per mara's review on #433, move the gating from the dashboard into
the host so a stopped container's stale on-disk state (rate_limited
sentinel, hyperhive-needs-login, last-turn-stats row, status blob)
never reaches the wire in the first place. when build_all sees
is_running == false:
- needs_login → false
- ctx_tokens / context_window_tokens → None
- rate_limited → false
- status_text / status_set_at → None
static / declared fields (extra_links, deployed_sha,
pending_reminders, needs_update, parent) stay populated regardless
of run state.
extend AgentMeta (both AgentResponse + ManagerResponse) with a
`running: bool` field so get_agent_meta callers can tell whether
the target is up — answers the second half of #432 ("agent meta
should probably show the info that it is not running as well").
read_agent_status_live wraps the existing read_agent_status with
the same is_running gate so the manager/agent socket handlers don't
have to know about sentinel semantics.
format_agent_meta now prints a `running: yes|no` line so claude
sees the run state in plain text alongside hyperhive_rev.
frontend follow-up in the same commit: drop the redundant
`c.running &&` guards on ctx_tokens / status_text in
renderContainers — the backend now guarantees those fields are
absent when the container is stopped, so the existing
truthy-check is sufficient. the `■ not running` badge + icon /
links fetch short-circuits stay (those are pure presentation /
network-noise wins the backend can't address).
CountPendingReminders and ReminderRollup were hardcoded to
MANAGER_AGENT. Both now take agent: Option<String> — None keeps the
current behavior (manager's own), Some(name) returns that agent's
reminder stats. The broker functions already take an agent name, so
this is a thin wire-protocol change. Callers (web UI stats page,
post-turn counts) pass None.
Closes#122
GetLooseEnds now takes agent: Option<String>:
- None = manager's own loose ends (default; the bug fix)
- Some("*") = hive-wide view (every approval/question/reminder)
- Some("name") = that agent's loose ends
The get_loose_ends MCP tool exposes this as an optional agent arg, so
the manager can still scan the whole swarm on demand. The web UI and
post-turn counts pass None (manager's own).
hive_wide returns ALL agents' reminders and questions, causing other
agents' reminders (e.g. triage) to appear on the manager's web page
and in the get_loose_ends MCP tool. The MCP tool spec says it shows
your own pending items — switch to for_agent(MANAGER_AGENT) which
includes all approvals (manager is sole submitter), questions where
the manager is asker/target, and only the manager's own reminders.
Fixes#118
Surface reminder activity statistics (scheduled, delivered, pending counts)
for each agent over configurable time windows. Needed by the per-agent
stats page to display reminder metrics.
Adds:
- ReminderStats struct and ReminderRollup request/response variants
- Broker::reminder_rollup_for(agent, since_secs) method
- Agent and manager socket handlers for the new RPC
- SocketReply mapping for response conversion
on startup (and after every applied-repo ref mutation) core pushes
each agent's hive-c0re-owned applied repo — main plus every
proposal/approved/building/deployed/failed/denied tag — to
agent-configs/<name> on the local forge. the org is private and
agents are not members, so core is the only principal that can read
it.
the tokenised push url is passed inline, never stored as a named
remote: the applied repo is bind-mounted read-only into the manager,
so a token in .git/config would leak the core admin credential to an
agent.
push_config is best-effort at every site (ensure_all, spawn,
approve, deny, submit) — a missing or down forge never blocks a
deploy.
new sqlite table at /state/hyperhive-turn-stats.sqlite on each
agent's state dir. one row per claude turn captures identity
(model, wake_from, result_kind), timing (started/ended_at,
duration_ms), cost (input/output/cache_read/cache_creation token
counts), behaviour (tool_call_count + per-tool breakdown JSON),
and post-turn snapshot metrics (open_threads_count,
open_reminders_count).
wire additions:
- AgentRequest/ManagerRequest::CountPendingReminders +
Broker::count_pending_reminders_for(agent)
- Bus::observe_stream + take_tool_calls — pumps the existing
stdout stream-json, picks out tool_use blocks, accumulates per
turn. bin loops fold the breakdown into each row.
