Commit Graph
417 Commits
Author SHA1 Message Date
tongzhou wang ce82e38b16 Gate new rollout work on shared budget exhaustion (#61582)
## Why

A budget can be exhausted while another thread waits to start work. New requests, tools, and automatic turns must observe that stop without discarding an already-consumed response whose cost exhausted the budget.

## What changed

- Share a work gate across the rollout tree while preserving native and host accounting ownership.
- Recheck the budget before HTTP and WebSocket requests, hook execution, tool dispatch, and compaction. Prevent automatic wakeups and late input from restarting stopped work, leaving pending input queued.
- Record response costs without rejecting the consumed response solely because its bill exhausts the budget, and stop new work when enforced accounting overflows.
- Expose a thread-registration receipt that remains committed after unload.

## Testing

Extend rollout-budget coverage to verify that accepted response text remains in history after exhaustion and that waiting tools observe the shared stop while completed tools retain their results.

GitOrigin-RevId: e583d657c6f29e374d374cdb014bf23fd6c28614
2026-11-15 00:03:23 +00:00
tongzhou wang 92c1a4dc2e Add response processing after completion and usage accounting (#61577)
## Why

Streaming can dispatch tools before a response finishes and its usage is accounted for. Allow callers to wait for completion and synchronous post-hooks so budget enforcement can block tools from the response that exhausts the budget.

## What changed

- Add `responses.process_mode = "after_complete_response"` to buffer response items and release them in order after completion, synchronous post-hooks, and usage accounting. Keep `streaming` as the default and deliver safety-buffering notifications immediately.
- Track whether response usage has already been charged to avoid duplicate accounting, including during compaction.
- Stop new tools across the agent tree when the rollout budget is exhausted. Coordinate steering with accounting and prevent buffered tool calls from dispatching after steering or cancellation.
- Bound buffered responses to 65,535 events and reject overflow.

## Testing

Add configuration coverage and extend integration tests for buffered output ordering, synchronous hooks, interrupted responses and resume, steering, invalid usage, and budget exhaustion preventing tool dispatch.

GitOrigin-RevId: bd06811cfd50cb701babe6353465c57dfed2a37a
2026-11-14 23:50:12 +00:00
tongzhou wang 81b995a6c9 Unify model request hook lifecycles across sampling and compaction (#61562)
## What changed

- Pair `PreModelRequest` and `PostModelRequest` hooks per sampling or compaction attempt, with distinct lifecycle IDs and cancellation reporting.
- Add `thread_id` and `kind` to hook inputs, distinguishing `sampling`, `foreground_compaction`, and `background_compaction`. Include the provider's `response_id` in post-hook inputs when available.
- Wait for synchronous post-hooks before releasing terminal response events, accounting for usage, or installing compaction results. Allow streaming output and tool execution to proceed before the hook finishes, and cancel synchronous post-hooks when their owning request is interrupted.
- Preserve incomplete-response, budget-exceeded, and hook-denied outcomes across sampling retries and compaction model fallback.

## Testing

Add coverage for streaming and tool ordering, interrupted post-hooks, per-attempt metadata, and foreground and background compaction accounting and installation ordering.

GitOrigin-RevId: 3e808c5b3bf2d5a6a326d9f5be5bbd0359b2d16e
2026-11-14 19:40:12 +00:00
goodman-oai 65a5410f72 Add trusted request-country metadata to Responses requests (#61535)
## What changed

- Add `RequestCountry` for host-supplied country codes. Normalize two-letter ASCII codes to uppercase, omit the field by default, and serialize explicit unknown (`XX`) as `null` to prevent fallback to request provenance.
- Carry `request_country` through thread defaults and captured step settings into Codex backend HTTP and WebSocket requests. Allow live country updates without enabling `step_model_switching`, and preserve WebSocket continuation reuse when the country changes.
- Propagate the captured country to subagents, reviews, and compaction requests.

## Testing

Add coverage for country validation and serialization, thread and live-turn update lifetimes, prewarm settings capture, agent inheritance and reloads, compaction and reviews, WebSocket country changes, and HTTP fallback.

GitOrigin-RevId: 787cd1fa7ba5d465a4eb64a92f13c79e93d9bca7
2026-11-14 15:44:38 +00:00
cassirer-openai b8dde1eb40 Move rollout trace recording to a background worker (#61253)
## Why

Recording inference starts synchronously serializes prompts and writes trace payloads before model work can proceed. Defer that work so inference dispatch can continue while the trace is recorded.

## What changed

- Use one worker per trace bundle to write events in submission order, with up to eight pending jobs.
- Share prepared prompts and encoded requests with the worker, and build remote compaction snapshots there. Write payloads before publishing events that reference them.
- Add `TraceWriter::flush` and `ThreadTraceContext::flush` for live reads. Drain accepted jobs and seal the bundle on shutdown; suppress the closing marker after a recording failure.

## Testing

Add tests for deferred prompt serialization, ordered start and completion events, shutdown draining, and serialization failures that preserve earlier evidence without publishing a closing marker. Verify compaction snapshots are built on the worker and skipped when tracing is disabled.

GitOrigin-RevId: 32fd787bb1d281f1814df2f08c73b667628f8add
2026-11-13 04:36:03 +00:00
cassirer-openai e73744b3f4 Store rollout trace payloads in compressed shards (#61222)
## What changed

- Replace individual JSON payload files with numbered Zstandard shards in trace schema v3. Add `PayloadReader` to resolve payload references, cache decoded shards, and validate payloads during replay.
- Capture exact outgoing HTTP bodies and WebSocket messages alongside prepared prompts. Preserve full formatted context for continuations from unrecorded WebSocket warmups while retaining the actual incremental request.
- Flush payload records before publishing references and seal the final shard before recording completion. Replace `recording_complete` with `recording_status` to distinguish unclosed recordings, closed recordings with partial payloads, and complete recordings.

