Files
kit/internal/models/custom.go
T
Ed Zynda 7a04bdfeba feat(kit): isolate viper config per Kit instance + add NewAgent (#42)
* feat(kit): isolate viper config per Kit instance + add NewAgent (#40)

- Give each kit.New()/NewAgent() call an isolated *viper.Viper store so
  multiple Kit instances in one process no longer clobber each other's
  config; runtime mutators (SetModel, SetThinkingLevel) touch only the
  owning instance, making subagent spawning and multi-Kit embedding
  race-free
- Thread the per-instance store through internal/config, internal/models
  (ProviderConfig.ConfigStore), internal/kitsetup, and the extension
  runner, with a nil -> process-global fallback so the CLI is unaffected
- Share the global store when Options.CLI != nil to preserve cobra flag
  bindings (also opted in for internal/acpserver)
- Remove viperInitMu; preserve the tri-state IsSet precedence contract
  and sdkDefaultMaxTokens floor
- Add ergonomic NewAgent + functional options (WithModel, WithStreaming,
  Ephemeral, etc.); NewAgent defaults streaming on, opt out via
  WithStreaming(false). New(ctx, *Options) behavior is unchanged
- Add config-isolation regression test and NewAgent/option coverage;
  document NewAgent and per-instance isolation in README

Fixes #40

* docs(sdk): document NewAgent options and per-instance config isolation

- Add "Functional options (NewAgent)" and "Per-instance config isolation"
  sections to the docs site SDK overview, with an options table and a
  "when to use which" constructor comparison
- Cross-reference NewAgent from the SDK options page and correct the now
  per-instance ProviderAPIKey precedence wording
- Document NewAgent + With* helpers and config isolation in pkg/kit/README
  and list NewAgent/Option in the API reference
- Show the NewAgent constructor in the SDK examples getting-started snippet

* fix(kit): correct config loading and isolate ACP sessions

- Isolate each ACP session's config store instead of sharing the global
  viper, preventing per-session SetModel/SetThinkingLevel races; seed the
  root-command flag values (model, thinking-level, provider URL/key) so
  `kit acp -m <model>` is still honored
- Run initConfig for isolated SDK stores by gating on opts.CLI instead of
  v.GetString("model"), which setSDKDefaults always populates and thus
  skipped .kit.yml / KIT_* loading for SDK callers
- Configure KIT_* env overrides unconditionally in initConfig so passing an
  explicit config file no longer disables environment variable support
- Wrap config unmarshal/validate errors with %w to preserve the error chain

* fix(kit): make Options.Streaming a *bool to honor unset

- Change Options.Streaming from bool to *bool so a zero-valued Options no
  longer forces stream=false; New only sets the key when non-nil, letting
  streaming resolve through the precedence chain (env -> config -> default
  true). This also fixes the CLI path, which never set the field
- Mirror the existing sampling-parameter pointer pattern instead of adding
  a separate StreamingSet sentinel, keeping Options internally consistent
- Update WithStreaming/NewAgent, subagent, and ACP callers to the pointer
  form; add regression tests for the nil-default and explicit opt-out paths
- Update SDK docs (README, pkg/kit/README, options page) with the ptrBool
  helper and *bool semantics

* fix(kit): inherit parent provider config in subagents

- Copy the parent's effective provider/runtime config (API key, URL,
  TLS, thinking level, max-tokens, samplers) onto child Options in
  Kit.Subagent. After the per-instance viper isolation, the child's
  isolated store only re-loaded .kit.yml / KIT_*, silently dropping
  config the parent set via programmatic Options or runtime setters
  like SetThinkingLevel
- Preserve the IsSet tri-state for max-tokens and samplers so per-model
  defaults still apply on the child when the parent left them unset
- Add TestInheritProviderConfig covering propagation, unset keys, and
  nil-safety
2026-06-02 14:41:35 +03:00

335 lines
12 KiB
Go

package models
import (
"log"
"os"
"strings"
"github.com/spf13/viper"
)
// loadCustomModelsFromConfig loads custom model definitions from the config file
// and returns them as a map of model ID -> ModelInfo. Returns nil if no custom
// models are configured. Reads from the process-global viper store (the model
// registry is a process-global singleton).
func loadCustomModelsFromConfig() map[string]ModelInfo {
return loadCustomModelsFrom(viper.GetViper())
}
// loadCustomModelsFrom loads custom model definitions from the supplied store.
// When v is nil the process-global store is used.
func loadCustomModelsFrom(v *viper.Viper) map[string]ModelInfo {
if v == nil {
v = viper.GetViper()
}
if !v.IsSet("customModels") {
return nil
}
var customModels map[string]CustomModelConfig
if err := v.UnmarshalKey("customModels", &customModels); err != nil {
log.Printf("Warning: Failed to parse customModels: %v", err)
return nil
}
result := make(map[string]ModelInfo, len(customModels))
for modelID, cfg := range customModels {
info := modelConfigToModelInfo(modelID, cfg)
result[modelID] = info
}
return result
}
// modelConfigToModelInfo converts a CustomModelConfig to a ModelInfo.
func modelConfigToModelInfo(modelID string, cfg CustomModelConfig) ModelInfo {
info := ModelInfo{
ID: modelID,
Name: cfg.Name,
Attachment: cfg.Attachment,
Reasoning: cfg.Reasoning,
Temperature: cfg.Temperature,
BaseURL: cfg.BaseURL,
APIKey: cfg.APIKey,
Cost: Cost{
Input: cfg.Cost.Input,
Output: cfg.Cost.Output,
},
Limit: Limit{
Context: cfg.Limit.Context,
Output: cfg.Limit.Output,
},
}
// Convert custom model generation params if any are set.
if p := convertGenerationParams(cfg.Params); p != nil {
info.Params = p
}
return info
}
// LoadModelSettingsFromConfig loads per-model generation parameter overrides
// from the process-global viper store. Keys are "provider/model" strings.
// Returns nil if no model settings are configured.
func LoadModelSettingsFromConfig() map[string]*GenerationParams {
return LoadModelSettingsFrom(viper.GetViper())
}
// LoadModelSettingsFrom loads per-model generation parameter overrides from the
// supplied per-instance store. When v is nil the process-global store is used.
// Keys are "provider/model" strings. Returns nil if no model settings are
// configured.
func LoadModelSettingsFrom(v *viper.Viper) map[string]*GenerationParams {
if v == nil {
v = viper.GetViper()
}
if !v.IsSet("modelSettings") {
return nil
}
var settings map[string]GenerationParamsConfig
if err := v.UnmarshalKey("modelSettings", &settings); err != nil {
log.Printf("Warning: Failed to parse modelSettings: %v", err)
return nil
}
result := make(map[string]*GenerationParams, len(settings))
for modelKey, cfg := range settings {
if p := convertGenerationParams(cfg); p != nil {
result[modelKey] = p
}
}
return result
}
// convertGenerationParams converts a GenerationParamsConfig to a GenerationParams.
// Returns nil if no parameters are set.
func convertGenerationParams(cfg GenerationParamsConfig) *GenerationParams {
p := &GenerationParams{}
any := false
if cfg.MaxTokens != nil {
p.MaxTokens = cfg.MaxTokens
any = true
}
if cfg.Temperature != nil {
p.Temperature = cfg.Temperature
any = true
}
if cfg.TopP != nil {
p.TopP = cfg.TopP
any = true
}
if cfg.TopK != nil {
p.TopK = cfg.TopK
any = true
}
if cfg.FrequencyPenalty != nil {
p.FrequencyPenalty = cfg.FrequencyPenalty
any = true
}
if cfg.PresencePenalty != nil {
p.PresencePenalty = cfg.PresencePenalty
any = true
}
if len(cfg.StopSequences) > 0 {
p.StopSequences = cfg.StopSequences
any = true
}
if cfg.ThinkingLevel != "" {
p.ThinkingLevel = ParseThinkingLevel(cfg.ThinkingLevel)
any = true
}
if cfg.SystemPrompt != "" {
p.SystemPrompt = cfg.SystemPrompt
any = true
}
