructuralFailureRejectOutput || profile.ValidationPolicy.SemanticRejection == nil || *profile.ValidationPolicy.SemanticRejection != pipeline.SemanticRejectionFailRun || profile.ValidationPolicy.ValidatorFailure != nil {
t.Fatalf("pipeline validation policy = %#v", profile.ValidationPolicy)
}
if profile.Chunk.ValidationPolicy == nil || profile.Chunk.ValidationPolicy.ValidatorFailure == nil || *profile.Chunk.ValidationPolicy.ValidatorFailure != pipeline.ValidatorFailureFailRun {
t.Fatalf("chunk validation policy = %#v", profile.Chunk.ValidationPolicy)
}
lane := profile.Artifacts["lane"]
if lane.Extract.ValidationPolicy == nil || lane.Extract.ValidationPolicy.SemanticRejection == nil || *lane.Extract.ValidationPolicy.SemanticRejection != pipeline.SemanticRejectionRejectOutput {
t.Fatalf("extract validation policy = %#v", lane.Extract.ValidationPolicy)
}
for _, test := range []struct {
name string
yaml string
}{
{"null object", strings.Replace(valid, "validation_policy:\n producer_structural_failure: reject_output\n semantic_rejection: fail_run", "validation_policy: null", 1)},
{"null field", strings.Replace(valid, "semantic_rejection: fail_run", "semantic_rejection: null", 1)},
{"unknown field", strings.Replace(valid, "semantic_rejection: fail_run", "unknown: fail_run", 1)},
{"duplicate field", strings.Replace(valid, "semantic_rejection: fail_run", "semantic_rejection: fail_run\n semantic_rejection: reject_output", 1)},
{"invalid enum", strings.Replace(valid, "semantic_rejection: fail_run", "semantic_rejection: continue", 1)},
} {
t.Run(test.name, func(t *testing.T) {
if _, err := ParseFileConfigYAML([]byte(test.yaml)); err == nil {
t.Fatal("ParseFileConfigYAML() error = nil, want strict validation-policy rejection")
}
})
}
}
func TestValidationPolicyPlacementRules(t *testing.T) {
policy := &pipeline.ValidationPolicyOverride{}
semantic := pipeline.SemanticRejectionRejectOutput
policy.SemanticRejection = &semantic
base := pipeline.PipelineProfile{
ID: "main",
Input: pipeline.Binding("input"),
Artifacts: map[string]pipeline.ArtifactLaneProfile{
"lane": {Extract: pipeline.Binding("extract")},
},
}
for _, test := range []struct {
name string
mutate func(*pipeline.PipelineProfile)
}{
{"input", func(profile *pipeline.PipelineProfile) { profile.Input.ValidationPolicy = policy }},
{"output", func(profile *pipeline.PipelineProfile) {
profile.Output = pipeline.Binding("output")
profile.Output.ValidationPolicy = policy
}},
{"validator", func(profile *pipeline.PipelineProfile) {
lane := profile.Artifacts["lane"]
lane.Extract.Validators = pipeline.ValidatorOverride{Set: true, Validators: []pipeline.ModuleBinding{{Module: "validator", ValidationPolicy: policy}}}
profile.Artifacts["lane"] = lane
}},
} {
t.Run(test.name, func(t *testing.T) {
profile := base
profile.Artifacts = map[string]pipeline.ArtifactLaneProfile{"lane": base.Artifacts["lane"]}
test.mutate(&profile)
cfg := Default()
cfg.Pipelines = map[string]pipeline.PipelineProfile{"main": profile}
if err := cfg.Validate(); err == nil || !strings.Contains(err.Error(), "validation_policy") {
t.Fatalf("Config.Validate() error = %v, want placement rejection", err)
}
})
}
}