pi-reply-thread
Index the replies one prompt produces in a Pi or Gentle Shell session: ordered and unique IDs, what triggered each reply, and the replies still waiting on you.
Package details
Install pi-reply-thread from npm and Pi will load the resources declared by the package manifest.
$ pi install npm:pi-reply-thread- Package
pi-reply-thread- Version
0.4.0- Published
- Nov 21, 2026
- Downloads
- 755/mo · 210/wk
- Author
- daniel2010001
- License
- MIT
- Types
- extension
- Size
- 184.5 KB
- Dependencies
- 0 dependencies · 2 peers
Pi manifest JSON
{
"extensions": [
"./extensions/reply-thread.ts"
]
}Security note
Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.
README
pi-reply-thread
Keep track of the replies one prompt produces in a Pi or Gentle Shell session.
An agent often answers a prompt more than once: it replies, a background job or a subagent finishes,
it replies again, another job finishes, a third reply arrives. By the third reply, the question the
first one asked you has scrolled away. pi-reply-thread groups every reply under the prompt that
started it, says what triggered each one, and gathers the questions still waiting on you in one
place, where you answer them by pasting a quote.
╭─ Replies ──────────────────────────────────────── 3 prompts · 6 replies ─╮
│ ▌P12 look for something like this 12:04 │
│ ›├ P12.R1 a1b2c3d4 prompt ⚠ I found two options. Which one… │
│ ├ P12.R2 e5f6a7b8 job: tests │
│ └ P12.R3 c9d0e1f2 worker: docs │
│ ▌P11 clean up the old branches 11:40 │
│ └ P11.R1 77aa01bc prompt ✓ │
╰─ ↑↓ move · enter open · esc close ───────────────────────────────────────╯
- No extra model call. Everything is computed from the session branch; only the optional triage (
/replies:triage, ortin Pending) calls your session model, after you confirm it. - Nothing enters the model context.
- Works after
/resumeand on any branch, because the index is rebuilt from the branch every time.
Which questions count as asks? See How asks are found: when a reply has a
## Needs your decision section, only that section counts by default.
Install
pi install npm:pi-reply-thread
# or from GitHub
pi install git:github.com/daniel2010001/pi-reply-thread
Or try it for one session from a clone:
pi -e ./extensions/reply-thread.ts
gsh -- -e ./extensions/reply-thread.ts # Gentle Shell
Update from an older minor version
While the package is below 1.0, pi update stays within the installed minor version: Pi records
the package as, say, ^0.2.0, and that range never reaches 0.3.0. Move to the latest release once with npm,
in Pi's package directory; your settings do not change:
cd ~/.pi/agent/npm && npm install pi-reply-thread@latest
cd ~/.gentle-shell/agent/npm && npm install pi-reply-thread@latest # Gentle Shell
If you set PI_CODING_AGENT_DIR, use its npm directory instead. Then /reload, or start a new
session. Check the version with npm ls pi-reply-thread in the same directory.
Use
| Command | What it does |
|---|---|
/replies or Alt+R |
Opens the overlay on Pending while any ask is open, else on Replies (the index of the current branch, newest prompt first). Tab cycles Pending → Replies → Answered. |
/replies pending |
Opens the Pending tab, even when nothing waits. |
/replies:triage or /replies triage |
Asks your session model which open asks a later prompt already answered or another ask repeats, after a confirm; t in Pending does the same. See Triage. |
/replies P12.R1 |
Opens one reply in full by its ordered ID (case-insensitive). |
/replies a1b2c3d4 |
Opens one reply in full by its entry ID. |
/replies P12.R1.Q2 or /replies a1b2c3d4.2 |
Opens the reply that asks that question. |
In the index, ↑/↓ move, Enter opens a reply, Esc closes. In the reply viewer, ↑/↓
scroll, PgUp/PgDn or Space page, Home/End jump, and Esc or q goes back. A reply
opened by ID closes on Esc. In any tab, ? shows a card with every key; ? or Esc hides it.
Its last line names the ask mode in use (Asks: decision section only or Asks: every question).
Outside the interactive TUI (print or RPC mode), /replies and Alt+R send the index or the reply as plain
text (the index marks a reply ⚠ while it has an open ask and ✓ once all its asks are closed), and /replies pending sends the open asks, one per line (P12.R1.Q1 a1b2c3d4.1 Which one do you prefer?),
or Nothing waits on you.
