Merge pull request #2316 from router-for-me/openai

Add per-model thinking support for OpenAI compatibility

config.example.yaml

@@ -206,7 +206,9 @@ nonstream-keepalive-interval: 0
 #       - api-key: "sk-or-v1-...b781" # without proxy-url
 #     models: # The models supported by the provider.
 #       - name: "moonshotai/kimi-k2:free" # The actual model name.
-#         alias: "kimi-k2" # The alias used in the API.
+#         alias: "kimi-k2"               # The alias used in the API.
+#         thinking:                      # optional: omit to default to levels ["low","medium","high"]
+#           levels: ["low", "medium", "high"]
 #       # You may repeat the same alias to build an internal model pool.
 #       # The client still sees only one alias in the model list.
 #       # Requests to that alias will round-robin across the upstream names below,

internal/config/config.go

@@ -13,6 +13,7 @@ import (
 	"strings"
 	"syscall"
 
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
 	log "github.com/sirupsen/logrus"
 	"golang.org/x/crypto/bcrypt"
 	"gopkg.in/yaml.v3"
@@ -511,6 +512,10 @@ type OpenAICompatibilityModel struct {
 
 	// Alias is the model name alias that clients will use to reference this model.
 	Alias string `yaml:"alias" json:"alias"`
+
+	// Thinking configures the thinking/reasoning capability for this model.
+	// If nil, the model defaults to level-based reasoning with levels ["low", "medium", "high"].
+	Thinking *registry.ThinkingSupport `yaml:"thinking,omitempty" json:"thinking,omitempty"`
 }
 
 func (m OpenAICompatibilityModel) GetName() string  { return m.Name }

internal/registry/model_registry.go

@@ -71,16 +71,16 @@ type availableModelsCacheEntry struct {
 // Values are interpreted in provider-native token units.
 type ThinkingSupport struct {
 	// Min is the minimum allowed thinking budget (inclusive).
-	Min int `json:"min,omitempty"`
+	Min int `json:"min,omitempty" yaml:"min,omitempty"`
 	// Max is the maximum allowed thinking budget (inclusive).
-	Max int `json:"max,omitempty"`
+	Max int `json:"max,omitempty" yaml:"max,omitempty"`
 	// ZeroAllowed indicates whether 0 is a valid value (to disable thinking).
-	ZeroAllowed bool `json:"zero_allowed,omitempty"`
+	ZeroAllowed bool `json:"zero_allowed,omitempty" yaml:"zero-allowed,omitempty"`
 	// DynamicAllowed indicates whether -1 is a valid value (dynamic thinking budget).
-	DynamicAllowed bool `json:"dynamic_allowed,omitempty"`
+	DynamicAllowed bool `json:"dynamic_allowed,omitempty" yaml:"dynamic-allowed,omitempty"`
 	// Levels defines discrete reasoning effort levels (e.g., "low", "medium", "high").
 	// When set, the model uses level-based reasoning instead of token budgets.
-	Levels []string `json:"levels,omitempty"`
+	Levels []string `json:"levels,omitempty" yaml:"levels,omitempty"`
 }
 
 // ModelRegistration tracks a model's availability

sdk/cliproxy/service.go

@@ -960,6 +960,10 @@ func (s *Service) registerModelsForAuth(a *coreauth.Auth) {
 						if modelID == "" {
 							modelID = m.Name
 						}
+						thinking := m.Thinking
+						if thinking == nil {
+							thinking = &registry.ThinkingSupport{Levels: []string{"low", "medium", "high"}}
+						}
 						ms = append(ms, &ModelInfo{
 							ID:          modelID,
 							Object:      "model",
@@ -967,7 +971,8 @@ func (s *Service) registerModelsForAuth(a *coreauth.Auth) {
 							OwnedBy:     compat.Name,
 							Type:        "openai-compatibility",
 							DisplayName: modelID,
-							UserDefined: true,
+							UserDefined: false,
+							Thinking:    thinking,
 						})
 					}
 					// Register and return