[renovate]

This PR contains the following updates:

Package	Type	Update	Change	Pending
aqua:openai/codex	tools	minor	rust-v0.164.0 → rust-v0.165.0	rust-v0.166.0
aqua:vercel-labs/agent-browser	tools	minor	0.39.4 → 0.40.0	0.41.1 (+1)
github:anthropics/claude-code	tools	patch	v2.1.311 → v2.1.312	v2.1.316 (+1)
github:backnotprop/plannotator	tools	patch	v0.28.33 → v0.28.35	v0.28.43 (+6)

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.

[scottames-github-bot]

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.

openai/codex (aqua:openai/codex)

rust-v0.165.0: 0.165.0

Compare Source

New Features

• Added a built-in Google Cloud Vertex AI provider, configured with model_provider = "gcp". (#56265)
• Added GPT-6.1 Terra to the model catalogs. (#57337)
• Added a repository filter to the session picker and directory grouping to the agent command center, making it easier to navigate sessions across linked worktrees. (#56308)
• Added experimental attached thread forks to the app-server API. (#56351)
• Enabled reasoning effort changes during a conversation by default for supported models. (#56163)
• Enabled memory v2 by default for fresh profiles and added support for importing external-agent memories into it. (#56211, #56414)

Bug Fixes

• Fixed fresh TUI sessions to honor the server’s default approval reviewer when no explicit override is provided. (#56090)
• Kept TUI preferences editable and immediately applicable when execution settings are invalid. (#56091)
• Cancelled remote MCP tool requests when their local response futures are dropped. (#56132)
• Prevented queued agent messages from restarting work after an interrupt or a switch to Plan mode. (#56330)
• Stopped retrying when a provider reports that a model was not found, preserving its error message. (#56445)
• Closed a marketplace URL validation gap that could allow Git to connect to a different host than the one checked against allowed patterns. (#56263)