Reply IDs
Every reply has two IDs:
- Ordered:
P<prompt>.R<reply>, for exampleP12.R2is the second reply to the twelfth prompt on the branch. - Unique: the 8-character Pi session entry ID of the reply, for example
e5f6a7b8.
Triggers
Each reply shows what arrived since the previous one:
| Label | Meaning |
|---|---|
prompt |
Your prompt. |
job: <label> |
A background job finished (bash_background). |
monitor: <label> |
A monitor job reported or timed out. |
worker: <label> |
A subagent finished. |
session: <id> |
A message from another session. |
follow-up |
Nothing new arrived; the agent kept going. |
Gentle Agents wakes the session with a system-generated user message after a job or subagent ends. That message is not counted as a prompt, so those replies stay under the prompt that started them.
How asks are found
An ask is a line of a reply that waits on you. Which lines count depends on one thing: does the
reply have a decision section? That is a heading with a decision marker, such as
## Needs your decision, with at least one ask under it (up to the next heading).
| The reply | Default (section) |
With --reply-thread-asks all |
|---|---|---|
| has a decision section | Only that section: each top-level list item, even without ?, and each other line in it that ends with ?. Questions elsewhere in the reply are not tracked. |
Every question in the reply, plus the section's top-level items. |
| has no decision section | Every line that ends with ? or holds a decision marker. |
The same. |
For example, this reply:
Tests are green. Should I also bump the version?
## Needs your decision
1. Merge `feat/x` into main?
2. Keep the old name
- with a squash
- By default it has 2 asks, numbered like the items:
Q1Mergefeat/xinto main?,Q2Keep the old name. The nestedwith a squashis part of item 2, not an ask. - With
allit has 3: the first line,Tests are green. Should I also bump the version?, becomesQ1, and the items becomeQ2andQ3.
Why doesn't a question in the middle of a reply show up?
Because that reply has a decision section, and by default only the decision section counts: it is
where the agent says what it needs from you, and it keeps Q1, Q2… equal to the item numbers.
The reply viewer says when this happens, under the asks: 1 more question outside the decision section is not tracked (--reply-thread-asks all tracks them).
To track every question, start the session with the flag:
pi --reply-thread-asks all
gsh -- --reply-thread-asks all # Gentle Shell
The values are section (the default) and all; any other value works as section and shows a
warning when the session starts.
Detection details
- Questions: a line that ends with
?(for exampleWhich one do you prefer?or¿Cuál preferís?). - Decision markers:
needs your decision,decision needed,waiting on you,waiting for you, and the Spanishnecesito que decidas,necesito tu OK,necesito tu decisión,necesito tu confirmación. A line with a marker is an ask; a marker inside double quotes ("…",“…”,«…») is only being mentioned and does not count. - Items: a top-level list item (bullet or numbered, indented at most 3 spaces) in a section headed
by a marker is an ask even without
?. A nested item (indented 4 or more spaces, or under another item) is an ask only when it ends with?, and never in the default mode when the reply has a decision section. - Headings: a heading that ends in
?(## Why not a model?) titles a section and does not count. A marker heading counts only while its section has no ask of its own, so a decision section yields its asks and not its title. - Code blocks, inline code, blockquotes and table rows are ignored.
Detection is deterministic: it can miss an ask phrased without a question mark outside a decision section, and it can flag a rhetorical question.
In the index, a reply shows ⚠ and its first ask while any of its asks is still open, and ✓ once
all of them are answered or dismissed. The reply viewer lists the open asks under ⚠ Waits on you
above the text, and the closed ones under ✓ Answered, each with the prompt that answered it
(→ P13) or dismissed.
Recommended agent instruction
Asks are easiest to catch when the agent gathers them in one place. Add this to your AGENTS.md
(~/.pi/agent/AGENTS.md for Pi, ~/.gentle-shell/agent/AGENTS.md for Gentle Shell). The package
never adds it to the prompt by itself. Every item of the final section is an ask, and its ? ends
the item, so any context goes before the question.
