mirror of
https://github.com/router-for-me/CLIProxyAPIPlus.git
synced 2026-03-21 16:40:22 +00:00
feat(cliproxy): introduce global model name mappings for improved aliasing and routing
This commit is contained in:
@@ -91,6 +91,13 @@ type Config struct {
|
||||
// OAuthExcludedModels defines per-provider global model exclusions applied to OAuth/file-backed auth entries.
|
||||
OAuthExcludedModels map[string][]string `yaml:"oauth-excluded-models,omitempty" json:"oauth-excluded-models,omitempty"`
|
||||
|
||||
// ModelNameMappings defines global per-channel model name mappings.
|
||||
// These mappings affect both model listing and model routing for supported channels.
|
||||
//
|
||||
// NOTE: This does not apply to existing per-credential model alias features under:
|
||||
// codex-api-key, claude-api-key, openai-compatibility, vertex-api-key, and ampcode.
|
||||
ModelNameMappings map[string][]ModelNameMapping `yaml:"model-name-mappings,omitempty" json:"model-name-mappings,omitempty"`
|
||||
|
||||
// Payload defines default and override rules for provider payload parameters.
|
||||
Payload PayloadConfig `yaml:"payload" json:"payload"`
|
||||
|
||||
@@ -137,6 +144,13 @@ type RoutingConfig struct {
|
||||
Strategy string `yaml:"strategy,omitempty" json:"strategy,omitempty"`
|
||||
}
|
||||
|
||||
// ModelNameMapping defines a model ID rename mapping for a specific channel.
|
||||
// It maps the original model name (From) to the client-visible alias (To).
|
||||
type ModelNameMapping struct {
|
||||
From string `yaml:"from" json:"from"`
|
||||
To string `yaml:"to" json:"to"`
|
||||
}
|
||||
|
||||
// AmpModelMapping defines a model name mapping for Amp CLI requests.
|
||||
// When Amp requests a model that isn't available locally, this mapping
|
||||
// allows routing to an alternative model that IS available.
|
||||
@@ -461,6 +475,9 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
|
||||
// Normalize OAuth provider model exclusion map.
|
||||
cfg.OAuthExcludedModels = NormalizeOAuthExcludedModels(cfg.OAuthExcludedModels)
|
||||
|
||||
// Normalize global model name mappings.
|
||||
cfg.SanitizeModelNameMappings()
|
||||
|
||||
if cfg.legacyMigrationPending {
|
||||
fmt.Println("Detected legacy configuration keys, attempting to persist the normalized config...")
|
||||
if !optional && configFile != "" {
|
||||
@@ -477,6 +494,50 @@ func LoadConfigOptional(configFile string, optional bool) (*Config, error) {
|
||||
return &cfg, nil
|
||||
}
|
||||
|
||||
// SanitizeModelNameMappings normalizes and deduplicates global model name mappings.
|
||||
// It trims whitespace, normalizes channel keys to lower-case, drops empty entries,
|
||||
// and ensures (From, To) pairs are unique within each channel.
