Commit Graph

483 Commits

Author SHA1 Message Date
Luis Pater
26c298ced1 Merge branch 'main' into plus 2026-04-10 21:58:14 +08:00
Luis Pater
f32c8c9620 fix(handlers): update listener to bind on all interfaces instead of localhost
Fixed: #2640
2026-04-10 07:24:34 +08:00
Luis Pater
938af75954 Merge branch 'router-for-me:main' into main 2026-04-09 21:14:30 +08:00
sususu98
cf249586a9 feat(antigravity): configurable signature cache with bypass-mode validation
Antigravity 的 Claude thinking signature 处理新增 cache/bypass 双模式,
并为 bypass 模式实现按 SIGNATURE-CHANNEL-SPEC.md 的签名校验。

新增 antigravity-signature-cache-enabled 配置项(默认 true):
- cache mode(true):使用服务端缓存的签名,行为与原有逻辑完全一致
- bypass mode(false):直接使用客户端提供的签名,经过校验和归一化

支持配置热重载,运行时可切换模式。

校验流程:
1. 剥离历史 cache-mode 的 'modelGroup#' 前缀(如 claude#Exxxx → Exxxx)
2. 首字符必须为 'E'(单层编码)或 'R'(双层编码),否则拒绝
3. R 开头:base64 解码 → 内层必须以 'E' 开头 → 继续单层校验
4. E 开头:base64 解码 → 首字节必须为 0x12(Claude protobuf 标识)
5. 所有合法签名归一化为 R 形式(双层 base64)发往 Antigravity 后端

非法签名处理策略:
- 非严格模式(默认):translator 静默丢弃无签名的 thinking block
- 严格模式(antigravity-signature-bypass-strict: true):
  executor 层在请求发往上游前直接返回 HTTP 400

按 SIGNATURE-CHANNEL-SPEC.md 解析 Claude 签名的完整 protobuf 结构:
- Top-level Field 2(容器)→ Field 1(渠道块)
- 渠道块提取:channel_id (Field 1)、infrastructure (Field 2)、
  model_text (Field 6)、field7 (Field 7)
- 计算 routing_class、infrastructure_class、schema_features
- 使用 google.golang.org/protobuf/encoding/protowire 解析

- resolveThinkingSignature 拆分为 resolveCacheModeSignature / resolveBypassModeSignature
- hasResolvedThinkingSignature:mode-aware 签名有效性判断
  (cache: len>=50 via HasValidSignature,bypass: non-empty)
- validateAntigravityRequestSignatures:executor 预检,
  仅在 bypass + strict 模式下拦截非法签名返回 400
- 响应侧签名缓存逻辑与 cache mode 集成
- Cache mode 行为完全保留:无 '#' 前缀的原生签名静默丢弃
2026-04-09 21:12:40 +08:00
Luis Pater
1dba2d0f81 fix(handlers): add base URL validation and improve API key deletion tests 2026-04-09 20:51:54 +08:00
Luis Pater
6a43d7285c Merge branch 'main' into plus 2026-04-08 23:42:05 +08:00
hkfires
d390b95b76 fix(tests): update test cases 2026-04-08 08:53:50 +08:00
Luis Pater
5ae38584b8 Merge branch 'main' into plus 2026-04-07 18:23:31 +08:00
Luis Pater
9eabdd09db Merge pull request #2522 from aikins01/fix/strip-tool-use-signature
fix(amp): strip signature from tool_use blocks before forwarding to Claude
2026-04-06 09:30:14 +08:00
Luis Pater
c1818f197b Merge pull request #1940 from Blue-B/fix/claude-interleaved-thinking-amp-gzip-budget
fix(claude): enable interleaved-thinking beta, decode AMP error gzip, fix budget 400
2026-04-06 09:08:23 +08:00
Aikins Laryea
b0653cec7b fix(amp): strip signature from tool_use blocks before forwarding to Claude
ensureAmpSignature injects signature:"" into tool_use blocks so the
Amp TUI does not crash on P.signature.length. when Amp sends the
conversation back, Claude rejects the extra field with 400:
  tool_use.signature: Extra inputs are not permitted

