foosinn/agentic-env

Watch

Fork 0

chore(deps): update dependency openai/codex to v0.163.0 #8

Open

renovate wants to merge 1 commit from renovate-openai-codex-0.x into main

renovate commented

2026-10-03 23:01:45 +00:00

Collaborator

This PR contains the following updates:

Package	Update	Change
openai/codex	minor	`0.156.1` → `0.163.0`

Release Notes

openai/codex

`v0.163.0`: 0.163.0

Compare Source

New Features

Open /config to search preferences across categories, change supported settings immediately, and see which changes require a restart. (#52990, #53429)
Send a follow-up while Codex is responding to steer it immediately. Interrupting a turn also stops active Code Mode cells and their nested tool calls. (#51812, #51835)
Configure a leader key in /keymap. The default is Ctrl+X, shortcut hints stay open until you choose or cancel, and voice mute moves to F9. (#52273)
Restart a managed background server from /daemon. Codex warns about work the restart could interrupt, then reconnects automatically. (#53173)
Codex can run independent read-only tools in parallel, including skill, memory, and conversation-history lookups. (#52245)
Daybreak is enabled by default for eligible accounts. codex exec can also select it with an OpenAI API key when the server offers access. (#53701, #53717)

Bug Fixes

Resuming a saved thread restores its permissions and network approvals, while respecting explicit overrides and current managed policy. (#53150, #53419, #53424)
The network proxy now checks permission before a DNS lookup, rejects duplicate Host headers, and prevents credential aliases from bypassing inspection hooks. (#51650, #52661, #53506)
Return to an existing side conversation with /side after switching threads. Answers to pending prompts also go back to the thread that asked. (#52184, #53436)
On Windows, Ctrl+V and Shift+Insert paste text as well as images. On WSL, repeated pastes reuse the clipboard reader, and copy attempts time out instead of hanging. (#53224, #52967, #53453)
Local commands finish promptly when a child keeps an output pipe open. Remote commands preserve late-arriving output so the final poll can still collect it. (#52652, #53331, #53622)
codex exec no longer prints the same file diff again after an unrelated command. (#53444)

Documentation

Updated the bundled OpenAI Docs guidance for migrations to the GPT-6 family, including model-specific reasoning, tool use, and data residency considerations. (#51768)
Clarified how the Linux sandbox uses bubblewrap for filesystem isolation and seccomp for syscall filtering. (#52610)

Chores

Codex now uses its standard shell executor and no longer bundles a patched zsh. Configurations using the retired shell flags receive a migration notice. (#52160, #52213)
Reduced Linux and macOS release package size by stripping symbols from packaged binaries while preserving them in the original build outputs. (#52178)

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.162.0...rust-v0.163.0

#51539 Add completion-aware realtime attachment and session-scoped detach @zahan-oai
#51547 Add a Windows MXC sandbox opt-out @iceweasel-oai
#51556 Complete dynamic tool lifecycles on cancellation @mikelam-oai
#51575 Expose package assembly helpers and support gzip DotSlash artifacts @bolinfest
#51595 Add thread ID exclusions to thread/list @btraut-openai
#51602 Distinguish thread listing failures from exhausted history @btraut-openai
#51611 Signal abandonment of unanswered MCP elicitations @nicksteele-oai
#51627 Stabilize Guardian snapshot prefixes by separating assistant context @jif-oai
#51642 Fix retained context handling for typed section content @jif-oai
#51650 Require hostname authorization before proxy DNS lookups @jif-oai
#51651 Persist Guardian review failures for reports across restarts @jif-oai
#51652 Record telemetry for AGENTS.md changes made by apply_patch @jif-oai
#51678 Move Windows sandbox tests into a dedicated integration binary @jif-oai
#51683 Roll back stale Guardian reviews before reusing reviewer history @olliem-oai
#51689 Wait for helper completion in HTTP header cancellation tests @jif-oai
#51690 Add a feature flag for Code Mode tool description ordering @swastik-oai
#51704 Honor tool-description-first ordering in Code Mode @swastik-oai
#51710 Fix a discovery race in the external auth refresh test @jgershen-oai
#51734 Load persisted sender context for Guardian reviews @jif-oai
#51755 Reuse MCP handler metadata for cache comparisons @owenlin0
#51761 Reduce tool metadata cloning in the code-mode runtime @akira-oai
#51768 Expand OpenAI Docs migration guidance to the GPT-6 model family @kkahadze-oai
#51775 Prevent recursive Tokio tracing in telemetry and SQLite logs @zbarsky-openai
#51786 Preserve sandbox overrides across execution requests @iceweasel-oai
#51794 Advertise Ultrafast for GPT-6.1 Sol on Amazon Bedrock @celia-oai
#51800 Remove duplicate field initializers in extension registry tests @anp-oai
#51808 Preserve diagnostic reasons for MCP user verification failures @berkdeniz-oai
#51812 Enable instant interrupts by default @pakrym-oai
#51819 Migrate the MXC sandbox to the 1.0.0 SDK @iceweasel-oai
#51822 Avoid sharing violations when repairing Windows runtime ACLs @johnl-oai
#51823 Share MCP binding tool metadata with prepared calls @owenlin0
#51828 Add policy-based file contents integrity checks @iceweasel-oai
#51831 Add MXC sandbox integrity dependency and policy preparation @iceweasel-oai
#51835 Enable code mode interruption by default @won-openai
#51840 Add a bubblewrap backend for sandbox integrity checks @iceweasel-oai
#51841 Add a macOS Seatbelt backend for sandbox integrity @iceweasel-oai
#51842 Add a sandbox integrity runner with outcome and timing metrics @iceweasel-oai
#51843 Run sandbox integrity checks before commands and filesystem operations @iceweasel-oai
#51847 Preserve Cargo package names in Bazel Rust builds @dkovalenko-oai
#51848 Align Bazel release builds with Cargo and fix platform compatibility @dkovalenko-oai
#51849 Fix package smoke tests for Cargo and Bazel debug symbols @dkovalenko-oai
#51850 Add Bazel release staging archives @dkovalenko-oai
#51855 Add Bazel support to the Codex package build action @dkovalenko-oai
#51856 Build Bazel release artifacts alongside Cargo artifacts @dkovalenko-oai
#51857 Add an app-server prompt prefix compatibility test @jif-oai
#51865 Use readable plugin mentions without suppressing same-name skills @canvrno-oai
#51866 Preserve line breaks and links in multiline async questions @pash-openai
#51868 Record tool registration metrics for each sampling request @akira-oai
#51872 Keep global app-server config independent of the launch directory @etraut-openai
#51884 Add experimental prediction forks that inherit parent context @liame-oai
#51890 Add the missing mxc-sdk UTF-8 resource patch for Bazel @iceweasel-oai
#51892 Preserve tool call completeness when recorded arguments are truncated @ningyi-oai
#51893 Record metrics for incremental tool updates @akira-oai
#51895 Report specific reasons for WebSocket continuation failures @pakrym-oai
#51896 Preserve native errors in Windows sandbox ACL diagnostics @alishobeiri-oai
#51897 Use a dedicated matcher for network domain policies @rafael-oai
#51908 Honor the user input setting for asynchronous questions @mandal-OAI
#51930 Support model-specific function description prefixes @tz-openai
#51963 Attribute compaction analytics to the correct voice session @reia-oai
#51974 Log Windows sandbox availability and backend selection @iceweasel-oai
#52034 Preserve agent state when unloading idle multi-agent v2 children @jif-oai
#52040 Add regression coverage for cancelled agent reloads @jif-oai
#52048 Cover instant interruption in steered-input persistence tests @jif-oai
#52061 Run Guardian conversation classifiers concurrently and preserve action order @felixxia-oai
#52062 Add scenario coverage for worker context across idle eviction @jif-oai
#52065 Require assessment text in the Guardian parser @ioanbudea-OAI
#52081 Fix idle cleanup for disconnected multi-agent v2 children @jif-oai
#52119 Expose originating tool call metadata in command environments @leo-oai
#52160 Remove the patched zsh shell execution backend @jif-oai
#52164 Make environment context date and timezone configurable @surajs-oai
#52176 Show AWS GovCloud guidance at startup and remember acknowledgment @jackz100
#52177 Set a User-Agent for package archive downloads @bolinfest
#52178 Strip symbols from source-built release package binaries @bolinfest
#52182 Expose a verified sandbox launcher to local MCP servers @bolinfest
#52183 Add optional descriptions to agent message board channels @jif-oai
#52184 Preserve side conversations across thread navigation @etraut-openai
#52193 Enforce managed MXC requirements on Windows @iceweasel-oai
#52195 Track source attribution for individual context parts @tz-openai
#52200 Allow plugin toggles while searching and preserve filters on refresh @fcoury-oai
#52203 Expose Codex lifecycle status in iTerm2 sessions @fcoury-oai
#52213 Stop bundling patched zsh in Codex packages @jif-oai
#52215 Enforce application network policy in standalone MCP commands @lsingh-oai
#52220 Add configurable default plugin activation policy @stevenlee-oai
#52223 Enforce application network policy for daemon updates @jackz100
#52225 Fix config rebuild call in the Windows MXC preference test @virajrai-oai
#52226 Include foreground activity in iTerm2 session status @fcoury-oai
#52228 Honor API-key feature gates in TUI Daybreak selection @julee-oai
#52234 Support request IDs in exec-server WebSocket handshakes @mattj-openai
#52235 Recover gRPC code-mode sessions after missing-session errors @surajs-oai
#52241 Preserve subagent capabilities independently of forked history @anp-oai
#52245 Enable parallel execution for read-only tools @zamoshchin-openai
#52250 Add opt-in Guardian trust for orchestrator connector identities @ankushg
#52256 Normalize formatting in docs, web assets, and sample scripts @anp-oai
#52268 Preserve large arguments in executed tool call metadata @ningyi-oai
#52270 Enable text selection in the fullscreen TUI footer @fcoury-oai
#52273 Add configurable persistent leader shortcuts to the TUI @fcoury-oai
#52274 Add structured tracing for Guardian reviews and background scoring @ioanbudea-OAI
#52277 Preserve UTF-8 byte semantics in network domain matching @rafael-oai
#52278 Honor custom OTLP metrics exporters when analytics is disabled @jackz100
#52288 Remove duplicate field initializers from extension registry tests @anp-oai
#52295 Emit one developer notice per incremental namespace update batch @akira-oai
#52299 Make Bazel release jobs advisory @anp-oai
#52302 Add opt-in credential masking for proxied sandboxed sessions @winston-openai
#52304 Persist remote-control RPC preferences in managed daemon settings @etraut-openai
#52325 Track history initialization in Responses turn metadata @anp-oai
#52329 Remove per-content source attribution metadata @anp-oai
#52330 Clamp wrapped source ranges before remapping terminal hyperlinks @bc-openai
#52337 Add durable thread read state with revision-checked updates @btraut-openai
#52350 Expose experimental durable thread read state in the app server @btraut-openai
#52363 Expand realtime v3 voice support @jacksonmoody-oai
#52381 Preserve per-session routing for gRPC code mode @cassirer-openai
#52384 Notify subscribers when thread read state changes @btraut-openai
#52395 Add experimental app-server thread read-state updates @btraut-openai
#52418 Avoid an extra blank quote line when pasting text with a trailing newline @bc-openai
#52535 Add opt-in history prefix preservation for full agent forks @jif-oai
#52557 Forward clipboard copies to the terminal in Herdr sessions @fcoury-oai
#52568 Expose message board permissions and structured denials @jif-oai
#52591 Fix races in remote environment and session replacement tests @jif-oai
#52608 Upgrade hyper to 1.11.1 and test connection closure @jif-oai
#52610 Align Linux sandbox names and docs with bubblewrap and seccomp @bolinfest
#52621 Add template setup for local agent message boards @jif-oai
#52629 Consolidate local message board storage helpers @jif-oai
#52635 Skip background workspace routing reads without ChatGPT auth @joesavona
#52637 Add experimental thread item lookup by ID @btraut-openai
#52640 Count interrupted goal continuations toward the no-activity limit @etraut-openai
#52648 Limit daemon feature compatibility checks to explicit CLI overrides @etraut-openai
#52652 Bound local exec-server output draining after process exit @jif-oai
#52659 Add an opt-in feature for subagent model context defaults @hlevy-openai
#52660 Handle completion events in either order in shell snapshot tests @jif-oai
#52661 Prevent brokered credential aliases from bypassing MITM hooks @viyatb-oai
#52671 Add retention annotations to submitted tool outputs @won-openai
#52674 Move the exec-server test fixture into shared test support @anp-oai
#52676 Refresh persisted capability roots from owner-provided configuration @teddywyly-oai
#52679 Add timeout-aware exec-server configuration reads @hlevy-openai
#52681 Reject reserved Serde JSON keys in code mode @cassirer-openai
#52682 Validate Windows sandbox accounts before password repair @zm-oai
#52685 Preserve code mode cancellation during output serialization @cassirer-openai
#52686 Add opt-in retention for turn tool outputs @won-openai
#52689 Forward per-turn Cyber access programs to Guardian @daneschneider-oai
#52696 Fix marketplace path matching for Windows junctions @zm-oai
#52700 Update the exec-server stable compatibility baseline to Codex 0.162.1 @iceweasel-oai
#52702 Retry bootstrap GETs through the system proxy after request failures @abhinav-oai
#52707 Migrate the Windows MXC sandbox to split MXC crates @iceweasel-oai
#52721 Explain session creation failures during server shutdown @etraut-openai
#52723 Add opt-in gRPC over stdio for the code-mode host @cconger
#52724 Add observers for initial exec-server connection attempts @aaronl-openai
#52725 Report terminal program status with OSC 7501 @fcoury-oai
#52736 Allow model catalogs to override incremental tool notices @akira-oai
#52742 Add opt-in output token replay for OpenAI requests @pakrym-oai
#52748 Make code-mode exit() stop the entire cell @cconger
#52756 Classify voice session failures and record terminal outcomes @bc-openai
#52778 Make pinned transcript prompts clickable @fcoury-oai
#52825 Report exec runtime resets before accepting further requests @JenZhao
#52923 Stabilize the realtime steering timeline test @anp-oai
#52937 Retain client-marked tool outputs across compaction @won-openai
#52946 Keep agent command center rows stable across progress updates @fcoury-oai
#52952 Verify reset notification during code-mode host recovery @etraut-openai
#52959 Reduce stack usage in async TUI tests @jif-oai
#52964 Defer owned transcript redraws during raw paste bursts @etraut-openai
#52967 Reuse and prewarm the WSL clipboard text reader @etraut-openai
#52968 Keep startup modals protected when terminal input draining times out @etraut-openai
#52972 Upgrade rmcp to 3.5.1 and harden lifecycle tests @alishobeiri-oai
#52990 Add a searchable /config preferences panel to the TUI @fcoury-oai
#53049 Add connection-bound reply handles for app-server requests @bc-openai
#53109 Handle broken pipes gracefully in plugin list output @fcoury-oai
#53148 Fix startup draft recovery for pending Vim Replace keys @etraut-openai
#53150 Restore thread-owned permissions on cold resume @etraut-openai
#53152 Allow selecting and copying TUI turn tips @etraut-openai
#53153 Show subagent navigation shortcuts in TUI help @etraut-openai
#53155 Keep remote app-server events deliverable during shutdown @etraut-openai
#53156 Simplify the custom terminal drawing API @bc-openai
#53173 Allow restarting managed background servers from the TUI @etraut-openai
#53201 Keep agents navigation available after a thread is archived @etraut-openai
#53224 Support Windows clipboard text paste shortcuts in the TUI @etraut-openai
#53331 Finish remote exec cleanup when output streams remain open @jif-oai
#53339 Test final polling of remote processes with open output streams @jif-oai
#53358 Remove selected protocol, apply-patch, MCP, and TUI tests @vb-openai
#53369 Allow turns when the agent message board is unavailable @jif-oai
#53382 Ignore the unsafe-libyaml advisory in dependency audits @swastik-oai
#53389 Use cached login credentials for Guardian decisions @swastik-oai
#53393 Distinguish Guardian parent-compaction failure reasons @ioanbudea-OAI
#53400 Add explicit local board connections with fixed runtime access @jif-oai
#53412 Isolate arg0 helper directories by operating system @jif-oai
#53419 Restore saved thread permissions during configuration loading @jif-oai
#53424 Add regression coverage for network grants on cold thread resume @jif-oai
#53426 Preserve Windows runtime registration failure diagnostics @zm-oai
#53429 Apply configuration toggles live and improve settings navigation @fcoury-oai
#53436 Route TUI request replies to their originating connection and thread @bc-openai
#53438 Stop identifying Apple Terminal from TERM_SESSION_ID @etraut-openai
#53440 Preserve status line accents on 16-color terminals @etraut-openai
#53443 Use local MSVC toolchains for native Windows Bazel tests @etraut-openai
#53444 Suppress repeated turn diffs in codex exec human output @fcoury-oai
#53451 Treat incomplete responses as terminal errors @jif-oai
#53452 Close input admission while a turn finishes recording @etraut-openai
#53453 Prefer the Windows clipboard and bound copy attempts on WSL @etraut-openai
#53485 Update quinn-proto to 0.11.18 @smurching-oai
#53496 Preserve pending Effects toggles across save refreshes @fcoury-oai
#53506 Reject duplicate Host headers in the network proxy @jfoo-oai
#53556 Deduplicate TUI modifier handling and terminal color caching @bc-openai
#53595 Add async compaction feature configuration @rka-oai
#53606 Prepare compaction helpers for background requests @rka-oai
#53614 Add infrastructure for speculative remote V2 compaction @rka-oai
#53617 Allow hiding native tools while retaining the multi-agent V2 runtime @jif-oai
#53620 Reuse background results for remote V2 compaction @rka-oai
#53622 Preserve remote exec output until it is collected @jif-oai
#53628 Record truncation metrics for accepted Guardian review inputs @ioanbudea-OAI
#53631 Materialize the thread before testing a discovered daemon restart @jif-oai
#53632 Stabilize write ordering in the shared message board scenario @jif-oai
#53633 Add an environment API key fallback for Guardian Decisions @swastik-oai
#53654 Keep spawned children provisional until the spawn result returns @jif-oai
#53657 Share hook configuration across cloned hook views @jif-oai
#53660 Extract shared multi-agent v2 thread spawning @jif-oai
#53668 Improve remote exec-server test startup diagnostics @jif-oai
#53670 Account for token usage from incomplete responses @jif-oai
#53672 Keep discovered Apps tools available during startup recovery @jif-oai
#53673 Publish Rust releases with the GitHub CLI @jif-oai
#53678 Preserve inherited context in prediction forks @keyz
#53689 Constrain API-key model access programs to server support @julee-oai
#53691 Account for replay caches in encrypted compaction budgets @ioanbudea-OAI
#53693 Add keyboard selection support to the transcript view @fcoury-oai
#53698 Interrupt and drain canceled classifier responses before socket reuse @felixxia-oai
#53699 Cancel Guardian V2 classifications that exceed the tool-call lag window @felixxia-oai
#53701 Enable CLI Daybreak by default and enforce background-turn eligibility @julee-oai
#53706 Preserve URLs and email addresses during external agent migration @jif-oai
#53709 Separate MCP sandbox policy from launcher metadata @bolinfest
#53717 Enable Cyber access programs for API-key sessions by default @julee-oai
#53723 Wire V2 capability discovery through exec-server RPC @TAFOYA-OAI

`v0.162.1`: 0.162.1

Compare Source

Bug Fixes

Fixed a TUI crash when asynchronous questions contain multiple lines, preserving line breaks and complete hyperlink destinations. (#51866)
Fixed startup failures caused by differences between a running background server's feature settings and CLI defaults. Compatibility checks now apply only to explicit command-line feature overrides. (#52648)

Full Changelog: https://github.com/openai/codex/compare/rust-v0.162.0...rust-v0.162.1

`v0.162.0`: 0.162.0

Compare Source

New Features

Add tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled. (#50148)
Pin tasks in the agent Command Center with p and keep them in a shared Pinned group when supported by the server. (#51500)
Navigate and copy transcript blocks with /copy, use Ctrl+Insert to copy selections, and tune mouse-wheel scrolling with tui.mouse_scroll_speed. (#50434, #50215, #50209)
Make URLs clickable in approval headers, questions, MCP prompts, warnings, banners, and verification prompts, including when links wrap across lines. (#51439, #51449, #51450, #51451, #51452, #51458)
Configure live web access and remote compaction capabilities for custom Responses-compatible model providers. (#50459)
Add JavaScript helpers for streaming promise results as they settle, plus opt-in ranked tool search in Code Mode. (#51126, #51209)

Bug Fixes

Respect server model and reasoning-summary defaults for new TUI threads while retaining explicit launch overrides. (#50013, #50811, #50913)
Preserve existing CRLF line endings in apply_patch updates without requiring an opt-in. (#51203)
Fix Linux sandbox startup with multiple denied files, reject writable sandbox-construction executables, and keep ripgrep configuration from weakening deny-glob masks. (#50059, #51211, #51407, #51527)
Restore ordinary drive-letter file access on Windows 10 and match Windows sandbox temp permissions to the child process environment. (#51511, #51512)
Honor server Retry-After advice for retryable Responses and WebSocket failures. (#50418, #51440)
Fix archive checksum verification when installing through Windows PowerShell with PowerShell 7 module paths present. (#51257)

Chores

Publish a signed PowerShell installer with Windows releases. (#51158)
Keep older stable releases and prereleases from replacing newer stable download targets or installer aliases. (#51186, #51425)

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.161.0...rust-v0.162.0

#50013 Honor server model defaults when starting fresh TUI threads @etraut-openai
#50018 Use descriptor-safe helpers for executable test fixtures @jif-oai
#50019 Protect the guardian decisions API key from environment forwarding @swastik-oai
#50026 Preserve user restrictions in Guardian handoff context @jif-oai
#50035 Follow MCP tool pagination in legacy protocol mode @jif-oai
#50039 Keep transcript Find results readable after closing the query @fcoury-oai
#50045 Keep transcript Find expansion scoped to the current match @fcoury-oai
#50046 Stabilize Windows voice build cache keys across tool reinstalls @anp-oai
#50050 Keep plugin and skill snapshots scoped to each step @sayan-oai
#50052 Preserve question context in recovered TUI answer drafts @imac-oai
#50054 Check token estimate filtering directly on the tracing subscriber @tamird
#50058 Upgrade Windows bindings to windows-sys 0.61.2 @tamird
#50059 Fix Linux sandbox startup with multiple denied files @yuzhu-oai
#50066 Add a bounded Decisions transport for Guardian comparison classification @swastik-oai
#50082 Enable dynamic tool inheritance for fresh V2 subagents @ke-oai
#50083 Add paginated reverse lookup for thread attachments @joeytrasatti-openai
#50087 Preserve queued agent mail across session eviction @jif-oai
#50093 Prevent shared instruction providers from delegating to themselves @bryanashley
#50094 Add attachment owner lookup to the app-server @joeytrasatti-openai
#50099 Add opt-in Decisions comparison for Guardian V2 @swastik-oai
#50105 Consolidate chat composer footer logic in footer_state @imac-oai
#50109 Keep fullscreen prompts bounded and scrollable @imac-oai
#50112 Centralize TUI loading glyphs and frame scheduling @imac-oai
#50113 Add a native gRPC client for cloud thread resume and attach @bc-openai
#50128 Expose the model selected for a running turn's next step @sayan-oai
#50129 Preserve Windows environment variables for remote MCP servers @aidanv-oai
#50131 Add opt-in JSON diagnostics for TCP tunnels @richardopenai
#50140 Use the server permission catalog for TUI permission shortcuts @etraut-openai
#50148 Add managed worktree tools to the TUI @bc-openai
#50162 Bound in-flight file opens in exec-server @anp-oai
#50166 Upgrade age to 0.12.1 and remove the obsolete advisory exception @michaelm-openai
#50177 Enable writable file streaming in exec-server @anp-oai
#50183 Add dots to issue labeler guidance @etraut-openai
#50189 Replace the Figma OAuth exception with Mercado Pago @mzeng-openai
#50199 Restore the account email in /status after account updates @etraut-openai
#50200 Report the configured TUI mode in codex doctor @etraut-openai
#50207 Release stable Markdown tables into scrollback during streaming @etraut-openai
#50209 Make transcript mouse scroll speed configurable @etraut-openai
#50215 Support Ctrl+Insert for copying TUI selections @etraut-openai
#50216 Use the shared text editor for command-center task renaming @bc-openai
#50219 Bound tmux option probes to one second @etraut-openai
#50273 Record Guardian V2 Decisions agreement and latency metrics @swastik-oai
#50339 Add end-to-end coverage for MCP sandbox state enforcement @bolinfest
#50345 Keep the subagent picker consistent with thread archive state @etraut-openai
#50348 Back off automatic remote control reconnects with jitter @cooper-oai
#50354 Skip unrelated subtrees during config alias normalization @btraut-openai
#50359 Render ANSI styles in TUI hook system messages @etraut-openai
#50360 Remove initial messages from session configuration events @owenlin0
#50375 Use printable ASCII terminal titles under GNU Screen @imac-oai
#50380 Fix thread unloading after disconnect during MCP startup @yuzhu-oai
#50384 Allow opting into 16 KiB ARM64 code pages for macOS signing @chess-oai
#50389 Honor configured keybindings before transcript navigation @etraut-openai
#50396 Honor pager bindings for transcript page keys @bc-openai
#50402 Consolidate command execution output into aggregated_output @owenlin0
#50416 Clarify Git worktree choices for new and forked conversations @bc-openai
#50418 Honor Retry-After headers in failed Responses events @anp-oai
#50427 Cap persisted command output in paginated history at 64 KiB @owenlin0
#50431 Preserve terminal hyperlinks in agents overview previews @bc-openai
#50433 Allow API-key accounts to use Daybreak in the TUI @etraut-openai
#50434 Add keyboard copy selection to the owned transcript @bc-openai
#50435 Persist additional tool definitions in rollout history @pakrym-oai
#50437 Add a CLI command to uninstall the legacy Windows sandbox @chess-oai
#50441 Support ordered response items in world-state context updates @pakrym-oai
#50442 Preserve native USD amounts in thread usage responses @asohrabi-oai
#50443 Stabilize paused-time code-mode service tests @seanh-oai
#50445 Assert that only direct tool calls emit timing events @seanh-oai
#50446 Bundle rollout attachments into a gzip tar archive @dkovalenko-oai
#50447 Remove the provider capability gate for tool namespaces @pakrym-oai
#50454 Measure rollout persistence size reductions @owenlin0
#50458 Truncate oversized MCP results in paginated thread history @owenlin0
#50459 Add capability overrides for custom model providers @celia-oai
#50462 Populate thread previews from delegated task inputs @bc-openai
#50464 Add the incremental_tools feature flag @pakrym-oai
#50465 Retry registry authentication outages and jitter executor reconnects @apanasenko-oai
#50467 Copy transcript selections as literal text while preserving rich HTML @fcoury-oai
#50470 Account for JSON overhead when truncating MCP tool results @owenlin0
#50472 Enable Ultrafast service tiers for Amazon Bedrock Astra models @celia-oai
#50477 Use the app-server default output cap for TUI workspace commands @etraut-openai
#50480 Skip managed config loading for registered Windows sandbox refreshes @zm-oai
#50499 Include installer stderr in daemon update failures @etraut-openai
#50503 Use Enter to accept transcript Find results and Escape to cancel @fcoury-oai
#50504 Center TUI confirmations over their retained backdrop @bc-openai
#50505 Keep Command Center selection adjacent after task removal @bc-openai
#50507 Record Windows sandbox service stop diagnostics @zm-oai
#50510 Require GovCloud guidance acknowledgment after Bedrock setup @jackz100
#50516 Add scenario coverage for remote /compact context preservation @pakrym-oai
#50525 Reject unknown TUI keys in strict config validation @etraut-openai
#50531 Persist realtime transcript tails before closure without inference @guinness-oai
#50536 Keep shared MCP types stable in Code Mode exec descriptions @aibrahim-oai
#50540 Send incremental tool catalog updates in Responses Lite @pakrym-oai
#50546 Keep MCP resource helpers available in code mode @aibrahim-oai
#50555 Skip daemon auto-start for Windows-mounted WSL homes @etraut-openai
#50558 Avoid reading the current directory when resolving absolute paths @etraut-openai
#50559 Distinguish daemon release identity from executable contents @etraut-openai
#50562 Keep Code Mode tool discovery guidance stable across catalog changes @aibrahim-oai
#50564 Allow transcript selection and copying while bottom modals are open @etraut-openai
#50687 Keep third-party tools deferred in strict Code Mode Only @aibrahim-oai
#50695 Preserve local Markdown link labels in the TUI @bc-openai
#50700 Let the transport create the Windows remote-control socket directory @etraut-openai
#50720 Decode Windows Terminal's mapped Shift+Enter sequence @bc-openai
#50727 Show model and reasoning effort near the top of task details @etraut-openai
#50741 Keep environment-backed tools exposed across readiness changes @won-openai
#50756 Show unavailable slash commands when searched in side conversations @bc-openai
#50764 Allow /archive while a turn is running @bc-openai
#50781 Restrict TUI MCP startup notifications to owned threads @etraut-openai
#50782 Retry Windows daemon release publication on transient file locks @etraut-openai
#50786 Remember Command Center grouping across launches @bc-openai
#50788 Open slash commands from empty drafts in Vim Normal mode @bc-openai
#50802 Fall back to mklink when Windows daemon junction updates are denied @etraut-openai
#50803 Use the managed daemon for eligible remote-control launches @etraut-openai
#50804 Preserve review lifecycle ordering on failure @etraut-openai
#50808 Prune TUI snapshots and consolidate behavior tests @etraut-openai
#50811 Honor server reasoning summary defaults in new TUI threads @etraut-openai
#50913 Use server model defaults for connected TUI fresh starts @etraut-openai
#50940 Recover malformed Windows deny-read ACL state safely @zm-oai
#50962 Gate stable environment tool exposure behind a feature flag @aibrahim-oai
#50964 Track inference tool changes in turn analytics @aibrahim-oai
#50977 Isolate tracing in the strict third-party tool deferral test @alishobeiri-oai
#51061 Gate Guardian continuation tests on classifier request capture @jif-oai
#51063 Honor prior cancellation before starting Codex delegates @jif-oai
#51064 Ignore stale refresh responses in agents overview tests @jif-oai
#51065 Scope Guardian V2 response timing to snapshot sampling @swastik-oai
#51067 Use issuing-step context for Guardian MCP elicitation reviews @jif-oai
#51070 Preserve trusted-tool context in Guardian Decisions requests @swastik-oai
#51117 Install full context in compaction replacement history @pakrym-oai
#51119 Clarify incremental tool namespace updates in Responses Lite @akira-oai
#51126 Add promise settlement streaming helpers to code mode @cconger
#51133 Allow Guardian Decisions to fall back to OPENAI_API_KEY @swastik-oai
#51137 Recover Guardian reviews from parent checkpoints @felixxia-oai
#51139 Force fresh Guardian sessions for parent-checkpoint recovery @felixxia-oai
#51140 Isolate Guardian checkpoint recovery flags per review attempt @felixxia-oai
#51156 Send base instructions as Responses input messages @pakrym-oai
#51157 Enforce required environment skills before model inference @anp-oai
#51158 Sign the PowerShell installer in Windows releases @chess-oai
#51184 Remove obsolete Guardian thread-context enables from tests @felixxia-oai
#51185 Retry transient gRPC code-mode session admission failures @cassirer-openai
#51186 Prevent stable release pointers from moving backward @andrewgu-oai
#51188 Record base instructions in incremental tool history @pakrym-oai
#51191 Clean up Unix app-server control-socket startup lock files @etraut-openai
#51192 Wait for SIGCONT when resuming the TUI @etraut-openai
#51193 Test thread archiving before the first turn @btraut-openai
#51194 Add browser extension request headers to config requirements @jn-openai
#51198 Allow concurrent release builds while serializing publication @andrewgu-oai
#51200 Upgrade Bazel to 9.2.0 and refresh the module lockfile @anp-oai
#51202 Distinguish namespace removals in incremental tool updates @akira-oai
#51203 Make apply_patch preserve line endings unconditionally @charliemarsh-oai
#51206 Record initialization analytics for resumed subagents @peilin-openai
#51207 Gate CLI Daybreak controls and selection behind an opt-in feature @julee-oai
#51209 Add ranked tool discovery to JavaScript code mode @zamoshchin-openai
#51211 Reject sandbox-writable bubblewrap executables from PATH @viyatb-oai
#51215 Measure raw MCP tool catalog sizes in telemetry @owenlin0
#51217 Preserve review targets and scope misalignment continuation metadata @yunhan-wei
#51220 Honor the OTLP metrics temporality preference @daniel-oai
#51221 Separate environment requests from runtime selections @anp-oai
#51223 Remove legacy personality template metadata @rhan-oai
#51230 Make session lookup pagination stable and report listing failures @etraut-openai
#51235 Remove default model labels from TUI model pickers @etraut-openai
#51241 Add a partial answer message phase @rb-oai
#51249 Handle partial answers consistently across agent workflows @rb-oai
#51253 Enforce Fast and Ultra Fast policies independently @dpatel-oai
#51256 Start the Windows sandbox service during registered Core setup @zm-oai
#51257 Fix installer checksum verification under Windows PowerShell @zm-oai
#51260 Handle partial answers in realtime routing and thread search @rb-oai
#51329 Remove partial-history subagent forks @jif-oai
#51330 Measure total Guardian approval decision duration @jif-oai
#51331 Track sub-agent result delivery outcomes @jif-oai
#51332 Record multi-agent wait duration by outcome @jif-oai
#51333 Record the multi-agent version in turn analytics @jif-oai
#51334 Count Guardian denial-limit interruptions in telemetry @jif-oai
#51335 Update collaboration snapshots for full-history fork instructions @jif-oai
#51347 Measure shell snapshot use and wait time per command @jif-oai
#51350 Allow larger shell snapshots when replaying from a file @jif-oai
#51355 Add bounded diagnostics for agent spawn failures @jif-oai
#51378 Keep Guardian v2 WebSocket pools warm with concurrent replenishment @jif-oai
#51391 Make URLs in asynchronous question titles clickable @charliemarsh-oai
#51396 Let late low-risk scores complete pending Guardian reviews @jif-oai
#51400 Prevent later Guardian scores from releasing earlier pending reviews @jif-oai
#51402 Preserve turn attribution across recovery and compaction @eddie-openai
#51407 Protect ripgrep lookup during Linux sandbox construction @viyatb-oai
#51411 Suppress repeated image paste presses in legacy terminals @etraut-openai
#51415 Expose and persist turn lineage across the app server @eddie-openai
#51419 Preserve turn attribution when queued mail wakes durable sleep @eddie-openai
#51420 Finish idle thread unloads after slow shutdown @jif-oai
#51421 Include root turn IDs in host-owned Apps tool calls @eddie-openai
#51422 Accept environment requests at thread and turn settings boundaries @anp-oai
#51425 Skip stable installer alias publishing for prereleases @zsol-openai
#51426 Remove the Bazel JVM override for Windows ARM64 voice builds @anp-oai
#51427 Prevent invalidated wakeups from starting a turn @jif-oai
#51433 Show hook status messages as titles in the hooks browser @abhinav-oai
#51439 Preserve clickable URLs in TUI approval headers @charliemarsh-oai
#51440 Honor Retry-After in WebSocket error events @anp-oai
#51441 Fix core integration tests for updated turn APIs @anp-oai
#51449 Make URLs clickable in TUI user input questions @charliemarsh-oai
#51450 Make URLs clickable in MCP elicitation prompts @charliemarsh-oai
#51451 Make URLs in the TUI warnings viewer clickable @charliemarsh-oai
#51452 Make banner URLs clickable across wrapped lines @charliemarsh-oai
#51457 Preserve status usage hyperlinks when the URL wraps @charliemarsh-oai
#51458 Make URLs clickable in user verification prompts @charliemarsh-oai
#51459 Preserve wrapped help links in Windows sandbox prompts @charliemarsh-oai
#51460 Retry realtime sideband attachment while an existing call activates @bullman-oai
#51463 Record resolved model and reasoning effort in sub-agent activity @sdcoffey
#51465 Add an optional JSON transcript format for Guardian @felixxia-oai
#51466 Keep Guardian transcript records structured through budget recovery @felixxia-oai
#51467 Keep submission logs useful without exposing payloads @chess-oai
#51470 Raise the managed app-server file descriptor limit on Unix @etraut-openai
#51471 Preserve clickable URLs in pending input previews @charliemarsh-oai
#51472 Preserve clickable URLs in TUI selection rows @charliemarsh-oai
#51473 Preserve URL destinations in wrapped hook details @charliemarsh-oai
#51480 Preserve tool declaration mode across resumed context windows @pakrym-oai
#51482 Use PathUri for skill identity and path matching @anp-oai
#51483 Add correlated, credential-free rendezvous connection diagnostics @alexi-openai
#51491 Classify executor capability root ownership independently of parsing @stevenlee-oai
#51492 Remove obsolete fields from persisted turn context @pakrym-oai
#51493 Bind capability roots to environment selections @anp-oai
#51499 Load rollout history on a single blocking worker @charliemarsh-oai
#51500 Add shared task pinning to the agent command center @etraut-openai
#51502 Bound relay connection attempts and handle pongs during blocked writes @alexi-openai
#51503 Expose selected environments to MCP contributors @mtsui-oai
#51510 Preserve live TUI settings when configuration reloads fail @imac-oai
#51511 Fix Windows 10 drive-letter opens for no-follow filesystem operations @zm-oai
#51512 Align Windows sandbox temp permissions with the child environment @zm-oai
#51515 Expose detailed agent tree shutdown failure reports @keitht-openai
#51517 Pass thread persistence intent to attachment uploads @kchainani-oai
#51525 Preserve the CLI MXC preference in executor config reads @zm-oai
#51527 Ignore ripgrep configuration when expanding sandbox deny globs @viyatb-oai

