Merge pull request #1914 from keh4l/feat/cc-mimicry-parity
fix(claude): align Claude Code OAuth mimicry with real CLI traffic
This commit is contained in:
@@ -12,17 +12,23 @@ import "encoding/json"
|
||||
|
||||
// AnthropicRequest is the request body for POST /v1/messages.
|
||||
type AnthropicRequest struct {
|
||||
Model string `json:"model"`
|
||||
MaxTokens int `json:"max_tokens"`
|
||||
System json.RawMessage `json:"system,omitempty"` // string or []AnthropicContentBlock
|
||||
Messages []AnthropicMessage `json:"messages"`
|
||||
Tools []AnthropicTool `json:"tools,omitempty"`
|
||||
Stream bool `json:"stream,omitempty"`
|
||||
Temperature *float64 `json:"temperature,omitempty"`
|
||||
TopP *float64 `json:"top_p,omitempty"`
|
||||
StopSeqs []string `json:"stop_sequences,omitempty"`
|
||||
Thinking *AnthropicThinking `json:"thinking,omitempty"`
|
||||
ToolChoice json.RawMessage `json:"tool_choice,omitempty"`
|
||||
Model string `json:"model"`
|
||||
MaxTokens int `json:"max_tokens"`
|
||||
System json.RawMessage `json:"system,omitempty"` // string or []AnthropicContentBlock
|
||||
Messages []AnthropicMessage `json:"messages"`
|
||||
Tools []AnthropicTool `json:"tools,omitempty"`
|
||||
Stream bool `json:"stream,omitempty"`
|
||||
Temperature *float64 `json:"temperature,omitempty"`
|
||||
TopP *float64 `json:"top_p,omitempty"`
|
||||
StopSeqs []string `json:"stop_sequences,omitempty"`
|
||||
Thinking *AnthropicThinking `json:"thinking,omitempty"`
|
||||
ToolChoice json.RawMessage `json:"tool_choice,omitempty"`
|
||||
// Metadata 会被原样透传给上游。OAuth/Claude-Code 路径依赖 metadata.user_id
|
||||
// 参与上游的"是否为官方 Claude Code 请求"判定;如果经由本结构体重新序列化
|
||||
// 时丢弃该字段,网关侧后续的 metadata 重写(ensureClaudeOAuthMetadataUserID/
|
||||
// RewriteUserIDWithMasking) 在 body 里拿不到起点,就无法重建一个合法的
|
||||
// user_id,进而导致请求被归类为第三方 app。
|
||||
Metadata json.RawMessage `json:"metadata,omitempty"`
|
||||
OutputConfig *AnthropicOutputConfig `json:"output_config,omitempty"`
|
||||
}
|
||||
|
||||
@@ -76,10 +82,18 @@ type AnthropicImageSource struct {
|
||||
|
||||
// AnthropicTool describes a tool available to the model.
|
||||
type AnthropicTool struct {
|
||||
Type string `json:"type,omitempty"` // e.g. "web_search_20250305" for server tools
|
||||
Name string `json:"name"`
|
||||
Description string `json:"description,omitempty"`
|
||||
InputSchema json.RawMessage `json:"input_schema"` // JSON Schema object
|
||||
Type string `json:"type,omitempty"` // e.g. "web_search_20250305" for server tools
|
||||
Name string `json:"name"`
|
||||
Description string `json:"description,omitempty"`
|
||||
InputSchema json.RawMessage `json:"input_schema"` // JSON Schema object
|
||||
CacheControl *AnthropicCacheControl `json:"cache_control,omitempty"`
|
||||
}
|
||||
|
||||
// AnthropicCacheControl 对应 Anthropic API 的 cache_control 字段。
|
||||
// ttl 默认由调用方决定;本项目策略见 claude.DefaultCacheControlTTL。
|
||||
type AnthropicCacheControl struct {
|
||||
Type string `json:"type"` // "ephemeral"
|
||||
TTL string `json:"ttl,omitempty"` // "5m" / "1h" / 省略=默认 5m(由 Anthropic 判定)
|
||||
}
|
||||
|
||||
// AnthropicResponse is the non-streaming response from POST /v1/messages.
|
||||
|
||||
@@ -4,6 +4,12 @@ package claude
|
||||
// Claude Code 客户端相关常量
|
||||
|
||||
// Beta header 常量
|
||||
//
|
||||
// 这里的常量对齐真实 Claude Code CLI 的最新流量(截至 2026-04)。
|
||||
// 选型参考:与 Parrot (src/transform/cc_mimicry.py) 的 BETAS 保持一致,
|
||||
// 原因:Anthropic 上游会基于 anthropic-beta 的完整集合判定请求来源;
|
||||
// 缺少任何"官方 Claude Code 请求才会带"的 beta,都会被降级到第三方额度,
|
||||
// 对应报错:`Third-party apps now draw from your extra usage, not your plan limits.`
|
||||
const (
|
||||
BetaOAuth = "oauth-2025-04-20"
|
||||
BetaClaudeCode = "claude-code-20250219"
|
||||
@@ -12,6 +18,13 @@ const (
|
||||
BetaTokenCounting = "token-counting-2024-11-01"
|
||||
BetaContext1M = "context-1m-2025-08-07"
|
||||
BetaFastMode = "fast-mode-2026-02-01"
|
||||
|
||||
// 新增(对齐官方 CLI 2.1.9x 以来的流量)
|
||||
BetaPromptCachingScope = "prompt-caching-scope-2026-01-05"
|
||||
BetaEffort = "effort-2025-11-24"
|
||||
BetaRedactThinking = "redact-thinking-2026-02-12"
|
||||
BetaContextManagement = "context-management-2025-06-27"
|
||||
BetaExtendedCacheTTL = "extended-cache-ttl-2025-04-11"
|
||||
)
|
||||
|
||||
// DroppedBetas 是转发时需要从 anthropic-beta header 中移除的 beta token 列表。
|
||||
@@ -44,11 +57,43 @@ const APIKeyBetaHeader = BetaClaudeCode + "," + BetaInterleavedThinking + "," +
|
||||
// APIKeyHaikuBetaHeader Haiku 模型在 API-key 账号下使用的 anthropic-beta header(不包含 oauth / claude-code)
|
||||
const APIKeyHaikuBetaHeader = BetaInterleavedThinking
|
||||
|
||||
// DefaultCacheControlTTL 是网关代理为自己生成的 cache_control 块默认使用的 ttl。
|
||||
// 真实 Claude Code CLI 当前使用 "1h",但本仓策略是"客户端透传 ttl 优先;
|
||||
// 客户端缺省时统一使用 5m",这样既不浪费 1h 缓存额度,也保留客户端自定义能力。
|
||||
const DefaultCacheControlTTL = "5m"
|
||||
|
||||
// CLICurrentVersion 是 sub2api 当前对外伪装的 Claude Code CLI 版本号(三段 semver)。
|
||||
// 用于 billing attribution block 中的 cc_version=X.Y.Z.{fp} 前缀以及 fingerprint 计算。
|
||||
// 必须与 DefaultHeaders["User-Agent"] 中的版本号严格一致;不一致会被 Anthropic 判第三方。
|
||||
const CLICurrentVersion = "2.1.92"
|
||||
|
||||
// FullClaudeCodeMimicryBetas 返回最"像"真实 Claude Code CLI 的完整 beta 列表,
|
||||
// 用于 OAuth 账号伪装成 Claude Code 时使用。
|
||||
// 顺序与真实 CLI 抓包一致。
|
||||
//
|
||||
// 使用建议:
|
||||
// - OAuth 账号 + 非 haiku:追加这整份列表,再按需保留 client 带来的 beta。
|
||||
// - OAuth 账号 + haiku:Anthropic 对 haiku 不做 third-party 判定,使用 HaikuBetaHeader 即可。
|
||||
// - API-key 账号:不要使用本函数,参见 APIKeyBetaHeader。
|
||||
func FullClaudeCodeMimicryBetas() []string {
|
||||
return []string{
|
||||
BetaClaudeCode,
|
||||
BetaOAuth,
|
||||
BetaInterleavedThinking,
|
||||
BetaPromptCachingScope,
|
||||
BetaEffort,
|
||||
BetaRedactThinking,
|
||||
BetaContextManagement,
|
||||
BetaExtendedCacheTTL,
|
||||
}
|
||||
}
|
||||
|
||||
// DefaultHeaders 是 Claude Code 客户端默认请求头。
|
||||
var DefaultHeaders = map[string]string{
|
||||
// Keep these in sync with recent Claude CLI traffic to reduce the chance
|
||||
// that Claude Code-scoped OAuth credentials are rejected as "non-CLI" usage.
