docs: update for recent commits (rate limiting, reply threading, screen, auto-reset, two-step spawn, ctx chip)

This commit is contained in:
iris 2026-05-20 16:41:43 +02:00
parent a024ca65c0
commit 69604407a9
4 changed files with 99 additions and 19 deletions

View file

@ -47,6 +47,15 @@ step — the operator just sees the name. On approve, hive-c0re
creates the container in a background task while the dashboard creates the container in a background task while the dashboard
shows a spinner. shows a spinner.
`InitConfig` approvals are the first step in a two-step spawn
flow. On approve, hive-c0re seeds the proposed config repo with
a default `agent.nix` template and sends the manager
`HelperEvent::ConfigReady { agent }`. The manager then reviews,
edits, and commits the template before calling `request_spawn`
to proceed to a Spawn approval. This gives the manager (and
operator) an explicit review gate on the initial configuration
before any container is created.
## Meta flake ## Meta flake
The hive-c0re-owned repo at `/var/lib/hyperhive/meta/` The hive-c0re-owned repo at `/var/lib/hyperhive/meta/`
@ -341,6 +350,10 @@ regular claude turn so the manager can react. Variants
the operator. the operator.
- `LoggedIn { agent }` — sub-agent just completed login. Manager - `LoggedIn { agent }` — sub-agent just completed login. Manager
often greets the agent on this event. often greets the agent on this event.
- `ConfigReady { agent }` — a new agent's proposed config repo was
just seeded (post-`InitConfig` approval). The manager can now
edit `/agents/<agent>/config/agent.nix`, commit the changes,
and submit `request_spawn` to create the container.
- `NeedsUpdate { agent }` — sub-agent's recorded flake rev is - `NeedsUpdate { agent }` — sub-agent's recorded flake rev is
stale. Manager calls `update(name)` to rebuild — idempotent, stale. Manager calls `update(name)` to rebuild — idempotent,
no approval required. no approval required.

View file

@ -9,7 +9,9 @@ Where state lives, what survives what, and how it's bounded.
Three tables, all in one file: Three tables, all in one file:
- `messages` — every inter-agent / operator-bound message. - `messages` — every inter-agent / operator-bound message.
`sender / recipient / body / sent_at / delivered_at`. `sender / recipient / body / sent_at / delivered_at / acked_at /
in_reply_to`. `in_reply_to` links a reply to its parent row id;
the dashboard and per-agent inbox render these as threaded rows.
- `approvals` — the queue. `agent / kind (apply_commit | spawn) / - `approvals` — the queue. `agent / kind (apply_commit | spawn) /
commit_ref / requested_at / status / resolved_at / note`. commit_ref / requested_at / status / resolved_at / note`.
- `operator_questions``ask` / `answer` queue (despite the - `operator_questions``ask` / `answer` queue (despite the
@ -72,6 +74,18 @@ No host-side vacuum yet — tracked as forge issue
[#10](http://localhost:3000/hyperhive/hyperhive/issues/10) [#10](http://localhost:3000/hyperhive/hyperhive/issues/10)
(target retention ~90 days, age-only sweep like events_vacuum). (target retention ~90 days, age-only sweep like events_vacuum).
### `/state/hyperhive-rate-limited` (per agent)
Sentinel file written by `Bus::emit_status("rate_limited")` when the
harness detects a 429 / rate-limit response from the Claude API, and
removed when the retry sleep expires (any subsequent status emit
clears it). The file's presence is checked by hive-c0re's
`container_view::is_rate_limited` on each `build_all` sweep (~10s) to
populate `ContainerView.rate_limited` for the dashboard. Survives a
harness restart (the Bus reads it back at boot and restores the flag),
so the badge remains accurate if hive-c0re restarts while the harness
is mid-sleep.
### `/state/hyperhive-model` (per agent) ### `/state/hyperhive-model` (per agent)
Single-line text file holding the claude model name currently Single-line text file holding the claude model name currently

