Add ConfigKit version 5 document boundary

This commit is contained in:
2026-09-13 16:18:30 +00:00
parent c403a38b50
commit b822e7f510
7 changed files with 398 additions and 0 deletions

View File

@@ -0,0 +1,122 @@
package config
import "gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
// Document is the version 5 configuration shape decoded by ConfigKit. It is
// deliberately separate from Config so YAML presence and composition concerns
// do not reach runtime pipeline types.
type Document struct {
Version string `yaml:"version"`
PromptKit *PromptKitDocument `yaml:"promptkit,omitempty"`
Pipelines map[string]PipelineDocument `yaml:"pipelines,omitempty"`
Concurrency *ConcurrencyDocument `yaml:"concurrency,omitempty"`
Output *OutputDocument `yaml:"output,omitempty"`
Cache *CacheDocument `yaml:"cache,omitempty"`
Debug *DebugDocument `yaml:"debug,omitempty"`
}
type PromptKitDocument struct {
ProfileDir *string `yaml:"profile_dir,omitempty"`
ProfileFile *string `yaml:"profile_file,omitempty"`
LocalBackend *PromptKitLocalBackendDocument `yaml:"local_backend,omitempty"`
}
type PromptKitLocalBackendDocument struct {
Endpoint *string `yaml:"endpoint,omitempty"`
ConcurrencyLimit *int `yaml:"concurrency_limit,omitempty"`
}
type PipelineDocument struct {
LLMProfile *string `yaml:"llm_profile,omitempty"`
StructuredOutputRepairAttempts *int `yaml:"structured_output_repair_attempts,omitempty"`
ValidationPolicy *ValidationPolicyDocument `yaml:"validation_policy,omitempty"`
Input BindingDocument `yaml:"input"`
Chunk *BindingDocument `yaml:"chunk,omitempty"`
Artifacts map[string]ArtifactLaneDocument `yaml:"artifacts,omitempty"`
Steps []PipelineStepDocument `yaml:"steps,omitempty"`
Output *BindingDocument `yaml:"output,omitempty"`
References map[string]ReferenceDocument `yaml:"references,omitempty"`
}
type PipelineStepDocument struct {
ID string `yaml:"id"`
Artifacts map[string]ArtifactLaneDocument `yaml:"artifacts"`
References map[string]ReferenceDocument `yaml:"references,omitempty"`
}
type ArtifactLaneDocument struct {
Extract BindingDocument `yaml:"extract"`
Merge *BindingDocument `yaml:"merge,omitempty"`
Normalize *BindingDocument `yaml:"normalize,omitempty"`
Validators []ValidatorDocument `yaml:"validators,omitempty"`
References map[string]ReferenceDocument `yaml:"references,omitempty"`
}
// BindingDocument represents a producer binding. ValidatorDocument is a
// deliberately finite subset so nested validator-only fields are rejected by
// ConfigKit's strict decoder.
type BindingDocument struct {
Module string `yaml:"module"`
LLMProfile *string `yaml:"llm_profile,omitempty"`
StructuredOutputRepairAttempts *int `yaml:"structured_output_repair_attempts,omitempty"`
ValidationPolicy *ValidationPolicyDocument `yaml:"validation_policy,omitempty"`
Retries int `yaml:"retries,omitempty"`
Options map[string]any `yaml:"options,omitempty"`
References map[string]ReferenceDocument `yaml:"references,omitempty"`
Validators []ValidatorDocument `yaml:"validators,omitempty"`
}
type ValidatorDocument struct {
Module string `yaml:"module"`
LLMProfile *string `yaml:"llm_profile,omitempty"`
StructuredOutputRepairAttempts *int `yaml:"structured_output_repair_attempts,omitempty"`
Retries int `yaml:"retries,omitempty"`
Options map[string]any `yaml:"options,omitempty"`
}
// ReferenceDocument is the explicit version 5 union. Later document
// validation establishes which locations permit generated references and
// requires exactly one populated branch.
type ReferenceDocument struct {
Path *string `yaml:"path,omitempty"`
Artifact *ArtifactReferenceDocument `yaml:"artifact,omitempty"`
}
type ArtifactReferenceDocument struct {
Step string `yaml:"step"`
Lane string `yaml:"lane"`
}
type ValidationPolicyDocument struct {
ProducerStructuralFailure *pipeline.ProducerStructuralFailureAction `yaml:"producer_structural_failure,omitempty"`
SemanticRejection *pipeline.SemanticRejectionAction `yaml:"semantic_rejection,omitempty"`
ValidatorFailure *pipeline.ValidatorFailureAction `yaml:"validator_failure,omitempty"`
}
type ConcurrencyDocument struct {
TotalLLM *int `yaml:"total_llm,omitempty"`
StageWorkers map[string]int `yaml:"stage_workers,omitempty"`
}
type OutputDocument struct {
Directory *string `yaml:"directory,omitempty"`
}
type CacheDocument struct {
ChunkPlans *ChunkPlanCacheDocument `yaml:"chunk_plans,omitempty"`
Checkpoints *CheckpointCacheDocument `yaml:"checkpoints,omitempty"`
}
type ChunkPlanCacheDocument struct {
Directory *string `yaml:"directory,omitempty"`
Mode *string `yaml:"mode,omitempty"`
}
type CheckpointCacheDocument struct {
Enabled *bool `yaml:"enabled,omitempty"`
Directory *string `yaml:"directory,omitempty"`
}
type DebugDocument struct {
Directory *string `yaml:"directory,omitempty"`
}

