feat(FN-1540): add lint as inline quality gate in task prompts

- Add ESLint configuration (eslint.config.mjs) for TypeScript/JavaScript linting
- Update executor prompts to include lint instruction before code submission
- Add lint check to triage prompt validation workflow
- Update agent prompts to emphasize lint compliance as quality requirement
- Add lint tool to agent toolset with file-level rule disabling capability
- Include lint in CI workflow with non-blocking status
- Update tests to verify lint-inclusive prompt behavior
- Add documentation for lint integration in contributing.md
- Add changeset for @gsxdsm/fusion minor release

packages/core/src/agent-prompts.test.ts

@@ -124,15 +124,15 @@ describe("resolveAgentPrompt", () => {
     expect(result).toContain("task execution agent");
   });
 
-  it("built-in executor prompt requires resolving ALL test failures including unrelated", () => {
+  it("built-in executor prompt requires resolving ALL lint and test failures including unrelated", () => {
     const result = resolveAgentPrompt("executor");
     // The stricter language must be present to prevent "unrelated failure" deferrals
-    expect(result).toContain("Resolve ALL test failures");
+    expect(result).toContain("Resolve ALL lint failures and test failures");
     expect(result).toContain("even if they appear unrelated or pre-existing");
     expect(result).toContain("do not defer them to a separate task");
   });
 
-  it("senior-engineer prompt requires resolving ALL test failures including unrelated", () => {
+  it("senior-engineer prompt requires resolving ALL lint and test failures including unrelated", () => {
     const config: AgentPromptsConfig = {
       roleAssignments: {
         executor: "senior-engineer",
@@ -140,7 +140,7 @@ describe("resolveAgentPrompt", () => {
     };
 
     const result = resolveAgentPrompt("executor", config);
-    expect(result).toContain("Resolve ALL test failures");
+    expect(result).toContain("Resolve ALL lint failures and test failures");
     expect(result).toContain("even if they appear unrelated or pre-existing");
     expect(result).toContain("do not defer them to a separate task");
   });

packages/core/src/agent-prompts.ts

@@ -102,7 +102,7 @@ If you attempt to write to a path outside the worktree, the file tools will reje
 - Treat the File Scope in PROMPT.md as the expected starting scope, not a hard boundary when quality gates fail
 - Read "Context to Read First" files before starting
 - Follow the "Do NOT" section strictly
-- If tests, build, or typecheck fail and the fix requires touching code outside the declared File Scope, fix those failures directly and keep the repo green
+- If tests, lint, build, or typecheck fail and the fix requires touching code outside the declared File Scope, fix those failures directly and keep the repo green
 - Use \`task_create\` for genuinely separate follow-up work, not for mandatory fixes required to make this task land cleanly
 - Update documentation listed in "Must Update" and check "Check If Affected"
 - NEVER delete, remove, or gut modules, interfaces, settings, exports, or test files outside your File Scope
@@ -139,7 +139,7 @@ spawn_agent({
 - Max 20 total spawned agents system-wide (configurable via settings)
 
 ## Completion
-After all steps are done, tests pass, typecheck passes, and docs are updated:
+After all steps are done, lint passes, tests pass, typecheck passes, and docs are updated:
 \`\`\`bash
 Call \`task_done()\` to signal completion.
 \`\`\`
@@ -149,11 +149,11 @@ If a project build command is listed in the prompt, it is a hard completion gate
 - Do not claim the build passes unless you actually ran it and got exit code 0
 - If the build fails, do NOT call \`task_done()\`; keep working until it passes
 
-Tests and typecheck are also hard quality gates:
-- Keep fixing failures until the configured/full test suite passes
+Lint, tests, and typecheck are also hard quality gates:
+- Keep fixing failures until lint, the configured/full test suite, and typecheck all pass
 - If the repository exposes a typecheck command, run it and keep fixing failures until it passes
-- Do not stop at "out of scope" if additional fixes are required to restore green tests, build, or typecheck
-- **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.`;
+- Do not stop at "out of scope" if additional fixes are required to restore green lint, tests, build, or typecheck
+- **CRITICAL: Resolve ALL lint failures and 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.`;
 
 const TRIAGE_PROMPT_TEXT = `You are a task specification agent for "fn", an AI-orchestrated task board.
 
