mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-30 07:51:45 +08:00
9f361cdca6
Closes #16612. cronjob(action='run') and POST /api/jobs/{id}/run previously only called trigger_job(), which just sets next_run_at=now. When no gateway process was running, there was no ticker to pick the job up, so last_run_at stayed null forever — the tool returned success=true with nothing actually executing. - cron.scheduler: extract the per-job run+save+deliver+mark pipeline from tick()'s closure into a module-level _execute_and_record helper, and add run_job_now() which acquires the shared tick file-lock and runs one job inline (advancing next_run_at first for recurring jobs to preserve at-most-once semantics). - tools/cronjob_tools: branch action='run' on gateway presence via find_gateway_pids(). Ticker up → defer to next tick (≤60s) with a clear message. Ticker down → execute inline via run_job_now() and return the updated job including last_run_at/last_status. Tool schema description updated to reflect the two modes. - gateway/platforms/api_server: same branching on the HTTP endpoint, running the inline call off the event loop via run_in_executor. - hermes_cli/cron: CLI 'hermes cron run' now surfaces the message, last_run_at, and last_status from the tool result instead of always printing 'It will run on the next scheduler tick.' - docs: update cli-commands and cron-troubleshooting to describe the inline-when-no-gateway behaviour. Tests: 11 new unit tests (tests/cron/test_run_job_now.py) covering run_job_now's inline path, _execute_and_record's success/empty/error paths, and the tool/API gateway-presence branching. Plus a new TestRunJob::test_run_job_executes_inline_when_no_gateway on the api_server suite. E2E verified in a temp HERMES_HOME against the real file-based job store.