Skip to content

feat(agents2): say the agents this copy runs are online - #862

Draft
baxen wants to merge 28 commits into
mainfrom
baxen/agent-presence
Draft

feat(agents2): say the agents this copy runs are online#862
baxen wants to merge 28 commits into
mainfrom
baxen/agent-presence

Conversation

@baxen

@baxen baxen commented Oct 11, 2026

Copy link
Copy Markdown
Collaborator

Summary

Stacked on #860. Needs block/buzz#8261 (kind 20003) on the relay; until that deploys, relays ignore these events and nothing changes.

App-hosted agents have no socket of their own, so they always read as offline — and an owner can't tell from their phone whether the laptop running them is awake.

  • RelaySession.publishAgentPresence(status, agents, signal): signs one kind 20003 event (content = status, a p tag per agent) and publishes it on the live socket. Ephemeral: never queued or retried by the outbox.
  • Agents2Service.announce(), per origin, from the 5s tick and after each update:
    • Online set = agents this copy holds (mayHold, after its claim was answered) and runs, with a live binding.
    • Sends on a new session, when the set changes, and every 60s otherwise (relay TTL is 180s), in chunks of 256.
    • Agents it stops running are said offline — unless another copy took them over (yielded), so a handoff doesn't flash offline.
    • A refused send logs once and retries after 30s, not every tick.

Testing

  • service.test.ts: online every minute + on a new session + offline on removal; an agent held by another copy is never said online or offline; a refused send is retried after 30s. Mutation-checked (ownership/yield/backoff removal each fail a test).
  • vitest run src/features/agents2 src/features/relay src/bundled/agents2: 112 files, 2047 tests pass. tsc clean.
  • Not yet run live against a relay with #8261.

🤖 Generated with Claude Code

Honey and others added 8 commits October 11, 2026 09:57
Honey @claude @baxen
fix(agents2): keep agents running when another community is selected
769892f 
Agents2 listened only to the selected community, and the Claude Code and
Codex runtimes stopped the processes of agents that left that list, so
switching communities killed work mid-turn and left the other community
unheard.

Agents2 now binds each joined community the viewer has an agent in (opened
through a new Communities.open, without selecting it), delivers each
community's live events only to its own agents, and exposes the running
agents and each agent's community connection. The runtimes keep processes
for every running agent and read conversations, names and memory from the
agent's own community. Processes stop when the agent is deleted, its
community is left or disconnected, or the viewer signs out.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Honey <8e307ae0076a4dab6b94b036ea3edc7e08f823a625269c1e6919e881a048b4d2@buzz.block.builderlab.xyz>
Honey @claude @baxen
fix(agents2): retry a failed unselected community connection
9011eb8 
A first connect that fails leaves the session in error, and only the
selected community has a Retry the viewer can press. Agents2 now tries an
unselected community's failed connection again every 30 seconds, so its
agents recover without the viewer opening it. Also covers
Communities.open directly.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Honey <8e307ae0076a4dab6b94b036ea3edc7e08f823a625269c1e6919e881a048b4d2@buzz.block.builderlab.xyz>
@baxen @claude
perf(claude-code): one shared spare process instead of one per agent
cb99f1c 
Each Claude Code agent kept its own warm `claude` process and up to six
processes in all. With agents in many communities kept running, that is
one idle ~300 MB process per agent.

Starting the process is what a spare saves (time to turn start ~530ms cold
vs ~45ms warm, measured against claude 2.1.296); sending `initialize`
costs almost nothing. So the spare is now spawned without `initialize`,
fixing only its folder and model, and the agent that takes it sends its
own prompt and installs its own tool handler. One spare serves every
agent; it follows the latest new conversation, and is replaced when no
agent runs where it was started. The per-agent process cap is removed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
fix(claude-code): only the runtime decides where a spare is kept
c06f6b5 
A conversation whose launch finished after its last agent was removed
took the spare and started a replacement, which then stayed with no
agents. Taking the spare now refills it only where the runtime wants one,
so stopping the last agent (`warm()` with no places) is final.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
fix(agents2): end agent lifetimes on teardown and inventory errors
10ddcc8 
- A native agent list still being read when Agents2 stops is now stale,
  so it cannot reopen agent communities after teardown.
- Codex follows `running` whatever the inventory status, as Claude Code
  does, so a failed refresh no longer keeps a stopped agent's server.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
perf(codex): one app-server for every agent
fafa5d6 
Codex agents each kept their own `codex app-server` (~300-400 MB with its
MCP children) until the agent stopped running. With agents now running
in every joined community, that cost grew with every Codex agent used.

