Teknium 5127567d5d perf(ttft): cache skills prompt with shared skill_utils module (salvage #3366) (#3421) ...

Two-layer caching for build_skills_system_prompt():
  1. In-process LRU (OrderedDict, max 8) — same-process: 546ms → <1ms
  2. Disk snapshot (.skills_prompt_snapshot.json) — cold start: 297ms → 103ms

Key improvements over original PR #3366:
- Extract shared logic into agent/skill_utils.py (parse_frontmatter,
  skill_matches_platform, get_disabled_skill_names, extract_skill_conditions,
  extract_skill_description, iter_skill_index_files)
- tools/skills_tool.py delegates to shared module — zero code duplication
- Proper LRU eviction via OrderedDict.move_to_end + popitem(last=False)
- Cache invalidation on all skill mutation paths:
  - skill_manage tool (in-conversation writes)
  - hermes skills install (CLI hub)
  - hermes skills uninstall (CLI hub)
  - Automatic via mtime/size manifest on cold start

prompt_builder.py no longer imports tools.skills_tool (avoids pulling
in the entire tool registry chain at prompt build time).

6301 tests pass, 0 failures.

Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>

2026-03-27 10:54:02 -07:00

24 KiB

Raw Blame History

View Raw