Commit Graph
52 Commits
Author SHA1 Message Date
ZyyandCodex f02bc80f15 fix(openai): keep frame metadata separate from forwarded headers
Co-authored-by: Codex <noreply@openai.com>
2026-11-18 21:21:37 +08:00
a0e7f38f7f fix(openai): preserve Claude Messages session affinity (#712)
Resolve explicit Claude session identities before account selection and
revalidate them after attempt middleware using the existing affinity policy.

Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
2026-11-14 17:22:03 +08:00
ZyyandCodex e2f194875f refactor: clarify protocol ownership and request observations
Separate protocol identifiers from Provider identities and centralize shared
request facts and observations in gateway-protocol. Keep endpoint models
and private continuation state owned by Providers.

Reorganize the architecture documentation and clarify the shutdown guarantees
for buffered charges and observations.

Validated with workspace formatting, strict Clippy, 3013 affected-module
tests and 16 architecture checks. One reference-binary TLS test is ignored.

Co-authored-by: Codex <noreply@openai.com>
2026-11-11 16:04:16 +08:00
c0fdc1bbff fix(openai): record explicit Anthropic reasoning effort (#680)
Observe top-level output_config.effort before the OpenAI encoder rejects
Messages payloads. Reuse the protocol parser without inferring an effort
from thinking budgets or changing upstream conversion behavior.

Cover absent and explicit effort values, native Messages forwarding, and
Messages-to-Responses conversion. Document the observation contract.

Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
2026-11-11 15:12:02 +08:00
koeriaandCursor Agent 914c00785c fix(openai): skip same-account retry on NO_MORE_RETRY (#675)
Treat x-retry-metadata: NO_MORE_RETRY as a hard signal to skip
same-account backoff and transport recovery, even when Retry-After
is within maxRetryAfterSeconds. Capacity failures still rotate under
the existing policy; server_error still returns the upstream error.

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-11-11 14:08:24 +08:00
ZyyandZyy 2fc347508a fix(peer): allow grouped API accounts and reject forwarding loops (#671)
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
2026-11-11 01:04:20 +08:00
ZyyandCodex dd65665128 feat(protocol): support Messages ingress and API upstreams
Support Responses, Chat Completions and Messages ingress with Responses
or Messages API upstreams in the existing OpenAI provider.

Share generation admission and delivery, preserve native protocol payloads,
and translate cross-protocol tools, reasoning, streams and usage. Add
Messages token counting and editable upstream protocol settings.

Co-authored-by: Codex <noreply@openai.com>
2026-11-10 22:07:46 +08:00
ZyyandCodex 0d44492309 fix(openai): scope active quota window reassignment to image endpoints
Co-authored-by: Codex <noreply@openai.com>
2026-11-09 11:16:15 +08:00
Zyy e770c94a9e fix(openai): preserve Codex quota after image generation 2026-11-08 18:04:45 +08:00
ZyyandCodex bdfc201795 fix(peer-link): update account identity on definitive sharing results
Clear the peer badge when the upstream explicitly disables sharing or does not support CPR Link. Preserve identity on transient failures and allow manual rediscovery from the quota panel.

Co-authored-by: Codex <noreply@openai.com>
2026-11-04 19:58:55 +08:00
ZyyandCodex 19ef484969 feat(peer-link)!: share upstream key concurrency and RPM limits
Use a fresh upstream key concurrency limit as the account default for scheduling, leases, and capacity reporting. Show disclosed limits alongside the upstream pool summary.

BREAKING CHANGE: Both peers must support CPR Link schema v3.

Refs: #587

Co-authored-by: Codex <noreply@openai.com>
2026-11-04 18:32:42 +08:00
ZyyandCodex db849c1251 feat(peer-link)!: simplify the CPR Link protocol
Make capability blocks optional and represent key budgets as named windows. Centralize validation and preserve unknown states for missing observations.

BREAKING CHANGE: CPR Link requires schema_version 2; v1 snapshots are no longer accepted.

