Switch config to Scriptorium profiles

This commit is contained in:
2026-07-05 18:03:23 +00:00
parent 49d94cc2e9
commit 0fc740470f
22 changed files with 319 additions and 797 deletions

View File

@@ -4,34 +4,25 @@ import (
"bytes"
"fmt"
"os"
"regexp"
"sort"
"strings"
"time"
"gitea.maximumdirect.net/eric/notarius/internal/core/diagnostics"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gopkg.in/yaml.v3"
)
var envVarNamePattern = regexp.MustCompile(`^[A-Za-z_][A-Za-z0-9_]*$`)
type FileConfig struct {
Version int `yaml:"version"`
LLMProfiles map[string]FileLLMProfile `yaml:"llm_profiles,omitempty"`
Scriptorium *FileScriptoriumConfig `yaml:"scriptorium,omitempty"`
Pipelines map[string]FilePipelineProfile `yaml:"pipelines,omitempty"`
Concurrency *FileConcurrencyConfig `yaml:"concurrency,omitempty"`
Diagnostics *FileDiagnosticsConfig `yaml:"diagnostics,omitempty"`
}
type FileLLMProfile struct {
Provider *string `yaml:"provider,omitempty"`
BaseURL *string `yaml:"base_url,omitempty"`
Model *string `yaml:"model,omitempty"`
APIKeyEnv *string `yaml:"api_key_env,omitempty"`
Timeout *fileDurationSeconds `yaml:"timeout,omitempty"`
MaxRetries *int `yaml:"max_retries,omitempty"`
MaxConcurrency *int `yaml:"max_concurrency,omitempty"`
type FileScriptoriumConfig struct {
ProfileDir *string `yaml:"profile_dir,omitempty"`
ProfileFile *string `yaml:"profile_file,omitempty"`
}
type FilePipelineProfile struct {
@@ -59,42 +50,6 @@ type FileDiagnosticsConfig struct {
Retention *string `yaml:"retention,omitempty"`
}
type fileDurationSeconds struct {
seconds int
}
func (d *fileDurationSeconds) UnmarshalYAML(node *yaml.Node) error {
if node.Kind != yaml.ScalarNode {
return fmt.Errorf("must be an integer seconds value or duration string")
}
if node.Tag == "!!int" {
var seconds int
if err := node.Decode(&seconds); err != nil {
return fmt.Errorf("must be an integer seconds value or duration string")
}
d.seconds = seconds
return nil
}
var raw string
if err := node.Decode(&raw); err != nil {
return fmt.Errorf("must be an integer seconds value or duration string")
}
duration, err := time.ParseDuration(strings.TrimSpace(raw))
if err != nil {
return fmt.Errorf("invalid duration %q", raw)
}
if duration%time.Second != 0 {
return fmt.Errorf("duration %q must resolve to whole seconds", raw)
}
d.seconds = int(duration / time.Second)
return nil
}
func (d fileDurationSeconds) Seconds() int {
return d.seconds
}
type fileModuleBinding struct {
Module string
LLMProfile string
@@ -196,23 +151,17 @@ func (c *Config) ApplyFileConfigWithLookup(fileCfg FileConfig, lookup func(strin
}
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.LLMProfiles == nil {
c.LLMProfiles = map[string]LLMProfile{}
}
if c.Pipelines == nil {
c.Pipelines = map[string]pipeline.PipelineProfile{}
}
profileIDs, rawLLMProfileIDs, err := normalizedMapKeys(fileCfg.LLMProfiles, "llm profile id")
if err != nil {
return err
}
pipelineIDs, rawPipelineIDs, err := normalizedMapKeys(fileCfg.Pipelines, "pipeline id")
if err != nil {
return err
@@ -267,36 +216,21 @@ func (c *Config) applyFileConfigWithLookup(fileCfg FileConfig, lookup func(strin
}
}
for _, profileID := range profileIDs {
fileProfile := fileCfg.LLMProfiles[rawLLMProfileIDs[profileID]]
profile := c.LLMProfiles[profileID]
if fileProfile.Provider != nil {
profile.Provider = strings.TrimSpace(*fileProfile.Provider)
}
if fileProfile.BaseURL != nil {
profile.BaseURL = strings.TrimSpace(*fileProfile.BaseURL)
}
if fileProfile.Model != nil {
profile.Model = strings.TrimSpace(*fileProfile.Model)
}
if fileProfile.APIKeyEnv != nil {
apiKey, err := resolveAPIKeyEnv(*fileProfile.APIKeyEnv, lookup)
if err != nil {
return fmt.Errorf("llm_profiles.%s.api_key_env: %w", profileID, err)
if fileCfg.Scriptorium != nil {
if fileCfg.Scriptorium.ProfileDir != nil {
value := strings.TrimSpace(*fileCfg.Scriptorium.ProfileDir)
if value == "" {
return fmt.Errorf("scriptorium.profile_dir must not be empty when set")
}
profile.APIKeyEnv = strings.TrimSpace(*fileProfile.APIKeyEnv)
profile.APIKey = apiKey
c.Scriptorium.ProfileDir = value
}
if fileProfile.Timeout != nil {
profile.TimeoutSeconds = fileProfile.Timeout.Seconds()
if fileCfg.Scriptorium.ProfileFile != nil {
value := strings.TrimSpace(*fileCfg.Scriptorium.ProfileFile)
if value == "" {
return fmt.Errorf("scriptorium.profile_file must not be empty when set")
}
c.Scriptorium.ProfileFile = value
}
if fileProfile.MaxRetries != nil {
profile.MaxRetries = *fileProfile.MaxRetries
}
if fileProfile.MaxConcurrency != nil {
profile.MaxConcurrency = *fileProfile.MaxConcurrency
}
c.LLMProfiles[profileID] = profile
}
for _, pipelineID := range pipelineIDs {
@@ -408,21 +342,6 @@ func mergeStringMaps(base map[string]string, override map[string]string) map[str
return out
}
func resolveAPIKeyEnv(envName string, lookup func(string) (string, bool)) (string, error) {
name := strings.TrimSpace(envName)
if name == "" {
return "", fmt.Errorf("must not be empty")
}
if !envVarNamePattern.MatchString(name) {
return "", fmt.Errorf("must be an environment variable name")
}
value, ok := lookup(name)
if !ok {
return "", fmt.Errorf("%s is not set", name)
}
return value, nil
}
func normalizeOptions(options map[string]any) map[string]any {
if len(options) == 0 {
return nil