Skip to content

chore(deps): update ⬆️ mise-packages - #1096

Merged
renovate[bot] merged 3 commits into
mainfrom
renovate/mise-packages
Oct 6, 2026
Merged

renovate[bot] merged 3 commits into
mainfrom
renovate/mise-packages

Conversation

@renovate

@renovate renovate Bot commented Oct 5, 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 0.12.21 → 0.12.22 0.12.23 age adoption passing confidence
aqua:borghei/ink tools minor 0.7.0 → 0.10.0 0.11.1 (+1) age adoption passing confidence
aqua:dagger/dagger tools patch 0.21.9 → 0.21.10 age adoption passing confidence
aqua:earendil-works/pi tools patch 0.99.1 → 0.99.2 age adoption passing confidence
aqua:openai/codex tools minor rust-v0.159.2 → rust-v0.160.0 rust-v0.160.1 age adoption passing confidence
aqua:vercel-labs/agent-browser tools patch 0.38.1 → 0.38.2 age adoption passing confidence
droid (source) minor 0.231.0 → 0.233.0 0.234.0 age adoption passing confidence
github:ZenNotes/tui tools minor v0.5.0 → v0.6.2 age adoption passing confidence
github:anthropics/claude-code tools patch v2.1.285 → v2.1.287 v2.1.291 (+3) age adoption passing confidence
github:backnotprop/plannotator tools patch v0.27.22 → v0.27.25 v0.28.6 (+6) age adoption passing confidence
github:dlvhdr/gh-enhance tools minor v0.7.2 → v0.8.0 age adoption passing confidence
github:janosmiko/lfk tools patch v0.19.1 → v0.19.2 v0.19.3 age adoption passing confidence
github:modem-dev/hunk tools minor v0.22.0 → v0.23.0 age adoption passing confidence
github:nolabs-ai/nono tools minor v0.78.0 → v0.79.0 age adoption passing confidence
rust (source, changelog) tools minor 1.98.1 → 1.99.0 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 October 5, 2026 10:17
@renovate renovate Bot added the dependencies label Oct 5, 2026
@renovate
renovate Bot enabled auto-merge (squash) October 5, 2026 10:17
@scottames-github-bot

scottames-github-bot Bot commented Oct 5, 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)

0.12.22: 0.12.22

Compare Source

Release Notes

Released on 2026-10-01.

Python

  • Add CPython 3.10.22, 3.11.17, 3.12.15, 3.13.16, and 3.14.8 (#22147)

Enhancements

  • Accept uppercase release suffixes in wheel platform tags (#22113)
  • Record workspace-member default groups in lockfiles (#22010, #22103)
  • Record workspace-member dependency-group Python requirements in lockfiles (#22044, #22103)
  • Record default groups for non-project workspace roots in lockfiles (#22104)
  • Record dependency-group Python requirements for non-project workspace roots in lockfiles (#22104)
  • Format URLs and paths consistently in CLI messages (#21937)
  • Hide the unsupported --offline option from uv publish help (#22124)

Preview features

  • Honor --no-default-groups in uv audit (#22090)
  • Report a clear error when uv audit or uv tool audit runs offline and hide the unsupported option from help (#22114)

Configuration

  • Add UV_PYTHON_ARCH to select an interpreter architecture independently of its Python version (#22098)

Performance

  • Reduce uv's binary size by compressing embedded Python download metadata (#22126)

Bug fixes

  • Verify unchanged requirements against existing lockfile hashes when relocking (#22083)
  • Honor dependency-group Python requirements at non-project workspace roots (#22101)
  • Use each selected workspace member's recorded default groups during frozen sync (#22015)
  • Avoid false entry-point warnings for required workspace members (#22112)

Other changes

  • Raise the minimum supported Rust version for building uv to 1.97 and update the toolchain to Rust 1.99 (#22121)

Install uv 0.12.22

Install prebuilt binaries via shell script

curl --proto '=https' --tlsv1.2 -LsSf https://releases.astral.sh/github/uv/releases/download/0.12.22/uv-installer.sh | sh

Install prebuilt binaries via powershell script

powershell -ExecutionPolicy Bypass -c "irm https://releases.astral.sh/github/uv/releases/download/0.12.22/uv-installer.ps1 | iex"

Download uv 0.12.22

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>
borghei/ink (aqua:borghei/ink)

v0.10.0: v0.10.0

Compare Source

Added

Changed

Fixed

What's Changed

Full Changelog: borghei/ink@v0.9.0...v0.10.0

v0.9.0: v0.9.0

Compare Source

Added

Fixed

Security

Changed

  • NO_COLOR now also drops bold and underline in --plain.
  • The unused C regex dependency (oniguruma) is gone; syntax highlighting runs on the pure-Rust engine.
  • The minimum supported Rust version is declared as 1.90.

What's Changed

Full Changelog: borghei/ink@v0.8.0...v0.9.0

v0.8.0: v0.8.0

Compare Source

Added

  • Link-hint mode shows each link's text next to its URL. The f popup used to list bare URLs, which made it hard to tell which letter belonged to which link in the document. Each row now reads letter, link text, URL. Text that wraps across lines is joined back together; autolinks and mailto: addresses still show the URL once. The popup grows up to 100 columns to fit, and shortens the text before the URL when a row is too long. Y (copy URL) uses the same rows. (chore(deps): update docker/setup-buildx-action action to v2.5.0 #8, chore(deps): update golang.org/x/exp digest to 133eef4 #13)
  • $XDG_CONFIG_HOME is honored on every platform. When it is set to an absolute path, ink reads $XDG_CONFIG_HOME/ink/config.toml and loads custom themes from $XDG_CONFIG_HOME/ink/themes/ — so macOS users who keep dotfiles under ~/.config no longer need ~/Library/Application Support. Unset, empty, or relative values fall back to the platform default, exactly as before, and an existing config in the platform folder stays in use until $XDG_CONFIG_HOME/ink exists, so upgrading never orphans it. ink config path prints whichever location is in effect. (chore(main): release 0.2.0 #5, chore(deps): update ⇡ aqua aquaproj/aqua-registry to v3.157.0 #11)
  • Conda and Pixi install instructions, for the community-maintained conda-forge package: conda install -c conda-forge ink-md or pixi global install ink-md. Thanks to @​mariusrueve. (chore(deps): update docker/build-push-action action to v4 #9)

Fixed

  • Linux binaries run on Ubuntu 22.04 LTS again. Release builds had moved to a runner with glibc 2.39, so the binary, the .deb/.rpm, and Homebrew on Linux all failed on 22.04 with GLIBC_2.39 not found. Linux builds are now pinned to a glibc 2.35 baseline (Ubuntu 22.04, Debian 12 and newer), and the release fails if a binary ever needs a newer glibc. (chore(deps): update ⇡ aqua homeport/dyff to v1.5.7 #6, chore(main): release 0.3.0 #10)

Security

Docs

What's Changed

New Contributors

Full Changelog: borghei/ink@v0.7.0...v0.8.0

dagger/dagger (aqua:dagger/dagger)

v0.21.10: v0.21.10

Compare Source

v0.21.10 - 2026-09-30

Added

  • Add opt-in engine CPU and memory telemetry from cgroup v2 by @​matipan in engine: add opt-in cgroup resource telemetry dagger/dagger#14285
    Enable telemetry.resourceMetrics in /etc/dagger/engine.json and set
    OTEL_EXPORTER_OTLP_METRICS_ENDPOINT in the engine environment. The new
    resource metrics use a separate OTLP export path. Client telemetry is
    unchanged, and engine resource telemetry is disabled by default.

Fixed

  • Container.withServiceBinding now works for a service whose custom hostname by @​Zaba505 in core: resolve bound services by their registered FQDN dagger/dagger#13751
    was scoped to another module's DNS domain. A service created with
    withHostname is namespaced into the domain of whichever module first starts
    it, so a module that started its own service before handing it to a caller
    left that caller's withExec failing at hosts-file setup with
    lookup <hostname> ... no such host. Binding the service explicitly now
    resolves it by the name it actually registered under. Reaching a module's
    custom hostname by bare DNS remains scoped to that module.
  • dag.CurrentModule().Source() and dag.CurrentModule().GeneratedContextDirectory() by @​marcosnils in https://github.com/dagger/dagger/pull/
    no longer re-resolve the running module's declared dependencies. The module's
    already-loaded dependency DAG is reused for codegen, so these APIs now work in
    modules whose dependencies point at private git repositories even when the
    runtime caller does not hold the author's credentials.

Contributors

Special thanks to our external contributors this release!

  • @​Zaba505

What to do next?

earendil-works/pi (aqua:earendil-works/pi)

v0.99.2: v0.99.2

Compare Source

New Features

  • MCP servers stay out of the way: servers with the default codemode exposure are no longer listed in the codemode description and no longer block the first prompt. They appear in a short system prompt section, and scripts find their tools with searchTools() and describeNamespace(). See Control tool exposure.
  • More MCP authentication options: oauth.clientName for servers that only accept known OAuth clients, and "auth": { "provider": "<provider>" } to authenticate HTTP servers with a provider's /login token. See Authenticate with OAuth.
  • Anthropic workload identity federation from the Anthropic SDK environment variables. See Use an API key from the environment.
  • /reload enables tools newly added to the defaultTools setting. See Tools.

