Tony_tech/veripath
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Log first real Overcome Fitness GBP cold-audit process run (2026-08-03). Form/template/card upgraded to v1.1. Inventory + threat register drafted. No formal Leonard scored run yet.

Browse Source
This commit is contained in:
Ty
2026-08-03 18:02:42 +00:00
parent 82d9318f66
commit 8767ee37dc
1 changed files with 35 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/operations/task-reliability-ledger.md
+35 -5
View File
@@ -11,9 +11,9 @@ Until a task type has documented runs, human approval remains required before an
| task_type | runs | errors | last_error_date | notes |
|-----------|------|--------|----------------|-------|
| gbp_snapshot_ingest_r1_r3 | 0 | 0 | — | Leonard execution card only |
| data_inventory_draft_l1a | 0 | 0 | — | Public baseline |
| threat_register_draft_l2 | 0 | 0 | — | Diagnosis only |
| gbp_snapshot_ingest_r1_r3 | 0 | 0 | — | Leonard execution card only; form/template/card at v1.1 as of 2026-08-03 |
| data_inventory_draft_l1a | 1 | 0 | — | Overcome Fitness public baseline written 2026-08-03 |
| threat_register_draft_l2 | 1 | 0 | — | Overcome Fitness; T-002 updated + T-011 added via R1/R2 |
| review_reply_draft | 0 | 0 | — | Not auto-publish |
| gbp_field_edit_draft | 0 | 0 | — | Not auto-publish |
| qa_answer_draft | 0 | 0 | — | Not auto-publish |
@@ -26,16 +26,46 @@ Until a task type has documented runs, human approval remains required before an
| date | agent | client | task_type | score_total | zeros? | pass? | reviewer | notes |
|------|-------|--------|-----------|-------------|--------|-------|----------|-------|
| — | — | — | — | — | — | — | — | No scored runs yet |
| — | — | — | — | — | — | — | — | No formal scored Leonard runs yet |
**Pass:** no zeros and total ≥ 7/10.
---
## Process log (first real client)
### 2026-08-03 — Overcome Fitness (first real non-Phoenix cold audit)
**What happened**
1. Human filled GBP observations (Maps) for Overcome Fitness.
2. Intake corrected live (booking button is on website, not GBP; services = strength training only; Updates/Posts present but empty; claimed status Unknown).
3. GBP snapshot form + intake template + Leonard execution card upgraded to **v1.1** so those fields are captured next time without chat back-and-forth.
4. Data Inventory GBP row written (Tier 2, Snapshot Date 2026-08-03).
5. Threat Register updated: T-002 evidence refreshed (R1); **T-011** added (R2 — unclear claimed + thin reviews).
6. Client README updated. Status remains **Draft Benchmark** (not Locked).
**Agents involved**
- Director (Grok) led mapping and commits following execution-card constraints.
- Leonard local model **not yet** run/scored on this intake.
**Artifacts**
- `docs/clients/overcome-fitness/data-inventory-v1.md`
- `docs/clients/overcome-fitness/threat-register-v1.md`
- `docs/clients/overcome-fitness/README.md`
- `tools/gbp-snapshot-form.html` (v1.1)
- `docs/templates/gbp-snapshot-intake.md` (v1.1)
- `docs/agents/leonard-gbp-execution-card.md` (v1.1)
**Next for this client**
- Human skim / accept Draft Benchmark or request edits.
- Optional: run same intake through Leonard (local model) and score vs rubric; log in scored-runs table.
---
## How to log a run
1. After human review of an agent draft, add one row to the appropriate table.
2. If the draft required material correction for an error (see definition), increment `errors` and set `last_error_date`.
3. Do not count unscored exploratory chat as a run.
**Last updated:** 2026-08-02
**Last updated:** 2026-08-03