mirror of
https://gitee.com/mateos/mateclaw.git
synced 2026-09-13 03:13:41 +08:00
fix(llm): support Volcano Ark base URLs and surface friendly errors
- Generalize the OpenAI-compatible chat/models path resolver so any
baseUrl ending in /v{N} (Ark /v3, Zhipu /v4, ...) drops the duplicate
/v1 prefix. Volcano Engine test-connection and chat were posting to
/api/v3/v1/chat/completions and getting 404.
- Replace the six pre-seeded Doubao alias rows (doubao-1.5-*) with five
valid Ark direct-call ids (doubao-seed-1-8-251228 etc.) and flip
support_model_discovery=TRUE so users can refresh their account's
actual catalog. Aliases were marketing names, not API names, so every
call hit InvalidEndpointOrModel.NotFound.
- Translate Ark business errors into actionable Chinese hints: include
the response body in the error chain, match ModelNotOpen and
InvalidEndpointOrModel codes, extract the offending model id, and
classify them as MODEL_NOT_FOUND so failover skips retries.
This commit is contained in:
matevip
parent
6a3df2a6e0
commit
69f065e212
@ -1408,17 +1408,28 @@ public class AgentGraphBuilder {
|
||||
return result;
|
||||
}
|
||||
|
||||
// Trailing "/v{digits}" segment in a base URL — the OpenAI-compatible convention
|
||||
// (/v1 OpenAI, /v3 Volcano Ark, /v4 Zhipu). When the baseUrl already carries this
|
||||
// segment, the default /v1 prefix on the path must be stripped to avoid building
|
||||
// a broken URL like /api/v3/v1/chat/completions.
|
||||
private static final java.util.regex.Pattern OPENAI_BASE_URL_VERSION_SUFFIX =
|
||||
java.util.regex.Pattern.compile(".*/v\\d+$");
|
||||
|
||||
private String resolveOpenAiCompletionsPath(String baseUrl, Map<String, Object> kwargs) {
|
||||
Object raw = kwargs.get("completionsPath");
|
||||
String path = raw instanceof String value && StringUtils.hasText(value) ? value.trim() : "/v1/chat/completions";
|
||||
boolean explicit = raw instanceof String value && StringUtils.hasText(value);
|
||||
String path = explicit ? ((String) raw).trim() : "/v1/chat/completions";
|
||||
if (!path.startsWith("/")) {
|
||||
path = "/" + path;
|
||||
}
|
||||
if (baseUrl.endsWith("/v1") && path.startsWith("/v1/")) {
|
||||
// An explicit completionsPath is honored as-is. Otherwise, dedupe the /v1
|
||||
// prefix when the baseUrl already ends with /v{N} (Volcano Engine Ark /v3,
|
||||
// Zhipu /v4, etc.).
|
||||
if (!explicit
|
||||
&& baseUrl != null
|
||||
&& OPENAI_BASE_URL_VERSION_SUFFIX.matcher(baseUrl).matches()
|
||||
&& path.startsWith("/v1/")) {
|
||||
path = path.substring(3);
|
||||
if (!path.startsWith("/")) {
|
||||
path = "/" + path;
|
||||
}
|
||||
}
|
||||
return path;
|
||||
}
|
||||
|
||||
@ -349,7 +349,12 @@ public class NodeStreamingChatHelper {
|
||||
|| msg.contains("does not exist")
|
||||
|| msg.contains("[InvalidParameter]")
|
||||
|| msg.contains("InvalidParameter")
|
||||
|| msg.contains("url error")) {
|
||||
|| msg.contains("url error")
|
||||
// Volcano Ark: model exists but the user's account hasn't opened it,
|
||||
// or the id isn't valid for this region. Both are hard failures —
|
||||
// retrying won't help, and a different provider may serve the model.
