Commit Graph
12663 Commits
Author SHA1 Message Date
Charlie Marsh c5cff4335c Treat statusless bio and cyber policy errors as terminal (#62354)
## Why

When the Responses API sends a policy rejection in an `error` event
without an HTTP status, the SSE client can wait until its idle timeout
to report the failure.

## What changed

Recognize `bio_policy` and `cyber_policy` in the shared terminal error
parser so both SSE and WebSocket clients surface the corresponding
policy error. Preserve the provider's message and use a default when
it is missing or blank. End the SSE stream as soon as the error arrives.

## Testing

Add SSE tests for both error codes, including when the stream stays
open, and WebSocket cases that verify both errors surface without a
close handshake.

GitOrigin-RevId: 1b46b6557a39a61a1bb10bdd0d8ede48ecd6fa13
2026-11-18 20:17:25 +00:00
Charlie Marsh 097a8a7439 Add a shared sandbox launcher for Linux and macOS (#62353)
## Why

Running each helper through `codex sandbox` keeps a separate Codex
supervisor process alive for each helper. A shared launcher lets one
supervisor manage multiple helpers concurrently.

## What changed

Add a launcher mode that multiplexes helper I/O and exit status over a
newline-delimited JSON protocol on stdin and stdout. Each helper uses
the host sandbox setup with its own configuration and network proxy.
The launcher applies backpressure to helper I/O, drains buffered output
on exit, and stops tracked helpers when the controller disconnects.

## Testing

Add integration coverage for per-helper filesystem isolation, stdin
backpressure, buffered output after helper exit, and controller
disconnect while output is blocked.

GitOrigin-RevId: a7f75fdedbe0928ff5b93a412c7223371d0f321a
2026-11-18 20:14:05 +00:00
Charlie Marsh 60fcb1649f Support piped I/O when starting Seatbelt sandbox commands (#62350)
## What changed

Split Seatbelt command startup from waiting for the command to exit.
The startup helper can pipe stdin, stdout, and stderr and returns a
handle that keeps the network proxy alive while the caller manages the
child process.

The sandbox CLI still inherits stdio, waits for the child, reports
Seatbelt denials when requested, and propagates the child's exit status.

GitOrigin-RevId: 6a52a1a539bc2861b2357e9e60fab61ee65265fb
2026-11-18 19:56:33 +00:00
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
colby-oai 0e011c0092 Verify dependency hashes when running Python repository tools (#62346)
## Why

Using `uv run --frozen` keeps dependency resolution fixed but does not require
installed packages to match the hashes in `uv.lock`.

## What changed

Run Ruff for the Python SDK and repository scripts, and regenerate Python SDK
types during repository schema refreshes, through a shared runner. It exports
the selected locked dependencies, installs them into a temporary virtual
environment with `uv pip sync --require-hashes`, and runs the tool without
resyncing the environment.

## Testing

Update tests to check the formatter invocations and verify that only repository
schema refreshes invoke Python type generation through the runner.

GitOrigin-RevId: 4e84da5d227eb99c24efb9a1cc7647af82105536
2026-11-18 19:21:39 +00:00
Benjamin Carlsson 42cf4edfcd Add slash command argument completion to the TUI composer (#62343)
## Why

The slash command menu helps users find commands, but leaves them to
recall fixed arguments such as `on` and `off` for `/raw`.

## What changed

Show prefix-filtered suggestions for the first argument of supported
slash commands. For example, type `/mcp lo` and press `Tab` to complete
`/mcp login`. `Enter` and configured submit shortcuts still submit the
draft as typed.

Give mention completion priority and limit argument suggestions to
commands available in the current thread and connection state.

## Testing

Add tests for popup rendering, argument replacement, submit shortcuts,
and changes in thread availability and connection state.

GitOrigin-RevId: 8682c323064457dd9307b0a1520469011a8df9f3
2026-11-18 19:11:14 +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
Benjamin Carlsson 58ad62ce09 Let users open the command center from provider error screens (#62335)
## Why

Read-only chats offer a Left Arrow shortcut to the command center when
agent navigation is available. Chats blocked by model provider errors
were missing that shortcut.

## What changed

Share notice rendering and shortcut availability between provider
errors and read-only threads. Show `← command center` on provider error
notices when the shortcut is available, and open it on a plain Left
Arrow press even when offline.

