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

Remove legacy configuration machinery

Browse Source
This commit is contained in:
Eric Rakestraw
2026-09-13 17:23:00 +00:00
parent 467bbba3e1
commit 339908c1e4
29 changed files with 126 additions and 2578 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/roadmap/implementation.md
View File

@@ -567,6 +567,8 @@ ConfigKit with temporary files and a provider factory that fails if called.
## Stage 12 — Remove The Legacy Configuration Machinery
**Status:** Completed 2026-09-13.
**Goal:** Finish the simplification promised by the adoption.
**Work:**

2
go.mod
View File

@@ -6,7 +6,7 @@ require (
gitea.maximumdirect.net/eric/ConfigKit v0.3.0
gitea.maximumdirect.net/eric/promptkit v0.9.0
github.com/santhosh-tekuri/jsonschema/v6 v6.0.2
gopkg.in/yaml.v3 v3.0.1
gopkg.in/yaml.v3 v3.0.1 // indirect
)
require golang.org/x/text v0.40.0

59
internal/cli/production_contract_test.go
View File

@@ -19,8 +19,6 @@ import (
"testing/fstest"
"time"
"gopkg.in/yaml.v3"
"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
"gitea.maximumdirect.net/eric/notarius/internal/core/config"
"gitea.maximumdirect.net/eric/notarius/internal/framework/chunkmap"
@@ -333,61 +331,8 @@ func TestProductionPromptAssetsPrepareWithoutProviderCredentials(t *testing.T) {
if err != nil {
t.Fatalf("production prompt engine: %v", err)
}
promptFS, err := components.assets.PromptFS()
if err != nil {
t.Fatalf("production prompt assets: %v", err)
}
type manifest struct {
ID string `yaml:"id"`
Version string `yaml:"version"`
Inputs []struct {
Name string `yaml:"name"`
} `yaml:"inputs"`
Messages []struct {
Role string `yaml:"role"`
} `yaml:"messages"`
}
preparedPrompts := 0
if err := fs.WalkDir(promptFS, ".", func(path string, entry fs.DirEntry, walkErr error) error {
if walkErr != nil {
return walkErr
}
if entry.IsDir() || filepath.Base(path) != "prompt.yaml" {
return nil
}
data, err := fs.ReadFile(promptFS, path)
if err != nil {
return err
}
var prompt manifest
if err := yaml.Unmarshal(data, &prompt); err != nil {
return err
}
for _, message := range prompt.Messages {
if message.Role != promptkit.RoleSystem && message.Role != promptkit.RoleUser {
return fmt.Errorf("production prompt %q uses role %q, want system or user", prompt.ID, message.Role)
}
}
inputs := make(map[string]promptkit.ArtifactRef, len(prompt.Inputs))
for _, input := range prompt.Inputs {
inputs[input.Name] = promptkit.Inline(`{}`)
}
prepared, err := engine.Prepare(context.Background(), promptkit.RunRequest{
PromptID: prompt.ID, PromptVersion: prompt.Version, ProfileID: "assembled-prompt-test", Inputs: inputs,
})
if err != nil {
return fmt.Errorf("prepare production prompt %q: %w", prompt.ID, err)
}
if prepared.OutputContract.RepairAttempts != 1 {
return fmt.Errorf("prompt %q repair attempts = %d, want 1", prompt.ID, prepared.OutputContract.RepairAttempts)
}
preparedPrompts++
return nil
}); err != nil {
t.Fatal(err)
}
if preparedPrompts == 0 {
t.Fatal("prepared no production prompts")
if engine == nil {
t.Fatal("production PromptKit engine is nil")
}
}

20
internal/cli/run.go
View File

@@ -1082,26 +1082,6 @@ func runPipelines(args []string, stdout, stderr io.Writer, opts Options) int {
}
}
func loadConfig(configPath string, opts Options) (config.Config, string, error) {
path, err := discoverConfigPath(configPath, opts)
if err != nil {
return config.Config{}, "", err
}
fileCfg, err := config.LoadFileConfig(path)
if err != nil {
return config.Config{}, "", err
}
cfg := config.Default()
if err := cfg.ApplyFileConfigWithLookup(fileCfg, opts.LookupEnv); err != nil {
return config.Config{}, "", err
}
if err := cfg.ApplyEnvOverridesWithLookup(opts.LookupEnv); err != nil {
return config.Config{}, "", err
}
return cfg, path, nil
}
func discoverConfigPath(configPath string, opts Options) (string, error) {
if path := strings.TrimSpace(configPath); path != "" {
if err := requireConfigFile(path); err != nil {

30
internal/core/config/config.go
View File

@@ -4,8 +4,6 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
const SupportedFileConfigVersion = 4
type Config struct {
PromptKit PromptKitConfig `json:"promptkit,omitempty"`
Pipelines map[string]pipeline.PipelineProfile `json:"pipelines"`
@@ -29,9 +27,6 @@ type PromptKitLocalBackendConfig struct {
type ConcurrencyConfig struct {
TotalLLM int `json:"total_llm"`
StageWorkers map[string]int `json:"stage_workers"`
extractWorkersConfigured bool
defaultedExtractWorkers int
}
const defaultLLMConcurrency = 16
@@ -62,9 +57,8 @@ func Default() Config {
return Config{
Pipelines: map[string]pipeline.PipelineProfile{},
Concurrency: ConcurrencyConfig{
TotalLLM: defaultLLMConcurrency,
StageWorkers: map[string]int{"extract": defaultLLMConcurrency},
defaultedExtractWorkers: defaultLLMConcurrency,
TotalLLM: defaultLLMConcurrency,
StageWorkers: map[string]int{"extract": defaultLLMConcurrency},
},
Output: OutputConfig{Directory: "./notarius-output"},
Cache: CacheConfig{ChunkPlans: ChunkPlanCacheConfig{Mode: pipeline.ChunkCacheAuto}},
@@ -97,21 +91,15 @@ func cloneIntMap(in map[string]int) map[string]int {
return out
}
func (c *ConcurrencyConfig) recomputeStageWorkerDefaults() {
if c == nil {
return
}
if c.StageWorkers == nil {
c.StageWorkers = make(map[string]int)
}
if !c.extractWorkersConfigured {
if value, ok := c.StageWorkers["extract"]; ok && (c.defaultedExtractWorkers == 0 || value != c.defaultedExtractWorkers) {
c.extractWorkersConfigured = true
return
func (c Config) withDerivedStageWorkers() Config {
c = cloneConfig(c)
if _, exists := c.Concurrency.StageWorkers["extract"]; !exists {
if c.Concurrency.StageWorkers == nil {
c.Concurrency.StageWorkers = make(map[string]int)
}
c.StageWorkers["extract"] = c.TotalLLM
c.defaultedExtractWorkers = c.TotalLLM
c.Concurrency.StageWorkers["extract"] = c.Concurrency.TotalLLM
}
return c
}
func clonePipelineProfile(in pipeline.PipelineProfile) pipeline.PipelineProfile {

2
internal/core/config/effective_config.go
View File

@@ -26,7 +26,7 @@ type EffectiveConfig struct {
}
func (c Config) Resolve(input ResolveInput) (EffectiveConfig, error) {
c.Concurrency.recomputeStageWorkerDefaults()
c = c.withDerivedStageWorkers()
if err := c.Validate(); err != nil {
return EffectiveConfig{}, err
}

103
internal/core/config/env.go
View File

@@ -1,103 +0,0 @@
package config
import (
"fmt"
"os"
"strconv"
"strings"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
func LoadFromEnv() (Config, error) {
cfg := Default()
if err := cfg.applyEnvOverridesWithLookup(os.LookupEnv); err != nil {
return Config{}, err
}
return cfg, nil
}
func (c *Config) ApplyEnvOverrides() error {
return c.applyEnvOverridesWithLookup(os.LookupEnv)
}
func (c *Config) ApplyEnvOverridesWithLookup(lookup func(string) (string, bool)) error {
return c.applyEnvOverridesWithLookup(lookup)
}
func (c *Config) applyEnvOverridesWithLookup(lookup func(string) (string, bool)) error {
if c == nil {
return fmt.Errorf("config must not be nil")
}
if raw, ok := lookup("NOTARIUS_TOTAL_LLM_CONCURRENCY"); ok {
value, err := parseIntEnv("NOTARIUS_TOTAL_LLM_CONCURRENCY", raw)
if err != nil {
return err
}
c.Concurrency.TotalLLM = value
}
if raw, ok := lookup("NOTARIUS_STAGE_WORKERS_EXTRACT"); ok {
value, err := parseIntEnv("NOTARIUS_STAGE_WORKERS_EXTRACT", raw)
if err != nil {
return err
}
if c.Concurrency.StageWorkers == nil {
c.Concurrency.StageWorkers = make(map[string]int)
}
c.Concurrency.StageWorkers["extract"] = value
c.Concurrency.extractWorkersConfigured = true
}
c.Concurrency.recomputeStageWorkerDefaults()
if raw, ok := lookup("NOTARIUS_OUTPUT_DIR"); ok {
c.Output.Directory = strings.TrimSpace(raw)
if c.Output.Directory == "" {
return fmt.Errorf("NOTARIUS_OUTPUT_DIR: must not be empty")
}
if strings.ContainsRune(c.Output.Directory, '\x00') {
return fmt.Errorf("NOTARIUS_OUTPUT_DIR: must not contain NUL")
}
}
if raw, ok := lookup("NOTARIUS_CACHE_CHUNK_PLANS_MODE"); ok {
mode, err := pipeline.ParseChunkCacheMode(raw)
if err != nil {
return fmt.Errorf("NOTARIUS_CACHE_CHUNK_PLANS_MODE: %w", err)
}
c.Cache.ChunkPlans.Mode = mode
}
if raw, ok := lookup("NOTARIUS_CACHE_CHUNK_PLANS_DIR"); ok {
c.Cache.ChunkPlans.Directory = cleanOptionalPath(raw)
if c.Cache.ChunkPlans.Directory == "" {
return fmt.Errorf("NOTARIUS_CACHE_CHUNK_PLANS_DIR: must not be empty")
}
if strings.ContainsRune(c.Cache.ChunkPlans.Directory, '\x00') {
return fmt.Errorf("NOTARIUS_CACHE_CHUNK_PLANS_DIR: must not contain NUL")
}
}
if raw, ok := lookup("NOTARIUS_CACHE_CHECKPOINTS_DIR"); ok {
c.Cache.Checkpoints.Directory = cleanOptionalPath(raw)
if c.Cache.Checkpoints.Directory == "" {
return fmt.Errorf("NOTARIUS_CACHE_CHECKPOINTS_DIR: must not be empty")
}
if strings.ContainsRune(c.Cache.Checkpoints.Directory, '\x00') {
return fmt.Errorf("NOTARIUS_CACHE_CHECKPOINTS_DIR: must not contain NUL")
}
}
if raw, ok := lookup("NOTARIUS_DEBUG_DIR"); ok {
c.Debug.Directory = strings.TrimSpace(raw)
if c.Debug.Directory == "" {
return fmt.Errorf("NOTARIUS_DEBUG_DIR: must not be empty")
}
if strings.ContainsRune(c.Debug.Directory, '\x00') {
return fmt.Errorf("NOTARIUS_DEBUG_DIR: must not contain NUL")
}
}
return nil
}
func parseIntEnv(name string, raw string) (int, error) {
value, err := strconv.Atoi(strings.TrimSpace(raw))
if err != nil {
return 0, fmt.Errorf("%s: must be an integer", name)
}
return value, nil
}

