docs/swarm/README.md gets the routes, the revision, the apply semantics
and the stopped-agent behaviour; the persistence doc points there from
the AGENTS.md entry. The swarm-controller, swarm-controller-api and
swarmctl READMEs and the repo map in AGENTS.md list the new bodies and
routes. docs/tools/swarmctl-cli.md is regenerated for
`swarmctl agent agents-md`, whose help text loses two passive phrasings
vale flags.
A subagent's terminal opened directly showed nothing until the subagent
published again: the relay was a core subscription, though its rows sit
in term-sub-<agent> for 24 hours. It now goes through the agent route's
replay-then-tail, so it opens with the subagent's newest 100 rows and
resumes after Last-Event-ID.
- term_stream.rs: the replay takes a stream name and a filter subject
instead of an agent, and `replay_or_live` (replay, else the live core
subscription) is the one fn both routes call. When the filter is one of
several subjects in the stream, a fresh reader's consumer starts at the
oldest row and drops all but the newest REPLAY_ROWS it counts as
pending, since the stream's newest sequences may belong to sibling
subagents. A single-subject stream (term-main-<agent>) picks its start
with replay_start exactly as before. Tests for both subagent cases.
- subagent_term.rs: the relay calls replay_or_live on the subagent's
subject in term-sub-<agent> and reads Last-Event-ID; module doc and
OpenAPI text no longer say "live only".
- main.rs: the handler test passes the new headers argument.
- swarm-queue-client agent_term.rs: replay_consumer_config takes the
filter subject instead of the agent.
- swarm-queue-client subagent_term.rs: consumer_create_grant, the
extended CONSUMER.CREATE form with a subagent subject as filter.
- swarm-nats-auth policy.rs: the controller holds that grant; the agent
grant's `$SWARM.term.*` filter is two tokens short of a subagent
subject, and the test that refused it now admits it.
- docs/swarm/ui.md, README.md: a subagent terminal opens with its newest
rows.
Fixes#5527
Pick agents from a grid of their icons (running or all), type the text, send.
The page posts the names and the text to the controller and shows what
happened to each agent, with a retry that selects just the ones that failed.
The selection rules and the controller's answer are read by plain functions
with tests.
Claude Code (>= 2.1.277) and opencode both read AGENTS.md, but Claude
Code reads it only when no CLAUDE.md exists in its cwd or above. So
this is a plain rename with no CLAUDE.md stub left behind.
- hive-agent/src/agents_md_migrate.rs: new. At harness start, before
the first turn, renames state/CLAUDE.md to state/AGENTS.md when only
the former exists; logs an error naming both paths when both exist
and touches neither; does nothing otherwise. Idempotent.
- hive-agent/src/main.rs: calls it in serve_main; checkpoint prompt
and a comment name AGENTS.md.
- hive-agent/src/claude_md_watch.rs: the size watch reads AGENTS.md;
todo text, doc comments and tests follow. Module name, todo
subsystem key ("claude_md") and metric name
(hyperhive.agent.claude_md.lines) are unchanged so existing todo
rows and dashboard history carry over.
- hive-agent/src/turn.rs, hive-agent/prompts/system.md: prompts tell
the agent its file is AGENTS.md.
- hive-agent/src/{otel_turn_metrics,stats}.rs,
frontend/packages/agent/src/stats.js, hive-subagent-mcp/src/*.rs:
comments and a tool parameter description naming the agent's file.
- nix/host-modules/swarm-grafana/dashboards/agents.json: panel title
and description.
- claude-plugins skills claude-subagents, state-hygiene: they mean the
agent's own state file.
- CLAUDE.md -> AGENTS.md at the repo root; docs/crates/README.md link
(checked by check-doc-refs.sh), hive-c0re/README.md,
.prettierignore and the nix/sources.nix comment follow.
- docs/: every prose mention of the agent's file; persistence.md
documents the boot-time rename, claude-invocation.md the shadowing.
Fixes#5509
The swarm UI's broadcast page (#5524) needs the controller to do the
fan-out, so POST /api/agents/broadcast takes {agents, body} and answers
200 with {results: [{agent, sent, reason?}]} in request order.
- agent_input.rs: the single-agent send is now send_one, which both
routes call; the single route maps its outcome to the same statuses
and texts as before. The broadcast validates the whole request first
(sender, empty body, empty or duplicated agents, more than 64, a name
outside the roster), then sends up to 16 at once with the single
route's no-responders window.