@@ -221,8 +221,9 @@ Follow this structure exactly:
 ### Step {N-1}: Testing & Verification
 
 > ZERO test failures allowed. Full test suite as quality gate.
-> If keeping tests/build/typecheck green requires edits outside the initial File Scope, make those fixes as part of this task.
+> If keeping lint/tests/build/typecheck green requires edits outside the initial File Scope, make those fixes as part of this task.
 
+- [ ] Run lint check (\`pnpm lint\`)
 - [ ] Run full test suite
 - [ ] Run project typecheck if available
 - [ ] Fix all failures
@@ -244,6 +245,7 @@ Follow this structure exactly:
 ## Completion Criteria
 
 - [ ] All steps complete
+- [ ] Lint passing
 - [ ] All tests passing
 - [ ] Build passing
 - [ ] Documentation updated
@@ -486,7 +488,7 @@ If you attempt to write to a path outside the worktree, the file tools will reje
 - Treat the File Scope in PROMPT.md as the expected starting scope, not a hard boundary when quality gates fail
 - Read "Context to Read First" files before starting
 - Follow the "Do NOT" section strictly
-- If tests, build, or typecheck fail and the fix requires touching code outside the declared File Scope, fix those failures directly and keep the repo green
+- If tests, lint, build, or typecheck fail and the fix requires touching code outside the declared File Scope, fix those failures directly and keep the repo green
 - Use \`task_create\` for genuinely separate follow-up work, not for mandatory fixes required to make this task land cleanly
 - NEVER delete, remove, or gut modules, interfaces, settings, exports, or test files outside your File Scope
 - NEVER remove features as "cleanup" — if something seems unused, create a task for investigation instead
@@ -511,14 +513,14 @@ spawn_agent({
 - When you end (task_done), all spawned children are terminated
 
 ## Completion
-After all steps are done, tests pass, typecheck passes, and docs are updated:
+After all steps are done, lint passes, tests pass, typecheck passes, and docs are updated:
 \`\`\`bash
 Call \`task_done()\` to signal completion.
 \`\`\`
 
 If a project build command is listed in the prompt, it is a hard completion gate.
-Tests and typecheck are also hard quality gates — keep fixing until 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.`;
+Lint, tests, and typecheck are also hard quality gates — keep fixing until green.
+**CRITICAL: Resolve ALL lint failures and 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.`;
 
 const STRICT_REVIEWER_PROMPT_TEXT = `You are a strict code and plan reviewer with rigorous standards.
 

packages/core/src/prompt-overrides.ts

@@ -88,7 +88,7 @@ You are working in a git worktree isolated from the main branch. Your job is to
 - Treat the File Scope in PROMPT.md as the expected starting scope, not a hard boundary when quality gates fail
 - Read "Context to Read First" files before starting
 - Follow the "Do NOT" section strictly
-- If tests, build, or typecheck fail and the fix requires touching code outside the declared File Scope, fix those failures directly and keep the repo green`,
+- If tests, lint, build, or typecheck fail and the fix requires touching code outside the declared File Scope, fix those failures directly and keep the repo green`,
   },
   "executor-spawning": {
     key: "executor-spawning",
@@ -119,7 +119,7 @@ spawn_agent({
     roles: ["executor"],
     description: "Completion criteria and signaling for executor",
     defaultContent: `## Completion
-After all steps are done, tests pass, typecheck passes, and docs are updated:
+After all steps are done, lint passes, tests pass, typecheck passes, and docs are updated:
 \`\`\`bash
 Call \`task_done()\` to signal completion.
 \`\`\``,

packages/engine/src/executor.ts

@@ -218,7 +218,7 @@ If you attempt to write to a path outside the worktree, the file tools will reje
 - Treat the File Scope in PROMPT.md as the expected starting scope, not a hard boundary when quality gates fail
 - Read "Context to Read First" files before starting
 - Follow the "Do NOT" section strictly
-- If tests, build, or typecheck fail and the fix requires touching code outside the declared File Scope, fix those failures directly and keep the repo green
+- If tests, lint, build, or typecheck fail and the fix requires touching code outside the declared File Scope, fix those failures directly and keep the repo green
 - Use \`task_create\` for genuinely separate follow-up work, not for mandatory fixes required to make this task land cleanly
 - Update documentation listed in "Must Update" and check "Check If Affected"
 - NEVER delete, remove, or gut modules, interfaces, settings, exports, or test files outside your File Scope
@@ -255,7 +255,7 @@ spawn_agent({
 - Max 20 total spawned agents system-wide (configurable via settings)
 
