Skip to content

Add behavioral evaluations for planning tools and workflow #17169

Closed
Task
#18457
#18437
Closed
Add behavioral evaluations for planning tools and workflow#17169
Task
#18457
#18437
Assignees
jerop
Labels
area/coreIssues related to User Interface, OS Support, Core Functionalityworkstream-rollupLabel used to tag epics and features that are associated with one of the three primary workstreams🔒 maintainer only⛔ Do not contribute. Internal roadmap item.
@jerop

Description

@jerop
jerop
opened on Jan 21, 2026

Add behavioral evals to verify that the agent correctly adheres to its restrictions to read-only tools. These tests validate that the model consistently refuses file modifications when in PLAN mode. Also include evals for EnterPlanMode and ExitPlanMode tools

This is dependent on refactor described in #17168.

Evals for AskUser tool is tracked in #17956.

Metadata

Metadata

Assignees

Labels

area/coreIssues related to User Interface, OS Support, Core Functionalityworkstream-rollupLabel used to tag epics and features that are associated with one of the three primary workstreams🔒 maintainer only⛔ Do not contribute. Internal roadmap item.

Type

Task

Fields

No fields configured for Task.

Projects

Gemini CLI Public Roadmap

Status

Closed

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions