fix: use createDeepSeek for kimi provider to handle reasoning_content in multi-turn conversations (fixes #824) (#825)

Kimi thinking models (e.g. kimi-k2.6) return reasoning_content in their
responses. The previous createOpenAI-based implementation silently ignored
this field, so reasoning was never captured or replayed in subsequent turns.
Switching to createDeepSeek (which natively understands reasoning_content)
ensures that reasoning context is preserved across conversation turns,
resolving the "cannot interact a second time" error with Kimi k2.6.

This mirrors the existing doubao provider pattern, which already uses
createDeepSeek for kimi-based models routed through Doubao.

Co-authored-by: octo-patch <octo-patch@github.com>

lib/ai-providers.ts

@@ -1262,7 +1262,6 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
         case "glm":
         case "qwen":
         case "qiniu":
-        case "kimi":
         case "novita": {
             const envVar = PROVIDER_ENV_VARS[provider]
             if (!envVar) {
@@ -1288,6 +1287,23 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
             break
         }
 
+        case "kimi": {
+            const apiKey = resolveApiKey(overrides, "KIMI_API_KEY")
+            const baseURL = resolveBaseURL(
+                overrides?.apiKey,
+                overrides?.baseUrl,
+                resolveBaseUrlEnv(overrides, "KIMI_BASE_URL"),
+                PROVIDER_INFO["kimi"]?.defaultBaseUrl,
+            )
+            // Use createDeepSeek to properly handle reasoning_content for Kimi
+            // thinking models (e.g., kimi-k2.6). Kimi's API uses the same
+            // reasoning_content field as DeepSeek, so this provider correctly
+            // captures and replays reasoning in multi-turn conversations.
+            const customProvider = createDeepSeek({ apiKey, baseURL })
+            model = customProvider(modelId)
+            break
+        }
+
         default:
             throw new Error(
                 `Unknown AI provider: ${provider}. Supported providers: bedrock, openai, anthropic, google, azure, ollama, openrouter, deepseek, siliconflow, sglang, gateway, edgeone, doubao, modelscope, glm, qwen, qiniu, kimi, minimax, novita`,