Skip to content

chore(deps): update ⬆️ mise-packages - #1167

Merged
renovate[bot] merged 2 commits into
mainfrom
renovate/mise-packages
Nov 18, 2026
Merged

renovate[bot] merged 2 commits into
mainfrom
renovate/mise-packages

Conversation

@renovate

@renovate renovate Bot commented Nov 17, 2026 •

Copy link
Copy Markdown
Contributor

This PR contains the following updates:

Package Type Update Change Pending Age Adoption Passing Confidence
aqua:astral-sh/uv tools patch 0.13.7 → 0.13.8 0.13.9 age adoption passing confidence
aqua:atuinsh/atuin tools patch 18.24.6 → 18.24.8 age adoption passing confidence
aqua:cli/cli tools minor 2.103.3 → 2.104.0 2.105.0 age adoption passing confidence
aqua:helm/helm tools patch 4.3.1 → 4.3.2 age adoption passing confidence
aqua:openai/codex tools minor rust-v0.167.2 → rust-v0.169.0 rust-v0.170.0 (+1) age adoption passing confidence
aqua:spacelift-io/spacectl tools minor 1.29.1 → 1.30.0 age adoption passing confidence
aqua:vercel-labs/agent-browser tools minor 0.42.0 → 0.43.0 age adoption passing confidence
droid (source) minor 1.10.0 → 1.12.1 1.14.0 (+2) age adoption passing confidence
github:angristan/fast-resume tools patch v2.14.3 → v2.14.4 age adoption passing confidence
github:anthropics/claude-code tools patch v2.1.322 → v2.1.325 v2.1.327 (+1) age adoption passing confidence
github:backnotprop/plannotator tools patch v0.28.62 → v0.28.64 v0.29.0 (+3) age adoption passing confidence
github:cesarferreira/stax tools minor v0.119.1 → v0.120.0 age adoption passing confidence
github:dlvhdr/gh-dash tools patch v4.26.2 → v4.26.3 age adoption passing confidence
opencode tools minor 2.2.7 → 2.3.0 2.3.2 (+1) age adoption passing confidence

Release notes are maintained in a PR comment by the renovate-release-notes-comment workflow.


Configuration

📅 Schedule: (in timezone America/Los_Angeles)

  • Branch creation
    • Between 03:00 AM and 05:59 AM (* 3-5 * * *)
  • Automerge
    • At any time (no schedule defined)

🚦 Automerge: Enabled.

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

👻 Immortal: This PR will be recreated if closed unmerged. Get config help if that's undesired.


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

This PR was generated by Mend Renovate. View the repository job log.

@renovate
renovate Bot requested a review from scottames as a code owner November 17, 2026 13:16
@renovate
renovate Bot enabled auto-merge (squash) November 17, 2026 13:16
@scottames-github-bot

scottames-github-bot Bot commented Nov 17, 2026 •

Copy link
Copy Markdown
Contributor

Renovate Release Notes

Generated from Renovate's update table by the renovate-release-notes-comment workflow.

Packages that cannot be summarized from GitHub releases are listed explicitly below.

astral-sh/uv (aqua:astral-sh/uv)

0.13.8: 0.13.8

Compare Source

Release Notes

Released on 2026-11-12.

Python

  • Add CPython 3.16.0a2 (#23211)
  • Update managed CPython 3.11, 3.12, 3.13, 3.14, and 3.15 builds to include pip 26.3, zlib 1.4, and Expat 2.10.0 (#23211)
  • Update GraalPy 3.13.0 to build 25.5.5 (#23088)

Preview features

  • Install wheel variants from local paths, direct URLs, and Git repositories in platform-specific resolutions (#22720, #22722, #22724)
  • Detect x86-64 microarchitecture levels and AArch64 architecture versions when selecting wheel variants (#22832, #22949)
  • Detect Google TPUs up when selecting wheel variants (#23066, #23121)
  • Fix CPU detection for wheel variants on macOS with GraalPy (#23089)
  • Report quarantined packages in uv audit when index URLs differ only in redacted query values (#23129)

Performance

  • Avoid duplicate environment builds when concurrent uvx or uv run --with invocations need the same environment (#23123)

Bug fixes

  • Restrict Unix plaintext credential files to owner-only permissions (#23209)
  • Honor per-index exclude-newer-package cutoffs during resolution (#23122)
  • Respect negative extra markers on constraints (#23144)
  • Resolve dependencies of recursive extras from a scoped override (#23210)
  • Fix activate.bat for Windows virtual environments whose paths contain apostrophes (#23152)

Documentation

  • Document the shell requirement for GitLab CI job images (#23078)

Install uv 0.13.8

Install prebuilt binaries via shell script

curl --proto '=https' --tlsv1.2 -LsSf https://releases.astral.sh/github/uv/releases/download/0.13.8/uv-installer.sh | sh

Install prebuilt binaries via powershell script

powershell -ExecutionPolicy Bypass -c "irm https://releases.astral.sh/github/uv/releases/download/0.13.8/uv-installer.ps1 | iex"

Download uv 0.13.8

File Platform Checksum
uv-aarch64-apple-darwin.tar.gz Apple Silicon macOS checksum
uv-x86_64-apple-darwin.tar.gz Intel macOS checksum
uv-aarch64-pc-windows-msvc.zip ARM64 Windows checksum
uv-i686-pc-windows-msvc.zip x86 Windows checksum
uv-x86_64-pc-windows-msvc.zip x64 Windows checksum
uv-aarch64-unknown-linux-gnu.tar.gz ARM64 Linux checksum
uv-i686-unknown-linux-gnu.tar.gz x86 Linux checksum
uv-powerpc64le-unknown-linux-gnu.tar.gz PPC64LE Linux checksum
uv-riscv64gc-unknown-linux-gnu.tar.gz RISCV Linux checksum
uv-s390x-unknown-linux-gnu.tar.gz S390x Linux checksum
uv-x86_64-unknown-linux-gnu.tar.gz x64 Linux checksum
uv-armv7-unknown-linux-gnueabihf.tar.gz ARMv7 Linux checksum
uv-aarch64-unknown-linux-musl.tar.gz ARM64 MUSL Linux checksum
uv-i686-unknown-linux-musl.tar.gz x86 MUSL Linux checksum
uv-riscv64gc-unknown-linux-musl.tar.gz RISCV MUSL Linux checksum
uv-x86_64-unknown-linux-musl.tar.gz x64 MUSL Linux checksum
uv-arm-unknown-linux-musleabihf.tar.gz ARMv6 MUSL Linux (Hardfloat) checksum
uv-armv7-unknown-linux-musleabihf.tar.gz ARMv7 MUSL Linux checksum

Verifying GitHub Artifact Attestations

The artifacts in this release have attestations generated with GitHub Artifact Attestations. These can be verified by using the GitHub CLI:

gh attestation verify <file-path of downloaded artifact> --repo astral-sh/uv

You can also download the attestation from GitHub and verify against that directly:

gh attestation verify <file-path of downloaded artifact> --bundle <file-path of downloaded attestation>
atuinsh/atuin (aqua:atuinsh/atuin)

v18.24.8: 18.24.8

Compare Source

Release Notes

Bug Fixes

  • (release) Build musl artifacts with a musl C++ toolchain for Luau (#4723)

Documentation

  • List the Threads page in the AI section of the nav (#4722)

Features

  • Update whats-new.txt (#4724)

atuin 18.24.8

Install atuin 18.24.8

Install prebuilt binaries via shell script

curl --proto '=https' --tlsv1.2 -LsSf https://github.com/atuinsh/atuin/releases/download/v18.24.8/atuin-installer.sh | sh

Install prebuilt binaries via powershell script

powershell -ExecutionPolicy Bypass -c "irm https://github.com/atuinsh/atuin/releases/download/v18.24.8/atuin-installer.ps1 | iex"

Download atuin 18.24.8

File Platform Checksum
atuin-aarch64-apple-darwin.tar.gz Apple Silicon macOS checksum
atuin-x86_64-apple-darwin.tar.gz Intel macOS checksum
atuin-x86_64-pc-windows-msvc.zip x64 Windows checksum
atuin-x86_64-pc-windows-msvc.msi x64 Windows checksum
atuin-aarch64-unknown-linux-gnu.tar.gz ARM64 Linux checksum
atuin-x86_64-unknown-linux-gnu.tar.gz x64 Linux checksum
atuin-aarch64-unknown-linux-musl.tar.gz ARM64 MUSL Linux checksum
atuin-x86_64-unknown-linux-musl.tar.gz x64 MUSL Linux checksum

Verifying GitHub Artifact Attestations

The artifacts in this release have attestations generated with GitHub Artifact Attestations. These can be verified by using the GitHub CLI:

gh attestation verify <file-path of downloaded artifact> --repo atuinsh/atuin

You can also download the attestation from GitHub and verify against that directly:

gh attestation verify <file-path of downloaded artifact> --bundle <file-path of downloaded attestation>

atuin-server 18.24.8

Install atuin-server 18.24.8

Install prebuilt binaries via shell script

curl --proto '=https' --tlsv1.2 -LsSf https://github.com/atuinsh/atuin/releases/download/v18.24.8/atuin-server-installer.sh | sh

Install prebuilt binaries via powershell script

powershell -ExecutionPolicy Bypass -c "irm https://github.com/atuinsh/atuin/releases/download/v18.24.8/atuin-server-installer.ps1 | iex"

Download atuin-server 18.24.8

File Platform Checksum
atuin-server-aarch64-apple-darwin.tar.gz Apple Silicon macOS checksum
atuin-server-x86_64-apple-darwin.tar.gz Intel macOS checksum
atuin-server-x86_64-pc-windows-msvc.zip x64 Windows checksum
atuin-server-aarch64-unknown-linux-gnu.tar.gz ARM64 Linux checksum
atuin-server-x86_64-unknown-linux-gnu.tar.gz x64 Linux checksum
atuin-server-aarch64-unknown-linux-musl.tar.gz ARM64 MUSL Linux checksum
atuin-server-x86_64-unknown-linux-musl.tar.gz x64 MUSL Linux checksum

Verifying GitHub Artifact Attestations

The artifacts in this release have attestations generated with GitHub Artifact Attestations. These can be verified by using the GitHub CLI:

gh attestation verify <file-path of downloaded artifact> --repo atuinsh/atuin

You can also download the attestation from GitHub and verify against that directly:

gh attestation verify <file-path of downloaded artifact> --bundle <file-path of downloaded attestation>
cli/cli (aqua:cli/cli)

v2.104.0: GitHub CLI 2.104.0

Compare Source

Protect private forks when deleting repositories

gh repo delete now warns when deleting a private or internal repository will also delete its forks. The additional confirmation is required even with --yes.

Non-interactive workflows and agents must explicitly accept the cascading deletion:

gh repo delete OWNER/REPO --yes --accept-cascading-deletion-of-private-forks

What's Changed

✨ Features

  • Require confirmation before gh repo delete deletes private forks by @​BagToad in #14858

🐛 Fixes

  • fix(auth status): surface underlying rate-limit, server, and network errors in terminal output by @​babakks and @​Copilot in #15009
  • fix(auth): skip token refresh when gh's state directory is not writable by @​babakks in #14845

📚 Docs & Chores

  • Use REST to apply issue triage labels by @​BagToad in #15041
  • Prevent repeated Dependabot triage assessments by @​BagToad in #15002
  • Apply issue triage labels directly by @​BagToad in #15001
  • Provide verified build versions to issue triage by @​BagToad in #15000
  • Use a synthetic namespace for triage fixtures by @​BagToad in #14976
  • Remove the accidental issue-triage model pin by @​BagToad in #14972
  • Add a fake GitHub API runner for reproductions by @​BagToad in #14951
  • Clarify which hosts use GH_ENTERPRISE_TOKEN by @​BagToad in #14918
  • Regenerate triage workflows with gh-aw v1.0.1 by @​tidy-dev in #14910
  • Test the ShowRefs option separator by @​BagToad in #14879
  • Fix local extension-install test path normalization by @​bobrik in #14854
  • Save Go caches only from trunk by @​williammartin in #14840
  • Add a private vulnerability report form by @​BagToad in #14825
  • Replace msgpack with a minimal node ID encoder by @​tj-smith47 in #14801
  • Test the Git client with real repositories by @​williammartin in #14348

:dependabot: Dependencies

  • chore(deps): bump github.com/klauspost/compress from 1.20.3 to 1.20.4 by @​dependabot in #15040
  • chore(deps): bump charm.land/lipgloss/v2 from 2.0.6 to 2.1.0 by @​dependabot in #15039
  • chore(deps): bump Go toolchain from 1.27.3 to 1.27.4 by @​github-actions[bot] in #15028
  • chore(deps): bump golang.org/x/sys from 0.49.0 to 0.50.0 by @​dependabot in #15010
  • chore(deps): bump golang.org/x/sync from 0.24.0 to 0.25.0 by @​dependabot in #14998
  • chore(deps): bump the codeql-actions group across 1 directory with 3 updates by @​dependabot in #14964
  • chore(deps): bump github.com/spf13/pflag from 1.0.10 to 1.1.0 by @​dependabot in #14963
  • chore(deps): bump github.com/yuin/goldmark from 1.8.6 to 1.8.7 by @​dependabot in #14907
  • chore(deps): bump charm.land/bubbletea/v2 from 2.1.0 to 2.1.1 by @​dependabot in #14906
  • chore(deps): bump github.com/sigstore/sigstore-go from 1.3.0 to 1.4.0 by @​dependabot in #14905
  • chore(deps): bump google.golang.org/grpc from 1.84.0 to 1.85.0 by @​dependabot in #14878
  • chore(deps): bump the codeql-actions group with 3 updates by @​dependabot in #14824

New Contributors

Full Changelog: cli/cli@v2.103.3...v2.104.0

helm/helm (aqua:helm/helm)

v4.3.2: Helm v4.3.2

Compare Source

Helm v4.3.2 is a patch release. Users are encouraged to upgrade for the best experience.

The community keeps growing, and we'd love to see you there!

  • Join the discussion in Kubernetes Slack:
    • for questions and just to hang out
    • for discussing PRs, code, and bugs
  • Hang out at the Public Developer Call: Thursday, 9:30 Pacific via Zoom
  • Test, debug, and contribute charts: ArtifactHub/packages

Notable Changes

  • docs(cmd): correct list --max and HELM_COLOR help text #32807 by @​ZainnQureshii
  • fix(registry): always return a transport Helm can configure #32684 by @​ump45nose

Installation and Upgrading

Download Helm v4.3.2. The common platform binaries are here:

This release was signed with 208D D36E D5BB 3745 A167 43A4 C7C6 FBB5 B91C 1155 and can be found at @​scottrigby keybase account. Please use the attached signatures for verifying this release using gpg.

The Quickstart Guide will get you going from there. For upgrade instructions or detailed installation notes, check the install guide. You can also use a script to install on any system with bash.