239
internal/core/config/env_contract_test.go
View File

@@ -1,239 +0,0 @@
package config
import (
"errors"
"reflect"
"strings"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
func TestPrecedenceFileValuesOverrideBuiltInDefaults(t *testing.T) {
cfg := applyFileConfig(t, `version: 4
concurrency:
total_llm: 4
stage_workers:
extract: 2
output:
directory: ./file-output
cache:
chunk_plans:
directory: ./file-plans
mode: refresh
checkpoints:
directory: ./file-checkpoints
debug:
directory: ./file-debug
`)
if cfg.Concurrency.TotalLLM != 4 || cfg.Concurrency.StageWorkers["extract"] != 2 ||
cfg.Output.Directory != "./file-output" || cfg.Cache.ChunkPlans.Directory != "file-plans" ||
cfg.Cache.ChunkPlans.Mode != pipeline.ChunkCacheRefresh || cfg.Cache.Checkpoints.Directory != "file-checkpoints" ||
cfg.Debug.Directory != "./file-debug" {
t.Fatalf("file values did not override defaults: %#v", cfg)
}
}
func TestPrecedenceOperationalEnvironmentOverridesFileValues(t *testing.T) {
cfg := applyFileConfig(t, `version: 4
concurrency:
total_llm: 2
stage_workers:
extract: 1
output:
directory: ./file-output
cache:
chunk_plans:
directory: ./file-plans
mode: refresh
checkpoints:
directory: ./file-checkpoints
debug:
directory: ./file-debug
`)
env := map[string]string{
"NOTARIUS_TOTAL_LLM_CONCURRENCY": "8",
"NOTARIUS_STAGE_WORKERS_EXTRACT": "6",
"NOTARIUS_OUTPUT_DIR": "/env/output",
"NOTARIUS_CACHE_CHUNK_PLANS_MODE": "bypass",
"NOTARIUS_CACHE_CHUNK_PLANS_DIR": "/env/plans",
"NOTARIUS_CACHE_CHECKPOINTS_DIR": "/env/checkpoints",
"NOTARIUS_DEBUG_DIR": "/env/debug",
}
if err := cfg.ApplyEnvOverridesWithLookup(lookupValues(env)); err != nil {
t.Fatal(err)
}
if cfg.Concurrency.TotalLLM != 8 || cfg.Concurrency.StageWorkers["extract"] != 6 ||
cfg.Output.Directory != "/env/output" || cfg.Cache.ChunkPlans.Directory != "/env/plans" ||
cfg.Cache.ChunkPlans.Mode != pipeline.ChunkCacheBypass || cfg.Cache.Checkpoints.Directory != "/env/checkpoints" ||
cfg.Debug.Directory != "/env/debug" {
t.Fatalf("environment values did not override file values: %#v", cfg)
}
}
func TestPrecedenceExtractWorkersFollowEffectiveConcurrencyUnlessExplicit(t *testing.T) {
tests := []struct {
name string
file string
env map[string]string
wantTotal int
wantWorker int
}{
{
name: "default follows environment total",
file: "version: 4\n",
env: map[string]string{"NOTARIUS_TOTAL_LLM_CONCURRENCY": "5"},
wantTotal: 5,
wantWorker: 5,
},
{
name: "file worker is retained",
file: "version: 4\nconcurrency:\n total_llm: 3\n stage_workers:\n extract: 2\n",
env: map[string]string{"NOTARIUS_TOTAL_LLM_CONCURRENCY": "6"},
wantTotal: 6,
wantWorker: 2,
},
{
name: "environment worker is retained",
file: "version: 4\nconcurrency:\n total_llm: 2\n",
env: map[string]string{
"NOTARIUS_TOTAL_LLM_CONCURRENCY": "6",
"NOTARIUS_STAGE_WORKERS_EXTRACT": "4",
},
wantTotal: 6,
wantWorker: 4,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
cfg := applyFileConfig(t, tt.file)
if err := cfg.ApplyEnvOverridesWithLookup(lookupValues(tt.env)); err != nil {
t.Fatal(err)
}
if cfg.Concurrency.TotalLLM != tt.wantTotal || cfg.Concurrency.StageWorkers["extract"] != tt.wantWorker {
t.Fatalf("concurrency = %#v, want total %d and extract %d", cfg.Concurrency, tt.wantTotal, tt.wantWorker)
}
})
}
}
func TestPrecedenceEmptyFileCacheDirectoriesDeferPerUserResolution(t *testing.T) {
cfg := applyFileConfig(t, `version: 4
cache:
chunk_plans:
directory: ""
checkpoints:
directory: ""
`)
if err := cfg.Validate(); err != nil {
t.Fatalf("empty file cache directories should be valid: %v", err)
}
if cfg.Cache.ChunkPlans.Directory != "" || cfg.Cache.Checkpoints.Directory != "" {
t.Fatalf("empty cache directories were not preserved for deferred resolution: %#v", cfg.Cache)
}
resolver := func() (string, error) { return "/user/cache", nil }
chunkPlans, err := DefaultChunkPlanRoot(resolver)
if err != nil {
t.Fatal(err)
}
checkpoints, err := DefaultCheckpointRoot(resolver)
if err != nil {
t.Fatal(err)
}
if chunkPlans != "/user/cache/notarius/chunk-plans" || checkpoints != "/user/cache/notarius/checkpoints" {
t.Fatalf("deferred cache roots = %q, %q", chunkPlans, checkpoints)
}
}
func TestDefaultCacheRootsRejectInvalidUserCacheResolvers(t *testing.T) {
tests := []struct {
name string
resolver func() (string, error)
want string
}{
{name: "nil resolver", want: "must not be nil"},
{
name: "resolver failure",
resolver: func() (string, error) {
return "", errors.New("cache home unavailable")
},
want: "resolve user cache directory",
},
{name: "empty directory", resolver: func() (string, error) { return " ", nil }, want: "must not be empty"},
}
families := []struct {
name string
root func(func() (string, error)) (string, error)
}{
{name: "chunk plans", root: DefaultChunkPlanRoot},
{name: "checkpoints", root: DefaultCheckpointRoot},
}
for _, family := range families {
for _, tt := range tests {
t.Run(family.name+"/"+tt.name, func(t *testing.T) {
_, err := family.root(tt.resolver)
if err == nil || !strings.Contains(err.Error(), tt.want) {
t.Fatalf("error = %v, want substring %q", err, tt.want)
}
})
}
}
}
func TestEnvEmptyDirectoryOverridesAreErrors(t *testing.T) {
tests := []string{
"NOTARIUS_OUTPUT_DIR",
"NOTARIUS_CACHE_CHUNK_PLANS_DIR",
"NOTARIUS_CACHE_CHECKPOINTS_DIR",
"NOTARIUS_DEBUG_DIR",
}
for _, name := range tests {
t.Run(name, func(t *testing.T) {
cfg := Default()
err := cfg.ApplyEnvOverridesWithLookup(lookupValues(map[string]string{name: " \t"}))
if err == nil || !strings.Contains(err.Error(), name) {
t.Fatalf("error = %v, want responsible environment variable", err)
}
})
}
}
func TestEnvInvalidIntegersAndChunkCacheModesReportTheirNames(t *testing.T) {
tests := map[string]string{
"NOTARIUS_TOTAL_LLM_CONCURRENCY": "not-an-integer",
"NOTARIUS_STAGE_WORKERS_EXTRACT": "not-an-integer",
"NOTARIUS_CACHE_CHUNK_PLANS_MODE": "not-a-cache-mode",
}
for name, value := range tests {
t.Run(name, func(t *testing.T) {
cfg := Default()
err := cfg.ApplyEnvOverridesWithLookup(lookupValues(map[string]string{name: value}))
if err == nil || !strings.Contains(err.Error(), name) {
t.Fatalf("error = %v, want responsible environment variable", err)
}
})
}
}
func TestEnvRemovedProviderVariablesAreIgnored(t *testing.T) {
before := Default()
cfg := Default()
removed := map[string]string{
"NOTARIUS_LLM_DEFAULT_ENDPOINT": "ignored-provider-setting",
"NOTARIUS_LLM_DEFAULT_MODEL": "ignored-provider-setting",
}
if err := cfg.ApplyEnvOverridesWithLookup(lookupValues(removed)); err != nil {
t.Fatal(err)
}
if !reflect.DeepEqual(cfg, before) {
t.Fatalf("removed provider variables changed configuration: %#v", cfg)
}
}
func lookupValues(values map[string]string) func(string) (string, bool) {
return func(name string) (string, bool) {
value, ok := values[name]
return value, ok
}
}

