Commit Graph
6530 Commits
Author SHA1 Message Date
jif 9d8ca1df71 Preserve queued agent messages when a parent turn is interrupted (#62348)
## Why

A parent turn can acknowledge a child agent's final reply while a model
request is in flight. If the parent is interrupted before consuming the
queued reply, turn cleanup can discard it.

## What changed

Record queued agent messages in conversation history during interruption
and flush the rollout before emitting `TurnAborted`, even when the
interruption marker is disabled.

## Testing

Add a regression test that interrupts a parent while a child's final
reply is queued. The test checks that the reply is persisted when
`TurnAborted` arrives and appears exactly once in the next model request.

GitOrigin-RevId: 5bd828c4101942fa4fe7ba5040355a8244f02018
2026-11-18 19:39:41 +00:00
Dylan Hurd c695d267e3 Box the config reload future for persistent MCP tool approvals (#62337)
## Why

The MCP tool call future reserves space for the large config reload
future even on ordinary calls that never reload configuration.

## What changed

Pin the reload future on the heap after successfully persisting a tool
approval. Ordinary MCP calls no longer carry the inline storage for it.

GitOrigin-RevId: a883f7619f520e730dda139d967c6a0f945b5df2
2026-11-18 19:00:47 +00:00
Alex Chang cc7a62e19c Report API spend limit errors by scope (#62329)
## Why

Generic quota errors hide whether the project or organization spend limit
blocked a request. Reporting the scope tells users which limit to check.

## What changed

Recognize API key, project, and organization spend limit errors across
HTTP, SSE, and WebSocket responses. Show a message that names the scope and
treat the error as non-retryable, even when the provider sends
`Retry-After`. Apply the existing usage-limit handling to goals and
compaction.

Expose distinct `CodexErrorInfo` values in the app-server protocol and
generated bindings so clients can identify the limit in live errors and
failed turn history.

## Testing

Extend the transport tests to cover all three scopes and verify that they
stop retries. Extend the app-server test to check that the error survives
`thread/read` and that a subsequent turn can succeed in the same thread.

GitOrigin-RevId: 03341f7a78daa7540e7baa519f1a29ec07e34509
2026-11-18 18:11:54 +00:00
bkotsopoulos 0ba514837d Measure plugin recommendation latency during initial context setup (#62326)
Record how long initial context assembly waits for prompt-only plugin
recommendations in `codex.initial_context.plugin_recommendations_wait_ms`.
Use named info-level spans for loading recommendations, reading the
tooling change marker, and fetching the recommendation catalog.

GitOrigin-RevId: 67b26f79252f8cba6e770f43df252ec1d73a569f
2026-11-18 17:57:12 +00:00
richardopenai c1ed51ca2c Accept inbound Noise connections in remote exec-server (#62325)
## Why

Remote Noise executors previously connected outbound to a rendezvous relay. An inbound listener lets harnesses that can reach the executor connect directly while retaining registry-backed authorization.

## What changed

Use `--listen ws://IP:PORT` with `--remote` in Noise mode to accept inbound WebSockets. The listener serves RPCs over encrypted Noise streams after the registry authorizes the harness. It limits concurrent connections and handshake attempts, closes sockets that miss the first authorization deadline, and drains connections on shutdown.

Noise clients can attach optional admission headers from the connection bundle to `wss://` requests.

## Testing

The inbound integration test exercises a registry-authorized file read, rejection of a registry-denied harness, the absence of a plaintext RPC response, and connection closure on shutdown. Unit tests cover handshake limits and rejection of admission headers before dialing a plaintext WebSocket.

GitOrigin-RevId: b388672e49a3fe806e38f6db38825435ba25d27a
2026-11-18 17:55:49 +00:00
viyatb-oai 6257fbc4bd Move sandbox preparation into platform backends (#62317)
## What changed

Have `SandboxManager` handle backend selection and shared preparation, then
delegate command wrapping and session setup to the Linux, macOS Seatbelt,
Windows token, and Windows MXC backends.

Centralize Windows managed proxy routing in `codex-sandboxing` so the exec
server and other callers use the same rule for selecting dedicated MXC
listeners.

GitOrigin-RevId: a75886809aefebf6c267bb39dbc104f76bda3409
2026-11-18 17:09:03 +00:00
rhan-oai daa59ebd29 Keep authorization evidence local to agent forks (#62314)
## Why

A prepared agent fork needs its ancestor's conversation for context.
Treating that conversation as the child's own authorization evidence
can attribute the ancestor's messages and approvals to the child.

## What changed

Allow host-started prepared forks that reference stored history to
inherit the root session ID. Keep ancestor messages as conversation
context and exclude ancestor authorization evidence when starting or
resuming the fork and when reconstructing sender evidence from storage.
Preserve the inherited disabled-plugin settings and the child's own
authorization evidence.

## Testing

Cover prepared forks across startup and resume, including inherited
context, plugin settings, and child-local authorization. Verify that
live and stored sender evidence both contain only the child's messages.

