diff --git a/llm/provider.go b/llm/provider.go
index 1031ad8..70c84a7 100644
--- a/llm/provider.go
+++ b/llm/provider.go
@@ -109,11 +109,7 @@ type GenerationOptions struct {
 	ThinkingMode         string
 	ThinkingDisplay      string
 	ThinkingEnabled      *bool
-	// GLMThinkingEnabled toggles GLM/Z.ai extended reasoning via the provider's
-	// non-OpenAI thinking={"type":"enabled"|"disabled"} request parameter. Only
-	// applied for OpenAI-compatible providers whose compat config sets
-	// ThinkingFormat to "zai". When nil the parameter is omitted and the model
-	// uses its default (GLM defaults to enabled).
+	// GLMThinkingEnabled is a deprecated alias of ThinkingEnabled (Z.AI-era).
 	GLMThinkingEnabled *bool
 	VirtualKeyID       string
 	KimiContextCacheID string
diff --git a/llm/types.go b/llm/types.go
index cac9387..5447020 100644
--- a/llm/types.go
+++ b/llm/types.go
@@ -99,11 +99,10 @@ type ChatOptions struct {
 	ThinkingMode         string          `json:"thinking_mode,omitempty"`
 	ThinkingDisplay      string          `json:"thinking_display,omitempty"`
 	ThinkingEnabled      *bool           `json:"thinking_enabled,omitempty"`
-	// GLMThinkingEnabled toggles GLM/Z.ai extended reasoning via the provider's
-	// non-OpenAI thinking={"type":"enabled"|"disabled"} request parameter. Only
-	// applied for OpenAI-compatible providers whose compat config sets
-	// ThinkingFormat to "zai". When nil the parameter is omitted and the model
-	// uses its default (GLM defaults to enabled).
+	// GLMThinkingEnabled is a deprecated alias of ThinkingEnabled kept for
+	// older Z.AI call sites. New code should set ThinkingEnabled. Adapters
+	// accept either field; wire encoding is selected per provider via
+	// OpenAICompatConfig.ThinkingFormat ("zai", "longcat", "agnes", …).
 	GLMThinkingEnabled *bool             `json:"glm_thinking_enabled,omitempty"`
 	VirtualKeyID       string            `json:"virtual_key_id,omitempty"`
 	KimiContextCacheID string            `json:"kimi_context_cache_id,omitempty"`
@@ -128,6 +127,38 @@ type ChatOptions struct {
 	AudioConfig        string            `json:"audio_config,omitempty"`
 	Prediction         string            `json:"prediction,omitempty"`
 	WebSearchOptions   string            `json:"web_search_options,omitempty"`
+	PromptCacheOptions *PromptCacheOpts  `json:"prompt_cache_options,omitempty"`
+	CacheControl       *CacheControl     `json:"cache_control,omitempty"`
+	// Responses API extensions (Concentrate)
+	PreviousResponseID string              `json:"previous_response_id,omitempty"`
+	Include            []string            `json:"include,omitempty"`
+	Routing            *RoutingConfig      `json:"routing,omitempty"`
+	MaxToolCalls       *int                `json:"max_tool_calls,omitempty"`
+	ContextManagement  []ContextManagement `json:"context_management,omitempty"`
+	SafetyIdentifier   *string             `json:"safety_identifier,omitempty"`
+	Background         *bool               `json:"background,omitempty"`
+	Truncation         *string             `json:"truncation,omitempty"`
+	Conversation       interface{}         `json:"conversation,omitempty"`
+}
+
+type PromptCacheOpts struct {
+	Mode string `json:"mode,omitempty"`
+	TTL  string `json:"ttl,omitempty"`
+}
+
+type CacheControl struct {
+	Type string `json:"type"`
+	TTL  string `json:"ttl,omitempty"`
+}
+
+type RoutingConfig struct {
+	Model    interface{} `json:"model,omitempty"`
+	Strategy string      `json:"strategy,omitempty"` // "min" or "max"
+	Metric   string      `json:"metric,omitempty"`   // "cost", "latency", "quality"
+}
+
+type ContextManagement struct {
+	Type string `json:"type"` // "compact_20260112", "clear_thinking_20251015", etc.
 }
 
 // ContinuationConfig controls output continuation behavior.