Everything agent-specific already travels with the thread: cwd,
developer instructions and dynamic tools go in thread/start, and tool
calls carry their threadId. So the runtime now owns one server, opened
on first use in ~/.buzz, and finds a tool call's agent by thread and
turn across all agents. Entries keep their conversations and saved
bindings but no longer own a process.

A stopped agent can no longer take its process down with it, so it
interrupts its own turns, then cleans the background shells its threads
left (a dev server from a finished turn, say). Starting the same agent
again waits for that, so it never resumes a thread mid-teardown. The
server ends with the last Codex agent, on dispose, or on a crash (the
next mention reopens it).

live.mjs passed the relay as an object since the per-agent relay
change; it now passes a function, expands ~ like the desktop host, and
checks two agents on one real server.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
[session-debug] live agent session viewer
da93663 
`bin/node scripts/session-debug.mjs '<thread>'` serves a loopback page that
follows a Codex or Claude Code transcript as it is written. The left rail is a
vertical wall-time chart: inference, tool waits and their overlap, gaps nobody
is accounted for, and idle time between runs, with each call's new tokens
marked beside it. A grey band shows which part of the session is on screen.
The conversation shows one harness/model/effort line, compact tool rows, and
messages posted to Buzz as cards, so text the agent never sent stands out.

Claude Code's zero-usage `<synthetic>` resume replies and queue bookkeeping no
longer count as activity, which had been inflating inference time. The
standalone exporters pick up the same tool rows and posted-message cards.

Started by codex00; chart and conversation design by claude00.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Squashed-from: baxen/session-debug
Squashed-head: 84d70727ddf9db15c352f070634ab47f7adb682f
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
[session-debug-context] show recorded prompt, tools and injected context
a7a305e 
The session page hid every instructions entry, so even Codex's recorded base
instructions and dynamic tools never appeared. Model-visible context now shows
as quiet collapsed rows where it was recorded, without a proxy:

- Claude: the system prompt and tool schemas from Claude Code's
  `prompt_snapshot` records, one disclosure per tool. Each snapshot pair counts
  as one, and repeats only show when the prompt or tools change. Every injected
  reminder (environment, skills, CLAUDE.md, hook context) is shown with its
  rendered text and role.
- Codex: base instructions, dynamic tools per tool, run settings from
  `turn_context` whenever they change, and developer/AGENTS.md context named
  by its tag.

A one-line reminder also shows inline, such as the token count. Request
framing, Claude's deferred tool schemas and Codex's native tool schemas are
not recorded, and the page says so.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Squashed-from: baxen/session-debug
Squashed-head: d7e8a3c248cdbbb693fdba2ef4c9262e412f21d8
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen baxen mentioned this pull request Oct 11, 2026
Open
@baxen
baxen force-pushed the baxen/agent-presence branch from a849850 to 8e39587 Compare October 11, 2026 21:52
@baxen
baxen force-pushed the baxen/agent-working-reactions branch from 71f044f to 737b32d Compare October 11, 2026 23:11
@baxen
baxen force-pushed the baxen/agent-presence branch from 8e39587 to 3c33201 Compare October 11, 2026 23:11
baxen and others added 2 commits October 11, 2026 16:50
@baxen claude00 @claude
fix(session-debug): let Vite's dependency scan resolve the inspector …
430392d 
…page

Browser fixtures scan every HTML file under the repo root, and
scripts/session-debug.html imported "client.js", which only the
inspector's own server maps to a real file. The scan failed, Vite
skipped pre-bundling and re-optimized mid-test, and the reloads broke
browser journeys across both engines. The page now names its files as
they are on disk and the server serves them under those names, so the
vite.config.ts exclusion (which fixture servers never read) goes away.

