test: update local-executor tests for relative path preference

revert: documentation changes for path preference
docs: prefer relative paths in tool documentation and system prompt
2026-07-24 00:30:59 -07:00 · 2026-02-26 20:42:26 +00:00 · 2026-02-26 20:33:17 +00:00 · 2026-02-26 20:26:08 +00:00 · 2026-02-26 20:24:22 +00:00
308 changed files with 3547 additions and 13968 deletions
@@ -1,29 +0,0 @@
-description = "Promote behavioral evals that have a 100% success rate over the last 7 nightly runs."
-prompt = """
-You are an expert at analyzing and promoting behavioral evaluations.
-
-1. **Investigate**:
-   - Use 'gh' cli to fetch the results from the most recent run from the main branch: https://github.com/google-gemini/gemini-cli/actions/workflows/evals-nightly.yml.
-   - DO NOT push any changes or start any runs. The rest of your evaluation will be local.
-   - Evals are in evals/ directory and are documented by evals/README.md.
-   - Identify tests that have passed 100% of the time for ALL enabled models across the past 7 runs in a row.
-   - NOTE: the results summary from the most recent run contains the last 7 runs test results. 100% means the test passed 3/3 times for that model and run.
-   - If a test meets this criteria, it is a candidate for promotion.
-
-2. **Promote**:
-   - For each candidate test, locate the test file in the evals/ directory.
-   - Promote the test according to the project's standard promotion process (e.g., moving it to a stable suite, updating its tags, or removing skip/flaky annotations). 
-   - Ensure you follow any guidelines in evals/README.md for stable tests.
-   - Your **final** change should be **minimal and targeted** to just promoting the test status.
-
-3. **Verify**:
-   - Run the promoted tests locally to validate that they still execute correctly. Be sure to run vitest in non-interactive mode.
-   - Check that the test is now part of the expected standard or stable test suites.
-
-4. **Report**:
-   - Provide a summary of the tests that were promoted.
-   - Include the success rate evidence (7/7 runs passed for all models) for each promoted test.
-   - If no tests met the criteria for promotion, clearly state that and summarize the closest candidates.
-
-{{args}}
-"""
@@ -9,5 +9,4 @@ code_review:
    help: false
    summary: true
    code_review: true
-    include_drafts: false
 ignore_patterns: []
@@ -31,7 +31,6 @@ jobs:
    name: 'Merge Queue Skipper'
    permissions: 'read-all'
    runs-on: 'gemini-cli-ubuntu-16-core'
-    if: "github.repository == 'google-gemini/gemini-cli'"
    outputs:
      skip: '${{ steps.merge-queue-e2e-skipper.outputs.skip-check }}'
    steps:
@@ -43,7 +42,7 @@ jobs:

  download_repo_name:
    runs-on: 'gemini-cli-ubuntu-16-core'
-    if: "github.repository == 'google-gemini/gemini-cli' && (github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_run')"
+    if: "${{github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_run'}}"
    outputs:
      repo_name: '${{ steps.output-repo-name.outputs.repo_name }}'
      head_sha: '${{ steps.output-repo-name.outputs.head_sha }}'
@@ -54,7 +53,7 @@ jobs:
          REPO_NAME: '${{ github.event.inputs.repo_name }}'
        run: |
          mkdir -p ./pr
-          echo "${REPO_NAME}" > ./pr/repo_name
+          echo '${REPO_NAME}' > ./pr/repo_name
      - uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
        with:
          name: 'repo_name'
@@ -92,7 +91,7 @@ jobs:
    name: 'Parse run context'
    runs-on: 'gemini-cli-ubuntu-16-core'
    needs: 'download_repo_name'
-    if: "github.repository == 'google-gemini/gemini-cli' && always()"
+    if: 'always()'
    outputs:
      repository: '${{ steps.set_context.outputs.REPO }}'
      sha: '${{ steps.set_context.outputs.SHA }}'
@@ -112,11 +111,11 @@ jobs:
    permissions: 'write-all'
    needs:
      - 'parse_run_context'
-    if: "github.repository == 'google-gemini/gemini-cli' && always()"
+    if: 'always()'
    steps:
      - name: 'Set pending status'
        uses: 'myrotvorets/set-commit-status-action@16037e056d73b2d3c88e37e393ff369047f70886' # ratchet:myrotvorets/set-commit-status-action@master
-        if: "github.repository == 'google-gemini/gemini-cli' && always()"
+        if: 'always()'
        with:
          allowForks: 'true'
          repo: '${{ github.repository }}'
@@ -132,7 +131,7 @@ jobs:
      - 'parse_run_context'
    runs-on: 'gemini-cli-ubuntu-16-core'
    if: |
-      github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
+      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
    strategy:
      fail-fast: false
      matrix:
@@ -185,7 +184,7 @@ jobs:
      - 'parse_run_context'
    runs-on: 'macos-latest'
    if: |
-      github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
+      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
    steps:
      - name: 'Checkout'
        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
@@ -223,7 +222,7 @@ jobs:
      - 'merge_queue_skipper'
      - 'parse_run_context'
    if: |
-      github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
+      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
    runs-on: 'gemini-cli-windows-16-core'
    steps:
      - name: 'Checkout'
@@ -283,7 +282,7 @@ jobs:
      - 'parse_run_context'
    runs-on: 'gemini-cli-ubuntu-16-core'
    if: |
-      github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
+      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
    steps:
      - name: 'Checkout'
        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
@@ -310,7 +309,7 @@ jobs:
  e2e:
    name: 'E2E'
    if: |
-      github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
+      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
    needs:
      - 'e2e_linux'
      - 'e2e_mac'
@@ -338,14 +337,14 @@ jobs:
  set_workflow_status:
    runs-on: 'gemini-cli-ubuntu-16-core'
    permissions: 'write-all'
-    if: "github.repository == 'google-gemini/gemini-cli' && always()"
+    if: 'always()'
    needs:
      - 'parse_run_context'
      - 'e2e'
    steps:
      - name: 'Set workflow status'
        uses: 'myrotvorets/set-commit-status-action@16037e056d73b2d3c88e37e393ff369047f70886' # ratchet:myrotvorets/set-commit-status-action@master
-        if: "github.repository == 'google-gemini/gemini-cli' && always()"
+        if: 'always()'
        with:
          allowForks: 'true'
          repo: '${{ github.repository }}'
@@ -37,7 +37,6 @@ jobs:
    permissions: 'read-all'
    name: 'Merge Queue Skipper'
    runs-on: 'gemini-cli-ubuntu-16-core'
-    if: "github.repository == 'google-gemini/gemini-cli'"
    outputs:
      skip: '${{ steps.merge-queue-ci-skipper.outputs.skip-check }}'
    steps:
@@ -50,7 +49,7 @@ jobs:
    name: 'Lint'
    runs-on: 'gemini-cli-ubuntu-16-core'
    needs: 'merge_queue_skipper'
-    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
+    if: "${{needs.merge_queue_skipper.outputs.skip == 'false'}}"
    env:
      GEMINI_LINT_TEMP_DIR: '${{ github.workspace }}/.gemini-linters'
    steps:
@@ -117,7 +116,6 @@ jobs:
  link_checker:
    name: 'Link Checker'
    runs-on: 'ubuntu-latest'
-    if: "github.repository == 'google-gemini/gemini-cli'"
    steps:
      - name: 'Checkout'
        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
@@ -131,7 +129,7 @@ jobs:
    runs-on: 'gemini-cli-ubuntu-16-core'
    needs:
      - 'merge_queue_skipper'
-    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
+    if: "${{needs.merge_queue_skipper.outputs.skip == 'false'}}"
    permissions:
      contents: 'read'
      checks: 'write'
@@ -218,7 +216,7 @@ jobs:
    runs-on: 'macos-latest'
    needs:
      - 'merge_queue_skipper'
-    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
+    if: "${{needs.merge_queue_skipper.outputs.skip == 'false'}}"
    permissions:
      contents: 'read'
      checks: 'write'
@@ -313,7 +311,7 @@ jobs:
    name: 'CodeQL'
    runs-on: 'gemini-cli-ubuntu-16-core'
    needs: 'merge_queue_skipper'
-    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
+    if: "${{needs.merge_queue_skipper.outputs.skip == 'false'}}"
    permissions:
      actions: 'read'
      contents: 'read'
@@ -336,7 +334,7 @@ jobs:
  bundle_size:
    name: 'Check Bundle Size'
    needs: 'merge_queue_skipper'
-    if: "github.repository == 'google-gemini/gemini-cli' && github.event_name == 'pull_request' && needs.merge_queue_skipper.outputs.skip == 'false'"
+    if: "${{github.event_name == 'pull_request' && needs.merge_queue_skipper.outputs.skip == 'false'}}"
    runs-on: 'gemini-cli-ubuntu-16-core'
    permissions:
      contents: 'read' # For checkout
@@ -361,7 +359,7 @@ jobs:
    name: 'Slow Test - Win - ${{ matrix.shard }}'
    runs-on: 'gemini-cli-windows-16-core'
    needs: 'merge_queue_skipper'
-    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
+    if: "${{needs.merge_queue_skipper.outputs.skip == 'false'}}"
    timeout-minutes: 60
    strategy:
      matrix:
@@ -453,7 +451,7 @@ jobs:

  ci:
    name: 'CI'
-    if: "github.repository == 'google-gemini/gemini-cli' && always()"
+    if: 'always()'
    needs:
      - 'lint'
      - 'link_checker'
@@ -27,7 +27,6 @@ jobs:
  deflake_e2e_linux:
    name: 'E2E Test (Linux) - ${{ matrix.sandbox }}'
    runs-on: 'gemini-cli-ubuntu-16-core'
-    if: "github.repository == 'google-gemini/gemini-cli'"
    strategy:
      fail-fast: false
      matrix:
@@ -78,7 +77,6 @@ jobs:
  deflake_e2e_mac:
    name: 'E2E Test (macOS)'
    runs-on: 'macos-latest'
-    if: "github.repository == 'google-gemini/gemini-cli'"
    steps:
      - name: 'Checkout'
        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
@@ -116,7 +114,6 @@ jobs:
  deflake_e2e_windows:
    name: 'Slow E2E - Win'
    runs-on: 'gemini-cli-windows-16-core'
-    if: "github.repository == 'google-gemini/gemini-cli'"

    steps:
      - name: 'Checkout'
@@ -19,7 +19,8 @@ concurrency:

 jobs:
  build:
-    if: "github.repository == 'google-gemini/gemini-cli' && !contains(github.ref_name, 'nightly')"
+    if: |-
+      ${{ !contains(github.ref_name, 'nightly') }}
    runs-on: 'ubuntu-latest'
    steps:
      - name: 'Checkout'
@@ -38,7 +39,6 @@ jobs:
        uses: 'actions/upload-pages-artifact@56afc609e74202658d3ffba0e8f6dda462b719fa' # ratchet:actions/upload-pages-artifact@v3

  deploy:
-    if: "github.repository == 'google-gemini/gemini-cli'"
    environment:
      name: 'github-pages'
      url: '${{ steps.deployment.outputs.page_url }}'
@@ -7,7 +7,6 @@ on:
      - 'docs/**'
 jobs:
  trigger-rebuild:
-    if: "github.repository == 'google-gemini/gemini-cli'"
    runs-on: 'ubuntu-latest'
    steps:
      - name: 'Trigger rebuild'
@@ -23,7 +23,6 @@ jobs:
  evals:
    name: 'Evals (USUALLY_PASSING) nightly run'
    runs-on: 'gemini-cli-ubuntu-16-core'
-    if: "github.repository == 'google-gemini/gemini-cli'"
    strategy:
      fail-fast: false
      matrix:
@@ -86,7 +85,7 @@ jobs:
  aggregate-results:
    name: 'Aggregate Results'
    needs: ['evals']
-    if: "github.repository == 'google-gemini/gemini-cli' && always()"
+    if: 'always()'
    runs-on: 'gemini-cli-ubuntu-16-core'
    steps:
      - name: 'Checkout'
@@ -21,7 +21,6 @@ defaults:

 jobs:
  close-stale-issues:
-    if: "github.repository == 'google-gemini/gemini-cli'"
    runs-on: 'ubuntu-latest'
    permissions:
      issues: 'write'
@@ -14,7 +14,7 @@ permissions:
 jobs:
  # Event-based: Quick reaction to new/edited issues in THIS repo
  labeler:
-    if: "github.repository == 'google-gemini/gemini-cli' && github.event_name == 'issues'"
+    if: "github.event_name == 'issues'"
    runs-on: 'ubuntu-latest'
    steps:
      - name: 'Checkout'
@@ -36,7 +36,7 @@ jobs:

  # Scheduled/Manual: Recursive sync across multiple repos
  sync-maintainer-labels:
-    if: "github.repository == 'google-gemini/gemini-cli' && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')"
+    if: "github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'"
    runs-on: 'ubuntu-latest'
    steps:
      - name: 'Checkout'
@@ -9,7 +9,6 @@ on:

 jobs:
  labeler:
-    if: "github.repository == 'google-gemini/gemini-cli'"
    runs-on: 'ubuntu-latest'
    permissions:
      issues: 'write'
@@ -32,7 +32,6 @@ on:

 jobs:
  change-tags:
-    if: "github.repository == 'google-gemini/gemini-cli'"
    runs-on: 'ubuntu-latest'
    environment: "${{ github.event.inputs.environment || 'prod' }}"
    permissions:
@@ -47,7 +47,6 @@ on:

 jobs:
  release:
-    if: "github.repository == 'google-gemini/gemini-cli'"
    runs-on: 'ubuntu-latest'
    environment: "${{ github.event.inputs.environment || 'prod' }}"
    permissions:
@@ -22,7 +22,6 @@ on:

 jobs:
  generate-release-notes:
-    if: "github.repository == 'google-gemini/gemini-cli'"
    runs-on: 'ubuntu-latest'
    permissions:
      contents: 'write'
@@ -42,7 +42,6 @@ on:

 jobs:
  change-tags:
-    if: "github.repository == 'google-gemini/gemini-cli'"
    environment: "${{ github.event.inputs.environment || 'prod' }}"
    runs-on: 'ubuntu-latest'
    permissions:
@@ -204,7 +203,7 @@ jobs:
        run: |
          ROLLBACK_COMMIT=$(git rev-parse -q --verify "$TARGET_TAG")
          if [ "$ROLLBACK_COMMIT" != "$TARGET_HASH" ]; then
-            echo "❌ Failed to add tag ${TARGET_TAG} to commit ${TARGET_HASH}"
+            echo '❌ Failed to add tag $TARGET_TAG to commit $TARGET_HASH'
            echo '❌ This means the tag was not added, and the workflow should fail.'
            exit 1
          fi
@@ -16,7 +16,6 @@ on:

 jobs:
  build:
-    if: "github.repository == 'google-gemini/gemini-cli'"
    runs-on: 'ubuntu-latest'
    permissions:
      contents: 'read'
@@ -20,7 +20,6 @@ on:

 jobs:
  smoke-test:
-    if: "github.repository == 'google-gemini/gemini-cli'"
    runs-on: 'ubuntu-latest'
    permissions:
      contents: 'write'
@@ -15,7 +15,6 @@ on:

 jobs:
  save_repo_name:
-    if: "github.repository == 'google-gemini/gemini-cli'"
    runs-on: 'gemini-cli-ubuntu-16-core'
    steps:
      - name: 'Save Repo name'
@@ -24,15 +23,14 @@ jobs:
          HEAD_SHA: '${{ github.event.inputs.head_sha || github.event.pull_request.head.sha }}'
        run: |
          mkdir -p ./pr
-          echo "${REPO_NAME}" > ./pr/repo_name
-          echo "${HEAD_SHA}" > ./pr/head_sha
+          echo '${REPO_NAME}' > ./pr/repo_name
+          echo '${HEAD_SHA}' > ./pr/head_sha
      - uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
        with:
          name: 'repo_name'
          path: 'pr/'
  trigger_e2e:
    name: 'Trigger e2e'
-    if: "github.repository == 'google-gemini/gemini-cli'"
    runs-on: 'gemini-cli-ubuntu-16-core'
    steps:
      - id: 'trigger-e2e'
@@ -28,7 +28,6 @@ on:

 jobs:
  verify-release:
-    if: "github.repository == 'google-gemini/gemini-cli'"
    environment: "${{ github.event.inputs.environment || 'prod' }}"
    strategy:
      fail-fast: false
@@ -1,6 +1,6 @@
-# Latest stable release: v0.30.1
+# Latest stable release: v0.30.0