Co-authored-by: Codex <noreply@openai.com>
2026-11-01 19:24:17 +08:00
ZyyandCodex bcf0582814 refactor(peer): reuse account quota storage for CPR Link
Store peer snapshots in existing account quota fields and remove dedicated node and synchronization tables. Keep CPR protocol handling in Admin and native quota handling in Providers, sharing persistence and the quota refresh endpoint.

Use runtime refresh coordination and preserve credential, connection, and observation-time guards. Update the unreleased migration, API contracts, documentation, and regression coverage.

Validated with 354 selected tests, strict workspace Clippy, Rustfmt, frontend lint and build, and migration checksum verification. Browser interaction remains unverified.

Co-authored-by: Codex <noreply@openai.com>
2026-10-31 20:43:15 +08:00
ZyyandCodex a5d3d9f12d fix(peer): recover quota from explicit upstream budget state
Export authoritative budget access flags and keep monetary fields display-only
for peer consumers. Use the official usage_limit_reached error type for budget
exhaustion while preserving ordinary rate-limit cooldowns.

Apply fresh quota facts atomically with peer snapshots through the shared quota
writer, retaining connection, claim, and observation-time guards. Reuse the
existing sync worker and document the recovery contract.

Validated with 234 selected tests, strict workspace Clippy, and Rustfmt.

Co-authored-by: Codex <noreply@openai.com>
2026-10-31 15:58:02 +08:00
58a1f7541e feat(peer): add CPR Link discovery and scoped quota sharing (#566)
* feat(peer): add automatic discovery and scalable quota sharing

Export authorized direct-account pools and budgets through the CPR peer
protocol, with durable upstream discovery and immutable scheduling views.

Show shared-pool node quotas through common quota popovers and lazy account
details. Bound snapshot reads and export concurrency, reduce Redis and SQL
work, and keep only the latest observation for each upstream connection.

Co-authored-by: Codex <noreply@openai.com>

* refactor(peer): centralize upstream discovery and quota projections

Move peer synchronization into Admin, HTTP transport into Host, and expose
neutral Core scheduling signals through explicitly wired provider capabilities.

Preserve provider-visible model catalogs and independent quota disclosure,
with stale windows following the existing OAuth quota layout.

Cover cross-provider discovery, lifecycle fencing, and database leases, and
update the architecture and usage documentation.

Co-authored-by: Codex <noreply@openai.com>

* fix(ui): center usage card loading and empty states

Co-authored-by: Codex <noreply@openai.com>

* fix(accounts): unify peer subscription badges across account views

Share CPR identity rendering through AccountPlanBadge, project upstream metadata into dashboard and proxy account views, and align quota empty states and API badges.

Co-authored-by: Codex <noreply@openai.com>

* fix(peer): bound snapshot work and preserve quota windows

Keep summary reads off full snapshots, reject oversized model expansion early, and yield export work. Preserve daily and weekly unlimited budgets, hide empty token counters, and unify quota empty states.

Co-authored-by: Codex <noreply@openai.com>

---------

Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
2026-10-31 15:00:12 +08:00
ZyyandCodex 1fa37ac92f fix(openai): observe reasoning effort updates across continuations
Resolve reasoning effort from configuration updates and preserve overrides in response-scoped session metadata without rewriting upstream requests. Cover HTTP and WebSocket continuations, new-chain resets, and baseline changes.

Co-authored-by: Codex <noreply@openai.com>
2026-10-28 11:04:29 +08:00
a7f95c3a78 fix(openai): preserve Retry-After when converting WS errors to SSE (#531)
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
2026-10-26 17:08:57 +08:00
ZyyandCodex 3f6607209b refactor(usage): remove reported model tracking and polish UI
Remove upstream response model tracking across providers, storage, APIs,
and plugin facts without migrating historical records.

Refine sidebar hints, locale loading indicators, model columns, and usage
page labels and filters.