- TurnStats::open_default + TurnStatRow + record() — best-effort
inserts; failures log + don't block the harness.
both ag3nt and m1nd bins capture started_at + duration via
Instant::elapsed, fetch open-thread + reminder counts from
hive-c0re via the existing socket (post-turn, best-effort), and
record one row at turn_end. record_kind splits ok / failed /
prompt_too_long; failures carry the error message in note.
todo entries for host-side vacuum sweep + reading the table back
into agent/dashboard badges.
questions pane now shows both operator-targeted threads
(target IS NULL) and agent-to-agent threads (target = some
agent). filter chips above the list: all / @operator / @peer /
per-participant. peer rows get a mauve left rule + a 0V3RR1D3
button that POSTs the same /answer-question endpoint
(OperatorQuestions::answer already permits the operator as
answerer on any target).
wire changes: OperatorQuestions gains pending_all +
recent_answered_all; QuestionAdded + QuestionResolved events
carry target: Option<String>; emit sites drop their
target.is_none() guard. answered-history rows show the
answerer prefix so override answers are auditable at a glance.
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.
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 boilerplate wraps agent.nix as a sub-module + passes every
flake input (minus self) through to it via _module.args.flake
Inputs. manager edits the inputs block of flake.nix to pull in
out-of-tree flakes (MCP servers etc.) and references them in
agent.nix as flakeInputs.<name>.packages.${pkgs.system}.default
— the new input's pinned sha lands in the agent's own flake
.lock (already tracked + part of the proposal flow), and
transitively rolls up into meta's lock.
migrate's MODULE_FLAKE_MARKER swaps to _module.args.flakeInputs
so existing agents on the old 'nixosModules.default = import
./agent.nix' template get re-rendered onto the new shape on
next hive-c0re start.
manager_server's flake.nix tamper-check goes away — the build
path's failed/<id> annotated tag already provides the safety
net when a manager edit breaks the flake; enforcing 'no
flake.nix edits at all' was overly strict (blocks the inputs-
addition pattern that's the whole point of this change).
manager prompt updated with a worked example for adding an
MCP-server flake input + wiring it through agent.nix.
new AgentRequest::AskOperator + AgentResponse::QuestionQueued on
the per-agent socket — same shape as the manager flavor, agent
gets the same wire surface (still uses the same operator_questions
table). agent_server::dispatch wires AskOperator through coord
.questions.submit(agent, ...) so the row's asker is the sub-agent
name; the ttl watchdog already in manager_server gets shared and
spawn_question_watchdog goes pub.
answer routing: operator_questions::answer now returns (question,
asker). post_answer_question + post_cancel_question + the watchdog
fire OperatorAnswered through new coord.notify_agent(asker, event)
instead of always notify_manager — the event lands in whichever
agent originally asked. notify_manager is now a thin wrapper.
agent socket plumbing: agent_server::start takes Arc<Coordinator>
instead of Arc<Broker> so dispatch has access to questions +
notify path; coordinator::{register_agent,ensure_runtime} take
self: &Arc<Self>. mcp::AgentServer grows the ask_operator tool;
allowed_mcp_tools(Agent) adds it; prompts/agent.md replaces the
'message the manager to ask the operator' guidance with the
direct tool description.
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.
submit_apply_commit (1) queues the approval row, (2) git-fetches
the manager-supplied sha from proposed into applied, pins it as
refs/tags/proposal/<id>, (3) persists the resolved sha on the
row via approvals.set_fetched_sha. from this point on the
proposal is immutable from the manager's perspective: amends
or force-pushes in proposed do not change what hive-c0re will
build. fetch failures mark the row failed and surface the error
to the manager so a phantom pending entry can't linger.
