zap 6642964ae6 docs(cost): add inference cost optimization plan — 4 phases ...

Phase 1: Enable prompt caching (cacheRetention: long on Claude models)
Phase 2: Heartbeat cache warming (25m main, 55m default)
Phase 3: Context pruning (cache-ttl mode, 1h TTL)
Phase 4: Cheaper models for subagents (GLM-4.7 free tier for bulk work)

All config-only, no OpenClaw code changes, fully reversible.

2026-03-05 20:20:03 +00:00

memory

docs(cost): add inference cost optimization plan — 4 phases

2026-03-05 20:20:03 +00:00

overlays

…

scripts

feat(scripts): add ops and mcp sentinel automation scripts

2026-03-05 02:17:32 +00:00

skills

feat(council): add D/P (Deterministic/Probabilistic) dual-group mode

2026-03-05 19:18:44 +00:00

.gitignore

chore(gitignore): allow tracking memory directory

2026-03-05 02:19:39 +00:00

AGENTS.md

docs(agents): no auto-push; commit proactively but push only when asked

2026-03-05 04:48:34 +00:00

BOOT.md

…

HEARTBEAT.md

…

IDENTITY.md

…

litellm-config.patched.yaml

…

MEMORY.md

docs(prefs): update git preference — auto-commit yes, auto-push no

2026-03-05 04:49:02 +00:00

SOUL.md

…

TOOLS.md

…

USER.md

docs(prefs): update git preference — auto-commit yes, auto-push no

2026-03-05 04:49:02 +00:00

Description

No description provided

591 KiB

Languages

Shell 61%

Python 28%

JavaScript 6.2%

Clojure 3.5%

TypeScript 1.3%