`v0.161.0`: 0.161.0

Compare Source

New Features

GPT-6.1 Sol is now the default model in the bundled and Amazon Bedrock catalogs. (#49318, #49339)
Amazon Bedrock supports multi-agent V2 and Ultra reasoning on compatible models; Bedrock Mantle also accepts AWS GovCloud regions. (#49345, #49813)
Sign in to MCP servers from an active terminal session with /mcp login <name>. (#49290)
Choose your microphone, speaker, and microphone input channels for voice conversations, with preferences saved locally. (#49437, #49836)
Daybreak is opt-in through --enable cli_daybreak or features.cli_daybreak=true; daybreak=true alone is insufficient. By default, controls and indicators are hidden, /daybreak is unavailable, and automatic Cyber routing is omitted—even for saved Daybreak threads. Saved preferences remain intact. Opt-in routing requires eligible ChatGPT sign-in, the OpenAI provider, and advertised model/program support. (#49856, #49858, #49859, #49861, #51207)
Select a Cyber access program per turn with codex exec --cyber-access-program or the TypeScript SDK’s cyberAccessProgram option. The explicit exec override remains available with cli_daybreak disabled and leaves the saved choice unchanged. (#49939, #51207)

Bug Fixes

Approved filesystem escalation can now grant broader write access while preserving denied reads and network restrictions. Background tasks retain their originating turn’s permissions. (#49353, #49880)
Explicit launch permissions survive terminal reconnects and new sessions, while implicit client settings no longer overwrite server or saved-thread web-search settings. (#49809, #49799)
Elevated Windows terminal sessions can start using an embedded server, and sandboxed PowerShell preserves relative paths beneath protected user profiles. (#49855, #49690)
Enter correctly submits buffered input after paste detection expires, including in Vim insert mode. (#49810)
Thread resume includes the latest committed history. Startup detects recoverable SQLite corruption earlier and preserves damaged databases as backups. (#49599, #49701)
Responses retries and WebSocket-to-HTTP fallback honor server retry guidance, reducing premature failures during overload. (#49441)

Documentation

Authentication guidance now accounts for keyring storage instead of implying credentials always reside in auth.json. (#49361)

Chores

Publishing an older alpha or hotfix no longer moves npm alpha tags backward. (#49704)

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.160.0...rust-v0.161.0

#49246 Use executable fixture copying in the bundled bwrap test @felixxia-oai
#49257 Allow Guardian cached approvals with incomplete root context @felixxia-oai
#49260 Restrict enterprise MCP auth and fail closed on config refresh @nicksteele-oai
#49261 Preserve Windows sandbox runner launch errors @zm-oai
#49262 Trace turn phases and correlate accepted input with turns @jif-oai
#49266 Remove the remote agent message board client README @jif-oai
#49267 Support remote agent message boards in multi-agent sessions @jif-oai
#49269 Preserve thread overrides and cloud policy validity during config reloads @nicksteele-oai
#49275 Isolate realtime conversation tests from Responses prewarm connections @felixxia-oai
#49276 Enable enterprise MCP sign-in and account-scoped grant cleanup @nicksteele-oai
#49277 Avoid a turn teardown race in the Guardian agent message test @felixxia-oai
#49280 Restrict capability roots to captured turn environments @miz-openai
#49286 Model exec-server session attachment state as an enum @jif-oai
#49290 Add /mcp login <name> to the TUI @nicksteele-oai
#49294 Record Guardian context mode in review and classification telemetry @felixxia-oai
#49295 Simplify configuration fingerprint canonicalization @jif-oai
#49297 Scan the session index backwards for batch thread name lookups @jif-oai
#49300 Compact the inline hidden tag buffer once per chunk @jif-oai
#49305 Batch metadata reads when resolving thread names @jif-oai
#49308 Run piped legacy Windows sandbox processes without a console @etraut-openai
#49312 Notify parent agents when Guardian stops a subagent @jif-oai
#49316 Bump taiki-e/install-action to v2.87.21 in CI setup @jgershen-oai
#49318 Add GPT-6.1 Sol as the default catalog model @andrewgu-oai
#49325 Retry Windows sandbox runner logon once on error 1056 @zm-oai
#49330 Keep remote control reconnect backoff capped during sustained failures @yansenzhou-oai
#49332 Clean up canceled exec-server RPC requests immediately @jif-oai
#49339 Add GPT-6.1 Sol to Bedrock catalogs and make it the default @celia-oai
#49345 Enable multi-agent V2 and Ultra reasoning on Amazon Bedrock @celia-oai
#49353 Allow approved filesystem escalation while preserving denied reads @viyatb-oai
#49357 Continue Markdown blockquotes when pasting multiline text @bc-openai
#49360 Carry shell invocation metadata and report executor PATH directories @anp-oai
#49361 Clarify credential storage wording across authentication UI and docs @celia-oai
#49369 Update Bedrock GPT-6 Sol catalog tests to expect multi-agent V2 @celia-oai
#49379 Compile hook matchers during discovery @jif-oai
#49384 Track credential storage outcomes and redact sensitive errors @celia-oai
#49388 Fix Windows path inference for opaque URIs with slash prefixes @dkovalenko-oai
#49389 Serialize tests that share Windows sandbox accounts @jgershen-oai
#49392 Add attributed MCP OAuth credential storage telemetry @celia-oai
#49395 Remove randomized greetings from TUI session headers @etraut-openai
#49401 Preserve live tool-call metadata across request windows @ningyi-oai
#49403 Add an experimental flag for bundled tools in login shells @anp-oai
#49406 Support explicit cyber access programs with OpenAI API keys @julee-oai
#49407 Recover exec-server sessions after environment info timeouts @vivi
#49408 Compare tool call metadata in the recorder refresh test @euroelessar
#49411 Bind the app-server time provider to a local variable @euroelessar
#49414 Filter graceful shutdown guard and trigger traces from SQLite logs @dkovalenko-oai
#49415 Truncate input text in protocol debug output @dkovalenko-oai
#49416 Omit payloads from multiline ANSI warnings @dkovalenko-oai
#49424 Infer Windows UNC paths with forward and mixed slashes @dkovalenko-oai
#49425 Prune diagnostic logs periodically by age and database size @dkovalenko-oai
#49426 Enable analytics by default for daemon-launched app servers @bc-openai
#49432 Preserve bootstrap discovery across authentication changes @cooper-oai
#49437 Add local audio device selection to TUI voice settings @bc-openai
#49441 Honor server retry advice across Responses retries and fallback @anp-oai
#49444 Use memrchr to find newlines in reverse JSONL scans @btraut-openai
#49467 Restore executor tool paths after login shell startup @anp-oai
#49472 Use server-authoritative permissions in the TUI @etraut-openai
#49473 Use the rmcp SDK for enterprise-managed token exchanges @nicksteele-oai
#49475 Complete turn abort callbacks before emitting terminal events @euroelessar
#49478 Discover and validate MCP authorization servers before ID-JAG exchange @nicksteele-oai
#49480 Add experimental thread prediction protocol types @keyz
#49489 Add regression coverage for account switches between analytics batches @anp-oai
#49517 Add a fork shortcut to the TUI command center @etraut-openai
#49560 Add an opt-in model catalog to multi-agent context @jif-oai
#49564 Copy selected file paths as plain text in the TUI @fcoury-oai
#49584 Skip host skill discovery for Guardian reviews @jif-oai
#49595 Make the strict network approval test independent of request order @jif-oai
#49598 Persist explicit user goal edits in model history @felixxia-oai
#49599 Return authoritative replay history when resuming a thread @felixxia-oai
#49600 Reuse unchanged history snapshots when resuming threads @felixxia-oai
#49624 Use server authentication for explicit remote session commands @cooper-oai
#49642 Allow managed requirements to disable the Windows MXC sandbox @iceweasel-oai
#49675 Serialize Responses routing fields before large inputs @jbeckwith-oai
#49678 Escape command drafts when recovering question answers @imac-oai
#49683 Add a managed feature gate for in-app voice @vishnu-oai
#49686 Deliver remote message board notifications to active turns @jif-oai
#49689 Export skill invocation events through OpenTelemetry @jif-oai
#49690 Preserve PowerShell relative paths in the elevated Windows sandbox @johnl-oai
#49692 Keep compressed rollout snippet searches on one blocking worker @npancha-openai
#49693 Move thread history projection into one blocking task @charliemarsh-oai
#49694 Batch rollout listing scans on cancellable blocking workers @charliemarsh-oai
#49696 Make exec-server file reads cancellable between chunks @charliemarsh-oai
#49701 Detect SQLite corruption during startup and preserve recovery backups @dkovalenko-oai
#49702 Rename exec-server file handle management identifiers @anp-oai
#49704 Prevent npm alpha dist-tags from moving backward @imac-oai
#49706 Upgrade the argument comment lint toolchain and Dylint @tamird
#49708 Move session index I/O off async runtime threads @charliemarsh-oai
#49710 Classify SQLite corruption using typed error codes @dkovalenko-oai
#49712 Avoid full-string scans in token-budget truncation @jif-oai
#49713 Remove repository-local Codex guidance, skills, and environment config @anp-oai
#49714 Decouple API-key cyber access programs from model discovery @julee-oai
#49715 Add account security setup reminders to the TUI @dennyku
#49778 Define exec-server protocol types for streamed file writes @anp-oai
#49781 Include the environment's MXC backend in MCP sandbox metadata @zm-oai
#49782 Clean up process groups for failed shell snapshot captures @jif-oai
#49783 Preserve background thread requests when forking in the TUI @etraut-openai
#49784 Add a requirements feature gate for the browser annotation API @tepman-oai
#49785 Persist empty paginated threads when naming them @rd-oai
#49786 Clarify V2 spawn model override guidance for context catalogs @jif-oai
#49787 Remove AGENTS.md from Bazel core test data @andrewgu-oai
#49792 Add retained conversation support to Guardian async sampling @felixxia-oai
#49793 Add conversation mode to Guardian v2 async classification @felixxia-oai
#49795 Avoid duplicate sync reviews in Guardian classifier continuations @felixxia-oai
#49796 Deduplicate Guardian retained-context omission notices @felixxia-oai
#49798 Share cached exec-server environment info with Arc @anp-oai
#49799 Preserve server web-search settings in the TUI @etraut-openai
#49800 Allow cleanup of replay-only side conversations with missing threads @bc-openai
#49801 Update the Rust toolchain action for argument-comment linting @andrewgu-oai
#49804 Use platform-specific modifier labels in TUI shortcut hints @bc-openai
#49805 Add capability-gated writable file streams to the exec-server client @anp-oai
#49806 Accept unknown Codex error variants in the app-server protocol @anp-oai
#49807 Enable API-key model discovery by default @andrewgu-oai
#49809 Preserve local launch permissions across TUI sessions and reconnects @etraut-openai
#49810 Flush expired paste bursts before handling Enter @bc-openai
#49811 Handle unsupported fs/writeBlock requests in exec-server @anp-oai
#49812 Move shadow skill ranking off the turn preparation path @vkg-oai
#49813 Support AWS GovCloud regions for Amazon Bedrock Mantle @alexsong-oai
#49814 Add coordinated shutdown for local agent trees @owenlin0
#49816 Remove browser-open success messages from the TUI @bc-openai
#49817 Add an advisory Bedrock GovCloud requirements check @alexsong-oai
#49818 Use dedicated parameters for sandboxed file opens @anp-oai
#49819 Recover daemon startup and updater re-exec after cwd deletion @etraut-openai
#49822 Box the resume future in the agents overview permissions test @sayan-oai
#49835 Clarify service tier default save errors in the TUI @etraut-openai
#49836 Allow microphone channel selection for voice conversations @bc-openai
#49843 Preserve daemon diagnostics and include updater logs in reports @etraut-openai
#49846 Capture host-supplied extension data for each turn @sayan-oai
#49847 Persist world-state snapshots alongside rendered context @pakrym-oai
#49850 Launch Windows daemon children in a dedicated working directory @etraut-openai
#49852 Improve diagnostics for report attachment failures @dkovalenko-oai
#49855 Use embedded mode for elevated Windows TUI sessions @etraut-openai
#49856 Support Daybreak selection in codex exec @etraut-openai
#49857 Use the model catalog to select TUI cyber refusal guidance @etraut-openai
#49858 Add a persistent /daybreak toggle to the TUI @etraut-openai
#49859 Honor Daybreak settings in TUI continuations and background tasks @etraut-openai
#49861 Add Daybreak state to the status line and terminal title @etraut-openai
#49867 Update elevated-launch warning snapshot to use ⌃o for copy @etraut-openai
#49874 Point usage and credit links to ChatGPT settings @etraut-openai
#49875 Decouple TUI startup presentation from execution configuration @etraut-openai
#49876 Remove personality plumbing from the TUI @etraut-openai
#49880 Bind permission grants to the originating turn @anp-oai
#49894 Return world-state snapshots and context updates together @pakrym-oai
#49898 Scope extension filesystem access to callback permissions @anp-oai
#49910 Preserve validation errors for invalid TUI keybindings @etraut-openai
#49912 Respect approval policies in temporary structured threads @etraut-openai
#49939 Add per-turn Cyber access program selection to exec and the SDK @mldangelo-oai
#49946 Prevent stale file search results from being labeled with a new query @jif-oai
#49951 Include preceding assistant context in Guardian sender reviews @jif-oai
#49956 Cache the placeholder regex for MCP hook argument expansion @jif-oai
#49959 Test session index thread-name append and removal @jif-oai
#49972 Share byte buffers across exec-server output chunks @jif-oai
#49987 Add renewable EMA HTTP authentication and credential versioning @nicksteele-oai
#49993 Preserve the async Guardian history prefix as retained context changes @felixxia-oai

`v0.160.1`: 0.160.1

Compare Source

Bug Fixes

Preserve SYSTEMROOT, TEMP, and TMP when launching remote stdio MCP servers with explicitly configured remote environment variables, allowing Unix hosts to retain the Windows executor's startup environment.

Changelog

#51121: Backport Windows remote MCP environment preservation to 0.160.

`v0.160.0`: 0.160.0

Compare Source

New Features

Browse older tasks in the agent command center with a keyboard-accessible “Show more” action. (#49106)
Select transcript text and paste with middle-click in fullscreen mode on supported local Linux X11 terminals. (#49112)
Start sessions outside a project with workspace defaults when policy permits, and restore saved permissions when resuming. (#49160)
Added opt-in Guardian review capabilities to retrieve earlier user instructions and include context from agent handoffs. (#49036, #49057)

Bug Fixes

Unsent queued messages now resume after reconnection once uncertain submissions are resolved, avoiding duplicate sends. (#49105)
The terminal UI now preserves server provider, reasoning-summary, and verbosity settings and shows the correct sessions in resume and fork history. (#49144, #49161, #49171)
Fixed Windows sandbox PowerShell fallbacks and long-path permission repairs, and suppressed unwanted console windows from background helpers. (#49019, #49058, #49098, #49164, #49386)
Subagents now retain environments that are still starting and receive their configuration or preparation failure. (#49075)
Prevented SQLite stalls during connection setup and logging, and surfaced initialization errors instead of masking them as timeouts. (#49032, #49102)
Explicit provider model catalogs no longer include unsupported bundled models or reuse stale entries after refresh failures. (#49135)

Documentation

Clarified how provider credentials use the configured storage backend and how env_key identifies the API-key environment variable. (#49118)

Chores

Reduced repeated plugin-loading work by caching parsed manifests and reusing HTTP connections for remote plugin requests. (#49099, #49100)
Added background reclamation of unused log database space to reduce disk usage. (#49069)

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.159.0...rust-v0.160.0

#48983 Avoid full metadata rewrites for thread timestamp updates @jif-oai
#49000 Isolate the memory startup metadata test from Git enrichment @jif-oai
#49019 Use a compatible PowerShell fallback for the Windows MXC sandbox @iceweasel-oai
#49028 Use the numeric ioctl value in the macOS sandbox policy @aionescu-oai
#49031 Clarify ChatGPT sign-in success copy @bc-openai
#49032 Avoid SQLite stalls from connection setup and stderr span logging @jif-oai
#49036 Add opt-in conversation history retrieval to Guardian reviews @felixxia-oai
#49037 Show the Plan mode cycling hint in the fullscreen status line @fcoury-oai
#49038 Preserve encrypted agent messages in Guardian reviews @felixxia-oai
#49041 Copy selections within inline code as plain text @fcoury-oai
#49043 Update Pro plan display names in the TUI @etraut-openai
#49057 Add handoff-aware root context for Guardian reviews @jif-oai
#49058 Fix Windows sandbox ACL repair for long runtime paths @darius-oai
#49060 Update Guardian messaging snapshots for native agent messages @dkovalenko-oai
#49065 Update Guardian handoff snapshot for separate agent messages @cassirer-openai
#49067 Keep configuration values out of Windows sandbox policy events @zm-oai
#49069 Reclaim unused SQLite log database pages in the background @dkovalenko-oai
#49073 Surface realtime voice catalog failures in the TUI @etraut-openai
#49074 Propagate Cargo package versions to Bazel Rust targets @tamird
#49075 Preserve pending environments when spawning subagents @sayan-oai
#49076 Avoid collecting unused Git metadata in skill analytics @tamird
#49079 Update and centralize TUI subscription labels @etraut-openai
#49082 Skip remote Git discovery for Guardian diff paths @jif-oai
#49084 Track app-server running turns incrementally @tamird
#49089 Render follow-up directive labels in the TUI and copied responses @etraut-openai
#49093 Simplify startup promotions to platform-specific desktop app tips @etraut-openai
#49096 Update h2 from 0.4.16 to 0.4.19 in Cargo and Bazel lockfiles @cassirer-openai
#49097 Notify lifecycle extensions of compaction usage limits @xli-oai
#49098 Resolve Windows sandbox PowerShell fallbacks on the exec server @zm-oai
#49099 Cache parsed plugin manifests across plugin workflows @dkovalenko-oai
#49100 Reuse the HTTP connection pool for remote plugin requests @dkovalenko-oai
#49102 Preserve SQLite vacuum modes and surface pool initialization errors @bc-openai
#49103 Balance Windows Bazel test shards using duration estimates @jgershen-oai
#49105 Resume unsent TUI input after reconnecting @etraut-openai
#49106 Add history pagination to the agent command center @bc-openai
#49112 Add X11 primary selection and middle-click paste support @fcoury-oai
#49114 Point remote compaction tests at the mock ChatGPT server @OLI-OAI
#49117 Attribute analytics requests to each thread's product SKU @papayo-oai
#49118 Correct provider authentication storage documentation @celia-oai
#49119 Add recovery guidance to content-filter retries @won-openai
#49127 Deduplicate cloud and executor skill listings before budgeting @TAFOYA-OAI
#49130 Move content-filter guidance into the shared Responses retry handler @won-openai
#49135 Treat explicit provider model catalogs as authoritative @andrewgu-oai
#49136 Remove the plus separator after Option symbols in TUI key hints @bc-openai
#49138 Expose original error details to turn lifecycle contributors @bryanashley
#49144 Preserve server reasoning summary and verbosity settings in the TUI @etraut-openai
#49145 Hide reasoning summary settings in /status for server connections @etraut-openai
#49147 Simplify cloud task base URL normalization @akira-oai
#49153 Omit blockquote markers when copying quoted selections in the TUI @bc-openai
#49160 Support projectless TUI sessions with workspace defaults @etraut-openai
#49161 Honor app-server provider defaults in the TUI @etraut-openai
#49164 Suppress Windows console windows for background subprocesses @etraut-openai
#49171 Fix model provider lookup for TUI history @etraut-openai
#49386 [0.160] Backport remaining Windows console fix to frozen alpha.6 @andrewgu-oai
#49763 [0.160] Backport maintenance-line catalog and security reminder updates @andrewgu-oai

`v0.159.3`: 0.159.3

Compare Source

New Features

Eligible local sessions signed in with ChatGPT can now show optional reminders to complete account security setup. (#49744)

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.159.2...rust-v0.159.3

#49744 [0.159] Backport account security setup reminders for 0.159.3 @andrewgu-oai

`v0.159.2`: 0.159.2

Compare Source

Bug Fixes

Suppressed console windows flashing on Windows when Codex launches background processes and sandboxed commands. (#49385)

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.159.1...rust-v0.159.2

#49385 [0.159] Backport Windows console suppression for 0.159.2 @andrewgu-oai

`v0.159.1`: 0.159.1

Compare Source

New Features

Added GPT-6.1 Sol as the default model in the bundled catalog and Amazon Bedrock Mantle and Runtime catalogs. (#49323, #49342)

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.159.0...rust-v0.159.1

#49323 [0.159] Prepare 0.159.1 release backports @andrewgu-oai
#49342 [0.159] Backport GPT-6.1 Sol Bedrock catalogs @celia-oai

`v0.159.0`: 0.159.0

Compare Source

New Features

Opt-in instant_interrupt lets new input steer Codex during model responses or long-running code-mode calls. (#48135, #48141)
New sessions get a compact welcome screen and consistent headers, with occasional tips during and after turns. (#48513, #48562, #48352)
The warnings viewer dismisses reviewed warnings when closed; press k to keep one for later. (#48205, #48206)
You can scroll the transcript while deciding whether to implement a plan. (#48805)
Native Mermaid rendering supports more flowchart edges, labels, and node groups. (#48814, #48895)
App-server clients can paginate thread history from a specific item. (#48151)

Bug Fixes

Windows launches avoid stray console windows for MCP servers, code-mode hosts, and piped commands; restrictive launchers can fall back to embedded mode. (#48138, #48238, #48483, #48491)
Copying transcript selections preserves Markdown tables, formatting, and significant whitespace. More terminals now copy automatically on selection. (#48548, #48549, #48469)
Blank sessions retain drafts when switching tasks, and threads can be archived and listed before their first turn. (#48628, #48828, #48199)
Local ChatGPT sign-in opens the browser reliably; onboarding also provides a shortcut to copy the login link. (#48502, #48544)
Approved commands retain explicit filesystem denials, and .aws directories are protected by default under writable roots. (#48155, #48176)
Fixed macOS TLS access in network-enabled sandboxes and remote environments that require proxy access. (#48565, #48198)

Chores

Removed automatic follow-up prompt suggestions and the tui.prompt_suggestions setting. (#48621)
Removed the bundled plugin-creator skill. (#48604)

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.158.0...rust-v0.159.0

#48135 Add opt-in code-mode yielding on new user input @pakrym-oai
#48138 Suppress console windows when spawning the code-mode host on Windows @zm-oai
#48141 Preempt model responses when new user input arrives @pakrym-oai
#48143 Preserve executor MCP credential boundaries across reconnects @rreichel3-oai
#48151 Add item anchors to thread/items/list pagination @btraut-openai
#48155 Preserve filesystem denials when preparing approved commands @viyatb-oai
#48157 Allow Windows daemon launches with residual job membership @etraut-openai
#48158 Fix Guardian retained context spacing and empty assistant handling @olliem-oai
#48168 Generate unique exec-server process IDs for every request @sdcoffey
#48174 Preserve usage limit windows in turn and compaction analytics @rhan-oai
#48176 Protect .aws directories under sandbox writable roots @jackz100
#48187 Fix zsh alias quoting in sourced shell snapshots @jif-oai
#48190 Bound agent message board SSE frames before parsing @jif-oai
#48197 Optimize blake3 in Bazel fastbuilds @jif-oai
#48198 Honor execution environment proxy requirements @seanh-oai
#48199 Keep archived threads with empty previews visible in listings @acrognale-oai
#48200 Extract Responses header conversion into a shared module @anp-oai
#48205 Dismiss viewed TUI warnings when closing the viewer @fcoury-oai
#48206 Add a keep-and-next action to the warnings viewer @fcoury-oai
#48207 Preserve queued output for observers during code-mode termination @pakrym-oai
#48211 Keep Codex visible during external editor handoff @etraut-openai
#48213 Isolate executable fixture copies in CLI tests on Linux @jif-oai
#48222 Preserve late result metadata for truncated code-mode calls @ningyi-oai
#48224 Preserve model and access program pairs during compaction @jamy-OAI
#48229 Extract Responses failure parsing into a dedicated module @anp-oai
#48238 Suppress console windows for local Windows MCP servers @malsamiri-oai
#48272 Prevent Windows daemon launches from retaining launcher stdio @zm-oai
#48318 Keep TUI reconnect attempts running until the shared deadline @etraut-openai
#48344 Preserve tool metadata for OpenAI provider endpoint overrides @peilin-openai
#48350 Display reconnect commands on a separate line @etraut-openai
#48352 Show turn tips while working and after completion in the TUI @fcoury-oai
#48353 Stabilize skill catalogs across executor availability changes @vkg-oai
#48469 Default to copying transcript selections in more terminals @fcoury-oai
#48483 Prevent console windows for piped Windows child processes @fcoury-oai
#48489 Fix Mermaid shape, relationship, and state description parsing @etraut-openai
#48491 Fall back to embedded mode under restrictive Windows launchers @fcoury-oai
#48502 Fix ChatGPT browser sign-in for local app servers @etraut-openai
#48508 Preserve WebSocket continuations when steering a turn @pakrym-oai
#48513 Refresh the TUI welcome screen for new sessions @fcoury-oai
#48531 Add context to Windows sandbox runtime registration errors @zm-oai
#48544 Make onboarding login links easier to copy @etraut-openai
#48547 Fade blossom replays back to the idle state @fcoury-oai
#48548 Preserve table cell source metadata through TUI rendering @fcoury-oai
#48549 Preserve Markdown tables and whitespace when copying TUI responses @fcoury-oai
#48551 Fix TUI math rendering for zero and big wedge expressions @etraut-openai
#48560 Keep working tips stable during transcript interaction @fcoury-oai
#48562 Use a consistent borderless session header in the TUI @fcoury-oai
#48565 Allow macOS TLS trust evaluation in network-enabled Seatbelt profiles @winston-openai
#48568 Allow exec-server to proxy permitted private IPs upstream @open-matt
#48574 Preserve deferred tool namespace names before descriptions @adaley-openai
#48575 Allow provisioned executors more time to come online @richardopenai
#48604 Remove the bundled plugin-creator skill @martinauyeung-oai
#48611 Centralize persistent mode enablement checks @alishobeiri-oai
#48621 Remove follow-up prompt suggestions from the TUI @etraut-openai
#48623 Preserve empty Markdown list markers in the TUI @etraut-openai
#48626 Stop showing previous-session summaries when switching TUI sessions @etraut-openai
#48628 Preserve blank TUI sessions when switching tasks @etraut-openai
#48643 Set the provisioned macOS CLI bundle name to ChatGPT @riley-oai
#48646 Fix the session-start helper call in the command center test @etraut-openai
#48686 Remove WebSocket headers and tool payloads from info logs @chess-oai
#48724 Prevent Linux ETXTBSY races in MCP stdio tests @jif-oai
#48725 Retain confirmed Code Mode messages for Guardian reviews @ankushg
#48727 Centralize executable fixture creation to avoid Linux ETXTBSY races @jif-oai
#48754 Render /status without borders and wrap long values @fcoury-oai
#48757 Match TUI status shimmer timing to desktop headers @fcoury-oai
#48761 Show hidden output line counts in compact terminal activity @fcoury-oai
#48764 Preserve MCP app resource URIs without defaulting display mode @victor-openai
#48772 Fix Unix socket connections through long symlink paths @etraut-openai
#48775 Match pinned transcript headers to the original prompt style @etraut-openai
#48776 Remove the current badge from TUI task rows @etraut-openai
#48779 Preserve independent Guardian history across parent compaction @felixxia-oai
#48783 Add single-server MCP status discovery with thread connection reuse @victor-openai
#48796 Add opt-in structured errors for Guardian circuit-breaker interruptions @won-openai
#48799 Fix SGR mouse reporting for Windows terminal capture @etraut-openai
#48800 Use the terminal palette for ordered Markdown list markers @etraut-openai
#48805 Allow transcript wheel scrolling while a modal is open @fcoury-oai
#48807 Show short turn durations in TUI completion footers @fcoury-oai
#48812 Add history-aware prewarming for idle threads @vkg-oai
#48814 Preserve punctuation and semicolons in Mermaid labels @etraut-openai
#48819 Use explicit histogram buckets for tool and skill context metrics @mzeng-openai
#48824 Keep voice RTP timestamps aligned to 20 ms packets @bc-openai
#48827 Show a hand pointer over transcript links in Ghostty and Kitty @bc-openai
#48828 Allow archiving threads before their first turn @bc-openai
#48829 Wait briefly for the Windows sandbox provisioning service to start @zm-oai
#48830 Show a short, neutral TUI interruption notice @fcoury-oai
#48895 Expand native Mermaid flowchart syntax support @etraut-openai
#48973 Isolate realtime auth fallback test from startup prewarm @jif-oai
#48982 Prevent message-board notifications from reopening final answers @eknight-oai

`v0.158.0`: 0.158.0

Compare Source

New Features

Configure copy-on-select and right-click paste in the fullscreen TUI. Copied transcript selections now preserve Markdown formatting. (#47639, #47896, #48118)
Connect to MCP servers that require pre-registered OAuth client secrets, including through codex mcp add --oauth-client-secret. (#47891)
Secure direct exec-server WebSocket connections with bearer tokens, including connections configured through app-server. (#47601, #47648)
Image generation and editing can explicitly request transparent backgrounds, and edits now accept file-backed conversation images. (#47484, #47956)
Terminal input approval is enabled by default for commands running with elevated permissions; runtime-only grants no longer cause unnecessary reviews. (#47799, #48073)

Bug Fixes

Fixed Windows sandbox failures involving ordinary Windows 10 paths, rejected stored credentials, and large permission policies. (#47672, #47695, #47919)
Fixed Linux sandbox startup with nested writable roots and preserved Git metadata protections across writable roots on Linux and macOS. (#47623, #47974)
macOS patch operations now recognize system path aliases covered by existing permissions, avoiding unnecessary approval prompts. (#47879)
Approval reviews now retry when new user input arrives, so a status question does not automatically abort a pending action. (#47819)
Mermaid flowcharts now render quoted labels and ampersands; unsupported diagrams explain why they fall back to source. (#47572, #47678)
Command completion events now include early output and report process-launch failures to clients. (#47529, #47665)

