mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-06-27 11:22:03 +00:00
aacc6bb0a8
The preflight-compression gate only ran the (expensive) token estimate when the message COUNT exceeded protect_first_n + protect_last_n + 1. A session with a handful of very large messages never tripped the count condition, so compression was never attempted and the turn eventually hit a hard context-overflow error. Add _should_run_preflight_estimate() with OR semantics: run the estimate when either the message count exceeds the protected ranges (the historical gate) OR a cheap char-based estimate already crosses the configured threshold. The downstream estimate_request_tokens_rough() stays authoritative — this is only a hint that decides whether to pay for the full estimate. Salvaged from #27435 by @texhy (authorship preserved). Re-applied on current main: the preflight gate moved from conversation_loop.py to turn_context.py since the PR was opened, so the helper + gate are placed there; the test imports the real MINIMUM_CONTEXT_LENGTH instead of a hardcoded literal. Closes #27405. |
||
|---|---|---|
| .. | ||
| ci | ||
| lib | ||
| tests | ||
| whatsapp-bridge | ||
| analyze_livetest.py | ||
| benchmark_browser_eval.py | ||
| build_model_catalog.py | ||
| build_skills_index.py | ||
| check-windows-footguns.py | ||
| check_subprocess_stdin.py | ||
| contributor_audit.py | ||
| discord-voice-doctor.py | ||
| docker_config_migrate.py | ||
| hermes-gateway | ||
| install.cmd | ||
| install.ps1 | ||
| install.sh | ||
| install_psutil_android.py | ||
| keystroke_diagnostic.py | ||
| kill_modal.sh | ||
| lint_diff.py | ||
| LIVETEST_README.md | ||
| profile-tui.py | ||
| release.py | ||
| run_tests.sh | ||
| run_tests_parallel.py | ||
| sample_and_compress.py | ||
| setup_open_webui.sh | ||
| tool_search_livetest.py | ||