View File

@@ -0,0 +1,154 @@
package config
import (
"errors"
"strings"
"testing"
configkit "gitea.maximumdirect.net/eric/ConfigKit"
)
func TestDocumentLoadAcceptsVersion5AndCanonicalShapes(t *testing.T) {
t.Parallel()
for _, source := range []string{
`version: 5
pipelines:
session:
input:
module: seriatim
references:
party:
path: ./party.txt
steps:
- id: describe
artifacts:
spells:
extract:
module: dnd/spells
validators:
- module: generic/valid_json
options:
strict: true
- id: use-artifact
references:
spells:
artifact:
step: describe
lane: spells
artifacts:
locations:
extract:
module: dnd/locations
`,
`version: "5"
pipelines:
session:
input:
module: seriatim
`,
} {
loaded, err := loadDocumentSource(configkit.Bytes("document.yml", []byte(source)), LoadOptions{})
if err != nil {
t.Fatalf("loadDocumentSource() error = %v", err)
}
profile, ok := loaded.Config.Pipelines["session"]
if !ok || profile.Input.Module != "seriatim" {
t.Fatalf("pipeline = %#v", profile)
}
}
}
func TestDocumentLoadRejectsUnsupportedVersionsBeforeDocumentDecoding(t *testing.T) {
t.Parallel()
tests := []struct {
name string
source string
code configkit.Code
}{
{name: "missing", source: "unknown: value\n", code: configkit.CodeVersionError},
{name: "null", source: "version: null\nunknown: value\n", code: configkit.CodeVersionError},
{name: "version four", source: "version: 4\nunknown: value\n", code: configkit.CodeVersionError},
{name: "unsupported", source: "version: 6\nunknown: value\n", code: configkit.CodeVersionError},
{name: "noninteger", source: "version: 5.0\n", code: configkit.CodeVersionType},
}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
_, err := loadDocumentSource(configkit.Bytes("document.yml", []byte(test.source)), LoadOptions{})
var loadError *configkit.LoadError
if !errors.As(err, &loadError) {
t.Fatalf("error = %v, want ConfigKit load error", err)
}
diagnostics := loadError.Diagnostics()
if len(diagnostics) != 1 || diagnostics[0].Code != test.code || diagnostics[0].Path.String() != "/version" {
t.Fatalf("diagnostics = %#v", diagnostics)
}
if strings.Contains(diagnostics[0].Message, "unknown") {
t.Fatalf("document decoding ran before version validation: %#v", diagnostics)
}
})
}
}
func TestDocumentLoadRejectsShorthandAndUnknownFields(t *testing.T) {
t.Parallel()
tests := []struct {
name string
source string
code configkit.Code
path string
}{
{
name: "binding shorthand",
source: "version: 5\npipelines:\n session:\n input: seriatim\n",
code: configkit.CodeDecodeType,
path: "/pipelines/session/input",
},
{
name: "validator nested producer field",
source: "version: 5\npipelines:\n session:\n input:\n module: seriatim\n validators:\n - module: generic/valid_json\n validators: []\n",
code: configkit.CodeDecodeUnknownField,
path: "/pipelines/session/input/validators/0/validators",
},
{
name: "unknown field",
source: "version: 5\npipelines:\n session:\n input:\n module: seriatim\n unknown: true\n",
code: configkit.CodeDecodeUnknownField,
path: "/pipelines/session/input/unknown",
},
}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
_, err := loadDocumentSource(configkit.Bytes("document.yml", []byte(test.source)), LoadOptions{})
var loadError *configkit.LoadError
if !errors.As(err, &loadError) {
t.Fatalf("error = %v, want ConfigKit load error", err)
}
diagnostics := loadError.Diagnostics()
if len(diagnostics) != 1 || diagnostics[0].Code != test.code || diagnostics[0].Path.String() != test.path {
t.Fatalf("diagnostics = %#v", diagnostics)
}
})
}
}
func TestDocumentDefinitionReturnsIndependentDefaults(t *testing.T) {
t.Parallel()
first, err := loadDocumentSource(configkit.Bytes("first.yml", []byte("version: 5\n")), LoadOptions{})
if err != nil {
t.Fatal(err)
}
first.Config.Pipelines["changed"] = PipelineDocument{}
first.Config.Concurrency.StageWorkers["extract"] = 3
second, err := loadDocumentSource(configkit.Bytes("second.yml", []byte("version: 5\n")), LoadOptions{})
if err != nil {
t.Fatal(err)
}
if len(second.Config.Pipelines) != 0 || len(second.Config.Concurrency.StageWorkers) != 0 {
t.Fatalf("defaults aliased across loads: %#v", second.Config)
}
}

