From 2eb5fe54f9c4102313107b96941b5b7c3942ba2d Mon Sep 17 00:00:00 2001 From: Deva4287 Date: Thu, 10 Sep 2026 15:49:08 +0530 Subject: [PATCH 1/2] docs: update README test status --- README.md | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index 161b6fc..1a4f587 100644 --- a/README.md +++ b/README.md @@ -8,10 +8,9 @@ scripts — `index_notes.py`, `brain_ask.py`, `turnstate_hook.py` — that give SQLite is the only database ([`schema.sql`](schema.sql)) and `[[wikilinks]]` are the graph. Status: **pilot**, and the word is load-bearing: it runs daily in one real setup (a ~100k-note -Obsidian vault driven by Claude Code), but it is deliberately minimal, has no tests, and makes -no attempt to be general — see [What's intentionally missing](#whats-intentionally-missing). -Published as the companion code for an upcoming write-up on lightweight Graph RAG for agents; -the one design note that is already written is [`docs/bitemporal.md`](docs/bitemporal.md). +Obsidian vault driven by Claude Code), but it is deliberately minimal, has 7 tests for +`index_notes.py`, while `brain_ask.py` and `turnstate_hook.py` have none, and makes no +attempt to be general — see [What's intentionally missing](#whats-intentionally-missing). ## Why @@ -83,10 +82,11 @@ an edge table only when hop depth or corpus size demands it. - No entity lane. The production setup has an extra retrieval lane over people/project cards; it is too entangled with personal data to publish. -- No incremental indexing, no eval suite, no packaging, and no tests — the status line - above says **pilot** on purpose. +- No incremental indexing, no eval suite, and no packaging; `index_notes.py` has 7 tests, + while `brain_ask.py` and `turnstate_hook.py` have none — the status line above says + **pilot** on purpose. -## Quickstart +## Quickstart ```bash pip install -r requirements.txt @@ -147,12 +147,11 @@ The pilot as it runs daily: retrieval pipeline, per-turn ledger and A/B telemetr open issues rather than footnotes: [#1](https://github.com/tonydzi/sqlite-graph-memory/issues/1) (the indexer ingests `.stversions` backups, sync-conflict copies and `.obsidian` junk as if they were notes) -and [#2](https://github.com/tonydzi/sqlite-graph-memory/issues/2) (no tests at -all — 677 lines of it). +and the former #2 test gap is now closed: `index_notes.py` has 7 tests, +while `brain_ask.py` and `turnstate_hook.py` have none. **Next:** -- **A smoke test that runs without downloading a model** ([#2](https://github.com/tonydzi/sqlite-graph-memory/issues/2)) — until that exists, "pilot" is the only word this repo is entitled to. - **Ignore rules for the indexer** ([#1](https://github.com/tonydzi/sqlite-graph-memory/issues/1)). - **v0.2**: a public benchmark — a synthetic 200–500 note mini-vault with real wikilinks, ~200 hand-labeled queries stratified by type (entity / theme / bridge / compare / From 6e438436e058cbaac02948b6d5ba91fac79a8dff Mon Sep 17 00:00:00 2001 From: Deva4287 Date: Thu, 10 Sep 2026 16:12:06 +0530 Subject: [PATCH 2/2] docs: restore README context --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 1a4f587..632ea03 100644 --- a/README.md +++ b/README.md @@ -11,6 +11,8 @@ Status: **pilot**, and the word is load-bearing: it runs daily in one real setup Obsidian vault driven by Claude Code), but it is deliberately minimal, has 7 tests for `index_notes.py`, while `brain_ask.py` and `turnstate_hook.py` have none, and makes no attempt to be general — see [What's intentionally missing](#whats-intentionally-missing). +Published as the companion code for an upcoming write-up on lightweight Graph RAG for agents; +the one design note that is already written is [docs/bitemporal.md](docs/bitemporal.md). ## Why