|
||||
|| msg.contains("ModelNotOpen")
|
||||
|| msg.contains("InvalidEndpointOrModel")) {
|
||||
return ErrorType.MODEL_NOT_FOUND;
|
||||
}
|
||||
// Client errors (400 Bad Request — unsupported format, invalid params, etc.) — NOT retryable
|
||||
@ -376,6 +381,20 @@ public class NodeStreamingChatHelper {
|
||||
sb.append(cur.getMessage()).append(" | ");
|
||||
}
|
||||
sb.append(cur.getClass().getSimpleName()).append(" | ");
|
||||
// Include the HTTP response body for WebClient errors. Many providers
|
||||
// (Volcano Ark, Ollama, …) put the actionable error code only in the
|
||||
// body, while the surface message is just "404 Not Found from POST X".
|
||||
// Without this, classifyError() can never see codes like ModelNotOpen.
|
||||
if (cur instanceof WebClientResponseException wre) {
|
||||
try {
|
||||
String body = wre.getResponseBodyAsString();
|
||||
if (body != null && !body.isEmpty()) {
|
||||
sb.append(body.length() > 1024 ? body.substring(0, 1024) : body)
|
||||
.append(" | ");
|
||||
}
|
||||
} catch (Exception ignored) {
|
||||
}
|
||||
}
|
||||
cur = cur.getCause();
|
||||
}
|
||||
return sb.toString();
|
||||
@ -1155,6 +1174,19 @@ public class NodeStreamingChatHelper {
|
||||
}
|
||||
}
|
||||
|
||||
// Pulls the offending model id out of a Volcano Ark error body. Both
|
||||
// ModelNotOpen and InvalidEndpointOrModel.NotFound mention it after a
|
||||
// recognizable phrase ("activated the model X" / "model or endpoint X").
|
||||
private static final java.util.regex.Pattern ARK_MODEL_NAME_PATTERN =
|
||||
java.util.regex.Pattern.compile(
|
||||
"(?:activated the model|model or endpoint)\\s+([A-Za-z0-9._-]+)");
|
||||
|
||||
private static String extractArkModelName(String body) {
|
||||
if (body == null) return null;
|
||||
java.util.regex.Matcher m = ARK_MODEL_NAME_PATTERN.matcher(body);
|
||||
return m.find() ? m.group(1) : null;
|
||||
}
|
||||
|
||||
/** 从异常链提取用户友好的错误信息 */
|
||||
private static String extractUserFriendlyError(Throwable error) {
|
||||
String msg = error.getMessage();
|
||||
@ -1188,6 +1220,26 @@ public class NodeStreamingChatHelper {
|
||||
+ "例如 qwen3、qwen2.5:7b+、llama3.1:8b+、mistral-nemo、command-r 等。";
|
||||
}
|
||||
|
||||
// Volcano Engine Ark — model exists but the user's account hasn't activated it.
|
||||
// Body shape: {"error":{"code":"ModelNotOpen","message":"Your account ... has not activated the model X. Please activate the model service in the Ark Console..."}}
|
||||
if (combined.contains("ModelNotOpen")) {
|
||||
String modelId = extractArkModelName(combined);
|
||||
String suffix = modelId != null ? "「" + modelId + "」" : "";
|
||||
return "火山方舟（Volcano Ark）尚未为该账号开通模型" + suffix
|
||||
+ "。请前往 Ark 控制台 → 模型广场，对该模型点击「开通服务」后重试。"
|
||||
+ "（控制台：https://console.volcengine.com/ark）";
|
||||
}
|
||||
|
||||
// Volcano Engine Ark — model id doesn't exist for the user's region/key.
|
||||
// Body shape: {"error":{"code":"InvalidEndpointOrModel.NotFound","message":"The model or endpoint X does not exist or you do not have access to it..."}}
|
||||
if (combined.contains("InvalidEndpointOrModel")) {
|
||||
String modelId = extractArkModelName(combined);
|
||||
String suffix = modelId != null ? "「" + modelId + "」" : "";
|
||||
return "火山方舟（Volcano Ark）找不到模型" + suffix
|
||||
+ "。原因可能是模型 ID 不在当前区域，或你的账号没有访问权限。"
|
||||
+ "建议在 设置 → 模型 里点「刷新模型」重新发现，或在 Ark 控制台创建「推理接入点」(ep-XXX) 后使用该 ID。";
|
||||
}
|
||||
|
||||
// DashScope "url error" is really "model name not mapped to any valid endpoint".
