From eb2cdc887193a5a47cdc0d7ff8288c7c99da33ec Mon Sep 17 00:00:00 2001 From: jared Date: Tue, 9 Jun 2026 13:29:55 -0400 Subject: [PATCH] Sharpen memsearch spec: memory_dir target, skill default, scope boundary Co-Authored-By: Claude Sonnet 4.6 --- .../specs/2026-06-09-memsearch-episodic-layer-design.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/docs/superpowers/specs/2026-06-09-memsearch-episodic-layer-design.md b/docs/superpowers/specs/2026-06-09-memsearch-episodic-layer-design.md index d9f60a8..00d939b 100644 --- a/docs/superpowers/specs/2026-06-09-memsearch-episodic-layer-design.md +++ b/docs/superpowers/specs/2026-06-09-memsearch-episodic-layer-design.md @@ -33,7 +33,7 @@ Ships with its own Stop hook (fires after each response turn), its own Claude gu After install, run `memsearch config list` to audit actual defaults before changing anything. -The one setting to verify: **memory_dir**. memsearch's Milvus database defaults to `~/.memsearch/milvus.db` (global). If memory_dir also defaults to a global path, no config change is needed. If it defaults to project-local (`.memsearch/memory/`), set it to `~/.memsearch/memory/` so all projects share one episodic store — essential for cross-project recall. +The one setting to confirm: **memory_dir** must be global (`~/.memsearch/memory/`) so all projects share one episodic store — essential for cross-project recall. Run `memsearch config list` after install; if memory_dir is not already global, set it explicitly in `~/.memsearch/config.toml`. memsearch's Milvus database already defaults to a global path (`~/.memsearch/milvus.db`), so memory_dir may match — verify rather than assume. All other defaults are kept: - Embedding: ONNX bge-m3-onnx-int8 (CPU, no API key, ~558MB one-time download) @@ -41,7 +41,7 @@ All other defaults are kept: ### 3. Built-in Guidance Audit -memsearch ships as a full Claude Code plugin and likely includes its own system prompt instructions telling Claude when and how to use `memsearch search`. After install, audit what it adds to Claude's context. Add a custom `memory-search` skill only if there are genuine gaps in the built-in guidance or conflicts with the existing `memory-vault`/`memory-project` skill boundary. +memsearch ships as a full Claude Code plugin and likely includes its own system prompt instructions telling Claude when and how to use `memsearch search`. After install, audit what it adds to Claude's context. The default outcome of this audit is **no custom skill**. Only create a `memory-search` skill if memsearch's built-in guidance fails to cover cross-project episodic queries, or if it creates ambiguity with the `memory-vault`/`memory-project` skill boundary (e.g., Claude routing knowledge questions to memsearch instead of Graphify). ## Data Flow @@ -78,6 +78,7 @@ The existing hook writes vault provenance (which vault notes were touched, proje - Does not add custom hook code - Does not configure Milvus Server or Zilliz Cloud (Milvus Lite is correct for personal use) - Does not integrate memsearch recall into SessionStart hook injection (deferred) +- Step 4 is complete when: plugin is installed, memory_dir is confirmed global, and at least one session has produced a daily memory file at `~/.memsearch/memory/YYYY-MM-DD.md`. SessionStart injection is a distinct future step. ## Installation Checklist