feat(providers): align codebuddy-cn catalog/capabilities with server config
- Sync codebuddy-cn catalog and capabilities with copilot.tencent.com server payload - Fix thinkingCanDisable semantics for glm-5.3 and deepseek-v4 models - Add missing glm-5.2 thinking levels to thinkingLevels.js - Add glm-5-turbo model to glm and glm-cn registries
This commit is contained in:
zmf
@@ -178,33 +178,37 @@ export const PROVIDER_CAPABILITIES = {
|
||||
// CodeBuddy.cn — authoritative per-model metadata from the gateway's model
|
||||
// config (contextWindow=maxInputTokens, maxOutput=maxOutputTokens, vision=
|
||||
// supportsImages). Every model reasons via OpenAI-style reasoning_effort
|
||||
// (see registry thinkingFormat). `onlyReasoning` models can't turn thinking
|
||||
// off → thinkingCanDisable:false (clamped to minimal instead of disabled).
|
||||
// (see registry thinkingFormat). For thinkingCanDisable use the server's
|
||||
// reasoning.canDisableThinking flag — see the note in the codebuddy-cn block
|
||||
// below; it is NOT the inverse of onlyReasoning.
|
||||
"codebuddy-cn": {
|
||||
"glm-5.2": { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 48000 },
|
||||
"glm-5.1": { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
|
||||
"glm-5.2": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: true, contextWindow: 1000000, maxOutput: 48000 },
|
||||
"glm-5.1": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
|
||||
"glm-5.0": { reasoning: true, thinkingFormat: "openai", contextWindow: 200000, maxOutput: 48000 },
|
||||
"glm-5.0-turbo": { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
|
||||
"glm-5v-turbo": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 38000 },
|
||||
// maxOutput 64000 per both the plugin-baked fallback and the live server
|
||||
// table (the old 38000 had no source and truncated output).
|
||||
"glm-5v-turbo": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 64000 },
|
||||
"glm-4.7": { reasoning: true, thinkingFormat: "openai", contextWindow: 200000, maxOutput: 48000 },
|
||||
"minimax-m3": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 512000, maxOutput: 48000 },
|
||||
"minimax-m2.7": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
|
||||
"minimax-m3": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 512000, maxOutput: 128000 },
|
||||
"kimi-k2.7": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 256000, maxOutput: 32000 },
|
||||
"kimi-k2.6": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 256000, maxOutput: 32000 },
|
||||
"kimi-k2.5": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 164000, maxOutput: 32000 },
|
||||
"hy3-preview": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 192000, maxOutput: 64000 },
|
||||
// hy3/hy3-x: 256K official (192K conservative, matches hy3-preview); hy4-preview: 1M official.
|
||||
// glm-5.3: 1M (GLM-5.x gen); glm-5.3-flash window unverified (200K conservative).
|
||||
// Per-model values mirror the server's product-config payload (the plugin
|
||||
// fetches it from copilot.tencent.com; the `models[]` entries carry
|
||||
// maxInputTokens/maxOutputTokens/supportsImages). contextWindow =
|
||||
// maxInputTokens, maxOutput = maxOutputTokens. Where the server and the
|
||||
// plugin-baked fallback disagree, the server table wins.
|
||||
// ⚠️ thinkingCanDisable maps to the server's reasoning.canDisableThinking —
|
||||
// it is NOT the inverse of onlyReasoning. onlyReasoning means "thinking is
|
||||
// on by default"; canDisableThinking means "it CAN be turned off". glm-5.3
|
||||
// and glm-5.3-flash are onlyReasoning:true BUT canDisableThinking:true, so
|
||||
// their thinking is switchable; the hy* models are forced always-on.
|
||||
"hy3": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 192000, maxOutput: 64000 },
|
||||
"hy3-x": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 192000, maxOutput: 64000 },
|
||||
"hy4-preview": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 64000 },
|
||||
"hy4-preview-x": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 64000 },
|
||||
"glm-5.3": { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 48000 },
|
||||
"glm-5.3-flash": { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 200000, maxOutput: 48000 },
|
||||
"kimi-k3-1": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 256000, maxOutput: 32000 },
|
||||
"deepseek-v4-pro": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 50000 },
|
||||
"deepseek-v4-flash": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 50000 },
|
||||
"deepseek-v3-2-volc": { reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 96000, maxOutput: 32000 },
|
||||
"glm-5.3": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: true, contextWindow: 1000000, maxOutput: 48000 },
|
||||
"glm-5.3-flash": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: true, contextWindow: 1000000, maxOutput: 32000 },
|
||||
"kimi-k3-1": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: false, contextWindow: 1000000, maxOutput: 32000 },
|
||||
"deepseek-v4-pro": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: true, contextWindow: 1000000, maxOutput: 50000 },
|
||||
"deepseek-v4-flash": { vision: true, reasoning: true, thinkingFormat: "openai", thinkingCanDisable: true, contextWindow: 1000000, maxOutput: 50000 },
|
||||
},
|
||||
// Qoder — upstream exposes opaque internal ids (dfmodel, kmodel, …); the
|
||||
// registry `name` is display-only and capability lookup matches on the raw
|
||||
|
||||
Reference in New Issue
Block a user