if !any {
return nil
}
return p
}
// ApplyModelSettings merges per-model generation parameter defaults from the
// registry into a ProviderConfig. Model-level params are only applied for
// fields where the user has not explicitly set a value (i.e., the
// corresponding viper key is not set via CLI flag or global config).
//
// The lookup order is:
// 1. modelSettings["provider/model"] from config (highest model-level priority)
// 2. ModelInfo.Params from custom model definitions
//
// Both are overridden by explicit CLI flags / global config values.
func ApplyModelSettings(config *ProviderConfig, modelInfo *ModelInfo) {
provider, modelName, err := ParseModelString(config.ModelString)
if err != nil {
return
}
// Resolve the config store: prefer the per-instance store carried on the
// ProviderConfig (set by BuildProviderConfig / Kit.New), falling back to
// the process-global store for callers that don't thread one through.
store := config.ConfigStore
// Collect model-level params: modelSettings override > custom model params.
// modelSettings takes priority because it's the more specific/intentional config.
var params *GenerationParams
// First check modelSettings from config.
if settings := LoadModelSettingsFrom(store); settings != nil {
modelKey := provider + "/" + modelName
if p, ok := settings[modelKey]; ok {
params = p
}
}
// Fall back to ModelInfo.Params (from custom model definitions).
if params == nil && modelInfo != nil && modelInfo.Params != nil {
params = modelInfo.Params
}
if params == nil {
return
}
// Apply each parameter only when the user hasn't explicitly set it.
// We check viper.IsSet() which returns true only when the key was
// set via CLI flag, environment variable, or config file global section.
if params.MaxTokens != nil && !isExplicitlySet(store, "max-tokens") {
config.MaxTokens = *params.MaxTokens
}
if params.Temperature != nil && !isExplicitlySet(store, "temperature") {
config.Temperature = params.Temperature
}
if params.TopP != nil && !isExplicitlySet(store, "top-p") {
config.TopP = params.TopP
}
if params.TopK != nil && !isExplicitlySet(store, "top-k") {
config.TopK = params.TopK
}
if params.FrequencyPenalty != nil && !isExplicitlySet(store, "frequency-penalty") {
config.FrequencyPenalty = params.FrequencyPenalty
}
if params.PresencePenalty != nil && !isExplicitlySet(store, "presence-penalty") {
config.PresencePenalty = params.PresencePenalty
}
if len(params.StopSequences) > 0 && !isExplicitlySet(store, "stop-sequences") {
config.StopSequences = params.StopSequences
}
if params.ThinkingLevel != "" && !isExplicitlySet(store, "thinking-level") {
config.ThinkingLevel = params.ThinkingLevel
}
if params.SystemPrompt != "" && config.SystemPrompt == "" {
// Resolve file paths: if the value points to an existing file, read it.
// We check config.SystemPrompt == "" rather than isExplicitlySet because
// viper.BindPFlag causes IsSet to return true even for unset flags.
config.SystemPrompt = LoadSystemPromptValue(params.SystemPrompt)
}
}
// LoadSystemPromptValue resolves a system prompt value that may be either
// inline text or a file path. If the value is a path to an existing file,
// its contents are read and returned. Otherwise the string is returned as-is.
// This mirrors config.LoadSystemPrompt but lives in the models package to
// avoid circular dependencies.
func LoadSystemPromptValue(input string) string {
if input == "" {
return ""
}
if info, err := os.Stat(input); err == nil && !info.IsDir() {
content, err := os.ReadFile(input)
if err != nil {
log.Printf("Warning: failed to read system prompt file %q: %v", input, err)
return input
}
return strings.TrimSpace(string(content))
}
return input
}
// isExplicitlySet returns true when the user has explicitly set a config key