Reduce trace bundles with the binary that recorded them.

## Testing

Add coverage for shard rotation, oversized records, live reads, cache eviction, and malformed or corrupt payloads. Extend HTTP and WebSocket integration assertions to verify captured requests and prepared prompts, including warmup continuations.

GitOrigin-RevId: 40ce3c11383f48e08f52e7120b706c61a449df9c
2026-11-13 01:22:19 +00:00
Alex Kira 64b8d019c8 Record reasoning replay removal metrics (#61017)
## What changed

Parse reasoning removals from response `input_transformations` and carry the counts through completion events to sampling telemetry.

- Add `codex.responses.reasoning_replay` to distinguish unavailable reports, no reported removals, prefix mismatches, and other removals.
- Add `codex.responses.reasoning_items_removed` histograms by bounded removal reason, grouping unknown or missing reasons under `other`.
- Include zero counts for usable reports; exclude missing, null, or malformed reports from histograms without failing the response.
- Use the sampling step's session telemetry when recording response events.

## Testing

Add SSE and WebSocket integration coverage for report availability, removal counts, unknown reasons, zero observations, and `product_sku` tags in exported metrics.

GitOrigin-RevId: 83c70ca6067fa4b34bf5c463958b4632a7a0a188
2026-11-12 04:31:25 +00:00
Ruslan Nigmatullin cbd4944092 Preserve allocated response item IDs in requests (#60977)
## Why

Providers can echo a bare reserved prefix or return an opaque item ID. Request preparation previously stripped these IDs when they lacked an underscore prefix, even if they carried allocation metadata.

## What changed

- Keep response item IDs with allocation metadata when preparing requests.
- Add `ResponseItemId::with_generation_prefix` to attach a request reservation's allocation while preserving the exact wire ID and recording a matching item-kind prefix and provider suffix.

GitOrigin-RevId: 3249c2669aca11ee5facbd8a246016490a29a4f4
2026-11-12 02:43:37 +00:00
Charlie Marsh bc3ccba6e1 Fall back to HTTP immediately for oversized WebSocket requests (#60840)
## Why

A WebSocket close with code `1009` before any text arrives indicates that the request exceeds the peer's message size limit. Retrying the request over another WebSocket does not address that limit.

## What changed

- Classify these early size rejections as requiring HTTP fallback and switch transports without exhausting WebSocket retries, including during prewarming.
- Preserve ordinary stream retry behavior for size closes after any text frame and for other close codes.

## Testing

Add integration coverage for early size rejections during generation and prewarming, size closes after metadata, rate limits, or response creation, and ordinary closes.

GitOrigin-RevId: 4550d289bb414fec1faae2a195bcc635d394117b
2026-11-11 18:58:21 +00:00
Won Park 6bd17ba6ae Revalidate request auth ownership after budget checks (#60436)
## Why

Account changes during asynchronous request setup can invalidate the credentials selected for a generation request.

## What changed

- Restart HTTP request setup if the auth owner changes during the budget check.
- Validate the WebSocket connection's retained auth owner with `AuthOwner::is_current()` after budget checks.

## Testing

Add regression coverage for account switches during HTTP budget checks and external credential changes before WebSocket request setup, in both dual-header and assertion-only runtime auth modes.

GitOrigin-RevId: 7a1e1475a40aa2d34cd94f60f729ad697f3f7028
2026-11-09 19:50:14 +00:00
cooper-oai efdacaf46f Stop retrying terminal runtime authentication denials (#60096)
## Why

Invalid assertions and paused or revoked runtime instances cannot recover through request retries or credential refresh. Permanent refresh-token failures also need to retain their sign-in error instead of becoming retryable stream errors.

## What changed

- Recognize terminal runtime denial codes in `401` and `403` response bodies and identity error headers, preserving HTTP diagnostics while stopping retries.
- Skip credential recovery for runtime denials in runtime-enabled model providers and backend requests, while preserving recovery for ordinary credential expiration.
- Propagate permanent refresh-token failures through runtime authentication as `RefreshTokenFailed` errors.

## Testing

Add coverage for body and header denials, preserved HTTP diagnostics, provider-scoped credential recovery, and cached permanent refresh failures. Complete-turn tests verify that runtime denials stop without retries or refreshes while expired credentials recover in both runtime authentication modes.

GitOrigin-RevId: 33f6f707454130e97e13f3b53e29d2c484602152
2026-11-07 09:48:46 +00:00
rhan-oai c4f0e09912 Allow asynchronous model request budget checks (#60080)
## What changed

Make `ModelRequestContributor::budget_exhausted` return an `ExtensionFuture` and await budget checks before HTTP and WebSocket generation. WebSocket warmup continues to skip budget checks.

If the account changes during the post-connect budget check, rebuild the request setup and reconnect before sending the WebSocket request.

## Testing

Update tests to cover a pending budget check that resolves to exhaustion, warmup connection reuse, and an account switch while the post-connect budget check is awaiting completion.