|
||||
"User-Agent": "claude-cli/2.1.22 (external, cli)",
|
||||
// 版本参考:对齐 Parrot (src/transform/cc_mimicry.py:49) 的 CLI_USER_AGENT。
|
||||
"User-Agent": "claude-cli/2.1.92 (external, cli)",
|
||||
"X-Stainless-Lang": "js",
|
||||
"X-Stainless-Package-Version": "0.70.0",
|
||||
"X-Stainless-OS": "Linux",
|
||||
|
||||
@@ -762,8 +762,14 @@ func TestGatewayService_AnthropicOAuth_ForwardPreservesBillingHeaderSystemBlock(
|
||||
system := gjson.GetBytes(upstream.lastBody, "system")
|
||||
require.True(t, system.Exists())
|
||||
require.True(t, system.IsArray(), "system should be an array")
|
||||
require.Equal(t, claudeCodeSystemPrompt, system.Array()[0].Get("text").String())
|
||||
require.Equal(t, "ephemeral", system.Array()[0].Get("cache_control.type").String())
|
||||
arr := system.Array()
|
||||
require.Len(t, arr, 2, "system array should have billing block + cc prompt block")
|
||||
|
||||
require.Contains(t, arr[0].Get("text").String(), "x-anthropic-billing-header:")
|
||||
require.Contains(t, arr[0].Get("text").String(), "cc_version=")
|
||||
|
||||
require.Equal(t, claudeCodeSystemPrompt, arr[1].Get("text").String())
|
||||
require.Equal(t, "ephemeral", arr[1].Get("cache_control.type").String())
|
||||
|
||||
// 原始 system prompt 应迁移至 messages 中
|
||||
messages := gjson.GetBytes(upstream.lastBody, "messages")
|
||||
|
||||
98
backend/internal/service/gateway_billing_block.go
Normal file
98
backend/internal/service/gateway_billing_block.go
Normal file
@@ -0,0 +1,98 @@
|
||||
package service
|
||||
|
||||
import (
|
||||
"crypto/sha256"
|
||||
"encoding/hex"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
|
||||
"github.com/tidwall/gjson"
|
||||
)
|
||||
|
||||
// fingerprintSalt 是计算 cc_version 后缀指纹的盐值。
|
||||
//
|
||||
// 来源:与 Parrot src/transform/cc_mimicry.py 的 FINGERPRINT_SALT 完全一致;
|
||||
// 这是真实 Claude Code CLI 抓包推导出的常量,改动会导致 fp 与 CLI 不一致,
|
||||
// 进一步触发 Anthropic 的第三方检测。
|
||||
const fingerprintSalt = "59cf53e54c78"
|
||||
|
||||
// computeClaudeCodeFingerprint 复刻真实 Claude Code CLI 的 cc_version 指纹算法:
|
||||
//
|
||||
// 1. 取 messages 中第一条 role=user 的纯文本(首块 text)
|
||||
// 2. 取该文本的第 4、7、20 字符(不足以 '0' 补齐)
|
||||
// 3. SHA256(SALT + chars + cc_version) 取 hex 前 3 字符
|
||||
//
|
||||
// 算法来自 Parrot src/transform/cc_mimicry.py:compute_fingerprint,与官方 CLI 字节对齐。
|
||||
// 任何偏差都会导致 cc_version=X.Y.Z.{fp} 在上游侧与真实 CLI 不一致。
|
||||
func computeClaudeCodeFingerprint(body []byte, version string) string {
|
||||
firstText := extractFirstUserText(body)
|
||||
indices := []int{4, 7, 20}
|
||||
chars := make([]byte, 0, 3)
|
||||
for _, i := range indices {
|
||||
if i < len(firstText) {
|
||||
chars = append(chars, firstText[i])
|
||||
} else {
|
||||
chars = append(chars, '0')
|
||||
}
|
||||
}
|
||||
sum := sha256.Sum256([]byte(fingerprintSalt + string(chars) + version))
|
||||
return hex.EncodeToString(sum[:])[:3]
|
||||
}
|
||||
|
||||
// extractFirstUserText 提取 messages 中第一条 user 消息的首段 text 内容。
|
||||
// 兼容 string 和 []block 两种 content 格式。
|
||||
func extractFirstUserText(body []byte) string {
|
||||
messages := gjson.GetBytes(body, "messages")
|
||||
if !messages.IsArray() {
|
||||
return ""
|
||||
}
|
||||
first := ""
|
||||
messages.ForEach(func(_, msg gjson.Result) bool {
|
||||
if msg.Get("role").String() != "user" {
|
||||
return true
|
||||
}
|
||||
content := msg.Get("content")
|
||||
if content.Type == gjson.String {
|
||||
first = content.String()
|
||||
return false
|
||||
}
|
||||
if content.IsArray() {
|
||||
content.ForEach(func(_, block gjson.Result) bool {
|
||||
if block.Get("type").String() == "text" {
|
||||
first = block.Get("text").String()
|
||||
return false
|
||||
}
|
||||
return true
|
||||
})
|
||||
return false
|
||||
}
|
||||
return false
|
||||
})
|
||||
return first
|
||||
}
|
||||
|
||||
// buildBillingAttributionBlockJSON 构造 system 数组的 billing attribution block。
|
||||
//
|
||||
// 形态严格对齐真实 Claude Code CLI:
|
||||
//
|
||||
// {"type":"text","text":"x-anthropic-billing-header: cc_version=2.1.92.{fp}; cc_entrypoint=cli; cch=00000;"}
|
||||
//
|
||||
// cch=00000 是签名占位符,由 signBillingHeaderCCH 在 buildUpstreamRequest 阶段
|
||||
// 替换为基于完整 body 的 xxhash64 5 位十六进制摘要。
|
||||
//
|
||||
// 此 block 不带 cache_control(与真实 CLI 一致;cache breakpoint 由后续的
|
||||
// Claude Code prompt block 承担)。
|
||||
func buildBillingAttributionBlockJSON(body []byte, cliVersion string) ([]byte, error) {
|
||||
if cliVersion == "" {
|
||||
return nil, fmt.Errorf("cliVersion required")
|
||||
}
|
||||
fp := computeClaudeCodeFingerprint(body, cliVersion)
|
||||
text := fmt.Sprintf(
|
||||
"x-anthropic-billing-header: cc_version=%s.%s; cc_entrypoint=cli; cch=00000;",
|
||||
cliVersion, fp,
|
||||
)
|
||||
return json.Marshal(map[string]string{
|
||||
"type": "text",
|
||||
"text": text,
|
||||
})
|
||||
}
|
||||
@@ -41,12 +41,13 @@ func TestNormalizeClaudeOAuthRequestBody_PreservesTopLevelFieldOrder(t *testing.
|
||||
resultStr := string(result)
|
||||
|
||||
require.Equal(t, claude.NormalizeModelID("claude-3-5-sonnet-latest"), modelID)
|
||||
assertJSONTokenOrder(t, resultStr, `"alpha"`, `"model"`, `"system"`, `"messages"`, `"omega"`, `"tools"`, `"metadata"`)
|
||||
require.NotContains(t, resultStr, `"temperature"`)
|
||||
assertJSONTokenOrder(t, resultStr, `"alpha"`, `"model"`, `"temperature"`, `"system"`, `"messages"`, `"omega"`, `"tools"`, `"metadata"`, `"max_tokens"`)
|
||||
require.Contains(t, resultStr, `"temperature":0.2`)
|
||||
require.NotContains(t, resultStr, `"tool_choice"`)
|
||||
require.Contains(t, resultStr, `"system":"`+claudeCodeSystemPrompt+`"`)
|
||||
require.Contains(t, resultStr, `"tools":[]`)
|
||||
require.Contains(t, resultStr, `"metadata":{"user_id":"user-1"}`)
|
||||
require.Contains(t, resultStr, `"max_tokens":128000`)
|
||||
}
|
||||
|
||||
func TestInjectClaudeCodePrompt_PreservesFieldOrder(t *testing.T) {
|
||||
|
||||
@@ -85,15 +85,16 @@ func (s *GatewayService) ForwardAsChatCompletions(
|
||||
return nil, fmt.Errorf("marshal anthropic request: %w", err)
|
||||
}
|
||||
|
||||
// 6. Apply Claude Code mimicry for OAuth accounts
|
||||
isClaudeCode := false // CC API is never Claude Code
|
||||
// 6. Apply Claude Code mimicry for OAuth accounts.
|
||||
// Chat Completions 协议进来的请求永远不是 Claude Code 客户端,所以对 OAuth 账号
|
||||
// 必须完整执行 /v1/messages 主路径上的伪装链路(system 重写 + normalize + metadata 注入),
|
||||
// 否则会被 Anthropic 判为第三方应用并扣 extra usage。
|
||||
// 见 applyClaudeCodeOAuthMimicryToBody 的 godoc。
|
||||
isClaudeCode := false
|
||||
shouldMimicClaudeCode := account.IsOAuth() && !isClaudeCode
|
||||
|
||||
if shouldMimicClaudeCode {
|
||||
if !strings.Contains(strings.ToLower(mappedModel), "haiku") &&
|
||||
!systemIncludesClaudeCodePrompt(anthropicReq.System) {
|
||||
anthropicBody = injectClaudeCodePrompt(anthropicBody, anthropicReq.System)
|
||||
}
|
||||
anthropicBody = s.applyClaudeCodeOAuthMimicryToBody(ctx, c, account, anthropicBody, anthropicReq.System, mappedModel)
|
||||
}
|
||||
|
||||
// 7. Enforce cache_control block limit
|
||||
@@ -312,7 +313,14 @@ func (s *GatewayService) handleCCBufferedFromAnthropic(
|
||||
if s.responseHeaderFilter != nil {
|
||||
responseheaders.WriteFilteredHeaders(c.Writer.Header(), resp.Header, s.responseHeaderFilter)
|
||||
}
|
||||
c.JSON(http.StatusOK, ccResp)
|
||||
// Marshal then bytes-replace so tool name mapping is reversed at byte level
|
||||
// (parity with Parrot non-stream flow that marshals → restore → emit).
|
||||
if respBytes, err := json.Marshal(ccResp); err == nil {
|
||||
respBytes = reverseToolNamesIfPresent(c, respBytes)
|
||||
c.Data(http.StatusOK, "application/json; charset=utf-8", respBytes)
|
||||
} else {
|
||||
c.JSON(http.StatusOK, ccResp)
|
||||
}
|
||||
|
||||
return &ForwardResult{
|
||||
RequestID: requestID,
|
||||
@@ -383,7 +391,10 @@ func (s *GatewayService) handleCCStreamingFromAnthropic(
|
||||
if err != nil {
|
||||
return false
|
||||
}
|
||||
if _, err := fmt.Fprint(c.Writer, sse); err != nil {
|
||||
// Reverse tool name mapping: fake → real, per-chunk bytes.Replace.
|
||||
// c 可能持有请求侧注入的 ToolNameRewrite;无则仅做静态前缀还原。
|
||||
out := string(reverseToolNamesIfPresent(c, []byte(sse)))
|
||||
if _, err := fmt.Fprint(c.Writer, out); err != nil {
|
||||
return true // client disconnected
|
||||
}
|
||||
return false
|
||||
|
||||
@@ -82,15 +82,16 @@ func (s *GatewayService) ForwardAsResponses(
|
||||
return nil, fmt.Errorf("marshal anthropic request: %w", err)
|
||||
}
|
||||
|
||||
// 6. Apply Claude Code mimicry for OAuth accounts (non-Claude-Code endpoints)
|
||||
isClaudeCode := false // Responses API is never Claude Code
|
||||
// 6. Apply Claude Code mimicry for OAuth accounts (non-Claude-Code endpoints).
