This repository has been archived on 2026-03-24. You can view files and clone it. You cannot open issues or pull requests or push a commit.

Kimi Agent b9b78adaa2 perf: eliminate redundant LLM calls in agentic loop (#24) ...

Three optimizations to the agentic loop:
1. Cache loop agent as singleton (avoid repeated warmups)
2. Sliding window for step context (last 2 results, not all)
3. Replace summary LLM call with deterministic summary

Saves 1 full LLM inference call per agentic loop invocation
(30-60s on local models) and reduces context window pressure.

Also fixes pre-existing test_cli.py repl test bugs (missing result= assignment).

2026-03-14 20:55:52 -04:00

3.5 KiB

Raw Blame History

View Raw