Co-authored-by: claude00 <fb8b76a01257932b8ca35060862c29bd09b2137638573731c2d5074fc02c5385@buzz.block.builderlab.xyz>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude @codex
[model] pick a mentioned agent's model and effort for its next run
c41320f 
Mentioning your own Claude Code or Codex agent shows a gauge in the
composer. Its popover is an effort slider with the model name in the
slider's tab; the name opens a compact menu of the agent's models. The
pick rides on that message as `model` and `effort` tags for that agent,
and the host honors them only from the owner and only for listed models
and levels.

- Codex passes the pick to `turn/start` for that turn only.
- Claude Code lists models from `initialize`, sends `set_model` and
  `apply_flag_settings` ahead of the picked turn, and restores its own
  on the next unpicked one.
- The slider opens at the effort an unpicked run uses (Claude Code's
  session effort, Codex's configured effort or the model's default);
  moving back to it is no pick.
- A configured Codex model its CLI does not list keeps the picker, with
  the listed models still pickable.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Squashed-from: baxen/model
Squashed-head: 053cee0dba93bb946f544c0c87804ceee90a49ef
Signed-off-by: Bradley Axen <baxen@squareup.com>
Co-authored-by: Codex <noreply@openai.com>
@baxen
baxen force-pushed the baxen/agent-working-reactions branch from 737b32d to 84e88c1 Compare October 11, 2026 23:55
@baxen
baxen force-pushed the baxen/agent-presence branch from 3c33201 to d52ccdb Compare October 11, 2026 23:56
baxen and others added 14 commits October 11, 2026 17:08
@baxen codex00
Bind the popup CSS contract test to completions
ba91a8b 
Composer model controls also use a popup class. Select the completion-specific data-mention variant instead of whichever CSS module loads first. Preserves all token and geometry assertions; reproduced before and passed in Chromium and WebKit after.

Co-authored-by: codex00 <6922125dbee102fcf02d2b32441fd56927c1298ac16119167f82f72529d13676@buzz.block.builderlab.xyz>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen
[agents2] preserve picture and description in ordinary profiles
f9d6811 
Store optional picture and about fields on Agents2 identities and publish them with the name. Track accepted metadata so updates and clears publish even without a rename. Preserve compatibility with older rows and publication receipts.

Implemented with goose AI assistance. Human acceptance: green confirmed working.

Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
[agents2-adopt] bring over agents from earlier agent systems
aa2cf6b 
Agents2 can now take over an identity that the harness controller or
old Buzz (installed or dev) saved on this machine. It keeps the key,
name and picture, and leaves the instructions and settings behind.
Neither old store is written.

- port.rs lists both stores as one flat list, one entry per key. The
  harness copy wins because its key is already in this app's store.
  It also re-reads an identity and its key at take-over time.
- AppAgents::adopt is prepare with an existing key. When a harness
  agent saved for the same community already holds the key under the
  same credential ID, commit shares that key and never adds or
  withdraws it. Without this, a failed add would have deleted the
  harness copy.
- An adopted agent keeps the profile its community already has.
  Without one, it publishes the name and picture it brought. If the
  read fails, it overwrites nothing until the agent is renamed.
  Agents2 profiles gain an optional picture.
- Adds a "Bring over" side panel on the Agents2 page.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @codex
Preserve complete publication receipts when adopting profiles
0859001 
Adapt adoption to the metadata layer so accepted pictures and descriptions are recorded with the name.

Co-authored-by: Codex <noreply@openai.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
Keep Agents2 agents through erase and renames, and show their pictures
84ed1b2 
Erase kept only the earlier agent registry: "keep agents" wiped
agents2/identities.json, orphaning its keys, and "remove agents" deleted
only keys listed in the earlier registry. Both registries are now kept,
and removing agents deletes the keys of both.

