feat(gemini): add Gemini thinking configuration support and metadata normalization

- Introduced logic to parse and apply `thinkingBudget` and `include_thoughts` configurations from metadata.
- Enhanced request handling to include normalized Gemini model metadata, preserving the original model identifier.
- Updated Gemini and Gemini-CLI executors to apply thinking configuration based on metadata overrides.
- Refactored handlers to support metadata extraction and cloning during request preparation.
This commit is contained in:
Luis Pater
2025-10-16 11:31:18 +08:00
parent 9c5ac2927a
commit ade279d1f2
4 changed files with 257 additions and 6 deletions

View File

@@ -60,7 +60,11 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
from := opts.SourceFormat
to := sdktranslator.FromString("gemini-cli")
budgetOverride, includeOverride, hasOverride := util.GeminiThinkingFromMetadata(req.Metadata)
basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
if hasOverride {
basePayload = util.ApplyGeminiCLIThinkingConfig(basePayload, budgetOverride, includeOverride)
}
basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
action := "generateContent"
@@ -149,7 +153,11 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
from := opts.SourceFormat
to := sdktranslator.FromString("gemini-cli")
budgetOverride, includeOverride, hasOverride := util.GeminiThinkingFromMetadata(req.Metadata)
basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
if hasOverride {
basePayload = util.ApplyGeminiCLIThinkingConfig(basePayload, budgetOverride, includeOverride)
}
basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
projectID := strings.TrimSpace(stringValue(auth.Metadata, "project_id"))
@@ -292,8 +300,12 @@ func (e *GeminiCLIExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.
var lastStatus int
var lastBody []byte
budgetOverride, includeOverride, hasOverride := util.GeminiThinkingFromMetadata(req.Metadata)
for _, attemptModel := range models {
payload := sdktranslator.TranslateRequest(from, to, attemptModel, bytes.Clone(req.Payload), false)
if hasOverride {
payload = util.ApplyGeminiCLIThinkingConfig(payload, budgetOverride, includeOverride)
}
payload = deleteJSONField(payload, "project")
payload = deleteJSONField(payload, "model")
payload = disableGeminiThinkingConfig(payload, attemptModel)

View File

@@ -77,6 +77,9 @@ func (e *GeminiExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
from := opts.SourceFormat
to := sdktranslator.FromString("gemini")
body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok {
body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
}
body = disableGeminiThinkingConfig(body, req.Model)
body = fixGeminiImageAspectRatio(req.Model, body)
@@ -136,6 +139,9 @@ func (e *GeminiExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
from := opts.SourceFormat
to := sdktranslator.FromString("gemini")
body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok {
body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
}
body = disableGeminiThinkingConfig(body, req.Model)
body = fixGeminiImageAspectRatio(req.Model, body)
@@ -208,6 +214,9 @@ func (e *GeminiExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Aut
from := opts.SourceFormat
to := sdktranslator.FromString("gemini")
translatedReq := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
if budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(req.Metadata); ok {
translatedReq = util.ApplyGeminiThinkingConfig(translatedReq, budgetOverride, includeOverride)
}
translatedReq = disableGeminiThinkingConfig(translatedReq, req.Model)
translatedReq = fixGeminiImageAspectRatio(req.Model, translatedReq)
respCtx := context.WithValue(ctx, "alt", opts.Alt)

View File

@@ -0,0 +1,181 @@
package util
import (
"encoding/json"
"strconv"
"strings"
"github.com/tidwall/sjson"
)
const (
GeminiThinkingBudgetMetadataKey = "gemini_thinking_budget"
GeminiIncludeThoughtsMetadataKey = "gemini_include_thoughts"
GeminiOriginalModelMetadataKey = "gemini_original_model"
)
func ParseGeminiThinkingSuffix(model string) (string, *int, *bool, bool) {
if model == "" {
return model, nil, nil, false
}
lower := strings.ToLower(model)
if !strings.HasPrefix(lower, "gemini-") {
return model, nil, nil, false
}
if strings.HasSuffix(lower, "-nothinking") {
base := model[:len(model)-len("-nothinking")]
budgetValue := 0
if strings.HasPrefix(lower, "gemini-2.5-pro") {
budgetValue = 128
}
include := false
return base, &budgetValue, &include, true
}
idx := strings.LastIndex(lower, "-thinking-")
if idx == -1 {
return model, nil, nil, false
}
digits := model[idx+len("-thinking-"):]
if digits == "" {
return model, nil, nil, false
}
end := len(digits)
for i := 0; i < len(digits); i++ {
if digits[i] < '0' || digits[i] > '9' {
end = i
break
}
}
if end == 0 {
return model, nil, nil, false
}
valueStr := digits[:end]
value, err := strconv.Atoi(valueStr)
if err != nil {
return model, nil, nil, false
}
base := model[:idx]
budgetValue := value
return base, &budgetValue, nil, true
}
func ApplyGeminiThinkingConfig(body []byte, budget *int, includeThoughts *bool) []byte {
if budget == nil && includeThoughts == nil {
return body
}
updated := body
if budget != nil {
valuePath := "generationConfig.thinkingConfig.thinkingBudget"
rewritten, err := sjson.SetBytes(updated, valuePath, *budget)
if err == nil {
updated = rewritten
}
}
if includeThoughts != nil {
valuePath := "generationConfig.thinkingConfig.include_thoughts"
rewritten, err := sjson.SetBytes(updated, valuePath, *includeThoughts)
if err == nil {
updated = rewritten
}
}
return updated
}
func ApplyGeminiCLIThinkingConfig(body []byte, budget *int, includeThoughts *bool) []byte {
if budget == nil && includeThoughts == nil {
return body
}
updated := body
if budget != nil {
valuePath := "request.generationConfig.thinkingConfig.thinkingBudget"
rewritten, err := sjson.SetBytes(updated, valuePath, *budget)
if err == nil {
updated = rewritten
}
}
if includeThoughts != nil {
valuePath := "request.generationConfig.thinkingConfig.include_thoughts"
rewritten, err := sjson.SetBytes(updated, valuePath, *includeThoughts)
if err == nil {
updated = rewritten
}
}
return updated
}
func GeminiThinkingFromMetadata(metadata map[string]any) (*int, *bool, bool) {
if len(metadata) == 0 {
return nil, nil, false
}
var (
budgetPtr *int
includePtr *bool
matched bool
)
if rawBudget, ok := metadata[GeminiThinkingBudgetMetadataKey]; ok {
switch v := rawBudget.(type) {
case int:
budget := v
budgetPtr = &budget
matched = true
case int32:
budget := int(v)
budgetPtr = &budget
matched = true
case int64:
budget := int(v)
budgetPtr = &budget
matched = true
case float64:
budget := int(v)
budgetPtr = &budget
matched = true
case json.Number:
if val, err := v.Int64(); err == nil {
budget := int(val)
budgetPtr = &budget
matched = true
}
}
}
if rawInclude, ok := metadata[GeminiIncludeThoughtsMetadataKey]; ok {
switch v := rawInclude.(type) {
case bool:
include := v
includePtr = &include
matched = true
case string:
if parsed, err := strconv.ParseBool(v); err == nil {
include := parsed
includePtr = &include
matched = true
}
case json.Number:
if val, err := v.Int64(); err == nil {
include := val != 0
includePtr = &include
matched = true
}
case int:
include := v != 0
includePtr = &include
matched = true
case int32:
include := v != 0
includePtr = &include
matched = true
case int64:
include := v != 0
includePtr = &include
matched = true
case float64:
include := v != 0
includePtr = &include
matched = true
}
}
return budgetPtr, includePtr, matched
}