I maintain two small open-source CLIs for working with AI agents. aisync is a local CLI for Multi-Agent Context Management, Coordination & Observability across AI coding tools. existence-trace is a journal that an AI reads, and it has to prove it used what it learned. This post tests the second one: its weekly audit, which the README sums up as "A weekly audit fails if a rule was never applied." I wanted to see when it fails and when it quietly passes.
I used a temporary HOME, so none of my real data was touched, and the v0.4.6 tag of existence-trace. It is not on PyPI, so I ran it straight from git:
export HOME="$(mktemp -d)"
uvx --from git+https://github.com/MaxonT/existence-trace@v0.4.6 etrace init
An empty week passes
Before I had written anything:
etrace audit weekly
{"week": "2026-W47", "passed": true, "broken": [], "scope_overlaps": [], ...}
There were no chains to check, so nothing was broken. That is fine as a rule, but it means a green audit tells you nothing about a week in which no feedback arrived.
A fresh decision passes without a receipt
The loop is feedback, then a decision with a rule change, then a usage receipt. I wrote one line in the "Feedback for the AI" block of today's note, "Keep the daily narrative to two sentences.", and ran etrace feedback ingest. The entry came back as pending. Then I stored a decision for it with etrace decide dec.json (a JSON file with feedback_ids, decision_text, value_source and one rule change). The rules went from version 9 to 10.
There was still no receipt, and the audit still passed. The report lists the decision under "Still open (not broken)":
decision D-20261116-1 is within the 2-day grace period
The grace period is GRACE = datetime.timedelta(days=2) in etrace/container/audit.py. So the README sentence is true after two days, not before.
Past the grace period it fails
I needed a decision that was three days old. The CLI has no option for that, but decisions.decide() takes a now argument, so I called it from Python in the temp data folder with a timestamp three days back, for a second feedback entry ("Ask about sleep before work when energy is low."). Then:
etrace audit weekly # passed: false, broken: ["2026-11-16:feedback:9c02e8d550dd"]
etrace validate; echo $?
decision D-20261113-1 is older than 2 days with no usage receipt and is not pending
1
The audit report says the same thing in its "Broken chains" section: decision D-20261113-1 has no usage receipt and is not pending. validate exits with 1, so a script can stop on it.
A receipt makes it pass
etrace usage add rec.json
The receipt has task, target, rule_version, before, after, status (changed), verified_readback (true) and the decision and feedback ids. After it was stored, audit weekly returned passed: true and validate exited 0. The report now includes a spot check for a person to read:
applied: U-20261116-1 (daily -> journal/2026-11-16.md, changed)
before: question order: free (the agent asked about work first)
after: questions for 2026-11-16 ask about sleep first
What this does not show
- I wrote the receipt myself. No AI rewrote a narrative or changed a question order in this run. The audit accepted a receipt whose
beforeandafterI typed, and it cannot know whether they are true. That is what the spot check is for: it samples one applied receipt and puts it in front of a person. - The three-day-old decision came from a Python call, not from three real days of use.
- One version (v0.4.6), one machine (macOS, arm64), uv, a synthetic journal with two entries.
- I did not test
scope_overlaps, the email intake, or the Notion mirror. - The empty-week result was filed as https://github.com/MaxonT/existence-trace/issues/4, with a suggestion to report how many chains were audited. I did not change the code myself.
- Update, 2026-11-16 09:21 CT: an outside contributor, i-sayankh, fixed that in https://github.com/MaxonT/existence-trace/pull/8, merged on
mainas 188b5a8. The v0.4.6 tag still behaves as shown above. Onmain, an empty week now reads "Result: passed (0 chains this week, nothing was audited)." and the JSON has achains_auditedfield. I read the diff and ran the test suite on the PR branch (650 tests OK), but I did not re-run this post's runs against the new code.
If you build something like this
Decide what an empty period should report, and say how long a rule may wait before it counts as ignored. In existence-trace both answers are visible in the audit report, and the second one is a constant in the source.
- Repo (MIT): https://github.com/MaxonT/existence-trace
- Site: https://maxont.github.io/existence-trace/
- Sibling project: https://github.com/MaxonT/aisync (Multi-Agent Context Management, Coordination & Observability)
This post and the test runs were written and run by an AI agent (Claude Code) for the maintainer. The outputs above are copied from those runs.
Top comments (0)