Commit Graph
11 Commits
Author SHA1 Message Date
jy.liu 1631b19f84 fix: preserve system cache breakpoint in OAuth mimic 2026-07-27 19:28:45 +08:00
harukaandClaude Opus 4.8 6cfb7898df fix(claude-mimicry): drop the cch sign to match new Claude Code CLI
Recent Claude Code CLI versions no longer emit the cch=... signature field in
their x-anthropic-billing-header system block (issue #3358). sub2api still
injected cch=00000 when mimicking Claude Code for OAuth accounts and optionally
signed it, so mimicked requests now diverge from real CLI traffic — the opposite
of what the mimicry is for.

- buildBillingAttributionText emits the block without the cch=00000 segment;
  cc_version + cc_entrypoint=cli are kept (detection and Anthropic's first-party
  signal rely on the block, not on cch).
- Retire signing: remove the two enableCCH signBillingHeaderCCH call sites in
  buildUpstreamRequest / buildCountTokensRequest and delete the now-dead
  signBillingHeaderCCH, cchPlaceholderRe, cchSeed, xxHash64Seeded helpers.
- enable_cch_signing is now a documented no-op (kept for backward compat).
- Drop the obsolete signing tests (TestSignBillingHeaderCCH, TestXXHash64Seeded,
  TestSanitizeMustBeBeforeCCHSigning_HashConsistency) and update the prompt test
  to assert the injected block no longer carries cch=.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-19 08:01:29 -07:00
dailingfei 8ce7b9a8f6 feat: configure Claude OAuth system prompt blocks 2026-06-13 04:12:13 +08:00
eyre 219da4b9e5 feat(claude-mimicry): align Claude Code fingerprint with CLI 2.1.161
- bump impersonated CLI version 2.1.92 -> 2.1.161; derive User-Agent from
  CLICurrentVersion so the two hardcoded copies can no longer drift apart
- fix x-stainless headers to real 2.1.161 values: package-version
  0.70.0 -> 0.94.0, runtime-version v24.13.0 -> v24.3.0 (verified against
  the installed Bun-compiled binary)
- expand the disguise-path system prompt from a 2-block identity skeleton
  to a 3-block layout (billing + identity + tool-agnostic prose), matching
  real CC's multi-block shape; cache breakpoint moved to the last static
  block. Deliberately excludes # Doing tasks / # Using your tools /
  # Executing actions to avoid polluting proxied-client behavior
- stabilize the synthesized metadata.user_id session_id across conversation
  turns: derive it from (account + client discriminator + first user
  message) instead of a per-turn content/body hash. Sticky-routing
  GenerateSessionHash is intentionally left untouched; remove now-dead
  hashBodyForSessionSeed

Tests: update the 3-block system assertions in gateway_prompt_test and
gateway_anthropic_apikey_passthrough_test; add a session_id cross-turn
stability test in gateway_oauth_metadata_test.
2026-06-06 01:01:58 +08:00
shaw 496469ac4e fix(gateway): skip body mimicry for real Claude Code clients to restore prompt caching
PR #1914 unconditionally applied the full mimicry pipeline to all OAuth
accounts, including real Claude Code CLI clients. This replaced the
client's long system prompt (~10K+ tokens with stable cache_control
breakpoints) with a short ~45 token [billing, CC prompt] pair, which
falls below Anthropic's 1024-token minimum cacheable prefix threshold.
The result: every request created a new cache but never hit an existing
one.

Fix: restore the Claude Code client detection gate so that real CC
clients bypass body-level mimicry (system rewrite, message cache
management, tool name obfuscation). Non-CC third-party clients
(opencode, etc.) continue to receive full mimicry.

