Board (/board):
- Drag an AGENT chip onto a task card to (re)assign it (realtime-notified).
- Drag a task card to a column to change status; open→in_progress auto-assigns
from the title's "<agent>:" prefix — no manual agent picking.
- "+ New task" composer (agent dropdown removed; agent comes from the title).
- Live Cost & Budget panel.
Team (/team): live SSE sync of busy state + always-on ambient animation
(connector shimmer, idle glow) that brightens to a busy pulse when an agent
works. Org-chart hierarchy stays.
Token accounting: new budgetService/rosterService + GET /budget and /agents.
Real doneTokens + time-on-task estimate capped at 45 min/task (avoids the
wall-clock overcount that produced multi-million-token totals), blended
per-model EUR cost + optional budget bars. All estimates flagged "~".
Autostart: `agent setup` writes deterministic SessionStart hooks for Codex
(~/.codex/config.toml) and Kimi (~/.kimi-code/config.toml), not just Claude
Code. Verified: both auto-enter the agenthub_work loop.
Realtime architect review: agenthub_work is role-aware — architect/reviewer
blocks on SSE and wakes when a task hits review (no manual watcher re-arm).
mDNS: server advertises agenthub.local (bonjour-service) so the hub is
reachable in a browser on the LAN without an IP.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The recurring "agent doesn't read messages in realtime / isn't triggered for the
next task" problem: agents weren't STAYING in the agenthub_work loop, so they went
dormant after each task. Two reinforcements:
- agenthub_work now ends every response with a LOOP directive: "the instant you
finish, call agenthub_work again (in the background) so the next task/message
reaches you in realtime — never end your turn without relaunching it."
- The auto-start hook-context now stresses the BACKGROUND loop + relaunch pattern,
so a Claude Code session is woken on each event instead of blocking.
Layer 1 (auto-start) gets agents INTO the loop; this keeps them IN it. Honest
limit: turn-based agents still rely on obeying the relaunch nudge — there's no
100% always-on without a supervisor. Bump 0.9.0 -> 0.9.1.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Closes the dormancy gap: an agent no longer needs to be told "call agenthub_work".
`agenthub agent setup --agent <name> --role <role>` writes a verified Claude Code
SessionStart hook (.claude/settings.json) whose command runs `agenthub hook-context`,
which prints the work-loop instruction injected into every new session — so the
agent claims tasks AND surfaces messages from the first turn, no manual trigger.
- agentSetup.ts: agentSetup() (idempotent hook write, project or --user scope) +
hookContext() (the injected instruction).
- Honest limit (per Claude Code docs): SessionStart context is a strong nudge the
model reads, not a hard directive; the guide reinforces it. Can't block startup.
- Codex/Kimi aren't Claude Code — their guide already nudges agenthub_work first.
Run once per agent machine. Bump 0.8.1 -> 0.9.0.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Closes the fire-and-forget gap the user hit: the sender now sees when a message
is read. When markMessageRead fires, the read event carries the reader, and the
watch stream renders it as a receipt:
AgentHub: ✓ Read MSG-0002 read by windows-claude
Plus an ack convention in the implementer guide: when you act on a message-
request, send a brief "on it …" + a result message — so the sender sees progress,
not silence. (Board-side activity feed with messages is folded into TSK-0032.)
Bump 0.8.0 -> 0.8.1.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Direct messages between agents through the hub — architect↔agent and agent↔agent
questions, clarifications and pings that handoffs/memories don't cover. Built as
MCP tools so kimi + codex get it too (not Claude-only), plus REST + CLI.
- Message entity (MSG-NNNN): schema, counter, messages/ dir, messageService
(createMessage / listInbox / listMessages / markMessageRead).
- REST: POST /messages, GET /messages[?agent&unread], POST /messages/:id/read,
with SSE emit. fsWatch + statusRefresh wired ('message' events; status skips them).
- MCP: agenthub_message {from,to,text,taskId?} + agenthub_inbox {agent,unreadOnly?}.
agenthub_work now surfaces + drains unread messages and wakes on message events,
so an agent sees messages inside its work loop. (18 tools total.)
- CLI: `agenthub message <to> <text> --from <agent>` + `agenthub inbox --agent`.
watch stream shows "Message" events (architect-visible).
- Architect-visible by design: the hub stays the coordination point.