Added

  • Added a description field for MCP servers (pi mcp add --description), shown with the server in the system prompt and used to rank its tools in tool search, and a describeNamespace(name) codemode helper that returns a namespace's instructions and tool names. describeNamespace() and searchTools() accept a namespace as mcp__dev-radius, mcp__dev_radius, dev-radius, or dev_radius.
  • Added an oauth.clientName setting for MCP servers (pi mcp add --oauth-client-name) to change the client name sent during OAuth client registration, for servers that only accept known clients (#10226).
  • Added "auth": { "provider": "<provider>" } for HTTP MCP servers to send a provider's current /login token as the bearer token instead of using MCP OAuth. The token is read on every request, so provider refreshes apply. Only allowed in the global mcp.json and from extensions, and requires https except on loopback hosts.
  • Added Anthropic workload identity federation from the ANTHROPIC_FEDERATION_RULE_ID, ANTHROPIC_ORGANIZATION_ID, and ANTHROPIC_IDENTITY_TOKEN_FILE environment variables (see Providers) (#10177, #10242 by @​philfreo).
  • /reload now enables tools newly added to the defaultTools setting. Tools removed from it stay enabled, tools turned off during the session stay off unless newly added, and --tools, --no-tools, and --no-builtin-tools still override the setting (#10245).

Changed

  • MCP servers with the default codemode exposure no longer appear in the codemode description; scripts find them with searchTools(). codemode-deferred is now an alias for codemode. Use direct exposure for tools the model should see without searching (#10212).
  • The codemode description no longer includes deferred tools, tool counts, or MCP server instructions, so it no longer changes when MCP servers connect or change their tools. The tool_search description no longer lists the servers whose tools it can load, for the same reason. Servers are listed instead in an mcp_servers system prompt section with a one-line summary, updated at the start of each prompt; a changed section is appended to the conversation. Scripts read server instructions with describeNamespace() (#10212).
  • The first prompt no longer waits for MCP servers without direct tools. They connect in the background and are waited for when a codemode script names them, a script searches tools, or tool_search runs (#10212).

Fixed

  • Fixed new sessions intermittently ignoring the saved default model, or warning that no models are available, when it belongs to an extension-registered native provider with a stored credential (#9962, #10190 by @​davidbrai).
  • Fixed the /mcp sign-in URL not being clickable when it wraps across lines, by emitting it as a terminal hyperlink with a Cmd/Ctrl+click to open line like /login (#10186).
  • Fixed codemode image() accepting malformed base64 data or unsupported image types, which persisted an invalid image block that made every later provider request fail with HTTP 400 (#10215).
  • Fixed codemode failing to start its script worker from the standalone Windows executable (#10204).
  • Fixed prompt submission slowing down with session length, because resolving the session's model selection looked up the model catalog once per assistant message (#10198).
  • Fixed model lookups slowing down for providers with a refreshed pi.dev catalog, because merging remote catalog models took quadratic time.
  • Fixed the built-in-tool-renderer.ts and minimal-mode.ts extension examples removing the built-in tools' summaries and guidelines from the system prompt (#10072, #10193 by @​christianklotz).
  • Fixed context overflow detection for Z.AI CN endpoint Prompt exceeds max length errors (#10208).
  • Fixed Anthropic requests failing when a tool schema uses keywords Anthropic strict tool use rejects, such as minimum/maximum; such tools are now sent non-strict (#9953).
  • Fixed provider retries firing immediately when a Retry-After header contains an unparseable date; they now use exponential backoff (#9571).
  • Fixed extension commands registered without a string name or handler crashing pi when typing /; the extension now fails to load with an error instead (#10054).
  • Fixed collapsed codemode and MCP tool results filling the screen when the output is one long line, such as minified JSON. Like bash output, the preview is now limited to wrapped lines instead of logical lines.
  • Fixed codemode.mode: "only" listing read, bash, edit, and write in the system prompt's tool list although requests only declare codemode (#10192).
  • Fixed codemode scripts calling the wrong MCP tool when two tool names differ only in - and _, such as read-file and read_file. Like in Codex, MCP tool and namespace names now replace - with _ (mcp__my-server__x is now mcp__my_server__x), colliding tools of a server all get a hash suffix, and server names that differ only in - and _ are rejected (#10239).
openai/codex (aqua:openai/codex)

rust-v0.160.0: 0.160.0

Compare Source

New Features

  • Browse older tasks in the agent command center with a keyboard-accessible “Show more” action. (#49106)
  • Select transcript text and paste with middle-click in fullscreen mode on supported local Linux X11 terminals. (#49112)
  • Start sessions outside a project with workspace defaults when policy permits, and restore saved permissions when resuming. (#49160)
  • Added opt-in Guardian review capabilities to retrieve earlier user instructions and include context from agent handoffs. (#49036, #49057)

Bug Fixes

  • Unsent queued messages now resume after reconnection once uncertain submissions are resolved, avoiding duplicate sends. (#49105)
  • The terminal UI now preserves server provider, reasoning-summary, and verbosity settings and shows the correct sessions in resume and fork history. (#49144, #49161, #49171)
  • Fixed Windows sandbox PowerShell fallbacks and long-path permission repairs, and suppressed unwanted console windows from background helpers. (#49019, #49058, #49098, #49164, #49386)
  • Subagents now retain environments that are still starting and receive their configuration or preparation failure. (#49075)
  • Prevented SQLite stalls during connection setup and logging, and surfaced initialization errors instead of masking them as timeouts. (#49032, #49102)
  • Explicit provider model catalogs no longer include unsupported bundled models or reuse stale entries after refresh failures. (#49135)

Documentation

  • Clarified how provider credentials use the configured storage backend and how env_key identifies the API-key environment variable. (#49118)

Chores

  • Reduced repeated plugin-loading work by caching parsed manifests and reusing HTTP connections for remote plugin requests. (#49099, #49100)
  • Added background reclamation of unused log database space to reduce disk usage. (#49069)

Changelog

Full Changelog: openai/codex@rust-v0.159.0...rust-v0.160.0

  • #48983 Avoid full metadata rewrites for thread timestamp updates @​jif-oai
  • #49000 Isolate the memory startup metadata test from Git enrichment @​jif-oai
  • #49019 Use a compatible PowerShell fallback for the Windows MXC sandbox @​iceweasel-oai
  • #49028 Use the numeric ioctl value in the macOS sandbox policy @​aionescu-oai
  • #49031 Clarify ChatGPT sign-in success copy @​bc-openai
  • #49032 Avoid SQLite stalls from connection setup and stderr span logging @​jif-oai
  • #49036 Add opt-in conversation history retrieval to Guardian reviews @​felixxia-oai
  • #49037 Show the Plan mode cycling hint in the fullscreen status line @​fcoury-oai
  • #49038 Preserve encrypted agent messages in Guardian reviews @​felixxia-oai
  • #49041 Copy selections within inline code as plain text @​fcoury-oai
  • #49043 Update Pro plan display names in the TUI @​etraut-openai
  • #49057 Add handoff-aware root context for Guardian reviews @​jif-oai
  • #49058 Fix Windows sandbox ACL repair for long runtime paths @​darius-oai
  • #49060 Update Guardian messaging snapshots for native agent messages @​dkovalenko-oai
  • #49065 Update Guardian handoff snapshot for separate agent messages @​cassirer-openai
  • #49067 Keep configuration values out of Windows sandbox policy events @​zm-oai
  • #49069 Reclaim unused SQLite log database pages in the background @​dkovalenko-oai
  • #49073 Surface realtime voice catalog failures in the TUI @​etraut-openai
  • #49074 Propagate Cargo package versions to Bazel Rust targets @​tamird
  • #49075 Preserve pending environments when spawning subagents @​sayan-oai
  • #49076 Avoid collecting unused Git metadata in skill analytics @​tamird
  • #49079 Update and centralize TUI subscription labels @​etraut-openai
  • #49082 Skip remote Git discovery for Guardian diff paths @​jif-oai
  • #49084 Track app-server running turns incrementally @​tamird
  • #49089 Render follow-up directive labels in the TUI and copied responses @​etraut-openai
  • #49093 Simplify startup promotions to platform-specific desktop app tips @​etraut-openai
  • #49096 Update h2 from 0.4.16 to 0.4.19 in Cargo and Bazel lockfiles @​cassirer-openai
  • #49097 Notify lifecycle extensions of compaction usage limits @​xli-oai
  • #49098 Resolve Windows sandbox PowerShell fallbacks on the exec server @​zm-oai
  • #49099 Cache parsed plugin manifests across plugin workflows @​dkovalenko-oai
  • #49100 Reuse the HTTP connection pool for remote plugin requests @​dkovalenko-oai
  • #49102 Preserve SQLite vacuum modes and surface pool initialization errors @​bc-openai
  • #49103 Balance Windows Bazel test shards using duration estimates @​jgershen-oai
  • #49105 Resume unsent TUI input after reconnecting @​etraut-openai
  • #49106 Add history pagination to the agent command center @​bc-openai
  • #49112 Add X11 primary selection and middle-click paste support @​fcoury-oai
  • #49114 Point remote compaction tests at the mock ChatGPT server @​OLI-OAI
  • #49117 Attribute analytics requests to each thread's product SKU @​papayo-oai
  • #49118 Correct provider authentication storage documentation @​celia-oai
  • #49119 Add recovery guidance to content-filter retries @​won-openai
  • #49127 Deduplicate cloud and executor skill listings before budgeting @​TAFOYA-OAI
  • #49130 Move content-filter guidance into the shared Responses retry handler @​won-openai
  • #49135 Treat explicit provider model catalogs as authoritative @​andrewgu-oai
  • #49136 Remove the plus separator after Option symbols in TUI key hints @​bc-openai
  • #49138 Expose original error details to turn lifecycle contributors @​bryanashley
  • #49144 Preserve server reasoning summary and verbosity settings in the TUI @​etraut-openai
  • #49145 Hide reasoning summary settings in /status for server connections @​etraut-openai
  • #49147 Simplify cloud task base URL normalization @​akira-oai
  • #49153 Omit blockquote markers when copying quoted selections in the TUI @​bc-openai
  • #49160 Support projectless TUI sessions with workspace defaults @​etraut-openai
  • #49161 Honor app-server provider defaults in the TUI @​etraut-openai
  • #49164 Suppress Windows console windows for background subprocesses @​etraut-openai
  • #49171 Fix model provider lookup for TUI history @​etraut-openai
  • #49386 [0.160] Backport remaining Windows console fix to frozen alpha.6 @​andrewgu-oai
  • #49763 [0.160] Backport maintenance-line catalog and security reminder updates @​andrewgu-oai
vercel-labs/agent-browser (aqua:vercel-labs/agent-browser)