View file

@ -20,7 +20,12 @@ Each agent harness (`hive-ag3nt serve` or `hive-m1nd serve`) runs:
`LiveEvent::Stream(value)`. Pump stderr as `Note`. `LiveEvent::Stream(value)`. Pump stderr as `Note`.
6. Wait for claude to exit. Compaction is two-pronged — *reactive* 6. Wait for claude to exit. Compaction is two-pronged — *reactive*
on `Prompt is too long` and *proactive* on a context watermark on `Prompt is too long` and *proactive* on a context watermark
(see [Compaction](#compaction) below). (see [Compaction](#compaction) below). **Rate-limit detection**:
if stdout contains `429` or `rate_limit` markers, the harness
sets the `rate_limited` sentinel (`Bus::emit_status("rate_limited")`),
sleeps `HIVE_RATE_LIMIT_SLEEP_SECS` (default 300), then retries.
The dashboard and per-agent page show a `⊘ rate limited` badge
while the harness is parked.
7. Emit `LiveEvent::TurnEnd { ok, note }`. Sleep `poll_ms` to avoid 7. Emit `LiveEvent::TurnEnd { ok, note }`. Sleep `poll_ms` to avoid
tight loops on transient failures. tight loops on transient failures.
@ -78,6 +83,20 @@ best-effort — a failed checkpoint turn or `/compact` is surfaced as a
`Note` but never fails the turn that already succeeded. The operator `Note` but never fails the turn that already succeeded. The operator
can also force a compaction any time via `/api/compact`. can also force a compaction any time via `/api/compact`.
- **Auto session-reset** — a third path that fires when both
conditions hold: context is ≥ a watermark (`HIVE_AUTO_RESET_WATERMARK_TOKENS`,
default `100_000`) AND the time since the last turn exceeds the
assumed prompt-cache TTL (`HIVE_CACHE_TTL_SECS`, default `300`).
Claude's prompt cache lives ~5 minutes; if the cache is already
cold, resuming with `--continue` pays the full re-upload cost of
the current context with no benefit over starting fresh. So:
`drive_turn` injects one `AUTO_RESET_CHECKPOINT_PROMPT` notes turn
("flush state to files, cache is cold") then arms
`Bus::take_skip_continue()` for the real turn — the next turn runs
without `--continue`, starting a fresh session. Unlike proactive
compaction the session is dropped entirely, not compacted. Set
`HIVE_AUTO_RESET_WATERMARK_TOKENS=0` to disable.
The child runs with `cwd = /state` (when the bind exists; falls The child runs with `cwd = /state` (when the bind exists; falls
back to the parent's cwd in dev), so any relative path in a tool back to the parent's cwd in dev), so any relative path in a tool
call (`Read foo.md`, `Bash ls`, `Write notes.md`) lands in the call (`Read foo.md`, `Bash ls`, `Write notes.md`) lands in the
@ -126,9 +145,11 @@ it as a stdio child via `--mcp-config`. The hyperhive socket name is
### Sub-agent tools ### Sub-agent tools
- `send(to, body)` — message a peer (logical agent name), another - `send(to, body, in_reply_to?)` — message a peer (logical agent
agent, or the operator (recipient `operator`, surfaces in the name), another agent, or the operator (recipient `operator`,
dashboard inbox). surfaces in the dashboard inbox). Optional `in_reply_to: i64`
links this message to a prior message id for thread rendering
in the dashboard message flow and the per-agent inbox.
- `recv(wait_seconds?, max?)` — drain inbox messages. Without - `recv(wait_seconds?, max?)` — drain inbox messages. Without
`wait_seconds` (or with `0`) returns immediately, a cheap `wait_seconds` (or with `0`) returns immediately, a cheap
"anything pending?" peek. Positive value parks the turn up "anything pending?" peek. Positive value parks the turn up
@ -161,7 +182,9 @@ it as a stdio child via `--mcp-config`. The hyperhive socket name is
this agent's own inbox at a future time (sender shows as this agent's own inbox at a future time (sender shows as
`reminder`). Large payloads spill to `reminder`). Large payloads spill to
`/agents/<self>/state/reminders/` with the inbox message a `/agents/<self>/state/reminders/` with the inbox message a
short pointer. short pointer. Each agent's pending-reminder count is capped
(default 50, override via `HIVE_REMIND_MAX_PENDING_PER_AGENT`);
scheduling a new one fails if the cap is already hit.
- `whoami()``{ name, role, pronouns, hyperhive_rev }` for - `whoami()``{ name, role, pronouns, hyperhive_rev }` for
self-identification without scraping the system prompt. self-identification without scraping the system prompt.
@ -209,8 +232,17 @@ meta's.
### Manager tools (in addition to send/recv) ### Manager tools (in addition to send/recv)
- `request_spawn(name)` — queue a Spawn approval for a brand-new - `request_init_config(name, description?)` — first step of a
sub-agent (≤9 char name). Operator approves on the dashboard. two-step spawn. Queues an `InitConfig` approval (≤9 char name);
on operator approve, hive-c0re seeds the proposed config repo
with a default `agent.nix` template and sends the manager a
`HelperEvent::ConfigReady { agent }`. The manager then edits
`agent.nix`, commits the changes, and calls `request_spawn`.
Fails if a proposed repo for this name already exists.
- `request_spawn(name)` — second step of a two-step spawn. Queues
a Spawn approval; requires the proposed config repo to exist
(from a prior approved `request_init_config`). Operator approves
on the dashboard to create the container.
- `kill(name)` — graceful stop. No approval required. - `kill(name)` — graceful stop. No approval required.
- `start(name)` — start a stopped sub-agent. No approval. - `start(name)` — start a stopped sub-agent. No approval.
- `restart(name)` — stop + start. No approval. - `restart(name)` — stop + start. No approval.