GitOrigin-RevId: 462c74b86a46a4b2276f901c69187fc7cbc3ff81
2026-11-07 07:45:36 +00:00
cooper-oai d4a341bd52 Reauthenticate runtime requests before reusing WebSocket access (#60055)
## Why

An open WebSocket can remain usable after its runtime is paused. Runtime-authenticated requests need a fresh handshake to revalidate access before submitting more work.

## What changed

- Reconnect before each runtime-authenticated Responses request and skip speculative preconnection. Preserve turn routing when the runtime identity is unchanged.
- Open a fresh connection for each runtime-authenticated Guardian classification instead of prewarming or reusing pooled sockets.
- Preserve HTTP fallback for unsupported upgrades and connection failures, while propagating authentication, authorization, rate-limit, and policy errors.

## Testing

Add regression coverage for pause and unpause behavior, credential changes, fresh assertions, and Guardian HTTP and WebSocket transports in both runtime authentication modes.

GitOrigin-RevId: 9f650147260da5cbbf5bb23dfff0af095fff3955
2026-11-07 04:06:26 +00:00
cooper-oai 44f1b0e867 Apply runtime authentication to realtime connections (#60003)
## Why

Realtime connections bypassed runtime authentication and reused captured authentication headers for sideband handshakes. They need to honor the selected credential source and its transport policy across call creation, retries, and reconnects.

## What changed

- Use runtime authentication for realtime WebSocket connections, WebRTC call creation, and sideband attachment when enabled for supported OpenAI destinations.
- Resolve authentication on every WebSocket handshake, preserving credential ownership and request scope while generating fresh assertions. Reject authentication failures without falling back to bearer authentication.
- Keep call creation and sideband attachment bound to the selected credentials and account network policy, including when inference uses a different provider.
- Avoid runtime initialization for local marketplace and MCP operations, plugin commands that do not use the remote catalog, and model debugging with a configured catalog.

## Testing

Add coverage for fresh handshake credentials on retries and reconnects, credential and account changes, runtime authentication modes, destination validation, and registration failures.

GitOrigin-RevId: 57e53122912fa78a524427b0f51013f76f9f7681
2026-11-06 22:27:23 +00:00
cooper-oai faeb379646 Bind runtime auth to the provider's selected credential source (#59823)
## Why

Runtime authentication must use the credential selected by the model provider. Explicit API keys and command credentials need independent ownership so cached connections and in-flight work cannot cross credential sources.

## What changed

- Register and reuse runtimes per credential source, supporting explicit provider keys and command credentials without falling back to saved login credentials.
- Track `AuthOwner` by credential manager and owner generation across WebSocket state, compaction, and scoring.
- Preserve cached identity and runtime registration state during credential-source outages or failed storage reloads. Require a successful auth reload before logout revokes credentials.
- Reject requests whose production or staging environment differs from runtime registration, including model catalog requests.

## Testing

Add regression coverage for credential selection and runtime reuse, owner isolation, source outages, failed reloads and logout recovery, and environment mismatches.

GitOrigin-RevId: 7bab55e0ea502593393df10046309fd8502edbd0
2026-11-06 04:33:14 +00:00
rhan-oai 1031a7b9aa Check extension budgets before model generation requests (#59794)
## What changed

Add a default `ModelRequestContributor::budget_exhausted` hook and fail generation with `SessionBudgetExceeded` when any contributor reports an exhausted budget for the thread.

Check budgets before HTTP requests and before WebSocket connection setup, then check again after the connection is established. WebSocket warmup remains available when the budget is exhausted.

## Testing

Add coverage for budget changes during a tool call, verifying that exhaustion prevents the next model request while an available budget allows completion. Extend WebSocket coverage to verify that exhausted generation opens no connection and warmup still permits connection reuse once the budget becomes available.

GitOrigin-RevId: 97ce02dc7f9bd54830e4b73c4f0334a30367eebf
2026-11-06 02:31:54 +00:00
Charlie Marsh 74417e9c6b Reuse decoded WebSocket event kinds in telemetry (#59769)
## Why

WebSocket telemetry reparses text frames to extract event kinds that the transport already decodes.

## What changed

Pass decoded event kinds to telemetry and report receive failures separately. Keep JSON parsing for timing metrics and as a fallback when stream event decoding fails. Remove the `tokio-tungstenite` dependency from `codex-otel` and restrict it to tests in `codex-core`.

Limit wrapped error parsing to error events or failed stream decoding, preserving HTTP error forwarding when unrelated stream fields are malformed.

## Testing

Update runtime summary coverage to include receive failures and extend the WebSocket error forwarding test with a malformed stream field.

GitOrigin-RevId: e1f9d200fd6d30ec124a2354bdbc01f3082ddde3
2026-11-06 00:24:03 +00:00
jamy-OAI b313cca1cf Enforce host-required cyber access programs per thread (#59754)
## What changed

- Expose `RequiredCyberAccessPrograms` so hosts can require an explicit allowed program on a thread. Snapshot the requirement before extension callbacks; hosts must reapply it on cold resume.
- Validate resolved `access_programs` before HTTP and WebSocket model requests, rejecting omitted or disallowed programs. Explicit `Standard` remains distinct from omission. Reject memory summarization and realtime requests when a requirement is present.
- Keep required programs scoped to the parent thread by preventing Guardian reviewers from inheriting its program, including Guardian v2 reviews.

## Testing

Add HTTP and WebSocket coverage for allowed programs, omission, disallowed programs, unsupported providers, and connection reuse. Extend Guardian tests to verify parent-only program scope and that removing the public attachment does not erase the startup snapshot.