Changelog

Full Changelog: openai/codex@rust-v0.164.0...rust-v0.165.0

• #56081 Cache decrypted Codex auth and managed secrets @​celia-oai
• #56090 Honor server approval reviewer defaults on fresh TUI startup @​etraut-openai
• #56091 Keep TUI preferences editable when execution settings are invalid @​etraut-openai
• #56097 Prepare TUI startup to accept multiple backend sessions @​bc-openai
• #56124 Forward Guardian reviewer events to parent raw-event subscribers @​jif-oai
• #56127 Avoid blocking EMA auth status checks on account refresh @​jif-oai
• #56132 Cancel MCP tool requests when response futures are dropped @​rhan-oai
• #56133 Defer agent mail after empty final answers @​eknight-oai
• #56139 Fix the MCP auth status test's IdP OAuth configuration @​jif-oai
• #56153 Preserve safe enterprise MCP authentication error details @​jif-oai
• #56154 Add managed network review domains before allow rules @​olliem-oai
• #56163 Enable reasoning effort overrides by default @​felixxia-oai
• #56182 Add AWS SigV4 signing to network proxy MITM hooks @​viyatb-oai
• #56210 Stabilize the marketplace staging cleanup test @​felixxia-oai
• #56211 Default fresh memory profiles to v2 @​jif-oai
• #56214 Remove the u64 cast from WSL DrvFS detection @​felixxia-oai
• #56220 Use cargo_bin in the Windows sandbox manifest test @​felixxia-oai
• #56222 Consolidate Bazel CI setup into prepare-bazel-ci @​anp-oai
• #56224 Reuse current model context across paginated resume config loading @​charliemarsh-oai
• #56233 Make Opus encoder test timestamps follow sample time @​goodman-oai
• #56234 Emit prompt telemetry only after hooks accept input @​abhinav-oai
• #56236 Make the code mode yield/resume test yield explicitly between phases @​goodman-oai
• #56246 Bump Bazelisk to 1.30.0 in the Bazel CI setup action @​anp-oai
• #56247 Consolidate Rust unit tests under dedicated test modules @​dkovalenko-oai
• #56248 Bump uv to 0.13.5 in CI and release workflows @​anp-oai
• #56250 Avoid redundant settings checkpoints when resuming threads @​owenlin0
• #56261 Isolate V8 source dependencies and their C++ runtime settings @​seanh-oai
• #56263 Reject backslashes in HTTP(S) marketplace URL userinfo @​willwang-openai
• #56265 Add a built-in Google Cloud Vertex AI provider @​celia-oai
• #56266 Preserve MCP disable reasons across runtime overlays @​mzeng-openai
• #56272 Upgrade Python SDK model generation to datamodel-code-generator 0.64.0 @​anp-oai
• #56274 Wait for cloud config refresh cancellation in loader lifetime tests @​goodman-oai
• #56277 Support bounded request bodies in AWS SigV4 signing @​viyatb-oai
• #56278 Add negotiated network policy metadata support for MCP calls @​viyatb-oai
• #56280 Group consecutive transcript prompts into one background block @​bc-openai
• #56284 Scope model catalogs and caches by thread originator @​kennyyi-oai
• #56286 Bump @​modelcontextprotocol/sdk to 1.32.0 @​anp-oai
• #56288 Pin Linux artifact signing to Cosign v3.1.4 @​anp-oai
• #56290 Lock Python release build tools with uv @​anp-oai
• #56292 Fix MCP cancellation tests to use the metadata callback @​anp-oai
• #56293 Use fixed-token auth fixtures in Vertex tests @​anp-oai
• #56295 Decouple managed configuration loading from ChatGPT authentication @​smurching-oai
• #56297 Mark built-in dummy credentials and strengthen collision checks @​viyatb-oai
• #56301 Add TLS forwarding tests for MITM SigV4 requests @​viyatb-oai
• #56302 Add hook configuration to environment attachments @​andrewgu-oai
• #56304 Add support for environment-scoped managed hooks @​andrewgu-oai
• #56308 Separate directory and repository scopes in the TUI @​bc-openai
• #56309 Support model-specific writable-root permission wording @​goodman-oai
• #56312 Track accepted conversation history in rollout traces @​cassirer-openai
• #56313 Apply model catalog overrides to history, notes, and context tools @​rhan-oai
• #56314 Add managed configuration loaders for custom config servers @​smurching-oai
• #56330 Make agent-message wakes respect interrupts and Plan mode @​alishobeiri-oai
• #56342 Match rollout trace image content across request snapshots @​cassirer-openai
• #56343 Run environment hooks on their owning executors @​andrewgu-oai
• #56351 Add experimental attached thread forks @​btraut-openai
• #56364 Allow callers to set the thread source for sampling @​keyz
• #56371 Make the Guardian review timeout configurable @​vivi
• #56414 Support memory v2 in external-agent memory imports @​jif-oai
• #56439 Update ctutils from 0.4.2 to 0.4.5 @​felixxia-oai
• #56445 Treat model-not-found provider errors as terminal failures @​charliemarsh-oai
• #56453 Make the Realtime V2 background-agent steering test deterministic @​felixxia-oai
• #56454 Make sandbox mount cleanup tests tolerate file descriptor reuse @​felixxia-oai
• #56459 Add Guardian V3 feature configuration @​felixxia-oai
• #56460 Add Guardian v3 local board helpers @​felixxia-oai
• #56461 Add silent append support to message boards @​felixxia-oai
• #56462 Prevent memory imports from racing with consolidation @​jif-oai
• #56465 Add experimental thread memory summary reads @​jif-oai
• #57337 [0.165.0-alpha.1.2] Backport GPT-6.1 Terra to the model catalogs @​shijie-oai

vercel-labs/agent-browser (aqua:vercel-labs/agent-browser)

v0.40.0: v0.40.0

Compare Source

Breaking Changes

• @​agent-browser/eve now requires eve 0.84.0 or later. eve 0.84.0 rejects extensions built by earlier releases, so the extension is now built with it. Apps on older eve should stay on @​agent-browser/eve@​0.39 (#2226)

New Features

• Added one MCP server per Vercel Sandbox with startAgentBrowserMcp in @​agent-browser/sandbox/vercel, which keeps a single agent-browser mcp running over Sandbox stdin, and connectAgentBrowserMcp for any runtime that exposes stdin and stdout streams (#2228)
• Added --omit-command to batch and omitCommand to the MCP batch tool, replacing repeated raw command arrays in JSON output with zero-based indexes (#2216)

Bug Fixes

• Fixed state load and launch-time storage restores exposing saved tokens to page scripts and writing one origin's storage into another after a redirect; storage is now written through DevTools only while the page is on the saved origin, and skipped origins are reported (#2212)
• Fixed <session>.config files piling up in the socket directory after daemons exit (#2128)
• Fixed mocked cross-origin responses failing CORS: network route --body now takes --allow-origin <origin> (also in the MCP network_route tool) to answer preflights and send CORS headers to that origin, and sends a JSON body as application/json when no content type is set (#2229)
• Fixed Windows sessions where a dead daemon could keep holding a pinned tab, and where two sessions with the same name in different socket directories could connect to each other's daemon (#2223)

