new NixOS option in harness-base.nix:
hyperhive.allowedRecipients = [ 'alice' 'manager' ]; # whitelist
hyperhive.allowedRecipients = [ ]; # default = unrestricted
module writes the list as JSON to /etc/hyperhive/send-allow
.json at activation. AgentServer::send reads the file before
issuing the broker request; if the list is non-empty and
`to` isn't on it, the tool returns a claude-readable refusal
string without touching the broker. the manager is always
implicitly permitted regardless of the list — otherwise a
misconfigured allow-list could strand a sub-agent without an
escalation path.
enforcement is in the in-container MCP server (not on the
host's per-agent socket) because the agent's nix config is the
trust boundary anyway — the operator audits agent.nix at
deploy time, the activation-time /etc/hyperhive/send-allow
.json is r/o under /nix/store, so the agent can't tamper at
runtime without going through a new approval.
agent prompt mentions the option + tells claude to route
through the manager when refused. retires the matching TODO
under Permissions / policy.
after reverting the 3-column attempt (74ba8a6), keep the
single-column layout but put related sections adjacent:
swarm: containers → kept-state → meta-inputs
decisions: questions → approvals
messages: operator-inbox → message-flow + compose
this is a free improvement — the operator scrolls through one
logical group at a time instead of bouncing between swarm /
decisions / messages mid-page. follow-up improvements
(collapsing rarely-active sections, multi-column at wide
viewports done less aggressively) captured in TODO under
'Dashboard layout overhaul'.
every snapshot source backing /api/state used .unwrap_or_default()
— sqlite errors, broker errors, nixos-container list failures,
operator_questions decode crashes all degraded to empty lists
without a log line. the 'pending question doesn't render'
bug we've been chasing was likely a row-decode panic in
OperatorQuestions::pending() being swallowed this way.
new log_default(what, result) replaces each call site: same
default value on Err but emits target=api_state warn with the
source name + dbg error first. five sources covered:
nixos-container list, approvals.pending,
approvals.recent_resolved, broker.recent_for(operator),
questions.pending. next time the question goes missing the
journal will say which source failed and how.
todo updated — pending-question entry now points at the new
log instead of three suspect paths.
old behavior: omitted wait_seconds fell through to the 30s
RECV_LONG_POLL_DEFAULT — claude calling 'is there anything in
my inbox right now?' between actions blocked the turn for half
a minute. flip the semantics: None (or 0) returns immediately,
positive value parks up to MAX (180s, unchanged). cleaner
'peek vs wait' distinction; tool descriptions + agent/manager
prompts updated to point at the new shape.
harness's own serve loops in hive-ag3nt + hive-m1nd relied on
the old default for their inbox poll. they now explicitly pass
wait_seconds: Some(180) to opt into the full park — same
effective behavior as before, just spelled out.
retires the matching TODO under Turn loop.
new tabs above the approvals list: 'pending · N' and
'history · M'. active tab persists in localStorage so the
operator can park on history if they prefer. on a fresh
dashboard the default is pending (matches the prior shape).
history view shows the last 30 resolved approvals — newest
first by resolved_at — with one row per approval: status
glyph (✓ approved / ✗ denied / ⚠ failed), id, agent, kind,
short sha, status label, and a relative time chip. when the
row has a note (deny reason or build error), it renders
below in a muted block with line wraps preserved.
backend: Approvals::recent_resolved(limit) queries by
status IN ('approved', 'denied', 'failed') ORDER BY
resolved_at DESC. StateSnapshot gets approval_history (a
lean ApprovalHistoryView without diff_html — rendering 30
git diffs per state poll would be expensive and the operator
already saw the diff at decision time). dashboard's
history_view fn projects the sqlite row.
retires the matching TODO entry.
new entry under UI/UX for an approval history tab on the
P3NDING APPR0VALS section — sqlite already has every row + the
applied repo's annotated denied/failed tags carry the
human-readable reasons, so this is a render-side change.
retire the 'stream nixos-container stdout' entry — landed in
6f1b664. run() now pipes child output line-by-line into
tracing so 'slow build' no longer looks like 'wedged daemon'.
new NixOS option in harness-base.nix:
hyperhive.extraMcpServers.<key> = {
command = "/path/to/server";
args = [ ... ];
env = { KEY = "value"; };
allowedTools = [ "send_message" "join_room" ]; # or ["*"]
};
declared as attrsOf submodule so agents stack arbitrarily many.