A rename republished an adopted agent's profile with only its name, bot
flag and picture, dropping about, banner, NIP-05 and the rest. It now
reads the community's current profile and changes only the name and bot
flag, adding the picture only where there is none.

The Agents2 grid, peek and build view now show the picture an agent
brought over instead of only its initials.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen
[agents2] import picture and description as ordinary profile state
3d9af33 
Import authored descriptions and retained pictures from legacy and harness records. Publish ordinary stored metadata and track accepted picture/about changes without a persistent adopted flag or community-profile preservation path. Retain transient shared-key custody protections and compatibility with saved adoption flags.

Implemented with goose AI assistance. Validated on tail with 46 controller unit tests, 5 integration tests, 4 native host tests, formatting and diff checks. Live tail acceptance remains deferred.

Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
[agents2] set an agent's picture from the build view
c3f4fbe 
Agents2 had no way to set a picture, and its grid, peek and build view
passed raw relay media URLs straight to <img>, which community media
refuses without the media proxy, so even agents brought over with a
picture showed initials.

AppAgents::set_picture (app_agent_set_picture) saves or clears an HTTPS
picture; Agents2.save takes { picture } and republishes the profile
through the existing refresh. The build view's identity rail uses the
shared AvatarEditor (uploads as the owner, like your own profile), and
every agent portrait goes through useAvatarPreview.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
[remove-agents-v1-ui] Remove the v1 Agents page, Channel templates an…
0ffdec2 
…d agent-mention popups

Delete the bundled Agents and Channel templates plugins and every v1
mention popup: wake notices, owner-review requests, the mention attach
path in agent control, and snapshot previews. Adding an agent to a
channel no longer starts it.

Settings > Agents keeps only "Remember mentioned agents" and the saved
activity archive. The shell's collapsible-sidebar, retry and icon
special cases move from the v1 Agents page to Agents2.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
[remove-agents-v1-profiles] Drop v1 agents from the Profiles plugin
d8745ea 
Keep the Profiles panel for people and Agents2 agents, and drop only what
served v1 agents: Runtime, Instances, harness log, start/stop/restart,
archive, Memories, Add to channel, exact-instance targets and the
kind-10100 Agent type and Capabilities rows. Human profiles render as
before. Agents2 agents keep their type's tabs and Delete, and Message for
an agent follows the Agents2 LocalAgents snapshot. Browser fixtures use
LocalAgents instead of AgentControl; v1-only cases are removed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
[remove-agents-v1-cleanup] Remove v1 agent control, snapshots, catalo…
0b0c7c4 
…g and security

With the v1 Agents page, Profiles and Channel templates gone, the services
behind them have no consumer. Delete v1 AgentControl and its native bridge,
AgentSecurity, agent snapshots and snapshot sharing, team bundles and
import, the community catalog, the agent-management request lease, and the
channel kit's team payload/text write paths.

Names, mentions and New message now read a LocalAgents snapshot published
by Agents2 (the viewer's own live identities) instead of v1 native control,
so Agents2 agents stay "managed" for DMs and mention invitations. The
plugin author API no longer exports the AgentControl or AgentSecurity
types. Docs drop agent-control.md and agent-security.md and describe the
remaining agent surfaces.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
[remove-agents-v1-templates] Remove the channel template extension point
5293289 
Templates & teams was the only TemplateProviders contributor, so with it
gone the extension point only rendered empty slots and "templates are off"
notes. Remove ctx.channelTemplates and its editor, group-default and
save-as slots from Create channel, the channel menu, Channel settings and
Personal groups. Create now sends name, privacy, duration and destination
group only.

The channel kit model and session setup stay: groups and Canvas depend on
them, and frozen setup receipts saved by earlier builds still retry with
their original agents and Canvas.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
[remove-agents-v1-native] Remove the v1 native agent host
6088ea3 
Nothing in the frontend drives the v1 agent controller any more. Delete
AgentHost and every agent_control_* command, agent_security, native model
discovery (agent/codex/goose/pi models), harness installers and managed
npm, media_snapshot_read, the kit team-catalog reader and the agent
supervisor dispatch, with their build.rs, capability and permission-test
entries, plus the orphaned authorize-agent route in native-api and the
dev broker. Drop the now-unused buzz-agent dependency.