|
||||
func (cfg *Config) SanitizeModelNameMappings() {
|
||||
if cfg == nil || len(cfg.ModelNameMappings) == 0 {
|
||||
return
|
||||
}
|
||||
out := make(map[string][]ModelNameMapping, len(cfg.ModelNameMappings))
|
||||
for rawChannel, mappings := range cfg.ModelNameMappings {
|
||||
channel := strings.ToLower(strings.TrimSpace(rawChannel))
|
||||
if channel == "" || len(mappings) == 0 {
|
||||
continue
|
||||
}
|
||||
seenFrom := make(map[string]struct{}, len(mappings))
|
||||
seenTo := make(map[string]struct{}, len(mappings))
|
||||
clean := make([]ModelNameMapping, 0, len(mappings))
|
||||
for _, mapping := range mappings {
|
||||
from := strings.TrimSpace(mapping.From)
|
||||
to := strings.TrimSpace(mapping.To)
|
||||
if from == "" || to == "" {
|
||||
continue
|
||||
}
|
||||
if strings.EqualFold(from, to) {
|
||||
continue
|
||||
}
|
||||
fromKey := strings.ToLower(from)
|
||||
toKey := strings.ToLower(to)
|
||||
if _, ok := seenFrom[fromKey]; ok {
|
||||
continue
|
||||
}
|
||||
if _, ok := seenTo[toKey]; ok {
|
||||
continue
|
||||
}
|
||||
seenFrom[fromKey] = struct{}{}
|
||||
seenTo[toKey] = struct{}{}
|
||||
clean = append(clean, ModelNameMapping{From: from, To: to})
|
||||
}
|
||||
if len(clean) > 0 {
|
||||
out[channel] = clean
|
||||
}
|
||||
}
|
||||
cfg.ModelNameMappings = out
|
||||
}
|
||||
|
||||
// SanitizeOpenAICompatibility removes OpenAI-compatibility provider entries that are
|
||||
// not actionable, specifically those missing a BaseURL. It trims whitespace before
|
||||
// evaluation and preserves the relative order of remaining entries.
|
||||
|
||||
@@ -76,7 +76,12 @@ func (e *AntigravityExecutor) PrepareRequest(_ *http.Request, _ *cliproxyauth.Au
|
||||
|
||||
// Execute performs a non-streaming request to the Antigravity API.
|
||||
func (e *AntigravityExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (resp cliproxyexecutor.Response, err error) {
|
||||
if strings.Contains(req.Model, "claude") {
|
||||
upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
|
||||
if upstreamModel == "" {
|
||||
upstreamModel = req.Model
|
||||
}
|
||||
isClaude := strings.Contains(strings.ToLower(upstreamModel), "claude")
|
||||
if isClaude {
|
||||
return e.executeClaudeNonStream(ctx, auth, req, opts)
|
||||
}
|
||||
|
||||
@@ -98,7 +103,7 @@ func (e *AntigravityExecutor) Execute(ctx context.Context, auth *cliproxyauth.Au
|
||||
translated = applyThinkingMetadataCLI(translated, req.Metadata, req.Model)
|
||||
translated = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, translated)
|
||||
translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
|
||||
translated = normalizeAntigravityThinking(req.Model, translated)
|
||||
translated = normalizeAntigravityThinking(req.Model, translated, isClaude)
|
||||
translated = applyPayloadConfigWithRoot(e.cfg, req.Model, "antigravity", "request", translated)
|
||||
|
||||
baseURLs := antigravityBaseURLFallbackOrder(auth)
|
||||
@@ -109,7 +114,7 @@ func (e *AntigravityExecutor) Execute(ctx context.Context, auth *cliproxyauth.Au
|
||||
var lastErr error
|
||||
|
||||
for idx, baseURL := range baseURLs {
|
||||
httpReq, errReq := e.buildRequest(ctx, auth, token, req.Model, translated, false, opts.Alt, baseURL)
|
||||
httpReq, errReq := e.buildRequest(ctx, auth, token, upstreamModel, translated, false, opts.Alt, baseURL)
|
||||
if errReq != nil {
|
||||
err = errReq
|
||||
return resp, err
|
||||
@@ -190,10 +195,15 @@ func (e *AntigravityExecutor) executeClaudeNonStream(ctx context.Context, auth *
|
||||
to := sdktranslator.FromString("antigravity")
|
||||
translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
|
||||
|
||||
upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
|
||||
if upstreamModel == "" {
|
||||
upstreamModel = req.Model
|
||||
}
|
||||
|
||||
translated = applyThinkingMetadataCLI(translated, req.Metadata, req.Model)