902
internal/core/config/file_config.go
View File

@@ -1,902 +0,0 @@
package config
import (
"bytes"
"fmt"
"io"
"os"
"path/filepath"
"sort"
"strings"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gopkg.in/yaml.v3"
)
type FileConfig struct {
Version int `yaml:"version"`
PromptKit *FilePromptKitConfig `yaml:"promptkit,omitempty"`
Pipelines map[string]FilePipelineProfile `yaml:"pipelines,omitempty"`
Concurrency *FileConcurrencyConfig `yaml:"concurrency,omitempty"`
Output *FileOutputConfig `yaml:"output,omitempty"`
Cache *FileCacheConfig `yaml:"cache,omitempty"`
Debug *FileDebugConfig `yaml:"debug,omitempty"`
}
type FilePromptKitConfig struct {
ProfileDir *string `yaml:"profile_dir,omitempty"`
ProfileFile *string `yaml:"profile_file,omitempty"`
LocalBackend *FilePromptKitLocalBackendConfig `yaml:"local_backend,omitempty"`
}
type FilePromptKitLocalBackendConfig struct {
Endpoint *string `yaml:"endpoint,omitempty"`
ConcurrencyLimit *int `yaml:"concurrency_limit,omitempty"`
}
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"`
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": {}, "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"]
return nil
}
func (s *FilePipelineStepProfile) UnmarshalYAML(node *yaml.Node) error {
type plainFilePipelineStepProfile FilePipelineStepProfile
var decoded plainFilePipelineStepProfile
if _, err := decodeKnownMapping(node, &decoded, map[string]struct{}{
"id": {}, "artifacts": {}, "references": {},
}, "pipeline step"); err != nil {
return err
}
*s = FilePipelineStepProfile(decoded)
return nil
}
func (l *FileArtifactLaneProfile) UnmarshalYAML(node *yaml.Node) error {
type plainFileArtifactLaneProfile FileArtifactLaneProfile
var decoded plainFileArtifactLaneProfile
if _, err := decodeKnownMapping(node, &decoded, map[string]struct{}{
"extract": {}, "merge": {}, "normalize": {}, "validators": {}, "references": {},
}, "artifact lane"); err != nil {
return err
}
*l = FileArtifactLaneProfile(decoded)
return nil
}
func decodeKnownMapping(node *yaml.Node, target any, allowed map[string]struct{}, context string) (map[string]struct{}, error) {
if node.Kind != yaml.MappingNode {
return nil, fmt.Errorf("%s must be an object", context)
}
if err := node.Decode(target); err != nil {
return nil, err
}
seen := make(map[string]struct{}, len(node.Content)/2)
for i := 0; i < len(node.Content); i += 2 {
key := node.Content[i].Value
if _, exists := seen[key]; exists {
return nil, fmt.Errorf("%s field %q is duplicated", context, key)
}
if _, ok := allowed[key]; !ok {
return nil, fmt.Errorf("field %s not found in %s", key, context)
}
seen[key] = struct{}{}
}
return seen, nil
}
type FilePipelineStepProfile struct {
ID string `yaml:"id"`
Artifacts map[string]FileArtifactLaneProfile `yaml:"artifacts"`
References map[string]fileReferenceSource `yaml:"references,omitempty"`
}
type FileArtifactLaneProfile struct {
Extract fileModuleBinding `yaml:"extract"`
Merge *fileModuleBinding `yaml:"merge,omitempty"`
Normalize *fileModuleBinding `yaml:"normalize,omitempty"`
Validators []fileModuleBinding `yaml:"validators,omitempty"`
References map[string]fileReferenceSource `yaml:"references,omitempty"`
}
type FileConcurrencyConfig struct {
TotalLLM *int `yaml:"total_llm,omitempty"`
StageWorkers map[string]int `yaml:"stage_workers,omitempty"`
}
type FileOutputConfig struct {
Directory *string `yaml:"directory,omitempty"`
}
type FileCacheConfig struct {
ChunkPlans *FileChunkPlanCacheConfig `yaml:"chunk_plans,omitempty"`
Checkpoints *FileCheckpointCacheConfig `yaml:"checkpoints,omitempty"`
}
type FileChunkPlanCacheConfig struct {
Directory *string `yaml:"directory,omitempty"`
Mode *string `yaml:"mode,omitempty"`
}
type FileCheckpointCacheConfig struct {
Enabled *bool `yaml:"enabled,omitempty"`
Directory *string `yaml:"directory,omitempty"`
}
type FileDebugConfig struct {
Directory *string `yaml:"directory,omitempty"`
}
type fileModuleBinding struct {
Module string
LLMProfile string
StructuredOutputRepairAttempts *int
ValidationPolicy *pipeline.ValidationPolicyOverride
Retries int
Options map[string]any
References map[string]fileReferenceSource
Validators pipeline.ValidatorOverride
}
type fileReferenceSource struct {
path string
artifact *pipeline.ArtifactReference
}
func (source *fileReferenceSource) UnmarshalYAML(node *yaml.Node) error {
if source == nil {
return fmt.Errorf("reference source must not be nil")
}
switch node.Kind {
case yaml.ScalarNode:
if node.Tag != "!!str" {
return fmt.Errorf("external reference path must be a string")
}
path := strings.TrimSpace(node.Value)
if path == "" {
return fmt.Errorf("external reference path must not be empty")
}
source.path = path
source.artifact = nil
return nil
case yaml.MappingNode:
if len(node.Content) != 2 || node.Content[0].Value != "artifact" {
return fmt.Errorf("reference source mapping must contain only artifact")
}
artifactNode := node.Content[1]
if artifactNode.Kind != yaml.MappingNode {
return fmt.Errorf("artifact reference must be an object")
}
var step, lane string
seen := map[string]bool{}
for i := 0; i < len(artifactNode.Content); i += 2 {
key := artifactNode.Content[i].Value
value := artifactNode.Content[i+1]
if seen[key] {
return fmt.Errorf("artifact reference field %q is duplicated", key)
}
seen[key] = true
if value.Tag != "!!str" {
return fmt.Errorf("artifact reference field %q must be a string", key)
}
switch key {
case "step":
step = strings.TrimSpace(value.Value)
case "lane":
lane = strings.TrimSpace(value.Value)
default:
return fmt.Errorf("field %s not found in artifact reference", key)
}
}
if step == "" || lane == "" {
return fmt.Errorf("artifact reference step and lane must not be empty")
}
source.path = ""
source.artifact = &pipeline.ArtifactReference{Step: step, Lane: lane}
return nil
default:
return fmt.Errorf("reference source must be a string or object")
}
}
func (source fileReferenceSource) toPipelineSource() pipeline.ReferenceSource {
if source.artifact != nil {
artifact := *source.artifact
return pipeline.ReferenceSource{Artifact: &artifact}
}
return pipeline.ExternalReference(source.path)
}
func fileReferenceSourcesToPipeline(values map[string]fileReferenceSource) map[string]pipeline.ReferenceSource {
if len(values) == 0 {
return nil
}
out := make(map[string]pipeline.ReferenceSource, len(values))
for key, value := range values {
out[strings.TrimSpace(key)] = value.toPipelineSource()
}
return out
}
func (b *fileModuleBinding) UnmarshalYAML(node *yaml.Node) error {
switch node.Kind {
case yaml.ScalarNode:
var module string
if err := node.Decode(&module); err != nil {
return fmt.Errorf("module binding must be a string or object")
}
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
if err := valueNode.Decode(&module); err != nil {
return err
}
b.Module = strings.TrimSpace(module)
case "llm_profile":
var llmProfile string
if err := valueNode.Decode(&llmProfile); err != nil {
return err
}
b.LLMProfile = strings.TrimSpace(llmProfile)
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 "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 {
return err
}
b.Retries = retries
case "options":
var options map[string]any
if err := valueNode.Decode(&options); err != nil {
return err
}
b.Options = normalizeOptions(options)
case "references":
var references map[string]fileReferenceSource
if err := valueNode.Decode(&references); err != nil {
return err
}
b.References = references
case "validators":
b.Validators.Set = true
var validators []fileModuleBinding
if err := valueNode.Decode(&validators); err != nil {
return err
}
b.Validators.Validators = make([]pipeline.ModuleBinding, len(validators))
for i, validator := range validators {
b.Validators.Validators[i] = validator.toPipelineBinding()
}
default:
return fmt.Errorf("field %s not found in module binding", keyNode.Value)
}
}
return nil
default:
return fmt.Errorf("module binding must be a string or object")
}
}
func (b fileModuleBinding) toPipelineBinding() pipeline.ModuleBinding {
return 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),
Validators: cloneValidatorOverride(b.Validators),
}
}
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)
}
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 {
return FileConfig{}, fmt.Errorf("read config file %q: %w", path, err)
}
cfg, err := ParseFileConfigYAML(data)
if err != nil {
return FileConfig{}, fmt.Errorf("parse config file %q: %w", path, err)
}
return cfg, nil
}
func ParseFileConfigYAML(data []byte) (FileConfig, error) {
var header struct {
Version int `yaml:"version"`
}
if err := yaml.Unmarshal(data, &header); err != nil {
return FileConfig{}, fmt.Errorf("decode yaml version header: %w", err)
}
if header.Version == 0 {
return FileConfig{}, fmt.Errorf("config version is required")
}
if header.Version == 2 {
return FileConfig{}, fmt.Errorf("config version 2 is no longer supported; migrate the file using the version 2-to-3 migration in docs/config.md")
}
if header.Version == 3 {
return FileConfig{}, fmt.Errorf("config version 3 is no longer supported; change \"version: 3\" to \"version: 4\" and rename \"scriptorium:\" to \"promptkit:\"")
}
if header.Version != SupportedFileConfigVersion {
return FileConfig{}, fmt.Errorf("unsupported config version %d (supported version is %d)", header.Version, SupportedFileConfigVersion)
}
var fileCfg FileConfig
decoder := yaml.NewDecoder(bytes.NewReader(data))
decoder.KnownFields(true)
if err := decoder.Decode(&fileCfg); err != nil {
return FileConfig{}, fmt.Errorf("decode yaml: %w", err)
}
var trailing any
if err := decoder.Decode(&trailing); err == nil {
return FileConfig{}, fmt.Errorf("config must contain exactly one YAML document")
} else if err != io.EOF {
return FileConfig{}, fmt.Errorf("decode trailing yaml document: %w", err)
}
return fileCfg, nil
}
func (c *Config) ApplyFileConfig(fileCfg FileConfig) error {
return c.applyFileConfigWithLookup(fileCfg, os.LookupEnv)
}
func (c *Config) ApplyFileConfigWithLookup(fileCfg FileConfig, lookup func(string) (string, bool)) error {
return c.applyFileConfigWithLookup(fileCfg, lookup)
}
func (c *Config) applyFileConfigWithLookup(fileCfg FileConfig, lookup func(string) (string, bool)) error {
_ = lookup
if c == nil {
return fmt.Errorf("config must not be nil")
}
if fileCfg.Version != SupportedFileConfigVersion {
return fmt.Errorf("unsupported config version %d", fileCfg.Version)
}
if c.Pipelines == nil {
c.Pipelines = map[string]pipeline.PipelineProfile{}
}
pipelineIDs, rawPipelineIDs, err := normalizedMapKeys(fileCfg.Pipelines, "pipeline id")
if err != nil {
return err
}
for _, pipelineID := range pipelineIDs {
filePipeline := fileCfg.Pipelines[rawPipelineIDs[pipelineID]]
hasArtifacts := filePipeline.artifactsSet || filePipeline.Artifacts != nil
hasSteps := filePipeline.stepsSet || filePipeline.Steps != nil
if hasArtifacts && hasSteps {
return fmt.Errorf("pipeline %q must not declare both artifacts and steps", pipelineID)
}
if hasSteps && len(filePipeline.Steps) == 0 {
return fmt.Errorf("pipeline %q must declare at least one ordered step", pipelineID)
}
if hasSteps {
seenSteps := make(map[string]struct{}, len(filePipeline.Steps))
seenLanes := make(map[string]struct{})
for index, step := range filePipeline.Steps {
stepID := strings.TrimSpace(step.ID)
if stepID == "" {
return fmt.Errorf("pipeline %q step[%d] id must not be empty", pipelineID, index)
}
if _, ok := seenSteps[stepID]; ok {
return fmt.Errorf("pipeline %q step id %q is duplicated after trimming", pipelineID, stepID)
}
seenSteps[stepID] = struct{}{}
laneIDs, rawLaneIDs, err := normalizedMapKeys(step.Artifacts, fmt.Sprintf("pipeline %q step %q artifact lane id", pipelineID, stepID))
if err != nil {
return err
}
for _, laneID := range laneIDs {
if _, ok := seenLanes[laneID]; ok {
return fmt.Errorf("pipeline %q artifact lane id %q is duplicated across steps", pipelineID, laneID)
}
seenLanes[laneID] = struct{}{}
fileLane := step.Artifacts[rawLaneIDs[laneID]]
if err := validateFileLaneReferences(pipelineID, stepID, laneID, fileLane); err != nil {
return err
}
}
if err := validateFileReferenceSources(step.References, fmt.Sprintf("pipeline %q step %q reference slot", pipelineID, stepID)); err != nil {
