New Features
- Browse model providers under Sessions → Model providers and choose the default for new chats. (#59541, [#59722])
- Enable
features.tui_workspaceto view a side conversation beside the main chat. Drag the divider to resize the panes or pressleader zto zoom the focused pane. (#58992, [#59527], [#59595]) - Attach recordings when using an audio-capable model. Codex skips confirmed rejected recordings on later turns and uses clip duration to keep more short recordings in context. (#59234, [#59268])
- Enable
features.image_generation_animationto generate or edit animated GIFs with optional frame count and timing controls. (#59073) - Fullscreen Codex displays image previews and pets in tmux on Ghostty and Kitty with
allow-passthrough all. (#59579, [#59580]) - Set
tui.notification_method = "osc777"for terminal notifications. Approval notifications show longer command previews and distinguish terminal input from network access requests. (#59256)
Bug Fixes
- Local TUI history and resume pickers filter newly created threads by the signed-in ChatGPT account. (#58918)
- Open and resumed chats use their saved model provider after you change the default for new chats. (#59503)
- The TUI renders replies interrupted by tool calls as a single Markdown message and restores reasoning summaries when replaying a conversation. (#59698, [#59700])
- Steering messages reach running turns when sent during the final transcript save or after switching back to a long-running chat. (#58877, [#58998])
- Fuzzy file search gives filename matches more weight so matching parent directories are less likely to crowd them out. (#59709)
- Idle local MCP servers on Windows leave filesystem I/O available to the rest of Codex. (#59726)
Documentation
- The app-server reference covers listing model providers, creating custom gateways, and updating gateway, Bedrock, and GCP settings. (#58845, [#58876])
Chores
- Codex warns when
features.multi_agentis explicitly configured and points toagents.enabledfor disabling subagent tools. (#59479) - Contributors can run Bazel CI jobs locally without BuildBuddy credentials. (#59055)
Changelog
Full Changelog: https://github.com/openai/codex/compare/rust-v0.167.0...rust-v0.168.0
- [#58766] Distinguish update handoffs in TUI startup telemetry @etraut-openai
- [#58767] Validate
/forkbefore consuming the composer draft @etraut-openai - [#58829] Accept agent follow-ups through native turn input delivery @won-openai
- [#58845] Add model provider discovery to the app server @alexsong-oai
- [#58876] Add model provider configuration writes to the app-server @alexsong-oai
- [#58877] Handle steers accepted during the final transcript flush @charliemarsh-oai
- [#58886] Preserve timestamp ties when paginating threads @jif-oai
- [#58890] Add a feature-gated account check for CLI thread resume @jif-oai
- [#58894] Support model catalog overrides for plugin guidance @goodman-oai
- [#58899] Add native patch support to direct Guardian review @swastik-oai
- [#58903] Support permission requests in direct Guardian review @swastik-oai
- [#58904] Add a standalone HTTP MCP server for the agent message board @jif-oai
- [#58908] Package the message board MCP connection as a plugin @jif-oai
- [#58909] Add an in-memory launcher for the message-board MCP server @jif-oai
- [#58918] Scope local history discovery to the current ChatGPT account @jif-oai
- [#58927] Fix live stream reflow at the allocated conversation width @fcoury-oai
- [#58931] Support direct Guardian review of patches invoked through exec_command @swastik-oai
- [#58933] Release message-board state before HTTP shutdown returns @jif-oai
- [#58935] Defer Guardian context trimming in elastic preparation @ioanbudea-OAI
- [#58936] Extract model-provider unit tests into separate files @ioanbudea-OAI
- [#58937] Verify queued network approval wakeups before polling again @seanh-oai
- [#58938] Skip attribution for direct MCP tool calls @victor-openai
- [#58939] Refine additional-context byte histogram buckets @akira-oai