-Released: February 27, 2026
+Released: February 25, 2026

 For most users, our latest stable release is the recommended release. Install
 the latest stable version with:
@@ -28,9 +28,6 @@ npm install -g @google/gemini-cli

 ## What's Changed

- fix(patch): cherry-pick 58df1c6 to release/v0.30.0-pr-20374 [CONFLICTS] by
-  @gemini-cli-robot in
-  [#20567](https://github.com/google-gemini/gemini-cli/pull/20567)
 - feat(ux): added text wrapping capabilities to markdown tables by @devr0306 in
  [#18240](https://github.com/google-gemini/gemini-cli/pull/18240)
 - Revert "fix(mcp): ensure MCP transport is closed to prevent memory leaks" by
@@ -333,4 +330,4 @@ npm install -g @google/gemini-cli
  [#20112](https://github.com/google-gemini/gemini-cli/pull/20112)

 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.29.7...v0.30.1
+https://github.com/google-gemini/gemini-cli/compare/v0.29.7...v0.30.0
@@ -1,6 +1,6 @@
-# Preview release: v0.31.0-preview.1
+# Preview release: v0.31.0-preview.0

-Released: February 27, 2026
+Released: February 25, 2026

 Our preview release includes the latest, new, and experimental features. This
 release may not be as stable as our [latest weekly release](latest.md).
@@ -33,10 +33,6 @@ npm install -g @google/gemini-cli@preview

 ## What's Changed

- fix(patch): cherry-pick 58df1c6 to release/v0.31.0-preview.0-pr-20374 to patch
-  version v0.31.0-preview.0 and create version 0.31.0-preview.1 by
-  @gemini-cli-robot in
-  [#20568](https://github.com/google-gemini/gemini-cli/pull/20568)
 - Use ranged reads and limited searches and fuzzy editing improvements by
  @gundermanc in
  [#19240](https://github.com/google-gemini/gemini-cli/pull/19240)
@@ -413,4 +409,4 @@ npm install -g @google/gemini-cli@preview
  [#20240](https://github.com/google-gemini/gemini-cli/pull/20240)

 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.30.0-preview.6...v0.31.0-preview.1
+https://github.com/google-gemini/gemini-cli/compare/v0.30.0-preview.6...v0.31.0-preview.0
@@ -80,37 +80,18 @@ manually during a session.

 ### Planning Workflow

-Plan Mode uses an adaptive planning workflow where the research depth, plan
-structure, and consultation level are proportional to the task's complexity:
-
 1.  **Explore & Analyze:** Analyze requirements and use read-only tools to map
-    affected modules and identify dependencies.
-2.  **Consult:** The depth of consultation is proportional to the task's
-    complexity:
-    - **Simple Tasks:** Proceed directly to drafting.
-    - **Standard Tasks:** Present a summary of viable approaches via
-      [`ask_user`] for selection.
-    - **Complex Tasks:** Present detailed trade-offs for at least two viable
-      approaches via [`ask_user`] and obtain approval before drafting.
-3.  **Draft:** Write a detailed implementation plan to the
-    [plans directory](#custom-plan-directory-and-policies). The plan's structure
-    adapts to the task:
-    - **Simple Tasks:** Focused on specific **Changes** and **Verification**
-      steps.
-    - **Standard Tasks:** Includes an **Objective**, **Key Files & Context**,
-      **Implementation Steps**, and **Verification & Testing**.
-    - **Complex Tasks:** Comprehensive plans including **Background &
-      Motivation**, **Scope & Impact**, **Proposed Solution**, **Alternatives
-      Considered**, a phased **Implementation Plan**, **Verification**, and
-      **Migration & Rollback** strategies.
+    the codebase and validate assumptions. For complex tasks, identify at least
+    two viable implementation approaches.
+2.  **Consult:** Present a summary of the identified approaches via [`ask_user`]
+    to obtain a selection. For simple or canonical tasks, this step may be
+    skipped.
+3.  **Draft:** Once an approach is selected, write a detailed implementation
+    plan to the plans directory.
 4.  **Review & Approval:** Use the [`exit_plan_mode`] tool to present the plan
    and formally request approval.
    - **Approve:** Exit Plan Mode and start implementation.
    - **Iterate:** Provide feedback to refine the plan.
-    - **Refine manually:** Press **Ctrl + X** to open the plan file in your
-      [preferred external editor]. This allows you to manually refine the plan
-      steps before approval. The CLI will automatically refresh and show the
-      updated plan after you save and close the editor.

 For more complex or specialized planning tasks, you can
 [customize the planning workflow with skills](#customizing-planning-with-skills).
@@ -309,4 +290,3 @@ performance. You can disable this automatic switching in your settings:
  https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/policy/policies/plan.toml
 [auto model]: /docs/reference/configuration.md#model-settings
 [model routing]: /docs/cli/telemetry.md#model-routing
-[preferred external editor]: /docs/reference/configuration.md#general
@@ -72,7 +72,6 @@ they appear in the UI.
 | Incremental Rendering                | `ui.incrementalRendering`              | Enable incremental rendering for the UI. This option will reduce flickering but may cause rendering artifacts. Only supported when useAlternateBuffer is enabled. | `true`   |
 | Show Spinner                         | `ui.showSpinner`                       | Show the spinner during operations.                                                                                                                               | `true`   |
 | Loading Phrases                      | `ui.loadingPhrases`                    | What to show while the model is working: tips, witty comments, both, or nothing.                                                                                  | `"tips"` |
-| Error Verbosity                      | `ui.errorVerbosity`                    | Controls whether recoverable errors are hidden (low) or fully shown (full).                                                                                       | `"low"`  |
 | Screen Reader Mode                   | `ui.accessibility.screenReader`        | Render output in plain-text to be more screen reader accessible                                                                                                   | `false`  |

 ### IDE
@@ -81,12 +80,6 @@ they appear in the UI.
 | -------- | ------------- | ---------------------------- | ------- |
 | IDE Mode | `ide.enabled` | Enable IDE integration mode. | `false` |

-### Billing
-
-| UI Label         | Setting                   | Description                                                                                                                                                | Default |
-| ---------------- | ------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
-| Overage Strategy | `billing.overageStrategy` | How to handle quota exhaustion when AI credits are available. 'ask' prompts each time, 'always' automatically uses credits, 'never' disables credit usage. | `"ask"` |
-
 ### Model

 | UI Label                | Setting                      | Description                                                                            | Default     |
@@ -125,7 +118,6 @@ they appear in the UI.
 | ------------------------------------- | ----------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------- |
 | Disable YOLO Mode                     | `security.disableYoloMode`                      | Disable YOLO mode, even if enabled by a flag.                                                                                                                                                                                        | `false` |
 | Allow Permanent Tool Approval         | `security.enablePermanentToolApproval`          | Enable the "Allow for all future sessions" option in tool confirmation dialogs.                                                                                                                                                      | `false` |
-| Auto-add to Policy                    | `security.autoAddPolicy`                        | Automatically add "Proceed always" approvals to your persistent policy.                                                                                                                                                              | `true`  |
 | Blocks extensions from Git            | `security.blockGitExtensions`                   | Blocks installing and loading extensions from Git.                                                                                                                                                                                   | `false` |
 | Extension Source Regex Allowlist      | `security.allowedExtensions`                    | List of Regex patterns for allowed extensions. If nonempty, only extensions that match the patterns in this list are allowed. Overrides the blockGitExtensions setting.                                                              | `[]`    |
 | Folder Trust                          | `security.folderTrust.enabled`                  | Setting to track whether Folder trust is enabled.                                                                                                                                                                                    | `true`  |
@@ -148,7 +140,6 @@ they appear in the UI.
 | Plan                       | `experimental.plan`                      | Enable planning features (Plan Mode and tools).                                                                                                           | `false` |
 | Model Steering             | `experimental.modelSteering`             | Enable model steering (user hints) to guide the model during tool execution.                                                                              | `false` |
 | Direct Web Fetch           | `experimental.directWebFetch`            | Enable web fetch behavior that bypasses LLM summarization.                                                                                                | `false` |
-| Enable Gemma Model Router  | `experimental.gemmaModelRouter.enabled`  | Enable the Gemma Model Router. Requires a local endpoint serving Gemma via the Gemini API using LiteRT-LM shim.                                           | `false` |

 ### Skills

@@ -176,12 +176,11 @@ Sends telemetry directly to Google Cloud services. No collector needed.
   }
   ```
 2. Run Gemini CLI and send prompts.
-3. View logs, metrics, and traces:
+3. View logs and metrics:
   - Open the Google Cloud Console in your browser after sending prompts:
-     - Logs (Logs Explorer): https://console.cloud.google.com/logs/
-     - Metrics (Metrics Explorer):
-       https://console.cloud.google.com/monitoring/metrics-explorer
-     - Traces (Trace Explorer): https://console.cloud.google.com/traces/list
+     - Logs: https://console.cloud.google.com/logs/
+     - Metrics: https://console.cloud.google.com/monitoring/metrics-explorer
+     - Traces: https://console.cloud.google.com/traces/list

 ### Collector-based export (advanced)

@@ -209,12 +208,11 @@ forward data to Google Cloud.
   - Save collector logs to `~/.gemini/tmp/<projectHash>/otel/collector-gcp.log`
   - Stop collector on exit (e.g. `Ctrl+C`)
 3. Run Gemini CLI and send prompts.
-4. View logs, metrics, and traces:
+4. View logs and metrics:
   - Open the Google Cloud Console in your browser after sending prompts:
-     - Logs (Logs Explorer): https://console.cloud.google.com/logs/
-     - Metrics (Metrics Explorer):
-       https://console.cloud.google.com/monitoring/metrics-explorer
-     - Traces (Trace Explorer): https://console.cloud.google.com/traces/list
+     - Logs: https://console.cloud.google.com/logs/
+     - Metrics: https://console.cloud.google.com/monitoring/metrics-explorer
+     - Traces: https://console.cloud.google.com/traces/list
   - Open `~/.gemini/tmp/<projectHash>/otel/collector-gcp.log` to view local
     collector logs.

@@ -272,10 +270,10 @@ For local development and debugging, you can capture telemetry data locally:
 3. View traces at http://localhost:16686 and logs/metrics in the collector log
   file.

-## Logs, metrics, and traces
+## Logs and metrics

-The following section describes the structure of logs, metrics, and traces
-generated for Gemini CLI.
+The following section describes the structure of logs and metrics generated for
+Gemini CLI.

 The `session.id`, `installation.id`, `active_approval_mode`, and `user.email`
 (available only when authenticated with a Google account) are included as common
@@ -826,32 +824,6 @@ Optional performance monitoring for startup, CPU/memory, and phase timing.
    - `current_value` (number)
    - `baseline_value` (number)

-### Traces
-
-Traces offer a granular, "under-the-hood" view of every agent and backend
-operation. By providing a high-fidelity execution map, they enable precise
-debugging of complex tool interactions and deep performance optimization. Each
-trace captures rich, consistent metadata via custom span attributes:
-
- `gen_ai.operation.name` (string): The high-level operation kind (e.g.
-  "tool_call", "llm_call").
- `gen_ai.agent.name` (string): The service agent identifier ("gemini-cli").
- `gen_ai.agent.description` (string): The service agent description.
- `gen_ai.input.messages` (string): Input messages or metadata specific to the
-  operation.
- `gen_ai.output.messages` (string): Output messages or metadata generated from
-  the operation.
- `gen_ai.request.model` (string): The request model name.
- `gen_ai.response.model` (string): The response model name.
- `gen_ai.system_instructions` (json string): The system instructions.
- `gen_ai.prompt.name` (string): The prompt name.
- `gen_ai.tool.name` (string): The executed tool's name.
- `gen_ai.tool.call_id` (string): The generated specific ID of the tool call.
- `gen_ai.tool.description` (string): The executed tool's description.
- `gen_ai.tool.definitions` (json string): The executed tool's description.
- `gen_ai.conversation.id` (string): The current CLI session ID.
- Additional user-defined Custom Attributes passed via the span's configuration.
-
 #### GenAI semantic convention

 The following metrics comply with [OpenTelemetry GenAI semantic conventions] for
@@ -227,42 +227,6 @@ skill definitions in a `skills/` directory. For example,
 Provide [sub-agents](../core/subagents.md) that users can delegate tasks to. Add
 agent definition files (`.md`) to an `agents/` directory in your extension root.

-### <a id="policy-engine"></a>Policy Engine
-
-Extensions can contribute policy rules and safety checkers to the Gemini CLI
-[Policy Engine](../reference/policy-engine.md). These rules are defined in
-`.toml` files and take effect when the extension is activated.
-
-To add policies, create a `policies/` directory in your extension's root and
-place your `.toml` policy files inside it. Gemini CLI automatically loads all
-`.toml` files from this directory.
-
-Rules contributed by extensions run in their own tier (tier 2), alongside
-workspace-defined policies. This tier has higher priority than the default rules
-but lower priority than user or admin policies.
-
-> **Warning:** For security, Gemini CLI ignores any `allow` decisions or `yolo`
-> mode configurations in extension policies. This ensures that an extension
-> cannot automatically approve tool calls or bypass security measures without
-> your confirmation.
-
-**Example `policies.toml`**
-
-```toml
-[[rule]]
-toolName = "my_server__dangerous_tool"
-decision = "ask_user"
-priority = 100
-
-[[safety_checker]]
-toolName = "my_server__write_data"
-priority = 200
-[safety_checker.checker]
-type = "in-process"
-name = "allowed-path"
-required_context = ["environment"]
-```
-
 ### Themes

 Extensions can provide custom themes to personalize the CLI UI. Themes are
@@ -1,6 +1,6 @@
 # Gemini CLI installation, execution, and releases

-This document provides an overview of Gemini CLI's system requirements,
+This document provides an overview of Gemini CLI's sytem requriements,
 installation methods, and release types.

 ## Recommended system specifications
@@ -1,21 +1,23 @@
 # Local development guide

 This guide provides instructions for setting up and using local development
-features, such as tracing.
+features, such as development tracing.

-## Tracing
+## Development tracing

-Traces are OpenTelemetry (OTel) records that help you debug your code by
-instrumenting key events like model calls, tool scheduler operations, and tool
-calls.
+Development traces (dev traces) are OpenTelemetry (OTel) traces that help you
+debug your code by instrumenting interesting events like model calls, tool
+scheduler, tool calls, etc.

-Traces provide deep visibility into agent behavior and are invaluable for
-debugging complex issues. They are captured automatically when telemetry is
-enabled.
+Dev traces are verbose and are specifically meant for understanding agent
+behavior and debugging issues. They are disabled by default.

-### Viewing traces
+To enable dev traces, set the `GEMINI_DEV_TRACING=true` environment variable
+when running Gemini CLI.

-You can view traces using either Jaeger or the Genkit Developer UI.
+### Viewing dev traces
+
+You can view dev traces using either Jaeger or the Genkit Developer UI.

 #### Using Genkit

@@ -35,12 +37,13 @@ Genkit provides a web-based UI for viewing traces and other telemetry data.
    Genkit Developer UI: http://localhost:4000
    ```

-2.  **Run Gemini CLI:**
+2.  **Run Gemini CLI with dev tracing:**

-    In a separate terminal, run your Gemini CLI command:
+    In a separate terminal, run your Gemini CLI command with the
+    `GEMINI_DEV_TRACING` environment variable:

    ```bash
-    gemini
+    GEMINI_DEV_TRACING=true gemini
    ```

 3.  **View the traces:**
@@ -50,7 +53,7 @@ Genkit provides a web-based UI for viewing traces and other telemetry data.

 #### Using Jaeger

-You can view traces in the Jaeger UI. To get started, follow these steps:
+You can view dev traces in the Jaeger UI. To get started, follow these steps:

 1.  **Start the telemetry collector:**

@@ -64,12 +67,13 @@ You can view traces in the Jaeger UI. To get started, follow these steps:
    This command also configures your workspace for local telemetry and provides
    a link to the Jaeger UI (usually `http://localhost:16686`).

-2.  **Run Gemini CLI:**
+2.  **Run Gemini CLI with dev tracing:**

-    In a separate terminal, run your Gemini CLI command:
+    In a separate terminal, run your Gemini CLI command with the
+    `GEMINI_DEV_TRACING` environment variable:

    ```bash
-    gemini
+    GEMINI_DEV_TRACING=true gemini
    ```

 3.  **View the traces:**
@@ -80,10 +84,10 @@ You can view traces in the Jaeger UI. To get started, follow these steps:
 For more detailed information on telemetry, see the
 [telemetry documentation](./cli/telemetry.md).

-### Instrumenting code with traces
+### Instrumenting code with dev traces

-You can add traces to your own code for more detailed instrumentation. This is
-useful for debugging and understanding the flow of execution.
+You can add dev traces to your own code for more detailed instrumentation. This
+is useful for debugging and understanding the flow of execution.

 Use the `runInDevTraceSpan` function to wrap any section of code in a trace
 span.
@@ -92,39 +96,29 @@ Here is a basic example:

 ```typescript
 import { runInDevTraceSpan } from '@google/gemini-cli-core';
-import { GeminiCliOperation } from '@google/gemini-cli-core/lib/telemetry/constants.js';

-await runInDevTraceSpan(
-  {
-    operation: GeminiCliOperation.ToolCall,
-    attributes: {
-      [GEN_AI_AGENT_NAME]: 'gemini-cli',
-    },
-  },
-  async ({ metadata }) => {
-    // The `metadata` object allows you to record the input and output of the
-    // operation as well as other attributes.
-    metadata.input = { key: 'value' };
-    // Set custom attributes.
-    metadata.attributes['custom.attribute'] = 'custom.value';
+await runInDevTraceSpan({ name: 'my-custom-span' }, async ({ metadata }) => {
+  // The `metadata` object allows you to record the input and output of the
+  // operation as well as other attributes.
+  metadata.input = { key: 'value' };
+  // Set custom attributes.
+  metadata.attributes['gen_ai.request.model'] = 'gemini-4.0-mega';

-    // Your code to be traced goes here
-    try {
-      const output = await somethingRisky();
-      metadata.output = output;
-      return output;
-    } catch (e) {
-      metadata.error = e;
-      throw e;
-    }
-  },
-);
+  // Your code to be traced goes here
+  try {
+    const output = await somethingRisky();
+    metadata.output = output;
+    return output;
+  } catch (e) {
+    metadata.error = e;
+    throw e;
+  }
+});
 ```

 In this example:

- `operation`: The operation type of the span, represented by the
-  `GeminiCliOperation` enum.
+- `name`: The name of the span, which will be displayed in the trace.
 - `metadata.input`: (Optional) An object containing the input data for the
  traced operation.
 - `metadata.output`: (Optional) An object containing the output data from the
@@ -322,12 +322,6 @@ their corresponding top-level category object in your `settings.json` file.
  - **Default:** `"tips"`
  - **Values:** `"tips"`, `"witty"`, `"all"`, `"off"`

- **`ui.errorVerbosity`** (enum):
-  - **Description:** Controls whether recoverable errors are hidden (low) or
-    fully shown (full).
-  - **Default:** `"low"`
-  - **Values:** `"low"`, `"full"`
-
 - **`ui.customWittyPhrases`** (array):
  - **Description:** Custom witty phrases to display during loading. When
    provided, the CLI cycles through these instead of the defaults.
@@ -363,15 +357,6 @@ their corresponding top-level category object in your `settings.json` file.
  - **Default:** `true`
  - **Requires restart:** Yes

-#### `billing`
-
- **`billing.overageStrategy`** (enum):
-  - **Description:** How to handle quota exhaustion when AI credits are
-    available. 'ask' prompts each time, 'always' automatically uses credits,
-    'never' disables credit usage.
-  - **Default:** `"ask"`
-  - **Values:** `"ask"`, `"always"`, `"never"`
-
 #### `model`

 - **`model.name`** (string):
@@ -866,11 +851,6 @@ their corresponding top-level category object in your `settings.json` file.
    confirmation dialogs.
  - **Default:** `false`

- **`security.autoAddPolicy`** (boolean):
-  - **Description:** Automatically add "Proceed always" approvals to your
-    persistent policy.
-  - **Default:** `true`
-
 - **`security.blockGitExtensions`** (boolean):
  - **Description:** Blocks installing and loading extensions from Git.
  - **Default:** `false`
@@ -1034,23 +1014,6 @@ their corresponding top-level category object in your `settings.json` file.
  - **Default:** `false`
  - **Requires restart:** Yes

- **`experimental.gemmaModelRouter.enabled`** (boolean):
-  - **Description:** Enable the Gemma Model Router. Requires a local endpoint
-    serving Gemma via the Gemini API using LiteRT-LM shim.
-  - **Default:** `false`
-  - **Requires restart:** Yes
-
- **`experimental.gemmaModelRouter.classifier.host`** (string):
-  - **Description:** The host of the classifier.
-  - **Default:** `"http://localhost:9379"`
-  - **Requires restart:** Yes
-
- **`experimental.gemmaModelRouter.classifier.model`** (string):
-  - **Description:** The model to use for the classifier. Only tested on
-    `gemma3-1b-gpu-custom`.
-  - **Default:** `"gemma3-1b-gpu-custom"`
-  - **Requires restart:** Yes
-
 #### `skills`

 - **`skills.enabled`** (boolean):
@@ -87,12 +87,12 @@ available combinations.

 #### Text Input

-| Action                                                     | Keys                                                                                      |
-| ---------------------------------------------------------- | ----------------------------------------------------------------------------------------- |
-| Submit the current prompt.                                 | `Enter (no Shift, Alt, Ctrl, Cmd)`                                                        |
-| Insert a newline without submitting.                       | `Ctrl + Enter`<br />`Cmd + Enter`<br />`Alt + Enter`<br />`Shift + Enter`<br />`Ctrl + J` |
-| Open the current prompt or the plan in an external editor. | `Ctrl + X`                                                                                |
-| Paste from the clipboard.                                  | `Ctrl + V`<br />`Cmd + V`<br />`Alt + V`                                                  |
+| Action                                         | Keys                                                                                      |
+| ---------------------------------------------- | ----------------------------------------------------------------------------------------- |
+| Submit the current prompt.                     | `Enter (no Shift, Alt, Ctrl, Cmd)`                                                        |
+| Insert a newline without submitting.           | `Ctrl + Enter`<br />`Cmd + Enter`<br />`Alt + Enter`<br />`Shift + Enter`<br />`Ctrl + J` |
+| Open the current prompt in an external editor. | `Ctrl + X`                                                                                |
+| Paste from the clipboard.                      | `Ctrl + V`<br />`Cmd + V`<br />`Alt + V`                                                  |

 #### App Controls

@@ -97,10 +97,9 @@ has a designated number that forms the base of the final priority calculation.
 | Tier      | Base | Description                                                                |
 | :-------- | :--- | :------------------------------------------------------------------------- |
 | Default   | 1    | Built-in policies that ship with the Gemini CLI.                           |
-| Extension | 2    | Policies defined in extensions.                                            |
-| Workspace | 3    | Policies defined in the current workspace's configuration directory.       |
-| User      | 4    | Custom policies defined by the user.                                       |
-| Admin     | 5    | Policies managed by an administrator (e.g., in an enterprise environment). |
+| Workspace | 2    | Policies defined in the current workspace's configuration directory.       |
+| User      | 3    | Custom policies defined by the user.                                       |
+| Admin     | 4    | Policies managed by an administrator (e.g., in an enterprise environment). |

 Within a TOML policy file, you assign a priority value from **0 to 999**. The
 engine transforms this into a final priority using the following formula:
@@ -5,19 +5,6 @@ problems encountered while using Gemini CLI.

 ## General issues

-This section addresses common questions about Gemini CLI usage, security, and
-troubleshooting general errors.
-
-### Why can't I use third-party software (e.g. Claude Code, OpenClaw, OpenCode) with Gemini CLI?
-
-Using third-party software, tools, or services to harvest or piggyback on Gemini
-CLI's OAuth authentication to access our backend services is a direct violation
-of our [applicable terms and policies](tos-privacy.md). Doing so bypasses our
-intended authentication and security structures, and such actions may be grounds
-for immediate suspension or termination of your account. If you would like to
-use a third-party coding agent with Gemini, the supported and secure method is
-to use a Vertex AI or Google AI Studio API key.
-
 ### Why am I getting an `API error: 429 - Resource exhausted`?

 This error indicates that you have exceeded your API request limit. The Gemini
@@ -7,12 +7,6 @@ is licensed under the
 When you use Gemini CLI to access or use Google’s services, the Terms of Service
 and Privacy Notices applicable to those services apply to such access and use.

-Directly accessing the services powering Gemini CLI (e.g., the Gemini Code
-Assist service) using third-party software, tools, or services (for example,
-using OpenClaw with Gemini CLI OAuth) is a violation of applicable terms and
-policies. Such actions may be grounds for suspension or termination of your
-account.
-
 Your Gemini CLI Usage Statistics are handled in accordance with Google's Privacy
 Policy.

@@ -1066,11 +1066,6 @@ command has no flags.
 gemini mcp list
 ```

-> **Note on Trust:** For security, `stdio` MCP servers (those using the
-> `command` property) are only tested and displayed as "Connected" if the
-> current folder is trusted. If the folder is untrusted, they will show as
-> "Disconnected". Use `gemini trust` to trust the current folder.
-
 **Example output:**

 ```sh
@@ -1079,23 +1074,6 @@ gemini mcp list
 ✗ sse-server: https://api.example.com/sse (sse) - Disconnected
 ```

-## Troubleshooting and Diagnostics
-
-To minimize noise during startup, MCP connection errors for background servers
-are "silent by default." If issues are detected during startup, a single
-informational hint will be shown: _"MCP issues detected. Run /mcp list for
-status."_
-
-Detailed, actionable diagnostics for a specific server are automatically
-re-enabled when:
-
-1.  You run an interactive command like `/mcp list`, `/mcp auth`, etc.
-2.  The model attempts to execute a tool from that server.
-3.  You invoke an MCP prompt from that server.
-
-You can also use `gemini mcp list` from your shell to see connection errors for
-all configured servers.
-
 ### Removing a server (`gemini mcp remove`)

 To delete a server from your configuration, use the `remove` command with the
@@ -46,20 +46,18 @@ two arguments:

 #### Policies

-Policies control how strictly a test is validated.
+Policies control how strictly a test is validated. Tests should generally use
+the ALWAYS_PASSES policy to offer the strictest guarantees.
+
+USUALLY_PASSES exists to enable assertion of less consistent or aspirational
+behaviors.

 - `ALWAYS_PASSES`: Tests expected to pass 100% of the time. These are typically
-  trivial and test basic functionality. These run in every CI and can block PRs
-  on failure.
+  trivial and test basic functionality. These run in every CI.
 - `USUALLY_PASSES`: Tests expected to pass most of the time but may have some
  flakiness due to non-deterministic behaviors. These are run nightly and used
  to track the health of the product from build to build.

-**All new behavioral evaluations must be created with the `USUALLY_PASSES`
-policy.** A subset that prove to be highly stable over time may be promoted to
-`ALWAYS_PASSES`. For more information, see
-[Test promotion process](#test-promotion-process).
-
 #### `EvalCase` Properties

 - `name`: The name of the evaluation case.
@@ -78,8 +76,7 @@ import { describe, expect } from 'vitest';
 import { evalTest } from './test-helper.js';

 describe('my_feature', () => {
-  // New tests MUST start as USUALLY_PASSES and be promoted via /promote-behavioral-eval
-  evalTest('USUALLY_PASSES', {
+  evalTest('ALWAYS_PASSES', {
    name: 'should do something',
    prompt: 'do it',
    assert: async (rig, result) => {
@@ -117,39 +114,6 @@ npm run test:all_evals
 This command sets the `RUN_EVALS` environment variable to `1`, which enables the
 `USUALLY_PASSES` tests.

-## Ensuring Eval is Stable Prior to Check-in
-
-The
-[Evals: Nightly](https://github.com/google-gemini/gemini-cli/actions/workflows/evals-nightly.yml)
-run is considered to be the source of truth for the quality of an eval test.
-Each run of it executes a test 3 times in a row, for each supported model. The
-result is then scored 0%, 33%, 66%, or 100% respectively, to indicate how many
-of the individual executions passed.
-
-Googlers can schedule a manual run against their branch by clicking the link
-above.
-
-Tests should score at least 66% with key models including Gemini 3.1 pro, Gemini
-3.0 pro, and Gemini 3 flash prior to check in and they must pass 100% of the
-time before they are promoted.
-
-## Test promotion process
-
-To maintain a stable and reliable CI, all new behavioral evaluations follow a
-mandatory deflaking process.
-
-1. **Incubation**: You must create all new tests with the `USUALLY_PASSES`
-   policy. This lets them be monitored in the nightly runs without blocking PRs.
-2. **Monitoring**: The test must complete at least 10 nightly runs across all
-   supported models.
-3. **Promotion**: Promotion to `ALWAYS_PASSES` happens exclusively through the
-   `/promote-behavioral-eval` slash command. This command verifies the 100%
-   success rate requirement is met across many runs before updating the test
-   policy.
-
-This promotion process is essential for preventing the introduction of flaky
-evaluations into the CI.
-
 ## Reporting

 Results for evaluations are available on GitHub Actions:
@@ -171,7 +135,7 @@ aggregated into a **Nightly Summary** attached to the workflow run.

 - **Pass Rate (%)**: Each cell represents the percentage of successful runs for
  a specific test in that workflow instance.
- **History**: The table shows the pass rates for the last 7 nightly runs,
+- **History**: The table shows the pass rates for the last 10 nightly runs,
  allowing you to identify if a model's behavior is trending towards
  instability.
 - **Total Pass Rate**: An aggregate metric of all evaluations run in that batch.
@@ -220,35 +184,8 @@ gemini /fix-behavioral-eval https://github.com/google-gemini/gemini-cli/actions/
 When investigating failures manually, you can also enable verbose agent logs by
 setting the `GEMINI_DEBUG_LOG_FILE` environment variable.

