fix(core): resolve nested plan directory duplication and relative path policies (#25138)

This commit is contained in:
Mahima Shanware
2026-04-21 14:20:57 -04:00
committed by GitHub
parent c260550146
commit a4e98c0a4c
17 changed files with 283 additions and 76 deletions
+45 -1
View File
@@ -305,7 +305,7 @@ describe('plan_mode', () => {
settings,
},
prompt:
'Enter plan mode and plan to create a new module called foo. The plan should be saved as foo-plan.md. Then, exit plan mode.',
'I agree with your strategy. Please enter plan mode and draft the plan to create a new module called foo. The plan should be saved as foo-plan.md. Then, exit plan mode.',
assert: async (rig, result) => {
const enterPlanCalled = await rig.waitForToolCall('enter_plan_mode');
expect(
@@ -376,4 +376,48 @@ describe('plan_mode', () => {
assertModelHasOutput(result);
},
});
evalTest('USUALLY_PASSES', {
name: 'should handle nested plan directories correctly',
suiteName: 'plan_mode',
suiteType: 'behavioral',
approvalMode: ApprovalMode.PLAN,
params: {
settings,
},
prompt:
'Please create a new architectural plan in a nested folder called "architecture/frontend-v2.md" within the plans directory. The plan should contain the text "# Frontend V2 Plan". Then, exit plan mode',
assert: async (rig, result) => {
await rig.waitForTelemetryReady();
const toolLogs = rig.readToolLogs();
const writeCalls = toolLogs.filter((log) =>
['write_file', 'replace'].includes(log.toolRequest.name),
);
const wroteToNestedPath = writeCalls.some((log) => {
try {
const args = JSON.parse(log.toolRequest.args);
if (!args.file_path) return false;
// In plan mode, paths can be passed as relative (architecture/frontend-v2.md)
// or they might be resolved as absolute by the tool depending on the exact mock state.
// We strictly ensure it ends exactly with the expected nested path and doesn't contain extra nesting.
const normalizedPath = args.file_path.replace(/\\/g, '/');
return (
normalizedPath === 'architecture/frontend-v2.md' ||
normalizedPath.endsWith('/plans/architecture/frontend-v2.md')
);
} catch {
return false;
}
});
expect(
wroteToNestedPath,
'Expected model to successfully target the nested plan file path',
).toBe(true);
assertModelHasOutput(result);
},
});
});