airkjw/CLIProxyAPI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #1761 from margbug01/fix/thinking-chain-display

Browse Source 
fix: support thinking.type=auto from Amp client and decouple thinking translation from unsigned history
This commit is contained in:
Luis Pater
2026-03-01 02:30:42 +08:00
committed by GitHub
parent a6ce5f36e6 8de0885b7d
commit 5446cd2b02
2 changed files with 10 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/registry/model_definitions_static_data.go
+3 -2
View File
@@ -958,8 +958,9 @@ func GetAntigravityModelConfig() map[string]*AntigravityModelConfig {
"claude-sonnet-4-5-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 64000}, "claude-sonnet-4-5-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 64000},
"claude-opus-4-5-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 64000}, "claude-opus-4-5-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 64000},
"claude-opus-4-6-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 64000}, "claude-opus-4-6-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 64000},
"claude-sonnet-4-5": {MaxCompletionTokens: 64000}, "claude-opus-4-6": {Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 128000},
"claude-sonnet-4-6": {MaxCompletionTokens: 64000}, "claude-sonnet-4-5": {Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 64000},
"claude-sonnet-4-6": {Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 64000},
"claude-sonnet-4-6-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 64000}, "claude-sonnet-4-6-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 64000},
"gpt-oss-120b-medium": {}, "gpt-oss-120b-medium": {},
"tab_flash_lite_preview": {}, "tab_flash_lite_preview": {},
internal/translator/antigravity/claude/antigravity_claude_request.go
+7 -1
View File
@@ -400,7 +400,7 @@ func ConvertClaudeRequestToAntigravity(modelName string, inputRawJSON []byte, _
hasTools := toolDeclCount > 0 hasTools := toolDeclCount > 0
thinkingResult := gjson.GetBytes(rawJSON, "thinking") thinkingResult := gjson.GetBytes(rawJSON, "thinking")
thinkingType := thinkingResult.Get("type").String() thinkingType := thinkingResult.Get("type").String()
hasThinking := thinkingResult.Exists() && thinkingResult.IsObject() && (thinkingType == "enabled" || thinkingType == "adaptive") hasThinking := thinkingResult.Exists() && thinkingResult.IsObject() && (thinkingType == "enabled" || thinkingType == "adaptive" || thinkingType == "auto")
isClaudeThinking := util.IsClaudeThinkingModel(modelName) isClaudeThinking := util.IsClaudeThinkingModel(modelName)
if hasTools && hasThinking && isClaudeThinking { if hasTools && hasThinking && isClaudeThinking {
@@ -440,6 +440,12 @@ func ConvertClaudeRequestToAntigravity(modelName string, inputRawJSON []byte, _
out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.thinkingBudget", budget) out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.thinkingBudget", budget)
out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.includeThoughts", true) out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.includeThoughts", true)
} }
case "auto":
// Amp sends thinking.type="auto" — use max budget from model config
// Antigravity API for Claude models requires a concrete positive budget,
// not -1. Use a high default that ApplyThinking will cap to model max.
out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.thinkingBudget", 128000)
out, _ = sjson.Set(out, "request.generationConfig.thinkingConfig.includeThoughts", true)
case "adaptive": case "adaptive":
// Keep adaptive as a high level sentinel; ApplyThinking resolves it // Keep adaptive as a high level sentinel; ApplyThinking resolves it
// to model-specific max capability. // to model-specific max capability.