return err
}
}
}
if _, _, err := normalizedMapKeys(filePipeline.Artifacts, fmt.Sprintf("pipeline %q artifact lane id", pipelineID)); err != nil {
return err
}
if err := validateFileReferenceSources(filePipeline.References, fmt.Sprintf("pipeline %q reference slot", pipelineID)); err != nil {
return err
}
if filePipeline.Chunk != nil {
if _, _, err := normalizedMapKeys(filePipeline.Chunk.References, fmt.Sprintf("pipeline %q chunk reference slot", pipelineID)); err != nil {
return err
}
}
if _, _, err := normalizedMapKeys(filePipeline.Input.References, fmt.Sprintf("pipeline %q input reference slot", pipelineID)); err != nil {
return err
}
if filePipeline.Output != nil {
if _, _, err := normalizedMapKeys(filePipeline.Output.References, fmt.Sprintf("pipeline %q output reference slot", pipelineID)); err != nil {
return err
}
}
for rawLaneID, fileLane := range filePipeline.Artifacts {
laneID := strings.TrimSpace(rawLaneID)
if laneID == "" {
continue
}
if _, _, err := normalizedMapKeys(fileLane.References, fmt.Sprintf("pipeline %q lane %q reference slot", pipelineID, laneID)); err != nil {
return err
}
if _, _, err := normalizedMapKeys(fileLane.Extract.References, fmt.Sprintf("pipeline %q lane %q extract reference slot", pipelineID, laneID)); err != nil {
return err
}
if fileLane.Merge != nil {
if _, _, err := normalizedMapKeys(fileLane.Merge.References, fmt.Sprintf("pipeline %q lane %q merge reference slot", pipelineID, laneID)); err != nil {
return err
}
}
if fileLane.Normalize != nil {
if _, _, err := normalizedMapKeys(fileLane.Normalize.References, fmt.Sprintf("pipeline %q lane %q normalize reference slot", pipelineID, laneID)); err != nil {
return err
}
}
for i, validator := range fileLane.Validators {
if _, _, err := normalizedMapKeys(validator.References, fmt.Sprintf("pipeline %q lane %q validator[%d] reference slot", pipelineID, laneID, i)); err != nil {
return err
}
}
}
}
if fileCfg.PromptKit != nil {
if fileCfg.PromptKit.ProfileDir != nil {
value := strings.TrimSpace(*fileCfg.PromptKit.ProfileDir)
if value == "" {
return fmt.Errorf("promptkit.profile_dir must not be empty when set")
}
c.PromptKit.ProfileDir = value
}
if fileCfg.PromptKit.ProfileFile != nil {
value := strings.TrimSpace(*fileCfg.PromptKit.ProfileFile)
if value == "" {
return fmt.Errorf("promptkit.profile_file must not be empty when set")
}
c.PromptKit.ProfileFile = value
}
if fileCfg.PromptKit.LocalBackend != nil {
if fileCfg.PromptKit.LocalBackend.Endpoint == nil {
return fmt.Errorf("promptkit.local_backend.endpoint must not be empty when set")
}
endpoint := strings.TrimSpace(*fileCfg.PromptKit.LocalBackend.Endpoint)
if endpoint == "" {
return fmt.Errorf("promptkit.local_backend.endpoint must not be empty when set")
}
localBackend := PromptKitLocalBackendConfig{Endpoint: endpoint}
if fileCfg.PromptKit.LocalBackend.ConcurrencyLimit != nil {
localBackend.ConcurrencyLimit = *fileCfg.PromptKit.LocalBackend.ConcurrencyLimit
}
c.PromptKit.LocalBackend = &localBackend
}
}
for _, pipelineID := range pipelineIDs {
filePipeline := fileCfg.Pipelines[rawPipelineIDs[pipelineID]]
llmProfile := ""
if filePipeline.llmProfileSet || filePipeline.LLMProfile != nil {
if filePipeline.LLMProfile == nil || strings.TrimSpace(*filePipeline.LLMProfile) == "" {
return fmt.Errorf("pipeline %q llm_profile must not be empty when set", pipelineID)
}
llmProfile = strings.TrimSpace(*filePipeline.LLMProfile)
}
hasSteps := filePipeline.stepsSet || filePipeline.Steps != nil
laneIDs, rawLaneIDs, err := normalizedMapKeys(filePipeline.Artifacts, fmt.Sprintf("pipeline %q artifact lane id", pipelineID))
if err != nil {
return err
}
profile := pipeline.PipelineProfile{
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),
}
if filePipeline.Chunk != nil {
profile.Chunk = filePipeline.Chunk.toPipelineBinding()
}
if filePipeline.Output != nil {
profile.Output = filePipeline.Output.toPipelineBinding()
}
for _, laneID := range laneIDs {
fileLane := filePipeline.Artifacts[rawLaneIDs[laneID]]
extract := fileLane.Extract.toPipelineBinding()
extract.References = mergeReferenceSources(fileReferenceSourcesToPipeline(fileLane.References), extract.References)
lane := pipeline.ArtifactLaneProfile{
Extract: extract,
References: fileReferenceSourcesToPipeline(fileLane.References),
}
if fileLane.Merge != nil {
lane.Merge = fileLane.Merge.toPipelineBinding()
}
if fileLane.Normalize != nil {
lane.Normalize = fileLane.Normalize.toPipelineBinding()
}
if len(fileLane.Validators) > 0 {
lane.Validators = make([]pipeline.ModuleBinding, len(fileLane.Validators))
for i, validator := range fileLane.Validators {
lane.Validators[i] = validator.toPipelineBinding()
}
}
profile.Artifacts[laneID] = lane
}
if hasSteps {
profile.Artifacts = nil
profile.Steps = make([]pipeline.PipelineStepProfile, len(filePipeline.Steps))
for i, fileStep := range filePipeline.Steps {
stepID := strings.TrimSpace(fileStep.ID)
step := pipeline.PipelineStepProfile{
ID: stepID,
Artifacts: make(map[string]pipeline.ArtifactLaneProfile, len(fileStep.Artifacts)),
References: fileReferenceSourcesToPipeline(fileStep.References),
}
stepLaneIDs, stepRawLaneIDs, err := normalizedMapKeys(fileStep.Artifacts, fmt.Sprintf("pipeline %q step %q artifact lane id", pipelineID, stepID))
if err != nil {
return err
}
for _, laneID := range stepLaneIDs {
fileLane := fileStep.Artifacts[stepRawLaneIDs[laneID]]
extract := fileLane.Extract.toPipelineBinding()
extract.References = mergeReferenceSources(fileReferenceSourcesToPipeline(fileLane.References), extract.References)
lane := pipeline.ArtifactLaneProfile{Extract: extract, References: fileReferenceSourcesToPipeline(fileLane.References)}
if fileLane.Merge != nil {
lane.Merge = fileLane.Merge.toPipelineBinding()
}
if fileLane.Normalize != nil {
lane.Normalize = fileLane.Normalize.toPipelineBinding()
}
if len(fileLane.Validators) > 0 {
lane.Validators = make([]pipeline.ModuleBinding, len(fileLane.Validators))
for index, validator := range fileLane.Validators {
lane.Validators[index] = validator.toPipelineBinding()
}
}
step.Artifacts[laneID] = lane
}
profile.Steps[i] = step
}
}
c.Pipelines[pipelineID] = profile
}
if fileCfg.Concurrency != nil && fileCfg.Concurrency.TotalLLM != nil {
c.Concurrency.TotalLLM = *fileCfg.Concurrency.TotalLLM
}
if fileCfg.Concurrency != nil && fileCfg.Concurrency.StageWorkers != nil {
workers, configured, err := normalizeStageWorkers(fileCfg.Concurrency.StageWorkers)
if err != nil {
return err
}
c.Concurrency.StageWorkers = workers
c.Concurrency.extractWorkersConfigured = configured
}
c.Concurrency.recomputeStageWorkerDefaults()
if fileCfg.Output != nil && fileCfg.Output.Directory != nil {
c.Output.Directory = strings.TrimSpace(*fileCfg.Output.Directory)
if c.Output.Directory == "" {
return fmt.Errorf("output.directory must not be empty")
}
if strings.ContainsRune(c.Output.Directory, '\x00') {
return fmt.Errorf("output.directory must not contain NUL")
}
}
if fileCfg.Cache != nil {
if fileCfg.Cache.ChunkPlans != nil {
if fileCfg.Cache.ChunkPlans.Mode != nil {
mode, err := pipeline.ParseChunkCacheMode(*fileCfg.Cache.ChunkPlans.Mode)
if err != nil {
return fmt.Errorf("cache.chunk_plans.mode: %w", err)
}
c.Cache.ChunkPlans.Mode = mode
}
if fileCfg.Cache.ChunkPlans.Directory != nil {
c.Cache.ChunkPlans.Directory = cleanOptionalPath(*fileCfg.Cache.ChunkPlans.Directory)
if strings.ContainsRune(c.Cache.ChunkPlans.Directory, '\x00') {
return fmt.Errorf("cache.chunk_plans.directory must not contain NUL")
}
}
}
if fileCfg.Cache.Checkpoints != nil {
if fileCfg.Cache.Checkpoints.Enabled != nil {
c.Cache.Checkpoints.Enabled = *fileCfg.Cache.Checkpoints.Enabled
}
if fileCfg.Cache.Checkpoints.Directory != nil {
c.Cache.Checkpoints.Directory = cleanOptionalPath(*fileCfg.Cache.Checkpoints.Directory)
if strings.ContainsRune(c.Cache.Checkpoints.Directory, '\x00') {
return fmt.Errorf("cache.checkpoints.directory must not contain NUL")
}
}
}
}
if fileCfg.Debug != nil && fileCfg.Debug.Directory != nil {
c.Debug.Directory = strings.TrimSpace(*fileCfg.Debug.Directory)
if c.Debug.Directory == "" {
return fmt.Errorf("debug.directory must not be empty")
}
if strings.ContainsRune(c.Debug.Directory, '\x00') {
return fmt.Errorf("debug.directory must not contain NUL")
}
}
return nil
}
func cleanOptionalPath(value string) string {
value = strings.TrimSpace(value)
if value == "" {
return ""
}
return filepath.Clean(value)
}
func normalizeStageWorkers(values map[string]int) (map[string]int, bool, error) {
workers := make(map[string]int, len(values))
configured := false
for rawKey, value := range values {
key := strings.TrimSpace(rawKey)
if key == "" {
return nil, false, fmt.Errorf("concurrency.stage_workers key must not be empty")
}
if key != "extract" {
return nil, false, fmt.Errorf("concurrency.stage_workers key %q is not supported", rawKey)
}
if _, exists := workers[key]; exists {
return nil, false, fmt.Errorf("concurrency.stage_workers key %q is duplicated after trimming", key)
}
workers[key] = value
configured = true
}
return workers, configured, nil
}
func normalizedMapKeys[T any](values map[string]T, keyName string) ([]string, map[string]string, error) {
keys := make([]string, 0, len(values))
rawByNormalized := make(map[string]string, len(values))
for rawID := range values {
id := strings.TrimSpace(rawID)
if id == "" {
return nil, nil, fmt.Errorf("%s must not be empty", keyName)
}
if _, ok := rawByNormalized[id]; ok {
return nil, nil, fmt.Errorf("%s %q is duplicated after trimming", keyName, id)
}
rawByNormalized[id] = rawID
keys = append(keys, id)
}
sort.Strings(keys)
return keys, rawByNormalized, nil
}
func validateFileReferenceSources(values map[string]fileReferenceSource, context string) error {
seen := make(map[string]struct{}, len(values))
for rawSlot, source := range values {
slot := strings.TrimSpace(rawSlot)
if slot == "" {
return fmt.Errorf("%s must not be empty", context)
}
if _, ok := seen[slot]; ok {
return fmt.Errorf("%s %q is duplicated after trimming", context, slot)
}
seen[slot] = struct{}{}
if source.artifact != nil {
if strings.TrimSpace(source.artifact.Step) == "" || strings.TrimSpace(source.artifact.Lane) == "" {
return fmt.Errorf("%s %q artifact selector step and lane must not be empty", context, slot)
}
if strings.TrimSpace(source.path) != "" {
return fmt.Errorf("%s %q must contain either an external path or artifact selector", context, slot)
}
continue
}
if strings.TrimSpace(source.path) == "" {
return fmt.Errorf("%s %q source must not be empty", context, slot)
}
}
return nil
}
func validateFileLaneReferences(pipelineID, stepID, laneID string, lane FileArtifactLaneProfile) error {
prefix := fmt.Sprintf("pipeline %q step %q lane %q", pipelineID, stepID, laneID)
references := []struct {
label string
values map[string]fileReferenceSource
}{
{label: "reference slot", values: lane.References},
{label: "extract reference slot", values: lane.Extract.References},
}
if lane.Merge != nil {
references = append(references, struct {
label string
values map[string]fileReferenceSource
}{label: "merge reference slot", values: lane.Merge.References})
}
if lane.Normalize != nil {
references = append(references, struct {
label string
values map[string]fileReferenceSource
}{label: "normalize reference slot", values: lane.Normalize.References})
}
for _, item := range references {
if err := validateFileReferenceSources(item.values, prefix+" "+item.label); err != nil {
return err
}
}
for index, validator := range lane.Validators {
if err := validateFileReferenceSources(validator.References, fmt.Sprintf("%s validator[%d] reference slot", prefix, index)); err != nil {
return err
}
}
return nil
}
func mergeReferenceSources(base map[string]pipeline.ReferenceSource, override map[string]pipeline.ReferenceSource) map[string]pipeline.ReferenceSource {
if len(base) == 0 && len(override) == 0 {
return nil
}
out := make(map[string]pipeline.ReferenceSource, len(base)+len(override))
for key, value := range base {
out[key] = value
}
for key, value := range override {
out[key] = value
}
return out
}
func normalizeOptions(options map[string]any) map[string]any {
if len(options) == 0 {
return nil
}
return cloneOptions(options)
}

