SecondBrain/reference/memsearch-sessionstart-inje...

1.6 KiB
Raw Permalink Blame History

summary tags scope type source date last_updated
memsearch's SessionStart "Recent Memory" injection size is hardcoded in its hook script — no config knob controls it, and the documented TOML surface doesn't cover it.
type/reference
tool/memsearch
global reference cc-os docs/plans/b3-memsearch-injection-review.md 2026-07-08 2026-07-08

memsearch SessionStart injection is hardcoded (no cap knob)

Verified on memsearch v0.4.6 and the v0.4.11 plugin cache (2026-07-08).

  • The SessionStart # Recent Memory injection is produced by hooks/session-start.sh, which hardcodes head -2 daily memory files × head -40 heading/bullet lines each.
  • No user-facing config knob controls this. The documented TOML surface (the memory-config skill: summarize / project_review / user_profile / memory_to_skill / prompts) does not touch the injection size — don't waste time looking for a cap there.
  • Measured cost across 61 real sessions (cc-os, 7 days): min ~6.0 KB / median ~11.7 KB / max ~15.4 KB per session (~1.5k3.9k tokens), injected every SessionStart.

Levers (in order of durability)

  1. Upstream fix: a memsearch config option for injection size (doesn't exist yet; would be the only durable cap).
  2. Reduce bullet density at the source via the Stop-hook summarizer prompts/config — fewer, denser bullets in the daily files shrink what head -40 captures.
  3. Unsupported stopgap: hand-edit the cached hook's head -2/head -40 constants (~75% reduction) — any plugin cache refresh silently reverts it.

Related: cc-os-hub