Codex 업데이트 기록

Radar Ultra

릴리스 217개

0.90.0

CLIGitHub 원문

AI 요약

  • A network sandbox proxy now helps control outbound network access through policy enforcement.
  • Collaboration mode is available as a TUI beta, with a clearer plan-to-execute handoff and simpler Coding or Plan mode selection.
  • Connectors support has begun through the app server and MCP integration, with related configuration and documentation updates.
  • Resume is more reliable: Codex handles out-of-order events and prompts for the working directory when it differs.
  • Several usability fixes make errors and defaults more dependable: configuration errors are clearer, filtered model presets are respected, and --yolo no longer fails outside a Git repository.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.89.0

CLIGitHub 원문

AI 요약

  • You can now use /permissions for a shorter approval workflow; /approvals remains available for compatibility.
  • A new /skill screen lets you turn individual skills on or off.
  • Slash-command suggestions now favor exact and prefix matches over fuzzy matches.
  • The app server can read individual threads and filter archived threads from thread lists. Its clients also support layered configuration files, and config/read can calculate effective settings for a specified working directory.
  • Tilde paths such as ~//... can no longer expand outside your home directory.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.88.0

CLIGitHub 원문

AI 요약

  • Headless environments now have device-code authentication as a standalone fallback.
  • Configuration is loaded only from trusted folders, and symlinked config.toml files are now resolved correctly.
  • Interrupted turns no longer repeat.
  • Fixed Azure endpoint input errors, a memory leak in the core runtime, and an image-paste regression in the WSL interface.
  • Updated MCP documentation links and collaboration-mode developer instructions, and corrected a naming typo.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.87.0

CLIGitHub 원문

AI 요약

  • Piped commands that don’t use a terminal no longer hang while waiting for input.
  • User shell commands now use your shell settings and aliases.
  • The TUI now shows approval requests from spawned or unsubscribed threads.
  • Token estimates during compaction are more accurate, improving budget estimates in long sessions.
  • User-message annotations can now survive history rebuilds, and MCP tool results include a thread ID and defined output schema for compatibility.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.86.0

CLIGitHub 원문

AI 요약

  • Skill metadata can now be set in SKILL.toml, including names, descriptions, icons, brand color, and a default prompt, and is surfaced in the app server and TUI.
  • Clients can explicitly disable web search and send an eligibility header, supporting alignment with server-side rollout controls.
  • Accepting an MCP elicitation now sends an empty JSON payload instead of null, for servers that expect content.
  • Several interaction and process issues were fixed: prompt placeholders are no longer italic, empty paste events no longer read clipboard images, and Unified exec cleans up background processes to prevent late End events.
  • Internal changes refresh the orchestrator prompt to improve routing behavior and reduce noisy needs_follow_up error logs.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.85.0

CLIGitHub 원문

AI 요약

  • App-server v2 now sends collaboration tool calls as turn-stream events, letting clients show agent coordination as it happens.
  • You can assign a role preset when spawning an agent, and optionally interrupt a running agent before sending it a message.
  • codex resume --last now resumes sessions from the current working directory; use --all to override that limit.
  • Model upgrade suggestions can include richer guidance from migration notes, when the client displays the new metadata.
  • Linux sandboxing now uses Landlock-only restrictions if user namespaces are unavailable, and sets no_new_privs before applying sandbox rules.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.84.0

CLIGitHub 원문

AI 요약

  • Text elements can now include additional metadata, allowing clients to render them in richer ways and making the schema easier to evolve.
  • Rust release builds have a longer job timeout to reduce flaky pipeline failures, particularly on Windows.
  • Rust release builds have a longer job timeout to reduce flaky pipeline failures, particularly on Windows.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.81.0

CLIGitHub 원문

AI 요약

  • The default API model is now gpt-5.2-codex.
  • Headless runs now switch to device-code sign-in automatically, so you can sign in without a browser.
  • On Linux, the sandbox can mount paths read-only to better protect files from changes.
  • The codex tool in codex mcp-server now returns a threadId that can be used with codex-reply.
  • Several issues were fixed: Zellij scrollback handling, unsafe-command prompts on Windows with a read-only sandbox, reporting configuration and rules parsing errors, a macOS proxy-discovery crash, and errors for invalid image uploads.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.80.0

CLIGitHub 원문

AI 요약

  • CLI subprocesses again inherit important environment variables, fixing runtime problems that could cause 10× or greater performance regressions, especially for GPU-related subprocesses.
  • You can now branch a session into a separate thread using new conversation-fork endpoints.
  • Codex now offers elevated-sandbox onboarding, including prompts for upgrading or continuing in degraded mode and an /elevate-sandbox command.
  • In the TUI and TUI2, /review <instructions> now starts the review flow instead of being sent as ordinary text.
  • Other updates add explicit skill invocation through the v2 API, expose requirements for clients, and add observability counters.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.79.0

CLIGitHub 원문

AI 요약

  • Sessions can now spawn or message other conversations, making it possible to coordinate work across multiple conversations.
  • IDE clients can undo the last several turns in a conversation without rewriting its history.
  • Web Search can use cached results only, as an alternative to making live requests.
  • A production policy bypass was closed: CODEX_MANAGED_CONFIG_PATH can no longer override managed configuration in production.
  • Several usability and reliability fixes improve transcript resizing and copy/paste, tolerate extra whitespace in apply_patch markers, and reduce TUI glitches.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.78.0