View file

@ -150,10 +150,14 @@ the previous process's socket release resolves itself.
Two-line layout (`assets/app.js::renderContainers`): Two-line layout (`assets/app.js::renderContainers`):
- Line 1: agent name (link → new tab), m1nd/ag3nt chip, `needs - Line 1: agent name (link → new tab), m1nd/ag3nt chip, status
login` / `needs update` warning badges, in-flight ` badges — `⊘ rate limited` (red, while the harness is parked
after a 429), `needs login`, `needs update` — in-flight `◐
pending-state…` pill (replaces buttons during start / stop / pending-state…` pill (replaces buttons during start / stop /
restart / rebuild / destroy), container name + port. restart / rebuild / destroy), container name + port, and a
`ctx · Nk` chip showing the agent's last-turn context size
(from `ContainerView.ctx_tokens`, read from the turn-stats
sqlite on each `build_all` sweep; absent until the first turn).
- Line 2: action buttons — `↻ R3BU1LD` always, `DESTR0Y` + `PURG3` - Line 2: action buttons — `↻ R3BU1LD` always, `DESTR0Y` + `PURG3`
on sub-agents, `↺ R3ST4RT` + (sub-agents) `■ ST0P` when running, on sub-agents, `↺ R3ST4RT` + (sub-agents) `■ ST0P` when running,
`▶ ST4RT` when stopped. Buttons dim + disable while a transient `▶ ST4RT` when stopped. Buttons dim + disable while a transient
@ -296,9 +300,12 @@ Wire vocabulary on `/dashboard/stream` (kind tag is in the JSON
payload): payload):
- `sent` / `delivered` — broker traffic, mirrored from the - `sent` / `delivered` — broker traffic, mirrored from the
intra-process channel by a forwarder task. Used by the intra-process channel by a forwarder task. Both carry `id: i64`
message-flow terminal renderer and the operator-inbox (the broker row id) and `in_reply_to: Option<i64>` for thread
derived state. rendering. The dashboard message-flow terminal renders reply
rows with a `↳ reply` tag that scroll-highlights the parent
row on click. Used by the message-flow terminal renderer and
the operator-inbox derived state.
- `approval_added` (id, agent, approval_kind, sha_short, diff, - `approval_added` (id, agent, approval_kind, sha_short, diff,
description) / `approval_resolved` (id, agent, approval_kind, description) / `approval_resolved` (id, agent, approval_kind,
sha_short, status, resolved_at, note, description) — pending sha_short, status, resolved_at, note, description) — pending
@ -355,8 +362,10 @@ Layout, top to bottom:
badge + last-turn timing + cancel-turn button + new-session badge + last-turn timing + cancel-turn button + new-session
button. Every chip carries a `title=...` tooltip with the button. Every chip carries a `title=...` tooltip with the
detailed breakdown. detailed breakdown.
- Alive badge: `● alive` (green) / `◌ needs login` (amber) / - Alive badge: `● alive` (green) / `⊘ rate limited` (red, while
`◌ logging in` / `○ offline` / `… connecting`. Driven by the harness is parked after a 429 — clears automatically when
