hand agents the dashboard port, pinned claude and otel labels at container start
The three values that differ per host (deploy.hive-controller.dashboardPort, claudeCodePackage and otel.extraResourceAttributes) no longer go into the meta flake. hive-priv writes them into the container's /etc/hyperhive-hive-facts with the hive name and domain, and the agent reads them at boot: - HIVE_DASHBOARD_PORT reaches every unit through the hive-facts generator; the web UI still defaults to 7000 without it. - `claude` on PATH is a wrapper that runs HYPERHIVE_CLAUDE_CODE_PATH's claude when it is there, and the container's own claude-code otherwise. The host's serve.json keeps gc-rooting the pinned build. - OTEL_RESOURCE_ATTRIBUTES moves out of the units' Environment= into a boot-time generator, which appends HYPERHIVE_OTEL_EXTRA_RESOURCE_ATTRIBUTES. The agent options services.hyperhive.agent.claudeCodePath (now a removed option) and otel.extraResourceAttributes go; only the meta render set them. render_flake takes no HiveEnv any more, so the memory-cap render test and render_hive_flake_at, which only existed to vary HiveEnv into the render, go with it. Refs #4857
This commit is contained in:
atlas
mara
parent
a32c144b80
commit
9113651c10
23 changed files with 408 additions and 335 deletions
|
|
@ -1,7 +1,9 @@
|
|||
# `checks.script-test-agent-hive-facts` — runs the two readers of
|
||||
# `/etc/hyperhive-hive-facts` in ../agent-modules/hive-facts.nix: the systemd
|
||||
# environment generator and the login-shell snippet `/etc/set-environment`
|
||||
# sources. The cases are in ./agent-hive-facts.sh.
|
||||
# sources. Also the two consumers of what they pass on: ../agent-modules/otel.nix's
|
||||
# `OTEL_RESOURCE_ATTRIBUTES` generator and ../agent-modules/default.nix's `claude`.
|
||||
# The cases are in ./agent-hive-facts.sh.
|
||||
#
|
||||
# What runs is the rendered generator and snippet. The one edit is the facts
|
||||
# file's path, moved under the build directory, and the snippet's reference to
|
||||
|
|
@ -26,6 +28,11 @@ let
|
|||
;
|
||||
|
||||
machine = agentWith { services.hyperhive.agent.user.name = "a1"; };
|
||||
|
||||
# As text: building it would build the claude-code it falls back to.
|
||||
claude = lib.findFirst (
|
||||
p: (p.name or "") == "claude"
|
||||
) (throw "no `claude` in systemPackages") machine.environment.systemPackages;
|
||||
in
|
||||
pkgs.runCommand "hyperhive-script-test-agent-hive-facts"
|
||||
{
|
||||
|
|
@ -33,6 +40,9 @@ pkgs.runCommand "hyperhive-script-test-agent-hive-facts"
|
|||
machine.environment.etc."systemd/system-environment-generators/50-hyperhive-hive-facts".source;
|
||||
PROFILE = machine.environment.etc."hyperhive/hive-facts.sh".source;
|
||||
EXTRA_INIT = machine.environment.extraInit;
|
||||
OTEL_GENERATOR =
|
||||
machine.environment.etc."systemd/system-environment-generators/60-hyperhive-otel-resource".source;
|
||||
CLAUDE_WRAPPER = builtins.unsafeDiscardStringContext claude.text;
|
||||
SHELLS = "${pkgs.dash}/bin/dash ${pkgs.bash}/bin/sh";
|
||||
}
|
||||
''
|
||||
|
|
|
|||
|
|
@ -40,7 +40,7 @@ check() {
|
|||
for sh in $SHELLS; do
|
||||
# Only what the snippet exported reaches the child's environment. No PATH:
|
||||
# the snippet must not need one.
|
||||
got=$(env -i "$sh" -c ". '$dir/profile'; exec '$envbin'" | grep -E '^(HYPERHIVE_|CLAUDE_|LD_PRELOAD=|__hyperhive)' | sort)
|
||||
got=$(env -i "$sh" -c ". '$dir/profile'; exec '$envbin'" | grep -E '^(HYPERHIVE_|HIVE_DASHBOARD_PORT=|CLAUDE_|LD_PRELOAD=|__hyperhive)' | sort)
|
||||
if [ "$got" != "$(printf '%s\n' "$want" | sort)" ]; then
|
||||
fail "$sh: a child of the sourcing shell saw:"$'\n'"$got"
|
||||
fi
|
||||
|
|
@ -61,11 +61,69 @@ check "a last line without a newline is kept" "HYPERHIVE_HIVE_DOMAIN=pr1ma.examp
|
|||
HYPERHIVE_HIVE_NAME=pr1ma
|
||||
CLAUDE_REMOTE_CONTROL_SESSION_NAME_PREFIX=pr1ma-a1"
|
||||
|
||||
printf 'HIVE_DASHBOARD_PORT=7123\nHYPERHIVE_CLAUDE_CODE_PATH=/nix/store/0abc-claude-code\nHYPERHIVE_OTEL_EXTRA_RESOURCE_ATTRIBUTES=team=a,env=prod\n' >"$facts"
|
||||
check "the per-host values, a value holding = kept whole" "HIVE_DASHBOARD_PORT=7123
|
||||
HYPERHIVE_CLAUDE_CODE_PATH=/nix/store/0abc-claude-code
|
||||
HYPERHIVE_OTEL_EXTRA_RESOURCE_ATTRIBUTES=team=a,env=prod
|
||||
CLAUDE_REMOTE_CONTROL_SESSION_NAME_PREFIX=unknown-a1"
|
||||
|
||||
: >"$facts"
|
||||
check "an empty file (no facts)" "CLAUDE_REMOTE_CONTROL_SESSION_NAME_PREFIX=unknown-a1"
|
||||
|
||||
rm -f "$facts"
|
||||
check "no file" "CLAUDE_REMOTE_CONTROL_SESSION_NAME_PREFIX=unknown-a1"