## Testing

Add a regression test that checks the shortcut hint, verifies that
repeat events leave the notice open, and confirms that opening the
command center preserves the draft both online and offline. Update
provider error snapshots to cover the new hint, including at narrow
terminal widths.

GitOrigin-RevId: be2ce80cade02c84baeff7fd48fa8973f0dcc1dc
2026-11-18 18:48:22 +00:00
Benjamin Carlsson 0a82fdf49d Open Codex thread links inside the TUI (#62332)
## Why

Conversation search results can point users to saved transcripts. Users
need to be able to follow those links without leaving their terminal session.

## What changed

- Make Markdown links such as `[Review notes](codex://threads/<id>)`
  open the linked conversation from chat and transcript views. In the
  resume picker, follow the link to another transcript preview.
- Resolve nested agent links through their owning session and select the
  requested agent. Show archived conversations in read-only mode and
  let users explicitly reopen them.
- Include the Markdown link format in thread search results, including
  archived results.

## Testing

Add coverage for thread link parsing and activation, nested agent
navigation, archived thread reopening, and mouse capture during
transcript preview transitions.

GitOrigin-RevId: 40a39c43acf643b97e066ba663aefcf9cda0bc81
2026-11-18 18:28:58 +00:00
iceweasel-oai c39f047d24 Migrate the Windows MXC sandbox to the public V1 SDK (#62331)
## What changed

Update `mxc-sdk` and use its V1 API to launch commands in a
`ProcessContainer` with inherited stdio. Build the V1 request from Codex's
filesystem, network, UI, and environment settings.

Cache the SDK's ProcessContainer availability probe and surface failures
to create the security environment at launch. Let the SDK reject deny
paths the host cannot enforce and drop Codex's direct `flatbuffers`
dependency.

## Testing

Update the request-building tests to check the V1 filesystem and network
policies, including loopback access for proxied commands.

GitOrigin-RevId: 0fb9955b5df847595c142f5fd1da7a0cc83e1c28
2026-11-18 18:27:21 +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
bkotsopoulos f2d3086682 Trace MCP binding capture and tool catalog refresh (#62320)
## Why

When MCP binding capture or a catalog refresh is slow, separate spans
help identify whether the time went to startup, lock waits, or tool
catalog processing.

## What changed

- Trace server startup waits, catalog revision checks and snapshot
  reads, and tool preparation and normalization.
- Trace catalog refresh lock waits, fetching, and publication, including
  time spent waiting for active tool calls to finish.
- Record `cache_hit` on the binding capture span and trace the cache lock
  wait. Box the catalog capture future on cache misses to keep it out of
  callers' future layouts.

GitOrigin-RevId: e5a5c037455c755fe74ead9f0efabfcd7a9529bf
2026-11-18 17:37:57 +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 081f205f42 Use Guardian V3 board evidence for synchronous approvals (#62310)
## Why

A pending action can reach approval review before Guardian V3 has routed
the latest user messages to the reviewer's subscribed channels. That
can leave a revocation or renewed approval out of the evidence used to
decide the action.

## What changed

Attach the Guardian V3 reviewer to the synchronous approval path when
available. Start evidence catch-up when the action requests review,
then deliver queued evidence before submitting it for a verdict. If
preparation fails, report the reason and block the action.

Request strict structured output for board routing. Represent channel
description updates as a list, reject duplicate descriptions and empty
routes, and write each source once per distinct destination.

## Testing

Add app-server coverage for subscribed revocation and reapproval,
unavailable evidence, routing failures, and native review when V3 is
disabled or the thread is ephemeral. Add routing tests for duplicate
descriptions, duplicate destinations, and empty routes.

GitOrigin-RevId: 193802d39c120fbad9d77544ab57f4b5d02576b0
2026-11-18 16:18:34 +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
ioanbudea-OAI 17e79ae616 Support independent refreshes of managed Guardian policy (#62274)
## Why

Refreshing Guardian policy should preserve session configuration and
allow policy updates even when unrelated managed settings are invalid.

## What changed

Add a revisioned snapshot that loads and applies Guardian reviewer
restrictions, required models, and policy text together. Preserve the
cloud bundle binding and allow the active policy to carry forward when
another refresh rebuilds the configuration stack. Merge refreshed
`auto_review.policy` fallbacks with retained layers in precedence order
before validating the result.