|
||||
// OpenAI Responses 协议进来的请求永远不是 Claude Code 客户端,所以对 OAuth 账号
|
||||
// 必须完整执行 /v1/messages 主路径上的伪装链路(system 重写 + normalize + metadata 注入),
|
||||
// 否则会被 Anthropic 判为第三方应用并扣 extra usage。
|
||||
// 见 applyClaudeCodeOAuthMimicryToBody 的 godoc。
|
||||
isClaudeCode := false
|
||||
shouldMimicClaudeCode := account.IsOAuth() && !isClaudeCode
|
||||
|
||||
if shouldMimicClaudeCode {
|
||||
if !strings.Contains(strings.ToLower(mappedModel), "haiku") &&
|
||||
!systemIncludesClaudeCodePrompt(anthropicReq.System) {
|
||||
anthropicBody = injectClaudeCodePrompt(anthropicBody, anthropicReq.System)
|
||||
}
|
||||
anthropicBody = s.applyClaudeCodeOAuthMimicryToBody(ctx, c, account, anthropicBody, anthropicReq.System, mappedModel)
|
||||
}
|
||||
|
||||
// 7. Enforce cache_control block limit
|
||||
@@ -331,7 +332,12 @@ func (s *GatewayService) handleResponsesBufferedStreamingResponse(
|
||||
if s.responseHeaderFilter != nil {
|
||||
responseheaders.WriteFilteredHeaders(c.Writer.Header(), resp.Header, s.responseHeaderFilter)
|
||||
}
|
||||
c.JSON(http.StatusOK, responsesResp)
|
||||
if respBytes, err := json.Marshal(responsesResp); err == nil {
|
||||
respBytes = reverseToolNamesIfPresent(c, respBytes)
|
||||
c.Data(http.StatusOK, "application/json; charset=utf-8", respBytes)
|
||||
} else {
|
||||
c.JSON(http.StatusOK, responsesResp)
|
||||
}
|
||||
|
||||
return &ForwardResult{
|
||||
RequestID: requestID,
|
||||
@@ -419,7 +425,8 @@ func (s *GatewayService) handleResponsesStreamingResponse(
|
||||
)
|
||||
continue
|
||||
}
|
||||
if _, err := fmt.Fprint(c.Writer, sse); err != nil {
|
||||
out := string(reverseToolNamesIfPresent(c, []byte(sse)))
|
||||
if _, err := fmt.Fprint(c.Writer, out); err != nil {
|
||||
logger.L().Info("forward_as_responses stream: client disconnected",
|
||||
zap.String("request_id", requestID),
|
||||
)
|
||||
@@ -439,7 +446,8 @@ func (s *GatewayService) handleResponsesStreamingResponse(
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
fmt.Fprint(c.Writer, sse) //nolint:errcheck
|
||||
out := string(reverseToolNamesIfPresent(c, []byte(sse)))
|
||||
fmt.Fprint(c.Writer, out) //nolint:errcheck
|
||||
}
|
||||
c.Writer.Flush()
|
||||
}
|
||||
|
||||
141
backend/internal/service/gateway_messages_cache.go
Normal file
141
backend/internal/service/gateway_messages_cache.go
Normal file
@@ -0,0 +1,141 @@
|
||||
package service
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
|
||||
"github.com/Wei-Shaw/sub2api/internal/pkg/claude"
|
||||
"github.com/tidwall/gjson"
|
||||
"github.com/tidwall/sjson"
|
||||
)
|
||||
|
||||
// stripMessageCacheControl 移除 $.messages[*].content[*].cache_control。
|
||||
// 与 Parrot _strip_message_cache_control 语义一致。
|
||||
//
|
||||
// 为什么必须整体清空:客户端(特别是 Claude Code)经常把 cache_control 打在
|
||||
// "当前最后一条 user message" 上;下一轮对话 messages 追加后,原本的最后一条
|
||||
// 变成中间某条,cache_control 还挂着就导致"前缀签名变化",破坏缓存命中。
|
||||
// 统一由代理重新打断点(addMessageCacheBreakpoints)才能在多轮间稳定。
|
||||
func stripMessageCacheControl(body []byte) []byte {
|
||||
messages := gjson.GetBytes(body, "messages")
|
||||
if !messages.IsArray() {
|
||||
return body
|
||||
}
|
||||
msgIdx := -1
|
||||
messages.ForEach(func(_, msg gjson.Result) bool {
|
||||
msgIdx++
|
||||
content := msg.Get("content")
|
||||
if !content.IsArray() {
|
||||
return true
|
||||
}
|
||||
blockIdx := -1
|
||||
content.ForEach(func(_, block gjson.Result) bool {
|
||||
blockIdx++
|
||||
if !block.Get("cache_control").Exists() {
|
||||
return true
|
||||
}
|
||||
path := fmt.Sprintf("messages.%d.content.%d.cache_control", msgIdx, blockIdx)
|
||||
if next, err := sjson.DeleteBytes(body, path); err == nil {
|
||||
body = next
|
||||
}
|
||||
return true
|
||||
})
|
||||
return true
|
||||
})
|
||||
return body
|
||||
}
|
||||
|
||||
// addMessageCacheBreakpoints 在 messages 上注入两个稳定的 cache 断点:
|
||||
// 1. 最后一条 message
|
||||
// 2. 当 messages 数量 ≥ 4 时,倒数第二个 role=user 的 message
|
||||
//
|
||||
// 与 Parrot add_cache_breakpoints 一致。两个断点 + system prompt block 的断点
|
||||
// + tools[-1] 的断点共同构成最多 4 个断点(Anthropic 上限)。
|
||||
//
|
||||
// cache_control ttl 策略:
|
||||
// - 若目标 block 已有 cache_control.ttl → 不覆盖
|
||||
// - 否则写入 {"type":"ephemeral","ttl": claude.DefaultCacheControlTTL}
|
||||
//
|
||||
// 调用前应先 stripMessageCacheControl 以保证幂等和稳定。
|
||||
func addMessageCacheBreakpoints(body []byte) []byte {
|
||||
messages := gjson.GetBytes(body, "messages")
|
||||
if !messages.IsArray() {
|
||||
return body
|
||||
}
|
||||
arr := messages.Array()
|
||||
if len(arr) == 0 {
|
||||
return body
|
||||
}
|
||||
|
||||
body = injectCacheControlOnLastContentBlock(body, len(arr)-1, &arr[len(arr)-1])
|
||||
|
||||
if len(arr) >= 4 {
|
||||
userCount := 0
|
||||
for i := len(arr) - 1; i >= 0; i-- {
|
||||
if arr[i].Get("role").String() != "user" {
|
||||
continue
|
||||
}
|
||||
userCount++
|
||||
if userCount == 2 {
|
||||
body = injectCacheControlOnLastContentBlock(body, i, &arr[i])
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return body
|
||||
}
|
||||
|
||||
// injectCacheControlOnLastContentBlock 把 cache_control 断点打在 messages[idx]
|
||||
// 的最后一个 content block 上。若 content 是 string,先升级成单块 text 数组
|
||||
// (对齐 Parrot _inject_cache_on_msg 的行为)。
|
||||
//
|
||||
// msg 是调用方已持有的 gjson.Result 快照,用于省一次 GetBytes。
|
||||
func injectCacheControlOnLastContentBlock(body []byte, idx int, msg *gjson.Result) []byte {
|
||||
content := msg.Get("content")
|
||||
|
||||
if content.Type == gjson.String {
|
||||
text := content.String()
|
||||
blockRaw := fmt.Sprintf(
|
||||
`[{"type":"text","text":%s,"cache_control":{"type":"ephemeral","ttl":%q}}]`,
|
||||
mustJSONString(text), claude.DefaultCacheControlTTL,
|
||||
)
|
||||
if next, err := sjson.SetRawBytes(body, fmt.Sprintf("messages.%d.content", idx), []byte(blockRaw)); err == nil {
|
||||
body = next
|
||||
}
|
||||
return body
|
||||
}
|
||||
|
||||
if !content.IsArray() {
|
||||
return body
|
||||
}
|
||||
contentArr := content.Array()
|
||||
if len(contentArr) == 0 {
|
||||
return body
|
||||
}
|
||||
lastBlockIdx := len(contentArr) - 1
|
||||
lastBlock := contentArr[lastBlockIdx]
|
||||
|
||||
if cc := lastBlock.Get("cache_control"); cc.Exists() && cc.Get("ttl").String() != "" {
|
||||
return body
|
||||
}
|
||||
|
||||
pathPrefix := fmt.Sprintf("messages.%d.content.%d.cache_control", idx, lastBlockIdx)
|
||||
existingCC := lastBlock.Get("cache_control")
|
||||
if existingCC.Exists() {
|
||||
if next, err := sjson.SetBytes(body, pathPrefix+".ttl", claude.DefaultCacheControlTTL); err == nil {
|
||||
body = next
|
||||
}
|
||||
return body
|
||||
}
|
||||
raw := fmt.Sprintf(`{"type":"ephemeral","ttl":%q}`, claude.DefaultCacheControlTTL)
|
||||
if next, err := sjson.SetRawBytes(body, pathPrefix, []byte(raw)); err == nil {
|
||||
body = next
|
||||
}
|
||||
return body
|
||||
}
|
||||
|
||||
// mustJSONString 把一个 Go string 序列化为合法 JSON string(含引号),
|
||||
// 用于 sjson.SetRawBytes 场景下手工拼 JSON。
|
||||
func mustJSONString(s string) string {
|
||||
return fmt.Sprintf("%q", s)
|
||||
}
|
||||
@@ -378,16 +378,27 @@ func TestRewriteSystemForNonClaudeCode(t *testing.T) {
|
||||
err := json.Unmarshal(result, &parsed)
|
||||
require.NoError(t, err)
|
||||
|
||||
// system 应为 array 格式: [{type: "text", text: "...", cache_control: {type: "ephemeral"}}]
|
||||
// system 应为 array 格式,对齐真实 Claude Code CLI 的 2-block 形态:
|
||||
// [0] billing attribution block (x-anthropic-billing-header: cc_version=...;)
|
||||
// [1] Claude Code prompt block (带 cache_control)
|
||||
systemArr, ok := parsed["system"].([]any)
|
||||
require.True(t, ok, "system should be an array, got %T", parsed["system"])
|
||||
require.Len(t, systemArr, 1, "system array should have exactly 1 block")
|
||||
systemBlock, ok := systemArr[0].(map[string]any)
|
||||
require.Len(t, systemArr, 2, "system array should have exactly 2 blocks (billing + cc prompt)")
|
||||
|
||||
billingBlock, ok := systemArr[0].(map[string]any)
|
||||
require.True(t, ok)
|
||||
require.Equal(t, "text", billingBlock["type"])
|
||||
require.Contains(t, billingBlock["text"], "x-anthropic-billing-header:")
|
||||
require.Contains(t, billingBlock["text"], "cc_version=")
|
||||
require.Contains(t, billingBlock["text"], "cc_entrypoint=cli")
|
||||
require.Contains(t, billingBlock["text"], "cch=00000")
|
||||
|
||||
systemBlock, ok := systemArr[1].(map[string]any)
|
||||
require.True(t, ok)
|
||||
