Termux rust-v0.140.0-alpha.2 - #204
Merged
Merged
Conversation
- The Python SDK now supports first-class authentication, including API key login, ChatGPT browser and device-code flows, account inspection, and logout APIs. (openai#23093) - Python turn APIs are easier to use for text-only workflows: you can pass a plain string as input, and handle-based runs now return a richer `TurnResult` with collected items, timing, and usage data. (openai#23151, openai#23162) - `codex exec resume` now accepts `--output-schema`, so resumed automations can keep session context while still enforcing structured JSON output. (openai#23123) - TUI startup is faster because terminal capability probes are now batched instead of waiting on several serial checks before the first interactive frame. (openai#23175) - Remote executor registration can now use standard Codex auth instead of a separate registry credential flow. (openai#22769) - App-server turns can preserve requested image fidelity, including original-resolution local images, across user inputs and image-producing tools. (openai#20693) ## Bug Fixes - Goal continuations now stop when they hit usage limits or a repeated blocker instead of looping and burning more tokens, and completion responses phrase usage more naturally. (openai#23094, openai#22907) - The session picker is easier to trust: renamed threads now show `name (thread-id)` in resume hints, and pasted text works in the picker search box. (openai#23234, openai#23338) - Multi-session TUI flows are more reliable: in-progress MCP calls stay marked as active during replay, and elicitation replies are sent back to the thread that requested them. (openai#23236, openai#23241) - Remote sessions now keep websocket connections alive and show repo-relative diff paths again instead of `/tmp/...`-prefixed paths. (openai#23226, openai#23261) - Windows installs are more robust: `codex doctor` now detects npm-managed installs correctly, and MSVC release binaries no longer depend on separately installed VC++ runtime DLLs. (openai#22967, openai#22905) - TUI polish fixes include immediate shutdown feedback on exit, hiding the ChatGPT usage link for non-OpenAI providers, and keeping a cleared Fast tier from reappearing after side-thread resume. (openai#23323, openai#23127, openai#23121) ## Documentation - The Python SDK docs, FAQ, and examples were refreshed around the new auth flow and turn APIs, with clearer setup guidance and simpler text-only examples. (openai#22941, openai#23093, openai#23151, openai#23162) ## Chores - Memory summaries are now versioned and rebuilt when the stored format is stale, which should keep long-lived memory context leaner and more predictable. (openai#23148) ## Changelog Full Changelog: openai/codex@rust-v0.131.0...rust-v0.132.0 - openai#20693 Preserve image detail in app-server inputs @fjord-oai - openai#22891 tui: pass active permission profiles through app commands @bolinfest - openai#22924 app-server-protocol: remove PermissionProfile from API @bolinfest - openai#22941 [codex] Refine Python SDK user-facing docs @aibrahim-oai - openai#22967 Fix Windows doctor npm root probe @etraut-openai - openai#22920 core: set permission profiles from snapshots @bolinfest - openai#22939 [codex] Split Python SDK helper logic @aibrahim-oai - openai#22907 Improve goal completion usage reporting @etraut-openai - openai#23030 test: construct permission profiles directly @bolinfest - openai#22769 exec-server: support auth-backed remote executor registration @miz-openai - openai#22946 [codex] preserve MCP result meta in McpToolCallItemResult @miaolin-oai - openai#23069 multiagent: trim model-visible description, cap to 5 models @sayan-oai - openai#22913 [1 of 4] tui: route primary settings writes through app server @etraut-openai - openai#23093 sdk/python: add first-class login support @aibrahim-oai - openai#23151 [codex] Return TurnResult from Python turn handles @aibrahim-oai - openai#23147 Make multi-agent v2 tool namespace configurable @jif-oai - openai#23036 test: reduce core sandbox policy test setup @bolinfest - openai#23162 [codex] Accept string input for Python turns @aibrahim-oai - openai#23226 Add exec-server websocket keepalive @starr-openai - openai#23148 Densify and version memory summaries @jif-oai - openai#22448 [codex] Add installed-plugin mention API @xli-oai - openai#23288 chore: goal ext skeleton @jif-oai - openai#23291 Make extension lifecycle hooks async @jif-oai - openai#23293 feat: add extension event