LLM/CLIProxyAPIPlus
1
0
Fork 0
mirror of https://github.com/router-for-me/CLIProxyAPIPlus.git synced 2026-03-08 06:43:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: support thinking.type="auto" from Amp client for Antigravity Claude models

Browse Source 
## Problem

When using Antigravity Claude models through CLIProxyAPI, the thinking
chain (reasoning content) does not display in the Amp client.

## Root Cause

The Amp client sends `thinking: {"type": "auto"}` in its requests,
but `ConvertClaudeRequestToAntigravity` only handled `"enabled"` and
`"adaptive"` types in its switch statement. The `"auto"` type was
silently ignored, resulting in no `thinkingConfig` being set in the
translated Gemini request. Without `thinkingConfig`, the Antigravity
API returns responses without any thinking content.

Additionally, the Antigravity API for Claude models does not support
`thinkingBudget: -1` (auto mode sentinel). It requires a concrete
positive budget value. The fix uses 128000 as the budget for "auto"
mode, which `ApplyThinking` will then normalize to stay within the
model's actual limits (e.g., capped to `maxOutputTokens - 1`).

## Changes

### internal/translator/antigravity/claude/antigravity_claude_request.go

1. **Add "auto" case** to the thinking type switch statement.
   Sets `thinkingBudget: 128000` and `includeThoughts: true`.
   The budget is subsequently normalized by `ApplyThinking` based
   on model-specific limits.

2. **Add "auto" to hasThinking check** so that interleaved thinking
   hints are injected for tool-use scenarios when Amp sends
   `thinking.type="auto"`.

### internal/registry/model_definitions_static_data.go

3. **Add Thinking configuration** for `claude-sonnet-4-6`,
   `claude-sonnet-4-5`, and `claude-opus-4-6` in
   `GetAntigravityModelConfig()` -- these were previously missing,
   causing `ApplyThinking` to skip thinking config entirely.

## Testing

- Deployed to Railway test instance (cpa-thinking-test)
- Verified via debug logging that:
  - Amp sends `thinking: {"type": "auto"}`
  - CPA now translates this to `thinkingConfig: {thinkingBudget: 128000, includeThoughts: true}`
  - `ApplyThinking` normalizes the budget to model-specific limits
  - Antigravity API receives the correct thinkingConfig

Amp-Thread-ID: https://ampcode.com/threads/T-019ca511-710d-776d-a07c-4b750f871a93
Co-authored-by: Amp <amp@ampcode.com>
This commit is contained in:
margbug01
2026-03-01 00:54:17 +08:00
parent 27c68f5bb2
commit 8de0885b7d
2 changed files with 10 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
internal/registry/model_definitions_static_data.go
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-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-sonnet-4-5": {MaxCompletionTokens: 64000},
"claude-sonnet-4-6": {MaxCompletionTokens: 64000},
"claude-opus-4-6": {Thinking: &ThinkingSupport{Min: 1024, Max: 128000, ZeroAllowed: true, DynamicAllowed: true}, MaxCompletionTokens: 128000},
"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},
"gpt-oss-120b-medium": {},
"tab_flash_lite_preview": {},

8
internal/translator/antigravity/claude/antigravity_claude_request.go
View File

@@ -400,7 +400,7 @@ func ConvertClaudeRequestToAntigravity(modelName string, inputRawJSON []byte, _
hasTools := toolDeclCount > 0
thinkingResult := gjson.GetBytes(rawJSON, "thinking")
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)
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.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":
// Keep adaptive as a high level sentinel; ApplyThinking resolves it
// to model-specific max capability.