the sleep expires) / `◌ needs login` (amber) / `◌ logging in` /
`○ offline` / `… connecting`. Driven by
`LiveEvent::StatusChanged`; replaces the old "harness alive `LiveEvent::StatusChanged`; replaces the old "harness alive
— turn loop running" paragraph so the state row carries — turn loop running" paragraph so the state row carries
every reachability signal. every reachability signal.
@ -401,7 +410,9 @@ Layout, top to bottom:
updates from SSE; no periodic refresh timer runs. updates from SSE; no periodic refresh timer runs.
- Inbox `<details>` block (collapsed): `inbox · N` — last 30 - Inbox `<details>` block (collapsed): `inbox · N` — last 30
messages addressed to this agent, fetched via messages addressed to this agent, fetched via
`AgentRequest::Recent { limit: 30 }`. (Separate from `AgentRequest::Recent { limit: 30 }`. Reply messages (those
with a non-null `in_reply_to`) are indented and prefixed with
`↳ reply ·` in amber. (Separate from
`AgentRequest::Recv { wait_seconds, max }` which the harness `AgentRequest::Recv { wait_seconds, max }` which the harness
uses internally to long-poll the broker.) uses internally to long-poll the broker.)
- Loose-ends `<details>` block: `loose ends · N` — questions, - Loose-ends `<details>` block: `loose ends · N` — questions,
@ -506,12 +517,22 @@ shaped).
- `POST /api/new-session` — arm a one-shot for the next turn to - `POST /api/new-session` — arm a one-shot for the next turn to
drop `--continue`. Emits a `LiveEvent::Note`. drop `--continue`. Emits a `LiveEvent::Note`.
- `GET /events/history` — replay buffer for the terminal. - `GET /events/history` — replay buffer for the terminal.
- `GET /screen` — VNC viewer page (minimal RFB-over-WebSocket
renderer). Only accessible when `hyperhive.gui.enable = true`
in the agent's `agent.nix`; the harness shows a 🖥 screen link
in the state row when `gui_vnc_port` is present.
- `GET /screen/ws` — raw RFB byte relay: proxies WebSocket
frames to the weston VNC server at `127.0.0.1:<vnc_port>`.
Transparent to any RFB variant. VNC port comes from
`/etc/hyperhive/gui.json` (written by the weston startup
script in `weston-vnc.nix`).
Bus events (new vocabulary on `/events/stream`): Bus events (new vocabulary on `/events/stream`):
- `status_changed { status }``online` / - `status_changed { status }``online` / `rate_limited` /
`needs_login_idle` / `needs_login_in_progress`. Drives the `needs_login_idle` / `needs_login_in_progress`. Drives the
alive-badge. alive-badge. `rate_limited` is set when the harness detects a
429 response and cleared when the retry sleep expires.
- `model_changed { model }` — drives the model chip. - `model_changed { model }` — drives the model chip.
- `token_usage_changed { ctx: TokenUsage, cost: TokenUsage }` - `token_usage_changed { ctx: TokenUsage, cost: TokenUsage }`
— drives the ctx + cost badges. Emitted from — drives the ctx + cost badges. Emitted from