- main.rs: wires the route.
- docs/swarm/ui.md: describes the route next to the single-agent one.
An N running subagents badge opens a list of the agent's subagents, each a
link to its terminal, so you can switch without going back to the agents page.
A subagent counts as running when it published a row in the last 15 minutes;
the quiet ones are listed below it, dimmed. The list under the preview and the
menu now share one fetch hook and one definition of running.
/builds lists the builder's recent builds newest first, one card each with how
it ended, and opens a failed build's nix tail. /builds?run=<id> opens that
build's card and scrolls to it. The swarm-builder commit status now links
there instead of to the raw JSON record.
The forge and matrix containers belong to the services host, not to a
hive. hive-priv's container-name validator still accepted hive-forge and
hive-matrix for WriteNspawnFlags, WriteResourceLimits and
RemoveServiceDropin; hive-c0re only ever sends h-<agent> names there.
- hive-priv-sock/src/lib.rs: drop SIBLING_CONTAINERS, its only user was
the validator, and its test.
- hive-priv/src/main.rs: the validator accepts only h-<name> and returns
the logical name, so write_resource_limits loses its non-h- fallback;
test that all three requests refuse both names.
- hive-priv/README.md, docs/trust-boundary/security.md: the allowlist
no longer lists the forge and matrix.
Fixes#5508
After a failed or timed-out store read the responder denies for LOOKUP_FAILURE_WINDOW (3 s) without a new lookup, so a burst of requests during an outage costs one lookup instead of one per request.
Three edits besides the code in main.rs belong to this change:
- swarm-metrics-auth/Cargo.toml gains tokio's test-util dev-dependency because the burst test runs on paused time (start_paused) to let a hanging store sleep past LOOKUP_TIMEOUT without a real 5 s wait.
- docs/swarm/services.md gains the sentence that a failed or timed-out read is denied for three seconds without a retry, which documents the window this change adds.
- docs/swarm/credentials.md gains the clause "every three seconds while the store fails" on the Grafana bearer row, which documents the same window in the secrets table.
A request that waits behind another build, e.g. one a controller
restart orphaned, could start a full build after most of the
controller's 61-minute reply deadline was gone. The builder now waits
at most REPLY_DEADLINE - BUILD_DEADLINE - 30 s for the slot and
answers Failed, without building, past that. The 30 s covers the
forge token read, now bounded to 20 s, and the reply's trip back.
Fixes#5437
The poller's forge, authelia and collector calls go to leaves issued by
the swarm's own CA, and its reqwest/rustls roots come from SSL_CERT_FILE,
which the unit never set. Every pass since it was deployed fails
"invalid peer certificate: UnknownIssuer" before pushing, so the CI runs
dashboard has no hyperhive.ci.run.* samples (#5438).
- nix/host-modules/swarm-ci-metrics.nix: import lib/hive-ca-trust.nix and
register a host trustBundle for the unit, as swarm-controller does; it
adds swarm-ci-metrics-ca-bundle.service and sets SSL_CERT_FILE.
- nix/module-eval/ci-metrics.nix: a case asserting the unit's
SSL_CERT_FILE is its bundle path when self-signed, with the bundle
unit's ordering, and absent where the poller is off.
- docs/swarm/ci-metrics.md: how the poller trusts the swarm's CA.
The forge and matrix are swarm services; per mara's ruling on #5475
(shape a) a hive no longer starts, stops or restarts them.
- hive-priv-sock: InfraContainer keeps only Gateway; InfraTarget goes,
service_unit maps the gateway to nginx.service directly. A
ControlInfraContainer naming Forge/Matrix fails to decode.
- hive-host-sock: LifecycleScope drops forge/matrix and refuses unknown
fields, so an older hivectl's --forge is an error rather than an
all-false scope meaning everything.
- hive-c0re: scoped_infra selects only the gateway.
- hivectl: --forge/--matrix removed from stop/start/restart.
- docs: services.md says how the forge and matrix are managed;
security.md, coordinator.md and hivectl-cli.md follow.
- hive-host-sock, hivectl/power.rs: Stop and RestartScoped doc comments name the gateway (host nginx.service), not infra containers.
The user JWT the callout issues carried no exp, so nats-server armed no
expiry timer and a connection kept its grant until the client dropped it:
a deleted or re-minted agent queue secret, a removed OIDC client or an
expired access token never reached a live connection.
