feat(config): add per-auth disable_cooling override support

- Introduced `disable_cooling` metadata field for fine-grained control over cooldown scheduling.
- Updated `Auth` object to include `Metadata` with conditional logic for handling empty states.
- Added YAML configuration support for `disable_cooling` in API key definitions across providers.
- Enhanced unit tests to validate `disable_cooling` behavior in various scenarios.

internal/config/config.go

@@ -226,12 +226,6 @@ type RoutingConfig struct {
 	// Supported values: "round-robin" (default), "fill-first".
 	Strategy string `yaml:"strategy,omitempty" json:"strategy,omitempty"`
 
-	// ClaudeCodeSessionAffinity enables session-sticky routing for Claude Code clients.
-	// When enabled, requests with the same session ID (extracted from metadata.user_id)
-	// are routed to the same auth credential when available.
-	// Deprecated: Use SessionAffinity instead for universal session support.
-	ClaudeCodeSessionAffinity bool `yaml:"claude-code-session-affinity,omitempty" json:"claude-code-session-affinity,omitempty"`
-
 	// SessionAffinity enables universal session-sticky routing for all clients.
 	// Session IDs are extracted from multiple sources:
 	// metadata.user_id (Claude Code session format), X-Session-ID, Session_id (Codex),
@@ -403,6 +397,9 @@ type ClaudeKey struct {
 	// ExcludedModels lists model IDs that should be excluded for this provider.
 	ExcludedModels []string `yaml:"excluded-models,omitempty" json:"excluded-models,omitempty"`
 
+	// DisableCooling disables auth/model cooldown scheduling for this credential when true.
+	DisableCooling bool `yaml:"disable-cooling,omitempty" json:"disable-cooling,omitempty"`
+
 	// Cloak configures request cloaking for non-Claude-Code clients.
 	Cloak *CloakConfig `yaml:"cloak,omitempty" json:"cloak,omitempty"`
 
@@ -458,6 +455,9 @@ type CodexKey struct {
 
 	// ExcludedModels lists model IDs that should be excluded for this provider.
 	ExcludedModels []string `yaml:"excluded-models,omitempty" json:"excluded-models,omitempty"`
+
+	// DisableCooling disables auth/model cooldown scheduling for this credential when true.
+	DisableCooling bool `yaml:"disable-cooling,omitempty" json:"disable-cooling,omitempty"`
 }
 
 func (k CodexKey) GetAPIKey() string  { return k.APIKey }
@@ -502,6 +502,9 @@ type GeminiKey struct {
 
 	// ExcludedModels lists model IDs that should be excluded for this provider.
 	ExcludedModels []string `yaml:"excluded-models,omitempty" json:"excluded-models,omitempty"`
+
+	// DisableCooling disables auth/model cooldown scheduling for this credential when true.
+	DisableCooling bool `yaml:"disable-cooling,omitempty" json:"disable-cooling,omitempty"`
 }
 
 func (k GeminiKey) GetAPIKey() string  { return k.APIKey }
@@ -546,6 +549,9 @@ type OpenAICompatibility struct {
 
 	// Headers optionally adds extra HTTP headers for requests sent to this provider.
 	Headers map[string]string `yaml:"headers,omitempty" json:"headers,omitempty"`
+
+	// DisableCooling disables auth/model cooldown scheduling for this provider when true.
+	DisableCooling bool `yaml:"disable-cooling,omitempty" json:"disable-cooling,omitempty"`
 }
 
 // OpenAICompatibilityAPIKey represents an API key configuration with optional proxy setting.