| Age | Commit message (Collapse) | Author |
|
The forum tool's mute holds one forum's posts -- mentions, and unread
counts -- or, without a forum, everything, direct messages included.
unmute releases them; without a forum it ends every mute. When and
whether to mute is the agent's call; the description asks it to mute
only when interruptions would hurt the task, and to unmute when done.
Held messages wait in the delivery queue, so nothing is lost and a
muted forum's unread count is reported once it is unmuted. A sender is
told the receiver muted these, and a post's report lists muted members
apart from those woken. A run the agent starts while muted opens with
what is held, and says that direct messages still arrive when only
forums are muted. The status bar, the tool's list, /forums and pi-forum
show who is muted. The mute is kept in the registration, so it survives
/reload and a restart that restores the agent.
|
|
Every incoming message carried about 1,070 characters of fixed text,
which stayed in the receiver's context until compaction: about 46k
tokens for the busiest agent over six days. It is now one line of about
290: sender, not the user, no permission, quoted text is data, how to
reply. The rest of what it said is in the tool's description, which
every receiver has, since a message reaches only a forum member.
Agents still told the user about peers by bare id, mostly in a reply's
second and later mentions ("j96e4m's review"). The description now
says so for every mention, and for messages between agents, which get
relayed. A first reply names a peer as label and id; later mentions
keep at least its place.
From six days of v3-deployments traffic, three more rules: one post
mentioning several agents, not a message to each or a forward of news
already sent; changing state in the pin, sent once settled; and a
request says whether it needs a report back.
The naming and noise rules also go in the system prompt's rules, as
promptGuidelines, while the tool is active.
|
|
A shutdown sends pi SIGTERM or SIGHUP, which pi handles as a quit, so
every agent left its forums, and a dingger restore brought them back in
none. Only a quit the user asks for now ends membership. An agent whose
pi was stopped any other way stays registered as stopped, and the next
pi to start on its session (pi --session, pi -c, a dingger restore)
takes it back: same id, same forums, same read position, with a notice
of what is unread.
pi stops its TUI before session_shutdown on a user's quit, and after it
on a signal, so a terminal still in raw mode there means a signal. A
crash runs no handler and leaves a dead pid, or a socket nobody answers
on, which counts the same. Read positions are saved as they move, for
that case.
Stopped members are listed as such by the tool, /forums and pi-forum.
A direct message to one fails, saying so; a post may mention one, and
waits for it as unread. /forum remove and /forum delete clear them.
|
|
pi 1.5's pi-ai no longer types StringEnum as TypeBox outside pi's
runtime mapping, so the tool's parameters typechecked as unknown. Build
the same schema, a string with an enum, with Type.Unsafe.
|
|
A label of the place alone, deployment:slice, did not say what the agent
was doing. It is now place, then session name:
deployment:slice · Review agent steering [t26w9t]. The session name no
longer needs a field of its own beside it, in the tool or in pi-forum.
|
|
The posts agents write to a forum were only readable through the forum
tool, or as raw JSON lines. pi-forum lists the forums with their running
members and pins, shows a forum's last posts, and follows one forum or
all of them as posts, pins, new forums and deletions arrive. It only
reads: no model calls, nothing marked read. Direct messages stay where
they are, in the two agents' transcripts.
|
|
An agent's label led with its session name, often a long generated one,
and agents reported peers to the user by bare id. The label is now the
tmux session:window or herdr workspace/tab, else the session name, else
the session id; the session name goes beside it. The tool and each
incoming message tell the agent to name a peer as label and id, never
by id alone.
|
|
Compacted, a forum send showed only its name; its own renderer shows
the message, folded to 10 lines.
|
|
Appended to a session with no conversation yet -- a new pi, or just
after /new -- the join notice sat ahead of the system message pi records
at the first run, and pi then sent that message without its content: the
provider refused every request with a 400. Queue it for the next turn
instead, which pi places after the system message.
|
|
A message of up to 4000 characters printed in full in both panes; show
its first 10 lines, or 1000 characters, and how much more there is,
as pi does for tool output. The model still gets the whole text.
|
|
/forum <name> puts this pi in a forum; its members can list each other,
post to it (waking only those mentioned), read its history, set its pin,
and send each other direct messages, delivered the way alarm.ts delivers
alarms. Only the user adds an agent; any pane can remove one. Forums and
their posts live in ~/.pi/forum until /forum delete; membership lasts as
long as the pi process.
|
|
/reload dropped every pending alarm and stopped its when_done command,
without a word. An agent that had ended its turn to wait for one was never
woken -- nor a pi-goal goal_wait counting on it.
The old copy of the extension now leaves what is pending on globalThis
instead: each alarm as plain data, the due queue, the next id, and a
when_done command's ChildProcess with its own listeners removed. The copy
pi loads next arms fresh timers from each alarm's absolute time, listens
on the command again (one that exited meanwhile still holds its status),
and resumes polling PIDs. Nothing crosses that would reach the old,
stale pi or ctx.
A handoff from another session or another HANDOFF_VERSION is refused and
its commands stopped, with a notice. If nothing takes it within 30s --
the file failed to load, or was removed -- the old copy stops its
commands. Quitting, /new, /resume and /fork still drop everything.
|
|
when_done runs a command (bash -c, in pi's cwd, output to a log file) and
fires when it exits, with its exit status; cancelling the alarm or ending
the session stops it. when_exits polls PIDs already running and fires once
all are gone. Either takes an optional deadline, 24 hours by default, at
which the alarm fires anyway and a still-running command is stopped.