Every issued user JWT now expires at the presented OIDC token's exp
(read from the introspection answer) or an hour after issue, whichever
is sooner; the agent queue-secret path has no exp of its own and gets
the hour. Every queue client reconnects through an auth callback that
re-reads or re-mints its credential, so the forced reconnect presents a
current one.
Fixes#5432
The operator-boundary sentence about config PRs moves into the config:repo
block, the extra MCP servers bullet no longer names agent.nix, and agent
creation is described without a config repo. config_bind_source's doc
covers the empty mount of an archetype agent. The archetype doc says to
deploy swarm-nats-auth before the hives.
Refs #5386
The hive reads the agent-archetype key when it provisions and rebuilds an
agent and keeps it in swarm-agent-archetypes.json. For an archetype agent
the meta flake has no agent-<name> input and mkAgent imports
hyperhive.hyperhiveArchetypes.<name>.module; provisioning, rebuilds, the
meta-input cascade, a deploy's rev and the startup migration skip the
config repos. The harness gets HIVE_ARCHETYPE and the system prompt says
the agent has no config repo. The create form sends the picked archetype.
Adds the android-dev built-in.
Refs #5386
The dashboard vhost, the hive domain vhost and the dashboard's local
name move to hive-c0re/vhosts.nix; the matrix .well-known discovery and
the legacy /matrix/ redirect move to glue-matrix-hive-discovery.nix,
which adds them to the hive domain vhost. Both declare through
gateway.vhosts. hive-gateway/vhosts.nix keeps the catch-all only, and
the gateway no longer reads deploy.matrix or c0re.servedFrontend, nor
deploy.hive-controller.enable for its vhosts.
Part of #3742.
These three are per-host choices that hive-c0re reads and renders into
its agents, so they belong under the hive controller's deploy namespace
rather than swarm-wide:
- c0re.dashboardPort -> deploy.hive-controller.dashboardPort
- c0re.claudeCodePackage -> deploy.hive-controller.claudeCodePackage
(the claude-login and review-classifier containers on the same host
keep following it)
- otel.extraResourceAttributes -> deploy.hive-controller.otel.extraResourceAttributes
The old paths stay as mkRenamedOptionModule aliases, now in deploy.nix
with the namespace's other renames. github.enable and the collector port
stay swarm-wide.
Five host options whose values hive-c0re renders into every agent's
build move under services.hyperhive.swarm, so the swarm states each of
them once instead of every hive carrying its own copy:
c0re.dashboardPort -> swarm.dashboardPort
c0re.claudeCodePackage -> swarm.claudeCodePackage
github.enable -> swarm.github.enable
otel.collector.port -> swarm.hiveOtel.collectorPort
otel.extraResourceAttributes -> swarm.hiveOtel.extraResourceAttributes
Every old path is a mkRenamedOptionModule alias, so a host that sets one
keeps its value and gets an eval warning naming the new path. Types and
defaults are unchanged, so the rendered meta flake, serve.json and
hive-c0re's environment are the same as before on a host that sets
none of them.
The readers move with them: serve.json and its gc-root assertion, the
hive-c0re environment, the hive collector's listen address and bridge
port, the swarm collector's port-collision assertion, and the
claude-login and review-classifier containers' claude pin. The
swarm-services-switch fixture sets the swarm path and now also checks
that serve.json carries the pinned claude.
Part of #4857 (slice 2).
The builder's hyperhive input is the docs-stripped flake source, so an
agent config with docs.enable = true failed to evaluate: docs.source
defaults to reference-docs, built from the missing docs/. Pass the host's
c0re.hyperhiveDocs as a hyperhive-docs input and set docs.source from it,
as the hive's meta flake does.
Fixes#5411
The agent read the operator-profiles bucket with a keys() listing, an
ordered consumer whose grant (STREAM.INFO, CONSUMER.CREATE) and flow-control
reply had never run against a permissioned queue. The controller now writes
the whole list as one JSON array under one key, only when it changed, and
the agent reads it with one DIRECT.GET the way agent_inference::read_own
reads its key. The agent grant shrinks to that one subject.
swarm-controller reads each member of authelia's operator group's forge
profile every five minutes and keeps one key per operator in the new
operator-profiles bucket. Every agent may list and read that bucket, and
hive-agent renders it into the system prompt at harness start, falling
back to today's prompt when the bucket is empty or doesn't answer within
five seconds.