-### Best practices
-
 It's highly recommended to manually review and/or ask the agent to iterate on
 any prompt changes, even if they pass all evals. The prompt should prefer
 positive traits ('do X') and resort to negative traits ('do not do X') only when
 unable to accomplish the goal with positive traits. Gemini is quite good at
 instrospecting on its prompt when asked the right questions.
-
-## Promoting evaluations
-
-Evaluations must be promoted from `USUALLY_PASSES` to `ALWAYS_PASSES`
-exclusively using the `/promote-behavioral-eval` slash command. Manual promotion
-is not allowed to ensure that the 100% success rate requirement is empirically
-met.
-
-### `/promote-behavioral-eval`
-
-This command automates the promotion of stable tests by:
-
-1.  **Investigating**: Analyzing the results of the last 7 nightly runs on the
-    `main` branch using the `gh` CLI.
-2.  **Criteria Check**: Identifying tests that have passed 100% of the time for
-    ALL enabled models across the entire 7-run history.
-3.  **Promotion**: Updating the test file's policy from `USUALLY_PASSES` to
-    `ALWAYS_PASSES`.
-4.  **Verification**: Running the promoted test locally to ensure correctness.
-
-To run it:
-
-```bash
-gemini /promote-behavioral-eval
-```
@@ -8,7 +8,7 @@ import { describe, expect } from 'vitest';
 import { evalTest } from './test-helper.js';

 describe('validation_fidelity', () => {
-  evalTest('USUALLY_PASSES', {
+  evalTest('ALWAYS_PASSES', {
    name: 'should perform exhaustive validation autonomously when guided by system instructions',
    files: {
      'src/types.ts': `
@@ -72,6 +72,7 @@ describe('ACP telemetry', () => {
          GEMINI_TELEMETRY_ENABLED: 'true',
          GEMINI_TELEMETRY_TARGET: 'local',
          GEMINI_TELEMETRY_OUTFILE: telemetryPath,
+          // GEMINI_DEV_TRACING not set: fake responses aren't instrumented for spans
        },
      },
    );
@@ -2292,6 +2292,7 @@
      "integrity": "sha512-t54CUOsFMappY1Jbzb7fetWeO0n6K0k/4+/ZpkS+3Joz8I4VcvY9OiEBFRYISqaI2fq5sCiPtAjRDOzVYG8m+Q==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "@octokit/auth-token": "^6.0.0",
        "@octokit/graphql": "^9.0.2",
@@ -2472,6 +2473,7 @@
      "resolved": "https://registry.npmjs.org/@opentelemetry/api/-/api-1.9.0.tgz",
      "integrity": "sha512-3giAOQvZiH5F9bMlMiv8+GSPMeqg0dbaeo58/0SlA9sxSqZhnUtxzX9/2FzyhS9sWQf5S0GJE0AKBrFqjpeYcg==",
      "license": "Apache-2.0",
+      "peer": true,
      "engines": {
        "node": ">=8.0.0"
      }
@@ -2521,6 +2523,7 @@
      "resolved": "https://registry.npmjs.org/@opentelemetry/core/-/core-2.5.0.tgz",
      "integrity": "sha512-ka4H8OM6+DlUhSAZpONu0cPBtPPTQKxbxVzC4CzVx5+K4JnroJVBtDzLAMx4/3CDTJXRvVFhpFjtl4SaiTNoyQ==",
      "license": "Apache-2.0",
+      "peer": true,
      "dependencies": {
        "@opentelemetry/semantic-conventions": "^1.29.0"
      },
@@ -2895,6 +2898,7 @@
      "resolved": "https://registry.npmjs.org/@opentelemetry/resources/-/resources-2.5.0.tgz",
      "integrity": "sha512-F8W52ApePshpoSrfsSk1H2yJn9aKjCrbpQF1M9Qii0GHzbfVeFUB+rc3X4aggyZD8x9Gu3Slua+s6krmq6Dt8g==",
      "license": "Apache-2.0",
+      "peer": true,
      "dependencies": {
        "@opentelemetry/core": "2.5.0",
        "@opentelemetry/semantic-conventions": "^1.29.0"
@@ -2928,6 +2932,7 @@
      "resolved": "https://registry.npmjs.org/@opentelemetry/sdk-metrics/-/sdk-metrics-2.5.0.tgz",
      "integrity": "sha512-BeJLtU+f5Gf905cJX9vXFQorAr6TAfK3SPvTFqP+scfIpDQEJfRaGJWta7sJgP+m4dNtBf9y3yvBKVAZZtJQVA==",
      "license": "Apache-2.0",
+      "peer": true,
      "dependencies": {
        "@opentelemetry/core": "2.5.0",
        "@opentelemetry/resources": "2.5.0"
@@ -2982,6 +2987,7 @@
      "resolved": "https://registry.npmjs.org/@opentelemetry/sdk-trace-base/-/sdk-trace-base-2.5.0.tgz",
      "integrity": "sha512-VzRf8LzotASEyNDUxTdaJ9IRJ1/h692WyArDBInf5puLCjxbICD6XkHgpuudis56EndyS7LYFmtTMny6UABNdQ==",
      "license": "Apache-2.0",
+      "peer": true,
      "dependencies": {
        "@opentelemetry/core": "2.5.0",
        "@opentelemetry/resources": "2.5.0",
@@ -4178,6 +4184,7 @@
      "integrity": "sha512-6mDvHUFSjyT2B2yeNx2nUgMxh9LtOWvkhIU3uePn2I2oyNymUAX1NIsdgviM4CH+JSrp2D2hsMvJOkxY+0wNRA==",
      "devOptional": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "csstype": "^3.0.2"
      }
@@ -4451,6 +4458,7 @@
      "integrity": "sha512-klQbnPAAiGYFyI02+znpBRLyjL4/BrBd0nyWkdC0s/6xFLkXYQ8OoRrSkqacS1ddVxf/LDyODIKbQ5TgKAf/Fg==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "@typescript-eslint/scope-manager": "8.56.1",
        "@typescript-eslint/types": "8.56.1",
@@ -5298,6 +5306,7 @@
      "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.15.0.tgz",
      "integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
      "license": "MIT",
+      "peer": true,
      "bin": {
        "acorn": "bin/acorn"
      },
@@ -7851,6 +7860,7 @@
      "integrity": "sha512-VmQ+sifHUbI/IcSopBCF/HO3YiHQx/AVd3UVyYL6weuwW+HvON9VYn5l6Zl1WZzPWXPNZrSQpxwkkZ/VuvJZzg==",
      "dev": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "@eslint-community/eslint-utils": "^4.8.0",
        "@eslint-community/regexpp": "^4.12.1",
@@ -8483,6 +8493,7 @@
      "resolved": "https://registry.npmjs.org/express/-/express-5.2.1.tgz",
      "integrity": "sha512-hIS4idWWai69NezIdRt2xFVofaF4j+6INOpJlVOLDO8zXGpUVEVzIYk12UUi2JzjEzWL3IOAxcTubgz9Po0yXw==",
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "accepts": "^2.0.0",
        "body-parser": "^2.2.1",
@@ -9777,6 +9788,7 @@
      "resolved": "https://registry.npmjs.org/hono/-/hono-4.12.2.tgz",
      "integrity": "sha512-gJnaDHXKDayjt8ue0n8Gs0A007yKXj4Xzb8+cNjZeYsSzzwKc0Lr+OZgYwVfB0pHfUs17EPoLvrOsEaJ9mj+Tg==",
      "license": "MIT",
+      "peer": true,
      "engines": {
        "node": ">=16.9.0"
      }
@@ -10056,6 +10068,7 @@
      "resolved": "https://registry.npmjs.org/@jrichman/ink/-/ink-6.4.11.tgz",
      "integrity": "sha512-93LQlzT7vvZ1XJcmOMwN4s+6W334QegendeHOMnEJBlhnpIzr8bws6/aOEHG8ZCuVD/vNeeea5m1msHIdAY6ig==",
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "@alcalzone/ansi-tokenize": "^0.2.1",
        "ansi-escapes": "^7.0.0",
@@ -13705,6 +13718,7 @@
      "resolved": "https://registry.npmjs.org/react/-/react-19.2.4.tgz",
      "integrity": "sha512-9nfp2hYpCwOjAN+8TZFGhtWEwgvWHXqESH8qT89AT/lWklpLON22Lc8pEtnpsZz7VmawabSU0gCjnj8aC0euHQ==",
      "license": "MIT",
+      "peer": true,
      "engines": {
        "node": ">=0.10.0"
      }
@@ -13715,6 +13729,7 @@
      "integrity": "sha512-ePrwPfxAnB+7hgnEr8vpKxL9cmnp7F322t8oqcPshbIQQhDKgFDW4tjhF2wjVbdXF9O/nyuy3sQWd9JGpiLPvA==",
      "devOptional": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "shell-quote": "^1.6.1",
        "ws": "^7"
@@ -15674,6 +15689,7 @@
      "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
      "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
      "license": "MIT",
+      "peer": true,
      "engines": {
        "node": ">=12"
      },
@@ -15897,7 +15913,8 @@
      "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.8.1.tgz",
      "integrity": "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w==",
      "dev": true,
-      "license": "0BSD"
+      "license": "0BSD",
+      "peer": true
    },
    "node_modules/tsx": {
      "version": "4.20.3",
@@ -15905,6 +15922,7 @@
      "integrity": "sha512-qjbnuR9Tr+FJOMBqJCW5ehvIo/buZq7vH7qD7JziU98h6l3qGy0a/yPFjwO+y0/T7GFpNgNAvEcPPVfyT8rrPQ==",
      "devOptional": true,
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "esbuild": "~0.25.0",
        "get-tsconfig": "^4.7.5"
@@ -16064,6 +16082,7 @@
      "integrity": "sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ==",
      "devOptional": true,
      "license": "Apache-2.0",
+      "peer": true,
      "bin": {
        "tsc": "bin/tsc",
        "tsserver": "bin/tsserver"
@@ -16272,6 +16291,7 @@
      "resolved": "https://registry.npmjs.org/vite/-/vite-7.2.2.tgz",
      "integrity": "sha512-BxAKBWmIbrDgrokdGZH1IgkIk/5mMHDreLDmCJ0qpyJaAteP8NvMhkwr/ZCQNqNH97bw/dANTE9PDzqwJghfMQ==",
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "esbuild": "^0.25.0",
        "fdir": "^6.5.0",
@@ -16385,6 +16405,7 @@
      "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
      "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
      "license": "MIT",
+      "peer": true,
      "engines": {
        "node": ">=12"
      },
@@ -16397,6 +16418,7 @@
      "resolved": "https://registry.npmjs.org/vitest/-/vitest-3.2.4.tgz",
      "integrity": "sha512-LUCP5ev3GURDysTWiP47wRRUpLKMOfPh+yKTx3kVIEiu5KOMeqzpnYNsKyOoVrULivR8tLcks4+lga33Whn90A==",
      "license": "MIT",
+      "peer": true,
      "dependencies": {
        "@types/chai": "^5.2.2",
        "@vitest/expect": "3.2.4",
@@ -17041,6 +17063,7 @@
      "resolved": "https://registry.npmjs.org/zod/-/zod-3.25.76.tgz",
      "integrity": "sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ==",
      "license": "MIT",
+      "peer": true,
      "funding": {
        "url": "https://github.com/sponsors/colinhacks"
      }
@@ -17440,6 +17463,7 @@
      "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
      "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
      "license": "MIT",
+      "peer": true,
      "engines": {
        "node": ">=12"
      },
@@ -15,11 +15,4 @@
 - **Utilities**: Use `renderWithProviders` and `waitFor` from
  `packages/cli/src/test-utils/`.
 - **Snapshots**: Use `toMatchSnapshot()` to verify Ink output.
- **SVG Snapshots**: Use `await expect(renderResult).toMatchSvgSnapshot()` for
-  UI components whenever colors or detailed visual layout matter. SVG snapshots
-  capture styling accurately. Make sure to await the `waitUntilReady()` of the
-  render result before asserting. After updating SVG snapshots, always examine
-  the resulting `.svg` files (e.g. by reading their content or visually
-  inspecting them) to ensure the render and colors actually look as expected and
-  don't just contain an error message.
 - **Mocks**: Use mocks as sparingly as possible.
@@ -1,41 +0,0 @@
-# Policy engine example extension
-
-This extension demonstrates how to contribute security rules and safety checkers
-to the Gemini CLI Policy Engine.
-
-## Description
-
-The extension uses a `policies/` directory containing `.toml` files to define:
-
- A rule that requires user confirmation for `rm -rf` commands.
- A rule that denies searching for sensitive files (like `.env`) using `grep`.
- A safety checker that validates file paths for all write operations.
-
-## Structure
-
- `gemini-extension.json`: The manifest file.
- `policies/`: Contains the `.toml` policy files.
-
-## How to use
-
-1.  Link this extension to your local Gemini CLI installation:
-
-    ```bash
-    gemini extensions link packages/cli/src/commands/extensions/examples/policies
-    ```
-
-2.  Restart your Gemini CLI session.
-
-3.  **Observe the policies:**
-    - Try asking the model to delete a directory: The policy engine will prompt
-      you for confirmation due to the `rm -rf` rule.
-    - Try asking the model to search for secrets: The `grep` rule will deny the
-      request and display the custom deny message.
-    - Any file write operation will now be processed through the `allowed-path`
-      safety checker.
-
-## Security note
-
-For security, Gemini CLI ignores any `allow` decisions or `yolo` mode
-configurations contributed by extensions. This ensures that extensions can
-strengthen security but cannot bypass user confirmation.
@@ -1,5 +0,0 @@
-{
-  "name": "policy-example",
-  "version": "1.0.0",
-  "description": "An example extension demonstrating Policy Engine support."
-}
@@ -1,28 +0,0 @@
-# Example Policy Rules for Gemini CLI Extension
-#
-# Extensions run in Tier 2 (Extension Tier).
-# Security Note: 'allow' decisions and 'yolo' mode configurations are ignored.
-
-# Rule: Always ask the user before running a specific dangerous shell command.
-[[rule]]
-toolName = "run_shell_command"
-commandPrefix = "rm -rf"
-decision = "ask_user"
-priority = 100
-
-# Rule: Deny access to sensitive files using the grep tool.
-[[rule]]
-toolName = "grep_search"
-argsPattern = "(\.env|id_rsa|passwd)"
-decision = "deny"
-priority = 200
-deny_message = "Access to sensitive credentials or system files is restricted by the policy-example extension."
-
-# Safety Checker: Apply path validation to all write operations.
-[[safety_checker]]
-toolName = ["write_file", "replace"]
-priority = 300
-[safety_checker.checker]
-type = "in-process"
-name = "allowed-path"
-required_context = ["environment"]
@@ -4,15 +4,7 @@
 * SPDX-License-Identifier: Apache-2.0
 */

-import {
-  vi,
-  describe,
-  it,
-  expect,
-  beforeEach,
-  afterEach,
-  type Mock,
-} from 'vitest';
+import { vi, describe, it, expect, beforeEach, type Mock } from 'vitest';
 import { listMcpServers } from './list.js';
 import { loadSettings, mergeSettings } from '../../config/settings.js';
 import { createTransport, debugLogger } from '@google/gemini-cli-core';
@@ -114,10 +106,6 @@ describe('mcp list command', () => {
    mockedGetUserExtensionsDir.mockReturnValue('/mocked/extensions/dir');
  });