GitOrigin-RevId: 5c5a6547d31fe78dfad3742efb8a41df539173c6
2026-11-18 16:37:03 +00:00
felixxia-oai 924a48835d Use attached Guardian reviewers for synchronous approvals (#62309)
## Why

An attached reviewer needs to catch up on evidence before issuing a verdict. If the approval context changes during that preparation, the first verdict must still be checked against the authorization captured before preparation began.

## What changed

Bind the attached reviewer to the pending action and reserve a review session after evidence preparation. Submit the action and its permissions for a synchronous verdict, checking authorization before and after the verdict. Retries reserve a new session under the original review deadline.

## Testing

Extend the review tests to check that preparation and verdict execution share a deadline. Cover when optional synchronous review falls back to user approval after local input exhaustion and when context-limit or server failures result in denial.

GitOrigin-RevId: 0ea835ba897069d19d045605d97b58f47406a4b4
2026-11-18 16:17:57 +00:00
felixxia-oai 665b147afd Extract Guardian verdict execution and pending-action context (#62308)
## What changed

- Extract synchronous verdict execution into the Guardian review session.
  It starts the review turn, tracks evidence admission, and clears
  pending routing and context when the attempt ends.
- Add a context builder for reviewers that already have the evidence.
  It presents the exact pending action and any applicable permission
  restrictions without repeating the transcript.

## Testing

Add a composition test that checks that an encrypted tool call is
replayed unchanged with its matching evidence-only output.

GitOrigin-RevId: a0c120936c80459b0928550d23ba1137e125013c
2026-11-18 16:16:32 +00:00
jif 5a6fb36a4d Route local MCP board notifications through response item injection (#62302)
## What changed

In opt-in local MCP mode, deliver board notifications through
`inject_response_items` when the recipient uses Multi-Agent V2 with native
tools enabled. Other deliveries continue to use `Op::InterAgentCommunication`.

## Testing

Extend the HTTP board scenario to check that the parent receives exactly one
`CHANNEL_POST` agent message with the worker as author, the parent as
recipient, and the expected post preview text.

GitOrigin-RevId: deaa1451619a94d9c70c771327892069325c5e60
2026-11-18 15:38:06 +00:00
Zahan Malkani bd00a8a42e Preserve pending realtime speech when a call ends (#62299)
## Why

A realtime call can end with completed speech that has yet to reach a
Codex turn. The next turn needs that context even if the call's transport
has already disconnected.

## What changed

- For V3 calls with realtime frame history enabled, save pending speech
  as context for the next turn. Restore it on thread reload and exclude
  it from the turn count used by rollback.
- Drain already received transcript events and settle pending handoffs
  before saving the call's closing marker. Report recovery required if
  shutdown cannot confirm that history was saved.
- Keep transport detach separate from ending a call. Reattaching restores
  saved pending speech, and an open call can be ended from persisted
  history after a reload. Use the call ID for TUI attachments so successive
  calls on one thread have distinct history.

## Testing

Add coverage for queued speech at hangup, reconnect and stop after
reload, retries after an uncertain write, and rollback across saved
session-end context.

GitOrigin-RevId: 657491f1d7e446a1a48e22189758810c8bdd82cb
2026-11-18 15:24:29 +00:00
jif bd3eaf7829 Route injected plaintext agent mail through the native mailbox (#62292)
## Why

Raw response injection bypasses the native mailbox wake policy, so
injected agent messages cannot wake a sleeping thread through that
policy.

## What changed

In native Multi-Agent v2, route batches consisting entirely of
single-text agent messages with valid agent paths through the mailbox
as queue-only mail. Hold a residency pin across the batch so capacity
eviction cannot interrupt delivery between submissions. Mixed batches,
multipart or encrypted messages, and configurations with native tools
disabled continue to use raw response injection.

Only preempt model sampling for pending mail when the matching turn
still accepts mailbox delivery.

## Testing

Extend coverage for waking live and reloaded sleeping threads,
delivering older queued mail before a new task, and retaining mail in
order when a batch exceeds the submission channel capacity and
eviction is attempted.

GitOrigin-RevId: 3df60d2a4a9e7b193ef298e01f31c565ad8a2785
2026-11-18 14:53:00 +00:00
Zahan Malkani ad5dd4a110 Persist realtime handoffs before accepting turn input (#62288)
## Why

Realtime history needs to record which transcript frames reached the
coding agent and which turn received them. If a handoff fails or the
conversation reconnects, Codex needs to distinguish speech that was
already used from speech that is still available for the next input.

## What changed

- Route handoffs through normal turn admission to start or steer a turn.
  When realtime frame history is enabled, persist the transcript frames
  and the receiving turn's input before publishing acceptance or exposing
  the input to the model. Attribute only transcript frames represented
  in the rendered input.
- Reserve transcript frames across overlapping handoffs and release them
  on definite rejection. Retry an uncertain write with the same input
  and require history recovery if the write still cannot be confirmed.
- On V3 reconnect, restore persisted speech that has not been consumed
  and put it before newly captured speech.