Contributors

• @​OwenKephart
• @​Railly
• @​lahfir
• @​hichipli
• @​jomatsu

anthropics/claude-code (github:anthropics/claude-code)

v2.1.312: v2.1.312

Compare Source

What's changed

• Added oidc.user_id_claim to the Claude apps gateway, to identify people by an id_token claim other than sub, such as Microsoft Entra ID's oid
• Added click to send: in fullscreen, clicking the "to send now" hint under a queued message sends it right away, as its key does
• Fixed managed settings and organization policy not being fetched for the rest of the session after signing in from the VS Code extension
• Fixed Claude overwriting a very large CLAUDE.md, rules file or @​-included file in a subdirectory after seeing only its start; Write now asks Claude to read it all or edit in place
• Fixed per-directory and paths: skills not being found after a Bash cd deeper into a git repository
• Fixed a rare case where the first reply after resuming a session in the terminal could be missing the next time the session was resumed
• Fixed a command with an invalid name stopping all commands from loading, which could leave claude -p with no output
• Fixed the Read tool sometimes failing on PDF pages with "pdftoppm failed: Could not write image" when the clean-up of old session files ran at the same time
• Fixed the spinner, OpenTelemetry effort values and transcripts naming a newly picked effort level during a task before the model applied it; they now show the level in force
• Fixed the /model and /effort cache warning saying the re-read waits for your next message; a change made while Claude is working can trigger it sooner
• Fixed some sessions showing as waiting on you when the last message only mentioned items waiting on you mid-sentence
• Fixed agent view restoring input text on the next launch after it was cleared with Ctrl+C just before exiting
• Fixed agent view reopening in shell mode after exiting with Ctrl+D from an empty ! input
• Fixed vim mode d, c and y with a gj or gk count larger than the lines left deleting or copying text; like Vim, they now only move the cursor
• Fixed /verify showing a long description meant for Claude in /help and the / command menu instead of a short one
• Improved the prompt's effort indicator: a change made mid-task now says it may wait for your next message, and the note clears when it no longer applies
• Improved WebFetch errors in cloud sessions: a host that does not resolve is now explained as possibly outside the allowed network domains, so Claude names the host to allow
• Changed Bedrock, Vertex, Foundry and Mantle to use the shorter system prompt for model names Claude Code doesn't recognize, such as custom deployment names and inference profile ARNs, even when they front Sonnet or Haiku; set CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=0 to keep the full prompt
• Changed automatic model switches after a flagged message to also cover model names Claude Code doesn't recognize, such as custom deployment names; set CLAUDE_CODE_DISABLE_REFUSAL_FALLBACK=1 to turn them off
• Changed usage limit messages to call the 5-hour window the "5-hour limit" instead of the "session limit"
• Changed cloud sessions started from the CLI to get their names and branch names from the server
• Changed prompt and agent hooks to run at most 24 at a time per session, sub-agents included, plus at most 12 that have waited longer than their event's timeout; a timeout under 1 second now counts as 1 second
• Changed a subagent's autoCompactWindow to lower the window set by CLAUDE_CODE_AUTO_COMPACT_WINDOW, where it had no effect before; it still never raises that window
• Changed OpenTelemetry mcp_server.name to report the real name of fixed-URL remote MCP servers declared by plugins from the official Anthropic marketplace, instead of custom
• Changed Claude Code to stop sending the claude_code.safety_event OpenTelemetry event
• [VSCode] Fixed sessions ending on a bare exit code when your organization's settings couldn't be loaded or were refused at startup; the tab now says why and offers Retry or Sign in again
• [VSCode] Changed usage limit resets to show a clock time ("Resets at 3:10 PM") and to say "5-hour limit"
• [Cloud sessions] Added an effort level to the model picker when you create or edit a routine that runs in the cloud
• [Cloud sessions] Added a Bash editor with colors, line numbers and a Copy button to the setup script box in cloud environment settings
• [Cloud sessions] Improved the step shown when Claude adds a repository to a cloud session: opening it now shows a short table of what happened instead of raw JSON
• [Cloud sessions] Fixed resending an unchanged message after a failed send in a cloud session sometimes running it twice
• [Cloud sessions] Fixed a failed cloud environment creation showing its error only as a toast outside the open dialog; it now appears inside the dialog
• [Cloud sessions] Fixed Edit in a routine's menu on the Routines page going to the routine's page without opening its edit dialog
• [Remote Control] Fixed an unarchived Remote Control session showing as working until a computer reconnected; it now shows as idle
• [Claude Tag] Improved Claude Tag's retry notice in Slack to name the model in use, or say rate limits were hit, instead of a generic API error
• [Claude Tag] Fixed a Claude Tag channel's on/off switch and agent settings falling back to workspace defaults when an older private Slack channel goes public and gets a new ID
• [Claude Tag] Fixed Claude in Slack not replying in channels whose environment has network access set to None
• [Claude Tag] Fixed Claude in Slack sometimes posting a file in the wrong thread when it was answering in another thread of the same channel
• [Code Review] Fixed Code Review reviewing an outdated commit, or none at all, when GitHub delivered a push event late; it now reviews the pull request's current commit