## Questions for the user
When a reply needs anything from the user (a decision, a confirmation, an output, an action), end it
with a `## Needs your decision` section: a numbered list, one item per ask. Each item is one
question that ends with `?`: put any context before the question, never after it. One decision
per item: split "Do we do A and B?" into two items. Never leave an ask in the middle of the reply
or phrased without `?` ("Let me know when it is done" becomes "Can you tell me when it is done?").
Before writing the section, review the asks of your earlier replies in this conversation: drop the
ones the user already answered, even without quoting them, and repeat a still-open one word for
word instead of rewording it. Leave the section out when nothing is needed. Choices with fixed
options still go through `ask_user_question` when it is available.
Pending asks
Every ask gets two IDs, like a reply:
- Ordered:
P<prompt>.R<reply>.Q<n>, for exampleP12.R1.Q2is the second ask ofP12.R1. - Unique:
<reply entry ID>.<n>, for examplea1b2c3d4.2.
The Pending tab lists the asks still open, grouped under their prompt, newest prompt first. Asks that look alike show as one row, on the newest of them (see Repeated asks):
╭─ Pending ────────────────────────────────────────────────────────── 3 open · 0 linked ─╮
│ ▌P2 look for something like this 12:01 │
│ ›○ P2.R1.Q1 I found two options. Which one do you prefer? │
│ ○ P2.R2.Q1 Should I delete the three old branches? ≈ 1 similar │
│ ▌P1 clean up the old branches 11:47 │
│ ○ P1.R1.Q2 Needs your decision: push to main. │
╰─ enter answer · y yes · f format · t triage · ? help · esc close ──────────────────────╯
| Key | What it does |
|---|---|
↑/↓, PgUp/PgDn |
Move. |
Space |
Marks or unmarks an ask (●; an unmarked ask shows ○, or ✎ when your draft already answers it). |
Enter |
Answers the marked asks, or the selected one: closes the overlay and pastes a > P2.R1.Q1: <ask> quote per ask into the editor, with room for your answer (see below). Asks marked ✎ are not pasted again; when all of them are, it closes without pasting. |
y |
The same, with Yes. as the answer. |
f |
Switches the answer format between R: lines and same line; the ? card shows the current one. |
x |
Dismisses the marked asks, or the selected one. |
o |
Opens the reply that asks it; Esc comes back. |
→ / ← |
Expands a row with ≈ N similar to show its similar asks under it / collapses it again. |
l / u |
Links the marked asks (2 or more) as one chain, or the selected row and its similar asks to the oldest of them / unlinks the chain. |
t |
Closes the overlay and runs the triage (see Triage); Pending reopens with its proposals. |
a / n |
Accepts / rejects the row's ✦ proposal (see Loose answers and Triage). On a row with ≈ N similar, the first a opens the group and the second closes the whole group with that proposal. |
Backspace (⌫) |
Undoes the last x, l, u, a or n (see Undo). |
Tab |
Goes to the next tab: Pending → Replies → Answered → Pending. |
? |
Shows a card with every key of each tab; ? or Esc hides it. |
Esc |
Closes. |
The hint line names only enter, y, f, ? and esc; the ? card lists the rest.
The pasted text ends where you type, with no trailing newline. In the R: lines format (the default)
each quote gets an R: line under it and the asks are apart by an empty line:
> P2.R1.Q1: I found two options. Which one do you prefer?
R:
> P1.R1.Q1: There are three old branches. Should I delete them?
R: Yes.
In the same line format the answer follows the quote after → , one ask per line:
> P2.R1.Q1: I found two options. Which one do you prefer? →
> P1.R1.Q1: There are three old branches. Should I delete them? → Yes.
The format is stored as a reply-thread.format custom entry on the branch; the latest one wins.
Draft and place
Each time the overlay opens it reads what you have typed in the editor and not sent yet. An open ask
that this draft would close if you sent it (its quote, or its ordered or unique ID) shows ✎ instead
of ○, also on a group row whose hidden similar ask is in the draft; the title adds · N in draft.
Enter and y skip those asks, so nothing is pasted twice. The draft closes nothing: sending the
message closes them as always, except a quote whose answer you left empty (see below).
The overlay also reopens where you left it: each tab selects the same ask (or reply) again, or the row that took its place once that ask closed. The opening tab is chosen as before. The place lives in memory only and is forgotten when the session starts or switches and when the extension reloads.
