Commit Graph
6539 Commits
Author SHA1 Message Date
lyy0709 62cd63bfda fix(openai): retain capabilities when model listing is unavailable 2026-09-05 16:24:15 +08:00
lyy0709 dee35a841d merge: reconcile Astra fixes with upstream capability sync 2026-09-05 16:19:57 +08:00
lyy0709 d7f048a265 fix(openai): preserve synced Astra capabilities and continuation 2026-09-05 16:13:28 +08:00
Wesley Liddick 0d9e7e1530 Merge pull request #6628 from baryon/contrib/openai-gpt6-astra-capability-sync
fix(openai): persist GPT-6 Astra Codex capabilities from upstream sync
2026-09-05 16:07:50 +08:00
Wesley Liddick 9b4fcfb897 Merge pull request #6606 from luckydududu/feat/claude-cli-version-env-override
feat(claude): allow operators to override the advertised CLI version
2026-09-05 16:05:33 +08:00
Wesley Liddick 9517f12cdd Merge pull request #6510 from wall-wxk/fix/release-session-slot-on-forward-failure
fix(gateway): 转发失败的请求立即释放会话槽,不再占用整个空闲超时窗口
2026-09-05 16:05:06 +08:00
Wesley Liddick 40f4d450be Merge pull request #6507 from wucm667/fix/issue-6501-glm53-thinking-effort
fix(gateway): normalize GLM-5.3 thinking effort
2026-09-05 16:04:16 +08:00
Wesley Liddick 620eb3fd00 Merge pull request #6581 from r266-tech/r266/forward-opencode-session
fix(openai): scope OpenCode session forwarding
2026-09-05 16:03:57 +08:00
Wesley Liddick c6ff69fd12 Merge pull request #6542 from wucm667/fix/issue-6530-gateway-concurrency-origin
fix(handler): distinguish gateway admission rejections
2026-09-05 16:03:17 +08:00
Wesley Liddick 7b271bbee9 Merge pull request #6529 from wucm667/fix/issue-6521-preserve-passthrough-reasoning
fix(openai): preserve reasoning effort in API-key passthrough
2026-09-05 16:02:56 +08:00
Wesley Liddick 68f099707e Merge pull request #6553 from wucm667/fix/issue-6547-heartbeat-bootstrap
fix(openai): normalize automation heartbeat bootstrap
2026-09-05 16:02:36 +08:00
lyy0709 3a8c9f16de Merge remote-tracking branch 'upstream/main' into codex/gpt-6-astra 2026-09-05 15:48:49 +08:00
Wesley Liddick 07bf8b92fd Merge pull request #6550 from weiness/fix/alipay-payment-reconciliation
修复支付宝回调延迟或丢失,已支付订单可能长时间停留在待支付状态的问题
2026-09-05 15:08:56 +08:00
Wesley Liddick 63dc24b5e8 Merge pull request #6626 from wucm667/feat/issue-6624-none-reasoning-mapping
feat(openai): allow none as reasoning mapping source
2026-09-05 15:06:32 +08:00
Wesley Liddick 8f1d6af3ed Merge pull request #6531 from wucm667/fix/issue-6524-continuation-unavailable-recovery
fix(openai): recover unavailable continuation responses
2026-09-05 15:06:02 +08:00
Wesley Liddick 85f431a072 Merge pull request #6620 from wucm667/fix/issue-6615-astra-messages-cache
fix(openai): enable Astra messages prompt caching
2026-09-05 15:04:13 +08:00
Wesley Liddick d7fb9b5d35 Merge pull request #6593 from wucm667/fix/issue-6584-chat-tool-discovery
fix(apicompat): preserve discovered tools in chat fallback
2026-09-05 15:03:52 +08:00
Wesley Liddick eba6ea5639 Merge pull request #6590 from wucm667/fix/issue-6582-search-tool-capability
fix(codex): advertise search capability for bridged routes
2026-09-05 15:03:31 +08:00
Wesley Liddick 2ad6e8fb75 Merge pull request #6599 from wucm667/fix/issue-6598-gemini-custom-models-list
fix(gemini): apply custom list to native models endpoint
2026-09-05 15:03:08 +08:00
Wesley Liddick 570bd084c2 Merge pull request #6594 from wucm667/fix/issue-6592-preserve-zero-system-metrics
fix(ops): preserve zero-valued system metrics
2026-09-05 15:02:40 +08:00
Wesley Liddick 15278fe2f9 Merge pull request #6580 from OG-Wang/fix/sidebar-collapse-when-active
fix(frontend): allow collapsing sidebar groups while a child route is active
2026-09-05 15:02:30 +08:00
Wesley Liddick c4e6dcfd80 Merge pull request #6602 from ZeroClover/feat/codex-manifest-pinned-accounts
feat(codex): pinned-accounts Codex model manifest for OpenAI groups
2026-09-05 14:51:17 +08:00
Wesley Liddick 701f844755 Merge pull request #6555 from feeeei/feat/usage-upstream-request-id
feat(usage): 用量记录落库直接上游的请求 ID,并支持按账户配置响应头名
2026-09-05 14:36:07 +08:00
Wesley Liddick 91cf660377 Merge pull request #6397 from feeeei/fix/openai-ws-replay-oom-6382
fix(openai-ws): eliminate O(T²) replay copying and invalid_encrypted_content retry storms
2026-09-05 14:32:11 +08:00
Wesley Liddick 78e1aaedb9 Merge pull request #6535 from feeeei/feat/pricing-custom-file-hot-reload
feat(pricing): fallback/override 定价文件按内容哈希热重载,改动无需重启生效
2026-09-05 14:31:09 +08:00
shaw 708b85a6a4 fix: complete upstream request id handling 2026-09-05 14:18:13 +08:00
shaw 1cab4d8c22 fix: make custom pricing reload coherent 2026-09-05 14:18:13 +08:00
Wesley Liddick d8b9a83f8c Merge pull request #6492 from feeeei/main
fix(gateway): 负载感知调度补齐渠道模型限制的逐账号检查
2026-09-05 14:06:21 +08:00
Long LiandCursor a016bd4ba5 style: gofmt upstream models capability sync tests
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-05 14:58:51 +09:00
Long LiandCursor 983a3db3af fix(openai): persist GPT-6 Astra Codex capabilities from upstream sync
Official OpenAI hosts and models.dev entries without an api field left
Astra falling back to reasoning effort none and empty Fast tiers. Persist
complete per-model metadata, advertise Astra reasoning/Fast locally, and
surface partial sync warnings when image models remain incomplete.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-05 14:45:06 +09:00
wucm667 7969751f1f feat(openai): allow none as reasoning mapping source 2026-09-05 12:32:30 +08:00
wucm667 4aaf5cb73b fix(openai): enable Astra messages prompt caching 2026-09-05 10:58:05 +08:00
LuckyandClaude Opus 5 e9bad40b10 feat(claude): allow operators to override the advertised CLI version
Anthropic gates newer models on a minimum Claude Code client version. With
CLICurrentVersion pinned at 2.1.220, claude-fable-5-1 fails every request with
"Claude Code 2.1.220 does not support this model; version 2.1.251 or newer is
required", and the only fix is a release that bumps one constant.