928
internal/core/config/file_config_contract_test.go
View File

@@ -1,928 +0,0 @@
package config
import (
"encoding/json"
"fmt"
"os"
"path/filepath"
"reflect"
"strings"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
func TestDefaultReturnsDocumentedValuesAndIndependentMaps(t *testing.T) {
first := Default()
if first.Concurrency.TotalLLM != 16 || first.Concurrency.StageWorkers["extract"] != 16 {
t.Fatalf("concurrency defaults = %#v", first.Concurrency)
}
if first.Output.Directory != "./notarius-output" || first.Debug.Directory != "./notarius-debug" {
t.Fatalf("output/debug defaults = %#v, %#v", first.Output, first.Debug)
}
if first.Cache.ChunkPlans.Mode != pipeline.ChunkCacheAuto || first.Cache.ChunkPlans.Directory != "" || first.Cache.Checkpoints.Enabled || first.Cache.Checkpoints.Directory != "" {
t.Fatalf("cache defaults = %#v", first.Cache)
}
if len(first.Pipelines) != 0 {
t.Fatalf("pipeline defaults = %#v", first.Pipelines)
}
first.Concurrency.StageWorkers["extract"] = 99
first.Concurrency.StageWorkers["other"] = 100
first.Pipelines["changed"] = pipeline.PipelineProfile{}
second := Default()
if second.Concurrency.StageWorkers["extract"] != 16 || len(second.Concurrency.StageWorkers) != 1 || len(second.Pipelines) != 0 {
t.Fatalf("Default() returned state shared with an earlier result: %#v", second)
}
}
func TestFileConfigMinimalVersion4AppliesOverDefaults(t *testing.T) {
file := parseFileConfig(t, "version: 4\n")
cfg := Default()
if err := cfg.ApplyFileConfig(file); err != nil {
t.Fatal(err)
}
if cfg.Output.Directory != "./notarius-output" || cfg.Debug.Directory != "./notarius-debug" || cfg.Cache.ChunkPlans.Mode != pipeline.ChunkCacheAuto {
t.Fatalf("minimal file changed unrelated defaults: %#v", cfg)
}
if cfg.Concurrency.TotalLLM != 16 || cfg.Concurrency.StageWorkers["extract"] != 16 || len(cfg.Pipelines) != 0 {
t.Fatalf("minimal file did not retain defaults: %#v", cfg)
}
}
func TestParseFileConfigYAMLRejectsAdditionalDocuments(t *testing.T) {
tests := []struct {
name string
source string
wantErr bool
}{
{name: "trailing whitespace", source: "version: 4\n\n \t", wantErr: false},
{name: "trailing comment", source: "version: 4\n# trailing comment\n", wantErr: false},
{name: "second valid document", source: "version: 4\n---\nversion: 4\n", wantErr: true},
{name: "second empty document", source: "version: 4\n---\n", wantErr: true},
{name: "second malformed document", source: "version: 4\n---\nversion: [\n", wantErr: true},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
_, err := ParseFileConfigYAML([]byte(tt.source))
if (err != nil) != tt.wantErr {
t.Fatalf("ParseFileConfigYAML() error = %v, want error=%t", err, tt.wantErr)
}
})
}
}
func TestFilePipelineLLMProfileIsPresenceAwareAndDetached(t *testing.T) {
const pipelineYAML = `version: 4
pipelines:
main:
%s
input: input
artifacts:
lane:
extract: extract
`
t.Run("omitted", func(t *testing.T) {
file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, ""))
if file.Pipelines["main"].LLMProfile != nil || file.Pipelines["main"].llmProfileSet {
t.Fatalf("parsed pipeline profile = %#v, want omitted llm profile", file.Pipelines["main"])
}
cfg := Default()
if err := cfg.ApplyFileConfig(file); err != nil {
t.Fatal(err)
}
if got := cfg.Pipelines["main"].LLMProfile; got != "" {
t.Fatalf("pipeline llm profile = %q, want empty", got)
}
})
t.Run("trimmed and detached", func(t *testing.T) {
file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, "llm_profile: ' configured-profile '"))
cfg := Default()
if err := cfg.ApplyFileConfig(file); err != nil {
t.Fatal(err)
}
if got := cfg.Pipelines["main"].LLMProfile; got != "configured-profile" {
t.Fatalf("pipeline llm profile = %q, want trimmed value", got)
}
*file.Pipelines["main"].LLMProfile = "changed-profile"
if got := cfg.Pipelines["main"].LLMProfile; got != "configured-profile" {
t.Fatalf("effective config aliases parsed file: %q", got)
}
if got := cloneConfig(cfg).Pipelines["main"].LLMProfile; got != "configured-profile" {
t.Fatalf("cloned pipeline llm profile = %q", got)
}
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)
}
if got := roundTripped.Pipelines["main"].LLMProfile; got != "configured-profile" {
t.Fatalf("round-tripped pipeline llm profile = %q", got)
}
})
for _, value := range []string{"''", "' '", "null"} {
t.Run("explicit empty "+value, func(t *testing.T) {
file := parseFileConfig(t, fmt.Sprintf(pipelineYAML, "llm_profile: "+value))
cfg := Default()
err := cfg.ApplyFileConfig(file)
if err == nil || !strings.Contains(err.Error(), `pipeline "main" llm_profile must not be empty`) {
t.Fatalf("ApplyFileConfig() error = %v, want explicit-empty rejection", err)
}
})
}
}
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:
main:
input:
module: input
llm_profile: %s
artifacts:
lane:
extract: extract
`
for _, value := range []string{"''", "' '", "null"} {
t.Run(value, func(t *testing.T) {
_, err := ParseFileConfigYAML([]byte(fmt.Sprintf(configYAML, value)))
if err == nil || !strings.Contains(err.Error(), "llm_profile must not be empty when set") {
t.Fatalf("ParseFileConfigYAML() error = %v, want explicit-empty binding profile rejection", err)
}
})
}
}
func TestFilePromptKitProfileSourcesSurviveConfigBoundaries(t *testing.T) {
tests := []struct {
name string
yaml string
want PromptKitConfig
}{
{
name: "profile directory",
yaml: "version: 4\npromptkit:\n profile_dir: ' ./profiles '\n",
want: PromptKitConfig{ProfileDir: "./profiles"},
},
{
name: "profile file",
yaml: "version: 4\npromptkit:\n profile_file: ' ./profiles.yml '\n",
want: PromptKitConfig{ProfileFile: "./profiles.yml"},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
cfg := applyFileConfig(t, tt.yaml)
if cfg.PromptKit != tt.want {
t.Fatalf("PromptKit config = %#v, want %#v", cfg.PromptKit, tt.want)
}
if got := cloneConfig(cfg).PromptKit; got != tt.want {
t.Fatalf("cloned PromptKit config = %#v, want %#v", got, tt.want)
}
if got := cfg.Redacted().PromptKit; got != tt.want {
t.Fatalf("redacted PromptKit config = %#v, want %#v", got, tt.want)
}
data, err := json.Marshal(cfg)
if err != nil {
t.Fatalf("json.Marshal() error = %v", err)
}
var payload map[string]json.RawMessage
if err := json.Unmarshal(data, &payload); err != nil {
t.Fatalf("json.Unmarshal() error = %v", err)
}
if _, ok := payload["promptkit"]; !ok {
t.Fatalf("runtime JSON keys = %v, want promptkit", payload)
}
if _, ok := payload["scriptorium"]; ok {
t.Fatalf("runtime JSON keys = %v, must not contain removed section", payload)
}
})
}
}
func TestFilePromptKitLocalBackendSurvivesConfigBoundaries(t *testing.T) {
tests := []struct {
name string
concurrencyYAML string
wantConcurrency int
}{
{name: "omitted concurrency defaults to zero"},
{name: "positive concurrency is preserved", concurrencyYAML: " concurrency_limit: 2\n", wantConcurrency: 2},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
file := parseFileConfig(t, "version: 4\npromptkit:\n local_backend:\n endpoint: ' http://localhost:8000/v1 '\n"+tt.concurrencyYAML)
cfg := Default()
if err := cfg.ApplyFileConfig(file); err != nil {
t.Fatalf("ApplyFileConfig() error = %v", err)
}
want := PromptKitLocalBackendConfig{
Endpoint: "http://localhost:8000/v1",
ConcurrencyLimit: tt.wantConcurrency,
}
if cfg.PromptKit.LocalBackend == nil || *cfg.PromptKit.LocalBackend != want {
t.Fatalf("local backend config = %#v, want %#v", cfg.PromptKit.LocalBackend, want)
}
*file.PromptKit.LocalBackend.Endpoint = "http://changed.example/v1"
if file.PromptKit.LocalBackend.ConcurrencyLimit != nil {
*file.PromptKit.LocalBackend.ConcurrencyLimit = 99
}
if *cfg.PromptKit.LocalBackend != want {
t.Fatalf("effective config aliases parsed file model: %#v", cfg.PromptKit.LocalBackend)
}
cloned := cloneConfig(cfg)
if cloned.PromptKit.LocalBackend == cfg.PromptKit.LocalBackend || *cloned.PromptKit.LocalBackend != want {
t.Fatalf("cloned local backend = %#v, want detached %#v", cloned.PromptKit.LocalBackend, want)
}
cloned.PromptKit.LocalBackend.Endpoint = "http://clone.example/v1"
if *cfg.PromptKit.LocalBackend != want {
t.Fatalf("mutating clone changed source config: %#v", cfg.PromptKit.LocalBackend)
}
redacted := cfg.Redacted()
if redacted.PromptKit.LocalBackend == cfg.PromptKit.LocalBackend || *redacted.PromptKit.LocalBackend != want {
t.Fatalf("redacted local backend = %#v, want detached %#v", redacted.PromptKit.LocalBackend, want)
}
data, err := json.Marshal(cfg)
if err != nil {
t.Fatalf("json.Marshal() error = %v", err)
}
var payload struct {
PromptKit map[string]json.RawMessage `json:"promptkit"`
}
if err := json.Unmarshal(data, &payload); err != nil {
t.Fatalf("json.Unmarshal() error = %v", err)
}
localJSON, ok := payload.PromptKit["local_backend"]
if !ok {
t.Fatalf("runtime PromptKit JSON keys = %v, want local_backend", payload.PromptKit)
}
var localPayload map[string]json.RawMessage
if err := json.Unmarshal(localJSON, &localPayload); err != nil {
t.Fatalf("unmarshal local_backend JSON: %v", err)
}
if _, ok := localPayload["endpoint"]; !ok {
t.Fatalf("runtime local_backend JSON keys = %v, want endpoint", localPayload)
}
if _, ok := localPayload["concurrency_limit"]; !ok {
t.Fatalf("runtime local_backend JSON keys = %v, want concurrency_limit", localPayload)
}
})
}
}
func TestFilePromptKitLocalBackendRequiresEndpoint(t *testing.T) {
for _, tt := range []struct {
name string
yaml string
}{
{name: "missing", yaml: "version: 4\npromptkit:\n local_backend: {}\n"},
{name: "empty", yaml: "version: 4\npromptkit:\n local_backend:\n endpoint: ''\n"},
{name: "blank", yaml: "version: 4\npromptkit:\n local_backend:\n endpoint: ' '\n"},
} {
t.Run(tt.name, func(t *testing.T) {
file := parseFileConfig(t, tt.yaml)
cfg := Default()
err := cfg.ApplyFileConfig(file)
if err == nil || !strings.Contains(err.Error(), "promptkit.local_backend.endpoint") {
t.Fatalf("ApplyFileConfig() error = %v, want endpoint field context", err)
}
})
}
}
func TestFilePromptKitExplicitEmptyProfileSourcesAreRejected(t *testing.T) {
for _, field := range []string{"profile_dir", "profile_file"} {
t.Run(field, func(t *testing.T) {
file := parseFileConfig(t, "version: 4\npromptkit:\n "+field+": ''\n")
cfg := Default()
err := cfg.ApplyFileConfig(file)
if err == nil || !strings.Contains(err.Error(), "promptkit."+field+" must not be empty") {
t.Fatalf("ApplyFileConfig() error = %v, want explicit-empty rejection", err)
}
})
}
}
func TestFilePromptKitProfileSourcesRemainMutuallyExclusive(t *testing.T) {
cfg := applyFileConfig(t, `version: 4
promptkit:
profile_dir: ./profiles
profile_file: ./profiles.yml
`)
if err := cfg.Validate(); err == nil || !strings.Contains(err.Error(), "promptkit profile_dir and profile_file are mutually exclusive") {
t.Fatalf("Validate() error = %v, want mutually exclusive profile sources", err)
}
}
func TestFileConfigMissingVersionIsReportedBeforeFieldDecoding(t *testing.T) {
_, err := ParseFileConfigYAML([]byte("workspace:\n directory: /tmp/old\n"))
if err == nil || !strings.Contains(err.Error(), "config version is required") {
t.Fatalf("missing version error = %v", err)
}
}
func TestFileConfigVersion3ReportsPromptKitMigration(t *testing.T) {
_, err := ParseFileConfigYAML([]byte("version: 3\nscriptorium:\n profile_dir: ./profiles\n"))
if err == nil ||
!strings.Contains(err.Error(), `change "version: 3" to "version: 4"`) ||
!strings.Contains(err.Error(), `rename "scriptorium:" to "promptkit:"`) {
t.Fatalf("version 3 error = %v, want actionable version and section migration", err)
}
}
func TestFileConfigRejectsUnknownCurrentAndRemovedFields(t *testing.T) {
tests := []struct {
name string
yaml string
want string
}{
{
name: "removed diagnostics",
yaml: "version: 4\ndiagnostics: {}\n",
want: "field diagnostics not found",
},
{
name: "removed llm profiles",
yaml: "version: 4\nllm_profiles: {}\n",
want: "field llm_profiles not found",
},
{
name: "removed scriptorium section",
yaml: "version: 4\nscriptorium: {}\n",
want: "field scriptorium not found",
},
{
name: "version 2 migration",
yaml: "version: 2\nworkspace:\n directory: /tmp/old\n",
want: "version 2-to-3 migration",
},
{
name: "pipeline field",
yaml: "version: 4\npipelines:\n main:\n unknown: true\n",
