Defend against ACP server reporting used > size#364
Closed
timvisher-dd wants to merge 10 commits intoxenodium:mainfrom
Closed
Defend against ACP server reporting used > size#364timvisher-dd wants to merge 10 commits intoxenodium:mainfrom
timvisher-dd wants to merge 10 commits intoxenodium:mainfrom
Conversation
timvisher-dd
force-pushed
the
timvisher-dd/tests/add-shell-usage-regression-tests
branch
from
e528a97 to
3e99679
Compare
timvisher-dd
changed the title
timvisher-dd
force-pushed
the
timvisher-dd/tests/add-shell-usage-regression-tests
branch
from
3e99679 to
6d914d4
Compare
timvisher-dd
changed the title
1 task
timvisher-dd
force-pushed
the
timvisher-dd/tests/add-shell-usage-regression-tests
branch
from
6d914d4 to
c98e427
Compare
timvisher-dd
force-pushed
the
timvisher-dd/tests/add-shell-usage-regression-tests
branch
2 times, most recently
from
e2ce5c0 to
f64cdbd
Compare
timvisher-dd
force-pushed
the
timvisher-dd/tests/add-shell-usage-regression-tests
branch
from
f64cdbd to
2f153b2
Compare
timvisher-dd
force-pushed
the
timvisher-dd/tests/add-shell-usage-regression-tests
branch
from
2f153b2 to
8b63348
Compare
CI workflow runs byte-compilation and ERT tests on push/PR using GitHub Actions with deps checked out from timvisher-dd/acp.el-plus and xenodium/shell-maker. bin/test parses ci.yml with yq so local runs stay in sync with CI automatically. It symlinks local dependency checkouts into deps/ to match the CI layout. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New library for sending desktop notifications from Emacs. In GUI mode on macOS, uses native UNUserNotificationCenter via a dynamic module (agent-shell-alert-mac.dylib) compiled JIT on first use (inspired by vterm). When compilation fails (e.g. missing Xcode CLI tools), a message recommends `xcode-select --install`. In terminal mode, auto-detects the host terminal emulator and sends the appropriate OSC escape sequence: - OSC 9: iTerm2, Ghostty, WezTerm, foot, mintty, ConEmu - OSC 99: kitty - OSC 777: urxvt, VTE-based terminals Inside tmux, wraps in DCS passthrough (checking allow-passthrough first). Falls back to osascript on macOS when the terminal is unknown or tmux passthrough is not enabled. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Follows the same pattern as acp.el: a boolean toggle (agent-shell-logging-enabled, off by default), a per-shell log buffer stored in state, and label+format-string logging. Adds log calls to idle notification start/cancel/fire for observability. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
After each agent turn completes, a 30s timer starts. Any user input in the buffer cancels it; otherwise it fires a desktop notification via agent-shell-alert. The echo area message is only shown when the shell buffer is not the active buffer. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Validate that agent-shell-buffers and agent-shell-project-buffers reflect (buffer-list) ordering correctly: switch-to-buffer and select-window promote, with-current-buffer does not, bury-buffer demotes, and project filtering preserves order. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fails PRs that modify .el files or tests/ without also updating README.org, ensuring the soft-fork features list stays current. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add comprehensive ERT tests for agent-shell-usage.el covering notification updates, context indicator scaling/colors, compaction replay, token saving, and number formatting. The ACP server has a bug where model switches cause used to exceed size in session/update notifications. Rather than clamping, signal unreliable data: indicator shows ? with warning face, format shows (?) instead of a bogus percentage. A regression test replays real observed traffic from the Opus 1M -> Sonnet 200k switch scenario. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
timvisher-dd
force-pushed
the
timvisher-dd/tests/add-shell-usage-regression-tests
branch
from
8b63348 to
b9ca659
Compare
4 tasks
timvisher-dd
deleted the
timvisher-dd/tests/add-shell-usage-regression-tests
branch
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The ACP server (claude-agent-acp) has a bug where model switches cause
usedto exceedsizeinsession/updatenotifications. For example, switching from Opus 1M to Sonnet 200k dropssizeto 200000 whileusedkeeps growing past it (observed: 419574/200000 = 209.8%). This results in nonsensical context indicators and percentages e.g. (from a real session)While I intend to get a fix for this improper reporting into claude-agent-acp, agent-shell should be robust against it. To that end, when the garbage usage data is observed, the UI now signals unreliable data instead of showing nonsense:
?with warning face whenused > size(?)instead of a bogus percentageThis also adds comprehensive ERT test coverage for
agent-shell-usage.el: notification updates, indicator scaling/colors, compaction replay, token saving, and number formatting.For the
claude-agent-acpside of this see agentclientprotocol/claude-agent-acp#412Test plan