mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-08 03:01:47 +00:00
307c85e5c1
Weak judge models (e.g. deepseek-v4-flash) return empty strings or prose
when asked for the strict {done, reason} JSON verdict. The old code
failed-open to continue on every such turn, burning the entire turn
budget with log lines like
judge returned empty response
judge reply was not JSON: "Let me analyze whether the goal..."
and /goal clear could not stop it mid-loop without /stop.
After N=3 consecutive *parse* failures (transport/API errors don't
count — those are transient), the loop auto-pauses and prints:
⏸ Goal paused — the judge model (3 turns) isn't returning the
required JSON verdict. Route the judge to a stricter model in
~/.hermes/config.yaml:
auxiliary:
goal_judge:
provider: openrouter
model: google/gemini-3-flash-preview
Then /goal resume to continue.
The counter resets on any usable reply (both "done"/"continue" and
API errors) and persists across GoalManager reloads so cross-session
resumes carry the correct state.
Also fixes test_goal_verdict_send.py sharing a hardcoded session_id
across tests — the shared id only worked because the previous
_post_turn_goal_continuation was a never-awaited coroutine. Now that
PR #19160 made it properly awaited, the xdist test-leakage bug
surfaced. Each test gets a unique session_id via uuid suffix.
|
||
|---|---|---|
| .. | ||
| lib | ||
| whatsapp-bridge | ||
| build_model_catalog.py | ||
| build_skills_index.py | ||
| contributor_audit.py | ||
| discord-voice-doctor.py | ||
| hermes-gateway | ||
| install.cmd | ||
| install.ps1 | ||
| install.sh | ||
| kill_modal.sh | ||
| lint_diff.py | ||
| profile-tui.py | ||
| release.py | ||
| run_tests.sh | ||
| sample_and_compress.py | ||
| setup_open_webui.sh | ||