vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 2

Compare commits

base: vinzenz:90cd602d4e1b89d2bfe0d2a33a2dd378ce09c2f5
Branches Tags
vinzenz:main
..
compare: vinzenz:36b2e2a16ca503121f61b1358d9cf584e4a755b6
Branches Tags
vinzenz:main
1 changed files with 6 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

15
hive-bash-mcp/src/runner.rs
View file

@ -526,15 +526,12 @@ async fn run_task(mut task: TaskFile, socket: &Path) {
if let Err(e) = write_task(&task) { if let Err(e) = write_task(&task) {
tracing::warn!(id = %id, error = ?e, "bash_runner: write running state failed"); tracing::warn!(id = %id, error = ?e, "bash_runner: write running state failed");
} }
// No command text in the summary: `id` is already the human-chosen upsert_bash_todo(
// `name` when the caller passed one, and even the auto-generated socket,
// hex id was already returned to the agent in the `run` tool's own &id,
// result — the todo only needs to say which task, not repeat the format!("bash task `{id}` running: `{}`", task.cmd),
// command. An unbounded raw command (e.g. a multi-line heredoc )
// script) would balloon every UI that renders todo summaries; the .await;
// full command stays on disk in the task file for `status`/`view`
// instead.
upsert_bash_todo(socket, &id, format!("bash task `{id}` running")).await;
// Best-effort: tally the normalised command head for the /stats // Best-effort: tally the normalised command head for the /stats
// "favorite tools" view. Counted once per execution, regardless of // "favorite tools" view. Counted once per execution, regardless of
// exit status. Never fails the task. // exit status. Never fails the task.