- Added search across local conversation history, including case-insensitive content matches with result previews. (openai#23519, openai#23921)
- Made `--profile` the primary profile selector across CLI, TUI permissions, and sandbox flows, with legacy profile configs rejected through migration guidance. (openai#23708, openai#23883, openai#23890, openai#24051, openai#24055, openai#24059, openai#24067, openai#24110)
- Improved MCP setup with per-server environment targeting and OAuth options for streamable HTTP servers. (openai#23583, openai#24120)
- Made connector tool schemas more reliable by preserving local `$ref`/`$defs` structures and compacting oversized schemas before exposure. (openai#23357, openai#23904)
- Let read-only MCP tools run concurrently when they advertise `readOnlyHint`. (openai#23750)
- Added richer extension and hook context, including conversation history for extension tools and subagent identity in hook inputs. (openai#22882, openai#23963)

## Bug Fixes
- Improved remote reliability by reconnecting stale exec-server websocket clients, retrying remote control immediately after auth recovery, and retrying remote compaction v2 streams. (openai#23867, openai#23775, openai#23951)
- Fixed Windows TUI rendering corruption by restoring virtual terminal mode before drawing. (openai#24082)
- Displayed workspace-specific usage-limit messages for credit and spend-cap failures. (openai#24114)
- Allowed plugin skills to reuse shared plugin-level icon assets. (openai#23776)
- Preserved active permission profile metadata when syncing auto-review runtime settings. (openai#23956)
- Ensured Node-based tools honor Codex’s managed network proxy environment. (openai#23905)

## Documentation
- Documented the curl and PowerShell installer paths in the README. (openai#24106)
- Updated developer docs to prefer `just test` over direct `cargo test` for repo-local test runs. (openai#23910)
- Added profile migration documentation links to relevant config errors. (openai#23879)

## Chores
- Simplified release packaging around canonical native artifacts, reusable DotSlash fetching, and a new macOS x64 zsh artifact. (openai#23833, openai#23836, openai#24129, openai#24165)
- Added release-build support for Codex-produced V8 artifacts. (openai#23934)
- Added image re-encoding benchmarks and connector-style JSON schema policy fixtures. (openai#23935, openai#24152)
- Improved tracing and analytics for websocket requests, turn starts, and remote compaction v2. (openai#23581, openai#23980, openai#24146)

## Changelog

Full Changelog: openai/codex@rust-v0.133.0...rust-v0.134.0

- openai#23581 Trace logical websocket request after untraced warmup @jif-oai
- openai#23718 [codex] Steer budget-limited goal extension turns @jif-oai
- openai#23861 fix: cargo lock @jif-oai
- openai#23728 feat: retain remote compaction truncation parity in v2 @jif-oai
- openai#23870 Make tool executor specs mandatory @jif-oai
- openai#23882 [codex] Stabilize subagent start hook test @jif-oai
- openai#23876 refactor: centralize tool exposure planning @jif-oai
- openai#23879 chore: link doc in profile error messages @jif-oai
- openai#23883 cli: rename profile v2 flag to --profile @jif-oai
- openai#23835 docs: add description to codex-cli/package.json @bolinfest
- openai#23583 Route MCP servers through explicit environments @starr-openai
- openai#23886 cli: remove legacy profile v1 plumbing @jif-oai
- openai#23708 tui: plumb permission profile selection @viyatb-oai
- openai#23833 packaging: move rg manifest out of npm bin @bolinfest
- openai#23796 Improve `/goal` error messages for ephemeral sessions @etraut-openai
- openai#23867 Reconnect disconnected exec-server websocket clients with fresh sessions @starr-openai
- openai#23792 TUI: skip goal replace prompt for completed goals @etraut-openai
- openai#23519 [codex] Add rollout-backed thread content search @fc-oai
- openai#22552 Remove plugin hooks feature flag @abhinav-oai
- openai#23836 npm: remove legacy package artifact synthesis @bolinfest
- openai#23921 [codex] Make thread search case-insensitive @fc-oai
- openai#23775 fix(remote-control): retry after auth recovery @apanasenko-oai
- openai#22882 Add subagent identity to hook inputs @abhinav-oai
- openai#22915 [3 of 4] tui: route feature and memory toggles through app server @etraut-openai
- openai#23776 fix: Allow plugin skills to share plugin-level icon assets @xl-openai
- openai#23860 Add Bedrock Mantle GovCloud region @CHARLESPALEN-OAI
- openai#23956 Fix auto-review permission profile override @etraut-openai
- openai#23357 feat: support local refs and defs in tool input schemas @celia-oai
- openai#23963 Expose conversation history to extension tools @sayan-oai
- openai#23904 feat: best-effort compact large tool schemas @celia-oai
- openai#23750 Allow parallel MCP tool calls when annotated readOnly @anp-oai
- openai#23905 [codex] Enable Node env proxy for managed network proxy @rreichel3-oai
- openai#23890 mcp: surface profile migration guidance under --profile @jif-oai
- openai#24051 config: remove legacy profile v1 resolution @jif-oai
- openai#24055 config: remove legacy profile write paths @jif-oai
- openai#24057 Avoid config snapshots in live agent subtree traversal @jif-oai
- openai#24061 otel: drop legacy profile usage telemetry @jif-oai
- openai#24059 fix: reject legacy profile selectors @jif-oai
- openai#23934 ci: Use codex produced v8 artifacts for release builds @cconger
- openai#24099 fix(app-server): fix optional bool annotations @owenlin0
- openai#23910 Prefer `just test` over `cargo test` in docs @anp-oai
- openai#23951 retry remote compaction v2 requests @rhan-oai
- openai#24081 tui: make `codex-tui.log` opt-in @jif-oai
- openai#24102 cli: infer host sandbox backend @bolinfest
- openai#24067 app-server: drop legacy profile config surface @jif-oai
- openai#23736 Add new enterprise requirement gate @adams-oai
- openai#24117 [codex] Use rolling files for Windows sandbox logs @iceweasel-oai
- openai#24106 docs: update README.md to mention curl-based installer @bolinfest
- openai#24082 fix(tui): restore Windows VT before TUI renders @fcoury-oai
- openai#24110 cli: support --profile for codex sandbox @bolinfest
- openai#23980 Add trace_id to TurnStartedEvent @mchen-oai
- openai#24120 Support OAuth options in codex mcp add @mzeng-openai
- openai#23989 Add typed Images client to codex-api @won-openai
- openai#24146 [codex-analytics] split compaction v2 analytics implementation @rhan-oai
- openai#24129 package: factor DotSlash executable fetching @bolinfest
- openai#24151 [codex] Use TurnInput for session task input @pakrym-oai
- openai#23935 [codex] Add image re-encoding benchmarks @anp-oai
- openai#24152 chore: add JSON schema policy fixture coverage @celia-oai
- openai#24157 [codex] Remove external client session reset plumbing @pakrym-oai
- openai#24114 Display workspace usage limit error copy from response header @dhruvgupta-oai
- openai#24165 release: build macOS x64 zsh artifact @bolinfest