Cache Warmer
Fork-based prompt-cache warmer for Claude Code. Keeps long sessions warm in the Anthropic prompt cache without modifying them: idle sessions nearing cache expiry are warmed through disposable interactive forks, with per-warm cache_read receipts proving each refresh worked.
- Zero session impact — live transcripts verified byte-identical before/after warming
- Empirical TTL measurement from session history (measure-ttl.py, zero API spend)
- Self-verifying: every warm logs the measured cache_read token count
- Disproved two naive approaches empirically (print-mode pings, local heartbeat files)
- ~20x cheaper resume on large sessions vs paying a cold cache re-write
Activity Timeline
- v3 hardening: 10 commits closing 5 Sol-review defects; v2 engine blocked.
Fixed fallback interaction guards, honest cap reporting, capture store consolidation, human-turn counting, and malformed session-id rejection. Install script updated to v3; v2 explicitly refused at entry.
- Output capping and capture retention enforcement shipped (bq-314, bq-315).
Replay warm generation now caps output. Capture retention enforcement wired into proxy independent of ENABLED status.
- RC bridge deregistration bug diagnosed and worked around; full reverse proxy fix specified.
Proxy's 404 on RC availability checks caused silent session deregistration from the bridge. Workaround: unset ANTHROPIC_BASE_URL before RC session registration. Full fix (true reverse proxy + Account B opt-in warming) specified, awaiting test pass with throwaway session.
- v0.4.1 released: fixed transient-failure chain break.
Reliability patch applied after review hardening. Transient failures were causing chain breaks that interrupted cache warming sequences.
- v0.4.0: v3 replay architecture replaces deprecated fork-warming.
Fork-warming deprecated in Claude Code ≥2.1.198. v3 replay is now the primary mechanism. Clean architectural succession.
- v0.3.3 released; adversarial hardening complete; GitHub release queued for Codex Pro review.
Fork startup prompt handling added for large MCP sessions; busy and remote-control session behavior improved. End-to-end testing passed with transparent cache refresh and no session state side effects.
- Built, verified, and open-sourced the fork-based cache warmer in a single day.
Investigated a pending cache-warming idea, measured the effective prompt-cache TTL (~1h cliff) from session history, discovered that print-mode pings cannot refresh an interactive session's cache, and landed on disposable interactive forks as the zero-impact mechanism. Published to GitHub with a TTL measurement tool and systemd timer install.