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.157.0...rust-v0.158.0

#47441 Use secondary text styling for the transcript footer shortcut hint @etraut-openai
#47447 Extract WebSocket authentication into codex-websocket-auth @euroelessar
#47458 Parallelize instruction refresh and tool preparation @hlevy-openai
#47484 Add explicit background control to image generation @alicec-oai
#47520 Route session agent operations through AgentControl @jif-oai
#47529 Emit command lifecycle events for unified exec launch failures @steipete-oai
#47536 Route agent lookups and V2 context through AgentControl @jif-oai
#47539 Test interrupted one-shot command launch failure persistence @jif-oai
#47540 Add an option to disable multi-agent v2 direct messaging @jif-oai
#47565 Classify rollout read failures by reason and progress @jif-oai
#47568 Record sandbox backends in command execution analytics @iceweasel-oai
#47571 Wait for idle before injecting remote compaction test history @felixxia-oai
#47572 Explain Mermaid rendering fallbacks in the TUI @etraut-openai
#47582 Retain assistant context for Guardian authorization reviews @felixxia-oai
#47584 Preserve streamed assistant message order in retained context @felixxia-oai
#47585 Preserve delivered assistant messages in Guardian retained context @felixxia-oai
#47589 Keep unfinished link destinations out of rich streaming previews @etraut-openai
#47590 Serialize numeric custom reasoning effort as JSON numbers @dylan-hurd-oai
#47591 Stream daemon executable hashing off the async runtime @etraut-openai
#47596 Refresh realtime context for each model request @reia-oai
#47597 Guard prerelease channel and canary updates against older versions @imac-oai
#47601 Add opt-in WebSocket authentication to exec-server @euroelessar
#47603 Add a reap-only drop policy for child processes @charliemarsh-oai
#47604 Extend child commands with session and descriptor controls @charliemarsh-oai
#47605 Route pipe processes through the shared child launcher @charliemarsh-oai
#47610 Use native POSIX spawning for command hooks @charliemarsh-oai
#47611 Use the shared process launcher for Unix shell snapshots @charliemarsh-oai
#47612 Launch Linux pipe processes through a fresh setup helper @freeqaz-openai
#47613 Expand Linux spawn-helper lifecycle test coverage @charliemarsh-oai
#47617 Route Linux PTY launches through the process setup helper @charliemarsh-oai
#47618 Prefer Shift-arrow hints for queued messages and questions @imac-oai
#47619 Add bounded buffering for global operation metrics @celia-oai
#47620 Add portable project trust lookup APIs @seanh-oai
#47623 Fix read-only metadata mount ordering for nested writable roots @jif-oai
#47624 Recognize user_message tools in Guardian authorization context @ankushg
#47625 Allow history and notes without experimental context capability @pmccrary-oai
#47629 Route V2 child loading through AgentControl @jif-oai
#47630 Bind Guardian reviews to the action's target environment @jif-oai
#47633 Route message board agent resolution through the selected controller @jif-oai
#47635 Overlap startup WebSocket preconnect with tool discovery @bromano-oai
#47638 Classify retryable exec-server preparation errors by type @mtsui-oai
#47639 Add configurable copy-on-select for transcript selections @fcoury-oai
#47641 Honor Retry-After and preserve server retry deadlines @anp-oai
#47642 Add model-specific prefixes to indirect tool descriptions @rhan-oai
#47647 Apply Guardian computer-use review to the Browser connector @johnl-oai
#47648 Support bearer tokens for app-server executor connections @euroelessar
#47649 Add opt-in OTLP logging for final agent responses @xli-oai
#47653 Attach inherited rollout history to diagnostic reports @dkovalenko-oai
#47654 Make Linux descriptor cleanup fork-safe @yuzhu-oai
#47655 Bump the exec-server stable compatibility test to Codex 0.156.1 @imac-oai
#47657 Restrict the default Bedrock GovCloud model catalog @jackz100
#47662 Expose tool dispatch and timing observations to extensions @euroelessar
#47663 Preserve managed network policy in route-aware transports @jackz100
#47665 Preserve early unified exec output in completion events @sdcoffey
#47670 Support model-specific descriptions for agent message board tools @eknight-oai
#47672 Fix no-reparse directory opens on Windows 10 @zm-oai
#47673 Clarify registered Windows sandbox setup errors @zm-oai
#47677 Support model catalog overrides for MCP resource tool specs @rhan-oai
#47678 Support quoted labels and ampersands in Mermaid flowcharts @etraut-openai
#47679 Add extension hooks for model requests and response streams @euroelessar
#47680 Add exec-server RPC timing and process startup tracing @anp-oai
#47683 Add executor capability discovery V2 infrastructure @TAFOYA-OAI
#47686 Make thread-owned Guardian context always enabled @felixxia-oai
#47688 Remove legacy Guardian authorization evidence paths @felixxia-oai
#47689 Make Guardian thread context capture unconditional @felixxia-oai
#47690 Remove obsolete Guardian context capture mode branches @felixxia-oai
#47691 Materialize rollout persistence for pending inter-agent messages @dermanyang-oai
#47693 Configure curl retries for DotSlash installation in CI @anp-oai
#47695 Repair rejected Windows sandbox credentials during provisioning @zm-oai
#47696 Avoid the shutdown timeout in the lagged-event test @jgershen-oai
#47698 Allow WebSocket test server shutdown while waiting for requests @jgershen-oai
#47701 Allow idle threads to prewarm and repair WebSocket connections @vkg-oai
#47703 Preserve account network policy for ChatGPT backend requests @jackz100
#47704 Fix spawn flag typing and isolate project configuration tests @seanh-oai
#47709 Route resume prewarm through the cached WebSocket session @vkg-oai
#47712 Update unified exec output buffers atomically @sdcoffey
#47713 Reduce dependency coupling in shared configuration crates @aibrahim-oai
#47714 Preserve tool result metadata more selectively under size limits @ningyi-oai
#47717 Avoid recursive TUI event dispatch for model picker selections @etraut-openai
#47741 Attribute tool telemetry to the invoking turn's product SKU @rennie-openai
#47742 Honor network policy in history notes and image generation extensions @jackz100
#47745 Skip startup prewarm preparation when the WebSocket is ready @vkg-oai
#47748 Align Cargo and Bazel Rust debug information defaults @aibrahim-oai
#47751 Reduce generic code duplication in RPC and Markdown rendering @aibrahim-oai
#47755 Centralize typed app-server response decoding @aibrahim-oai
#47757 Refactor tool telemetry product SKU matching to use an allowlist @rennie-openai
#47758 Preserve more tool metadata within outgoing message budgets @ningyi-oai
#47773 Honor catalog schemas for asynchronous user input @rhan-oai
#47797 Support close-on-exec attachments without changing PTY semantics @jif-oai
#47799 Enable terminal input approval by default @jif-oai
#47808 Allow hosts to provide agent controllers through ThreadManager @jif-oai
#47811 Preserve explicit user goal updates in Guardian authorization @felixxia-oai
#47813 Fix sleep interruption test event handling and fixture lifetime @felixxia-oai
#47814 Fix a lost wakeup in the unified exec termination test @felixxia-oai
#47817 Stabilize thread resume and memory dual-write tests @jif-oai
#47819 Retry Guardian reviews when authorization changes @teddywyly-oai
#47820 Add integration coverage for host agent controllers @jif-oai
#47824 Allow four concurrent threads in the multi-agent resume test @felixxia-oai
#47828 Wait for login completion in recommended plugin tests @felixxia-oai
#47830 Bind Guardian async scores to target environment permissions @jif-oai
#47832 Stabilize Rosetta test timing and retry delay telemetry @jif-oai
#47847 Keep the TUI responsive during clipboard copies @fcoury-oai
#47851 Preserve human overrides across repeated heartbeat instructions @felixxia-oai
#47852 Avoid blocking async proxy resolution on the system proxy cache @jif-oai
#47856 Initialize media estimates outside the global cache lock @jif-oai
#47858 Validate loaded plugins outside the cache lock @jif-oai
#47861 Avoid nested read locking when rendering browser sign-in @jif-oai
#47867 Render remote permission paths using executor context @iceweasel-oai
#47870 Add opt-in OTLP logging for Guardian assessments @jif-oai
#47871 Fix PID reservation test race and update guardian heartbeat snapshot @jif-oai
#47873 Measure deferred tool namespace fragments before and after truncation @mzeng-openai
#47879 Fix macOS system-alias matching in patch permission checks @felixxia-oai
#47881 Use Tokio's clock for TUI paste timing @charliemarsh-oai
#47886 Preserve diagnostic logs when SQLite logging fails @dkovalenko-oai
#47887 Warn users when SQLite diagnostic log writes fail @dkovalenko-oai
#47889 Include TUI client logs in diagnostic uploads @etraut-openai
#47891 Support client secrets for pre-registered MCP OAuth clients @willwang-openai
#47894 Clean up temporary Codex homes after TUI tests @fcoury-oai
#47896 Preserve Markdown formatting when copying transcript selections @fcoury-oai
#47898 Preserve local-binding inheritance in environment network policies @seanh-oai
#47899 Add diagnostic reasons to MCP attribution errors @peilin-openai
#47900 Default local threads to paginated history @owenlin0
#47901 Add bounded credential-storage telemetry helpers @celia-oai
#47902 Avoid repeated table clones during config merging @imac-oai
#47903 Move config key alias normalization ahead of merging @imac-oai
#47904 Support nested canonical paths in config key aliases @imac-oai
#47908 Alias tui.whimsy to tui.effects.starfield @imac-oai
#47912 Fix attestation routing during thread startup @charliemarsh-oai
#47913 Add an opt-in flag to defer mailbox preemption @jif-oai
#47915 Reuse verified V8 checksum manifests from the artifact cache @aibrahim-oai
#47918 Parameterize the turn-start originator header test @aibrahim-oai
#47919 Transport large Windows sandbox launch payloads through the environment @malsamiri-oai
#47920 Allow directory moves under global Seatbelt basename denies @chess-oai
#47922 Allow full-access Windows setup to provision through registered Core @zm-oai
#47924 Make project trust lookup paths explicit and defer root resolution @seanh-oai
#47926 Retry file blob uploads on HTTP 502 and 504 @mtsui-oai
#47927 Use 127.0.0.1 for local login redirects @willwang-openai
#47932 Remove GPT-5.4 from bundled catalogs and preserve migration prompts @andrewgu-oai
#47934 Apply the unchanged-model compaction shortcut to all session sources @hlevy-openai
#47935 Allow cached catalogs to satisfy MCP startup readiness @hlevy-openai
#47936 Make MCP and Code Mode input schema budgets configurable @vivi
#47937 Add direct replies for thread settings updates @sayan-oai
#47939 Separate selected plugin identities from MCP contributions @sayan-oai
#47943 Remove unused Windows world-writable audit code @iceweasel-oai
#47945 Parameterize the thread initialization analytics test by originator @eddie-openai
#47946 Add an in-memory agent message board for ephemeral sessions @jif-oai
#47947 Expand root authorization context to 16 messages @felixxia-oai
#47951 Use prebuilt V8 archives for Bazel on macOS and GNU Linux @aibrahim-oai
#47952 Prune expired in-memory message board registry entries @jif-oai
#47954 Move fullscreen startup tips into the transcript @etraut-openai
#47956 Support file references in image edit requests @kchainani-oai
#47957 Bound tool-call observations to the outgoing Responses message budget @ningyi-oai
#47962 Request transparent huge pages for Cargo and eligible Bazel rustc jobs @aibrahim-oai
#47964 Preserve the client-agent header for Amazon Bedrock Runtime @celia-oai
#47967 Surface Flex capacity failures as a distinct terminal error @sdcoffey
#47968 Handle Btrfs device mismatches when masking daemon sockets @etraut-openai
#47970 Expose current environment selections for a running turn @sayan-oai
#47971 Add Pro Max plan support and update Pro display names @etraut-openai
#47974 Preserve Git directory protections across writable roots @aionescu-oai
#47975 Prevent stale voice answers from reappearing during speech recovery @etraut-openai
#47981 Prepare MCP calls directly from advertised tool identities @hlevy-openai
#47984 Add multi-agent spawn latency and failure metrics @owenlin0
#47988 Reuse MCP handlers across equivalent bindings @hlevy-openai
#47989 Add startup-only PID namespace inheritance to exec-server @open-matt
#48004 Respect configured authentication in the thread manager sample @celia-oai
#48015 Validate tool suggestion install URLs before showing the app link @aionescu-oai
#48017 Test same-cell permission grants and strict review in code mode @anp-oai
#48035 Remove plugin extension metadata from discovery and summaries @victor-openai
#48060 Deduplicate retained instructions across Guardian reviews @felixxia-oai
#48069 Handle early command yields in the Guardian network approval test @jif-oai
#48072 Skip message-board notification previews when there are no recipients @jif-oai
#48073 Avoid stdin approval for runtime-only permission grants @jif-oai
#48077 Add Serde support to agent message board request types @jif-oai
#48078 Replay exec-server shell snapshots through unnamed files @jif-oai
#48098 Preserve recent authorization context for Guardian reviews @felixxia-oai
#48099 Honor shell environment policy in legacy snapshots @jif-oai
#48100 Add an HTTP client for remote agent message boards @jif-oai
#48101 Show multiline command previews in /ps @etraut-openai
#48109 Deduplicate retained instructions against Guardian transcripts @felixxia-oai
#48110 Deduplicate retained instructions in async Guardian context @felixxia-oai
#48115 Preserve user text parts during local compaction @felixxia-oai
#48116 Allow reasoning shortcuts to reach Max @etraut-openai
#48118 Add configurable right-click paste to the fullscreen TUI @fcoury-oai
#48119 Prevent worker completion races in the guardian authorization test @felixxia-oai
#48121 Keep startup drafts visible during command center session handoff @etraut-openai
#48123 Add early yielding for code-mode observations @pakrym-oai
#48130 Use request notifications in the cloud config loader lifetime test @felixxia-oai
#48132 Allow Left to open the command center from read-only conversations @etraut-openai

`v0.157.1`: 0.157.1

Compare Source

Chores

Release highlights could not be determined: the supplied PR index is empty, and the GitHub tag comparison returned 404.

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.157.0...rust-v0.157.1

`v0.157.0`: 0.157.0

Compare Source

New Features

Added GPT-6 Sol and Luna, including Amazon Bedrock support and migration prompts for older models. (#47332, #47347)
Enabled fullscreen transcripts by default and added Shift-click to extend text selections. (#47178, #47414)
Enabled automatic background-server startup for eligible interactive sessions, with recovery choices when server settings are incompatible. (#47179, #47318)
Added an f shortcut to fork conversations open in another app, preserving drafts and queued prompts. (#47185)
Made /import available in remote sessions and local background-server sessions. (#47317)
Improved terminal rendering with Unicode bullets, checkboxes, aligned equations, and optimization notation. (#47191, #47322)

Bug Fixes

Preserved active voice conversations when switching threads. (#47381)
Recovered unsent question answers into the composer when turns end, without disrupting active history searches. (#47422, #47423)
Respected tmux mouse settings and restored native scrollback for Terminal.app over SSH in automatic screen mode. (#47399, #47417)
Fixed configured proxy routing for realtime connections and standalone web search, including search redirects. (#47101, #47142, #47204)
Added retries for transient file-upload failures and increased the upload timeout to five minutes. (#47122, #47393)
Enforced network restrictions across redirects and ongoing HTTP and WebSocket traffic, including cancellation when policy changes revoke access. (#47389, #47407)

Changelog

Full Changelog: https://github.com/openai/codex/compare/rust-v0.156.0...rust-v0.157.0

#47063 Add a partial index for agent message board root posts @jif-oai
#47064 Stop redundant message-board reads when limits reach one @jif-oai
#47065 Deduplicate deprecation notices in the TUI transcript @etraut-openai
#47068 Highlight selected newlines in the transcript view @etraut-openai
#47073 Wait for thread idle in Guardian context budget tests @jif-oai
#47074 Refresh host-supplied cloud skills at turn startup @TAFOYA-OAI
#47075 Include attributed previews in agent message board notifications @jif-oai
#47077 Serialize environment updates and cancel removed pending attachments @sayan-oai
#47079 Mask daemon socket paths exposed through ancestor bind mounts @nicksteele-oai
#47081 Track cumulative MCP attribution across requests and thread history @peilin-openai
#47082 Show the voice toggle in the TUI shortcut overlay @etraut-openai
#47083 Extract per-thread enrichment into a dedicated async helper @aibrahim-oai
#47084 Avoid building a host SQLite driver for SQLx macros @aibrahim-oai
#47085 Update model catalog descriptions and GPT-5.6-Sol priority @andrewgu-oai
#47086 Format analytics credit usage with consistent decimal precision @fcoury-oai
#47088 Disable unused default dependency features @aibrahim-oai
#47089 Centralize JSON-RPC response serialization through payloads @aibrahim-oai
#47094 Restrict Unix local MCP servers to stdio descriptors @yuzhu-oai
#47095 Remove the rust-release-prepare workflow @andrewgu-oai
#47096 Keep TUI hints immediately above the composer @fcoury-oai
#47100 Preserve assistant answers in bounded TUI task responses @etraut-openai
#47101 Honor configured proxies for realtime WebSocket connections @celia-oai
#47106 Preserve originating turn metadata for yielded skill calls @eddie-openai
#47108 Preserve required Windows runtime variables for filesystem helpers @iceweasel-oai
#47112 Lowercase the retry hint for conversations open in another app @fcoury-oai
#47113 Persist thread creator identity in rollouts and SQLite @nornagon-openai
#47114 Preserve and expose thread item lifecycle timestamps @chiam-oai
#47116 Honor the configured product SKU in remote plugin requests @jessedu-oai
#47118 Support model-catalog overrides for Code Mode tool messages @rhan-oai
#47121 Pass thread IDs to attachment uploads @kchainani-oai
#47122 Increase OpenAI file blob upload timeout from 60 seconds to 5 minutes @wilkes-oai
#47125 Add extra policy configuration for Guardian reviews @won-openai
#47129 Preserve foreign working directories in extension tool environments @anp-oai
#47130 Remove the ultrafast service tier from gpt-5.6-sol @andrewgu-oai
#47132 Support caller-provided MITM CAs in the network proxy @viyatb-oai
#47137 Prevent horizontal transcript selection from triggering autoscroll @imac-oai
#47142 Honor system proxy settings for standalone web search @celia-oai
#47143 Extract exec-server CLI startup into a dedicated module @anp-oai
#47149 Update code mode catalog snapshot hashes @andrewgu-oai
#47155 Ignore stale thread-close notifications after resuming a thread @etraut-openai
#47158 Harden gateway OAuth credential persistence and error redaction @alexsong-oai
#47159 Expose HTTP origins in MCP server status @frantic-openai
#47162 Apply workspace routing to Guardian v2 classifier requests @acrognale-oai
#47170 Add explicit gateway login control and authentication status @alexsong-oai
#47174 Preserve empty cell metadata under pending tool-call pressure @ningyi-oai
#47178 Enable the fullscreen transcript by default @etraut-openai
#47179 Enable automatic daemon startup by default @etraut-openai
#47185 Allow forking conversations locked by another app in the TUI @fcoury-oai
#47191 Render aligned equations and optimization notation in TUI math @etraut-openai
#47199 Separate thread preparation from execution persistence @dermanyang-oai
#47204 Resolve proxy routes for standalone web search redirects @celia-oai
#47207 Add explicit gateway OAuth sign-in to app-server @alexsong-oai
#47212 Preserve MCP request trace context across transport workers @bromano-oai
#47235 Route multi-agent spawning through SpawnRequest @jif-oai
#47236 Suppress agent message board notifications to the post author @jif-oai
#47240 Prevent V2 agent eviction from racing with queued messages @jif-oai
#47244 Centralize agent resume handling in LocalAgentControl @jif-oai
#47248 Add explicit app and account targets to MCP resource reads @victor-openai
#47249 Drop descendant channel posts from retained remote compaction v2 history @jif-oai
#47252 Return agent snapshots from close_agent @jif-oai
#47257 Preserve explicit message-board unsubscribes when posting @jif-oai
#47258 Test spawn settings reporting after child removal @jif-oai
#47259 Subscribe authors to message-board channels created by posting @jif-oai
#47263 Expose hosted plugin extensions in app-server summaries @victor-openai
#47267 Stream agent snapshots from local status subscriptions @jif-oai
#47271 Implement AgentControl for LocalAgentControl @jif-oai
#47272 Allow Guardian sync review across compaction hash differences @felixxia-oai
#47275 Enable Guardian thread context by default @felixxia-oai
#47281 Add regression coverage for message board unsubscribe persistence @jif-oai
#47287 Update the Guardian extra-policy snapshot for retained instructions @felixxia-oai
#47292 Consolidate agent operations in the AgentControl implementation @jif-oai
#47301 Separate local agent runtime state from controller handles @jif-oai
#47302 Use compact display metadata for Guardian review threads @charliemarsh-oai
#47303 Clean up legacy Guardian thread metadata in SQLite @charliemarsh-oai
#47317 Enable /import in remote and local daemon sessions @etraut-openai
#47318 Offer explicit recovery for incompatible background servers @etraut-openai
#47319 Match agent status symbols to the selected row style @etraut-openai
#47320 Fix Escape navigation in read-only agent sessions @etraut-openai
#47321 Honor the system clock preference across more TUI timestamps @etraut-openai
#47322 Render TUI Markdown lists with Unicode bullets and checkboxes @etraut-openai
#47323 Persist resume metadata in compaction checkpoints @owenlin0
#47325 Keep report reason tags within Sentry limits @ningyi-oai
#47326 Restrict MCP OAuth authorization endpoints to HTTP(S) @viyatb-oai
#47327 Preserve image generation request IDs on failure @chrisdong-oai
#47329 Standardize TUI menu description wording and punctuation @etraut-openai
#47330 Identify failed SQLite databases in codex doctor output @dkovalenko-oai
#47331 Avoid redundant spacing above the transcript composer @fcoury-oai
#47332 Add GPT-6 Sol and Luna to the model catalog @andrewgu-oai
#47338 Move the activity inspection hint into keyboard shortcut help @fcoury-oai
#47340 Add conditional turn interruption that preserves pending input @pmccrary-oai
#47342 Skip stored title lookups for ephemeral forks @keyz
#47347 Add GPT-6 Sol and Luna to Amazon Bedrock catalogs @celia-oai
#47348 Overlap subagent spawn persistence and clean up cancelled children @owenlin0
#47349 Move plugin recommendations into developer context @adaley-openai
#47350 Reuse cloud skill catalogs across turns until invalidated @hlevy-openai
#47353 Preserve invalid_prompt as a distinct error classification @rennie-openai
#47355 Reserve spacing after recaps at the transcript tail @fcoury-oai
#47358 Color paths and URLs in codex doctor by check status @dkovalenko-oai
#47360 Preserve user prompt URL destinations across terminal widths @fcoury-oai
#47361 Restrict Windows sandbox default object access to the logon session @viyatb-oai
#47362 Bound inbound exec-server requests across client transports @viyatb-oai
#47365 Resume model context from the latest compaction boundary @owenlin0
#47369 Overlap agent metadata reads when resuming a V2 root @vkg-oai
#47375 Add an opt-in preference for the local MXC sandbox @iceweasel-oai
#47377 Add opt-in reasoning status for realtime V3 delegations @guinness-oai
#47380 Route TUI voice controls through the app @etraut-openai
#47381 Keep voice conversations running across TUI thread navigation @etraut-openai
#47382 Show a voice badge in the agents overview @etraut-openai
#47384 Restore composer hints after clearing selection at the transcript bottom @fcoury-oai
#47389 Enforce network policy throughout HTTP and WebSocket requests @acrognale-oai
#47393 Retry transient OpenAI file blob upload failures @mtsui-oai
#47397 Refresh bundled model metadata and instructions @andrewgu-oai
#47399 Respect tmux mouse settings in fullscreen and overlays @fcoury-oai
#47407 Enforce application network policy across app-server requests @acrognale-oai
#47408 Enforce application network policy for AWS auth and telemetry @acrognale-oai
#47410 Honor network policy in remote control and recover remote execution @acrognale-oai
#47411 Apply shared network policy throughout embedded Codex startup @acrognale-oai
#47413 Cache decrypted gateway OAuth secrets per backend @charliemarsh-oai
#47414 Support Shift-click to extend transcript selections @etraut-openai
#47417 Use native scrollback for Terminal.app over SSH in auto mode @fcoury-oai
#47422 Recover unsent question drafts when TUI turns end @imac-oai
#47423 Preserve history search during background draft recovery @imac-oai
#47424 Clear pending async question notifications when turns end @imac-oai
#47428 Apply inherited environment settings at turn boundaries @sayan-oai
#47435 Allow environment selection updates during an active turn @sayan-oai
#47437 Stabilize retry timing and WebSocket tests @anp-oai

Configuration

📅 Schedule: (UTC)

Branch creation
- At any time (no schedule defined)
Automerge
- At any time (no schedule defined)

🚦 Automerge: Enabled.

♻ Rebasing: Whenever PR is behind base branch, or you tick the rebase/retry checkbox.

🔕 Ignore: Close this PR and you won't be reminded about this update again.

If you want to rebase/retry this PR, check this box

This PR has been generated by Mend Renovate CLI.

