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

CUST-WP-0075-T03: route human gates to hub decisions; encode human gate on TD-WP-0003-T07

Browse source 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 3775@bnt-lap001
Assistant-Session: cfacb6a5-ad5b-4f79-ac67-053e3b0d34a3
This commit is contained in:
tegwick 2026-10-03 03:35:00 +02:00
parent b0bac44aef
commit fe28966063
3 changed files with 15 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
WORK-RECORDS.md
View file

@ -31,7 +31,7 @@
| task | TD-WP-0003-T04 | done | — | workplans/TD-WP-0003-generalise-and-settle.md |
| task | TD-WP-0003-T05 | done | — | workplans/TD-WP-0003-generalise-and-settle.md |
| task | TD-WP-0003-T06 | wait | — | workplans/TD-WP-0003-generalise-and-settle.md |
| task | TD-WP-0003-T07 | wait | — | workplans/TD-WP-0003-generalise-and-settle.md |
| task | TD-WP-0003-T07 | todo | — | workplans/TD-WP-0003-generalise-and-settle.md |
| task | TD-WP-0003-T08 | done | — | workplans/TD-WP-0003-generalise-and-settle.md |
| task | TD-WP-0004-T01 | done | — | workplans/TD-WP-0004-scope-evidence-and-variants.md |
| task | TD-WP-0004-T02 | done | — | workplans/TD-WP-0004-scope-evidence-and-variants.md |

14
workplans/TD-WP-0003-generalise-and-settle.md
View file

@ -86,6 +86,7 @@ consumes the kernel as a library. Two consequences for this workplan:
id: TD-WP-0003-T01
status: wait
needs_human: true
decision_id: b6a44b55-8d10-4b96-8a71-524a0c34d2f3
blocking_reason: "Bounded live-model experiment: run count and cost ceiling agreed with the operator before the first call."
priority: high
state_hub_task_id: "0090ce51-0086-5079-a094-fb63b3b53415"
@ -119,6 +120,8 @@ the suite deterministic and free, run the live arm on demand).
**2026-09-28 closeout — wait.** Await an explicit model, fixed run count, cost ceiling and suite policy from Bernd Worsch before the first live call. No live calls or costs were incurred; local heuristic evidence cannot close capability/economics.
2026-10-03: human gate routed to hub decision b6a44b55-8d10-4b96-8a71-524a0c34d2f3 (D11: Operator setups with low fan-in: test-driver live-model budget and Playwright, fin-hub Qonto/DATEV confirmation) by CUST-WP-0075; resolving that decision raises C-40 here.
## Two further use cases
```task
@ -228,6 +231,7 @@ consumes `Claim` directly.
id: TD-WP-0003-T06
status: wait
needs_human: true
decision_id: b6a44b55-8d10-4b96-8a71-524a0c34d2f3
blocking_reason: "Operator establishes Playwright and clears its licence."
priority: low
state_hub_task_id: "19f8e687-0ab2-5650-9efa-4eba3cb25d12"
@ -250,12 +254,16 @@ the surface is for.
**2026-09-28 closeout — wait.** Still requires the existing Playwright setup/licence decision and T01 live-model prerequisite. T02/T03 are now complete. Structural HTML results do not satisfy the browser-engine/visual experiment.
2026-10-03: human gate routed to hub decision b6a44b55-8d10-4b96-8a71-524a0c34d2f3 (D11: Operator setups with low fan-in: test-driver live-model budget and Playwright, fin-hub Qonto/DATEV confirmation) by CUST-WP-0075; resolving that decision raises C-40 here.
## Measure the cost of expressing a use case
```task
id: TD-WP-0003-T07
status: todo
depends_on: [TD-WP-0003-T02]
status: wait
needs_human: true
decision_id: b6a44b55-8d10-4b96-8a71-524a0c34d2f3
blocking_reason: "Needs an independently timed fresh implementation by an author who does not copy the fixtures."
priority: medium
state_hub_task_id: "62f08e27-f307-560f-9583-64c08835e29e"
```
@ -275,7 +283,7 @@ first. It cannot be reconstructed later.
**2026-09-28 closeout — wait.** Partial evidence only: concepts, adapter friction, line counts and raw timer receipts recorded in docs/TestDriverGeneralisationReview.md and research/evidence/2026-09-28-authoring.json. Timer placement missed code composition, so first-authoring elapsed costs are invalid and cannot be reconstructed. Await an independently timed fresh implementation by an author who does not copy these fixtures; retain this task, no replacement record.
2026-10-03: every depends_on target is terminal (C-40); cleared to todo by CUST-WP-0075.
2026-10-03: the depends_on target T02 is done, so C-40 read this as satisfied; the real gate (a fresh, independently timed author) was prose only. CUST-WP-0075 encoded it as a human gate routed to hub decision b6a44b55-8d10-4b96-8a71-524a0c34d2f3 (D11) and returned the task to wait.
## Readiness review for real-system application

4
workplans/TD-WP-0004-scope-evidence-and-variants.md
View file

@ -8,7 +8,7 @@ status: blocked
owner: codex
topic_slug: custodian
created: "2026-09-28"
updated: "2026-09-28"
updated: "2026-10-03"
state_hub_workstream_id: "efd2200b-4856-5655-a010-0c3b3a858391"
---
@ -93,6 +93,7 @@ Register/sync records and commit/push implementation and documents.
id: TD-WP-0004-T05
status: wait
needs_human: true
decision_id: b6a44b55-8d10-4b96-8a71-524a0c34d2f3
blocking_reason: "Operator/target-owner-selected system and approved bounded engagement."
priority: high
state_hub_task_id: "aeacea6b-20db-5dd6-9585-4d7fefe412a2"
@ -114,6 +115,7 @@ duplicate those tasks. Longer-term concurrency, resilience fault scheduling and
multi-step artifact generation are follow-on decisions informed by the pilot,
not implementation commitments in this bounded workplan.
2026-10-03: human gate routed to hub decision b6a44b55-8d10-4b96-8a71-524a0c34d2f3 (D11: Operator setups with low fan-in: test-driver live-model budget and Playwright, fin-hub Qonto/DATEV confirmation) by CUST-WP-0075; resolving that decision raises C-40 here.
## Local implementation closeout — 2026-09-28