backnotprop/plannotator (github:backnotprop/plannotator)

v0.28.35: v0.28.35

Compare Source

Follow @​plannotator on X for updates

Missed recent releases?

Release	Highlights
v0.28.34	Start a Grok Build session from the Inbox, action items in your reply, a tidier Board, Settings → Capabilities, a failed feedback send is shown
v0.28.33	Pi updates no longer get stuck on 0.28.31
v0.28.32	A security update (built on Bun 1.4.4, eMudhra certificates), the Inbox Board, custom Inbox prompts, hover cards for issue and PR links, rich-text Copy
v0.28.31	An onboarding tour for the Inbox, pinned threads, picture choices in questions, palettes in Inbox Settings, tailnet reviews from the plugin tool
v0.28.30	An Artifacts view in the Inbox, comments on part of an image, diagrams in code review, Ask AI keeps its conversation in annotate
v0.28.29	Plan review opens on OpenCode 2, a DOMPurify security update, closing a review stops the agent everywhere
v0.28.27	Jump to open questions, files side by side or full screen, image zoom in the Inbox, empty To field, text size for plan review and annotate
v0.28.26	Action items and reply drafts in the Inbox, one decision button for plan review, Enter to save a comment, a custom code font
v0.28.25	Re-ask open questions, delivery ticks on the list, a count of new messages on the tab, right-click a thread, click Inbox to refresh
v0.28.24	A new look for the Inbox, Send now, tag agents, comment on an agent's message, much smaller reads for agents, links in HTML pages
v0.28.23	Inbox replies reach sessions with background subagents, dictated text no longer goes missing, 👍 Looks good reaches the agent, notifications that never fail silently
v0.28.22	👍 Looks good, full view for files, one viewer for a thread's images and files, every session prints its URL, PLANNOTATOR_BROWSER=none opens nothing

What's New in v0.28.35

Plannotator

Updates check the download against checksums Plannotator fetches itself

On macOS and Linux, plannotator update, the Inbox's Update now and the background auto-update no longer download with the system curl. On macOS, curl still trusts the leaked eMudhra root certificates. Plannotator now downloads the install script and the release's checksums over its own connection. The install script then checks the new binary against those checksums before it replaces anything. Windows is unchanged, because Windows already blocks those certificates.

When a download does not match, nothing changes: the update stops with a plain message, and your Plannotator keeps working. The background auto-update then waits 1 day, then 3, then 7, before it tries that version again. A newer release, Update now and plannotator update try at once.

• #2218

Smaller changes

• The install scripts carry the checksums of the sem download instead of reading them from the archive's own checksums.txt. #2218

Install / Update

macOS / Linux:

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

Windows:

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

Claude Code Plugin: The plugin and the plannotator binary update separately, so run the install script above as well. In a terminal:

claude plugin marketplace update plannotator
claude plugin update plannotator@​plannotator

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

Pi:

pi update npm:@​plannotator/pi-extension

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

What's Changed

• Safe updates, step 1: Plannotator downloads the install script and checksums itself by @​backnotprop in #2218

Full Changelog: backnotprop/plannotator@v0.28.34...v0.28.35

v0.28.34: v0.28.34

Compare Source

Follow @​plannotator on X for updates

Missed recent releases?