sink capability @jif-oai - openai#23295 chore: isolate thread goal storage behind GoalStore @jif-oai - openai#23301 chore: goal resumed metrics @jif-oai - openai#23305 chore: make token usage async @jif-oai - openai#23306 Emit goal update events from goal extension tools @jif-oai - openai#23121 tui: keep cleared Fast tier from reappearing after side-thread resume @etraut-openai - openai#23123 Support --output-schema for exec resume @etraut-openai - openai#23128 Fix TUI stream cleanup after turn errors @etraut-openai - openai#23127 Hide ChatGPT usage link for non-OpenAI status @etraut-openai - openai#23175 [1 of 2] Optimize TUI startup terminal probes @etraut-openai - openai#22706 [codex] Remove legacy shell output formatting paths @pakrym-oai - openai#23332 nit: read prompt @jif-oai - openai#22905 windows: link MSVC release binaries with static CRT @iceweasel-oai - openai#23323 fix(tui): show shutdown feedback on exit @fcoury-oai - openai#23261 Fix remote turn diff display roots @starr-openai - openai#22569 Simplify legacy Windows sandbox ACL persistence @iceweasel-oai - openai#23273 Upload rust full CI JUnit reports @starr-openai - openai#22893 fix: harden plugin creator sharing validation @efrazer-oai - openai#23094 goal: pause continuation loops on usage limits and blockers @etraut-openai - openai#23234 Clarify resume hints for renamed threads @etraut-openai - openai#23241 TUI: route elicitation responses to request thread @etraut-openai - openai#23236 TUI: replay in-progress MCP calls as started @etraut-openai - openai#23088 goals: keep pause transitions explicit @etraut-openai - openai#23338 feat(tui): handle paste in session picker @fcoury-oai - openai#23335 feat(app-server): add optional thread_id to experimentalFeature/list @owenlin0
(cherry picked from commit 337303c)
Termux rust-v0.132.0
…nt/wallentx_termux-target_from_release_0.132.0_a234e07f3bcf # Conflicts: # .github/workflows/rust-release.yml # codex-rs/Cargo.toml
…et_from_release_0.132.0_a234e07f3bcf checkpoint: into wallentx/termux-target from release/0.132.0 @ a234e07
Termux rust-v0.133.0-alpha.1
…nt/wallentx_termux-target_from_release_0.133.0_5180a72112f6 # Conflicts: # .github/workflows/rust-release.yml # codex-rs/Cargo.toml
…et_from_release_0.133.0_5180a72112f6 checkpoint: into wallentx/termux-target from release/0.133.0 @ 5180a72
Termux rust-v0.133.0-alpha.3
…nt/wallentx_termux-target_from_release_0.133.0_cf55321c25b5 # Conflicts: # codex-rs/Cargo.toml
…et_from_release_0.133.0_cf55321c25b5 checkpoint: into wallentx/termux-target from release/0.133.0 @ cf55321
- Goals are now enabled by default, backed by dedicated storage, and track progress across active turns. (openai#23300, openai#23685, openai#23696, openai#23732) - `codex remote-control` now runs like a foreground command, waits for readiness, reports machine status, and keeps explicit daemon-style `start`/`stop` commands. (openai#22878) - Permission profiles gained list APIs, inheritance, managed `requirements.toml` support, runtime refresh behavior, and stronger Windows sandbox integration. (openai#22928, openai#23412, openai#22270, openai#23433, openai#22931, openai#23715) - Plugin discovery is easier to inspect, with marketplace-aware list output, installed versions, visible marketplace roots, and remote collection support. (openai#23372, openai#23584, openai#23727, openai#23730) - Extensions can observe more lifecycle events, including subagent start/stop, tool execution, turn metadata, and async approval/turn processing. (openai#22782, openai#22873, openai#23309, openai#23688, openai#23690, openai#23692) ## Bug Fixes - Fixed TUI startup choosing the wrong working directory when reusing a local app-server socket. (openai#23538) - Fixed plan-mode free-form answers so modified Enter keys, like Shift+Enter, no longer submit unexpectedly. (openai#23536) - Removed stale background terminal poll events after a process exits. (openai#23231) - Preserved raw code-mode exec output unless an explicit output token limit is requested. (openai#23564) - Made AGENTS instruction loading more reliable, including local global reads and warnings for invalid UTF-8 instead of silent drops. (openai#23343, openai#23232) - Fixed app-server startup/shutdown races, empty resume/fork paths, plugin upgrade failures, and realtime v1 websocket compatibility. (openai#23516, openai#23578, openai#23400, openai#23356, openai#23771) ## Documentation - Added clearer plugin-creator guidance for updating and reinstalling