mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-09 08:21:50 +00:00
9231a335d4
The summary_target_tokens parameter was accepted in the constructor,
stored on the instance, and never used — the summary budget was always
computed from hardcoded module constants (_SUMMARY_RATIO=0.20,
_MAX_SUMMARY_TOKENS=8000). This caused two compounding problems:
1. The config value was silently ignored, giving users no control
over post-compression size.
2. Fixed budgets (20K tail, 8K summary cap) didn't scale with
context window size. Switching from a 1M-context model to a
200K model would trigger compression that nuked 350K tokens
of conversation history down to ~30K.
Changes:
- Replace summary_target_tokens with summary_target_ratio (default 0.40)
which sets the post-compression target as a fraction of context_length.
Tail token budget and summary cap now scale proportionally:
MiniMax 200K → ~80K post-compression
GPT-5 1M → ~400K post-compression
- Change threshold_percent default: 0.50 → 0.80 (don't fire until
80% of context is consumed)
- Change protect_last_n default: 4 → 20 (preserve ~10 full turns)
- Summary token cap scales to 5% of context (was fixed 8K), capped
at 32K ceiling
- Read target_ratio and protect_last_n from config.yaml compression
section (both are now configurable)
- Remove hardcoded summary_target_tokens=500 from run_agent.py
- Add 5 new tests for ratio scaling, clamping, and new defaults
|
||
|---|---|---|
| .. | ||
| __init__.py | ||
| anthropic_adapter.py | ||
| auxiliary_client.py | ||
| context_compressor.py | ||
| context_references.py | ||
| copilot_acp_client.py | ||
| display.py | ||
| insights.py | ||
| model_metadata.py | ||
| models_dev.py | ||
| prompt_builder.py | ||
| prompt_caching.py | ||
| redact.py | ||
| skill_commands.py | ||
| smart_model_routing.py | ||
| title_generator.py | ||
| trajectory.py | ||
| usage_pricing.py | ||