|
||||
translated = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, translated)
|
||||
translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
|
||||
translated = normalizeAntigravityThinking(req.Model, translated)
|
||||
translated = normalizeAntigravityThinking(req.Model, translated, true)
|
||||
translated = applyPayloadConfigWithRoot(e.cfg, req.Model, "antigravity", "request", translated)
|
||||
|
||||
baseURLs := antigravityBaseURLFallbackOrder(auth)
|
||||
@@ -204,7 +214,7 @@ func (e *AntigravityExecutor) executeClaudeNonStream(ctx context.Context, auth *
|
||||
var lastErr error
|
||||
|
||||
for idx, baseURL := range baseURLs {
|
||||
httpReq, errReq := e.buildRequest(ctx, auth, token, req.Model, translated, true, opts.Alt, baseURL)
|
||||
httpReq, errReq := e.buildRequest(ctx, auth, token, upstreamModel, translated, true, opts.Alt, baseURL)
|
||||
if errReq != nil {
|
||||
err = errReq
|
||||
return resp, err
|
||||
@@ -524,10 +534,16 @@ func (e *AntigravityExecutor) ExecuteStream(ctx context.Context, auth *cliproxya
|
||||
to := sdktranslator.FromString("antigravity")
|
||||
translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
|
||||
|
||||
upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
|
||||
if upstreamModel == "" {
|
||||
upstreamModel = req.Model
|
||||
}
|
||||
isClaude := strings.Contains(strings.ToLower(upstreamModel), "claude")
|
||||
|
||||
translated = applyThinkingMetadataCLI(translated, req.Metadata, req.Model)
|
||||
translated = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, translated)
|
||||
translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
|
||||
translated = normalizeAntigravityThinking(req.Model, translated)
|
||||
translated = normalizeAntigravityThinking(req.Model, translated, isClaude)
|
||||
translated = applyPayloadConfigWithRoot(e.cfg, req.Model, "antigravity", "request", translated)
|
||||
|
||||
baseURLs := antigravityBaseURLFallbackOrder(auth)
|
||||
@@ -538,7 +554,7 @@ func (e *AntigravityExecutor) ExecuteStream(ctx context.Context, auth *cliproxya
|
||||
var lastErr error
|
||||
|
||||
for idx, baseURL := range baseURLs {
|
||||
httpReq, errReq := e.buildRequest(ctx, auth, token, req.Model, translated, true, opts.Alt, baseURL)
|
||||
httpReq, errReq := e.buildRequest(ctx, auth, token, upstreamModel, translated, true, opts.Alt, baseURL)
|
||||
if errReq != nil {
|
||||
err = errReq
|
||||
return nil, err
|
||||
@@ -676,6 +692,12 @@ func (e *AntigravityExecutor) CountTokens(ctx context.Context, auth *cliproxyaut
|
||||
to := sdktranslator.FromString("antigravity")
|
||||
respCtx := context.WithValue(ctx, "alt", opts.Alt)
|
||||
|
||||
upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
|
||||
if upstreamModel == "" {
|
||||
upstreamModel = req.Model
|
||||
}
|
||||
isClaude := strings.Contains(strings.ToLower(upstreamModel), "claude")
|
||||
|
||||
baseURLs := antigravityBaseURLFallbackOrder(auth)
|
||||
httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
|
||||
|
||||
@@ -694,7 +716,7 @@ func (e *AntigravityExecutor) CountTokens(ctx context.Context, auth *cliproxyaut
|
||||
payload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
|
||||
payload = applyThinkingMetadataCLI(payload, req.Metadata, req.Model)
|
||||
payload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, payload)
|
||||
payload = normalizeAntigravityThinking(req.Model, payload)
|
||||
payload = normalizeAntigravityThinking(req.Model, payload, isClaude)
|
||||
payload = deleteJSONField(payload, "project")
|
||||
payload = deleteJSONField(payload, "model")
|
||||
payload = deleteJSONField(payload, "request.safetySettings")
|
||||
@@ -1308,7 +1330,7 @@ func alias2ModelName(modelName string) string {
|
||||
|
||||
// normalizeAntigravityThinking clamps or removes thinking config based on model support.