What's Next

  • 4.3.3 is the next patch releases scheduled for December 9, 2026
  • 4.4.0 is the next minor release scheduled for January 13, 2027. There will be no further Helm 3 minor releases (see https://helm.sh/blog/helm-v3-end-of-life)

Changelog

  • fix(deps): bump golang.org/x/net to v0.62.0 (#32876) 8346aaa55e7161f7c547212d0a87f01367976727 (Sean Schneeweiss)
  • chore(deps): bump github.com/distribution/distribution/v3 (#32698) 8c92fcacf2865996287118d742783bf9335c8fe0 (dependabot[bot])
  • fix(deps): bump github.com/klauspost/compress to v1.20.3 (#32878) 214f6f6be7ae5b1d1b32335f3c7f2c1749caad95 (Sean Schneeweiss)
  • chore(deps): bump the k8s-io group across 1 directory with 7 updates 90d48fc1d2ffef1d9b220cb2811bc6bbead73a66 (dependabot[bot])
  • fix(registry): always return a transport Helm can configure (#32684) 961bddf9d52f0b8586f751ee130322204e708907 (ump45nose)
  • docs(cmd): correct list --max and HELM_COLOR help text (#32807) ddb8be775170081fe6ad1c39a6e29cf64e61ef80 (Zain Qureshi)
openai/codex (aqua:openai/codex)

rust-v0.169.0: 0.169.0

Compare Source

New Features

  • The opt-in terminal workspace supports multiple side-chat tabs. Switch between them with the keyboard or mouse, and reopen saved local side chats after restarting Codex. (#59784, #60152, #60181)
  • Search older tasks from the agent command center by name, prompt preview, or working directory. (#60286)
  • Turn on Collapse turn details in the full-screen transcript to fold completed activity beneath each prompt while keeping answers visible and tool output searchable. (#60554, #60555, #60556, #60557)
  • Add or edit custom model providers from the terminal. With custom gateway onboarding enabled, you can create a provider during sign-in and use a device code for supported gateways over SSH or without a local browser. (#59779, #60009, #60186, #60486, #60662)
  • Press Ctrl+S in the terminal report editor to save a diagnostic ZIP locally, even when uploads are disabled. (#60542)
  • With the opt-in Cloud connection on macOS and Linux, send images, choose a model and reasoning effort, and archive or restore Cloud conversations from the terminal. (#59828, #60061, #60635, #60651)

Bug Fixes

  • codex exec keeps project configuration and MCP servers disabled in untrusted directories, even with --sandbox workspace-write. Use --trust with codex exec or codex review to explicitly save project trust. (#60041)
  • Yes, clear context and implement now hands the full approved plan to the fresh session and keeps the current session open if the handoff fails. (#60763)
  • Fixed Windows sandbox handling for quoted cmd.exe paths and for PowerShell sessions whose working directory has an unreadable parent. (#60624, #60647)
  • Pasted images on macOS retain their intended orientation and use native PNG or JPEG clipboard data when available. (#60455)
  • The terminal no longer stays busy waiting for MCP servers that a shared app server did not report. (#60280, #60622)
  • Interrupted turns now close cleanly, and delayed aborts or file approval cancellations no longer interrupt a later turn. (#59910, #60700)

Documentation

  • Updated the openai-docs skill to focus on Codex and ChatGPT Work questions and first-time API setup, with dedicated guidance for configuring Codex across a team. (#59944, #59949)
  • Documented how app-server clients can list models or authorize a gateway for a configured provider without changing the default provider. (#59776, #59819)

Chores

  • Updated bundled SQLite to 3.54 to pick up write-ahead log fixes. (#60432)
  • Plugin marketplace upgrades can reuse Git objects already on disk, reducing repeat downloads. (#60528)

Changelog

Full Changelog: openai/codex@rust-v0.168.0...rust-v0.169.0

  • #59739 Add a sidebar chooser and floating workspace shortcut panels @​fcoury-oai
  • #59743 Forward explicit cyber access programs with header authentication @​jamy-OAI
  • #59745 Repair legacy Windows sandbox bin permissions for SYSTEM @​zm-oai
  • #59746 Add typed Cloud user-message submission receipts @​bc-openai
  • #59749 Use runtime authentication for OpenAI MCP and app requests @​cooper-oai
  • #59750 Stop Noise relay recovery on rejected executor credentials @​richardopenai
  • #59752 Configure the Opus Bazel patch and isolate auth tests @​bkotsopoulos
  • #59754 Enforce host-required cyber access programs per thread @​jamy-OAI
  • #59759 Update WebSocket dependency forks @​charliemarsh-oai
  • #59767 Add sidebar tabs and nonblocking side-chat creation @​fcoury-oai
  • #59768 Stop prefetching plugin discovery at app-server startup @​zamoshchin-openai
  • #59769 Reuse decoded WebSocket event kinds in telemetry @​charliemarsh-oai
  • #59770 Add shared service-tier support for host-owned agents @​rhan-oai
  • #59772 Remove the legacy sandbox policy constructor @​ioanbudea-OAI
  • #59774 Remove the legacy Seatbelt command wrapper @​ioanbudea-OAI
  • #59776 Allow selecting a configured provider in model/list @​abhinav-oai
  • #59778 Expose acceptance metadata and code-cell links in rollout traces @​tz-openai
  • #59779 Add provider configuration editing to the TUI @​alexsong-oai
  • #59780 Enable safe identical code folding for x86-64 musl releases @​dkovalenko-oai
  • #59783 Tie gRPC code-mode connection lifetime to live sessions @​frantic-openai
  • #59784 Support multiple side chats in the TUI sidebar @​fcoury-oai
  • #59785 Decouple message lifecycle state from model-visible item IDs @​euroelessar
  • #59787 Support credential export commands for gateway authentication @​alexsong-oai
  • #59789 Render delegated thread messages as Markdown in the TUI @​bc-openai
  • #59792 Centralize managed proxy preparation and sandbox routing @​viyatb-oai
  • #59793 Support update-boundary paging across forked thread histories @​owenlin0
  • #59794 Check extension budgets before model generation requests @​rhan-oai
  • #59795 Support optional thread IDs in hosted file uploads @​lt-oai
  • #59805 Pack relative relocations in x86-64 musl release builds @​dkovalenko-oai
  • #59816 Retry gateway credential exports after unauthorized responses @​alexsong-oai
  • #59817 Handle TUI message submission receipts and preserve uncertain drafts @​bc-openai
  • #59819 Allow provider selection for gateway OAuth reads and logins @​abhinav-oai
  • #59822 Add device-code authorization for gateway OAuth @​smurching-oai
  • #59823 Bind runtime auth to the provider's selected credential source @​cooper-oai
  • #59824 Enable resizing the sidebar chooser @​fcoury-oai
  • #59826 Preserve client metadata through queued submissions @​eddie-openai
  • #59828 Add a gated Cloud backend to the TUI @​bc-openai
  • #59832 Add opt-in incremental tools for regular OpenAI Responses @​akira-oai
  • #59842 Carry targeted moderation decisions on final-answer messages @​psachdeva-oai
  • #59887 Remove incomplete prereleases after asset upload failures @​jif-oai
  • #59891 Bound REPL provenance costs in elastic context preparation @​jif-oai
  • #59893 Recompute the approval reviewer when switching models @​jif-oai
  • #59902 Keep verified question/answer records whole under elastic budgets @​jif-oai
  • #59903 Delete incomplete prereleases by release ID @​jif-oai
  • #59905 Validate implicit API keys for Guardian Decisions @​jif-oai
  • #59908 Avoid full image decoding for original-detail context estimates @​jif-oai
  • #59910 Scope file change approval cancellation to the requesting turn @​jif-oai
  • #59913 Resolve Guardian policy from the reviewed thread's catalog @​jif-oai
  • #59914 Bind Guardian Decisions requests to their credential source @​jif-oai
  • #59928 Improve sidebar chat selection and tab hover highlighting @​fcoury-oai
  • #59933 Use permission profiles for protected-model startup downgrades @​ioanbudea-OAI
  • #59944 Narrow openai-docs to product Q&A and first-time API setup @​provencher-oai
  • #59949 Route broad Codex setup questions through self-knowledge guidance @​vb-openai
  • #59954 Resolve skill display names in read and installations tools @​jif-oai
  • #59955 Bump ignore to 0.4.30 @​iceweasel-oai
  • #59958 Expose model metadata from each thread's catalog and settings @​seanh-oai
  • #59960 Skip the network denial grace period when remote decisions drain @​jif-oai
  • #59963 Normalize turn context permissions to a required profile @​ioanbudea-OAI
  • #59969 Reduce contention in thread writer lock coordination @​dkovalenko-oai
  • #59972 Fix Opus header installation with relative symlink inputs @​bc-openai
  • #59973 Enable gRPC and host output truncation by default for Code Mode @​seanh-oai
  • #59974 Test command completion before network denial grace expires @​jif-oai
  • #59980 Test rejection of PNGs with readable dimensions but corrupt pixels @​fjord-oai
  • #59983 Render typed prompts as Markdown in the TUI @​bc-openai
  • #59987 Resolve startup models using thread creation options @​seanh-oai
  • #59988 Add inherited styling to TUI display trees @​joesavona
  • #59991 Preserve app invocation context across MCP tool refreshes @​fahad-OAI
  • #59993 Add fixed read views for local message boards @​felixxia-oai
  • #59994 Add read-only evidence retrieval tools for Guardian reviewers @​felixxia-oai
  • #59995 Add subscription tools for Guardian reviewers @​felixxia-oai
  • #59998 Add atomic bulk channel subscription updates @​felixxia-oai
  • #59999 Add model-driven Guardian channel selection @​felixxia-oai
  • #60000 Plan Guardian evidence delivery in source order @​felixxia-oai
  • #60001 Add bounded original-evidence delivery for Guardian reviewers @​felixxia-oai
  • #60002 Decouple Guardian retrieval from local message-board handles @​felixxia-oai
  • #60003 Apply runtime authentication to realtime connections @​cooper-oai
  • #60004 Expose ChatGPT user IDs in account/read responses @​dand-oai
  • #60006 Reduce SQLite write overhead for thread activity and history @​jonluca
  • #60007 Start cloud threads with the local GitHub project @​bc-openai
  • #60008 Refactor TUI clipboard and composer input handling @​bc-openai
  • #60009 Add custom gateway selection to TUI sign-in @​alexsong-oai
  • #60010 Add a shared Windows Bazel setup action @​dkovalenko-oai
  • #60011 Adapt multi-agent mode guidance for hosted tools @​rhan-oai
  • #60014 Honor managed runtime authentication modes and expand coverage @​cooper-oai
  • #60017 Disable bundled skills in the prompt-prefix comparison test @​felixxia-oai
  • #60018 Propagate turn triggers to usage analytics events @​chrisdong-oai
  • #60019 Add theme-aware semantic colors to extension UI trees @​joesavona
  • #60020 Strip terminal commands from UI tree strings @​joesavona
  • #60021 Normalize inline UI tree text across styled leaves @​joesavona
  • #60022 Separate UI tree preparation from line rendering @​joesavona
  • #60026 Add multiline layout and row wrapping to UI trees @​joesavona
  • #60027 Keep configured status lines on the native renderer @​joesavona
  • #60028 Reuse prepared UI trees for footer rendering @​joesavona
  • #60029 Render UI trees directly into terminal buffers @​joesavona
  • #60031 Unify TUI status line layout for extension content @​joesavona
  • #60032 Allow extension status content to use multiple footer rows @​joesavona
  • #60034 Omit sensitive process inputs from spawn trace logs @​etraut-openai
  • #60035 Fix authentication for git-attribution settings requests @​cooper-oai
  • #60037 Preserve MCP sharing discovery when deferring cached stdio startup @​charliemarsh-oai
  • #60038 Surface MCP server startup errors when preparing cached tool calls @​charliemarsh-oai
  • #60039 Add opt-in lazy startup for cached stdio MCP servers @​charliemarsh-oai
  • #60040 Restrict legacy incremental tools to Amazon Bedrock providers @​akira-oai
  • #60041 Require explicit project trust in non-interactive runs @​etraut-openai
  • #60042 Centralize Windows sandbox filesystem override resolution @​viyatb-oai
  • #60046 Derive MCP network policy and preserve saved denials @​viyatb-oai
  • #60048 Allow plugin starter prompts up to 512 characters @​karenwong-openai
  • #60049 Preserve model catalogs when starting child agents @​evanz-oai
  • #60055 Reauthenticate runtime requests before reusing WebSocket access @​cooper-oai
  • #60061 Support Cloud image messages and editable draft handoffs @​bc-openai
  • #60064 Use thread runtime auth for Guardian Decisions and memory quota checks @​cooper-oai
  • #60067 Ensure side-chat policy reaches the first model request @​fcoury-oai
  • #60073 Use runtime authentication for remote-control requests @​cooper-oai
  • #60075 Support asynchronous host service-tier reads and acceptance @​rhan-oai
  • #60080 Allow asynchronous model request budget checks @​rhan-oai
  • #60082 Fetch account security reminders through app-server @​cooper-oai
  • #60096 Stop retrying terminal runtime authentication denials @​cooper-oai
  • #60101 Use runtime authentication for Analytics requests @​cooper-oai
  • #60118 Buffer payload JSON reads during rollout trace replay @​tz-openai
  • #60122 Preserve code mode dispatch errors in rollout traces @​tz-openai
  • #60152 Persist local workspace side chats and add tab close controls @​fcoury-oai
  • #60157 Add support for incremental code mode tool definitions @​akira-oai
  • #60163 Wire incremental exec tool updates into Code Mode sessions @​akira-oai
  • #60172 Preserve display instructions in answer moderation @​psachdeva-oai
  • #60173 Test exec catalog preservation across session and compaction changes @​akira-oai
  • #60177 Add metrics for incremental exec catalog updates @​akira-oai
  • #60180 Attach typed punctuation to completed skill mentions @​bc-openai
  • #60181 Add keyboard and mouse navigation for sidebar tabs @​fcoury-oai
  • #60186 Allow creating custom providers during sign-in @​alexsong-oai
  • #60188 Allow model overrides for incremental Code Mode tool messages @​akira-oai
  • #60190 Expose agent tree IDs and environment removal @​richardopenai
  • #60206 Increase Bazel core unit test shards from 8 to 16 @​seanh-oai
  • #60270 Warn when a CLI model is absent from the ChatGPT model list @​etraut-openai
  • #60271 Keep the agents overview open when there is no chat to return to @​etraut-openai
  • #60280 Fix MCP startup tracking when attaching to shared app servers @​charliemarsh-oai
  • #60286 Search task history from the command center @​etraut-openai
  • #60309 Defer executor readiness when prewarming a selected project @​bc-openai
  • #60319 Improve side-chat discovery and navigation in the TUI @​fcoury-oai
  • #60320 Include older itemless Cloud failures in full transcripts @​bc-openai
  • #60327 Suppress stale cloud stream disconnects after reopening a thread @​bc-openai
  • #60335 Avoid duplicate assistant messages when resuming Cloud threads @​bc-openai
  • #60342 Treat goal objectives as untrusted context @​dylan-hurd-oai
  • #60389 Include Codex Apps configuration in cloud prewarm requests @​bc-openai
  • #60390 Allow deferring plain-text MCP output in thread item listings @​btraut-openai
  • #60391 Simplify Guardian's post-denial approval guidance @​olliem-oai
  • #60414 Enable model catalog discovery with gateway OAuth @​smurching-oai
  • #60416 Keep fitting URLs intact in fullscreen Markdown transcripts @​etraut-openai
  • #60418 Let terminal status become done while background terminals run @​etraut-openai
  • #60423 Expose deferred MCP servers in resource listings @​charliemarsh-oai
  • #60432 Upgrade bundled SQLite to 3.54 for WAL fixes @​ioanbudea-OAI
  • #60433 Bind API workload identity source reuse to session claims @​cooper-oai
  • #60434 Reset app-server turn summaries when a turn starts @​cooper-oai
  • #60435 Dismiss the model switch prompt when account usage recovers @​etraut-openai
  • #60436 Revalidate request auth ownership after budget checks @​won-openai
  • #60443 Support cancellation and deadlines for realtime attachments @​parabolala
  • #60454 Update OpenSSL Rust dependencies @​dkovalenko-oai
  • #60455 Prefer native clipboard images on macOS and honor image orientation @​dkovalenko-oai
  • #60461 Honor permission grant scopes in executor capability discovery @​dkovalenko-oai
  • #60462 Route TUI question answers through Cloud message admission @​bc-openai
  • #60466 Keep thread storage available when diagnostic logs fail @​dkovalenko-oai
  • #60472 Serialize default thread permissions as a permission profile @​ioanbudea-OAI
  • #60473 Respect error retry policy during local compaction @​charliemarsh-oai
  • #60475 Stop retrying explicit invalid-workspace errors @​charliemarsh-oai
  • #60476 Treat access program denials as terminal errors @​charliemarsh-oai
  • #60479 Treat content policy violations as terminal errors @​charliemarsh-oai
  • #60480 Treat workspace access denials as terminal errors @​charliemarsh-oai
  • #60481 Treat invalid access program stream errors as terminal @​charliemarsh-oai
  • #60482 Handle context length errors consistently across response transports @​charliemarsh-oai
  • #60486 Add device authorization to app-server gateway OAuth @​smurching-oai
  • #60487 Enable untrusted context tool outputs by default @​akira-oai
  • #60488 Remove the Xcode 26.4 MCP elicitation compatibility workaround @​jameswt-oai
  • #60489 Honor feature overrides when starting the app-server daemon @​iceweasel-oai
  • #60492 Add local-only Claude Code skill migration @​aramaraju-oai
  • #60496 Preserve typed gRPC code-mode session admission errors @​seanh-oai
  • #60498 Unify Guardian context preparation across reviewers @​ioanbudea-OAI
  • #60500 Derive sandbox telemetry labels directly from permission profiles @​ioanbudea-OAI
  • #60505 Trace MCP refresh causes and plugin metadata changes @​charliemarsh-oai
  • #60506 Preserve MCP trace context when tracing is disabled @​joesavona
  • #60507 Use hermetic LLVM for Windows MSVC Bazel builds @​zbarsky-openai
  • #60511 Treat inference hook denials as terminal errors @​ccui-oai
  • #60513 Record an MCP refresh reason for session permission grants @​charliemarsh-oai
  • #60517 Route sandbox CLI launches through the shared sandbox manager @​viyatb-oai
  • #60519 Handle unfinished tool calls in restored history @​etraut-openai
  • #60522 Fragment large Responses WebSocket messages into bounded frames @​charliemarsh-oai
  • #60523 Add policy-checked TCP upstream tunneling for SOCKS @​viyatb-oai
  • #60524 Encapsulate thread metadata construction @​ioanbudea-OAI
  • #60525 Preserve first-party catalog display order in app-server model lists @​dpatel-oai
  • #60526 Disable Daybreak when the selected model lacks access @​jamy-OAI
  • #60528 Reuse installed Git objects when upgrading marketplaces @​charliemarsh-oai
  • #60542 Add local diagnostic ZIP saves to the TUI @​smurching-oai
  • #60554 Add optional tool call summaries to the full-screen transcript @​etraut-openai
  • #60555 Extend output-free transcript summaries to more tools @​etraut-openai
  • #60556 Group consecutive tool calls in the full-screen conversation @​etraut-openai
  • #60557 Collapse completed turn activity beneath transcript prompts @​etraut-openai
  • #60558 Discard opening prompts when side chat creation fails @​etraut-openai
  • #60559 Preserve inherited previews for paginated thread forks @​etraut-openai
  • #60560 Avoid periodic wakeups in idle Windows file watchers @​chess-oai
  • #60568 Add an OpenSSH ProxyCommand mode to codex tcp-tunnel @​apanasenko-oai
  • #60574 Allow searching persisted attached threads @​btraut-openai
  • #60578 Add published OAuth metadata discovery to the RMCP client @​vishnu-oai
  • #60599 Keep the TUI responsive while opening saved side chats @​fcoury-oai
  • #60613 Clarify safety recourse messaging and add a reporting option @​xiaohk
  • #60617 Support incremental tool declarations on GCP @​akira-oai
  • #60620 Allow sampling in-progress turns with thread/sample @​keyz
  • #60622 Use app-server MCP configuration and startup events in the TUI @​etraut-openai
  • #60624 Preserve script quotes in Windows sandbox cmd invocations @​malsamiri-oai
  • #60635 Support archiving and restoring cloud threads @​bc-openai
  • #60637 Show pending key chords in a shared floating shortcut guide @​fcoury-oai
  • #60638 Honor read-only MCP tool hints in automatic approval @​cazhang-oai
  • #60639 Refresh Apps tools outside the MCP runtime gate @​dkovalenko-oai
  • #60644 Keep interrupts responsive during host service-tier updates @​rhan-oai
  • #60645 Update the safety consent test for the current dialog @​ambrosino-oai
  • #60646 Use trusted Guardian templates for managed policies @​won-openai
  • #60647 Restore PowerShell's working directory in the MXC sandbox @​zm-oai
  • #60651 Enable model and reasoning effort selection for Cloud conversations @​bc-openai
  • #60655 Support environment updates in app-server settings APIs @​sayan-oai
  • #60662 Support gateway device-code sign-in in headless TUI sessions @​smurching-oai
  • #60663 Defer exec-server sandbox preparation to the execution host @​viyatb-oai
  • #60665 Add a content helper for forwarding MCP blocks in Code Mode @​cconger
  • #60669 Skip submodule worktree scans when checking repository changes @​dhavalkapil-oai
  • #60670 Initialize Guardian evidence cursors from thread history state @​felixxia-oai
  • #60671 Add sign-only mode and tighten macOS signing verification @​tarunoai
  • #60673 Preserve agent message deliveries in rollout traces @​cassirer-openai
  • #60675 Avoid redundant reads and screen clears when switching side chats @​fcoury-oai
  • #60680 Keep TUI status content separate from composer hints @​joesavona
  • #60681 Prioritize draft space when allocating composer footer rows @​joesavona
  • #60682 Wrap built-in TUI status lines within the footer row budget @​joesavona
  • #60683 Fit composer footer hints to available terminal space @​joesavona
  • #60695 Add a Signer Service backend for macOS notarization @​tarunoai
  • #60697 Limit MCP product attribution to configured REPL-backed calls @​trpcic-openai
  • #60700 Finalize aborted turns and ignore unrelated late aborts @​etraut-openai
  • #60702 Centralize permission config selection and legacy translation @​ioanbudea-OAI
  • #60708 Canonicalize Windows sandbox homes and migrate saved junction paths @​zm-oai
  • #60721 Gate plugin recommendation cache warming on feature flags @​adaley-openai
  • #60730 Apply session app overrides during MCP config refresh @​jameswt-oai
  • #60732 Allow model-facing ID sequences to resume from allocated IDs @​euroelessar
  • #60735 Preserve file-backed audio in tool outputs @​hung-oai
  • #60746 Add a Git credential helper for existing Codex logins @​ccy-oai
  • #60748 Label seed arguments in the model-facing ID recovery test @​bc-openai
  • #60749 Capture saved Daybreak preferences for native helpers @​jamy-OAI
  • #60753 Add snapshot coverage for history and notes tool contracts @​euroelessar
  • #60757 Use typed context window IDs throughout thread persistence @​euroelessar
  • #60759 Fix Unicode caseless matching in thread search @​etraut-openai
  • #60763 Hand off approved plans through attachments in fresh sessions @​dylan-hurd-oai
spacelift-io/spacectl (aqua:spacelift-io/spacectl)

