feat: add 2026 Q2 flagship models (#76)

Add latest flagships released in April 2026 that registry missed:
- deepseek: V4-Pro, V4-Flash (2026-04-24, 1M context)
- qwen: qwen3.6-max-preview (2026-04-20, 256K context)
- moonshot: kimi-k2.6 (2026-04-20, 256K context)
- zhipu: glm-5.1 (2026-04-08), glm-4.7-flash (free tier)

Update default aliases: deepseek -> v4-pro, kimi -> k2.6, glm -> 5.1.

providers/moonshot.toml

@@ -1,5 +1,5 @@
 # Moonshot / Kimi — https://moonshot.ai
-# Models: 2
+# Models: 3
 
 [provider]
 id = "moonshot"
@@ -9,17 +9,18 @@ base_url = "https://api.moonshot.ai/v1"
 key_required = true
 
 [[models]]
-id = "kimi-k2"
-display_name = "Kimi K2"
+id = "kimi-k2.6"
+display_name = "Kimi K2.6"
 tier = "frontier"
-context_window = 131072
+context_window = 262144
 max_output_tokens = 16384
-input_cost_per_m = 0.57
-output_cost_per_m = 2.3
+input_cost_per_m = 0.95
+output_cost_per_m = 4.00
 supports_tools = true
 supports_vision = true
 supports_streaming = true
-aliases = ["kimi"]
+supports_thinking = true
+aliases = ["kimi", "kimi-k2.6-0420"]
 
 [[models]]
 id = "kimi-k2.5"
@@ -34,3 +35,16 @@ supports_vision = true
 supports_streaming = true
 supports_thinking = true
 aliases = ["kimi-k2.5-0711"]
+
+[[models]]
+id = "kimi-k2"
+display_name = "Kimi K2"
+tier = "frontier"
+context_window = 131072
+max_output_tokens = 16384
+input_cost_per_m = 0.57
+output_cost_per_m = 2.3
+supports_tools = true
+supports_vision = true
+supports_streaming = true
+aliases = []