v0.38.2: v0.38.2

Compare Source

Bug Fixes

  • Fixed auth vault login to pick usable controls when hidden duplicates exist, and to bind credential entry to the selected field so replaced fields or redirected focus are rejected before submitting (#2014)
  • Fixed chat mode to allow webmcp, skills, and other top-level browser commands, so the model uses page WebMCP tools instead of falling back to eval (#2015)
  • Fixed Kernel profiles so KERNEL_PROFILE_NAME sessions send the profile as an object instead of failing with a 400, and added KERNEL_PROFILE_SAVE_CHANGES to opt into saving changes back (#2004)
  • Fixed Chrome freezing after launch by draining its stderr for the browser's lifetime, so a full log pipe no longer blocks the browser (#2003)
  • Fixed Browser Use by switching to Cloud V4, which creates, attaches to, and stops the same browser with bounded timeouts (#1879)
  • Fixed Vercel Sandbox shared memory detection by measuring /dev/shm capacity and adding --disable-dev-shm-usage below 256 MiB, so Chrome no longer terminates renderers on the undersized mount (#1890)

Improvements

  • Upgraded the eve integration from eve 0.47.3 to 0.57.0, so apps on eve 0.50 and later build again (#1945)

Documentation

  • Updated the contact sheet example with the loading-flash demo output (#1871)

Contributors

  • @​Railly
  • @​benjamincanac
  • @​boatri
  • @​luxleader
  • @​petehunt
  • @​robertjamesprior
  • @​simonellefsen
  • @​zyz619963502zyz
ZenNotes/tui (github:ZenNotes/tui)

v0.6.2: ZenNotes CLI 0.6.2

Compare Source

ZenNotes CLI 0.6.2

From this release on, every ZenNotes CLI release carries a signed manifest, and ZenNotes desktop uses it to keep the zn it manages up to date. CLI fixes no longer wait for a desktop release.

Signed release manifest

Each release now includes two more files:

  • terminal-release.json: the version, the desktop integration protocol, the source commit, and the SHA-256 of each macOS and Linux archive. It uses the same format as the CLI pin inside ZenNotes desktop.
  • terminal-release.json.sig: an Ed25519 signature over those exact bytes, by key zn-release-1. The public key is in packaging/release-signing/zn-release-1.pub.

The release workflow builds the manifest from the release archives, signs it, and checks it against the committed public key before uploading, so a release can't ship a manifest the desktop would reject. To check a release by hand:

go run ./scripts/releasemanifest verify -manifest terminal-release.json -sig terminal-release.json.sig -public-key-file packaging/release-signing/zn-release-1.pub

Desktop-managed installations

ZenNotes desktop 2.60.0 and later check the latest release once a day for a zn installed from Settings > CLI. They install it only when the signature, the archive checksum and the new binary's integration check all pass, and they keep the previous version on disk. On those installations zn update now points at Settings > CLI > Check for updates instead of telling you to update the desktop app. zn update --check still reports the latest release.

Upgrade

zn update

Standalone macOS and Linux installations update in place and keep zn.previous as a backup. Homebrew users run brew update && brew upgrade zn. With Go:

go install github.com/ZenNotes/tui/cmd/zn@&#8203;v0.6.2

Or download an archive below. Desktops from ZenNotes 2.60.0 on pick this release up by themselves within a day; earlier desktop releases keep the CLI they bundle.

Verification

The release workflow ran the Go tests, built the archives with GoReleaser, then built, signed and checked this release's manifest against the committed public key before uploading it (run 36882848479). Checked again after publishing:

  • The signature verifies with the committed public key and with the key built into ZenNotes desktop.
  • The manifest names 0.6.2, protocol 1 and commit 140a38f, and all four macOS and Linux archives match it, checksums.txt and their downloaded bytes.
  • zn --version reports v0.6.2 and the integration check answers protocol 1, version 0.6.2. On a desktop-managed path, zn update points at Settings > CLI > Check for updates.
  • A ZenNotes desktop development build that bundles 0.6.0, with no test overrides, found this release on GitHub, verified it with its built-in key and updated itself to 0.6.2.
  • The Homebrew formula in zennotes/tap points at 0.6.2; brew style reports no offenses.

v0.6.1: ZenNotes CLI 0.6.1

Compare Source

ZenNotes CLI 0.6.1

A fix release from a full QA sweep of every zn command against a local vault, a Docker-hosted ZenNotes server, and native managed servers under systemd, plus MCP over stdio and the TUI in a real terminal. Two of the fixes come from reports in Discord. Every fix carries a regression test.

Faster startup everywhere

Every zn command, zn --version included, waited five seconds on terminals that never answer a background-color query (the Linux console, some IDE and serial terminals): the terminal library asked for the background before main ran and timed out. Startup no longer queries the terminal. The TUI's automatic theme and zn read --pretty still ask, once and on purpose, when they need the real answer.

Vaults and servers you can actually forget

zn vault list now shows where each entry comes from: terminal for the vaults and servers zn saved, app for the ones the ZenNotes desktop app knows. The JSON output carries the same source field. zn vault remove, zn disconnect and zn use explain when a name belongs to the desktop app, suggest the saved name that contains what you typed (workspace finds workspace (notes.example.com)), and list zn's own names. An exact saved name wins over another entry's folder or host.

zn vault remove of a server also forgets its token, as zn disconnect does; it reports a token that could not be removed and restores the token if the list cannot be saved, so a failed removal is always retryable. It supports --json and completes names. zn use <desktop vault name> adopts that folder instead of failing.

Help that lines up

Rows whose name is wider than the command column (comment reply <path> <id> "<body>", --workspace-source <app|terminal>) ran straight into their descriptions. A wide name now takes a line of its own and every description starts at the column.

Your saved vaults survive a broken config file

A workspaces.toml or credentials.toml that failed to parse was treated as an empty list, so the next zn connect, zn init or zn vault add wrote that empty list back and lost every saved vault, server and token. zn now refuses to write over a file it could not read and says what to fix. zn connect refuses up front, zn doctor reports a saved vaults check and a credentials parse problem (showing only a line number, never a token), and zn status warns.

Databases

Record pages for rows with only a title were written with an empty frontmatter block that the frontmatter parser did not recognise, so every zn base set added another pair of --- fences. Empty blocks are recognised, pages without properties get no block, re-mirroring is idempotent, and pages from earlier builds shed their stray fences on the next edit.

Smaller fixes

  • A body that starts with a frontmatter fence can follow --body; any value starting with --- or -x is a value, not the next flag.
  • zn tag find --tag <tag> works as documented.
  • Typo suggestions count a swap of adjacent letters as one edit, so zn lsit suggests list.
  • zn delete <missing> --yes reports Note not found on a local vault instead of printing Deleted, matching a server's answer.
  • Ctrl-C on zn server run no longer prints context canceled twice; it exits 0 after the server's own shutdown line.
  • zn mcp exits quietly when the client closes the pipe, which is how MCP clients end a session. Genuine transport failures still surface.

Upgrade

zn update

Standalone macOS and Linux installations of 0.6.0 update in place and keep zn.previous as a backup. Homebrew users run brew update && brew upgrade zn. With Go:

go install github.com/ZenNotes/tui/cmd/zn@&#8203;v0.6.1

Or download an archive below. Desktop-managed installations receive the CLI pinned by their desktop release; publishing this CLI release does not change an existing app bundle.

Verification

Full Go race tests, vet, gofmt, Windows/macOS/Linux builds, both contributor sandboxes (local and real-server), and the release artifacts themselves: all seven archives verified against checksums.txt and GitHub's asset digests, zn --version and the desktop integration probe report 0.6.1, and a copied standalone 0.6.0 binary updated itself to the published 0.6.1, byte-identical to the archive, with its backup retained. The QA sweep ran about 1,400 scripted assertions across roughly 730 command invocations: local vault and data matrix, zn connect to a Docker server with the same matrix, the managed-server lifecycle (install, start, status, logs, restart, bind and base-path changes with rollback, update 2.55.0 to 2.56.0, rollback, pin, downgrade, stop, foreground run), diagnostics, configuration, completion, MCP, and the TUI driven in a pty including the first-run wizard.

v0.6.0: ZenNotes CLI 0.6.0

Compare Source

ZenNotes CLI 0.6.0

Set up a self-hosted server, keep it updated, and make the terminal work better with your scripts. This release also fixes cross-note yanking and makes bug reports much easier to prepare.

Manage a server from the terminal

zn server setup home --vault ~/Notes
zn server status home
zn server update home --check

Setup downloads and verifies an official native server, creates a private token outside the vault, starts a user service, checks authentication and the exact vault, and saves the connection. Start, stop, restart, logs, configuration changes, foreground execution, pinned updates, and rollback are available as separate commands.

Updates verify the candidate before accepting it and retain the previous executable. Failed health checks restore the working service. macOS uses launchd agents; Linux uses systemd user services. Windows supports foreground operation where a native server release is available. Management runs on the machine executing zn; SSH and Docker provisioning are outside this first adapter.