|
||||
if (msg.contains("url error") || msg.contains("[InvalidParameter]")
|
||||
|| msg.contains("Model not exist") || msg.contains("model_not_found")
|
||||
|
||||
@ -385,11 +385,11 @@ public class ModelDiscoveryService {
|
||||
.defaultHeader(HttpHeaders.ACCEPT, MediaType.APPLICATION_JSON_VALUE)
|
||||
.build();
|
||||
|
||||
RestClient.RequestHeadersSpec<?> spec = client.get().uri("/v1/models");
|
||||
RestClient.RequestHeadersSpec<?> spec = client.get().uri(resolveModelsPath(baseUrl));
|
||||
if (modelProviderService.hasUsableApiKey(apiKey)) {
|
||||
spec = spec.header(HttpHeaders.AUTHORIZATION, "Bearer " + apiKey.trim());
|
||||
}
|
||||
// 添加自定义 headers（从 generateKwargs 中读取）
|
||||
// Apply any custom headers declared in generateKwargs.
|
||||
Map<String, Object> kwargs = modelProviderService.readProviderGenerateKwargs(provider);
|
||||
applyCustomHeaders(spec, kwargs);
|
||||
|
||||
@ -717,29 +717,51 @@ public class ModelDiscoveryService {
|
||||
|
||||
// ==================== 工具方法 ====================
|
||||
|
||||
// Trailing "/v{digits}" segment in a base URL — restricted to numeric major versions,
|
||||
// which is the OpenAI-compatible convention (/v1 OpenAI, /v3 Volcano Ark, /v4 Zhipu).
|
||||
private static final java.util.regex.Pattern BASE_URL_VERSION_SUFFIX =
|
||||
java.util.regex.Pattern.compile(".*/v\\d+$");
|
||||
|
||||
/**
|
||||
* 从 generateKwargs 中解析 completionsPath，处理 baseUrl 与路径前缀的重叠。
|
||||
* 例如：baseUrl 以 /v4 结尾，completionsPath 为 /chat/completions → 最终 /chat/completions
|
||||
* baseUrl 以 /v1 结尾，completionsPath 为 /v1/chat/completions → 最终 /chat/completions
|
||||
* Resolve the chat-completions path. An explicit {@code completionsPath} in
|
||||
* {@code generateKwargs} is always honored as-is. Otherwise we default to
|
||||
* {@code /v1/chat/completions} and dedupe the {@code /v1} prefix when the
|
||||
* baseUrl already carries a {@code /v{N}} segment (e.g. Volcano Engine Ark
|
||||
* base {@code https://ark.cn-beijing.volces.com/api/v3}).
|
||||
*/
|
||||
private String resolveCompletionsPath(String baseUrl, Map<String, Object> kwargs) {
|
||||
String path = "/v1/chat/completions";
|
||||
if (kwargs != null) {
|
||||
Object raw = kwargs.get("completionsPath");
|
||||
if (raw instanceof String value && StringUtils.hasText(value)) {
|
||||
path = value.trim();
|
||||
String path = value.trim();
|
||||
if (!path.startsWith("/")) {
|
||||
path = "/" + path;
|
||||
}
|
||||
return path;
|
||||
}
|
||||
}
|
||||
// 避免路径重叠：如果 baseUrl 以 /v1 结尾且 path 以 /v1/ 开头，去掉重复
|
||||
if (baseUrl != null && baseUrl.endsWith("/v1") && path.startsWith("/v1/")) {
|
||||
String path = "/v1/chat/completions";
|
||||
// If baseUrl already ends with /v{N}, strip the /v1 prefix from the default
|
||||
// so we don't end up with /api/v3/v1/chat/completions (404).
