From 58fe43f9730542dcc342d8455bba0b936a772b29 Mon Sep 17 00:00:00 2001 From: Ty Date: Mon, 3 Aug 2026 18:12:59 +0000 Subject: [PATCH] Log first scored Leonard GBP ingest run: DS4FLASH0731, Overcome Fitness, 9/10 PASS (2026-08-03) --- docs/operations/task-reliability-ledger.md | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/docs/operations/task-reliability-ledger.md b/docs/operations/task-reliability-ledger.md index b76764c..4aa19a6 100644 --- a/docs/operations/task-reliability-ledger.md +++ b/docs/operations/task-reliability-ledger.md @@ -11,7 +11,7 @@ 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; form/template/card at v1.1 as of 2026-08-03 | +| gbp_snapshot_ingest_r1_r3 | 1 | 0 | — | First scored run 2026-08-03 DS4FLASH0731; 9/10 PASS; minor phone redaction + template shape | | 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 | @@ -26,10 +26,13 @@ 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 formal scored Leonard runs yet | +| 2026-08-03 | DS4FLASH0731 (Leonard caveman) | Overcome Fitness | gbp_snapshot_ingest_r1_r3 | 9/10 | No | Yes | Director (Grok) | R1+R2 correct; R3 correctly not fired. Phone partially redacted (not in intake). Flat table vs inventory Notes format (template 1/2). Severity “Standard” on completeness vs register Major. | **Pass:** no zeros and total ≥ 7/10. +**Rubric detail (this run)** +Evidence 2 · Tier 2 · Scope 2 · Recency 2 · Template 1 + --- ## Process log (first real client) @@ -43,10 +46,11 @@ Until a task type has documented runs, human approval remains required before an 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). +7. **First scored Leonard run:** DS4FLASH0731, inlined execution rules (no repo file access), caveman mode. **9/10 PASS.** Logged above. **Agents involved** -- Director (Grok) led mapping and commits following execution-card constraints. -- Leonard local model **not yet** run/scored on this intake. +- Director (Grok) led mapping, commits, scoring. +- Leonard = DS4FLASH0731 (first scored ingest). **Artifacts** - `docs/clients/overcome-fitness/data-inventory-v1.md` @@ -57,8 +61,9 @@ Until a task type has documented runs, human approval remains required before an - `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. +- Human accept Draft Benchmark or request edits. +- Optional: re-run on RTX 3060 target model with same intake; compare scores. +- Optional: deeper social/website surfaces. ---