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.
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.
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 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 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.
new NixOS module option services.hive-c0re.operatorPronouns
(free text, default 'she/her', example 'they/them'). hive-c0re
takes it as a CLI flag (--operator-pronouns, lib.escapeShellArg'd
in the systemd unit), stores it on Coordinator, threads it into
the meta flake's mkAgent so each agent's systemd service gets
HIVE_OPERATOR_PRONOUNS set. the harness reads the env at boot
and substitutes {operator_pronouns} into the agent / manager
system prompt alongside {label}. nix string is escaped against
backslash + double-quote so non-ascii / quoted values
round-trip safely. prompt addendum: both agent.md and
manager.md mention the operator's pronouns up front so claude
uses them naturally in third-person reference. propagates on
next ↻ R3BU1LD (meta lock bump, no per-agent approval).
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.
new TurnFiles bundle (mcp_config + settings + system_prompt +
flavor) materialised once per harness boot, passed to drive_turn
and compact_session alike. operator-initiated /compact now uses
the exact same session shape as a normal turn — same MCP
surface, same allowed tools, same role prompt — only the stdin
payload differs (/compact vs the wake-up body). web_ui's
AppState carries the TurnFiles instead of (label + socket +
flavor + ad-hoc file writes per click). bin/hive-ag3nt and
bin/hive-m1nd prepare TurnFiles before spawning the web UI and
pass them to both surfaces. web_ui::Flavor folds into a type
alias for mcp::Flavor — no two-stage enum mapping.
removes ClaudeMode + the run_claude variant fork (system prompt
was Option, mcp args were skipped on Compact). dead 'mode'
plumbing gone.
every claude invocation now runs with current_dir set to
/state — relative paths in tool calls (Read notes.md, Bash ls,
Write blob) land in the agent's durable bind-mounted dir
instead of the harness's systemd cwd. /state is RW + survives
destroy/recreate so this matches where the agent is told to
keep notes anyway. dev/test setups without the bind silently
fall back to the parent cwd.
bus carries a one-shot AtomicBool armed by POST
/api/new-session (or the /new-session slash command). next
turn drops --continue, starting a fresh claude session; the
flag clears automatically so subsequent turns resume normal
behavior. /compact still always uses --continue — compacting
a non-existent session is a no-op anyway.
per-agent page grows an ↻ new session button next to the
cancel-turn one (always visible, amber, confirms before
posting since dropping --continue context isn't reversible).
slash-command surface picks up /new-session for parity with
the button. note row emitted on the live feed both at arm-
time and again when the turn actually consumes the flag, so
the operator can confirm it landed.
agent.nix becomes a plain NixOS module function — flake.nix is
fixed boilerplate the manager mustn't edit; meta flake at /meta/
owns the wrapper. proposed repos ship with an 'applied' remote
pre-wired, so 'git fetch applied' / 'git log applied/main' /
'git show applied/refs/tags/deployed/<id>' all just work without
constructing paths by hand. /meta/ exposes the system-wide
deploy log (git log /meta) + flake.lock for cross-agent sha
introspection.
manager prompt: explain that arbitrary files now travel with
the proposal, document the /applied/<n>/.git RO mount and the
tag scheme (git show applied/deployed/<id> etc.), call out
that applied/main only advances on deployed so a failed build
isn't terminal. approvals.md: drop the old per-agent
applied.git phrasing in favour of the single /applied RO
bind, mention both manager binds together. claude.md
scratchpad flips from in-flight to just-landed.
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).
send was truncating to 80 chars in the tool_use row, hiding
anything past the first sentence. now renders as a collapsed
<details> like Write/Edit — summary still shows the recipient +
headline (so the operator can scan), expanding reveals the full
body unchanged.
recv side was already covered: the wake prompt shows the full
incoming body, and explicit recv() tool_result rows expand to
the full text via the existing collapsed-results path.
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'.
AgentRequest::Recv and ManagerRequest::Recv grow an optional
wait_seconds field (default None → 30s, capped at 60s server-side).
agent_server / manager_server clamp via recv_timeout(). MCP tool
schemas advertise the param so claude can pick its own poll window
— useful when an agent wants to throttle wakes without entering a
distinct nap state.
both harness loops still pass None, keeping the existing 30s
default behaviour for system-level Recvs.
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.
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).
operator hit 'Address already in use (os error 98)' on a harness
restart — the new harness raced the old socket's release. add a
bind_with_retry helper that backs off (250ms doubling, capped at
2s, 12 tries ≈ 22s total) on AddrInUse before giving up. applied
to both the per-agent web UI and the hive-c0re dashboard.
proper fix would be SO_REUSEADDR via socket2 but retry covers the
TIME_WAIT case fine and keeps the dep count down. Other bind errors
still fail immediately (port permission, fd exhaustion).
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.
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.
five POST handlers (post_kill / post_restart / post_start / post_rebuild)
were all repeating the same boilerplate: strip prefix, set_transient,
call lifecycle::X, clear_transient, match the result. extract one
helper that takes the transient kind, error-message verb, the work
body, and an optional 'on success' tail (used by kill to also
unregister + emit HelperEvent::Killed). each handler shrinks to a
single lifecycle_action(..) call. zero behavior change.