|
||||
if (baseUrl != null && BASE_URL_VERSION_SUFFIX.matcher(baseUrl).matches() && path.startsWith("/v1/")) {
|
||||
path = path.substring(3);
|
||||
}
|
||||
return path;
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolve the OpenAI-compatible {@code /v1/models} path against a base URL,
|
||||
* stripping the {@code /v1} prefix when the base already carries a {@code /v{N}}
|
||||
* suffix (Volcano Engine Ark, etc.).
|
||||
*/
|
||||
private String resolveModelsPath(String baseUrl) {
|
||||
String path = "/v1/models";
|
||||
if (baseUrl != null && BASE_URL_VERSION_SUFFIX.matcher(baseUrl).matches()) {
|
||||
path = "/models";
|
||||
}
|
||||
return path;
|
||||
}
|
||||
|
||||
private String normalizeBaseUrl(String baseUrl) {
|
||||
if (!StringUtils.hasText(baseUrl)) {
|
||||
return null;
|
||||
|
||||
@ -112,7 +112,7 @@ VALUES ('zhipu-intl', 'Zhipu AI (International)', '', 'OpenAIChatModel', '', 'ht
|
||||
|
||||
MERGE INTO mate_model_provider (provider_id, name, api_key_prefix, chat_model, api_key, base_url, generate_kwargs, is_custom, is_local, support_model_discovery, support_connection_check, freeze_url, require_api_key, create_time, update_time)
|
||||
KEY (provider_id)
|
||||
VALUES ('volcengine', 'Volcano Engine', '', 'OpenAIChatModel', '', 'https://ark.cn-beijing.volces.com/api/v3', '{}', FALSE, FALSE, FALSE, TRUE, TRUE, TRUE, NOW(), NOW());
|
||||
VALUES ('volcengine', 'Volcano Engine', '', 'OpenAIChatModel', '', 'https://ark.cn-beijing.volces.com/api/v3', '{}', FALSE, FALSE, TRUE, TRUE, TRUE, TRUE, NOW(), NOW());
|
||||
|
||||
MERGE INTO mate_model_provider (provider_id, name, api_key_prefix, chat_model, api_key, base_url, generate_kwargs, is_custom, is_local, support_model_discovery, support_connection_check, freeze_url, require_api_key, auth_type, create_time, update_time)
|
||||
KEY (provider_id)
|
||||
@ -248,12 +248,11 @@ MERGE INTO mate_model_config (id, name, provider, model_name, description, tempe
|
||||
(1000000221, 'GLM-5V-Turbo', 'zhipu-intl', 'glm-5v-turbo', 'Multimodal vision model (International, recommended)', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000222, 'GLM-5', 'zhipu-intl', 'glm-5', 'Flagship model (International)', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000223, 'GLM-5.1', 'zhipu-intl', 'glm-5.1', 'Latest flagship model (International)', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000230, 'Doubao 1.5 Pro 256K', 'volcengine', 'doubao-1.5-pro-256k', 'Doubao flagship model with 256K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000231, 'Doubao 1.5 Pro 32K', 'volcengine', 'doubao-1.5-pro-32k', 'Doubao flagship model with 32K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000232, 'Doubao 1.5 Lite 32K', 'volcengine', 'doubao-1.5-lite-32k', 'Doubao lite model, cost-effective', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000233, 'Doubao 1.5 Vision Pro 32K', 'volcengine', 'doubao-1.5-vision-pro-32k', 'Doubao multimodal vision model', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000234, 'Doubao 1.5 Thinking Pro', 'volcengine', 'doubao-1.5-thinking-pro', 'Doubao deep reasoning model', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000235, 'Doubao 1.5 Thinking Lite', 'volcengine', 'doubao-1.5-thinking-lite', 'Doubao lite reasoning model', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000310, 'Doubao Seed 1.8', 'volcengine', 'doubao-seed-1-8-251228', 'Doubao flagship multimodal model, text + image, 