hermes - 💡(How to fix) Fix bug: oneshot exits 0 with empty final response [2 pull requests]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

hermes -z / oneshot mode can exit with status 0 while emitting no final response text. For non-interactive foreground automation, an empty final response is not a usable successful result: callers cannot distinguish a completed answer from a silent no-op unless they add an external wrapper.

Error Message

In local foreground runs using --provider copilot --model gpt-5.5 -z <prompt>, the process exited 0, produced no stdout/final response text, and made no working-tree change. Downstream automation treated this as a command-level success until a separate manual diff/stdout check caught it.

Root Cause

hermes -z / oneshot mode can exit with status 0 while emitting no final response text. For non-interactive foreground automation, an empty final response is not a usable successful result: callers cannot distinguish a completed answer from a silent no-op unless they add an external wrapper.

Fix Action

Fixed

RAW_BUFFERClick to expand / collapse

Summary

hermes -z / oneshot mode can exit with status 0 while emitting no final response text. For non-interactive foreground automation, an empty final response is not a usable successful result: callers cannot distinguish a completed answer from a silent no-op unless they add an external wrapper.

Expected behavior

If oneshot mode completes without a non-empty final response, it should fail closed with a nonzero exit code and a short stderr diagnostic. Successful runs with final text should continue to print only the final text to stdout and exit 0.

Observed behavior

In local foreground runs using --provider copilot --model gpt-5.5 -z <prompt>, the process exited 0, produced no stdout/final response text, and made no working-tree change. Downstream automation treated this as a command-level success until a separate manual diff/stdout check caught it.

Scope

This is about the -z command contract only. It should not add retries, queues, schedulers, daemons, controllers, or background behavior.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

If oneshot mode completes without a non-empty final response, it should fail closed with a nonzero exit code and a short stderr diagnostic. Successful runs with final text should continue to print only the final text to stdout and exit 0.

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

hermes - 💡(How to fix) Fix bug: oneshot exits 0 with empty final response [2 pull requests]