local personal plugins. (openai#23542) - Expanded app-server/API docs and schema coverage around managed permission profile requirements. (openai#23433, openai#23555) ## Chores - Added a canonical Codex package archive pipeline and moved installers, npm packages, DotSlash, and SDK runtimes toward that shared layout. (openai#23513, openai#23582, openai#23586, openai#23596, openai#23635, openai#23636, openai#23637, openai#23638, openai#23786) - Fixed Linux Python runtime wheel tags so glibc-based systems can install the runtime artifacts. (openai#21812) - Improved release and CI reliability with package-builder tests, prebuilt resource packaging, DotSlash zstd handling, platform-sharded Rust tests, and Codex Linux release runners. (openai#23760, openai#23759, openai#23752, openai#23358, openai#23761) ## Changelog Full Changelog: openai/codex@rust-v0.132.0...rust-v0.133.0 - openai#23343 codex: route global AGENTS reads through LOCAL_FS @starr-openai - openai#22380 fix: default unknown tool schemas to empty schemas @celia-oai - openai#23309 Add tool lifecycle extension contributor @jif-oai - openai#23253 Reduce rust-ci-full Windows nextest timeout flakes @starr-openai - openai#22878 Improve `codex remote-control` CLI UX @owenlin0 - openai#21812 Publish Linux runtime wheels with glibc-compatible tags @aibrahim-oai - openai#22709 [codex] Trim unused TurnContextItem fields @pakrym-oai - openai#23353 Include plugin id in plugin MCP tool metadata @mzeng-openai - openai#22728 [codex] Move pending input into input queue @pakrym-oai - openai#23371 fix(tui): warn on unsupported iTerm2 pet versions @fcoury-oai - openai#23376 [codex-analytics] preserve user thread source for exec threads @marksteinbrick-oai - openai#23360 app-server: use profile ids in v2 permission params @bolinfest - openai#23384 [codex] Remove external websocket session resets @pakrym-oai - openai#22721 cleanup: Remove skill env var dependency prompting @xl-openai - openai#23389 Remove ToolSearch feature toggle @sayan-oai - openai#23080 [1 of 7] Add thread settings to UserInput @etraut-openai - openai#23081 [2 of 7] Remove UserInputWithTurnContext @etraut-openai - openai#23075 [3 of 7] Remove UserTurn @etraut-openai - openai#23396 [codex] Extract turn skill and plugin injections @pakrym-oai - openai#23356 fix(plugins): keep version upgrades additive @iceweasel-oai - openai#22508 [5 of 7] Replace OverrideTurnContext with ThreadSettings @etraut-openai - openai#22086 CI: Customize v8 building @cconger - openai#23390 Remove explicit connector tool undeferral @sayan-oai - openai#22928 core: expose permission profile picker metadata @viyatb-oai - openai#23352 Preserve context baselines for full-history agent forks @jif-oai - openai#23300 feat: dedicated goal DB @jif-oai - openai#22835 Remove ToolsConfig from tool planning @jif-oai - openai#22870 Add `body_after_prefix` auto-compact token limit scope @jif-oai - openai#23144 Defer v1 multi-agent tools behind tool search @jif-oai - openai#23409 [codex] Allow empty turn/start requests @pakrym-oai - openai#23388 [codex] Move hook request plumbing into hook runtime @pakrym-oai - openai#23405 [codex] Preserve steer input as user input @pakrym-oai - openai#22914 [2 of 4] tui: route app and skill enablement through app server @etraut-openai - openai#23397 [codex] Make contextual user fragments dyn-renderable @pakrym-oai - openai#23475 chore: namespace v1 sub-agent tools @jif-oai - openai#23493 Make `deny` canonical for filesystem permission entries @viyatb-oai - openai#22929 Harden CLI rate limit window labels @ase-openai - openai#22782 Add SubagentStart hook @abhinav-oai - openai#23513 build: add Codex package builder @bolinfest - openai#23369 Make local environment optional in EnvironmentManager @starr-openai - openai#23327 Refactor exec-server websocket pump @starr-openai - openai#23536 fix(tui): preserve modified enter in plan questions @fcoury-oai - openai#23400 Fix empty rollout path app-server handling @wiltzius-openai - openai#23551 Route local-only app-server gating through processors @starr-openai - openai#23372 Split plugin install discovery into list and request tools @mzeng-openai - openai#23516 fix: serialize unix app-server startup @efrazer-oai - openai#22169 [codex] Honor role-defined spawn service tiers @aibrahim-oai - openai#23555 Add CUA requirements subsection for locked computer use @adams-oai - openai#23538 Fix: TUI starting in wrong CWD @canvrno-oai - openai#23526 build: fetch rg for Codex packages @bolinfest - openai#23573 Remove unused ARC monitor path @mzeng-openai - openai#23576 test: fix multi-agent service tier assertion @bolinfest - openai#23541 build: default Codex package target and output @bolinfest - openai#23358 Fan out rust-ci-full nextest by platform @starr-openai - openai#23593 feat: expose codex-app-server version flag @bolinfest - openai#23412 feat: add permission profile list api @viyatb-oai - openai#23535 Move plugin and skill warmup into session startup @aibrahim-oai - openai#23231 Fix stale background terminal poll events @etraut-openai - openai#23564 [codex] Preserve raw code-mode exec output by default @aibrahim-oai - openai#23232 Warn on invalid UTF-8 in AGENTS.md files @etraut-openai - openai#23584 feat: Add vertical remote plugin collection support @xl-openai - openai#23586 build: package prebuilt Codex entrypoints @bolinfest - openai#23582 ci: build Codex package archives in release workflow @bolinfest - openai#23596 runtime: detect Codex package layout @bolinfest - openai#23500 add encryptedcontent to functioncalloutput @sayan-oai - openai#23633 Migrate exec-server remote registration to environments @richardopenai - openai#23451 Add timeout for remote compaction requests @jif-oai - openai#23667 feat: rename 1 @jif-oai - openai#23669 feat: rename 3 @jif-oai - openai#23668 feat: rename 2 @jif-oai - openai#23675 fix: main @jif-oai - openai#23685 feat: wire goal extension tools to the dedicated goal store @jif-oai - openai#23690 feat: async approval contrib @jif-oai - openai#23692 feat: async turn item process @jif-oai - openai#23688 feat: expose turn-start metadata to extensions @jif-oai - openai#23605 [codex] Hide deferred tools from code mode prompt @pakrym-oai - openai#23634 runtime: use install context for bundled bwrap @bolinfest - openai#23635 release: publish Codex package archive checksums @bolinfest - openai#23592 feat: Add btw alias for side slash command @anp-oai - openai#23696 feat: account active goal progress in the goal extension @jif-oai - openai#23176 [2 of 2] Start fresh TUI thread in background @etraut-openai - openai#23578 fix(app-server): speed up shutdown @fcoury-oai - openai#22896 windows-sandbox: add resolved permissions helper @bolinfest - openai#23502 Add thread/settings/update app-server API @etraut-openai - openai#23507 Sync TUI thread settings through app server @etraut-openai - openai#23666 feat: add turn_id and truncation_policy to extension tool calls @jif-oai - openai#23636 install: consume Codex package archives @bolinfest - openai#23717 [codex] Preserve failed goal accounting flushes @jif-oai - openai#23655 add standalone websearch api client @sayan-oai - openai#23724 Fix thread settings clippy failure @etraut-openai - openai#23637 npm: ship platform packages in Codex package layout @bolinfest - openai#23729 fix(config): resolve cloud requirements deny-read globs @viyatb-oai - openai#23638 dotslash: publish Codex entrypoints from package archives @bolinfest - openai#22918 windows-sandbox: send permission profiles to elevated runner @bolinfest - openai#23735 windows-sandbox: share bundled helper lookup @bolinfest - openai#18868 Add MITM hook config model @evawong-oai - openai#22270 feat(permissions): resolve permission profile inheritance @viyatb-oai - openai#23719 cli: add strict config to exec-server @bolinfest - openai#23542 [skills] Create a personal update flow for plugin creator @caseychow-oai - openai#21272 Support compact SessionStart hooks @abhinav-oai - openai#20659 Wire MITM hooks into runtime enforcement @evawong-oai - openai#23752 release: use DotSlash zstd for package archives @bolinfest - openai#22923 windows-sandbox: drive write roots from resolved permissions @bolinfest - openai#23761 chore: use Codex Linux runners for Rust releases @bolinfest - openai#23759 release: package prebuilt resource binaries @bolinfest - openai#23167 windows-sandbox: feed setup from resolved permissions @bolinfest - openai#22931 core: refresh active permission profiles at runtime @viyatb-oai - openai#22873 Add SubagentStop hook @abhinav-oai - openai#23727 feat(plugins): tabulate plugin list output @caseychow-oai - openai#23732 Make goals feature on by default and no longer experimental @etraut-openai - openai#23537 Honor client-resolved service tier defaults @shijie-oai - openai#23771 [codex] Fix realtime v1 websocket compatibility @guinness-oai - openai#23764 Remove Windows sandbox resource stamping @iceweasel-oai - openai#23730 [codex] List marketplaces considered by plugin discovery @caseychow-oai - openai#23760 ci: run Codex package builder tests @bolinfest - openai#23737 [codex] Add plugin id to MCP tool call items @mzeng-openai - openai#18240 Use named MITM permissions config @evawong-oai - openai#23774 [codex] Reject read-only fallback with approvals disabled @viyatb-oai - openai#23714 windows-sandbox: add profile-native elevated APIs @bolinfest - openai#23433 feat: support managed permission profiles in requirements.toml @viyatb-oai - openai#23715 core: pass permission profiles to Windows runner @bolinfest - openai#23786 sdk: launch packaged Codex runtimes @bolinfest