Release	Highlights
v0.28.33	Pi updates no longer get stuck on 0.28.31
v0.28.32	A security update (built on Bun 1.4.4, eMudhra certificates), the Inbox Board, custom Inbox prompts, hover cards for issue and PR links, rich-text Copy
v0.28.31	An onboarding tour for the Inbox, pinned threads, picture choices in questions, palettes in Inbox Settings, tailnet reviews from the plugin tool
v0.28.30	An Artifacts view in the Inbox, comments on part of an image, diagrams in code review, Ask AI keeps its conversation in annotate
v0.28.29	Plan review opens on OpenCode 2, a DOMPurify security update, closing a review stops the agent everywhere
v0.28.27	Jump to open questions, files side by side or full screen, image zoom in the Inbox, empty To field, text size for plan review and annotate
v0.28.26	Action items and reply drafts in the Inbox, one decision button for plan review, Enter to save a comment, a custom code font
v0.28.25	Re-ask open questions, delivery ticks on the list, a count of new messages on the tab, right-click a thread, click Inbox to refresh
v0.28.24	A new look for the Inbox, Send now, tag agents, comment on an agent's message, much smaller reads for agents, links in HTML pages
v0.28.23	Inbox replies reach sessions with background subagents, dictated text no longer goes missing, 👍 Looks good reaches the agent, notifications that never fail silently
v0.28.22	👍 Looks good, full view for files, one viewer for a thread's images and files, every session prints its URL, PLANNOTATOR_BROWSER=none opens nothing
v0.28.21	Message an agent from the Inbox, video attachments, Open in for attachments, Code / Tests / Generated in code review, writes from other websites refused

What's New in v0.28.34

A tidier Board in the Inbox, a Board chip in compose, action items in your reply, hover cards in review, and failed sends that no longer look like they worked. Usage counts are removed. 25 PRs.

Plannotator Inbox

A tidier Board

Lane cards are one title row now, with the marks and the age on the right. A second line shows only when you owe something ("You: …") or a send is waiting. "You: …" opens the thread where you decide, and an opened card has Open thread or Create thread at the top. Agents now give cards short titles of 2 to 5 words.

• #2248, #2240

Ask the agent to track new work on the Board

Compose has a Board chip beside the Thread row. Turn it on, and the agent puts the work you ask for on the Board, unless a card already links the thread. The chip shows only while the Board is on.

• #2249

Settings → Capabilities

A new Capabilities section holds the Board switch, with the Experimental switches under it.

The Board switch has moved from Settings → General to Settings → Capabilities.

• #2234

Action items go in your reply

Done and Can't do it now go into your reply draft, with any note, and reach the agent with your next Send.

A Done no longer goes to the agent by itself after a few seconds; it waits for your Send.

• #2216

Agents reply in the right thread after compaction

After the agent compacts its context or resumes, it gets the list of its open Inbox threads, so it replies where it should and not to a thread it half remembers. A decision that waits in the Inbox stays there: the agent no longer asks it again in the chat.

• #2246

Decide inside a thread (experimental)

Decision mode now starts from a thread. When 2 or more decisions wait in a thread, "Decide these N" is the first row of its open questions.

The Decide button beside the list title and the Decide row in the sidebar are gone.

• #2241

Start a Grok Build session from the Inbox

When Grok Build is installed, New message can start a Grok Build session in any of your projects. The Inbox runs the session, so every reply you send reaches it as a real turn. You answer its permission requests in the thread. To turn it off, use Settings → Agents → Run in the Inbox.

• #2174

Smaller changes

• Full screen goes back to where you opened it. ×, Escape and the browser's Back return to the thread or to the file beside it. #2245
• A recommendation written into a choice label counts. "Foo (Recommended)" shows as the recommended choice, with Accept recommended. #2247
• A Recommended: line finds a choice written as a link or with formatting. #2251
• A click anywhere in the reply box puts the cursor in it, so typed and dictated text no longer goes nowhere. #1960
• A new Inbox tab is always counted as open, and a closed one no longer is. #2237, #2250
• While the Board is off, agents see one line saying it exists and where to read about it. #2260
• Cursor's Inbox note says plainly that you paste it into Cursor yourself, and the copy no longer carries markers that promise an automatic removal. #2162, for #1991

Plannotator

You see when feedback does not send

In plan review, annotate and code review, a send that fails now shows why, with Retry and Copy feedback, and your annotations stay where they were.

A failed approve or send now keeps you on the page; before, it could show the Approved or Feedback Sent screen.

• #2242, for #1392

Hover cards for issue, PR and MR links

In plan review, annotate and code review, pointing at a GitHub issue or PR link, or a GitLab MR link, shows its title and state, read through gh or glab on your computer. This works in Pi too. Remote sessions don't show the cards.

