opensource/mateclaw
2
0
Fork 0
mirror of https://gitee.com/mateos/mateclaw.git synced 2026-09-15 20:08:18 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix(embedding): respect requireApiKey flag in OpenAI-compatible embedding factory (#171)

Browse Source 
Closes #167

EmbeddingModelFactory.buildOpenAi() hard-failed on any provider whose API
key was empty or unusable, so keyless providers like Ollama and OpenCode
(declared with requireApiKey=false) could pass the chat connectivity test
but bounce when the same provider's embedding model was tested.

Mirror the chat path in OpenAiCompatibleChatModelBuilder.buildOpenAiApi:

- If requireApiKey is not explicitly false, an unusable key still throws.
- If requireApiKey == false, the key check is skipped and an empty string
  is passed to OpenAiApi.builder() so no Authorization: Bearer header is
  attached to the outgoing request.
This commit is contained in:
倪程伟 2026-05-20 09:25:16 +08:00 committed by GitHub
parent 8e00613e69
commit e0f66eef25
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
mateclaw-server/src/main/java/vip/mate/llm/embedding/EmbeddingModelFactory.java
View File

@ -165,7 +165,11 @@ public class EmbeddingModelFactory {
"Provider '" + provider.getProviderId() + "' 未完成配置（缺少 API Key 或 Base URL）"); "Provider '" + provider.getProviderId() + "' 未完成配置（缺少 API Key 或 Base URL）");
} }
String apiKey = provider.getApiKey(); String apiKey = provider.getApiKey();
if (!providerService.hasUsableApiKey(apiKey)) { // Mirror the chat model builder: only require an API key when the provider row says so.
// Keyless providers (requireApiKey=false, e.g. OpenCode, local Ollama) must be allowed
// through; otherwise their cloud-model connection test passes but embedding test fails.
boolean keyRequired = !Boolean.FALSE.equals(provider.getRequireApiKey());
if (keyRequired && !providerService.hasUsableApiKey(apiKey)) {
throw new MateClawException("err.embedding.openai_key_invalid", throw new MateClawException("err.embedding.openai_key_invalid",
"Provider API Key 未配置或无效: " + provider.getProviderId()); "Provider API Key 未配置或无效: " + provider.getProviderId());
} }
@ -175,10 +179,11 @@ public class EmbeddingModelFactory {
"Provider Base URL 未配置: " + provider.getProviderId()); "Provider Base URL 未配置: " + provider.getProviderId());
} }
String effectiveApiKey = providerService.hasUsableApiKey(apiKey) ? apiKey.trim() : "";
// 最简构造：不做 chat-specific 的 header 重写、reasoning patch 等 // 最简构造：不做 chat-specific 的 header 重写、reasoning patch 等
OpenAiApi api = OpenAiApi.builder() OpenAiApi api = OpenAiApi.builder()
.baseUrl(baseUrl) .baseUrl(baseUrl)
.apiKey(apiKey.trim()) .apiKey(effectiveApiKey)
.embeddingsPath(resolveEmbeddingsPath(baseUrl)) .embeddingsPath(resolveEmbeddingsPath(baseUrl))
.build(); .build();