Co-authored-by: Codex <noreply@openai.com>
2026-10-25 04:03:27 +08:00
ZyyandCodex ab8c61b118 chore(toolchain): upgrade Node to 26.12.0 and Rust to 1.99.1
Align Docker images, CI inputs, Rust requirements and development commands.
Adapt strict compiler checks and reuse owned buffers in UTF-8 conversion.

Validate 4,021 backend tests, SDK feature configurations, Clippy, frontend
checks, and the amd64 container build and startup.

Co-authored-by: Codex <noreply@openai.com>
2026-10-18 04:57:48 +08:00
ZyyandCodex e0a022518c refactor(backend): simplify shared rules and redundant tests
Reuse Core error classification and token presentation, remove unused
operation APIs and redundant tests, and avoid unnecessary context cloning.
Fix expired reset timestamp underflow and SSE metadata frame boundaries.
Consolidate architecture checks and document the backend audit results.

Validation: backend tests, architecture tests, rustfmt and strict Clippy.
PostgreSQL/Redis integration was not verified without dedicated services.

Co-authored-by: Codex <noreply@openai.com>
2026-10-15 13:46:11 +08:00
ZyyandCodex cc69368f77 perf(store): scale request analytics and isolate request history (#389)
Build durable request facts and bounded aggregate queries, freeze historical
identities, and move recovery lease updates out of request history rows.
Align token fields across storage, APIs and pages.

Invalidate analytics only after actual request deletions and track embedded
migration inputs during builds.

Co-authored-by: Codex <noreply@openai.com>
2026-10-11 20:57:36 +08:00
ZyyandCodex 52981f40f9 fix(providers): align Codex 0.162 protocol handling
Apply latest incremental tool declarations during Grok normalization and align nested Retry-After header parsing with official Codex semantics.

Cover developer instructions in input, Responses Lite tool declarations, partial_answer phases, and end_turn preservation.

Pin the upstream SQLx fix for cancelled BEGIN rollback and add a deterministic pooled-connection regression test.

Report safe Redis error categories and timeout status when the cooldown persistence regression fails.

Co-authored-by: Codex <noreply@openai.com>
2026-10-09 12:10:02 +08:00
ZyyandCodex 74f749f49d fix(openai): unify conversation account bindings
Share the current account across root and descendant requests, including
Search, Images turn aliases, and Live creation. Keep root recovery and
explicit plugin scheduling intact while descendant requests wait for the
current owner and follow root migrations.

Use versioned admission before sending so concurrent claims and late
responses cannot overwrite newer bindings. Cover queue lifecycle,
continuation recovery, endpoint routing, and Redis concurrency behavior.

Co-authored-by: Codex <noreply@openai.com>
2026-10-06 07:04:41 +08:00
78ba7e412e fix(codex): align upstream contracts and transport behavior (#352)
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
2026-10-05 23:41:46 +08:00
ZyyandCodex 24f39f7f0e docs(backend): standardize Rust file comments
Add Chinese responsibility summaries to every backend Rust source, test,
and build script. Remove sentence-ending periods from comments while
preserving meaningful dots in URLs, versions, identifiers, and examples.

Keep generated SDK documentation in sync with its contract generator,
group middleware module declarations and exports, and record the comment
conventions in the development skill.

Validated with Rustfmt, strict Clippy, backend tests, documentation tests,
and skill validation. Database-backed integration cases were skipped
because dedicated PostgreSQL and Redis test services were not configured.

Co-authored-by: Codex <noreply@openai.com>
2026-10-05 11:52:56 +08:00
ZyyandCodex 0490e28cfc feat(accounts): show Codex credit balances in quota reset dialog
Expose upstream credit facts through the account quota API while preserving
decimal balances and distinguishing zero, unlimited, and missing values.
Clear stale balances on passive updates without changing quota availability.

Display credits below reset cards, label OpenAI quota as Codex quota, and
standardize the account quota action icons.