## Testing

Add regression tests for attribution after transcript truncation,
overlapping handoffs, V3 reconnect ordering, and preservation of typed
input when a handoff in the same turn fails before model sampling.

GitOrigin-RevId: 432dd51971f7ced20344ebc7f0c7b007bb849f54
2026-11-18 14:26:53 +00:00
jif df975851bf Use the system clock for in-memory MCP message boards (#62284)
## Why

The in-memory MCP backend depended on the runner's clock, so a runner
clock failure could prevent posting. The standalone SQLite backend
already uses the system clock.

## What changed

Read UTC time from the MCP backend's system clock after validating
caller membership. Apply this to both tree and agent-specific bindings.

## Testing

Update the HTTP integration scenario to make the runner clock fail and
verify that a child agent's post timestamp falls within the posting
window.

GitOrigin-RevId: bad5dec5a9be7246cf627b017897fbfe2c960cd1
2026-11-18 14:11:08 +00:00
ioanbudea-OAI a05444bbeb Refresh managed Guardian policy independently of MCP (#62276)
## Why

Managed approval requirements can change while an MCP runtime is still in use.
Later turns need to honor those changes without restarting MCP, while in-flight
MCP actions need to retain the mandatory review requirements of their issuing
turn.

## What changed

- Add `CodexThread::refresh_guardian_policy` to apply managed policy updates to
  an existing thread. MCP configuration refreshes preserve the active Guardian
  policy, including when a policy update lands while MCP configuration is loading.
- Resolve MCP tool and elicitation reviewers against the issuing turn's policy.
  Live requirements can still require Guardian review, and a live policy change
  cannot waive mandatory review captured by the turn.

## Testing

Extend coverage for overlapping Guardian and MCP refreshes and for an existing
MCP runtime that must prompt the user on the next turn after a policy update
allows only the `user` reviewer.

GitOrigin-RevId: 5a1649f917313f6fb152a206bc89986fe6345481
2026-11-18 13:08:51 +00:00
Zahan Malkani 29cb67623c Gate local realtime frame history on paginated storage (#62271)
## Why

Legacy rollout migration rewrites rolled-back history and can disrupt
the realtime stream. Enroll local threads once they use paginated history
so the stream stays intact.

## What changed

- Add the off-by-default `features.realtime_frames_local` flag for
  paginated local threads with a state database. Accept runtime updates
  through the app server and keep threads enrolled once they have a
  persisted canonical session start.
- Add thread-store APIs to recover a realtime session and look up the
  latest session ID from durable history. Route frame completion through
  a store seal so completion acknowledges durable writes.
- Add a local seal for accepted model input that writes source frames
  before the input and lets callers retry an uncertain flush without
  appending the input twice.

## Testing

Cover enrollment for legacy and paginated threads, continued enrollment
after disabling the flag, and retrying a local input seal after a failed
directory sync.

GitOrigin-RevId: 2012feeca3857da90f9b026f077b31a26d15191b
2026-11-18 12:55:14 +00:00
Zahan Malkani 4389a526d5 Derive realtime input receipts from thread history (#62251)
## Why

Accepted handoffs and saved transcript chunks need to appear in realtime
history. Their text can come from the same user message that model history
uses, avoiding a second persisted copy for the receipt.

## What changed

- Reconstruct `turnInputAccepted` and transcript chunk receipts from user
  messages annotated with realtime provenance. Use the stored observation
  time when restoring the realtime clock.
- Replace `sessionEndInputSaved` in the app-server protocol with
  `sessionInputSaved` and a `reason` of `chunk` or `sessionEnd`. Update the
  generated schemas and bindings.

## Testing

Add coverage for reconstructing both receipt types, preserving rollout
order in paginated realtime history, and restoring observation time
across a restart after wall-clock rollback.

GitOrigin-RevId: fcb4e0e539f4e4066726e83fa1e945fb659a2ca8
2026-11-18 11:01:02 +00:00
Zahan Malkani 6d9f0199ed Refactor realtime handoff and history access (#62245)
## What changed

Move realtime text routing into `realtime_handoff` and keep it on the shared start-or-steer path. Extract UTF-8-safe range selection for realtime delegation truncation.

Use `RolloutItem` accessors for realtime timestamps and items in recording, clock restoration, and thread history reads. Pass annotated response items to turn-boundary checks in core and migration rollback so callers can work directly with history envelopes.

GitOrigin-RevId: 3dd37cf91ee5abdca84e87b7d7e304749d9baf04
2026-11-18 09:55:30 +00:00
cazhang-oai ca21fe65d1 Tag Guardian review counts with turn origin (#62225)
## Why

Guardian review counts need a way to distinguish automation-triggered
turns from other turns, including when a subagent requests the review.