GitOrigin-RevId: 9306a9af0e03e7a1728dfeb610cd7ec7517367fd
2026-11-05 22:49:46 +00:00
Rohan Mehta 41cbd5b9b2 Add per-turn prompt cache TTL options (#59480)
## What changed

- Expose `PromptCacheTtl` through `TurnStartOptions` and `RecoverTurnRequest`, supporting `30m` and `12h` minimum cache lifetimes.
- Carry the selected TTL through turn execution and compaction into `prompt_cache_options.ttl` on Responses HTTP and WebSocket requests. Omit the field when unset and keep the selection scoped to the turn.
- Include prompt cache options in WebSocket request reuse checks.

## Testing

Add coverage for both TTL values and omission on a subsequent turn without an override, and extend WebSocket serialization coverage to include prompt cache options.

GitOrigin-RevId: 8529306e6ad6030fe77c5e6bf19f3810717c0c5e
2026-11-04 19:58:24 +00:00
Ruslan Nigmatullin d84c872464 Route response item IDs through a shared generator (#59312)
## What changed

Introduce `ItemIdGenerator` and pass the runtime-owned generator through sessions, model clients, history, hooks, tool outputs, and memory requests. Keep UUIDv7 generation as the default and replace direct calls to `ResponseItemId::new` with the shared callable.

Preserve existing item IDs and backfill missing or empty IDs through the same generator, including forked history before reconstruction and persistence.

## Testing

Extend coverage for UUIDv7 IDs on user messages, agent messages, and additional tools, and assert that forked model context matches the backfilled items persisted to history.

GitOrigin-RevId: 0dd9ccf0f46f0f1005a6acfc740133b03ce82259
2026-11-04 04:02:00 +00:00
cooper-oai 079e17a422 Wire shared runtime authentication through threads and API clients (#59177)
## What changed

- Share a lazily registered runtime across threads, model discovery, and extension clients when `runtime_agent_instances` is enabled, while honoring each thread's authentication mode and credential owner.
- Bind model catalogs to the effective provider and authentication context while preserving cache policy and live API-key discovery settings.
- Resolve credentials, routing, and transport policy together for each request. Preserve proxy and TLS settings, validate runtime account selectors, and prevent pooled connections from crossing runtime identities.
- Accept supported ChatGPT subdomains when selecting the registration environment.

## Testing

Add integration coverage for shared runtime registration, dual-header and assertion-only modes, disabled and third-party providers, credential replacement, subagents, and delegated review. Add coverage for catalog cache policy and runtime-aware connection reuse.

GitOrigin-RevId: 99dd9d987c29c93597a648f6586f98ac6a932c3c
2026-11-03 15:02:57 +00:00
Ben Romano dec38fc9bb Add WebSocket connection metrics with reauthentication labels (#59018)
## What changed

- Record connection attempts and durations as `codex.websocket.connect` and `codex.websocket.connect.duration_ms`, labeled with `success`, `reauth`, and the configured `product_sku` when present.
- Detect reauthentication by comparing the current auth revision with the last successful connection, preserving that revision across connection resets. Include `auth.reauth` in connection logs and traces.
- Populate session telemetry with the configured product SKU.

## Testing

Extend tests to check reauthentication labels after account switches, product SKU labels for restored sessions, and failed-handshake counts, durations, and labels.

GitOrigin-RevId: 53a38b4460ab9021058dfe2fe104d0441993b18a
2026-11-03 00:59:43 +00:00
Charlie Marsh 4460449921 Keep HTTP fallback active for the rest of the session (#58989)
## What changed

Once Responses requests fall back to HTTP after exhausting WebSocket retries or receiving HTTP 426, keep subsequent requests and turns on HTTP for the remainder of the session. Clear cached WebSocket state and remove background recovery probes, recovery trials, and their acknowledgement timeout.

## Testing

Update fallback tests to verify that a second turn stays on HTTP without additional WebSocket attempts. Adjust retry and `Retry-After` request-count assertions to exclude background probes.

GitOrigin-RevId: a4f6376604527c14db8d60f79bd21c3aaf289f70
2026-11-02 21:37:17 +00:00
Charlie Marsh 0a2dda4b5e Recover WebSocket transport after transient HTTP fallback (#58950)
## Why

A transient WebSocket failure previously kept the session on HTTP for its remaining lifetime, even if WebSocket connectivity recovered.

## What changed

- Probe WebSocket connectivity in the background during HTTP fallback, allowing a subsequent request to use a ready connection without delaying HTTP requests.
- Verify recovery with a real request and bound its first-response wait to five seconds. Keep HTTP 426 responses and recovery timeouts on HTTP for the rest of the session.
- Keep retries of an HTTP request on HTTP. If a recovered connection fails before output, replay the request over HTTP without consuming its ordinary retry budget; failures after output use normal retry accounting.
- Rate-limit recovery probes and honor `Retry-After` deadlines.

## Testing

Extend integration coverage for successful recovery within a turn, disconnects before and after output, full-context replay followed by incremental WebSocket requests, persistent HTTP 426 fallback, and retry deadlines.

GitOrigin-RevId: 1c139a4bbce1a67442db5622fd70ff0cc8056c9c
2026-11-02 19:02:50 +00:00
cassirer-openai 7656a23b8d Preserve incomplete response output in failed inference traces (#58456)
## Why

When a response fails with incomplete output, attempted tool calls can appear only in the terminal response payload. Failed inference traces previously omitted those items, losing evidence of the attempted call.