- [#58940] Retire the daemon_auto_start feature flag @etraut-openai
- [#58945] Fix model selection after provider setup @etraut-openai
- [#58946] Preserve Guardian sender context for cloud deliveries with orbit IDs @felixxia-oai
- [#58950] Recover WebSocket transport after transient HTTP fallback @charliemarsh-oai
- [#58953] Support caller-owned sideband channels for realtime attachments @jiahao-oai
- [#58954] Add a thread-store builder with host cleanup support @felixxia-oai
- [#58955] Delete Guardian evidence boards when permanently deleting threads @felixxia-oai
- [#58956] Allow volatile World State sections to refresh after compaction @rhan-oai
- [#58957] Cache marketplace name mismatches during automatic upgrades @charliemarsh-oai
- [#58959] Recover inherited history from alternate rollout copies @charliemarsh-oai
- [#58960] Prefer indexed rollout paths when resolving ancestors @charliemarsh-oai
- [#58962] Preserve Guardian budget policy through review recovery @ioanbudea-OAI
- [#58963] Add host-owned turn admission to the agent runtime @rhan-oai
- [#58964] Stabilize and enable client tool output retention by default @jif-oai
- [#58966] Move protocol permissions tests into a separate file @viyatb-oai
- [#58969] Avoid unnecessary rendering during TUI history loading and insertion @etraut-openai
- [#58970] Keep automatic thread title saves off the TUI event loop @etraut-openai
- [#58971] Fix Escape handling in memory reset confirmation @imac-oai
- [#58973] Add opt-in MCP discovery for in-memory agent message boards @jif-oai
- [#58974] Bind final-message output before running sandboxed tools @viyatb-oai
- [#58975] Add usage accounting for host-owned agent runtimes @rhan-oai
- [#58978] Enable the segment heap on Windows CI runners @anp-oai
- [#58980] Record turn critical path metrics and trace fields @bkotsopoulos
- [#58983] Extend and bound exec-server session recovery @richardopenai
- [#58984] Allow hosts to restrict a thread's root-only capabilities @rhan-oai
- [#58986] Move agent message-board backend construction into the extension @jif-oai
- [#58988] Respect delivery boundaries for injected agent messages @won-openai
- [#58989] Keep HTTP fallback active for the rest of the session @charliemarsh-oai
- [#58990] Preserve modified Ctrl+C keys in active TUI views @imac-oai
- [#58992] Add opt-in side conversation panes to the TUI @fcoury-oai
- [#58996] Deliver environment hook decisions while output reads are queued @andrewgu-oai
- [#58998] Preserve steering when returning to a long-running turn @tamird
- [#59000] Allow hosted child threads to inherit a root session ID @rhan-oai
- [#59001] Test connection events against active environment selections @anp-oai
- [#59003] Preserve Guardian review framing under elastic context limits @ioanbudea-OAI
- [#59007] Add host cycling and saved defaults for new TUI conversations @bc-openai
- [#59009] Centralize filesystem permission resolution for sandbox enforcement @viyatb-oai
- [#59011] Add optional total token limits to elastic section configuration @ioanbudea-OAI
- [#59015] Make SQLite schema migrations safe for concurrent startup @dkovalenko-oai
- [#59016] Make observed thread metadata writes atomic and retryable @dkovalenko-oai
- [#59018] Add WebSocket connection metrics with reauthentication labels @bromano-oai
- [#59020] Preserve sandbox context in prepared MCP calls @sayan-oai
- [#59021] Allow concurrent readers of the installation ID @dkovalenko-oai
- [#59025] Remove strict third-party tool deferral in Code Mode Only @rishab-openai
- [#59028] Use prepared MCP owner permissions in Guardian reviews @sayan-oai
- [#59033] Add web search provider metadata and configuration @yitaoh-oai
- [#59034] Add model Search discovery to MCP bindings @yitaoh-oai
- [#59036] Resolve model-selected search providers with policy-aware fallback @yitaoh-oai
- [#59041] Expose assistant content token counts in completion notifications @aojiao-oai
- [#59043] Tie executor attachments to environment selection lifetimes @anp-oai
- [#59047] Decode live transcript updates in the cloud client @bc-openai