|
||||
// For Claude models, it additionally ensures thinking budget < max_tokens.
|
||||
func normalizeAntigravityThinking(model string, payload []byte) []byte {
|
||||
func normalizeAntigravityThinking(model string, payload []byte, isClaude bool) []byte {
|
||||
payload = util.StripThinkingConfigIfUnsupported(model, payload)
|
||||
if !util.ModelSupportsThinking(model) {
|
||||
return payload
|
||||
@@ -1320,7 +1342,6 @@ func normalizeAntigravityThinking(model string, payload []byte) []byte {
|
||||
raw := int(budget.Int())
|
||||
normalized := util.NormalizeThinkingBudget(model, raw)
|
||||
|
||||
isClaude := strings.Contains(strings.ToLower(model), "claude")
|
||||
if isClaude {
|
||||
effectiveMax, setDefaultMax := antigravityEffectiveMaxTokens(model, payload)
|
||||
if effectiveMax > 0 && normalized >= effectiveMax {
|
||||
|
||||
@@ -7,10 +7,11 @@ import (
|
||||
)
|
||||
|
||||
const (
|
||||
ThinkingBudgetMetadataKey = "thinking_budget"
|
||||
ThinkingIncludeThoughtsMetadataKey = "thinking_include_thoughts"
|
||||
ReasoningEffortMetadataKey = "reasoning_effort"
|
||||
ThinkingOriginalModelMetadataKey = "thinking_original_model"
|
||||
ThinkingBudgetMetadataKey = "thinking_budget"
|
||||
ThinkingIncludeThoughtsMetadataKey = "thinking_include_thoughts"
|
||||
ReasoningEffortMetadataKey = "reasoning_effort"
|
||||
ThinkingOriginalModelMetadataKey = "thinking_original_model"
|
||||
ModelMappingOriginalModelMetadataKey = "model_mapping_original_model"
|
||||
)
|
||||
|
||||
// NormalizeThinkingModel parses dynamic thinking suffixes on model names and returns
|
||||
@@ -215,6 +216,13 @@ func ResolveOriginalModel(model string, metadata map[string]any) string {
|
||||
}
|
||||
|
||||
if metadata != nil {
|
||||
if v, ok := metadata[ModelMappingOriginalModelMetadataKey]; ok {
|
||||
if s, okStr := v.(string); okStr && strings.TrimSpace(s) != "" {
|
||||
if base := normalize(s); base != "" {
|
||||
return base
|
||||
}
|
||||
}
|
||||
}
|
||||
if v, ok := metadata[ThinkingOriginalModelMetadataKey]; ok {
|
||||
if s, okStr := v.(string); okStr && strings.TrimSpace(s) != "" {
|
||||
if base := normalize(s); base != "" {
|
||||
|
||||
@@ -6,6 +6,7 @@ import (
|
||||
"crypto/sha256"
|
||||
"encoding/hex"
|
||||
"os"
|
||||
"reflect"
|
||||
"time"
|
||||
|
||||
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
|
||||
@@ -126,7 +127,7 @@ func (w *Watcher) reloadConfig() bool {
|
||||
}
|
||||
|
||||
authDirChanged := oldConfig == nil || oldConfig.AuthDir != newConfig.AuthDir
|
||||
forceAuthRefresh := oldConfig != nil && oldConfig.ForceModelPrefix != newConfig.ForceModelPrefix
|
||||
forceAuthRefresh := oldConfig != nil && (oldConfig.ForceModelPrefix != newConfig.ForceModelPrefix || !reflect.DeepEqual(oldConfig.ModelNameMappings, newConfig.ModelNameMappings))
|
||||
|
||||
log.Infof("config successfully reloaded, triggering client reload")
|
||||
w.reloadClients(authDirChanged, affectedOAuthProviders, forceAuthRefresh)
|
||||
|
||||
Reference in New Issue
Block a user