256K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000311, 'Doubao Seed Code Preview', 'volcengine', 'doubao-seed-code-preview-251028', 'Doubao code preview model, text + image, 256K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000312, 'Kimi K2.5', 'volcengine', 'kimi-k2-5-260127', 'Kimi K2.5 (hosted on Volcano Ark), text + image, 256K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000313, 'GLM 4.7', 'volcengine', 'glm-4-7-251222', 'GLM 4.7 (hosted on Volcano Ark), text + image, 200K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000314, 'DeepSeek V3.2', 'volcengine', 'deepseek-v3-2-251201', 'DeepSeek V3.2 (hosted on Volcano Ark), text + image, 128K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000240, 'Kimi for Coding', 'kimi-code', 'kimi-for-coding', 'Kimi Code dedicated coding model', 0.2, 32768, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000250, 'GPT-5.4', 'openai-chatgpt', 'gpt-5.4', 'ChatGPT Plus/Pro member model (OAuth login)', NULL, 128000, NULL, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000251, 'GPT-5.4 Mini', 'openai-chatgpt', 'gpt-5.4-mini', 'ChatGPT member lightweight model', NULL, 128000, NULL, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
|
||||
@ -127,7 +127,7 @@ VALUES ('zhipu-intl', 'Zhipu AI (International)', '', 'OpenAIChatModel', '', 'ht
|
||||
ON DUPLICATE KEY UPDATE name=VALUES(name), api_key_prefix=VALUES(api_key_prefix), chat_model=VALUES(chat_model), api_key=VALUES(api_key), base_url=VALUES(base_url), generate_kwargs=VALUES(generate_kwargs), is_custom=VALUES(is_custom), is_local=VALUES(is_local), support_model_discovery=VALUES(support_model_discovery), support_connection_check=VALUES(support_connection_check), freeze_url=VALUES(freeze_url), require_api_key=VALUES(require_api_key), update_time=VALUES(update_time);
|
||||
|
||||
INSERT INTO mate_model_provider (provider_id, name, api_key_prefix, chat_model, api_key, base_url, generate_kwargs, is_custom, is_local, support_model_discovery, support_connection_check, freeze_url, require_api_key, create_time, update_time)
|
||||
VALUES ('volcengine', 'Volcano Engine', '', 'OpenAIChatModel', '', 'https://ark.cn-beijing.volces.com/api/v3', '{}', FALSE, FALSE, FALSE, TRUE, TRUE, TRUE, NOW(), NOW())
|
||||
VALUES ('volcengine', 'Volcano Engine', '', 'OpenAIChatModel', '', 'https://ark.cn-beijing.volces.com/api/v3', '{}', FALSE, FALSE, TRUE, TRUE, TRUE, TRUE, NOW(), NOW())
|
||||
ON DUPLICATE KEY UPDATE name=VALUES(name), api_key_prefix=VALUES(api_key_prefix), chat_model=VALUES(chat_model), api_key=VALUES(api_key), base_url=VALUES(base_url), generate_kwargs=VALUES(generate_kwargs), is_custom=VALUES(is_custom), is_local=VALUES(is_local), support_model_discovery=VALUES(support_model_discovery), support_connection_check=VALUES(support_connection_check), freeze_url=VALUES(freeze_url), require_api_key=VALUES(require_api_key), update_time=VALUES(update_time);
|
||||
|
||||
INSERT INTO mate_model_provider (provider_id, name, api_key_prefix, chat_model, api_key, base_url, generate_kwargs, is_custom, is_local, support_model_discovery, support_connection_check, freeze_url, require_api_key, auth_type, create_time, update_time)
|
||||
@ -286,12 +286,11 @@ VALUES
|
||||