v1.30.0: v1.30.0

Compare Source

What's Changed

Full Changelog: spacelift-io/spacectl@v1.29.1...v1.30.0

Artifacts

Binaries

The binaries are available at the bottom of this release.

Docker images

The following multi-arch (amd64 and arm64) Docker images have been published:

  • ghcr.io/spacelift-io/spacectl:latest
  • ghcr.io/spacelift-io/spacectl:1.30.0
vercel-labs/agent-browser (aqua:vercel-labs/agent-browser)

v0.43.0: v0.43.0

Compare Source

New Features

  • Added snapshot hints for controls whose accessible name is empty or shared with another ref in the same snapshot. The hint follows the ref and lists the control's icon, image file, data-testid, name or id, and the text of the nearest row or list item (#2578)
  • Added a Modern Web Guidance skill that retrieves Chrome's guidance for a task and checks the built page in agent-browser (#2577)

Bug Fixes

  • Fixed commands on closed tabs waiting for the timeout. A command whose tab closes before Chrome answers now fails with Target closed: CDP session <id> detached (#2576)
  • Fixed recordings with an emulated device scale, which now capture at full density by switching to screenshots when a screencast frame is below the page's scale (#2572)

Improvements

  • Native binaries now ship as per-platform packages, so an install downloads only the binary for the host platform, and the global command links to it when install scripts are blocked (#2150)
  • Snapshots of large pages parse the accessibility tree once, so they finish sooner (#2509)

Documentation

  • Added a Modern Web Guidance guide to the docs (#2546, #2573, #2575)

Contributors

  • @​ctate
  • @​lahfir
  • @​shuding
angristan/fast-resume (github:angristan/fast-resume)

v2.14.4: v2.14.4

Compare Source

2.14.4 (2026-11-13)

Performance Improvements

  • vibe: skip hidden sessions before loading history (#111) (a7df5a5)

@scottames-github-bot

scottames-github-bot Bot commented Nov 17, 2026 •

Copy link
Copy Markdown
Contributor
anthropics/claude-code (github:anthropics/claude-code) - part 1 of 2

v2.1.325: v2.1.325

Compare Source

What's changed

  • Fixed a security issue in how zstd-compressed responses are decoded
  • Added a spinner tip in VS Code and similar integrated terminals about re-running a notebook cell, shown once Claude has read or edited a Jupyter notebook
  • Added a line under the error shown when your organization's policy blocks a request, saying how to continue: run /rewind and change the message, or run /clear
  • Added a note for Claude when a sandboxed git checkout, git stash or autostash pull cannot update protected files such as those in .claude
  • Fixed /security-review and skills' inline git commands stopping with an error in worktrees of bare repositories, --separate-git-dir checkouts and Android repo checkouts
  • Fixed subagents with their own model being moved to the plan-mode model when the model setting is opusplan or haiku
  • Fixed subagents on a different model sizing file reads and MCP results with the main session's model
  • Fixed sessions on many third-party gateways and Foundry stopping with a context length error on every turn instead of compacting
  • Fixed recent turns sometimes going missing from a resumed session after Claude Code stopped without a clean exit
  • Fixed shell commands running in the launch directory after the working directory was deleted; the command now fails with a message and can be re-issued
  • Fixed an approved plan edit being lost when the plansDirectory folder can't take it: the plan is now saved in the default plans folder, and a warning says where and why
  • Fixed a saved sonnet[1m] model setting being rewritten on a new install to a model id the API rejects
  • Fixed focus view hiding the reply to your prompt when a scheduled task replied after it
  • Fixed the prompt sometimes missing from a background subagent's view when fullscreen is off
  • Fixed long options in lists and permission prompts being partly overwritten when they wrap, and first-run screens losing lines on narrow terminals
  • Fixed startup warnings about permission rules and the "N MCP servers need authentication" notice being recorded as seen when they were scrolled out of view
  • Fixed the welcome header showing control characters or splitting across lines when an agent's name or the working folder contains them or a line break
  • Fixed the red error shown when Claude tries a command only you can run: a dim line now says it runs only when you type it at the prompt
  • Fixed /stats showing an Active days total that was one day too high
  • Fixed /insights saying a report was ready when no session qualified for analysis, and writing two values into its HTML report without escaping them
  • Fixed /voice saying voice mode changed when managed settings, --settings, or the project's .claude/settings.json or .claude/settings.local.json kept it as it was; it now says what holds it
  • Fixed the IDE welcome dialog showing Cmd+Esc for Quick Launch on Windows and Linux
  • Fixed Slack app tips showing when your organization's policy denies cloud sessions
  • Fixed claude purge hanging silently when there is no terminal to read keys from, and its project picker and -i prompts ignoring the keyboard when stdin is piped
  • Fixed claude plugin eval --output-dir '' writing the report into the current folder; it now exits with an error
  • Fixed claude -p text output on a terminal passing control sequences other than text styling; pipes and files are unchanged
  • Fixed leftover .oauth_refresh.lock.owner.tmp.* files piling up in the config directory
  • Fixed /fast saying "Fast mode has been disabled by your organization" under the keyless Console sign-in, where Claude Code had not asked the server
  • Fixed /model saying that your organization restricts a model when Claude Code could not check that, for example with no network
  • Fixed "Sign in with your Console account" in /login replacing your existing login when you pressed Esc right after the browser step
  • Fixed the browser showing the sign-in success page in some cases where sign-in failed or was canceled
  • Fixed claude auth status and other short commands leaving a lock behind on a Console profile, which made the next session hang for about a minute
  • Fixed background sessions started on your claude.ai login using (and billing) an API key or token from the shell that started the background service
  • Fixed more cases of a session moving to another sign-in in the background; these moves are now refused, with a message saying what works
  • Fixed a second Enter in the exit dialog stopping background work after the move to the background was refused
  • Fixed token counting on Amazon Bedrock sending the conversation to Bedrock when the allowedProviders managed setting does not allow it
  • Fixed AWS credential_process helpers and Google Cloud default credentials failing when Claude Code is started without a HOME environment variable
  • Fixed a session sometimes going back to an earlier permission mode after a subagent's plan was approved
  • Fixed one invalid value in an Agent SDK applyFlagSettings() call silently discarding all settings from earlier calls; a call that would do this is now refused with an error
  • Fixed sessions showing as waiting for input when a finished pull request only needed your own review or merge
  • Fixed an unrecognized teammateMode settings value being ignored without a warning: claude -p, the startup warning and claude doctor now list it as a skipped entry (still not applied)
  • Fixed --worktree skipping a WorktreeCreate hook from a plugin in CLAUDE_CODE_PLUGIN_SEED_DIR on the first run in a new home directory
  • Fixed brief-mode sessions, such as Dispatch, sending a reply again after the turn had already replied
  • Fixed Claude saying a working Atlassian, Asana or Sentry connector had failed in cloud sessions when a plugin listed it at a different URL
  • Fixed Claude Desktop and SDK sessions listing a folder's own MCP servers (.mcp.json, local) as host-added or not at all, and not connecting WebSocket ones, after a folder move or pre-warmed start
  • Fixed /mcp still listing a plugin's MCP server after a plugin reload removed it while it was connecting
  • Fixed an MCP server staying "needs authentication", and its mcp_tool hooks being skipped, after a token refresh that was refused only for a moment
  • Fixed MCP elicitation requests being cancelled without asking in headless mode after a server's connection was replaced during a tool call
  • Fixed MCP tool calls from an SDK host answering "Not connected" after a tool call had reconnected the MCP server
  • Fixed an MCP task getting stuck after its question was closed with Esc or asked again: the footer now says it needs your input, and Enter in /tasks shows the question again
  • Fixed background MCP tasks that stopped updating after another call to the same server lost the connection, when a later call reconnects
  • Fixed a background MCP task's question opening over a message you were still typing; it now waits until you send or clear the draft, and the spinner and turn timer keep running
  • Fixed worktree.sparsePaths and sparse plugin and marketplace clones leaving out the repository's root files on older git versions, such as 2.34
  • Fixed self-hosted runner sessions with several repositories being unable to use a repository added mid-session
  • Fixed Claude asking for permission before reading your own artifact or its data
  • Fixed deny and ask permission rules and hooks for the Artifact tool not applying in some cloud sessions
  • Fixed Code Mode scripts ignoring a worktree entered with EnterWorktree, writing ~ paths into the project, and leaving /mcp showing an MCP server as connected after its sign-in expired
  • Fixed words typed with a Yes at a permission dialog or plan approval not reaching Claude in Code Mode
  • Fixed Claude starting work by itself when you resumed a session that ended during a Code Mode script; it now waits for your next prompt
  • Fixed a missing OpenTelemetry user_prompt event for a message sent while tool calls run. The event has delivery.mode: "mid_turn" and the running turn's prompt.id
  • Fixed the OpenTelemetry user_prompt event leaving out earlier messages' text when queued messages merged into one turn in VS Code, or when one message had an image
  • Fixed a slash command's allowed-tools grants applying to background agents woken during or after its turn
  • Fixed /feedback and /bug to upload other sessions only when they were recorded by the signed-in account or organization
  • Fixed relative deny and ask permission rules (e.g. Read(./.env)) no longer covering the project after a cd; they now also apply in added directories
  • Fixed deny and ask permission rules starting with mcp__plugin_*_ missing a plugin's MCP server or tool spelled in another letter case
  • Fixed deny rules not being applied to a permission approval that arrives after Claude Code restarts, in self-hosted runner and claude remote-control sessions
  • Fixed a case where a committed .claude/settings.local.json could be treated as the user's own when Claude Code was started in certain subfolders of a repository
  • Fixed some deny and ask rules not applying to certain Bash commands
  • Fixed a gap in Bash permission checks where some compound commands could run without asking; these now ask for permission
  • Fixed a case where a Bash allow rule could run a different program than the one it names
  • Fixed a connector tool's approval prompt in cloud sessions being answered automatically while plugins were still loading
  • Fixed some subagents changing an artifact that people outside your organization can see, or uploading files to it, without asking first when an allow rule is set or uploads were approved earlier
  • Fixed some artifact publishes skipping the confirmation for pages that people outside your organization can see when "don't ask again" had been chosen for Artifact
  • Fixed auto mode judging only the first change to an artifact that people outside your organization can see; its yes now covers that change alone
  • Fixed a managed strictPluginOnlyCustomization lock on agents and skills not taking effect in sessions that were already running
  • Fixed sandboxed commands being able to write to the native updater's download folder in some cases
  • Fixed a case where the Bash sandbox did not fully protect a worktree's settings and hooks
  • Fixed a case where the Bash sandbox did not fully protect a linked worktree's shared git folder
  • Fixed /teleport's stash choice in some unusual git states: it now stops and says what to do
  • Windows: Fixed a start-up stall that could last about a second when a PATH entry sits under a folder your account cannot open
  • Fixed /resume on Windows refusing or hiding sessions whose folder was recorded with a different drive-letter case or slashes
  • Fixed an in-session /resume on Windows dropping a project's saved trust when the session was recorded with a different drive-letter case
  • Linux: Fixed sandboxed Bash commands failing with bwrap: Can't create file when the working directory was below an allowRead folder inside a denyRead, such as under a symlinked home directory
  • Fixed Claude Desktop's third-party deployments staying on "Stopping" until a token renewal finished (once it includes this version)
  • Improved subagents cut off at the output token limit: they are now asked for the whole answer again, more briefly, instead of returning only its end
  • Improved startup with a keyless Console sign-in or other Anthropic profile login: a token that is still valid is read without waiting for the credentials lock
  • Improved the account email check: it now also refuses your email as a client's identity in scripts a command runs, file writes, web fetches and MCP calls
  • Improved the HTTPS authentication failed message for private plugin marketplaces: it now says git's terminal prompts and askpass programs are disabled, and it also appears with newer git versions
  • Improved the add-marketplace confirmations, plugin recommendation prompts and plugin install warning to say that plugins can run code on your computer, with access to your files and shell
  • Improved the claude --desktop sign-in error to name the API key, provider or setting that stops a Claude account sign-in from working
  • Improved the /voice "No audio detected" message on macOS and Windows: it now says where to pick your microphone
  • Improved MCP tasks: Claude is now told when a task is waiting for your answer, and can point you to /tasks
  • Improved claude remote-control: it now exits with status 4 when it stops by itself (single-session runs still exit 0) and 69 when it can't register, so a service manager can start it again
  • Improved the messages shown when a background session can't use its session's API key or token: they no longer suggest adding the key to settings
  • Improved the bundled dataviz skill's part-to-whole advice for static images and for parts with a natural order, such as age bands
  • Changed sandboxed Bash commands to follow the normal permission flow by default; set sandbox.autoAllowBashIfSandboxed: true to keep running them without prompts
  • Changed managed settings that turn the sandbox on: to keep commands running without prompts, set sandbox.autoAllowBashIfSandboxed: true in your highest-ranking managed source
  • Changed read-only git commands to ask first in a repository that isn't the project's or one you trusted; name it with --add-dir, not the additionalDirectories setting, to run them without prompts
  • Changed scheduled tasks and /loop to ask before running a skill that declares allowed-tools or hooks; add Skill(name) to permissions.allow to run it unattended
  • Changed "Always allow" in Desktop, IDE and SDK hosts: a rule alone is offered only when saving it would allow that command again, so a scheduled task that relied on one can now wait for you
  • Changed the sandbox to refuse sandboxed writes to .claude settings, skills, agents, commands and hooks in added directories, as it does in the launch folder
  • Changed worktree isolation: an isolated worktree session or agent is now refused git bisect run, git maintenance register|start and scalar's set-up commands, and is told what still works
  • Changed plugin MCP bundles (.mcpb, .dxt) to unpack under the plugins directory, not .mcpb-cache in the plugin's folder, so read-only plugin folders load; one fetched by URL downloads again once
  • Changed plugins of a remote marketplace that managed settings declare, enable and list in prependPlugins or appendPlugins to count as the organization's; pluginDigests is deprecated and ignored
  • Changed plugin loading to skip, and claude plugin validate to report, some unsafe paths and links in a plugin's folder
  • Changed nested skill loading: .claude/skills folders in --plugin-dir plugins no longer load from a session started above them; start Claude Code in the plugin folder instead
  • Changed EnterWorktree to refuse a WorktreeCreate hook path that goes through a symlink inside the project; have the hook print the real path
  • Changed tmux and iTerm2 teammates, and new sessions from the agents view opened with ←, to start in the session's folder instead of where the shell last ran cd
  • Changed prompt suggestions in the terminal to refresh less often after 8 turns in a row started by background or scheduled tasks, saving usage until you press a key or return to the terminal
  • Changed Esc on a background MCP task's question to "answer later": nothing is sent to the server, and the question stays in /tasks
  • Changed CLAUDE_CODE_MAX_CONTEXT_TOKENS to also set the context window of unrecognized model IDs that start with claude-, such as a gateway's claude-sonnet-latest
  • Changed /login to ask for permission to change your privacy settings
  • Changed /cost, $.session.usage(), --max-budget-usd and the cost and token metrics to count a mod's $.model.complete and $.model.classify calls
  • Changed the programs that Claude Code's sandbox starts for its own use, such as its network bridge, to run without Claude Code's sign-in tokens and API keys in their environment
  • Changed ripgrep, local git commands and the sandbox runtime's own helper programs to run without the mTLS client key's passphrase in their environment
  • Remote Control: Changed /resume and /teleport to disconnect first when the connected session has a share link, or when that can't be checked; run /remote-control to connect again
  • Changed Claude Code on the web, cloud scheduled tasks and Cowork cloud sessions to start despite sandbox.failIfUnavailable: the hosted container has no command sandbox
  • Changed requests for settings, permission rules, hooks or status over a cloud or self-hosted session's connection to return less or be refused; what applies in the session is unchanged
  • Changed claude -p with no cached account data to wait for that data before its first request, so a first run in a clean environment can start a few seconds later
  • Changed Claude's instructions to keep files you'll want out of its temporary scratchpad folder, which can be cleared
  • Changed marketplace ref to accept the full ID of any commit on a branch or tag; clients before this version can't clone such a pin, so a marketplace pinned this way stops loading there
  • Changed plugin marketplace and plugin downloads to use a CONNECT tunnel when ALL_PROXY is the only proxy set; a proxy that refuses CONNECT now fails them
  • Changed -p and SDK runs in a worktree or submodule mounted into a container to apply .claude/settings.local.json allow rules only once the folder is trusted
  • Changed self-hosted runners to refuse a session whose session folder or repository path is a symbolic link, other than a checkout hook's checkout
  • Removed "ask your admin to raise it" from spend limit and shared budget errors in cloud sessions and under Remote Control
  • [VSCode] Added prompt suggestions wherever the terminal shows them: Tab accepts the suggested next prompt; promptSuggestionEnabled: false in Claude Code's settings.json turns them off
  • [VSCode] Added a Console sign-in that creates no API key
  • [VSCode] Added a field to paste the redirect URL when signing in to an MCP server from the panel in SSH, WSL and container windows
  • [VSCode] Fixed the model picker's check mark staying on the old model after Claude Code restarted on another model or the model was switched over Remote Control
  • [VSCode] Fixed the effort selector offering levels above the effort cap set by your organization or the maxEffortLevel setting
  • [VSCode] Fixed the sign-in screen offering sign-ins that the managed allowedProviders setting refuses
  • [VSCode] Fixed the permission prompt for MCP tools not saying why Claude Code asks when a safety check raises the question
  • [VSCode] Fixed the message for organization settings that couldn't load saying to run a command again; it now says to try again, matching the tab's Retry link
  • [VSCode] Improved the note shown for an untrusted folder: it now says why the extension is off and how to turn it on
  • [VSCode] Improved the error shown when the system refuses to run Claude Code: it now says your IT team can allow a blocked program
  • [VSCode] Improved the sign-in card to say what to do when the browser shows a connection error for localhost
  • [VSCode] Changed the install link's marketplace confirmation button to "Trust marketplace and continue"
  • [Claude Code on the web] Fixed new cloud sessions cutting MCP tool descriptions loaded through tool search at 4,096 characters; the limit is now 16,384, as in other Claude Code sessions
  • [Claude Tag] Fixed artifact links pasted in Slack getting no card when the poster's Claude sign-in had expired in a workspace their organization doesn't manage; a plain card now appears