This PR contains the following updates: | Package | Update | Change | |---|---|---| | [openai/codex](https://github.com/openai/codex) | minor | `0.156.1` → `0.163.0` | --- ### Release Notes <details> <summary>openai/codex</summary> ### [`v0.163.0`](https://github.com/openai/codex/releases/tag/rust-v0.163.0): 0.163.0 [Compare Source](https://github.com/openai/codex/compare/rust-v0.162.1...rust-v0.163.0-alpha.11.2) #### New Features - Open `/config` to search preferences across categories, change supported settings immediately, and see which changes require a restart. ([#52990](https://github.com/openai/codex/issues/52990), [#53429](https://github.com/openai/codex/issues/53429)) - Send a follow-up while Codex is responding to steer it immediately. Interrupting a turn also stops active Code Mode cells and their nested tool calls. ([#51812](https://github.com/openai/codex/issues/51812), [#51835](https://github.com/openai/codex/issues/51835)) - Configure a leader key in `/keymap`. The default is `Ctrl+X`, shortcut hints stay open until you choose or cancel, and voice mute moves to `F9`. ([#52273](https://github.com/openai/codex/issues/52273)) - Restart a managed background server from `/daemon`. Codex warns about work the restart could interrupt, then reconnects automatically. ([#53173](https://github.com/openai/codex/issues/53173)) - Codex can run independent read-only tools in parallel, including skill, memory, and conversation-history lookups. ([#52245](https://github.com/openai/codex/issues/52245)) - Daybreak is enabled by default for eligible accounts. `codex exec` can also select it with an OpenAI API key when the server offers access. ([#53701](https://github.com/openai/codex/issues/53701), [#53717](https://github.com/openai/codex/issues/53717)) #### Bug Fixes - Resuming a saved thread restores its permissions and network approvals, while respecting explicit overrides and current managed policy. ([#53150](https://github.com/openai/codex/issues/53150), [#53419](https://github.com/openai/codex/issues/53419), [#53424](https://github.com/openai/codex/issues/53424)) - The network proxy now checks permission before a DNS lookup, rejects duplicate `Host` headers, and prevents credential aliases from bypassing inspection hooks. ([#51650](https://github.com/openai/codex/issues/51650), [#52661](https://github.com/openai/codex/issues/52661), [#53506](https://github.com/openai/codex/issues/53506)) - Return to an existing side conversation with `/side` after switching threads. Answers to pending prompts also go back to the thread that asked. ([#52184](https://github.com/openai/codex/issues/52184), [#53436](https://github.com/openai/codex/issues/53436)) - On Windows, `Ctrl+V` and `Shift+Insert` paste text as well as images. On WSL, repeated pastes reuse the clipboard reader, and copy attempts time out instead of hanging. ([#53224](https://github.com/openai/codex/issues/53224), [#52967](https://github.com/openai/codex/issues/52967), [#53453](https://github.com/openai/codex/issues/53453)) - Local commands finish promptly when a child keeps an output pipe open. Remote commands preserve late-arriving output so the final poll can still collect it. ([#52652](https://github.com/openai/codex/issues/52652), [#53331](https://github.com/openai/codex/issues/53331), [#53622](https://github.com/openai/codex/issues/53622)) - `codex exec` no longer prints the same file diff again after an unrelated command. ([#53444](https://github.com/openai/codex/issues/53444)) #### Documentation - Updated the bundled OpenAI Docs guidance for migrations to the GPT-6 family, including model-specific reasoning, tool use, and data residency considerations. ([#51768](https://github.com/openai/codex/issues/51768)) - Clarified how the Linux sandbox uses bubblewrap for filesystem isolation and seccomp for syscall filtering. ([#52610](https://github.com/openai/codex/issues/52610)) #### Chores - Codex now uses its standard shell executor and no longer bundles a patched `zsh`. Configurations using the retired shell flags receive a migration notice. ([#52160](https://github.com/openai/codex/issues/52160), [#52213](https://github.com/openai/codex/issues/52213)) - Reduced Linux and macOS release package size by stripping symbols from packaged binaries while preserving them in the original build outputs. ([#52178](https://github.com/openai/codex/issues/52178)) #### Changelog Full Changelog: <https://github.com/openai/codex/compare/rust-v0.162.0...rust-v0.163.0> - [#51539](https://github.com/openai/codex/issues/51539) Add completion-aware realtime attachment and session-scoped detach [@zahan-oai](https://github.com/zahan-oai) - [#51547](https://github.com/openai/codex/issues/51547) Add a Windows MXC sandbox opt-out [@iceweasel-oai](https://github.com/iceweasel-oai) - [#51556](https://github.com/openai/codex/issues/51556) Complete dynamic tool lifecycles on cancellation [@mikelam-oai](https://github.com/mikelam-oai) - [#51575](https://github.com/openai/codex/issues/51575) Expose package assembly helpers and support gzip DotSlash artifacts [@bolinfest](https://github.com/bolinfest) - [#51595](https://github.com/openai/codex/issues/51595) Add thread ID exclusions to `thread/list` [@btraut-openai](https://github.com/btraut-openai) - [#51602](https://github.com/openai/codex/issues/51602) Distinguish thread listing failures from exhausted history [@btraut-openai](https://github.com/btraut-openai) - [#51611](https://github.com/openai/codex/issues/51611) Signal abandonment of unanswered MCP elicitations [@nicksteele-oai](https://github.com/nicksteele-oai) - [#51627](https://github.com/openai/codex/issues/51627) Stabilize Guardian snapshot prefixes by separating assistant context [@jif-oai](https://github.com/jif-oai) - [#51642](https://github.com/openai/codex/issues/51642) Fix retained context handling for typed section content [@jif-oai](https://github.com/jif-oai) - [#51650](https://github.com/openai/codex/issues/51650) Require hostname authorization before proxy DNS lookups [@jif-oai](https://github.com/jif-oai) - [#51651](https://github.com/openai/codex/issues/51651) Persist Guardian review failures for reports across restarts [@jif-oai](https://github.com/jif-oai) - [#51652](https://github.com/openai/codex/issues/51652) Record telemetry for AGENTS.md changes made by apply_patch [@jif-oai](https://github.com/jif-oai) - [#51678](https://github.com/openai/codex/issues/51678) Move Windows sandbox tests into a dedicated integration binary [@jif-oai](https://github.com/jif-oai) - [#51683](https://github.com/openai/codex/issues/51683) Roll back stale Guardian reviews before reusing reviewer history [@olliem-oai](https://github.com/olliem-oai) - [#51689](https://github.com/openai/codex/issues/51689) Wait for helper completion in HTTP header cancellation tests [@jif-oai](https://github.com/jif-oai) - [#51690](https://github.com/openai/codex/issues/51690) Add a feature flag for Code Mode tool description ordering [@swastik-oai](https://github.com/swastik-oai) - [#51704](https://github.com/openai/codex/issues/51704) Honor tool-description-first ordering in Code Mode [@swastik-oai](https://github.com/swastik-oai) - [#51710](https://github.com/openai/codex/issues/51710) Fix a discovery race in the external auth refresh test [@jgershen-oai](https://github.com/jgershen-oai) - [#51734](https://github.com/openai/codex/issues/51734) Load persisted sender context for Guardian reviews [@jif-oai](https://github.com/jif-oai) - [#51755](https://github.com/openai/codex/issues/51755) Reuse MCP handler metadata for cache comparisons [@owenlin0](https://github.com/owenlin0) - [#51761](https://github.com/openai/codex/issues/51761) Reduce tool metadata cloning in the code-mode runtime [@akira-oai](https://github.com/akira-oai) - [#51768](https://github.com/openai/codex/issues/51768) Expand OpenAI Docs migration guidance to the GPT-6 model family [@kkahadze-oai](https://github.com/kkahadze-oai) - [#51775](https://github.com/openai/codex/issues/51775) Prevent recursive Tokio tracing in telemetry and SQLite logs [@zbarsky-openai](https://github.com/zbarsky-openai) - [#51786](https://github.com/openai/codex/issues/51786) Preserve sandbox overrides across execution requests [@iceweasel-oai](https://github.com/iceweasel-oai) - [#51794](https://github.com/openai/codex/issues/51794) Advertise Ultrafast for GPT-6.1 Sol on Amazon Bedrock [@celia-oai](https://github.com/celia-oai) - [#51800](https://github.com/openai/codex/issues/51800) Remove duplicate field initializers in extension registry tests [@anp-oai](https://github.com/anp-oai) - [#51808](https://github.com/openai/codex/issues/51808) Preserve diagnostic reasons for MCP user verification failures [@berkdeniz-oai](https://github.com/berkdeniz-oai) - [#51812](https://github.com/openai/codex/issues/51812) Enable instant interrupts by default [@pakrym-oai](https://github.com/pakrym-oai) - [#51819](https://github.com/openai/codex/issues/51819) Migrate the MXC sandbox to the 1.0.0 SDK [@iceweasel-oai](https://github.com/iceweasel-oai) - [#51822](https://github.com/openai/codex/issues/51822) Avoid sharing violations when repairing Windows runtime ACLs [@johnl-oai](https://github.com/johnl-oai) - [#51823](https://github.com/openai/codex/issues/51823) Share MCP binding tool metadata with prepared calls [@owenlin0](https://github.com/owenlin0) - [#51828](https://github.com/openai/codex/issues/51828) Add policy-based file contents integrity checks [@iceweasel-oai](https://github.com/iceweasel-oai) - [#51831](https://github.com/openai/codex/issues/51831) Add MXC sandbox integrity dependency and policy preparation [@iceweasel-oai](https://github.com/iceweasel-oai) - [#51835](https://github.com/openai/codex/issues/51835) Enable code mode interruption by default [@won-openai](https://github.com/won-openai) - [#51840](https://github.com/openai/codex/issues/51840) Add a bubblewrap backend for sandbox integrity checks [@iceweasel-oai](https://github.com/iceweasel-oai) - [#51841](https://github.com/openai/codex/issues/51841) Add a macOS Seatbelt backend for sandbox integrity [@iceweasel-oai](https://github.com/iceweasel-oai) - [#51842](https://github.com/openai/codex/issues/51842) Add a sandbox integrity runner with outcome and timing metrics [@iceweasel-oai](https://github.com/iceweasel-oai) - [#51843](https://github.com/openai/codex/issues/51843) Run sandbox integrity checks before commands and filesystem operations [@iceweasel-oai](https://github.com/iceweasel-oai) - [#51847](https://github.com/openai/codex/issues/51847) Preserve Cargo package names in Bazel Rust builds [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#51848](https://github.com/openai/codex/issues/51848) Align Bazel release builds with Cargo and fix platform compatibility [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#51849](https://github.com/openai/codex/issues/51849) Fix package smoke tests for Cargo and Bazel debug symbols [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#51850](https://github.com/openai/codex/issues/51850) Add Bazel release staging archives [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#51855](https://github.com/openai/codex/issues/51855) Add Bazel support to the Codex package build action [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#51856](https://github.com/openai/codex/issues/51856) Build Bazel release artifacts alongside Cargo artifacts [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#51857](https://github.com/openai/codex/issues/51857) Add an app-server prompt prefix compatibility test [@jif-oai](https://github.com/jif-oai) - [#51865](https://github.com/openai/codex/issues/51865) Use readable plugin mentions without suppressing same-name skills [@canvrno-oai](https://github.com/canvrno-oai) - [#51866](https://github.com/openai/codex/issues/51866) Preserve line breaks and links in multiline async questions [@pash-openai](https://github.com/pash-openai) - [#51868](https://github.com/openai/codex/issues/51868) Record tool registration metrics for each sampling request [@akira-oai](https://github.com/akira-oai) - [#51872](https://github.com/openai/codex/issues/51872) Keep global app-server config independent of the launch directory [@etraut-openai](https://github.com/etraut-openai) - [#51884](https://github.com/openai/codex/issues/51884) Add experimental prediction forks that inherit parent context [@liame-oai](https://github.com/liame-oai) - [#51890](https://github.com/openai/codex/issues/51890) Add the missing `mxc-sdk` UTF-8 resource patch for Bazel [@iceweasel-oai](https://github.com/iceweasel-oai) - [#51892](https://github.com/openai/codex/issues/51892) Preserve tool call completeness when recorded arguments are truncated [@ningyi-oai](https://github.com/ningyi-oai) - [#51893](https://github.com/openai/codex/issues/51893) Record metrics for incremental tool updates [@akira-oai](https://github.com/akira-oai) - [#51895](https://github.com/openai/codex/issues/51895) Report specific reasons for WebSocket continuation failures [@pakrym-oai](https://github.com/pakrym-oai) - [#51896](https://github.com/openai/codex/issues/51896) Preserve native errors in Windows sandbox ACL diagnostics [@alishobeiri-oai](https://github.com/alishobeiri-oai) - [#51897](https://github.com/openai/codex/issues/51897) Use a dedicated matcher for network domain policies [@rafael-oai](https://github.com/rafael-oai) - [#51908](https://github.com/openai/codex/issues/51908) Honor the user input setting for asynchronous questions [@mandal-OAI](https://github.com/mandal-OAI) - [#51930](https://github.com/openai/codex/issues/51930) Support model-specific function description prefixes [@tz-openai](https://github.com/tz-openai) - [#51963](https://github.com/openai/codex/issues/51963) Attribute compaction analytics to the correct voice session [@reia-oai](https://github.com/reia-oai) - [#51974](https://github.com/openai/codex/issues/51974) Log Windows sandbox availability and backend selection [@iceweasel-oai](https://github.com/iceweasel-oai) - [#52034](https://github.com/openai/codex/issues/52034) Preserve agent state when unloading idle multi-agent v2 children [@jif-oai](https://github.com/jif-oai) - [#52040](https://github.com/openai/codex/issues/52040) Add regression coverage for cancelled agent reloads [@jif-oai](https://github.com/jif-oai) - [#52048](https://github.com/openai/codex/issues/52048) Cover instant interruption in steered-input persistence tests [@jif-oai](https://github.com/jif-oai) - [#52061](https://github.com/openai/codex/issues/52061) Run Guardian conversation classifiers concurrently and preserve action order [@felixxia-oai](https://github.com/felixxia-oai) - [#52062](https://github.com/openai/codex/issues/52062) Add scenario coverage for worker context across idle eviction [@jif-oai](https://github.com/jif-oai) - [#52065](https://github.com/openai/codex/issues/52065) Require assessment text in the Guardian parser [@ioanbudea-OAI](https://github.com/ioanbudea-OAI) - [#52081](https://github.com/openai/codex/issues/52081) Fix idle cleanup for disconnected multi-agent v2 children [@jif-oai](https://github.com/jif-oai) - [#52119](https://github.com/openai/codex/issues/52119) Expose originating tool call metadata in command environments [@leo-oai](https://github.com/leo-oai) - [#52160](https://github.com/openai/codex/issues/52160) Remove the patched zsh shell execution backend [@jif-oai](https://github.com/jif-oai) - [#52164](https://github.com/openai/codex/issues/52164) Make environment context date and timezone configurable [@surajs-oai](https://github.com/surajs-oai) - [#52176](https://github.com/openai/codex/issues/52176) Show AWS GovCloud guidance at startup and remember acknowledgment [@jackz100](https://github.com/jackz100) - [#52177](https://github.com/openai/codex/issues/52177) Set a User-Agent for package archive downloads [@bolinfest](https://github.com/bolinfest) - [#52178](https://github.com/openai/codex/issues/52178) Strip symbols from source-built release package binaries [@bolinfest](https://github.com/bolinfest) - [#52182](https://github.com/openai/codex/issues/52182) Expose a verified sandbox launcher to local MCP servers [@bolinfest](https://github.com/bolinfest) - [#52183](https://github.com/openai/codex/issues/52183) Add optional descriptions to agent message board channels [@jif-oai](https://github.com/jif-oai) - [#52184](https://github.com/openai/codex/issues/52184) Preserve side conversations across thread navigation [@etraut-openai](https://github.com/etraut-openai) - [#52193](https://github.com/openai/codex/issues/52193) Enforce managed MXC requirements on Windows [@iceweasel-oai](https://github.com/iceweasel-oai) - [#52195](https://github.com/openai/codex/issues/52195) Track source attribution for individual context parts [@tz-openai](https://github.com/tz-openai) - [#52200](https://github.com/openai/codex/issues/52200) Allow plugin toggles while searching and preserve filters on refresh [@fcoury-oai](https://github.com/fcoury-oai) - [#52203](https://github.com/openai/codex/issues/52203) Expose Codex lifecycle status in iTerm2 sessions [@fcoury-oai](https://github.com/fcoury-oai) - [#52213](https://github.com/openai/codex/issues/52213) Stop bundling patched zsh in Codex packages [@jif-oai](https://github.com/jif-oai) - [#52215](https://github.com/openai/codex/issues/52215) Enforce application network policy in standalone MCP commands [@lsingh-oai](https://github.com/lsingh-oai) - [#52220](https://github.com/openai/codex/issues/52220) Add configurable default plugin activation policy [@stevenlee-oai](https://github.com/stevenlee-oai) - [#52223](https://github.com/openai/codex/issues/52223) Enforce application network policy for daemon updates [@jackz100](https://github.com/jackz100) - [#52225](https://github.com/openai/codex/issues/52225) Fix config rebuild call in the Windows MXC preference test [@virajrai-oai](https://github.com/virajrai-oai) - [#52226](https://github.com/openai/codex/issues/52226) Include foreground activity in iTerm2 session status [@fcoury-oai](https://github.com/fcoury-oai) - [#52228](https://github.com/openai/codex/issues/52228) Honor API-key feature gates in TUI Daybreak selection [@julee-oai](https://github.com/julee-oai) - [#52234](https://github.com/openai/codex/issues/52234) Support request IDs in exec-server WebSocket handshakes [@mattj-openai](https://github.com/mattj-openai) - [#52235](https://github.com/openai/codex/issues/52235) Recover gRPC code-mode sessions after missing-session errors [@surajs-oai](https://github.com/surajs-oai) - [#52241](https://github.com/openai/codex/issues/52241) Preserve subagent capabilities independently of forked history [@anp-oai](https://github.com/anp-oai) - [#52245](https://github.com/openai/codex/issues/52245) Enable parallel execution for read-only tools [@zamoshchin-openai](https://github.com/zamoshchin-openai) - [#52250](https://github.com/openai/codex/issues/52250) Add opt-in Guardian trust for orchestrator connector identities [@ankushg](https://github.com/ankushg) - [#52256](https://github.com/openai/codex/issues/52256) Normalize formatting in docs, web assets, and sample scripts [@anp-oai](https://github.com/anp-oai) - [#52268](https://github.com/openai/codex/issues/52268) Preserve large arguments in executed tool call metadata [@ningyi-oai](https://github.com/ningyi-oai) - [#52270](https://github.com/openai/codex/issues/52270) Enable text selection in the fullscreen TUI footer [@fcoury-oai](https://github.com/fcoury-oai) - [#52273](https://github.com/openai/codex/issues/52273) Add configurable persistent leader shortcuts to the TUI [@fcoury-oai](https://github.com/fcoury-oai) - [#52274](https://github.com/openai/codex/issues/52274) Add structured tracing for Guardian reviews and background scoring [@ioanbudea-OAI](https://github.com/ioanbudea-OAI) - [#52277](https://github.com/openai/codex/issues/52277) Preserve UTF-8 byte semantics in network domain matching [@rafael-oai](https://github.com/rafael-oai) - [#52278](https://github.com/openai/codex/issues/52278) Honor custom OTLP metrics exporters when analytics is disabled [@jackz100](https://github.com/jackz100) - [#52288](https://github.com/openai/codex/issues/52288) Remove duplicate field initializers from extension registry tests [@anp-oai](https://github.com/anp-oai) - [#52295](https://github.com/openai/codex/issues/52295) Emit one developer notice per incremental namespace update batch [@akira-oai](https://github.com/akira-oai) - [#52299](https://github.com/openai/codex/issues/52299) Make Bazel release jobs advisory [@anp-oai](https://github.com/anp-oai) - [#52302](https://github.com/openai/codex/issues/52302) Add opt-in credential masking for proxied sandboxed sessions [@winston-openai](https://github.com/winston-openai) - [#52304](https://github.com/openai/codex/issues/52304) Persist remote-control RPC preferences in managed daemon settings [@etraut-openai](https://github.com/etraut-openai) - [#52325](https://github.com/openai/codex/issues/52325) Track history initialization in Responses turn metadata [@anp-oai](https://github.com/anp-oai) - [#52329](https://github.com/openai/codex/issues/52329) Remove per-content source attribution metadata [@anp-oai](https://github.com/anp-oai) - [#52330](https://github.com/openai/codex/issues/52330) Clamp wrapped source ranges before remapping terminal hyperlinks [@bc-openai](https://github.com/bc-openai) - [#52337](https://github.com/openai/codex/issues/52337) Add durable thread read state with revision-checked updates [@btraut-openai](https://github.com/btraut-openai) - [#52350](https://github.com/openai/codex/issues/52350) Expose experimental durable thread read state in the app server [@btraut-openai](https://github.com/btraut-openai) - [#52363](https://github.com/openai/codex/issues/52363) Expand realtime v3 voice support [@jacksonmoody-oai](https://github.com/jacksonmoody-oai) - [#52381](https://github.com/openai/codex/issues/52381) Preserve per-session routing for gRPC code mode [@cassirer-openai](https://github.com/cassirer-openai) - [#52384](https://github.com/openai/codex/issues/52384) Notify subscribers when thread read state changes [@btraut-openai](https://github.com/btraut-openai) - [#52395](https://github.com/openai/codex/issues/52395) Add experimental app-server thread read-state updates [@btraut-openai](https://github.com/btraut-openai) - [#52418](https://github.com/openai/codex/issues/52418) Avoid an extra blank quote line when pasting text with a trailing newline [@bc-openai](https://github.com/bc-openai) - [#52535](https://github.com/openai/codex/issues/52535) Add opt-in history prefix preservation for full agent forks [@jif-oai](https://github.com/jif-oai) - [#52557](https://github.com/openai/codex/issues/52557) Forward clipboard copies to the terminal in Herdr sessions [@fcoury-oai](https://github.com/fcoury-oai) - [#52568](https://github.com/openai/codex/issues/52568) Expose message board permissions and structured denials [@jif-oai](https://github.com/jif-oai) - [#52591](https://github.com/openai/codex/issues/52591) Fix races in remote environment and session replacement tests [@jif-oai](https://github.com/jif-oai) - [#52608](https://github.com/openai/codex/issues/52608) Upgrade `hyper` to 1.11.1 and test connection closure [@jif-oai](https://github.com/jif-oai) - [#52610](https://github.com/openai/codex/issues/52610) Align Linux sandbox names and docs with bubblewrap and seccomp [@bolinfest](https://github.com/bolinfest) - [#52621](https://github.com/openai/codex/issues/52621) Add template setup for local agent message boards [@jif-oai](https://github.com/jif-oai) - [#52629](https://github.com/openai/codex/issues/52629) Consolidate local message board storage helpers [@jif-oai](https://github.com/jif-oai) - [#52635](https://github.com/openai/codex/issues/52635) Skip background workspace routing reads without ChatGPT auth [@joesavona](https://github.com/joesavona) - [#52637](https://github.com/openai/codex/issues/52637) Add experimental thread item lookup by ID [@btraut-openai](https://github.com/btraut-openai) - [#52640](https://github.com/openai/codex/issues/52640) Count interrupted goal continuations toward the no-activity limit [@etraut-openai](https://github.com/etraut-openai) - [#52648](https://github.com/openai/codex/issues/52648) Limit daemon feature compatibility checks to explicit CLI overrides [@etraut-openai](https://github.com/etraut-openai) - [#52652](https://github.com/openai/codex/issues/52652) Bound local exec-server output draining after process exit [@jif-oai](https://github.com/jif-oai) - [#52659](https://github.com/openai/codex/issues/52659) Add an opt-in feature for subagent model context defaults [@hlevy-openai](https://github.com/hlevy-openai) - [#52660](https://github.com/openai/codex/issues/52660) Handle completion events in either order in shell snapshot tests [@jif-oai](https://github.com/jif-oai) - [#52661](https://github.com/openai/codex/issues/52661) Prevent brokered credential aliases from bypassing MITM hooks [@viyatb-oai](https://github.com/viyatb-oai) - [#52671](https://github.com/openai/codex/issues/52671) Add retention annotations to submitted tool outputs [@won-openai](https://github.com/won-openai) - [#52674](https://github.com/openai/codex/issues/52674) Move the exec-server test fixture into shared test support [@anp-oai](https://github.com/anp-oai) - [#52676](https://github.com/openai/codex/issues/52676) Refresh persisted capability roots from owner-provided configuration [@teddywyly-oai](https://github.com/teddywyly-oai) - [#52679](https://github.com/openai/codex/issues/52679) Add timeout-aware exec-server configuration reads [@hlevy-openai](https://github.com/hlevy-openai) - [#52681](https://github.com/openai/codex/issues/52681) Reject reserved Serde JSON keys in code mode [@cassirer-openai](https://github.com/cassirer-openai) - [#52682](https://github.com/openai/codex/issues/52682) Validate Windows sandbox accounts before password repair [@zm-oai](https://github.com/zm-oai) - [#52685](https://github.com/openai/codex/issues/52685) Preserve code mode cancellation during output serialization [@cassirer-openai](https://github.com/cassirer-openai) - [#52686](https://github.com/openai/codex/issues/52686) Add opt-in retention for turn tool outputs [@won-openai](https://github.com/won-openai) - [#52689](https://github.com/openai/codex/issues/52689) Forward per-turn Cyber access programs to Guardian [@daneschneider-oai](https://github.com/daneschneider-oai) - [#52696](https://github.com/openai/codex/issues/52696) Fix marketplace path matching for Windows junctions [@zm-oai](https://github.com/zm-oai) - [#52700](https://github.com/openai/codex/issues/52700) Update the exec-server stable compatibility baseline to Codex 0.162.1 [@iceweasel-oai](https://github.com/iceweasel-oai) - [#52702](https://github.com/openai/codex/issues/52702) Retry bootstrap GETs through the system proxy after request failures [@abhinav-oai](https://github.com/abhinav-oai) - [#52707](https://github.com/openai/codex/issues/52707) Migrate the Windows MXC sandbox to split MXC crates [@iceweasel-oai](https://github.com/iceweasel-oai) - [#52721](https://github.com/openai/codex/issues/52721) Explain session creation failures during server shutdown [@etraut-openai](https://github.com/etraut-openai) - [#52723](https://github.com/openai/codex/issues/52723) Add opt-in gRPC over stdio for the code-mode host [@cconger](https://github.com/cconger) - [#52724](https://github.com/openai/codex/issues/52724) Add observers for initial exec-server connection attempts [@aaronl-openai](https://github.com/aaronl-openai) - [#52725](https://github.com/openai/codex/issues/52725) Report terminal program status with OSC 7501 [@fcoury-oai](https://github.com/fcoury-oai) - [#52736](https://github.com/openai/codex/issues/52736) Allow model catalogs to override incremental tool notices [@akira-oai](https://github.com/akira-oai) - [#52742](https://github.com/openai/codex/issues/52742) Add opt-in output token replay for OpenAI requests [@pakrym-oai](https://github.com/pakrym-oai) - [#52748](https://github.com/openai/codex/issues/52748) Make code-mode `exit()` stop the entire cell [@cconger](https://github.com/cconger) - [#52756](https://github.com/openai/codex/issues/52756) Classify voice session failures and record terminal outcomes [@bc-openai](https://github.com/bc-openai) - [#52778](https://github.com/openai/codex/issues/52778) Make pinned transcript prompts clickable [@fcoury-oai](https://github.com/fcoury-oai) - [#52825](https://github.com/openai/codex/issues/52825) Report exec runtime resets before accepting further requests [@JenZhao](https://github.com/JenZhao) - [#52923](https://github.com/openai/codex/issues/52923) Stabilize the realtime steering timeline test [@anp-oai](https://github.com/anp-oai) - [#52937](https://github.com/openai/codex/issues/52937) Retain client-marked tool outputs across compaction [@won-openai](https://github.com/won-openai) - [#52946](https://github.com/openai/codex/issues/52946) Keep agent command center rows stable across progress updates [@fcoury-oai](https://github.com/fcoury-oai) - [#52952](https://github.com/openai/codex/issues/52952) Verify reset notification during code-mode host recovery [@etraut-openai](https://github.com/etraut-openai) - [#52959](https://github.com/openai/codex/issues/52959) Reduce stack usage in async TUI tests [@jif-oai](https://github.com/jif-oai) - [#52964](https://github.com/openai/codex/issues/52964) Defer owned transcript redraws during raw paste bursts [@etraut-openai](https://github.com/etraut-openai) - [#52967](https://github.com/openai/codex/issues/52967) Reuse and prewarm the WSL clipboard text reader [@etraut-openai](https://github.com/etraut-openai) - [#52968](https://github.com/openai/codex/issues/52968) Keep startup modals protected when terminal input draining times out [@etraut-openai](https://github.com/etraut-openai) - [#52972](https://github.com/openai/codex/issues/52972) Upgrade `rmcp` to `3.5.1` and harden lifecycle tests [@alishobeiri-oai](https://github.com/alishobeiri-oai) - [#52990](https://github.com/openai/codex/issues/52990) Add a searchable `/config` preferences panel to the TUI [@fcoury-oai](https://github.com/fcoury-oai) - [#53049](https://github.com/openai/codex/issues/53049) Add connection-bound reply handles for app-server requests [@bc-openai](https://github.com/bc-openai) - [#53109](https://github.com/openai/codex/issues/53109) Handle broken pipes gracefully in plugin list output [@fcoury-oai](https://github.com/fcoury-oai) - [#53148](https://github.com/openai/codex/issues/53148) Fix startup draft recovery for pending Vim Replace keys [@etraut-openai](https://github.com/etraut-openai) - [#53150](https://github.com/openai/codex/issues/53150) Restore thread-owned permissions on cold resume [@etraut-openai](https://github.com/etraut-openai) - [#53152](https://github.com/openai/codex/issues/53152) Allow selecting and copying TUI turn tips [@etraut-openai](https://github.com/etraut-openai) - [#53153](https://github.com/openai/codex/issues/53153) Show subagent navigation shortcuts in TUI help [@etraut-openai](https://github.com/etraut-openai) - [#53155](https://github.com/openai/codex/issues/53155) Keep remote app-server events deliverable during shutdown [@etraut-openai](https://github.com/etraut-openai) - [#53156](https://github.com/openai/codex/issues/53156) Simplify the custom terminal drawing API [@bc-openai](https://github.com/bc-openai) - [#53173](https://github.com/openai/codex/issues/53173) Allow restarting managed background servers from the TUI [@etraut-openai](https://github.com/etraut-openai) - [#53201](https://github.com/openai/codex/issues/53201) Keep agents navigation available after a thread is archived [@etraut-openai](https://github.com/etraut-openai) - [#53224](https://github.com/openai/codex/issues/53224) Support Windows clipboard text paste shortcuts in the TUI [@etraut-openai](https://github.com/etraut-openai) - [#53331](https://github.com/openai/codex/issues/53331) Finish remote exec cleanup when output streams remain open [@jif-oai](https://github.com/jif-oai) - [#53339](https://github.com/openai/codex/issues/53339) Test final polling of remote processes with open output streams [@jif-oai](https://github.com/jif-oai) - [#53358](https://github.com/openai/codex/issues/53358) Remove selected protocol, apply-patch, MCP, and TUI tests [@vb-openai](https://github.com/vb-openai) - [#53369](https://github.com/openai/codex/issues/53369) Allow turns when the agent message board is unavailable [@jif-oai](https://github.com/jif-oai) - [#53382](https://github.com/openai/codex/issues/53382) Ignore the unsafe-libyaml advisory in dependency audits [@swastik-oai](https://github.com/swastik-oai) - [#53389](https://github.com/openai/codex/issues/53389) Use cached login credentials for Guardian decisions [@swastik-oai](https://github.com/swastik-oai) - [#53393](https://github.com/openai/codex/issues/53393) Distinguish Guardian parent-compaction failure reasons [@ioanbudea-OAI](https://github.com/ioanbudea-OAI) - [#53400](https://github.com/openai/codex/issues/53400) Add explicit local board connections with fixed runtime access [@jif-oai](https://github.com/jif-oai) - [#53412](https://github.com/openai/codex/issues/53412) Isolate arg0 helper directories by operating system [@jif-oai](https://github.com/jif-oai) - [#53419](https://github.com/openai/codex/issues/53419) Restore saved thread permissions during configuration loading [@jif-oai](https://github.com/jif-oai) - [#53424](https://github.com/openai/codex/issues/53424) Add regression coverage for network grants on cold thread resume [@jif-oai](https://github.com/jif-oai) - [#53426](https://github.com/openai/codex/issues/53426) Preserve Windows runtime registration failure diagnostics [@zm-oai](https://github.com/zm-oai) - [#53429](https://github.com/openai/codex/issues/53429) Apply configuration toggles live and improve settings navigation [@fcoury-oai](https://github.com/fcoury-oai) - [#53436](https://github.com/openai/codex/issues/53436) Route TUI request replies to their originating connection and thread [@bc-openai](https://github.com/bc-openai) - [#53438](https://github.com/openai/codex/issues/53438) Stop identifying Apple Terminal from `TERM_SESSION_ID` [@etraut-openai](https://github.com/etraut-openai) - [#53440](https://github.com/openai/codex/issues/53440) Preserve status line accents on 16-color terminals [@etraut-openai](https://github.com/etraut-openai) - [#53443](https://github.com/openai/codex/issues/53443) Use local MSVC toolchains for native Windows Bazel tests [@etraut-openai](https://github.com/etraut-openai) - [#53444](https://github.com/openai/codex/issues/53444) Suppress repeated turn diffs in `codex exec` human output [@fcoury-oai](https://github.com/fcoury-oai) - [#53451](https://github.com/openai/codex/issues/53451) Treat incomplete responses as terminal errors [@jif-oai](https://github.com/jif-oai) - [#53452](https://github.com/openai/codex/issues/53452) Close input admission while a turn finishes recording [@etraut-openai](https://github.com/etraut-openai) - [#53453](https://github.com/openai/codex/issues/53453) Prefer the Windows clipboard and bound copy attempts on WSL [@etraut-openai](https://github.com/etraut-openai) - [#53485](https://github.com/openai/codex/issues/53485) Update `quinn-proto` to 0.11.18 [@smurching-oai](https://github.com/smurching-oai) - [#53496](https://github.com/openai/codex/issues/53496) Preserve pending Effects toggles across save refreshes [@fcoury-oai](https://github.com/fcoury-oai) - [#53506](https://github.com/openai/codex/issues/53506) Reject duplicate Host headers in the network proxy [@jfoo-oai](https://github.com/jfoo-oai) - [#53556](https://github.com/openai/codex/issues/53556) Deduplicate TUI modifier handling and terminal color caching [@bc-openai](https://github.com/bc-openai) - [#53595](https://github.com/openai/codex/issues/53595) Add async compaction feature configuration [@rka-oai](https://github.com/rka-oai) - [#53606](https://github.com/openai/codex/issues/53606) Prepare compaction helpers for background requests [@rka-oai](https://github.com/rka-oai) - [#53614](https://github.com/openai/codex/issues/53614) Add infrastructure for speculative remote V2 compaction [@rka-oai](https://github.com/rka-oai) - [#53617](https://github.com/openai/codex/issues/53617) Allow hiding native tools while retaining the multi-agent V2 runtime [@jif-oai](https://github.com/jif-oai) - [#53620](https://github.com/openai/codex/issues/53620) Reuse background results for remote V2 compaction [@rka-oai](https://github.com/rka-oai) - [#53622](https://github.com/openai/codex/issues/53622) Preserve remote exec output until it is collected [@jif-oai](https://github.com/jif-oai) - [#53628](https://github.com/openai/codex/issues/53628) Record truncation metrics for accepted Guardian review inputs [@ioanbudea-OAI](https://github.com/ioanbudea-OAI) - [#53631](https://github.com/openai/codex/issues/53631) Materialize the thread before testing a discovered daemon restart [@jif-oai](https://github.com/jif-oai) - [#53632](https://github.com/openai/codex/issues/53632) Stabilize write ordering in the shared message board scenario [@jif-oai](https://github.com/jif-oai) - [#53633](https://github.com/openai/codex/issues/53633) Add an environment API key fallback for Guardian Decisions [@swastik-oai](https://github.com/swastik-oai) - [#53654](https://github.com/openai/codex/issues/53654) Keep spawned children provisional until the spawn result returns [@jif-oai](https://github.com/jif-oai) - [#53657](https://github.com/openai/codex/issues/53657) Share hook configuration across cloned hook views [@jif-oai](https://github.com/jif-oai) - [#53660](https://github.com/openai/codex/issues/53660) Extract shared multi-agent v2 thread spawning [@jif-oai](https://github.com/jif-oai) - [#53668](https://github.com/openai/codex/issues/53668) Improve remote exec-server test startup diagnostics [@jif-oai](https://github.com/jif-oai) - [#53670](https://github.com/openai/codex/issues/53670) Account for token usage from incomplete responses [@jif-oai](https://github.com/jif-oai) - [#53672](https://github.com/openai/codex/issues/53672) Keep discovered Apps tools available during startup recovery [@jif-oai](https://github.com/jif-oai) - [#53673](https://github.com/openai/codex/issues/53673) Publish Rust releases with the GitHub CLI [@jif-oai](https://github.com/jif-oai) - [#53678](https://github.com/openai/codex/issues/53678) Preserve inherited context in prediction forks [@keyz](https://github.com/keyz) - [#53689](https://github.com/openai/codex/issues/53689) Constrain API-key model access programs to server support [@julee-oai](https://github.com/julee-oai) - [#53691](https://github.com/openai/codex/issues/53691) Account for replay caches in encrypted compaction budgets [@ioanbudea-OAI](https://github.com/ioanbudea-OAI) - [#53693](https://github.com/openai/codex/issues/53693) Add keyboard selection support to the transcript view [@fcoury-oai](https://github.com/fcoury-oai) - [#53698](https://github.com/openai/codex/issues/53698) Interrupt and drain canceled classifier responses before socket reuse [@felixxia-oai](https://github.com/felixxia-oai) - [#53699](https://github.com/openai/codex/issues/53699) Cancel Guardian V2 classifications that exceed the tool-call lag window [@felixxia-oai](https://github.com/felixxia-oai) - [#53701](https://github.com/openai/codex/issues/53701) Enable CLI Daybreak by default and enforce background-turn eligibility [@julee-oai](https://github.com/julee-oai) - [#53706](https://github.com/openai/codex/issues/53706) Preserve URLs and email addresses during external agent migration [@jif-oai](https://github.com/jif-oai) - [#53709](https://github.com/openai/codex/issues/53709) Separate MCP sandbox policy from launcher metadata [@bolinfest](https://github.com/bolinfest) - [#53717](https://github.com/openai/codex/issues/53717) Enable Cyber access programs for API-key sessions by default [@julee-oai](https://github.com/julee-oai) - [#53723](https://github.com/openai/codex/issues/53723) Wire V2 capability discovery through exec-server RPC [@TAFOYA-OAI](https://github.com/TAFOYA-OAI) ### [`v0.162.1`](https://github.com/openai/codex/releases/tag/rust-v0.162.1): 0.162.1 [Compare Source](https://github.com/openai/codex/compare/rust-v0.162.0-alpha.18.1...rust-v0.162.1) #### Bug Fixes - Fixed a TUI crash when asynchronous questions contain multiple lines, preserving line breaks and complete hyperlink destinations. ([#51866](https://github.com/openai/codex/issues/51866)) - Fixed startup failures caused by differences between a running background server's feature settings and CLI defaults. Compatibility checks now apply only to explicit command-line feature overrides. ([#52648](https://github.com/openai/codex/issues/52648)) Full Changelog: <https://github.com/openai/codex/compare/rust-v0.162.0...rust-v0.162.1> ### [`v0.162.0`](https://github.com/openai/codex/releases/tag/rust-v0.162.0): 0.162.0 [Compare Source](https://github.com/openai/codex/compare/rust-v0.161.0-alpha.13.1...rust-v0.162.0-alpha.18.1) #### New Features - Add tools for creating and listing managed Git worktrees from trusted local projects when the worktrees feature is enabled. ([#50148](https://github.com/openai/codex/issues/50148)) - Pin tasks in the agent Command Center with `p` and keep them in a shared Pinned group when supported by the server. ([#51500](https://github.com/openai/codex/issues/51500)) - Navigate and copy transcript blocks with `/copy`, use `Ctrl+Insert` to copy selections, and tune mouse-wheel scrolling with `tui.mouse_scroll_speed`. ([#50434](https://github.com/openai/codex/issues/50434), [#50215](https://github.com/openai/codex/issues/50215), [#50209](https://github.com/openai/codex/issues/50209)) - Make URLs clickable in approval headers, questions, MCP prompts, warnings, banners, and verification prompts, including when links wrap across lines. ([#51439](https://github.com/openai/codex/issues/51439), [#51449](https://github.com/openai/codex/issues/51449), [#51450](https://github.com/openai/codex/issues/51450), [#51451](https://github.com/openai/codex/issues/51451), [#51452](https://github.com/openai/codex/issues/51452), [#51458](https://github.com/openai/codex/issues/51458)) - Configure live web access and remote compaction capabilities for custom Responses-compatible model providers. ([#50459](https://github.com/openai/codex/issues/50459)) - Add JavaScript helpers for streaming promise results as they settle, plus opt-in ranked tool search in Code Mode. ([#51126](https://github.com/openai/codex/issues/51126), [#51209](https://github.com/openai/codex/issues/51209)) #### Bug Fixes - Respect server model and reasoning-summary defaults for new TUI threads while retaining explicit launch overrides. ([#50013](https://github.com/openai/codex/issues/50013), [#50811](https://github.com/openai/codex/issues/50811), [#50913](https://github.com/openai/codex/issues/50913)) - Preserve existing CRLF line endings in `apply_patch` updates without requiring an opt-in. ([#51203](https://github.com/openai/codex/issues/51203)) - Fix Linux sandbox startup with multiple denied files, reject writable sandbox-construction executables, and keep ripgrep configuration from weakening deny-glob masks. ([#50059](https://github.com/openai/codex/issues/50059), [#51211](https://github.com/openai/codex/issues/51211), [#51407](https://github.com/openai/codex/issues/51407), [#51527](https://github.com/openai/codex/issues/51527)) - Restore ordinary drive-letter file access on Windows 10 and match Windows sandbox temp permissions to the child process environment. ([#51511](https://github.com/openai/codex/issues/51511), [#51512](https://github.com/openai/codex/issues/51512)) - Honor server `Retry-After` advice for retryable Responses and WebSocket failures. ([#50418](https://github.com/openai/codex/issues/50418), [#51440](https://github.com/openai/codex/issues/51440)) - Fix archive checksum verification when installing through Windows PowerShell with PowerShell 7 module paths present. ([#51257](https://github.com/openai/codex/issues/51257)) #### Chores - Publish a signed PowerShell installer with Windows releases. ([#51158](https://github.com/openai/codex/issues/51158)) - Keep older stable releases and prereleases from replacing newer stable download targets or installer aliases. ([#51186](https://github.com/openai/codex/issues/51186), [#51425](https://github.com/openai/codex/issues/51425)) #### Changelog Full Changelog: <https://github.com/openai/codex/compare/rust-v0.161.0...rust-v0.162.0> - [#50013](https://github.com/openai/codex/issues/50013) Honor server model defaults when starting fresh TUI threads [@etraut-openai](https://github.com/etraut-openai) - [#50018](https://github.com/openai/codex/issues/50018) Use descriptor-safe helpers for executable test fixtures [@jif-oai](https://github.com/jif-oai) - [#50019](https://github.com/openai/codex/issues/50019) Protect the guardian decisions API key from environment forwarding [@swastik-oai](https://github.com/swastik-oai) - [#50026](https://github.com/openai/codex/issues/50026) Preserve user restrictions in Guardian handoff context [@jif-oai](https://github.com/jif-oai) - [#50035](https://github.com/openai/codex/issues/50035) Follow MCP tool pagination in legacy protocol mode [@jif-oai](https://github.com/jif-oai) - [#50039](https://github.com/openai/codex/issues/50039) Keep transcript Find results readable after closing the query [@fcoury-oai](https://github.com/fcoury-oai) - [#50045](https://github.com/openai/codex/issues/50045) Keep transcript Find expansion scoped to the current match [@fcoury-oai](https://github.com/fcoury-oai) - [#50046](https://github.com/openai/codex/issues/50046) Stabilize Windows voice build cache keys across tool reinstalls [@anp-oai](https://github.com/anp-oai) - [#50050](https://github.com/openai/codex/issues/50050) Keep plugin and skill snapshots scoped to each step [@sayan-oai](https://github.com/sayan-oai) - [#50052](https://github.com/openai/codex/issues/50052) Preserve question context in recovered TUI answer drafts [@imac-oai](https://github.com/imac-oai) - [#50054](https://github.com/openai/codex/issues/50054) Check token estimate filtering directly on the tracing subscriber [@tamird](https://github.com/tamird) - [#50058](https://github.com/openai/codex/issues/50058) Upgrade Windows bindings to `windows-sys` 0.61.2 [@tamird](https://github.com/tamird) - [#50059](https://github.com/openai/codex/issues/50059) Fix Linux sandbox startup with multiple denied files [@yuzhu-oai](https://github.com/yuzhu-oai) - [#50066](https://github.com/openai/codex/issues/50066) Add a bounded Decisions transport for Guardian comparison classification [@swastik-oai](https://github.com/swastik-oai) - [#50082](https://github.com/openai/codex/issues/50082) Enable dynamic tool inheritance for fresh V2 subagents [@ke-oai](https://github.com/ke-oai) - [#50083](https://github.com/openai/codex/issues/50083) Add paginated reverse lookup for thread attachments [@joeytrasatti-openai](https://github.com/joeytrasatti-openai) - [#50087](https://github.com/openai/codex/issues/50087) Preserve queued agent mail across session eviction [@jif-oai](https://github.com/jif-oai) - [#50093](https://github.com/openai/codex/issues/50093) Prevent shared instruction providers from delegating to themselves [@bryanashley](https://github.com/bryanashley) - [#50094](https://github.com/openai/codex/issues/50094) Add attachment owner lookup to the app-server [@joeytrasatti-openai](https://github.com/joeytrasatti-openai) - [#50099](https://github.com/openai/codex/issues/50099) Add opt-in Decisions comparison for Guardian V2 [@swastik-oai](https://github.com/swastik-oai) - [#50105](https://github.com/openai/codex/issues/50105) Consolidate chat composer footer logic in `footer_state` [@imac-oai](https://github.com/imac-oai) - [#50109](https://github.com/openai/codex/issues/50109) Keep fullscreen prompts bounded and scrollable [@imac-oai](https://github.com/imac-oai) - [#50112](https://github.com/openai/codex/issues/50112) Centralize TUI loading glyphs and frame scheduling [@imac-oai](https://github.com/imac-oai) - [#50113](https://github.com/openai/codex/issues/50113) Add a native gRPC client for cloud thread resume and attach [@bc-openai](https://github.com/bc-openai) - [#50128](https://github.com/openai/codex/issues/50128) Expose the model selected for a running turn's next step [@sayan-oai](https://github.com/sayan-oai) - [#50129](https://github.com/openai/codex/issues/50129) Preserve Windows environment variables for remote MCP servers [@aidanv-oai](https://github.com/aidanv-oai) - [#50131](https://github.com/openai/codex/issues/50131) Add opt-in JSON diagnostics for TCP tunnels [@richardopenai](https://github.com/richardopenai) - [#50140](https://github.com/openai/codex/issues/50140) Use the server permission catalog for TUI permission shortcuts [@etraut-openai](https://github.com/etraut-openai) - [#50148](https://github.com/openai/codex/issues/50148) Add managed worktree tools to the TUI [@bc-openai](https://github.com/bc-openai) - [#50162](https://github.com/openai/codex/issues/50162) Bound in-flight file opens in exec-server [@anp-oai](https://github.com/anp-oai) - [#50166](https://github.com/openai/codex/issues/50166) Upgrade `age` to 0.12.1 and remove the obsolete advisory exception [@michaelm-openai](https://github.com/michaelm-openai) - [#50177](https://github.com/openai/codex/issues/50177) Enable writable file streaming in exec-server [@anp-oai](https://github.com/anp-oai) - [#50183](https://github.com/openai/codex/issues/50183) Add `dots` to issue labeler guidance [@etraut-openai](https://github.com/etraut-openai) - [#50189](https://github.com/openai/codex/issues/50189) Replace the Figma OAuth exception with Mercado Pago [@mzeng-openai](https://github.com/mzeng-openai) - [#50199](https://github.com/openai/codex/issues/50199) Restore the account email in `/status` after account updates [@etraut-openai](https://github.com/etraut-openai) - [#50200](https://github.com/openai/codex/issues/50200) Report the configured TUI mode in `codex doctor` [@etraut-openai](https://github.com/etraut-openai) - [#50207](https://github.com/openai/codex/issues/50207) Release stable Markdown tables into scrollback during streaming [@etraut-openai](https://github.com/etraut-openai) - [#50209](https://github.com/openai/codex/issues/50209) Make transcript mouse scroll speed configurable [@etraut-openai](https://github.com/etraut-openai) - [#50215](https://github.com/openai/codex/issues/50215) Support Ctrl+Insert for copying TUI selections [@etraut-openai](https://github.com/etraut-openai) - [#50216](https://github.com/openai/codex/issues/50216) Use the shared text editor for command-center task renaming [@bc-openai](https://github.com/bc-openai) - [#50219](https://github.com/openai/codex/issues/50219) Bound tmux option probes to one second [@etraut-openai](https://github.com/etraut-openai) - [#50273](https://github.com/openai/codex/issues/50273) Record Guardian V2 Decisions agreement and latency metrics [@swastik-oai](https://github.com/swastik-oai) - [#50339](https://github.com/openai/codex/issues/50339) Add end-to-end coverage for MCP sandbox state enforcement [@bolinfest](https://github.com/bolinfest) - [#50345](https://github.com/openai/codex/issues/50345) Keep the subagent picker consistent with thread archive state [@etraut-openai](https://github.com/etraut-openai) - [#50348](https://github.com/openai/codex/issues/50348) Back off automatic remote control reconnects with jitter [@cooper-oai](https://github.com/cooper-oai) - [#50354](https://github.com/openai/codex/issues/50354) Skip unrelated subtrees during config alias normalization [@btraut-openai](https://github.com/btraut-openai) - [#50359](https://github.com/openai/codex/issues/50359) Render ANSI styles in TUI hook system messages [@etraut-openai](https://github.com/etraut-openai) - [#50360](https://github.com/openai/codex/issues/50360) Remove initial messages from session configuration events [@owenlin0](https://github.com/owenlin0) - [#50375](https://github.com/openai/codex/issues/50375) Use printable ASCII terminal titles under GNU Screen [@imac-oai](https://github.com/imac-oai) - [#50380](https://github.com/openai/codex/issues/50380) Fix thread unloading after disconnect during MCP startup [@yuzhu-oai](https://github.com/yuzhu-oai) - [#50384](https://github.com/openai/codex/issues/50384) Allow opting into 16 KiB ARM64 code pages for macOS signing [@chess-oai](https://github.com/chess-oai) - [#50389](https://github.com/openai/codex/issues/50389) Honor configured keybindings before transcript navigation [@etraut-openai](https://github.com/etraut-openai) - [#50396](https://github.com/openai/codex/issues/50396) Honor pager bindings for transcript page keys [@bc-openai](https://github.com/bc-openai) - [#50402](https://github.com/openai/codex/issues/50402) Consolidate command execution output into `aggregated_output` [@owenlin0](https://github.com/owenlin0) - [#50416](https://github.com/openai/codex/issues/50416) Clarify Git worktree choices for new and forked conversations [@bc-openai](https://github.com/bc-openai) - [#50418](https://github.com/openai/codex/issues/50418) Honor Retry-After headers in failed Responses events [@anp-oai](https://github.com/anp-oai) - [#50427](https://github.com/openai/codex/issues/50427) Cap persisted command output in paginated history at 64 KiB [@owenlin0](https://github.com/owenlin0) - [#50431](https://github.com/openai/codex/issues/50431) Preserve terminal hyperlinks in agents overview previews [@bc-openai](https://github.com/bc-openai) - [#50433](https://github.com/openai/codex/issues/50433) Allow API-key accounts to use Daybreak in the TUI [@etraut-openai](https://github.com/etraut-openai) - [#50434](https://github.com/openai/codex/issues/50434) Add keyboard copy selection to the owned transcript [@bc-openai](https://github.com/bc-openai) - [#50435](https://github.com/openai/codex/issues/50435) Persist additional tool definitions in rollout history [@pakrym-oai](https://github.com/pakrym-oai) - [#50437](https://github.com/openai/codex/issues/50437) Add a CLI command to uninstall the legacy Windows sandbox [@chess-oai](https://github.com/chess-oai) - [#50441](https://github.com/openai/codex/issues/50441) Support ordered response items in world-state context updates [@pakrym-oai](https://github.com/pakrym-oai) - [#50442](https://github.com/openai/codex/issues/50442) Preserve native USD amounts in thread usage responses [@asohrabi-oai](https://github.com/asohrabi-oai) - [#50443](https://github.com/openai/codex/issues/50443) Stabilize paused-time code-mode service tests [@seanh-oai](https://github.com/seanh-oai) - [#50445](https://github.com/openai/codex/issues/50445) Assert that only direct tool calls emit timing events [@seanh-oai](https://github.com/seanh-oai) - [#50446](https://github.com/openai/codex/issues/50446) Bundle rollout attachments into a gzip tar archive [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#50447](https://github.com/openai/codex/issues/50447) Remove the provider capability gate for tool namespaces [@pakrym-oai](https://github.com/pakrym-oai) - [#50454](https://github.com/openai/codex/issues/50454) Measure rollout persistence size reductions [@owenlin0](https://github.com/owenlin0) - [#50458](https://github.com/openai/codex/issues/50458) Truncate oversized MCP results in paginated thread history [@owenlin0](https://github.com/owenlin0) - [#50459](https://github.com/openai/codex/issues/50459) Add capability overrides for custom model providers [@celia-oai](https://github.com/celia-oai) - [#50462](https://github.com/openai/codex/issues/50462) Populate thread previews from delegated task inputs [@bc-openai](https://github.com/bc-openai) - [#50464](https://github.com/openai/codex/issues/50464) Add the `incremental_tools` feature flag [@pakrym-oai](https://github.com/pakrym-oai) - [#50465](https://github.com/openai/codex/issues/50465) Retry registry authentication outages and jitter executor reconnects [@apanasenko-oai](https://github.com/apanasenko-oai) - [#50467](https://github.com/openai/codex/issues/50467) Copy transcript selections as literal text while preserving rich HTML [@fcoury-oai](https://github.com/fcoury-oai) - [#50470](https://github.com/openai/codex/issues/50470) Account for JSON overhead when truncating MCP tool results [@owenlin0](https://github.com/owenlin0) - [#50472](https://github.com/openai/codex/issues/50472) Enable Ultrafast service tiers for Amazon Bedrock Astra models [@celia-oai](https://github.com/celia-oai) - [#50477](https://github.com/openai/codex/issues/50477) Use the app-server default output cap for TUI workspace commands [@etraut-openai](https://github.com/etraut-openai) - [#50480](https://github.com/openai/codex/issues/50480) Skip managed config loading for registered Windows sandbox refreshes [@zm-oai](https://github.com/zm-oai) - [#50499](https://github.com/openai/codex/issues/50499) Include installer stderr in daemon update failures [@etraut-openai](https://github.com/etraut-openai) - [#50503](https://github.com/openai/codex/issues/50503) Use Enter to accept transcript Find results and Escape to cancel [@fcoury-oai](https://github.com/fcoury-oai) - [#50504](https://github.com/openai/codex/issues/50504) Center TUI confirmations over their retained backdrop [@bc-openai](https://github.com/bc-openai) - [#50505](https://github.com/openai/codex/issues/50505) Keep Command Center selection adjacent after task removal [@bc-openai](https://github.com/bc-openai) - [#50507](https://github.com/openai/codex/issues/50507) Record Windows sandbox service stop diagnostics [@zm-oai](https://github.com/zm-oai) - [#50510](https://github.com/openai/codex/issues/50510) Require GovCloud guidance acknowledgment after Bedrock setup [@jackz100](https://github.com/jackz100) - [#50516](https://github.com/openai/codex/issues/50516) Add scenario coverage for remote `/compact` context preservation [@pakrym-oai](https://github.com/pakrym-oai) - [#50525](https://github.com/openai/codex/issues/50525) Reject unknown TUI keys in strict config validation [@etraut-openai](https://github.com/etraut-openai) - [#50531](https://github.com/openai/codex/issues/50531) Persist realtime transcript tails before closure without inference [@guinness-oai](https://github.com/guinness-oai) - [#50536](https://github.com/openai/codex/issues/50536) Keep shared MCP types stable in Code Mode exec descriptions [@aibrahim-oai](https://github.com/aibrahim-oai) - [#50540](https://github.com/openai/codex/issues/50540) Send incremental tool catalog updates in Responses Lite [@pakrym-oai](https://github.com/pakrym-oai) - [#50546](https://github.com/openai/codex/issues/50546) Keep MCP resource helpers available in code mode [@aibrahim-oai](https://github.com/aibrahim-oai) - [#50555](https://github.com/openai/codex/issues/50555) Skip daemon auto-start for Windows-mounted WSL homes [@etraut-openai](https://github.com/etraut-openai) - [#50558](https://github.com/openai/codex/issues/50558) Avoid reading the current directory when resolving absolute paths [@etraut-openai](https://github.com/etraut-openai) - [#50559](https://github.com/openai/codex/issues/50559) Distinguish daemon release identity from executable contents [@etraut-openai](https://github.com/etraut-openai) - [#50562](https://github.com/openai/codex/issues/50562) Keep Code Mode tool discovery guidance stable across catalog changes [@aibrahim-oai](https://github.com/aibrahim-oai) - [#50564](https://github.com/openai/codex/issues/50564) Allow transcript selection and copying while bottom modals are open [@etraut-openai](https://github.com/etraut-openai) - [#50687](https://github.com/openai/codex/issues/50687) Keep third-party tools deferred in strict Code Mode Only [@aibrahim-oai](https://github.com/aibrahim-oai) - [#50695](https://github.com/openai/codex/issues/50695) Preserve local Markdown link labels in the TUI [@bc-openai](https://github.com/bc-openai) - [#50700](https://github.com/openai/codex/issues/50700) Let the transport create the Windows remote-control socket directory [@etraut-openai](https://github.com/etraut-openai) - [#50720](https://github.com/openai/codex/issues/50720) Decode Windows Terminal's mapped Shift+Enter sequence [@bc-openai](https://github.com/bc-openai) - [#50727](https://github.com/openai/codex/issues/50727) Show model and reasoning effort near the top of task details [@etraut-openai](https://github.com/etraut-openai) - [#50741](https://github.com/openai/codex/issues/50741) Keep environment-backed tools exposed across readiness changes [@won-openai](https://github.com/won-openai) - [#50756](https://github.com/openai/codex/issues/50756) Show unavailable slash commands when searched in side conversations [@bc-openai](https://github.com/bc-openai) - [#50764](https://github.com/openai/codex/issues/50764) Allow `/archive` while a turn is running [@bc-openai](https://github.com/bc-openai) - [#50781](https://github.com/openai/codex/issues/50781) Restrict TUI MCP startup notifications to owned threads [@etraut-openai](https://github.com/etraut-openai) - [#50782](https://github.com/openai/codex/issues/50782) Retry Windows daemon release publication on transient file locks [@etraut-openai](https://github.com/etraut-openai) - [#50786](https://github.com/openai/codex/issues/50786) Remember Command Center grouping across launches [@bc-openai](https://github.com/bc-openai) - [#50788](https://github.com/openai/codex/issues/50788) Open slash commands from empty drafts in Vim Normal mode [@bc-openai](https://github.com/bc-openai) - [#50802](https://github.com/openai/codex/issues/50802) Fall back to mklink when Windows daemon junction updates are denied [@etraut-openai](https://github.com/etraut-openai) - [#50803](https://github.com/openai/codex/issues/50803) Use the managed daemon for eligible remote-control launches [@etraut-openai](https://github.com/etraut-openai) - [#50804](https://github.com/openai/codex/issues/50804) Preserve review lifecycle ordering on failure [@etraut-openai](https://github.com/etraut-openai) - [#50808](https://github.com/openai/codex/issues/50808) Prune TUI snapshots and consolidate behavior tests [@etraut-openai](https://github.com/etraut-openai) - [#50811](https://github.com/openai/codex/issues/50811) Honor server reasoning summary defaults in new TUI threads [@etraut-openai](https://github.com/etraut-openai) - [#50913](https://github.com/openai/codex/issues/50913) Use server model defaults for connected TUI fresh starts [@etraut-openai](https://github.com/etraut-openai) - [#50940](https://github.com/openai/codex/issues/50940) Recover malformed Windows deny-read ACL state safely [@zm-oai](https://github.com/zm-oai) - [#50962](https://github.com/openai/codex/issues/50962) Gate stable environment tool exposure behind a feature flag [@aibrahim-oai](https://github.com/aibrahim-oai) - [#50964](https://github.com/openai/codex/issues/50964) Track inference tool changes in turn analytics [@aibrahim-oai](https://github.com/aibrahim-oai) - [#50977](https://github.com/openai/codex/issues/50977) Isolate tracing in the strict third-party tool deferral test [@alishobeiri-oai](https://github.com/alishobeiri-oai) - [#51061](https://github.com/openai/codex/issues/51061) Gate Guardian continuation tests on classifier request capture [@jif-oai](https://github.com/jif-oai) - [#51063](https://github.com/openai/codex/issues/51063) Honor prior cancellation before starting Codex delegates [@jif-oai](https://github.com/jif-oai) - [#51064](https://github.com/openai/codex/issues/51064) Ignore stale refresh responses in agents overview tests [@jif-oai](https://github.com/jif-oai) - [#51065](https://github.com/openai/codex/issues/51065) Scope Guardian V2 response timing to snapshot sampling [@swastik-oai](https://github.com/swastik-oai) - [#51067](https://github.com/openai/codex/issues/51067) Use issuing-step context for Guardian MCP elicitation reviews [@jif-oai](https://github.com/jif-oai) - [#51070](https://github.com/openai/codex/issues/51070) Preserve trusted-tool context in Guardian Decisions requests [@swastik-oai](https://github.com/swastik-oai) - [#51117](https://github.com/openai/codex/issues/51117) Install full context in compaction replacement history [@pakrym-oai](https://github.com/pakrym-oai) - [#51119](https://github.com/openai/codex/issues/51119) Clarify incremental tool namespace updates in Responses Lite [@akira-oai](https://github.com/akira-oai) - [#51126](https://github.com/openai/codex/issues/51126) Add promise settlement streaming helpers to code mode [@cconger](https://github.com/cconger) - [#51133](https://github.com/openai/codex/issues/51133) Allow Guardian Decisions to fall back to `OPENAI_API_KEY` [@swastik-oai](https://github.com/swastik-oai) - [#51137](https://github.com/openai/codex/issues/51137) Recover Guardian reviews from parent checkpoints [@felixxia-oai](https://github.com/felixxia-oai) - [#51139](https://github.com/openai/codex/issues/51139) Force fresh Guardian sessions for parent-checkpoint recovery [@felixxia-oai](https://github.com/felixxia-oai) - [#51140](https://github.com/openai/codex/issues/51140) Isolate Guardian checkpoint recovery flags per review attempt [@felixxia-oai](https://github.com/felixxia-oai) - [#51156](https://github.com/openai/codex/issues/51156) Send base instructions as Responses input messages [@pakrym-oai](https://github.com/pakrym-oai) - [#51157](https://github.com/openai/codex/issues/51157) Enforce required environment skills before model inference [@anp-oai](https://github.com/anp-oai) - [#51158](https://github.com/openai/codex/issues/51158) Sign the PowerShell installer in Windows releases [@chess-oai](https://github.com/chess-oai) - [#51184](https://github.com/openai/codex/issues/51184) Remove obsolete Guardian thread-context enables from tests [@felixxia-oai](https://github.com/felixxia-oai) - [#51185](https://github.com/openai/codex/issues/51185) Retry transient gRPC code-mode session admission failures [@cassirer-openai](https://github.com/cassirer-openai) - [#51186](https://github.com/openai/codex/issues/51186) Prevent stable release pointers from moving backward [@andrewgu-oai](https://github.com/andrewgu-oai) - [#51188](https://github.com/openai/codex/issues/51188) Record base instructions in incremental tool history [@pakrym-oai](https://github.com/pakrym-oai) - [#51191](https://github.com/openai/codex/issues/51191) Clean up Unix app-server control-socket startup lock files [@etraut-openai](https://github.com/etraut-openai) - [#51192](https://github.com/openai/codex/issues/51192) Wait for SIGCONT when resuming the TUI [@etraut-openai](https://github.com/etraut-openai) - [#51193](https://github.com/openai/codex/issues/51193) Test thread archiving before the first turn [@btraut-openai](https://github.com/btraut-openai) - [#51194](https://github.com/openai/codex/issues/51194) Add browser extension request headers to config requirements [@jn-openai](https://github.com/jn-openai) - [#51198](https://github.com/openai/codex/issues/51198) Allow concurrent release builds while serializing publication [@andrewgu-oai](https://github.com/andrewgu-oai) - [#51200](https://github.com/openai/codex/issues/51200) Upgrade Bazel to 9.2.0 and refresh the module lockfile [@anp-oai](https://github.com/anp-oai) - [#51202](https://github.com/openai/codex/issues/51202) Distinguish namespace removals in incremental tool updates [@akira-oai](https://github.com/akira-oai) - [#51203](https://github.com/openai/codex/issues/51203) Make apply_patch preserve line endings unconditionally [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51206](https://github.com/openai/codex/issues/51206) Record initialization analytics for resumed subagents [@peilin-openai](https://github.com/peilin-openai) - [#51207](https://github.com/openai/codex/issues/51207) Gate CLI Daybreak controls and selection behind an opt-in feature [@julee-oai](https://github.com/julee-oai) - [#51209](https://github.com/openai/codex/issues/51209) Add ranked tool discovery to JavaScript code mode [@zamoshchin-openai](https://github.com/zamoshchin-openai) - [#51211](https://github.com/openai/codex/issues/51211) Reject sandbox-writable bubblewrap executables from PATH [@viyatb-oai](https://github.com/viyatb-oai) - [#51215](https://github.com/openai/codex/issues/51215) Measure raw MCP tool catalog sizes in telemetry [@owenlin0](https://github.com/owenlin0) - [#51217](https://github.com/openai/codex/issues/51217) Preserve review targets and scope misalignment continuation metadata [@yunhan-wei](https://github.com/yunhan-wei) - [#51220](https://github.com/openai/codex/issues/51220) Honor the OTLP metrics temporality preference [@daniel-oai](https://github.com/daniel-oai) - [#51221](https://github.com/openai/codex/issues/51221) Separate environment requests from runtime selections [@anp-oai](https://github.com/anp-oai) - [#51223](https://github.com/openai/codex/issues/51223) Remove legacy personality template metadata [@rhan-oai](https://github.com/rhan-oai) - [#51230](https://github.com/openai/codex/issues/51230) Make session lookup pagination stable and report listing failures [@etraut-openai](https://github.com/etraut-openai) - [#51235](https://github.com/openai/codex/issues/51235) Remove default model labels from TUI model pickers [@etraut-openai](https://github.com/etraut-openai) - [#51241](https://github.com/openai/codex/issues/51241) Add a partial answer message phase [@rb-oai](https://github.com/rb-oai) - [#51249](https://github.com/openai/codex/issues/51249) Handle partial answers consistently across agent workflows [@rb-oai](https://github.com/rb-oai) - [#51253](https://github.com/openai/codex/issues/51253) Enforce Fast and Ultra Fast policies independently [@dpatel-oai](https://github.com/dpatel-oai) - [#51256](https://github.com/openai/codex/issues/51256) Start the Windows sandbox service during registered Core setup [@zm-oai](https://github.com/zm-oai) - [#51257](https://github.com/openai/codex/issues/51257) Fix installer checksum verification under Windows PowerShell [@zm-oai](https://github.com/zm-oai) - [#51260](https://github.com/openai/codex/issues/51260) Handle partial answers in realtime routing and thread search [@rb-oai](https://github.com/rb-oai) - [#51329](https://github.com/openai/codex/issues/51329) Remove partial-history subagent forks [@jif-oai](https://github.com/jif-oai) - [#51330](https://github.com/openai/codex/issues/51330) Measure total Guardian approval decision duration [@jif-oai](https://github.com/jif-oai) - [#51331](https://github.com/openai/codex/issues/51331) Track sub-agent result delivery outcomes [@jif-oai](https://github.com/jif-oai) - [#51332](https://github.com/openai/codex/issues/51332) Record multi-agent wait duration by outcome [@jif-oai](https://github.com/jif-oai) - [#51333](https://github.com/openai/codex/issues/51333) Record the multi-agent version in turn analytics [@jif-oai](https://github.com/jif-oai) - [#51334](https://github.com/openai/codex/issues/51334) Count Guardian denial-limit interruptions in telemetry [@jif-oai](https://github.com/jif-oai) - [#51335](https://github.com/openai/codex/issues/51335) Update collaboration snapshots for full-history fork instructions [@jif-oai](https://github.com/jif-oai) - [#51347](https://github.com/openai/codex/issues/51347) Measure shell snapshot use and wait time per command [@jif-oai](https://github.com/jif-oai) - [#51350](https://github.com/openai/codex/issues/51350) Allow larger shell snapshots when replaying from a file [@jif-oai](https://github.com/jif-oai) - [#51355](https://github.com/openai/codex/issues/51355) Add bounded diagnostics for agent spawn failures [@jif-oai](https://github.com/jif-oai) - [#51378](https://github.com/openai/codex/issues/51378) Keep Guardian v2 WebSocket pools warm with concurrent replenishment [@jif-oai](https://github.com/jif-oai) - [#51391](https://github.com/openai/codex/issues/51391) Make URLs in asynchronous question titles clickable [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51396](https://github.com/openai/codex/issues/51396) Let late low-risk scores complete pending Guardian reviews [@jif-oai](https://github.com/jif-oai) - [#51400](https://github.com/openai/codex/issues/51400) Prevent later Guardian scores from releasing earlier pending reviews [@jif-oai](https://github.com/jif-oai) - [#51402](https://github.com/openai/codex/issues/51402) Preserve turn attribution across recovery and compaction [@eddie-openai](https://github.com/eddie-openai) - [#51407](https://github.com/openai/codex/issues/51407) Protect ripgrep lookup during Linux sandbox construction [@viyatb-oai](https://github.com/viyatb-oai) - [#51411](https://github.com/openai/codex/issues/51411) Suppress repeated image paste presses in legacy terminals [@etraut-openai](https://github.com/etraut-openai) - [#51415](https://github.com/openai/codex/issues/51415) Expose and persist turn lineage across the app server [@eddie-openai](https://github.com/eddie-openai) - [#51419](https://github.com/openai/codex/issues/51419) Preserve turn attribution when queued mail wakes durable sleep [@eddie-openai](https://github.com/eddie-openai) - [#51420](https://github.com/openai/codex/issues/51420) Finish idle thread unloads after slow shutdown [@jif-oai](https://github.com/jif-oai) - [#51421](https://github.com/openai/codex/issues/51421) Include root turn IDs in host-owned Apps tool calls [@eddie-openai](https://github.com/eddie-openai) - [#51422](https://github.com/openai/codex/issues/51422) Accept environment requests at thread and turn settings boundaries [@anp-oai](https://github.com/anp-oai) - [#51425](https://github.com/openai/codex/issues/51425) Skip stable installer alias publishing for prereleases [@zsol-openai](https://github.com/zsol-openai) - [#51426](https://github.com/openai/codex/issues/51426) Remove the Bazel JVM override for Windows ARM64 voice builds [@anp-oai](https://github.com/anp-oai) - [#51427](https://github.com/openai/codex/issues/51427) Prevent invalidated wakeups from starting a turn [@jif-oai](https://github.com/jif-oai) - [#51433](https://github.com/openai/codex/issues/51433) Show hook status messages as titles in the hooks browser [@abhinav-oai](https://github.com/abhinav-oai) - [#51439](https://github.com/openai/codex/issues/51439) Preserve clickable URLs in TUI approval headers [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51440](https://github.com/openai/codex/issues/51440) Honor Retry-After in WebSocket error events [@anp-oai](https://github.com/anp-oai) - [#51441](https://github.com/openai/codex/issues/51441) Fix core integration tests for updated turn APIs [@anp-oai](https://github.com/anp-oai) - [#51449](https://github.com/openai/codex/issues/51449) Make URLs clickable in TUI user input questions [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51450](https://github.com/openai/codex/issues/51450) Make URLs clickable in MCP elicitation prompts [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51451](https://github.com/openai/codex/issues/51451) Make URLs in the TUI warnings viewer clickable [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51452](https://github.com/openai/codex/issues/51452) Make banner URLs clickable across wrapped lines [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51457](https://github.com/openai/codex/issues/51457) Preserve status usage hyperlinks when the URL wraps [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51458](https://github.com/openai/codex/issues/51458) Make URLs clickable in user verification prompts [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51459](https://github.com/openai/codex/issues/51459) Preserve wrapped help links in Windows sandbox prompts [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51460](https://github.com/openai/codex/issues/51460) Retry realtime sideband attachment while an existing call activates [@bullman-oai](https://github.com/bullman-oai) - [#51463](https://github.com/openai/codex/issues/51463) Record resolved model and reasoning effort in sub-agent activity [@sdcoffey](https://github.com/sdcoffey) - [#51465](https://github.com/openai/codex/issues/51465) Add an optional JSON transcript format for Guardian [@felixxia-oai](https://github.com/felixxia-oai) - [#51466](https://github.com/openai/codex/issues/51466) Keep Guardian transcript records structured through budget recovery [@felixxia-oai](https://github.com/felixxia-oai) - [#51467](https://github.com/openai/codex/issues/51467) Keep submission logs useful without exposing payloads [@chess-oai](https://github.com/chess-oai) - [#51470](https://github.com/openai/codex/issues/51470) Raise the managed app-server file descriptor limit on Unix [@etraut-openai](https://github.com/etraut-openai) - [#51471](https://github.com/openai/codex/issues/51471) Preserve clickable URLs in pending input previews [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51472](https://github.com/openai/codex/issues/51472) Preserve clickable URLs in TUI selection rows [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51473](https://github.com/openai/codex/issues/51473) Preserve URL destinations in wrapped hook details [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51480](https://github.com/openai/codex/issues/51480) Preserve tool declaration mode across resumed context windows [@pakrym-oai](https://github.com/pakrym-oai) - [#51482](https://github.com/openai/codex/issues/51482) Use PathUri for skill identity and path matching [@anp-oai](https://github.com/anp-oai) - [#51483](https://github.com/openai/codex/issues/51483) Add correlated, credential-free rendezvous connection diagnostics [@alexi-openai](https://github.com/alexi-openai) - [#51491](https://github.com/openai/codex/issues/51491) Classify executor capability root ownership independently of parsing [@stevenlee-oai](https://github.com/stevenlee-oai) - [#51492](https://github.com/openai/codex/issues/51492) Remove obsolete fields from persisted turn context [@pakrym-oai](https://github.com/pakrym-oai) - [#51493](https://github.com/openai/codex/issues/51493) Bind capability roots to environment selections [@anp-oai](https://github.com/anp-oai) - [#51499](https://github.com/openai/codex/issues/51499) Load rollout history on a single blocking worker [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#51500](https://github.com/openai/codex/issues/51500) Add shared task pinning to the agent command center [@etraut-openai](https://github.com/etraut-openai) - [#51502](https://github.com/openai/codex/issues/51502) Bound relay connection attempts and handle pongs during blocked writes [@alexi-openai](https://github.com/alexi-openai) - [#51503](https://github.com/openai/codex/issues/51503) Expose selected environments to MCP contributors [@mtsui-oai](https://github.com/mtsui-oai) - [#51510](https://github.com/openai/codex/issues/51510) Preserve live TUI settings when configuration reloads fail [@imac-oai](https://github.com/imac-oai) - [#51511](https://github.com/openai/codex/issues/51511) Fix Windows 10 drive-letter opens for no-follow filesystem operations [@zm-oai](https://github.com/zm-oai) - [#51512](https://github.com/openai/codex/issues/51512) Align Windows sandbox temp permissions with the child environment [@zm-oai](https://github.com/zm-oai) - [#51515](https://github.com/openai/codex/issues/51515) Expose detailed agent tree shutdown failure reports [@keitht-openai](https://github.com/keitht-openai) - [#51517](https://github.com/openai/codex/issues/51517) Pass thread persistence intent to attachment uploads [@kchainani-oai](https://github.com/kchainani-oai) - [#51525](https://github.com/openai/codex/issues/51525) Preserve the CLI MXC preference in executor config reads [@zm-oai](https://github.com/zm-oai) - [#51527](https://github.com/openai/codex/issues/51527) Ignore ripgrep configuration when expanding sandbox deny globs [@viyatb-oai](https://github.com/viyatb-oai) ### [`v0.161.0`](https://github.com/openai/codex/releases/tag/rust-v0.161.0): 0.161.0 [Compare Source](https://github.com/openai/codex/compare/rust-v0.160.1...rust-v0.161.0-alpha.13.1) #### New Features - GPT-6.1 Sol is now the default model in the bundled and Amazon Bedrock catalogs. ([#49318](https://github.com/openai/codex/issues/49318), [#49339](https://github.com/openai/codex/issues/49339)) - Amazon Bedrock supports multi-agent V2 and Ultra reasoning on compatible models; Bedrock Mantle also accepts AWS GovCloud regions. ([#49345](https://github.com/openai/codex/issues/49345), [#49813](https://github.com/openai/codex/issues/49813)) - Sign in to MCP servers from an active terminal session with `/mcp login <name>`. ([#49290](https://github.com/openai/codex/issues/49290)) - Choose your microphone, speaker, and microphone input channels for voice conversations, with preferences saved locally. ([#49437](https://github.com/openai/codex/issues/49437), [#49836](https://github.com/openai/codex/issues/49836)) - Daybreak is opt-in through `--enable cli_daybreak` or `features.cli_daybreak=true`; `daybreak=true` alone is insufficient. By default, controls and indicators are hidden, `/daybreak` is unavailable, and automatic Cyber routing is omitted—even for saved Daybreak threads. Saved preferences remain intact. Opt-in routing requires eligible ChatGPT sign-in, the OpenAI provider, and advertised model/program support. ([#49856](https://github.com/openai/codex/issues/49856), [#49858](https://github.com/openai/codex/issues/49858), [#49859](https://github.com/openai/codex/issues/49859), [#49861](https://github.com/openai/codex/issues/49861), [#51207](https://github.com/openai/codex/issues/51207)) - Select a Cyber access program per turn with `codex exec --cyber-access-program` or the TypeScript SDK’s `cyberAccessProgram` option. The explicit exec override remains available with `cli_daybreak` disabled and leaves the saved choice unchanged. ([#49939](https://github.com/openai/codex/issues/49939), [#51207](https://github.com/openai/codex/issues/51207)) #### Bug Fixes - Approved filesystem escalation can now grant broader write access while preserving denied reads and network restrictions. Background tasks retain their originating turn’s permissions. ([#49353](https://github.com/openai/codex/issues/49353), [#49880](https://github.com/openai/codex/issues/49880)) - Explicit launch permissions survive terminal reconnects and new sessions, while implicit client settings no longer overwrite server or saved-thread web-search settings. ([#49809](https://github.com/openai/codex/issues/49809), [#49799](https://github.com/openai/codex/issues/49799)) - Elevated Windows terminal sessions can start using an embedded server, and sandboxed PowerShell preserves relative paths beneath protected user profiles. ([#49855](https://github.com/openai/codex/issues/49855), [#49690](https://github.com/openai/codex/issues/49690)) - Enter correctly submits buffered input after paste detection expires, including in Vim insert mode. ([#49810](https://github.com/openai/codex/issues/49810)) - Thread resume includes the latest committed history. Startup detects recoverable SQLite corruption earlier and preserves damaged databases as backups. ([#49599](https://github.com/openai/codex/issues/49599), [#49701](https://github.com/openai/codex/issues/49701)) - Responses retries and WebSocket-to-HTTP fallback honor server retry guidance, reducing premature failures during overload. ([#49441](https://github.com/openai/codex/issues/49441)) #### Documentation - Authentication guidance now accounts for keyring storage instead of implying credentials always reside in `auth.json`. ([#49361](https://github.com/openai/codex/issues/49361)) #### Chores - Publishing an older alpha or hotfix no longer moves npm alpha tags backward. ([#49704](https://github.com/openai/codex/issues/49704)) #### Changelog Full Changelog: <https://github.com/openai/codex/compare/rust-v0.160.0...rust-v0.161.0> - [#49246](https://github.com/openai/codex/issues/49246) Use executable fixture copying in the bundled bwrap test [@felixxia-oai](https://github.com/felixxia-oai) - [#49257](https://github.com/openai/codex/issues/49257) Allow Guardian cached approvals with incomplete root context [@felixxia-oai](https://github.com/felixxia-oai) - [#49260](https://github.com/openai/codex/issues/49260) Restrict enterprise MCP auth and fail closed on config refresh [@nicksteele-oai](https://github.com/nicksteele-oai) - [#49261](https://github.com/openai/codex/issues/49261) Preserve Windows sandbox runner launch errors [@zm-oai](https://github.com/zm-oai) - [#49262](https://github.com/openai/codex/issues/49262) Trace turn phases and correlate accepted input with turns [@jif-oai](https://github.com/jif-oai) - [#49266](https://github.com/openai/codex/issues/49266) Remove the remote agent message board client README [@jif-oai](https://github.com/jif-oai) - [#49267](https://github.com/openai/codex/issues/49267) Support remote agent message boards in multi-agent sessions [@jif-oai](https://github.com/jif-oai) - [#49269](https://github.com/openai/codex/issues/49269) Preserve thread overrides and cloud policy validity during config reloads [@nicksteele-oai](https://github.com/nicksteele-oai) - [#49275](https://github.com/openai/codex/issues/49275) Isolate realtime conversation tests from Responses prewarm connections [@felixxia-oai](https://github.com/felixxia-oai) - [#49276](https://github.com/openai/codex/issues/49276) Enable enterprise MCP sign-in and account-scoped grant cleanup [@nicksteele-oai](https://github.com/nicksteele-oai) - [#49277](https://github.com/openai/codex/issues/49277) Avoid a turn teardown race in the Guardian agent message test [@felixxia-oai](https://github.com/felixxia-oai) - [#49280](https://github.com/openai/codex/issues/49280) Restrict capability roots to captured turn environments [@miz-openai](https://github.com/miz-openai) - [#49286](https://github.com/openai/codex/issues/49286) Model exec-server session attachment state as an enum [@jif-oai](https://github.com/jif-oai) - [#49290](https://github.com/openai/codex/issues/49290) Add `/mcp login <name>` to the TUI [@nicksteele-oai](https://github.com/nicksteele-oai) - [#49294](https://github.com/openai/codex/issues/49294) Record Guardian context mode in review and classification telemetry [@felixxia-oai](https://github.com/felixxia-oai) - [#49295](https://github.com/openai/codex/issues/49295) Simplify configuration fingerprint canonicalization [@jif-oai](https://github.com/jif-oai) - [#49297](https://github.com/openai/codex/issues/49297) Scan the session index backwards for batch thread name lookups [@jif-oai](https://github.com/jif-oai) - [#49300](https://github.com/openai/codex/issues/49300) Compact the inline hidden tag buffer once per chunk [@jif-oai](https://github.com/jif-oai) - [#49305](https://github.com/openai/codex/issues/49305) Batch metadata reads when resolving thread names [@jif-oai](https://github.com/jif-oai) - [#49308](https://github.com/openai/codex/issues/49308) Run piped legacy Windows sandbox processes without a console [@etraut-openai](https://github.com/etraut-openai) - [#49312](https://github.com/openai/codex/issues/49312) Notify parent agents when Guardian stops a subagent [@jif-oai](https://github.com/jif-oai) - [#49316](https://github.com/openai/codex/issues/49316) Bump taiki-e/install-action to v2.87.21 in CI setup [@jgershen-oai](https://github.com/jgershen-oai) - [#49318](https://github.com/openai/codex/issues/49318) Add GPT-6.1 Sol as the default catalog model [@andrewgu-oai](https://github.com/andrewgu-oai) - [#49325](https://github.com/openai/codex/issues/49325) Retry Windows sandbox runner logon once on error 1056 [@zm-oai](https://github.com/zm-oai) - [#49330](https://github.com/openai/codex/issues/49330) Keep remote control reconnect backoff capped during sustained failures [@yansenzhou-oai](https://github.com/yansenzhou-oai) - [#49332](https://github.com/openai/codex/issues/49332) Clean up canceled exec-server RPC requests immediately [@jif-oai](https://github.com/jif-oai) - [#49339](https://github.com/openai/codex/issues/49339) Add GPT-6.1 Sol to Bedrock catalogs and make it the default [@celia-oai](https://github.com/celia-oai) - [#49345](https://github.com/openai/codex/issues/49345) Enable multi-agent V2 and Ultra reasoning on Amazon Bedrock [@celia-oai](https://github.com/celia-oai) - [#49353](https://github.com/openai/codex/issues/49353) Allow approved filesystem escalation while preserving denied reads [@viyatb-oai](https://github.com/viyatb-oai) - [#49357](https://github.com/openai/codex/issues/49357) Continue Markdown blockquotes when pasting multiline text [@bc-openai](https://github.com/bc-openai) - [#49360](https://github.com/openai/codex/issues/49360) Carry shell invocation metadata and report executor PATH directories [@anp-oai](https://github.com/anp-oai) - [#49361](https://github.com/openai/codex/issues/49361) Clarify credential storage wording across authentication UI and docs [@celia-oai](https://github.com/celia-oai) - [#49369](https://github.com/openai/codex/issues/49369) Update Bedrock GPT-6 Sol catalog tests to expect multi-agent V2 [@celia-oai](https://github.com/celia-oai) - [#49379](https://github.com/openai/codex/issues/49379) Compile hook matchers during discovery [@jif-oai](https://github.com/jif-oai) - [#49384](https://github.com/openai/codex/issues/49384) Track credential storage outcomes and redact sensitive errors [@celia-oai](https://github.com/celia-oai) - [#49388](https://github.com/openai/codex/issues/49388) Fix Windows path inference for opaque URIs with slash prefixes [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49389](https://github.com/openai/codex/issues/49389) Serialize tests that share Windows sandbox accounts [@jgershen-oai](https://github.com/jgershen-oai) - [#49392](https://github.com/openai/codex/issues/49392) Add attributed MCP OAuth credential storage telemetry [@celia-oai](https://github.com/celia-oai) - [#49395](https://github.com/openai/codex/issues/49395) Remove randomized greetings from TUI session headers [@etraut-openai](https://github.com/etraut-openai) - [#49401](https://github.com/openai/codex/issues/49401) Preserve live tool-call metadata across request windows [@ningyi-oai](https://github.com/ningyi-oai) - [#49403](https://github.com/openai/codex/issues/49403) Add an experimental flag for bundled tools in login shells [@anp-oai](https://github.com/anp-oai) - [#49406](https://github.com/openai/codex/issues/49406) Support explicit cyber access programs with OpenAI API keys [@julee-oai](https://github.com/julee-oai) - [#49407](https://github.com/openai/codex/issues/49407) Recover exec-server sessions after environment info timeouts [@vivi](https://github.com/vivi) - [#49408](https://github.com/openai/codex/issues/49408) Compare tool call metadata in the recorder refresh test [@euroelessar](https://github.com/euroelessar) - [#49411](https://github.com/openai/codex/issues/49411) Bind the app-server time provider to a local variable [@euroelessar](https://github.com/euroelessar) - [#49414](https://github.com/openai/codex/issues/49414) Filter graceful shutdown guard and trigger traces from SQLite logs [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49415](https://github.com/openai/codex/issues/49415) Truncate input text in protocol debug output [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49416](https://github.com/openai/codex/issues/49416) Omit payloads from multiline ANSI warnings [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49424](https://github.com/openai/codex/issues/49424) Infer Windows UNC paths with forward and mixed slashes [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49425](https://github.com/openai/codex/issues/49425) Prune diagnostic logs periodically by age and database size [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49426](https://github.com/openai/codex/issues/49426) Enable analytics by default for daemon-launched app servers [@bc-openai](https://github.com/bc-openai) - [#49432](https://github.com/openai/codex/issues/49432) Preserve bootstrap discovery across authentication changes [@cooper-oai](https://github.com/cooper-oai) - [#49437](https://github.com/openai/codex/issues/49437) Add local audio device selection to TUI voice settings [@bc-openai](https://github.com/bc-openai) - [#49441](https://github.com/openai/codex/issues/49441) Honor server retry advice across Responses retries and fallback [@anp-oai](https://github.com/anp-oai) - [#49444](https://github.com/openai/codex/issues/49444) Use `memrchr` to find newlines in reverse JSONL scans [@btraut-openai](https://github.com/btraut-openai) - [#49467](https://github.com/openai/codex/issues/49467) Restore executor tool paths after login shell startup [@anp-oai](https://github.com/anp-oai) - [#49472](https://github.com/openai/codex/issues/49472) Use server-authoritative permissions in the TUI [@etraut-openai](https://github.com/etraut-openai) - [#49473](https://github.com/openai/codex/issues/49473) Use the rmcp SDK for enterprise-managed token exchanges [@nicksteele-oai](https://github.com/nicksteele-oai) - [#49475](https://github.com/openai/codex/issues/49475) Complete turn abort callbacks before emitting terminal events [@euroelessar](https://github.com/euroelessar) - [#49478](https://github.com/openai/codex/issues/49478) Discover and validate MCP authorization servers before ID-JAG exchange [@nicksteele-oai](https://github.com/nicksteele-oai) - [#49480](https://github.com/openai/codex/issues/49480) Add experimental thread prediction protocol types [@keyz](https://github.com/keyz) - [#49489](https://github.com/openai/codex/issues/49489) Add regression coverage for account switches between analytics batches [@anp-oai](https://github.com/anp-oai) - [#49517](https://github.com/openai/codex/issues/49517) Add a fork shortcut to the TUI command center [@etraut-openai](https://github.com/etraut-openai) - [#49560](https://github.com/openai/codex/issues/49560) Add an opt-in model catalog to multi-agent context [@jif-oai](https://github.com/jif-oai) - [#49564](https://github.com/openai/codex/issues/49564) Copy selected file paths as plain text in the TUI [@fcoury-oai](https://github.com/fcoury-oai) - [#49584](https://github.com/openai/codex/issues/49584) Skip host skill discovery for Guardian reviews [@jif-oai](https://github.com/jif-oai) - [#49595](https://github.com/openai/codex/issues/49595) Make the strict network approval test independent of request order [@jif-oai](https://github.com/jif-oai) - [#49598](https://github.com/openai/codex/issues/49598) Persist explicit user goal edits in model history [@felixxia-oai](https://github.com/felixxia-oai) - [#49599](https://github.com/openai/codex/issues/49599) Return authoritative replay history when resuming a thread [@felixxia-oai](https://github.com/felixxia-oai) - [#49600](https://github.com/openai/codex/issues/49600) Reuse unchanged history snapshots when resuming threads [@felixxia-oai](https://github.com/felixxia-oai) - [#49624](https://github.com/openai/codex/issues/49624) Use server authentication for explicit remote session commands [@cooper-oai](https://github.com/cooper-oai) - [#49642](https://github.com/openai/codex/issues/49642) Allow managed requirements to disable the Windows MXC sandbox [@iceweasel-oai](https://github.com/iceweasel-oai) - [#49675](https://github.com/openai/codex/issues/49675) Serialize Responses routing fields before large inputs [@jbeckwith-oai](https://github.com/jbeckwith-oai) - [#49678](https://github.com/openai/codex/issues/49678) Escape command drafts when recovering question answers [@imac-oai](https://github.com/imac-oai) - [#49683](https://github.com/openai/codex/issues/49683) Add a managed feature gate for in-app voice [@vishnu-oai](https://github.com/vishnu-oai) - [#49686](https://github.com/openai/codex/issues/49686) Deliver remote message board notifications to active turns [@jif-oai](https://github.com/jif-oai) - [#49689](https://github.com/openai/codex/issues/49689) Export skill invocation events through OpenTelemetry [@jif-oai](https://github.com/jif-oai) - [#49690](https://github.com/openai/codex/issues/49690) Preserve PowerShell relative paths in the elevated Windows sandbox [@johnl-oai](https://github.com/johnl-oai) - [#49692](https://github.com/openai/codex/issues/49692) Keep compressed rollout snippet searches on one blocking worker [@npancha-openai](https://github.com/npancha-openai) - [#49693](https://github.com/openai/codex/issues/49693) Move thread history projection into one blocking task [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#49694](https://github.com/openai/codex/issues/49694) Batch rollout listing scans on cancellable blocking workers [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#49696](https://github.com/openai/codex/issues/49696) Make exec-server file reads cancellable between chunks [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#49701](https://github.com/openai/codex/issues/49701) Detect SQLite corruption during startup and preserve recovery backups [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49702](https://github.com/openai/codex/issues/49702) Rename exec-server file handle management identifiers [@anp-oai](https://github.com/anp-oai) - [#49704](https://github.com/openai/codex/issues/49704) Prevent npm alpha dist-tags from moving backward [@imac-oai](https://github.com/imac-oai) - [#49706](https://github.com/openai/codex/issues/49706) Upgrade the argument comment lint toolchain and Dylint [@tamird](https://github.com/tamird) - [#49708](https://github.com/openai/codex/issues/49708) Move session index I/O off async runtime threads [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#49710](https://github.com/openai/codex/issues/49710) Classify SQLite corruption using typed error codes [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49712](https://github.com/openai/codex/issues/49712) Avoid full-string scans in token-budget truncation [@jif-oai](https://github.com/jif-oai) - [#49713](https://github.com/openai/codex/issues/49713) Remove repository-local Codex guidance, skills, and environment config [@anp-oai](https://github.com/anp-oai) - [#49714](https://github.com/openai/codex/issues/49714) Decouple API-key cyber access programs from model discovery [@julee-oai](https://github.com/julee-oai) - [#49715](https://github.com/openai/codex/issues/49715) Add account security setup reminders to the TUI [@dennyku](https://github.com/dennyku) - [#49778](https://github.com/openai/codex/issues/49778) Define exec-server protocol types for streamed file writes [@anp-oai](https://github.com/anp-oai) - [#49781](https://github.com/openai/codex/issues/49781) Include the environment's MXC backend in MCP sandbox metadata [@zm-oai](https://github.com/zm-oai) - [#49782](https://github.com/openai/codex/issues/49782) Clean up process groups for failed shell snapshot captures [@jif-oai](https://github.com/jif-oai) - [#49783](https://github.com/openai/codex/issues/49783) Preserve background thread requests when forking in the TUI [@etraut-openai](https://github.com/etraut-openai) - [#49784](https://github.com/openai/codex/issues/49784) Add a requirements feature gate for the browser annotation API [@tepman-oai](https://github.com/tepman-oai) - [#49785](https://github.com/openai/codex/issues/49785) Persist empty paginated threads when naming them [@rd-oai](https://github.com/rd-oai) - [#49786](https://github.com/openai/codex/issues/49786) Clarify V2 spawn model override guidance for context catalogs [@jif-oai](https://github.com/jif-oai) - [#49787](https://github.com/openai/codex/issues/49787) Remove `AGENTS.md` from Bazel core test data [@andrewgu-oai](https://github.com/andrewgu-oai) - [#49792](https://github.com/openai/codex/issues/49792) Add retained conversation support to Guardian async sampling [@felixxia-oai](https://github.com/felixxia-oai) - [#49793](https://github.com/openai/codex/issues/49793) Add conversation mode to Guardian v2 async classification [@felixxia-oai](https://github.com/felixxia-oai) - [#49795](https://github.com/openai/codex/issues/49795) Avoid duplicate sync reviews in Guardian classifier continuations [@felixxia-oai](https://github.com/felixxia-oai) - [#49796](https://github.com/openai/codex/issues/49796) Deduplicate Guardian retained-context omission notices [@felixxia-oai](https://github.com/felixxia-oai) - [#49798](https://github.com/openai/codex/issues/49798) Share cached exec-server environment info with Arc [@anp-oai](https://github.com/anp-oai) - [#49799](https://github.com/openai/codex/issues/49799) Preserve server web-search settings in the TUI [@etraut-openai](https://github.com/etraut-openai) - [#49800](https://github.com/openai/codex/issues/49800) Allow cleanup of replay-only side conversations with missing threads [@bc-openai](https://github.com/bc-openai) - [#49801](https://github.com/openai/codex/issues/49801) Update the Rust toolchain action for argument-comment linting [@andrewgu-oai](https://github.com/andrewgu-oai) - [#49804](https://github.com/openai/codex/issues/49804) Use platform-specific modifier labels in TUI shortcut hints [@bc-openai](https://github.com/bc-openai) - [#49805](https://github.com/openai/codex/issues/49805) Add capability-gated writable file streams to the exec-server client [@anp-oai](https://github.com/anp-oai) - [#49806](https://github.com/openai/codex/issues/49806) Accept unknown Codex error variants in the app-server protocol [@anp-oai](https://github.com/anp-oai) - [#49807](https://github.com/openai/codex/issues/49807) Enable API-key model discovery by default [@andrewgu-oai](https://github.com/andrewgu-oai) - [#49809](https://github.com/openai/codex/issues/49809) Preserve local launch permissions across TUI sessions and reconnects [@etraut-openai](https://github.com/etraut-openai) - [#49810](https://github.com/openai/codex/issues/49810) Flush expired paste bursts before handling Enter [@bc-openai](https://github.com/bc-openai) - [#49811](https://github.com/openai/codex/issues/49811) Handle unsupported `fs/writeBlock` requests in exec-server [@anp-oai](https://github.com/anp-oai) - [#49812](https://github.com/openai/codex/issues/49812) Move shadow skill ranking off the turn preparation path [@vkg-oai](https://github.com/vkg-oai) - [#49813](https://github.com/openai/codex/issues/49813) Support AWS GovCloud regions for Amazon Bedrock Mantle [@alexsong-oai](https://github.com/alexsong-oai) - [#49814](https://github.com/openai/codex/issues/49814) Add coordinated shutdown for local agent trees [@owenlin0](https://github.com/owenlin0) - [#49816](https://github.com/openai/codex/issues/49816) Remove browser-open success messages from the TUI [@bc-openai](https://github.com/bc-openai) - [#49817](https://github.com/openai/codex/issues/49817) Add an advisory Bedrock GovCloud requirements check [@alexsong-oai](https://github.com/alexsong-oai) - [#49818](https://github.com/openai/codex/issues/49818) Use dedicated parameters for sandboxed file opens [@anp-oai](https://github.com/anp-oai) - [#49819](https://github.com/openai/codex/issues/49819) Recover daemon startup and updater re-exec after cwd deletion [@etraut-openai](https://github.com/etraut-openai) - [#49822](https://github.com/openai/codex/issues/49822) Box the resume future in the agents overview permissions test [@sayan-oai](https://github.com/sayan-oai) - [#49835](https://github.com/openai/codex/issues/49835) Clarify service tier default save errors in the TUI [@etraut-openai](https://github.com/etraut-openai) - [#49836](https://github.com/openai/codex/issues/49836) Allow microphone channel selection for voice conversations [@bc-openai](https://github.com/bc-openai) - [#49843](https://github.com/openai/codex/issues/49843) Preserve daemon diagnostics and include updater logs in reports [@etraut-openai](https://github.com/etraut-openai) - [#49846](https://github.com/openai/codex/issues/49846) Capture host-supplied extension data for each turn [@sayan-oai](https://github.com/sayan-oai) - [#49847](https://github.com/openai/codex/issues/49847) Persist world-state snapshots alongside rendered context [@pakrym-oai](https://github.com/pakrym-oai) - [#49850](https://github.com/openai/codex/issues/49850) Launch Windows daemon children in a dedicated working directory [@etraut-openai](https://github.com/etraut-openai) - [#49852](https://github.com/openai/codex/issues/49852) Improve diagnostics for report attachment failures [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49855](https://github.com/openai/codex/issues/49855) Use embedded mode for elevated Windows TUI sessions [@etraut-openai](https://github.com/etraut-openai) - [#49856](https://github.com/openai/codex/issues/49856) Support Daybreak selection in `codex exec` [@etraut-openai](https://github.com/etraut-openai) - [#49857](https://github.com/openai/codex/issues/49857) Use the model catalog to select TUI cyber refusal guidance [@etraut-openai](https://github.com/etraut-openai) - [#49858](https://github.com/openai/codex/issues/49858) Add a persistent `/daybreak` toggle to the TUI [@etraut-openai](https://github.com/etraut-openai) - [#49859](https://github.com/openai/codex/issues/49859) Honor Daybreak settings in TUI continuations and background tasks [@etraut-openai](https://github.com/etraut-openai) - [#49861](https://github.com/openai/codex/issues/49861) Add Daybreak state to the status line and terminal title [@etraut-openai](https://github.com/etraut-openai) - [#49867](https://github.com/openai/codex/issues/49867) Update elevated-launch warning snapshot to use `⌃o` for copy [@etraut-openai](https://github.com/etraut-openai) - [#49874](https://github.com/openai/codex/issues/49874) Point usage and credit links to ChatGPT settings [@etraut-openai](https://github.com/etraut-openai) - [#49875](https://github.com/openai/codex/issues/49875) Decouple TUI startup presentation from execution configuration [@etraut-openai](https://github.com/etraut-openai) - [#49876](https://github.com/openai/codex/issues/49876) Remove personality plumbing from the TUI [@etraut-openai](https://github.com/etraut-openai) - [#49880](https://github.com/openai/codex/issues/49880) Bind permission grants to the originating turn [@anp-oai](https://github.com/anp-oai) - [#49894](https://github.com/openai/codex/issues/49894) Return world-state snapshots and context updates together [@pakrym-oai](https://github.com/pakrym-oai) - [#49898](https://github.com/openai/codex/issues/49898) Scope extension filesystem access to callback permissions [@anp-oai](https://github.com/anp-oai) - [#49910](https://github.com/openai/codex/issues/49910) Preserve validation errors for invalid TUI keybindings [@etraut-openai](https://github.com/etraut-openai) - [#49912](https://github.com/openai/codex/issues/49912) Respect approval policies in temporary structured threads [@etraut-openai](https://github.com/etraut-openai) - [#49939](https://github.com/openai/codex/issues/49939) Add per-turn Cyber access program selection to exec and the SDK [@mldangelo-oai](https://github.com/mldangelo-oai) - [#49946](https://github.com/openai/codex/issues/49946) Prevent stale file search results from being labeled with a new query [@jif-oai](https://github.com/jif-oai) - [#49951](https://github.com/openai/codex/issues/49951) Include preceding assistant context in Guardian sender reviews [@jif-oai](https://github.com/jif-oai) - [#49956](https://github.com/openai/codex/issues/49956) Cache the placeholder regex for MCP hook argument expansion [@jif-oai](https://github.com/jif-oai) - [#49959](https://github.com/openai/codex/issues/49959) Test session index thread-name append and removal [@jif-oai](https://github.com/jif-oai) - [#49972](https://github.com/openai/codex/issues/49972) Share byte buffers across exec-server output chunks [@jif-oai](https://github.com/jif-oai) - [#49987](https://github.com/openai/codex/issues/49987) Add renewable EMA HTTP authentication and credential versioning [@nicksteele-oai](https://github.com/nicksteele-oai) - [#49993](https://github.com/openai/codex/issues/49993) Preserve the async Guardian history prefix as retained context changes [@felixxia-oai](https://github.com/felixxia-oai) ### [`v0.160.1`](https://github.com/openai/codex/releases/tag/rust-v0.160.1): 0.160.1 [Compare Source](https://github.com/openai/codex/compare/rust-v0.160.0-alpha.6.2...rust-v0.160.1) #### Bug Fixes - Preserve `SYSTEMROOT`, `TEMP`, and `TMP` when launching remote stdio MCP servers with explicitly configured remote environment variables, allowing Unix hosts to retain the Windows executor's startup environment. #### Changelog - [#51121](https://github.com/openai/codex/pull/51121): Backport Windows remote MCP environment preservation to 0.160. ### [`v0.160.0`](https://github.com/openai/codex/releases/tag/rust-v0.160.0): 0.160.0 [Compare Source](https://github.com/openai/codex/compare/rust-v0.159.3...rust-v0.160.0-alpha.6.2) #### New Features - Browse older tasks in the agent command center with a keyboard-accessible “Show more” action. ([#49106](https://github.com/openai/codex/issues/49106)) - Select transcript text and paste with middle-click in fullscreen mode on supported local Linux X11 terminals. ([#49112](https://github.com/openai/codex/issues/49112)) - Start sessions outside a project with workspace defaults when policy permits, and restore saved permissions when resuming. ([#49160](https://github.com/openai/codex/issues/49160)) - Added opt-in Guardian review capabilities to retrieve earlier user instructions and include context from agent handoffs. ([#49036](https://github.com/openai/codex/issues/49036), [#49057](https://github.com/openai/codex/issues/49057)) #### Bug Fixes - Unsent queued messages now resume after reconnection once uncertain submissions are resolved, avoiding duplicate sends. ([#49105](https://github.com/openai/codex/issues/49105)) - The terminal UI now preserves server provider, reasoning-summary, and verbosity settings and shows the correct sessions in resume and fork history. ([#49144](https://github.com/openai/codex/issues/49144), [#49161](https://github.com/openai/codex/issues/49161), [#49171](https://github.com/openai/codex/issues/49171)) - Fixed Windows sandbox PowerShell fallbacks and long-path permission repairs, and suppressed unwanted console windows from background helpers. ([#49019](https://github.com/openai/codex/issues/49019), [#49058](https://github.com/openai/codex/issues/49058), [#49098](https://github.com/openai/codex/issues/49098), [#49164](https://github.com/openai/codex/issues/49164), [#49386](https://github.com/openai/codex/issues/49386)) - Subagents now retain environments that are still starting and receive their configuration or preparation failure. ([#49075](https://github.com/openai/codex/issues/49075)) - Prevented SQLite stalls during connection setup and logging, and surfaced initialization errors instead of masking them as timeouts. ([#49032](https://github.com/openai/codex/issues/49032), [#49102](https://github.com/openai/codex/issues/49102)) - Explicit provider model catalogs no longer include unsupported bundled models or reuse stale entries after refresh failures. ([#49135](https://github.com/openai/codex/issues/49135)) #### Documentation - Clarified how provider credentials use the configured storage backend and how `env_key` identifies the API-key environment variable. ([#49118](https://github.com/openai/codex/issues/49118)) #### Chores - Reduced repeated plugin-loading work by caching parsed manifests and reusing HTTP connections for remote plugin requests. ([#49099](https://github.com/openai/codex/issues/49099), [#49100](https://github.com/openai/codex/issues/49100)) - Added background reclamation of unused log database space to reduce disk usage. ([#49069](https://github.com/openai/codex/issues/49069)) #### Changelog Full Changelog: <https://github.com/openai/codex/compare/rust-v0.159.0...rust-v0.160.0> - [#48983](https://github.com/openai/codex/issues/48983) Avoid full metadata rewrites for thread timestamp updates [@jif-oai](https://github.com/jif-oai) - [#49000](https://github.com/openai/codex/issues/49000) Isolate the memory startup metadata test from Git enrichment [@jif-oai](https://github.com/jif-oai) - [#49019](https://github.com/openai/codex/issues/49019) Use a compatible PowerShell fallback for the Windows MXC sandbox [@iceweasel-oai](https://github.com/iceweasel-oai) - [#49028](https://github.com/openai/codex/issues/49028) Use the numeric ioctl value in the macOS sandbox policy [@aionescu-oai](https://github.com/aionescu-oai) - [#49031](https://github.com/openai/codex/issues/49031) Clarify ChatGPT sign-in success copy [@bc-openai](https://github.com/bc-openai) - [#49032](https://github.com/openai/codex/issues/49032) Avoid SQLite stalls from connection setup and stderr span logging [@jif-oai](https://github.com/jif-oai) - [#49036](https://github.com/openai/codex/issues/49036) Add opt-in conversation history retrieval to Guardian reviews [@felixxia-oai](https://github.com/felixxia-oai) - [#49037](https://github.com/openai/codex/issues/49037) Show the Plan mode cycling hint in the fullscreen status line [@fcoury-oai](https://github.com/fcoury-oai) - [#49038](https://github.com/openai/codex/issues/49038) Preserve encrypted agent messages in Guardian reviews [@felixxia-oai](https://github.com/felixxia-oai) - [#49041](https://github.com/openai/codex/issues/49041) Copy selections within inline code as plain text [@fcoury-oai](https://github.com/fcoury-oai) - [#49043](https://github.com/openai/codex/issues/49043) Update Pro plan display names in the TUI [@etraut-openai](https://github.com/etraut-openai) - [#49057](https://github.com/openai/codex/issues/49057) Add handoff-aware root context for Guardian reviews [@jif-oai](https://github.com/jif-oai) - [#49058](https://github.com/openai/codex/issues/49058) Fix Windows sandbox ACL repair for long runtime paths [@darius-oai](https://github.com/darius-oai) - [#49060](https://github.com/openai/codex/issues/49060) Update Guardian messaging snapshots for native agent messages [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49065](https://github.com/openai/codex/issues/49065) Update Guardian handoff snapshot for separate agent messages [@cassirer-openai](https://github.com/cassirer-openai) - [#49067](https://github.com/openai/codex/issues/49067) Keep configuration values out of Windows sandbox policy events [@zm-oai](https://github.com/zm-oai) - [#49069](https://github.com/openai/codex/issues/49069) Reclaim unused SQLite log database pages in the background [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49073](https://github.com/openai/codex/issues/49073) Surface realtime voice catalog failures in the TUI [@etraut-openai](https://github.com/etraut-openai) - [#49074](https://github.com/openai/codex/issues/49074) Propagate Cargo package versions to Bazel Rust targets [@tamird](https://github.com/tamird) - [#49075](https://github.com/openai/codex/issues/49075) Preserve pending environments when spawning subagents [@sayan-oai](https://github.com/sayan-oai) - [#49076](https://github.com/openai/codex/issues/49076) Avoid collecting unused Git metadata in skill analytics [@tamird](https://github.com/tamird) - [#49079](https://github.com/openai/codex/issues/49079) Update and centralize TUI subscription labels [@etraut-openai](https://github.com/etraut-openai) - [#49082](https://github.com/openai/codex/issues/49082) Skip remote Git discovery for Guardian diff paths [@jif-oai](https://github.com/jif-oai) - [#49084](https://github.com/openai/codex/issues/49084) Track app-server running turns incrementally [@tamird](https://github.com/tamird) - [#49089](https://github.com/openai/codex/issues/49089) Render follow-up directive labels in the TUI and copied responses [@etraut-openai](https://github.com/etraut-openai) - [#49093](https://github.com/openai/codex/issues/49093) Simplify startup promotions to platform-specific desktop app tips [@etraut-openai](https://github.com/etraut-openai) - [#49096](https://github.com/openai/codex/issues/49096) Update `h2` from 0.4.16 to 0.4.19 in Cargo and Bazel lockfiles [@cassirer-openai](https://github.com/cassirer-openai) - [#49097](https://github.com/openai/codex/issues/49097) Notify lifecycle extensions of compaction usage limits [@xli-oai](https://github.com/xli-oai) - [#49098](https://github.com/openai/codex/issues/49098) Resolve Windows sandbox PowerShell fallbacks on the exec server [@zm-oai](https://github.com/zm-oai) - [#49099](https://github.com/openai/codex/issues/49099) Cache parsed plugin manifests across plugin workflows [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49100](https://github.com/openai/codex/issues/49100) Reuse the HTTP connection pool for remote plugin requests [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#49102](https://github.com/openai/codex/issues/49102) Preserve SQLite vacuum modes and surface pool initialization errors [@bc-openai](https://github.com/bc-openai) - [#49103](https://github.com/openai/codex/issues/49103) Balance Windows Bazel test shards using duration estimates [@jgershen-oai](https://github.com/jgershen-oai) - [#49105](https://github.com/openai/codex/issues/49105) Resume unsent TUI input after reconnecting [@etraut-openai](https://github.com/etraut-openai) - [#49106](https://github.com/openai/codex/issues/49106) Add history pagination to the agent command center [@bc-openai](https://github.com/bc-openai) - [#49112](https://github.com/openai/codex/issues/49112) Add X11 primary selection and middle-click paste support [@fcoury-oai](https://github.com/fcoury-oai) - [#49114](https://github.com/openai/codex/issues/49114) Point remote compaction tests at the mock ChatGPT server [@OLI-OAI](https://github.com/OLI-OAI) - [#49117](https://github.com/openai/codex/issues/49117) Attribute analytics requests to each thread's product SKU [@papayo-oai](https://github.com/papayo-oai) - [#49118](https://github.com/openai/codex/issues/49118) Correct provider authentication storage documentation [@celia-oai](https://github.com/celia-oai) - [#49119](https://github.com/openai/codex/issues/49119) Add recovery guidance to content-filter retries [@won-openai](https://github.com/won-openai) - [#49127](https://github.com/openai/codex/issues/49127) Deduplicate cloud and executor skill listings before budgeting [@TAFOYA-OAI](https://github.com/TAFOYA-OAI) - [#49130](https://github.com/openai/codex/issues/49130) Move content-filter guidance into the shared Responses retry handler [@won-openai](https://github.com/won-openai) - [#49135](https://github.com/openai/codex/issues/49135) Treat explicit provider model catalogs as authoritative [@andrewgu-oai](https://github.com/andrewgu-oai) - [#49136](https://github.com/openai/codex/issues/49136) Remove the plus separator after Option symbols in TUI key hints [@bc-openai](https://github.com/bc-openai) - [#49138](https://github.com/openai/codex/issues/49138) Expose original error details to turn lifecycle contributors [@bryanashley](https://github.com/bryanashley) - [#49144](https://github.com/openai/codex/issues/49144) Preserve server reasoning summary and verbosity settings in the TUI [@etraut-openai](https://github.com/etraut-openai) - [#49145](https://github.com/openai/codex/issues/49145) Hide reasoning summary settings in `/status` for server connections [@etraut-openai](https://github.com/etraut-openai) - [#49147](https://github.com/openai/codex/issues/49147) Simplify cloud task base URL normalization [@akira-oai](https://github.com/akira-oai) - [#49153](https://github.com/openai/codex/issues/49153) Omit blockquote markers when copying quoted selections in the TUI [@bc-openai](https://github.com/bc-openai) - [#49160](https://github.com/openai/codex/issues/49160) Support projectless TUI sessions with workspace defaults [@etraut-openai](https://github.com/etraut-openai) - [#49161](https://github.com/openai/codex/issues/49161) Honor app-server provider defaults in the TUI [@etraut-openai](https://github.com/etraut-openai) - [#49164](https://github.com/openai/codex/issues/49164) Suppress Windows console windows for background subprocesses [@etraut-openai](https://github.com/etraut-openai) - [#49171](https://github.com/openai/codex/issues/49171) Fix model provider lookup for TUI history [@etraut-openai](https://github.com/etraut-openai) - [#49386](https://github.com/openai/codex/issues/49386) \[0.160] Backport remaining Windows console fix to frozen alpha.6 [@andrewgu-oai](https://github.com/andrewgu-oai) - [#49763](https://github.com/openai/codex/issues/49763) \[0.160] Backport maintenance-line catalog and security reminder updates [@andrewgu-oai](https://github.com/andrewgu-oai) ### [`v0.159.3`](https://github.com/openai/codex/releases/tag/rust-v0.159.3): 0.159.3 [Compare Source](https://github.com/openai/codex/compare/rust-v0.159.2...rust-v0.159.3) #### New Features - Eligible local sessions signed in with ChatGPT can now show optional reminders to complete account security setup. ([#49744](https://github.com/openai/codex/issues/49744)) #### Changelog Full Changelog: <https://github.com/openai/codex/compare/rust-v0.159.2...rust-v0.159.3> - [#49744](https://github.com/openai/codex/issues/49744) \[0.159] Backport account security setup reminders for 0.159.3 [@andrewgu-oai](https://github.com/andrewgu-oai) ### [`v0.159.2`](https://github.com/openai/codex/releases/tag/rust-v0.159.2): 0.159.2 [Compare Source](https://github.com/openai/codex/compare/rust-v0.159.1...rust-v0.159.2) #### Bug Fixes - Suppressed console windows flashing on Windows when Codex launches background processes and sandboxed commands. ([#49385](https://github.com/openai/codex/issues/49385)) #### Changelog Full Changelog: <https://github.com/openai/codex/compare/rust-v0.159.1...rust-v0.159.2> - [#49385](https://github.com/openai/codex/issues/49385) \[0.159] Backport Windows console suppression for 0.159.2 [@andrewgu-oai](https://github.com/andrewgu-oai) ### [`v0.159.1`](https://github.com/openai/codex/releases/tag/rust-v0.159.1): 0.159.1 [Compare Source](https://github.com/openai/codex/compare/rust-v0.159.0-alpha.12.1...rust-v0.159.1) #### New Features - Added GPT-6.1 Sol as the default model in the bundled catalog and Amazon Bedrock Mantle and Runtime catalogs. ([#49323](https://github.com/openai/codex/issues/49323), [#49342](https://github.com/openai/codex/issues/49342)) #### Changelog Full Changelog: <https://github.com/openai/codex/compare/rust-v0.159.0...rust-v0.159.1> - [#49323](https://github.com/openai/codex/issues/49323) \[0.159] Prepare 0.159.1 release backports [@andrewgu-oai](https://github.com/andrewgu-oai) - [#49342](https://github.com/openai/codex/issues/49342) \[0.159] Backport GPT-6.1 Sol Bedrock catalogs [@celia-oai](https://github.com/celia-oai) ### [`v0.159.0`](https://github.com/openai/codex/releases/tag/rust-v0.159.0): 0.159.0 [Compare Source](https://github.com/openai/codex/compare/rust-v0.158.0-alpha.15.4...rust-v0.159.0-alpha.12.1) #### New Features - Opt-in `instant_interrupt` lets new input steer Codex during model responses or long-running code-mode calls. ([#48135](https://github.com/openai/codex/issues/48135), [#48141](https://github.com/openai/codex/issues/48141)) - New sessions get a compact welcome screen and consistent headers, with occasional tips during and after turns. ([#48513](https://github.com/openai/codex/issues/48513), [#48562](https://github.com/openai/codex/issues/48562), [#48352](https://github.com/openai/codex/issues/48352)) - The warnings viewer dismisses reviewed warnings when closed; press `k` to keep one for later. ([#48205](https://github.com/openai/codex/issues/48205), [#48206](https://github.com/openai/codex/issues/48206)) - You can scroll the transcript while deciding whether to implement a plan. ([#48805](https://github.com/openai/codex/issues/48805)) - Native Mermaid rendering supports more flowchart edges, labels, and node groups. ([#48814](https://github.com/openai/codex/issues/48814), [#48895](https://github.com/openai/codex/issues/48895)) - App-server clients can paginate thread history from a specific item. ([#48151](https://github.com/openai/codex/issues/48151)) #### Bug Fixes - Windows launches avoid stray console windows for MCP servers, code-mode hosts, and piped commands; restrictive launchers can fall back to embedded mode. ([#48138](https://github.com/openai/codex/issues/48138), [#48238](https://github.com/openai/codex/issues/48238), [#48483](https://github.com/openai/codex/issues/48483), [#48491](https://github.com/openai/codex/issues/48491)) - Copying transcript selections preserves Markdown tables, formatting, and significant whitespace. More terminals now copy automatically on selection. ([#48548](https://github.com/openai/codex/issues/48548), [#48549](https://github.com/openai/codex/issues/48549), [#48469](https://github.com/openai/codex/issues/48469)) - Blank sessions retain drafts when switching tasks, and threads can be archived and listed before their first turn. ([#48628](https://github.com/openai/codex/issues/48628), [#48828](https://github.com/openai/codex/issues/48828), [#48199](https://github.com/openai/codex/issues/48199)) - Local ChatGPT sign-in opens the browser reliably; onboarding also provides a shortcut to copy the login link. ([#48502](https://github.com/openai/codex/issues/48502), [#48544](https://github.com/openai/codex/issues/48544)) - Approved commands retain explicit filesystem denials, and `.aws` directories are protected by default under writable roots. ([#48155](https://github.com/openai/codex/issues/48155), [#48176](https://github.com/openai/codex/issues/48176)) - Fixed macOS TLS access in network-enabled sandboxes and remote environments that require proxy access. ([#48565](https://github.com/openai/codex/issues/48565), [#48198](https://github.com/openai/codex/issues/48198)) #### Chores - Removed automatic follow-up prompt suggestions and the `tui.prompt_suggestions` setting. ([#48621](https://github.com/openai/codex/issues/48621)) - Removed the bundled `plugin-creator` skill. ([#48604](https://github.com/openai/codex/issues/48604)) #### Changelog Full Changelog: <https://github.com/openai/codex/compare/rust-v0.158.0...rust-v0.159.0> - [#48135](https://github.com/openai/codex/issues/48135) Add opt-in code-mode yielding on new user input [@pakrym-oai](https://github.com/pakrym-oai) - [#48138](https://github.com/openai/codex/issues/48138) Suppress console windows when spawning the code-mode host on Windows [@zm-oai](https://github.com/zm-oai) - [#48141](https://github.com/openai/codex/issues/48141) Preempt model responses when new user input arrives [@pakrym-oai](https://github.com/pakrym-oai) - [#48143](https://github.com/openai/codex/issues/48143) Preserve executor MCP credential boundaries across reconnects [@rreichel3-oai](https://github.com/rreichel3-oai) - [#48151](https://github.com/openai/codex/issues/48151) Add item anchors to `thread/items/list` pagination [@btraut-openai](https://github.com/btraut-openai) - [#48155](https://github.com/openai/codex/issues/48155) Preserve filesystem denials when preparing approved commands [@viyatb-oai](https://github.com/viyatb-oai) - [#48157](https://github.com/openai/codex/issues/48157) Allow Windows daemon launches with residual job membership [@etraut-openai](https://github.com/etraut-openai) - [#48158](https://github.com/openai/codex/issues/48158) Fix Guardian retained context spacing and empty assistant handling [@olliem-oai](https://github.com/olliem-oai) - [#48168](https://github.com/openai/codex/issues/48168) Generate unique exec-server process IDs for every request [@sdcoffey](https://github.com/sdcoffey) - [#48174](https://github.com/openai/codex/issues/48174) Preserve usage limit windows in turn and compaction analytics [@rhan-oai](https://github.com/rhan-oai) - [#48176](https://github.com/openai/codex/issues/48176) Protect `.aws` directories under sandbox writable roots [@jackz100](https://github.com/jackz100) - [#48187](https://github.com/openai/codex/issues/48187) Fix zsh alias quoting in sourced shell snapshots [@jif-oai](https://github.com/jif-oai) - [#48190](https://github.com/openai/codex/issues/48190) Bound agent message board SSE frames before parsing [@jif-oai](https://github.com/jif-oai) - [#48197](https://github.com/openai/codex/issues/48197) Optimize `blake3` in Bazel fastbuilds [@jif-oai](https://github.com/jif-oai) - [#48198](https://github.com/openai/codex/issues/48198) Honor execution environment proxy requirements [@seanh-oai](https://github.com/seanh-oai) - [#48199](https://github.com/openai/codex/issues/48199) Keep archived threads with empty previews visible in listings [@acrognale-oai](https://github.com/acrognale-oai) - [#48200](https://github.com/openai/codex/issues/48200) Extract Responses header conversion into a shared module [@anp-oai](https://github.com/anp-oai) - [#48205](https://github.com/openai/codex/issues/48205) Dismiss viewed TUI warnings when closing the viewer [@fcoury-oai](https://github.com/fcoury-oai) - [#48206](https://github.com/openai/codex/issues/48206) Add a keep-and-next action to the warnings viewer [@fcoury-oai](https://github.com/fcoury-oai) - [#48207](https://github.com/openai/codex/issues/48207) Preserve queued output for observers during code-mode termination [@pakrym-oai](https://github.com/pakrym-oai) - [#48211](https://github.com/openai/codex/issues/48211) Keep Codex visible during external editor handoff [@etraut-openai](https://github.com/etraut-openai) - [#48213](https://github.com/openai/codex/issues/48213) Isolate executable fixture copies in CLI tests on Linux [@jif-oai](https://github.com/jif-oai) - [#48222](https://github.com/openai/codex/issues/48222) Preserve late result metadata for truncated code-mode calls [@ningyi-oai](https://github.com/ningyi-oai) - [#48224](https://github.com/openai/codex/issues/48224) Preserve model and access program pairs during compaction [@jamy-OAI](https://github.com/jamy-OAI) - [#48229](https://github.com/openai/codex/issues/48229) Extract Responses failure parsing into a dedicated module [@anp-oai](https://github.com/anp-oai) - [#48238](https://github.com/openai/codex/issues/48238) Suppress console windows for local Windows MCP servers [@malsamiri-oai](https://github.com/malsamiri-oai) - [#48272](https://github.com/openai/codex/issues/48272) Prevent Windows daemon launches from retaining launcher stdio [@zm-oai](https://github.com/zm-oai) - [#48318](https://github.com/openai/codex/issues/48318) Keep TUI reconnect attempts running until the shared deadline [@etraut-openai](https://github.com/etraut-openai) - [#48344](https://github.com/openai/codex/issues/48344) Preserve tool metadata for OpenAI provider endpoint overrides [@peilin-openai](https://github.com/peilin-openai) - [#48350](https://github.com/openai/codex/issues/48350) Display reconnect commands on a separate line [@etraut-openai](https://github.com/etraut-openai) - [#48352](https://github.com/openai/codex/issues/48352) Show turn tips while working and after completion in the TUI [@fcoury-oai](https://github.com/fcoury-oai) - [#48353](https://github.com/openai/codex/issues/48353) Stabilize skill catalogs across executor availability changes [@vkg-oai](https://github.com/vkg-oai) - [#48469](https://github.com/openai/codex/issues/48469) Default to copying transcript selections in more terminals [@fcoury-oai](https://github.com/fcoury-oai) - [#48483](https://github.com/openai/codex/issues/48483) Prevent console windows for piped Windows child processes [@fcoury-oai](https://github.com/fcoury-oai) - [#48489](https://github.com/openai/codex/issues/48489) Fix Mermaid shape, relationship, and state description parsing [@etraut-openai](https://github.com/etraut-openai) - [#48491](https://github.com/openai/codex/issues/48491) Fall back to embedded mode under restrictive Windows launchers [@fcoury-oai](https://github.com/fcoury-oai) - [#48502](https://github.com/openai/codex/issues/48502) Fix ChatGPT browser sign-in for local app servers [@etraut-openai](https://github.com/etraut-openai) - [#48508](https://github.com/openai/codex/issues/48508) Preserve WebSocket continuations when steering a turn [@pakrym-oai](https://github.com/pakrym-oai) - [#48513](https://github.com/openai/codex/issues/48513) Refresh the TUI welcome screen for new sessions [@fcoury-oai](https://github.com/fcoury-oai) - [#48531](https://github.com/openai/codex/issues/48531) Add context to Windows sandbox runtime registration errors [@zm-oai](https://github.com/zm-oai) - [#48544](https://github.com/openai/codex/issues/48544) Make onboarding login links easier to copy [@etraut-openai](https://github.com/etraut-openai) - [#48547](https://github.com/openai/codex/issues/48547) Fade blossom replays back to the idle state [@fcoury-oai](https://github.com/fcoury-oai) - [#48548](https://github.com/openai/codex/issues/48548) Preserve table cell source metadata through TUI rendering [@fcoury-oai](https://github.com/fcoury-oai) - [#48549](https://github.com/openai/codex/issues/48549) Preserve Markdown tables and whitespace when copying TUI responses [@fcoury-oai](https://github.com/fcoury-oai) - [#48551](https://github.com/openai/codex/issues/48551) Fix TUI math rendering for zero and big wedge expressions [@etraut-openai](https://github.com/etraut-openai) - [#48560](https://github.com/openai/codex/issues/48560) Keep working tips stable during transcript interaction [@fcoury-oai](https://github.com/fcoury-oai) - [#48562](https://github.com/openai/codex/issues/48562) Use a consistent borderless session header in the TUI [@fcoury-oai](https://github.com/fcoury-oai) - [#48565](https://github.com/openai/codex/issues/48565) Allow macOS TLS trust evaluation in network-enabled Seatbelt profiles [@winston-openai](https://github.com/winston-openai) - [#48568](https://github.com/openai/codex/issues/48568) Allow exec-server to proxy permitted private IPs upstream [@open-matt](https://github.com/open-matt) - [#48574](https://github.com/openai/codex/issues/48574) Preserve deferred tool namespace names before descriptions [@adaley-openai](https://github.com/adaley-openai) - [#48575](https://github.com/openai/codex/issues/48575) Allow provisioned executors more time to come online [@richardopenai](https://github.com/richardopenai) - [#48604](https://github.com/openai/codex/issues/48604) Remove the bundled `plugin-creator` skill [@martinauyeung-oai](https://github.com/martinauyeung-oai) - [#48611](https://github.com/openai/codex/issues/48611) Centralize persistent mode enablement checks [@alishobeiri-oai](https://github.com/alishobeiri-oai) - [#48621](https://github.com/openai/codex/issues/48621) Remove follow-up prompt suggestions from the TUI [@etraut-openai](https://github.com/etraut-openai) - [#48623](https://github.com/openai/codex/issues/48623) Preserve empty Markdown list markers in the TUI [@etraut-openai](https://github.com/etraut-openai) - [#48626](https://github.com/openai/codex/issues/48626) Stop showing previous-session summaries when switching TUI sessions [@etraut-openai](https://github.com/etraut-openai) - [#48628](https://github.com/openai/codex/issues/48628) Preserve blank TUI sessions when switching tasks [@etraut-openai](https://github.com/etraut-openai) - [#48643](https://github.com/openai/codex/issues/48643) Set the provisioned macOS CLI bundle name to ChatGPT [@riley-oai](https://github.com/riley-oai) - [#48646](https://github.com/openai/codex/issues/48646) Fix the session-start helper call in the command center test [@etraut-openai](https://github.com/etraut-openai) - [#48686](https://github.com/openai/codex/issues/48686) Remove WebSocket headers and tool payloads from info logs [@chess-oai](https://github.com/chess-oai) - [#48724](https://github.com/openai/codex/issues/48724) Prevent Linux ETXTBSY races in MCP stdio tests [@jif-oai](https://github.com/jif-oai) - [#48725](https://github.com/openai/codex/issues/48725) Retain confirmed Code Mode messages for Guardian reviews [@ankushg](https://github.com/ankushg) - [#48727](https://github.com/openai/codex/issues/48727) Centralize executable fixture creation to avoid Linux ETXTBSY races [@jif-oai](https://github.com/jif-oai) - [#48754](https://github.com/openai/codex/issues/48754) Render `/status` without borders and wrap long values [@fcoury-oai](https://github.com/fcoury-oai) - [#48757](https://github.com/openai/codex/issues/48757) Match TUI status shimmer timing to desktop headers [@fcoury-oai](https://github.com/fcoury-oai) - [#48761](https://github.com/openai/codex/issues/48761) Show hidden output line counts in compact terminal activity [@fcoury-oai](https://github.com/fcoury-oai) - [#48764](https://github.com/openai/codex/issues/48764) Preserve MCP app resource URIs without defaulting display mode [@victor-openai](https://github.com/victor-openai) - [#48772](https://github.com/openai/codex/issues/48772) Fix Unix socket connections through long symlink paths [@etraut-openai](https://github.com/etraut-openai) - [#48775](https://github.com/openai/codex/issues/48775) Match pinned transcript headers to the original prompt style [@etraut-openai](https://github.com/etraut-openai) - [#48776](https://github.com/openai/codex/issues/48776) Remove the `current` badge from TUI task rows [@etraut-openai](https://github.com/etraut-openai) - [#48779](https://github.com/openai/codex/issues/48779) Preserve independent Guardian history across parent compaction [@felixxia-oai](https://github.com/felixxia-oai) - [#48783](https://github.com/openai/codex/issues/48783) Add single-server MCP status discovery with thread connection reuse [@victor-openai](https://github.com/victor-openai) - [#48796](https://github.com/openai/codex/issues/48796) Add opt-in structured errors for Guardian circuit-breaker interruptions [@won-openai](https://github.com/won-openai) - [#48799](https://github.com/openai/codex/issues/48799) Fix SGR mouse reporting for Windows terminal capture [@etraut-openai](https://github.com/etraut-openai) - [#48800](https://github.com/openai/codex/issues/48800) Use the terminal palette for ordered Markdown list markers [@etraut-openai](https://github.com/etraut-openai) - [#48805](https://github.com/openai/codex/issues/48805) Allow transcript wheel scrolling while a modal is open [@fcoury-oai](https://github.com/fcoury-oai) - [#48807](https://github.com/openai/codex/issues/48807) Show short turn durations in TUI completion footers [@fcoury-oai](https://github.com/fcoury-oai) - [#48812](https://github.com/openai/codex/issues/48812) Add history-aware prewarming for idle threads [@vkg-oai](https://github.com/vkg-oai) - [#48814](https://github.com/openai/codex/issues/48814) Preserve punctuation and semicolons in Mermaid labels [@etraut-openai](https://github.com/etraut-openai) - [#48819](https://github.com/openai/codex/issues/48819) Use explicit histogram buckets for tool and skill context metrics [@mzeng-openai](https://github.com/mzeng-openai) - [#48824](https://github.com/openai/codex/issues/48824) Keep voice RTP timestamps aligned to 20 ms packets [@bc-openai](https://github.com/bc-openai) - [#48827](https://github.com/openai/codex/issues/48827) Show a hand pointer over transcript links in Ghostty and Kitty [@bc-openai](https://github.com/bc-openai) - [#48828](https://github.com/openai/codex/issues/48828) Allow archiving threads before their first turn [@bc-openai](https://github.com/bc-openai) - [#48829](https://github.com/openai/codex/issues/48829) Wait briefly for the Windows sandbox provisioning service to start [@zm-oai](https://github.com/zm-oai) - [#48830](https://github.com/openai/codex/issues/48830) Show a short, neutral TUI interruption notice [@fcoury-oai](https://github.com/fcoury-oai) - [#48895](https://github.com/openai/codex/issues/48895) Expand native Mermaid flowchart syntax support [@etraut-openai](https://github.com/etraut-openai) - [#48973](https://github.com/openai/codex/issues/48973) Isolate realtime auth fallback test from startup prewarm [@jif-oai](https://github.com/jif-oai) - [#48982](https://github.com/openai/codex/issues/48982) Prevent message-board notifications from reopening final answers [@eknight-oai](https://github.com/eknight-oai) ### [`v0.158.0`](https://github.com/openai/codex/releases/tag/rust-v0.158.0): 0.158.0 [Compare Source](https://github.com/openai/codex/compare/rust-v0.157.1...rust-v0.158.0-alpha.15.4) #### New Features - Configure copy-on-select and right-click paste in the fullscreen TUI. Copied transcript selections now preserve Markdown formatting. ([#47639](https://github.com/openai/codex/issues/47639), [#47896](https://github.com/openai/codex/issues/47896), [#48118](https://github.com/openai/codex/issues/48118)) - Connect to MCP servers that require pre-registered OAuth client secrets, including through `codex mcp add --oauth-client-secret`. ([#47891](https://github.com/openai/codex/issues/47891)) - Secure direct exec-server WebSocket connections with bearer tokens, including connections configured through app-server. ([#47601](https://github.com/openai/codex/issues/47601), [#47648](https://github.com/openai/codex/issues/47648)) - Image generation and editing can explicitly request transparent backgrounds, and edits now accept file-backed conversation images. ([#47484](https://github.com/openai/codex/issues/47484), [#47956](https://github.com/openai/codex/issues/47956)) - Terminal input approval is enabled by default for commands running with elevated permissions; runtime-only grants no longer cause unnecessary reviews. ([#47799](https://github.com/openai/codex/issues/47799), [#48073](https://github.com/openai/codex/issues/48073)) #### Bug Fixes - Fixed Windows sandbox failures involving ordinary Windows 10 paths, rejected stored credentials, and large permission policies. ([#47672](https://github.com/openai/codex/issues/47672), [#47695](https://github.com/openai/codex/issues/47695), [#47919](https://github.com/openai/codex/issues/47919)) - Fixed Linux sandbox startup with nested writable roots and preserved Git metadata protections across writable roots on Linux and macOS. ([#47623](https://github.com/openai/codex/issues/47623), [#47974](https://github.com/openai/codex/issues/47974)) - macOS patch operations now recognize system path aliases covered by existing permissions, avoiding unnecessary approval prompts. ([#47879](https://github.com/openai/codex/issues/47879)) - Approval reviews now retry when new user input arrives, so a status question does not automatically abort a pending action. ([#47819](https://github.com/openai/codex/issues/47819)) - Mermaid flowcharts now render quoted labels and ampersands; unsupported diagrams explain why they fall back to source. ([#47572](https://github.com/openai/codex/issues/47572), [#47678](https://github.com/openai/codex/issues/47678)) - Command completion events now include early output and report process-launch failures to clients. ([#47529](https://github.com/openai/codex/issues/47529), [#47665](https://github.com/openai/codex/issues/47665)) #### Changelog Full Changelog: <https://github.com/openai/codex/compare/rust-v0.157.0...rust-v0.158.0> - [#47441](https://github.com/openai/codex/issues/47441) Use secondary text styling for the transcript footer shortcut hint [@etraut-openai](https://github.com/etraut-openai) - [#47447](https://github.com/openai/codex/issues/47447) Extract WebSocket authentication into `codex-websocket-auth` [@euroelessar](https://github.com/euroelessar) - [#47458](https://github.com/openai/codex/issues/47458) Parallelize instruction refresh and tool preparation [@hlevy-openai](https://github.com/hlevy-openai) - [#47484](https://github.com/openai/codex/issues/47484) Add explicit background control to image generation [@alicec-oai](https://github.com/alicec-oai) - [#47520](https://github.com/openai/codex/issues/47520) Route session agent operations through `AgentControl` [@jif-oai](https://github.com/jif-oai) - [#47529](https://github.com/openai/codex/issues/47529) Emit command lifecycle events for unified exec launch failures [@steipete-oai](https://github.com/steipete-oai) - [#47536](https://github.com/openai/codex/issues/47536) Route agent lookups and V2 context through `AgentControl` [@jif-oai](https://github.com/jif-oai) - [#47539](https://github.com/openai/codex/issues/47539) Test interrupted one-shot command launch failure persistence [@jif-oai](https://github.com/jif-oai) - [#47540](https://github.com/openai/codex/issues/47540) Add an option to disable multi-agent v2 direct messaging [@jif-oai](https://github.com/jif-oai) - [#47565](https://github.com/openai/codex/issues/47565) Classify rollout read failures by reason and progress [@jif-oai](https://github.com/jif-oai) - [#47568](https://github.com/openai/codex/issues/47568) Record sandbox backends in command execution analytics [@iceweasel-oai](https://github.com/iceweasel-oai) - [#47571](https://github.com/openai/codex/issues/47571) Wait for idle before injecting remote compaction test history [@felixxia-oai](https://github.com/felixxia-oai) - [#47572](https://github.com/openai/codex/issues/47572) Explain Mermaid rendering fallbacks in the TUI [@etraut-openai](https://github.com/etraut-openai) - [#47582](https://github.com/openai/codex/issues/47582) Retain assistant context for Guardian authorization reviews [@felixxia-oai](https://github.com/felixxia-oai) - [#47584](https://github.com/openai/codex/issues/47584) Preserve streamed assistant message order in retained context [@felixxia-oai](https://github.com/felixxia-oai) - [#47585](https://github.com/openai/codex/issues/47585) Preserve delivered assistant messages in Guardian retained context [@felixxia-oai](https://github.com/felixxia-oai) - [#47589](https://github.com/openai/codex/issues/47589) Keep unfinished link destinations out of rich streaming previews [@etraut-openai](https://github.com/etraut-openai) - [#47590](https://github.com/openai/codex/issues/47590) Serialize numeric custom reasoning effort as JSON numbers [@dylan-hurd-oai](https://github.com/dylan-hurd-oai) - [#47591](https://github.com/openai/codex/issues/47591) Stream daemon executable hashing off the async runtime [@etraut-openai](https://github.com/etraut-openai) - [#47596](https://github.com/openai/codex/issues/47596) Refresh realtime context for each model request [@reia-oai](https://github.com/reia-oai) - [#47597](https://github.com/openai/codex/issues/47597) Guard prerelease channel and canary updates against older versions [@imac-oai](https://github.com/imac-oai) - [#47601](https://github.com/openai/codex/issues/47601) Add opt-in WebSocket authentication to exec-server [@euroelessar](https://github.com/euroelessar) - [#47603](https://github.com/openai/codex/issues/47603) Add a reap-only drop policy for child processes [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#47604](https://github.com/openai/codex/issues/47604) Extend child commands with session and descriptor controls [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#47605](https://github.com/openai/codex/issues/47605) Route pipe processes through the shared child launcher [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#47610](https://github.com/openai/codex/issues/47610) Use native POSIX spawning for command hooks [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#47611](https://github.com/openai/codex/issues/47611) Use the shared process launcher for Unix shell snapshots [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#47612](https://github.com/openai/codex/issues/47612) Launch Linux pipe processes through a fresh setup helper [@freeqaz-openai](https://github.com/freeqaz-openai) - [#47613](https://github.com/openai/codex/issues/47613) Expand Linux spawn-helper lifecycle test coverage [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#47617](https://github.com/openai/codex/issues/47617) Route Linux PTY launches through the process setup helper [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#47618](https://github.com/openai/codex/issues/47618) Prefer Shift-arrow hints for queued messages and questions [@imac-oai](https://github.com/imac-oai) - [#47619](https://github.com/openai/codex/issues/47619) Add bounded buffering for global operation metrics [@celia-oai](https://github.com/celia-oai) - [#47620](https://github.com/openai/codex/issues/47620) Add portable project trust lookup APIs [@seanh-oai](https://github.com/seanh-oai) - [#47623](https://github.com/openai/codex/issues/47623) Fix read-only metadata mount ordering for nested writable roots [@jif-oai](https://github.com/jif-oai) - [#47624](https://github.com/openai/codex/issues/47624) Recognize `user_message` tools in Guardian authorization context [@ankushg](https://github.com/ankushg) - [#47625](https://github.com/openai/codex/issues/47625) Allow history and notes without experimental context capability [@pmccrary-oai](https://github.com/pmccrary-oai) - [#47629](https://github.com/openai/codex/issues/47629) Route V2 child loading through `AgentControl` [@jif-oai](https://github.com/jif-oai) - [#47630](https://github.com/openai/codex/issues/47630) Bind Guardian reviews to the action's target environment [@jif-oai](https://github.com/jif-oai) - [#47633](https://github.com/openai/codex/issues/47633) Route message board agent resolution through the selected controller [@jif-oai](https://github.com/jif-oai) - [#47635](https://github.com/openai/codex/issues/47635) Overlap startup WebSocket preconnect with tool discovery [@bromano-oai](https://github.com/bromano-oai) - [#47638](https://github.com/openai/codex/issues/47638) Classify retryable exec-server preparation errors by type [@mtsui-oai](https://github.com/mtsui-oai) - [#47639](https://github.com/openai/codex/issues/47639) Add configurable copy-on-select for transcript selections [@fcoury-oai](https://github.com/fcoury-oai) - [#47641](https://github.com/openai/codex/issues/47641) Honor Retry-After and preserve server retry deadlines [@anp-oai](https://github.com/anp-oai) - [#47642](https://github.com/openai/codex/issues/47642) Add model-specific prefixes to indirect tool descriptions [@rhan-oai](https://github.com/rhan-oai) - [#47647](https://github.com/openai/codex/issues/47647) Apply Guardian computer-use review to the Browser connector [@johnl-oai](https://github.com/johnl-oai) - [#47648](https://github.com/openai/codex/issues/47648) Support bearer tokens for app-server executor connections [@euroelessar](https://github.com/euroelessar) - [#47649](https://github.com/openai/codex/issues/47649) Add opt-in OTLP logging for final agent responses [@xli-oai](https://github.com/xli-oai) - [#47653](https://github.com/openai/codex/issues/47653) Attach inherited rollout history to diagnostic reports [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#47654](https://github.com/openai/codex/issues/47654) Make Linux descriptor cleanup fork-safe [@yuzhu-oai](https://github.com/yuzhu-oai) - [#47655](https://github.com/openai/codex/issues/47655) Bump the exec-server stable compatibility test to Codex 0.156.1 [@imac-oai](https://github.com/imac-oai) - [#47657](https://github.com/openai/codex/issues/47657) Restrict the default Bedrock GovCloud model catalog [@jackz100](https://github.com/jackz100) - [#47662](https://github.com/openai/codex/issues/47662) Expose tool dispatch and timing observations to extensions [@euroelessar](https://github.com/euroelessar) - [#47663](https://github.com/openai/codex/issues/47663) Preserve managed network policy in route-aware transports [@jackz100](https://github.com/jackz100) - [#47665](https://github.com/openai/codex/issues/47665) Preserve early unified exec output in completion events [@sdcoffey](https://github.com/sdcoffey) - [#47670](https://github.com/openai/codex/issues/47670) Support model-specific descriptions for agent message board tools [@eknight-oai](https://github.com/eknight-oai) - [#47672](https://github.com/openai/codex/issues/47672) Fix no-reparse directory opens on Windows 10 [@zm-oai](https://github.com/zm-oai) - [#47673](https://github.com/openai/codex/issues/47673) Clarify registered Windows sandbox setup errors [@zm-oai](https://github.com/zm-oai) - [#47677](https://github.com/openai/codex/issues/47677) Support model catalog overrides for MCP resource tool specs [@rhan-oai](https://github.com/rhan-oai) - [#47678](https://github.com/openai/codex/issues/47678) Support quoted labels and ampersands in Mermaid flowcharts [@etraut-openai](https://github.com/etraut-openai) - [#47679](https://github.com/openai/codex/issues/47679) Add extension hooks for model requests and response streams [@euroelessar](https://github.com/euroelessar) - [#47680](https://github.com/openai/codex/issues/47680) Add exec-server RPC timing and process startup tracing [@anp-oai](https://github.com/anp-oai) - [#47683](https://github.com/openai/codex/issues/47683) Add executor capability discovery V2 infrastructure [@TAFOYA-OAI](https://github.com/TAFOYA-OAI) - [#47686](https://github.com/openai/codex/issues/47686) Make thread-owned Guardian context always enabled [@felixxia-oai](https://github.com/felixxia-oai) - [#47688](https://github.com/openai/codex/issues/47688) Remove legacy Guardian authorization evidence paths [@felixxia-oai](https://github.com/felixxia-oai) - [#47689](https://github.com/openai/codex/issues/47689) Make Guardian thread context capture unconditional [@felixxia-oai](https://github.com/felixxia-oai) - [#47690](https://github.com/openai/codex/issues/47690) Remove obsolete Guardian context capture mode branches [@felixxia-oai](https://github.com/felixxia-oai) - [#47691](https://github.com/openai/codex/issues/47691) Materialize rollout persistence for pending inter-agent messages [@dermanyang-oai](https://github.com/dermanyang-oai) - [#47693](https://github.com/openai/codex/issues/47693) Configure curl retries for DotSlash installation in CI [@anp-oai](https://github.com/anp-oai) - [#47695](https://github.com/openai/codex/issues/47695) Repair rejected Windows sandbox credentials during provisioning [@zm-oai](https://github.com/zm-oai) - [#47696](https://github.com/openai/codex/issues/47696) Avoid the shutdown timeout in the lagged-event test [@jgershen-oai](https://github.com/jgershen-oai) - [#47698](https://github.com/openai/codex/issues/47698) Allow WebSocket test server shutdown while waiting for requests [@jgershen-oai](https://github.com/jgershen-oai) - [#47701](https://github.com/openai/codex/issues/47701) Allow idle threads to prewarm and repair WebSocket connections [@vkg-oai](https://github.com/vkg-oai) - [#47703](https://github.com/openai/codex/issues/47703) Preserve account network policy for ChatGPT backend requests [@jackz100](https://github.com/jackz100) - [#47704](https://github.com/openai/codex/issues/47704) Fix spawn flag typing and isolate project configuration tests [@seanh-oai](https://github.com/seanh-oai) - [#47709](https://github.com/openai/codex/issues/47709) Route resume prewarm through the cached WebSocket session [@vkg-oai](https://github.com/vkg-oai) - [#47712](https://github.com/openai/codex/issues/47712) Update unified exec output buffers atomically [@sdcoffey](https://github.com/sdcoffey) - [#47713](https://github.com/openai/codex/issues/47713) Reduce dependency coupling in shared configuration crates [@aibrahim-oai](https://github.com/aibrahim-oai) - [#47714](https://github.com/openai/codex/issues/47714) Preserve tool result metadata more selectively under size limits [@ningyi-oai](https://github.com/ningyi-oai) - [#47717](https://github.com/openai/codex/issues/47717) Avoid recursive TUI event dispatch for model picker selections [@etraut-openai](https://github.com/etraut-openai) - [#47741](https://github.com/openai/codex/issues/47741) Attribute tool telemetry to the invoking turn's product SKU [@rennie-openai](https://github.com/rennie-openai) - [#47742](https://github.com/openai/codex/issues/47742) Honor network policy in history notes and image generation extensions [@jackz100](https://github.com/jackz100) - [#47745](https://github.com/openai/codex/issues/47745) Skip startup prewarm preparation when the WebSocket is ready [@vkg-oai](https://github.com/vkg-oai) - [#47748](https://github.com/openai/codex/issues/47748) Align Cargo and Bazel Rust debug information defaults [@aibrahim-oai](https://github.com/aibrahim-oai) - [#47751](https://github.com/openai/codex/issues/47751) Reduce generic code duplication in RPC and Markdown rendering [@aibrahim-oai](https://github.com/aibrahim-oai) - [#47755](https://github.com/openai/codex/issues/47755) Centralize typed app-server response decoding [@aibrahim-oai](https://github.com/aibrahim-oai) - [#47757](https://github.com/openai/codex/issues/47757) Refactor tool telemetry product SKU matching to use an allowlist [@rennie-openai](https://github.com/rennie-openai) - [#47758](https://github.com/openai/codex/issues/47758) Preserve more tool metadata within outgoing message budgets [@ningyi-oai](https://github.com/ningyi-oai) - [#47773](https://github.com/openai/codex/issues/47773) Honor catalog schemas for asynchronous user input [@rhan-oai](https://github.com/rhan-oai) - [#47797](https://github.com/openai/codex/issues/47797) Support close-on-exec attachments without changing PTY semantics [@jif-oai](https://github.com/jif-oai) - [#47799](https://github.com/openai/codex/issues/47799) Enable terminal input approval by default [@jif-oai](https://github.com/jif-oai) - [#47808](https://github.com/openai/codex/issues/47808) Allow hosts to provide agent controllers through ThreadManager [@jif-oai](https://github.com/jif-oai) - [#47811](https://github.com/openai/codex/issues/47811) Preserve explicit user goal updates in Guardian authorization [@felixxia-oai](https://github.com/felixxia-oai) - [#47813](https://github.com/openai/codex/issues/47813) Fix sleep interruption test event handling and fixture lifetime [@felixxia-oai](https://github.com/felixxia-oai) - [#47814](https://github.com/openai/codex/issues/47814) Fix a lost wakeup in the unified exec termination test [@felixxia-oai](https://github.com/felixxia-oai) - [#47817](https://github.com/openai/codex/issues/47817) Stabilize thread resume and memory dual-write tests [@jif-oai](https://github.com/jif-oai) - [#47819](https://github.com/openai/codex/issues/47819) Retry Guardian reviews when authorization changes [@teddywyly-oai](https://github.com/teddywyly-oai) - [#47820](https://github.com/openai/codex/issues/47820) Add integration coverage for host agent controllers [@jif-oai](https://github.com/jif-oai) - [#47824](https://github.com/openai/codex/issues/47824) Allow four concurrent threads in the multi-agent resume test [@felixxia-oai](https://github.com/felixxia-oai) - [#47828](https://github.com/openai/codex/issues/47828) Wait for login completion in recommended plugin tests [@felixxia-oai](https://github.com/felixxia-oai) - [#47830](https://github.com/openai/codex/issues/47830) Bind Guardian async scores to target environment permissions [@jif-oai](https://github.com/jif-oai) - [#47832](https://github.com/openai/codex/issues/47832) Stabilize Rosetta test timing and retry delay telemetry [@jif-oai](https://github.com/jif-oai) - [#47847](https://github.com/openai/codex/issues/47847) Keep the TUI responsive during clipboard copies [@fcoury-oai](https://github.com/fcoury-oai) - [#47851](https://github.com/openai/codex/issues/47851) Preserve human overrides across repeated heartbeat instructions [@felixxia-oai](https://github.com/felixxia-oai) - [#47852](https://github.com/openai/codex/issues/47852) Avoid blocking async proxy resolution on the system proxy cache [@jif-oai](https://github.com/jif-oai) - [#47856](https://github.com/openai/codex/issues/47856) Initialize media estimates outside the global cache lock [@jif-oai](https://github.com/jif-oai) - [#47858](https://github.com/openai/codex/issues/47858) Validate loaded plugins outside the cache lock [@jif-oai](https://github.com/jif-oai) - [#47861](https://github.com/openai/codex/issues/47861) Avoid nested read locking when rendering browser sign-in [@jif-oai](https://github.com/jif-oai) - [#47867](https://github.com/openai/codex/issues/47867) Render remote permission paths using executor context [@iceweasel-oai](https://github.com/iceweasel-oai) - [#47870](https://github.com/openai/codex/issues/47870) Add opt-in OTLP logging for Guardian assessments [@jif-oai](https://github.com/jif-oai) - [#47871](https://github.com/openai/codex/issues/47871) Fix PID reservation test race and update guardian heartbeat snapshot [@jif-oai](https://github.com/jif-oai) - [#47873](https://github.com/openai/codex/issues/47873) Measure deferred tool namespace fragments before and after truncation [@mzeng-openai](https://github.com/mzeng-openai) - [#47879](https://github.com/openai/codex/issues/47879) Fix macOS system-alias matching in patch permission checks [@felixxia-oai](https://github.com/felixxia-oai) - [#47881](https://github.com/openai/codex/issues/47881) Use Tokio's clock for TUI paste timing [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#47886](https://github.com/openai/codex/issues/47886) Preserve diagnostic logs when SQLite logging fails [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#47887](https://github.com/openai/codex/issues/47887) Warn users when SQLite diagnostic log writes fail [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#47889](https://github.com/openai/codex/issues/47889) Include TUI client logs in diagnostic uploads [@etraut-openai](https://github.com/etraut-openai) - [#47891](https://github.com/openai/codex/issues/47891) Support client secrets for pre-registered MCP OAuth clients [@willwang-openai](https://github.com/willwang-openai) - [#47894](https://github.com/openai/codex/issues/47894) Clean up temporary Codex homes after TUI tests [@fcoury-oai](https://github.com/fcoury-oai) - [#47896](https://github.com/openai/codex/issues/47896) Preserve Markdown formatting when copying transcript selections [@fcoury-oai](https://github.com/fcoury-oai) - [#47898](https://github.com/openai/codex/issues/47898) Preserve local-binding inheritance in environment network policies [@seanh-oai](https://github.com/seanh-oai) - [#47899](https://github.com/openai/codex/issues/47899) Add diagnostic reasons to MCP attribution errors [@peilin-openai](https://github.com/peilin-openai) - [#47900](https://github.com/openai/codex/issues/47900) Default local threads to paginated history [@owenlin0](https://github.com/owenlin0) - [#47901](https://github.com/openai/codex/issues/47901) Add bounded credential-storage telemetry helpers [@celia-oai](https://github.com/celia-oai) - [#47902](https://github.com/openai/codex/issues/47902) Avoid repeated table clones during config merging [@imac-oai](https://github.com/imac-oai) - [#47903](https://github.com/openai/codex/issues/47903) Move config key alias normalization ahead of merging [@imac-oai](https://github.com/imac-oai) - [#47904](https://github.com/openai/codex/issues/47904) Support nested canonical paths in config key aliases [@imac-oai](https://github.com/imac-oai) - [#47908](https://github.com/openai/codex/issues/47908) Alias `tui.whimsy` to `tui.effects.starfield` [@imac-oai](https://github.com/imac-oai) - [#47912](https://github.com/openai/codex/issues/47912) Fix attestation routing during thread startup [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#47913](https://github.com/openai/codex/issues/47913) Add an opt-in flag to defer mailbox preemption [@jif-oai](https://github.com/jif-oai) - [#47915](https://github.com/openai/codex/issues/47915) Reuse verified V8 checksum manifests from the artifact cache [@aibrahim-oai](https://github.com/aibrahim-oai) - [#47918](https://github.com/openai/codex/issues/47918) Parameterize the turn-start originator header test [@aibrahim-oai](https://github.com/aibrahim-oai) - [#47919](https://github.com/openai/codex/issues/47919) Transport large Windows sandbox launch payloads through the environment [@malsamiri-oai](https://github.com/malsamiri-oai) - [#47920](https://github.com/openai/codex/issues/47920) Allow directory moves under global Seatbelt basename denies [@chess-oai](https://github.com/chess-oai) - [#47922](https://github.com/openai/codex/issues/47922) Allow full-access Windows setup to provision through registered Core [@zm-oai](https://github.com/zm-oai) - [#47924](https://github.com/openai/codex/issues/47924) Make project trust lookup paths explicit and defer root resolution [@seanh-oai](https://github.com/seanh-oai) - [#47926](https://github.com/openai/codex/issues/47926) Retry file blob uploads on HTTP 502 and 504 [@mtsui-oai](https://github.com/mtsui-oai) - [#47927](https://github.com/openai/codex/issues/47927) Use `127.0.0.1` for local login redirects [@willwang-openai](https://github.com/willwang-openai) - [#47932](https://github.com/openai/codex/issues/47932) Remove GPT-5.4 from bundled catalogs and preserve migration prompts [@andrewgu-oai](https://github.com/andrewgu-oai) - [#47934](https://github.com/openai/codex/issues/47934) Apply the unchanged-model compaction shortcut to all session sources [@hlevy-openai](https://github.com/hlevy-openai) - [#47935](https://github.com/openai/codex/issues/47935) Allow cached catalogs to satisfy MCP startup readiness [@hlevy-openai](https://github.com/hlevy-openai) - [#47936](https://github.com/openai/codex/issues/47936) Make MCP and Code Mode input schema budgets configurable [@vivi](https://github.com/vivi) - [#47937](https://github.com/openai/codex/issues/47937) Add direct replies for thread settings updates [@sayan-oai](https://github.com/sayan-oai) - [#47939](https://github.com/openai/codex/issues/47939) Separate selected plugin identities from MCP contributions [@sayan-oai](https://github.com/sayan-oai) - [#47943](https://github.com/openai/codex/issues/47943) Remove unused Windows world-writable audit code [@iceweasel-oai](https://github.com/iceweasel-oai) - [#47945](https://github.com/openai/codex/issues/47945) Parameterize the thread initialization analytics test by originator [@eddie-openai](https://github.com/eddie-openai) - [#47946](https://github.com/openai/codex/issues/47946) Add an in-memory agent message board for ephemeral sessions [@jif-oai](https://github.com/jif-oai) - [#47947](https://github.com/openai/codex/issues/47947) Expand root authorization context to 16 messages [@felixxia-oai](https://github.com/felixxia-oai) - [#47951](https://github.com/openai/codex/issues/47951) Use prebuilt V8 archives for Bazel on macOS and GNU Linux [@aibrahim-oai](https://github.com/aibrahim-oai) - [#47952](https://github.com/openai/codex/issues/47952) Prune expired in-memory message board registry entries [@jif-oai](https://github.com/jif-oai) - [#47954](https://github.com/openai/codex/issues/47954) Move fullscreen startup tips into the transcript [@etraut-openai](https://github.com/etraut-openai) - [#47956](https://github.com/openai/codex/issues/47956) Support file references in image edit requests [@kchainani-oai](https://github.com/kchainani-oai) - [#47957](https://github.com/openai/codex/issues/47957) Bound tool-call observations to the outgoing Responses message budget [@ningyi-oai](https://github.com/ningyi-oai) - [#47962](https://github.com/openai/codex/issues/47962) Request transparent huge pages for Cargo and eligible Bazel rustc jobs [@aibrahim-oai](https://github.com/aibrahim-oai) - [#47964](https://github.com/openai/codex/issues/47964) Preserve the client-agent header for Amazon Bedrock Runtime [@celia-oai](https://github.com/celia-oai) - [#47967](https://github.com/openai/codex/issues/47967) Surface Flex capacity failures as a distinct terminal error [@sdcoffey](https://github.com/sdcoffey) - [#47968](https://github.com/openai/codex/issues/47968) Handle Btrfs device mismatches when masking daemon sockets [@etraut-openai](https://github.com/etraut-openai) - [#47970](https://github.com/openai/codex/issues/47970) Expose current environment selections for a running turn [@sayan-oai](https://github.com/sayan-oai) - [#47971](https://github.com/openai/codex/issues/47971) Add Pro Max plan support and update Pro display names [@etraut-openai](https://github.com/etraut-openai) - [#47974](https://github.com/openai/codex/issues/47974) Preserve Git directory protections across writable roots [@aionescu-oai](https://github.com/aionescu-oai) - [#47975](https://github.com/openai/codex/issues/47975) Prevent stale voice answers from reappearing during speech recovery [@etraut-openai](https://github.com/etraut-openai) - [#47981](https://github.com/openai/codex/issues/47981) Prepare MCP calls directly from advertised tool identities [@hlevy-openai](https://github.com/hlevy-openai) - [#47984](https://github.com/openai/codex/issues/47984) Add multi-agent spawn latency and failure metrics [@owenlin0](https://github.com/owenlin0) - [#47988](https://github.com/openai/codex/issues/47988) Reuse MCP handlers across equivalent bindings [@hlevy-openai](https://github.com/hlevy-openai) - [#47989](https://github.com/openai/codex/issues/47989) Add startup-only PID namespace inheritance to exec-server [@open-matt](https://github.com/open-matt) - [#48004](https://github.com/openai/codex/issues/48004) Respect configured authentication in the thread manager sample [@celia-oai](https://github.com/celia-oai) - [#48015](https://github.com/openai/codex/issues/48015) Validate tool suggestion install URLs before showing the app link [@aionescu-oai](https://github.com/aionescu-oai) - [#48017](https://github.com/openai/codex/issues/48017) Test same-cell permission grants and strict review in code mode [@anp-oai](https://github.com/anp-oai) - [#48035](https://github.com/openai/codex/issues/48035) Remove plugin extension metadata from discovery and summaries [@victor-openai](https://github.com/victor-openai) - [#48060](https://github.com/openai/codex/issues/48060) Deduplicate retained instructions across Guardian reviews [@felixxia-oai](https://github.com/felixxia-oai) - [#48069](https://github.com/openai/codex/issues/48069) Handle early command yields in the Guardian network approval test [@jif-oai](https://github.com/jif-oai) - [#48072](https://github.com/openai/codex/issues/48072) Skip message-board notification previews when there are no recipients [@jif-oai](https://github.com/jif-oai) - [#48073](https://github.com/openai/codex/issues/48073) Avoid stdin approval for runtime-only permission grants [@jif-oai](https://github.com/jif-oai) - [#48077](https://github.com/openai/codex/issues/48077) Add Serde support to agent message board request types [@jif-oai](https://github.com/jif-oai) - [#48078](https://github.com/openai/codex/issues/48078) Replay exec-server shell snapshots through unnamed files [@jif-oai](https://github.com/jif-oai) - [#48098](https://github.com/openai/codex/issues/48098) Preserve recent authorization context for Guardian reviews [@felixxia-oai](https://github.com/felixxia-oai) - [#48099](https://github.com/openai/codex/issues/48099) Honor shell environment policy in legacy snapshots [@jif-oai](https://github.com/jif-oai) - [#48100](https://github.com/openai/codex/issues/48100) Add an HTTP client for remote agent message boards [@jif-oai](https://github.com/jif-oai) - [#48101](https://github.com/openai/codex/issues/48101) Show multiline command previews in `/ps` [@etraut-openai](https://github.com/etraut-openai) - [#48109](https://github.com/openai/codex/issues/48109) Deduplicate retained instructions against Guardian transcripts [@felixxia-oai](https://github.com/felixxia-oai) - [#48110](https://github.com/openai/codex/issues/48110) Deduplicate retained instructions in async Guardian context [@felixxia-oai](https://github.com/felixxia-oai) - [#48115](https://github.com/openai/codex/issues/48115) Preserve user text parts during local compaction [@felixxia-oai](https://github.com/felixxia-oai) - [#48116](https://github.com/openai/codex/issues/48116) Allow reasoning shortcuts to reach Max [@etraut-openai](https://github.com/etraut-openai) - [#48118](https://github.com/openai/codex/issues/48118) Add configurable right-click paste to the fullscreen TUI [@fcoury-oai](https://github.com/fcoury-oai) - [#48119](https://github.com/openai/codex/issues/48119) Prevent worker completion races in the guardian authorization test [@felixxia-oai](https://github.com/felixxia-oai) - [#48121](https://github.com/openai/codex/issues/48121) Keep startup drafts visible during command center session handoff [@etraut-openai](https://github.com/etraut-openai) - [#48123](https://github.com/openai/codex/issues/48123) Add early yielding for code-mode observations [@pakrym-oai](https://github.com/pakrym-oai) - [#48130](https://github.com/openai/codex/issues/48130) Use request notifications in the cloud config loader lifetime test [@felixxia-oai](https://github.com/felixxia-oai) - [#48132](https://github.com/openai/codex/issues/48132) Allow Left to open the command center from read-only conversations [@etraut-openai](https://github.com/etraut-openai) ### [`v0.157.1`](https://github.com/openai/codex/releases/tag/rust-v0.157.1): 0.157.1 [Compare Source](https://github.com/openai/codex/compare/rust-v0.157.0-alpha.11.1...rust-v0.157.1) #### Chores - Release highlights could not be determined: the supplied PR index is empty, and the GitHub tag comparison returned 404. #### Changelog Full Changelog: <https://github.com/openai/codex/compare/rust-v0.157.0...rust-v0.157.1> ### [`v0.157.0`](https://github.com/openai/codex/releases/tag/rust-v0.157.0): 0.157.0 [Compare Source](https://github.com/openai/codex/compare/rust-v0.156.1...rust-v0.157.0-alpha.11.1) #### New Features - Added GPT-6 Sol and Luna, including Amazon Bedrock support and migration prompts for older models. ([#47332](https://github.com/openai/codex/issues/47332), [#47347](https://github.com/openai/codex/issues/47347)) - Enabled fullscreen transcripts by default and added Shift-click to extend text selections. ([#47178](https://github.com/openai/codex/issues/47178), [#47414](https://github.com/openai/codex/issues/47414)) - Enabled automatic background-server startup for eligible interactive sessions, with recovery choices when server settings are incompatible. ([#47179](https://github.com/openai/codex/issues/47179), [#47318](https://github.com/openai/codex/issues/47318)) - Added an `f` shortcut to fork conversations open in another app, preserving drafts and queued prompts. ([#47185](https://github.com/openai/codex/issues/47185)) - Made `/import` available in remote sessions and local background-server sessions. ([#47317](https://github.com/openai/codex/issues/47317)) - Improved terminal rendering with Unicode bullets, checkboxes, aligned equations, and optimization notation. ([#47191](https://github.com/openai/codex/issues/47191), [#47322](https://github.com/openai/codex/issues/47322)) #### Bug Fixes - Preserved active voice conversations when switching threads. ([#47381](https://github.com/openai/codex/issues/47381)) - Recovered unsent question answers into the composer when turns end, without disrupting active history searches. ([#47422](https://github.com/openai/codex/issues/47422), [#47423](https://github.com/openai/codex/issues/47423)) - Respected tmux mouse settings and restored native scrollback for Terminal.app over SSH in automatic screen mode. ([#47399](https://github.com/openai/codex/issues/47399), [#47417](https://github.com/openai/codex/issues/47417)) - Fixed configured proxy routing for realtime connections and standalone web search, including search redirects. ([#47101](https://github.com/openai/codex/issues/47101), [#47142](https://github.com/openai/codex/issues/47142), [#47204](https://github.com/openai/codex/issues/47204)) - Added retries for transient file-upload failures and increased the upload timeout to five minutes. ([#47122](https://github.com/openai/codex/issues/47122), [#47393](https://github.com/openai/codex/issues/47393)) - Enforced network restrictions across redirects and ongoing HTTP and WebSocket traffic, including cancellation when policy changes revoke access. ([#47389](https://github.com/openai/codex/issues/47389), [#47407](https://github.com/openai/codex/issues/47407)) #### Changelog Full Changelog: <https://github.com/openai/codex/compare/rust-v0.156.0...rust-v0.157.0> - [#47063](https://github.com/openai/codex/issues/47063) Add a partial index for agent message board root posts [@jif-oai](https://github.com/jif-oai) - [#47064](https://github.com/openai/codex/issues/47064) Stop redundant message-board reads when limits reach one [@jif-oai](https://github.com/jif-oai) - [#47065](https://github.com/openai/codex/issues/47065) Deduplicate deprecation notices in the TUI transcript [@etraut-openai](https://github.com/etraut-openai) - [#47068](https://github.com/openai/codex/issues/47068) Highlight selected newlines in the transcript view [@etraut-openai](https://github.com/etraut-openai) - [#47073](https://github.com/openai/codex/issues/47073) Wait for thread idle in Guardian context budget tests [@jif-oai](https://github.com/jif-oai) - [#47074](https://github.com/openai/codex/issues/47074) Refresh host-supplied cloud skills at turn startup [@TAFOYA-OAI](https://github.com/TAFOYA-OAI) - [#47075](https://github.com/openai/codex/issues/47075) Include attributed previews in agent message board notifications [@jif-oai](https://github.com/jif-oai) - [#47077](https://github.com/openai/codex/issues/47077) Serialize environment updates and cancel removed pending attachments [@sayan-oai](https://github.com/sayan-oai) - [#47079](https://github.com/openai/codex/issues/47079) Mask daemon socket paths exposed through ancestor bind mounts [@nicksteele-oai](https://github.com/nicksteele-oai) - [#47081](https://github.com/openai/codex/issues/47081) Track cumulative MCP attribution across requests and thread history [@peilin-openai](https://github.com/peilin-openai) - [#47082](https://github.com/openai/codex/issues/47082) Show the voice toggle in the TUI shortcut overlay [@etraut-openai](https://github.com/etraut-openai) - [#47083](https://github.com/openai/codex/issues/47083) Extract per-thread enrichment into a dedicated async helper [@aibrahim-oai](https://github.com/aibrahim-oai) - [#47084](https://github.com/openai/codex/issues/47084) Avoid building a host SQLite driver for SQLx macros [@aibrahim-oai](https://github.com/aibrahim-oai) - [#47085](https://github.com/openai/codex/issues/47085) Update model catalog descriptions and GPT-5.6-Sol priority [@andrewgu-oai](https://github.com/andrewgu-oai) - [#47086](https://github.com/openai/codex/issues/47086) Format analytics credit usage with consistent decimal precision [@fcoury-oai](https://github.com/fcoury-oai) - [#47088](https://github.com/openai/codex/issues/47088) Disable unused default dependency features [@aibrahim-oai](https://github.com/aibrahim-oai) - [#47089](https://github.com/openai/codex/issues/47089) Centralize JSON-RPC response serialization through payloads [@aibrahim-oai](https://github.com/aibrahim-oai) - [#47094](https://github.com/openai/codex/issues/47094) Restrict Unix local MCP servers to stdio descriptors [@yuzhu-oai](https://github.com/yuzhu-oai) - [#47095](https://github.com/openai/codex/issues/47095) Remove the `rust-release-prepare` workflow [@andrewgu-oai](https://github.com/andrewgu-oai) - [#47096](https://github.com/openai/codex/issues/47096) Keep TUI hints immediately above the composer [@fcoury-oai](https://github.com/fcoury-oai) - [#47100](https://github.com/openai/codex/issues/47100) Preserve assistant answers in bounded TUI task responses [@etraut-openai](https://github.com/etraut-openai) - [#47101](https://github.com/openai/codex/issues/47101) Honor configured proxies for realtime WebSocket connections [@celia-oai](https://github.com/celia-oai) - [#47106](https://github.com/openai/codex/issues/47106) Preserve originating turn metadata for yielded skill calls [@eddie-openai](https://github.com/eddie-openai) - [#47108](https://github.com/openai/codex/issues/47108) Preserve required Windows runtime variables for filesystem helpers [@iceweasel-oai](https://github.com/iceweasel-oai) - [#47112](https://github.com/openai/codex/issues/47112) Lowercase the retry hint for conversations open in another app [@fcoury-oai](https://github.com/fcoury-oai) - [#47113](https://github.com/openai/codex/issues/47113) Persist thread creator identity in rollouts and SQLite [@nornagon-openai](https://github.com/nornagon-openai) - [#47114](https://github.com/openai/codex/issues/47114) Preserve and expose thread item lifecycle timestamps [@chiam-oai](https://github.com/chiam-oai) - [#47116](https://github.com/openai/codex/issues/47116) Honor the configured product SKU in remote plugin requests [@jessedu-oai](https://github.com/jessedu-oai) - [#47118](https://github.com/openai/codex/issues/47118) Support model-catalog overrides for Code Mode tool messages [@rhan-oai](https://github.com/rhan-oai) - [#47121](https://github.com/openai/codex/issues/47121) Pass thread IDs to attachment uploads [@kchainani-oai](https://github.com/kchainani-oai) - [#47122](https://github.com/openai/codex/issues/47122) Increase OpenAI file blob upload timeout from 60 seconds to 5 minutes [@wilkes-oai](https://github.com/wilkes-oai) - [#47125](https://github.com/openai/codex/issues/47125) Add extra policy configuration for Guardian reviews [@won-openai](https://github.com/won-openai) - [#47129](https://github.com/openai/codex/issues/47129) Preserve foreign working directories in extension tool environments [@anp-oai](https://github.com/anp-oai) - [#47130](https://github.com/openai/codex/issues/47130) Remove the `ultrafast` service tier from `gpt-5.6-sol` [@andrewgu-oai](https://github.com/andrewgu-oai) - [#47132](https://github.com/openai/codex/issues/47132) Support caller-provided MITM CAs in the network proxy [@viyatb-oai](https://github.com/viyatb-oai) - [#47137](https://github.com/openai/codex/issues/47137) Prevent horizontal transcript selection from triggering autoscroll [@imac-oai](https://github.com/imac-oai) - [#47142](https://github.com/openai/codex/issues/47142) Honor system proxy settings for standalone web search [@celia-oai](https://github.com/celia-oai) - [#47143](https://github.com/openai/codex/issues/47143) Extract exec-server CLI startup into a dedicated module [@anp-oai](https://github.com/anp-oai) - [#47149](https://github.com/openai/codex/issues/47149) Update code mode catalog snapshot hashes [@andrewgu-oai](https://github.com/andrewgu-oai) - [#47155](https://github.com/openai/codex/issues/47155) Ignore stale thread-close notifications after resuming a thread [@etraut-openai](https://github.com/etraut-openai) - [#47158](https://github.com/openai/codex/issues/47158) Harden gateway OAuth credential persistence and error redaction [@alexsong-oai](https://github.com/alexsong-oai) - [#47159](https://github.com/openai/codex/issues/47159) Expose HTTP origins in MCP server status [@frantic-openai](https://github.com/frantic-openai) - [#47162](https://github.com/openai/codex/issues/47162) Apply workspace routing to Guardian v2 classifier requests [@acrognale-oai](https://github.com/acrognale-oai) - [#47170](https://github.com/openai/codex/issues/47170) Add explicit gateway login control and authentication status [@alexsong-oai](https://github.com/alexsong-oai) - [#47174](https://github.com/openai/codex/issues/47174) Preserve empty cell metadata under pending tool-call pressure [@ningyi-oai](https://github.com/ningyi-oai) - [#47178](https://github.com/openai/codex/issues/47178) Enable the fullscreen transcript by default [@etraut-openai](https://github.com/etraut-openai) - [#47179](https://github.com/openai/codex/issues/47179) Enable automatic daemon startup by default [@etraut-openai](https://github.com/etraut-openai) - [#47185](https://github.com/openai/codex/issues/47185) Allow forking conversations locked by another app in the TUI [@fcoury-oai](https://github.com/fcoury-oai) - [#47191](https://github.com/openai/codex/issues/47191) Render aligned equations and optimization notation in TUI math [@etraut-openai](https://github.com/etraut-openai) - [#47199](https://github.com/openai/codex/issues/47199) Separate thread preparation from execution persistence [@dermanyang-oai](https://github.com/dermanyang-oai) - [#47204](https://github.com/openai/codex/issues/47204) Resolve proxy routes for standalone web search redirects [@celia-oai](https://github.com/celia-oai) - [#47207](https://github.com/openai/codex/issues/47207) Add explicit gateway OAuth sign-in to app-server [@alexsong-oai](https://github.com/alexsong-oai) - [#47212](https://github.com/openai/codex/issues/47212) Preserve MCP request trace context across transport workers [@bromano-oai](https://github.com/bromano-oai) - [#47235](https://github.com/openai/codex/issues/47235) Route multi-agent spawning through `SpawnRequest` [@jif-oai](https://github.com/jif-oai) - [#47236](https://github.com/openai/codex/issues/47236) Suppress agent message board notifications to the post author [@jif-oai](https://github.com/jif-oai) - [#47240](https://github.com/openai/codex/issues/47240) Prevent V2 agent eviction from racing with queued messages [@jif-oai](https://github.com/jif-oai) - [#47244](https://github.com/openai/codex/issues/47244) Centralize agent resume handling in `LocalAgentControl` [@jif-oai](https://github.com/jif-oai) - [#47248](https://github.com/openai/codex/issues/47248) Add explicit app and account targets to MCP resource reads [@victor-openai](https://github.com/victor-openai) - [#47249](https://github.com/openai/codex/issues/47249) Drop descendant channel posts from retained remote compaction v2 history [@jif-oai](https://github.com/jif-oai) - [#47252](https://github.com/openai/codex/issues/47252) Return agent snapshots from `close_agent` [@jif-oai](https://github.com/jif-oai) - [#47257](https://github.com/openai/codex/issues/47257) Preserve explicit message-board unsubscribes when posting [@jif-oai](https://github.com/jif-oai) - [#47258](https://github.com/openai/codex/issues/47258) Test spawn settings reporting after child removal [@jif-oai](https://github.com/jif-oai) - [#47259](https://github.com/openai/codex/issues/47259) Subscribe authors to message-board channels created by posting [@jif-oai](https://github.com/jif-oai) - [#47263](https://github.com/openai/codex/issues/47263) Expose hosted plugin extensions in app-server summaries [@victor-openai](https://github.com/victor-openai) - [#47267](https://github.com/openai/codex/issues/47267) Stream agent snapshots from local status subscriptions [@jif-oai](https://github.com/jif-oai) - [#47271](https://github.com/openai/codex/issues/47271) Implement `AgentControl` for `LocalAgentControl` [@jif-oai](https://github.com/jif-oai) - [#47272](https://github.com/openai/codex/issues/47272) Allow Guardian sync review across compaction hash differences [@felixxia-oai](https://github.com/felixxia-oai) - [#47275](https://github.com/openai/codex/issues/47275) Enable Guardian thread context by default [@felixxia-oai](https://github.com/felixxia-oai) - [#47281](https://github.com/openai/codex/issues/47281) Add regression coverage for message board unsubscribe persistence [@jif-oai](https://github.com/jif-oai) - [#47287](https://github.com/openai/codex/issues/47287) Update the Guardian extra-policy snapshot for retained instructions [@felixxia-oai](https://github.com/felixxia-oai) - [#47292](https://github.com/openai/codex/issues/47292) Consolidate agent operations in the `AgentControl` implementation [@jif-oai](https://github.com/jif-oai) - [#47301](https://github.com/openai/codex/issues/47301) Separate local agent runtime state from controller handles [@jif-oai](https://github.com/jif-oai) - [#47302](https://github.com/openai/codex/issues/47302) Use compact display metadata for Guardian review threads [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#47303](https://github.com/openai/codex/issues/47303) Clean up legacy Guardian thread metadata in SQLite [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#47317](https://github.com/openai/codex/issues/47317) Enable `/import` in remote and local daemon sessions [@etraut-openai](https://github.com/etraut-openai) - [#47318](https://github.com/openai/codex/issues/47318) Offer explicit recovery for incompatible background servers [@etraut-openai](https://github.com/etraut-openai) - [#47319](https://github.com/openai/codex/issues/47319) Match agent status symbols to the selected row style [@etraut-openai](https://github.com/etraut-openai) - [#47320](https://github.com/openai/codex/issues/47320) Fix Escape navigation in read-only agent sessions [@etraut-openai](https://github.com/etraut-openai) - [#47321](https://github.com/openai/codex/issues/47321) Honor the system clock preference across more TUI timestamps [@etraut-openai](https://github.com/etraut-openai) - [#47322](https://github.com/openai/codex/issues/47322) Render TUI Markdown lists with Unicode bullets and checkboxes [@etraut-openai](https://github.com/etraut-openai) - [#47323](https://github.com/openai/codex/issues/47323) Persist resume metadata in compaction checkpoints [@owenlin0](https://github.com/owenlin0) - [#47325](https://github.com/openai/codex/issues/47325) Keep report reason tags within Sentry limits [@ningyi-oai](https://github.com/ningyi-oai) - [#47326](https://github.com/openai/codex/issues/47326) Restrict MCP OAuth authorization endpoints to HTTP(S) [@viyatb-oai](https://github.com/viyatb-oai) - [#47327](https://github.com/openai/codex/issues/47327) Preserve image generation request IDs on failure [@chrisdong-oai](https://github.com/chrisdong-oai) - [#47329](https://github.com/openai/codex/issues/47329) Standardize TUI menu description wording and punctuation [@etraut-openai](https://github.com/etraut-openai) - [#47330](https://github.com/openai/codex/issues/47330) Identify failed SQLite databases in `codex doctor` output [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#47331](https://github.com/openai/codex/issues/47331) Avoid redundant spacing above the transcript composer [@fcoury-oai](https://github.com/fcoury-oai) - [#47332](https://github.com/openai/codex/issues/47332) Add GPT-6 Sol and Luna to the model catalog [@andrewgu-oai](https://github.com/andrewgu-oai) - [#47338](https://github.com/openai/codex/issues/47338) Move the activity inspection hint into keyboard shortcut help [@fcoury-oai](https://github.com/fcoury-oai) - [#47340](https://github.com/openai/codex/issues/47340) Add conditional turn interruption that preserves pending input [@pmccrary-oai](https://github.com/pmccrary-oai) - [#47342](https://github.com/openai/codex/issues/47342) Skip stored title lookups for ephemeral forks [@keyz](https://github.com/keyz) - [#47347](https://github.com/openai/codex/issues/47347) Add GPT-6 Sol and Luna to Amazon Bedrock catalogs [@celia-oai](https://github.com/celia-oai) - [#47348](https://github.com/openai/codex/issues/47348) Overlap subagent spawn persistence and clean up cancelled children [@owenlin0](https://github.com/owenlin0) - [#47349](https://github.com/openai/codex/issues/47349) Move plugin recommendations into developer context [@adaley-openai](https://github.com/adaley-openai) - [#47350](https://github.com/openai/codex/issues/47350) Reuse cloud skill catalogs across turns until invalidated [@hlevy-openai](https://github.com/hlevy-openai) - [#47353](https://github.com/openai/codex/issues/47353) Preserve `invalid_prompt` as a distinct error classification [@rennie-openai](https://github.com/rennie-openai) - [#47355](https://github.com/openai/codex/issues/47355) Reserve spacing after recaps at the transcript tail [@fcoury-oai](https://github.com/fcoury-oai) - [#47358](https://github.com/openai/codex/issues/47358) Color paths and URLs in `codex doctor` by check status [@dkovalenko-oai](https://github.com/dkovalenko-oai) - [#47360](https://github.com/openai/codex/issues/47360) Preserve user prompt URL destinations across terminal widths [@fcoury-oai](https://github.com/fcoury-oai) - [#47361](https://github.com/openai/codex/issues/47361) Restrict Windows sandbox default object access to the logon session [@viyatb-oai](https://github.com/viyatb-oai) - [#47362](https://github.com/openai/codex/issues/47362) Bound inbound exec-server requests across client transports [@viyatb-oai](https://github.com/viyatb-oai) - [#47365](https://github.com/openai/codex/issues/47365) Resume model context from the latest compaction boundary [@owenlin0](https://github.com/owenlin0) - [#47369](https://github.com/openai/codex/issues/47369) Overlap agent metadata reads when resuming a V2 root [@vkg-oai](https://github.com/vkg-oai) - [#47375](https://github.com/openai/codex/issues/47375) Add an opt-in preference for the local MXC sandbox [@iceweasel-oai](https://github.com/iceweasel-oai) - [#47377](https://github.com/openai/codex/issues/47377) Add opt-in reasoning status for realtime V3 delegations [@guinness-oai](https://github.com/guinness-oai) - [#47380](https://github.com/openai/codex/issues/47380) Route TUI voice controls through the app [@etraut-openai](https://github.com/etraut-openai) - [#47381](https://github.com/openai/codex/issues/47381) Keep voice conversations running across TUI thread navigation [@etraut-openai](https://github.com/etraut-openai) - [#47382](https://github.com/openai/codex/issues/47382) Show a voice badge in the agents overview [@etraut-openai](https://github.com/etraut-openai) - [#47384](https://github.com/openai/codex/issues/47384) Restore composer hints after clearing selection at the transcript bottom [@fcoury-oai](https://github.com/fcoury-oai) - [#47389](https://github.com/openai/codex/issues/47389) Enforce network policy throughout HTTP and WebSocket requests [@acrognale-oai](https://github.com/acrognale-oai) - [#47393](https://github.com/openai/codex/issues/47393) Retry transient OpenAI file blob upload failures [@mtsui-oai](https://github.com/mtsui-oai) - [#47397](https://github.com/openai/codex/issues/47397) Refresh bundled model metadata and instructions [@andrewgu-oai](https://github.com/andrewgu-oai) - [#47399](https://github.com/openai/codex/issues/47399) Respect tmux mouse settings in fullscreen and overlays [@fcoury-oai](https://github.com/fcoury-oai) - [#47407](https://github.com/openai/codex/issues/47407) Enforce application network policy across app-server requests [@acrognale-oai](https://github.com/acrognale-oai) - [#47408](https://github.com/openai/codex/issues/47408) Enforce application network policy for AWS auth and telemetry [@acrognale-oai](https://github.com/acrognale-oai) - [#47410](https://github.com/openai/codex/issues/47410) Honor network policy in remote control and recover remote execution [@acrognale-oai](https://github.com/acrognale-oai) - [#47411](https://github.com/openai/codex/issues/47411) Apply shared network policy throughout embedded Codex startup [@acrognale-oai](https://github.com/acrognale-oai) - [#47413](https://github.com/openai/codex/issues/47413) Cache decrypted gateway OAuth secrets per backend [@charliemarsh-oai](https://github.com/charliemarsh-oai) - [#47414](https://github.com/openai/codex/issues/47414) Support Shift-click to extend transcript selections [@etraut-openai](https://github.com/etraut-openai) - [#47417](https://github.com/openai/codex/issues/47417) Use native scrollback for Terminal.app over SSH in auto mode [@fcoury-oai](https://github.com/fcoury-oai) - [#47422](https://github.com/openai/codex/issues/47422) Recover unsent question drafts when TUI turns end [@imac-oai](https://github.com/imac-oai) - [#47423](https://github.com/openai/codex/issues/47423) Preserve history search during background draft recovery [@imac-oai](https://github.com/imac-oai) - [#47424](https://github.com/openai/codex/issues/47424) Clear pending async question notifications when turns end [@imac-oai](https://github.com/imac-oai) - [#47428](https://github.com/openai/codex/issues/47428) Apply inherited environment settings at turn boundaries [@sayan-oai](https://github.com/sayan-oai) - [#47435](https://github.com/openai/codex/issues/47435) Allow environment selection updates during an active turn [@sayan-oai](https://github.com/sayan-oai) - [#47437](https://github.com/openai/codex/issues/47437) Stabilize retry timing and WebSocket tests [@anp-oai](https://github.com/anp-oai) </details> --- ### Configuration 📅 **Schedule**: (UTC) - Branch creation - At any time (no schedule defined) - Automerge - At any time (no schedule defined) 🚦 **Automerge**: Enabled. ♻ **Rebasing**: Whenever PR is behind base branch, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about this update again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Mend Renovate CLI](https://github.com/renovatebot/renovate).

