* fix(egress): honor deployment proxies for unbound outbound requests
Prefer the proxy selected for the request. Otherwise apply the deployment proxy and bypass rules consistently to HTTP and WebSocket connections, including background downloads. Keep explicit direct probes separate.
Co-authored-by: Codex <noreply@openai.com>
* fix(openai): preserve WebSocket dial errors
Recover the OS error or I/O kind from Hyper without retaining the endpoint. Keep refused connections distinguishable for both direct and proxied WebSocket dials.
Co-authored-by: Codex <noreply@openai.com>
---------
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
* feat(keys): add explicit budget windows with safe retries
Add revision-checked daily and weekly windows across admission, settlement
and queries. Reuse the existing budget ledger for atomic window updates,
latest-operation replay and audit records.
Expose typed SDK callbacks while keeping account associations and cycle
decisions in plugins.
Refs #658
Co-authored-by: Codex <noreply@openai.com>
* fix(keys): preserve budget accounting across window changes
Keep restored balances when historical charges are unavailable and reject window changes that would require those charges. Honor future start times after release and report actual spending windows to peers.
Require an explicit null to release a window through the plugin SDK.
Co-authored-by: Codex <noreply@openai.com>
* fix(plugins): preserve budget window precision across SDK calls
Co-authored-by: Codex <noreply@openai.com>
---------
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Drive each worker exit from the prepared generation so scheduling delays cannot turn a post-registration crash into a registration failure.
Co-authored-by: Codex <noreply@openai.com>
* 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>
Seal managed callback observations before Core retry decisions and synchronize RPC resource revocation with stream teardown.
Co-authored-by: Codex <noreply@openai.com>
Resolve identity and frozen access facts without constructing model execution
contexts. Coordinate parent task suspension, resumption and retained callbacks
at the SDK and Runtime boundary, with bounded admission and cancellation.
Expose account HTTP, client verification, access facts and quota details through
the existing host owners.
BREAKING CHANGE: Plugin sessions require RPC v7; rebuild and repackage plugins
with the matching SDK. No legacy protocol negotiation or fallback is provided.
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Resolve scenario defaults and plugin declarations consistently across the SDK
and runtime. Preserve maintenance across unrelated publications and cancel
long preparation when the runtime shuts down.
BREAKING CHANGE: Plugin RPC requires protocol v6. Rebuild plugins with the
updated SDK; previous protocol versions are not supported.
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Use request, attempt, and outbound middleware for plugin-owned identity
selection and complete request rewriting. Preserve native account identity
and partition WebSocket connections through existing outbound opening changes.
Remove the construction parameter channel and its obsolete tests and docs.
Keep middleware at v6 without a compatibility shim.
Co-authored-by: Codex <noreply@openai.com>
* feat(plugins): select upstream adapters within account scopes
* fix(plugins): defer adapter decisions until account selection
Keep scoped adapters pending until an account is known so unavailable
fallbacks cannot mask a healthy earlier match. Filter native xAI accounts
when only an adapter can accept the request, preserving normal selection
and cold-stream behavior.
Cover fallback precedence and mixed-pool prewarm eligibility regressions.
Co-authored-by: Codex <noreply@openai.com>
---------
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Remove redundant contract cases and express fixtures in terms of current behavior.
Reduce isolated database migration contention, run independent scenarios concurrently,
and replace fixed waits with clock and I/O synchronization. Check absolute Redis
session expiry and wait for PostgreSQL migration session locks to be released.
Document nextest for local test execution.
Validated 4060 tests, 70 Redis ACL tests, and five repeat runs of 26 focused tests.
The 10 plugin state tests also pass 50 repeat runs with four workers.
Rustfmt and strict Clippy pass. Local full-suite execution with 16 workers falls
from 162.760s to 89.072s, excluding compilation.
Co-authored-by: Codex <noreply@openai.com>
* fix(plugins): honor configured request body limits
* test(plugin-sdk): mirror upstream adapter module layout
Co-authored-by: Codex <noreply@openai.com>
* fix(plugins): preserve frozen request body budgets across callbacks
Carry the execution body budget through policy and attempt callbacks, and validate explicit-key model requests against their bound snapshot. Add regression coverage for configuration publication and document budget ownership and lifetime.
Co-authored-by: Codex <noreply@openai.com>
---------
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Move business JSON out of control metadata, encode request snapshot headers
compactly, and reuse encoded frames. Cache compiled configuration schemas
and prepare plugin instances with bounded concurrency.
Ignore unused plugin result fields and remove redundant business validation
while preserving host authorization, resource ownership, and capacity limits.
Keep response decoding failures local to their calls.
Seal callback side effects before completing or cancelling RPC calls, and
recover abandoned state migrations without allowing old owners to promote.
Validation: SDK 112 tests and its doctest, Runtime 203 tests, Core 542 tests,
40 PostgreSQL plugin tests, and 16 architecture checks passed. Strict Clippy,
formatting, and diff checks passed.
BREAKING CHANGE: RPC protocol v4 changes frame payload layout and request
snapshot header encoding. Plugins must update their SDK and protocol
manifest version and be rebuilt.
