hyperhive/nix/agent-modules/forge.nix
atlas 246c9471b1 refactor(hive-agent): split the forge notification poller into its own crate
The poller was a `tokio::spawn` inside the `hive-agent` serve loop. It
never needed anything from that loop except a socket path, so being
in-process bought nothing and cost two things: a harness restart took
forge notifications down with it, and the whole forge/HTTP dependency
tree was linked into the serve-loop binary.

It is now `hive-forge-notify`, a per-agent daemon with its own systemd
unit, a sibling of `hive-bash-daemon` and `hive-matrix-daemon`. Same
contract as those two: it reaches the harness only by upserting todos on
the in-agent socket, and nowhere else.

The module moves verbatim (`notify.rs`) — the formatters, the activation
gates, the dedupe map and all 33 tests are unchanged. Only the socket
call sites are rewritten, onto a small local `todo_client` rather than
the harness's. That mirrors what both sibling daemons already do, and
the etiquette differs on purpose: the harness's client carries a 60s
backoff schedule sized to ride out a hive-c0re restart, which its
callers need because they have no retry of their own. This poller's two
call sites both sit inside the 30s poll loop and both treat a failure as
"leave the thread unread, try next tick", so the poll interval already
is the retry; a second backoff would only stack sleeps and delay the
rest of the batch.

The unit is `Restart=on-failure`, not `always`. An agent with no forge
account is a supported configuration and the poller reports it by
logging why and exiting 0 — under `always` that clean exit would be a
restart loop on every forge-less agent.

`forgejo-api`, `url` and `time` drop out of `hive-agent`'s dependencies
with the module.

Also corrects docs that outlived the code they described: the persisted
`forge_cursor` field is long gone (forge's own read-state is the durable
record of what has been delivered), but `docs/persistence.md` and the
`harness_state` module docs still documented it as live.
2026-07-26 21:30:29 +02:00

