Commit Graph
143 Commits
Author SHA1 Message Date
Wesley Liddick 4726bdd08b Merge pull request #6890 from slovx2/feat/openai-images-75be
feat(openai): route OAuth image requests through native Codex Images
2026-09-11 17:29:54 +08:00
Wesley Liddick cdb5cfaf6c Merge pull request #6747 from DuskLin/feat/opencode-go-platform
feat(opencode): 增加 OpenCode 平台支持(Zen / GO)
2026-09-11 16:42:05 +08:00
song 1067e89fab fix(openai): address image route review findings 2026-09-11 16:30:32 +08:00
刘佳林 7c008bd8c1 fix(opencode): apply account model mapping in connection tests
Responses probes used the requested model as-is, so aliases like
opencode/muse-spark-* were sent upstream instead of the mapped ID.
2026-09-11 14:19:23 +08:00
刘佳林 242907854d feat(opencode): add OpenCode platform with Zen and GO account types
Keep the internal platform ID opencode_go. Product surface is OpenCode
with account_mode zen|go, model-aware routing across Chat Completions,
Responses, and Anthropic Messages, and X-OpenCode-Session derived from
prompt_cache_key / metadata.user_id so prompt cache can hit.

Unmatched models fall back to /v1/chat/completions. Related to #6742.
2026-09-11 10:05:24 +08:00
Zero Clover 6feefb7aec fix(openai): keep Codex manifest display names in account model lists 2026-09-11 03:18:00 +08:00
hansnow 7ccc8a6f50 fix(openai): 支持 Image 2.5 并修复 OAuth 生图主控模型 2026-09-09 11:04:59 +08:00
Wesley Liddick 14e0a49e17 Merge pull request #6767 from alfadb/fix/ollama-cloud-max-tokens-all-platforms
fix(ollama): 修复 DeepSeek 多协议输出上限并自动选择 Bearer 鉴权
2026-09-08 08:26:51 +08:00
Zero Clover e094a3f40b fix(accounts): populate display names for live test models 2026-09-07 21:59:35 +08:00
alfadb 57387445f3 fix(ollama): select Bearer auth for Anthropic endpoints automatically 2026-09-07 21:54:22 +08:00
Zero Clover f88d62ad28 fix(openai): use live account models in connection tests 2026-09-07 00:23:49 +08:00
Long LiandCursor 77b6c5bb0c merge: sync contrib/routed-codex-model-catalog with upstream v0.1.182
Keep catalog membership on schedulable accounts and intersect advertised
capabilities across all active group members that map an alias. Preserve
upstream plugin, service-tier, and models-list body-limit changes.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-25 21:28:57 +09:00
wucm667 99ec347eaf fix(antigravity): migrate legacy Sonnet tests to 4.6 2026-08-24 15:58:47 +08:00
shaw 40ea3aebad feat: add OAuth outbound transport plugin system 2026-08-24 09:03:37 +08:00
Long Li e39fce270d fix(codex): sync routed capabilities from upstream
Account model mappings decide availability, but generated Codex catalogs previously inferred capabilities from local model-name tables. Compatible upstreams can expose unknown models such as OpenCode x-preview-f-free, so reasoning levels, image input, and context limits were missing or wrong.

Sync capability metadata from the account model endpoint, enrich incomplete lists from the Models.dev provider matching the account base URL, and persist only complete snapshots. Mixed groups consume the safe intersection across schedulable accounts. When IDs sync without complete metadata, return an explicit warning and preserve the previous snapshot.

Third-party Responses providers often omit /models. If that endpoint returns 404 or 405 and the account already has concrete model mappings, use those configured upstream IDs for capability enrichment. Authentication, rate-limit, server, and network failures remain hard errors, and metadata is never guessed across providers by model name alone.

