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

provider "cerebras" {
	default-model "zai-glm-4.7"
	env "CEREBRAS_API_KEY"
	discovery label="Cerebras"

	// Replaces the strict-mode provider whitelist entry.
	supports-strict-mode #true
	// Replaces the Cerebras provider branches in the completions baseline.
	supports-usage-in-streaming #false
	tool-strict-mode "all_strict"
	// Replaces the provider check in agent-loop history normalization: replayed
	// assistant history drops its thinking blocks.
	strip-thinking-history #true
	// Prompt caching carries no discount: cached input tokens bill at the
	// standard input rate (https://inference-docs.cerebras.ai/capabilities/prompt-caching).
	cache-read-at-input-rate #true
	// Cerebras serves Gemma 4 with vision enabled; its /v1/models rows carry
	// no modality metadata.
	models "gemma-4-31b" {
		input-modalities "text" "image"
	}
	thinking-mode "effort"
	// Cerebras accepts OpenAI `reasoning_effort`, not Qwen-native thinking
	// fields such as `enable_thinking`.
	class "qwen" {
		thinking-format "openai"
	}
	// Qwen 3.8 accepts low/medium/high; `none` is its wire-only off value.
	models "qwen-3.8-27b" {
		thinking-efforts "low" "medium" "high"
		reasoning-disable-mode "none-effort"
	}
	// residue: taxonomy ranks and exact globs do not isolate these models.
	models "zai-glm-4.7" {
		thinking-efforts "minimal" "low" "medium" "high" "xhigh"
	}
}