## What changed

Retain output items marked `incomplete` on `ResponseIncompleteError` and include recognized items in failed inference traces, deduplicating by item ID. Keep these items out of streamed output, tool dispatch, and the continuation cache, and omit their payloads from the error's debug representation.

## Testing

Add tests for retaining only incomplete output from terminal responses and recording attempted calls in failed traces without streaming them or creating tool calls. Cover unknown response item types being skipped.

GitOrigin-RevId: 594f6a37a5af543694f19fcffe0c164cb2addb36
2026-10-30 23:55:47 +00:00
sgarg-oai 53d3d7f64e Centralize provider request preparation auth checks (#58121)
## What changed

Move the model client's request-preparation loop into the shared `prepare_provider_request` helper and add `RequestAuthChange` to classify auth state changes. For managed auth, retry preparation when credentials change and reject account changes, including when the provider starts or stops exposing an auth manager during setup.

Capture the auth owner and credential generations together and pass them into the preparation callback so the resulting client setup records the state used for that attempt.

## Testing

Add a test verifying that an explicit provider bearer token survives a workspace switch during setup without retrying preparation.

GitOrigin-RevId: ed8710d1c344b48ebf6182e25e6269214dd2d3fe
2026-10-29 16:39:38 +00:00
jif e742db9f7b Preserve parent routing affinity for Guardian reviews (#57710)
## Why

Shared routing cookies can change after a parent connection is established. Guardian reviews need the routing affinity captured with their parent response so unrelated traffic does not replace that hint.

## What changed

- Capture `__oailb` and `__cflb` cookies from successful ChatGPT WebSocket handshakes and pair them with the parent response ID.
- Retain the snapshot throughout a review and its retries, and apply it only to Guardian requests with the matching parent response. Reconnect cached reviewer sockets when the parent affinity changes.
- Preserve cookie expiry and restrict reuse to the original secure origin and endpoint path. Replace routing cookies while retaining unrelated cookies, and keep the captured affinity out of prompts, history, and serialized metadata.

## Testing

Add coverage for cookie scope, expiry, duplicate rejection, and merging; replaying a captured pin after shared cookies change or are deleted; and retaining the matching parent snapshot through compaction without exposing cookies in review prompts or metadata.

GitOrigin-RevId: d180679e6265b612a3617f20ca1f5dec89e73aa8
2026-10-28 11:48:00 +00:00
cooper-oai 9cce575134 Share runtime authentication with model providers and catalogs (#57607)
## Why

Model catalog refreshes need to use the same registered actor and credential owner as model requests when runtime authentication is enabled.

## What changed

- Add `ProviderAuthContext` to carry credentials and optional runtime authentication into model providers and catalog clients.
- Select runtime authentication independently for inference and catalog destinations. Reject unsupported OpenAI origins while preserving provider authentication for other destinations.
- Include API organization and project selectors in runtime registration. Reuse registered runtimes across projects within an organization and replace them when the organization changes.
- Preserve transport restrictions and account bindings, and strip sensitive headers on cross-origin redirects.
- Apply the catalog timeout to authentication and fetching while allowing credential refresh and registration to finish safely.

## Testing

Add coverage for runtime-authenticated catalogs, provider isolation, resource selection, gateway authentication, cross-origin redirects, and timeout recovery that preserves registration and refreshed tokens.

GitOrigin-RevId: c14f1a02159031ea0af1f9b26ea890f8dca7d6ad
2026-10-28 00:51:29 +00:00
Brent Traut d93071fae8 Avoid retaining unneeded output items in HTTP response streams (#57563)
## Why

HTTP response streams retained copies of completed output items even when inference tracing was disabled, keeping their payloads alive until the response completed.

## What changed

Collect completed output items only when inference tracing or WebSocket last-response bookkeeping needs them. Make the last-response sender optional and create its channel only for WebSocket requests.

## Testing

Add a regression test that verifies an untraced HTTP stream releases a completed item's shared payload after delivery, while the response remains open. Update existing tracing and WebSocket bookkeeping tests for the optional sender.

GitOrigin-RevId: 7695534c6d00f3002005324c43c23bf733f01804
2026-10-27 20:42:47 +00:00
jif e1dd7ed1ba Preserve Guardian request metadata with custom OpenAI base URLs (#57439)
## Why

Custom OpenAI base URLs caused Codex backend authentication to lose Responses headers and Guardian metadata when the URL did not match a recognized backend route.

## What changed

Apply model-scoped Responses headers, Guardian reviewer and classifier markers, and eligible ChatGPT parent credit requests based on the OpenAI provider and authentication configuration, regardless of the base URL. Keep API-key requests and other providers excluded from this behavior.

## Testing

Extend coverage for custom `/v1` URLs and direct `/api/codex` endpoints with ChatGPT, header-based, and API-key authentication, including HTTP fallback and WebSocket requests.

GitOrigin-RevId: cc4bb5b4a1a6596904ecf8965237c7a4f09e112b
2026-10-27 12:17:14 +00:00
cooper-oai cf29971d93 Integrate runtime authentication into model requests (#57171)
## What changed

- Add opt-in runtime authentication through `ModelClient::with_runtime_auth`, requiring the provider and runtime manager to share the selected OpenAI credentials.
- Keep runtime identity, credentials, routing, and transport selection consistent for each request and its retries, signing a fresh assertion for each attempt.
- Apply authentication asynchronously to WebSocket handshakes, replace stale authentication headers, and reconnect when the runtime changes.
- Reject account, organization, or project selectors that conflict with the registered runtime, and preserve gateway OAuth composition.

