MediaMetz/gemini-cli
1
0
Fork 0
mirror of https://github.com/google-gemini/gemini-cli.git synced 2026-04-04 18:31:36 -07:00
Code Issues Packages Projects Releases Wiki Activity

fix(plan): sandbox path resolution in Plan Mode to prevent hallucinations (#22737)

Browse Source 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Adib234
2026-03-24 09:19:29 -04:00
committed by GitHub
parent 46fd7b4864
commit dcedc42979
22 changed files with 193 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
evals/plan_mode.eval.ts
View File

@@ -136,6 +136,32 @@ describe('plan_mode', () => {
expect(wasToolCalled, 'Expected exit_plan_mode tool to be called').toBe(
true,
);
const toolLogs = rig.readToolLogs();
const exitPlanCall = toolLogs.find(
(log) => log.toolRequest.name === 'exit_plan_mode',
);
expect(
exitPlanCall,
'Expected to find exit_plan_mode in tool logs',
).toBeDefined();
const args = JSON.parse(exitPlanCall!.toolRequest.args);
expect(args.plan_filename, 'plan_filename should be a string').toBeTypeOf(
'string',
);
expect(args.plan_filename, 'plan_filename should end with .md').toMatch(
/\.md$/,
);
expect(
args.plan_filename,
'plan_filename should not be a path',
).not.toContain('/');
expect(
args.plan_filename,
'plan_filename should not be a path',
).not.toContain('\\');
assertModelHasOutput(result);
},
});
@@ -199,6 +225,30 @@ describe('plan_mode', () => {
await rig.waitForTelemetryReady();
const toolLogs = rig.readToolLogs();
const exitPlanCall = toolLogs.find(
(log) => log.toolRequest.name === 'exit_plan_mode',
);
expect(
exitPlanCall,
'Expected to find exit_plan_mode in tool logs',
).toBeDefined();
const args = JSON.parse(exitPlanCall!.toolRequest.args);
expect(args.plan_filename, 'plan_filename should be a string').toBeTypeOf(
'string',
);
expect(args.plan_filename, 'plan_filename should end with .md').toMatch(
/\.md$/,
);
expect(
args.plan_filename,
'plan_filename should not be a path',
).not.toContain('/');
expect(
args.plan_filename,
'plan_filename should not be a path',
).not.toContain('\\');
// Check if plan was written
const planWrite = toolLogs.find(
(log) =>