Bump 0.7.5 -> 0.8.0.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Architect implementation of the reopened TSK-0028 (option B). The team page now
reads config.agents (the roster) as the source of truth instead of inferring
role/identity from tasks:
- one fixed role per agent (fixes "codex in architect+implementer+tester")
- implementers grouped by provider with official Simple Icons brand logos
(Anthropic / OpenAI / Moonshot) + the model behind each agent (Opus 4.8,
Sonnet 4.6, GPT-5 Codex, Kimi K2)
- demo/throwaway agents gone (not in the roster)
- architect tier (claude) on top, implementer provider columns, tester tier
(ahmed); free/busy + live timer from in-progress tasks
- ui-shared: providerLogo()/providerMeta() with verified brand SVG paths
Bump 0.7.4 -> 0.7.5.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
One command, no hand-editing: `agenthub mcp install` writes/merges a project
.mcp.json (the standard config Claude Code and other .mcp.json-aware clients
auto-discover) with the hub URL filled in — so those agents register
automatically. Prints the global-config snippet for Codex/Kimi as fallback.
`--print` is a dry run. Bump 0.7.3 -> 0.7.4.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Removes the registration friction: `agenthub mcp install` prints ready-to-paste
MCP config for Claude Code, Codex and Kimi, with the hub URL filled in from the
project config. `agenthub mcp` (no action) still starts the stdio server, so the
MCP-client spawn command is unchanged. Bump 0.7.2 -> 0.7.3.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Implementer onboarding now points at the MCP tools first (agenthub_work ->
implement -> agenthub_task_review -> loop), with the CLI as the fallback when
the MCP server isn't registered. Reflects the MCP pivot. Bump 0.7.1 -> 0.7.2.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Adds an optional `agents` roster to the project config: agent name -> role +
model + provider (kind). The team view can now show named agents (claude,
codex, kimi, windows-claude, backyard, mo, zied, …) with a FIXED role and the
model behind them, instead of inferring role/identity from whichever tasks an
agent happened to touch (which made one agent appear under several roles).
Bump 0.7.0 -> 0.7.1.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Solid-collaboration foundation: agents invoke STRUCTURED tools instead of
shelling out to the CLI — so a tool can't be narrated away, hallucinated as
"doesn't exist", or mistyped. Confirmed working for Claude / Codex / Kimi
(all speak MCP).
- src/mcp/server.ts: `agenthub mcp` starts a stdio MCP server exposing 16
tools (work, task_list/show/create/assign/claim/review/reopen/done,
memory_add/search, handoff_read/create, decision_create, hello, status).
Thin layer over the SAME core: proxies through the REST API (remoteClient)
when a hub is configured — so board, SSE, status auto-refresh and CLI keep
working unchanged — else local services. agenthub_work blocks on SSE until
a task addressed to the agent is claimable, then returns it + its handoff.
- `agenthub mcp` command; excluded from the update-notify (stdio purity).
- Verified: initialize + tools/list (16) + tools/call (status, task_list)
proxy to the live hub.
Does NOT change the dormant-agent reality (agents still loop agenthub_work);
it makes every interaction reliable. Bump 0.6.1 -> 0.7.0.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The old auto path checked `HEAD..origin/branch` right after kicking off a
background fetch, so it read a stale origin ref and only fired on the SECOND
invocation (and never if the agent sat in one long-running `work`).
Now: when AGENTHUB_AUTO_UPDATE is set, a throttled tick (≤1h) spawns
`agenthub update` directly in the background. update does its OWN fresh fetch
+ reset + build and no-ops when current — so it self-heals on the FIRST
invocation, no stale-ref lag. Notify-only path (no flag) unchanged.
Removed the now-unused cooldown const. 122/122 green. Bump 0.6.0 -> 0.6.1.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Closes the addressing gap that left a waiting `agenthub work` blocked: the
remaining Win tasks were titled "Win L2: …" / unassigned, so they matched
no agent and the daemon waited forever.
`agenthub task assign <id> --agent <name>` sets assignedTo WITHOUT claiming
(status stays open) and fires task/updated — so an agent's blocked `work`
re-checks, matches via assignedTo, and auto-claims it. The architect can now
route a specific open task to a specific agent and have its daemon pick it up.
- taskService.assignTask; PATCH /tasks/:id handles assignedTo-without-status;
remoteClient.assignTask; CLI `task assign`.
- test: assign keeps status open + sets assignedTo; start/work then claims it
via the assignedTo match. 122/122 green.
Bump 0.5.0 -> 0.6.0.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Closes the architect-side gap: the auto-claim daemon wakes implementers on
new tasks, but the architect had no signal when an implementer submitted.