- [#59055] Run Bazel CI locally without BuildBuddy credentials @dkovalenko-oai
- [#59057] Tailor MCP doctor remediation to detected problems @etraut-openai
- [#59058] Classify daemon auto-start failures in TUI telemetry @etraut-openai
- [#59066] Add typed item lifecycle events to the cloud client @bc-openai
- [#59068] Enable Bedrock onboarding through the local daemon @etraut-openai
- [#59071] Enforce strict third-party tool deferral in Code Mode Only @rishab-openai
- [#59073] Add optional animated GIF output to image generation @Gan-Tu
- [#59075] Add paginated history reads to the cloud client @bc-openai
- [#59076] Clarify argument meanings in marketplace and guardian tests @fcoury-oai
- [#59082] Make native startup libraries available to Windows voice-host tests @fcoury-oai
- [#59107] Add opt-in reconsideration of Guardian denials @jif-oai
- [#59111] Normalize saved chat settings after model catalog refreshes @dpatel-oai
- [#59115] Preserve worker permissions across sibling-triggered reloads @jif-oai
- [#59118] Preserve Guardian denials when reconsideration times out @jif-oai
- [#59120] Allow dangerous-command review when sandbox approvals are disabled @jif-oai
- [#59124] Remove a redundant permission profile clone in exec policy tests @jif-oai
- [#59125] Add context to Guardian test setup failures @jif-oai
- [#59130] Add a shortcut to hide the focused side conversation pane @fcoury-oai
- [#59131] Clarify test failures and annotate a backend registration invariant @oh-openai
- [#59136] Parse Guardian review responses once @felixxia-oai
- [#59139] Route message-board notifications through agent mailboxes @jif-oai
- [#59154] Expose thread APIs for message board access @jif-oai
- [#59159] Move Guardian unit tests into their owning crates @felixxia-oai
- [#59161] Clarify token-count and screen-ownership arguments in tests @jif-oai
- [#59162] Move agent message board host integration to app-server @jif-oai
- [#59167] Move agent message board cleanup into the app server @jif-oai
- [#59177] Wire shared runtime authentication through threads and API clients @cooper-oai
- [#59192] Resolve saved Daybreak preferences against advertised model programs @jamy-OAI
- [#59201] Add cloud client message submission and turn interruption @bc-openai
- [#59208] Add shortcuts to focus the main composer and side conversation @fcoury-oai
- [#59217] Use the public managed-features constructor in the guardian config test @dylan-hurd-oai
- [#59219] Use Bazel's zstd library for zstd-sys @cayoub-oai
- [#59225] Revalidate Guardian denials when parent authorization changes @felixxia-oai
- [#59227] Preserve installer stderr when releasing the install lock @etraut-openai
- [#59228] Handle
budget_reachedas a terminal session budget error @yuning-oai - [#59231] Fix test fixtures for Bazel sandboxes and Windows voice runtimes @dkovalenko-oai
- [#59232] Suppress macOS warnings in the V8 libc++ Bazel build @dkovalenko-oai
- [#59233] Use resolved filesystem permissions in Windows sandbox policies @viyatb-oai
- [#59234] Enable uploaded audio with durable rejection recovery @hung-oai
- [#59237] Budget retained file audio during remote compaction @hung-oai
- [#59238] Register the Guardian additional-context feature flag @akira-oai
- [#59239] Honor Guardian's additional-context setting for tool outputs @akira-oai
- [#59240] Mark deny-path parent directories created by the Windows MXC launcher @iceweasel-oai
- [#59242] Set seven-day garbage collection ages for Bazel caches @anp-oai
- [#59245] Expand per-turn critical path capture and split inference timing @taohong339
- [#59250] Expand Windows deny-read globs without invoking ripgrep @iceweasel-oai
- [#59251] Track automatic review overhead in critical-path durations @taohong339
- [#59253] Clarify TUI reconnect status for HTTP 429 stream errors @etraut-openai
- [#59254] Add stdin bearer authentication for exec-server registration @apanasenko-oai
- [#59255] Bind reusable backend clients to runtime authentication @cooper-oai