Also harden the detection logic:
- Make UA regex case-insensitive (align with claude_code_validator.go)
- Validate metadata.user_id format via ParseMetadataUserID() instead of
  just checking non-empty, preventing third-party tools from spoofing
  a claude-cli/* UA with an arbitrary user_id string to bypass mimicry
2026-04-25 22:50:35 +08:00
keh4l a25faecadd feat(gateway): align body shape with real Claude Code CLI defaults
Three field-level alignments in normalizeClaudeOAuthRequestBody to
match real Claude Code CLI traffic byte-for-byte:

  1. temperature: previously deleted unconditionally; now passes
     through client value, defaults to 1 when absent (real CLI
     always sends temperature, default 1).

  2. max_tokens: defaults to 128000 when absent (real CLI default).

  3. context_management: when thinking.type is enabled/adaptive
     and the client did not provide context_management, inject
     {"edits":[{"type":"clear_thinking_20251015","keep":"all"}]}
     to mirror real CLI behavior.

tool_choice removal is unchanged (Claude Code OAuth credentials
do not allow client-supplied tool_choice).

Tests updated:
  - gateway_body_order_test.go: temperature/max_tokens are now
    expected in output; tool_choice still removed.
  - gateway_prompt_test.go: system array is now 2 blocks
    (billing + cc prompt), assertions adjusted.
  - gateway_anthropic_apikey_passthrough_test.go: same 2-block
    assertion.
2026-04-24 23:16:32 +08:00
shaw 1c9a2128cf fix: 修复非CC客户端OAuth伪装被Anthropic检测为第三方应用的问题
commit f3aa54b 的 rewriteSystemForNonClaudeCode 未能通过 Anthropic 第三方检测,
根因是两个关键信号与真实 Claude Code 不一致:

1. anthropic-beta 头缺少 claude-code-20250219:伪装路径主动将该 beta
   加入 drop set 并移除,但 Anthropic 依赖此 beta 识别 Claude Code 请求。
   修复:非 haiku 模型的伪装请求强制包含 claude-code beta。

2. system 字段使用 string 格式而非 array+cache_control:真实 Claude Code
   始终以 [{type,text,cache_control:{type:"ephemeral"}}] 发送 system,
   string 格式成为第三方检测信号。
   修复:rewriteSystemForNonClaudeCode 改为注入 array 格式。

附带调整:stripSystemCacheControl 按 system 是否被重写动态决定,
重写时保留 CC prompt 的 cache_control,未重写时(haiku/已含CC前缀)
保持原有剥离行为。
2026-04-08 14:06:06 +08:00
shaw f3aa54b770 fix: 非Claude Code客户端system prompt迁移至messages以绕过第三方应用检测
Anthropic近期引入基于system参数内容的第三方应用检测机制,原有的前置追加
Claude Code提示词策略无法通过检测(后续内容仍为非Claude Code格式触发429)。

新策略:对非Claude Code客户端的OAuth/SetupToken账号请求,将system字段
完整替换为Claude Code标识提示词,原始system内容作为user/assistant消息对
注入messages开头,模型仍接收完整指令。

仅影响/v1/messages路径,chat_completions和responses路径保持原有逻辑不变。
真正的Claude Code客户端请求完全不受影响(原样透传)。
2026-04-07 17:06:47 +08:00
QTomandClaude Opus 4.6 c729ee425f fix(gateway): 修复 OpenAI→Anthropic 转换路径 system prompt 被静默丢弃的 bug
injectClaudeCodePrompt 和 systemIncludesClaudeCodePrompt 的 type switch
无法匹配 json.RawMessage 类型(Go typed nil 陷阱),导致 ForwardAsResponses
和 ForwardAsChatCompletions 路径中用户 system prompt 被替换为仅 Claude Code
banner。新增 normalizeSystemParam 将 json.RawMessage 转为标准 Go 类型。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-27 14:51:36 +08:00
cyhhao be3b788b8f fix: also prefix next system block with Claude Code banner 2026-01-29 02:03:54 +08:00
shaw a11c71cea9 fix: 修复创建账号schedulable值默认为false的bug 2026-01-04 10:45:18 +08:00