Co-authored-by: Codex <noreply@openai.com>
2026-10-01 13:22:20 +08:00
ZyyandCodex b3fa5322f1 perf(test): reduce backend fixture and timeout overhead
Reuse immutable plugin archives across nextest processes and share admin fixtures within test matrices. Reduce log scanning, hashing, compression, database setup, and SSE scanning costs while preserving isolation and boundary coverage.

Use controllable clocks for recovery budgets and quota scheduling, retaining real socket and HTTP verification.

Validation: 3200 backend tests, 132 plugin persistence tests, 54 Redis ACL tests, 30 clock stress iterations, clippy, and formatting checks passed. Local full-suite runtime improved from 182.8s to 74.0s at unchanged concurrency.

Co-authored-by: Codex <noreply@openai.com>
2026-09-28 17:49:23 +08:00
ZyyandCodex 687ebd0331 feat(plugin): add the complete plugin development and management workflow (#256)
Introduce SDK 0.4, manifest v3, protocol v4, the isolated plugin runtime,
and cpr-plugin packaging CLI for independently maintained plugins.

Support installation, permissions, one active configuration per plugin,
version-specific settings, rollback, management pages, and CLI extensions.
Isolate plugin failures so native gateway startup and requests remain available.

Keep provider registration and UI choices fixed to built-in OpenAI and xAI.
Support nine extension capabilities with permission-scoped model and account
callbacks to the host.

Unify plugin settings and version management, support plugin icons,
and improve narrow layouts. Use the fixed GitHub UI dependency and pnpm 12
for standalone frontend and container builds. Reduce runtime test packaging
cost and align preparation modules with the repository layout.

Co-authored-by: Codex <noreply@openai.com>
2026-09-24 22:48:07 +08:00
71e26f44b7 fix(usage): bill sent models and show response model mismatches (#136)
* feat(usage): show upstream response model mismatches

Persist observed response models separately from routing and billing facts.
Surface mismatches with the existing model arrow and native title tooltips.
Keep response observations isolated across retries and WebSocket reuse.

Co-authored-by: Codex <noreply@openai.com>

* fix(usage): calculate costs from the outbound model

Co-authored-by: Codex <noreply@openai.com>

---------

Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-17 14:55:54 +08:00
1e6d69a349 fix(openai): align downstream requests with Codex protocol (#117)
Centralize downstream SDK, browser and proxy header compatibility in the
OpenAI provider. Normalize the session header alias and isolate known
non-Codex body parameters while preserving ordinary extensions.

Align account installation metadata with Codex Core and remove unverified
identity header classifications. Cover HTTP and WebSocket behavior and
document the request boundaries.

Validation: 1,105 scoped and architecture tests, Rustfmt and strict scoped
Clippy passed. Four real-account HTTP/WebSocket cases passed on gpt-5.5,
including connection reuse. Earlier gpt-reserve overload failures were
recorded separately without changing production retry policy.

Co-authored-by: Clarence <1297529513@qq.com>
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-17 00:30:52 +08:00
1bbae67040 fix(gateway-api): translate upstream WebSocket error events into SSE response.failed (#90)
* fix(gateway-api): translate upstream WebSocket error events into SSE response.failed

WS 上游协议用 `error` 事件报告流中途失败(如 OpenAI 的 server_is_overloaded),
SSE 协议的对应形态是 `response.failed`。SSE 交付边界此前把 `error` 事件按
未知事件原样透传,而 codex 等 SSE 客户端会静默忽略未知事件类型:客户端只看到
无原因的流 EOF("stream closed before response.completed"),丢失了上游的
完整错误负载(message/code/type),也无法据此分类重试。

现在 SSE 编码器在交付边界把 `error` wire 事件翻译成 `response.failed`:
错误负载(type/code/message/param)原样保留,response id 沿用已交付的
response.created。WS 客户端交付不变(WS 协议原生支持 error 帧)。
原有的会话级失败兜底(finish_with_gateway_error 合成 response.failed)不变。

* fix(gateway-api): preserve upstream response failures

Co-authored-by: Codex <noreply@openai.com>

---------

Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-15 10:49:29 +08:00
ZyyandCodex c75f0e7fd9 fix(openai): isolate downstream transport headers
Share transport-header classification between API ingress and OpenAI encoding. Strip proxy metadata and downstream compression negotiation while preserving opaque business extensions and upstream response diagnostics.

