bare set_transient/clear_transient pairs leak the in-memory transient
on task cancellation, panics, or any early return between the two
calls — dashboard then shows the agent stuck in 'rebuilding…'
forever (coder hit this today). add Coordinator::transient_guard
returning a TransientGuard whose Drop clears, and convert every
caller (dashboard lifecycle_action, auto_update::rebuild_agent,
manager_server Update, actions::destroy, actions Spawn task,
migrate phase 4). destroy() now takes &Arc<Coordinator> so it can
hold a guard. existing stuck transients clear on next hive-c0re
restart since transient state is in-memory only.
install_configured now takes an optional notify recipient. on a
non-zero or spawn-failed 'claude plugin install', sub-agents send
the spec + stderr to manager via the hyperhive socket; manager
passes None so it doesn't message itself. boot still proceeds either
way — notification is best-effort.
run_claude now keeps a 20-line stderr ring buffer and bails with it
inline (was just 'exit <status>'). agent serve loop, on Failed (not
PromptTooLong — that's already absorbed by drive_turn's compaction
retry), sends the error body to manager via the normal hyperhive
send. swallows transport errors — failure is already in journald
and the events sqlite. manager-only harness (hive-m1nd) is unchanged
so it doesn't try to notify itself.
claude-code rejects --dangerously-skip-permissions / defaultMode=
bypassPermissions when running as root, which all hyperhive
containers do. revert to the previous explicit allow-list plumbing
(per-flavor list spliced into permissions.allow + --tools enable
list), keep TodoWrite out of the built-in allow set, and keep the
deny list (TodoWrite, WebFetch, WebSearch, Task) as belt-and-braces
in case anything sneaks past the allow gate.
bus-only note made post-mortems require the web UI / events sqlite;
now stderr lines also land in 'journalctl -M <container> -b' alongside
the existing LiveEvent::Note for the dashboard.
socket client now retries connect/IO failures with 2-4-8-16-30s
backoffs (60s total budget). transparent for non-tool callers via
request(); tool handlers go through request_retried() which also
returns the retry count, then annotate_retries() appends a one-line
note to the tool result so claude knows the slow round-trip was a
c0re flicker, not a content failure — avoids burning tokens on an
LLM-level retry.
new hyperhive.claudePlugins NixOS option (list of strings) rendered
to /etc/hyperhive/claude-plugins.json. both hive-ag3nt and hive-m1nd
shell out 'claude plugin install <spec>' for each entry once at
startup before the turn loop opens. failures log a warning but don't
abort boot.
claude-settings.json now sets permissions.defaultMode=bypassPermissions
with a small deny list (WebFetch, WebSearch, Task, TodoWrite). The
per-flavor allow list and --tools / --allowedTools CLI flags are gone
— anything not denied auto-approves. mcp.rs loses ALLOWED_BUILTIN_TOOLS,
builtin_tools_arg, allow_list, allowed_mcp_tools. The extraMcpServers
allowedTools field is parsed for back-compat but no longer wired
anywhere; restrict via permissions.deny instead.
agents weren't being woken with the 'you were rebuilt — check
/state/ for notes, --continue intact' system message after
several recent rebuild surfaces:
- auto_update::rebuild_agent — used by the dashboard rebuild
button, admin-CLI rebuild via lifecycle_action, the startup
rev-scan, AND the new meta-input update batch loop. kick
moves *into* rebuild_agent's success arm so all four
paths benefit. (the dashboard's lifecycle_action extra
closure was already firing kick — now it's a no-op for the
rebuild path since rebuild_agent does it.)
- actions::run_apply_commit — apply-commit approve flow built
+ tagged deployed/<id> but never kicked. add kick on
success with the more specific 'config update applied' hint.
- server.rs::HostRequest::Rebuild — the admin-CLI direct path
calls lifecycle::rebuild bypassing rebuild_agent. add kick
on success.
dashboard's restart / start lifecycle_action extras still
kick via their own closures since they don't route through
rebuild_agent. stop / kill / destroy intentionally don't
kick — there's nothing to wake.
read_meta_inputs() previously only included direct inputs of
meta's root node — so a manager-added 'inputs.mcp-matrix' in
agent-dmatrix's flake.nix never surfaced in the dashboard
panel even though it's a real fetched input that nix can
update.
now: BFS the flake.lock graph from root to depth 2. emits
one MetaInputView per fetched (non-follows) node, names are
slash-paths from root — 'hyperhive', 'agent-coder',
'agent-dmatrix/mcp-matrix', 'hyperhive/nixpkgs', etc. that's
the same syntax 'nix flake update' accepts for transitive
inputs, so the existing POST /meta-update path needs no
nix-side change.
depth limit of 2 keeps the panel readable — deeper transitives
(nixpkgs's own deps etc.) would explode it; bumping a level-2
entry re-fetches its sub-inputs anyway.
