fix: switch alibaba-coding-plan to OpenAI-compat endpoint with proper compat flags (#1003)
The alibaba-coding-plan provider was using the Anthropic-compatible endpoint (/apps/anthropic) with anthropic-messages API, which caused issues with thinking mode on several models (MiniMax-M2.5 thinking loop, missing thinkingFormat for Qwen/GLM models). Changes for all 8 models: - API: anthropic-messages → openai-completions - Endpoint: /apps/anthropic → /v1 (OpenAI-compatible) - Added per-model compat flags: - Qwen models: thinkingFormat: 'qwen', supportsDeveloperRole: false - GLM models: thinkingFormat: 'qwen', supportsDeveloperRole: false - MiniMax-M2.5: supportsReasoningEffort: true, maxTokensField: 'max_tokens' - Kimi K2.5: thinkingFormat: 'zai', supportsDeveloperRole: false - Enabled reasoning for qwen3-max (was incorrectly false) - Fixed context windows to match tested values - Fixed MiniMax-M2.5 maxTokens: 24576 → 65536
This commit is contained in:
Tom Boucher
parent
7377a08d8e
commit
d252168de5
1 changed files with 42 additions and 34 deletions
|
|
@ -13388,27 +13388,28 @@ export const MODELS = {
|
|||
"qwen3.5-plus": {
|
||||
id: "qwen3.5-plus",
|
||||
name: "Qwen3.5 Plus",
|
||||
api: "anthropic-messages",
|
||||
api: "openai-completions",
|
||||
provider: "alibaba-coding-plan",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1000000,
|
||||
contextWindow: 983616,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
compat: { thinkingFormat: "qwen", supportsDeveloperRole: false },
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen3-max-2026-01-23": {
|
||||
id: "qwen3-max-2026-01-23",
|
||||
name: "Qwen3 Max 2026-01-23",
|
||||
api: "anthropic-messages",
|
||||
api: "openai-completions",
|
||||
provider: "alibaba-coding-plan",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic",
|
||||
reasoning: false,
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
|
|
@ -13416,15 +13417,16 @@ export const MODELS = {
|
|||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
contextWindow: 258048,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
compat: { thinkingFormat: "qwen", supportsDeveloperRole: false },
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen3-coder-next": {
|
||||
id: "qwen3-coder-next",
|
||||
name: "Qwen3 Coder Next",
|
||||
api: "anthropic-messages",
|
||||
api: "openai-completions",
|
||||
provider: "alibaba-coding-plan",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
|
|
@ -13433,15 +13435,16 @@ export const MODELS = {
|
|||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
contextWindow: 204800,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
compat: { supportsDeveloperRole: false },
|
||||
} satisfies Model<"openai-completions">,
|
||||
"qwen3-coder-plus": {
|
||||
id: "qwen3-coder-plus",
|
||||
name: "Qwen3 Coder Plus",
|
||||
api: "anthropic-messages",
|
||||
api: "openai-completions",
|
||||
provider: "alibaba-coding-plan",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
|
||||
reasoning: false,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
|
|
@ -13450,15 +13453,16 @@ export const MODELS = {
|
|||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 1000000,
|
||||
contextWindow: 997952,
|
||||
maxTokens: 65536,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
compat: { supportsDeveloperRole: false },
|
||||
} satisfies Model<"openai-completions">,
|
||||
"MiniMax-M2.5": {
|
||||
id: "MiniMax-M2.5",
|
||||
name: "MiniMax M2.5",
|
||||
api: "anthropic-messages",
|
||||
api: "openai-completions",
|
||||
provider: "alibaba-coding-plan",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
|
|
@ -13468,14 +13472,15 @@ export const MODELS = {
|
|||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 196608,
|
||||
maxTokens: 24576,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
maxTokens: 65536,
|
||||
compat: { supportsStore: false, supportsDeveloperRole: false, supportsReasoningEffort: true, maxTokensField: "max_tokens" },
|
||||
} satisfies Model<"openai-completions">,
|
||||
"glm-5": {
|
||||
id: "glm-5",
|
||||
name: "GLM-5",
|
||||
api: "anthropic-messages",
|
||||
api: "openai-completions",
|
||||
provider: "alibaba-coding-plan",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
|
|
@ -13486,13 +13491,14 @@ export const MODELS = {
|
|||
},
|
||||
contextWindow: 202752,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
compat: { thinkingFormat: "qwen", supportsDeveloperRole: false },
|
||||
} satisfies Model<"openai-completions">,
|
||||
"glm-4.7": {
|
||||
id: "glm-4.7",
|
||||
name: "GLM-4.7",
|
||||
api: "anthropic-messages",
|
||||
api: "openai-completions",
|
||||
provider: "alibaba-coding-plan",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
|
||||
reasoning: true,
|
||||
input: ["text"],
|
||||
cost: {
|
||||
|
|
@ -13501,26 +13507,28 @@ export const MODELS = {
|
|||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 202752,
|
||||
contextWindow: 169984,
|
||||
maxTokens: 16384,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
compat: { thinkingFormat: "qwen", supportsDeveloperRole: false },
|
||||
} satisfies Model<"openai-completions">,
|
||||
"kimi-k2.5": {
|
||||
id: "kimi-k2.5",
|
||||
name: "Kimi K2.5",
|
||||
api: "anthropic-messages",
|
||||
api: "openai-completions",
|
||||
provider: "alibaba-coding-plan",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic",
|
||||
baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1",
|
||||
reasoning: true,
|
||||
input: ["text", "image"],
|
||||
input: ["text"],
|
||||
cost: {
|
||||
input: 0,
|
||||
output: 0,
|
||||
cacheRead: 0,
|
||||
cacheWrite: 0,
|
||||
},
|
||||
contextWindow: 262144,
|
||||
contextWindow: 258048,
|
||||
maxTokens: 32768,
|
||||
} satisfies Model<"anthropic-messages">,
|
||||
compat: { thinkingFormat: "zai", supportsDeveloperRole: false },
|
||||
} satisfies Model<"openai-completions">,
|
||||
},
|
||||
"ollama-cloud": {
|
||||
"cogito-2.1:671b": {
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue