@staff0rd/assist 0.921.0 → 0.923.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -479,7 +479,6 @@ A config still holding a retired ssh link (`ssh:` / `port:` / `localPort:`) fail
479
479
  - `sessions.nodeName` — this install's node label. Defaults to the OS hostname, suffixed `-wsl` under WSL.
480
480
  - `sessions.tailscaleServe` — expose the web server on the tailnet. Defaults to **true**.
481
481
  - `sessions.includeCommittedChanges` — include the commits recorded against the session's backlog item, not just uncommitted work, in its change counts and diff. Defaults to **true**.
482
- - `sessions.parkWaitingAfterMs` — how long every session in a repo group must wait on input before the group collapses and parks at the bottom of the sidebar. Defaults to **300000**.
483
482
  - `sessions.newSessionMode` — the mode pre-selected in the new session dialog: `draft`, `bug`, `prompt` or `design`. Defaults to **draft**.
484
483
  - `sessions.maxLive` — the most live sessions one daemon holds at once. Defaults to **24**.
485
484
 
@@ -3,4 +3,4 @@ title: Asking for sign-off
3
3
  when: always
4
4
  ---
5
5
 
6
- When a plan, summary or proposed decision needs the user's sign-off before you act on it, don't ask in chat. Write it as markdown to a scratch file and run `assist ask --title '<title>' --body - < <file>` as a background task, doing no other work until it returns. It opens in the session's web preview pane with approve, reject and inline comments, and blocks until the user decides. Approval exits 0 and prints any comments to fold in; rejection exits non-zero with the reason and comments — revise and re-run. Outside a web session it just prints the markdown, so ask in chat.
6
+ When a plan, summary or proposed decision needs the user's sign-off before you act on it, don't ask in chat. Write it as markdown to a scratch file and run `assist ask --title '<title>' --body - < <file>` as a background task, doing no other work until it returns. It opens in the session's web preview pane with approve, reject and inline comments, and blocks until the user decides. Approval exits 0 and prints any comments to fold in; rejection exits non-zero with the reason and comments — revise and re-run. To revise a still-pending preview, re-run it directly without stopping the earlier task; that task then exits 0 as superseded — ignore its result. Outside a web session it just prints the markdown, so ask in chat.
@@ -21,6 +21,8 @@ assist ask --title '<short title>' --body - < <scratch file>
21
21
 
22
22
  Always run it **as a background task**, and do no other work until it returns. In a web session it blocks until the user decides, which can take far longer than the default command timeout, and the pending preview dies with the process.
23
23
 
24
+ To revise the update while it is still pending, re-run Step 2 directly — do not stop the earlier task. The pane swaps to the new version, and the earlier task exits 0 printing `Superseded by a newer preview — no decision; ignore this result.`: ignore it.
25
+
24
26
  Outside a web session it prints the markdown and exits 0 without a decision: ask the user in chat instead.
25
27
 
26
28
  ## Step 3: act on the decision
@@ -70,7 +70,7 @@ JSON
70
70
 
71
71
  The payload is strict JSON — an unknown key is an error. `\n` inside the `description` string is a JSON escape and becomes a real newline, which is what the markdown rendering needs.
72
72
 
73
- Always run `propose` **as a background task**, and do no other work until it returns. In a web session it blocks on the preview pane until the user decides, which can take far longer than the default command timeout, and the pending preview dies with the process — a killed `propose` abandons the item.
73
+ Always run `propose` **as a background task**, and do no other work until it returns. In a web session it blocks on the preview pane until the user decides, which can take far longer than the default command timeout, and the pending preview dies with the process — a killed `propose` abandons the item. To revise the report while its preview is still pending, re-run `propose` with the revised payload directly — do not stop the earlier task. The pane swaps to the new version, and the earlier task exits 0 printing `Superseded by a newer preview — no decision; ignore this result.` without creating anything: ignore it.
74
74
 
75
75
  `propose` decides where the bug report is reviewed and prints what to do next. Follow that instruction; never inspect the environment to work it out yourself:
76
76
 
@@ -104,7 +104,7 @@ JSON
104
104
 
105
105
  The payload is strict JSON — an unknown key is an error. `\n` inside the `description` string is a JSON escape and becomes a real newline, which is what the markdown rendering needs. Each phase needs at least one task; omit `manualChecks` for the phases that don't need any (most of them). A phase named `Review` is rejected: the runner appends that phase itself.
106
106
 
107
- Always run `propose` **as a background task**, and do no other work until it returns. In a web session it blocks on the preview pane until the user decides, which can take far longer than the default command timeout, and the pending preview dies with the process — a killed `propose` abandons the item.
107
+ Always run `propose` **as a background task**, and do no other work until it returns. In a web session it blocks on the preview pane until the user decides, which can take far longer than the default command timeout, and the pending preview dies with the process — a killed `propose` abandons the item. To revise the item while its preview is still pending, re-run `propose` with the revised payload directly — do not stop the earlier task. The pane swaps to the new version, and the earlier task exits 0 printing `Superseded by a newer preview — no decision; ignore this result.` without creating anything: ignore it.
108
108
 
109
109
  `propose` decides where the item is reviewed and prints what to do next. Follow that instruction; never inspect the environment to work it out yourself:
110
110
 
