fix: separate Anthropic output and context limits

Direct Anthropic connections reused the configured context window as max_tokens, which could impose an unintended output value or send a provider-invalid request. Anthropic connections now expose an independent per-response maximum output setting, defaulting to 32K for the protocol-required field, while OpenAI direct requests remain without an added output token cap and direct tool rounds remain unmetered. Release note: Anthropic 直连模型现在可单独配置单次最大输出，不再复用上下文窗口；OpenAI 直连请求和工具调用轮次不增加额外配额。
2026-08-26 22:53:49 +08:00
parent 49700bc7cf
commit b20c10f820
13 changed files with 96 additions and 12 deletions
@@ -386,6 +386,7 @@ export function createResolvedModelProfileDigest(
      authentication: profile.authentication,
      supportsImageInput: profile.supportsImageInput === true,
      contextWindowTokens: profile.contextWindowTokens ?? null,
+      maximumOutputTokens: profile.maximumOutputTokens ?? null,
      imageGenerationQuality: profile.imageGenerationQuality ?? null
    })
  )