An ask closes only explicitly:
- Answered: a later prompt of yours quotes it or cites its ordered or unique ID, which is what the
pasted quote does, with your answer filled in. A pasted quote whose answer is still empty (
R:with nothing after it, or nothing after the→) does not close the ask. Gentle Agents wake messages do not count. - Dismissed with
x.
Loose N: answers (no model)
When you answer the previous reply's decision section by number instead of
quoting it, each N: line becomes a ✦ proposal on item N of that section, with no model call:
## Needs your decision ← the reply right before your prompt
1. Should I start with T14?
2. Do we publish now?
1: yes ← your prompt
2. not yet
│ ›○ P1.R1.Q1 Should I start with T14? │
│ ✦ answered in P2: "yes" │
│ ○ P1.R1.Q2 Do we publish now? │
│ ✦ answered in P2: "not yet" │
- A line counts when it is
N: text,N. textorN) text; N is the position of the item among the section's top-level items, the same number the ask'sQ#shows when the section is all items. - Only the reply right before the prompt counts, only when it has a decision section, and only in
sectionmode (the default). A line in a>quote or anR:line is not read; N past the last item, or an ask already closed (also by a quote or ID in that same prompt), gives nothing. - Nothing closes by itself:
aaccepts it (the ask closes as answered by that prompt, with the text afterN:),nrejects it so it does not come back,Backspaceundoes both, as with the triage proposals. A triage proposal for the same ask and prompt shows instead of it. - A line like
1: about part 1 of the plangives a wrong proposal too;ndrops it.
Undo
A dismiss, link or unlink you did by mistake is one key away. Backspace (⌫), in the Pending and
Answered tabs, undoes the last action written since the overlay opened: a dismiss is reopened, a link
unlinked, an unlink linked again, and r (see Answered asks) dismissed again. Press
it again to undo the action before that, newest first. One key is one step: x on several marked
asks, l on a group and l on marked asks each undo as a whole. f is not an action and is not
undone; with nothing left to undo, Backspace does nothing.
Undo never deletes: it writes the opposite reply-thread.ask entry, so the branch keeps both. The
steps last while the overlay is open; a new overlay starts with none, and r reopens an ask closed
earlier. (Ctrl+Z would be the usual key, but Pi uses it to suspend the app on Linux.)
A quote line, > <ID>: <text>, closes the ask whose text it carries: the open ask with the same text
(compared as for repeated asks, case and punctuation aside), the one the ID names
when it has that text, else the newest one before your prompt. So a quote still closes the right ask
when its ID has changed since you copied it, for example after a reply was renumbered by its decision
section. In the same line format the text ends at the → before your answer. A quote with nothing
after the colon, or with a text no ask has, closes the ask its ID names; an ID outside a quote does
too.
A quote closes its ask only when you answered it. If the R: line right under the quote has nothing
after R:, or (in the same line format) nothing follows the →, the quote closes nothing, neither
by its text nor by the ID on it: send several pasted asks, fill in only some, and only those close.
A quote with no R: line and no → still closes its ask (its answer is the next plain line, or
your prompt's first line), and an ID you mention outside a quote still closes that ask. In your
unsent draft a quote counts even with its answer empty, so a fresh paste is marked ✎ and is not
pasted twice (see Draft and place).
Repeated asks
Asks often come back in a later reply. Two open asks look alike when they have the same text after
lowercasing and dropping inline code and punctuation, or 60% of their words longer than 3 letters in
common. Asks that look alike, directly or through another one, form a group: the Pending tab shows
it as one row, on its newest ask, with ≈ N similar for the N older ones, and counts it once in the
title. A linked chain joins a group by the text of its newest ask.
│ ›○ P4.R1.Q1 Should I delete the old branches? ≈ 2 similar │
→ expands the row: its similar asks show under it, newest first, as dimmed ≈ rows that you answer,
mark (●) and dismiss like any ask. ← collapses it again.