-  afterEach(() => {
-    vi.restoreAllMocks();
-  });
-
  it('should display message when no servers configured', async () => {
    const defaultMergedSettings = mergeSettings({}, {}, {}, {}, true);
    mockedLoadSettings.mockReturnValue({
@@ -145,7 +133,6 @@ describe('mcp list command', () => {
          },
        },
      },
-      isTrusted: true,
    });

    mockClient.connect.mockResolvedValue(undefined);
@@ -212,7 +199,6 @@ describe('mcp list command', () => {
          'config-server': { command: '/config/server' },
        },
      },
-      isTrusted: true,
    });

    mockExtensionManager.loadExtensions.mockReturnValue([
@@ -280,28 +266,4 @@ describe('mcp list command', () => {
      expect.anything(),
    );
  });
-
-  it('should show stdio servers as disconnected in untrusted folders', async () => {
-    const defaultMergedSettings = mergeSettings({}, {}, {}, {}, true);
-    mockedLoadSettings.mockReturnValue({
-      merged: {
-        ...defaultMergedSettings,
-        mcpServers: {
-          'test-server': { command: '/test/server' },
-        },
-      },
-      isTrusted: false,
-    });
-
-    // createTransport will throw in core if not trusted
-    mockedCreateTransport.mockRejectedValue(new Error('Folder not trusted'));
-
-    await listMcpServers();
-
-    expect(debugLogger.log).toHaveBeenCalledWith(
-      expect.stringContaining(
-        'test-server: /test/server  (stdio) - Disconnected',
-      ),
-    );
-  });
 });
@@ -20,7 +20,11 @@ import { ExtensionManager } from '../../config/extension-manager.js';
 import { requestConsentNonInteractive } from '../../config/extensions/consent.js';
 import { promptForSetting } from '../../config/extensions/extensionSettings.js';
 import { exitCli } from '../utils.js';
-import chalk from 'chalk';
+
+const COLOR_GREEN = '\u001b[32m';
+const COLOR_YELLOW = '\u001b[33m';
+const COLOR_RED = '\u001b[31m';
+const RESET_COLOR = '\u001b[0m';

 export async function getMcpServersFromConfig(
  settings?: MergedSettings,
@@ -62,56 +66,27 @@ async function testMCPConnection(
  serverName: string,
  config: MCPServerConfig,
 ): Promise<MCPServerStatus> {
-  const settings = loadSettings();
-
-  // SECURITY: Only test connection if workspace is trusted or if it's a remote server.
-  // stdio servers execute local commands and must never run in untrusted workspaces.
-  const isStdio = !!config.command;
-  if (isStdio && !settings.isTrusted) {
-    return MCPServerStatus.DISCONNECTED;
-  }
-
  const client = new Client({
    name: 'mcp-test-client',
    version: '0.0.1',
  });

-  const mcpContext = {
-    sanitizationConfig: {
-      enableEnvironmentVariableRedaction: true,
-      allowedEnvironmentVariables: [],
-      blockedEnvironmentVariables: settings.merged.advanced.excludedEnvVars,
-    },
-    emitMcpDiagnostic: (
-      severity: 'info' | 'warning' | 'error',
-      message: string,
-      error?: unknown,
-      serverName?: string,
-    ) => {
-      // In non-interactive list, we log everything through debugLogger for consistency
-      if (severity === 'error') {
-        debugLogger.error(
-          chalk.red(`Error${serverName ? ` (${serverName})` : ''}: ${message}`),
-          error,
-        );
-      } else if (severity === 'warning') {
-        debugLogger.warn(
-          chalk.yellow(
-            `Warning${serverName ? ` (${serverName})` : ''}: ${message}`,
-          ),
-          error,
-        );
-      } else {
-        debugLogger.log(message, error);
-      }
-    },
-    isTrustedFolder: () => settings.isTrusted,
+  const settings = loadSettings();
+  const sanitizationConfig = {
+    enableEnvironmentVariableRedaction: true,
+    allowedEnvironmentVariables: [],
+    blockedEnvironmentVariables: settings.merged.advanced.excludedEnvVars,
  };

  let transport;
  try {
    // Use the same transport creation logic as core
-    transport = await createTransport(serverName, config, false, mcpContext);
+    transport = await createTransport(
+      serverName,
+      config,
+      false,
+      sanitizationConfig,
+    );
  } catch (_error) {
    await client.close();
    return MCPServerStatus.DISCONNECTED;
@@ -150,7 +125,7 @@ export async function listMcpServers(settings?: MergedSettings): Promise<void> {
      blockedServerNames,
      undefined,
    );
-    debugLogger.log(chalk.yellow(message + '\n'));
+    debugLogger.log(COLOR_YELLOW + message + RESET_COLOR + '\n');
  }

  if (serverNames.length === 0) {
@@ -171,16 +146,16 @@ export async function listMcpServers(settings?: MergedSettings): Promise<void> {
    let statusText = '';
    switch (status) {
      case MCPServerStatus.CONNECTED:
-        statusIndicator = chalk.green('✓');
+        statusIndicator = COLOR_GREEN + '✓' + RESET_COLOR;
        statusText = 'Connected';
        break;
      case MCPServerStatus.CONNECTING:
-        statusIndicator = chalk.yellow('…');
+        statusIndicator = COLOR_YELLOW + '…' + RESET_COLOR;
        statusText = 'Connecting';
        break;
      case MCPServerStatus.DISCONNECTED:
      default:
-        statusIndicator = chalk.red('✗');
+        statusIndicator = COLOR_RED + '✗' + RESET_COLOR;
        statusText = 'Disconnected';
        break;
    }
@@ -2765,66 +2765,6 @@ describe('loadCliConfig approval mode', () => {
  });
 });

-describe('loadCliConfig gemmaModelRouter', () => {
-  beforeEach(() => {
-    vi.resetAllMocks();
-    vi.mocked(os.homedir).mockReturnValue('/mock/home/user');
-    vi.stubEnv('GEMINI_API_KEY', 'test-api-key');
-    vi.spyOn(ExtensionManager.prototype, 'getExtensions').mockReturnValue([]);
-  });
-
-  afterEach(() => {
-    vi.unstubAllEnvs();
-    vi.restoreAllMocks();
-  });
-
-  it('should have gemmaModelRouter disabled by default', async () => {
-    process.argv = ['node', 'script.js'];
-    const argv = await parseArguments(createTestMergedSettings());
-    const settings = createTestMergedSettings();
-    const config = await loadCliConfig(settings, 'test-session', argv);
-    expect(config.getGemmaModelRouterEnabled()).toBe(false);
-  });
-
-  it('should load gemmaModelRouter settings from merged settings', async () => {
-    process.argv = ['node', 'script.js'];
-    const argv = await parseArguments(createTestMergedSettings());
-    const settings = createTestMergedSettings({
-      experimental: {
-        gemmaModelRouter: {
-          enabled: true,
-          classifier: {
-            host: 'http://custom:1234',
-            model: 'custom-gemma',
-          },
-        },
-      },
-    });
-    const config = await loadCliConfig(settings, 'test-session', argv);
-    expect(config.getGemmaModelRouterEnabled()).toBe(true);
-    const gemmaSettings = config.getGemmaModelRouterSettings();
-    expect(gemmaSettings.classifier?.host).toBe('http://custom:1234');
-    expect(gemmaSettings.classifier?.model).toBe('custom-gemma');
-  });
-
-  it('should handle partial gemmaModelRouter settings', async () => {
-    process.argv = ['node', 'script.js'];
-    const argv = await parseArguments(createTestMergedSettings());
-    const settings = createTestMergedSettings({
-      experimental: {
-        gemmaModelRouter: {
-          enabled: true,
-        },
-      },
-    });
-    const config = await loadCliConfig(settings, 'test-session', argv);
-    expect(config.getGemmaModelRouterEnabled()).toBe(true);
-    const gemmaSettings = config.getGemmaModelRouterSettings();
-    expect(gemmaSettings.classifier?.host).toBe('http://localhost:9379');
-    expect(gemmaSettings.classifier?.model).toBe('gemma3-1b-gpu-custom');
-  });
-});
-
 describe('loadCliConfig fileFiltering', () => {
  const originalArgv = process.argv;

@@ -818,10 +818,9 @@ export async function loadCliConfig(
    model: resolvedModel,
    maxSessionTurns: settings.model?.maxSessionTurns,
    experimentalZedIntegration: argv.experimentalAcp || false,
+    listExtensions: argv.listExtensions || false,
    listSessions: argv.listSessions || false,
    deleteSession: argv.deleteSession,
-    autoAddPolicy:
-      settings.security?.autoAddPolicy && !settings.admin?.secureModeEnabled,
    enabledExtensions: argv.extensions,
    extensionLoader: extensionManager,
    enableExtensionReloading: settings.experimental?.extensionReloading,
@@ -857,7 +856,6 @@ export async function loadCliConfig(
      // eslint-disable-next-line @typescript-eslint/no-unsafe-type-assertion
      format: (argv.outputFormat ?? settings.output?.format) as OutputFormat,
    },
-    gemmaModelRouter: settings.experimental?.gemmaModelRouter,
    fakeResponses: argv.fakeResponses,
    recordResponses: argv.recordResponses,
    retryFetchErrors: settings.general?.retryFetchErrors,
@@ -52,10 +52,6 @@ import {
  applyAdminAllowlist,
  getAdminBlockedMcpServersMessage,
  CoreToolCallStatus,
-  loadExtensionPolicies,
-  isSubpath,
-  type PolicyRule,
-  type SafetyCheckerRule,
  HookType,
 } from '@google/gemini-cli-core';
 import { maybeRequestConsentOrFail } from './extensions/consent.js';
@@ -768,18 +764,9 @@ Would you like to attempt to install via "git clone" instead?`,
      }

      const contextFiles = getContextFileNames(config)
-        .map((contextFileName) => {
-          const contextFilePath = path.join(
-            effectiveExtensionPath,
-            contextFileName,
-          );
-          if (!isSubpath(effectiveExtensionPath, contextFilePath)) {
-            throw new Error(
-              `Invalid context file path: "${contextFileName}". Context files must be within the extension directory.`,
-            );
-          }
-          return contextFilePath;
-        })
+        .map((contextFileName) =>
+          path.join(effectiveExtensionPath, contextFileName),
+        )
        .filter((contextFilePath) => fs.existsSync(contextFilePath));

      const hydrationContext: VariableContext = {
@@ -833,24 +820,6 @@ Would you like to attempt to install via "git clone" instead?`,
        recursivelyHydrateStrings(skill, hydrationContext),
      );

-      let rules: PolicyRule[] | undefined;
-      let checkers: SafetyCheckerRule[] | undefined;
-
-      const policyDir = path.join(effectiveExtensionPath, 'policies');
-      if (fs.existsSync(policyDir)) {
-        const result = await loadExtensionPolicies(config.name, policyDir);
-        rules = result.rules;
-        checkers = result.checkers;
-
-        if (result.errors.length > 0) {
-          for (const error of result.errors) {
-            debugLogger.warn(
-              `[ExtensionManager] Error loading policies from ${config.name}: ${error.message}${error.details ? `\nDetails: ${error.details}` : ''}`,
-            );
-          }
-        }
-      }
-
      const agentLoadResult = await loadAgentsFromDirectory(
        path.join(effectiveExtensionPath, 'agents'),
      );
@@ -884,8 +853,6 @@ Would you like to attempt to install via "git clone" instead?`,
        skills,
        agents: agentLoadResult.agents,
        themes: config.themes,
-        rules,
-        checkers,
      };
    } catch (e) {
      debugLogger.error(
@@ -239,27 +239,6 @@ describe('extension tests', () => {
      expect(extensions[0].name).toBe('test-extension');
    });

-    it('should throw an error if a context file path is outside the extension directory', async () => {
-      const consoleSpy = vi
-        .spyOn(console, 'error')
-        .mockImplementation(() => {});
-      createExtension({
-        extensionsDir: userExtensionsDir,
-        name: 'traversal-extension',
-        version: '1.0.0',
-        contextFileName: '../secret.txt',
-      });
-
-      const extensions = await extensionManager.loadExtensions();
-      expect(extensions).toHaveLength(0);
-      expect(consoleSpy).toHaveBeenCalledWith(
-        expect.stringContaining(
-          'traversal-extension: Invalid context file path: "../secret.txt"',
-        ),
-      );
-      consoleSpy.mockRestore();
-    });
-
    it('should load context file path when GEMINI.md is present', async () => {
      createExtension({
        extensionsDir: userExtensionsDir,
@@ -384,111 +363,6 @@ describe('extension tests', () => {
      ]);
    });

-    it('should load extension policies from the policies directory', async () => {
-      const extDir = createExtension({
-        extensionsDir: userExtensionsDir,
-        name: 'policy-extension',
-        version: '1.0.0',
-      });
-
-      const policiesDir = path.join(extDir, 'policies');
-      fs.mkdirSync(policiesDir);
-
-      const policiesContent = `
-[[rule]]
-toolName = "deny_tool"
-decision = "deny"
-priority = 500
-
-[[rule]]
-toolName = "ask_tool"
-decision = "ask_user"
-priority = 100
-`;
-      fs.writeFileSync(
-        path.join(policiesDir, 'policies.toml'),
-        policiesContent,
-      );
-
-      const extensions = await extensionManager.loadExtensions();
-      expect(extensions).toHaveLength(1);
-      const extension = extensions[0];
-
-      expect(extension.rules).toBeDefined();
-      expect(extension.rules).toHaveLength(2);
-      expect(
-        extension.rules!.find((r) => r.toolName === 'deny_tool')?.decision,
-      ).toBe('deny');
-      expect(
-        extension.rules!.find((r) => r.toolName === 'ask_tool')?.decision,
-      ).toBe('ask_user');
-      // Verify source is prefixed
-      expect(extension.rules![0].source).toContain(
-        'Extension (policy-extension):',
-      );
-    });
-
-    it('should ignore ALLOW rules and YOLO mode from extension policies for security', async () => {
-      const consoleSpy = vi.spyOn(console, 'warn').mockImplementation(() => {});
-      const extDir = createExtension({
-        extensionsDir: userExtensionsDir,
-        name: 'security-test-extension',
-        version: '1.0.0',
-      });
-
-      const policiesDir = path.join(extDir, 'policies');
-      fs.mkdirSync(policiesDir);
-
-      const policiesContent = `
-[[rule]]
-toolName = "allow_tool"
-decision = "allow"
-priority = 100
-
-[[rule]]
-toolName = "yolo_tool"
-decision = "ask_user"
-priority = 100
-modes = ["yolo"]
-
-[[safety_checker]]
-toolName = "yolo_check"
-priority = 100
-modes = ["yolo"]
-[safety_checker.checker]
-type = "external"
-name = "yolo-checker"
-`;
-      fs.writeFileSync(
-        path.join(policiesDir, 'policies.toml'),
-        policiesContent,
-      );
-
-      const extensions = await extensionManager.loadExtensions();
-      expect(extensions).toHaveLength(1);
-      const extension = extensions[0];
-
-      // ALLOW rules and YOLO rules/checkers should be filtered out
-      expect(extension.rules).toBeDefined();
-      expect(extension.rules).toHaveLength(0);
-      expect(extension.checkers).toBeDefined();
-      expect(extension.checkers).toHaveLength(0);
-
-      // Should have logged warnings
-      expect(consoleSpy).toHaveBeenCalledWith(
-        expect.stringContaining('attempted to contribute an ALLOW rule'),
-      );
-      expect(consoleSpy).toHaveBeenCalledWith(
-        expect.stringContaining('attempted to contribute a rule for YOLO mode'),
-      );
-      expect(consoleSpy).toHaveBeenCalledWith(
-        expect.stringContaining(
-          'attempted to contribute a safety checker for YOLO mode',
-        ),
-      );
-      consoleSpy.mockRestore();
-    });
-
    it('should hydrate ${extensionPath} correctly for linked extensions', async () => {
      const sourceExtDir = getRealPath(
        createExtension({
@@ -666,7 +540,7 @@ name = "yolo-checker"

      // Bad extension
      const badExtDir = path.join(userExtensionsDir, 'bad-ext');
-      fs.mkdirSync(badExtDir, { recursive: true });
+      fs.mkdirSync(badExtDir);
      const badConfigPath = path.join(badExtDir, EXTENSIONS_CONFIG_FILENAME);
      fs.writeFileSync(badConfigPath, '{ "name": "bad-ext"'); // Malformed