Inside the TUI, :servers opens the same controls. Long operations run in the background.

A friendlier, more scriptable CLI

  • Bare zn opens the TUI in an interactive terminal and prints help when piped.
  • Command-specific help and argument validation catch mistakes before note operations. Help/version flags never create notes.
  • --no-input prevents prompts; JSON errors go to stderr with predictable usage, operation, and cancellation handling.
  • zn status explains workspace selection; zn doctor checks configuration and access.
  • zn config list|get|set|edit exposes shared preferences to the shell.
  • Completion scripts support Bash, Zsh, Fish, and PowerShell.
  • zn update --check and zn update respect Homebrew, Go, desktop-managed, and standalone installation ownership. Native macOS/Linux replacement verifies the executable and retains a backup; Windows standalone updates provide download instructions.

Two TUI fixes

  • Yank across notes: registers now belong to the TUI session. Yank, switch with [b/]b, and paste into another note. Named registers and line/block selections work too; undo stays local to each note. Thanks @​iwpnd for #4.
  • Useful version reports: :version / :ve opens OS, architecture, runtime, build, installation, terminal, and active-server details. Use :version copy, :version!, or c to copy. Settings also offers the report. Local paths and authentication details are omitted. Thanks @​vlcinsky for #5.

Upgrade

Versions 0.5.0 and earlier do not have zn update; use your original installer once:

brew update && brew upgrade zn

Or download an archive below. With Go:

go install github.com/ZenNotes/tui/cmd/zn@&#8203;v0.6.0

Desktop-managed installations receive the CLI pinned by their desktop release. The desktop bundle must be updated separately; publishing this CLI release does not change an existing app bundle.

The README and contributor guide include command recipes, configuration, troubleshooting, and a disposable local/remote sandbox.

Verification

Full Go race tests, vet, platform builds, isolated local/remote smoke checks, copied-executable self-update, real macOS launchd lifecycle, systemd unit validation, and TUI checks at 120×36 and 80×24.

@scottames-github-bot

scottames-github-bot Bot commented Oct 5, 2026 •

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

v2.1.287: v2.1.287

Compare Source

What's changed

  • Added Claude Mods: plugins may now modify deeper behavior
  • Added You should know, a built-in mod where a side agent watches your back and flags things you or Claude might miss. Turn it on with /plugin enable cc-plugin-you-should-know@&#8203;builtin (for first-party sessions with telemetry on)
  • Added an n:<text> filter to the agents view that matches session names and tasks; a filter now shows matches in collapsed sections and Enter opens the first match
  • Added prompt_text to the OpenTelemetry user_prompt event, a copy of prompt for backends that nest dotted keys; drop or mask it wherever you drop or mask prompt ([BUG] prompt.id unflattens into a nested prompt object and overwrites prompt attribute in telemetry anthropics/claude-code#70763)
  • Added URL prompts from MCP servers on the 2025-11-25 protocol, for example to sign in. If a server no longer connects after this update, add "bareElicitationCapability": true to its MCP config entry
  • Windows: Added a startup warning when denying the Bash tool also turns off the PowerShell tool, so Claude has no shell tool
  • Self-hosted runner: Added a built-in gh api (REST only) for sessions that use Anthropic-managed git on macOS and Linux machines where the GitHub CLI is not installed
  • Fixed fast mode staying off in remote sessions owned by an agent with no user account, even when the organization allows it
  • Fixed Remote Control not receiving messages for minutes at a time when a reconnect request got no response; it now gives up after 30 seconds and retries
  • Fixed hooks configured with asyncRewake waking Claude over and over with "found issues" notifications when the hook's script file is missing; the broken hook is now reported once
  • Fixed tool heartbeats not reaching SDK hosts while the model's response stream was stalled with no data arriving
  • Fixed Bedrock and Vertex startup model checks ignoring an enforced availableModels list, which could collapse /model to one Opus row
  • Fixed the Claude in Chrome browser picker showing a JSON parse error when Chrome could not be reached
  • Fixed picking Fable in /model on a claude.ai login saving the current version's id, so your saved default now follows the newest Fable like Opus and Sonnet do
  • Fixed switching between Opus 5.5 and Sonnet 5.5 (/model, opusplan) rewriting earlier MCP tool announcements, which could drop earlier extended thinking
  • Fixed Amazon Bedrock Guardrails blocks that arrive mid-response ending the turn with an API error instead of the guardrail's message when the reply began with thinking
  • Fixed a dangerous rm (such as one on / or the home directory) losing its always-ask safeguard when the same command also redirected output to a ~ or wildcard path
  • Fixed claude -p and SDK sessions repeating a model fallback on every later message after the model was switched while a reply was running
  • Fixed a folder's CLAUDE.md being attached a second time after resuming a session or after a compaction
  • Fixed background sessions that could not be reopened from claude agents after the agent exited and removed the worktree the session was started in
  • Fixed /advisor pairing checks: Sonnet 5.5 can now advise Opus 4.7 and 4.8, and advisors the API would refuse are flagged up front instead of being silently dropped
  • Fixed Bash permission prompts showing internal parser names such as "Contains simple_expansion" instead of a plain explanation
  • Fixed a cause of fullscreen sessions on slow or busy machines exiting with "Claude Code exited after an unrecoverable interface error" while a scroll key was held in a long conversation
  • Fixed organization per-tool permission ceilings being silently dropped for an MCP tool named __proto__
  • Fixed Claude being told to page large MCP results saved as JSON with Read's offset and limit, which cannot split one long line
  • Fixed the commit attribution reminder being delivered inside a tool result after a compaction
  • Fixed screen reader mode leaving the cursor away from the typed text in search boxes (such as /resume and /permissions) and sign-in code fields
  • Fixed screen reader mode refusing Enter with nothing typed on /rewind's summarize options, whose added context is optional
  • Fixed screen reader mode showing a "Tab to amend" hint on approval prompts, where Tab does nothing
  • Fixed screen reader mode listing arrow keys that do nothing in /permissions and /mcp, and saying "Select with numbers" in empty menus or while a search box has the keys
  • Fixed screen reader mode leaving out the changed lines in file edit approval prompts and other diffs
  • Fixed screen reader mode sending the claude --teleport progress screen, and an MCP form field while it is being checked, to the screen reader again on every spinner frame
  • Fixed CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS not removing the structured-output format from session-title and prompt-hook requests, which Bedrock-backed gateways reject
  • Fixed screen reader mode leaving out the top lines of a second approval prompt, a changed /config row or the rejected-plan line when the previous screen was taller than the terminal window
  • Fixed --include-partial-messages sending a cut-short reply's message_stop late or never, so apps could show the reply as still in progress
  • Fixed claude agents sometimes not showing the permission prompt a background session is waiting on
  • Fixed /ultrareview giving advice about .git/info/attributes when the upload stops on a committed .gitattributes it cannot read, such as one saved as UTF-16
  • Fixed claude remote-control failing to register behind an HTTP proxy with a misleading "Check your organization permissions" error (Remote Control cannot register behind an HTTP proxy: some requests are sent as absolute-URI instead of through CONNECT anthropics/claude-code#97352)
  • Fixed sandboxed Bash commands on Linux inheriting an open handle on the Claude Code executable
  • Fixed the running-tool dot and three spinners still moving with the "Reduce motion" setting on, and /rewind's confirm screen updating its "ago" time while you type a note
  • Fixed times in claude agents changing every second in screen reader mode; they now change at most every 10 seconds
  • Fixed a revoked claude.ai login showing a generic API Error: 401 instead of "OAuth token revoked"; in -p mode the error now starts with "Failed to authenticate"
  • Fixed /ultrareview upload refusals advising you to copy a variable named by a repository's settings file into your own user settings
  • Fixed --output-format stream-json and the SDK not streaming the turns of a context: fork skill run by typing /<skill> as the prompt, as they do for the Skill tool's fork
