Docs › Dify and Flowise scheduled workflow monitoring with RunVouch
Dify and Flowise scheduled workflow monitoring with RunVouch
Dify and Flowise scheduled workflow monitoring where the schedule lives outside the tool: both expose a workflow or chatflow over HTTP; the schedule lives in cron, n8n or a cloud scheduler. That outside caller is the thing that stops quietly.
How it runs on Dify and Flowise
Wrap the caller script with rv run; the script calls the Dify (/v1/workflows/run) or Flowise (/api/v1/prediction/{id}) endpoint and writes the answer to a file that serves as evidence.
Store the key
An environment variable in the caller's environment; the Dify or Flowise API key stays where it is.
Wrap the job
# crontab
0 7 * * * rv run daily-brief --evidence-file /out/brief.json -- python call_dify.py
# call_dify.py
import json, os, requests
r = requests.post("https://api.dify.ai/v1/workflows/run", timeout=600,
headers={"Authorization": f"Bearer {os.environ['DIFY_KEY']}"},
json={"inputs": {"topic": "overnight"}, "response_mode": "blocking", "user": "cron"})
r.raise_for_status()
json.dump(r.json(), open("/out/brief.json", "w"))rv fails open: if RunVouch is unreachable the job still runs and you get one warning line.
Register the cadence and caps
rv agent nightly-report --cadence 24h --grace 30m --max-runtime 1h --evidence --cap-run-cost 2
Register the agent once, from anywhere with the key. Cadence is what turns a schedule that stopped into an alert; --evidence makes a run without evidence a failure; the caps pause the agent when it overspends.
What goes silent on Dify and Flowise
- A workflow that returns 200 with an empty
outputsis a success to the caller; the evidence file being empty is not. - Token usage is in the Dify response (
metadata.usage); pass it as cost withrv endfor the daily cap.
What Dify and Flowise does not tell you
Dify and Flowise keep a log of API calls and workflow runs in their own UI, with status and usage per run. They cannot record a call that never came. A caller that stopped, a 200 with empty outputs, or a chatflow that answered with a refusal, are all successful runs in that log.
What RunVouch detects
| Alert | What it means here |
|---|---|
| MISSED | cadence plus grace passed and no run started |
| FAILED | non-zero exit or a reported failure, with the stderr excerpt |
| NO_EVIDENCE | the run said ok but the file, URL or assertion you required is missing |
| STALLED | a run started and never ended within max runtime |
| RETRY_STORM | the same tool called with identical input many times in one run |
| BUDGET_RUN / BUDGET_DAY | cost cap crossed; the agent is paused until you resume it |
| DRIFT | duration or output size far off its 7-run baseline |
Set up in two minutes
- Get a free key (3 agents, no card) and store it where this page says.
- wrap the job: copy the snippet above into the scheduled job.
- Register the cadence once:
rv agent nightly-report --cadence 24h --grace 30m --evidence, or let the first run create the agent and set the cadence on the dashboard. - Send one test alert:
curl -X POST https://api.runvouch.com/v1/settings/test-alert -H "X-API-Key: $RUNVOUCH_KEY". The next missed, failed or empty run reaches the same channels.
Also running agent frameworks?
Ollama and local LLM batch jobs. OpenClaw (verified-run skill). LangGraph. CrewAI. The full list of runtimes is on integrations, and the same agent can report from several of them: one job, one cadence, wherever it happens to run.
Need a key? Get a free key · Stuck? contact