## What changed

Add a `turn_origin` tag to the `codex.guardian.review` counter based on
the trigger recorded when the turn started. Recognized automation
triggers map to `automation`, missing or empty triggers map to
`unknown`, and all other values map to `other`. This keeps the set of
metric labels bounded.

## Testing

Cover trigger classification for both allow and deny verdicts and
verify that a later user turn on the same thread is counted separately
from an automation turn in both main and subagent threads.

GitOrigin-RevId: 6a5808798df7d184203cea18e60a94a82d71f036
2026-11-18 08:20:26 +00:00
viyatb-oai bcff988bd1 Resolve Linux sandbox mode once before launching the helper (#62215)
## Why

Managed proxy routes require bubblewrap's network namespace even when
`features.use_legacy_landlock` is enabled. WSL1 compatibility checks and
helper arguments need to agree on the effective mode.

## What changed

Resolve bubblewrap or legacy Landlock once and use that mode for both the
WSL1 check and the `codex-linux-sandbox` arguments. Use Linux sandbox
naming for the shared launcher and CLI code, and preserve the published
analytics category for a missing helper executable.

## Testing

Unit tests exercise the production argument builder, including managed
network context serialization when legacy Landlock is requested. They
also cover which sandbox configurations WSL1 accepts and rejects.

GitOrigin-RevId: 619ab9d3eef965de6bc6cb13ff8a33132018abcf
2026-11-18 07:23:25 +00:00
Ruslan Nigmatullin 86d0e458e3 Prevent duplicate initial context when injection races the first turn (#62206)
## Why

A first user turn and a concurrent raw response-item injection can both
observe that the session has no reference context. Both can then append
the initial prompt prefix and persist a full world-state snapshot.

## What changed

Allow context preparation to run concurrently, then serialize publication
of the initial prefix and its checkpoints. If injection publishes first,
the user turn computes its context updates against the published baseline.
If the user turn publishes first, injection appends only the
caller-provided items.

## Testing

Add an integration test that forces the overlap in both preparation
orders. It checks the first request's world-state updates, verifies that
the follow-up request contains the initial instructions and injected
content once each, and checks that history contains one full snapshot.

GitOrigin-RevId: b66f9c6ccc5d42a2be0e852b4d83b78adbc9e5b2
2026-11-18 06:35:41 +00:00
viyatb-oai a4495dd5c9 Keep sandbox preparation with the command through launch (#62205)
## What changed

- Keep the prepared `SandboxExecRequest` intact in core and let
  `command/exec` borrow the prepared command for streaming. Windows
  restricted-token commands continue through the dedicated sandbox launcher.
- Move runtime read-path selection for exec-server commands and filesystem
  helpers into `SandboxManager`. It derives the paths from the executor's
  binaries and, for managed process launches, finds the generated proxy CA
  bundle in the command environment.

GitOrigin-RevId: 8c9d278496d84589bc4a7b7d0ed08cb1b8e6ba21
2026-11-18 06:22:36 +00:00
Benjamin Carlsson e58677f0cb Add task group navigation to the agent command center (#62200)
## Why

Row and page navigation make users step through tasks to reach another group.

## What changed

Use `Shift+Down` or `Shift+J` to jump to the first task in the next
visible group, and `Shift+Up` or `Shift+K` to jump to the first task
in the previous group. Navigation stops at the ends of the list.

Expose `agents.next_group` and `agents.previous_group` in the keymap
picker and show the active shortcuts in Task shortcuts.

## Testing

Add coverage for jumps in both directions, list boundaries, and key
handling during search and rename. Update snapshots for shortcut help
and the keymap picker.

GitOrigin-RevId: 2542a75e7fdd7a3326c0914e19a9f5c191de082b
2026-11-18 05:49:12 +00:00
viyatb-oai 89feadf3cc Preserve saved sandbox permissions when resuming codex exec (#62194)
## Why

`codex exec resume` sends the current process's sandbox defaults as
overrides. A session started with `:read-only` can therefore resume with
workspace write access when the configured default is `:workspace`.

## What changed

- Restore the saved permission selection, working directory, and workspace
  roots by default. Honor explicit overrides and append directories requested
  with `--add-dir` to the resumed workspace roots.
- Recover built-in read-only permissions from older history without widening
  current read access. Require an explicit permission selection when a saved
  named profile cannot be loaded or saved read-only access cannot be restored.
- Report sandbox permissions and writable roots from the running thread.

## Testing

Add regression coverage for a denied write on the first resumed shell call,
legacy read-only history, explicit permission overrides, and workspace root
preservation with and without `--add-dir`.

GitOrigin-RevId: ed2cf3132f9ce34570661f801c9534a55696e3a5
2026-11-18 05:13:56 +00:00
Adam Perry @ OpenAI 8e1fc8e059 Route turn and response checkpoints through the rollout budget policy (#62190)
## What changed

Move rollout work admission into `RolloutWorkGate` and route compaction
deferral through `ThreadBudgetPolicy`. Use `TurnWork` to check the budget
when accepting a sampling response and to handle checkpoints after stop
hooks, compaction, and sampling errors. Pass sampling charges and response
completion through `ResponseWork`.