│ ○ P4.R1.Q1 Should I delete the old branches? ≈ 2 similar │
│ › ≈ P2.R1.Q1 Should I delete the three old branches? │
│ ≈ P1.R1.Q1 There are three old branches. Should I delete them? │
A group row answers only its newest ask. A group is a display fold, never a link: it only tells you the asks look alike, and closing an ask stays explicit. So answering or dismissing the row closes its newest ask, and the next newest takes the row. To close the whole group at once, use one of these ways:
l, then answer: presslon the row (or one of its expanded asks) to link the group: every other ask continues the oldest one and the row becomes a chain, which closes as a whole.→, then answer each: expand the row and answer or dismiss its asks one by one.atwice on a✦proposal: after a triage, the firstaon the row expands the group and the second closes all of it with the proposed answer.
The ? card says the same under the group keys. To link asks that do not look alike, mark 2 or more
with Space and press l: each one continues the next older one, and the marks clear.
Linked asks form a chain, shown once on its newest ask with ↺ <older IDs>; answering or dismissing
any of them closes the whole chain. u unlinks the newest ask from the chain.
Looks answered: ✓?
An open ask that looks like an older ask you already answered or dismissed shows ✓? like <ID>, dimmed, naming the newest such closed ask. A group row shows it when
any of its asks, hidden ones too, looks answered; an expanded ask shows its own. It comes after ↺
and ≈ N similar, joined by ·, and stays whole while the ask text is cut:
│ ›○ P4.R1.Q1 Should I delete the old branches? ≈ 1 similar · ✓? like P2.R1.Q1 │
It uses a looser test than repeats: the asks share at least 40% of their words (longer than 3 letters), where a group needs 60%. An agent that asks again after you answered usually rewords more, and a wrong hint costs little because it never folds or closes anything.
It is only a hint: nothing closes by itself. Answer the ask again, or press x to dismiss it.
When more than 10 prompts have open asks, the older ones fold into an Older (N) row; Enter
expands it.
Dismiss, reopen and link are stored as reply-thread.ask custom entries on the session branch (outside the
model context), so they follow /resume and branches like everything else.
Triage (optional, uses your session model)
Everything above works without a model. When the open asks pile up, /replies:triage (or
/replies triage, or t in the Pending tab) asks the model selected in your session to point out
two things: an open ask a later prompt already answered without quoting it, and two open asks that
ask the same thing in other words.
- What is sent: one message with the triage instructions, every open ask (ordered ID and text)
and every prompt of yours after the oldest open ask (
P#and text, each cut at 2000 characters), under your session's system prompt, unchanged. No other message of the session goes. - Why the system prompt goes too: some providers accept only the session's own system prompt.
pi-claude-bridge, for one, rejects any other (prompt-capture: no capture for this … system prompt), so the instructions travel in the message instead. The system prompt sent is the one of your latest turn, the one the bridge recorded; right after/reloadno turn has run yet, so send any prompt first (the error says so). - Cost: it is one model call on your account, and the session's system prompt (often thousands of tokens with your context files and skills) is most of it. A confirm names the model, how many asks and prompts it sends and their rough size in tokens, system prompt included; declining sends nothing.
- Esc while it waits cancels the call; nothing is written.
- Only the TUI runs it. Without open asks or without a selected model it says so and calls nothing.
tin Pending closes the overlay first. When the triage stores proposals, Pending opens again with them; when you decline, cancel, it fails or finds nothing, you only get its notice.
The model only proposes. Each proposal it gives that holds up (known IDs, the quote really in that
prompt, the prompt after the ask) is stored in a reply-thread.triage entry, and Pending opens with a
✦ line under the row it is for:
│ ›○ P1.R1.Q1 Should I start with T14? │
│ ✦ answered in P2: "let's go with T14" │
│ ○ P3.R1.Q1 Do we use Piper for the voice? │
│ ✦ same as P1.R1.Q2 Should the reader use Piper? +1 more │
Nothing closes or links until you press a key on the row:
aaccepts the first proposal shown.answeredcloses the ask as answered by that prompt, with the quote as its answer (the Answered tab shows↳ P2 let's go with T14);samelinks the two rows, asldoes.- On a group row (
≈ N similar),aasks first: it opens the group, as→does, and the hints becomea close all N with this answer · esc cancel, N counting every ask of the group, chain members too. A secondalinks the group asldoes and accepts the proposal for all of it:answeredcloses every ask of the group with the quote,samemakes the group and the other row one chain.Esccancels and leaves the overlay open; any other key cancels and does what it usually does. On an ask of an opened group, or a row without similar asks,aacts at once on that ask only. nrejects it: it hides, and a new triage does not show it again. The next one, if any, shows.Backspaceundoes either: an accepted answer is reopened, a link unlinked, a rejection restored. A whole group accepted withatwice comes back in one step.
