Bug Description

When a cron job’s pre-run script outputs {"wakeAgent": false}, the scheduler correctly skips the LLM call. However, the log message then says:

Job '...': agent returned [SILENT] — skipping delivery

This is misleading as the agent was never invoked at all; rather, the delivery was suppressed by the wakeAgent sentinel, not by the agent producing [SILENT] output.

Steps to Reproduce

1. Set up a cron job with a script that outputs {"wakeAgent": false} when nothing changed
2. Observe the two log lines in the scheduler output for the same tick.

Expected Behavior

The log should distinguish between:

1. Agent was invoked and returned [SILENT] → agent returned [SILENT] — skipping delivery
2. Script sent wakeAgent=false → wakeAgent=false, agent not invoked — skipping delivery.

Actual Behavior

The scheduler logs:

INFO cron.scheduler: Job '[redacted]' (ID: ...): wakeAgent=false, skipping agent run
INFO cron.scheduler: Job '...': agent returned [SILENT] — skipping delivery

Both lines refer to the same tick. The second line is incorrect—the agent was never invoked.

Affected Component

Agent Core (conversation loop, context compression, memory)

Messaging Platform (if gateway-related)

No response

Debug Report

Report       https://dpaste.com/2N6RL6XQ4

Sorry, I don't feel comfortable sharing the remaining reports as they contain personal chat data.  I feel all relevant excerpts are above.

Operating System

macOS 26.5

Python Version

No response

Hermes Version

No response

Additional Logs / Traceback (optional)

Root Cause Analysis (optional)

No response

Proposed Fix (optional)

No response

Are you willing to submit a PR for this?

• I'd like to fix this myself and submit a PR