Add protocol, decoder, HTTP, and WebSocket regressions and document the transport boundary.

Validation: 946 related and application tests, Rustfmt, and strict workspace Clippy passed. Application tests passed with incremental compilation disabled after a compiler cache panic. Real-account HTTP/WebSocket checks and a two-turn WebSocket session through Cloudflare Tunnel passed.

Refs #63, #64

Co-authored-by: Codex <noreply@openai.com>
2026-09-11 22:58:38 +08:00
Zyy ddc10d7c1a docs: add Apache 2.0 license and community link 2026-09-10 16:14:44 +08:00
ZyyandCodex 35988d0eb7 fix(billing): correct provider pricing and service tier accounting
Use the actual response tier for OpenAI costs and persisted observations.
Replace broad model-prefix pricing with explicit variants and documented
aliases and snapshots. Retain regular Sol prices, excluding temporary
promotions, and add GPT Image 2.5 Sunburst and Flare token pricing.

Include File Search call fees and leave incomplete tool totals unpriced.
Add Grok 4.6 and confirmed Priority rates, persist the served xAI tier,
and preserve authoritative zero-cost responses. Reject inconsistent cache
counts, invalid totals and token-count overflow during local estimation.

Validation: OpenAI, xAI and gateway-protocol tests, additional billing and
compaction regressions, workspace rustfmt, strict workspace Clippy with
all targets and features, and diff whitespace checks passed.

Co-authored-by: Codex <noreply@openai.com>
2026-09-09 13:37:12 +08:00
ZyyandCodex db0c294e83 fix(openai): prioritize session affinity and isolate child failover
Prefer client-scoped session bindings over ordinary account weights while
keeping existing availability checks and failover behavior. Let child
threads inherit the root account on first selection and update only their
own binding when they migrate.

Share session and thread identity extraction across Responses, Search and
image endpoints. Renew existing Redis bindings for 24 hours and preserve
account-bound state isolation without adding a table or scheduler.

Validation: workspace tests (1838 passed, none ignored), rustfmt, and strict
workspace Clippy with all targets and features.

Co-authored-by: Codex <noreply@openai.com>
2026-09-07 03:16:45 +08:00
ZyyandCodex 2585d4cd7d refactor(architecture): consolidate usage and provider contracts
Move Dashboard quota projection to the backend, share pagination request state, and fix independent usage loads while keeping trend switches free of loading overlays.

Stream billing facts within the query budget, share pending authorization and usage validation, and separate Core value ownership and response observations. Remove the unused theme helper and strengthen dependency checks.

Validated with workspace integration tests against isolated PostgreSQL and Redis, strict Clippy, Rust formatting, and frontend typecheck, lint and build.

Co-authored-by: Codex <noreply@openai.com>
2026-09-05 05:29:12 +08:00
ZyyandCodex 573b6b26db fix(openai): isolate quota buckets by limit id
Co-authored-by: Codex <noreply@openai.com>
2026-08-18 16:48:37 +08:00
ZyyandCodex 4117840f75 fix(xai): align OAuth and Codex compatibility
Co-authored-by: Codex <noreply@openai.com>
2026-08-14 22:24:08 +08:00
ZyyandCodex f4b75c42ed fix(openai): isolate quota and recovery signals
Co-authored-by: Codex <noreply@openai.com>
2026-08-11 13:37:16 +08:00
CodexandCodex 4533ae8850 fix(openai): preserve resettable quota exhaustion state
Co-authored-by: Codex <noreply@openai.com>
2026-07-29 14:48:23 +08:00
zyycnandCodex d5fc778ea7 fix(openai): reconcile account connection failures
Expose exact upstream responses to authenticated connection tests, reload the resulting account state, and classify usage-limit windows as resettable quota exhaustion. Restore non-quota availability after verified credential rotation and refresh quota after reauthorization.