Fixes#5383
The reviewer now has messaging, inbox and execution. execution is what
gives an agent the bash server, without which it cannot run hive-forge
or git to read a PR and post a review. meta is dropped: get_agent_meta
is not part of reviewing a PR.
Refs #5386
A flake declares agent archetypes in its `hyperhiveArchetypes` output,
`<name> = { module; meta; }`. The hyperhive flake ships `reviewer`
(default permissions without `execution`).
swarm-builder answers `$SWARM.builder.archetypes` with the `meta` of
every archetype its own hyperhive source declares. swarm-controller asks
once the queue connects and every 10 minutes, checks each archetype as
`POST /api/agents` checks its settings, and stores the result in the
`agent-archetypes` KV bucket when it changed. `GET /api/archetypes`
serves it, and the create form's archetype select prefills permissions,
resource caps and inference from it.
The agent created is an ordinary agent with its own config repo; the
archetype's module is not applied yet.
Refs #5386
A review request for a head whose newest recorded review approved or
requested changes now runs nothing: the classifier account posts that
verdict and table again, opening "Already reviewed <sha>, verdict
unchanged". A head whose newest review had no clean verdict, a failed
post, or no record gets a fresh run, as before.
An accepted request now keeps its key until its record is written, so a
request right after a run finishes reads that run's verdict instead of
starting a second run.
Part of #5387; the restart-loss half waits on #5219.
swarm-metrics reads the swarm's VictoriaMetrics from inside an agent
container: query, query-range, series, labels and label-values, each one
GET against the store's Prometheus read API through the gateway, printing
the store's JSON. It authenticates the way swarm-logs does, with the
agent's own queue secret read from bao under the agent's leaf, sent as
a swarm-agent bearer.
On the metrics store's host the read API's auth map gains an agent arm
ahead of the Grafana one. It routes to swarm-metrics-agent-auth, a
swarm-logs-auth instance logged in under the existing swarm-metrics-auth
leaf, whose bao grant now includes swarm/agents/+/queue read. The check is
rate-limited per address like the log store's
(deploy.victoriametrics.agentAuth{Rate,Burst,VerdictTtl}).
nix/agent-modules/metrics.nix installs the wrapped binary when the hive
forwards HIVE_AGENT_METRICS_URL (from swarm.victoriametrics.domain) and a
store address, the same gate as swarm-logs. Adds the base:swarm-metrics
skill and the CLI reference with its freshness check.
Fixes#5395
The collector's oidc/swarm authenticator verifies the bearer offline as a
JWT. The controller's authelia client was registered without
accessTokenSignedResponseAlg, so authelia mints it an opaque
authelia_at_ handle, which that authenticator cannot verify: by config,
no push from the vcs or jobq exporter can be accepted. Register it with
RS256 like every other client whose token lands on an oidc/* receiver.
The SDK logs a failed export at debug only, so a refused push never
reached the journal. AuthenticatedHttpClient now warns on a failed token
mint, a transport error, or a non-2xx answer (status plus a body
snippet), once per kind of failure and again every 10 minutes with a
count, and logs once when a push succeeds after failing.
Refs #5393
Delete nix/templates/ruth.nix, the ruth nixosConfiguration, module and
toplevel, the hive-c0re managerToplevel option, and the meta flake's
isManager switch with lifecycle::MANAGER_NAME. Every agent, ruth
included, now builds from nix/templates/agent.nix. The template's only
content beyond agent.nix was docs.enable = mkDefault true; docs.enable
is off by default for every agent and ruth's own agent.nix turns it on.
Refs #5377
nix_build::run read nix's stdout and stderr with read_to_end, so a long
--print-build-logs run held its whole log in memory until nix exited,
though the reply uses only the last 30 lines (4000 bytes) of stderr and
the last non-empty line of stdout. Both streams now go through a Tail
that holds at most 128 KiB and keeps the last 64 KiB. Output under 64 KiB
reaches tail() whole, so those replies are unchanged.
Permission::default_for and hive-sh4re's MANAGER_AGENT are gone: every
agent with no permissions key holds Permission::DEFAULT, ruth included.
The agent-name parameters that only fed default_for go with it
(permissions::effective, HiveCopy::before_read/after_read and their
callers).
swarm-controller seeds the grant ruth held by name: at start, a declared
ruth whose permissions are unset gets DEFAULT plus manage_root_agent
written into her key, once, logged. A set key is never touched. It is a
one-shot to delete once every swarm has passed it.