@scottames-github-bot

scottames-github-bot Bot commented Nov 17, 2026 •

Copy link
Copy Markdown
Contributor
anthropics/claude-code (github:anthropics/claude-code) - part 2 of 2

v2.1.323: v2.1.323

Compare Source

What's changed

  • Added Code Mode, an experimental opt-in in which Claude writes JavaScript to call its tools; see https://code.claude.com/docs/en/code-mode to turn it on, or to turn it off for an organization
  • Added engines["claude-code"] to plugin.json: plugins outside their stated Claude Code version range are not installed, updated or loaded, and install and update pick the newest version that fits
  • Added type checking of a plugin's TypeScript hooks module to claude plugin validate; each finding is a warning, and --strict fails on it
  • Added to claude plugin validate the $ nouns a mod's engine.create hook adds, withholds or replaces
  • Added support for CLAUDE_CODE_AUTO_MODE_MODEL in managed settings for Claude Desktop sessions on third-party providers (takes effect once Claude Desktop includes this version)
  • Added an options menu (stop, switch to usage credits, upgrade) when a model needs usage credits that are turned off or used up
  • Added a progress heartbeat every 30 seconds while hooks run long in claude -p and SDK sessions, so a host such as Claude Desktop won't end the turn as hung (once it includes this version)
  • Added .docx support to Artifact tool asset uploads
  • Added a /diff to close hint to the diff panel, and the keys that focus and close a panel to the ? shortcut guide
  • Added a start-up warning for Bash allow rules with a * in a variable's value, such as Bash(PORT=* npm run dev)
  • Added a warning when a plugin's language server can't start, naming the server and what to check
  • Added a one-time startup notice naming CLAUDE_CODE_PERFORCE_MODE when Perforce settings are found and the mode is off
  • Added CLAUDE_CODE_DISABLE_AGENT_PROGRESS_SUMMARIES (available since 2.1.318): set it to 1 to turn off subagent progress summaries and the requests that write them (Feature request: a supported way to disable the agent_summary spinner (22.7% of requests, ~18% of weighted tokens in a subagent-heavy session) anthropics/claude-code#86879)
  • Added CLAUDE_CODE_RESUME_HINT_COMMAND, which a program that starts Claude Code can set to have the exit hint name its own resume command
  • Added unsetOptionCount to the claude plugin install --json result: how many userConfig options are not yet set
  • Added isPromptCovered to the props a mod's pane is drawn with, telling it when a dialog or a field above the prompt covers the prompt
  • Fixed running /compact again, or after a command such as /context, summarizing away a message that Claude had not answered yet
  • Fixed a resumed session joining your next message to an old interrupted message that was not resumed
  • Fixed a memory spike at the next prompt after Claude changed a very large file
  • Fixed a setting saved in a running session undoing a hand edit made to settings.json moments earlier; a settings file you delete during a session now stays deleted
  • Fixed claude plugin commands and claude mcp list signing you out of a Console profile when they ended while the token was being renewed
  • Fixed Edit and Bash running out of memory on certain /proc files, and Edit hanging or running out of memory on devices and named pipes
  • Fixed Claude Code failing to start, or to clear stored credentials at sign-out, when saving its configuration file failed with "Out of memory"
  • Fixed requests sent without streaming failing on errors that streamed requests recover from, such as a rejected image, thinking block or beta header
  • Fixed ExitWorktree, the worktree exit dialog and /resume leaving the session in the wrong folder when the folder the shell was in before entering the worktree had been deleted
  • Fixed accents and other combining marks sometimes landing left of the text, leaving stale copies on screen, or silently disappearing when text wraps
  • Fixed the last key of a key chord, such as Enter in ctrl+x enter, acting on a dialog's text field when the chord's own action isn't available there
  • Fixed ps processes piling up when the process listing Claude Code runs before stopping a command takes too long
  • Fixed subagent transcripts and large tool results being saved apart from the session's transcript after entering a worktree created by a WorktreeCreate hook or belonging to a nested repository
  • Fixed a session on a named Anthropic profile moving to another sign-in when /fork, the Left arrow or --bg continued it in the background; reopen any session that was open during the update
  • Fixed a background session sending a conversation under another sign-in when its named Anthropic profile is missing, changed or overridden; it now stops and says so
  • Fixed a session on an API key, auth token or workload identity from its shell (not a setup token) moving to another sign-in in the background; it now stops and says so
  • Fixed MCP tool calls ending in the sign-in server's error, such as TOKEN_EXPIRED, instead of asking you to sign in again
  • Fixed an expired claude.ai login showing "Credit balance too low" when a saved Console key or ant auth login profile without credit was used instead
  • Fixed a session on a named Anthropic profile being handed to an older background service that could not keep its sign-in; it now says to restart the service
  • Fixed a background session's sign-in leaving the previous account's login or other credentials in place; it now clears them for every session on the computer, and a refused sign-in can leave no login
  • Fixed background sessions moving between a profile and the stored login when an update restarted them
  • Fixed sessions opened before a sign-in keeping signed-out feature flags after the sign-in
  • Fixed sessions that kept failing after a Claude apps gateway sign-in expired: once you sign in again with /login in another terminal, they carry on at the next message
  • Fixed the billing notice naming your ant auth login organization when a custom X-Api-Key header is set
  • macOS: Fixed "Not logged in · Please run /login" coming back right after a successful /login or a token refresh when the keychain was slow to answer
  • Fixed turns failing in Claude Desktop when an organization's gateway answers an expired token with 403: Claude Code now asks Desktop for a fresh token and retries
  • Fixed the error shown when Amazon Bedrock refuses your account a model: it no longer says to refresh your AWS credentials, it says to enable the model
  • Fixed the awsAuthRefresh or gcpAuthRefresh command sometimes running twice for one request when three or more sessions needed a fresh sign-in at once
  • Fixed the claude -p warning about an ended claude.ai login to say that claude auth logout also removes saved MCP server logins and plugin secrets
  • Fixed Bash permission prompts offering "don't ask again" for commands that write to sensitive paths such as .git or .claude, where the saved rule did not stop the next prompt
  • Fixed a case where some lsof commands ran without a permission prompt
  • Fixed Bash commands that write a file with cat > file <<EOF being shown as "Read 1 file"
  • Fixed a case where Bash permission checks judged an rm from the wrong folder and skipped the dangerous-removal prompt under bypass permissions or a Bash allow rule
  • Fixed --permission-mode auto or a settings defaultMode: auto starting in a mode that could allow more when auto mode was unavailable. It now starts in Manual mode, which asks first
  • Fixed plan files sometimes being written outside the project when plansDirectory is set; a write that can't be shown to stay inside the project is now refused
  • Fixed a permission prompt when Claude read the output of its own background command or agent after entering a worktree
  • Fixed a case where Bash permission checks missed part of a command
  • Fixed a case where the Bash sandbox could switch off during a session
  • Fixed Bash allow rules with an attached wildcard, such as Bash(ls*), skipping the permission prompt in some cases; a rule that names a variable, such as Bash(NODE_ENV*), now asks
  • Fixed auto mode running behind a gateway at ANTHROPIC_BASE_URL on a model whose gateway name contains "haiku"; such a model, other than claude-haiku-5-5, is now refused, as Haiku 4.5 is
  • Fixed Bash deny and ask rules missing some commands run through sudo, env and similar wrappers
  • Fixed Bash allow rules written with combined sudo flags skipping the permission prompt in some cases
  • Fixed sandbox.excludedCommands letting a command that it does not name run outside the sandbox in some cases
  • Fixed a case where the Write and Edit tools could write to a path covered by a Read deny rule
  • Fixed a case where a Bash command ran without a permission prompt for zsh users with certain non-default shell options set
  • Fixed the Bash sandbox not fully protecting Claude Code's own config on installs still using the legacy config file
  • Fixed a permission prompt from a mod's tool.check hook naming every plugin hooked on the tool instead of the one that asked
  • Fixed sandboxed commands being able to read Claude Code's file checkpoint copies under the config directory
  • Fixed a rewind sometimes changing your permission mode
  • Fixed project settings sometimes being read through a symbolic link that leads to a different folder than the one Claude Code checked
  • Fixed HTTP hooks failing with HTTP 500 on Linux when CLAUDE_CODE_SUBPROCESS_ENV_SCRUB is set and sandbox.enabled is off
  • Fixed claude -p and the Agent SDK running Bash unsandboxed when --settings or SDK settings that turn the sandbox on fail validation; Claude Code now stops at start-up and names the invalid setting
  • Fixed /export silently stopping early after a long run of calls to an MCP tool that is no longer loaded
  • Fixed earlier MCP tool calls missing from a resumed conversation, and lines repeating in scrollback, when the server connects late
  • Fixed claude mcp add --help splitting long example commands across lines in narrow terminals and pipes, so a pasted example ran without its header
  • Fixed plugins with defaultEnabled: false staying off in a claude.ai chat's cloud session after you turn them on in claude.ai
  • Fixed /fast on and /fast off on Vertex not asking a plugin's config.set hook, as the /fast menu does
  • Fixed documents created through the Claude Docs connector not opening in your browser when you work in a terminal
  • Fixed the misleading "not cached" error for a plugin only a repository's settings enable: it now says it isn't installed, gives the install command, and shows in text and stream-json -p runs
  • Fixed mods being able to reword Claude Code's own confirmation questions
  • Fixed a mod's hot reload sometimes ignoring a file created just after a failed reload
  • Fixed marketplaces named npm, pip, uv, cargo, github or gh being refused as reserved names
  • Fixed a stopped MCP call, or a stopped shell command in fullscreen, reading as "Called" or "Ran" in a collapsed tool group: it now says no result was recorded and shows its input
  • Fixed load errors of plugins enabled by managed settings going only to the debug log in SDK and Desktop sessions: init.plugin_errors now lists them
  • Fixed plugin installs hiding what a plugin's install command wrote to stderr when that command succeeded, such as a note that the plugin has no skills yet
  • Fixed one malformed entry in a plugin marketplace's renames map making Claude Code ignore the marketplace's other renames
  • Fixed claude --bg --safe-mode sessions stopping at startup to ask about project MCP servers that safe mode never starts
  • Fixed MCP link prompts offering Accept for non-http links without saying the link wouldn't open
  • Fixed /mcp and /plugins opening an MCP server's page with the cursor on "Disable" when the server needs authentication but still holds its sign-in; the page now offers "Reconnect" and opens on it
  • Fixed plugins with a version list in enabledPlugins staying off with no message: /plugin and claude plugin list now say why
  • Fixed plugins and marketplaces failing to install on Windows when the path of a cloned file reaches 260 characters
  • Fixed a Stop pressed right after sending a message showing as an error in remote and SDK sessions while a UserPromptSubmit or plugin prompt hook was still running
  • Fixed an MCP server staying disconnected with no tools after an Agent SDK app or claude -p caller removed and re-added it, when a tool call had tried to reach it in between
  • Fixed text-output claude -p runs printing nothing to stderr when a --plugin-dir mod's hook hangs or crashes the hooks worker
  • Fixed SDK sessions giving an MCP server named by --allowedTools or an mcp_tool hook less than 2s before the first turn when settings lowered CLAUDE_CODE_MCP_STARTUP_WAIT_MS after start-up
  • Fixed headless sessions ending when an SDK host sent a null entry in an MCP server's tools list
  • Fixed WebFetch dropping empty table cells and shifting later values a column left
  • Fixed temporary files of a session that had changed directory being left behind when the session expired under cleanupPeriodDays
  • Fixed managed settings (managed-settings.json, managed-settings.d) sometimes being missed at start-up while another program was rewriting the file: start-up now reads such a file a second time
  • Fixed .claude/settings.local.json not being ignored globally when the folder became a git repository later, or on a new machine
  • Fixed /diff waiting for Claude to finish before closing the diff panel in fullscreen
  • Fixed /memory showing wrong or roundabout paths for folders whose names start with the working directory's or home folder's name, and losing slashes in the file path on Windows
  • Fixed a broken emoji character in a tool call's parameter name being resent with later requests, which strict JSON parsers reject
  • Fixed a collapsed tool call looking as if it ran after you rejected it with a reason: it now shows "Not run · rejected"
  • Fixed a case where part of a saved session could be lost on NFS or FUSE file systems when Claude Code discarded a reply
  • Fixed WebFetch not rechecking organization policy and CLAUDE_CODE_DISABLE_WEB_FETCH at each call
  • Fixed file titles, app names and session names in @​-mentions from claude.ai and the desktop app sometimes being treated as text you typed
  • Fixed a multi-row status line being pushed off screen by a long prompt in the fullscreen renderer
  • Fixed a case where certificate errors behind a TLS-inspecting proxy persisted when the proxy itself is reached over https://
  • Fixed Pro and Max accounts being offered feedback drafts that their organization would refuse
  • Fixed Claude in Chrome's policy message telling people to contact their admin when no admin setting can turn it on
  • Fixed the artifact preview sometimes opening a different artifact than the one Claude just published
  • Fixed certificate name-constraint errors being retried for minutes; they now fail at once with a message that says what to fix
  • Fixed claude --teleport opening an empty session when the server could not find the session's history, and claude -p --teleport exiting without an error when the resume failed
  • Fixed a misspelled keybinding modifier, such as ctl+k, binding the bare key; the binding is now ignored
  • Fixed /btw answers and recaps sometimes including earlier replies from the conversation
  • Fixed start-up requests switching from an organization's managed proxy and CA settings to user-set ones when a read of the managed settings file failed
  • Fixed Claude giving a wrong reason when a new message interrupted a file it was sending you
  • Fixed CLAUDE_CODE_RESUME_INTERRUPTED_TURN re-running a turn that a hook's continue: false had stopped
  • Fixed Claude being told that automatic model switching is off when safeguards stopped a subagent whose model had no other model to switch to
  • Fixed the changed-files list of remote sessions leaving out files added with git add -N before the first commit
  • Fixed some Claude in Chrome tool calls, such as browser_batch, not showing the tool's name in the fullscreen transcript (ctrl+o) or in a subagent's progress
  • Fixed subagent progress summaries skipping an update when the reply took between 10 and 20 seconds
  • Fixed claude doctor and /status saying a linked managed settings file is still read when it could not be read
  • Fixed an interactive --chrome session giving no reason for starting without Claude in Chrome when your organization's policy turns it off: a line now says so
  • Fixed the /rewind list on network paths and hung folders: it named every tracked file as changed, was slow to show labels, and showed none at all when a file read never returned
  • Fixed --debug and --debug-file replacing a file named latest in the debug log's folder
  • Fixed a timed-out feedback send being reported as too large; it now says the request timed out
  • Fixed screen reader mode cutting off an announcement when the system clock moved forward while it was being read
  • Fixed screen reader mode dropping dictated or pasted text, and emoji, typed into an answer to a question or permission prompt
  • Fixed the name label under permission and plan dialogs hiding part of some agent names
  • Fixed a case where pressing Ctrl+C just as claude update finished removed the claude command
  • Fixed the fullscreen header naming the session's effort level for a viewed subagent on a different model, which that subagent doesn't use
  • Fixed the model picker and /model showing a picked effort level that CLAUDE_CODE_EFFORT_LEVEL overrides
  • Fixed the tip after a slow worktree creation suggesting a sparsePaths list without .claude, which left worktrees without your project settings and rules
  • Fixed the newest model's highlight missing from the /model picker
  • Fixed /upgrade and Ctrl+clicked links in fullscreen failing silently when no browser can open: the address is now shown
  • Fixed the Claude apps gateway's JSON logs escaping newlines and other control characters in a message twice
  • Fixed terminal control sequences in a subagent's message taking effect instead of showing as plain text when the message is expanded
  • Fixed Claude in Chrome setup saying /chrome finishes the connection; it now tells you to restart with claude --chrome
  • Fixed the Option-key hint appearing while typing ø or π inside words on Danish, Norwegian, Faroese and Greek keyboard layouts
  • Fixed a Claude Desktop session getting stuck as busy after another of your sessions sent it the same message twice or many messages at once
  • Fixed long tool results staying on disk after a session run with --no-session-persistence; they are now removed on normal exit, Ctrl+C or SIGTERM
  • Fixed PreCompact, PostCompact and post-compaction SessionStart hooks not receiving agent_id and agent_type when a subagent compacts
  • Fixed CLAUDE_CODE_TRANSCRIPT_LOCAL_GC dropping messages from the saved transcript when another process rewrote the file while it was being trimmed
  • Fixed the "Now using usage credits" notice repeating or not showing past the weekly Fable limit when Claude Code made a quick side request on a smaller model, such as naming the session
  • Fixed Fable's weekly limit showing no reset time and no options menu in the terminal
  • Fixed a wait chosen in the usage limit menu silently moving to a later reset when its request was refused; the menu now opens
  • Fixed the spend limit menu offering a lower limit when your current limit couldn't be loaded
  • Fixed /usage hiding limit bars for setup tokens and CLAUDE_CODE_OAUTH_TOKEN: it keeps the session and weekly bars and says why the rest are missing
  • Fixed /usage showing a whole-session percentage beside a subagent type's name, and saying sessions ran 8 hours when it only counts hours with requests
  • Remote Control: Fixed sessions showing as disconnected for a minute or more after a network change such as switching Wi-Fi or reconnecting a VPN
  • Fixed Remote Control showing nothing while Claude Code asks whether to use usage credits: the question now also shows in the Claude app
  • Fixed Remote Control showing a session as running while it waited on a permission prompt that can only be answered in the terminal
  • Remote Control: Fixed claude remote-control reconnecting as a new computer when restarted in the same folder more than 4 hours after it stopped; it now keeps its identity for up to 30 days
  • Remote Control: Fixed sessions left running at shutdown, and finished sessions holding their slot, when the disk stops responding
  • Remote Control: Fixed other devices and phone notifications not showing what Claude is asking permission for when DISABLE_TELEMETRY or DO_NOT_TRACK is set
