From ede4471b84bffc11fe78781c54ea710831acc6fb Mon Sep 17 00:00:00 2001
From: Ben Vargas <ben@vargas.com>
Date: Wed, 19 Nov 2025 12:46:13 -0700
Subject: [PATCH] feat(translator): add default thinkingConfig for
 gemini-3-pro-preview

Match official Gemini CLI behavior by always sending default
thinkingConfig when client doesn't specify reasoning parameters.

- Set thinkingBudget=-1 (dynamic) for gemini-3-pro-preview
- Set include_thoughts=true to return thinking process
- Apply to both /v1/chat/completions and /v1/responses endpoints
- See: ai-gemini-cli/packages/core/src/config/defaultModelConfigs.ts
---
 .../chat-completions/gemini-cli_openai_request.go    |  9 +++++++++
 .../responses/gemini_openai-responses_request.go     | 12 ++++++++++++
 2 files changed, 21 insertions(+)

diff --git a/internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go b/internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go
index 6f7ac724..99b50366 100644
--- a/internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go
+++ b/internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go
@@ -88,6 +88,15 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
 		}
 	}
 
+	// For gemini-3-pro-preview, always send default thinkingConfig when none specified.
+	// This matches the official Gemini CLI behavior which always sends:
+	// { thinkingBudget: -1, includeThoughts: true }
+	// See: ai-gemini-cli/packages/core/src/config/defaultModelConfigs.ts
+	if !gjson.GetBytes(out, "request.generationConfig.thinkingConfig").Exists() && modelName == "gemini-3-pro-preview" {
+		out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
+		out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
+	}
+
 	// Temperature/top_p/top_k
 	if tr := gjson.GetBytes(rawJSON, "temperature"); tr.Exists() && tr.Type == gjson.Number {
 		out, _ = sjson.SetBytes(out, "request.generationConfig.temperature", tr.Num)
diff --git a/internal/translator/gemini/openai/responses/gemini_openai-responses_request.go b/internal/translator/gemini/openai/responses/gemini_openai-responses_request.go
index 4eeebf3c..981fafc1 100644
--- a/internal/translator/gemini/openai/responses/gemini_openai-responses_request.go
+++ b/internal/translator/gemini/openai/responses/gemini_openai-responses_request.go
@@ -6,6 +6,7 @@ import (
 
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/translator/gemini/common"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
+	log "github.com/sirupsen/logrus"
 	"github.com/tidwall/gjson"
 	"github.com/tidwall/sjson"
 )
@@ -294,6 +295,17 @@ func ConvertOpenAIResponsesRequestToGemini(modelName string, inputRawJSON []byte
 			}
 		}
 	}
+
+	// For gemini-3-pro-preview, always send default thinkingConfig when none specified.
+	// This matches the official Gemini CLI behavior which always sends:
+	// { thinkingBudget: -1, includeThoughts: true }
+	// See: ai-gemini-cli/packages/core/src/config/defaultModelConfigs.ts
+	if !gjson.Get(out, "generationConfig.thinkingConfig").Exists() && modelName == "gemini-3-pro-preview" {
+		out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
+		out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)
+		log.Debugf("Applied default thinkingConfig for gemini-3-pro-preview (matches Gemini CLI): thinkingBudget=-1, include_thoughts=true")
+	}
+
 	result := []byte(out)
 	result = common.AttachDefaultSafetySettings(result, "safetySettings")
 	return result