renovate added 1 commit

2026-10-03 23:01:45 +00:00

chore(deps): update dependency openai/codex to v0.160.0 aec15ed746

renovate scheduled this pull request to auto merge when all checks succeed

2026-10-03 23:01:45 +00:00

renovate force-pushed renovate-openai-codex-0.x from aec15ed746 to 35311e290d

2026-10-04 01:00:33 +00:00

Compare

renovate force-pushed renovate-openai-codex-0.x from 35311e290d to 3816c55422

2026-10-05 19:00:56 +00:00

Compare

renovate changed title from ~~chore(deps): update dependency openai/codex to v0.160.0~~ to chore(deps): update dependency openai/codex to v0.160.1

2026-10-05 19:01:18 +00:00

renovate force-pushed renovate-openai-codex-0.x from 3816c55422 to faf4fbfb7e

2026-10-06 01:00:21 +00:00

Compare

renovate force-pushed renovate-openai-codex-0.x from faf4fbfb7e to 848275674f

2026-10-07 16:00:48 +00:00

Compare

renovate changed title from ~~chore(deps): update dependency openai/codex to v0.160.1~~ to chore(deps): update dependency openai/codex to v0.161.0

2026-10-07 16:01:12 +00:00

renovate force-pushed renovate-openai-codex-0.x from 848275674f to 67ddc51250

2026-10-07 20:00:18 +00:00

Compare

renovate force-pushed renovate-openai-codex-0.x from 67ddc51250 to ec57db45f0

2026-10-08 19:00:46 +00:00

Compare

renovate changed title from ~~chore(deps): update dependency openai/codex to v0.161.0~~ to chore(deps): update dependency openai/codex to v0.162.0

2026-10-08 19:01:09 +00:00

renovate force-pushed renovate-openai-codex-0.x from ec57db45f0 to 265905d733

2026-10-08 21:00:39 +00:00

Compare

renovate force-pushed renovate-openai-codex-0.x from 265905d733 to 72ce350609

2026-10-09 20:00:42 +00:00

Compare

renovate changed title from ~~chore(deps): update dependency openai/codex to v0.162.0~~ to chore(deps): update dependency openai/codex to v0.162.1

2026-10-09 20:01:03 +00:00

renovate force-pushed renovate-openai-codex-0.x from 72ce350609 to ac4d309dbd

2026-10-10 06:00:17 +00:00

Compare

renovate force-pushed renovate-openai-codex-0.x from ac4d309dbd to 341fbd0a65

2026-10-14 18:00:54 +00:00

Compare

renovate force-pushed renovate-openai-codex-0.x from 341fbd0a65 to b5f04f4e7e

2026-10-15 04:06:24 +00:00

Compare

renovate force-pushed renovate-openai-codex-0.x from b5f04f4e7e to 5424fa2716

2026-10-15 22:00:31 +00:00

Compare

renovate changed title from ~~chore(deps): update dependency openai/codex to v0.162.1~~ to chore(deps): update dependency openai/codex to v0.163.0

2026-10-15 22:00:51 +00:00

renovate force-pushed renovate-openai-codex-0.x from 5424fa2716 to e7fc1616a4

2026-10-16 22:00:35 +00:00

Compare

This pull request can be merged automatically.

You are not authorized to merge this pull request.

View command line instructions

Checkout

From your project repository, check out a new branch and test the changes.

git fetch -u origin "renovate-openai-codex-0.x:renovate-openai-codex-0.x"

git switch "renovate-openai-codex-0.x"

Merge

Merge the changes and update on Forgejo.

Warning: The "Autodetect manual merge" setting is not enabled for this repository, you will have to mark this pull request as manually merged afterwards.

git switch "main"

git merge --no-ff "renovate-openai-codex-0.x"

git switch "renovate-openai-codex-0.x"

git rebase "main"

git switch "main"

git merge --ff-only "renovate-openai-codex-0.x"

git switch "renovate-openai-codex-0.x"

git rebase "main"

git switch "main"

git merge --no-ff "renovate-openai-codex-0.x"

git switch "main"

git merge --squash "renovate-openai-codex-0.x"

git switch "main"

git merge --ff-only "renovate-openai-codex-0.x"

git switch "main"

git merge "renovate-openai-codex-0.x"

git push origin "main"

No reviewers

No labels

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference

foosinn/agentic-env!8

No description provided.

Rows
Columns

chore(deps): update dependency openai/codex to v0.163.0 #8

Release Notes

v0.163.0: 0.163.0

New Features

Bug Fixes

Documentation

Chores

Changelog

v0.162.1: 0.162.1

Bug Fixes

v0.162.0: 0.162.0

New Features

Bug Fixes

Chores

Changelog

v0.161.0: 0.161.0

New Features

Bug Fixes

Documentation

Chores

Changelog

v0.160.1: 0.160.1

Bug Fixes

Changelog

v0.160.0: 0.160.0

New Features

Bug Fixes

Documentation

Chores

Changelog

v0.159.3: 0.159.3

New Features

Changelog

v0.159.2: 0.159.2

Bug Fixes

Changelog

v0.159.1: 0.159.1

New Features

Changelog

v0.159.0: 0.159.0

New Features

Bug Fixes

Chores

Changelog

v0.158.0: 0.158.0

New Features

Bug Fixes

Changelog

v0.157.1: 0.157.1

Chores

Changelog

v0.157.0: 0.157.0

New Features

Bug Fixes

Changelog

Configuration

Checkout

Merge

`v0.163.0`: 0.163.0

`v0.162.1`: 0.162.1

`v0.162.0`: 0.162.0

`v0.161.0`: 0.161.0

`v0.160.1`: 0.160.1

`v0.160.0`: 0.160.0

`v0.159.3`: 0.159.3

`v0.159.2`: 0.159.2

`v0.159.1`: 0.159.1

`v0.159.0`: 0.159.0

`v0.158.0`: 0.158.0

`v0.157.1`: 0.157.1

`v0.157.0`: 0.157.0