Teknium f374ae4c61 fix: prevent compression death spiral from API disconnects (#2153) (#4750) ...

Three fixes for long-running gateway sessions that enter a death spiral
when API disconnects prevent token data collection, which prevents
compression, which causes more disconnects:

Layer 1 — Stale token counter fallback (run_agent.py in-loop):
When last_prompt_tokens is 0 (stale after API disconnect or provider
returned no usage data), fall back to estimate_messages_tokens_rough()
instead of passing 0 to should_compress(), which would never fire.

Layer 2 — Server disconnect heuristic (run_agent.py error handler):
When ReadError/RemoteProtocolError hits a large session (>60% context
or >200 messages), treat it as a context-length error and trigger
compression rather than burning through retries that all fail the
same way.

Layer 3 — Hard message count limit (gateway/run.py hygiene):
Force compression when a session exceeds 400 messages, regardless of
token estimates. This catches runaway growth even when all token-based
checks fail due to missing API data.

Based on the analysis from PR #2157 by ygd58 — the gateway threshold
direction fix (1.4x multiplier) was already resolved on main.

2026-04-03 02:16:46 -07:00

438 KiB

Raw Blame History

View Raw