A new triage replaces the proposals of the previous one; a proposal that no longer applies (its ask closed, or the other ask closed or linked) does not show.
Answered asks
The Answered tab lists the closed asks, grouped under the prompt of their reply, newest prompt
first. Under each ask, ↳ names the prompt that answered it and the answer it gave, or ✕ dismissed
says you dismissed it. A closed chain shows once, on its newest ask, with ↺ <older IDs>. ↑/↓
move and Enter or o opens the reply (on a dialog's ask, its card: see
Dialogs (pauses)).
r reopens the selected ask, answered or dismissed, and every ask of a closed chain: it writes a
reopen entry for each, and the ask goes back to Pending, with ⚠ on its reply again. Backspace
undoes r by dismissing the asks it reopened, so an ask first closed by an answer shows as dismissed
then; either way it is closed again.
╭─ Answered ──────────────────────────────────────────────────── 1 answered · 1 dismissed ─╮
│ ▌P1 clean up the old branches 12:00 │
│ ›✓ P1.R1.Q1 There are three old branches. Should I delete them? │
│ ↳ P3 Yes, all three. │
│ ✓ P1.R1.Q2 Needs your decision: push to main. │
│ ✕ dismissed │
╰─ ↑↓ move · enter open · esc close ───────────────────────────────────────────────────────╯
The answer is read from the quote that closed the ask: the R: line under it, the text after → on
the quote line, or the first line after it that is not a quote. A prompt that cites the ID without a
quote, or has nothing after the quote, answers with its first line.
Dialogs (pauses)
When the agent stops a turn to ask you in a dialog (ask_user_question, ask_user_choice), the
session keeps the questions and what you chose. Each question becomes an ask of the reply that ends
that turn, numbered after the reply's own asks (a reply with two asks in its text and a dialog of one
question has Q1, Q2 and the dialog's Q3), so no reply or earlier question changes its ID. These
asks are closed from the start: they never show in Pending, the Answered tab shows them with
↳ chose: <your answer> (the option, the selected options joined with , , or the text you typed),
the viewer lists them under ✓ Answered with → chose: <your answer>, and r does not reopen them.
A dialog whose turn ended without a reply (you interrupted it) is not shown, nor a call that failed
validation.
Other dialogs count too: a confirm or select shown while a tool runs (a command guard's
confirmation, a host-resolved review consent) is recorded as a reply-thread.pause entry with only
its title (the ask shows its first line), the tool and, for bash, the program name (the command's first word after any
NAME=value assignments and a sudo or env without options, without its folder; never its
arguments), for example Allow this command? [bash: git]; a dialog without a title shows as
confirm dialog [<tool>]. Pi does not tell extensions which button was pressed, so the ask closes
with the tool's outcome instead: ran when the tool finished without an error, else
stopped: <first line of the tool's result>. It joins the same reply as the other dialogs, in the
order they happened. A dialog shown outside any tool (this package's own triage confirm) is not
recorded.
In the Answered tab, Enter or o on a dialog's ask opens its card instead of the reply: the
question, the options the dialog offered with the ones you chose marked ✓ (none for a typed
answer; no Options block for a dialog without options), Chose: <your answer>, the tool
(Tool: bash · rm for a command guard), and the reply that ended the turn. On a short screen the
options are cut to … N more first, then the question down to two lines. When the agent wrote some
text in the same message as the ask_user_question or ask_user_choice call, the card shows that
text first, rendered as Markdown like the reply viewer (tables, code, emphasis), above the question (cut before anything else on a short screen,
down to … context above the question cut to fit); other dialogs have none. In the card, o opens
that reply (Esc there comes back to the card) and Esc goes back to Answered on the same row.