The existing budget check still rejects responses after exhaustion. The
new checkpoints leave retry, completion, compaction, and charge handling
behavior unchanged.

GitOrigin-RevId: 7526416b8ce24ca84035494aeb2a23abd8ca3ddc
2026-11-18 04:41:01 +00:00
viyatb-oai 6ee9bc1ba7 Select process sandboxes during launch preparation (#62183)
## Why

Workspace-relative permission rules need to resolve against the execution
host's workspace roots so a grant applies to the intended directory.
Restricted launches also need to check that the host can provide the
required sandbox.

## What changed

- Select the platform sandbox while preparing a launch, using the permission
  profile, network requirements, and Windows sandbox settings.
- Pass workspace roots into policy resolution for local commands and shell
  snapshots. Already-bound command profiles validate their concrete paths
  without resolving Windows launcher hints on hosts that do not use them.
- Share local launch preparation between tool commands and shell snapshots,
  and require a platform sandbox for exec-server launches that request one.

## Testing

Cover network-only restrictions and verify that a
`:workspace_roots` write grant allows writes to the configured subdirectory
under the command's working directory while denying writes to a sibling file
and the corresponding subdirectory under the parent. Exercise the path grant
through both app-server command execution and WebSocket exec-server execution.

GitOrigin-RevId: 492fe7ab8deddf30cfd2e2bdabf28d02d67e00c5
2026-11-18 03:59:37 +00:00
Sean Huang f09fb197f5 Remove Python from MCP permission request hook tests (#62172)
The MCP permission request hook tests depend on a Python interpreter to
run their fixture, so running them requires Python on the host or in
Bazel's test inputs.

Run the Rust test binary as the hook subprocess. It reads the hook
payload from stdin, appends it to the JSON Lines log, and writes the
configured response to stdout. Drop the Python runtime and files from
the core Bazel test dependencies.

GitOrigin-RevId: b9e26384c6b455b0f0936c7009a445d3eabfe2c6
2026-11-18 02:56:01 +00:00
Dylan Hurd 3aaa23a437 Reduce overhead in CLI integration tests (#62153)
## Why

SSE-only mocks return 404 on WebSocket upgrades by default, causing
retries before the tests reach the HTTP stream. In parallel runs, each
CLI subprocess can also start a Tokio worker per host CPU.

## What changed

- Share an SSE mock that returns HTTP 426 on WebSocket upgrades to
  trigger immediate HTTP fallback. Reuse it in the fallback test.
- Set `TOKIO_WORKER_THREADS=2` for CLI subprocesses launched by the
  affected test helpers. Run streaming and resume cases that don't need
  the repository checkout in temporary working directories.
- Test promptless `codex exec fork` option validation without creating a
  source thread. In the successful promptless fork case, keep stdin
  open and rely on the test runner's timeout to catch a blocked read.

GitOrigin-RevId: 94c20d4b2fd7cc65bc0f2a1cd0318ac188f59f22
2026-11-18 01:48:42 +00:00
Owen Lin 06789c7618 Preserve web search provider ownership across thread resumes (#62144)
## Why

Search MCP and native web search produce provider-specific references.
Switching providers after a thread resumes can mix those references and
break follow-up calls that use them.

## What changed

Persist whether a thread has used Search MCP, native web search, or
neither. Restore that state from response history, including compacted
history, and use legacy attribution and fallback markers for older
threads. When resumed history lacks a search state or legacy attribution
checkpoint, withhold native fallback unless a legacy marker identifies
native search.

Require every Search MCP call to claim the thread's search provider
before execution, including calls retained by Code Mode.

## Testing

Cover resuming a thread with Search MCP references after discovery
becomes unavailable, both with a saved search state and with imported
history that lacks search checkpoints.

GitOrigin-RevId: 100d21c92b0bdbf737ec36c3474f0bc020df8efc
2026-11-18 00:45:07 +00:00
felixxia-oai 18d82cf7eb Add reusable per-agent reviewer conversations to Guardian v3 (#62134)
## What changed

Give the root agent and subagents with a board identity their own Guardian
reviewer reservation. Each new reviewer thread starts with empty history
and uses the acting agent's live message-board retrieval tools.

Keep one reservation active per agent and retain the conversation only
when the caller marks it reusable. Reuse requires matching reviewer settings
and history-reset version. Dropping a reservation retires its thread.

## Testing

Add an integration test that checks thread reuse after a reusable
disposition, replacement after an unfinished reservation is dropped, and
exclusion of legacy subagents without a board identity.

GitOrigin-RevId: c7bccf4651ad4e04c42d9aee1d9e8de24b5b48df
2026-11-17 23:48:01 +00:00
felixxia-oai c2595ad343 Add live evidence retrieval for Guardian v3 reviewers (#62133)
## Why

A captured board view limits evidence searches to the review's cutoff. A
verdict reviewer needs to be able to check for later evidence, including
restrictions or revocations, before deciding on an action.