## Testing

Add a regression test covering an invalid unrelated managed setting,
fallback validation after merging a session override, and removal of
stale policy text when its managed bundle disappears.

GitOrigin-RevId: ac42925eb916355d9972c3e2a0dd91041b06e47a
2026-11-18 13:07:45 +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
alexsong-oai 24e236514b Allow Bedrock Runtime selection during setup and login (#62222)
## Why

The app server's Bedrock setup and login flows always selected Mantle.
Clients using Bedrock Runtime had to configure that provider separately.

## What changed

Accept an optional `providerId` in `account/bedrock/setup` for AWS profiles
and environment credentials, and in `account/login/start` for Bedrock API
keys and AWS access keys. Pass `"amazon-bedrock-runtime"` to select
Runtime. Omit the field or pass `null` to keep the Mantle default.

Save configuration for the selected provider and check that provider for
an existing `aws.credential_export` before changing credential sources.

## Testing

Extend app-server tests to cover Runtime setup with profiles and
environment credentials, Runtime login with both key types, and Mantle
fallback. Verify that environment setup selects the Runtime default
model for a new thread and that a configured Runtime credential exporter
blocks profile setup.

GitOrigin-RevId: 6396b638208ab9b12f50f13f13bd517a919d0848
2026-11-18 07:43:45 +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
Benjamin Carlsson ba8ab2d050 Allow paging through long choices in async questions (#62209)
## Why

A choice taller than the TUI's answer area could never be displayed in
full at that terminal size, so users could neither read it to the end
nor submit it.

## What changed

Let `PageUp` and `PageDown` scroll through the wrapped lines of an
oversized choice while keeping it selected. Allow submission once every
line of the choice has been displayed in order and at full width.

## Testing

Add regression coverage for paging without changing the selection,
rejecting submission when repeated page keys skip lines before redraw,
and rejecting choices clipped horizontally.

GitOrigin-RevId: c296323494bd387581c2bb046272a8ccd773ad75
2026-11-18 06:50:26 +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 a734a13ad7 Omit unknown server versions from /status (#62202)
## Why

`/status` appends `(unknown)` to the server label when a cloud or remote
server does not report a version.

## What changed

Show the cloud label or remote address on its own when the version is
unavailable. When a version is reported, use the same `v` prefix for cloud
and remote servers. The daemon menu still displays `unknown` for a running
local daemon whose version is unavailable.

## Testing

Add `/status` snapshots for cloud connections with and without a reported
version and for a remote WebSocket connection without a reported version.

GitOrigin-RevId: 113d2502fc7de6af37da3b3029ee28923af29e6f
2026-11-18 06:06:46 +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
zm-oai b78fa4af86 Distinguish Windows sandbox provisioning timeouts and pipe closures (#62192)
## Why

When a registered Core provisioning request timed out or its pipe closed
before a reply, setup reported only that the service was unavailable. That
made the two failures indistinguishable in setup metrics.

## What changed

Preserve the underlying I/O error and attach distinct setup error codes for
timeouts and pipe closures. Registered Core still reports the service as
unavailable and refuses helper fallback. `codex doctor` advises checking
that the sandbox service is running and letting pending setup finish before
retrying.

## Testing

Add a unit test that checks error classification for timeouts, unexpected
EOF, and broken pipes. It also checks that a non-registered request still
returns an unavailable response on timeout and that permission errors
receive neither new code.

GitOrigin-RevId: fa6653fe5f9cafd10fc1562eb0763857a1bd628f
2026-11-18 04:52:38 +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
richardopenai 1b84166252 Flush HTTP/2 tunnel data to the local TCP writer (#62186)
## Why

An interactive tunnel can stall when a buffered local writer holds data
that the client needs before it can reply.

## What changed

Flush the local TCP writer after each HTTP/2 data chunk, before releasing
receive flow-control capacity.

## Testing

Extend the relay test to verify that the client receives the server's
initial bytes through a buffered writer before sending its upload.

GitOrigin-RevId: 7c6c37a707319ce77f2abb627924337b0c944c32
2026-11-18 04:16:11 +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
Owen Lin 9f80bb5957 Expose bioPolicy errors in app-server v2 (#62176)
## Why

App-server clients received the generic `other` error code for biology
policy errors, so they couldn't distinguish them by code.