(1000000221, 'GLM-5V-Turbo', 'zhipu-intl', 'glm-5v-turbo', 'Multimodal vision model (International, recommended)', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000222, 'GLM-5', 'zhipu-intl', 'glm-5', 'Flagship model (International)', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000223, 'GLM-5.1', 'zhipu-intl', 'glm-5.1', 'Latest flagship model (International)', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000230, 'Doubao 1.5 Pro 256K', 'volcengine', 'doubao-1.5-pro-256k', 'Doubao flagship model with 256K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000231, 'Doubao 1.5 Pro 32K', 'volcengine', 'doubao-1.5-pro-32k', 'Doubao flagship model with 32K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000232, 'Doubao 1.5 Lite 32K', 'volcengine', 'doubao-1.5-lite-32k', 'Doubao lite model, cost-effective', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000233, 'Doubao 1.5 Vision Pro 32K', 'volcengine', 'doubao-1.5-vision-pro-32k', 'Doubao multimodal vision model', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000234, 'Doubao 1.5 Thinking Pro', 'volcengine', 'doubao-1.5-thinking-pro', 'Doubao deep reasoning model', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000235, 'Doubao 1.5 Thinking Lite', 'volcengine', 'doubao-1.5-thinking-lite', 'Doubao lite reasoning model', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000310, 'Doubao Seed 1.8', 'volcengine', 'doubao-seed-1-8-251228', 'Doubao flagship multimodal model, text + image, 256K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000311, 'Doubao Seed Code Preview', 'volcengine', 'doubao-seed-code-preview-251028', 'Doubao code preview model, text + image, 256K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000312, 'Kimi K2.5', 'volcengine', 'kimi-k2-5-260127', 'Kimi K2.5 (hosted on Volcano Ark), text + image, 256K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000313, 'GLM 4.7', 'volcengine', 'glm-4-7-251222', 'GLM 4.7 (hosted on Volcano Ark), text + image, 200K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000314, 'DeepSeek V3.2', 'volcengine', 'deepseek-v3-2-251201', 'DeepSeek V3.2 (hosted on Volcano Ark), text + image, 128K context', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000240, 'Kimi for Coding', 'kimi-code', 'kimi-for-coding', 'Kimi Code dedicated coding model', 0.2, 32768, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000250, 'GPT-5.4', 'openai-chatgpt', 'gpt-5.4', 'ChatGPT Plus/Pro member model (OAuth login)', NULL, 128000, NULL, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000251, 'GPT-5.4 Mini', 'openai-chatgpt', 'gpt-5.4-mini', 'ChatGPT member lightweight model', NULL, 128000, NULL, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
|
||||
@ -127,7 +127,7 @@ VALUES ('zhipu-intl', 'Zhipu AI (International)', '', 'OpenAIChatModel', '', 'ht
|
||||
ON DUPLICATE KEY UPDATE name=VALUES(name), api_key_prefix=VALUES(api_key_prefix), chat_model=VALUES(chat_model), api_key=VALUES(api_key), base_url=VALUES(base_url), generate_kwargs=VALUES(generate_kwargs), is_custom=VALUES(is_custom), is_local=VALUES(is_local), support_model_discovery=VALUES(support_model_discovery), support_connection_check=VALUES(support_connection_check), freeze_url=VALUES(freeze_url), require_api_key=VALUES(require_api_key), update_time=VALUES(update_time);
|
||||
|
||||
INSERT INTO mate_model_provider (provider_id, name, api_key_prefix, chat_model, api_key, base_url, generate_kwargs, is_custom, is_local, support_model_discovery, support_connection_check, freeze_url, require_api_key, create_time, update_time)
|
||||
VALUES ('volcengine', 'Volcano Engine (火山引擎)', '', 'OpenAIChatModel', '', 'https://ark.cn-beijing.volces.com/api/v3', '{}', FALSE, FALSE, FALSE, TRUE, TRUE, TRUE, NOW(), NOW())