 ## Completion
-After all steps are done, tests pass, typecheck passes, and docs are updated:
+After all steps are done, lint passes, tests pass, typecheck passes, and docs are updated:
 \`\`\`bash
 Call \`task_done()\` to signal completion.
 \`\`\`
@@ -265,11 +265,11 @@ If a project build command is listed in the prompt, it is a hard completion gate
 - Do not claim the build passes unless you actually ran it and got exit code 0
 - If the build fails, do NOT call \`task_done()\`; keep working until it passes
 
-Tests and typecheck are also hard quality gates:
-- Keep fixing failures until the configured/full test suite passes
+Lint, tests, and typecheck are also hard quality gates:
+- Keep fixing failures until lint, the configured/full test suite, and typecheck all pass
 - If the repository exposes a typecheck command, run it and keep fixing failures until it passes
-- Do not stop at "out of scope" if additional fixes are required to restore green tests, build, or typecheck
-- **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.`;
+- Do not stop at "out of scope" if additional fixes are required to restore green lint, tests, build, or typecheck
+- **CRITICAL: Resolve ALL lint failures and 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.`;
 
 /** Resolve the executor system prompt from settings, falling back to the hardcoded constant. */
 function getExecutorSystemPrompt(settings: Settings): string {

packages/engine/src/triage.test.ts

@@ -375,11 +375,13 @@ describe("buildSpecificationPrompt", () => {
 });
 
 describe("TRIAGE_SYSTEM_PROMPT", () => {
-  it("requires specs to keep tests, build, and typecheck green even outside initial file scope", () => {
-    expect(TRIAGE_SYSTEM_PROMPT).toContain("If keeping tests/build/typecheck green requires edits outside the initial File Scope");
+  it("requires specs to keep lint, tests, build, and typecheck green even outside initial file scope", () => {
+    expect(TRIAGE_SYSTEM_PROMPT).toContain("If keeping lint/tests/build/typecheck green requires edits outside the initial File Scope");
+    expect(TRIAGE_SYSTEM_PROMPT).toContain("Run lint check");
     expect(TRIAGE_SYSTEM_PROMPT).toContain("Run project typecheck if available");
+    expect(TRIAGE_SYSTEM_PROMPT).toContain("Lint passing");
     expect(TRIAGE_SYSTEM_PROMPT).toContain("Typecheck passing (if available)");
-    expect(TRIAGE_SYSTEM_PROMPT).toContain("Specs must instruct executors to fix quality-gate failures directly");
+    expect(TRIAGE_SYSTEM_PROMPT).toContain("Specs must instruct executors to fix lint failures and quality-gate failures directly");
     expect(TRIAGE_SYSTEM_PROMPT).toContain("Refuse necessary fixes just because they touch files outside the initial File Scope");
   });
 });

packages/engine/src/triage.ts

@@ -100,8 +100,9 @@ Follow this structure exactly:
 ### Step {N-1}: Testing & Verification
 
 > ZERO test failures allowed. Full test suite as quality gate.
-> If keeping tests/build/typecheck green requires edits outside the initial File Scope, make those fixes as part of this task.
+> If keeping lint/tests/build/typecheck green requires edits outside the initial File Scope, make those fixes as part of this task.
 
+- [ ] Run lint check (\`pnpm lint\`)
 - [ ] Run full test suite
 - [ ] Run project typecheck if available
 - [ ] Fix all failures
@@ -123,6 +124,7 @@ Follow this structure exactly:
 ## Completion Criteria
 
 - [ ] All steps complete
+- [ ] Lint passing
 - [ ] All tests passing
 - [ ] Typecheck passing (if available)
 - [ ] Documentation updated
@@ -158,9 +160,8 @@ files with assertions that run via a test runner. Typechecks and builds are NOT
 tests. Manual verification is NOT a test.
 
 - Each implementation step should include writing tests for the code being changed
-- The final Testing step runs the FULL test suite
-- The final Testing step also runs project typecheck when the repo exposes one
-- Specs must instruct executors to fix quality-gate failures directly, even when the required edits extend beyond the original File Scope
+- The final Testing step runs lint, the FULL test suite, and project typecheck when the repo exposes one
+- Specs must instruct executors to fix lint failures and quality-gate failures directly, even when the required edits extend beyond the original File Scope
 - If the project has no test framework, the Testing step must include setting one up
   as part of this task (not just skipping tests)