2.5 KiB
Scene Skill 102 Pseudo-Production Batch Execution Preparation Design
Date: 2026-04-20 Parent:
2026-04-20-scene-skill-102-pseudoprod-batch-selection-plan.md
Intent
Prepare the first pseudo-production execution batch without running it.
This design defines environment handoff requirements, evidence collection rules, and execution record templates for the 10 selected scenes from the batch selection plan.
Fixed Batch
The execution preparation batch is fixed by:
tests/fixtures/generated_scene/scene_skill_102_pseudoprod_batch_selection_2026-04-20.json
The batch contains 10 scenes across:
paginated_enrichment: 4multi_mode_request: 2single_request_enrichment: 2multi_endpoint_inventory: 1page_state_eval: 1
Preparation Only
This design does not allow real execution.
It only prepares:
- environment handoff checklist
- evidence package layout
- per-scene execution record template
- failure taxonomy mapping
- operator instructions
Environment Handoff Requirements
The operator must provide or confirm these outside the repository:
- target browser or quasi-production host
- network access to required internal endpoints
- valid login/session state where needed
- allowed output directory for downloaded/exported artifacts
- console log capture method
- network log capture method
- screenshot capture method
No credentials, tokens, cookies, or secrets should be stored in the repository.
Evidence Package Layout
Each scene should use a local evidence folder outside tracked credentials:
pseudoprod_evidence/
<scene-id>/
execution-record.json
console.log
network-summary.json
screenshot.png
exported-artifact.*
notes.md
The repository may store templates and redacted summaries, but not sensitive raw credentials or session material.
Execution Result States
Each scene must resolve to one of:
pseudo-prod-passlogin-blockednetwork-blockedhost-bridge-blockedlocal-doc-runtime-blockeddata-mismatchartifact-mismatchenvironment-unavailableruntime-error
Forbidden Scope
This design does not allow:
- running browser automation
- invoking real target systems
- storing credentials
- modifying generated skills
- modifying
analyzer.rs,generator.rs, dispatch, or runtime code - updating official board status
Expected Outputs
- environment handoff checklist JSON
- per-scene execution record template JSON
- evidence checklist JSON
- preparation report