  • Fixed /feedback and /bug: the pre-filled GitHub issue no longer includes your recent error messages, and the confirmation screen now lists them as part of the report
  • Fixed claude plugin marketplace add --sparse and git-subdir plugin installs failing with "transport 'http' not allowed" when the repository is served over plain http
  • Fixed cloud sessions sometimes losing the earlier conversation when the session restarted while it was being compacted
  • Fixed a plugin reload that overlapped the startup --plugin-url download corrupting the session's cached copy of the plugin archive
  • Fixed /desktop quoting partial output when opening Claude Desktop timed out or printed too much output; the error now names the cause
  • Fixed an MCP connector tool call occasionally running twice, or the connector's calls failing until restart, when its server changed which MCP protocol version it supports
  • Fixed SessionStart hooks from synced plugins not running in new cloud sessions
  • Fixed the transcript's "N hooks ran" summary and the verbose debug log's matched-hooks count including Claude Code's internal callbacks, so one configured hook no longer shows as two
  • Fixed files Claude sends from cloud and Remote Control sessions failing when the upload finished just after the 30-second timeout; it now waits 35 seconds
  • Fixed repositories added mid-session in cloud and SDK sessions not loading their skills and plugins, and loading CLAUDE.md late, after Claude changed directory
  • Fixed PNG, JPEG and WebP images over 8,000 pixels on a side failing to send from a remote session; Claude now sends a scaled-down copy
  • Fixed messages sent from the Claude apps with 17 to 20 attached files delivering only the first 16
  • Fixed headless sessions reporting an MCP server as needing authentication after one refused call, even though later calls succeed
  • macOS: Fixed Remote Control sessions started with claude remote-control stopping mid-turn when the Mac went to idle sleep
  • Windows: Fixed interactive claude hanging or crashing with "Raw mode is not supported" when its input is piped or redirected; it now says why and exits (use -p for piped input)
  • Bedrock, Vertex, Mantle: Fixed model availability checks under CLAUDE_CODE_SKIP_*_AUTH sending a different Authorization header than real requests when ANTHROPIC_CUSTOM_HEADERS repeats it
  • Improved /config: settings that cycle show ‹ › and step both ways with ←/→, narrow terminals stack each value under its label, and PgUp/PgDn page the list
  • Improved plugin marketplace errors to say in plain words why a marketplace was ignored or refused, and what to do
  • Improved plugin listings to note when a plugin's dependencies were not installed, and updating a plugin now retries an install that did not finish
  • Improved the Claude apps gateway's error when Amazon Bedrock rejects a model ID: developers now see which model is unavailable, and the gateway log names the ID that was sent
  • Improved SDK sessions so a message sent with priority "now" no longer cancels a running web fetch or web search; it keeps loading in the background
  • Improved /memory: the left and right arrow keys now flip its on/off settings, such as Auto-memory
  • Improved /skill names typed mid-message: Claude is now told they are skills, including disable-model-invocation ones
  • Improved the contrast of the prompt input border in light themes and of the ❯ before your earlier messages
  • Improved delivery of files Claude sends from cloud sessions and Remote Control: an upload that fails on a timeout, a network error or a 502, 503 or 504 is now retried once
  • Improved what Claude says when a file cannot be sent for a reason that may be temporary: it now mentions that you can ask for the file again in a few minutes
  • Improved the prompt for a held message from another session to show the message between dashed lines, matching other permission prompts
  • Improved MCP and other tool permission prompts to show the tool call between dashed lines, matching file edit prompts
  • Improved MCP startup in headless mode: a remote server whose first connect fails transiently is now retried without waiting for the slowest server to finish connecting
  • Improved files Claude sends from a remote session: large files now stream from disk instead of being read into memory, and a file over the size limit is refused with the server's limit named
  • Improved the explanation Claude gives when the server refuses a file it sends from a Remote Control or cloud session, such as an oversized image
  • Improved handling of large MCP tool results: less memory, smaller session files, and no extra upload to count tokens for results far over the limit
  • Windows: Improved Bash tool speed by removing a subshell that ran before every command
  • Changed a shell write through a repo-committed symlink onto a sensitive file or out of the working tree to name where it lands and wait for a person, on lines with a ~ target too
  • Changed Opus 4.7+ and Fable to use a 1M context window by default on Bedrock, Vertex, Foundry and the Claude apps gateway, with no [1m] suffix (CLAUDE_CODE_DISABLE_1M_CONTEXT=1 keeps 200K)
  • Changed replies from claude agents to arrive as queued messages; slash commands other than /stop sent while a turn is running now run when it ends
  • Changed whole-tool Bash allow rules and allowing hooks to prompt for, not run, shell writes to files Claude Code's file tools refuse outright (the Anthropic profile store, the host credentials file)
  • Changed right-click paste on Windows and Linux, and middle-click paste on Linux, to happen when the button is released; moving the pointer away before releasing cancels it
  • Changed MCP server alwaysLoad: false to defer all of that server's tools behind tool search
  • Changed screen reader mode to write new or changed lines without first pausing with the cursor at the start of the line; set CLAUDE_AX_PREPARK_MS=50 to restore the pause
  • Changed automatic model switches after a flagged message to keep your current effort level instead of the new model's default
  • Changed waiting permission prompts to show oldest first, so a new prompt no longer covers the one you're reading (prompts with a countdown still open on top)
  • [VSCode] Added "Run in background" to a running command or sub-agent, to move it to the background and keep working
  • [VSCode] Added the output of background shells and Monitors to their cards in the agent map
  • [VSCode] Fixed settings dialogs blaming a timeout when Claude Code's reply was too large to confirm a save
  • [VSCode] Fixed reopening a cloud session that the side bar already brought to this machine opening it again in a new tab; the side bar is shown instead
  • [VSCode] Fixed the side bar's Web tab not listing cloud sessions started after the window loaded; a failed load now says "Remote server is not connected" instead of "No web sessions yet"
  • [VSCode] Fixed a tab restored after a reload starting a second Claude process on a conversation the side bar already has open; it now shows the "still open somewhere else" notice
  • [VSCode] Fixed tool-row file links, session-list links and two hints showing in plain text
  • [VSCode] Fixed a background agent's still-running command showing as failed once the main turn ended
  • [VSCode] Fixed a user's own /usage or /context command opening the extension's dialog instead of running when picked from the command menu
  • [VSCode] Fixed file links in the plan preview tab doing nothing when clicked; they now open the file like links in chat replies
  • [VSCode] Fixed opening a tool's input or output in an editor tab failing with "Timeout waiting after 1000ms" on remote hosts such as WSL when the tab is slow to appear
  • [VSCode] Improved the Manage plugins dialog: a failed marketplace add, remove or refresh now says what went wrong
  • [VSCode] Changed the Claude in Chrome "Enabled by default" switch to also connect the editor's own sessions, which still ask before browser actions
  • [Cloud sessions] Fixed occasional failures to fetch from or push to GitHub when GitHub briefly refused a newly issued access token
  • [Claude Tag] Fixed Claude posting a failure warning, such as a spend limit notice, in a Slack thread when a background event like GitHub activity woke it and nobody was waiting on a reply
  • [Claude Tag] Fixed Claude Tag's spend limits page in admin settings leaving out recently created and private channels in organizations with many channels
  • [Claude Tag] Improved Claude's task list in long Slack threads: background work no longer reposts it as a new message on its own, so people following the thread aren't notified
  • [Code Review] Fixed finding comments and their "Why this was flagged" text stopping mid-sentence; they now end on a complete sentence
  • [Code Review] Fixed Code Review skipping a pull request after a new push when its review had failed twice on the previous commit; it now reviews the latest commit
  • [Code Review] Improved the failed-review card on a pull request whose conversation is locked: it now says the lock blocked the review and that nothing was posted or charged

