coulomb/frontend-patterns
5
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Preregister fresh atomic-criteria replication with 12-call budget

Browse source 
Assistant: codex
Assistant-Model: gpt-6.1-sol
Assistant-Session: 01a1045b-933d-7aa1-b2db-104557487a79
This commit is contained in:
tegwick 2026-10-04 11:08:31 +02:00
parent bd85fcd179
commit 1e2741a959
30 changed files with 2229 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

12
workplans/FEP-WP-0008-use-driven-improvement.md
View file

@ -312,3 +312,15 @@ integration still block it. T03's stale pre-scheduling blocker is replaced by it
remaining execution/publication acceptance, including ACTIVITY-WP-0041-T03.
All three tasks remain wait and this workplan remains blocked. No evidence gate,
policy, budget, authority or parked research workplan is changed.
## Gap-work consumer discovery — 2026-10-04
The user requested implementation of the assessed gaps. A bounded State Hub scan
joined 49 todo and 2 progress tasks to active/ready workplans and matched frontend,
interaction, editor/navigation/offline/component/designbook/keyboard/accessibility
text outside FEP. No candidate met that index filter. [Discovery receipt](../docs/evidence/2026-10-04-consumer-discovery.json)
records method and limits: this is not proof that no eligible consumer exists anywhere.
No external task was reopened or invented, and no synthetic event was enrolled.
T01/T02 retain actual source-verified task selection and common-template integration.
WP-0009's authorized fresh replication advances independent-validation preparation;
it does not replace the consumer decision/outcome acceptance in this plan.

22
workplans/FEP-WP-0009-m1-independent-validation.md
View file

@ -4,7 +4,7 @@ type: workplan
title: "Obtain independent validation for the M1 seed gate"
domain: infotech
repo: frontend-patterns
status: backlog
status: active
owner: codex
topic_slug: canon
origin: residual
@ -43,7 +43,7 @@ submitted-review-01 worksheet was a model review and does not count.
```task
id: FEP-WP-0009-T02
status: todo
status: progress
priority: medium
state_hub_task_id: "8e0ac763-eba4-5625-ad63-af53322bcac4"
```
@ -76,3 +76,21 @@ at T01's human gate here, or at external owners (GLAS-WP-0012, ACTIVITY-WP-0041)
an actual consumer for WP-0008. Those plans stay blocked; no task or workplan opened.
2026-10-04 CUST-WP-0075 owner routing: `FEP-WP-0009-T01` remains a human wait under open decision `6f698650-de45-4402-a84f-ea19ae5f96af`. Exact scoped human act and native receipts remain required; this metadata records no approval or execution.
## Gap implementation resumed — 2026-10-04
The user asked to work the assessed gaps, reopening this parked plan. Coverage audit:
WP-0008 owns real consumers/outcomes and admitted improvement; WP-0009 owns independent
validation/replication; WP-0003/0004 owns broader/gated applicability; WP-0006 owns
comparable learning. No uncovered ownership requires a duplicate workplan.
T02 starts with a fresh replication packet: authored variants separate from pilot-01,
atomic binary criteria, equivalent named/prose guidance, frozen release and input pins,
condition-isolated prompts and evidence-bearing scoring validation. Preparation makes
no inference call and cannot satisfy the independent human gate. Explicit paid-call
budget is requested separately; absent authorization, execution remains pending.
The user then explicitly authorized **up to 12 calls, 1,400 output tokens per call,
no retries**. This is the fresh replication budget only, not a grant for further model
reviews, autonomous editing, policy changes or human-score substitution. Freeze and
commit the packet/runner before execution; reserve every attempt and retain failures.