Agents2's app_agent_* commands are unchanged; app_agents.rs now owns the
NIP-98 header helper it borrowed from the v1 module. Quit, update restart
and sign-out no longer wait on a native agent host: Agents2 agents are
plugin host processes that stop when Buzz exits. Sign-out still deletes
keys listed in the v1 agent registry.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @codex
[remove-agents-v1-tail] remove retired runtime packaging and controller
b8a26e7 
Stop building and shipping the unused v1 agent runtime. Keep desktop launch,
application signing, installer verification and AppImage launch repairs.

Trim the controller crate to Agents2 identities, credentials, profile signing
and legacy import. Preserve legacy key deletion with bounded registry reads,
identity validation and controller locking, without retaining the v1 runtime.

Co-authored-by: Codex <noreply@openai.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen claude00 @claude
fix(agent-controller): compile the private-directory helper only wher…
0ab40dd 
…e it is used

With the v1 controller gone, credential locking is its only caller, and
that is compiled only on macOS and in tests. Linux and Windows lint
failed on the now-unused function.

Co-authored-by: claude00 <fb8b76a01257932b8ca35060862c29bd09b2137638573731c2d5074fc02c5385@buzz.block.builderlab.xyz>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
baxen and others added 3 commits October 11, 2026 17:09
@baxen @claude
feat(agents2): react 👀 💬 to a mention while its agent works
c5bdc7e 
Until Agents2 agents show as typing, the host reacts to a mention as the
agent with 👀 and 💬 when its run starts, and deletes both once the run and
the work it handed off have settled (at most the longest run allowed).

Plugins return from `run` early and finish their turns in the background,
so `Delivery.workingUntil(done)` lets them say when that work settles.
Claude Code and Codex now call it. The reactions live in
working-reactions.ts and its one call in the service, so they can be
deleted once typing indicators ship; `workingUntil` stays for those.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
feat(agents2): show an agent typing on this device while it works
3f9611e 
STOPGAP until agents' typing pulses reach the relay: the host shows a
mention's agent typing in the mention's thread on this device only, for as
long as the run counts as working. Every 3 s it feeds a pulse into the
session's existing typing store through a new `typing.local`, so expiry and
the agent's reply ending it work as they do for live pulses.

Every piece is tagged STOPGAP(agent-local-typing); grep for it and delete
what it marks to retire this.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen @claude
fix(codex): stop counting a request as working once it is answered
ba9b31b 
Codex makes one more model call after a final send before its turn
ends, so the request's working handoff, and with it the agent's working
reactions and typing, outlasted its reply by about 3s. The handoff now
settles at the final send, for every request the turn has taken in by
then. The turn itself still ends on its own: interrupting it would leave
a <turn_aborted> note in Codex's history after every reply.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen
baxen force-pushed the baxen/agent-working-reactions branch from 84e88c1 to ba9b31b Compare October 12, 2026 00:12
@baxen @claude
feat(agents2): say the agents this copy runs are online
31a8ded 
App-hosted agents have no socket of their own, so they always read as
offline, and an owner cannot tell from another device whether the laptop
running them is awake.

Each origin now sends one owner-signed kind 20003 batch for the agents this
copy holds and runs: on a new session, when the set changes, and every
minute otherwise (presence expires after three minutes). Agents it stops
running are said offline, unless another copy has taken them over. A
refused send is retried after 30 seconds rather than every tick. Relays
without kind 20003 ignore it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Bradley Axen <baxen@squareup.com>
@baxen
baxen force-pushed the baxen/agent-presence branch from d52ccdb to 31a8ded Compare October 12, 2026 00:14
@matt2e
matt2e force-pushed the baxen/agent-working-reactions branch from ba9b31b to 04c3944 Compare October 12, 2026 05:51
Base automatically changed from baxen/agent-working-reactions to main October 12, 2026 07:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@baxen