root/fusion
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(prompts): require lint alongside tests and typecheck in agent instructions

Browse Source 
Every agent-facing quality gate that used to pair tests with typecheck now
also includes lint. Specifically:

- core/src/types.ts: QA Check skill prompt runs lint, tests, typecheck (was
  tests only) and gates task_done() on all three.
- core/src/agent-prompts.ts + engine/src/reviewer.ts: "Do NOT issue REVISE"
  exclusion list now covers lint as well, so out-of-scope fixes that
  restore lint remain allowed (matches the already-lint-aware completion
  gate text at the top of the same prompts).
- engine/src/executor.ts: task_done() pre-flight checklist adds an explicit
  "if the repo has a lint command, run it and fix failures" bullet, mirrors
  the typecheck bullet, and expands the CRITICAL line from "ALL test
  failures" to "ALL lint, test, and typecheck failures".
- core/src/store.ts: default Step 2 checklist (Testing & Verification) now
  includes Lint and Typecheck alongside "All tests pass".
- cli/src/commands/plugin-scaffold.ts: generated plugin README and the
  "Next steps" CLI output include \`pnpm lint\` between install and test.

Existing prompts that already paired lint with tests+typecheck (the
Completion section, hard quality gates, triage testing requirements) are
unchanged.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Fusion
2026-04-23 19:35:51 -07:00
committed by gsxdsm
parent 8def13ee2e
commit d62bf8e24c
12 changed files with 334 additions and 128 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
packages/engine/src/executor.ts
View File

@@ -4930,9 +4930,11 @@ When all steps are complete: call \`task_done()\`
If a build command is configured, run that exact command in this worktree before calling \`task_done()\`.
Treat a non-zero exit code as a blocking failure. Do not claim success without a real passing run.
Run the configured/full test suite and fix failures even when that requires edits outside the original File Scope.
If the repo has a lint command (e.g. \`pnpm lint\`, \`npm run lint\`), run it before \`task_done()\` and fix any failures it reports.
If the repo has a typecheck command, run it before \`task_done()\` and fix any failures it reports.
Use \`task_create\` for truly separate follow-up work, not for fixes required to get tests, build, or typecheck back to green.
**CRITICAL: Resolve ALL test failures before completing the task, even if they appear unrelated or pre-existing.** Unrelated failures left unfixed accumulate technical debt and block future integrations. Investigate and fix or suppress them — do not defer them to a separate task.`;
If lint is configured and failing, fix that too before completion.
**CRITICAL: Resolve ALL test failures (and any lint/typecheck failures) before completing the task, even if they appear unrelated or pre-existing.** Unrelated failures left unfixed accumulate technical debt and block future integrations. Investigate and fix or suppress them — do not defer them to a separate task.`;
}
/**

2
packages/engine/src/reviewer.ts
View File

@@ -54,7 +54,7 @@ access to the codebase and can run commands to inspect code.
### Do NOT issue REVISE for
- STATUS/formatting preferences
- Splitting outcome checkboxes into implementation sub-steps
- Necessary fixes outside the initial File Scope when they are required to restore green tests, build, or typecheck and do not delete/gut unrelated functionality
- Necessary fixes outside the initial File Scope when they are required to restore green lint, tests, build, or typecheck and do not delete/gut unrelated functionality
- Suggestions that improve quality but aren't required for correctness
## Plan Review Format