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).
new POST /api/compact on the per-agent web UI: spawns
turn::compact_session in the background so the http handler returns
immediately. claude runs '/compact' over the persistent --continue
session; output streams into the live panel like any other turn.
slash command /compact wired to the new endpoint. SLASH_COMMANDS list
now lists all four (/help /clear /cancel /compact). postCancelTurn +
postCompact share a postSimple() helper.
deliberately not gated against an in-flight turn — claude's own
session lock will reject a concurrent compact and the failure
surfaces as a Note in the live panel.
ask_operator now accepts a multi: bool. when true and options is
non-empty, the dashboard renders the choices as checkboxes — operator
picks any subset, answer comes back as a ', '-joined string. when
false (default), options are radio buttons.
independent of multi, a free-text input ('or type your own…') is
always rendered alongside options so the operator is never trapped
by an incomplete list. submit merges checked options + free text into
the single 'answer' field.
schema migration: operator_questions grows a multi INTEGER column
with a one-shot ALTER TABLE on open. backward compatible — old rows
default to 0 (not multi).
prompt + mcp tool description updated; existing dashboard css for
.qform was rewritten around the new vertical layout.
new POST /api/cancel on the per-agent web UI: shells out
pkill -INT claude (procps added to harness-base.nix). emits a Note
on the bus so the operator sees the cancel landed; state goes back
to idle when run_claude wakes and emits TurnEnd as usual.
frontend:
- /cancel slash command in the terminal input
- ■ cancel turn button in the state row, visible only while
state === 'thinking' (driven from the same SSE-based state
machine). disabled briefly during the POST.
claude gets SIGINT (not TERM) so it flushes anything in-flight and
emits a final result row before exiting.
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.
new badge between the status line and the terminal. shows current
state with a glyph + label + age suffix (e.g. '🧠 thinking · 12s').
state transitions are driven from existing SSE turn_start/turn_end —
no harness changes needed. on page load, history backfill detects an
in-flight turn (turn_start without matching turn_end) and starts in
thinking. state-just-changed flash kicks in on each transition. age
timer ticks client-side every 1s.
compacting/napping states will be added when /compact and nap land —
their slots are reserved in the state enum, just unused for now.
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 rows no longer yank the view if the operator is scrolled up.
threshold for 'near bottom' is 48px. when not near bottom, an amber
'↓ N new' pill appears in the bottom-right of the terminal-wrap;
clicking it jumps to bottom. scrolling back near bottom clears the
counter. backfilled (history-replay) rows always scroll to bottom
since the operator hasn't started reading yet.
terminal height is now min(72vh, 60em) instead of a 32em strip — on a
1080p screen that's ~3x more visible lines. body max-width raised
to 110em so a wide window doesn't waste the available width on the
margin.
intercept any line starting with / before sending it to the agent inbox.
two commands today:
- /help — render command list locally
- /clear — wipe the local terminal view (server-side event history kept,
so a page reload restores it)
unknown /xxx surfaces an error row instead of being silently sent. tab
on a /prefix cycles through matching command names. submit-hint
mentions /help so the operator can discover it.
scaffolding for the bigger commands (/compact /cancel /model) is in
place — adding them later is a switch arm plus harness work.
swap the single-line <input> for an auto-growing <textarea>. enter
submits, shift+enter newlines, ime composition respected (skip submit
while isComposing). height caps at ~12em then scrolls. submit-hint
updates to '↵ send · ⇧↵ newline'. async-form handler now also clears
textareas on success.
agent terminal-wrap + dashboard msgflow get a translucent bg with
backdrop-filter blur+saturate so page-bg glow softens behind them.
new rows in the live panel and the dashboard message flow fade in
with a 4px slide-up. unread badge pulses; pending-operator-questions
section pulses its glow. history-backfilled rows skip the animation
(.no-anim) so the page doesn't stagger 100 fade-ins on load.
new manager tools mcp__hyperhive__{start,restart} that delegate to the
existing lifecycle::start / lifecycle::restart on the host. kill was
already at the manager's discretion; rounding out start + restart for
parity so day-to-day container care doesn't have to round-trip through
the operator.
guard: refuse self-targeting on kill/start/restart — the manager would
just be cutting its own legs. spawn (request_spawn) and config changes
(request_apply_commit) still go through the approval queue, since those
are the actual gate. prompt + claude.md updated to make the boundary
explicit. kill now also emits HelperEvent::Killed (it didn't before).
agent page restructure:
- send form moves into the terminal panel as a prompt-style row beneath
the live tail (status line stays above so it still reads as a header).
- live panel + prompt share a single bordered 'terminal-wrap' box.
- harness-alive / login-state status lines drop their decorative ascii
bookends; just a leading dot/glyph remains.
- banner gradient is now a real css gradient with a shimmer animation
toggled by an .active class. turn_start adds it, turn_end removes it.
dashboard side mirrors this: each broker sse event nudges a 4s
shimmer window.
- dashboard container rows drop their static ▓█▓▒░ / ▒░▒░░ glyph
prefixes; the role chips already disambiguate m1nd vs ag3nt.
- empty-state placeholders drop the ▓ bookends.
terminal pre-fill: hive-ag3nt::events::Bus grows a 500-event ring
buffer; new GET /events/history endpoint returns it. The agent JS
fetches history before opening the SSE stream so opening the page mid-
turn shows the last N events instead of a blank panel. The replay
walks turn_start/turn_end pairs to seed the banner-active state
correctly if a turn was still open.