Co-authored-by: Codex <noreply@openai.com>
2026-07-29 02:31:38 +08:00
zyycnandCodex 0c90ed30fb fix(proxy): restore transparent wire semantics
Preserve raw request and response data across HTTP, SSE, and WebSocket adapters, including opaque headers and upstream error envelopes. Remove private payload and catalog gates, keep account switching behind the pre-delivery barrier, and make observation failures unable to replace client-visible protocol data.

Co-authored-by: Codex <noreply@openai.com>
2026-07-29 00:10:35 +08:00
ZyyandCodex 2e9213a784 fix(backend): derive Codex metadata from provider catalogs
Share Codex Responses request semantics across OpenAI and xAI providers so reasoning effort, presets, request kind, subagent kind, and compaction observations stay consistent.

Read xAI reasoning efforts from official catalog feature options instead of model-name hardcoding, and make Codex service tiers data-driven through ModelPresentation rather than API adapter defaults.

Co-authored-by: Codex <noreply@openai.com>
2026-07-27 16:27:41 +08:00
zyycnandClaude 5c66dc198d perf(protocol,api): incremental SSE scanning and map-based frame decode
Track a scanned-prefix cursor in SseEventDecoder so a large frame arriving across many chunks is scanned incrementally instead of rescanned from the start on every push (separator matching backs off three bytes to catch CRLF pairs split across chunks). Decode WebSocket response.create frames through a Map-accepting request-decode core, dropping the serialize-and-reparse round trip on the request start path.

Co-authored-by: Claude <noreply@anthropic.com>
2026-07-26 20:09:57 +08:00
zyycnandClaude 114084107c refactor: remove dead code across backend crates
Drop production APIs with no callers: the model-request history module, dead ClientApiKey/ProviderAccount repository methods, the CollectedResponse IR, canonical_facts_mut, the UsageExtraction error variant, unused xAI credential-refresh helpers, and the unused uuid/zeroize/chrono dependencies.

Co-authored-by: Claude <noreply@anthropic.com>
2026-07-26 18:18:08 +08:00
zyycnandCodex 5364508219 refactor(gateway): restore provider-owned protocol boundaries
Keep OpenAI Responses bodies and wire events transparent, remove the generic typed compaction and response reconstruction path, and localize Grok compaction adaptation to the xAI provider.

Co-authored-by: Codex <noreply@openai.com>
2026-07-25 00:33:12 +08:00
zyycnandCodex bcf57351d6 fix(gateway): restore upstream response transparency
Co-authored-by: Codex <noreply@openai.com>
2026-07-25 00:33:12 +08:00
zyycnandCodex 7cb898b40a refactor(gateway): finalize production API audit
Remove unused full-response transports and unconnected domain reservations while keeping test-only setup inside integration tests.

Restore image-generation accounting and OpenAI WebSocket pool observations across the engine, store, and admin boundaries without changing the transparent OpenAI WS/SSE path.

Co-authored-by: Codex <noreply@openai.com>
2026-07-25 00:33:11 +08:00
zyycnandCodex 8ddafb9af5 refactor(gateway): remove test-only production APIs
Move protocol and provider fixtures and observations into integration tests while exercising the production decoder, encoder, transport, DNS, and lease paths.

Remove direct credential seeding and routing test setters while preserving OpenAI transparent proxy and WebSocket/SSE fallback behavior.

Co-authored-by: Codex <noreply@openai.com>
2026-07-25 00:33:11 +08:00
zyycnandCodex 198368363e fix(gateway): restore provider request semantics
Restore Provider-owned connection probes, xAI Grok Build request translation, continuation state, credential recovery, SSE metadata, and transport diagnostics without compatibility paths.

Keep upstream identity presentation and startup output aligned with the final package boundaries.

Co-authored-by: Codex <noreply@openai.com>
2026-07-25 00:33:11 +08:00