require.Equal(t, "text", systemBlock["type"])
|
||||
require.Equal(t, tt.wantSystemText, systemBlock["text"])
|
||||
cc, ok := systemBlock["cache_control"].(map[string]any)
|
||||
require.True(t, ok, "system block should have cache_control")
|
||||
require.True(t, ok, "cc prompt block should have cache_control")
|
||||
require.Equal(t, "ephemeral", cc["type"])
|
||||
|
||||
// 检查 messages
|
||||
|
||||
@@ -850,6 +850,7 @@ func (s *GatewayService) hashContent(content string) string {
|
||||
|
||||
type anthropicCacheControlPayload struct {
|
||||
Type string `json:"type"`
|
||||
TTL string `json:"ttl,omitempty"`
|
||||
}
|
||||
|
||||
type anthropicSystemTextBlockPayload struct {
|
||||
@@ -898,7 +899,10 @@ func marshalAnthropicSystemTextBlock(text string, includeCacheControl bool) ([]b
|
||||
Text: text,
|
||||
}
|
||||
if includeCacheControl {
|
||||
block.CacheControl = &anthropicCacheControlPayload{Type: "ephemeral"}
|
||||
block.CacheControl = &anthropicCacheControlPayload{
|
||||
Type: "ephemeral",
|
||||
TTL: claude.DefaultCacheControlTTL,
|
||||
}
|
||||
}
|
||||
return json.Marshal(block)
|
||||
}
|
||||
@@ -1074,19 +1078,52 @@ func normalizeClaudeOAuthRequestBody(body []byte, modelID string, opts claudeOAu
|
||||
}
|
||||
}
|
||||
|
||||
if gjson.GetBytes(out, "temperature").Exists() {
|
||||
if next, ok := deleteJSONPathBytes(out, "temperature"); ok {
|
||||
// temperature:真实 Claude Code CLI 总是发送 temperature(默认 1,客户端可覆盖)。
|
||||
// 之前的实现直接 delete 会导致 payload 缺字段,与真实 CLI 字节级不一致。
|
||||
// 策略:客户端传了什么就透传;没传则补默认 1。
|
||||
if !gjson.GetBytes(out, "temperature").Exists() {
|
||||
if next, ok := setJSONValueBytes(out, "temperature", 1); ok {
|
||||
out = next
|
||||
modified = true
|
||||
}
|
||||
}
|
||||
if gjson.GetBytes(out, "tool_choice").Exists() {
|
||||
if next, ok := deleteJSONPathBytes(out, "tool_choice"); ok {
|
||||
|
||||
// max_tokens:真实 CLI 的默认值是 128000。缺失时补齐以对齐指纹。
|
||||
if !gjson.GetBytes(out, "max_tokens").Exists() {
|
||||
if next, ok := setJSONValueBytes(out, "max_tokens", 128000); ok {
|
||||
out = next
|
||||
modified = true
|
||||
}
|
||||
}
|
||||
|
||||
// context_management:thinking.type 为 enabled/adaptive 时,真实 CLI 会自动
|
||||
// 附带 {"edits":[{"type":"clear_thinking_20251015","keep":"all"}]}。
|
||||
// 客户端显式传了就透传;否则按 CLI 行为补齐。
|
||||
if !gjson.GetBytes(out, "context_management").Exists() {
|
||||
thinkingType := gjson.GetBytes(out, "thinking.type").String()
|
||||
if thinkingType == "enabled" || thinkingType == "adaptive" {
|
||||
const cmDefault = `{"edits":[{"type":"clear_thinking_20251015","keep":"all"}]}`
|
||||
if next, ok := setJSONRawBytes(out, "context_management", []byte(cmDefault)); ok {
|
||||
out = next
|
||||
modified = true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// tool_choice:与 Parrot 对齐,不再无条件删除。
|
||||
// - 客户端传了 {"type":"tool","name":"X"} → 保留结构,name 由
|
||||
// applyToolNameRewriteToBody 同步映射为假名
|
||||
// - 其他形态(auto/any/none)原样透传
|
||||
// 如果 body 里完全没有 tools(空数组),tool_choice 没意义时才删除
|
||||
if !gjson.GetBytes(out, "tools").IsArray() || len(gjson.GetBytes(out, "tools").Array()) == 0 {
|
||||
if gjson.GetBytes(out, "tool_choice").Exists() {
|
||||
if next, ok := deleteJSONPathBytes(out, "tool_choice"); ok {
|
||||
out = next
|
||||
modified = true
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if !modified {
|
||||
return body, modelID
|
||||
}
|
||||
@@ -1128,6 +1165,135 @@ func (s *GatewayService) buildOAuthMetadataUserID(parsed *ParsedRequest, account
|
||||
return FormatMetadataUserID(userID, accountUUID, sessionID, uaVersion)
|
||||
}
|
||||
|
||||
// applyClaudeCodeOAuthMimicryToBody 将"非 Claude Code 客户端 + Claude OAuth 账号"
|
||||
// 路径上原本只在 /v1/messages 里做的完整伪装应用到任意 body 上。
|
||||
//
|
||||
// 这是 /v1/messages 主路径上 rewriteSystemForNonClaudeCode +
|
||||
// normalizeClaudeOAuthRequestBody 流程的通用版,供 OpenAI 协议兼容层
|
||||
// (ForwardAsChatCompletions / ForwardAsResponses) 复用。
|
||||
//
|
||||
// 未抽离之前,OpenAI 协议兼容层仅做 injectClaudeCodePrompt(前置追加),
|
||||
// 而仓内 /v1/messages 路径自己的注释明确说过"仅前置追加无法通过 Anthropic
|
||||
// 第三方检测";那条注释就是本函数存在的根因。
|
||||
//
|
||||
// 参数:
|
||||
// - ctx / c:用于读取指纹和 gateway settings;c 可为 nil(如 count_tokens)。
|
||||
// - account:必须是 OAuth 账号,且调用方已判断不是 Claude Code 客户端。
|
||||
// - body:已经 marshal 成 Anthropic /v1/messages 格式的请求体。
|
||||
// - systemRaw:body 中原始 system 字段(用于判断是否需要 rewrite)。
|
||||
// - model:最终会发给上游的模型 ID(用于 haiku 旁路 + metadata 版本选择)。
|
||||
//
|
||||
// 返回:改写后的 body。即使中间任何一步失败,也会退化成原 body(不会 panic)。
|
||||
func (s *GatewayService) applyClaudeCodeOAuthMimicryToBody(
|
||||
ctx context.Context,
|
||||
c *gin.Context,
|
||||
account *Account,
|
||||
body []byte,
|
||||
systemRaw any,
|
||||
model string,
|
||||
) []byte {
|
||||
if account == nil || !account.IsOAuth() || len(body) == 0 {
|
||||
return body
|
||||
}
|
||||
|
||||
systemRewritten := false
|
||||
if !strings.Contains(strings.ToLower(model), "haiku") {
|
||||
body = rewriteSystemForNonClaudeCode(body, systemRaw)
|
||||
systemRewritten = true
|
||||
}
|
||||
|
||||
normalizeOpts := claudeOAuthNormalizeOptions{stripSystemCacheControl: !systemRewritten}
|
||||
|
||||
if s.identityService != nil && c != nil && c.Request != nil {
|
||||
if fp, err := s.identityService.GetOrCreateFingerprint(ctx, account.ID, c.Request.Header); err == nil && fp != nil {
|
||||
mimicMPT := false
|
||||
if s.settingService != nil {
|
||||
_, mimicMPT, _ = s.settingService.GetGatewayForwardingSettings(ctx)
|
||||
}
|
||||
if !mimicMPT {
|
||||
if uid := s.buildOAuthMetadataUserIDFromBody(ctx, account, fp, body); uid != "" {
|
||||
normalizeOpts.injectMetadata = true
|
||||
normalizeOpts.metadataUserID = uid
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
body, _ = normalizeClaudeOAuthRequestBody(body, model, normalizeOpts)
|
||||
|
||||
// Phase D+E+F: messages cache 策略 + 工具名混淆 + tools[-1] 断点
|
||||
// 对齐 Parrot transform_request 里剩余的字段级改写。三步顺序有语义约束:
|
||||
// 1) strip:先清除客户端的 messages[*].cache_control(多轮稳定性)
|
||||
// 2) breakpoints:再注入 2 个断点(最后一条 + 倒数第二个 user turn)
|
||||
// 3) tool rewrite:最后改 tools[*].name / tool_choice.name 并在 tools[-1]
|
||||
// 上打断点;mapping 存入 gin.Context 供响应侧 bytes.Replace 还原。
|
||||
body = stripMessageCacheControl(body)
|
||||
body = addMessageCacheBreakpoints(body)
|
||||
|
||||
if rw := buildToolNameRewriteFromBody(body); rw != nil {
|
||||
body = applyToolNameRewriteToBody(body, rw)
|
||||
if c != nil {
|
||||
c.Set(toolNameRewriteKey, rw)
|
||||
}
|
||||
} else {
|
||||
body = applyToolsLastCacheBreakpoint(body)
|
||||
}
|
||||
|
||||
return body
|
||||
}
|
||||
|
||||
// buildOAuthMetadataUserIDFromBody 是 buildOAuthMetadataUserID 的变体,
|
||||
// 适用于调用方手上没有 ParsedRequest 的场景(如 OpenAI 协议兼容层)。
|
||||
//
|
||||
// 与 buildOAuthMetadataUserID 的唯一区别:
|
||||
// - session hash 从 body 本体按同样规则重算,而不是读取 ParsedRequest 缓存值。
|
||||
// - 如果 body 里已经存在 metadata.user_id,则返回空(由 ensureClaudeOAuthMetadataUserID
|
||||
// 自行决定是否覆盖)。
|
||||
func (s *GatewayService) buildOAuthMetadataUserIDFromBody(
|
||||
ctx context.Context,
|
||||
account *Account,
|
||||
fp *Fingerprint,
|
||||
body []byte,
|
||||
) string {
|
||||
_ = ctx
|
||||
if account == nil {
|
||||
return ""
|
||||
}
|
||||
if existing := gjson.GetBytes(body, "metadata.user_id").String(); existing != "" {
|
||||
return ""
|
||||
}
|
||||
|
||||
userID := strings.TrimSpace(account.GetClaudeUserID())
|
||||
if userID == "" && fp != nil {
|
||||
userID = fp.ClientID
|
||||
}
|
||||
if userID == "" {
|
||||
userID = generateClientID()
|
||||
}
|
||||
|
||||
sessionID := uuid.NewString()
|
||||
if hash := hashBodyForSessionSeed(body); hash != "" {
|
||||
sessionID = generateSessionUUID(fmt.Sprintf("%d::%s", account.ID, hash))
|
||||
}
|
||||
|
||||
var uaVersion string
|
||||
if fp != nil {
|
||||
uaVersion = ExtractCLIVersion(fp.UserAgent)
|
||||
}
|
||||
accountUUID := strings.TrimSpace(account.GetExtraString("account_uuid"))
|
||||
return FormatMetadataUserID(userID, accountUUID, sessionID, uaVersion)
|
||||
}
|
||||
|
||||
// hashBodyForSessionSeed 为 sessionID 提供一个稳定但仅对本次请求特征化的种子。
|
||||
// 复用 SHA-256 + 截断,与 generateSessionUUID 的输入格式对齐。
|
||||
func hashBodyForSessionSeed(body []byte) string {
|
||||
if len(body) == 0 {
|
||||
return ""
|
||||
}
|
||||
sum := sha256.Sum256(body)
|
||||
return fmt.Sprintf("%x", sum[:16])
|
||||
}
|
||||
|
||||
// GenerateSessionUUID creates a deterministic UUID4 from a seed string.