## What changed

Add a live `guardian_board` binding that lets reviewers search and read
any Guardian evidence channel, including channels they do not follow.
Search also matches text inside JSON-encoded tool arguments.

Reviewers can list their own subscriptions with `subscribed_channels`
and subscribe or unsubscribe by channel. Subscriptions control delivery
of future evidence. Earlier posts are available through search and read
tools.

Let review setup and prewarming select guidance for the installed
retrieval tools. The live board guidance explains how to find original
user messages and assess their authority. Share the provider-scoped
reviewer header setup through the core Guardian review API.

## Testing

Cover searches beyond the captured cutoff and in unsubscribed channels,
paginated listing of the reviewer's own subscriptions, and channel-only
subscription changes in both live and captured views.

GitOrigin-RevId: c2e1c6c849346cd3d6e316bcf17e44260fcd4c8e
2026-11-17 23:47:24 +00:00
Nick Steele 7066a55a7b Support enterprise MCP sign-in without refresh tokens (#62129)
## Why

An enterprise identity provider can return an OpenID Connect ID token
without issuing a refresh token, even when Codex requests
`offline_access`. The refresh-token requirement blocked those sign-ins.

## What changed

For `ema_auth`, keep requesting `offline_access` and prefer a refresh
token when available. Otherwise, use the stored ID token for the ID-JAG
exchange after checking its issuer, audience, and expiry. Require
reauthentication when the ID token is expired or invalid and no refresh
token is available.

Update `rmcp` to 3.6.0 for ID token exchange support.

## Testing

Add regression coverage for sign-in with and without a refresh token,
ID token expiry and issuer binding, and the subject token type sent to
the identity provider.

GitOrigin-RevId: ee7e253627c8274f9b3096e3b87e92e2f99885ea
2026-11-17 23:33:09 +00:00
jif e73da8bd1b Preserve base and developer instructions in host child preparation (#62128)
## Why

Hosts preparing a child thread lacked the parent's effective base
instructions and the developer instructions a native subagent would inherit.
Hosts also need the base instruction provenance to preserve custom text
while letting model-owned instructions resolve for the child's model.

## What changed

Include effective base instruction text and provenance in
`PreparedChildContext`. Share developer instruction selection with native
subagent creation so host preparation uses the configured V2 subagent
override when present and falls back to the parent turn's developer
instructions otherwise.

## Testing

Add integration coverage that starts a child on a different model and
checks that custom base instructions persist, model-owned instructions
resolve for the child model, and the V2 override takes precedence over
the parent developer instructions.

GitOrigin-RevId: 0e151e343e58d995c8901a9ba819cb7f60d248f5
2026-11-17 23:31:58 +00:00
andrewgu-oai 4e51bfbacc Refresh tool hashes in core scenario snapshots (#62124)
## What changed

Update the expected hashes for tool lists and incremental tool declarations
across seven core scenario snapshots. The fixtures cover Code Mode, dynamic
tools, and MCP discovery and sharing.

GitOrigin-RevId: 8d69870b488dffc5a24afe0e1c8f522335b25105
2026-11-17 22:58:38 +00:00
Shuo 8dcd56d0cb Add external header auth for existing realtime calls (#62114)
## What changed

Add `RealtimeExistingCallAuth` to `RealtimeAttachmentOptions`, with model-provider authentication as the default. Embedding hosts can explicitly select `ExternalHeaders` for existing calls to use header-based credentials and the host's transport without adding model-provider headers or performing runtime agent registration.

Require an explicit, nonempty sideband URL and header-based authentication for this mode. Destination authorization remains the trusted host's responsibility, and application network policy still applies.

## Testing

Add integration coverage for external-header and model-provider authentication through event delivery, reconnect, and detach. Verify that model-provider credentials are excluded in external-header mode and that invalid authentication, missing URLs, and network policy denials reject the attachment before a WebSocket handshake.

GitOrigin-RevId: 2c915e1cf76a3563f58f751272db1ec50718d925
2026-11-17 22:00:20 +00:00
nvogt-oai 39a7b53fa4 Trust the bundled Memory session hook without saved hashes (#62112)
## Why

The bundled Memory hook needs to supply context at startup and after compaction without requiring saved hook trust.

## What changed

Recognize the exact bundled Memory `SessionStart` declaration as a built-in hook: the `^(startup|compact)$` matcher, `codex_apps` server, `codex_dream_memory.get_mec` tool, and empty input. Carry the expected app connector identity through discovery for dispatch checks, and hide this built-in hook from hook listings while preserving other plugin hooks.

## Testing

Add coverage for exact declaration matching, hook listings without an Apps connection, and a scenario snapshot verifying memory context injection at startup and after compaction without saved trust.