Advertise a single none choice for non-reasoning models so current Codex can select them, then omit that catalog placeholder when forwarding to compatible Responses upstreams while preserving official OpenAI request semantics.
2026-08-22 15:33:12 +09:00
Wesley Liddick fb56bcbd07 Merge pull request #5913 from xuhaihan/fix/deepseek-responses-account-test
fix(deepseek): route Responses account tests through OpenAI probe
2026-08-21 21:27:01 +08:00
HypoxanthineOvO a749673de3 fix(accounts): route CN provider anthropic-protocol tests to the native endpoint
CN-provider accounts explicitly configured with api_protocol=anthropic
(the frontend offers per-provider presets such as GLM Anthropic) fell
through the account-test router to the generic Claude tester, which:

- appended ?beta=true, which the native passthrough deliberately avoids
  for third-party Anthropic endpoints, and
- defaulted a missing base_url to https://api.anthropic.com — sending
  the provider's API key to Anthropic instead of the provider's own
  Anthropic-compatible endpoint (guaranteed 401 plus cross-provider
  credential exposure).

Route them to a dedicated probe that mirrors the adaptive Anthropic
check: resolve the endpoint via GetAnthropicProtocolBaseURL (same
resolution as real /v1/messages forwarding, including per-platform
defaults), use the shared API-key auth header, and mark 401/403 as the
account error state.

Also fail fast with an actionable hint when the anthropic-protocol
base_url still points at an OpenAI-compatible endpoint (paas path,
version segment, or chat/completions suffix): the naive {base}/v1/messages
join would 404 (e.g. /api/paas/v4/v1/messages) without any pointer to
the actual misconfiguration.
2026-08-21 16:37:25 +08:00
IanShaw 3243983b72 完善 Grok Realtime 与默认映射测试 2026-08-20 04:26:24 -07:00
xuhaihan 01a0083948 fix(deepseek): route responses account tests to OpenAI probe 2026-08-20 18:40:05 +08:00
xuhaihan f75c4161f2 fix(deepseek): make account test links platform-aware 2026-08-20 18:18:44 +08:00
SavitarC b3092145db fix(accounts): harden adaptive protocol compatibility 2026-08-20 13:57:25 +08:00
SavitarC 85051616f9 feat(accounts): add adaptive API protocol routing 2026-08-20 11:52:05 +08:00
UnlastingR ac6208de16 fix(accounts): route CN provider chat tests correctly 2026-08-18 08:46:28 -04:00
spongehah bb6c3b4f6a fix: unify Codex OAuth outbound identity onto the inference resolver
Token exchange, PAT whoami, models, probes, and pre-writes now follow
the same UA/version chain as Codex inference instead of hardcoded
codex-cli/0.91.0 or compile-time constants.
2026-08-18 13:03:22 +08:00
shaw 8ae6d8f67e fix(openai): send session-level beta features and probe native compaction v2
OpenAI sunset the legacy unary /responses/compact endpoint (404, #5598,
#5624), so the account "compact probe" in the admin UI kept failing even for
healthy accounts, and the beta-feature negotiation header was only attached
to compaction turns.

Beta features (codex-rs session/mod.rs build_model_client_beta_features_header
+ client.rs build_responses_headers): the header is a session-level constant
attached to every /responses request, the WS handshake and /responses/compact.
Enumerating FEATURES shows no Experimental feature is enabled by default, so a
default install sends exactly "remote_compaction_v2". Mirror that:

- OAuth requests without a client-declared header get the default shape, so we
  no longer produce a "header only on compaction turns" pattern real Codex
  never emits (#5586 chains that strip the header)
- a client-declared header is preserved as-is: non-empty without v2 means the
  user disabled the feature and the gateway must not rewrite that
- native v2 turns (compaction_trigger in body) always ensure v2 is present
- non-OAuth upstreams keep the compaction-turn-only behaviour
- the WS injection sits outside the client-header copy block so prewarm and
  turn handshakes cannot land in different pool compatibility buckets

Compact probe now exercises native v2 (streaming /responses +
compaction_trigger) instead of the dead endpoint. Success requires an actual
compaction output item — scanning output_item.done/added, the terminal
response.output[] and the whole-JSON fallback — so a 2xx that silently drops
the trigger is reported as unsupported (the "got 0 items" class, #5478,
#5648). Probe identity is now UUID-shaped and applies the account's
convergence, matching real traffic on the same endpoint.
2026-08-15 16:35:08 +08:00
IanShaw027 363cc4994b fix: SuperGrokPro 用 4.5 窗口区分 Heavy,容量抖动只封单模型
JWT 的 SuperGrokPro 同时覆盖 SuperGrok 与 Heavy,账单月额度又滞后,
账号会误升/误降。multi-agent 容量抖动还会把整号提出调度。

