feat(ai): add Qwen Token Plan as built-in provider (#6858)

Add Alibaba Cloud Model Studio Token Plan subscription service as two
built-in API-key providers: qwen-token-plan (international, Singapore)
and qwen-token-plan-cn (China, Beijing).

Each provider exposes 15 text-generation models (Qwen, DeepSeek, GLM,
Kimi, MiniMax) via the OpenAI-compatible endpoint with DashScope
enable_thinking support. Model metadata is sourced from models.dev;
qwen3.8-max-preview is hardcoded until models.dev includes it.

Also fixes kimi-coding test references (k2p7 -> kimi-for-coding) after
models.dev catalog update picked up by generate-models.

Closes #6850

packages/ai/src/utils/overflow.ts

@@ -31,6 +31,7 @@ import type { AssistantMessage } from "../types.ts";
  * - Xiaomi MiMo: Truncates input to fill contextWindow exactly, then returns finish_reason "length"
  *   with output=0 (no room left to generate). Detected via stopReason "length" + zero output +
  *   input filling the context window.
+ * - DashScope/Qwen: "Range of input length should be [1, X]" (HTTP 400 invalid_parameter_error)
  * - Ollama: Some deployments truncate silently, others return errors like "prompt too long; exceeded max context length by X tokens"
  */
 const OVERFLOW_PATTERNS = [
@@ -54,6 +55,7 @@ const OVERFLOW_PATTERNS = [
 	/prompt has [\d,]+ tokens?, but the configured context size is [\d,]+ tokens?/i, // DS4 server
 	/model_context_window_exceeded/i, // z.ai non-standard finish_reason surfaced as error text
 	/prompt too long; exceeded (?:max )?context length/i, // Ollama explicit overflow error
+	/range of input length should be/i, // DashScope / Qwen Token Plan
 	/context[_ ]length[_ ]exceeded/i, // Generic fallback
 	/too many tokens/i, // Generic fallback
 	/token limit exceeded/i, // Generic fallback
@@ -101,6 +103,7 @@ const NON_OVERFLOW_PATTERNS = [
  * - LM Studio: "greater than the context length"
  * - Kimi For Coding: "exceeded model token limit: X (requested: Y)"
  * - DS4: "Prompt has X tokens, but the configured context size is Y tokens"
+ * - DashScope/Qwen: "Range of input length should be [1, X]"
  *
  * **Unreliable detection:**
  * - z.ai: Sometimes accepts overflow silently (detectable via usage.input > contextWindow),