View File

@@ -0,0 +1,60 @@
package config
import (
configkit "gitea.maximumdirect.net/eric/ConfigKit"
)
// LoadOptions contains configuration selections supplied by an application
// boundary. It is intentionally narrow: configuration discovery and CLI flag
// parsing remain outside this package.
type LoadOptions struct {
Profile string
Overrides []configkit.Override
}
// loadDocument is the private ConfigKit load boundary under construction.
// Production commands continue to use the existing version 4 loader until the
// runtime conversion and command wiring are complete.
func loadDocument(path string, options LoadOptions) (*configkit.Result[Document], error) {
return loadDocumentSource(configkit.File(path), options)
}
func loadDocumentSource(source configkit.Source, options LoadOptions) (*configkit.Result[Document], error) {
return configkit.Load(source, configkit.Options[Document]{
Definition: documentDefinition(),
Profile: options.Profile,
Overrides: options.Overrides,
})
}
func documentDefinition() configkit.Definition[Document] {
return configkit.Definition[Document]{
Defaults: func() Document {
return Document{
Pipelines: map[string]PipelineDocument{},
Concurrency: &ConcurrencyDocument{
StageWorkers: map[string]int{},
},
}
},
Version: &configkit.VersionRule{
Path: configkit.Keys("version"),
Check: validateDocumentVersion,
},
}
}
func validateDocumentVersion(version configkit.Version, validation *configkit.Validation) error {
if !version.Present || version.Null {
validation.Error(configkit.Keys("version"), "configuration version is required")
return nil
}
if version.Text == "4" {
validation.Error(configkit.Keys("version"), "configuration version 4 is no longer supported; migrate to version 5")
return nil
}
if version.Text != "5" {
validation.Error(configkit.Keys("version"), "unsupported configuration version")
}
return nil
}