@@ -62,6 +62,8 @@ Display the output so the user can see what happened. If the command exits non-z
62
62
  - **Request changes** — the reason and every inline comment, each with the excerpt it was left on. The output names the working file holding the pane's markdown, collapses included. Revise **that file in place** to address the comments — never recompose the body from scratch — then re-run the command, which previews the revised file with the earlier collapses intact. Pass `--fresh` only when the working file should be thrown away and the issue re-fetched.
63
63
  - **The issue moved on GitHub** — it names the working file holding the markdown. Someone else edited the issue, so nothing was pushed; tell the user rather than re-running blind.
64
64
 
65
+ Any preview in this skill (`edit`, `create`, `comment`) can be revised while still pending by re-running the command directly — do not stop the earlier task. The earlier task exits 0 printing `Superseded by a newer preview — no decision; ignore this result.` without touching GitHub: ignore it.
66
+
65
67
  ## Action: create
66
68
 
67
69
  Create a new issue from a free-form request (e.g. `create bug against owner/repo, Sprint 3 milestone, Roadmap project: login fails on Safari`). Step 2 does not apply — there is no issue yet. Work out from the args:
@@ -64,7 +64,7 @@ The payload is the whole plan, not a patch: every phase you want the item to end
64
64
 
65
65
  Do not chain `add-phase`, `update-phase`, `remove-phase` and `move-phase` calls to build up a change — that is one preview per command and leaves the item half-edited if the user rejects part way. Those commands remain for a human typing a quick one-liner at a terminal.
66
66
 
67
- In a web session this renders the whole change into the preview pane as one diff — each phase marked unchanged, added, edited or moved, removed phases listed separately, phases the item has already completed flagged, and any clamp of `currentPhase` into the shorter plan shown at the top — and blocks until the user decides. The review can take far longer than the default command timeout, so run `update-plan` **as a background task** and do no other work until it returns; the pending preview dies with the process.
67
+ In a web session this renders the whole change into the preview pane as one diff — each phase marked unchanged, added, edited or moved, removed phases listed separately, phases the item has already completed flagged, and any clamp of `currentPhase` into the shorter plan shown at the top — and blocks until the user decides. The review can take far longer than the default command timeout, so run `update-plan` **as a background task** and do no other work until it returns; the pending preview dies with the process. To revise the change while it is still pending, re-run `update-plan` with the revised payload directly — do not stop the earlier task. The pane swaps to the new diff, and the earlier task exits 0 printing `Superseded by a newer preview — no decision; ignore this result.` without writing anything: ignore it.
68
68
 
69
69
  When it returns:
70
70
 
@@ -46,6 +46,7 @@ assist ask --title 'High-level review config' --body - < <scratch file>
46
46
 
47
47
  - **Approved (exit 0)** — fold every printed inline comment into the answers (a comment on a glob edits or drops it; a comment on the scope switches it), then write.
48
48
  - **Rejected (non-zero exit)** — write nothing. Address the reason and each comment, re-check any changed glob still matches files, revise the scratch file and re-run `assist ask`.
49
+ - **Superseded (exit 0)** — you re-ran `assist ask` while this one was pending, which is how to revise it; do not stop the earlier task first. Ignore this result and wait for the newer one.
49
50
 
50
51
  Outside a web session `assist ask` only prints the markdown and exits 0 without a decision: ask the user in chat instead, and write only once they have answered.
51
52
 
@@ -9,7 +9,7 @@ Run the high-level review (see `docs/high-level-review.md`) for the PR given in
9
9
  assist review --high-level $ARGUMENTS
10
10
  ```
11
11
 
12
- If this is a re-invocation in a session that already ran it, re-run it anyway — never assume the checklist is still open, since the pane may have gone even while a previous task still looks alive. Stop any still-running previous `assist review --high-level` background task first, then launch it afresh.
12
+ If this is a re-invocation in a session that already ran it, re-run it anyway — never assume the checklist is still open, since the pane may have gone even while a previous task still looks alive. Do not stop a still-running previous `assist review --high-level` task: launch it afresh, and the new checklist replaces the old one in place. The earlier task then exits 0 printing `Superseded by a newer preview — no decision; ignore this result.` — ignore it.
13
13
 
14
14
  Run it as a background task. In an assist web session it opens the checklist in the web UI preview pane and returns once the user approves or requests changes; otherwise it prints the checklist and exits straight away. Do not review the PR yourself or post anything to GitHub.
15
15
 
@@ -38,6 +38,7 @@ In an assist web session this renders each message in the preview pane for appro
38
38
  - **Approved (`--body`)** — the last line of stdout is the path to the approved body under `~/.assist/slack/`. That file, not your scratch file, is what gets posted. The line above it names the target channel, and the resolved `thread_ts` when `--thread` was passed.
39
39
  - **Approved (`--parts`)** — only after the last part is approved does the command print anything: a line naming the target, then one `k/N <path>` line per part in thread order under `~/.assist/slack/`, then a line saying how to thread them. Those files, not your scratch files, are what get posted.
40
40
  - **Rejected** — the command exits non-zero with the reason and any inline comments, and names the working file of the message that was rejected (with its position, for a batch). No path is handed back, so nothing from the batch is posted. Address every comment, rewrite that working file in place, and re-run the same command with that working file in place of the scratch file it came from — a batch re-previews from part 1. Do not post, and do not recompose the messages from scratch.
41
+ - **Superseded** — the command was re-run while this preview was pending, which is how to revise a pending preview; never stop the earlier task first. It exits 0 printing `Superseded by a newer preview — no decision; ignore this result.` and posts nothing: ignore it and wait for the newer run.
41
42
 
42
43
  Outside a web session there is no pane: the bodies pass straight through and the working files are written immediately.
43
44