// Provider-wire compat for "alibaba-token-plan"; regenerated from the frozen census using deployment contract selectors.

provider "alibaba-token-plan" {
	default-model "qwen3.7-plus"
	env "ALIBABA_TOKEN_PLAN_API_KEY" "BAILIAN_TOKEN_PLAN_API_KEY"
	dynamic-models-authoritative #true
	discovery label="QwenCloud Token Plan"

	// QwenCloud Token Plan's documented Individual text-model allowlist, bundled
	// when credentialed discovery is unavailable. A successful `/models` response
	// is authoritative for the subscribed edition and must not be widened by this
	// seed; when it is bundled it outranks same-id rows so incomplete upstream
	// metadata cannot replace its capabilities.
	seed api="openai-completions" base-url="https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1" bundle="fallback" precedence="seed" {
		model "qwen3.8-max-preview" name="Qwen3.8 Max Preview" {
			reasoning #true
			input "text" "image"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits context=983616 max-tokens=131072
			thinking-mode "effort"
			thinking-efforts "low" "high" "xhigh"
			thinking-requires-effort #true
			supports-developer-role #false
			supports-reasoning-effort #true
		}
		// Qwen3.8-Max combines Qwen's binary thinking toggle with OpenAI-style
		// `reasoning_effort`. The base Qwen view encodes disabled turns; reasoning
		// requests swap to the OpenAI effort dialect and explicitly enable thinking.
		model "qwen3.8-max" name="Qwen3.8 Max" {
			reasoning #true
			input "text" "image"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits context=1000000 max-tokens=131072
			thinking-mode "effort"
			thinking-efforts "low" "medium" "xhigh"
			thinking-default-level "xhigh"
			supports-developer-role #false
			supports-reasoning-effort #true
			when-thinking {
				thinking-format "openai"
				extra-body {
					enable_thinking #true
				}
			}
		}
		model "qwen3.8-flash" name="Qwen3.8 Flash" {
			reasoning #true
			input "text" "image"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits context=1000000 max-tokens=131072
			thinking-mode "effort"
			thinking-efforts "minimal" "low" "medium" "high"
			supports-developer-role #false
		}
		model "qwen3.7-max" name="Qwen3.7 Max" {
			reasoning #true
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits context=1000000 max-tokens=65536
			thinking-mode "effort"
			thinking-efforts "minimal" "low" "medium" "high"
			supports-developer-role #false
		}
		model "qwen3.7-plus" name="Qwen3.7 Plus" {
			reasoning #true
			input "text" "image"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits context=1000000 max-tokens=64000
			thinking-mode "effort"
			thinking-efforts "minimal" "low" "medium" "high"
			supports-developer-role #false
		}
		model "qwen3.6-flash" name="Qwen3.6 Flash" {
			reasoning #true
			input "text" "image"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits context=1000000 max-tokens=65536
			thinking-mode "effort"
			thinking-efforts "minimal" "low" "medium" "high"
			supports-developer-role #false
		}
		model "glm-5.2" name="GLM-5.2" {
			reasoning #true
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits context=1000000 max-tokens=131072
			thinking-mode "effort"
			thinking-efforts "minimal" "low" "medium" "high" "max"
			supports-developer-role #false
		}
		model "deepseek-v4-pro" name="DeepSeek V4 Pro" {
			reasoning #true
			input "text"
			cost input=0 output=0 cache-read=0 cache-write=0
			limits context=1000000 max-tokens=384000
			thinking-mode "effort"
			thinking-efforts "high" "max"
			supports-developer-role #false
		}
	}

	// Replaces the Alibaba-compatible thinking-format branch.
	thinking-format "qwen"
	thinking-mode "effort"
	class "qwen" {
		revision ">=3.6 <3.8" {
			thinking-efforts "minimal" "low" "medium" "high"
		}
		revision ">=3.8 <3.9" {
			supports-reasoning-effort #true
		}
	}
	// residue: taxonomy ranks and exact globs do not isolate these models.
	models "deepseek-v4-pro" {
		thinking-format "qwen"
	}
	// Max Preview rides only Alibaba's binary enable_thinking toggle: it stays on
	// the Qwen dialect and must not emit an unsupported reasoning_effort field.
	models "qwen3.8-max-preview" {
		thinking-efforts "low" "high" "xhigh"
		thinking-requires-effort #true
	}
	// Max and Flash steer thinking depth through the OpenAI reasoning_effort
	// control and replay reasoning_content across turns (preserve_thinking
	// defaults on for both).
	models "qwen3.8-max" "qwen3.8-flash" {
		replay-reasoning-content #true
		when-thinking {
			extra-body {
				enable_thinking #true
			}
			thinking-format "openai"
		}
	}
	// Max exposes a distinct low/medium/xhigh ladder; Flash retains its
	// provider-authored minimal/low/medium/high ladder.
	models "qwen3.8-max" {
		thinking-default-level "xhigh"
		thinking-efforts "low" "medium" "xhigh"
	}
}