## Testing

Add coverage for dual-header and assertion-only authentication, HTTP retries, runtime replacement and account switches, stale WebSocket headers, selector mismatches, gateway OAuth failures, transport revocation, and Realtime compatibility.

GitOrigin-RevId: 45b9efc2c80481406a0f6f6396a8cdd21d933c12
2026-10-26 18:06:07 +00:00
cassirer-openai 5b792948f9 Track accepted conversation history in rollout traces (#56312)
## Why

Model output alone does not establish that an item entered conversation history. Treating every response item as accepted can include discarded attempts, while relying on a later request misses accepted final output when a turn ends or is interrupted.

## What changed

- Record `HistoryItemAccepted` events and retain Responses item IDs, generating missing IDs consistently across item events.
- Build thread conversation history from request inputs, compaction checkpoints, and explicit acceptance. Keep unaccepted output accessible through its inference call.
- Preserve inference provenance across retries and late response records without overwriting newer request or compaction snapshots.
- Mark turns with errors as failed. Bump trace schemas to version 2 and reject incompatible bundles and event schemas during replay.

## Testing

Add reducer coverage for discarded attempts with identical text, late responses, compaction, inherited context, and legacy bundle rejection. Add CLI integration tests that run `debug trace-reduce` after success, stream failure, and interruption followed by shutdown, including responses without provider item IDs.

GitOrigin-RevId: 8e387a91d9b3f704df82847d630e6f0b08f998b3
2026-10-23 00:45:20 +00:00
Celia Chen 3fd148a20c Add a built-in Google Cloud Vertex AI provider (#56265)
## What changed

- Support `model_provider = "gcp"` with a Vertex AI endpoint derived from `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION`, defaulting to the `global` location.
- Obtain credentials through `gcloud auth application-default print-access-token` by default, and allow `base_url`, `auth`, and `http_headers` overrides under `model_providers.gcp`.
- Use a static model catalog tailored to Vertex AI, preserve function tools, namespaces, and client-side tool search, and support remote compaction V2. Disable unsupported reasoning summaries, Responses Lite, custom tools, web search, and image generation.
- Expose a `gcp` account type through the app-server protocol and generated clients without resolving credentials during account reads or requiring OpenAI authentication.

## Testing

Add coverage for endpoint resolution, configuration overrides, model catalog filtering, authenticated requests, unsupported request fields, missing credentials, account reporting across provider changes, and automatic remote compaction.

GitOrigin-RevId: 97a3158269e6dbc2605e2cf576998e09817ea12a
2026-10-22 21:01:14 +00:00
cooper-oai f29d55ff06 Propagate authentication header failures before sending requests (#55607)
## Why

Synchronous auth header construction could silently return no credentials when managed authentication became unavailable. Callers need an error to avoid sending requests with missing or partial authentication.

## What changed

- Make `AuthProvider::add_auth_headers`, `to_auth_headers`, and auth header telemetry fallible, and propagate failures through request and WebSocket setup.
- Return a transient error when managed authentication is unavailable, and preserve network policy denials through auth error conversion.
- Retry transient MCP authentication errors while treating build errors and policy denials as terminal.
- Cancel local MCP event streams before resolving authentication so cleanup still works when credentials become unavailable.

## Testing

Add regression coverage for rejected partial authentication, async header resolution, terminal auth errors without sending requests, managed account changes, MCP retry classification, and local stream cancellation after authentication becomes unavailable.

GitOrigin-RevId: 39d981e232cba1e302de502a2fa6239101114ed1
2026-10-20 15:43:19 +00:00
Rohan Mehta ab6095dde0 Allow callers to control prompt cache keys independently of session IDs (#55587)
## What changed

Expose `PromptCacheKey` through `StartThreadOptions` with three policies: retain the default session-derived key, send a custom key, or omit `prompt_cache_key` from model requests. Keep session identity headers independent of this policy.

Propagate the policy to child agents, delegated sessions, and guardian review sessions. Hosts must reapply the policy when resuming a thread from storage.

## Testing

Add coverage for all three policies across turns, including unchanged session and thread headers. Extend subagent coverage to verify inheritance of the default and omitted-key policies.

GitOrigin-RevId: f9e8ab31fcf568636f9712726760e4e9a4672428
2026-10-20 14:14:59 +00:00
felixxia-oai 7c073196a1 Keep only the latest adjacent reasoning effort update in requests (#55293)
## Why

Turn recovery and retries after a server overload can leave consecutive reasoning effort updates in history when settings change without an intervening message. Requests should use the latest update in each consecutive run.

## What changed

Coalesce adjacent `configuration_update` items when building Responses requests with reasoning effort overrides enabled, retaining the latest update. Preserve saved history and updates separated by other input items.

## Testing

Extend integration coverage for recovery with unchanged or changed effort, retries after a server overload, and WebSocket continuation and replay after coalescing. Verify that requests retain the latest adjacent update while saved history keeps all updates.

GitOrigin-RevId: bcf97db4c93dac5f466bd276176ac9d238329ecd
2026-10-19 14:34:11 +00:00
ioanbudea-OAI 99f617bf74 Bucket admitted Guardian request metrics by input size (#55226)
## Why

Guardian request counts grouped by input size should reflect admitted sampling inputs without counting synchronous transport retries more than once.