|
||||
VALUES ('volcengine', 'Volcano Engine (火山引擎)', '', 'OpenAIChatModel', '', 'https://ark.cn-beijing.volces.com/api/v3', '{}', FALSE, FALSE, TRUE, TRUE, TRUE, TRUE, NOW(), NOW())
|
||||
ON DUPLICATE KEY UPDATE name=VALUES(name), api_key_prefix=VALUES(api_key_prefix), chat_model=VALUES(chat_model), api_key=VALUES(api_key), base_url=VALUES(base_url), generate_kwargs=VALUES(generate_kwargs), is_custom=VALUES(is_custom), is_local=VALUES(is_local), support_model_discovery=VALUES(support_model_discovery), support_connection_check=VALUES(support_connection_check), freeze_url=VALUES(freeze_url), require_api_key=VALUES(require_api_key), update_time=VALUES(update_time);
|
||||
|
||||
INSERT INTO mate_model_provider (provider_id, name, api_key_prefix, chat_model, api_key, base_url, generate_kwargs, is_custom, is_local, support_model_discovery, support_connection_check, freeze_url, require_api_key, auth_type, create_time, update_time)
|
||||
@ -286,12 +286,11 @@ VALUES
|
||||
(1000000221, 'GLM-5V-Turbo', 'zhipu-intl', 'glm-5v-turbo', '多模态视觉模型（国际版，推荐）', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000222, 'GLM-5', 'zhipu-intl', 'glm-5', '旗舰模型（国际版）', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000223, 'GLM-5.1', 'zhipu-intl', 'glm-5.1', '最新旗舰模型（国际版）', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000230, 'Doubao 1.5 Pro 256K', 'volcengine', 'doubao-1.5-pro-256k', '豆包旗舰模型，256K 超长上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000231, 'Doubao 1.5 Pro 32K', 'volcengine', 'doubao-1.5-pro-32k', '豆包旗舰模型，32K 上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000232, 'Doubao 1.5 Lite 32K', 'volcengine', 'doubao-1.5-lite-32k', '豆包轻量模型，高性价比', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000233, 'Doubao 1.5 Vision Pro 32K', 'volcengine', 'doubao-1.5-vision-pro-32k', '豆包多模态视觉模型', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000234, 'Doubao 1.5 Thinking Pro', 'volcengine', 'doubao-1.5-thinking-pro', '豆包深度推理模型', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000235, 'Doubao 1.5 Thinking Lite', 'volcengine', 'doubao-1.5-thinking-lite', '豆包轻量推理模型', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000310, 'Doubao Seed 1.8', 'volcengine', 'doubao-seed-1-8-251228', '豆包旗舰多模态模型，文本+图像，256K 上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000311, 'Doubao Seed Code Preview', 'volcengine', 'doubao-seed-code-preview-251028', '豆包代码预览模型，文本+图像，256K 上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000312, 'Kimi K2.5', 'volcengine', 'kimi-k2-5-260127', 'Kimi K2.5（火山方舟托管），文本+图像，256K 上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000313, 'GLM 4.7', 'volcengine', 'glm-4-7-251222', 'GLM 4.7（火山方舟托管），文本+图像，200K 上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000314, 'DeepSeek V3.2', 'volcengine', 'deepseek-v3-2-251201', 'DeepSeek V3.2（火山方舟托管），文本+图像，128K 上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000240, 'Kimi for Coding', 'kimi-code', 'kimi-for-coding', 'Kimi Code 专用编码模型', 0.2, 32768, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000250, 'GPT-5.4', 'openai-chatgpt', 'gpt-5.4', 'ChatGPT Plus/Pro 会员模型（OAuth 登录）', NULL, 128000, NULL, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000251, 'GPT-5.4 Mini', 'openai-chatgpt', 'gpt-5.4-mini', 'ChatGPT 会员轻量模型', NULL, 128000, NULL, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
|
||||
@ -112,7 +112,7 @@ VALUES ('zhipu-intl', 'Zhipu AI (International)', '', 'OpenAIChatModel', '', 'ht
|