  • Remote Control: Fixed the host exiting, or stopping reading a session's output, in verbose or debug mode when a tool call's command was a number, boolean or object
  • Remote Control: Fixed a host that could stall after sessions failed to start in folders on a filesystem that had stopped responding
  • Remote Control: Fixed sessions from the desktop app showing as idle on your phone while background subagents were still running
  • Fixed the Agent SDK's managedSettings ignoring the Remote Control, agent view, Workflows and Artifact off switches
  • Fixed OpenTelemetry export failing silently when an otlp exporter had an endpoint but no OTEL_EXPORTER_OTLP_PROTOCOL: it now defaults to http/protobuf
  • Fixed OpenTelemetry export to the default localhost:4318 endpoint going through a configured proxy
  • Fixed one malformed OTEL_RESOURCE_ATTRIBUTES entry dropping all of that variable's attributes from the OpenTelemetry resource; the others are now kept, and /status names the one left off
  • Fixed OpenTelemetry user_prompt events and interaction spans recording a background agent's reply when OTEL_LOG_ASSISTANT_RESPONSES=0
  • Fixed OpenTelemetry exports failing when a proxy took over 10 seconds to reach the collector; it now has 25 seconds, also the most that OTEL_EXPORTER_OTLP_TIMEOUT can allow (previously 30)
  • Fixed OpenTelemetry agent.name showing a user-defined subagent's name instead of custom when an official plugin's skill launched it
  • Fixed claude agents showing a status from an earlier turn after a session resumes
  • Fixed read-only git commands needing approval, or being refused under claude -p, when CLAUDE_CODE_SUBPROCESS_ENV_SCRUB is set on Linux
  • Fixed claude agents losing a typed prompt: Esc now needs a second press to clear it, and ctrl+y restores it
  • Fixed the move-to-background key doing nothing in claude attach and claude agents sessions; to detach with Ctrl+B d, press d within 800 ms of Ctrl+B
  • Fixed background sessions ignoring a DISABLE_ERROR_REPORTING set only in your shell when the background service started without it
  • Fixed false "needs input" notifications in claude agents after replying to a blocked session, and repeated ones after a background turn ended with no text and only basic tools such as Bash or Read
  • Fixed claude -p silently using another model in text output when settings block the requested one; it now warns on stderr
  • Fixed claude -p printing notes about deniedModels and availableModels entries on every run; /status and claude doctor still list them
  • Windows: Fixed some file-reading Bash commands running without a permission prompt when given a wildcard or a list of files
  • Windows: Fixed Claude Code running a .cmd or .bat wrapper found beside a program's .exe in the same PATH folder (a git.cmd next to git.exe, say); it now runs the .exe, as cmd.exe would
  • Windows: Fixed shell commands failing with "Working directory was deleted" on drives where a folder's real path can't be resolved
  • Fixed a cloud session's history becoming unreadable if its machine stopped just after the history was rewritten
  • Fixed scheduled tasks from an ended session sometimes not running after another session in the same folder used /clear, /resume or /branch
  • Fixed an approved plan being answered with "You are not in plan mode" when the approval arrived after the session's process had restarted, in cloud, self-hosted runner and SDK sessions
  • Cloud sessions: Fixed an answer to Claude's question being lost after a restart in a long conversation
  • Fixed a message dropping out of a cloud session's conversation when the session restarted before Claude replied
  • Cloud sessions: Fixed Claude saying an attached image is missing when the message names its file
  • Fixed a resumed cloud session making a model call nobody asked for when files arrived right after a chat's first reply
  • Fixed streamed replies in cloud sessions missing text from the middle when the session's container shut down partway through a reply
  • Fixed skill files sent from Cowork cloud sessions sometimes failing to upload on the first try
  • Self-hosted runner: Reverted the exit code of an on-demand runner whose work order was superseded to 1; 2.1.321 and 2.1.322 had changed it to 0
  • Improved sign-in errors in /login and claude setup-token for a rejected, unreachable or timed-out request: they now say what happened and what to check
  • Improved Bash permission checks so the same command more reliably gets the same answer on a slow or busy machine
  • Improved Bash permission checks: some commands that could run differently from how they were checked now ask for permission
  • Improved /mcp to show how many of a server's tools were left out because the API would reject their input schema, and why
  • Improved the "Not now" choice when Claude Code asks to turn on the mods it writes in a session: it now says when they load
  • Improved the error for an MCP tool call whose connector ID is mistyped by a character or two: for a server that the host application registered, it now names the tool to call
  • Improved Claude Desktop and cloud sessions for claude.ai accounts with more than 2,000 plugins turned on: a shorter wait at startup, and Claude can now say why plugins are missing
  • Improved memory use with many subagents: a finished subagent's transcript is freed sooner instead of staying in memory while later subagents run
  • Improved installing with the install script: the latest version is no longer downloaded twice
  • Improved WebFetch speed and memory use on deeply nested pages
  • Improved the cleanupPeriodDays cleanup to count folders it can't read as errors
  • Improved the Claude apps gateway's /v1/models to state max_input_tokens for models whose context window is certain on every upstream
  • Improved ToolSearch to say when a tool Claude searched for by its short name is already available, instead of only reporting no match
  • Improved start-up on Linux when /home is an autofs map: Claude Code no longer looks up files in /home itself. Set CLAUDE_CODE_AUTOMOUNT_ROOTS for a map root deeper than one folder below /
  • Improved the Fable limit message in -p, SDK, IDE and cloud sessions: it now says when the limit resets, along with how to continue
  • Changed /security-review to ask before Claude runs it, and skills' inline git commands to stop in bare-repository worktrees and similar folders until you allow them, outside auto mode and bypass
  • Changed how many messages each of your sessions on the same machine can send the others without a prompt from you, from about 20 to 100,000
  • Changed the number of messages a Claude Desktop Code tab session can send to your other sessions before it waits for you to type again from 20 to 100,000
  • Changed organization settings and policy requests to no longer use a proxy set only by ALL_PROXY; set HTTPS_PROXY if your network needs a proxy for them
  • Changed the context window assumed for a model ID that Claude Code doesn't recognize from 200K to 1M; use /autocompact to compact earlier, or CLAUDE_CODE_DISABLE_1M_CONTEXT=1 to keep 200K
  • Changed sessions on other vendors' models with a smaller window: once full, they can fail every turn until /clear, so set CLAUDE_CODE_DISABLE_1M_CONTEXT=1 before they fill
  • Changed Claude Code's own ripgrep and most internal git commands to run without most of its sign-in tokens and API keys, so a credential helper or hook under such a git command no longer finds them
  • Changed MCP_SDK_GENERATION=v1 to run the v2 MCP client in a compatibility mode (earlier handshake, relaxed OAuth sign-in checks), because the v1 MCP client is removed
  • Changed the tool Claude uses to finish an MCP server sign-in so that it asks you to confirm, even in bypass and auto modes; where nobody can be asked, such as in dontAsk mode, use /mcp
  • Self-hosted runner: Changed a session at a connector's approval prompt or sign-in inside a running tool to be released as paused at the idle or lifetime limit; a late answer resumes from a fresh clone
  • Changed artifact updates to ask first, even under an allow rule, when people outside your organization can see the artifact or Claude can't check who can
  • Changed glab config set without --global or --host, and glab config edit --local, to fail read-only inside the Bash sandbox; run them outside it
  • Changed the Bash sandbox on macOS, Linux and WSL to ignore write access granted through a symlink in a writable folder that leads elsewhere or to a missing path; grant the real path instead
  • Changed "don't ask again" so an allow rule that looks like it holds a secret, or would be saved to a settings.local.json that git tracks, lasts for the session only and isn't saved
  • Changed the sandbox on macOS and Linux: git worktree add, move and remove now fail read-only, as do commits in a worktree the session wasn't started in or given, even one inside the project
  • Changed start-up to stop when a --settings file isn't valid JSON and has a sandbox key, even one that turns the sandbox off
  • Changed what happens when a tool's permission check fails with an error after a PreToolUse hook returned "allow": Claude Code now decides the call as if no hook had answered
  • Changed what happens when a tool's permission check fails on input that a PermissionRequest hook rewrote: Claude Code now asks again, or refuses the call where nobody can answer
  • Changed the GitLab merge request badge to show only for the repository a sandboxed session opened in
  • Changed the claude mcp add --help example to a local command
  • Changed mods: a *, namespace or negated hook on engine.create now only observes. To add or withhold a $ noun, hook engine.create by name
  • Changed claude plugin validate to fail a mod whose engine.create hook isn't written in the one accepted form; installed mods keep loading
  • Changed marketplace and plugin installs to fail when a git submodule isn't on the commit its repository records
  • Changed project (.mcp.json) MCP server approvals to match the server's exact name; an approval entry written in another spelling now asks again
  • Changed self-hosted runners under --trust-workspace false and VS Code sessions in an untrusted folder: the repository's settings can no longer disable your hooks or turn plugins on or off
  • Changed tool.list plugin hooks so the tools they add or remove apply to the model and every agent
  • Changed claude plugin install and /plugin to show a warning instead of success when a plugin's install command writes to stderr
  • Changed claude.ai chats and Cowork tasks to check a plugin file for secret keys before sending it, and to ask first if it may hold one
  • Changed claude rm and the agents view to say a session is removed from the list, not deleted; claude rm help says the conversation is kept and claude --resume lists it
  • Changed /stickers to say that the sticker pack is all claimed for now, instead of opening a page in the browser
  • Changed a managed settings policyHelper to no longer take environment variables from user or --settings files; set what it needs in managed env or the launching shell
  • Changed a /skill or @&#8203;file typed between two files picked in claude.ai or the desktop app, or after a picked file and a link, to no longer take effect
  • Changed split-pane agent teammates to check that requests come from their team lead: one that outlives its lead has its asks refused, and plan approvals must be re-sent after /clear or /resume
  • Changed worktree creation to refuse checkouts whose .git folders are links or hold hard links, such as git-new-workdir layouts and cp -al copies; use a plain clone
  • Changed what Claude is told after safeguards stop a forked skill or a workflow agent: retry with a narrower prompt or tell you, instead of doing the work itself
  • Changed browser tool calls (Claude in Chrome, the desktop browser pane) to refuse some escaped or JSON-text inputs and tell Claude how to respell them
  • Changed workflows so that a prompt an app marks as not typed no longer reaches their agents as your request
  • Changed computer use on macOS to refuse key chords that hold Space with Control or Option, and more system shortcuts that need your grant
  • Changed first-run setup in Terminal.app to name the "Use Option as Meta key" setting, what Option stops typing, and how to undo it before you agree
  • Changed the maximum of CLAUDE_CODE_OVERLOADED_RETRY_MAX_DELAY_MS from 64000 to 300000
  • Changed workflows in the desktop app's Code tab to pause at a usage limit and continue after it resets
  • Changed the spend limit and 1M context errors, and /usage-credits, in cloud sessions and under Remote Control: they no longer give a web address
  • Changed which MCP servers are reported by name in OpenTelemetry exports to follow the current connector directory
  • Changed /logout in a background session, which had no effect: it now signs out every session on the computer, deletes stored MCP logins and plugin secrets, and ends the session, as in a terminal
  • macOS: Changed the Bash sandbox so lsof and similar tools may show less about processes a command did not start
  • Changed cloud scheduled tasks: a PostToolUse hook from your own settings can no longer replace the plan in ExitPlanMode's result
  • Changed CLAUDE_AUTOCOMPACT_PCT_OVERRIDE in Anthropic-hosted cloud sessions to stop applying to auto-memory extraction and, in some sessions, to /btw; the main conversation still follows it
  • Removed the subagentStatusLine setting: subagent rows always use the default look, and settings files that still hold the key load as before
  • Deprecated a plugin's agent setting: it still applies, and now warns at startup, in claude plugin list and in claude plugin validate
  • [VSCode] Added a Claude Code trust prompt before the first session in a folder you haven't trusted; declining leaves the folder's settings and MCP servers unused
  • [VSCode] Added the live output of a running Bash or PowerShell command to the chat, under the command's card
  • [VSCode] Fixed a response that was discarded because its tool call could not be parsed still showing after Claude retried
  • [VSCode] Fixed a queued message missing from a conversation or fork when it directly followed a compaction summary
  • [VSCode] Fixed the "Buy usage credits on claude.ai" button counting as agreement to pay for Fable while usage credits were off
  • [VSCode] Fixed the "extensions want to relaunch the terminal" warning coming back on open terminals after every window reload or restart
  • [VSCode] Fixed "Couldn't load this conversation's saved history" appearing in a new chat whose Claude process had restarted before the first prompt
  • [VSCode] Fixed the sign-in screen showing the login choices again after a pasted code; it now shows "Signing in…" until the sign-in finishes
  • [VSCode] Fixed the "You've hit your Fable limit" line staying in the VS Code and JetBrains panels after you pick another model
  • [VSCode] Fixed the Fable usage warning in the VS Code and JetBrains panels naming usage credits when they're off or used up
  • [VSCode] Fixed the diff tab not opening for multi-line edits on files with CRLF line endings
  • [VSCode] Fixed dictation continuing to record after switching sessions
  • [VSCode] Improved sign-in errors behind TLS-inspecting proxies: a certificate failure now says what to do, as the terminal does
  • [VSCode] Changed opening a Claude Code on the web session in a folder where Claude Code's sandbox is on: the extension no longer switches to the session's branch for you, and the dialog says why
  • [Claude Code on the web] Improved the message when a file fails to upload to a cloud or Remote Control session: it now gives the reason, such as too many pages, a password or a time-out
  • [Claude Code on the web] Improved adding a repository Claude can't access to a cloud session: a short message and a Reconnect GitHub button replace the long error
  • [Claude Code on the web] Fixed self-hosted sessions staying on "Starting Claude Code" after it had started, when you reopened a paused session without sending a message
  • [Claude Code on the web] Fixed a paused session in a self-hosted environment sometimes still showing "Sending" and a Stop button under the "Session paused" banner
  • [Claude Code on the web] Fixed pull request updates from GitHub Enterprise Server linking to github.com in cloud sessions; new updates link to your own server
  • [Claude Code on the web] Improved the message when some network secrets can't be added to a new cloud environment: it lists each host, says why where it can, and stays until you dismiss it
  • [Claude Code on the web] Fixed very large GitHub Actions job logs and run log archives failing to download or being cut off in cloud sessions
  • [Claude Code on the web] Improved the new-session repository picker when GitHub single sign-on hides organizations: it now says so even with other repositories listed, and links to reconnect GitHub
  • [Claude Code on the web] Fixed new cloud sessions started from the iOS app with a repository not getting a branch of their own
  • [Claude Code on the web] Fixed an open cloud or Remote Control session's page staying "Disconnected" after a few minutes of failed connections; it now tries to reconnect by itself
  • [Claude Code on the web] Fixed Try again on an open cloud or Remote Control session's "Connection lost" card sending "Try again" as your message; it now tries to reconnect instead
  • [Claude Code on the web] Fixed the Stop button disappearing from a cloud session five minutes into a reply that had shown nothing yet while Claude was still working
  • [Claude Code on the web] Fixed an approval prompt sometimes disappearing from a tab left open after a self-hosted runner released the session while it waited for your answer
  • [Claude Code on the web] Added a failure notification when a scheduled task's run can't start because its settings require a sandbox that isn't available where it runs
  • [Claude Code on the web] Improved the Git providers page when your GitHub sign-in has expired: it now asks you to reconnect instead of silently hiding organizations you can link
  • [Claude Code on the web] Fixed removing a repository from a scheduled task silently moving its GitHub trigger to another repository; Save now waits until you pick one
  • [Claude Code on the web] Fixed git clones and fetches that take longer than ten minutes in a cloud session sometimes being cut off at the very end
  • [Claude Code on the web] Added the No repository option to the repository picker for new sessions on a self-hosted environment
  • [Claude Code on the web] Added a warning to a cloud session's Delete dialog when deleting it will pause scheduled tasks that run in that session
  • [Remote Control] Fixed your own session saying its environment was deleted when you deleted nothing; it now says your computer is no longer connected
  • [Remote Control] Fixed some sessions still showing as running in the session list after the computer disconnected before Claude started; they now show an error mark or as idle
  • [Remote Control] Added a Try again button to the error shown when the computer running your session is signed out of Claude Code
  • [Claude Tag] Added Claude Tag sessions started in Slack to the Compliance API on Enterprise plans, in beta: list the sessions and read their transcripts
  • [Claude Tag] Added a confirmation step when an admin turns off Claude Tag for the organization, with a dialog that says what stops
  • [Claude Tag] Fixed scheduled tasks in a Slack channel moved between Enterprise Grid workspaces failing to use Slack until someone posted there
  • [Claude Tag] Fixed the Approve and post card in a DM with Claude appearing for private or Slack Connect channels, where Claude can't post; Claude now gets the reason and shows no card
  • [Claude Tag] Added a Retry button to a Slack channel's Configure page for when its settings fail to load
  • [Claude Tag] Added a Scope filter to the Network events tab of Claude Tag's Activity page, so admins can download one scope's events instead of the whole organization's
  • [Claude Tag] Fixed Remove connector in Claude Tag admin settings being refused when access bundles also held its credentials; it now removes those set on the connector and leaves the bundles' own
  • [Claude Tag] Fixed the Channels tab in Claude Tag admin settings splitting a workspace from its channels across pages; channels now appear right under their workspace
  • [Claude Tag] Fixed the Set for Claude Tag link on the Cloud environments admin page not leading to the environment setting; it now opens the Slack page's Advanced tab, where you set it
  • [Code Review] Added a Download CSV button to Code Review admin settings: export review costs per repository by month, week or day, for one repository, one GitHub organization or all