CLIGitHub 원문

AI 요약

  • You can press Ctrl+G to edit your current prompt in your configured external editor; edits sync back into Codex.
  • Codex can combine project-level .codex/config.toml settings with system configuration. Project-root detection can use configurable markers, and enterprise-managed configuration requirements are supported on macOS through an MDM-provided TOML payload.
  • Multiple tool calls returned by a model in one turn are now handled in the expected format, fixing failures in those cases.
  • The tui2 interface has improved transcript selection, copying, and scrolling, along with fixes for rendering and input edge cases.
  • Windows PowerShell sessions now start in UTF-8 mode to reduce encoding-related prompt and output issues.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.77.0

CLIGitHub 원문

AI 요약

  • The /undo command is fixed so it no longer disrupts Git staging or ghost commits.
  • Mouse-wheel and trackpad scrolling are more consistent across terminals, with new settings to adjust scrolling.
  • Requirements can now specify which sandbox modes are allowed, helping constrain the modes Codex may use.
  • OAuth login for streamable HTTP MCP servers no longer requires the rmcp_client feature flag.
  • File search now uses centralized filename handling to improve the display and consistency of fuzzy search results.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.76.0

CLIGitHub 원문

AI 요약

  • Skills are enabled by default, with support for administrator-scoped skills and short descriptions. The notes do not specify the default behavior on Windows.
  • A model-list interface was added.
  • On UNIX, Codex can now use /etc/codex/requirements.toml.
  • A macOS disk-image (DMG) build target was added.
  • Bug fixes improve pipe access in restricted sandbox tokens and the timing of command-runner directory access.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.75.0

CLIGitHub 원문

공식적으로 정리된 릴리스 노트가 없습니다.

0.74.0

CLIGitHub 원문

AI 요약

  • Codex adds gpt-5.2-codex, a new model with improvements in knowledge, reasoning, and coding.
  • A new /experimental slash command lets you try experimental features.
  • You can now disable ghost snapshot warnings with a toggle.
  • The interface has been polished, including background terminals and a cleaned-up picker.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.73.0

CLIGitHub 원문

AI 요약

  • Codex is less likely to crash when a session contains a tool call with no output.
  • Skills are now discovered through a new shared loading system, for more consistent discovery.
  • Ghost snapshot v2 improves session capture, and ghost commits can now be configured.
  • Codex adds OpenTelemetry tracing, which records tracing data about Codex.
  • Several smaller fixes adjust how the interface responds to bursts of typing, change the default text-wrapping method, and include errors in log messages.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.72.0

CLIGitHub 원문

AI 요약

  • API-key users can now use remote compacting in their sessions.
  • Configuration loading and its API have been cleaned up.
  • The TUI again shows MCP startup progress and uses the latest on-disk values for server status.
  • Windows improvements include more reliable discovery of PowerShell, parsing PowerShell with PowerShell, signing two additional executables, and fixing toasts under WSL 2.
  • Safety and model guidance were updated: the release adds Elevated Sandbox 3 and 4 plus more safe commands, and clarifies gpt-5.2 xhigh reasoning warnings and documentation.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.71.0

CLIGitHub 원문

AI 요약

  • Codex now introduces GPT-5.2, a new frontier model with improvements in knowledge, reasoning, and coding.
  • Learn more about GPT-5.2 in the linked announcement.
  • The notes do not specify further details about these improvements.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.69.0

CLIGitHub 원문

AI 요약

  • When you explicitly select a skill, Codex now adds its SKILL.md content to that turn. Skills load once per session, and Codex warns if it can’t read the file.
  • Configuration handling is more compatible with real config files: config reads are typed, writes preserve comments and ordering, and the model setting can be omitted.
  • Several usability fixes improve navigation and transcripts: vim-style keys work in option selection and the transcript pager, transcript paging continuity is fixed, invalid input no longer opens the slash-command popup, and TUI log files omit ANSI codes.
  • Execution and sandbox changes include shell snapshotting, updated unified-exec events, allowing sendmsg/recvmsg in the Linux sandbox, clearer rate-limit warnings, and request-ID logging.
  • Other additions and fixes include MCP in-session login, review support using remote branches, graceful errors for unsupported images, and a feature-flagged experimental tui2 frontend.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

0.66.0

CLIGitHub 원문

AI 요약

  • Cloud runs now accept a branch name, and you can check their status, inspect changes, and apply them.
  • After approving a command, you can allow its command prefix for future use. If a command is blocked by the sandbox, Codex can suggest a rule change for you to accept. Shell MCP tools follow the same execution rules, and safety checks inspect each part of a command pipeline.
  • Several stability and usability fixes improve command progress display, long-command layout, Windows unified-exec reliability, and cleanup of tool sessions.
  • Keyboard shortcuts for navigating lists and overlays now work consistently across platforms.
  • Patch handling on Windows preserves CRLF line endings, with additional tests covering patch flows.

공식 노트를 바탕으로 AI가 정리했습니다. 원문이 우선합니다.

Radar Ultra
OpenAI와 관련 없는 비공식 도구입니다. 공개 게시물을 정리한 것이며 원본 게시물이 기준입니다.