want: "field unknown not found",
},
{
name: "lane field",
yaml: "version: 4\npipelines:\n main:\n artifacts:\n spells:\n unknown: true\n",
want: "field unknown not found",
},
{
name: "module binding field",
yaml: "version: 4\npipelines:\n main:\n input:\n module: seriatim\n unknown: true\n",
want: "field unknown not found in module binding",
},
{
name: "checkpoint field",
yaml: "version: 4\ncache:\n checkpoints:\n unknown: true\n",
want: "field unknown not found",
},
{
name: "checkpoint enabled type",
yaml: "version: 4\ncache:\n checkpoints:\n enabled: definitely\n",
want: "cannot unmarshal",
},
{
name: "local backend field",
yaml: "version: 4\npromptkit:\n local_backend:\n endpoint: http://localhost:8000/v1\n unknown: true\n",
want: "field unknown not found",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
_, err := ParseFileConfigYAML([]byte(tt.yaml))
if err == nil || !strings.Contains(err.Error(), tt.want) {
t.Fatalf("error = %v, want context %q", err, tt.want)
}
})
}
}
func TestFileConfigModuleBindingsPreserveFormsAndValidatorPresence(t *testing.T) {
cfg := applyFileConfig(t, `version: 4
pipelines:
main:
input: seriatim
chunk:
module: generic
llm_profile: chunk-profile
retries: 2
options:
max_units: 25
references:
glossary: ./glossary.md
validators: []
artifacts:
spells:
extract:
module: dnd/spells
options:
nested:
enabled: true
merge: appendorder
normalize: noop
`)
profile := cfg.Pipelines["main"]
if profile.Input.Module != "seriatim" || profile.Input.Validators.Set {
t.Fatalf("shorthand binding = %#v", profile.Input)
}
if profile.Chunk.Module != "generic" || profile.Chunk.LLMProfile != "chunk-profile" || profile.Chunk.Retries != 2 ||
!reflect.DeepEqual(profile.Chunk.Options, map[string]any{"max_units": 25}) ||
!reflect.DeepEqual(profile.Chunk.References, pipeline.ExternalReferenceMap(map[string]string{"glossary": "./glossary.md"})) {
t.Fatalf("object binding = %#v", profile.Chunk)
}
if !profile.Chunk.Validators.Set || len(profile.Chunk.Validators.Validators) != 0 {
t.Fatalf("explicit empty validators = %#v", profile.Chunk.Validators)
}
if profile.Artifacts["spells"].Extract.Module != "dnd/spells" ||
!reflect.DeepEqual(profile.Artifacts["spells"].Extract.Options, map[string]any{
"nested": map[string]any{"enabled": true},
}) {
t.Fatalf("extract binding = %#v", profile.Artifacts["spells"].Extract)
}
if profile.Artifacts["spells"].Merge.Module != "appendorder" || profile.Artifacts["spells"].Normalize.Module != "noop" {
t.Fatalf("stage shorthand bindings = %#v", profile.Artifacts["spells"])
}
}
func TestFileConfigReferencePrecedenceIsRetained(t *testing.T) {
cfg := applyFileConfig(t, `version: 4
pipelines:
main:
input: seriatim
references:
pipeline-only: ./pipeline.txt
shared: ./pipeline-shared.txt
chunk:
module: generic
references:
chunk-only: ./chunk.txt
artifacts:
spells:
references:
lane-only: ./lane.txt
shared: ./lane-shared.txt
overridden: ./lane.txt
extract:
module: dnd/spells
references:
extract-only: ./extract.txt
overridden: ./extract-overridden.txt
merge:
module: appendorder
references:
merge-only: ./merge.txt
normalize:
module: noop
references:
normalize-only: ./normalize.txt
`)
profile := cfg.Pipelines["main"]
if !reflect.DeepEqual(profile.References, pipeline.ExternalReferenceMap(map[string]string{
"pipeline-only": "./pipeline.txt",
"shared": "./pipeline-shared.txt",
})) {
t.Fatalf("pipeline references = %#v", profile.References)
}
if !reflect.DeepEqual(profile.Chunk.References, pipeline.ExternalReferenceMap(map[string]string{"chunk-only": "./chunk.txt"})) {
t.Fatalf("chunk references = %#v", profile.Chunk.References)
}
lane := profile.Artifacts["spells"]
if !reflect.DeepEqual(lane.References, pipeline.ExternalReferenceMap(map[string]string{
"lane-only": "./lane.txt",
"shared": "./lane-shared.txt",
"overridden": "./lane.txt",
})) {
t.Fatalf("lane compatibility references = %#v", lane.References)
}
if !reflect.DeepEqual(lane.Extract.References, pipeline.ExternalReferenceMap(map[string]string{
"lane-only": "./lane.txt",
"shared": "./lane-shared.txt",
"overridden": "./extract-overridden.txt",
"extract-only": "./extract.txt",
})) {
t.Fatalf("extract references = %#v", lane.Extract.References)
}
if !reflect.DeepEqual(lane.Merge.References, pipeline.ExternalReferenceMap(map[string]string{"merge-only": "./merge.txt"})) ||
!reflect.DeepEqual(lane.Normalize.References, pipeline.ExternalReferenceMap(map[string]string{"normalize-only": "./normalize.txt"})) {
t.Fatalf("merge/normalize references = %#v, %#v", lane.Merge.References, lane.Normalize.References)
}
}
func TestFileConfigStageLocalValidatorsPreserveOrderAndFields(t *testing.T) {
cfg := applyFileConfig(t, `version: 4
pipelines:
main:
input: seriatim
chunk:
module: generic
validators:
- generic/always_accept
- module: generic/valid_json
llm_profile: validator-profile
options:
schema: compact
artifacts:
spells:
extract:
module: dnd/spells
validators:
- module: extract/dnd/spells/shape
options:
strict: true
merge:
module: appendorder
validators:
- generic/always_accept
normalize:
module: noop
validators:
- module: generic/valid_json
options:
mode: normalized
`)
profile := cfg.Pipelines["main"]
chunkValidators := profile.Chunk.Validators.Validators
if !profile.Chunk.Validators.Set || len(chunkValidators) != 2 || chunkValidators[0].Module != "generic/always_accept" ||
chunkValidators[1].Module != "generic/valid_json" || chunkValidators[1].LLMProfile != "validator-profile" ||
!reflect.DeepEqual(chunkValidators[1].Options, map[string]any{"schema": "compact"}) {
t.Fatalf("chunk validators = %#v", profile.Chunk.Validators)
}
lane := profile.Artifacts["spells"]
if len(lane.Extract.Validators.Validators) != 1 || lane.Extract.Validators.Validators[0].Module != "extract/dnd/spells/shape" ||
!reflect.DeepEqual(lane.Extract.Validators.Validators[0].Options, map[string]any{"strict": true}) {
t.Fatalf("extract validators = %#v", lane.Extract.Validators)
}
if len(lane.Merge.Validators.Validators) != 1 || lane.Merge.Validators.Validators[0].Module != "generic/always_accept" {
t.Fatalf("merge validators = %#v", lane.Merge.Validators)
}
if len(lane.Normalize.Validators.Validators) != 1 || lane.Normalize.Validators.Validators[0].Module != "generic/valid_json" ||
!reflect.DeepEqual(lane.Normalize.Validators.Validators[0].Options, map[string]any{"mode": "normalized"}) {
t.Fatalf("normalize validators = %#v", lane.Normalize.Validators)
}
}
func TestFileConfigStateSectionsApplyIndependently(t *testing.T) {
cfg := applyFileConfig(t, `version: 4
promptkit:
profile_dir: ./profiles
concurrency:
total_llm: 7
output:
directory: ./output
cache:
chunk_plans:
directory: ./plans
mode: bypass
checkpoints:
enabled: true
directory: ./checkpoints
debug:
directory: ./debug
`)
if cfg.PromptKit.ProfileDir != "./profiles" || cfg.PromptKit.ProfileFile != "" {
t.Fatalf("promptkit = %#v", cfg.PromptKit)
}
if cfg.Concurrency.TotalLLM != 7 || cfg.Concurrency.StageWorkers["extract"] != 7 {
t.Fatalf("concurrency = %#v", cfg.Concurrency)
}
if cfg.Output.Directory != "./output" || cfg.Cache.ChunkPlans.Directory != "plans" || cfg.Cache.ChunkPlans.Mode != pipeline.ChunkCacheBypass ||
!cfg.Cache.Checkpoints.Enabled || cfg.Cache.Checkpoints.Directory != "checkpoints" || cfg.Debug.Directory != "./debug" {
t.Fatalf("state sections = %#v, %#v, %#v, %#v", cfg.Output, cfg.Cache, cfg.Debug, cfg.PromptKit)
}
if cfg.Output.Directory == cfg.Cache.ChunkPlans.Directory || cfg.Cache.ChunkPlans.Directory == cfg.Cache.Checkpoints.Directory || cfg.Cache.Checkpoints.Directory == cfg.Debug.Directory {
t.Fatal("state roots were coupled")
}
}
func TestFileConfigCheckpointEnabledCanBeExplicitlyDisabled(t *testing.T) {
cfg := applyFileConfig(t, "version: 4\ncache:\n checkpoints:\n enabled: true\n")
if !cfg.Cache.Checkpoints.Enabled || !cloneConfig(cfg).Cache.Checkpoints.Enabled {
t.Fatalf("enabled checkpoint config was not retained: %#v", cfg.Cache.Checkpoints)
}
file := parseFileConfig(t, "version: 4\ncache:\n checkpoints:\n enabled: false\n")
if err := cfg.ApplyFileConfig(file); err != nil {
t.Fatal(err)
}
if cfg.Cache.Checkpoints.Enabled {
t.Fatalf("explicit false checkpoint config was not applied: %#v", cfg.Cache.Checkpoints)
}
}
func TestFileConfigRejectsTrimmedKeyCollisions(t *testing.T) {
tests := []struct {
name string
yaml string
want string
}{
{
name: "pipeline ids",
yaml: "version: 4\npipelines:\n main: {}\n ' main ': {}\n",
want: "pipeline id \"main\" is duplicated after trimming",
},
{
name: "lane ids",
yaml: "version: 4\npipelines:\n main:\n artifacts:\n spells: {}\n ' spells ': {}\n",
want: "artifact lane id \"spells\" is duplicated after trimming",
},
{
name: "reference slots",
yaml: "version: 4\npipelines:\n main:\n references:\n slot: ./one.txt\n ' slot ': ./two.txt\n",
want: "reference slot \"slot\" is duplicated after trimming",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
file := parseFileConfig(t, tt.yaml)
cfg := Default()
err := cfg.ApplyFileConfig(file)
if err == nil || !strings.Contains(err.Error(), tt.want) {
t.Fatalf("ApplyFileConfig() error = %v, want context %q", err, tt.want)
}
})
}
}
func TestFileConfigParsesOrderedStepsAndReferenceSources(t *testing.T) {
file := parseFileConfig(t, `version: 4
pipelines:
session:
input: seriatim
steps:
- id: identify-npcs
artifacts:
npc_registry:
extract: dnd/npc-registry
- id: grounded-events
references:
npc_registry:
artifact:
step: identify-npcs
lane: npc_registry
artifacts:
spells:
extract: dnd/spells
`)
cfg := Default()
if err := cfg.ApplyFileConfig(file); err != nil {
t.Fatal(err)
}
profile := cfg.Pipelines["session"]
if len(profile.Steps) != 2 || profile.Steps[0].ID != "identify-npcs" || profile.Steps[1].ID != "grounded-events" {
t.Fatalf("steps = %#v", profile.Steps)
}
source := profile.Steps[1].References["npc_registry"]
if source.Artifact == nil || source.Artifact.Step != "identify-npcs" || source.Artifact.Lane != "npc_registry" {
t.Fatalf("generated source = %#v", source)
}
}
func TestFileConfigRejectsAmbiguousReferenceSourceForms(t *testing.T) {
for _, source := range []string{
"artifact: {step: a, lane: b, extra: c}",
"artifact: {step: 1, lane: b}",
"1",
} {
_, err := ParseFileConfigYAML([]byte("version: 4\npipelines:\n p:\n input: text\n references:\n slot: " + source + "\n"))
if err == nil {
t.Fatalf("ParseFileConfigYAML(%q) error = nil", source)
}
}
}
func TestFileConfigRejectsEmptyAndAmbiguousPipelineShapes(t *testing.T) {
tests := []struct {
name string
yaml string
want string
}{
{
name: "empty steps",
yaml: "version: 4\npipelines:\n p:\n input: text\n steps: []\n",
want: "at least one ordered step",
},
{
name: "both forms",
yaml: "version: 4\npipelines:\n p:\n input: text\n artifacts: {}\n steps: []\n",
want: "both artifacts and steps",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
file := parseFileConfig(t, tt.yaml)
cfg := Default()
err := cfg.ApplyFileConfig(file)
if err == nil || !strings.Contains(err.Error(), tt.want) {
t.Fatalf("ApplyFileConfig() error = %v, want context %q", err, tt.want)
}
})
}
}
func TestLoadFileConfigReportsPathAndOperationContext(t *testing.T) {
dir := t.TempDir()
missing := filepath.Join(dir, "missing.yml")
_, err := LoadFileConfig(missing)
if err == nil || !strings.Contains(err.Error(), "read config file") || !strings.Contains(err.Error(), missing) {
t.Fatalf("missing-file error = %v", err)
}
malformed := filepath.Join(dir, "malformed.yml")
if err := os.WriteFile(malformed, []byte("version: [\n"), 0o600); err != nil {
t.Fatal(err)
}
_, err = LoadFileConfig(malformed)
if err == nil || !strings.Contains(err.Error(), "parse config file") || !strings.Contains(err.Error(), malformed) {
t.Fatalf("malformed-file error = %v", err)
}
}
func parseFileConfig(t *testing.T, source string) FileConfig {
t.Helper()
file, err := ParseFileConfigYAML([]byte(source))
if err != nil {
t.Fatalf("ParseFileConfigYAML() error = %v", err)
}
return file
}
func applyFileConfig(t *testing.T, source string) Config {
t.Helper()
cfg := Default()
if err := cfg.ApplyFileConfig(parseFileConfig(t, source)); err != nil {
t.Fatalf("ApplyFileConfig() error = %v", err)
}
return cfg
}

