# Keep an agent queue's speed caps separate from what a run may touch

My agent queue's throughput caps govern speed, never what a run may touch.

By Ki Moon · 2026-10-19 · technique · current
Canonical: https://kihmoon.com/bench-notes/p/rate-limits-not-permissions/

**Symptom:** Raising a daily cap or a parallel-slot count on your agent queue also widens which tools or systems a run can reach.

I build GTM systems with agents. They work from a board with many dials, such as how much work starts each day, how many runs go in parallel and how crashed runs restart. Each time I loosened one, the worry was that I had loosened safety with it.

I answer it by construction. Every dial is a rate limit, and none can widen what a dispatch may do. Reach lives in floors that no throughput setting touches.

- Nothing sends outward, under any label.
- A deny list covers paths no agent may edit.
- Anything that writes to a live system goes through a separate approval lane.

That split let me move fast on throughput. Because reach is fixed by separate floors, throughput changes don't need a safety review.

Parallel slots have moved up and down. When a higher setting ran through the token budget, I turned it back down as a cost limit rather than a safety one.

Ordering follows the same rule. A blocked ticket inherits its blocker's place in line and capability labels, never the most powerful one. A comment from me on a parked ticket resumes it from its existing files, ahead of the queue.

## Check your setup (read-only)

Find the agent runner: the script or service that starts agent runs from a queue. Search your scheduler entries for the command that starts agent runs. Open the config file that command reads, with slot counts, concurrency or daily caps. List every cap in it. Compare each cap with the runner's capability grants. A cap is a gap if raising it would widen the tools, labels or systems a run can reach.

**Passes if:** Every cap in the runner config limits throughput only. The tools, labels and systems a run can reach come from separate grants.

**Access needed:** local-config

## If it fails (changes to make later, not part of the check)

1. Record whether each cap limits speed or reach. Keep reach out of every environment variable and label.
2. Enforce reach with floors. The floors are no outward sends, a deny list of protected paths, and a separate approval lane for live writes.
3. Reserve some dispatch capacity for intake.
4. Raise a cap to the size of the queue when the cap blocks approved work. Stay within what the shared token budget can carry. Do not raise the cap for one day only.
5. Close extra parallel slots for 24 hours after any run that stops at the usage limit.

**Applies if:** A scheduler entry starts agent runs from a queue, and its config holds throughput caps for 2 or more agents.

**Skip if:** No scheduler entry starts agent runs. Agents start only by hand, one task at a time.

Tags: autonomy, agents, reliability