## What changed

- Add a shared `token_bucket` label to admitted total-input observations in `codex.guardian.context.request_tokens` for synchronous and asynchronous reviews. Use inclusive upper bounds in 20k-token steps through 240k, followed by 256k and overflow buckets.
- Record synchronous request tokens after budget admission, once per sampling step, including the complete input. A fresh step counts again even when its input is identical.
- Preserve asynchronous component histograms for oversized classifications, but omit `token_bucket` so rejected inputs do not contribute to counts grouped by that label.

## Testing

Add coverage for bucket boundaries, synchronous retry deduplication and budget rejection, asynchronous retained-history reuse and reset, and admitted versus oversized classification metrics.

GitOrigin-RevId: fac2f102a4c48c5fd21d56bfa701b95a1ff852d0
2026-10-19 09:03:12 +00:00
Charlie Marsh 1cc7dc8f2a Share additional tool declarations across response item clones (#54945)
## Why

Cloning `ResponseItem::AdditionalTools` deep-copies its tool declarations for history and request copies.

## What changed

Store `tools` in an `Arc<[serde_json::Value]>` so clones share immutable declarations. Update constructors and existing test fixtures to use the shared representation.

GitOrigin-RevId: eb8831774afb45fe8431a796f34ae9d1243e884a
2026-10-17 23:17:51 +00:00
tongzhou wang 1b6e0d8145 Track content provenance through prompt assembly and compaction (#53831)
## Why

Message roles and content classifications do not identify who supplied each context part. Source attribution needs to survive prompt assembly and history truncation, including messages that combine text from different producers.

## What changed

- Add per-part `ContentItemMetadata` for user input, developer instructions, `AGENTS.md`, skills, harness context, command hooks, and tool context with optional callable namespaces.
- Carry attribution alongside content and classifications through contextual fragments, extension prompts, hook output, and agent messages. Keep tool-provided context-window hints separate from harness text.
- Preserve the source of retained text slices during compaction and attribute generated truncation notices to the harness. Default missing historical attribution to unknown.
- Attribute host MCP calls using cached tool namespaces only when catalog revisions remain stable, without starting servers or refreshing catalogs for attribution.
- Send the new metadata to Responses Lite and strip it from requests to endpoints that do not support it.

## Testing

Extend compaction tests to cover mixed sources, missing or extra metadata entries, and discarded media. Update Responses Lite request assertions to verify endpoint-specific attribution handling.

GitOrigin-RevId: b0ebc929b7c60f3ec49d1affbf897312d63edcc8
2026-10-14 02:01:49 +00:00
rka-oai 9e03960cf8 Wire background compaction into the turn lifecycle (#53800)
## What changed

- Launch background compaction at eligible pre-turn, mid-turn, and post-turn checkpoints when `AsyncCompaction` is enabled, capturing the current world state and client routing state.
- Adopt ready results at compaction checkpoints while preserving newer messages, tool outputs, and world-state updates. Continue normally if an optional result is rejected.
- Run one foreground compaction if an adopted result still exceeds the context limit.
- Prevent cancelled turns from launching new background work while preserving already-running work for later reuse.

## Testing

Add unit and scenario coverage for stale history and account changes, cancellation, pending-result reuse and fallback, retained tool outputs, compaction event pairing, and token usage accounting. Add a context snapshot covering a collaboration-mode change while compaction runs.

GitOrigin-RevId: 04ac028d9fe2e3ea64aacaaeb351c3c776cf3940
2026-10-13 23:51:47 +00:00
rka-oai be5296d467 Prepare compaction helpers for background requests (#53606)
## What changed

- Extract an HTTP Responses executor that can run without owning a turn's WebSocket state, with optional authentication-owner checks.
- Add cancellation-aware compaction output collection that records background token usage against the rollout budget.
- Support installing a compacted history prefix while preserving later history items and placing initial context around real user or agent messages.
- Allow callers to supply a context window for history trimming and a captured window for compaction request metadata.

GitOrigin-RevId: 29f3ca0ae8841f295058feb207e3a225af9a1487
2026-10-13 08:13:34 +00:00
pakrym-oai 5ef96ab278 Add opt-in output token replay for OpenAI requests (#52742)
## What changed

- Add the disabled-by-default `output_token_replay` feature to request `output.encrypted_content` from OpenAI providers.
- Preserve encrypted message and tool-call output, message and function-call status, and output-text `annotations` and `logprobs` through history and replay. Update the generated protocol schemas and SDK types.
- Strip output ciphertext from requests to other providers while retaining it in stored history, including after replay is disabled. Remove encrypted content from memory extraction inputs.

## Testing

Add integration coverage for the feature/provider combinations, metadata replay across follow-up requests, and history preservation when resuming with replay disabled.

GitOrigin-RevId: 77729a021b6771933402aebe74ece8eb39c057e2
2026-10-10 01:25:00 +00:00
Adam Perry @ OpenAI 806d2d1cc1 Remove per-content source attribution metadata (#52329)
## What changed

- Remove `ContentItemMetadata`, provenance and namespace types, and the `content_item_metadata` protocol field while retaining `content_item_kinds` classifications.
- Simplify context fragments, extension contributions, and hook output to carry content without source attribution. Return MCP tool results directly without an attribution wrapper.
- Render context-window hints together in a single text fragment.

## Testing

Update Responses and Responses Lite request assertions to expect content-kind classifications without per-content attribution, and adapt context, hook, and extension tests to the simplified types.