`agenthub watch --await-review` exits (after printing) the moment a task
enters `review` — including any task already in review on connect (initial
check) — so the architect can run it in the background and be re-invoked by
the harness the instant a submission needs a verdict.
- watch.ts: awaitReview option, initial fetchReviewTasks() check + SSE exit
on task→review.
- index.ts: --await-review flag.
- tests: returns immediately on already-pending review; exits on a review
transition while watching. 121/121 green.
Bump 0.4.0 -> 0.5.0.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The missing autonomy step: an implementer no longer needs a human prompt
per task. `agenthub work --agent <name> --role <role>` announces, then:
- claims an already-open task addressed to the agent immediately, or
- blocks on the SSE stream until one appears (newly delegated OR
reopened after review), then claims + prints it.
Loop: work → implement → `task review` → work. New/reopened tasks are
picked up automatically; run it in the background so the wait doesn't tie
up the turn.
- src/cli/commands/start.ts: extracted announceAgent / findAddressedOpenTask
/ claimAndPrintTask (shared by start + work); addressed-match now also
covers assignedTo (reopened tasks coming back for rework).
- src/cli/commands/work.ts: wait-and-claim via /events, with a gap-close
re-check after subscribing and an optional --timeout.
- index.ts: `agenthub work` command.
- templates: implementer guides lead with `work` (the autonomous loop),
keep `start` as the one-shot.
- tests: immediate claim (local) + wait-then-claim (server SSE). 119/119.
Bump 0.3.1 -> 0.4.0.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The status snapshot (.agenthub/status/latest.md) was only refreshed on an
explicit `status --update`, so it drifted stale and misled agents that
follow golden rule #2 ("read status/latest.md") — e.g. an implementer
seeing an old task list and picking the wrong task.
- src/server/statusRefresh.ts: subscribe to the event bus and regenerate
the snapshot on every task/handoff/decision/memory change (REST and
filesystem-watch paths), debounced 300 ms. Presence ('agent') events
are skipped; the snapshot lives outside the watched dirs so it can't
feed back into the watcher.
- wired into startServer lifecycle (start + stop on close).
- test: status/latest.md reflects a new task shortly after POST /tasks.
117/117 green.
Bump 0.3.0 -> 0.3.1.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
An agent runs ONE command and is working: it announces presence, claims
the open task addressed to it, and prints the task + its handoff + the
next step. Removes the per-agent kickoff copy-paste.
- src/cli/commands/start.ts: `agenthub start --agent <name> --role <role>`.
"Addressed to <agent>" = task title starts with "<agent>:" OR a handoff
has toAgent=<agent>. Claims it, prints task body + handoff + the review
gate reminder. No addressed task → lists open role tasks to pick.
Works on local + --server paths.
- templates: implementer guides (AGENTS/CODEX/KIMI.md) now lead with
"On your first turn, RUN `agenthub start …` — do not just summarize",
so a fresh session self-onboards from one trigger word.
- tests: start auto-claims the addressed task, ignores others, no-ops on
empty queue; templates test updated for the new commands. 116/116 green.
Bump 0.2.2 -> 0.3.0.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Set AGENTHUB_AUTO_UPDATE=1 and the install keeps itself current with no
manual `agenthub update` — ideal for the Windows client.
maybeNotifyUpdate now:
- auto mode: refreshes the behind-count hourly (vs 24h) and, when behind,
spawns a detached `agenthub update` (fetch → reset → install → build)
that doesn't block the current command; the next invocation runs the
new version. A 10-min cooldown stamp prevents a second build spawning
while one is in flight.
- otherwise: unchanged "run `agenthub update`" hint.
Safe to enable anywhere: `update` no-ops when current and refuses to
discard unpushed local commits, so the authoring machine is protected.
Cross-platform (no OS scheduler needed). Bump 0.2.1 -> 0.2.2.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Implements the architect-controlled workflow: implementers submit work
for review, only the architect closes tasks.
- CLI: `agenthub task review <id>` (implementer submits → status review)
and `agenthub task reopen <id>` (architect re-triggers → status open).
Server already supported both statuses; now exposed on local + --server
paths, with remoteClient.reviewTask/reopenTask.
- templates: AGENTS.md + role guides rewritten so agents self-drive the
CLI on open (hello → claim → implement → task review → wait), with the
hard rule that ONLY the architect runs `task done`. Implementer guides
(codex/kimi) never call done; architect guide documents done/reopen.
- tests: review/reopen SSE events + formatEvent "Task review"/"Task
reopened" lines. 113/113 green.