Termux rust-v0.133.0
…nt/wallentx_termux-target_from_release_0.133.0_7bcabc22ebc3
…et_from_release_0.133.0_7bcabc22ebc3 checkpoint: into wallentx/termux-target from release/0.133.0 @ 7bcabc2
…et_from_release_0.138.0_2ae55f9a4229 checkpoint: into wallentx/termux-target from release/0.138.0 @ 2ae55f9
- The `/app` command can now hand off the current CLI thread into Codex Desktop on macOS and native Windows, and Windows workspace launches can open directly into Desktop instead of stopping at a manual prompt. (openai#25638, openai#26500) - Local image attachments and standalone image generations now expose their saved file paths to the model, which makes follow-up edits and file references more reliable. (openai#25944, openai#25947) - Reasoning effort selection is more flexible: the TUI adds fallback shortcuts for terminals that miss `Alt` bindings, and model-defined effort levels now flow through in the order advertised by the model. (openai#25623, openai#26444, openai#26446) - App-server integrations can now read account token usage, and Codex auth supports v2 personal access tokens in CLI and app-server flows. (openai#25344, openai#25731) - Plugin automation got richer structured output: add/remove and marketplace commands support `--json`, plugin list JSON includes marketplace source, and plugin detail data now exposes default prompts, remote MCP servers, and unavailable app templates. (openai#26631, openai#26417, openai#25887, openai#26453, openai#26317) ## Bug Fixes - Goal workflows are more predictable: multiline paste in `/goal edit` no longer submits early, idle auto-turns stay out of Plan mode, and goals stop auto-continuing after terminal turn failures. (openai#26047, openai#26147, openai#26690) - Forked threads now keep user-renamed titles instead of falling back to the original first-prompt name. (openai#26075) - The TUI no longer adds extra blank space while streaming, and cancelled prompts reopen with the cursor at the end so you can keep editing naturally. (openai#26636, openai#26457) - TUI config write failures now show the underlying cause, making validation problems and read-only filesystem issues much easier to diagnose. (openai#26537) - Startup is more resilient across environments, with support for `/usr/bin/bash`, shorter Linux proxy socket paths, and pre-refresh of expired OAuth-backed MCP credentials. (openai#26538, openai#26553, openai#26482) - Workspace instruction loading is more accurate for remote and symlinked workspaces, so the right `AGENTS.md` files are picked up consistently. (openai#26205, openai#26465) ## Documentation - The CLI README was refreshed to remove stale guidance and better match the current documentation flow. (openai#26313) ## Chores - TUI startup does less repeated plugin work by reusing discovery results and loading only hook metadata on the critical path. (openai#26469, openai#26272) - `resume --last` now finds the newest matching session through the state DB first, which speeds up restore on large local histories. (openai#26462) - Large MCP/Ollama streams and long message histories process much faster thanks to optimized byte scanning. (openai#26265) ## Changelog Full Changelog: openai/codex@rust-v0.137.0...rust-v0.138.0 - openai#26179 nit: small prompt update for MAv2 @jif-oai - openai#26175 feat: guard git enrichment @jif-oai - openai#26047 Fix multiline paste in /goal edit @etraut-openai - openai#25700 core: stop threading SandboxPolicy through exec @bolinfest - openai#25925 [codex] Copy user Bazel settings into Codex worktrees @anp-oai - openai#26216 [codex] Pin Python SDK to runtime 0.137.0a4 @aibrahim-oai - openai#25887 Preserve remote plugin default prompts @ericning-o - openai#25944 Expose local image paths to models @won-openai - openai#25469 [profile-switcher][rust] -- [1/2] Add app-server account session protocol @dhruvgupta-oai - openai#26075 Fix forked thread name inheritance @etraut-openai - openai#25960 Restore Windows coverage for code-mode image generation exposure @won-openai - openai#26226 [codex] Split Python runtime release workflow @aibrahim-oai - openai#26254 feat: catalog multi-agent v2 config @jif-oai - openai#26251 Rewrite oversized tool outputs during remote compaction @pakrym-oai - openai#26260 codex-pr-body: avoid confidential references @anp-oai - openai#26074 Use Windows setup marker as completion signal @abhinav-oai - openai#26002 log plugin MCP server names @chrisdong-oai - openai#25623 fix(tui): add reasoning effort fallback shortcuts @fcoury-oai - openai#25638 feat(tui): add /app desktop handoff @fcoury-oai - openai#26189 cli: add package path from install context @bolinfest - openai#25946 [codex-analytics] report compaction request token counts @rhan-oai - openai#26252 ci: sign macOS release artifacts with Azure Key Vault @eburke-openai - openai#26367 chore: calm down @jif-oai - openai#26147 Gate automatic idle turns in Plan mode @jif-oai - openai#26172 Bridge host-loaded skills into the skills extension @jif-oai - openai#26265 Optimize unbounded byte scans with memchr @charliemarsh-oai - openai#26396 Reduce SQLite contention from OpenTelemetry SDK debug logs @zanie-oai - openai#26272 Load plugin hooks without other plugin capabilities @charliemarsh-oai - openai#26313 Simplify Codex CLI README @etraut-openai - openai#25947 Add saved image path hint to standalone image generation @won-openai - openai#26291 Bound external agent session detection work @stefanstokic-oai - openai#26417 Expose configured marketplace source in plugin list JSON @mpc-oai - openai#26436 app-server: support -c config overrides @bolinfest - openai#26435 external-agent-migration: avoid mixed MCP transport configs @stefanstokic-oai - openai#26248 [codex-analytics] emit forked thread id on initialization @kbazzi - openai#26320 core: allow excluding tool namespaces from code mode @sayan-oai - openai#25945 Use Azure artifact signing environment secrets @shijie-oai - openai#26205 Route AGENTS.md loading through environment filesystems @anp-oai - openai#26445 [codex] Fix Windows sandbox build script lint @pakrym-oai - openai#23710 build: use ThinLTO for release binaries @anp-oai - openai#26447 Remove response.processed websocket request @pakrym-oai - openai#26312 Cleanup experimentalFeature/enablement/set @mzeng-openai - openai#26444 [codex] Support model-defined reasoning efforts @aibrahim-oai - openai#26446 [codex] Use model-advertised reasoning effort order @aibrahim-oai - openai#26466 Use Winget release environment secret @shijie-oai - openai#26465 [codex] Preserve logical paths during AGENTS.md discovery @anp-oai - openai#26453 fix(app-server): expose remote MCP servers in plugin read @ericning-o - openai#26473 Add skill for pushing CI configuration changes @anp-oai - openai#26317 [codex] Expose unavailable app templates in plugin detail @charlesgong-openai - openai#26471 Improve Windows sandbox setup refresh diagnostics @iceweasel-oai - openai#26431 Pull plugin service less frequently @beggers-openai - openai#25000 ci: test windows cross build @cconger - openai#25955 [codex] Emit sandbox outcome telemetry event @rreichel3-oai - openai#26487 [codex] Add use_responses_lite 'override' logic @rka-oai - openai#26482 fix(rmcp): refresh expired OAuth tokens before startup @anp-oai - openai#26256 [codex] Keep Bazel startup options stable across commands @anp-oai - openai#26499 core: derive exec policy filesystem policy from profile @bolinfest - openai#26215 feat(remote-control): allow pairing while disabled @apanasenko-oai - openai#26480 [codex] Add environment shell info @pakrym-oai - openai#26210 Encrypt multi-agent v2 message payloads @jif-oai - openai#26566 nit: doc @jif-oai - openai#25710 [codex] Forward turn moderation metadata through app-server @carlc-oai - openai#26599 [codex] Keep v1 spawn metadata visible @jif-oai - openai#26610 refactor: split agent control modules @jif-oai - openai#25344 feat(app-server): expose account token usage [1 of 2] @fcoury-oai - openai#26553 [codex] Fix long proxy socket paths @viyatb-oai - openai#26537 Surface TUI config write error causes @etraut-openai - openai#26500 Open Windows app workspaces via deep link @etraut-openai - openai#26551 Fix `/goal` usage text for control commands @etraut-openai - openai#26554 Render code comment directives in TUI replay @etraut-openai - openai#26623 feat: reload v2 agents on