- CanonicalGrokPlan:明确 JWT 优先;模糊档仅采新鲜的 grok-4.5 Responses 窗口
- 配额快照写入 plan_from_45_responses 时间戳,过期信号不用
- engine_overloaded 对 multi-agent 只封当前模型 0.5s–5min
2026-08-13 07:49:14 +08:00
IanShaw027 cec922d335 fix(grok): clear golangci-lint findings on complete-integration branch
Check Close/CloseNow errors, drop unused helpers and dead constants,
lowercase ST1005 error strings, and stop discarding unwrap status as an
unused assignment so CI golangci-lint passes.
2026-08-08 12:56:40 +08:00
IanShaw027 12db0f906a fix(grok): drop account-test ZDR path and align media CLI headers
Remove optional upload_url / fake connectivity-only success from admin video
tests. Stamp Grok CLI headers only on the CLI proxy so OAuth media against
api.x.ai can complete and preview video like the gateway path.
2026-08-08 09:45:12 +08:00
IanShaw027 8399a30417 fix(grok): treat free-usage and billing exhaustion as recoverable
Classify free-usage bodies during account tests without quarantining content
policy, and mark billing/spending-limit refresh failures as transient so
accounts stay probe-eligible.
2026-08-08 08:48:38 +08:00
IanShaw027 d0767eab9d feat(grok): admin account test modes with real media preview
Add mode-first connectivity probes for text/image/video/search/tts/stt/realtime,
standalone voice and web-search paths, media upload options, and in-browser
image/audio/video preview (including ZDR-safe b64 images and edit validation).
2026-08-08 01:07:08 +08:00
shaw dbb42881c0 fix(openai): default OAuth identity to codex-tui 2026-08-07 09:56:03 +08:00
shaw c899c8cf37 fix(codex): 管理员配置的 UA 只贡献指纹,版本段一律用生效版本重建
面板「OpenAI Codex UA」此前只在客户端 UA 是浏览器型时才生效,本分支把它提升为
所有 OAuth 出站的规范身份来源,作用域扩大了一个数量级。而它的旧 placeholder 原文
就是 codex_cli_rs/0.144.1 (...):照抄填写过的存量部署会被永久钉在 0.144.1 上——
该值不低于上游门槛 0.144.0,version 头也随之变成 0.144.1,绕过版本自动同步,
稳定落在上游优先降载的那一侧,且面板、日志、审计都不提示。账号级自定义 UA
(credentials.user_agent)有完全相同的陷阱。

改为:管理员配置的 UA 只贡献客户端名与 OS / 架构 / 终端指纹(这是该输入框唯一
不可替代的价值),版本段一律用当前生效版本重建。存量的陈旧配置无需迁移即自愈,
UA 与 version 头从此由构造保证同源,原先「覆写 UA 陈旧时二者不一致」的次优解消失。

- 新增 openai.SetCodexUserAgentVersion:重建首段版本声明,OS / 架构 / 终端指纹
  原样保留;尾部官方客户端标识组 (name; version) 与首段同源,一并更新,避免拼出
  首段声明新版本、尾部仍是旧版本的自相矛盾身份;非官方括号组(如 OS 组)不动。
- resolveCodexOutboundIdentity 收敛为单一funnel:生效版本只从规范身份取,
  候选 UA 的版本段不再参与判定。
- GetOpenAICodexCanonicalUserAgent 重建面板 UA 的版本段;原「面板值等于兜底常量
  视同未填」的特例随之成为恒等变换,删除。
- 补齐 4 处静默丢弃账号级自定义 UA 的出站路径(WS 握手、账号测试 x2、用量探针):
  它们先写 customUA 再调不带 override 的收口,赋值随即被覆盖,既是行为不一致
  也是死代码;账号测试尤其要紧——注释写着「与真实转发一致」而实际不一致。
- 补测试:SetCodexUserAgentVersion / CodexUserAgentVersion 包内用例、陈旧面板 UA
  与账号 UA 的版本重建回归、WS 握手尊重账号级 UA。
2026-08-03 21:50:49 +08:00
shaw 017f6bbd5e fix(gateway): 收紧上游 URL 路径片段校验
网关有若干位置会把客户端可控的字符串拼进上游请求的 URL path(Responses
子路径、Gemini 模型名)。此前这些字符串未经校验直接参与拼接,可能改变上游
请求的路径结构,使实际发出的请求与客户端意图不一致。