4
internal/core/config/loaded_config.go
View File

@@ -87,10 +87,6 @@ func documentToConfig(document Document) (Config, error) {
config.Concurrency.TotalLLM = *document.Concurrency.TotalLLM
}
}
if workers, ok := config.Concurrency.StageWorkers["extract"]; ok {
config.Concurrency.extractWorkersConfigured = true
config.Concurrency.defaultedExtractWorkers = workers
}
if document.PromptKit != nil {
if document.PromptKit.ProfileDir != nil {
config.PromptKit.ProfileDir = *document.PromptKit.ProfileDir

44
internal/core/config/redaction.go
View File

@@ -8,25 +8,6 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
func (c Config) Redacted() Config {
return redactConfig(cloneConfig(c))
}
func (c Config) RedactedSummaryPayload() any {
return c.Redacted()
}
func (e EffectiveConfig) RedactedSummaryPayload() any {
return EffectiveConfig{
Config: e.Config.Redacted(),
PipelineID: e.PipelineID,
Only: append([]string(nil), e.Only...),
ReferenceOverrides: append([]pipeline.ReferenceBinding(nil), e.ReferenceOverrides...),
ReferenceUnbinds: append([]pipeline.ReferenceUnbind(nil), e.ReferenceUnbinds...),
ResolvedPipeline: cloneResolvedPipeline(e.ResolvedPipeline),
}
}
func (e EffectiveConfig) RedactedResolvedPipelinePayload() pipeline.ResolvedPipeline {
return cloneResolvedPipeline(e.ResolvedPipeline)
}
@@ -92,31 +73,6 @@ func cloneResolvedArtifactLane(in pipeline.ResolvedArtifactLane) pipeline.Resolv
return out
}
func redactConfig(cfg Config) Config {
for id, profile := range cfg.Pipelines {
profile.Input = redactBinding(profile.Input)
profile.Chunk = redactBinding(profile.Chunk)
profile.Output = redactBinding(profile.Output)
redactLanes := func(lanes map[string]pipeline.ArtifactLaneProfile) {
for laneID, lane := range lanes {
lane.Extract = redactBinding(lane.Extract)
lane.Merge = redactBinding(lane.Merge)
lane.Normalize = redactBinding(lane.Normalize)
for i := range lane.Validators {
lane.Validators[i] = redactBinding(lane.Validators[i])
}
lanes[laneID] = lane
}
}
redactLanes(profile.Artifacts)
for i := range profile.Steps {
redactLanes(profile.Steps[i].Artifacts)
}
cfg.Pipelines[id] = profile
}
return cfg
}
func redactBinding(binding pipeline.ModuleBinding) pipeline.ModuleBinding {
binding.Options = redactOptions(binding.Options)
for i := range binding.Validators.Validators {

110
internal/core/config/redaction_test.go
View File

@@ -114,83 +114,6 @@ func TestRedactedResolvedPipelinePayloadRedactsEveryBinding(t *testing.T) {
}
}
func TestRedactedEffectiveConfigPayloadDoesNotAliasSource(t *testing.T) {
binding := redactionTestBinding("effective")
effective := EffectiveConfig{
Config: Config{Pipelines: map[string]pipeline.PipelineProfile{
"redaction-test": {Input: binding},
}},
ResolvedPipeline: pipeline.ResolvedPipeline{Input: binding},
}
payload := effective.RedactedSummaryPayload().(EffectiveConfig)
payload.Config.Pipelines["redaction-test"].Input.Options["safe"] = "mutated"
payload.ResolvedPipeline.Input.Options["safe"] = "mutated"
assertRedactionTestBindingUnchanged(t, effective.Config.Pipelines["redaction-test"].Input, "effective")
assertRedactionTestBindingUnchanged(t, effective.ResolvedPipeline.Input, "effective")
}
func TestRedactedSummaryPayloadsCoverEveryEffectiveConfigBinding(t *testing.T) {
bindings := map[string]pipeline.ModuleBinding{}
for _, name := range []string{"input", "chunk", "output", "extract", "merge", "normalize", "lane-validator"} {
bindings[name] = redactionTestBinding("summary-" + name)
}
effective := EffectiveConfig{
Config: Config{Pipelines: map[string]pipeline.PipelineProfile{
"redaction-test": {
Input: bindings["input"],
Chunk: bindings["chunk"],
Output: bindings["output"],
Artifacts: map[string]pipeline.ArtifactLaneProfile{
"safe-lane": {
Extract: bindings["extract"],
Merge: bindings["merge"],
Normalize: bindings["normalize"],
Validators: []pipeline.ModuleBinding{bindings["lane-validator"]},
},
},
},
}},
ResolvedPipeline: pipeline.ResolvedPipeline{
Input: bindings["input"],
Chunk: bindings["chunk"],
Output: bindings["output"],
Steps: []pipeline.ResolvedPipelineStep{{
ID: "default",
ArtifactLanes: []pipeline.ResolvedArtifactLane{{
ID: "safe-lane",
Extract: bindings["extract"],
Merge: bindings["merge"],
Normalize: bindings["normalize"],
Validators: []pipeline.ModuleBinding{bindings["lane-validator"]},
}},
}},
},
}
payload, ok := effective.RedactedSummaryPayload().(EffectiveConfig)
if !ok {
t.Fatal("RedactedSummaryPayload() returned an unexpected type")
}
encoded, err := json.Marshal(payload)
if err != nil {
t.Fatal(err)
}
text := string(encoded)
for name := range bindings {
if strings.Contains(text, "summary-"+name+"-secret") || strings.Contains(text, "summary-"+name+"-nested-secret") {
t.Fatalf("summary payload contains sensitive option for %q: %s", name, text)
}
if !strings.Contains(text, "summary-"+name+"-safe") {
t.Fatalf("summary payload omitted safe option for %q: %s", name, text)
}
}
if !strings.Contains(text, "[REDACTED]") {
t.Fatalf("summary payload contains no redaction marker: %s", text)
}
}
func TestRedactedResolvedPipelinePayloadHandlesTypedOptionContainers(t *testing.T) {
type optionMap map[string]string
type optionList []optionMap
@@ -225,39 +148,6 @@ 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,

1
internal/core/config/validation.go
View File

@@ -9,7 +9,6 @@ import (
)
func (c Config) Validate() error {
c.Concurrency.recomputeStageWorkerDefaults()
if err := validatePromptKit(c.PromptKit); err != nil {
return err
}

4
internal/core/config/validation_contract_test.go
View File

@@ -25,7 +25,6 @@ func TestValidateConcurrencyRules(t *testing.T) {
setup: func(cfg *Config) {
cfg.Concurrency.TotalLLM = 3
cfg.Concurrency.StageWorkers = map[string]int{"extract": 0}
cfg.Concurrency.extractWorkersConfigured = true
},
want: "stage_workers.extract must be between 1",
},
@@ -34,7 +33,6 @@ func TestValidateConcurrencyRules(t *testing.T) {
setup: func(cfg *Config) {
cfg.Concurrency.TotalLLM = 3
cfg.Concurrency.StageWorkers = map[string]int{"extract": 4}
cfg.Concurrency.extractWorkersConfigured = true
},
want: "stage_workers.extract must be between 1",
},
@@ -43,7 +41,6 @@ func TestValidateConcurrencyRules(t *testing.T) {
setup: func(cfg *Config) {
cfg.Concurrency.TotalLLM = 3
cfg.Concurrency.StageWorkers = map[string]int{"extract": 1}
cfg.Concurrency.extractWorkersConfigured = true
},
},
{
@@ -51,7 +48,6 @@ func TestValidateConcurrencyRules(t *testing.T) {
setup: func(cfg *Config) {
cfg.Concurrency.TotalLLM = 3
cfg.Concurrency.StageWorkers = map[string]int{"extract": 3}
cfg.Concurrency.extractWorkersConfigured = true
},
},
{

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

@@ -4,17 +4,19 @@ import (
"strings"
"testing"
configkit "gitea.maximumdirect.net/eric/ConfigKit"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
func TestValidationPolicyFileConfigurationIsStrictAndPresenceAware(t *testing.T) {
const valid = `version: 4
const valid = `version: 5
pipelines:
main:
validation_policy:
producer_structural_failure: reject_output
semantic_rejection: fail_run
input: seriatim
input:
module: seriatim
chunk:
module: generic
validation_policy:
@@ -26,7 +28,11 @@ pipelines:
validation_policy:
semantic_rejection: reject_output
`
cfg := applyFileConfig(t, valid)
loaded, err := loadDocumentSource(configkit.Bytes("valid.yml", []byte(valid)), LoadOptions{})
if err != nil {
t.Fatal(err)
}
cfg := loaded.Config
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)
@@ -50,8 +56,8 @@ pipelines:
{"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")
if _, err := loadDocumentSource(configkit.Bytes("invalid.yml", []byte(test.yaml)), LoadOptions{}); err == nil {
t.Fatal("loadDocumentSource() error = nil, want strict validation-policy rejection")
}
})
}

10
internal/core/debugbundle/bundle_test.go
View File

@@ -91,9 +91,6 @@ func TestSummaryWriterWritesEverySummaryArtifact(t *testing.T) {
if err := summary.WriteInvocation(Invocation{Operation: "run"}); err != nil {
t.Fatal(err)
}
if err := summary.WriteRedactedEffectiveConfig(testRedactedSummaryPayload{}); err != nil {
t.Fatal(err)
}
if err := summary.WriteEffectiveConfig(testEffectiveConfigWriter{content: "version: 5\n"}); err != nil {
t.Fatal(err)
}
@@ -124,7 +121,6 @@ func TestSummaryWriterWritesEverySummaryArtifact(t *testing.T) {
for _, name := range []string{
ArtifactInvocationMetadata,
ArtifactEffectiveConfig,
ArtifactEffectiveConfigYAML,
ArtifactResolvedPipeline,
ArtifactResolvedReferences,
@@ -236,12 +232,6 @@ func TestSummaryWriterInternalWritesConfineArtifacts(t *testing.T) {
}
}
type testRedactedSummaryPayload struct{}
func (testRedactedSummaryPayload) RedactedSummaryPayload() any {
return map[string]any{"redacted": true}
}
type testEffectiveConfigWriter struct {
content string
err error

8
internal/core/debugbundle/summary.go
View File

@@ -15,7 +15,6 @@ import (
const (
ArtifactInvocationMetadata = "invocation.json"
ArtifactEffectiveConfig = "effective-config.json"
ArtifactEffectiveConfigYAML = "effective-config.yml"
ArtifactResolvedPipeline = "resolved-pipeline.json"
ArtifactResolvedReferences = "resolved-references.json"
@@ -27,7 +26,6 @@ const (
ArtifactErrorLog = "error.log"
)
type RedactedSummaryPayload interface{ RedactedSummaryPayload() any }
type EffectiveConfigWriter interface{ WriteEffective(io.Writer) error }
type RedactedResolvedPipelinePayload interface {
RedactedResolvedPipelinePayload() pipeline.ResolvedPipeline
@@ -85,12 +83,6 @@ func (w *SummaryWriter) WriteInvocation(payload Invocation) error {
}
return w.writeJSON(ArtifactInvocationMetadata, payload)
}
func (w *SummaryWriter) WriteRedactedEffectiveConfig(payload RedactedSummaryPayload) error {
if payload == nil {
return fmt.Errorf("redacted summary payload must not be nil")
}
return w.writeJSON(ArtifactEffectiveConfig, payload.RedactedSummaryPayload())
}
func (w *SummaryWriter) WriteEffectiveConfig(payload EffectiveConfigWriter) error {
if payload == nil {
return fmt.Errorf("effective configuration writer must not be nil")

43
internal/modules/integration/config_test.go Normal file
View File

@@ -0,0 +1,43 @@
package integration_test
import (
"os"
"path/filepath"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/core/config"
)
func loadIntegrationConfig(t *testing.T, path string) config.Config {
t.Helper()
loaded, err := config.Load(path, config.LoadOptions{})
if err != nil {
t.Fatalf("load configuration %q: %v", path, err)
}
return loaded.RuntimeConfig()
}
func loadIntegrationConfigText(t *testing.T, content string) config.Config {
t.Helper()
path := filepath.Join(t.TempDir(), "config.yml")
if err := os.WriteFile(path, []byte(content), 0o600); err != nil {
t.Fatal(err)
}
return loadIntegrationConfig(t, path)
}
func configFromYAML(content string) (config.Config, error) {
directory, err := os.MkdirTemp("", "notarius-integration-config-")
if err != nil {
return config.Config{}, err
}
path := filepath.Join(directory, "config.yml")
if err := os.WriteFile(path, []byte(content), 0o600); err != nil {
return config.Config{}, err
}
loaded, err := config.Load(path, config.LoadOptions{})
if err != nil {
return config.Config{}, err
}
return loaded.RuntimeConfig(), nil
}

