You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: .github/ISSUE_TEMPLATE/issue.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -11,9 +11,9 @@ assignees: ''
11
11
-[ ]*I agree to communicate with the author myself* (not AI-generated).
12
12
-[ ] I've read the README's [Filing issues](https://github.com/xenodium/agent-shell?tab=readme-ov-file#filing-issues) section.
13
13
-[ ] I'm running the latest versions (fill in below).
14
-
- agent-shell:
15
-
- acp.el:
16
-
- ACP package (e.g. claude-code-acp):
17
-
- Agent CLI (e.g. claude, gemini):
14
+
- agent-shell version:
15
+
- acp.el version:
16
+
- ACP package (e.g. claude-agent-acp) version:
17
+
- Agent CLI (e.g. claude, gemini) version:
18
18
-[ ] For requesting new agent support, I'm including a link to the ACP-capable agent or related ACP package.
19
19
-[ ] For issues, I'm including [ACP traffic](https://github.com/xenodium/agent-shell?tab=readme-ov-file#how-do-i-viewget-agent-client-protocol-traffic) (as per README).
Copy file name to clipboardExpand all lines: CONTRIBUTING.org
+15-1Lines changed: 15 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -54,6 +54,18 @@ Accessing and working with =alists=? Please prefer =map.el= unless we have a str
54
54
(map-elt animal :species)
55
55
#+end_src
56
56
57
+
** Prefer =map-nested-elt= over nested =map-elt=
58
+
59
+
When accessing nested alist values, use =map-nested-elt= instead of nesting =map-elt= calls.
60
+
61
+
#+begin_src emacs-lisp :lexical no
62
+
;; Avoid
63
+
(map-elt (map-elt response 'usage) 'totalTokens)
64
+
65
+
;; Prefer
66
+
(map-nested-elt response '(usage totalTokens))
67
+
#+end_src
68
+
57
69
** cl-lib (limited to =cl-defun=)
58
70
59
71
While I'm a fan of =cl-defun=, please limit =cl= usage to =cl-defun= if possible. Nothing against =cl-lib=. I'm just limiting the surface and number of idioms I need to keep in my head to maintain the codebase. Often, =seq.el= and =map.el= can do the job just fine.
@@ -146,7 +158,9 @@ When defining hook functions or callbacks, prefer a single alist/event parameter
146
158
147
159
Remove comments obviously by an LLM (e.g. referencing "previous code" or restating the obvious). Avoid emojis in code and output strings.
148
160
149
-
** Keep PRs focused
161
+
** Keep PRs small and focused
162
+
163
+
Prefer smaller PRs whenever possible. They're easier to review and less likely to introduce issues. If a change can be split into independent steps, submit them as separate PRs.
150
164
151
165
Don't include unrelated changes (whitespace, indentation, formatting) in your PR. If you'd like to do a cleanup, please submit it as a separate PR.
Copy file name to clipboardExpand all lines: README.org
+9-8Lines changed: 9 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -32,7 +32,7 @@ Thank you!
32
32
33
33
A native Emacs shell to interact with LLM agents powered by ACP ([[https://agentclientprotocol.com][Agent Client Protocol]]).
34
34
35
-
With agent-shell, you can chat with the likes of Gemini CLI, Claude Code, Auggie, Mistral Vibe, or any other ACP-driven agent.
35
+
With agent-shell, you can chat with the likes of Gemini CLI, Claude Agent, Auggie, Mistral Vibe, or any other ACP-driven agent.
36
36
37
37
Watch on [[https://www.youtube.com/watch?v=R2Ucr3amgGg][YouTube]]
38
38
@@ -60,7 +60,8 @@ We now have a handful of additional packages to extend the =agent-shell= experie
60
60
- [[https://github.com/gveres/agent-shell-workspace][agent-shell-workspace]]: Dedicated tab-bar workspace for managing multiple =agent-shell= sessions.
