hep-graph

Update fallback: 자동 업데이트가 안 되면 hephaestus update를 한 번 실행하세요. 업데이트하지 않아도 현재 버전 명령은 그대로 동작합니다.

/hep-graph

Saved automation graphs live in the local Agentlas database, shared with the desktop app. This command reads that database and can ask for a graph to run.

Raw arguments: $ARGUMENTS

What this command can and cannot do. It lists graphs, shows what a graph does, and requests a run. It does not execute the graph — the desktop app is what runs it. Say that plainly when you report back; do not tell the user their automation ran.

Locate the CLI

CLI=""
for candidate in \
  "$(command -v agentlas 2>/dev/null)" \
  "$HOME/.agentlas/runtime/current/bin/agentlas" \
  "./bin/agentlas"
do
  if [ -n "$candidate" ] && [ -x "$candidate" ]; then CLI="$candidate"; break; fi
done
[ -n "$CLI" ] || { echo "Agentlas CLI not found. Install it with: npm i -g agentlas" >&2; exit 1; }

New — build one by talking it through

With new <what they want> (or when the user describes an automation they want and no saved graph matches), run the CLI's interview. It asks the user things it must not decide for them — when it runs, whether a step goes outside, how many times a repeat may run.

The CLI reads answers from stdin, one per line. So: run it once with no answers to see the first questions, relay them to the user in their own words, get their answers, then run it again with every answer so far:

printf '%s\n' "<answer 1>" "<answer 2>" "y" | "$CLI" graph new "<what they want>"

Rules that matter here:

• Never invent an answer. If the user has not said when it runs, ask them — do not pick a time. The whole point of the interview is that these come from the person.
• The interview proposes a grading checklist for steps that repeat until good enough (what must exist / what must not appear). Relay those items so the user can confirm or edit them — they are the pass/fail criteria, and the person should see them before saving.
• If the user does not know or says you decide, pass that through verbatim (알아서 해주세요 / you decide). The CLI then takes the most conservative option and says what it chose. Do not decide on their behalf yourself.
• The last line must be y to save. Until then nothing is written.
• It is created switched off. Say so, and relay the two commands the CLI prints (graph show to look it over, automation on to turn it on).
• If the CLI stops with "answer 를 받지 못해 멈췄습니다" / "Stopped without an answer to", it needed one more answer. Relay that exact question to the user and run again with the fuller list. Do not retry with a guess.