|
||||
func GenerateSessionUUID(seed string) string {
|
||||
return generateSessionUUID(seed)
|
||||
@@ -3738,17 +3904,20 @@ func rewriteSystemForNonClaudeCode(body []byte, system any) []byte {
|
||||
originalSystemText = strings.Join(parts, "\n\n")
|
||||
}
|
||||
|
||||
// 2. 将 system 替换为 Claude Code 标准提示词(array 格式,与真实 Claude Code 一致)
|
||||
// 真实 Claude Code 始终以 [{type: "text", text: "...", cache_control: {type: "ephemeral"}}] 发送 system。
|
||||
// 使用 string 格式会被 Anthropic 检测为第三方应用。
|
||||
claudeCodeSystemBlock := []map[string]any{
|
||||
{
|
||||
"type": "text",
|
||||
"text": claudeCodeSystemPrompt,
|
||||
"cache_control": map[string]string{"type": "ephemeral"},
|
||||
},
|
||||
// 2. 构造 system 数组,对齐真实 Claude Code CLI 的 2-block 形态:
|
||||
// [0] billing attribution block(cc_version={cliVer}.{fp}; cc_entrypoint=cli; cch=00000;)
|
||||
// [1] "You are Claude Code..." prompt block(带 cache_control 作为稳定缓存断点)
|
||||
//
|
||||
// billing block 的 cch=00000 是占位符,会被 buildUpstreamRequest 里的
|
||||
// signBillingHeaderCCH 替换成 xxhash64 签名。缺失 billing block 的系统 payload
|
||||
// 是 Anthropic 判定第三方的关键信号之一(真实 CLI 每个请求都带)。
|
||||
billingBlock, billingErr := buildBillingAttributionBlockJSON(body, claude.CLICurrentVersion)
|
||||
ccPromptBlock, ccErr := marshalAnthropicSystemTextBlock(claudeCodeSystemPrompt, true)
|
||||
if billingErr != nil || ccErr != nil {
|
||||
logger.LegacyPrintf("service.gateway", "Warning: failed to build system blocks (billing=%v, cc=%v)", billingErr, ccErr)
|
||||
return body
|
||||
}
|
||||
out, ok := setJSONValueBytes(body, "system", claudeCodeSystemBlock)
|
||||
out, ok := setJSONRawBytes(body, "system", buildJSONArrayRaw([][]byte{billingBlock, ccPromptBlock}))
|
||||
if !ok {
|
||||
logger.LegacyPrintf("service.gateway", "Warning: failed to set Claude Code system prompt")
|
||||
return body
|
||||
@@ -3985,15 +4154,21 @@ func (s *GatewayService) Forward(ctx context.Context, c *gin.Context, account *A
|
||||
})
|
||||
}
|
||||
|
||||
isClaudeCode := isClaudeCodeRequest(ctx, c, parsed)
|
||||
shouldMimicClaudeCode := account.IsOAuth() && !isClaudeCode
|
||||
// OAuth 账号无条件走完整 mimicry,与 Parrot 对齐。
|
||||
// 不再检查 isClaudeCodeRequest —— 即使客户端自称 Claude Code(opencode 等
|
||||
// 第三方工具会伪装 UA / X-App / system prompt),它的伪装往往不完整(缺 billing
|
||||
// block / 工具名混淆 / cache 策略等),被 Anthropic 判为 third-party。
|
||||
// 无条件覆盖不会对真正的 Claude Code 造成问题,因为我们的伪装更完整。
|
||||
shouldMimicClaudeCode := account.IsOAuth()
|
||||
|
||||
if shouldMimicClaudeCode {
|
||||
// 非 Claude Code 客户端:将 system 替换为 Claude Code 标识,原始 system 迁移至 messages
|
||||
// 条件:1) OAuth/SetupToken 账号 2) 不是 Claude Code 客户端 3) 不是 Haiku 模型 4) system 中还没有 Claude Code 提示词
|
||||
// 与 Parrot 对齐:OAuth 账号无条件重写 system(即使客户端已发了 Claude Code
|
||||
// 风格的 system prompt)。原因:第三方工具(opencode 等)会发 "You are Claude
|
||||
// Code..." system prompt 但缺少 billing attribution block,导致 Anthropic
|
||||
// 检测到"有 CC prompt 但无 billing block"的不一致而判为 third-party。
|
||||
// Parrot 的 transform_request 从不检查客户端 system 内容,直接覆盖。
|
||||
systemRewritten := false
|
||||
if !strings.Contains(strings.ToLower(reqModel), "haiku") &&
|
||||
!systemIncludesClaudeCodePrompt(parsed.System) {
|
||||
if !strings.Contains(strings.ToLower(reqModel), "haiku") {
|
||||
body = rewriteSystemForNonClaudeCode(body, parsed.System)
|
||||
systemRewritten = true
|
||||
}
|
||||
@@ -4017,6 +4192,18 @@ func (s *GatewayService) Forward(ctx context.Context, c *gin.Context, account *A
|
||||
}
|
||||
|
||||
body, reqModel = normalizeClaudeOAuthRequestBody(body, reqModel, normalizeOpts)
|
||||
|
||||
// D/E/F: messages cache 策略 + 工具名混淆 + tools[-1] 断点
|
||||
// 与 forward_as_chat_completions / forward_as_responses 路径对齐,
|
||||
// 保证原生 /v1/messages 路径也经过完整的 Parrot 字段级改写。
|
||||
body = stripMessageCacheControl(body)
|
||||
body = addMessageCacheBreakpoints(body)
|
||||
if rw := buildToolNameRewriteFromBody(body); rw != nil {
|
||||
body = applyToolNameRewriteToBody(body, rw)
|
||||
c.Set(toolNameRewriteKey, rw)
|
||||
} else {
|
||||
body = applyToolsLastCacheBreakpoint(body)
|
||||
}
|
||||
}
|
||||
|
||||
// 强制执行 cache_control 块数量限制(最多 4 个)
|
||||
@@ -4955,7 +5142,8 @@ func (s *GatewayService) handleStreamingResponseAnthropicAPIKeyPassthrough(
|
||||
}
|
||||
|
||||
if !clientDisconnected {
|
||||
if _, err := io.WriteString(w, line); err != nil {
|
||||
restored := string(reverseToolNamesIfPresent(c, []byte(line)))
|
||||
if _, err := io.WriteString(w, restored); err != nil {
|
||||
clientDisconnected = true
|
||||
logger.LegacyPrintf("service.gateway", "[Anthropic passthrough] Client disconnected during streaming, continue draining upstream for usage: account=%d", account.ID)
|
||||
} else if _, err := io.WriteString(w, "\n"); err != nil {
|
||||
@@ -5125,6 +5313,7 @@ func (s *GatewayService) handleNonStreamingResponseAnthropicAPIKeyPassthrough(
|
||||
if contentType == "" {
|
||||
contentType = "application/json"
|
||||
}
|
||||
body = reverseToolNamesIfPresent(c, body)
|
||||
c.Data(resp.StatusCode, contentType, body)
|
||||
return usage, nil
|
||||
}
|
||||
@@ -5580,13 +5769,19 @@ func (s *GatewayService) buildUpstreamRequest(ctx context.Context, c *gin.Contex
|
||||
setHeaderRaw(req.Header, "x-api-key", token)
|
||||
}
|
||||
|
||||
// 白名单透传headers(恢复真实 wire casing)
|
||||
for key, values := range clientHeaders {
|
||||
lowerKey := strings.ToLower(key)
|
||||
if allowedHeaders[lowerKey] {
|
||||
wireKey := resolveWireCasing(key)
|
||||
for _, v := range values {
|
||||
addHeaderRaw(req.Header, wireKey, v)
|
||||
// 白名单透传 headers
|
||||
// OAuth mimicry 路径:跳过客户端 header 透传,与 Parrot 对齐。
|
||||
// Parrot 的 build_upstream_headers 只发 9 个精确 header,不透传任何客户端 header。
|
||||
// 透传客户端 header 会引入不一致的 x-stainless-* / anthropic-beta / user-agent /
|
||||
// x-claude-code-session-id 等值,和我们注入的伪装 header 冲突,被 Anthropic 判 third-party。
|
||||
if !(tokenType == "oauth" && mimicClaudeCode) {
|
||||
for key, values := range clientHeaders {
|
||||
lowerKey := strings.ToLower(key)
|
||||
if allowedHeaders[lowerKey] {
|
||||
wireKey := resolveWireCasing(key)
|
||||
for _, v := range values {
|
||||
addHeaderRaw(req.Header, wireKey, v)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -5627,7 +5822,7 @@ func (s *GatewayService) buildUpstreamRequest(ctx context.Context, c *gin.Contex
|
||||
// Haiku models are exempt from third-party detection and don't need it.