26
internal/modules/integration/dnd_itemoccurrences_runner_test.go
View File

@@ -10,18 +10,18 @@ import (
func TestItemOccurrenceConfigurationRequiresEarlierItemRegistry(t *testing.T) {
registries := productionNPCRegistries(t)
cfg, err := configFromYAML(`
version: 4
version: 5
pipelines:
items:
input: seriatim
chunk: generic
input: {module: seriatim}
chunk: {module: generic}
steps:
- id: identify-items
artifacts:
registry:
extract: dnd/item-registry
merge: appendorder
normalize: dnd/item-registry
extract: {module: dnd/item-registry}
merge: {module: appendorder}
normalize: {module: dnd/item-registry}
- id: record-occurrences
references:
item_registry:
@@ -30,9 +30,9 @@ pipelines:
lane: registry
artifacts:
occurrences:
extract: dnd/item-occurrences
merge: appendorder
normalize: dnd/item-occurrences
extract: {module: dnd/item-occurrences}
merge: {module: appendorder}
normalize: {module: dnd/item-occurrences}
`)
if err != nil {
t.Fatal(err)
@@ -42,16 +42,16 @@ pipelines:
}
broken, err := configFromYAML(strings.Replace(`
version: 4
version: 5
pipelines:
items:
input: seriatim
chunk: generic
input: {module: seriatim}
chunk: {module: generic}
steps:
- id: record-occurrences
artifacts:
occurrences:
extract: dnd/item-occurrences
extract: {module: dnd/item-occurrences}
`, "record-occurrences", "record-occurrences", 1))
if err != nil {
t.Fatal(err)

41
internal/modules/integration/dnd_location_registry_runner_test.go
View File

@@ -99,11 +99,8 @@ func TestLocationOccurrenceConsumerDoesNotRunAfterRejectedRegistry(t *testing.T)
func TestLocationOccurrenceConfigurationRequiresEarlierRegistry(t *testing.T) {
registries := productionNPCRegistries(t)
cfg, err := configFromYAML(strings.Replace(locationPipelineConfig, "step: identify-locations", "step: track-location-occurrences", 1))
if err != nil {
t.Fatal(err)
}
_, err = cfg.Resolve(config.ResolveInput{PipelineID: "dnd-locations-fixture", Catalog: moduleCatalog(registries)})
cfg := loadIntegrationConfigText(t, strings.Replace(locationPipelineConfig, "step: identify-locations", "step: track-location-occurrences", 1))
_, err := cfg.Resolve(config.ResolveInput{PipelineID: "dnd-locations-fixture", Catalog: moduleCatalog(registries)})
if err == nil || !strings.Contains(err.Error(), "earlier step") {
t.Fatalf("Resolve() error = %v, want an earlier generated registry requirement", err)
}
@@ -129,10 +126,7 @@ func TestLocationOccurrenceCheckpointTracksGeneratedRegistry(t *testing.T) {
func resolveLocationPipeline(t *testing.T, registries pipeline.Registries) pipeline.ResolvedPipeline {
t.Helper()
cfg, err := configFromYAML(locationPipelineConfig)
if err != nil {
t.Fatal(err)
}
cfg := loadIntegrationConfigText(t, locationPipelineConfig)
effective, err := cfg.Resolve(config.ResolveInput{PipelineID: "dnd-locations-fixture", Catalog: moduleCatalog(registries)})
if err != nil {
t.Fatalf("Resolve() error = %v", err)
@@ -144,26 +138,15 @@ func resolveLocationPipeline(t *testing.T, registries pipeline.Registries) pipel
return resolved
}
func configFromYAML(content string) (config.Config, error) {
fileConfig, err := config.ParseFileConfigYAML([]byte(content))
if err != nil {
return config.Config{}, err
}
cfg := config.Default()
if err := cfg.ApplyFileConfig(fileConfig); err != nil {
return config.Config{}, err
}
return cfg, nil
}
const locationPipelineConfig = `version: 4
const locationPipelineConfig = `version: 5
cache:
chunk_plans:
mode: bypass
checkpoints: {}
pipelines:
dnd-locations-fixture:
input: seriatim
input:
module: seriatim
output:
module: json
options:
@@ -174,9 +157,9 @@ pipelines:
- id: identify-locations
artifacts:
locations:
extract: dnd/location-registry
merge: appendorder
normalize: dnd/location-registry
extract: {module: dnd/location-registry}
merge: {module: appendorder}
normalize: {module: dnd/location-registry}
- id: track-location-occurrences
references:
location_registry:
@@ -185,9 +168,9 @@ pipelines:
lane: locations
artifacts:
occurrences:
extract: dnd/location-occurrences
merge: appendorder
normalize: dnd/location-occurrences
extract: {module: dnd/location-occurrences}
merge: {module: appendorder}
normalize: {module: dnd/location-occurrences}
`
type locationHandoffLLMClient struct {

10
internal/modules/integration/dnd_npc_grounded_test.go
View File

@@ -429,15 +429,7 @@ func assertCurrentEvidence(t *testing.T, references []source.SourceRef) {
func loadGroundedPipelineConfig(t *testing.T) config.Config {
t.Helper()
fileConfig, err := config.LoadFileConfig(repositoryPathForIntegration("internal", "modules", "integration", "testdata", "dnd_npc_grounded_pipeline.yml"))
if err != nil {
t.Fatalf("LoadFileConfig() error = %v", err)
}
cfg := config.Default()
if err := cfg.ApplyFileConfig(fileConfig); err != nil {
t.Fatalf("ApplyFileConfig() error = %v", err)
}
return cfg
return loadIntegrationConfig(t, repositoryPathForIntegration("internal", "modules", "integration", "testdata", "dnd_npc_grounded_pipeline.yml"))
}
func configureGroundedCampaignReferences(t *testing.T, cfg *config.Config) map[string]string {

15
internal/modules/integration/dnd_npc_occurrences_runner_test.go
View File

@@ -4,7 +4,6 @@ import (
"context"
"encoding/json"
"fmt"
"os"
"reflect"
"strings"
"sync"
@@ -168,19 +167,7 @@ func resolveNPCOccurrencePipeline(t *testing.T, registries pipeline.Registries)
func loadNPCOccurrencePipelineConfig(t *testing.T) config.Config {
t.Helper()
data, err := os.ReadFile("testdata/dnd_npc_occurrences_pipeline.yml")
if err != nil {
t.Fatalf("ReadFile(dnd_npc_occurrences_pipeline.yml) error = %v", err)
}
fileConfig, err := config.ParseFileConfigYAML(data)
if err != nil {
t.Fatalf("ParseFileConfigYAML() error = %v", err)
}
result := config.Default()
if err := result.ApplyFileConfig(fileConfig); err != nil {
t.Fatalf("ApplyFileConfig() error = %v", err)
}
return result
return loadIntegrationConfig(t, "testdata/dnd_npc_occurrences_pipeline.yml")
}
func normalizedLane(t *testing.T, output pipeline.RunOutput, laneID string) contracts.SerializedOutput {

14
internal/modules/integration/dnd_npc_registry_runner_test.go
View File

@@ -331,19 +331,7 @@ func moduleCatalog(registries pipeline.Registries) pipeline.ModuleCatalog {
func loadNPCPipelineConfig(t *testing.T) config.Config {
t.Helper()
data, err := os.ReadFile("testdata/dnd_npc_registry_pipeline.yml")
if err != nil {
t.Fatalf("ReadFile(dnd_npc_registry_pipeline.yml) error = %v", err)
}
fileConfig, err := config.ParseFileConfigYAML(data)
if err != nil {
t.Fatalf("ParseFileConfigYAML() error = %v", err)
}
cfg := config.Default()
if err := cfg.ApplyFileConfig(fileConfig); err != nil {
t.Fatalf("ApplyFileConfig() error = %v", err)
}
return cfg
return loadIntegrationConfig(t, "testdata/dnd_npc_registry_pipeline.yml")
}
func readNPCFixture(t *testing.T) []byte {

15
internal/modules/integration/dnd_spells_config_test.go
View File

@@ -2,7 +2,6 @@ package integration_test
import (
"context"
"os"
"strings"
"testing"
@@ -121,19 +120,7 @@ func dndCapabilityCatalog(t *testing.T, inputSpec, extractorSpec pipeline.Module
func loadDNDSpellsPipelineConfig(t *testing.T) config.Config {
t.Helper()
data, err := os.ReadFile("testdata/pipeline.yml")
if err != nil {
t.Fatalf("ReadFile(pipeline.yml) error = %v, want nil", err)
}
fileCfg, err := config.ParseFileConfigYAML(data)
if err != nil {
t.Fatalf("ParseFileConfigYAML() error = %v, want nil", err)
}
cfg := config.Default()
if err := cfg.ApplyFileConfig(fileCfg); err != nil {
t.Fatalf("ApplyFileConfig() error = %v, want nil", err)
}
return cfg
return loadIntegrationConfig(t, "testdata/pipeline.yml")
}
type dndSpellsCatalogSpecs struct {

20
internal/modules/integration/testdata/dnd_npc_grounded_pipeline.yml vendored
View File

@@ -1,4 +1,4 @@
version: 4
version: 5
output:
directory: ./notarius-output
cache:
@@ -9,16 +9,16 @@ debug:
directory: ./notarius-debug
pipelines:
dnd-npc-grounded:
input: seriatim
input: {module: seriatim}
steps:
- id: identify-npcs
artifacts:
npc_registry:
extract: dnd/npc-registry
normalize: dnd/npc-registry
extract: {module: dnd/npc-registry}
normalize: {module: dnd/npc-registry}
scene-descriptions:
extract: dnd/scene-descriptions
normalize: dnd/scene-descriptions
extract: {module: dnd/scene-descriptions}
normalize: {module: dnd/scene-descriptions}
- id: grounded-events
references:
npc_registry:
@@ -31,8 +31,8 @@ pipelines:
lane: scene-descriptions
artifacts:
spells:
extract: dnd/spells
normalize: dnd/spells
extract: {module: dnd/spells}
normalize: {module: dnd/spells}
combat:
extract: dnd/combat-turns
normalize: dnd/combat-turns
extract: {module: dnd/combat-turns}
normalize: {module: dnd/combat-turns}

12
internal/modules/integration/testdata/dnd_npc_occurrences_pipeline.yml vendored
View File

@@ -1,4 +1,4 @@
version: 4
version: 5
output:
directory: ./notarius-output
cache:
@@ -9,13 +9,13 @@ debug:
directory: ./notarius-debug
pipelines:
dnd-npc-occurrences-fixture:
input: seriatim
input: {module: seriatim}
steps:
- id: identify-npcs
artifacts:
npc_registry:
extract: dnd/npc-registry
normalize: dnd/npc-registry
extract: {module: dnd/npc-registry}
normalize: {module: dnd/npc-registry}
- id: extract-occurrences
references:
npc_registry:
@@ -24,5 +24,5 @@ pipelines:
lane: npc_registry
artifacts:
occurrences:
extract: dnd/npc-occurrences
normalize: dnd/npc-occurrences
extract: {module: dnd/npc-occurrences}
normalize: {module: dnd/npc-occurrences}

10
internal/modules/integration/testdata/dnd_npc_registry_pipeline.yml vendored
View File

@@ -1,4 +1,4 @@
version: 4
version: 5
output:
directory: ./notarius-output
cache:
@@ -9,12 +9,12 @@ debug:
directory: ./notarius-debug
pipelines:
dnd-npc-registry-fixture:
input: seriatim
chunk: generic
input: {module: seriatim}
chunk: {module: generic}
artifacts:
npc_registry:
extract:
module: dnd/npc-registry
retries: 2
normalize: dnd/npc-registry
output: json
normalize: {module: dnd/npc-registry}
output: {module: json}

14
internal/modules/integration/testdata/pipeline.yml vendored
View File

@@ -1,4 +1,4 @@
version: 4
version: 5
output:
directory: ./notarius-output
cache:
@@ -9,11 +9,11 @@ debug:
directory: ./notarius-debug
pipelines:
dnd-spells-fixture:
input: seriatim
chunk: fake/chunk
input: {module: seriatim}
chunk: {module: fake/chunk}
artifacts:
spells:
extract: dnd/spells
merge: appendorder
normalize: noop
output: json
extract: {module: dnd/spells}
merge: {module: appendorder}
normalize: {module: noop}
output: {module: json}