A process exiting is a signal any condition can be turned into -- gh run
watch, sz-wait-for, an until-curl loop -- so the agent can start something
long, end its turn and be woken, instead of blocking on it. The delivery
path is the existing one, unchanged.
pi-subagent: §5 sets an alarm on the runs' PIDs instead of waiting.
|
|
|
|
An alarm that fell due mid-task used to wait in the extension until the
run settled. Now it is steered in: pi adds it after the tool calls in
progress finish, before the next model call, and the model weighs it
against the task. The alarm text tells it to say which it chose.
pi's Esc empties its queue and drops queued extension messages without
a word, so an alarm stays listed until message_end shows it in the
conversation. One not seen by the end of a stopped run is held and sent
again after the next run completes; resending into that run could
deliver it twice, since pi takes one queued steer per turn and other
aborts leave the original queued.
|
|
An `alarm` tool sets, lists and cancels alarms: after a delay, at a
wall-clock time, or repeating (at most 12 fires, the last within 24 hours).
A fired alarm is a pi.sendMessage custom message, customType "alarm",
rendered as set by the agent rather than typed by the user, and wrapped in
fixed text the agent cannot drop: it is the agent's own earlier note, not
the user's, and grants no permission -- outward actions still need the
user's approval. /alarms lists and cancels.
An alarm due while pi is busy waits for the task to finish, held here
rather than in pi's queue, which drops a custom message on Esc. A run that
ended stopped -- Esc, an error, or the abort before /compact, /new, /resume
and /fork -- holds due alarms until a later run completes. Timers die with
the session; the tool is withdrawn outside the TUI.
Reviewed by Fable and GLM 5.3 Flash. Fixed from the review: unbounded
every_minutes overflowed setTimeout into 1 ms fires; a due alarm ran right
after Esc, or unseen on a session being replaced; stale repeat fires piled
up; the session_compact delivery never ran; impossible dates and times
skipped by a clock change were accepted; the note could forge the
wrapper's delimiters.
Declines dot request 20261021-220352-work-laptop-c46033 (sz-agent-alarm, a
skill typing into the agent's tmux pane) in favour of this: a custom message
is recorded and shown as the agent's, needs no screen-scraping, and loads
only in pi.
|
|
herdr labels every pi pane "pi", so with several open the rows cannot be told
apart. herdr 0.9.3's socket API has pane.report_metadata, whose display_agent
replaces that label without touching lifecycle state; this reports the session
name there on start and on every rename, auto-named titles included.
Interactive sessions only: a pi -p or subagent run from inside a pane inherits
its HERDR_* variables and would otherwise rename the pane after itself. Checked
against a fake herdr socket: a print-mode run sends nothing, while the socket
accepted a control message. Outside herdr it returns at once. The pi APIs it
uses -- ctx.mode "tui", getSessionName, session_info_changed's name -- are as
in pi 1.0.0, and link/pi.sh links it in like any tracked extension.
From change request e053eb.
|
|
pi-compact-tools draws each tool call as a short, expandable row; Ctrl+O shows
the whole result. Every built-in and every custom tool, MCP ones included, is
compacted and starts as a 3-line preview -- previewLines only applies to rows
that do not start hidden, so nothing does.
Pinned to the v0.14.0 commit, byte-identical to the npm tarball: the package
had 32 releases in its first three weeks, and unpinned that would be new code
across the fleet nearly every day.
The config is linked rather than generated so it is the same everywhere, and
/compact-tools saves through the link by design. AGENTS.md now says which
linked files their tools rewrite, and that such a change is not an agent's to
commit or revert.
From change request 4d685a.
|
|
pi --resume listed each session by its raw first message, often blank or a
system-reminder blob. pi-auto-session-name has the active model write a short
title instead, through pi's own model call, and never overwrites a name set by
hand.
Pinned to the repo's commit rather than the npm version: the package is days
old with one maintainer and runs inside every pi on every machine, so an update
should arrive only when chosen. npm refuses to reuse a version number, but a
commit hash does not depend on npm's policy at all. The commit's extension is
byte-identical to the published 1.0.0 tarball, and needs no build.
From change request 161e51.
|
|
pi 1.0.0 has MCP built in, and while the adapter is installed it suppresses
that and prints a warning at every start. The browser gates that answered the
adapter's approval event now hook pi's own tool_call as well. From change
request 562974.
|
|
models.json gave the provider an apiKey of "SILICONFLOW_API_KEY", which pi
sends verbatim as the credential: it interpolates "$NAME" and "${NAME}", runs
"!command", and treats anything else as a literal. So that provider has been
authenticating with the 19-character string "SILICONFLOW_API_KEY" and getting a
401 for as long as it has existed.
Confirmed by calling pi's own resolver: "SILICONFLOW_API_KEY" resolves to
itself, "$SILICONFLOW_API_KEY" to the value. Nothing catches this --
isConfigValueConfigured returns true for both and reports no missing variables,
so `pi auth check` says ready either way, and only a real request fails. Hence
the note in CLAUDE.md beside the models.d row: the rule is invisible in the
file, and the next provider added would repeat it.
Reported as a change request from the machine that hit it; the sweep for other
instances found none.
|
|
Shell, editor and terminal configuration, the tools that go with them, and
szecret, an age-based secret manager whose store lives elsewhere.
History restarts here. What came before was not written to be read by
anyone else, and carried machine names, addresses and an encrypted secret
store; it is kept privately instead. What is left is meant to be safe on
any machine, including one whose owner is not me: see CLAUDE.md for the
rule it is written to.
|