mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
67275641f8
The gateway had a SEPARATE compression system ('session hygiene')
with hardcoded thresholds (100k tokens / 200 messages) that were
completely disconnected from the model's context length and the
user's compression config in config.yaml. This caused premature
auto-compression on Telegram/Discord — triggering at ~60k tokens
(from the 200-message threshold) or inconsistent token counts.
Changes:
- Gateway hygiene now reads model name from config.yaml and uses
get_model_context_length() to derive the actual context limit
- Compression threshold comes from compression.threshold in
config.yaml (default 0.85), same as the agent's ContextCompressor
- Removed the message-count-based trigger (was redundant and caused
false positives in tool-heavy sessions)
- Removed the undocumented session_hygiene config section — the
standard compression.* config now controls everything
- Env var overrides (CONTEXT_COMPRESSION_THRESHOLD,
CONTEXT_COMPRESSION_ENABLED) are respected
- Warn threshold is now 95% of model context (was hardcoded 200k)
- Updated tests to verify model-aware thresholds, scaling across
models, and that message count alone no longer triggers compression
For claude-opus-4.6 (200k context) at 85% threshold: gateway
hygiene now triggers at 170k tokens instead of the old 100k.
|
||
|---|---|---|
| .. | ||
| platforms | ||
| __init__.py | ||
| channel_directory.py | ||
| config.py | ||
| delivery.py | ||
| hooks.py | ||
| mirror.py | ||
| pairing.py | ||
| run.py | ||
| session.py | ||
| status.py | ||
| sticker_cache.py | ||