Let plugins page through retained account observations and find a prior baseline without reading raw provider documents or refreshing upstream. Reuse provider window identities and the existing completion index, preserving resets and gaps.
Co-authored-by: Codex <noreply@openai.com>
Scheduler v4 reports session ownership separately from native selection preferences and pins. Only eligible candidates are annotated, and cache preferences do not imply a session binding.
BREAKING CHANGE: scheduler plugins must declare capability version 4 and accept the new candidate fields.
Co-authored-by: Codex <noreply@openai.com>
* 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>
Reuse connection-scoped peer discovery for native HTTP and WebSocket forwarding. Strip the route header for ordinary upstreams and leave explicit plugin forwarding changes to plugins.
Co-authored-by: Codex <noreply@openai.com>
* feat(accounts): redeem reset credits when weekly quota runs low
Co-authored-by: Codex <noreply@openai.com>
* fix(accounts): observe weekly quota recovery after the last reset credit
Keep checking the local quota snapshot while recovery is unconfirmed. Once recovery is observed with no cards left, return to daily discovery.
Co-authored-by: Codex <noreply@openai.com>
---------
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.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>
* 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>
* feat(accounts): support configurable error protection rules
Replace capacity-specific freezing with bounded, configurable account error rules and shared attempt feedback.
Drop legacy settings without conversion and expose rule editing and freeze reasons in the admin UI.
Co-authored-by: Codex <noreply@openai.com>
* fix(accounts): preserve error protection scheduling boundaries
Keep xAI accounts excluded while recovery probes are pending, and cover
selection before and after recovery.
Separate scheduling cooldown reads from admin display details, share the
atomic Redis migration and selection logic, and use one policy revision.
Remove the unused adaptive concurrency reduction path and its tests.
Validation: 393 targeted backend tests, workspace Clippy with -D warnings,
Rustfmt, frontend type checking and build, and local service health checks.
Co-authored-by: Codex <noreply@openai.com>
---------
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Keep direct aliases in v2 and update the SDK builder, runtime compatibility declaration, tests and migration guidance.
BREAKING CHANGE: model_catalog plugins must declare version 2, move their alias list to aliases and return models for adapted models.
Co-authored-by: Codex <noreply@openai.com>
* feat(plugin): publish account-scoped adapted model catalogs
* fix(core): preserve candidate account scope during execution
Apply the narrowed candidate scope before provider account selection, including affinity and account rotation. Cover adapted-only models and same-name models with incompatible tool capabilities through the real OpenAI selector and local HTTP fixtures.
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>
Keep incompatible plugins out of execution sets during automatic startup.
Require scoped confirmation for manual compatibility overrides and show
the stopped state and upgrade effects in the management UI.
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>
Preserve request evidence and cold middleware boundaries across cancellation. Make backup auditing atomic, retain committed account-group results, and serialize restart operations.
Unify frontend stream authentication and session recovery, clear stale secrets, and remove redundant runtime paths. Correct CI permissions and database test URL handling.
Align documentation with current module responsibilities, APIs, and validation workflows, including both submodules.
* 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>
Transfer upstream stream lifetime to the model request after the initial RPC reply and give managed HTTP body reads an operation budget. Cover heartbeat continuity, cancellation cleanup, and per-read timeouts.
Co-authored-by: Zyy <zyycn@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.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>
Skip new automatic redemptions above the configured remaining weekly
quota limit, leaving it unset by default and preserving pending retries.
Keep temporarily ineligible credits scheduled and expose the setting
beside the redemption lead time.
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>
Register typed account automation operations for server and CLI plugins, reusing the native account service. Preserve the initiating actor across service continuations and generate the SDK contract from host declarations.
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>
Pause Runtime and SDK processing budgets while middleware delegates to host next, then resume the remaining budget. Preserve request deadlines and cancellation, share callback deadline state, and add timeout diagnostics and regression coverage.
Fixes#392
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>
Share unchanged prepared instances across extension sets and close each
process when its last owner releases it. Keep inflight request plans intact.
Unify migration recovery and publication, centralize authentication binding
validation, avoid duplicate package inspection, and separate middleware plans.
Validated with 292 admin, 182 runtime, 37 plugin storage and 15 architecture
tests, rustfmt, and strict workspace Clippy.
Co-authored-by: Codex <noreply@openai.com>
Remove version migration narratives, consolidate repeated explanations, and organize settings and architecture references.
Co-authored-by: Codex <noreply@openai.com>
Allow long model responses to finish without a fixed 600-second deadline,
while preserving explicit plugin deadlines and upstream idle timeouts.
Renew request recovery, client admission and provider scheduling leases
for the session lifetime, and release their renewal tasks with the owners.
Keep observation renewal best-effort and cancel on lost concurrency leases.
Fixes#342
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>
Keep documentation focused on current behavior and clear ownership.
Load skill references by task and clarify official source priority and reply tone.
Co-authored-by: Codex <noreply@openai.com>