|
||||
requiredBetas := []string{claude.BetaOAuth, claude.BetaInterleavedThinking}
|
||||
if !strings.Contains(strings.ToLower(modelID), "haiku") {
|
||||
requiredBetas = []string{claude.BetaClaudeCode, claude.BetaOAuth, claude.BetaInterleavedThinking}
|
||||
requiredBetas = claude.FullClaudeCodeMimicryBetas()
|
||||
}
|
||||
setHeaderRaw(req.Header, "anthropic-beta", mergeAnthropicBetaDropping(requiredBetas, incomingBeta, effectiveDropSet))
|
||||
} else {
|
||||
@@ -6099,6 +6294,11 @@ func applyClaudeCodeMimicHeaders(req *http.Request, isStream bool) {
|
||||
if isStream {
|
||||
setHeaderRaw(req.Header, "x-stainless-helper-method", "stream")
|
||||
}
|
||||
// Real Claude CLI 每个请求都会生成一个新的 UUID 放在 x-client-request-id。
|
||||
// 上游会以此作为会话/请求指纹的一部分,缺失或重复都可能触发第三方判定。
|
||||
if getHeaderRaw(req.Header, "x-client-request-id") == "" {
|
||||
setHeaderRaw(req.Header, "x-client-request-id", uuid.NewString())
|
||||
}
|
||||
}
|
||||
|
||||
func truncateForLog(b []byte, maxBytes int) string {
|
||||
@@ -6864,7 +7064,8 @@ func (s *GatewayService) handleStreamingResponse(ctx context.Context, resp *http
|
||||
|
||||
for _, block := range outputBlocks {
|
||||
if !clientDisconnected {
|
||||
if _, werr := fmt.Fprint(w, block); werr != nil {
|
||||
restored := reverseToolNamesIfPresent(c, []byte(block))
|
||||
if _, werr := fmt.Fprint(w, string(restored)); werr != nil {
|
||||
clientDisconnected = true
|
||||
logger.LegacyPrintf("service.gateway", "Client disconnected during streaming, continuing to drain upstream for billing")
|
||||
break
|
||||
@@ -7206,6 +7407,8 @@ func (s *GatewayService) handleNonStreamingResponse(ctx context.Context, resp *h
|
||||
}
|
||||
}
|
||||
|
||||
body = reverseToolNamesIfPresent(c, body)
|
||||
|
||||
// 写入响应
|
||||
c.Data(resp.StatusCode, contentType, body)
|
||||
|
||||
@@ -8194,12 +8397,19 @@ func (s *GatewayService) ForwardCountTokens(ctx context.Context, c *gin.Context,
|
||||
// Pre-filter: strip empty text blocks to prevent upstream 400.
|
||||
body = StripEmptyTextBlocks(body)
|
||||
|
||||
isClaudeCode := isClaudeCodeRequest(ctx, c, parsed)
|
||||
shouldMimicClaudeCode := account.IsOAuth() && !isClaudeCode
|
||||
shouldMimicClaudeCode := account.IsOAuth()
|
||||
|
||||
if shouldMimicClaudeCode {
|
||||
normalizeOpts := claudeOAuthNormalizeOptions{stripSystemCacheControl: true}
|
||||
body, reqModel = normalizeClaudeOAuthRequestBody(body, reqModel, normalizeOpts)
|
||||
|
||||
body = stripMessageCacheControl(body)
|
||||
body = addMessageCacheBreakpoints(body)
|
||||
if rw := buildToolNameRewriteFromBody(body); rw != nil {
|
||||
body = applyToolNameRewriteToBody(body, rw)
|
||||
} else {
|
||||
body = applyToolsLastCacheBreakpoint(body)
|
||||
}
|
||||
}
|
||||
|
||||
// Antigravity 账户不支持 count_tokens,返回 404 让客户端 fallback 到本地估算。
|
||||
@@ -8623,7 +8833,7 @@ func (s *GatewayService) buildCountTokensRequest(ctx context.Context, c *gin.Con
|
||||
applyClaudeCodeMimicHeaders(req, false)
|
||||
|
||||
incomingBeta := getHeaderRaw(req.Header, "anthropic-beta")
|
||||
requiredBetas := []string{claude.BetaClaudeCode, claude.BetaOAuth, claude.BetaInterleavedThinking, claude.BetaTokenCounting}
|
||||
requiredBetas := append(claude.FullClaudeCodeMimicryBetas(), claude.BetaTokenCounting)
|
||||
setHeaderRaw(req.Header, "anthropic-beta", mergeAnthropicBetaDropping(requiredBetas, incomingBeta, ctEffectiveDropSet))
|
||||
} else {
|
||||
clientBetaHeader := getHeaderRaw(req.Header, "anthropic-beta")
|
||||
|
||||
313
backend/internal/service/gateway_tool_rewrite.go
Normal file
313
backend/internal/service/gateway_tool_rewrite.go
Normal file
@@ -0,0 +1,313 @@
|
||||
package service
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"hash/fnv"
|
||||
"math/rand"
|
||||
"sort"
|
||||
"strings"
|
||||
|
||||
"github.com/Wei-Shaw/sub2api/internal/pkg/claude"
|
||||
"github.com/tidwall/gjson"
|
||||
"github.com/tidwall/sjson"
|
||||
)
|
||||
|
||||
// toolNameRewriteKey 是 gin.Context 上存 ToolNameRewrite 映射的 key。
|
||||
// 请求阶段写入,响应阶段读取,用于 bytes 级逆向还原假名 → 真名。
|
||||
const toolNameRewriteKey = "claude_tool_name_rewrite"
|
||||
|
||||
// staticToolNameRewrites 是"静态前缀映射",与 Parrot src/transform/cc_mimicry.py
|
||||
// TOOL_NAME_REWRITES 完全一致。只有以这些前缀开头的工具会被重写。
|
||||
var staticToolNameRewrites = map[string]string{
|
||||
"sessions_": "cc_sess_",
|
||||
"session_": "cc_ses_",
|
||||
}
|
||||
|
||||
// fakeToolNamePrefixes 是"动态映射"的前缀池,与 Parrot _FAKE_PREFIXES 一致。
|
||||
// 当 tools 数量 > dynamicToolMapThreshold 时随机选用其中前缀生成可读假名。
|
||||
var fakeToolNamePrefixes = []string{
|
||||
"analyze_", "compute_", "fetch_", "generate_", "lookup_", "modify_",
|
||||
"process_", "query_", "render_", "resolve_", "sync_", "update_",
|
||||
"validate_", "convert_", "extract_", "manage_", "monitor_", "parse_",
|
||||
"review_", "search_", "transform_", "handle_", "invoke_", "notify_",
|
||||
}
|
||||
|
||||
// dynamicToolMapThreshold 与 Parrot 一致:tools 数量超过 5 才启用动态映射。
|
||||
// 少量工具不需要混淆(一般是 Claude Code 自己的核心工具 bash/edit/read 等)。
|
||||
const dynamicToolMapThreshold = 5
|
||||
|
||||
// ToolNameRewrite 是单次请求内的工具名混淆映射。
|
||||
// - Forward: real → fake,请求阶段在 body 上应用。
|
||||
// - Reverse: fake → real,响应阶段对每个 chunk 做 bytes.Replace 还原。
|
||||
//
|
||||
// ReverseOrdered 是按假名长度倒序的 (fake, real) 列表,用于防止短假名是长假名的
|
||||
// 子串时 bytes.Replace 先被吃掉(对齐 Parrot _restore_tool_names_in_chunk 的
|
||||
// `sorted(..., key=lambda x: len(x[1]), reverse=True)`)。
|
||||
type ToolNameRewrite struct {
|
||||
Forward map[string]string
|
||||
Reverse map[string]string
|
||||
ReverseOrdered [][2]string
|
||||
}
|
||||
|
||||
// buildDynamicToolMap 构造 tools 的动态假名映射。
|
||||
//
|
||||
// 与 Parrot _build_dynamic_tool_map 语义等价:
|
||||
// - tools 数量 ≤ dynamicToolMapThreshold 时返回 nil(不做动态映射,走静态 fallback)
|
||||
// - 同一组 tool_names 在同进程内映射稳定(保证 cache 命中)
|
||||
//
|
||||
// Parrot 用 `random.Random(hash(tuple(tool_names)))` 作 seed + shuffle 前缀池;
|
||||
// Go 无法字节级复刻 Python hash,但"稳定性"和"前缀池打散"两个不变量都保留:
|
||||
// 用 fnv64a(strings.Join(names, "\x00")) 作 seed 喂 math/rand.New。
|
||||
// 字节级不同不影响上游判定(Anthropic 不会验证我们的随机种子算法)。
|
||||
func buildDynamicToolMap(toolNames []string) map[string]string {
|
||||
if len(toolNames) <= dynamicToolMapThreshold {
|
||||
return nil
|
||||
}
|
||||
h := fnv.New64a()
|
||||
for i, n := range toolNames {
|
||||
if i > 0 {
|
||||
_, _ = h.Write([]byte{0})
|
||||
}
|
||||
_, _ = h.Write([]byte(n))
|
||||
}
|
||||
rng := rand.New(rand.NewSource(int64(h.Sum64())))
|
||||
|
||||
available := make([]string, len(fakeToolNamePrefixes))
|
||||
copy(available, fakeToolNamePrefixes)
|
||||
rng.Shuffle(len(available), func(i, j int) { available[i], available[j] = available[j], available[i] })
|
||||
|
||||
mapping := make(map[string]string, len(toolNames))
|
||||
for i, name := range toolNames {
|
||||
prefix := available[i%len(available)]
|
||||
headLen := 3
|
||||
if len(name) < 3 {
|
||||
headLen = len(name)
|
||||
}
|
||||
fake := fmt.Sprintf("%s%s%02d", prefix, name[:headLen], i)
|
||||
mapping[name] = fake
|
||||
}
|
||||
return mapping
|
||||
}
|
||||
|
||||
// sanitizeToolName 把真名转成假名。
|
||||
// 与 Parrot _sanitize_tool_name 语义一致:动态映射优先,再走静态前缀映射。
|
||||
func sanitizeToolName(name string, dynamic map[string]string) string {
|
||||
if dynamic != nil {
|
||||
if fake, ok := dynamic[name]; ok {
|
||||
return fake
|
||||
}
|
||||
}
|
||||
for prefix, replacement := range staticToolNameRewrites {
|
||||
if strings.HasPrefix(name, prefix) {
|
||||
return replacement + name[len(prefix):]
|
||||
}
|
||||
}
|
||||
return name
|
||||
}
|
||||
|
||||
// shouldMimicToolName 指示某个 tool 是否需要重命名。
|
||||
// server tool(type != "" 且不是 "function" / "custom")是 Anthropic 协议语义的一部分,
|
||||
// 比如 "web_search_20250305" / "computer_20250124";误改会导致上游拒绝。
|
||||
func shouldMimicToolName(toolType string) bool {
|
||||
if toolType == "" || toolType == "function" || toolType == "custom" {
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// buildToolNameRewriteFromBody 扫描 body 的 tools[*].name,构造 ToolNameRewrite