226 lines
9.6 KiB
Nix
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# In-container forge (Forgejo) integration: the `tea` CLI login
# oneshot, the `hive-forge` verb CLI on PATH, and the icon → forge
# avatar sync.
{
pkgs,
lib,
config,
...
}:
let
userName = config.hyperhive.user.name;
homeDir = "/home/${userName}";
# Same 512×512 rasterization of the agent icon the matrix avatar
# sync uses (./matrix.nix — identical derivation, same store path).
# Only forced when an icon is configured (the avatar-sync unit below
# is gated on `hyperhive.icon != null`).
iconPng = pkgs.runCommand "hive-agent-icon.png" { nativeBuildInputs = [ pkgs.librsvg ]; } ''
rsvg-convert -f png -w 512 -h 512 ${config.hyperhive.icon} -o $out
'';
in
{
options.hyperhive.forge.url = lib.mkOption {
type = lib.types.str;
default = "http://localhost:3000";
example = "http://forge.internal:3000";
description = ''
Base URL of the hyperhive-managed Forgejo. Used at container
boot by a oneshot systemd unit that calls
`tea login add --url <this> --token "$(cat $HYPERHIVE_STATE_DIR/forge-token)"`
(= `/agents/<name>/state/forge-token`) so the agent's claude can
shell out to `tea` without an extra auth dance. No-op when the
forge-token file is missing (i.e. hive-forge isn't running on
the host).
'';
};
config = {
assertions = [
# hyperhive.forge.url must look like an HTTP URL when non-default.
{
assertion =
config.hyperhive.forge.url == ""
|| lib.hasPrefix "http://" config.hyperhive.forge.url
|| lib.hasPrefix "https://" config.hyperhive.forge.url;
message = "hyperhive.forge.url must be an http:// or https:// URL (got: \"${config.hyperhive.forge.url}\")";
}
];
environment.systemPackages = [
# tea: gitea/forgejo CLI client. Configured at boot by the
# tea-login oneshot below if /state/forge-token is present, so
# claude can `tea repos create`, `tea pulls create`, etc.
pkgs.tea
# hive-forge <verb>: CLI wrapping common Forgejo REST API operations
# (view, pr, issue, comment, assign, close, labels, branches, etc.).
# The per-bin split package — narrow closure, no hivectl/wireguard.
config.hyperhive.packages.hive-forge
];
# Forge notification poller — a long-running sibling of
# `hive-bash-daemon` / `hive-matrix-daemon`. Polls the agent's unread
# notification list and upserts each thread as a todo on the harness's
# in-agent socket; it needs nothing else from the harness, which is why
# it is its own process rather than a task inside the serve loop.
systemd.services.hive-forge-notify = {
description = "Forgejo notification poller for this agent";
wantedBy = [ "multi-user.target" ];
after = [ "network.target" ];
environment = {
# In-agent todo socket the harness serves (loose-ends v2). Must
# match the harness's HIVE_AGENT_SOCKET (agent-service.nix) — the
# poller upserts one todo per forge thread here rather than firing
# a hive-c0re wake.
HIVE_AGENT_SOCKET = "/run/hive-agent/${userName}/agent.sock";
RUST_LOG = "info";
# HIVE_FORGE_URL and HYPERHIVE_STATE_DIR come from
# systemd.globalEnvironment (forwarded into every container by the
# meta flake) — the poller reads the forge base URL from the first
# and the agent's `forge-token` from under the second.
};
serviceConfig = {
ExecStart = "${config.hyperhive.packages.hive-forge-notify}/bin/hive-forge-notify";
SyslogIdentifier = "hive-forge-notify";
# `on-failure`, NOT `always`: an agent with no forge account is a
# supported configuration, and the poller reports that by logging
# why and exiting 0. Under `always` that clean exit would become a
# restart loop on every forge-less agent. A crash still restarts.
Restart = "on-failure";
RestartSec = 5;
User = userName;
Group = userName;
};
};
# One-shot: tea config.yml from the seeded forge token. Shape
# contract (always exit 0, no set -e, skip-silently, re-runnable):
# docs/conventions.md::Best-effort oneshot services.
systemd.services.tea-login = {
description = "configure tea CLI from hive-forge token (best-effort)";
wantedBy = [ "multi-user.target" ];
after = [ "local-fs.target" ];
serviceConfig = {
Type = "oneshot";
RemainAfterExit = true;
# Pin the journal identity (else it's the `script` store-path wrapper).
SyslogIdentifier = "tea-login";
};
path = [
pkgs.curl
pkgs.jq
pkgs.coreutils
];
environment.HOME_DIR = homeDir;
environment.AGENT_USER = userName;
script = ''
# No `set -e`: best-effort posture (see docs pointer above).
FORGE_URL=${lib.escapeShellArg config.hyperhive.forge.url}
# $HYPERHIVE_STATE_DIR is system-wide via the meta flake.
TOKEN_FILE="$HYPERHIVE_STATE_DIR/forge-token"
if [ ! -f "$TOKEN_FILE" ]; then
echo "tea-login: no forge-token at $TOKEN_FILE; skipping"
exit 0
fi
TOKEN=$(cat "$TOKEN_FILE")
# Resolve the agent username from the forge API.
USER=$(curl -sf --max-time 5 \
-H "Authorization: token $TOKEN" \
"$FORGE_URL/api/v1/user" \
| jq -r '.login // empty' 2>/dev/null || true)
if [ -z "$USER" ]; then
echo "tea-login: could not resolve username from forge API; skipping"
exit 0
fi
# Config under the agent user's home, chown'd to them;
# service stays root-owned (see docs pointer above).
CONFIG="$HOME_DIR/.config/tea/config.yml"
mkdir -p "$(dirname "$CONFIG")" || true
cat > "$CONFIG" << EOF
logins:
- name: forge
url: $FORGE_URL
token: $TOKEN
default: true
ssh_host: ""
ssh_key: ""
insecure: false
ssh_agent: false
user: $USER
preferences:
editor: false
flag_defaults:
remote: ""
EOF
chown -R "$AGENT_USER:$AGENT_USER" "$HOME_DIR/.config" 2>/dev/null || true
echo "tea-login: configured for $FORGE_URL as $USER (config at $CONFIG)"
'';
};
# Path-trigger sibling: re-fires forge-avatar-sync the moment
# `<state>/forge-token` appears. Mirrors the hive-matrix-daemon
# token-watcher pattern — on first agent deployment the container
# boots before hive-c0re has provisioned the forge-token, so the
# service fires too early and exits with "no forge-token found".
# Without this path unit, RemainAfterExit=true would prevent systemd
# from ever re-running the service. See
# docs/persistence.md::forge-avatar-sync.
systemd.paths.forge-avatar-sync = lib.mkIf (config.hyperhive.icon != null) {
description = "trigger forge-avatar-sync when forge-token appears";
wantedBy = [ "multi-user.target" ];
pathConfig.PathExistsGlob = "/agents/*/state/forge-token";
};
# One-shot: hyperhive.icon → Forgejo profile avatar. Shape contract:
# docs/conventions.md::Best-effort oneshot services.
# RemainAfterExit = false so the .path trigger above can re-fire
# this unit when the forge-token arrives after boot. The PNG is
# rasterized at build time (`iconPng`, shared shape with the matrix
# avatar sync), so the unit only exists when an icon is configured
# and needs no librsvg at runtime — Forgejo's Go image library
# can't decode SVG, hence PNG.
systemd.services.forge-avatar-sync = lib.mkIf (config.hyperhive.icon != null) {
description = "sync agent icon to Forgejo user avatar (best-effort)";
wantedBy = [ "multi-user.target" ];
after = [ "tea-login.service" ];
serviceConfig = {
Type = "oneshot";
RemainAfterExit = false;
# Pin the journal identity (else it's the `script` store-path wrapper).
SyslogIdentifier = "forge-avatar-sync";
};
path = [
pkgs.curl
pkgs.coreutils
pkgs.jq
];
script = ''
FORGE_URL=${lib.escapeShellArg config.hyperhive.forge.url}
# $HYPERHIVE_STATE_DIR is set system-wide by the meta flake
# (systemd.globalEnvironment) to `/agents/<name>/state`.
TOKEN_FILE="$HYPERHIVE_STATE_DIR/forge-token"
if [ ! -f "$TOKEN_FILE" ]; then
echo "forge-avatar-sync: no forge-token found; skipping"
exit 0
fi
TOKEN=$(cat "$TOKEN_FILE")
IMAGE=$(base64 -w 0 < ${iconPng})
# Forgejo POST /user/avatar expects {"image":"<base64>"} just the
# raw base64 string, NOT a data URI (data:image/png;base64,...).
# Use jq to build the payload so the large base64 value is safely quoted.
PAYLOAD=$(jq -n --arg img "$IMAGE" '{image:$img}')
RESP=$(curl -sf --max-time 10 \
-X POST "$FORGE_URL/api/v1/user/avatar" \
-H "Authorization: token $TOKEN" \
-H "Content-Type: application/json" \
-d "$PAYLOAD" \
-w "\n%{http_code}" 2>/dev/null || true)
CODE=$(printf '%s' "$RESP" | tail -1)
if [ "$CODE" = "204" ] || [ "$CODE" = "200" ]; then
echo "forge-avatar-sync: avatar uploaded (HTTP $CODE)"
else
echo "forge-avatar-sync: upload returned HTTP $CODE skipping (non-fatal)"
fi
'';
};
};
}