@@ -674,7 +548,7 @@ name = "yolo-checker"

      expect(extensions).toHaveLength(1);
      expect(extensions[0].name).toBe('good-ext');
-      expect(consoleSpy).toHaveBeenCalledWith(
+      expect(consoleSpy).toHaveBeenCalledExactlyOnceWith(
        expect.stringContaining(
          `Warning: Skipping extension in ${badExtDir}: Failed to load extension config from ${badConfigPath}`,
        ),
@@ -697,7 +571,7 @@ name = "yolo-checker"

      // Bad extension
      const badExtDir = path.join(userExtensionsDir, 'bad-ext-no-name');
-      fs.mkdirSync(badExtDir, { recursive: true });
+      fs.mkdirSync(badExtDir);
      const badConfigPath = path.join(badExtDir, EXTENSIONS_CONFIG_FILENAME);
      fs.writeFileSync(badConfigPath, JSON.stringify({ version: '1.0.0' }));

@@ -705,7 +579,7 @@ name = "yolo-checker"

      expect(extensions).toHaveLength(1);
      expect(extensions[0].name).toBe('good-ext');
-      expect(consoleSpy).toHaveBeenCalledWith(
+      expect(consoleSpy).toHaveBeenCalledExactlyOnceWith(
        expect.stringContaining(
          `Warning: Skipping extension in ${badExtDir}: Failed to load extension config from ${badConfigPath}: Invalid configuration in ${badConfigPath}: missing "name"`,
        ),
@@ -489,7 +489,7 @@ export const commandDescriptions: Readonly<Record<Command, string>> = {
  [Command.SUBMIT]: 'Submit the current prompt.',
  [Command.NEWLINE]: 'Insert a newline without submitting.',
  [Command.OPEN_EXTERNAL_EDITOR]:
-    'Open the current prompt or the plan in an external editor.',
+    'Open the current prompt in an external editor.',
  [Command.PASTE_CLIPBOARD]: 'Paste from the clipboard.',

  // App Controls
@@ -177,13 +177,13 @@ describe('Policy Engine Integration Tests', () => {
      );
      const engine = new PolicyEngine(config);

-      // MCP server allowed (priority 4.1) provides general allow for server
-      // MCP server allowed (priority 4.1) provides general allow for server
+      // MCP server allowed (priority 3.1) provides general allow for server
+      // MCP server allowed (priority 3.1) provides general allow for server
      expect(
        (await engine.check({ name: 'my-server__safe-tool' }, undefined))
          .decision,
      ).toBe(PolicyDecision.ALLOW);
-      // But specific tool exclude (priority 4.4) wins over server allow
+      // But specific tool exclude (priority 3.4) wins over server allow
      expect(
        (await engine.check({ name: 'my-server__dangerous-tool' }, undefined))
          .decision,
@@ -476,25 +476,25 @@ describe('Policy Engine Integration Tests', () => {

      // Find rules and verify their priorities
      const blockedToolRule = rules.find((r) => r.toolName === 'blocked-tool');
-      expect(blockedToolRule?.priority).toBe(4.4); // Command line exclude
+      expect(blockedToolRule?.priority).toBe(3.4); // Command line exclude

      const blockedServerRule = rules.find(
        (r) => r.toolName === 'blocked-server__*',
      );
-      expect(blockedServerRule?.priority).toBe(4.9); // MCP server exclude
+      expect(blockedServerRule?.priority).toBe(3.9); // MCP server exclude

      const specificToolRule = rules.find(
        (r) => r.toolName === 'specific-tool',
      );
-      expect(specificToolRule?.priority).toBe(4.3); // Command line allow
+      expect(specificToolRule?.priority).toBe(3.3); // Command line allow

      const trustedServerRule = rules.find(
        (r) => r.toolName === 'trusted-server__*',
      );
-      expect(trustedServerRule?.priority).toBe(4.2); // MCP trusted server
+      expect(trustedServerRule?.priority).toBe(3.2); // MCP trusted server

      const mcpServerRule = rules.find((r) => r.toolName === 'mcp-server__*');
-      expect(mcpServerRule?.priority).toBe(4.1); // MCP allowed server
+      expect(mcpServerRule?.priority).toBe(3.1); // MCP allowed server

      const readOnlyToolRule = rules.find((r) => r.toolName === 'glob');
      // Priority 70 in default tier → 1.07 (Overriding Plan Mode Deny)
@@ -641,16 +641,16 @@ describe('Policy Engine Integration Tests', () => {

      // Verify each rule has the expected priority
      const tool3Rule = rules.find((r) => r.toolName === 'tool3');
-      expect(tool3Rule?.priority).toBe(4.4); // Excluded tools (user tier)
+      expect(tool3Rule?.priority).toBe(3.4); // Excluded tools (user tier)

      const server2Rule = rules.find((r) => r.toolName === 'server2__*');
-      expect(server2Rule?.priority).toBe(4.9); // Excluded servers (user tier)
+      expect(server2Rule?.priority).toBe(3.9); // Excluded servers (user tier)

      const tool1Rule = rules.find((r) => r.toolName === 'tool1');
-      expect(tool1Rule?.priority).toBe(4.3); // Allowed tools (user tier)
+      expect(tool1Rule?.priority).toBe(3.3); // Allowed tools (user tier)

      const server1Rule = rules.find((r) => r.toolName === 'server1__*');
-      expect(server1Rule?.priority).toBe(4.1); // Allowed servers (user tier)
+      expect(server1Rule?.priority).toBe(3.1); // Allowed servers (user tier)

      const globRule = rules.find((r) => r.toolName === 'glob');
      // Priority 70 in default tier → 1.07
@@ -12,8 +12,6 @@ import {
  resolveWorkspacePolicyState,
  autoAcceptWorkspacePolicies,
  setAutoAcceptWorkspacePolicies,
-  disableWorkspacePolicies,
-  setDisableWorkspacePolicies,
 } from './policy.js';
 import { writeToStderr } from '@google/gemini-cli-core';

@@ -47,9 +45,6 @@ describe('resolveWorkspacePolicyState', () => {
    fs.mkdirSync(workspaceDir);
    policiesDir = path.join(workspaceDir, '.gemini', 'policies');

-    // Enable policies for these tests to verify loading logic
-    setDisableWorkspacePolicies(false);
-
    vi.clearAllMocks();
  });

@@ -72,13 +67,6 @@ describe('resolveWorkspacePolicyState', () => {
    });
  });

-  it('should have disableWorkspacePolicies set to true by default', () => {
-    // We explicitly set it to false in beforeEach for other tests,
-    // so here we test that setting it to true works.
-    setDisableWorkspacePolicies(true);
-    expect(disableWorkspacePolicies).toBe(true);
-  });
-
  it('should return policy directory if integrity matches', async () => {
    // Set up policies directory with a file
    fs.mkdirSync(policiesDir, { recursive: true });
@@ -200,26 +188,7 @@ describe('resolveWorkspacePolicyState', () => {
    expect(result.policyUpdateConfirmationRequest).toBeUndefined();
  });

-  it('should return empty state if disableWorkspacePolicies is true even if folder is trusted', async () => {
-    setDisableWorkspacePolicies(true);
-
-    // Set up policies directory with a file
-    fs.mkdirSync(policiesDir, { recursive: true });
-    fs.writeFileSync(path.join(policiesDir, 'policy.toml'), 'rules = []');
-
-    const result = await resolveWorkspacePolicyState({
-      cwd: workspaceDir,
-      trustedFolder: true,
-      interactive: true,
-    });
-
-    expect(result).toEqual({
-      workspacePoliciesDir: undefined,
-      policyUpdateConfirmationRequest: undefined,
-    });
-  });
-
-  it('should return empty state if cwd is a symlink to the home directory', async () => {
+  it('should not return workspace policies if cwd is a symlink to the home directory', async () => {
    const policiesDir = path.join(tempDir, '.gemini', 'policies');
    fs.mkdirSync(policiesDir, { recursive: true });
    fs.writeFileSync(path.join(policiesDir, 'policy.toml'), 'rules = []');
@@ -35,20 +35,6 @@ export function setAutoAcceptWorkspacePolicies(value: boolean) {
  autoAcceptWorkspacePolicies = value;
 }

-/**
- * Temporary flag to disable workspace level policies altogether.
- * Exported as 'let' to allow monkey patching in tests via the setter.
- */
-export let disableWorkspacePolicies = true;
-
-/**
- * Sets the disableWorkspacePolicies flag.
- * Used primarily for testing purposes.
- */
-export function setDisableWorkspacePolicies(value: boolean) {
-  disableWorkspacePolicies = value;
-}
-
 export async function createPolicyEngineConfig(
  settings: Settings,
  approvalMode: ApprovalMode,
@@ -95,7 +81,7 @@ export async function resolveWorkspacePolicyState(options: {
    | PolicyUpdateConfirmationRequest
    | undefined;

-  if (trustedFolder && !disableWorkspacePolicies) {
+  if (trustedFolder) {
    const storage = new Storage(cwd);

    // If we are in the home directory (or rather, our target Gemini dir is the global one),
@@ -96,14 +96,6 @@ describe('SettingsSchema', () => {
      ]);
    });

-    it('should have errorVerbosity enum property', () => {
-      const definition = getSettingsSchema().ui?.properties?.errorVerbosity;
-      expect(definition).toBeDefined();
-      expect(definition?.type).toBe('enum');
-      expect(definition?.default).toBe('low');
-      expect(definition?.options?.map((o) => o.value)).toEqual(['low', 'full']);
-    });
-
    it('should have checkpointing nested properties', () => {
      expect(
        getSettingsSchema().general?.properties?.checkpointing.properties
@@ -452,60 +444,6 @@ describe('SettingsSchema', () => {
      expect(hookItemProperties.description).toBeDefined();
      expect(hookItemProperties.description.type).toBe('string');
    });
-
-    it('should have gemmaModelRouter setting in schema', () => {
-      const gemmaModelRouter =
-        getSettingsSchema().experimental.properties.gemmaModelRouter;
-      expect(gemmaModelRouter).toBeDefined();
-      expect(gemmaModelRouter.type).toBe('object');
-      expect(gemmaModelRouter.category).toBe('Experimental');
-      expect(gemmaModelRouter.default).toEqual({});
-      expect(gemmaModelRouter.requiresRestart).toBe(true);
-      expect(gemmaModelRouter.showInDialog).toBe(true);
-      expect(gemmaModelRouter.description).toBe(
-        'Enable Gemma model router (experimental).',
-      );
-
-      const enabled = gemmaModelRouter.properties.enabled;
-      expect(enabled).toBeDefined();
-      expect(enabled.type).toBe('boolean');
-      expect(enabled.category).toBe('Experimental');
-      expect(enabled.default).toBe(false);
-      expect(enabled.requiresRestart).toBe(true);
-      expect(enabled.showInDialog).toBe(true);
-      expect(enabled.description).toBe(
-        'Enable the Gemma Model Router. Requires a local endpoint serving Gemma via the Gemini API using LiteRT-LM shim.',
-      );
-
-      const classifier = gemmaModelRouter.properties.classifier;
-      expect(classifier).toBeDefined();
-      expect(classifier.type).toBe('object');
-      expect(classifier.category).toBe('Experimental');
-      expect(classifier.default).toEqual({});
-      expect(classifier.requiresRestart).toBe(true);
-      expect(classifier.showInDialog).toBe(false);
-      expect(classifier.description).toBe('Classifier configuration.');
-
-      const host = classifier.properties.host;
-      expect(host).toBeDefined();
-      expect(host.type).toBe('string');
-      expect(host.category).toBe('Experimental');
-      expect(host.default).toBe('http://localhost:9379');
-      expect(host.requiresRestart).toBe(true);
-      expect(host.showInDialog).toBe(false);
-      expect(host.description).toBe('The host of the classifier.');
-
-      const model = classifier.properties.model;
-      expect(model).toBeDefined();
-      expect(model.type).toBe('string');
-      expect(model.category).toBe('Experimental');
-      expect(model.default).toBe('gemma3-1b-gpu-custom');
-      expect(model.requiresRestart).toBe(true);
-      expect(model.showInDialog).toBe(false);
-      expect(model.description).toBe(
-        'The model to use for the classifier. Only tested on `gemma3-1b-gpu-custom`.',
-      );
-    });
  });

  it('has JSON schema definitions for every referenced ref', () => {
@@ -719,20 +719,6 @@ const SETTINGS_SCHEMA = {
          { value: 'off', label: 'Off' },
        ],
      },
-      errorVerbosity: {
-        type: 'enum',
-        label: 'Error Verbosity',
-        category: 'UI',
-        requiresRestart: false,
-        default: 'low',
-        description:
-          'Controls whether recoverable errors are hidden (low) or fully shown (full).',
-        showInDialog: true,
-        options: [
-          { value: 'low', label: 'Low' },
-          { value: 'full', label: 'Full' },
-        ],
-      },
      customWittyPhrases: {
        type: 'array',
        label: 'Custom Witty Phrases',
@@ -842,36 +828,6 @@ const SETTINGS_SCHEMA = {
    ref: 'TelemetrySettings',
  },

-  billing: {
-    type: 'object',
-    label: 'Billing',
-    category: 'Advanced',
-    requiresRestart: false,
-    default: {},
-    description: 'Billing and AI credits settings.',
-    showInDialog: false,
-    properties: {
-      overageStrategy: {
-        type: 'enum',
-        label: 'Overage Strategy',
-        category: 'Advanced',
-        requiresRestart: false,
-        default: 'ask',
-        description: oneLine`
-          How to handle quota exhaustion when AI credits are available.
-          'ask' prompts each time, 'always' automatically uses credits,
-          'never' disables credit usage.
-        `,
-        showInDialog: true,
-        options: [
-          { value: 'ask', label: 'Ask each time' },
-          { value: 'always', label: 'Always use credits' },
-          { value: 'never', label: 'Never use credits' },
-        ],
-      },
-    },
-  },
-
  model: {
    type: 'object',
    label: 'Model',
@@ -1480,16 +1436,6 @@ const SETTINGS_SCHEMA = {
          'Enable the "Allow for all future sessions" option in tool confirmation dialogs.',
        showInDialog: true,
      },
-      autoAddPolicy: {
-        type: 'boolean',
-        label: 'Auto-add to Policy',
-        category: 'Security',
-        requiresRestart: false,
-        default: true,
-        description:
-          'Automatically add "Proceed always" approvals to your persistent policy.',
-        showInDialog: true,
-      },
      blockGitExtensions: {
        type: 'boolean',
        label: 'Blocks extensions from Git',
@@ -1841,57 +1787,6 @@ const SETTINGS_SCHEMA = {
          'Enable web fetch behavior that bypasses LLM summarization.',
        showInDialog: true,
      },
-      gemmaModelRouter: {
-        type: 'object',
-        label: 'Gemma Model Router',
-        category: 'Experimental',
-        requiresRestart: true,
-        default: {},
-        description: 'Enable Gemma model router (experimental).',
-        showInDialog: true,
-        properties: {
-          enabled: {
-            type: 'boolean',
-            label: 'Enable Gemma Model Router',
-            category: 'Experimental',
-            requiresRestart: true,
-            default: false,
-            description:
-              'Enable the Gemma Model Router. Requires a local endpoint serving Gemma via the Gemini API using LiteRT-LM shim.',
-            showInDialog: true,
-          },
-          classifier: {
-            type: 'object',
-            label: 'Classifier',
-            category: 'Experimental',
-            requiresRestart: true,
-            default: {},
-            description: 'Classifier configuration.',
-            showInDialog: false,
-            properties: {
-              host: {
-                type: 'string',
-                label: 'Host',
-                category: 'Experimental',
-                requiresRestart: true,
-                default: 'http://localhost:9379',
-                description: 'The host of the classifier.',
-                showInDialog: false,
-              },
-              model: {
-                type: 'string',
-                label: 'Model',
-                category: 'Experimental',
-                requiresRestart: true,
-                default: 'gemma3-1b-gpu-custom',
-                description:
-                  'The model to use for the classifier. Only tested on `gemma3-1b-gpu-custom`.',
-                showInDialog: false,
-              },
-            },
-          },
-        },
-      },
    },
  },