v2.1.286: v2.1.286

Compare Source

What's changed

  • Added a count such as "2 of 5" to the permission prompt when several permission requests stack up
  • Added mouse support for the "N more" rows of lists in fullscreen mode: click one to jump to that end of the list, with hover and pressed states
  • Fixed several Claude Code processes and IDE extensions each opening a login browser when gcpAuthRefresh or awsAuthRefresh credentials expire
  • Fixed claude --resume and --continue sometimes losing every turn after a batch of parallel tool calls when the earlier session crashed or was killed
  • Fixed API 400 errors after a tool or hook returned an object, number or boolean instead of text, including in resumed sessions
  • Fixed cloud sessions with very large histories never waking up because the container was stopped while the transcript was still loading
  • Fixed the Claude apps gateway's spend meter pricing 1-hour prompt cache writes at the cheaper 5-minute rate, and counting only the first model call's input tokens on streamed turns that run a server-side tool such as web search
  • Fixed macOS sessions still showing "Not logged in" or "Login expired" after /login succeeds in another Claude Code window when a leftover ~/.claude/.credentials.json exists
  • Fixed every turn failing when the Anthropic API refuses the model your default or a model alias resolves to: Claude Code now retries once on the previous model of the same tier
  • Fixed Remote Control sessions (including claude remote-control) staying connected after your organization's policy turns Remote Control off; they now disconnect with a notice
  • Fixed refusal and --fallback-model retries failing when the fallback model can't run fast; they now run at standard speed, with a one-time notice in interactive sessions
  • Fixed headless sessions repeating the "MCP servers require authentication" reminder after a successful re-authentication when the MCP discovery cache is enabled
  • Fixed claude auth status reporting a Console sign-in's stored API key as claude.ai; it now reports api_key, and the VS Code extension treats that session as an API key session
  • Fixed /status listing an Anthropic profile beside an API key as if both were in effect; the profile is now marked as not in use
  • Fixed Claude not being told when a file attached to a message sent over Remote Control did not arrive, and a file sometimes getting only 10 seconds for its last download try
  • Fixed a Remote Control message that arrived while Claude Code was exiting being marked delivered and then never answered; it now stays queued for the session's next run
  • Fixed MCP error messages showing a credential's value when "Bearer" or "Basic" came before its key name
  • Fixed percent-encoded Bearer tokens being only partly masked in error messages
  • Fixed redacted logs and transcripts showing a secret whose key name has an invisible character inside, such as a zero-width space
  • Fixed logs and transcripts showing part of a URL password that contains punctuation such as ), quotes, ], & or a second @&#8203;, or that runs past a / to a bracketed host such as [::1] in an ssh URL
  • Fixed the session transcript in the zip that /feedback saves to disk containing invalid JSON lines after secret redaction
  • Fixed MCP connectors listing no tools for up to a day after their server dropped the older MCP handshake
  • Fixed a repeat MCP sign-in request from Claude replacing the pending sign-in link, which could stop that link from working
  • Fixed /usage not crediting an MCP server for a tool call made while that server was still connecting or had only just connected, such as right after a restart
  • Fixed plugins enabled on claude.ai occasionally going missing from Claude Code for a session after a transient server error
  • Fixed a message typed into a running subagent showing twice in its transcript after the subagent read it
  • Fixed subagent hand-back messages showing a raw task id instead of the agent's name when the subagent had no registered name
  • Fixed foreground subagents sometimes missing the task-tracking tools (TaskCreate/Get/Update/List, TodoWrite) in sessions that have them enabled
  • Fixed subagents spawned with worktree isolation loading the project CLAUDE.md and its imports a second time from the worktree copy on their first file read
  • Fixed Workflow tool subagents being restarted from their original prompt when a connection stalled for a few minutes mid-response
  • Fixed /compact, /clear, and /rewind typed while viewing a background agent's or teammate's transcript silently acting on the main conversation: a dialog now names the target and asks first
  • Fixed background jobs showing done while waiting for your approval
  • Fixed the commit attribution reminder being re-sent inside tool output when a model fallback lasts only one turn
  • Fixed a click on the space between words of a collapsed row (such as "Thought for 4s") highlighting the row without expanding it in fullscreen mode
  • Fixed a row with no details, such as an action row with a long name, pushing every other row's details to the right in list screens
  • Fixed files with very long names not reaching a cloud session when attached to it
  • Fixed plugin errors for a marketplace Claude Code refuses to load: they now say why and how to fix it instead of "not found"
  • Fixed /plugin's Discover tab showing a marketplace name unquoted in its "Checking … for new plugins" line when its rows already show that name in quotes
  • Improved commit guidance: when your project or user skills include one named verify, Claude is now told to run it right before committing, except for docs-only and tests-only commits
  • Improved send now (ctrl+enter) in a subagent's view: it now moves the subagent's running command to the background so your message is read right away
  • Improved replies from background agents to your messages so they no longer open with a separate recap of what you said
  • Improved claude.ai artifact link reads: WebFetch now asks the same questions as the Artifact tool's read (no artifact prompt while the session's network access is on, one per artifact while it is off), and an auto-mode yes no longer counts where only you can answer
  • Improved fetch, skill, file read, sandbox network, Claude in Chrome, workflow script and notebook edit permission prompts to match the look of file edit prompts
  • Improved Bash, PowerShell and Monitor permission prompts to show the command between dashed lines, matching file edit prompts
  • Improved list scrollbars in fullscreen mode: in most lists the bar no longer shifts as the "N more" rows come and go, and it now has ↑/↓ arrows you can click or hold to scroll
  • Improved the external editor (Ctrl+G): editors that take a line number now open on the line your cursor is on in the prompt
  • Improved slash command suggestion responsiveness while typing when many skills or plugin commands are installed; command descriptions now match by word prefix
  • Improved the output style picker: it now opens on your current style instead of Default, with each style's description on the line under its name; number keys no longer pick a style
  • Improved /hooks: the closing line of a hook's detail screen now says "this hook" instead of "it"
  • Improved the model fallback notice and the autocompact-thrashing error to say when a fallback dropped the context window from 1M to 200K tokens
  • Improved responsiveness of SDK and -p sessions when a host re-sends an MCP server enable for a server that is already connected
  • Improved the protocol page a Claude apps gateway serves at /protocol: it now says not to reject unknown input and matches what Claude Code sends today
  • Changed prompts sent while nothing is running or queued to show in the normal text color right away instead of gray
  • Changed how failed API requests are retried: one limit now covers a whole model call, so with the default retry settings a failing call sends at most 14 requests
  • Changed --bare to connect only the MCP servers named on the command line, send the model no system reminders, and start no background tasks; under --bare, a shell command that reaches its timeout now stops instead of moving to the background
  • Changed the send-now key (ctrl+enter) to move a skill's own shell command to the background instead of ending it
  • Changed the WebFetch error for a rate-limited domain safety check to tell Claude not to retry it in a loop
  • Changed plugin installs to refuse npm sources that are git repositories or folders, and to install plugin dependencies only from registry packages
  • Changed list screens (/artifacts, /mcp, /skills, /hooks and others) to always line up each row's details in one column after the names
  • Changed the overflow rows of lists to read "↑ N more" / "↓ N more" instead of "N more above" / "N more below"
  • Changed /hooks to open on one list of your configured hooks grouped by event, so viewing a hook takes one Enter instead of three
  • Changed the theme picker to a scrolling list that fits your terminal instead of pushing the preview off screen; number keys no longer pick a theme
  • Changed /exit's Remove worktree to run after Claude Code stops the servers and shells it started there, which on Windows could keep the folder from being deleted
  • Changed the claude-api skill's Managed Agents examples to create environments with limited networking
  • Removed the browser link from /ultrareview and claude ultrareview output
  • Windows: Fixed claude --bg and the agents view refusing a folder that claude already trusts when its trust record was saved with different letter case
  • [VSCode] Added bookmarks: save Claude's responses and keep them in view in a Bookmarks side panel
  • [VSCode] Added the questions Claude asks and your answers to the conversation: after you answer a question card, a Questions row shows each question with your picks
  • [VSCode] Added option previews to question cards in the chat panel: the highlighted choice's mockup or snippet shows beside or under the options
  • [VSCode] Added rows under a message that open to the terminal output, browser tab, browser instructions and selected code sent with it
  • [VSCode] Fixed a second copy of a conversation opening in a tab when it was already open in the side bar; the side bar now switches to it
  • [VSCode] Fixed settings dialogs reporting a failed save, without re-checking, when Claude Code printed more than 1 MB of output
  • [VSCode] Fixed an endless "Teleporting session…" spinner when the extension stops responding
  • [VSCode] Improved the Manage plugins dialog: it says when a turned-off plugin is still on because of other settings, and explains a plugin folder clash
  • [VSCode] Changed Stop and Escape to end only the current turn; background agents keep running and can be stopped one by one from the agent map
  • [VSCode] Changed the "✻ Claude Code" status bar item to show in every window, so you can open Claude when no file is open
  • [Cloud sessions] Fixed an answered question card or approved tool call getting no reply when the session had gone idle after Claude sent a message
  • [Cloud sessions] Fixed clearing an organization environment's setup script in admin settings leaving new cloud sessions still running the old script
  • [Cloud sessions] Fixed the Runner actions menu on the self-hosted environments admin page closing on its own a few seconds after it opened
  • [Cloud sessions] Fixed routine runs whose cloud session never started showing as Succeeded in the Runs pane, the routine's page and the sidebar; they now show as Failed
  • [Cloud sessions] Fixed clicking an audio or video file in a cloud session's Outputs card opening an empty file search instead of playing the file
  • [Cloud sessions] Changed a routine's page to read "Due" with the scheduled time, instead of a next run time in the past, when a scheduled run is late and hasn't started
  • [Claude Tag] Added an Add channel button to Claude Tag's spend limits page in admin settings, so a limit can be set on any channel, including a private one, from its channel ID or Slack link
  • [Claude Tag] Fixed memory recall finding nothing in organizations that cannot use the default Sonnet model
  • [Claude Tag] Fixed a Slack channel losing its Claude settings when an Enterprise Grid admin moves it to another workspace and the first post afterward doesn't mention Claude
  • [Claude Tag] Fixed Claude in a Slack thread occasionally starting over on a fresh machine, losing work it hadn't pushed, when your reply answered a question it had just asked
  • [Claude Tag] Fixed public channel names on Claude Tag's spend limits page in admin settings showing as raw Slack IDs in larger organizations
  • [Claude Tag] Improved the titles of sessions started from Slack as shown on claude.ai: they now read as the words you typed, without Slack user IDs or escape codes
backnotprop/plannotator (github:backnotprop/plannotator)

v0.27.25: v0.27.25

Compare Source

Follow @​plannotator on X for updates

Missed recent releases?

Release Highlights
v0.27.24 Image previews stay in the all-files view, PR comment previews open on the commented line
v0.27.23 Bitbucket Cloud PR review, Question UI for answering agents in place, opt-in auto-update, viewed files remembered, review another repo or worktree
v0.27.22 Plans open the docs they link to, Claude review jobs locked down, Code Tour on Linux without Claude's sandbox, Pi reviews the latest plan
v0.27.21 Remote and phone sessions load several times faster, real Request changes on GitHub, model pickers show real names, OpenCode fixes
v0.27.20 Mistral Vibe support, annotate gets the full Options menu and Settings, jj Commits panel, long lines wrap in plan code blocks
v0.27.19 Before/After image previews in code review, file comments as GitHub file threads, forge-correct #123 links, /plannotator-last finds the right session
v0.27.18 Model pickers from your installed Claude and Codex (Opus 5.5, Fable 5.1, GPT-6), unsent PR review comments survive new pushes
v0.27.17 Diagram files open in the diagram viewer, OpenCode switches model with agent, idle review stops polling the git remote, Tree is the default review view
v0.27.16 Themed diagrams on Mermaid 12, comment on any node or edge, patch-file review, embedded HTML documents render
v0.27.15 Plannotator TUI and Herdr Annotate announcement, element context on pinpoints, HTML links open as linked documents, All files panel, Classic diff default
v0.27.14 Pi plan progress survives compaction, Codex threads across rollout files, WSL browser setting, Mod+E edit mode

What's New in v0.27.25

A fix release driven by reports from people using the last two releases: code review with a colorized git config, Bitbucket reviews on large pull requests, wide tables in Firefox, Ask AI on Windows, and a failing install. Six pull requests, two of them from community contributors.

Code review works with color.diff = always

If your git config set color.diff = always, a common line in dotfiles, plannotator review showed 0 files with no explanation. Git wrapped every line of the diff in terminal color codes even though Plannotator reads it through a pipe, and the diff parser skipped every line it could not recognize. Viewed-file marks also stopped saving.

Plannotator now turns color off for every git command it runs during a review, in every runtime. Setting color.ui=never alone is not enough, because a more specific color.diff=always wins over it, so each color setting is turned off explicitly. jj gets --color=never, gh pr diff gets --color=never, and the review agents and Call Flow analysis run their own git with color off. A normal diff is byte for byte what it was before, so saved comments and viewed marks are unaffected.