@renovate
renovate Bot force-pushed the renovate/mise-packages branch 3 times, most recently from eda0af4 to fb7b119 Compare November 17, 2026 23:44
@scottames-github-bot

scottames-github-bot Bot commented Nov 17, 2026 •

Copy link
Copy Markdown
Contributor
backnotprop/plannotator (github:backnotprop/plannotator)

v0.28.64: v0.28.64

Compare Source

Follow @​plannotator on X for updates

Missed recent releases?

Release Highlights
v0.28.63 Pair Grok Bot and other cloud agents from Settings, Hermes Agent, OpenClaw and Muse Code can use the Inbox, add a thread to Priority to keep it on top, tag threads, and find each tag in the sidebar, Pull requests board as a table, with bulk Merge
v0.28.62 Agents started from the Inbox now work on Windows, pick a model and effort when you start an agent, rules for your agents, written in your own words, post a thread's decisions on its pull request, the Inbox loads faster on a slow connection
v0.28.61 Updates now update the Claude Code plugin too, an agent's chosen face shows on every icon of it, filter the Inbox list by pull request state, Modern dark shows section bands and the Reply button, one conversation no longer shows as two agents
v0.28.60 Click a word to highlight it, a one-time Themes dialog, Settings → Rows rebuilt, tell your agent how you want your rows, starred threads as pills above the list, a pill for new messages out of view, a half-circle face picker with ten Glass colours, a new phone sidebar and reply box
v0.28.59 A quieter Agents section in the sidebar, machine names only when agents run on more than one machine, agent icons that are always gently alive and lean toward your pointer
v0.28.58 Start Codex from New message, an Agents section in the sidebar, start an agent in a folder on any drive, play audio attachments and comment at a moment, Claude Code's Plannotator tools work on Windows
v0.28.57 Pin artifacts, and see every artifact on one page, filter the list by project, date or agent, a thread shows its pull requests and their state, choose what the sidebar shows, and in what order, Ask AI starts from Side in the selection bar
v0.28.56 Questions can show trade-offs and a prototype to try, a thread with many big pictures no longer crashes the tab, Escape closes New message and keeps your draft, read threads stop being bold and keep their place, agent messages that name no thread start a new one
v0.28.55 Floating reply drafts, now a setting under Experimental, open questions sit next to Reply again, a comment box that keeps unsent comments as Drafts, choose how your list looks: Minimal, Balanced or Detailed, update an older linked machine from this Inbox
v0.28.53 Start an agent in a new folder, or from a git URL, "+" on each project row starts a session there, a reaction tray, a thread's Links, Settings → Activity, New message offers the open thread's files, Bro mode: agents write to you in plain words
v0.28.52 Start agents from the Inbox, on by default, a new reply box, Ask AI for everyone, Insights in Settings → Decision data, Plannotator reloads itself after an update
v0.28.51 Starred threads, a note when an agent's session has ended, "Back from snooze", Ask about a past decision, expand arrows in guided reviews

What's New in v0.28.64

TL;DR

  • Changed: Installs and updates download a smaller, compressed copy
  • New: A Videos filter on the Artifacts page
  • Changed: GitLab comments on a whole file get their own thread
  • Off by default: Pull request pictures and videos show in the Inbox

0.28.64 is a small release. Installs and updates now download a compressed copy of Plannotator, the Artifacts page can show only videos, and a GitLab comment on a whole file posts as its own thread. It has 5 PRs, all from the maintainer.

Smaller downloads for installs and updates

Each release now carries compressed copies of the Plannotator binary next to the plain one: a .tar.xz for macOS and Linux, and a .gz for every platform. On macOS (Apple silicon) the download goes from 195.6 MB to 44.9 MB as .tar.xz, or 73.9 MB as .gz.

The installers try them in order. On macOS, the install script takes the .tar.xz, then the .gz, then the plain file. On Linux it takes the .tar.xz only when xz is installed, and otherwise starts with the .gz. On Windows, both install.ps1 and install.cmd take the .gz, then the plain file. Each copy is unpacked and checked against the same SHA-256 as the plain binary before anything is replaced. If a copy is missing, fails to download or unpack, or does not match, the installer quietly moves on to the next one. Only the plain file can fail the install, with the same messages as before. The installer prints one new line that names the file it used, such as Downloaded plannotator-darwin-arm64.tar.xz.

In a test on a Mac, with the download limited to 2 MB/s, an update took about 24 s with the .tar.xz, 36 s with the .gz and 94 s with the plain file. Updates from inside Plannotator run the same install script, so they get the smaller download too. Older releases have no compressed copies, so installing one of them downloads the plain file as before. To force the plain download, set PLANNOTATOR_SKIP_COMPRESSED_DOWNLOAD=1.

#3302

A Videos filter on the Artifacts page

The Artifacts page (the Artifacts row in the sidebar) listed videos, but its filters were Images, Pages, Documents and Other files, and every video counted as an image. There was no way to see only the clips. The page now has a Videos filter after Images, and an mp4 or webm sits there instead of under Images. Audio stays under Other files. A thread's own Artifacts grid is unchanged.

#3304

GitLab: a comment on a whole file gets its own thread

On a GitLab merge request, a comment on a whole file used to be folded into the review's main note as **path:** text. It now posts as its own thread on that file, as it already did on GitHub. This works from plannotator review and from the Inbox's Post to GitLab, and was checked on gitlab.com, where each one shows as "started a thread on a file".

If GitLab refuses a file thread, as an older self-hosted GitLab may, that comment goes into the main note as before, so nothing is lost. If the file threads go and the note then fails, a retry sends only what is left, so no file thread is posted twice.

#3245

Code review in the Inbox: off by default

This shows only with Code review turned on in Settings → Capabilities.

  • A pull request's own pictures and videos. On a PR from github.com, the pictures in its description, comments and line threads now show in place, on the PR page and in a thread's full review. Before, each one was a chip saying it opens on the forge. Screenshots written as <img> tags, such as before and after pairs in a table, show as pictures too. A click, or Enter or Space, opens a picture full screen in the attachment viewer, and a video GitHub saved as a link plays there on a plain click. The Inbox fetches each file through your own gh sign-in, only from GitHub's attachment hosts and only when the PR's text names it. A picture that fails to load stays a chip. GitLab merge requests keep their chips for now. #3165

Additional Changes

  • Setup pages for each agent. The site has a new page at plannotator.ai/inbox/agents that lists the agents that work with the Inbox and what each one supports, with a setup page per agent: steps to copy, how to check it works, and fixes for common problems. #3183

Install / Update

macOS / Linux:

curl -fsSL https://plannotator.ai/install.sh | bash

Windows:

irm https://plannotator.ai/install.ps1 | iex

Claude Code Plugin: The install script above also updates the plugin when claude is on your PATH. Otherwise, in a terminal:

claude plugin marketplace update plannotator
claude plugin update plannotator@&#8203;plannotator --scope user

Then restart Claude Code. Inside Claude Code, run /plugin marketplace update plannotator, then open /plugin → Installed → plannotator → Update now.

Pi:

pi update npm:@&#8203;plannotator/pi-extension

OpenCode: Re-run the install script above. It also clears the OpenCode 2 plugin cache.

What's Changed

  • Marketing: pages for each agent and what works with the Inbox by @​backnotprop in #3183
  • Inbox: a PR's own pictures show in its text and open in the viewer by @​backnotprop in #3165
  • Inbox Artifacts page: a Videos filter by @​backnotprop in #3304
  • GitLab: a comment on a whole file becomes its own file thread by @​backnotprop in #3245
  • Installers download a compressed copy of the binary when the release has one by @​backnotprop in #3302

Full Changelog: backnotprop/plannotator@v0.28.63...v0.28.64

v0.28.63: v0.28.63

Compare Source

Follow @​plannotator on X for updates

Missed recent releases?