## What changed

Map the core `BioPolicy` error to `bioPolicy` in app-server v2 and include
the new value in the generated JSON schemas, TypeScript types, and Python
SDK enum.

## Testing

Update the error conversion test to assert that `BioPolicy` serializes as
`"bioPolicy"`.

GitOrigin-RevId: 77fa969a3d8cbd4c12fe6f7aa5d4833f6adaa99b
2026-11-18 03:37:23 +00:00
Eric Traut fc25d8f120 Fix stale terminal dimensions in immediate TUI redraws (#62175)
## Why

An immediate redraw can happen before the TUI receives a resize event.
For example, submitting a turn just after shrinking the terminal can
render the frame using the previous dimensions.

## What changed

Resolve the screen size and run resize handling before immediate paints
for turn submission, session lifecycle actions, startup modals, Cloud
switching, and shutdown. Consume the reserved size when drawing the frame
and preserve the scheduled recheck for settled terminal dimensions.

## Testing

Add regression coverage for fullscreen turn submission and archive
progress after a terminal shrink, plus checks that a draw consumes its
reserved size and an early paint preserves the scheduled size recheck.

GitOrigin-RevId: 494c746cb02712350cc600ea4aea64460c608639
2026-11-18 03:36:14 +00:00
Eric Traut 3dbc6f8657 Keep the TUI composer caret anchored while typing (#62174)
## Why

When the composer footer gains or loses a hint row, typing the first
character or deleting the last one can move the caret vertically.

## What changed

Reserve a row for passive footer hints when the status line is visible
and there is room after laying out the input, slash-command suggestions,
and previews. The row can stay blank until a hint appears.

## Testing

Add a regression test that checks the caret row before typing, after
typing one character, and after pressing Backspace. Extend coverage to
check that slash-command suggestions and a short status line fit together
when space is tight.

GitOrigin-RevId: 25df697826cebc4b7cb4aab4460c432b7454d5ea
2026-11-18 03:08:53 +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
Benjamin Carlsson 409973e0e2 Extract TUI thread resume finalization (#62171)
## What changed

Move subscription state updates, history hydration, and resumed session
setup into `finish_thread_resume`. Let callers supply a
`HistoryHydrationScope` and keep using `HistoryHydrationScope::Initial`
for the existing resume path.

GitOrigin-RevId: ebb8b422827a2374d8dce194e8d59afe57327f29
2026-11-18 02:54:51 +00:00
Dylan Hurd 345f166d01 Wait for the search connector in hosted web search tests (#62165)
## Why

MCP tool catalogs can change during startup, so a search binding
captured during startup may go uncached. That makes the test's
per-turn discovery request count depend on startup timing.

## What changed

When hosted search is allowed, wait for the thread's connector to
report `ready` before starting the first turn. This lets the test
check discovery reuse with a stable binding.

GitOrigin-RevId: 50d77eca6bfa7a6bfd5657e4c1ed3aad52beb8c5
2026-11-18 02:31:46 +00:00
Michael Bolin bb6b4b63b9 Move the app-server socket relay into the Codex CLI (#62163)
## What changed

Move the stdio-to-Unix-socket relay used by `codex app-server proxy`
into the CLI crate. Remove the standalone `codex-stdio-to-uds` crate
and binary and the hidden `codex stdio-to-uds` subcommand.

## Testing

Replace the standalone binary test with a CLI integration test that
runs `codex app-server proxy --sock` and checks that the socket receives
the bytes from stdin and the reply appears on stdout.

GitOrigin-RevId: e630f8f70e93ce90b0005e4992a3d0b257b208db
2026-11-18 02:18:36 +00:00
Dylan Hurd b65d9a3b2d Stabilize app-server app/list integration tests (#62162)
## Why

Fixed delays make notification-order assertions sensitive to when the mock
directory and tool requests finish. Model discovery can also make network
requests while these tests exercise app listing.

## What changed

- Pause mock directory responses until the tests receive the expected tool
  update. During forced refetch, assert that the next notification includes
  the fresh directory so an intermediate inaccessible-only update fails the
  test.
- Use the bundled model catalog through `model_catalog_json` and preserve
  that setting when the thread feature flag test rewrites `config.toml`.

GitOrigin-RevId: 0356d757391f15cdcee99a6ac3311dc78b8df00b
2026-11-18 02:17:25 +00:00