agent-shell 0.87 updates

Agent-shell 0.87.4 brings the Emacs AI agent client to 23 supported agents with the additions of Junie and OpenClaw, up from the two agents (Claude and Gemini) it launched with just over a year ago. The release, which follows 0.78.2, is focused primarily on bugfixes and polish but adds animated prompt busy indicators, a default-on agent-shell-prompt-queue-merge setting that joins queued prompts into a single turn, and decoupled @ and / completion via agent-shell-file-completion-enabled and agent-shell-command-completion-enabled. The project is powered by the Agent Client Protocol (ACP).

It's October. New month, new agent-shell https://github.com/xenodium/agent-shell update. If you missed the last post, have a look at the 0.78 update https://xenodium.com/agent-shell-0-78-updates . While the latest changes are focused primarily on bugfixes and polish, we have a handful of new features too. As usual, this post showcases highlights, but please check out the full list of changes https://github.com/xenodium/agent-shell/compare/v0.78.2...v0.87.4 if you're after the nitty-gritty. agent-shell ? agent-shell https://github.com/xenodium/agent-shell brings your favorite AI agents to Emacs https://www.gnu.org/software/emacs/ , keeping you at home: familiar buffers and bindings, no terminal emulation. All powered by ACP, the Agent Client Protocol https://agentclientprotocol.com/ . I introduced agent-shell https://xenodium.com/introducing-agent-shell just over a year ago, with support for two agents: Claude and Gemini. Today, it speaks to 23. Development hasn't let up either. Improvements and new features land every month. Thank you to all users, contributors, and sponsors. A couple more join the family, bringing it to 23 agents . As usual, they're all reachable via M-x agent-shell , or go straight to the new ones: M-x agent-shell-junie-start-agent . M-x agent-shell-openclaw-start-agent . With the ability to prompt at any time see my last post https://xenodium.com/agent-shell-0-78-updates prompt-any-time , you can queue prompts or steer agents straight from the persistent shell prompt. Animating the prompt ties it all together: it's now obvious at a glance that the agent is busy, and that anything else you submit will queue. Check out agent-shell-prompt-busy-frames for relevant customizations more on that shortly . Thanks to @cark https://github.com/cark for the proposal https://github.com/xenodium/agent-shell/issues/843 . The header's busy indicator has been animated for some time now. Amongst the existing customizations, agent-shell-show-busy-indicator could turn it off altogether. Having said that, there's now a middle ground: use static text via agent-shell-busy-indicator-frames . Just set it to a string like so: setopt agent-shell-busy-indicator-frames " busy " If you'd like to use smarter logic, you can now set it to a function as follows: setopt agent-shell-busy-indicator-frames lambda if agent-shell-session-id " busy " " connecting " agent-shell-prompt-busy-frames takes all the same forms, so the prompt's own animation can also be a list of frames, a static string, or a function. With the new agent-shell-prompt-queue-merge setting enabled by default , pending prompts are joined separated by blank lines and submitted as a single turn. Queued prompts are typically follow-ups to the same instruction, so the agent now sees them together rather than acting on the first before reading the rest. If you prefer the previous behaviour, disable it with: setopt agent-shell-prompt-queue-merge nil Thank you @Gleek https://github.com/Gleek for the proposal https://github.com/xenodium/agent-shell/issues/791 . While on the subject of queueing, cancelling now offers to continue with the queue rather than quietly dropping it, and killing a shell now warns you about the pending work you'd lose. @ and / completion used to bundle two things: how to complete, and when to pop up. Turning the popping off lost completion altogether, leaving corfu https://github.com/minad/corfu and company users out. They're now decoupled. The completion functions are always registered, so completion-at-point , corfu and company work either way. Two options decide whether completion pops as you type: agent-shell-file-completion-enabled for @ and agent-shell-command-completion-enabled for / . For example, listing files can be slow in a large project, so to only complete @ on demand while / keeps popping: setopt agent-shell-file-completion-enabled nil Trailing spaces and @ mention quoting are now only inserted on a finished completion, fixing the stray spaces corfu and company users were seeing. Thanks to @bcc32 https://github.com/bcc32 for proposing the split and separate @ and / options in 537 https://github.com/xenodium/agent-shell/issues/537 , and to @jcubic https://github.com/jcubic for filing it and flagging the stray spaces. C-M-a and C-M-e beginning-of-defun and end-of-defun now move between blocks. Thank you @OSadovy https://github.com/OSadovy for 876 https://github.com/xenodium/agent-shell/pull/876 . Chat mode draws "Me" and "Agent" labels or rather "Claude", "Codex" etc. . If the current style isn't your jam, agent-shell-chat-label-function now lets you draw them yourself. It's handed an alist with :text and :role