strip the proxy-injected signature from tool_use blocks in
SanitizeAmpRequestBody before forwarding to the upstream API.
2026-04-05 12:26:24 +00:00
Luis Pater
7223fee2de Merge branch 'pr-488'
# Conflicts:
#	README.md
#	README_CN.md
#	README_JA.md
2026-04-05 02:08:45 +08:00
Luis Pater
ada8e2905e feat(api): enhance proxy resolution for API key-based auth
Added comprehensive support for resolving proxy URLs from configuration based on API key and provider attributes. Introduced new helper functions and extended the test suite to validate fallback mechanisms and compatibility cases.
2026-04-05 01:56:34 +08:00
kunish
59af2c57b1 fix(copilot): reduce premium request inflation and enable thinking
This commit addresses three issues with Claude Code through GitHub
Copilot:

1. **Premium request inflation**: Responses API requests were missing
   Openai-Intent headers and proper defaults, causing Copilot to bill
   each tool-loop continuation as a new premium request. Fixed by adding
   isAgentInitiated() heuristic (checks for tool_result content or
   preceding assistant tool_use), applying Responses API defaults
   (store, include, reasoning.summary), and local tiktoken-based token
   counting to avoid extra API calls.

2. **Context overflow**: Claude Code's modelSupports1M() hardcodes
   opus-4-6 as 1M-capable, but Copilot only supports ~128K-200K.
   Fixed by stripping the context-1m-2025-08-07 beta from translated
   request bodies. Also forwards response headers in non-streaming
   Execute() and registers the GET /copilot-quota management API route.

3. **Thinking not working**: Add ThinkingSupport with level-based
   reasoning to Claude models in the static definitions. Normalize
   Copilot's non-standard 'reasoning_text' response field to
   'reasoning_content' before passing to the SDK translator. Use
   caller-provided context in CountTokens instead of Background().
2026-04-03 20:24:30 +08:00
Luis Pater
75da02af55 Merge branch 'router-for-me:main' into main 2026-04-02 22:34:47 +08:00
Luis Pater
ab9ebea592 Merge PR #2474
# Conflicts:
#	internal/api/modules/amp/response_rewriter.go
#	internal/api/modules/amp/response_rewriter_test.go
2026-04-02 22:31:12 +08:00
Luis Pater
7ee37ee4b9 feat: add /healthz endpoint and test coverage for health check
Closes: #2493
2026-04-02 21:56:27 +08:00
Luis Pater
03a1bac898 Merge upstream v6.9.9 (PR #483) 2026-04-02 21:31:21 +08:00
Luis Pater
a59e92435b Merge pull request #2490 from router-for-me/logs
Refactor websocket logging and error handling
2026-04-02 20:47:31 +08:00
Luis Pater
09e480036a feat(auth): add support for managing custom headers in auth files
Closes #2457
2026-04-02 19:11:09 +08:00
hkfires
34339f61ee Refactor websocket logging and error handling
- Introduced new logging functions for websocket requests, handshakes, errors, and responses in `logging_helpers.go`.
- Updated `CodexWebsocketsExecutor` to utilize the new logging functions for improved clarity and consistency in websocket operations.
- Modified the handling of websocket upgrade rejections to log relevant metadata.
- Changed the request body key to a timeline body key in `openai_responses_websocket.go` to better reflect its purpose.
- Enhanced tests to verify the correct logging of websocket events and responses, including disconnect events and error handling scenarios.
2026-04-02 17:30:51 +08:00
Luis Pater
c744179645 Merge PR #479 2026-04-02 12:15:33 +08:00
Aikins Laryea
ff7dbb5867 test(amp): update tests to expect thinking blocks to pass through during streaming 2026-04-01 20:21:39 +00:00
Aikins Laryea
e34b2b4f1d fix(gemini): clean tool schemas and eager_input_streaming
delegate schema sanitization to util.CleanJSONSchemaForGemini and drop the top-level eager_input_streaming key to prevent validation errors when sending claude tools to the gemini api
2026-04-01 19:49:38 +00:00
CharTyr
279cbbbb8a fix(amp): don't suppress thinking blocks in streaming mode
Reverts the streaming thinking suppression introduced in b15453c.
rewriteStreamEvent should only inject signatures and rewrite model
names — suppressing thinking blocks in streaming mode breaks SSE
index alignment and causes the Amp TUI to render empty responses
on the second message onward (especially with model-mapped
non-Claude providers like GPT-5.4).