POST /meta-update's 'which agents to rebuild' derivation
updated for the slash names: anything under hyperhive/
fans out to all agents (shared base); 'agent-<n>/...' picks
out the agent name from before the first slash.
read_meta_locked_revs (used by the deployed:<sha> chip per
container) split out into its own straight root-input lookup
since the chip only cares about the agent's own input.
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.
regroups the 7 stacked sections into three semantic columns
backed by a CSS grid (single column under 1400px, 3 columns
above). column headers are sticky so vertical scrolling
inside a column doesn't lose context.
- SW4RM (left, slightly wider): containers + kept-state +
spawn-agent form + meta-input update form. all
swarm-mutating operator knobs live here.
- 0PER4T0R 1N (middle): mind-questions + pending approvals.
the two things waiting on operator action.
- M3SS4G3S (right): operator-inbox + msg-flow tail + the
@-mention compose box. broker traffic in one place.
spawn form moves out of renderApprovals into static HTML
under sw4rm; renderApprovals no longer injects it.
cosmetic: per-section h2/divider replaced with smaller cyan
sub-heads + a dashed underline so each column reads as one
cohesive unit instead of seven competing banners. body
max-width grows 70em → 110em to actually use the new
horizontal real estate.
new section 'M3T4 1NPUTS' between approvals and message flow:
one row per input in meta/flake.lock (hyperhive first, then
agent-<n> alphabetically). each row shows the input name, the
first 12 chars of the locked sha, a relative timestamp from
locked.lastModified, and the original.url when available.
checkbox per row; submit button is disabled until at least one
box is checked; submitting confirms then POSTs the selected
names to /meta-update.
backend:
- meta::lock_update(inputs: &[String]) — runs 'nix flake update
<names>' in the meta dir, commits the lock change with a
combined message ('lock update: hyperhive, agent-coder').
preserves the existing META_LOCK serialization. existing
lock_update_for_rebuild / lock_update_hyperhive stay for
their single-input callers.
- POST /meta-update — comma-separated 'inputs' form field
(JS joins checkboxes since axum::Form doesn't natively
decode repeated keys); spawns a background task that runs
the lock update + per-agent rebuild loop. hyperhive
selection fans out to all agents; agent-<n> selection only
rebuilds <n>. each rebuild fires Rebuilt to the manager
exactly like dashboard / admin-CLI / auto-update.
rebuild loop is sequential — auto_update::run too (was
parallel via tokio::spawn). parallel rebuilds collide on
nix-store's sqlite cache ('sqlite db busy, not using cache')
and the meta META_LOCK contention. nix-daemon serializes the
heavy build steps anyway, so this isn't a throughput loss.
HostRequest::Rebuild was the only rebuild path that bypassed
notify_manager. dashboard / auto_update / actions::approve
already emit Rebuilt events on both success + failure, but a
'hive-c0re rebuild <name>' from the host CLI (and the recent
matrix-flake build failure that surfaced in journald) left the
manager in the dark.
mirror auto_update::rebuild_agent's pattern: on success →
Rebuilt{ok:true}, on failure → Rebuilt{ok:false, note=
format!('{e:#}')}. note carries the stderr tail lifecycle::run
collected (the actual nix error: missing prompt file, dep
build failure, etc.), so the manager has enough context to
adjust the agent's agent.nix without ssh-ing to the host.
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 AgentRequest::Wake { from, body } drops a message into
this agent's inbox via the per-agent socket. matrix-style MCP
servers can use it when they receive an external event
(matrix message, webhook, scrape result) to nudge claude
into running a turn. broker.send wakes whatever Recv is
currently long-polling, the harness picks the message up,
formats a wake prompt with the caller's chosen from label
('matrix: new dm', 'webhook: deploy succeeded', etc.).
new `hive-ag3nt wake --from <label> --body <text>` subcommand
on the harness binary so MCP servers can shell out instead of
implementing the line-JSON protocol themselves; body=='-'
reads from stdin for multi-line / quoting-friendly payloads.
identity = socket: anything that can connect to /run/hive/mcp
.sock is implicitly trusted to inject. that's fine because the
bind-mount is the agent's own container; no new auth surface
opens up.
docs/turn-loop.md gets a new 'Waking the agent from inside
the container' section pointing at both paths (CLI + raw
JSON).
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.
lifecycle::GIT_{NAME,EMAIL}, meta::GIT_{NAME,EMAIL}, and the
inline strings migrate.rs uses for its bootstrap commits all
move from 'hive-c0re' / 'hive-c0re@hyperhive' to 'c0re' /
'c0re@hyperhive'. shows up shorter in git log everywhere
(applied + meta repos).
git_tag_annotated planted failed/<id> + denied/<id> as
annotated tags via 'git tag -a' — which produces a git
object and therefore needs user.name + user.email. without a
global git config on the host that fell through to
'fatal: unable to auto-detect email address (got
root@muede-lpt2.(none))' and the tag never landed.
pass the hive-c0re identity inline with -c user.name=… -c
user.email=… (same shape git_commit already uses), so the
applied repo's deny/failure audit tags get planted reliably
without depending on the host user's git config.