the module writes the whole map as JSON to
/etc/hyperhive/extra-mcp.json at activation; the harness reads
that file in mcp::render_claude_config and merges each entry
into the rendered --mcp-config under its own mcpServers.<key>
block. allowed_mcp_tools(flavor) extends the --allowedTools
arg with mcp__<key>__<pattern> for every entry — "*" (the
default) becomes mcp__<key>__* so every tool from that server
is auto-approved, or pass a concrete list to tighten.
collision guard: an extra server keyed "hyperhive" is dropped
with a warn-log so user config can't shadow the built-in
surface. malformed JSON / missing file fall back to "no
extras" silently.
prompt note added: agents see "(some agents only) extra MCP
tools surfaced as mcp__<server>__<tool>" and learn they're
declared via agent.nix. retires the matching TODO under
Per-agent extension. matrix-chat agents + bitburner-agent
migration unblocked.
submit_apply_commit now diffs the freshly-tagged proposal/<id>
against applied/main and refuses if flake.nix is in the
changeset. flake.nix is fixed boilerplate the meta flake
depends on (it exports nixosModules.default = import ./agent
.nix); silent edits there would break the nixosConfiguration
in subtle ways. the manager prompt already says don't touch
it; this is the host-side belt — clear error to the manager
on submit, row marked failed in sqlite, no orphan pending
approval to chase. diff-failure is logged + ignored: the
build path surfaces concrete errors if flake.nix is actually
broken.
surfaced by a real hang investigation today — lifecycle::run
uses .output() which buffers stdout/stderr until exit, so a
multi-minute nix build through nixos-container update looks
identical to a wedged daemon. line-buffered streaming into
tracing (and ideally the per-agent live event bus when the
agent is known) makes 'still building, just slow' visible
without strace gymnastics.
three things surfaced by the meta-flake overhaul + the nix CLI
deprecation we just fixed worth tracking explicitly. extend
the web-UI-for-config-repos entry to also cover the /meta
deploy log now that meta's git history is the swarm-wide
audit trail.
scratchpad in claude.md marks this as in-flight; docs/approvals.md
gets the new tag state machine (proposal/approved/building/deployed/
failed/denied) and the manager applied.git read-only mount. todo
picks up the unprivileged-containers git-identity caveat and a web
ui for config repos as a downstream follow-up.
readme: manager mcp surface picks up update; operator-surface
recap mentions /model + last-turn + model chip + the three
collapsibles (inbox / journald / agent.nix).
web-ui.md: details-restore-key story under shape; port-conflict
banner mention on containers; agent.nix viewer alongside journald;
notifications use per-event tags + console.debug log on
block/show; deny endpoint takes note=<reason>; data-prompt /
data-prompt-field generalisation noted.
conventions.md: data-prompt and snapshot/restoreOpenDetails added
to the async-forms section.
persistence.md: operator_questions row picks up deadline_at (ttl)
column with a migration note.
todo.md: new 'Bugs' section captures the manager-question
not-rendering issue with three suspect paths to chase.
claude.md scratchpad rewritten as a clean handoff for the
compaction + the upcoming config-git overhaul. flags the
two-repo (proposed/ + applied/) split as the thing to
reconsider.
new GET /api/agent-config/{name} returns the contents of
/var/lib/hyperhive/applied/<name>/agent.nix — the file the
container actually builds against. validated against the live
container list to avoid arbitrary filesystem reads.
frontend mirrors the journald viewer: collapsed <details> on each
container row, lazy-fetches on expand, refresh button re-fetches.
restore-keyed (agent-config:<name>) so it survives the dashboard
heartbeat refresh.
read-only — mutating the applied config goes through the existing
request_apply_commit + operator approval flow.
crash_watch grows two more state-axes alongside running/stopped:
- logged-in (claude session dir populated for the agent)
- up-to-date (recorded flake rev matches current)
per-tick transitions emit HelperEvent::NeedsLogin / LoggedIn /
NeedsUpdate. seed-on-first-tick semantics retained — nothing fires
on harness boot for agents that were already in their state. only
needs_update fires the 'stale appeared' direction; the resolved
direction is already covered by Rebuilt.
new mcp__hyperhive__update(name) on the manager surface: idempotent
rebuild via auto_update::rebuild_agent. transient-aware (Rebuilding)
so the dashboard shows the spinner. login intentionally has NO tool
— it's interactive OAuth, only the operator can complete it.
prompts + approvals doc + turn-loop doc updated. todo grows a
'show per-agent applied config in dashboard' entry (separate
follow-up).
revert the earlier 'operator must set allowUnfree' move:
per-agent containers evaluate their own nixpkgs and the operator's
host-level allowUnfree doesn't propagate in. restoring the scoped
allowUnfreePredicate inside both the claude-unstable overlay and
harness-base.nix; documented in README + gotchas as 'nothing to
set on the operator side'.
docs:
- claude.md file map adds crash_watch.rs, kick_agent on coordinator,
/api/model + journald viewer + bind-with-retry references.
