Add ConfigKit version 5 document boundary

2026-09-13 16:18:30 +00:00
parent c403a38b50
commit b822e7f510
7 changed files with 398 additions and 0 deletions
--- a/internal/core/config/document.go
+++ b/internal/core/config/document.go
@@ -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"`
+}