• #2262

Usage counts are removed

Plannotator no longer has any code that counts the use of experimental features. Nothing was ever sent on its own: only a hidden command could send counts, and only when someone typed it. The experimental switches work as before.

The hidden plannotator telemetry command is gone.

• #2259

A one-time introduction to the Plannotator Inbox

Plan review, annotate and code review show a short film about the Inbox once, with Close and Learn about the Inbox. After you close it, it does not show again anywhere.

• #2256

Smaller changes

• Plan review keeps a plan's versions when Claude Code changes folder between submits, so the Versions tab and the diff stay. #2199, for #2197
• Code review: "Edit Code to Suggest" moves to a new Experimental tab in Settings. #2234
• Every published package is checked before release for settings that could hold an update back without a word, as happened to Pi on 0.28.31. #2238, for #902
• The privacy page's contact email is now ramos@​plannotator.ai. #2252

Install / Update

macOS / Linux:

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

Windows:

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

Claude Code Plugin: The plugin and the plannotator binary update separately, so run the install script above as well. In a terminal:

claude plugin marketplace update plannotator
claude plugin update plannotator@​plannotator

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

Pi:

pi update npm:@​plannotator/pi-extension

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

What's Changed

• test: deflake four tests (clock, shared-events, multiTarget, auto-update SIGINT) by @​backnotprop in #2237
• refactor(core): move the Inbox thread's pure rules into @​plannotator/core by @​backnotprop in #2224
• test(inbox): pixel and DOM parity harness for the thread by @​backnotprop in #2222
• Board: "You:" opens the thread where you decide; less padding under the lanes by @​backnotprop in #2240
• Settings: Capabilities section (Board, with Experimental inside) in the Inbox; Experimental tab in code review by @​backnotprop in #2234
• Inbox: Decide works inside a thread (no global queue) by @​backnotprop in #2241
• fix(questions): read a recommendation marked in a choice label, and nudge the agent toward Recommended: by @​backnotprop in #2247
• Board: Title-row lane cards, Open/Create thread on the opened card, short titles by @​backnotprop in #2248
• Show when feedback or a decision fails to send (Retry, Copy feedback) by @​backnotprop in #2242
• feat(inbox): open threads after compaction/resume, reply_to checks, chat-or-Inbox rule, notes refreshed at start by @​backnotprop in #2246
• Compose: a Board chip that asks the agent to track the work by @​backnotprop in #2249
• fix(questions): a Recommended: line names a markdown label by its plain words by @​backnotprop in #2251
• fix(inbox): full screen goes back to where it was opened from by @​backnotprop in #2245
• Remove the usage counts for experimental features; keep the flags by @​backnotprop in #2259
• Privacy page: contact email is ramos@​plannotator.ai by @​backnotprop in #2252
• Inbox: a press anywhere in the reply box puts the caret in it by @​backnotprop in #1960
• One-time Plannotator Inbox announcement in plan review, annotate and code review by @​backnotprop in #2256
• fix: honest wording for Cursor's copy-by-hand Inbox note (follow-up to #2153) by @​backnotprop in #2162
• fix(plan): keep a plan's version history when the session cd's into another repo (#2197) by @​backnotprop in #2199
• chore(deps): bump motion from 12.43.0 to 14.4.0 by @​dependabot in #2202
• Inbox: one Board line for agents while the Board is off by @​backnotprop in #2260
• Hover cards for issue, PR and MR links in plan review, annotate and code review (Bun and Pi) by @​backnotprop in #2262
• fix(inbox): a closing tab no longer counts itself again after pagehide (notify_reach e2e) by @​backnotprop in #2250
• Inbox: action items go in the person's reply by @​backnotprop in #2216
• ci: guard every published package against update-blocking fields by @​backnotprop in #2238
• Inbox: start a Grok Build session from New message, every reply a real turn (ACP runner, step 1) by @​backnotprop in #2174

Community

• @​HunterClarke-git: reported in #1392 that feedback could be lost
• @​zane668: gave a step-by-step reproduction in #1392 of feedback lost after Plannotator stopped, and reported in #902 the Pi update that stuck on 0.28.31, which the new release check guards against
• @​kyletruong: asked in #1991 for the Inbox note in Cursor
• @​aomalov: reported in #2197 that plan history lost its versions after a change of folder, and proposed a fix in #2205

Full Changelog: backnotprop/plannotator@v0.28.33...v0.28.34