||||
|
||||
MERGE INTO mate_model_provider (provider_id, name, api_key_prefix, chat_model, api_key, base_url, generate_kwargs, is_custom, is_local, support_model_discovery, support_connection_check, freeze_url, require_api_key, create_time, update_time)
|
||||
KEY (provider_id)
|
||||
VALUES ('volcengine', 'Volcano Engine (火山引擎)', '', 'OpenAIChatModel', '', 'https://ark.cn-beijing.volces.com/api/v3', '{}', FALSE, FALSE, FALSE, TRUE, TRUE, TRUE, NOW(), NOW());
|
||||
VALUES ('volcengine', 'Volcano Engine (火山引擎)', '', 'OpenAIChatModel', '', 'https://ark.cn-beijing.volces.com/api/v3', '{}', FALSE, FALSE, TRUE, TRUE, TRUE, TRUE, NOW(), NOW());
|
||||
|
||||
MERGE INTO mate_model_provider (provider_id, name, api_key_prefix, chat_model, api_key, base_url, generate_kwargs, is_custom, is_local, support_model_discovery, support_connection_check, freeze_url, require_api_key, auth_type, create_time, update_time)
|
||||
KEY (provider_id)
|
||||
@ -252,12 +252,11 @@ MERGE INTO mate_model_config (id, name, provider, model_name, description, tempe
|
||||
(1000000221, 'GLM-5V-Turbo', 'zhipu-intl', 'glm-5v-turbo', '多模态视觉模型（国际版，推荐）', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000222, 'GLM-5', 'zhipu-intl', 'glm-5', '旗舰模型（国际版）', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000223, 'GLM-5.1', 'zhipu-intl', 'glm-5.1', '最新旗舰模型（国际版）', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000230, 'Doubao 1.5 Pro 256K', 'volcengine', 'doubao-1.5-pro-256k', '豆包旗舰模型，256K 超长上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000231, 'Doubao 1.5 Pro 32K', 'volcengine', 'doubao-1.5-pro-32k', '豆包旗舰模型，32K 上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000232, 'Doubao 1.5 Lite 32K', 'volcengine', 'doubao-1.5-lite-32k', '豆包轻量模型，高性价比', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000233, 'Doubao 1.5 Vision Pro 32K', 'volcengine', 'doubao-1.5-vision-pro-32k', '豆包多模态视觉模型', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000234, 'Doubao 1.5 Thinking Pro', 'volcengine', 'doubao-1.5-thinking-pro', '豆包深度推理模型', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000235, 'Doubao 1.5 Thinking Lite', 'volcengine', 'doubao-1.5-thinking-lite', '豆包轻量推理模型', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000310, 'Doubao Seed 1.8', 'volcengine', 'doubao-seed-1-8-251228', '豆包旗舰多模态模型，文本+图像，256K 上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000311, 'Doubao Seed Code Preview', 'volcengine', 'doubao-seed-code-preview-251028', '豆包代码预览模型，文本+图像，256K 上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000312, 'Kimi K2.5', 'volcengine', 'kimi-k2-5-260127', 'Kimi K2.5（火山方舟托管），文本+图像，256K 上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000313, 'GLM 4.7', 'volcengine', 'glm-4-7-251222', 'GLM 4.7（火山方舟托管），文本+图像，200K 上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000314, 'DeepSeek V3.2', 'volcengine', 'deepseek-v3-2-251201', 'DeepSeek V3.2（火山方舟托管），文本+图像，128K 上下文', 0.7, 4096, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000240, 'Kimi for Coding', 'kimi-code', 'kimi-for-coding', 'Kimi Code 专用编码模型', 0.2, 32768, 0.8, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000250, 'GPT-5.4', 'openai-chatgpt', 'gpt-5.4', 'ChatGPT Plus/Pro 会员模型（OAuth 登录）', NULL, 128000, NULL, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
(1000000251, 'GPT-5.4 Mini', 'openai-chatgpt', 'gpt-5.4-mini', 'ChatGPT 会员轻量模型', NULL, 128000, NULL, TRUE, TRUE, FALSE, NOW(), NOW(), 0),
|
||||
|
||||
Loading…
Reference in New Issue
Block a user