## Why
A connected account or app can choose an approval reviewer, but that
setting applies across its tools. Users may want to review calendar
event creation themselves while keeping automatic review for other tools.
## What changed
Set `approvals_reviewer` on an individual app tool in `config.toml`:
```toml
[apps.calendar.tools.calendar_create_event]
approvals_reviewer = "user"
```
Codex matches the tool by raw name first and falls back to its title.
The tool's reviewer takes precedence over the connected account, app,
app defaults, and session settings, subject to managed requirements.
This applies to tool-call approval prompts and MCP approval requests
that match a verified app tool invocation. The app-server
`config/read` response also exposes the per-tool setting.
## Testing
Extend coverage for reviewer precedence, tool title fallback, managed
review requirements, tool-call approval routing, strict MCP elicitation,
and app-server config reads.
GitOrigin-RevId: c92bd39b9e708dada9d314c19a446b4c580edf91
## What changed
Reserve `[permissions.credentials]` in `requirements.toml` for shared
credential policy. The table currently accepts no settings and should be
omitted. Empty tables and legacy profile definitions with profile fields
produce a migration error that tells administrators to rename the managed
profile and update references. Profiles named `credentials` remain valid
in `config.toml`.
Accept an empty `[permissions.<profile>.credentials]` table in named
profiles in both files and expose it in the `config.toml` schema.
## Testing
Add regression coverage for rejecting direct and inherited selection of a
user profile through an empty managed credentials table, preserving MCP
configuration reads, and enforcing network policy inheritance checks for
legacy managed profiles.
GitOrigin-RevId: 33dcca30b37d3f07ce670967342199f5302e1d98
## Why
The `incomplete` status alone gives no indication of which timing dependency was missing or which operation prevented capture.
## What changed
Emit deduplicated `critical_path_incomplete_reasons` in turn analytics for incomplete captures. Reasons cover unsupported Code Mode and agent operations, unattributed reviews and user waits, missing turn starts, and forced teardown, with an `unclassified` fallback. External tools that share a built-in name can still invalidate capture without being classified as the built-in operation.
During interruption, use the task's join result to distinguish forced teardown from normal completion so a task that already finished can still report a complete path.
## Testing
Add coverage for analytics serialization, concurrent reason deduplication, tool name collisions, and interrupted tasks that finish normally or require forced teardown.
GitOrigin-RevId: fab9aa1ff881997a34dcf75adc5638133cedc7fe
## Why
If a provider keeps an SSE connection open after reporting a failure, Codex
can hit the idle timeout and lose the original error and its retry advice.
## What changed
End the SSE stream immediately on `response.failed` or a recognized
`error` event. Classify statusless quota, plan usage, invalid prompt, and
misalignment errors consistently across both event forms. Preserve
`Retry-After` for overload and capacity errors, preferring error-level
headers over event-level headers when both provide valid advice.
## Testing
Add SSE regression tests that hold the connection open and verify immediate
error delivery, terminal error handling, and retry delays. Extend WebSocket
coverage for statusless errors received before the close handshake.
GitOrigin-RevId: 69afd1d3b18ca3139e9b7ad98ae1481a432179f0
## 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
## 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
## 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
## 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
## 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
## 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
## Why
The local native voice prefix build can run eight jobs in parallel.
Bazel needs to account for those jobs when scheduling other local
compile actions against the same CPU budget.
## What changed
Use the same job count for the native build and the macOS
`VoiceNativePrefix` action's CPU estimate.
GitOrigin-RevId: 0bda242b98bae8b3f3c412c95c85e398a0dfc9b2
## 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
## 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
## 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
## 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
## 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
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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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
## 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