╭─ P4.R1.Q1 · pause ────────────────────────────────────╮
│ Delete the old branch? │
│ │
│ Options │
│ ✓ Yes, go ahead │
│ • No │
│ Chose: Yes, go ahead │
│ Tool: ask_user_question │
│ In P4.R1, the reply that ended the turn. │
╰─ o open reply · esc back ─────────────────────────────╯
Widget
A widget above the editor summarizes the latest prompt while it has two or more replies, with ⚠
on each reply that still has an open ask, and counts the open asks like the Pending title (a chain or a group of repeats counts once) whenever
there are any:
P12 · 3 replies: R1 prompt ⚠ · R2 job: tests · R3 worker: docs · alt+r
⚠ 4 pending · newest: P12.R1.Q1 I found two options. Which one do you prefer? · alt+r
When open rows have a ✦ proposal (a loose N: answer or a triage
one), the pending line counts them: ⚠ 4 pending · ✦ 2 look answered · newest: … · alt+r.
The summary clears when the next prompt starts; the pending line stays until every ask is answered
or dismissed. Alt+R opens the overlay.
Read aloud (with pi-reply-reader)
When pi-reply-reader is loaded too
(pi install npm:pi-reply-reader), s reads aloud
from the overlay, the same way /read does: in Replies and the reply viewer it reads the whole
reply; in Pending and Answered it reads only the selected ask. The overlay stays open. The
hint s read and the ? lines show only while the reader answers; without it, s does nothing.
While a reading plays, the first Esc stops it (Pi hands keys to the reader before the overlay)
and the next one closes the overlay as usual.
The two packages do not depend on each other. On each open the overlay emits reply-reader:ping
({ v: 1 }) on Pi's shared event bus and shows s only if reply-reader:ready ({ v: 1 }) comes
back; s then emits reply-reader:read with { v: 1, id, text }, where id is the ordinal shown
(P12.R1 or P12.R1.Q1) and text the Markdown to read.
Themes
Every colour comes from the active Pi theme (frame borderAccent, prompts userMessageBg, selection
selectedBg, jobs and closed asks success, workers customMessageLabel, asks warning, marks accent, chains
muted, similar asks and ✓? muted, scrollbar scrollbarThumb/scrollbarTrack), so the overlay
follows your theme, including Gentle Shell's.
When is it a bug?
These are failures. If you see one, please open an issue with your Pi version and the smallest reply and prompt that show it (remove anything private from them first):
- A cited ask stays open. You sent a prompt quoting the ask (
> P12.R1.Q2: …, with its ordered ID, its entry ID or its text), and the ask is still in Pending. - An ask appears that is not one. A line from a code block, inline code, a blockquote or a table is listed, or a line that is not in the reply at all.
- A decision-section item is missing or misnumbered. In the default mode, an item of the
## Needs your decisionlist is not listed, or itsQ#differs from its item number. - A key changes the wrong ask.
x,l,u,r,a,norBackspacechanges an ask other than the one you acted on, or Enter/ypastes another ask. - The overlay or the widget does not fit. A line runs past the screen width, the card is taller than the screen, or the bottom border with the keys is cut off.
- Something reaches the model. The package never adds messages to the model's context; only the
prompt you send (a pasted quote, for example) does.
/replies triagemakes its own call only after you confirm it. - A triage proposal acts by itself. An ask closes or links after
/replies triagewithout you pressinga. - The state changes on its own. After
/resume, a restart or switching branches, an ask closes or reopens without anything new on that branch. - Pi shows an error from the extension or crashes.
These work as designed and are not bugs:
- In the default mode, a question outside the decision section is not tracked; the reply viewer says
so. Use
--reply-thread-asks allto track every question. - An answer that does not quote the ask (by ID or text) does not close it. Close it with
x. - A pasted quote sent with its answer empty (
R:or→with nothing after) does not close its ask. - A group row answers only its newest ask; press
lfirst to close the group together. - A reworded repeat that shares few words is neither grouped nor marked
✓?. /repliesonly runs with an empty editor, so while the agent works useAlt+R.
Develop
pnpm install
pnpm test
pnpm typecheck
To try the central without a real session, write a demo session with repeated asks and open it:
pnpm demo # prints the file it wrote and the command to open it
pi --session <file> -e ./extensions/reply-thread.ts
The session is in English: three prompts, a reply woken by a background job notice, and a
## Why did it take so long? section title that is not an ask. Its Pending tab has two rows with
≈ 1 similar to expand with → and link with l. Pi appends to the file when you use it, so write a new one for a fresh start.
License
MIT