@@ -2637,9 +2532,7 @@ type InferSettings<T extends SettingsSchema> = {
        : T[K]['default']
      : T[K]['default'] extends boolean
        ? boolean
-        : T[K]['default'] extends string
-          ? string
-          : T[K]['default'];
+        : T[K]['default'];
 };

 type InferMergedSettings<T extends SettingsSchema> = {
@@ -2651,9 +2544,7 @@ type InferMergedSettings<T extends SettingsSchema> = {
        : T[K]['default']
      : T[K]['default'] extends boolean
        ? boolean
-        : T[K]['default'] extends string
-          ? string
-          : T[K]['default'];
+        : T[K]['default'];
 };

 export type Settings = InferSettings<SettingsSchemaType>;
@@ -54,7 +54,6 @@ describe('Workspace-Level Policy CLI Integration', () => {

  beforeEach(() => {
    vi.clearAllMocks();
-    Policy.setDisableWorkspacePolicies(false);
    // Default to MATCH for existing tests
    mockCheckIntegrity.mockResolvedValue({
      status: 'match',
@@ -17,6 +17,7 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
    await importOriginal<typeof import('@google/gemini-cli-core')>();
  return {
    ...actual,
+    getErrorMessage: (e: unknown) => (e as Error).message,
  };
 });

@@ -31,7 +32,7 @@ describe('auth', () => {

  it('should return null if authType is undefined', async () => {
    const result = await performInitialAuth(mockConfig, undefined);
-    expect(result).toEqual({ authError: null, accountSuspensionInfo: null });
+    expect(result).toBeNull();
    expect(mockConfig.refreshAuth).not.toHaveBeenCalled();
  });

@@ -40,7 +41,7 @@ describe('auth', () => {
      mockConfig,
      AuthType.LOGIN_WITH_GOOGLE,
    );
-    expect(result).toEqual({ authError: null, accountSuspensionInfo: null });
+    expect(result).toBeNull();
    expect(mockConfig.refreshAuth).toHaveBeenCalledWith(
      AuthType.LOGIN_WITH_GOOGLE,
    );
@@ -53,10 +54,7 @@ describe('auth', () => {
      mockConfig,
      AuthType.LOGIN_WITH_GOOGLE,
    );
-    expect(result).toEqual({
-      authError: 'Failed to login. Message: Auth failed',
-      accountSuspensionInfo: null,
-    });
+    expect(result).toBe('Failed to login. Message: Auth failed');
    expect(mockConfig.refreshAuth).toHaveBeenCalledWith(
      AuthType.LOGIN_WITH_GOOGLE,
    );
@@ -70,48 +68,7 @@ describe('auth', () => {
      mockConfig,
      AuthType.LOGIN_WITH_GOOGLE,
    );
-    expect(result).toEqual({ authError: null, accountSuspensionInfo: null });
-    expect(mockConfig.refreshAuth).toHaveBeenCalledWith(
-      AuthType.LOGIN_WITH_GOOGLE,
-    );
-  });
-
-  it('should return accountSuspensionInfo for 403 TOS_VIOLATION error', async () => {
-    vi.mocked(mockConfig.refreshAuth).mockRejectedValue({
-      response: {
-        data: {
-          error: {
-            code: 403,
-            message:
-              'This service has been disabled for violation of Terms of Service.',
-            details: [
-              {
-                '@type': 'type.googleapis.com/google.rpc.ErrorInfo',
-                reason: 'TOS_VIOLATION',
-                domain: 'example.googleapis.com',
-                metadata: {
-                  appeal_url: 'https://example.com/appeal',
-                  appeal_url_link_text: 'Appeal Here',
-                },
-              },
-            ],
-          },
-        },
-      },
-    });
-    const result = await performInitialAuth(
-      mockConfig,
-      AuthType.LOGIN_WITH_GOOGLE,
-    );
-    expect(result).toEqual({
-      authError: null,
-      accountSuspensionInfo: {
-        message:
-          'This service has been disabled for violation of Terms of Service.',
-        appealUrl: 'https://example.com/appeal',
-        appealLinkText: 'Appeal Here',
-      },
-    });
+    expect(result).toBeNull();
    expect(mockConfig.refreshAuth).toHaveBeenCalledWith(
      AuthType.LOGIN_WITH_GOOGLE,
    );
@@ -9,28 +9,20 @@ import {
  type Config,
  getErrorMessage,
  ValidationRequiredError,
-  isAccountSuspendedError,
 } from '@google/gemini-cli-core';

-import type { AccountSuspensionInfo } from '../ui/contexts/UIStateContext.js';
-
-export interface InitialAuthResult {
-  authError: string | null;
-  accountSuspensionInfo: AccountSuspensionInfo | null;
-}
-
 /**
 * Handles the initial authentication flow.
 * @param config The application config.
 * @param authType The selected auth type.
- * @returns The auth result with error message and account suspension status.
+ * @returns An error message if authentication fails, otherwise null.
 */
 export async function performInitialAuth(
  config: Config,
  authType: AuthType | undefined,
-): Promise<InitialAuthResult> {
+): Promise<string | null> {
  if (!authType) {
-    return { authError: null, accountSuspensionInfo: null };
+    return null;
  }

  try {
@@ -41,24 +33,10 @@ export async function performInitialAuth(
    if (e instanceof ValidationRequiredError) {
      // Don't treat validation required as a fatal auth error during startup.
      // This allows the React UI to load and show the ValidationDialog.
-      return { authError: null, accountSuspensionInfo: null };
+      return null;
    }
-    const suspendedError = isAccountSuspendedError(e);
-    if (suspendedError) {
-      return {
-        authError: null,
-        accountSuspensionInfo: {
-          message: suspendedError.message,
-          appealUrl: suspendedError.appealUrl,
-          appealLinkText: suspendedError.appealLinkText,
-        },
-      };
-    }
-    return {
-      authError: `Failed to login. Message: ${getErrorMessage(e)}`,
-      accountSuspensionInfo: null,
-    };
+    return `Failed to login. Message: ${getErrorMessage(e)}`;
  }

-  return { authError: null, accountSuspensionInfo: null };
+  return null;
 }
@@ -72,10 +72,7 @@ describe('initializer', () => {
    vi.mocked(IdeClient.getInstance).mockResolvedValue(
      mockIdeClient as unknown as IdeClient,
    );
-    vi.mocked(performInitialAuth).mockResolvedValue({
-      authError: null,
-      accountSuspensionInfo: null,
-    });
+    vi.mocked(performInitialAuth).mockResolvedValue(null);
    vi.mocked(validateTheme).mockReturnValue(null);
  });

@@ -87,7 +84,6 @@ describe('initializer', () => {

    expect(result).toEqual({
      authError: null,
-      accountSuspensionInfo: null,
      themeError: null,
      shouldOpenAuthDialog: false,
      geminiMdFileCount: 5,
@@ -107,7 +103,6 @@ describe('initializer', () => {

    expect(result).toEqual({
      authError: null,
-      accountSuspensionInfo: null,
      themeError: null,
      shouldOpenAuthDialog: false,
      geminiMdFileCount: 5,
@@ -121,10 +116,7 @@ describe('initializer', () => {
  });

  it('should handle auth error', async () => {
-    vi.mocked(performInitialAuth).mockResolvedValue({
-      authError: 'Auth failed',
-      accountSuspensionInfo: null,
-    });
+    vi.mocked(performInitialAuth).mockResolvedValue('Auth failed');
    const result = await initializeApp(
      mockConfig as unknown as Config,
      mockSettings,
@@ -17,11 +17,9 @@ import {
 import { type LoadedSettings } from '../config/settings.js';
 import { performInitialAuth } from './auth.js';
 import { validateTheme } from './theme.js';
-import type { AccountSuspensionInfo } from '../ui/contexts/UIStateContext.js';

 export interface InitializationResult {
  authError: string | null;
-  accountSuspensionInfo: AccountSuspensionInfo | null;
  themeError: string | null;
  shouldOpenAuthDialog: boolean;
  geminiMdFileCount: number;
@@ -39,7 +37,7 @@ export async function initializeApp(
  settings: LoadedSettings,
 ): Promise<InitializationResult> {
  const authHandle = startupProfiler.start('authenticate');
-  const { authError, accountSuspensionInfo } = await performInitialAuth(
+  const authError = await performInitialAuth(
    config,
    settings.merged.security.auth.selectedType,
  );
@@ -62,7 +60,6 @@ export async function initializeApp(

  return {
    authError,
-    accountSuspensionInfo,
    themeError,
    shouldOpenAuthDialog,
    geminiMdFileCount: config.getGeminiMdFileCount(),
@@ -1182,7 +1182,6 @@ describe('startInteractiveUI', () => {
    getProjectRoot: () => '/root',
    getScreenReader: () => false,
    getDebugMode: () => false,
-    getUseAlternateBuffer: () => true,
  });
  const mockSettings = {
    merged: {
@@ -1202,7 +1201,6 @@ describe('startInteractiveUI', () => {
  const mockWorkspaceRoot = '/root';
  const mockInitializationResult = {
    authError: null,
-    accountSuspensionInfo: null,
    themeError: null,
    shouldOpenAuthDialog: false,
    geminiMdFileCount: 0,
@@ -1218,8 +1216,6 @@ describe('startInteractiveUI', () => {
    runExitCleanup: vi.fn(),
    registerSyncCleanup: vi.fn(),
    registerTelemetryConfig: vi.fn(),
-    setupSignalHandlers: vi.fn(),
-    setupTtyCheck: vi.fn(() => vi.fn()),
  }));

  beforeEach(() => {
@@ -1326,8 +1322,7 @@ describe('startInteractiveUI', () => {

    // Verify all startup tasks were called
    expect(getVersion).toHaveBeenCalledTimes(1);
-    // 5 cleanups: mouseEvents, consolePatcher, lineWrapping, instance.unmount, and TTY check
-    expect(registerCleanup).toHaveBeenCalledTimes(5);
+    expect(registerCleanup).toHaveBeenCalledTimes(4);

    // Verify cleanup handler is registered with unmount function
    const cleanupFn = vi.mocked(registerCleanup).mock.calls[0][0];
@@ -32,8 +32,6 @@ import {
  registerSyncCleanup,
  runExitCleanup,
  registerTelemetryConfig,
-  setupSignalHandlers,
-  setupTtyCheck,
 } from './utils/cleanup.js';
 import {
  cleanupToolOutputFiles,
@@ -102,8 +100,8 @@ import { loadSandboxConfig } from './config/sandboxConfig.js';
 import { deleteSession, listSessions } from './utils/sessions.js';
 import { createPolicyUpdater } from './config/policy.js';
 import { ScrollProvider } from './ui/contexts/ScrollProvider.js';
-import { TerminalProvider } from './ui/contexts/TerminalContext.js';
 import { isAlternateBufferEnabled } from './ui/hooks/useAlternateBuffer.js';
+import { TerminalProvider } from './ui/contexts/TerminalContext.js';
 import { OverflowProvider } from './ui/contexts/OverflowContext.js';

 import { setupTerminalAndTheme } from './utils/terminalTheme.js';
@@ -196,7 +194,7 @@ export async function startInteractiveUI(
  // and the Ink alternate buffer mode requires line wrapping harmful to
  // screen readers.
  const useAlternateBuffer = shouldEnterAlternateScreen(
-    isAlternateBufferEnabled(config),
+    isAlternateBufferEnabled(settings),
    config.getScreenReader(),
  );
  const mouseEventsEnabled = useAlternateBuffer;
@@ -321,8 +319,6 @@ export async function startInteractiveUI(
    });

  registerCleanup(() => instance.unmount());
-
-  registerCleanup(setupTtyCheck());
 }

 export async function main() {
@@ -344,8 +340,6 @@ export async function main() {

  setupUnhandledRejectionHandler();

-  setupSignalHandlers();
-
  const slashCommandConflictHandler = new SlashCommandConflictHandler();
  slashCommandConflictHandler.start();
  registerCleanup(() => slashCommandConflictHandler.stop());
@@ -594,13 +588,6 @@ export async function main() {
    const messageBus = config.getMessageBus();
    createPolicyUpdater(policyEngine, messageBus, config.storage);

-    // Listen for settings changes to update reactive config properties
-    coreEvents.on(CoreEvent.SettingsChanged, () => {
-      if (settings.merged.security.autoAddPolicy !== undefined) {
-        config.setAutoAddPolicy(settings.merged.security.autoAddPolicy);
-      }
-    });
-
    // Register SessionEnd hook to fire on graceful exit
    // This runs before telemetry shutdown in runExitCleanup()
    registerCleanup(async () => {
@@ -659,7 +646,10 @@ export async function main() {
      process.stdin.setRawMode(true);

      // This cleanup isn't strictly needed but may help in certain situations.
-      registerSyncCleanup(() => {
+      process.on('SIGTERM', () => {
+        process.stdin.setRawMode(wasRaw);
+      });
+      process.on('SIGINT', () => {
        process.stdin.setRawMode(wasRaw);
      });
    }
@@ -685,7 +675,7 @@ export async function main() {

    let input = config.getQuestion();
    const useAlternateBuffer = shouldEnterAlternateScreen(
-      isAlternateBufferEnabled(config),
+      isAlternateBufferEnabled(settings),
      config.getScreenReader(),
    );
    const rawStartupWarnings = await getStartupWarnings();
@@ -104,8 +104,6 @@ vi.mock('../ui/auth/useAuth.js', () => ({
    onAuthError: vi.fn(),
    apiKeyDefaultValue: 'test-api-key',
    reloadApiKey: vi.fn().mockResolvedValue('test-api-key'),
-    accountSuspensionInfo: null,
-    setAccountSuspensionInfo: vi.fn(),
  }),
  validateAuthMethodWithSettings: () => null,
 }));
@@ -389,7 +387,6 @@ export class AppRig {
          version="test-version"
          initializationResult={{
            authError: null,
-            accountSuspensionInfo: null,
            themeError: null,
            shouldOpenAuthDialog: false,
            geminiMdFileCount: 0,
@@ -141,10 +141,7 @@ export const createMockConfig = (overrides: Partial<Config> = {}): Config =>
    getMcpClientManager: vi.fn().mockReturnValue({
      getMcpInstructions: vi.fn().mockReturnValue(''),
      getMcpServers: vi.fn().mockReturnValue({}),
-      getLastError: vi.fn().mockReturnValue(undefined),
    }),
-    setUserInteractedWithMcp: vi.fn(),
-    emitMcpDiagnostic: vi.fn(),
    getEnableEventDrivenScheduler: vi.fn().mockReturnValue(false),
    getAdminSkillsEnabled: vi.fn().mockReturnValue(false),
    getDisabledSkills: vi.fn().mockReturnValue([]),
@@ -159,7 +156,6 @@ export const createMockConfig = (overrides: Partial<Config> = {}): Config =>
    getExperiments: vi.fn().mockReturnValue(undefined),
    getHasAccessToPreviewModel: vi.fn().mockReturnValue(false),
    validatePathAccess: vi.fn().mockReturnValue(null),
-    getUseAlternateBuffer: vi.fn().mockReturnValue(false),
    ...overrides,
  }) as unknown as Config;