- scratchpad rewritten to reflect the recent run.
- web-ui.md: notification row + browser notifications section,
state row (badge + model chip + last-turn chip + cancel button),
per-agent inbox, /model slash, /cancel-question + journald
endpoints, focus-preservation on refresh.
- turn-loop.md: --model is read from Bus::model() per turn (runtime
override via /model); recv(wait_seconds) up to 180s with the
rationale; ask_operator gains ttl_seconds; new TurnState section;
kick_agent inbox-on-startup hint.
- approvals.md: ttl/cancel resolution paths for operator questions.
- persistence.md: /state/hyperhive-model file.
- gotchas.md: web UI port collision policy (rename, don't probe);
bind retry + SO_REUSEADDR shape; auto-unfree restored.
- todo.md: cleaned up empty sections and stale entries; /model
shipped, dropped from the list.
three signals fire OS notifications:
- new approval lands in the queue (per id, via /api/state delta)
- new ask_operator question queued (per id)
- broker message sent to operator (live via SSE)
first /api/state render after page load seeds the 'seen' sets
without firing — only items that arrive while the page is open
count. controls in a row under the banner: 🔔 enable
notifications (calls requestPermission, hides on grant), 🔕 mute /
🔔 unmute toggle (localStorage-backed so operator can silence
without revoking the permission), inline status text when blocked
or unsupported.
notification tag='hyperhive' collapses rapid bursts; onclick
focuses the dashboard tab. requires secure context (HTTPS or
localhost) — on other origins the API is unavailable and the
controls hide themselves.
todo: entry dropped.
pure frontend — Notification API + existing /api/state and
/messages/stream signals. Caveats: secure-context requirement
(HTTPS or localhost), per-browser permission grant. Includes a
sketch of the implementation: request-permission button, count
deltas on refreshState, SSE hook on operator-bound sends,
localStorage 'muted' toggle.
model persistence: /model <name> now writes to /state/hyperhive-model
(in-container), Bus::new reads it on init. operator override survives
harness restart and container rebuild; gone on --purge like every
other piece of agent state. path overridable via HYPERHIVE_MODEL_FILE
for tests. failure to persist is a warn, not fatal — runtime override
still applies, just won't survive a restart.
unfree opt-in: drop the auto-allowUnfreePredicate from
harness-base.nix and the claude-unstable overlay. operator now has to
set nixpkgs.config.allowUnfree (or a predicate listing claude-code)
in their own host config. silent unfree bypass was sketchy; this is
honest. readme + gotchas updated to spell out the snippet.
todo: drops model-persistence + container-crash + journald (all
shipped); adds per-agent send allow-list (constrain who an agent can
message).
new hive_c0re::crash_watch task polls every 10s, builds the set of
currently-running containers, and on running→stopped transitions
checks the transient snapshot: if no Stopping / Restarting /
Destroying / Rebuilding flag is set, the container exited
unexpectedly and we fire HelperEvent::ContainerCrash into the
manager's inbox so it can react (typically: start it again).
first poll is a seeding pass — no events on harness startup. dbus
subscription would be lower-latency but polling is honest and
debuggable, and a 10s delay on crash detection is fine for our
scale.
manager prompt + approvals doc updated to advertise the new
event variant. todo drops the entry (and the journald-viewer
entry that already shipped).
- runtime model override: Bus::{model,set_model} + POST /api/model
(form-encoded {model: name}). turn.rs reads bus.model() per turn
so a flip lands on the next claude invocation. /api/state grows
a model field; agent page shows a 'model · <name>' chip in the
state row. '/model <name>' slash command POSTs to the endpoint
and refreshes state.
- port regression fix: agent_web_port no longer probes forward for
*existing* agents (the previous fix shifted ports for any agent
without a port file, including legacy ones whose container was
already bound to the bare hashed port — dashboard rendered the
new port, container was still on the old one, conn errors). new
rule: port file exists → use it; absent + applied flake present
→ legacy, persist port_hash without probing; absent + no applied
flake → fresh spawn, probe forward.
