hermes-agent/gateway
Teknium 7dac75f2ae
fix: prevent context pressure warning spam after compression (#4012)
* feat: add /yolo slash command to toggle dangerous command approvals

Adds a /yolo command that toggles HERMES_YOLO_MODE at runtime, skipping
all dangerous command approval prompts for the current session. Works in
both CLI and gateway (Telegram, Discord, etc.).

- /yolo -> ON: all commands auto-approved, no confirmation prompts
- /yolo -> OFF: normal approval flow restored

The --yolo CLI flag already existed for launch-time opt-in. This adds
the ability to toggle mid-session without restarting.

Session-scoped — resets when the process ends. Uses the existing
HERMES_YOLO_MODE env var that check_all_command_guards() already
respects.

* fix: prevent context pressure warning spam (agent loop + gateway rate-limit)

Two complementary fixes for repeated context pressure warnings spamming
gateway users (Telegram, Discord, etc.):

1. Agent-level loop fix (run_agent.py):
   After compression, only reset _context_pressure_warned if the
   post-compression estimate is actually below the 85% warning level.
   Previously the flag was unconditionally reset, causing the warning
   to re-fire every loop iteration when compression couldn't reduce
   below 85% of the threshold (e.g. very low threshold like 15%,
   or system prompt alone exceeds the warning level).

2. Gateway-level rate-limit (gateway/run.py, salvaged from PR #3786):
   Per-chat_id cooldown of 1 hour on compression warning messages.
   Both warning paths ('still large after compression' and 'compression
   failed') are gated. Defense-in-depth — even if the agent-level fix
   has edge cases, users won't see more than one warning per hour.

Co-authored-by: dlkakbs <dlkakbs@users.noreply.github.com>

---------

Co-authored-by: dlkakbs <dlkakbs@users.noreply.github.com>
2026-03-30 13:18:21 -07:00
..
builtin_hooks feat: built-in boot-md hook — run BOOT.md on gateway startup (#3733) 2026-03-29 10:19:54 -07:00
platforms fix: fit all 100 commands in Telegram menu with 40-char descriptions (#4010) 2026-03-30 11:21:13 -07:00
__init__.py Enhance CLI with multi-platform messaging integration and configuration management 2026-02-02 19:01:51 -08:00
channel_directory.py chore: remove ~100 unused imports across 55 files (#3016) 2026-03-25 15:02:03 -07:00
config.py feat(telegram): add group mention gating and regex triggers (#3870) 2026-03-29 21:53:59 -07:00
delivery.py chore: remove ~100 unused imports across 55 files (#3016) 2026-03-25 15:02:03 -07:00
hooks.py feat: built-in boot-md hook — run BOOT.md on gateway startup (#3733) 2026-03-29 10:19:54 -07:00
mirror.py chore: remove ~100 unused imports across 55 files (#3016) 2026-03-25 15:02:03 -07:00
pairing.py refactor: consolidate ~/.hermes directory layout with backward compat (#3610) 2026-03-28 15:22:19 -07:00
run.py fix: prevent context pressure warning spam after compression (#4012) 2026-03-30 13:18:21 -07:00
session.py fix: gateway token double-counting — use absolute set instead of increment (#3317) 2026-03-26 19:13:07 -07:00
status.py refactor: consolidate get_hermes_home() and parse_reasoning_effort() (#3062) 2026-03-25 15:54:28 -07:00
sticker_cache.py chore: remove ~100 unused imports across 55 files (#3016) 2026-03-25 15:02:03 -07:00
stream_consumer.py fix: handle message length overflow in streaming mode (#1783) 2026-03-17 11:00:52 -07:00