// via CLI flag, environment variable, or the global section of the config file.
// Model-level defaults should not override explicitly set values.
//
// The check runs against the supplied per-instance store when non-nil,
// otherwise the process-global store. This keeps the "explicit vs unset"
// precedence contract per-Kit-instance once a store is threaded through.
func isExplicitlySet(v *viper.Viper, key string) bool {
if v == nil {
v = viper.GetViper()
}
// viper.IsSet returns true if the key has been set in any of the
// data stores (flag, env, config file, default). We need to check
// whether the value was set at the global config level (not just
// as a default). For generation params, the global config keys use
// hyphenated names (e.g. "max-tokens", "top-p").
//
// Since viper merges all sources, IsSet returns true even for config
// file values. This means global config file values (e.g.
// temperature: 0.7 at the top level) will correctly take precedence
// over model-level defaults, which is the desired behavior.
return v.IsSet(key)
}
// GenerationParams holds per-model generation parameter defaults.
// These are stored on ModelInfo and applied during provider creation.
// Nil pointer fields mean "no model-level default" — the global config
// or CLI flag value (if any) will be used instead.
type GenerationParams struct {
MaxTokens *int
Temperature *float32
TopP *float32
TopK *int32
FrequencyPenalty *float32
PresencePenalty *float32
StopSequences []string
ThinkingLevel ThinkingLevel
SystemPrompt string // Per-model system prompt (inline text or file path)
}
// CustomModelConfig defines a custom model configuration loaded from the config file.
// This is a duplicate here to avoid circular dependencies with internal/config.
type CustomModelConfig struct {
Name string `json:"name" yaml:"name"`
BaseURL string `json:"baseUrl,omitempty" yaml:"baseUrl,omitempty"`
APIKey string `json:"apiKey,omitempty" yaml:"apiKey,omitempty"`
Family string `json:"family,omitempty" yaml:"family,omitempty"`
Attachment bool `json:"attachment,omitempty" yaml:"attachment,omitempty"`
Reasoning bool `json:"reasoning,omitempty" yaml:"reasoning,omitempty"`
Temperature bool `json:"temperature,omitempty" yaml:"temperature,omitempty"`
Knowledge string `json:"knowledge,omitempty" yaml:"knowledge,omitempty"`
Cost CostConfig `json:"cost" yaml:"cost"`
Limit LimitConfig `json:"limit" yaml:"limit"`
Params GenerationParamsConfig `json:"params,omitzero" yaml:"params,omitempty"`
}
// GenerationParamsConfig is the JSON/YAML-serializable form of generation
// parameter defaults. Used in both customModels[].params and modelSettings[].
type GenerationParamsConfig struct {
MaxTokens *int `json:"maxTokens,omitempty" yaml:"maxTokens,omitempty"`
Temperature *float32 `json:"temperature,omitempty" yaml:"temperature,omitempty"`
TopP *float32 `json:"topP,omitempty" yaml:"topP,omitempty"`
TopK *int32 `json:"topK,omitempty" yaml:"topK,omitempty"`
FrequencyPenalty *float32 `json:"frequencyPenalty,omitempty" yaml:"frequencyPenalty,omitempty"`
PresencePenalty *float32 `json:"presencePenalty,omitempty" yaml:"presencePenalty,omitempty"`
StopSequences []string `json:"stopSequences,omitempty" yaml:"stopSequences,omitempty"`
ThinkingLevel string `json:"thinkingLevel,omitempty" yaml:"thinkingLevel,omitempty"`
SystemPrompt string `json:"systemPrompt,omitempty" yaml:"systemPrompt,omitempty"`
}
// CostConfig defines the pricing for a custom model.
type CostConfig struct {
Input float64 `json:"input" yaml:"input"`
Output float64 `json:"output" yaml:"output"`
}
// LimitConfig defines context and output limits for a custom model.
type LimitConfig struct {
Context int `json:"context" yaml:"context"`
Output int `json:"output" yaml:"output"`
}