61
61
- [[https://github.com/ElleNajt/agent-shell-to-go][agent-shell-to-go]]: Interact with =agent-shell= sessions from your mobile or any other device via Slack.
62
62
- [[https://github.com/ElleNajt/meta-agent-shell][meta-agent-shell]]: Multi-agent coordination system for =agent-shell= with inter-agent communication, task tracking, and project-level dispatching.
63
-
- [[https://github.com/xenodium/emacs-skills][emacs-skills]]: Claude Code skills for Emacs.
63
+
- [[https://github.com/xenodium/agent-shell-knockknock][agent-shell-knockknock]]: Notifications for =agent-shell= via [[https://github.com/konrad1977/knockknock][knockknock.el]].
64
+
- [[https://github.com/xenodium/emacs-skills][emacs-skills]]: Claude Agent skills for Emacs.
64
65
65
66
* Icons
66
67
@@ -70,9 +71,9 @@ Thanks to [[https://github.com/lobehub/lobe-icons][Lobe Icons]] for the lovely i
70
71
71
72
** External dependencies
72
73
73
-
*** Claude Code
74
+
*** Claude Agent SDK
74
75
75
-
For Anthropic's Claude Code, follow [[https://github.com/zed-industries/claude-agent-acp][Zed's claude-agent-acp instructions]], typically something like:
76
+
For Anthropic's [[https://platform.claude.com/docs/en/agent-sdk/overview][Claude Agent SDK]] (formerly known as the Claude Code SDK), follow [[https://github.com/zed-industries/claude-agent-acp][Zed's claude-agent-acp instructions]], typically something like:
76
77
77
78
#+begin_src bash
78
79
npm install -g @zed-industries/claude-agent-acp
@@ -390,7 +391,7 @@ For API key authentication:
390
391
391
392
*** Customizing Available Agents
392
393
393
-
By default, =agent-shell= includes configurations for all supported agents (Claude Code, Gemini CLI, Codex, Goose, Qwen Code, and Auggie). You can customize which agents are available through the =agent-shell-agent-configs= variable.
394
+
By default, =agent-shell= includes configurations for all supported agents (Claude Agent, Gemini CLI, Codex, Goose, Qwen Code, and Auggie). You can customize which agents are available through the =agent-shell-agent-configs= variable.
394
395
395
396
** Usage
396
397
@@ -404,7 +405,7 @@ You can select and start any of the known agent shells (see =agent-shell-agent-c
404
405
405
406
Start a specific agent shell session directly:
406
407
407
-
- =M-x agent-shell-anthropic-start-claude-code= - Start a Claude Code agent session
408
+
- =M-x agent-shell-anthropic-start-claude-code= - Start a Claude Agent session
408
409
- =M-x agent-shell-auggie-start-agent= - Start an Auggie agent session
409
410
- =M-x agent-shell-openai-start-codex= - Start a Codex agent session
410
411
- =M-x agent-shell-google-start-gemini= - Start a Gemini agent session
@@ -717,7 +718,7 @@ always go to Evil modes if you need to with ~C-z~).
| | agent-shell-clear-buffer | Clear the current shell buffer. |
723
724
| | agent-shell-completion-mode | Toggle agent shell completion with @ or / prefix. |
@@ -834,7 +835,7 @@ Sometimes including a traffic screenshot in an issue is enough. Other times incl
834
835
835
836
If you're able to determine the agent is missing a feature (or a bug is present) in their [[https://agentclientprotocol.com][Agent Client Protocol]] implementation, please file an issue directly with the agent folks. For example:
836
837
837
-
- [[https://github.com/zed-industries/claude-code-acp][claude-code-acp]]: For Claude Code.
838
+
- [[https://github.com/zed-industries/claude-code-acp][claude-code-acp]]: For Claude Agent.
838
839
- [[https://github.com/zed-industries/codex-acp][codex-acp]]: For Codex.
0 commit comments