|
||||
// 并返回它。若不需要混淆(tools 数量不足 + 没有匹配静态前缀的工具)返回 nil。
|
||||
//
|
||||
// 注意:只扫描,不改 body。真正的 body 改写在 applyToolNameRewriteToBody。
|
||||
func buildToolNameRewriteFromBody(body []byte) *ToolNameRewrite {
|
||||
tools := gjson.GetBytes(body, "tools")
|
||||
if !tools.IsArray() {
|
||||
return nil
|
||||
}
|
||||
|
||||
mimicableNames := make([]string, 0)
|
||||
toolsArr := tools.Array()
|
||||
for _, t := range toolsArr {
|
||||
if !shouldMimicToolName(t.Get("type").String()) {
|
||||
continue
|
||||
}
|
||||
name := t.Get("name").String()
|
||||
if name == "" {
|
||||
continue
|
||||
}
|
||||
mimicableNames = append(mimicableNames, name)
|
||||
}
|
||||
|
||||
dynamic := buildDynamicToolMap(mimicableNames)
|
||||
|
||||
rw := &ToolNameRewrite{
|
||||
Forward: make(map[string]string),
|
||||
Reverse: make(map[string]string),
|
||||
}
|
||||
for _, name := range mimicableNames {
|
||||
fake := sanitizeToolName(name, dynamic)
|
||||
if fake == name {
|
||||
continue
|
||||
}
|
||||
rw.Forward[name] = fake
|
||||
rw.Reverse[fake] = name
|
||||
}
|
||||
if len(rw.Forward) == 0 {
|
||||
return nil
|
||||
}
|
||||
|
||||
rw.ReverseOrdered = make([][2]string, 0, len(rw.Reverse))
|
||||
for fake, real := range rw.Reverse {
|
||||
rw.ReverseOrdered = append(rw.ReverseOrdered, [2]string{fake, real})
|
||||
}
|
||||
sort.SliceStable(rw.ReverseOrdered, func(i, j int) bool {
|
||||
return len(rw.ReverseOrdered[i][0]) > len(rw.ReverseOrdered[j][0])
|
||||
})
|
||||
|
||||
return rw
|
||||
}
|
||||
|
||||
// applyToolNameRewriteToBody 把已构造的 ToolNameRewrite 应用到 body 上:
|
||||
// - 改写 $.tools[*].name(仅对 shouldMimicToolName 通过的 tool)
|
||||
// - 在 $.tools[last].cache_control 上打 ephemeral 缓存断点(Parrot 行为对齐,
|
||||
// ttl 客户端已有则透传,否则默认 claude.DefaultCacheControlTTL)
|
||||
// - 改写 $.tool_choice.name(仅当 $.tool_choice.type == "tool")
|
||||
//
|
||||
// 历史 $.messages[*].content[*].name(tool_use)不在请求侧改写——这与 Parrot 一致;
|
||||
// 响应侧 bytes.Replace 会连带还原它们。
|
||||
func applyToolNameRewriteToBody(body []byte, rw *ToolNameRewrite) []byte {
|
||||
if rw == nil || len(rw.Forward) == 0 {
|
||||
body = applyToolsLastCacheBreakpoint(body)
|
||||
return body
|
||||
}
|
||||
|
||||
tools := gjson.GetBytes(body, "tools")
|
||||
if tools.IsArray() {
|
||||
idx := -1
|
||||
tools.ForEach(func(_, t gjson.Result) bool {
|
||||
idx++
|
||||
if !shouldMimicToolName(t.Get("type").String()) {
|
||||
return true
|
||||
}
|
||||
name := t.Get("name").String()
|
||||
if name == "" {
|
||||
return true
|
||||
}
|
||||
fake, ok := rw.Forward[name]
|
||||
if !ok {
|
||||
return true
|
||||
}
|
||||
if next, err := sjson.SetBytes(body, fmt.Sprintf("tools.%d.name", idx), fake); err == nil {
|
||||
body = next
|
||||
}
|
||||
return true
|
||||
})
|
||||
}
|
||||
|
||||
if tc := gjson.GetBytes(body, "tool_choice"); tc.Exists() && tc.Get("type").String() == "tool" {
|
||||
name := tc.Get("name").String()
|
||||
if fake, ok := rw.Forward[name]; ok {
|
||||
if next, err := sjson.SetBytes(body, "tool_choice.name", fake); err == nil {
|
||||
body = next
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
body = applyToolsLastCacheBreakpoint(body)
|
||||
return body
|
||||
}
|
||||
|
||||
// applyToolsLastCacheBreakpoint 在 tools 数组最后一个工具上注入 cache_control
|
||||
// 断点,对齐 Parrot `tools[-1]["cache_control"] = {"type":"ephemeral","ttl":"1h"}`
|
||||
// 行为,但 ttl 按本仓规则:
|
||||
// - 客户端已为该 tool 显式设置 cache_control.ttl → 完全透传不覆盖
|
||||
// - 否则注入 {"type":"ephemeral","ttl": claude.DefaultCacheControlTTL}
|
||||
//
|
||||
// 纯副作用函数,tools 不存在或为空数组时 no-op。
|
||||
func applyToolsLastCacheBreakpoint(body []byte) []byte {
|
||||
tools := gjson.GetBytes(body, "tools")
|
||||
if !tools.IsArray() {
|
||||
return body
|
||||
}
|
||||
arr := tools.Array()
|
||||
if len(arr) == 0 {
|
||||
return body
|
||||
}
|
||||
lastIdx := len(arr) - 1
|
||||
existingCC := arr[lastIdx].Get("cache_control")
|
||||
|
||||
if existingCC.Exists() && existingCC.Get("ttl").String() != "" {
|
||||
return body
|
||||
}
|
||||
|
||||
if existingCC.Exists() {
|
||||
if next, err := sjson.SetBytes(body, fmt.Sprintf("tools.%d.cache_control.ttl", lastIdx), claude.DefaultCacheControlTTL); err == nil {
|
||||
body = next
|
||||
}
|
||||
return body
|
||||
}
|
||||
|
||||
raw := fmt.Sprintf(`{"type":"ephemeral","ttl":%q}`, claude.DefaultCacheControlTTL)
|
||||
if next, err := sjson.SetRawBytes(body, fmt.Sprintf("tools.%d.cache_control", lastIdx), []byte(raw)); err == nil {
|
||||
body = next
|
||||
}
|
||||
return body
|
||||
}
|
||||
|
||||
// restoreToolNamesInBytes 对 bytes chunk 做逆向还原:假名 → 真名。
|
||||
// 按 ReverseOrdered 的假名长度倒序逐个 bytes.Replace,防止子串冲突
|
||||
// (与 Parrot _restore_tool_names_in_chunk 的 sorted(..., reverse=True) 等价)。
|
||||
// 再做静态前缀还原(cc_sess_ → sessions_ / cc_ses_ → session_)。
|
||||
//
|
||||
// rw 可为 nil;nil 时仍会做静态前缀还原。
|
||||
func restoreToolNamesInBytes(data []byte, rw *ToolNameRewrite) []byte {
|
||||
if rw != nil {
|
||||
for _, pair := range rw.ReverseOrdered {
|
||||
fake, real := pair[0], pair[1]
|
||||
if fake == "" || fake == real {
|
||||
continue
|
||||
}
|
||||
data = replaceAllBytes(data, fake, real)
|
||||
}
|
||||
}
|
||||
for prefix, replacement := range staticToolNameRewrites {
|
||||
data = replaceAllBytes(data, replacement, prefix)
|
||||
}
|
||||
return data
|
||||
}
|
||||
|
||||
// replaceAllBytes 是 bytes.ReplaceAll 的便捷封装,避免每个调用点各自做 []byte 转换。
|
||||
func replaceAllBytes(data []byte, from, to string) []byte {
|
||||
if len(data) == 0 || from == to || !strings.Contains(string(data), from) {
|
||||
return data
|
||||
}
|
||||
return []byte(strings.ReplaceAll(string(data), from, to))
|
||||
}
|
||||
|
||||
// toolNameRewriteFromContext 从 gin.Context 取出请求阶段保存的工具名映射。
|
||||
// 找不到(c==nil 或 key 不存在或类型不对)时返回 nil;调用方必须能处理 nil。
|
||||
func toolNameRewriteFromContext(c interface {
|
||||
Get(string) (any, bool)
|
||||
}) *ToolNameRewrite {
|
||||
if c == nil {
|
||||
return nil
|
||||
}
|
||||
raw, ok := c.Get(toolNameRewriteKey)
|
||||
if !ok || raw == nil {
|
||||
return nil
|
||||
}
|
||||
rw, _ := raw.(*ToolNameRewrite)
|
||||
return rw
|
||||
}
|
||||
|
||||
// reverseToolNamesIfPresent 是响应侧 5 处注入点的统一封装:从 c 取出 mapping
|
||||
// 并对 chunk 做 bytes 级假名→真名替换。c 没有 mapping 时仍会做静态前缀还原。
|
||||
func reverseToolNamesIfPresent(c interface {
|
||||
Get(string) (any, bool)
|
||||
}, chunk []byte) []byte {
|
||||
rw := toolNameRewriteFromContext(c)
|
||||
if rw == nil && len(staticToolNameRewrites) == 0 {
|
||||
return chunk
|
||||
}
|
||||
return restoreToolNamesInBytes(chunk, rw)
|
||||
}
|
||||
185
backend/internal/service/gateway_tool_rewrite_test.go
Normal file
185
backend/internal/service/gateway_tool_rewrite_test.go
Normal file
@@ -0,0 +1,185 @@
|
||||
package service
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/require"
|
||||
"github.com/tidwall/gjson"
|
||||
)
|
||||
|
||||
func TestBuildDynamicToolMap_BelowThreshold(t *testing.T) {
|
||||
// Parrot 行为:tools 数量 ≤ 5 时不做动态映射。
|
||||
names := []string{"bash", "edit", "read", "write", "search"}
|
||||
require.Nil(t, buildDynamicToolMap(names))
|
||||
}
|
||||
|
||||
func TestBuildDynamicToolMap_AboveThresholdIsStable(t *testing.T) {
|
||||
// Parrot 不变量:同一组 tool_names 在同进程内映射稳定(保证 cache 命中)。
|
||||
names := []string{"alpha", "beta", "gamma", "delta", "epsilon", "zeta"}
|
||||
a := buildDynamicToolMap(names)
|
||||
b := buildDynamicToolMap(names)
|
||||
require.NotNil(t, a)
|
||||
require.Equal(t, a, b, "same input tool_names must yield identical mapping")
|
||||
require.Len(t, a, 6)
|
||||
for _, name := range names {
|
||||
require.Contains(t, a, name)
|
||||
require.NotEqual(t, name, a[name])
|
||||
}
|
||||
}
|
||||
|
||||
func TestSanitizeToolName_StaticPrefix(t *testing.T) {
|
||||
require.Equal(t, "cc_sess_list", sanitizeToolName("sessions_list", nil))
|
||||
require.Equal(t, "cc_ses_get", sanitizeToolName("session_get", nil))
|
||||
require.Equal(t, "bash", sanitizeToolName("bash", nil))
|
||||
}
|
||||
|
||||