Add SUB2API_CLAUDE_CLI_VERSION, mirroring what internal/pkg/xai already does
with XAI_GROK_CLI_VERSION. CLICurrentVersion remains the built-in pin; the new
CLIVersion() is what every consumer reads. With no env var set the resolved
value equals the pin, so existing deployments are unaffected.

The value is resolved once at package init rather than per call: the User-Agent
header and the request body's cc_version are written by different code paths for
the same request, and reading different values would make that request
contradict itself.

Validation is strict (three numeric segments, not below the pin) because
identity_service.go documents what a malformed version does once it reaches an
account's persistent fingerprint: sustained 429s without reset headers, 5s
fallback cooldown, pool collapse into a 503 storm, and no reset entry point.
Invalid values warn and fall back rather than being silently dropped.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0168uDMAj9anaJrnH8CeFze6
2026-09-04 18:01:34 +00:00
Zero Clover 1e28ef5942 feat(codex): pinned-accounts Codex model manifest for OpenAI groups 2026-09-05 00:10:24 +08:00
wucm667 28f673e4cd fix(gemini): honor custom native models list 2026-09-04 22:29:36 +08:00
wucm667 9ddf69698d fix(ops): preserve zero-valued system metrics 2026-09-04 18:51:24 +08:00
wucm667 51631d0324 fix(apicompat): preserve discovered tools in chat fallback 2026-09-04 18:33:23 +08:00
wucm667 c7538cd256 fix(codex): advertise search capability for bridged routes 2026-09-04 16:43:15 +08:00
r266-tech 6cf645f87c fix(openai): scope OpenCode session forwarding 2026-09-04 12:45:06 +08:00
Rick aa556c372f fix(frontend): allow collapsing sidebar groups while a child route is active
A collapsible sidebar group was force-expanded whenever the active route
was one of its children, so clicking the chevron did nothing: the toggle
only updated the internal set while isGroupActive() kept reporting the
group as expanded. Any click that produces no visible change reads as a
bug to users.

