AutoForge/prompts/STATE.md

5.9 KiB

AutoForge orchestration state

Current handoff

Field Value
Updated 2026-10-28
Phase Initial orchestration complete; application foundation not started
Active step Step-01 - Repository and solution foundation
Assignment Step-01.md
Assignment status READY FOR WORKER / AWAITING MANUAL HANDOFF
Expected worker report prompts/Step-01-Report.md - not yet created
Last accepted step None
Outstanding corrections None
Worker execution Not invoked; user controls handoff
Immediate next action User manually directs the worker to execute Step-01 only
Next orchestrator action After manual return, inspect the assignment, report, implementation, tests, Git changes, documentation and recorded command evidence

Repository baseline

  • Repository: D:\_Repos\Code\GAJ3T\AutoForge.
  • Branch observed: main, tracking origin/main.
  • Initial worktree: clean.
  • Initial tracked files: root README.md and .gitignore.
  • No existing solution, projects, tests, docs, src, or prompts were present.
  • No applicable AGENTS.md was found in the repository or its ancestor locations.
  • No .github instruction files were found. In particular, .github/copilot-instructions.md was absent and must remain absent.
  • Existing README describes the product vision, not verified implemented features; Step-01 requires preserving it while making implementation status explicit.
  • Existing .gitignore already includes common Visual Studio/.NET build patterns. Worker must extend only where necessary and preserve existing entries.
  • Orchestrator changes are limited to prompts/ROADMAP.md, this file, and prompts/Step-01.md. Existing tracked files and Git metadata are preserved.

Architecture decisions in force

See ROADMAP.md for the full planned architecture and milestones.

  1. The repository has only three top-level project directories: docs, src, prompts; existing protected infrastructure is preserved. Tests are under src/tests. No root tests, root artifacts, or nested AutoForge directory.
  2. The worker creates src/AutoForge.slnx targeting .NET 10. Initial production projects are Core and Application; initial test projects are UnitTests and IntegrationTests. No unused placeholder assemblies.
  3. Step-01 is headless with real target-selection validation and composition tests. Simulation/diagnostics are introduced in Steps 02-04; both required UI shells and shared components/screens RCLs are introduced in Step-05.
  4. Domain logic is platform-neutral. Application use cases depend inward on Core. Hardware, inference, storage, and UI implementations never own domain truth.
  5. Simulation, replay, and physical hardware targets are explicit and cannot silently substitute for one another. Selection is not connection or execution.
  6. Synthetic data is labeled; simulation is deterministic and independent of AI, and verification uses an isolated oracle unavailable to ordinary UI/AI paths.
  7. AI plans are validated runbooks; no arbitrary hardware commands or offsets. Local inference is replaceable; core operation does not require AI/cloud.
  8. Initial hardware integration is read-only. Simulated approval, physical capability discovery, and driver availability cannot authorize physical writes. Bench and vehicle programming require separate future authorization/evidence.
  9. All handoffs are manual. Orchestrator never invokes the worker, implements application changes, or executes application builds/tests.
  10. The worker does not change the roadmap, state, or assignment; it may write only the current assignment's report under prompts. No automatic commits/pushes.

Prerequisites and known issues

  • The worker must inspect installed SDKs, templates and package compatibility before choosing exact versions. .NET 10 compatibility is not yet verified.
  • No major SDK/workload/driver installation has been authorized. Report exact missing prerequisites and mark blocked checks honestly; do not replace .NET 10 or either required UI architecture.
  • Step-01 does not need MAUI workloads, an AI model, containers, a vehicle, a native driver, or cloud infrastructure.
  • No confirmed implementation defects or environmental blockers are known because there is no implementation yet.
  • No application build or test has been executed by the orchestrator.

Review and progression gate

On manual return, evaluate every Step-01 acceptance criterion using the original assignment, worker report, actual code/tests, dependency graph, Git changes, README/docs, and recorded build/test evidence. Do not accept solely on a success claim; do not claim independent runtime verification.

  • If accepted: record the decision and evidence, update roadmap/state, create Step-02.md, and stop for manual handoff.
  • If deficient: create Step-01A.md with measurable corrections, update state, and stop. Further corrections use Step-01B.md, etc., with matching reports.
  • If blocked: retain the active step, document the prerequisite and required worker evidence; do not advance or mark unexecuted checks as successful.
  • Never create the next major assignment while acceptance or corrections are open.

History

Date Event Evidence / result
2026-10-28 Initial repository inspection Clean main; only root README and ignore file tracked; no application or protected instruction files found
2026-10-28 Initial roadmap, state, and Step-01 prepared Amendment layout/naming adopted; READY FOR WORKER, no implementation accepted

Manual handoff instruction

Provide Step-01.md to the separate worker and request execution of that assignment only. The worker must produce prompts/Step-01-Report.md and stop. Return manually to the orchestrator for review. Reports, including final chat reports, must follow the single plain triple-backtick copy-window requirement.