either user or agent , and must return a single-line propertized string. The display property is honored, so labels can also be rendered as images. Thanks to @nhojb https://github.com/nhojb for the idea. Transcripts now open with YAML frontmatter, including a start timestamp as follows: --- agent: "Claude" started: "2026-10-11T09:30:12+01:00" working directory: "~/stuff/active/code/agent-shell" session id: "0f3c9a1e-5b7d-4e2a-9c81-6d4f2b8e7a35" model: "claude-opus-4-5" --- Thank you @vermiculus https://github.com/vermiculus for 854 https://github.com/xenodium/agent-shell/pull/854 . While on topic, transcripts also got a little sturdier, thanks to @mrcnski https://github.com/mrcnski 's proposal https://github.com/xenodium/agent-shell/issues/859 . M-x yank-media support M-x yank-media now pastes images straight from the system clipboard 853 https://github.com/xenodium/agent-shell/issues/853 , no external utilities needed, the same way Org mode handles it. Pasted image previews also survive being queued or steered, thanks to @Gleek https://github.com/Gleek for 852 https://github.com/xenodium/agent-shell/pull/852 . Codex gained agent-shell-openai-default-config-options for setting config options at session start, reasoning effort included. For example: setopt agent-shell-openai-default-config-options ' "reasoning effort" . "high" Thank you @ianthetechie https://github.com/ianthetechie for 855 https://github.com/xenodium/agent-shell/pull/855 . Tool call output can be fairly long. A single chunky line was enough to bog a buffer down. Long tool output lines are now limited 844 https://github.com/xenodium/agent-shell/pull/844 by @Gleek https://github.com/Gleek , and fallback titles are truncated so they no longer flash chunkily as they stream. File summaries also count distinct files now, so reading the same file three times counts as one file rather than three 863 https://github.com/xenodium/agent-shell/pull/863 , also by @Gleek https://github.com/Gleek . While we have a handful of new features, the bulk of this release went into fixes. Rendering: M-x agent-shell-copy-as-markdown no longer mangles bullets carrying bold text Performance and responsiveness: path:line references are now found in linear time visual-wrap-prefix-mode enabled no longer hangs Emacs Elsewhere: display-buffer-overriding-action is preserved when displaying asynchronously tramp-remote-path and direct async processes rather than a bug. New shells now show the last few release posts on the welcome screen, so they are a little more discoverable. A few additions for package authors building on agent-shell . agent-shell-initialized-p returns non-nil once the handshake, authentication, session and any default options are all done. Until then, subscribe to the new init-finished event via agent-shell-subscribe-to 860 https://github.com/xenodium/agent-shell/issues/860 . Agent config options are now reachable from elisp rather than the UI alone: agent-shell-config-options agent-shell-config-option :category "thought level" agent-shell-config-option-value :id "effort" agent-shell-set-config-option-value :id "effort" :value "high" :on-success lambda message "Set" agent-shell-last-activity-time returns when the shell last saw a submitted prompt or an incoming notification M-x agent-shell-save-traffic writes the session's ACP traffic to a .traffic file and reveals it in dired , simplifying the bug-filing process. agent-shell-gc https://github.com/izeigerman/agent-shell-gc joins the lot, bringing buffer garbage collection auto-kill to agent-shell . If you peeked at the commit logs https://github.com/xenodium/agent-shell/compare/v0.78.2...v0.87.4 for the period, you'll see it's been a busy few weeks. Since the last post, 125 commits shipped, 33 issues have been closed and 15 pull requests merged. As of this writing, the backlog sits at 4 open issues and 6 open PRs versus 16 and 6 last time around . Zooming out a little, here's how the backlog has tracked: As usual, this chart was generated using the /github-activity skill shared in my emacs-skills https://github.com/xenodium/emacs-skills repo. Four open issues is the lowest it's been since the project's first week, which I'm pleased about. All of this requires daily attention. Tokens keep your agents running. Sponsors https://github.com/sponsors/xenodium keep agent-shell running. agent-shell is built and maintained by me, an indie dev, while the tools it competes with have well-funded teams behind them. Vendor-neutral tooling matters more than ever. Using agent-shell at work? Ask your employer to sponsor https://github.com/sponsors/xenodium too. Companies can contribute at a scale individuals can't. Thank you to all contributors for these improvements agent-shell stands on acp.el https://github.com/xenodium/acp.el to speak ACP and shell-maker https://github.com/xenodium/shell-maker for its shell foundations, so fixes landing there reach you just the same: As of this writing, we're 88% of the way to the 150 monthly sponsors goal . If agent-shell is part of your daily workflow, please consider becoming a monthly sponsor https://github.com/sponsors/xenodium or ask your employer to . Not in a position to sponsor? A GitHub star https://github.com/xenodium/agent-shell/ helps with exposure and brings in new users.