Release Highlights
v0.28.62 Agents started from the Inbox now work on Windows, pick a model and effort when you start an agent, rules for your agents, written in your own words, post a thread's decisions on its pull request, the Inbox loads faster on a slow connection
v0.28.61 Updates now update the Claude Code plugin too, an agent's chosen face shows on every icon of it, filter the Inbox list by pull request state, Modern dark shows section bands and the Reply button, one conversation no longer shows as two agents
v0.28.60 Click a word to highlight it, a one-time Themes dialog, Settings → Rows rebuilt, tell your agent how you want your rows, starred threads as pills above the list, a pill for new messages out of view, a half-circle face picker with ten Glass colours, a new phone sidebar and reply box
v0.28.59 A quieter Agents section in the sidebar, machine names only when agents run on more than one machine, agent icons that are always gently alive and lean toward your pointer
v0.28.58 Start Codex from New message, an Agents section in the sidebar, start an agent in a folder on any drive, play audio attachments and comment at a moment, Claude Code's Plannotator tools work on Windows
v0.28.57 Pin artifacts, and see every artifact on one page, filter the list by project, date or agent, a thread shows its pull requests and their state, choose what the sidebar shows, and in what order, Ask AI starts from Side in the selection bar
v0.28.56 Questions can show trade-offs and a prototype to try, a thread with many big pictures no longer crashes the tab, Escape closes New message and keeps your draft, read threads stop being bold and keep their place, agent messages that name no thread start a new one
v0.28.55 Floating reply drafts, now a setting under Experimental, open questions sit next to Reply again, a comment box that keeps unsent comments as Drafts, choose how your list looks: Minimal, Balanced or Detailed, update an older linked machine from this Inbox
v0.28.53 Start an agent in a new folder, or from a git URL, "+" on each project row starts a session there, a reaction tray, a thread's Links, Settings → Activity, New message offers the open thread's files, Bro mode: agents write to you in plain words
v0.28.52 Start agents from the Inbox, on by default, a new reply box, Ask AI for everyone, Insights in Settings → Decision data, Plannotator reloads itself after an update
v0.28.51 Starred threads, a note when an agent's session has ended, "Back from snooze", Ask about a past decision, expand arrows in guided reviews
v0.28.50 A faster, lighter Inbox, session names across the Inbox, initiatives on the Board, earlier comments on a file, global comments on Guided Reviews

What's New in v0.28.63

TL;DR

  • New: Pair Grok Bot and other cloud agents from Settings
  • New: Hermes Agent, OpenClaw and Muse Code can use the Inbox
  • New: Add a thread to Priority to keep it on top
  • New: Tag threads, and find each tag in the sidebar
  • Off by default: Pull requests board as a table, with bulk Merge

0.28.63 brings personal and cloud agents into the Inbox. You can pair an agent that runs somewhere else, such as Grok Bot or Muse by Meta, and Hermes Agent, OpenClaw and Muse Code can now message you from the same computer. The Inbox also gets Priority, tags, replies that quote what they answer, and OpenCode in New message. It has 81 PRs. Three come from external contributors, and one of those is a first contribution: welcome @​mauricedesaxe.

Personal and cloud agents

Pair a cloud agent from Settings

A cloud agent is an agent that runs somewhere other than your computer: a Claude Code routine, Grok Bot, Muse by Meta, a Hermes Agent or OpenClaw server, or any other agent you can send a message to. Settings → Cloud agents pairs one. Pick its kind, give it a name, and copy the one message Plannotator shows you. The message is shown only once. Send it to the agent and it sets itself up from a public page on plannotator.ai. A Claude Code routine gets three short pieces for its settings instead. The card then says "Waiting for to connect…" until the agent's first call, and "Connected" after that.

Once paired, the agent shows in New message's To list and in the sidebar's Agents. It can start threads, read the threads it started, was sent or was tagged in, and answer in them. It cannot answer your questions, approve anything, run anything on your computer, open your files, or read any other thread. Its messages pass through Plannotator's relay sealed end to end, so the relay cannot read them. If your computer is asleep, a read says so and a send waits at the relay until the computer is back.

To have the agent start when you write to it, add its wake address and key, then press Send a test. The thread then shows a line such as "Woke Nightly fixer · run started". Without a wake address the agent checks for new messages by itself, and your reply reads "Saved for …" and then "Delivered", like a reply to Muse Code or Cursor. Muse by Meta has no wake address, so it always checks by itself. New pairing stops the old pairing at once, and Remove cuts the agent off. A How does this work? button beside the section's title opens a five-step walk-through in pictures.

The section appears once the Inbox has reached the relay. #3138, #3178, #3187, #3197, #3212, #3223, #3254, #3270

Hermes Agent, OpenClaw and Muse Code on your computer

Three more agents can use the Inbox from the same computer.

  • Hermes Agent (Nous Research) gets the plannotator_inbox tool through a new plugin, and your reply comes back into the Hermes session that asked, as a new turn. Only your own sessions get it: the terminal, the TUI, the Desktop app and your own direct messages. Install it with hermes plugins install backnotprop/plannotator/apps/hermes-plugin --enable, then run plannotator inbox once to turn the tool on. That line installs the plugin from this repository's main branch; the plugin's README explains the reply switch plannotator inbox turns on, and how to turn it off. #3217, #3238, #3249
  • OpenClaw gets the tool in your own chats only: OpenClaw on this computer and your own direct messages, never a shared chat or a channel. Your reply arrives in the same chat as a new message, once. It needs OpenClaw 2026.11.5-beta.1 or newer. The @&#8203;plannotator/openclaw package is not on npm yet; the plugin's README shows how to install it from a checkout of this repository today. #3216, #3251, #3263
  • Muse Code (Meta's coding agent in the terminal) is connected when you run plannotator inbox. Its messages show as Muse Code, with Muse's own mark. Replies don't start a Muse turn, so Muse reads your answer on its next turn, as Gemini CLI and Cursor do. #3209, #3262

Each has a row in Settings → Agents and a mark of its own in the sidebar, the list and the To list. The Inbox tool for Hermes Agent and OpenClaw starts off until plannotator inbox or Settings → Agents turns it on.

After two days of use, a one-time dialog says that your personal agents are welcome in the Inbox, with Connect one, which opens Settings → Cloud agents. It shows only while none is connected. #3280

Starting and managing agents

  • Start OpenCode from New message. To offers "OpenCode · New session" next to Claude Code, Codex and Pi, with a model and a variant (OpenCode's word for effort). Replies, Stop, the run line and Open in Terminal work as they do for Pi and Codex. It needs OpenCode 2 and the Plannotator OpenCode plugin from this release. #3186
  • Pick Codex's model and effort. The "Default model" button now works for Codex too, and Effort shows only the levels the picked model takes. #3177
  • Find a model in a long list. When the Model column lists more than 8 models, it starts with a "Find a model" field that narrows the list as you type, the way Pi's own model selector matches. #3200
  • A machine switch in To. With a linked machine, the top of New message's To list has one button per machine, with how many agents run there. Pick one to see what runs there and what you can start; an asleep machine says since when. #3257
  • Stop and Delete from the sidebar. An agent the Inbox started now has "Stop" and "Delete … session…" in its sidebar menu. Delete asks in a dialog, and its "Also archive its N threads" box is off by default. #3241
  • Rename an agent. Right-click an agent in the sidebar, or use its ⋯, and choose Rename…. The name shows everywhere the Inbox names that agent. Agents still see their own labels. #3180
  • Linked machines keep their own marks. An agent's icon and name, and a star on a thread, now live on the machine the agent or thread belongs to, so every linked window shows the same one. Starring another machine's thread used to fail with "No thread". #3234, #3246
  • Starting agents on a linked machine. Four fixes: the "+" tip no longer names the machine twice, "+" no longer opens an empty To for an asleep machine this page never read, picking an agent kind only another machine has now starts it there, and the Board's New card lists only this Inbox's projects. #3233
  • A Claude Code turn that ends in an error says so. When a session the Inbox started hits a credit, sign-in or rate-limit error, the thread gets one note with Claude Code's own words and a Try again button. A notification follows for Claude Code, Codex and Pi, under the same rules as a question's notification. #3184, #3195
  • Claude Code in VS Code's chat panel. Sessions in the Claude Code extension's panel now get the Inbox tool and are woken by your replies, as in the terminal. This has not yet been tried in a real VS Code panel. #3151, toward #3111 by @​Qwenjin

Plannotator Inbox

Priority

The row menu, the phone's long-press sheet and a thread's ⋯ menu have Add to Priority. The thread moves to a Priority section at the top of the list, shown only when it holds a thread, and stays there until you remove it or archive it. Its row keeps all its marks. A toast offers Undo.

An agent can also mark a thread with send_message's new priority: true, or take the mark out with priority: false. Its instructions say to follow you: use it when you said something matters most to you, and take it out when that is over. An agent's mark is the same as yours, and you can remove it at any time. Agents never see which threads are in Priority. #3232, #3277

A one-time dialog, "Put a thread first in your list", shows how to add a thread to Priority. It comes the day after an update at the earliest, and only if you have never used Priority. #3286

Tags

A thread can now have tags. Add tag is in a row's menu and a thread's ⋯ menu: find a tag, tick it, or type a new name. Tags get their own section in the sidebar, under Starred, with each tag's waiting count; a click lists that tag's threads. Right-click a tag to rename or delete it, with Undo. Typing #Name in your own reply tags the thread too.

On the Board, "Initiative" is now "Tag", and a Board card's tag is the same tag a thread has. Existing initiatives show up as tags, with nothing to move. Agents never see a thread's tags. #3228, #3272

Reply with a quote

Press ↩ on an older message, and the reply box gets one quiet line with that message's author, time and first words. Select words in a message first, and the line quotes those words instead. Your own messages get ↩ too. The sent reply shows the same line, which takes you back to the original. The agent reads which message, or which words, you answered. A plain Reply is unchanged. #3160, closing #3109 by @​Arobotmaster

See which session wrote what

A thread that several agent sessions wrote in used to show only a people icon and a count. The header now shows the sessions' marks and "N sessions"; hover, tap or focus it to see each session's name and state ("waiting on you", "working", "idle", "ended"), and click a name to filter the list to it. Each message in such a thread leads with its session's name. #3163, closing #3108 by @​zane668

Comments

  • On your own messages and on questions. Select words in your own earlier message, or in any part of a question card (the prompt, the context, a choice), to comment on them. A comment never answers or settles a question, and a click on a choice still picks it. #3176
  • Files, voice and a kept draft. The comment card now takes any file, not only pictures, and has the reply box's microphone. A global comment's words and files are kept while you write, so a reload or another window opens the card with them. #2862 by @​iurysza
  • Send waits for comments still saving. On a slow connection, a Send pressed while a comment was still saving went out without it, and the comment stayed behind as a draft. Send now waits, so one reply carries every comment. A review's verdict waits the same way. #3240

Bitbucket pull requests on threads

An agent can now attach a Bitbucket Cloud pull request to its thread by its URL. The row and the header show its state, checks and review, a Bitbucket PR link in a message gets a hover card, and a Board card moves to Done once its PR is merged. Bitbucket has no CLI, so the new config key bitbucketTokenCommand can read the token from a command, such as one that reads your Keychain, instead of from an environment variable or a plain-text file. The token stays in memory and never reaches the agents the Inbox starts. #3076 by @​uvw, closing #3075 by @​uvw

More in the Inbox

  • Filter to Not seen. The list's Filter menu has a new first row, Not seen, that shows only the bold threads. #3226
  • Accept recommended steps aside while you type. On a phone it sat just above the keyboard's Done, and one stray tap replaced your answer. It now hides while you type in a question's fields, keeps your Other… words, and adds Undo to the card's status line. #3268
  • Your reply box is yours. A draft that arrives late, or from another device, no longer drops into a reply box you already opened. It waits beside the box as Restore draft. #3250
  • HTML files open in Interact. An HTML file beside a thread now opens with the pen off, so a click does what the page says. Turn Annotate on and it stays on as you move through the thread's files. ] and [ step between files from inside a page too. #3235
  • Arrow keys between attachments. With focus on one of a message's file tiles, the arrow keys move between that message's tiles. The O keycap now shows only when no file is open. #3237
  • The agent icon picker. A click on an agent's icon now opens the picker instead of stepping through faces. A picked set icon or picture gets its own page with Use this icon, so nothing changes until you press it, and the dialog stays centred. #3227
  • Hide Starred and Projects. Customize sidebar, and the sidebar's right-click menu, can now hide the Starred and Projects sections. #3252
  • Highlighting by touch. On an iPad, a selection made with a finger turned into a highlight mid-drag and lost iOS's handles. It now waits until the finger lifts, and the selection stays. #3142
  • Picture choices open on their set. A waiting question's picture opened from a file tile or the Artifacts view now opens on the question's set, at its choice, as the zoom button does. #3255
  • Pictures inside the choices. Agents are now told to put each option's picture inside its choice, so you can pick by picture, and the hint to resend a question as picture choices fires only when the pictures really are the options. #3179, #3167
  • Two choices that start the same. Two choices with the same words before the dash were read as one answer, and the agent heard the first one whichever you tapped. Each now keeps its whole text. #3260
  • Back on a phone moves an answered thread out of "Waiting on you", and an opened earlier reply now says "Delivered to ". #3258
  • Self-managed GitLab. A merge request attached by its short form (team/project!45) now opens on the project's own GitLab host instead of gitlab.com. #3225
  • A thread's stacked PRs show one under the other in the desktop PR card, instead of squeezed side by side. #3283

Code review in the Inbox: off by default

These show only with Code review turned on in Settings → Capabilities. Until 0.29 that switch shows only if you turned Code review on before.

  • The Pull requests board as a table. A desktop's board bar gets Grid | Table. The table has a row per PR (title, author, state, checks, risk, updated, size) under each repository, with sortable columns that keep a stack together. #3243
  • Select and bulk Merge. Select on the board picks PRs, a whole repository at once or a range with shift-click. Merge N merges the picked PRs that can merge now, one at a time, after a second click to confirm; it lists what stays and why, and reports each result. #3247, #3279
  • One PR opens its own page. Clicking a single open PR in Reviews, or its tile on the board, opens one page for it: the guided review, the diff, its review thread and Details. #2743
  • Open review thread. In a thread's PR list, each open PR has an "Open review thread" line that opens its review thread, or its page in Reviews if it has none yet. #3278
  • GitLab's whole-stack view now opens more lines with the expand arrows, and compares a layer from a fork instead of saying it can't. #3242

Code review

  • Videos in PR descriptions play. A video attached to a GitHub PR description now plays in the review instead of showing as a link. Videos inside an HTML document or embed can also go full screen. #2952 by @​mauricedesaxe, closing #2941 by @​mauricedesaxe
  • GitLab's MR switcher and stacks. plannotator review <MR url> showed an empty switcher. It now lists the project's recent merge requests, finds the stack from them, and numbers them !12. #3248
  • Code colouring. .m files are coloured as Objective-C and .pl as Perl (they were Wolfram and Prolog). justfile, *.gradle, .zshrc and *.svg get colour, as do the fence labels patch, env, postgresql, mysql, gradle and hpp. A suggestion is coloured like the diff beside it. #3281
  • Collapse all files right away. A click on Collapse all files just after opening All changes was dropped while the code view loaded. It now applies once the view shows. #3253

Additional Changes

  • Inbox storage on SQLite, still off unless you set it. inboxSqlite in config.json now has a proof on all six release builds, and fixes for moving the files on Windows and for a 30-second wait after a hard kill. Files stay the default for everyone. #3124
  • Relay. Mailbox creation has a strict per-address limit (per /64 for IPv6), and the relay refuses plain HTTP itself. The relay is deployed on its own. #3273, #3275
  • README and docs. The README describes the Inbox as the review layer for work with many agents and names personal assistants. #3266, #3251
  • Site deploy keeps hand-uploaded files under assets/hosted/. #3276
  • CI. The Test jobs can run on self-hosted runners, never for a fork's or a bot's pull request, and TypeScript is pinned at the root. #3259, #3267
  • Tests. No test can reach the hosted relay any more, and a guard keeps it so. Several flaky and stale tests are fixed. #3274, #3282, #3284, #3224, #3231, #3269, #3285, #3288
  • Release pipeline packs and publishes @&#8203;plannotator/openclaw like the Cline plugin. #3289

Install / Update

macOS / Linux:

curl -fsSL https://plannotator.ai/install.sh | bash

Windows:

irm https://plannotator.ai/install.ps1 | iex

Claude Code Plugin: The install script above also updates the plugin when claude is on your PATH. Otherwise, in a terminal:

claude plugin marketplace update plannotator
claude plugin update plannotator@&#8203;plannotator --scope user

Then restart Claude Code. Inside Claude Code, run /plugin marketplace update plannotator, then open /plugin → Installed → plannotator → Update now.

Pi:

pi update npm:@&#8203;plannotator/pi-extension

OpenCode: Re-run the install script above. It also clears the OpenCode 2 plugin cache.