- 新增 internal/service/upstream_path_guard.go:路径片段闭集允许清单
  (\w + `-` + `.`),拒绝空片段、纯点片段、超长片段与过深后缀
- /responses/*subpath 三条路由入口新增守卫,不可转发的子路径直接 404;
  service 层同时保证不产出不合规后缀,拼接函数再兜底一层
- Gemini AI Studio 原先 5 处重复的 URL 拼接收敛为唯一构造点
  buildGeminiAIStudioModelActionURL(校验模型片段 + action 白名单)
- Gemini native / GetModel handler 增加入口校验;ForwardAIStudioGET 逐片段校验
- Grok video 端点的 request_id 增加片段合规校验

合法子路径(/compact、/compact/detail、/{id}/cancel 形态)与既有模型名行为
不变,通配路由保留。
2026-07-31 16:11:45 +08:00
eyre 248236ce6d fix(gateway): 修复模拟响应使用 Bedrock msg_bdrk_ 格式,改为正宗 Anthropic msg_01 格式
问题:
探针拦截(suggestion mode / warmup / max_tokens=1 haiku)的模拟响应以及
Gemini/Antigravity 兼容层生成的 message ID 不符合 Anthropic 官方 API 格式,
容易被客户端识别为非正宗响应。

修复:
1. generateRealisticMsgID():msg_bdrk_ + 24字符 → msg_01 + 22位 Base62
   (与官方 API 返回的 msg_011CdS6b8gAhoKWdW9jE87Zs 格式一致)
2. 去掉固定的 msg_mock_suggestion / msg_mock_warmup,统一使用随机 ID
3. 流式响应格式对齐官方:
   - message_start 增加 stop_details/cache token 字段
   - content_block_start 字段顺序修正
   - message_delta.usage 只含 output_tokens
4. 非流式响应:增加 stop_details:null,移除非标准 total_tokens
5. Gemini Messages/ChatCompletions 兼容层:msg_ + hex → msg_01 + Base62
6. Antigravity response/stream transformer:msg_ + 12位 → msg_01 + 22位 Base62

验证方式:对照 Anthropic 官方 API 实际响应格式确认。
2026-07-27 15:20:03 +00:00
yan9651688 2db0cbd292 fix(grok): pause accounts after manual test payment failure
Manual Grok connection tests previously surfaced upstream HTTP 402 errors without changing account availability. Persist the same 30-minute payment-required cooldown used by the live forwarding path so refreshed account lists no longer present the account as schedulable.

Constraint: Keep manual-test HTTP 402 handling aligned with existing Grok forwarding semantics.
Rejected: Mark the account permanently error | payment state can recover and the forwarding path intentionally uses a bounded cooldown.
Confidence: high
Scope-risk: narrow
Directive: Keep the manual-test cooldown reason and duration aligned with handleGrokAccountUpstreamError.
Tested: go test -tags=unit ./internal/service -count=1; go vet -tags=unit ./internal/service; production package compile check
Not-tested: Live xAI account with an exhausted subscription
Related: #4794
2026-07-26 21:04:18 +08:00
Chenhao 8ffa2a31ff fix(codex): 保留级联中继的客户端指纹 2026-07-21 05:02:30 -07:00
superman2003 4a97491be6 fix(grok): let manual connection tests bypass the scheduling gate
Grok OAuth 'test connection' reused the production GrokTokenProvider
request path, whose eligibility gate rejects any account that is not
currently schedulable (manual switch off, rate limited, overloaded,
temporarily cooled down). Every such test failed before reaching xAI
with the generic 'oauth refresh account state changed', while
Codex/OpenAI account tests read credentials regardless of scheduling
state (#4598).

