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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
* 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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
Rebuild the backend as the frozen gateway workspace with a single PostgreSQL schema, provider-owned OpenAI and xAI boundaries, and mirrored domain tests.
Restore the admin product contracts for accounts, model catalogs, usage observability, billing details, and provider-scoped settings without compatibility shims.
Co-authored-by: Codex <noreply@openai.com>