GitOrigin-RevId: edc0e8ffa955227328345f46afecc2a868c0be49
2026-11-17 21:40:36 +00:00
Abhinav 8fca6ffb92 Support OTel header helpers in local managed requirements (#62110)
## What changed

- Allow system `requirements.toml` and MDM requirements to set `otel.headers_helper` and `otel.headers_helper_refresh_interval_ms`, and expose both fields through the requirements API.
- Require an absolute executable path and run managed helpers directly from their installation directory. Reject helper settings from cloud requirements.
- Restrict managed helper headers to OTLP HTTP exporters with nonempty endpoints configured in the same requirements layer. Replacing the helper or an exporter revokes the previous binding.
- Document deployment and rollback requirements, including client compatibility and pausing affected exports until a failed helper recovers.

## Testing

Add coverage for exporter layer boundaries, cloud policy rejection, relative path rejection, managed helper execution and recovery, missing executable diagnostics, and requirements API output.

GitOrigin-RevId: 271058010c2e3090eb97cb357b70be4dc41b43db
2026-11-17 21:10:09 +00:00
andrewgu-oai 6c0cee502d Add GPT-6.2 Sol and Astra to model catalogs (#62106)
## What changed

- Add `gpt-6.2-sol` and `gpt-6.2-astra` to the bundled, Amazon Bedrock, and Vertex catalogs, including Bedrock Runtime global and US cross-region variants.
- Make GPT-6.2 Sol the default catalog selection and refresh model ordering, descriptions, and bundled instructions.
- Increase the GPT-6.1 Sol context window to 500,000 tokens.
- Advertise the `ultrafast` service tier for GPT-6.2 Astra on Bedrock.
- Supply the same current model catalog to both executors in the prompt-prefix compatibility test so catalog updates do not cause prefix mismatches.

## Testing

Extend provider, app-server, and TUI coverage for catalog ordering, model fallback, Vertex requests, and GPT-6.2 Astra's Bedrock `ultrafast` selection and clearing behavior. Refresh model-picker and request snapshots.

GitOrigin-RevId: f28940e4a255fcdd88f7114873259bd1f3399812
2026-11-17 20:04:36 +00:00
Tom 7457b7268f Preserve trace context during WebSocket startup prewarm (#62103)
## What changed

- Inject the current span's W3C trace headers into WebSocket handshakes.
- Promote `startup_prewarm` to an info span and fall back to the current span when it is disabled, preserving trace context in the spawned task.

## Testing

Add a regression test for `traceparent` and `tracestate` propagation through the handshake, prewarm request, and subsequent turn on the same connection. Verify that prewarm uses the startup trace while the turn uses its own trace, with the prewarm span both enabled and filtered out.

GitOrigin-RevId: 1e196e132a1991206469060ab80a474857fa7909
2026-11-17 19:24:17 +00:00
RJ 6d40c0ac9b Clarify recovery guidance for stale Guardian authorization (#62099)
## What changed

Give `StaleAuthorization` failures specific guidance explaining that the action did not run and the failure is not a policy denial. Instruct the agent to retry once through Guardian if current instructions authorize the action, resolve unclear authorization before proceeding, and avoid bypassing approval or repeatedly retrying a failed review.

## Testing

Extend the authorization refresh tests to verify the blocked tool output includes this guidance when repeated authorization changes exhaust the review budget, for both approval and denial responses.

GitOrigin-RevId: f6fcbe46fdb5131f70ee905220a58c7331b543fd
2026-11-17 19:09:21 +00:00
adi-oai 0122b120cd Centralize app-server turn error conversion (#62096)
## What changed

Add a shared `From<ErrorEvent>` implementation for `TurnError` and reuse it in thread history, rollout projection, and live event handling. Preserve the existing field mappings and keep `additional_details` unset.

Parameterize the compaction replay test by error code and recoverability, retaining the existing `server_error` case, and document retry expectations for WebSocket closes.

GitOrigin-RevId: 3afcc23e9fdc314477febe6b4a4aeb680efafd5a
2026-11-17 18:56:05 +00:00
Adnan Hajar cb64621bf3 Normalize Bedrock Mantle commentary before replay (#62095)
## Why

Bedrock Mantle's reasoning prefix omits empty `annotations` on assistant commentary. Replayed commentary needs to preserve that form to keep the prefix stable.

## What changed

Add a provider hook to normalize completed output items before they enter model history. For Mantle, omit empty `annotations` from assistant commentary text while preserving nonempty annotations, final answers, and Bedrock Runtime output.

## Testing

Add regression coverage for Mantle and Runtime that checks commentary replay across a tool continuation and a subsequent turn, including reasoning and tool item ordering and preservation of final-answer content.

GitOrigin-RevId: ecd5b9b5dca8c24956a6379c9d0fb643e4427af3
2026-11-17 18:55:30 +00:00
surajs-oai e9a43d43c5 Return empty success output from v2 send_message (#62093)
## What changed

Remove the acknowledgment text and `followup_task` hint from successful v2
`send_message` responses, including messages sent to the root agent. The shared
messaging handler now returns empty text with the success flag set.