Bump 0.2.0 -> 0.2.1.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Agents now connect to the hub with no manual env/flag, and announce
themselves on join — restoring the agreed onboarding flow.
Auto-connect (resolveContext):
- An initialized project WITHOUT a configured serverUrl now falls
through to LAN auto-discovery (previously it went straight to local
mode, so agents in an initialized repo never found the server). The
discovered URL is persisted to the project config, so the next
command is instant.
- IP-change self-heal: when a configured server is unreachable,
runRemote re-discovers the live server and updates the config so the
next command reconnects automatically.
Presence (join-announce):
- POST /announce broadcasts an ephemeral 'agent/joined' event (not
written to disk). New `agenthub hello --agent <name> --role <role>`
posts it; watchers print "AgentHub: <agent> joined (<role>)".
- AgentHubEvent extended with type 'agent' + actions 'joined'/'left';
formatEvent renders presence lines; remoteClient.announce() added.
Tests: formatEvent agent lines + /announce SSE e2e. 109/109 green.
Bump 0.1.2 -> 0.2.0 (CLI --version too).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Every user-facing line — the watch stream and each command's success
line, on both the local and --server (remote) paths — now carries an
"AgentHub:" prefix so it's recognizable in any agent's console
(Claude / Codex / Kimi), independent of the board.
- watch: formatEvent rewritten to verb-based, branded lines
("AgentHub: Task received <id> <title> [status]",
"AgentHub: Task done <id> by <agent>", "AgentHub: Handoff …"),
plus an "AgentHub: connected" line on stream start.
- task/handoff/decision/memory/delegate/init + server-listening lines
branded on the local command path.
- cli/index.ts: same branding on the --server remote path (the path
agents actually hit), so CLI line and SSE stream now match.
- tests: formatEvent assertions updated to the branded format
(regex-tolerant of column padding). 106/106 green.
codex + kimi stay implementers by convention (role=implementer +
assignedTo) — no schema change. Bump 0.1.1 -> 0.1.2.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Local-mode branch of 'memory add' omitted category when calling memoryAdd, so it always fell through to an interactive select() prompt — which throws in non-TTY agent contexts and breaks the reporting loop. Forward category; add tests for the non-interactive flag path.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
GET /tasks/:id/activity returns a time-sorted ActivityItem[] assembled from existing data (task created, handoffs by taskId, memory by relatedTasks, current status). memory add + task done gain optional tokens/duration/by metadata surfaced in the timeline. Board cards expand inline to show the timeline. Index gains taskId + relatedTasks columns with migrations. 74 -> 97 tests.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- src/server/events.ts: in-process EventEmitter bus (AgentHubEventBus);
singleton per server process, unlimited listeners for SSE fan-out.
- src/server/routes.ts: GET /events SSE endpoint — keepalive every 25 s,
optional ?role= server-side filter, reply.hijack() for clean streaming;
eventBus.publish() called on every successful mutating route (POST tasks/
handoffs/decisions/memory, PATCH tasks/:id).
- src/cli/commands/watch.ts: SSE client using Node fetch + ReadableStream
reader; exports parseSSEBuffer + formatEvent for testability; --once flag
exits 0 after first event (turn-based agent use case); --role for client-
side filtering (additive to server-side filter).
- src/cli/index.ts: register agenthub watch command via resolveContext.
- tests/sse.test.ts: 18 new tests (74 total, all green) — unit tests for
parseSSEBuffer + formatEvent, integration tests for eventBus on each
mutation type, E2E SSE stream + role-filter tests over real HTTP.
Limitation (documented): only REST mutations through the server emit events.
Local-CLI writes (direct file+SQLite) are invisible to subscribers — a
filesystem-watch increment is deferred to a later phase.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
agenthub update: fetch + reset install to origin/<branch> + reinstall + rebuild, so users never touch git or pnpm. Robust to a dirty working tree (the 'commit before pull' wall) by resetting to remote; guards unpushed local commits and refuses to discard them. Adds a daily, non-blocking update hint on startup (detached background fetch + instant local comparison, like gh/npm/brew) that never auto-applies. Tests for the non-git-install path.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Make the network MVP simple to operate: server start refuses a second instance on a port already serving AgentHub (single source of truth, prevents discovery split-brain); commands auto-discover a LAN server when run outside any project so the CLI works from any directory with zero config; walk up to the nearest .agenthub project (cwd-robust) and serve the project root; replace raw stack traces with actionable messages; add tests for findProjectRoot and the single-instance guard.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