func TestSanitizeToolName_DynamicTakesPrecedence(t *testing.T) {
|
||||
dyn := map[string]string{"sessions_list": "analyze_ses00"}
|
||||
got := sanitizeToolName("sessions_list", dyn)
|
||||
require.Equal(t, "analyze_ses00", got, "dynamic mapping wins over static prefix")
|
||||
}
|
||||
|
||||
func TestRestoreToolNamesInBytes_LongestFirst(t *testing.T) {
|
||||
// 当假名 "abc_12" 是另一个更长假名的子串(真实场景极少但算法必须防御)时,
|
||||
// 长的必须先替换。本测试用显式构造的映射来验证排序不变量。
|
||||
rw := &ToolNameRewrite{
|
||||
Forward: map[string]string{"foo": "abc_12", "bar": "abc_12_ext"},
|
||||
Reverse: map[string]string{"abc_12": "foo", "abc_12_ext": "bar"},
|
||||
}
|
||||
// 手工构造 ReverseOrdered:长的在前
|
||||
rw.ReverseOrdered = [][2]string{
|
||||
{"abc_12_ext", "bar"},
|
||||
{"abc_12", "foo"},
|
||||
}
|
||||
data := []byte(`{"tool":"abc_12_ext","other":"abc_12"}`)
|
||||
restored := string(restoreToolNamesInBytes(data, rw))
|
||||
require.Equal(t, `{"tool":"bar","other":"foo"}`, restored)
|
||||
}
|
||||
|
||||
func TestRestoreToolNamesInBytes_StaticPrefixRollback(t *testing.T) {
|
||||
data := []byte(`{"name":"sessions_list","id":"cc_ses_xyz"}`)
|
||||
got := string(restoreToolNamesInBytes(data, nil))
|
||||
require.Equal(t, `{"name":"sessions_list","id":"session_xyz"}`, got)
|
||||
}
|
||||
|
||||
func TestApplyToolNameRewriteToBody_RenamesToolsAndToolChoice(t *testing.T) {
|
||||
body := []byte(`{"tools":[{"name":"sessions_list","input_schema":{}},{"name":"session_get","input_schema":{}},{"name":"web_search","type":"web_search_20250305"}],"tool_choice":{"type":"tool","name":"sessions_list"}}`)
|
||||
rw := buildToolNameRewriteFromBody(body)
|
||||
require.NotNil(t, rw)
|
||||
require.Contains(t, rw.Forward, "sessions_list")
|
||||
require.Contains(t, rw.Forward, "session_get")
|
||||
// web_search is a server tool, not rewritten
|
||||
require.NotContains(t, rw.Forward, "web_search")
|
||||
|
||||
out := applyToolNameRewriteToBody(body, rw)
|
||||
|
||||
// tools[0].name and tools[1].name rewritten; tools[2].name untouched
|
||||
require.Equal(t, "cc_sess_list", gjson.GetBytes(out, "tools.0.name").String())
|
||||
require.Equal(t, "cc_ses_get", gjson.GetBytes(out, "tools.1.name").String())
|
||||
require.Equal(t, "web_search", gjson.GetBytes(out, "tools.2.name").String())
|
||||
|
||||
// tool_choice.name rewritten
|
||||
require.Equal(t, "cc_sess_list", gjson.GetBytes(out, "tool_choice.name").String())
|
||||
require.Equal(t, "tool", gjson.GetBytes(out, "tool_choice.type").String())
|
||||
}
|
||||
|
||||
func TestApplyToolsLastCacheBreakpoint_InjectsDefault(t *testing.T) {
|
||||
body := []byte(`{"tools":[{"name":"a","input_schema":{}},{"name":"b","input_schema":{}}]}`)
|
||||
out := applyToolsLastCacheBreakpoint(body)
|
||||
require.Equal(t, "ephemeral", gjson.GetBytes(out, "tools.1.cache_control.type").String())
|
||||
require.Equal(t, "5m", gjson.GetBytes(out, "tools.1.cache_control.ttl").String())
|
||||
// First tool untouched
|
||||
require.False(t, gjson.GetBytes(out, "tools.0.cache_control").Exists())
|
||||
}
|
||||
|
||||
func TestApplyToolsLastCacheBreakpoint_PassesThroughClientTTL(t *testing.T) {
|
||||
body := []byte(`{"tools":[{"name":"a","input_schema":{},"cache_control":{"type":"ephemeral","ttl":"1h"}}]}`)
|
||||
out := applyToolsLastCacheBreakpoint(body)
|
||||
// User-provided ttl must be preserved.
|
||||
require.Equal(t, "1h", gjson.GetBytes(out, "tools.0.cache_control.ttl").String())
|
||||
}
|
||||
|
||||
func TestStripMessageCacheControl(t *testing.T) {
|
||||
body := []byte(`{"messages":[{"role":"user","content":[{"type":"text","text":"hi","cache_control":{"type":"ephemeral"}}]}]}`)
|
||||
out := stripMessageCacheControl(body)
|
||||
require.False(t, gjson.GetBytes(out, "messages.0.content.0.cache_control").Exists())
|
||||
}
|
||||
|
||||
func TestAddMessageCacheBreakpoints_LastMessageOnly(t *testing.T) {
|
||||
body := []byte(`{"messages":[{"role":"user","content":[{"type":"text","text":"hello"}]}]}`)
|
||||
out := addMessageCacheBreakpoints(body)
|
||||
require.Equal(t, "ephemeral", gjson.GetBytes(out, "messages.0.content.0.cache_control.type").String())
|
||||
require.Equal(t, "5m", gjson.GetBytes(out, "messages.0.content.0.cache_control.ttl").String())
|
||||
}
|
||||
|
||||
func TestAddMessageCacheBreakpoints_SecondToLastUserTurn(t *testing.T) {
|
||||
// Parrot 不变量:messages ≥ 4 时才打第二个断点,且位置是"倒数第二个 user turn"。
|
||||
body := []byte(`{"messages":[
|
||||
{"role":"user","content":[{"type":"text","text":"q1"}]},
|
||||
{"role":"assistant","content":[{"type":"text","text":"a1"}]},
|
||||
{"role":"user","content":[{"type":"text","text":"q2"}]},
|
||||
{"role":"assistant","content":[{"type":"text","text":"a2"}]}
|
||||
]}`)
|
||||
out := addMessageCacheBreakpoints(body)
|
||||
// 最后一条 assistant 被打断点
|
||||
require.Equal(t, "ephemeral", gjson.GetBytes(out, "messages.3.content.0.cache_control.type").String())
|
||||
// 倒数第二个 user turn = index 0(唯一另一个 user)
|
||||
require.Equal(t, "ephemeral", gjson.GetBytes(out, "messages.0.content.0.cache_control.type").String())
|
||||
// 其他不打断点
|
||||
require.False(t, gjson.GetBytes(out, "messages.1.content.0.cache_control").Exists())
|
||||
require.False(t, gjson.GetBytes(out, "messages.2.content.0.cache_control").Exists())
|
||||
}
|
||||
|
||||
func TestAddMessageCacheBreakpoints_StringContentPromoted(t *testing.T) {
|
||||
body := []byte(`{"messages":[{"role":"user","content":"hi"}]}`)
|
||||
out := addMessageCacheBreakpoints(body)
|
||||
// content 升级成数组
|
||||
require.True(t, gjson.GetBytes(out, "messages.0.content").IsArray())
|
||||
require.Equal(t, "text", gjson.GetBytes(out, "messages.0.content.0.type").String())
|
||||
require.Equal(t, "hi", gjson.GetBytes(out, "messages.0.content.0.text").String())
|
||||
require.Equal(t, "5m", gjson.GetBytes(out, "messages.0.content.0.cache_control.ttl").String())
|
||||
}
|
||||
|
||||
func TestBuildToolNameRewriteFromBody_ReverseOrderedByLengthDesc(t *testing.T) {
|
||||
// 超过阈值触发动态映射,验证 ReverseOrdered 按假名长度倒序排列
|
||||
body := []byte(`{"tools":[
|
||||
{"name":"t1","input_schema":{}},
|
||||
{"name":"t2","input_schema":{}},
|
||||
{"name":"t3","input_schema":{}},
|
||||
{"name":"t4","input_schema":{}},
|
||||
{"name":"t5","input_schema":{}},
|
||||
{"name":"t6","input_schema":{}}
|
||||
]}`)
|
||||
rw := buildToolNameRewriteFromBody(body)
|
||||
require.NotNil(t, rw)
|
||||
require.NotEmpty(t, rw.ReverseOrdered)
|
||||
for i := 1; i < len(rw.ReverseOrdered); i++ {
|
||||
require.GreaterOrEqual(t, len(rw.ReverseOrdered[i-1][0]), len(rw.ReverseOrdered[i][0]),
|
||||
"ReverseOrdered must be sorted by fake-name length descending")
|
||||
}
|
||||
}
|
||||
|
||||
func TestRestoreToolNamesInBytes_NoMapping_NoStaticMatch_IsNoop(t *testing.T) {
|
||||
data := []byte("plain text without any tool names")
|
||||
require.Equal(t, string(data), string(restoreToolNamesInBytes(data, nil)))
|
||||
}
|
||||
|
||||
// Ensure the fake name format follows Parrot's "{prefix}{name[:3]}{i:02d}".
|
||||
func TestBuildDynamicToolMap_FakeNameShape(t *testing.T) {
|
||||
names := []string{"alphabet", "bravo", "charlie", "delta", "echo", "foxtrot"}
|
||||
m := buildDynamicToolMap(names)
|
||||
require.NotNil(t, m)
|
||||
for _, name := range names {
|
||||
fake, ok := m[name]
|
||||
require.True(t, ok)
|
||||
// fake = prefix + head3 + "%02d"
|
||||
// ends with two decimal digits
|
||||
require.Regexp(t, `^[a-z]+_[a-z0-9]{1,3}\d{2}$`, fake)
|
||||
head := name
|
||||
if len(head) > 3 {
|
||||
head = head[:3]
|
||||
}
|
||||
require.True(t, strings.Contains(fake, head), "fake %q should contain head3 %q of %q", fake, head, name)
|
||||
}
|
||||
}
|
||||
@@ -26,7 +26,7 @@ var (
|
||||
|
||||
// 默认指纹值(当客户端未提供时使用)
|
||||
var defaultFingerprint = Fingerprint{
|
||||
UserAgent: "claude-cli/2.1.22 (external, cli)",
|
||||
UserAgent: "claude-cli/2.1.92 (external, cli)",
|
||||
StainlessLang: "js",
|
||||
StainlessPackageVersion: "0.70.0",
|
||||
StainlessOS: "Linux",
|
||||
|
||||
Reference in New Issue
Block a user