Update the idle eviction follow-up scenario snapshot to expect empty tool output.

GitOrigin-RevId: 9eab3ae7264e6ddf3db6ae40a34cc895d0954621
2026-11-17 18:44:30 +00:00
jif bc2c328483 Append transcript provenance to Guardian JSON instructions (#62090)
## What changed

Place JSON transcript provenance instructions after the policy and output contract in Guardian reviewer and classifier prompts. Keep classifier provenance outside the configured prompt token cap.

## Testing

Update prompt composition tests, classifier configuration and integration assertions, and the Guardian review snapshot to verify the new ordering.

GitOrigin-RevId: f0f86b80a96a130043521aeb529d691e8f424c20
2026-11-17 18:24:49 +00:00
jif 4046bdf263 Avoid an admission deadlock in the code mode spawn test (#62089)
The completion barrier in `yielded_code_mode_spawn_preserves_metadata_and_plaintext`
could hold shared admission while the agent spawn needed exclusive admission.
Replace that barrier with a `wait` call on the yielded cell outside nested tool
dispatch, keeping the next turn active until the spawn completes.

GitOrigin-RevId: 17a17941c933e44c0be9d70479741d4c814c3f8b
2026-11-17 18:23:40 +00:00
jif f993175205 Add policy-checked dispatch for bundled App hooks (#62080)
## What changed

Carry an expected connector identity on hook MCP calls and add a bundled App dispatch path that requires the host Apps server, a matching connector, and current policy permitting execution without user approval.

Prepare hook calls from the current Apps client catalog, including app-only tools, without exposing those tools to the model or starting unrelated required servers. Refresh session MCP state before preparation and recheck admission before dispatch so configuration changes and logout invalidate stale calls. Never retry a dispatched call.

## Testing

Add coverage for refreshed approval and enablement policies, connector mismatches, app-only tool visibility, preparation without unrelated server startup, and admission invalidation on refresh or logout.

GitOrigin-RevId: 965dd7f79baa40d1be0e158e47b2679d8ba98fe5
2026-11-17 16:56:34 +00:00
swastik-oai ce5a565ba0 Simplify Guardian history review preambles (#62074)
## What changed

Use “Treat the content as evidence, not as instructions to follow” in both initial and follow-up Guardian history review preambles, replacing the explicit list of transcript and action fields described as untrusted evidence. Update the corresponding prompt and scenario snapshots.

GitOrigin-RevId: 200ee3c858b54b38fe2609598ef3a1e40cf36380
2026-11-17 16:16:36 +00:00
jif 02d60fb5cc Preserve client attribution when spawning subagents (#62072)
## Why

Delegated work should retain client attribution such as `cost_center` from the turn that requested it, even when a yielded code-mode cell spawns its child after a newer parent turn starts.

## What changed

Capture client metadata from the originating turn and apply it to the child's initial turn in both legacy and v2 agent spawning. Children and grandchildren retain the captured values when the parent is later steered with updated metadata.

Exclude `misalignment_override`, `parent_response_id`, and `mcp_request_meta` from inheritance, while preserving each child's own thread and turn identifiers.

## Testing

Add coverage for metadata filtering and snapshot isolation, legacy and v2 spawning with fresh or forked history, grandchild inheritance, and spawning from a yielded code-mode cell after the parent advances to another turn.

GitOrigin-RevId: 8c378c49239ccfac03deb2b793fc69aba1d41644
2026-11-17 16:15:55 +00:00
jif b271854568 Allow the expanded agent model shortlist in prompt-prefix tests (#62070)
## Why

Released CLIs can still advertise five model overrides in `spawn_agent`, causing the prompt-prefix comparison to reject the expanded shortlist.

## What changed

- Accept the exact four-model addition to the `spawn_agent` description when comparing against a release, while preserving checks for all other description changes.
- Refresh the collaboration tool hashes in the bundled statusline skill snapshot.

GitOrigin-RevId: 22cfd81215734d9f3aba84eda2102c25d75fce96
2026-11-17 16:12:36 +00:00
jif 58627e6fea Fix turn interrupt reply ordering and shutdown handling (#62066)
## Why

A delayed terminal event from an earlier turn could acknowledge interrupts for a later turn. Interrupts could also remain pending after the thread listener shut down.

## What changed

- Associate pending `turn/interrupt` requests with their target turn and reply only when that turn completes or aborts.
- Track the current Core turn through stop hooks and resolve review delegate IDs to the owning turn when validating interrupts.
- Settle pending interrupts with an error on listener shutdown and reject further interrupts against the retired runtime.

## Testing

Add regression tests for delayed terminal events, queued turn starts, review delegates, and interrupt handling during thread revert and runtime replacement.

GitOrigin-RevId: 9695fc3f718baa6b792a14d54136bb87fc003100
2026-11-17 15:33:21 +00:00