GitOrigin-RevId: 201894cd4c93c6d4b4c41c845e7a9af1dd3c95ca
2026-10-08 23:57:36 +00:00
tongzhou wang ad54b75574 Track source attribution for individual context parts (#52195)
## What changed

- Add `ContentItemMetadata` to distinguish user input, developer instructions, `AGENTS.md`, skills, harness context, and tool-supplied context independently of message role and content classification.
- Keep attribution attached to content through prompt assembly, history processing, and hook-output spilling. Distinguish command hooks from MCP hooks and retain tool namespaces when known.
- Treat missing historical attribution as unknown and send per-content metadata only to Responses Lite.

## Testing

Update request and history assertions to cover attribution persistence and Responses Lite metadata handling.

GitOrigin-RevId: 24e56005f5bdb98bf82f2b3943f29c4c81f3d587
2026-10-08 17:56:54 +00:00
pakrym-oai fac5d0ba91 Report specific reasons for WebSocket continuation failures (#51895)
## Why

Full WebSocket requests previously used the generic `other` reason when continuation failed because request properties or input changed, obscuring why incremental reuse was unavailable.

## What changed

- Report specific reasons for changed request properties, shortened or mismatched input, and missing response state or response IDs.
- Add `previous_item_type` and `current_item_type` labels to continuation metrics and failure traces. Diagnostics use bounded labels without request contents or identifiers.
- Centralize response item type names in `ResponseItem::item_type()` and reuse them for output logging.

## Testing

Add coverage for unavailable response state and empty response IDs. Expand WebSocket tests to check fallback reasons and item types for rewritten or shortened input, replaced input, changed model, and changed output schema, including precedence when multiple properties change.

GitOrigin-RevId: 3951853dfe87d40b7046af6f6a8efd5d4f5b06d1
2026-10-08 01:02:21 +00:00
pakrym-oai c9253c4977 Send base instructions as Responses input messages (#51156)
## What changed

Move base instructions from the top-level `instructions` field into a prefixed `developer` message in `input` for standard Responses requests, matching Responses Lite. Remove the field from HTTP and WebSocket request types and assign instruction messages stable IDs derived from the thread and instruction text.

## Testing

Extend standard and Responses Lite tests to cover instruction message serialization, stable IDs, and resume consistency. Update WebSocket tests to verify that changed instructions trigger a full request without `previous_response_id`.

GitOrigin-RevId: e2de4b8e30a9339377fac133ceda981abd1a112b
2026-10-05 18:52:51 +00:00
Ahmed Ibrahim 4ad985e2ca Track inference tool changes in turn analytics (#50964)
## What changed

Add `tools_change_count` to turn profiles and turn analytics events. Compare the full model-visible tool list before each sampling request, retaining the previous list across turns and connection resets. The first list establishes a baseline; subsequent changes increment the current turn's count.

## Testing

Add coverage for schema changes, tool additions, ordering changes, empty lists, and tracking across sessions and transport fallback. Extend the turn event serialization test to include `tools_change_count`.

GitOrigin-RevId: 44a15c42dc7d0b35c166666faeb9627b718b33dd
2026-10-04 21:19:05 +00:00
pakrym-oai 6326163b9a Send incremental tool catalog updates in Responses Lite (#50540)
## What changed

When `IncrementalTools` is enabled for Responses Lite, track tool definitions in world state and conversation history. Send the initial catalog once, then append only added or changed definitions while preserving earlier request history. Emit developer notices for removed tools and namespace instruction changes.

Use history-supplied definitions for normal requests and remote compaction, and omit empty `additional_tools` prefixes. Keep the existing tool delivery behavior for the Responses API and when the feature is disabled.

## Testing

Add unit and snapshot coverage for catalog and namespace transitions, empty catalogs, and stable hashing across JSON object key order. Add a request-history scenario covering unchanged tools, a model switch that changes one definition, persisted catalog hashes, and Responses API behavior.

GitOrigin-RevId: 76bde175973b81f8ad23873919da3c8ddcdf6065
2026-10-03 05:59:07 +00:00
Celia Chen 604061ce51 Enable Ultrafast service tiers for Amazon Bedrock Astra models (#50472)
## Why

Bedrock catalogs cleared all service-tier metadata, and requests omitted every selected tier. This prevented users from selecting `ultrafast` or using tiers defined in custom catalogs.

## What changed

- Advertise `ultrafast` for `openai.gpt-6-astra` on Mantle and the `global.openai.gpt-6-astra` and `us.openai.gpt-6-astra` Runtime variants, while retaining the implicit default tier unless users select otherwise.
- Preserve custom catalog speed tiers, service-tier definitions, and defaults while continuing to normalize Bedrock web search compatibility.
- Send selected service tiers only when the Bedrock model advertises them, including `flex`.

## Testing

Add coverage for `model/list` tier discovery, custom catalog preservation, configured and per-turn HTTP request tiers, and TUI slash-command selection, toggling, and model switching.

GitOrigin-RevId: 4793e7af7b9f604a6b7812611030da6adb8acd35
2026-10-03 00:31:51 +00:00
pakrym-oai fd75aa116c Remove the provider capability gate for tool namespaces (#50447)
## What changed

- Remove `namespace_tools` from `ProviderCapabilities` and `namespaceTools` from `ModelProviderCapabilitiesReadResponse`, updating generated schemas and SDK types.
- Preserve tool namespaces and configured collaboration tool namespaces without a provider capability check, and always use Responses Lite tool serialization for Responses Lite requests.
- Gate tool search on `supports_search_tool` and retain the existing image generation and web search checks without requiring a namespace capability.

GitOrigin-RevId: ae1843563736765a40e03a02c41ff5e470018a93
2026-10-02 22:55:08 +00:00