Non-streaming responses still suppress thinking when tool_use is
present via rewriteModelInResponse.
2026-03-30 20:09:32 +08:00
CharTyr
b15453c369 fix(amp): address PR review - stream thinking suppression, SSE detection, test init
- Call suppressAmpThinking in rewriteStreamEvent for streaming path
- Handle nil return from suppressAmpThinking to skip suppressed events
- Narrow looksLikeSSEChunk to line-prefix detection (HasPrefix vs Contains)
- Initialize suppressedContentBlock map in test
2026-03-30 00:42:04 -04:00
CharTyr
04ba8c8bc3 feat(amp): sanitize signatures and handle stream suppression for Amp compatibility 2026-03-29 22:23:18 -04:00
Luis Pater
b8b89f34f4 Merge pull request #442 from LuxVTZ/feat/gitlab-duo-panel-parity
Improve GitLab Duo gateway compatibility\n\nRestore internal/runtime/executor/claude_executor.go to main during merge.
2026-03-28 05:06:41 +08:00
Luis Pater
1fa094dac6 Merge pull request #461 from MrHuangJser/main
feat(cursor): Full Cursor provider with H2 streaming, MCP tools, multi-turn & multi-account
2026-03-28 05:01:27 +08:00
Luis Pater
ac26e7db43 Merge branch 'main' into plus 2026-03-28 04:51:18 +08:00
Luis Pater
10b824fcac fix(security): validate auth file names to prevent unsafe input 2026-03-28 04:48:23 +08:00
MrHuangJser
7386a70724 feat(cursor): auto-identify accounts from JWT sub for multi-account support
Previously Cursor required a manual ?label=xxx parameter to distinguish
accounts (unlike Codex which auto-generates filenames from JWT claims).

Cursor JWTs contain a "sub" claim (e.g. "auth0|user_XXXX") that uniquely
identifies each account. Now we:

- Add ParseJWTSub() + SubToShortHash() to extract and hash the sub claim
- Refactor GetTokenExpiry() to share the new decodeJWTPayload() helper
- Update CredentialFileName(label, subHash) to auto-generate filenames
  from the sub hash when no explicit label is provided
  (e.g. "cursor.8f202e67.json" instead of always "cursor.json")
- Add DisplayLabel() for human-readable account identification
- Store "sub" in metadata for observability
- Update both management API handler and SDK authenticator

Same account always produces the same filename (deterministic), different
accounts get different files. Explicit ?label= still takes priority.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-27 17:40:02 +08:00
MrHuangJser
8902e1cccb style(cursor): replace fmt.Print* with log package for consistent logging
Address Gemini Code Assist review feedback: use logrus log package
instead of fmt.Printf/Println in Cursor auth handlers and CLI for
unified log formatting and level control.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 17:03:32 +08:00
黄姜恒
de5fe71478 feat(cursor): multi-account routing with round-robin and session isolation
- Add cursor/filename.go for multi-account credential file naming
- Include auth.ID in session and checkpoint keys for per-account isolation
- Record authID in cursorSession, validate on resume to prevent cross-account access
- Management API /cursor-auth-url supports ?label= for creating named accounts
- Leverages existing conductor round-robin + failover framework