|
||||
|
||||
# OTEL_RESOURCE_ATTRIBUTES, for units (the generator, run with what the
|
||||
# hive-facts generator printed) and for login shells (the extraInit line, after
|
||||
# the snippet). The base labels come from the build; the hive's are appended.
|
||||
base="service.name=hyperhive-agent,agent=a1,swarm=unknown"
|
||||
otel_check() {
|
||||
case=$1
|
||||
count=$((count + 1))
|
||||
local want="OTEL_RESOURCE_ATTRIBUTES=$2" got sh passed
|
||||
mapfile -t passed < <(env -i "$dir/generator")
|
||||
got=$(env -i "${passed[@]}" "$OTEL_GENERATOR")
|
||||
if [ "$got" != "$want" ]; then fail "generator printed: $got, wanted: $want"; fi
|
||||
for sh in $SHELLS; do
|
||||
got=$(env -i "$sh" -c ". '$dir/profile'; $otel_init; exec '$envbin'" | grep '^OTEL_RESOURCE_ATTRIBUTES=')
|
||||
if [ "$got" != "$want" ]; then fail "$sh: a login shell saw: $got"; fi
|
||||
done
|
||||
}
|
||||
|
||||
case="otel setup"
|
||||
otel_init=$(printf '%s\n' "$EXTRA_INIT" | grep -F "$OTEL_GENERATOR")
|
||||
if [ -z "$otel_init" ]; then fail "/etc/set-environment does not run the OTEL resource generator"; fi
|
||||
if [ "$(printf '%s\n' "$EXTRA_INIT" | grep -n . | grep -F "$OTEL_GENERATOR" | cut -d: -f1)" -lt \
|
||||
"$(printf '%s\n' "$EXTRA_INIT" | grep -nxF '. /etc/hyperhive/hive-facts.sh' | cut -d: -f1)" ]; then
|
||||
fail "/etc/set-environment runs the OTEL resource generator before the hive-facts snippet"
|
||||
fi
|
||||
|
||||
printf 'HYPERHIVE_OTEL_EXTRA_RESOURCE_ATTRIBUTES=team=a,env=prod\n' >"$facts"
|
||||
otel_check "the hive's labels are appended" "$base,team=a,env=prod"
|
||||
rm -f "$facts"
|
||||
otel_check "no hive labels: the base alone, no trailing comma" "$base"
|
||||
|
||||
# `claude`: the hive's pinned build when it is there, this container's own
|
||||
# otherwise. Both builds are stand-ins that print which one ran.
|
||||
mkdir -p "$dir/own/bin" "$dir/pinned/bin"
|
||||
printf '#!%s\necho own "$@"\n' "$BASH" >"$dir/own/bin/claude"
|
||||
printf '#!%s\necho pinned "$@"\n' "$BASH" >"$dir/pinned/bin/claude"
|
||||
chmod +x "$dir/own/bin/claude" "$dir/pinned/bin/claude"
|
||||
printf '%s' "$CLAUDE_WRAPPER" | sed -E "s|/nix/store/[^ ]+/bin/claude|$dir/own/bin/claude|" >"$dir/claude"
|
||||
case="claude setup"
|
||||
if ! grep -qF "$dir/own/bin/claude" "$dir/claude"; then fail "the rewrite did not reach the fallback claude"; fi
|
||||
claude_check() {
|
||||
case=$1
|
||||
count=$((count + 1))
|
||||
local got pin=()
|
||||
if [ -n "$2" ]; then pin=("HYPERHIVE_CLAUDE_CODE_PATH=$2"); fi
|
||||
# Under this shell: the shebang names the build's bash, not in this sandbox.
|
||||
got=$(env -i "${pin[@]}" "$BASH" "$dir/claude" -p hi)
|
||||
if [ "$got" != "$3 -p hi" ]; then fail "ran: $got, wanted: $3 -p hi"; fi
|
||||
}
|
||||
claude_check "the pinned claude when the hive hands one over" "$dir/pinned" pinned
|
||||
claude_check "the container's own claude with no pin" "" own
|
||||
claude_check "the container's own claude when the pinned path is gone" "$dir/gone" own
|
||||
|
||||
echo "$count cases, $failures failed"
|
||||
[ "$failures" -eq 0 ]
|
||||
|
|
|
|||
Loading…
Reference in a new issue