(#1662, #1663, closing #1661, reported by @​sholsinger)

Bitbucket review fixes from real use

@​Toparvion tested Bitbucket Cloud review on a large pull request with several reviewers, existing comments, and Guided Review, and reported three things:

  • "View on Bitbucket after submitting" now opens. The browser only lets a page open a tab within a few seconds of a click, and posting a large review takes longer, so the tab was blocked as a popup. Plannotator now opens the tab the moment you click submit, sends it to the pull request once the review posts, and closes it if posting fails. The Feedback Sent screen also has a plain link. This affected GitHub and GitLab too, and links now also open from the VS Code panel.
  • Your overall comment shows at the top. Bitbucket's activity feed lists the newest comment first, so the summary comment posted before the inline comments ended up at the bottom. It is now posted after them, so it lands on top. A retry after a partial failure still never posts it twice.
  • Long reviews in Claude Code. Claude Code stops a slash command's shell after about 30 minutes. That limit belongs to Claude Code, not Plannotator. The Claude Code guide now shows how to raise it with BASH_DEFAULT_TIMEOUT_MS, and the review skill tells Claude it can re-run the review in the background. Your comments come back either way, because drafts are saved.

(#1653, from #1583, reported by @​Toparvion)

Wide tables no longer collapse in Firefox

In Firefox, commenting inside a wide table while the action bar was pinned to the top squeezed the table into a narrow strip beside the bar. The bar was both a float and sticky, and Firefox laid the table out around where the bar sat once stuck. The bar is now sticky without being a float, and tables keep their width in Firefox, Chrome and Safari. Plan review had the same problem and is fixed too.

(#1660, closing #1659, by @​ruaridhw)

Additional Changes

  • Ask AI dropdowns are readable in dark mode on Windows. The provider, model and reasoning-effort lists showed light text on a light background. They now use the theme's own colors (#1658, by @​Aayushyaash).
  • The install script reads the latest version correctly. It found the version with a line-based text match, which picked up the wrong value when GitHub returned its answer on a single line, and the install failed with a 404. It now reads the version by name, and the Windows install.cmd parses it as JSON. This fix has been live on plannotator.ai since it merged (#1656, closing #1655, reported by @​jdppettit).

Install / Update

macOS / Linux:

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

Windows:

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

Claude Code Plugin: Run /plugin in Claude Code, find plannotator, and click "Update now".

Pi: Update @&#8203;plannotator/pi-extension to 0.27.25 and restart Pi.

OpenCode: Clear cache and restart:

rm -rf ~/.bun/install/cache/@&#8203;plannotator

What's Changed

  • fix(review): Bitbucket feedback from #1583 by @​backnotprop in #1653
  • fix(install): parse the latest release tag by key, not by line by @​backnotprop in #1656
  • fix(ui): stop long tables collapsing in Firefox while annotating by @​ruaridhw in #1660
  • fix(ui): style Ask AI dropdown options for dark themes by @​Aayushyaash in #1658
  • fix(review): keep git and jj output color-free under color.diff=always by @​backnotprop in #1662
  • fix(call-flow): run CallDiff with color-free git config by @​backnotprop in #1663

New Contributors

  • @​Aayushyaash made their first contribution in #1658

Contributors

@​ruaridhw tracked the Firefox table collapse down to a sticky float, measured it across browsers, and sent the fix.

@​Aayushyaash fixed the unreadable Ask AI dropdowns on Windows dark mode, with before and after screenshots.

Community

  • @​sholsinger diagnosed the 0-files review down to colorized git output and suggested the fix in #1661
  • @​Toparvion tested Bitbucket review on a real team pull request and reported the popup, comment order, and timeout issues in #1583
  • @​jdppettit reported the failing install, with a workaround, in #1655

Full Changelog: backnotprop/plannotator@v0.27.24...v0.27.25

v0.27.24: v0.27.24

Compare Source

Follow @​plannotator on X for updates

Missed recent releases?

Release Highlights
v0.27.23 Bitbucket Cloud PR review, Question UI for answering agents in place, opt-in auto-update, viewed files remembered, review another repo or worktree
v0.27.22 Plans open the docs they link to, Claude review jobs locked down, Code Tour on Linux without Claude's sandbox, Pi reviews the latest plan
v0.27.21 Remote and phone sessions load several times faster, real Request changes on GitHub, model pickers show real names, OpenCode fixes
v0.27.20 Mistral Vibe support, annotate gets the full Options menu and Settings, jj Commits panel, long lines wrap in plan code blocks
v0.27.19 Before/After image previews in code review, file comments as GitHub file threads, forge-correct #123 links, /plannotator-last finds the right session
v0.27.18 Model pickers from your installed Claude and Codex (Opus 5.5, Fable 5.1, GPT-6), unsent PR review comments survive new pushes
v0.27.17 Diagram files open in the diagram viewer, OpenCode switches model with agent, idle review stops polling the git remote, Tree is the default review view
v0.27.16 Themed diagrams on Mermaid 12, comment on any node or edge, patch-file review, embedded HTML documents render
v0.27.15 Plannotator TUI and Herdr Annotate announcement, element context on pinpoints, HTML links open as linked documents, All files panel, Classic diff default
v0.27.14 Pi plan progress survives compaction, Codex threads across rollout files, WSL browser setting, Mod+E edit mode
v0.27.13 Open a review on a specific base (--base, --diff-type), symlink containment on /api/doc, CI flake fix, Amp decision relay

What's New in v0.27.24

A small fix release for two code review problems found while recording a walkthrough of v0.27.23.

Image previews stay in the all-files view

When a diff changed images, the Before/After previews in the all-files view disappeared after a short scroll, and the view jumped ahead to the code files. The list measured each image card as having no height, so it dropped the cards as soon as they left the top of the screen. The cards are now measured at their real size, so they stay in place and keep their height while you scroll up and down. Scrolling a large diff is as fast as before.

(#1652)

PR comment previews open on the commented line

In the PR Comments panel, the small code preview under a comment showed the start of the changed block, not the line that was commented on. For a new file that meant lines 1 to 5, even when the comment was on line 28. This was most visible on Bitbucket, but long blocks on GitHub had the same problem. The preview now opens on the commented line and the three lines above it, or on exactly the lines of a range comment. "Show full context" still shows the whole block.

(#1651)

Install / Update

macOS / Linux:

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

Windows:

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

Claude Code Plugin: Run /plugin in Claude Code, find plannotator, and click "Update now".

Pi: Update @&#8203;plannotator/pi-extension to 0.27.24 and restart Pi.

OpenCode: Clear cache and restart:

rm -rf ~/.bun/install/cache/@&#8203;plannotator

What's Changed

  • fix(review): PR comment previews open on the commented lines by @​backnotprop in #1651
  • fix(review): keep all-files image previews in the virtual list by @​backnotprop in #1652

Full Changelog: backnotprop/plannotator@v0.27.23...v0.27.24

v0.27.23: v0.27.23

Compare Source

Follow @​plannotator on X for updates

Missed recent releases?

Release Highlights
v0.27.22 Plans open the docs they link to, Claude review jobs locked down, Code Tour on Linux without Claude's sandbox, Pi reviews the latest plan
v0.27.21 Remote and phone sessions load several times faster, real Request changes on GitHub, model pickers show real names, OpenCode fixes
v0.27.20 Mistral Vibe support, annotate gets the full Options menu and Settings, jj Commits panel, long lines wrap in plan code blocks
v0.27.19 Before/After image previews in code review, file comments as GitHub file threads, forge-correct #123 links, /plannotator-last finds the right session
v0.27.18 Model pickers from your installed Claude and Codex (Opus 5.5, Fable 5.1, GPT-6), unsent PR review comments survive new pushes
v0.27.17 Diagram files open in the diagram viewer, OpenCode switches model with agent, idle review stops polling the git remote, Tree is the default review view
v0.27.16 Themed diagrams on Mermaid 12, comment on any node or edge, patch-file review, embedded HTML documents render
v0.27.15 Plannotator TUI and Herdr Annotate announcement, element context on pinpoints, HTML links open as linked documents, All files panel, Classic diff default
v0.27.14 Pi plan progress survives compaction, Codex threads across rollout files, WSL browser setting, Mod+E edit mode
v0.27.13 Open a review on a specific base (--base, --diff-type), symlink containment on /api/doc, CI flake fix, Amp decision relay
v0.27.12 Unified decision control, token hover cards, local-vs-remote diff, approval notes

What's New in v0.27.23

This release brings Bitbucket Cloud to PR review, lets agents put questions in a plan that you answer in place, and adds an opt-in setting that keeps Plannotator up to date for you. Code review also remembers which files you have viewed, can be pointed at another repository or worktree, and several fixes land for Pi and keyboard users. It contains thirteen pull requests, three of them from community contributor @​oorestisime.

Bitbucket Cloud pull requests

PR review used to recognize only GitHub and GitLab links. plannotator review https://bitbucket.org/<workspace>/<repo>/pull-requests/<id> now opens a Bitbucket Cloud pull request with the same review experience:

  • the diff and a local checkout for full file access
  • existing comments, with their code context
  • image previews
  • Guided Review and Code Tour

From the review you can post general and inline comments, approve, or request changes. Bitbucket has no command-line tool like gh, so Plannotator talks to its API directly with an Atlassian API token. Set PLANNOTATOR_BITBUCKET_EMAIL and PLANNOTATOR_BITBUCKET_TOKEN; the docs list the scopes the token needs.

Under the hood, PR mode now runs through one provider per platform. The screen shows only what that platform supports, which is why the PR Artifacts panel is absent on Bitbucket. GitHub and GitLab were moved onto the same seam and behave exactly as before. We checked this by recording every gh call against real stacked PRs on the old and new code and comparing them.