- [#59256] Add OSC 777 notifications and improve approval notification text @etraut-openai
- [#59257] Preserve prompt contrast when terminal colors are unavailable @etraut-openai
- [#59258] Refactor sandbox request preparation by backend @viyatb-oai
- [#59260] Report auto-review overhead in turn critical-path analytics @taohong339
- [#59263] Normalize loading bullets in the safety recourse snapshot test @dkovalenko-oai
- [#59268] Use measured durations to budget uploaded audio @hung-oai
- [#59272] Preserve requested approval reviewers across policy overrides @ioanbudea-OAI
- [#59275] Support API workload identity authentication @cooper-oai
- [#59278] Enforce current filesystem permissions when reading repository skills @dkovalenko-oai
- [#59279] Preserve filesystem authority when loading skills @dkovalenko-oai
- [#59280] Respect filesystem permissions when discovering repository skills @dkovalenko-oai
- [#59282] Enable unified image budgeting by default @dkovalenko-oai
- [#59287] Add directional conversation focus shortcuts in workspace mode @fcoury-oai
- [#59291] Respect turn filesystem permissions during executor skill discovery @dkovalenko-oai
- [#59295] Add outcome metrics for skill reads and installation listings @TAFOYA-OAI
- [#59299] Switch rusty_v8 to the openai-oss-forks repository @seanh-oai
- [#59312] Route response item IDs through a shared generator @euroelessar
- [#59319] Restore background terminals from the displayed thread's live state @etraut-openai
- [#59328] Introduce a dedicated context window ID type @euroelessar
- [#59330] Stop TUI voice calls when the OS session locks @bc-openai
- [#59343] Add cloud thread activation with resolved settings @bc-openai
- [#59351] Add managed thread prewarming to the cloud client @bc-openai
- [#59354] Share context window ID allocation through the agent runtime @euroelessar
- [#59369] Stabilize cross-platform tests and directory-change fork permissions @dkovalenko-oai
- [#59401] Honor section limits in elastic Guardian context budgeting @ioanbudea-OAI
- [#59403] Fix missing item ID generators in retained instruction tests @jif-oai
- [#59404] Preserve pending agent messages across compaction @jif-oai
- [#59444] Add opt-in elastic budgeting for synchronous Guardian reviews @ioanbudea-OAI
- [#59445] Warn when project instructions exceed the configured byte budget @etraut-openai
- [#59447] Restore the daemon auto-start feature flag @etraut-openai
- [#59448] Prefer Launchpad for Linux zlib downloads in
rules_rs@jif-oai - [#59455] Carry per-input extension data to user message completion callbacks @wemmanuel-oai
- [#59458] Drain queued side-conversation events before switching focus @etraut-openai
- [#59468] Allow prepared forks to use source revalidation @owenlin0
- [#59472] Preserve transcript interaction when switching panes with arrow keys @fcoury-oai
- [#59473] Extract agent message board hosting into a dedicated crate @seanh-oai
- [#59474] Refactor MCP tool argument parsing and approval preparation @swastik-oai
- [#59476] Honor project agent opt-ins over lower-priority legacy opt-outs @jif-oai
- [#59478] Record saved multi-agent opt-outs in session telemetry @jif-oai
- [#59479] Deprecate the
multi_agentfeature flag @jif-oai - [#59480] Add per-turn prompt cache TTL options @rm-openai
- [#59481] Allow per-turn overrides for direct-only tool namespaces @hlevy-openai
- [#59489] Use MCP owner permissions for Guardian reviews and score reuse @sayan-oai
- [#59491] Preserve external auth through transient provider failures @cooper-oai
- [#59493] Add a native cloud backend to the app-server client @bc-openai
- [#59495] Honor the configured credential store in gateway test fixtures @jif-oai
- [#59496] Preserve project agent opt-ins across enabled legacy feature flags @jif-oai
- [#59497] Add debug timing for thread item pagination @yiqian-oai
- [#59501] Fix the workspace policy test's auth loading call @bc-openai
- [#59503] Keep threads on their saved model provider when defaults change @abhinav-oai
- [#59505] Upgrade argument comment lint to Dylint 6.3.0 @seanh-oai
