docs: update README test status

[Deva4287]

What this PR does

Updates the README to accurately describe the project's current test coverage.

• Documents the 7 tests in index_notes.py
• Clarifies that brain_ask.py and turnstate_hook.py have no tests
• Removes the outdated reference to closed issue No tests: add a smoke test that runs without downloading a model #2

Closes #3

[tonydzi]

hi, this is Mycroft, Anton's synthetic co-founder — I handle inbound on this repo.

The 49-hour silence is on us, and the cause is unglamorous: the watcher that surfaces inbound threads runs once a day on a single laptop and skipped a day. An issue about a stale claim, answered late, by a project about memory. I have chosen not to think about that too hard.

Your read of the issue is right, and the substance of the patch is correct: index_notes.py has 7 tests, the other two modules have none, and I verified that locally on your branch — 7 passed, merges clean on main.

Verdict: not merging this revision, but the work is good — three small things and it goes in.

1. README.md:91 picked up trailing whitespace on ## Quickstart.
2. [docs/bitemporal.md](docs/bitemporal.md) lost its backticks. The schema.sql link two lines above keeps them, so this reads as drift rather than a choice.
3. The real one, and it is the same defect as the issue you fixed. The paragraph you edited opens with "open issues rather than footnotes" and points at #1. #1 was closed on 5 September — five days before your PR. So the sentence still makes a false claim about the repo, in the same direction, in the paragraph you were already standing in. That is not a miss I blame you for; it is what the issue was actually about, and it is worth seeing.

For the status line, this scans better than the run-on we both ended up with:

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 and makes no attempt to be general — index_notes.py has 7 tests, brain_ask.py and turnstate_hook.py have none.

Push whenever suits you. If it is not up by Monday 15 September I will land your commits and do those three myself rather than let your work sit — your authorship stays either way.

One open question, and it is the interesting half: both issues the README names by number are now closed. Should a README name issue numbers at all, given they rot exactly like the "no tests" line did — or is the honest move to describe the gap and let the tracker hold the numbers? You have now been bitten by this twice in one file, so your answer is worth more than mine.

— TonyDzi (Palo Alto AI Research Lab) · the rest of the machine — second brain, fleet coordination, persistent memory — is at github.com/tonydzi, DMs open.