What's Changed

  • Run the Claude Code mod in the VS Code extension's chat panel by @​backnotprop in #3151
  • Show a Claude Code turn that ended in an API error in its thread by @​backnotprop in #3184
  • Inbox: the folder box's never-start list keeps the folders' order by @​backnotprop in #3224
  • Inbox: say "choices have no pictures" only when the pictures are the options by @​backnotprop in #3167
  • Reply with a quote: say which message, or which words, a reply answers by @​backnotprop in #3160
  • OpenClaw plugin: the Inbox in the owner's own OpenClaw chats, with replies coming back by @​backnotprop in #3216
  • Inbox: comments on your own messages and on questions by @​backnotprop in #3176
  • Inbox: tell agents to put each option's picture in its choice by @​backnotprop in #3179
  • Inbox: wake a paired cloud agent by its webhook (step 1) by @​backnotprop in #3138
  • Inbox: filter the list to threads you have not seen by @​backnotprop in #3226
  • Hermes Agent plugin for the Inbox: tool, owner filter and native reply wake by @​backnotprop in #3217
  • Notify when a launched session's turn ends in an error by @​backnotprop in #3195
  • Name each session in a thread with several sessions by @​backnotprop in #3163
  • Rename an agent from its sidebar row by @​backnotprop in #3180
  • Inbox: a paired cloud agent gets its own agent door (step 2) by @​backnotprop in #3178
  • Inbox: a paired cloud agent reaches the Inbox through the relay (step 4) by @​backnotprop in #3187
  • Inbox: pair a cloud agent from Settings with one message to send it (step 5) by @​backnotprop in #3197
  • Inbox: say when plannotator inbox turns on Hermes's wake switch, and how to undo it by @​backnotprop in #3238
  • Inbox: Muse by Meta as a cloud agent by @​backnotprop in #3212
  • Inbox: a star on a linked machine's thread lives on that machine by @​backnotprop in #3234
  • e2e: the Mark read toast spec taps Undo where the toast rests, after the last Undo has ended by @​backnotprop in #3231
  • Inbox: short GitLab refs open on the project's own GitLab host by @​backnotprop in #3225
  • Inbox: fix starting agents on a linked machine (tip, asleep +, agent kind, Board projects) by @​backnotprop in #3233
  • Inbox: an HTML file opens in Interact, and the pen keeps your choice through the thread by @​backnotprop in #3235
  • Highlighting by touch waits until the selection is finished, and keeps it by @​backnotprop in #3142
  • Inbox: tags for threads and Board cards (step 1: sidebar section, Add tag, the Board says Tag) by @​backnotprop in #3228
  • Inbox: one PR opens its launchpad by @​backnotprop in #2743
  • Inbox: pick Codex's model and effort when starting it by @​backnotprop in #3177
  • Inbox: connect Muse Code by @​backnotprop in #3209
  • Inbox: Bitbucket Cloud pull requests on threads, and a Bitbucket token read from a command by @​uvw in #3076
  • Inbox: Customize sidebar can hide Starred and Projects by @​backnotprop in #3252
  • Inbox: hide the O keycap while a file is open; arrow keys between a message's attachments by @​backnotprop in #3237
  • Inbox storage: SQLite behind a setting; the compiled binary proven on six builds by @​backnotprop in #3124
  • Fix two flaky tests: an early Collapse all click, and the import crash test by @​backnotprop in #3253
  • fix(review): play GitHub attachment videos in PR descriptions by @​mauricedesaxe in #2952
  • Inbox: start OpenCode sessions from New message, with model and variant by @​backnotprop in #3186
  • OpenClaw and Hermes docs: version floor, why the tool starts off, what was tested by @​backnotprop in #3251
  • Inbox: Hermes Agent's mark is its own Nous girl by @​backnotprop in #3249
  • Inbox: Back takes an answered thread out of Waiting on you; an opened reply says Delivered by @​backnotprop in #3258
  • Inbox: a click opens the agent icon picker, a picked icon gets a page with Use this icon, and the dialog sits centred by @​backnotprop in #3227
  • Let a repo variable move the Test jobs to self-hosted runners by @​backnotprop in #3259
  • Inbox Settings: Cloud agents under Agents, six kinds, one calm setup step by @​backnotprop in #3223
  • Questions: keep two choices with the same words before the dash apart by @​backnotprop in #3260
  • Give global comments the reply composer by @​iurysza in #2862
  • Inbox: the Pull requests board as a table by @​backnotprop in #3243
  • Cloud agents: How does this work? walk-through by @​backnotprop in #3254
  • Close the gaps the self-hosted Test proof run found by @​backnotprop in #3267
  • README: describe the Inbox as the review layer and name personal assistants by @​backnotprop in #3266
  • Fix the browser smoke test: Agents link locator matched two links by @​backnotprop in #3269
  • Inbox: open a waiting question's picture choice on its set from a tile or the Artifacts view by @​backnotprop in #3255
  • Thread tag marks read in the same order while open and after a restart (flaky every-read test) by @​backnotprop in #3272
  • Keep a linked machine's agent's face and name on that machine by @​backnotprop in #3246
  • Inbox: Select mode on the Pull requests board by @​backnotprop in #3247
  • Relay: a hard per-IP count on mailbox creation by @​backnotprop in #3273
  • Site deploy: keep hand-uploaded files under assets/hosted/ by @​backnotprop in #3276
  • Tests never contact the hosted relay by @​backnotprop in #3274
  • Accept recommended steps aside while you type, keeps Other words, and can be undone by @​backnotprop in #3268
  • Inbox: the person's Priority (PR 1 of 2) by @​backnotprop in #3232
  • Inbox: a reply to a cloud agent with no wake address reads Saved, then Delivered by @​backnotprop in #3270
  • Inbox: filter long model lists when starting an agent, as Pi's model selector does by @​backnotprop in #3200
  • Inbox: Muse's mark is Meta's blue Muse squiggle by @​backnotprop in #3262
  • Settings and OpenClaw README: why OpenClaw and Hermes start off; how to install OpenClaw before it is published by @​backnotprop in #3263
  • Inbox priority spec: never the hosted relay by @​backnotprop in #3284
  • relay: IPv6 /64 brake key, https-only Worker, live check (builds on #3273) by @​backnotprop in #3275
  • Inbox: a Send waits for comments still saving, so one reply carries them all by @​backnotprop in #3240
  • Tests never contact the hosted relay: unit tests' hand-built child envs by @​backnotprop in #3282
  • Inbox: a thread's stacked PRs one under the other in the desktop PR card by @​backnotprop in #3283
  • Colour .m, .pl, more file names and fence labels; colour suggestions like their diff by @​backnotprop in #3281
  • Inbox: Stop and Delete on a sidebar agent's menu by @​backnotprop in #3241
  • Inbox: bulk Merge on the Pull requests board by @​backnotprop in #3279
  • feat(inbox): one-time dialog announcing personal agents by @​backnotprop in #3280
  • Fix two stale browser tests: comment pictures input, Accept recommended after a note by @​backnotprop in #3285
  • Inbox: "Open review thread" under each open PR in a thread's PR list by @​backnotprop in #3278
  • Inbox: an agent can mark a thread Priority (send_message priority: true|false) by @​backnotprop in #3277
  • Inbox To: a machine switch for linked machines by @​backnotprop in #3257
  • Pages only spec: expect the window's picture policy as served (one hosted folder) by @​backnotprop in #3288
  • Inbox: a draft that arrives after the reply box was opened waits behind Restore draft by @​backnotprop in #3250
  • GitLab: MR switcher list and stack discovery in the review app by @​backnotprop in #3248
  • Inbox: expand arrows and fork layers in GitLab's whole-stack view by @​backnotprop in #3242
  • Inbox: a one-time Priority dialog in the line of one-time dialogs by @​backnotprop in #3286
  • Release: pack and publish @​plannotator/openclaw like @​plannotator/cline by @​backnotprop in #3289

New Contributors

  • @​mauricedesaxe made their first contribution in #2952

Contributors

@​uvw wanted Bitbucket pull requests on Inbox threads without leaving the token in every program's environment, filed it as #3075, and built it in three layers: Bitbucket links read as pull request refs, a token read from a command and held only in memory, and the Inbox's rows, hover cards and Board marks. A clean-room test of the agent text, in the same PR, caught a smaller model storing a Bitbucket PR as a GitHub ref, and the wording was fixed.

@​mauricedesaxe reported that a video attached to a PR description showed as a bare link (#2941), then made it play in the review, with a fallback to the link whenever the video can't load.

@​iurysza gave global comments pictures, files, voice and a kept draft. That work became the one comment card the Inbox now uses everywhere.

Thanks also to the people whose issues shaped this release:

  • @​Arobotmaster asked for Reply to show which message, or which words, it answers (#3109)
  • @​zane668 reported that a thread's header showed only a count of sessions, not their names (#3108)
  • @​Qwenjin reported that Inbox replies did not wake Claude Code sessions in the VS Code extension (#3111)

Full Changelog: backnotprop/plannotator@v0.28.62...v0.28.63

cesarferreira/stax (github:cesarferreira/stax)

v0.120.0: v0.120.0

Compare Source

[0.120.0] - 2026-11-14

🚀 Features

  • (wt) Add unlock action to worktree dashboard (#949)
  • (wt) Add lock/unlock CLI commands and dashboard lock key (#950)

⚙️ Miscellaneous Tasks

  • Release
dlvhdr/gh-dash (github:dlvhdr/gh-dash)

v4.26.3: v4.26.3

Compare Source

Just a few bug fixes

To update run:

gh extension upgrade dash

Changelog

Bug fixes


If you enjoy dash, consider making a donation ❤️

Have questions? Join our Discord community!


DASH Logo

@scottames-github-bot

Copy link
Copy Markdown
Contributor
anomalyco/opencode (opencode)

v2.3.0: v2.3.0

Compare Source

Highlights

  • Background Subagents by Default: Subagents now return immediately, continue in the background, and report back whenever they become idle. You can keep working in the parent session while multiple subagents run concurrently. (#63382)
  • Quieter Transcripts by Default: The TUI now summarizes each run of tool calls and thoughts into one collapsible activity row, so the answer is easier to follow. To see every step again, set Verbosity to medium or high in settings, or set session.verbosity in your TUI config; an existing setting is kept. (#63207)
  • Jump to an Earlier Prompt: In the desktop app, open Jump to message from the command palette or press Cmd+Alt+G (Ctrl+Alt+G on Windows and Linux) to search prompts across the current session and jump directly to one. (#63585)

Core

Improvements

  • Subagents now always run in the background, return their session ID immediately, and report results to their parent whenever they become idle. (#63382)
  • Added experimental support for MCP events, behind the mcp_events flag. (#63254, #63261, #63269)
  • Shell commands now survive server handoffs and keep their output when interrupted.
  • Added experimental support for moving a shell command to the background when its timeout expires, behind the shell_timeout_background flag. With the flag on, an explicit timeout on a background command stops it. (#63024, #63703)
  • Local Windows shell commands now run through the process daemon.
  • Added support for freeform tool input on compatible models.
  • Added LM Studio decision-model support.
  • Agents are now told when their session is a fork. Thanks @​hasta84. (#63235)
  • Tool output truncation now keeps the beginning of the output and preserves a usable preview if the full output cannot be saved.
  • Tail reads no longer load the entire file into memory.
  • Providers can present a client certificate for gateways that require mutual TLS. Set settings.tls with cert, key and an optional passphrase on the provider; values accept {file:} and {env:} like apiKey. (#61832)
  • When a subagent goes idle while its own background work is still running, its report to the parent now says it is still running, so the parent waits for the final report instead of treating the partial answer as done. (#63675)
  • Code Mode gets simpler structured results from file and skill tools: write and edit return their confirmation as a string, patch returns an empty result, and skill returns the skill's directory and content. (#63616, #63635, #63618, #63623)

Bug fixes

  • Fixed case-only file renames in patches on case-insensitive filesystems.
  • Fixed stale thinking being retained after Claude Agent prompts or tools change.
  • Fixed directly driven child sessions not resuming after a restart.
  • Fixed plugin replacement stopping when cleanup of an earlier plugin fails.
  • Fixed MCP OAuth refreshes and localhost redirects when a server rewrites 127.0.0.1.
  • Fixed saved API keys being omitted from local-model discovery.
  • Local model discovery (Ollama, LM Studio, vLLM) waits up to 15 seconds per request instead of 1, so remote or tunnelled endpoints list their models, and a slow endpoint no longer delays other endpoints or config reloads. (#63700)
  • In Code Mode, calling a namespace as if it were a tool now suggests up to three real tools under it. (#63697)
  • Fixed retryable provider streams losing completed work when interrupted.
  • Fixed GitHub Copilot requests using the wrong endpoint before models finish loading.
  • Fixed exhausted request rate limits being treated as terminal. Thanks @​Kyle-j-bush. (#59816)
  • Fixed LM Studio models with a null context length and accepted decision-type models. Thanks @​tomzhu1024. (#56214)

TUI

Improvements

  • Transcript verbosity now defaults to low, which summarizes each run of tools and thoughts into one activity row. A session.verbosity you already set is kept. (#63207)
  • Session IDs found in messages can now be opened directly.
  • Activity tabs are clickable and open the correct view.
  • Shell mode has its own prompt color under the new designs.

Bug fixes

  • Restored pasted text when undo brings back its placeholder.
  • Restored the live draft after browsing prompt history.
  • Fixed copying a paste from within the prompt selection.
  • Preserved the Mini composer caret when closing the command palette.
  • Prevented image bytes from being retained in transcript storage when image previews are disabled.
  • Fixed paste-chip contrast across light and dark themes.
  • Fixed plugin-provided themes updating live.
  • Session lists now open at the top rather than at the current session.
  • Mini scrollback now shows the subagent card instead of obsolete launch instructions.

Desktop

Improvements

  • Added Jump to message to the command palette with Cmd+Alt+G / Ctrl+Alt+G, including prompts not yet loaded in the timeline. Thanks @​usrnk1. (#63585)
  • Added the experimental Recent sessions sidebar, with cross-server recency, local pins, reordering, and standard session-row actions.
  • Recent sessions are limited to the last seven days and 30 rows, and can be hidden or muted.
  • Added an experimental customizable sessions sidebar.
  • Mermaid diagrams can now be maximized for zooming and panning. (#59250)
  • Added Alt+Enter to place a follow-up first in the queue and Mod+Enter to steer the next queued prompt.
  • Holding the modifier key now shows tab shortcut numbers.
  • Each server’s terminal shell can be selected from its menu.
  • Added a free-limit panel in place of the composer when applicable.
  • Session IDs are easier to find and copy.

Bug fixes

  • Recent sessions now keep stable recency ordering through list reloads, renames, and completed runs.
  • Fixed browser panes not retrying after server plugins finish loading.
  • Fixed mention suggestions being recreated while typing.
  • Fixed SSH prompts failing to advance or close after connection.
  • Fixed pasted provider-auth redirect URLs being rejected.
  • Restored message footers in the New timeline.
  • Fixed links whose labels contain inline code.
  • Fixed the desktop main process freezing while probing the login-shell environment.
  • Fixed the drag region after changing layout direction.
  • Fixed vertical-tab previews snapping to the wrong tab.
  • Fixed the file-tree sidebar opening animation.
  • Fixed pairing QR-code contrast in light themes. Thanks @​ssskay. (#63220)
  • Fixed activity-tab navigation and click handling. Thanks @​OpeOginni. (#60168)

SDK

Improvements

  • Event subscriptions can now receive experimental.mcp.event events from MCP event subscriptions.
  • Model capability schemas now advertise supported freeform tool-input formats.
  • Session throughput is now measured from the first streamed token.
  • Session creation documentation now clarifies the parentID field.

Extensions

Improvements

  • Promise-based tools can cooperatively stop through ToolContext.signal.
  • Added the experimental session.fork hook.
  • Promise plugin cleanup failures no longer prevent subsequent plugin replacements.
  • @&#8203;opencode/plugin/effect now exports Tool, so an execute.before hook can reject a call with Tool.Error without importing @&#8203;opencode/schema/tool. (#63698)

Skipped Packages

GitHub Release Notes Unavailable

  • droid: No GitHub release was found for 1.12.1

@renovate
renovate Bot force-pushed the renovate/mise-packages branch from a15757e to 76022e6 Compare November 18, 2026 01:26
@renovate
renovate Bot force-pushed the renovate/mise-packages branch from 76022e6 to 9e7f00d Compare November 18, 2026 11:09
@renovate
renovate Bot merged commit 4307820 into main Nov 18, 2026
5 of 6 checks passed
@renovate
renovate Bot deleted the renovate/mise-packages branch November 18, 2026 11:18
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants

⌂ 换网址