delivery @jif-oai - openai#26532 Require absolute cwd in thread settings @pakrym-oai - openai#26625 [codex] Allow socketpair in proxy-routed Linux sandbox @viyatb-oai - openai#26538 [codex] Add /usr/bin/bash shell fallback @pakrym-oai - openai#26449 feat(remote-control): add pairing status transport @hefuc-oai - openai#26433 Make turn diff tracker multi-env aware @pakrym-oai - openai#26636 fix(tui): avoid doubled blank rows while streaming @fcoury-oai - openai#26450 feat(app-server): add remote control pairing status RPC @hefuc-oai - openai#26335 Clean up Rust release workflow @shijie-oai - openai#26547 [1 of 2] Align goal extension with core behavior @etraut-openai - openai#26181 fix(tui): Windows composer background @fcoury-oai - openai#26457 fix(tui): restore cancelled prompt cursor at end @fcoury-oai - openai#26307 [codex] Respect Windows sandbox backend in exec policy @iceweasel-oai - openai#26484 [codex] Add turn profiling analytics @aibrahim-oai - openai#26552 Make runtime workspace roots absolute in app-server API @pakrym-oai - openai#26462 Use state DB first for `resume --last` @charliemarsh-oai - openai#26469 Speed up TUI startup by reusing plugin discovery @charliemarsh-oai - openai#26631 Add JSON output for plugin subcommands @mpc-oai - openai#26669 [codex] Bound WSL local curated discovery @xl-openai - openai#26548 [2 of 2] Finish moving goal runtime to extension @etraut-openai - openai#26674 protocol: remove submission-side serde from Op @pakrym-oai - openai#26690 Block active goals after terminal turn errors @etraut-openai - openai#25936 [codex] Remove legacy remote plugin startup sync @xl-openai - openai#26490 [codex] Use standalone tools for Responses Lite @rka-oai - openai#26013 [codex] Gate terminal visualization instructions in TUI @vie-oai - openai#25731 [codex-rs] support v2 personal access tokens @cooper-oai - openai#26542 [codex] Send Responses Lite transport header @rka-oai - openai#24852 permissions: enforce managed permission profile allowlists @viyatb-oai - openai#26698 [codex] Deduplicate skill load warnings @xl-openai - openai#26716 Remove `just bench-smoke` from `just test`. @anp-oai
Termux rust-v0.138.0-alpha.8
…nt/wallentx_termux-target_from_release_0.138.0_e82a4c4a5c22
…et_from_release_0.138.0_e82a4c4a5c22 checkpoint: into wallentx/termux-target from release/0.138.0 @ e82a4c4
Termux rust-v0.138.0
…nt/wallentx_termux-target_from_release_0.138.0_377cf926877e
…et_from_release_0.138.0_377cf926877e checkpoint: into wallentx/termux-target from release/0.138.0 @ 377cf92
- Code mode can now call standalone web search directly, including from nested JavaScript tool calls, and receive plaintext search results. (openai#26719) - Tool and connector input schemas now preserve `oneOf` and `allOf`, and large schemas keep more shallow structure when compacted, improving compatibility with richer MCP tools. (openai#24118, openai#27084) - `codex doctor` now includes editor and pager environment details in the local report while redacting raw values in JSON output. (openai#27081) - Plugin marketplace automation is more informative and responsive: `codex plugin marketplace list --json` now includes each marketplace source, and plugin lists can return from the cached remote catalog before refreshing in the background. (openai#27009, openai#26932) ## Bug Fixes - `codex resume --last "..."` and `codex fork --last "..."` now treat the trailing argument as the initial prompt instead of misreading it as a session ID. (openai#26818) - MCP startup warnings from subagents now stay in the thread that owns them, avoiding duplicate parent-thread alerts and stuck startup spinners in the TUI. (openai#26639) - Image edits now use the exact referenced image file paths instead of guessing from conversation history, so attached-image edits land on the intended input. (openai#26486) - Bare URLs with `~` in the path are now linkified end to end in the TUI instead of being truncated before the tilde. (openai#27088) - Thread resets such as `/new`, `/clear`, and `/fork` no longer drop cloud-managed requirements or feature flags during TUI config reloads. (openai#25177) - Sandbox execution now preserves approved escalation decisions and enforces configured proxy-only networking more consistently. (openai#24981, openai#27035) ## Chores - Release builds once again publish separate symbol archives with line tables, improving post-release crash symbolication without bringing back the earlier full-debug build slowdown. (openai#26202) - The