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 11:27:49 +08:00
黄姜恒
dcfbec2990 feat(cursor): add management API for Cursor OAuth authentication
- Add RequestCursorToken handler with PKCE + polling flow
- Register /v0/management/cursor-auth-url route
- Returns login URL + state for browser auth, polls in background
- Saves cursor.json with access/refresh tokens on success

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 11:10:07 +08:00
Luis Pater
0e4f669c8b Merge branch 'router-for-me:main' into main 2026-03-25 09:38:34 +08:00
hkfires
9e5693e74f feat(api): support batch auth file upload and delete 2026-03-25 09:20:17 +08:00
Luis Pater
1315f710f5 Merge branch 'main' into plus 2026-03-24 00:43:26 +08:00
Supra4E8C
5331d51f27 fix(auth): ensure absolute paths for auth file handling 2026-03-22 13:58:16 +08:00
Luis Pater
7c2ad4cda2 Merge branch 'router-for-me:main' into main 2026-03-17 00:09:43 +08:00
Luis Pater
59ad8f40dc Merge pull request #2124 from RGBadmin/feat/auth-list-priority-note
feat(api): expose priority and note in GET /auth-files response
2026-03-16 12:31:11 +08:00
Luis Pater
1b46d39b8b Merge branch 'router-for-me:main' into main 2026-03-15 23:57:47 +08:00
RGBadmin
c1241a98e2 fix(api): restrict fallback note to string-typed JSON values
Only emit note in listAuthFilesFromDisk when the JSON value is actually
a string (gjson.String), matching the synthesizer/buildAuthFileEntry
behavior. Non-string values like numbers or booleans are now ignored
instead of being coerced via gjson.String().

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 23:00:17 +08:00
RGBadmin
8d8f5970ee fix(api): fallback to Metadata for priority/note on uploaded auths
buildAuthFileEntry now falls back to reading priority/note from
auth.Metadata when Attributes lacks them. This covers auths registered
via UploadAuthFile which bypass the synthesizer and only populate
Metadata from the raw JSON.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 17:36:11 +08:00
RGBadmin
f90120f846 fix(api): propagate note to Gemini virtual auths and align priority parsing
- Read note from Attributes (consistent with priority) in buildAuthFileEntry,
  fixing missing note on Gemini multi-project virtual auth cards.
- Propagate note from primary to virtual auths in SynthesizeGeminiVirtualAuths,
  mirroring existing priority propagation.
- Sync note/priority writes to both Metadata and Attributes in PatchAuthFileFields,
  with refactored nil-check to reduce duplication (review feedback).
- Validate priority type in fallback disk-read path instead of coercing all values
  to 0 via gjson.Int(), aligning with the auth-manager code path.
- Add regression tests for note synthesis, virtual-auth note propagation, and
  end-to-end multi-project Gemini note inheritance.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 16:47:01 +08:00
Luis Pater
b5701f416b Fixed: #2102
fix(auth): ensure unique auth index for shared API keys across providers and credential identities
2026-03-15 02:48:54 +08:00
Luis Pater
c6cb24039d Merge branch 'main' into plus 2026-03-15 01:50:32 +08:00
luxvtz
5da0decef6 Improve GitLab Duo gateway compatibility 2026-03-14 03:18:43 -07:00
RGBadmin
5b6342e6ac feat(api): expose priority and note fields in GET /auth-files list response
The list endpoint previously omitted priority and note, which are stored
inside each auth file's JSON content. This adds them to both the normal
(auth-manager) and fallback (disk-read) code paths, and extends
PATCH /auth-files/fields to support writing the note field.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-14 14:47:31 +08:00
GrothKeiran
3960c93d51 refactor: derive copilot metadata from storage 2026-03-13 13:10:01 +00:00