Co-authored-by: Codex <noreply@openai.com>
* feat(accounts): add concurrency details and SDK request context
Co-authored-by: Codex <noreply@openai.com>
* fix(plugins): version request-context frames and preserve failed snapshots
Co-authored-by: Codex <noreply@openai.com>
* fix(dev): sync workbench with request-context contracts
Co-authored-by: Codex <noreply@openai.com>
* fix(accounts): refine concurrency and request context handling
Preserve entry context and recursion scopes in retry and public management callbacks. Encode queued RPC frames once and use a dedicated account existence query for concurrency polling. Sync workbench packaging tooling and CI through the plugin submodule.
Co-authored-by: Codex <noreply@openai.com>
---------
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
* feat(scheduling): add plugin filtering and remove automatic switchback
Add scheduler v2 filtered delegation across native selection, affinity,
capacity waits, and lease retries. Keep plugin configuration and business
rules owned by plugins without legacy scheduler compatibility.
Remove automatic switchback from the runtime, SDK, and settings UI.
Migrate the existing settings JSON without creating new tables.
Co-authored-by: Codex <noreply@openai.com>
* fix(dev): align plugin source checks with scheduler v2
Update the workbench submodule to the v2-capable SDK and scheduler,
and document the explicit scheduler manifest version.
Co-authored-by: Codex <noreply@openai.com>
---------
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Expose generic detail CRUD, aggregate contributions, and native pricing evaluation through Admin and the plugin SDK. Reuse existing request and statistics storage without schema changes; keep workflow state and recovery with callers.
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Rename inconsistent tables and their schema objects, update SQL references,
and preserve analytics trigger behavior through the upgrade.
Co-authored-by: Codex <noreply@openai.com>
Use the current host manifest format and require restart confirmation on
all management UI paths. Document v3.18.1 as the minimum online upgrade
source while retaining old release manifest reads for supported rollbacks.
Retire middleware v3 and upstream_adapter v1 Fast projections after their
compatibility window. Align SDK and host declarations with the current
contracts, keep risk warnings and per-instance failure isolation, and
exercise native fast_mode values through real plugin subprocesses.
Keep deployment, API and SDK documentation focused on current behavior.
Co-authored-by: Codex <noreply@openai.com>
Consolidate request diagnostics into typed request_observation_json with
migration 0025, preserving historical facts and query constraints.
Use upstream response timestamps for output throughput, align TTFT event
boundaries, and surface official timing metrics in the latency popover.
Co-authored-by: Codex <noreply@openai.com>
Separate execution, provider ports, administration, and plugin lifecycle responsibilities.
Fix shutdown ordering, account lock reclamation, multipart cancellation, budget windows, and WebSocket close handling.
Align xAI catalog, reasoning, tools, replay, quota, and cost handling with current Grok contracts and remove legacy fallbacks.
Update API and architecture documentation with regression coverage. Validated backend suites, strict workspace Clippy, isolated PostgreSQL/Redis integration, and real Codex/Grok client flows.
Co-authored-by: Codex <noreply@openai.com>
Preserve native failure causes through store, provider, plugin, admin, and
worker boundaries, including secondary cleanup failures. Route operational
failures through the shared diagnostics sink with protected error details.
Use bounded nonblocking file logging with batched writes and reserved
warning/error capacity. Reserve observation capacity for failures and
request lifecycle records, and rate-limit overload warnings.
Validate error propagation and blocked-output HTTP, admin, SSE, and WebSocket
behavior; keep the local migration plan out of version control.
Co-authored-by: Codex <noreply@openai.com>
Renew active administrator sessions with atomic Redis expiry updates,
synchronized cookies, and idle and absolute lifetime limits. Preserve
revocation after logout and password changes.
Coordinate session recovery, bounded retries, error handling, and raw
responses through request plugins. Gate initial navigation in the router
and organize frontend API modules by their views.
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>
Use one validated IANA timezone for backend display projections, calendar queries, budget windows, warmup slots, backups, and logs. Remove frontend date formatting and the independent backup timezone setting.
Preserve UTC instants and active budget windows, persist warmup deduplication, and advance backup schedules transactionally. Cover DST boundaries, timezone changes, invalid calendar anchors, and account cooldown displays.
Co-authored-by: Codex <noreply@openai.com>
Restore the pre-window host implementation and document plugin-owned policy and presentation. Keep native reset RPC coverage and run plugin integration tests with the standard isolated test services.
Co-authored-by: Codex <noreply@openai.com>
Compose HTTP, WebSocket, request, attempt and public service calls through
shared onion middleware with scoped settings and invocation context.
Adopt trusted-process manifests, unified observation and forward-compatible
SDK contracts. Align management UI, documentation and the workbench reference.
Preserve native response bytes and WebSocket failure lifecycles.
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>
Add model aliases, minimal read-only account and quota facts, bounded retry
policies and middleware capability declarations. Preserve unchanged payloads
and expose the new contracts in the SDK and plugin configuration UI.
Remove the ignored external observer example test.
Co-authored-by: Codex <noreply@openai.com>
Define the initial plugin manifest and wire protocol without legacy branches.
Preserve large request payloads and isolate local RPC encoding failures.
Co-authored-by: Codex <noreply@openai.com>
Detect and persist proxy locations on enable, connection changes, and explicit
tests. Preserve manual locations and guard stale detection results. Allow a
successful outlet probe to fill the manual location fields on request.
Co-authored-by: Yanshan Chen <16632048+chenyanshan@users.noreply.github.com>
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
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>