embedded V8 toolchain was updated to `rusty_v8` 149.2.0. (openai#26464) ## Changelog Full Changelog: openai/codex@rust-v0.138.0...rust-v0.139.0 - openai#26741 fix(remote-control): preserve enrollment on generic websocket 404s @apanasenko-oai - openai#26804 fix(core-plugins): send Codex product SKU to plugin-service @ericning-o - openai#26464 build(v8): update rusty_v8 to 149.2.0 @cconger - openai#26895 ci: use bazel environment for BuildBuddy secret @bolinfest - openai#24981 fix: preserve approval sandbox decisions in unified exec @bolinfest - openai#26818 fix(tui): accept prompts with resume and fork @fcoury-oai - openai#24820 deps: update starlark to 0.14.2 @bolinfest - openai#26639 fix(tui): scope MCP startup status by thread @fcoury-oai - openai#26719 [codex] Enable standalone web search in code mode @rka-oai - openai#26632 feat: add v2 agent residency lru @jif-oai - openai#26974 Ignore proc-macro-error2 advisory @jif-oai - openai#26969 feat: count V2 concurrency by active execution @jif-oai - openai#26994 Rename multi-agent v2 close_agent to interrupt_agent @jif-oai - openai#26997 Avoid reopening v2 descendants on resume @jif-oai - openai#26821 [codex] Exclude external tool output from memories @rka-oai - openai#26202 [codex] Restore release symbol artifacts with line tables @nornagon-openai - openai#26852 fix(app-server): avoid blocking connection cleanup @apanasenko-oai - openai#26923 Add HTTP window ID to Responses client metadata @ningyi-oai - openai#26680 [codex-analytics] report compaction analytics details @rhan-oai - openai#26637 [codex] Speed up external agent session imports @stefanstokic-oai - openai#27009 [plugins] Expose marketplace source in marketplace list JSON @mpc-oai - openai#27024 ci: template custom runner names by repo @bolinfest - openai#26230 fix: preserve auto review across config and delegation @viyatb-oai - openai#27038 [codex] Clarify PR babysitter state mutations @anp-oai - openai#27037 [codex] Calm multi-agent v2 usage prompts @jif-oai - openai#26687 Pair thread environment settings @pakrym-oai - openai#27054 cli: add -P sandbox permissions profile alias @bolinfest - openai#27035 Enforce configured network proxy in codex sandbox @viyatb-oai - openai#26486 Route image edits through referenced file paths @won-openai - openai#27060 [codex-analytics] stop sending codex error subreason @rhan-oai - openai#27044 [codex] Require complete main-agent skill reads @fchen-oai - openai#24118 feat: support oneOf and allOf in tool input schemas @celia-oai - openai#26934 [codex] Prune stale curated plugin caches @xl-openai - openai#26932 Use cached remote plugin catalog for plugin list @xl-openai - openai#26091 [codex] Add OTEL counter descriptions @richardopenai - openai#27081 feat(doctor): report editor and pager environment @fcoury-oai - openai#27084 chore: preserve one more schema layer during large tool compaction @celia-oai - openai#26840 Add typed file URIs @anp-oai - openai#27088 fix(tui): linkify complete bare URLs with tildes @fcoury-oai - openai#27068 Show effective sandbox modes in /debug-config @canvrno-oai - openai#27092 Add extra config to StoredThread, leave empty for now @kumquatexpress - openai#27096 Update web search citation prompt @yuning-oai - openai#25177 Preserve cloud requirements across TUI thread resets @canvrno-oai - openai#27106 [codex] Remove remote compaction failure log @pakrym-oai
Termux rust-v0.139.0
…nt/wallentx_termux-target_from_release_0.139.0_746530165eed
…et_from_release_0.139.0_746530165eed checkpoint: into wallentx/termux-target from release/0.139.0 @ 7465301
|
Termux Android artifact ready for testing:
You must be signed in to GitHub with repository access to download Actions artifacts. |
wallentx
approved these changes
Jun 10, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Termux release train
rust-v0.140.0-alpha.2rust-v0.140.0-alpha.2-termuxrelease/0.140.0wallentx/termux-targetThis PR is intentionally created from
wallentx/termux-targetwith the Termux release automation files copied fromdev, then targeted at the upstream release branch. If GitHub reports conflicts, resolve them manually by keeping the upstream release code while preserving the Termux compatibility fixes.Merging this PR is the manual approval gate. The release build workflow uploads the Android artifact to test; after merge, the deployment workflow attaches that exact artifact to
rust-v0.140.0-alpha.2-termuxand opens the checkpoint PR.Upstream notes
Release 0.140.0-alpha.2