feat(ai): add chat-template thinking compat

closes #5673
This commit is contained in:
Armin Ronacher
2026-06-19 23:34:17 +02:00
parent 128330e36f
commit 8b97e75c6b
12 changed files with 248 additions and 8 deletions

View File

@@ -967,7 +967,8 @@ interface OpenAICompletionsCompat {
requiresAssistantAfterToolResult?: boolean; // Whether tool results must be followed by an assistant message (default: false)
requiresThinkingAsText?: boolean; // Whether thinking blocks must be converted to text (default: false)
requiresReasoningContentOnAssistantMessages?: boolean; // Whether all replayed assistant messages must include empty reasoning_content when reasoning is enabled (default: auto-detected for DeepSeek)
thinkingFormat?: 'openai' | 'openrouter' | 'deepseek' | 'together' | 'zai' | 'qwen' | 'qwen-chat-template' | 'string-thinking' | 'ant-ling'; // Format for reasoning param: 'openai' uses reasoning_effort, 'openrouter' uses reasoning: { effort }, 'deepseek' uses thinking: { type } plus reasoning_effort when supported, 'together' uses reasoning: { enabled } plus reasoning_effort when supported, 'zai' uses enable_thinking, 'qwen' uses enable_thinking, 'qwen-chat-template' uses chat_template_kwargs.enable_thinking, 'string-thinking' uses top-level thinking, 'ant-ling' uses reasoning: { effort } only for mapped efforts (default: openai)
thinkingFormat?: 'openai' | 'openrouter' | 'deepseek' | 'together' | 'zai' | 'qwen' | 'chat-template' | 'qwen-chat-template' | 'string-thinking' | 'ant-ling'; // Format for reasoning param: 'openai' uses reasoning_effort, 'openrouter' uses reasoning: { effort }, 'deepseek' uses thinking: { type } plus reasoning_effort when supported, 'together' uses reasoning: { enabled } plus reasoning_effort when supported, 'zai' uses thinking: { type }, 'qwen' uses enable_thinking, 'chat-template' uses configurable chat_template_kwargs, 'qwen-chat-template' uses chat_template_kwargs.enable_thinking and preserve_thinking, 'string-thinking' uses top-level thinking, 'ant-ling' uses reasoning: { effort } only for mapped efforts (default: openai)
chatTemplateKwargs?: Record<string, string | number | boolean | null | { '$var': 'thinking.enabled' | 'thinking.effort'; omitWhenOff?: boolean }>; // chat_template_kwargs values; use $var for pi-controlled thinking values
cacheControlFormat?: 'anthropic'; // Anthropic-style cache_control on system prompt, last tool, and last user/assistant text content
openRouterRouting?: OpenRouterRouting; // OpenRouter routing preferences (default: {})
vercelGatewayRouting?: VercelGatewayRouting; // Vercel AI Gateway routing preferences (default: {})