Repository navigation
Description
Slice 3 of #388. Depends on slice 2 (bootstrap declares harnesses.analysis for Cursor).
Problem
The setup UI offers Cursor as a ready coding agent with no hint that it can't plan. After slice 2 the bootstrap picks the planning agent itself, but the user can't see or change that choice in the UI.
Change
- Coding agent step: Cursor's card says it codes only and needs a second agent for planning.
- Planning agent choice: when the chosen coding agent can't plan, show the ready planning-capable agents (Claude Code, Codex) and let the user pick one. Default to slice 2's choice.
POST /api/setup/createtakes an optional planning harness and passes it toonboarding.Prepare, which declaresharnesses.analysison it, reusing slice 1/2 code. Refuse a planning harness that isn't ready or can't plan, with the adapter's reason. - Formula review step: show both bindings, "Plans with X · Codes with Y".
- Keep the existing UI conventions in
lab/internal/ui: no external assets, all text escaped, keyboard accessible, a visible focus state.
Done when
- UI handler tests cover the planning choice (default, explicit Claude Code, explicit Codex, refused unready or Cursor) and the review view showing both bindings.
- With no planning choice in the request, Claude Code and Codex setups behave exactly as before.
Review checklist (read before coding)
The adversarial review checks these every time. Recent slices failed review on all of them, so build them in from the start:
- Bounds: sizes, counts, time and total work are bounded, and hitting a bound fails safe (incomplete or truncated, never silently accepted).
- Filesystem safety: paths cannot traverse. Use
LstatandO_NOFOLLOW, and check symlinks and ownership. Watch for TOCTOU races on shared dirs (/tmp). Only ever delete Forgecell-owned, marked paths. - Untrusted input: issue text, repository files, model and tool output, and ledgers can be malformed, huge or hostile. Validate them, never interpolate them into HTML or a shell, and never let them trigger retries or approvals.
- No local leaks: no absolute local paths, environment variables or credentials in output, logs, the UI or ledgers.
- Contract changes: a changed adapter invocation bumps the protocol, and approved digests still bind exactly what was shown.
- Tests: deterministic. Use no wall-clock budgets (use readiness markers or seams), write nothing into the user's real temp or home, and cover the failure path as well as the happy path.
Plan checks (for intake)
Check category must be one of regression, candidate or setup. Use targeted package tests only as plain go test -timeout 20m commands (for example go test -timeout 20m ./internal/<pkg>/...; without -timeout, go test stops a package after 10 minutes, and cli and molecule exceed that on a loaded machine); the protected view adds -json itself when protected deltas are declared. The Formula baseline already runs the full suite once, so don't add another full go test ./... check, and don't repeat its go vet or gofmt checks. A plan may hold at most 16 checks in total, counting the 5 Formula baseline checks, so prefer one combined targeted command over one check per package.
- Keep base tests compiling: the protected view runs the base
_test.gofiles against your code. Never change the signature of an existing function, method or type that a base test file calls. Add a new function or field instead. A protected build failure can't be declared as an expected delta. - Keep base tests runnable: changed defaults or behaviour must not make a base test hang or panic. A package that aborts in the protected view hides every test after it, and nothing can be declared. Keep the old default when unconfigured and opt in to the new one.
- Plan checks: the operator's visual or browser check is a manual step after delivery, never a plan check. Every check leaves
reviewedAcceptanceandindependentProvenanceempty. - Plan structure: new files need a parent component (in this repo, under
lab/; a new root-level file blocks intake). A check'sdefinitionsmust never include a file the change edits. A file the check only reads as data under test is not a definition. - Scope lists files, not directories: list every new file path, including each golden fixture under
testdata/. A directory entry doesn't cover the files inside it, and the scope audit blocks them.
Activity
Setup UI: say Cursor needs a planning agent and let the user pick it (#…
DanielNetzer commentedon Nov 8, 2026
Merged as #419.