Track per-group expand/collapse overrides instead. A group without an
entry keeps the automatic behavior (expanded while active, so context is
not lost on load or navigation), but a chevron click records the user's
choice and that choice wins, letting an active group be collapsed and
re-expanded at will.
2026-09-04 12:42:20 +08:00
lyy0709 3c8be00131 feat(openai): add GPT-6 Astra support 2026-09-04 10:04:44 +08:00
wucm667 f5ae32e53f fix(gateway): normalize GLM-5.3 thinking effort 2026-09-04 08:15:41 +08:00
feeeei de27905e88 feat(usage): 用量记录落库上游请求标识并支持按账户配置响应头名
- usage_logs 新增 upstream_request_id 列(迁移 232)与仅索引非空行的 CONCURRENTLY 部分索引(迁移 233,runner 登记失效索引清理)
- 账户 extra.upstream_request_id_header 指定要读取的上游响应头,只读该头;留空不记录;创建/更新/批量入口校验头名合法且不超过 64 字节
- ForwardResult/OpenAIForwardResult 携带 UpstreamHeaders,中央计费按账户解析落库,WS 轮次保持 NULL
- 管理端用量明细新增默认隐藏的"上游ID"列,带与请求ID列一致的复制按钮,并同步导出
- 创建/编辑账户弹窗新增"上游ID"输入(UpstreamRequestIdHeaderField),提示按接入类型与平台分条列出常见头名
- HelpTooltip 悬停模式下指针移入提示框时保持打开,便于选中复制提示内容
2026-09-03 18:02:15 +08:00
wucm667 28dde982cb fix(openai): normalize automation heartbeat bootstrap 2026-09-03 17:29:04 +08:00
weiness de8d756afa fix(payment): reconcile pending Alipay orders 2026-09-03 16:33:30 +08:00
shaw b1748c4ea9 chore: update sponsors 2026-09-03 15:40:51 +08:00
Wesley Liddick 432ebc498c Merge pull request #6179 from wwcchh0123/codex/upstream-error-proxy-attribution
fix(ops): preserve event-time proxy attribution for upstream errors
2026-09-03 15:34:59 +08:00
Wei-Shaw abc07bb079 test(ops): satisfy errcheck and gofmt in proxy attribution tests 2026-09-03 15:23:22 +08:00
Wei-Shaw 4c1f920d58 fix(ops): close proxy attribution gaps and bound queued upstream events
Follow-up to the event-time proxy snapshot: every upstream attempt now
carries attribution, the direct/unknown contract is enforced everywhere,
and the queued upstream_errors array has hard bounds again.

Attribution coverage
- compact fallback retry helper and the streaming compact failover event
  now stamp proxy_id/proxy_name; the non-streaming SSE compact retry
  previously dropped its first attempt on `continue` and now records it
- raw chat-completions stream truncation events (new on main) attributed
- Anthropic/Bedrock transport errors get attribution inside the shared
  handleUpstreamTransportError helper, so all five callers inherit it
- OpenAI first-output timeout takes attribution from the caller: HTTP
  callers pass the HTTP rule, the WS passthrough relay passes the WS rule
  (no managed proxy => unknown, never direct, because http.DefaultClient
  may honor environment proxies)

Contract hardening
- single opsUpstreamProxyAttribution returns (id, name) from one decision;
  a hydrated Proxy without a durable ID is unknown, not id=null+name
- both normalizers (struct at append time, JSON on detail reads) enforce
  proxy_id==null <=> sentinel name; blank managed name => "proxy"
- detail-read normalization edits only the attribution keys via sjson, so
  keys from older struct versions and stored key order are preserved

Queue bounds
- keep at most 256 attempts and ~512 KiB serialized per entry, newest
  first; the oldest retained event records dropped_earlier_attempts
- attempts outside the 16-event body window trim url/message to 512 bytes
- restore the empty-event drop rule, judged before the body window clears
  detail so older real attempts survive

Tests cover each site above (managed proxy, direct, WS unknown), the
normalizer invariants, key/order preservation, and the count/byte bounds.
2026-09-03 15:11:36 +08:00
wwcchh0123 e9e3c46cb7 fix(ops): snapshot proxy on upstream errors 2026-09-03 14:20:39 +08:00