- SO_REUSEADDR on both the dashboard and per-agent web UI binds
via tokio::net::TcpSocket. operator hit 12 retries failing on
manager :8000 — REUSEADDR handles the TIME_WAIT case cleanly
without a new dep; retry still covers the genuine
process-still-alive overlap.
todo: drops the model-override entry (shipped); adds two new
items — model persistence (optional, future), and custom
per-agent MCP tools (groundwork for moving bitburner-agent into
hyperhive).
recv-with-timeout is strictly better than a fixed sleep because it
wakes instantly on incoming messages. drop the half-written nap MCP
tool, raise the recv wait_seconds cap from 60s to 180s on both
agent and manager sockets.
prompts updated: agent.md + manager.md now spell out the pattern —
when there's nothing else useful to do, call recv with
wait_seconds=180 to park the turn; do NOT use Bash sleep for the
same purpose. todo drops the nap entry and the napping-state-badge
follow-up; both replaced by 'just use a long recv'.
new TurnState { Idle, Thinking, Compacting } on hive_ag3nt::events::Bus
with set_state + state_snapshot. the turn loops in hive-ag3nt and
hive-m1nd flip Thinking before drive_turn and Idle after; the
web_ui's /api/compact handler flips Compacting around compact_session.
per-agent /api/state grows turn_state + turn_state_since (unix
seconds). frontend prefers the server-reported state over the
client-derived one — setStateAbs takes the absolute since-time so
the 'last turn' chip reads the actual server-side duration instead
of the client's perceived gap between SSE events. SSE turn_start /
turn_end still drive state instantly between renders; /api/state
re-anchors on each turn_end refresh.
new compacting state gets its own purple badge with pulse
animation (mirrors thinking's amber). napping will slot in the
same way once the nap tool lands.
new GET /api/journal/{name}?unit=&lines= shells out journalctl -M
<container> -b --no-pager --output=short-iso --lines=<N> (cap 5000).
optional unit filter, restricted to hive-ag3nt.service /
hive-m1nd.service so the shell-out can't be coerced into reading
unrelated units. validates the container name against the live list
before invoking journalctl.
frontend renders a collapsed '↳ logs · <container>' details block
on each container row. expanding triggers a lazy fetch; refresh
button re-fetches; unit dropdown switches between the harness
service (default) and the full machine journal. output sits in a
24em-tall monospace pre, auto-scrolled to the bottom on fresh
fetch.
hive-c0re's systemd unit already runs as root, so journalctl has
the access it needs.
manager can pass ttl_seconds to ask_operator. on submit, host
stores deadline_at = now + ttl in operator_questions (new column,
migrated via existing pragma_table_info pattern), spawns a tokio
task that sleeps until the deadline then resolves the question with
answer '[expired]' and fires the same OperatorAnswered helper event.
already-resolved races no-op silently.
dashboard renders a '⏳ MM:SS' chip on the question row when
deadline_at is set. format collapses seconds → s, < 1h → m s, ≥ 1h
→ h m. heartbeat refresh (5s) keeps the chip current; the operator
sees it tick down.
manager prompt + mcp tool description updated. journald viewer per
container queued in todo (separate task).
new wire request AgentRequest::Recent { limit } / ManagerRequest::Recent
(plus matching responses with Vec<InboxRow>). InboxRow moved to
hive-sh4re so it lives on both surfaces without an internal-to-wire
conversion. host-side dispatch in agent_server / manager_server
calls broker.recent_for(name, limit).
per-agent web_ui /api/state grew an inbox: Vec<InboxRow> populated
via the same per-agent socket (best-effort; transport failure
returns empty). frontend renders as a collapsible <details> section
between the state row and the terminal — fmt timestamp / from /
body in a tight grid, capped at 16em scrollable. only visible when
there are rows.
title bar grows a '↑ DASHB04RD' link next to the rebuild button —
opens the host dashboard in a new tab so the operator can pivot
between agents without losing the live tail. uses the dashboardPort
already plumbed via /api/state.
state row picks up a 'last turn 12.3s' chip that fills in when
state transitions away from thinking. format: ms / s.s / m s.
hidden until the first turn completes.
new POST /cancel-question/{id} resolves a pending operator question
with the sentinel answer '[cancelled]' and fires the usual
HelperEvent::OperatorAnswered so the manager sees a terminal state
and can fall back. uses the same OperatorQuestions::answer path —
no special handling, the manager already has to deal with arbitrary
answer strings.
dashboard renders the cancel as a separate <form> below the main
qform so the answer-merge submit handler on the main form doesn't
inadvertently fire when the operator clicks cancel. confirm dialog
spells out what the manager will see.
ttl-based auto-cancel is still on the todo (would spawn a tokio task
per submitted question).