The swarm UI setup assistant opens the create form with
manage_root_agent checked, so a new ruth is created with the grant.
permissions_import no longer adds ruth to the import or splits her
default. Docs and help text no longer say ruth holds the grant by
default; swarmctl-cli.md regenerated.
hh-swarm-queue-connect-failed matched "swarm queue connect failed; this
agent publishes nothing upward", which nothing has logged since the
harness started retrying its first connect and exiting (235bc481b). The
rule now matches the error the harness logs when every attempt has
failed, CONNECT_EXHAUSTED in swarm_queue.rs, and its comment and summary
describe the retry-then-exit behaviour.
A failed MintAgentIdentity node logged nothing: the error reached only
the job graph. mint_identity now warns with the agent and the error, and
hh-agent-identity-mint-failed fires on that line.
Refs #4651
forgejo-api 0.11.1's sync client builds its own reqwest client with no
timeout and takes no caller-supplied client (sync.rs: new and
with_user_agent are the only constructors), so a forge that accepts a
connection and then stalls blocked every typed verb forever.
A watchdog thread now starts before the client is built. After
HIVE_FORGE_DEADLINE seconds (default 900, five minutes above
DOWNLOAD_TIMEOUT) it prints a hive-forge: FAILED: line and exits 75.
It bounds the whole command, not each request, and a write may already
have landed when it fires; the help text and docs/tools/forge.md say so.
Not every swarm's operator is she/her. The prompt now names no pronouns
and tells agents to say "the operator"; pronouns will come from a
per-operator profile setting. The operatorPronouns removal warning and
claude-invocation.md say the same.
Nothing sets the variable once otel.metricIntervalMs is gone, so the
turn-metrics, jobq-metrics and vcs-metrics exporters export at a fixed
60s, as hive-c0re's container-resource exporter already does. The
observability doc and the removal warning now say so.
Both are ignored with a warning through the same shim, now
nix/host-modules/hive-options-removed.nix.
- otel.metricIntervalMs: claude in every agent and hive-c0re's
container-resource exporter run at the 60s default. The agent-level
services.hyperhive.agent.otel.metricIntervalMs, set only by the meta
render, goes too (warning shim in nix/agent-modules/otel-removed.nix).
- otel.debug: services.hyperhive.agent.otel.debug stays, documented and
set in an agent's own config; the meta render no longer emits it.
Both options are now ignored with a warning (the swarm-peers-removed.nix
shape), so a host that still sets one keeps evaluating.
- operatorPronouns: the agents' system prompt names the pronouns as
she/her, the value the harness fell back to and the option's default.
The --operator-pronouns flag, HiveEnv field, meta-flake let binding
and HIVE_OPERATOR_PRONOUNS env var are gone.
- contextWindowTokens: the per-family defaults (haiku 200000, sonnet
1000000, opus 1000000) move into hive-agent's harness_state as a
table; the window the API reports after a turn still wins. The
--context-window-tokens flag, HiveEnv field and the rendered
HIVE_CONTEXT_WINDOW_TOKENS_<KEY> env vars are gone.
swarm-secret-publish and its path unit now run inside authelia's container,
beside the mint, and read each client secret at the path authelia writes it.
The host unit and host path unit, which read the secrets through the
container's root on the host, are gone, and so is
deploy.authelia.hostClientSecretDir, which only they read. The publisher keeps
its store identity, the secret-publisher leaf. The host hands the leaf and the
store's CA into the container as nspawn system credentials, and the unit loads
them; where this host mints the leaf, the container waits for swarm-bao-pki.
Authelia does not wait for the publisher, which retries every 30 seconds while
the store is down.
The container also runs the journal forwarder the other service containers
run, pushing to a receiver of its own on the swarm collector (serviceProducers
swarm-authelia) as a new machine OIDC client (swarm.authelia.otel.clientId)
that authelia registers for itself and the publisher carries to the store. The
fetch unit reads it back under the publisher's leaf, also handed to it as a
system credential, so the swarm-secret-publisher policy gains read on that one
leaf; its stanza keeps create and update, which the exact path would otherwise
take from the services/* prefix. Without the leaf the forwarder is off.
The container drops --link-journal=host, and the host collector stops reading
it. The services' "nothing at <path>" errors name the publisher in authelia's
container.