- [#59507] Bind memory consolidation permissions to the memory root @ioanbudea-OAI
- [#59509] Forward caller metadata on MCP resource reads @joesavona
- [#59510] Use server model defaults for fresh TUI sessions on every connection @etraut-openai
- [#59512] Bump the Python SDK build backend to
uv_build0.13 @ww-oai - [#59514] Add paginated cloud thread discovery to the cloud client @bc-openai
- [#59517] Simplify pending interactive request tracking in the TUI @dkovalenko-oai
- [#59518] Validate UI trees at decode time and simplify display elements @joesavona
- [#59520] Populate the local secrets cache after successful saves @celia-oai
- [#59524] Forward cloud message item lifecycle notifications @bc-openai
- [#59527] Make side conversation panes resizable and interactive @fcoury-oai
- [#59530] Resolve workspace permissions at the sandbox launch boundary @viyatb-oai
- [#59531] Render host-owned V2 subagent rosters in environment context @rhan-oai
- [#59535] Add opt-in Unicode canonical matching to exec policy rules @dylan-hurd-oai
- [#59540] Add a token-efficient model-facing ID generator @anp-oai
- [#59541] Add model provider browsing to the TUI configuration panel @alexsong-oai
- [#59544] Use paused time throughout the Noise relay recovery test @dylan-hurd-oai
- [#59564] Extend runtime auth to account, plugin, and file requests @cooper-oai
- [#59569] Add ChatGPT token stdin authentication to exec-server @aagrawal-oai
- [#59572] Use runtime authentication across backend request paths @cooper-oai
- [#59579] Enable pane-local image previews in tmux @etraut-openai
- [#59580] Enable pets in fullscreen tmux panes with Kitty passthrough @etraut-openai
- [#59590] Increase shared code-mode host capacity safely @pash-openai
- [#59595] Add keyboard controls for TUI pane resizing and zoom @fcoury-oai
- [#59598] Add a root-only option for background compaction @oliverye-oai
- [#59601] Add experimental command output deferral to thread item listings @btraut-openai
- [#59632] Remove the legacy Seatbelt network policy wrapper @ioanbudea-OAI
- [#59633] Expose retained command sessions in incremental world state @jif-oai
- [#59638] Ignore the unmaintained pin-utils advisory in dependency audits @jif-oai
- [#59642] Preserve turn configuration in Guardian scoring and approvals @ioanbudea-OAI
- [#59659] Resample Guardian denials with the original request @jif-oai
- [#59669] Add original-history evidence snapshots for Guardian V3 @felixxia-oai
- [#59670] Capture Guardian evidence incrementally with explicit acknowledgements @felixxia-oai
- [#59671] Add evidence housekeeping for Guardian v3 @felixxia-oai
- [#59677] Remove the legacy sandbox policy summary helper @ioanbudea-OAI
- [#59688] Extract channel notification formatting into
PostPreview@jif-oai - [#59691] Split MCP direct-mode exposure coverage into separate test cases @jif-oai
- [#59693] Support Cloud conversation requests in the app-server client @bc-openai
- [#59698] Fix reasoning summary restoration in the TUI @etraut-openai
- [#59700] Fix TUI assistant messages interrupted by tool execution @etraut-openai
- [#59709] Prioritize filename matches in fuzzy file search @omers-oai
- [#59711] Expand Linux sandbox deny globs in process @iceweasel-oai
- [#59713] Clarify message board notification delivery documentation @jif-oai
- [#59714] Set
output_deferredto false for cloud thread items @jif-oai - [#59722] Allow choosing the default provider for new chats in the TUI @alexsong-oai
- [#59725] Add host reporting for terminal agent turn outcomes @rhan-oai
- [#59726] Prevent idle Windows MCP pipes from blocking unrelated I/O @majapw-oai
- [#59728] Use Codex releases as the primary libcap source for musl builds @anp-oai
- [#59732] Omit native multi-agent guidance when native tools are disabled @won-openai
- [#59735] Support direct Guardian review of recorded MCP calls @swastik-oai
- [#59736] Stabilize the unreadable-glob traversal error test @maxwell-oai[bot]
- [#59737] Restrict Guardian native multi-agent history to the OpenAI provider @jif-oai