Write and Edit tool_use rows used to render as the bare file path. now
they're collapsed <details> blocks with the actual change inside —
Write shows every content line prefixed '+', Edit shows old_string as
'-' lines then new_string as '+' lines. summary carries the file path
+ counts ('→ Edit /foo · -3 +5'). lines colored via diff-add /
diff-del / diff-ctx; click to expand the full body.
renderFileWriteEdit returns null for any other tool so the existing
flat-row path (fmtToolUse) is untouched.
retention is a host concern — agents have no business doing their
own cleanup, and a misbehaving harness could skip it. drop
spawn_events_vacuum from both hive-ag3nt and hive-m1nd, drop the
matching Bus::vacuum + EventStore::vacuum methods. new
hive_c0re::events_vacuum module sweeps every existing
agents/<name>/state/hyperhive-events.sqlite on the same hourly
cadence as the broker vacuum. same two-stage delete (older than 7
days, trim to 2000 newest). called from main alongside broker
vacuum.
also: server-side state badge entered into todo.md (today's badge
is derived client-side from sse, fine for idle/thinking but a
state machine that grows compacting/napping wants authoritative
status from the harness).
submitting R3QU3ST SP4WN immediately queues an approval that lands
in the very next list. the form belonged with that list, not at the
top of containers — the agent doesn't exist yet at form time anyway.
docs: claude.md grows operator_questions.rs / events.rs sqlite /
broker vacuum to the file map; web-ui shape lists the actual current
endpoint set (per-agent cancel/compact/history, dashboard tombstone
purge/answer/spawn); live-view section now describes the state
badge, sticky-bottom scroll, history backfill, and the terminal-
embedded prompt with its slash commands; dashboard-action-surface
rewritten around the new six-section page (containers / kept-state /
questions / inbox / approvals / message-flow) and the two-line
container row. new 'persistence + retention' section documenting both
sqlite databases and their vacuum cadences. readme picks up the new
mgr mcp surface (start/restart/ask_operator) + operator-side
features list + ask_operator answer flow.
todo trimmed of shipped items (bigger terminal / sticky scroll /
cancel button / /compact trigger / /cancel command). new entry for
the two-step spawn-with-preconfig flow.
hive_ag3nt::events::Bus replaces its in-memory VecDeque with a sqlite-
backed store at /state/hyperhive-events.sqlite (overridable via
HYPERHIVE_EVENTS_DB). emit() inserts a row; history() reads back the
most recent 2000 events. survives harness restart now — operator reload
mid-investigation no longer wipes the trail.
vacuum runs hourly (immediate first sweep): drop rows older than 7
days, then trim to 2000 newest. two-stage so a quiet agent keeps a
useful tail and a chatty one stays bounded. wired into both
hive-ag3nt and hive-m1nd via spawn_events_vacuum.
if the db open fails (e.g. no /state mount in dev), Bus runs in
no-store mode — events still broadcast, just nothing persisted.
undelivered rows are always kept regardless of age (still in flight).
sweep runs immediately on serve start then every hour. logs row count
when non-zero. keep_secs is hard-coded for now (30 days); can be
config-driven later if a host wants to retain more / less for audit.
drop the one-shot send/recv/kill/start/restart/request-spawn/request-
apply-commit subcommands from both in-container binaries. they were
debug-only — the host admin socket (`hive-c0re ...`) exposes the
same verbs and the manager mcp surface covers the rest from inside
claude. now each binary's --help shows just `serve` and `mcp`,
which are the only commands either is meant to be started with.
removes the `one_shot` helper and the `render` / `check` glue.
new --purge flag on the destroy verb (cli + admin socket + dashboard).
default destroy still keeps /var/lib/hyperhive/{agents,applied}/<name>/
so recreating with the same name reuses prior config + creds.
with --purge, both dirs go too (config history, claude creds, /state/
notes). no undo. dashboard adds a separate PURG3 button with an
explicit confirmation copy; the existing DESTR0Y button keeps the
soft semantics.
claude.md dashboard-action-surface section updated; todo entry
dropped.
new mcp tool on the manager surface that queues a question on the
dashboard and returns the question id immediately. operator submits an
answer via /answer-question/<id>; the dashboard fires
HelperEvent::OperatorAnswered { id, question, answer } into the manager
inbox so the next turn picks it up.
also: fix async-form button stuck on spinner after successful submit
(refreshState skipped re-rendering, so the button was never re-enabled).