Not yet supported on Bitbucket:

  • replying to or resolving existing threads
  • syncing viewed files back to Bitbucket
  • stacked PRs
  • Bitbucket Data Center

(#1641, toward #1583 and #671, requested by @​Toparvion and @​bahayden)

Questions in plans, answered in place

An agent can now put questions in a plan or document as :::question blocks with checkbox choices and a Recommended: line. Plannotator draws each one as a card. You can:

  • pick an answer, type your own under "Other…", add a note, or skip it
  • take the agent's suggestion with Accept recommended

The header shows how many you have answered, and clicking that count jumps to the next open question. The sidebar lists them all.

Answers travel with your feedback in an "Answers to your questions" section at the top. If answering questions is all you did, the main button reads Send answers. The agent is then told you answered its questions and asked to revise the plan, rather than being told the plan was rejected. Answers are saved like any other annotation, so they survive a reload and can be undone. Question and option text stays selectable, so you can still comment on the wording.

The /plannotator skill teaches agents the syntax, including when not to ask. A document with no questions renders and exports exactly as before. If you already used :::question as an ordinary callout, it now renders as an answerable card. One limit to know: approving a plan in Claude Code passes no message to the agent, so answers given with Approve do not reach it. Plannotator warns you before that happens.

(#1637, #1638, #1639)

Opt-in automatic updates

The "new version available" notice tends to appear while you are busy with something else. You can now turn on Keep Plannotator up to date in Settings, with "autoUpdate": true in ~/.plannotator/config.json, or with PLANNOTATOR_AUTO_UPDATE=1.

With it on, Plannotator checks for a new release at most once a day, in the background, after a session has already started. It never slows down a hook or a command. When a newer version exists and no other review is open, it runs the normal install script for that exact version and writes the output to update.log. The next time you open Plannotator it tells you what version you are on now, or that the update failed and where the log is.

The installer now remembers the flags you installed with, such as --minimal or --skip-codex, so an automatic update installs the same way you did. The install scripts also replace the binary safely while it is running: on macOS and Linux the new file is renamed into place, and on Windows the running copy is moved aside first. Auto-update is off unless you turn it on, and it skips development builds, the OpenCode and Pi packages, and binaries in folders it cannot write to.

(#1636, closing #1634, requested by @​drj613)

Code review remembers what you have viewed

Files you mark as viewed now stay viewed the next time you review the same branch, including after a restart or after sending feedback. A mark is tied to the exact contents of the file you saw, so a file that changed since then comes back unviewed. This works for local Git reviews and pull requests. Each mark is a small record in ~/.plannotator/review-progress/ that holds the file's path. Turn it off with PLANNOTATOR_REVIEW_PROGRESS=0 or { "reviewProgress": false }, and plannotator uninstall --purge removes it.

Viewed marks are now kept per diff type. Viewed marks stored in older drafts are ignored once, the first time you open a review after updating.

(#1632, closing #1136, by @​oorestisime)

Review another repository or worktree

plannotator review ../other-repo and /plannotator-review ./worktrees/feature now review that directory without moving your agent session:

  • A folder inside a repository reviews the whole repository.
  • A folder that holds several repositories opens the combined workspace review.
  • Everything after that follows the chosen directory: staging, drafts, viewed marks, Guided Review and the feedback label.

Extra words still work as before. /plannotator-review please check my changes, or even look at the api/users code, reviews the current repository and tells you which words it ignored. A mistyped path given on its own, such as ./backnd, stops with an error instead of quietly opening the wrong repository. A PR link anywhere in the words now opens that PR.

(#1644, closing #896 and #1482, by @​oorestisime)

Additional Changes

  • Keyboard scrolling works as soon as a review opens. Down, Page Down, Space, Home and End did nothing in plan review and annotate until you clicked the document. They now scroll it right away, without moving focus or interfering with shortcuts, dialogs, comment boxes or vim mode. Code review is a follow-up (#1648, closing #1647, reported by @​henriquegeremia).
  • No more Pi skill conflict warning. With both the install script and the Pi extension installed, Pi warned on every start that two plannotator skills collided. The extension now adds its copy only when no other one is loaded, so extension-only users still get the skill (#1643, closing #1642, reported by @​tekumara).
  • OpenCode plugin on stable packages. The plugin now builds against the published @&#8203;opencode-ai/plugin for OpenCode 1 and @&#8203;opencode/plugin for OpenCode 2, instead of a nightly build. The published plugin is unchanged in behavior (#1640, closing #1196, by @​oorestisime).
  • OpenCode 2 checked on every change. CI now installs a current OpenCode 2 and loads the packed plugin into it (#1631).
  • Link widgets for hosts. @&#8203;plannotator/ui re-exports the editor's link-widget API, so apps that embed Plannotator's editor can draw their own chips for links (#1633).

Install / Update

macOS / Linux:

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

Windows:

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

Claude Code Plugin: Run /plugin in Claude Code, find plannotator, and click "Update now".

Pi: Update @&#8203;plannotator/pi-extension to 0.27.23 and restart Pi.

OpenCode: Clear cache and restart:

rm -rf ~/.bun/install/cache/@&#8203;plannotator

What's Changed

  • ci(opencode): smoke the v2 plugin against a current OpenCode 2 by @​backnotprop in #1631
  • feat(review): persist viewed-file progress across review sessions by @​oorestisime in #1632
  • feat(ui): re-export linkWidgets for host link widgets by @​backnotprop in #1633
  • feat: opt-in background auto-update by @​backnotprop in #1636
  • feat(ui,core): in-document question blocks, core and ui by @​backnotprop in #1637
  • feat(editor): question answers, history, progress chip, Questions panel, Send answers by @​backnotprop in #1638
  • feat: question answers reach the agent by @​backnotprop in #1639
  • chore(opencode): migrate plugin dependencies to stable APIs by @​oorestisime in #1640
  • feat(review): Bitbucket Cloud PR review behind a PR provider seam by @​backnotprop in #1641
  • fix(pi): stop the plannotator skill colliding with the CLI install by @​backnotprop in #1643
  • feat(review): accept repository and worktree directory targets by @​oorestisime in #1644
  • fix(editor): scroll keys work on load without clicking the document by @​backnotprop in #1648
  • fix(review): path-shaped prose words no longer fail the review by @​backnotprop in #1649

Contributors

@​oorestisime contributed three of this release's pull requests. They built durable viewed-file progress for code review, moved the OpenCode plugin onto the stable OpenCode packages, and added directory targets to plannotator review, each with thorough tests and clear notes on the tradeoffs.

Community

  • @​drj613 asked for automatic updates in #1634, and @​nclark added that they rarely update for exactly that reason
  • @​Toparvion explained how their team uses Plannotator with Bitbucket Cloud and Guided Review in #1583, and @​bahayden first asked for other PR platforms in #671
  • @​dm3ch asked to review a specific worktree in #896, and @​ben-reitz asked to pick a repository in a multi-repo workspace in #1482
  • @​tekumara reported the Pi skill conflict in #1642
  • @​henriquegeremia reported that keyboard scrolling needed a click first, with exact steps, in #1647
  • @​sergical opened #1196 to move the OpenCode 2 adapter to the stable plugin API
  • @​ashish921998 weighed in on keeping viewed state across review iterations in #1136

Full Changelog: backnotprop/plannotator@v0.27.22...v0.27.23

@renovate
renovate Bot force-pushed the renovate/mise-packages branch 2 times, most recently from be511d6 to 2beea65 Compare October 5, 2026 20:10
@scottames-github-bot

scottames-github-bot Bot commented Oct 5, 2026 •

Copy link
Copy Markdown
Contributor
dlvhdr/gh-enhance (github:dlvhdr/gh-enhance)

v0.8.0: v0.8.0

Compare Source

More filtering options

I've integrated robinovitch61/viewport for more filtering options (e.g. regex, sensitive, insensitive, fuzzy).
Also fixed an issue with GitHub not properly escaping escape sequences.

To update run:

gh extension upgrade enhance

Changelog

New Features


If you enjoy enhance, consider making a donation ❤️

Have questions? Join our Discord community!

DASH Logo
janosmiko/lfk (github:janosmiko/lfk)

v0.19.2: v0.19.2

Compare Source

0.19.2 (2026-09-30)

Features

  • add delete with volume action for released PVs (#833) (fc03af9)

Bug Fixes

  • prompt for exec plugin login instead of hanging (#831) (922c22a)
modem-dev/hunk (github:modem-dev/hunk)

v0.23.0: v0.23.0

Compare Source

What's Changed

New Contributors

Full Changelog: modem-dev/hunk@v0.22.0...v0.23.0

nolabs-ai/nono (github:nolabs-ai/nono)

v0.79.0: v0.79.0

Compare Source

Security Advisories

What's Changed

New Contributors

Full Changelog: nolabs-ai/nono@v0.78.0...v0.79.0

Skipped Packages

Non-GitHub Sources

GitHub Release Notes Unavailable

  • droid: No GitHub release was found for 0.233.0

@renovate
renovate Bot force-pushed the renovate/mise-packages branch 4 times, most recently from 8e38fa1 to 362e4df Compare October 6, 2026 04:01
@renovate
renovate Bot force-pushed the renovate/mise-packages branch from 362e4df to c433bed Compare October 6, 2026 19:00
@renovate

renovate Bot commented Oct 6, 2026

Copy link
Copy Markdown
Contributor Author

Edited/Blocked Notification

Renovate will not automatically rebase this PR, because it does not recognize the last commit author and assumes somebody else may have edited the PR.

You can manually request rebase by checking the rebase/retry box above.

⚠️ Warning: custom changes will be lost.

@renovate
renovate Bot merged commit 6c43d9e into main Oct 6, 2026
6 checks passed
@renovate
renovate Bot deleted the renovate/mise-packages branch October 6, 2026 19:23
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.

1 participant