Skip to content

fix(agents): disable aggressive default schedules in sample agent configs#1207

Open
Hypn0sis wants to merge 1 commit into
RightNow-AI:mainfrom
Hypn0sis:pr/fix-sample-agent-schedules
Open

fix(agents): disable aggressive default schedules in sample agent configs#1207
Hypn0sis wants to merge 1 commit into
RightNow-AI:mainfrom
Hypn0sis:pr/fix-sample-agent-schedules

Conversation

@Hypn0sis
Copy link
Copy Markdown
Contributor

Fixes #1206.

What changed

Removed active [schedule] sections from three sample agent configs that were generating unexpected LLM calls after the auto-spawn feature landed in efbefa1 (v0.6.9):

  • agents/orchestrator/agent.toml — was continuous { check_interval_secs = 120 } (~30 calls/hr)
  • agents/ops/agent.toml — was periodic { cron = "every 5m" } (~12 calls/hr)
  • agents/health-tracker/agent.toml — was periodic { cron = "every 1h" } (~1 call/hr)

Each section is replaced with a commented-out example at a conservative interval so users can opt-in explicitly.

agents/security-auditor/agent.toml is unchanged — its proactive schedule is event-driven, not timer-based.

Why

Before efbefa1, agents in ~/.openfang/agents/ were never auto-spawned on boot, so their [schedule] sections were inert. After efbefa1, they activate immediately on daemon restart, generating ~630 unexpected LLM calls/day and ~€5/day in API costs for users who have sample agents installed.

…figs

Commit efbefa1 ("chat agents", v0.6.9) introduced auto-spawning of all
agents found in ~/.openfang/agents/ on boot (issue RightNow-AI#1140). Three sample
agents carried [schedule] sections that were silently ignored before
auto-spawn existed:

  orchestrator: continuous every 120s  -> ~30 LLM calls/hr
  ops:          periodic  every 5m     -> ~12 LLM calls/hr
  health-tracker: periodic every 1h   -> ~1 LLM call/hr

Together these generated ~630 unexpected LLM calls/day and ~5 EUR/day
in API costs for any user who installed the sample agents before
enabling auto-spawn.

Fix: remove active [schedule] sections from all three files and replace
with commented-out examples at conservative intervals. Users who want
autonomous mode can uncomment and tune the values explicitly.

security-auditor is not changed — its proactive/event-driven schedule
only fires on agent_spawned/terminated events, not on a timer.
@Hypn0sis
Copy link
Copy Markdown
Contributor Author

The Security Audit CI failure is unrelated to this PR's changes.

Root cause: RUSTSEC-2026-0141 (lettre 0.11.21, severity 9.1 critical, advisory 2026-05-14) in openfang-channels — not touched by this PR (agent TOML files only).

The rand and gimli warnings are pre-existing and configured as allowed warnings in the audit config.

Fix is in a separate PR (upgrading lettre to 0.11.22). This PR can be reviewed and merged independently.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

fix(agents): sample agent configs have aggressive default schedules that generate unexpected LLM costs after v0.6.9 auto-spawn

1 participant