Add GetAccessTokenForManualTest and use it from the account test
service:

- skips the request-path scheduling eligibility gate so admins can
  probe excluded accounts; credential integrity checks (configured
  proxy present, refresh token present) still apply
- refreshes expired tokens through the shared OAuthRefreshAPI without
  the request-path marker, so the lock protocol and DB re-read keep
  working while scheduling state no longer blocks the refresh;
  credential rotation for non-active accounts stays blocked inside
  RefreshIfNeeded
- falls back to the still-valid current token when a refresh attempt
  fails or another worker holds the refresh lock, and otherwise
  surfaces the concrete refresh error instead of the generic message

Fixes #4598
2026-07-19 22:40:58 +08:00
superman2003 dd7a2b22f0 fix(grok): align Free probes with health checks 2026-07-18 21:05:50 +08:00
shaw 221581400b feat(grok): 支持账号级自定义上游地址与请求头覆写
将账号级请求头覆写从 anthropic/openai 的 api_key 账号扩展到 Grok 的
api_key 与 oauth 账号,并放开 Grok OAuth 账号的自定义上游地址(仅作用于
转发端点,授权与 token 刷新链路不变)。

后端:
- IsHeaderOverrideEligible 扩展到 Grok(api_key+oauth),禁止名单新增
  x-grok-conv-id(逐请求会话路由头)。
- 所有 Grok 上游请求路径接线 ApplyHeaderOverrides(Responses/Chat 桥/
  媒体/配额探测/billing 探测/连通性测试),统一置于内置默认头之后。
- GetGrokBaseURL/GetGrokMediaBaseURL 放开 OAuth 自定义地址:官方地址
  视同未定制回落官方网关,仅显式第三方 host 改发转发流量。
- 非官方 host 允许任意 path 前缀,官方 host 仍强制 /v1。
- OAuth base_url 校验按 host 判定官方/自定义,自定义 host 恒受运营方
  URL 策略约束,不受 XAI_ALLOW_UNSAFE_URL_OVERRIDES 调试开关放宽。
- 给 GrokQuotaService 注入 config,使配额/billing 探测与转发共用同一
  URL 策略。

前端:
- Edit 模态为 Grok OAuth 账号新增「自定义上游地址」开关。
- 请求头表单新增 JSON 快速导入与按 JSON 一键复制(复用 useClipboard,
  兼容非安全上下文 HTTP 页面)。
- 门控改为平台×类型判定,Bulk 批量 base_url 增加格式校验,zh/en 文案同步。
2026-07-15 20:30:23 +08:00
Wesley Liddick 4355861ef2 Merge pull request #4269 from catoncat/agent/sub2api-agent-identity
feat(openai): support Codex Agent Identity authentication
2026-07-15 09:47:00 +08:00
cat d68a2aac1a chore(openai): 同步上游并解决认证冲突 2026-07-14 19:04:04 +08:00
cat f479a5d10c fix(openai): 收紧 Agent Identity task 生命周期 2026-07-14 18:09:59 +08:00
cat 10aa88aab9 fix(openai): 补齐身份失效恢复路径 2026-07-14 17:19:15 +08:00
cat 57cf2df09f fix(openai): 收紧 Agent Identity 恢复与脱敏 2026-07-14 17:05:47 +08:00
cat 1dab126944 feat(openai): 支持 Agent Identity 认证 2026-07-14 17:05:46 +08:00
Heatherm Huang b32b815e46 fix(grok): harden OAuth pool recovery 2026-07-14 14:55:30 +08:00
Heatherm Huang 343390057d fix(grok): fail over OAuth credential errors safely 2026-07-14 14:55:30 +08:00
superman2003 c896cacf6d feat(grok): improve free quota probing and usage 2026-07-13 19:49:56 +08:00
Wesley Liddick b0d0de0547 Merge pull request #4045 from xiaopixiu2019/codex/upstream-gpt56-oauth-test
fix: normalize GPT-5.6 alias in OpenAI OAuth account tests
2026-07-13 15:31:44 +08:00
Heatherm Huang d9e466ad3a feat(grok): support xAI API key accounts
Allow Grok API-key accounts in Responses forwarding and connection tests, expose creation and edit defaults in the dashboard, and document the supported setup.
2026-07-13 10:11:33 +08:00