@@ -547,11 +547,6 @@ const baseMockUiState = {
  },
  hintMode: false,
  hintBuffer: '',
-  bannerData: {
-    defaultText: '',
-    warningText: '',
-  },
-  bannerVisible: false,
 };

 export const mockAppState: AppState = {
@@ -591,8 +586,6 @@ const mockUIActions: UIActions = {
  handleClearScreen: vi.fn(),
  handleProQuotaChoice: vi.fn(),
  handleValidationChoice: vi.fn(),
-  handleOverageMenuChoice: vi.fn(),
-  handleEmptyWalletChoice: vi.fn(),
  setQueueErrorMessage: vi.fn(),
  popAllMessages: vi.fn(),
  handleApiKeySubmit: vi.fn(),
@@ -615,7 +608,6 @@ const mockUIActions: UIActions = {
  handleRestart: vi.fn(),
  handleNewAgentsSelect: vi.fn(),
  getPreferredEditor: vi.fn(),
-  clearAccountSuspension: vi.fn(),
 };

 let capturedOverflowState: OverflowState | undefined;
@@ -706,21 +698,6 @@ export const renderWithProviders = (
    });
  }

-  // Wrap config in a Proxy so useAlternateBuffer hook (which reads from Config) gets the correct value,
-  // without replacing the entire config object and its other values.
-  let finalConfig = config;
-  if (useAlternateBuffer !== undefined) {
-    finalConfig = new Proxy(config, {
-      get(target, prop, receiver) {
-        if (prop === 'getUseAlternateBuffer') {
-          return () => useAlternateBuffer;
-        }
-        // eslint-disable-next-line @typescript-eslint/no-unsafe-return
-        return Reflect.get(target, prop, receiver);
-      },
-    });
-  }
-
  const mainAreaWidth = terminalWidth;

  const finalUiState = {
@@ -749,7 +726,7 @@ export const renderWithProviders = (

  const renderResult = render(
    <AppContext.Provider value={appState}>
-      <ConfigContext.Provider value={finalConfig}>
+      <ConfigContext.Provider value={config}>
        <SettingsContext.Provider value={finalSettings}>
          <UIStateContext.Provider value={finalUiState}>
            <VimModeProvider settings={finalSettings}>
@@ -761,7 +738,7 @@ export const renderWithProviders = (
                    <UIActionsContext.Provider value={finalUIActions}>
                      <OverflowProvider>
                        <ToolActionsProvider
-                          config={finalConfig}
+                          config={config}
                          toolCalls={allToolCalls}
                        >
                          <AskUserActionsProvider
@@ -2544,136 +2544,6 @@ describe('AppContainer State Management', () => {
    });
  });

-  describe('Expansion Persistence', () => {
-    let rerender: () => void;
-    let unmount: () => void;
-    let stdin: ReturnType<typeof render>['stdin'];
-
-    const setupExpansionPersistenceTest = async (
-      HighPriorityChild?: React.FC,
-    ) => {
-      const getTree = () => (
-        <SettingsContext.Provider value={mockSettings}>
-          <KeypressProvider config={mockConfig}>
-            <OverflowProvider>
-              <AppContainer
-                config={mockConfig}
-                version="1.0.0"
-                initializationResult={mockInitResult}
-              />
-              {HighPriorityChild && <HighPriorityChild />}
-            </OverflowProvider>
-          </KeypressProvider>
-        </SettingsContext.Provider>
-      );
-
-      const renderResult = render(getTree());
-      stdin = renderResult.stdin;
-      await act(async () => {
-        vi.advanceTimersByTime(100);
-      });
-      rerender = () => renderResult.rerender(getTree());
-      unmount = () => renderResult.unmount();
-    };
-
-    const writeStdin = async (sequence: string) => {
-      await act(async () => {
-        stdin.write(sequence);
-        // Advance timers to allow escape sequence parsing and broadcasting
-        vi.advanceTimersByTime(100);
-      });
-      rerender();
-    };
-
-    beforeEach(() => {
-      vi.useFakeTimers();
-    });
-
-    afterEach(() => {
-      vi.useRealTimers();
-      vi.restoreAllMocks();
-    });
-
-    it('should reset expansion when a key is NOT handled by anyone', async () => {
-      await setupExpansionPersistenceTest();
-
-      // Expand first
-      act(() => capturedUIActions.setConstrainHeight(false));
-      rerender();
-      expect(capturedUIState.constrainHeight).toBe(false);
-
-      // Press a random key that no one handles (hits Low priority fallback)
-      await writeStdin('x');
-
-      // Should be reset to true (collapsed)
-      expect(capturedUIState.constrainHeight).toBe(true);
-
-      unmount();
-    });
-
-    it('should toggle expansion when Ctrl+O is pressed', async () => {
-      await setupExpansionPersistenceTest();
-
-      // Initial state is collapsed
-      expect(capturedUIState.constrainHeight).toBe(true);
-
-      // Press Ctrl+O to expand (Ctrl+O is sequence \x0f)
-      await writeStdin('\x0f');
-      expect(capturedUIState.constrainHeight).toBe(false);
-
-      // Press Ctrl+O again to collapse
-      await writeStdin('\x0f');
-      expect(capturedUIState.constrainHeight).toBe(true);
-
-      unmount();
-    });
-
-    it('should NOT collapse when a high-priority component handles the key (e.g., up/down arrows)', async () => {
-      const NavigationHandler = () => {
-        // use real useKeypress
-        useKeypress(
-          (key: Key) => {
-            if (key.name === 'up' || key.name === 'down') {
-              return true; // Handle navigation
-            }
-            return false;
-          },
-          { isActive: true, priority: true }, // High priority
-        );
-        return null;
-      };
-
-      await setupExpansionPersistenceTest(NavigationHandler);
-
-      // Expand first
-      act(() => capturedUIActions.setConstrainHeight(false));
-      rerender();
-      expect(capturedUIState.constrainHeight).toBe(false);
-
-      // 1. Simulate Up arrow (handled by high priority child)
-      // CSI A is Up arrow
-      await writeStdin('\u001b[A');
-
-      // Should STILL be expanded
-      expect(capturedUIState.constrainHeight).toBe(false);
-
-      // 2. Simulate Down arrow (handled by high priority child)
-      // CSI B is Down arrow
-      await writeStdin('\u001b[B');
-
-      // Should STILL be expanded
-      expect(capturedUIState.constrainHeight).toBe(false);
-
-      // 3. Sanity check: press an unhandled key
-      await writeStdin('x');
-
-      // Should finally collapse
-      expect(capturedUIState.constrainHeight).toBe(true);
-
-      unmount();
-    });
-  });
-
  describe('Shortcuts Help Visibility', () => {
    let handleGlobalKeypress: (key: Key) => boolean;
    let mockedUseKeypress: Mock;
@@ -2805,10 +2675,6 @@ describe('AppContainer State Management', () => {
      isAlternateMode = false,
      childHandler?: Mock,
    ) => {
-      vi.spyOn(mockConfig, 'getUseAlternateBuffer').mockReturnValue(
-        isAlternateMode,
-      );
-
      // Update settings for this test run
      const defaultMergedSettings = mergeSettings({}, {}, {}, {}, true);
      const testSettings = {
@@ -3498,8 +3364,6 @@ describe('AppContainer State Management', () => {
      );
      vi.mocked(checkPermissions).mockResolvedValue([]);

-      vi.spyOn(mockConfig, 'getUseAlternateBuffer').mockReturnValue(true);
-
      let unmount: () => void;
      await act(async () => {
        unmount = renderAppContainer({
@@ -3732,8 +3596,6 @@ describe('AppContainer State Management', () => {
        },
      } as unknown as LoadedSettings;

-      vi.spyOn(mockConfig, 'getUseAlternateBuffer').mockReturnValue(true);
-
      let unmount: () => void;
      await act(async () => {
        const result = renderAppContainer({
@@ -47,7 +47,6 @@ import {
  type IdeInfo,
  type IdeContext,
  type UserTierId,
-  type GeminiUserTier,
  type UserFeedbackPayload,
  type AgentDefinition,
  type ApprovalMode,
@@ -83,8 +82,6 @@ import {
  CoreToolCallStatus,
  generateSteeringAckMessage,
  buildUserSteeringHintPrompt,
-  logBillingEvent,
-  ApiKeyUpdatedEvent,
 } from '@google/gemini-cli-core';
 import { validateAuthMethod } from '../config/auth.js';
 import process from 'node:process';
@@ -148,6 +145,7 @@ import { useSessionResume } from './hooks/useSessionResume.js';
 import { useIncludeDirsTrust } from './hooks/useIncludeDirsTrust.js';
 import { useSessionRetentionCheck } from './hooks/useSessionRetentionCheck.js';
 import { isWorkspaceTrusted } from '../config/trustedFolders.js';
+import { useAlternateBuffer } from './hooks/useAlternateBuffer.js';
 import { useSettings } from './contexts/SettingsContext.js';
 import { terminalCapabilityManager } from './utils/terminalCapabilityManager.js';
 import { useInputHistoryStore } from './hooks/useInputHistoryStore.js';
@@ -230,7 +228,7 @@ export const AppContainer = (props: AppContainerProps) => {
  });

  useMemoryMonitor(historyManager);
-  const isAlternateBuffer = config.getUseAlternateBuffer();
+  const isAlternateBuffer = useAlternateBuffer();
  const [corgiMode, setCorgiMode] = useState(false);
  const [forceRerenderKey, setForceRerenderKey] = useState(0);
  const [debugMessage, setDebugMessage] = useState<string>('');
@@ -266,16 +264,14 @@ export const AppContainer = (props: AppContainerProps) => {
    () => isWorkspaceTrusted(settings.merged).isTrusted,
  );

-  const [queueErrorMessage, setQueueErrorMessage] = useTimedMessage<string>(
-    QUEUE_ERROR_DISPLAY_DURATION_MS,
+  const [queueErrorMessage, setQueueErrorMessage] = useState<string | null>(
+    null,
  );

  const [newAgents, setNewAgents] = useState<AgentDefinition[] | null>(null);
  const [constrainHeight, setConstrainHeight] = useState<boolean>(true);
-  const [expandHintTrigger, triggerExpandHint] = useTimedMessage<boolean>(
-    EXPAND_HINT_DURATION_MS,
-  );
-  const showIsExpandableHint = Boolean(expandHintTrigger);
+  const [showIsExpandableHint, setShowIsExpandableHint] = useState(false);
+  const expandHintTimerRef = useRef<NodeJS.Timeout | null>(null);
  const overflowState = useOverflowState();
  const overflowingIdsSize = overflowState?.overflowingIds.size ?? 0;
  const hasOverflowState = overflowingIdsSize > 0 || !constrainHeight;
@@ -288,15 +284,39 @@ export const AppContainer = (props: AppContainerProps) => {
   * boolean dependency (hasOverflowState) to ensure the timer only resets on
   * genuine state transitions, preventing it from infinitely resetting during
   * active text streaming.
-   *
-   * In alternate buffer mode, we don't trigger the hint automatically on overflow
-   * to avoid noise, but the user can still trigger it manually with Ctrl+O.
   */
  useEffect(() => {
-    if (hasOverflowState && !isAlternateBuffer) {
-      triggerExpandHint(true);
+    if (isAlternateBuffer) {
+      setShowIsExpandableHint(false);
+      if (expandHintTimerRef.current) {
+        clearTimeout(expandHintTimerRef.current);
+      }
+      return;
    }
-  }, [hasOverflowState, isAlternateBuffer, triggerExpandHint]);
+
+    if (hasOverflowState) {
+      setShowIsExpandableHint(true);
+      if (expandHintTimerRef.current) {
+        clearTimeout(expandHintTimerRef.current);
+      }
+      expandHintTimerRef.current = setTimeout(() => {
+        setShowIsExpandableHint(false);
+      }, EXPAND_HINT_DURATION_MS);
+    }
+  }, [hasOverflowState, isAlternateBuffer, constrainHeight]);
+
+  /**
+   * Safe cleanup to ensure the expansion hint timer is cancelled when the
+   * component unmounts, preventing memory leaks.
+   */
+  useEffect(
+    () => () => {
+      if (expandHintTimerRef.current) {
+        clearTimeout(expandHintTimerRef.current);
+      }
+    },
+    [],
+  );

  const [defaultBannerText, setDefaultBannerText] = useState('');
  const [warningBannerText, setWarningBannerText] = useState('');
@@ -394,9 +414,6 @@ export const AppContainer = (props: AppContainerProps) => {
      ? { remaining, limit, resetTime }
      : undefined;
  });
-  const [paidTier, setPaidTier] = useState<GeminiUserTier | undefined>(
-    undefined,
-  );

  const [isConfigInitialized, setConfigInitialized] = useState(false);

@@ -550,7 +567,7 @@ export const AppContainer = (props: AppContainerProps) => {
  const { consoleMessages, clearConsoleMessages: clearConsoleMessagesState } =
    useConsoleMessages();

-  const mainAreaWidth = calculateMainAreaWidth(terminalWidth, config);
+  const mainAreaWidth = calculateMainAreaWidth(terminalWidth, settings);
  // Derive widths for InputPrompt using shared helper
  const { inputWidth, suggestionsWidth } = useMemo(() => {
    const { inputWidth, suggestionsWidth } =
@@ -675,14 +692,7 @@ export const AppContainer = (props: AppContainerProps) => {
    onAuthError,
    apiKeyDefaultValue,
    reloadApiKey,
-    accountSuspensionInfo,
-    setAccountSuspensionInfo,
-  } = useAuthCommand(
-    settings,
-    config,
-    initializationResult.authError,
-    initializationResult.accountSuspensionInfo,
-  );
+  } = useAuthCommand(settings, config, initializationResult.authError);
  const [authContext, setAuthContext] = useState<{ requiresRestart?: boolean }>(
    {},
  );
@@ -699,20 +709,12 @@ export const AppContainer = (props: AppContainerProps) => {
    handleProQuotaChoice,
    validationRequest,
    handleValidationChoice,
-    // G1 AI Credits
-    overageMenuRequest,
-    handleOverageMenuChoice,
-    emptyWalletRequest,
-    handleEmptyWalletChoice,
  } = useQuotaAndFallback({
    config,
    historyManager,
    userTier,
-    paidTier,
-    settings,
    setModelSwitchedFromQuotaError,
    onShowAuthSelection: () => setAuthState(AuthState.Updating),
-    errorVerbosity: settings.merged.ui.errorVerbosity,
  });

  // Derive auth state variables for backward compatibility with UIStateContext
@@ -750,8 +752,6 @@ export const AppContainer = (props: AppContainerProps) => {
  const handleAuthSelect = useCallback(
    async (authType: AuthType | undefined, scope: LoadableSettingScope) => {
      if (authType) {
-        const previousAuthType =
-          config.getContentGeneratorConfig()?.authType ?? 'unknown';
        if (authType === AuthType.LOGIN_WITH_GOOGLE) {
          setAuthContext({ requiresRestart: true });
        } else {
@@ -764,10 +764,6 @@ export const AppContainer = (props: AppContainerProps) => {
          config.setRemoteAdminSettings(undefined);
          await config.refreshAuth(authType);
          setAuthState(AuthState.Authenticated);
-          logBillingEvent(
-            config,
-            new ApiKeyUpdatedEvent(previousAuthType, authType),
-          );
        } catch (e) {
          if (e instanceof ChangeAuthRequestedError) {
            return;
@@ -830,7 +826,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
    // Only sync when not currently authenticating
    if (authState === AuthState.Authenticated) {
      setUserTier(config.getUserTier());
-      setPaidTier(config.getUserPaidTier());
    }
  }, [config, authState]);

@@ -1257,7 +1252,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
    async (submittedValue: string) => {
      reset();
      // Explicitly hide the expansion hint and clear its x-second timer when a new turn begins.
-      triggerExpandHint(null);
+      setShowIsExpandableHint(false);
+      if (expandHintTimerRef.current) {
+        clearTimeout(expandHintTimerRef.current);
+      }
      if (!constrainHeight) {
        setConstrainHeight(true);
        if (!isAlternateBuffer) {
@@ -1329,14 +1327,16 @@ Logging in with Google... Restarting Gemini CLI to continue.
      refreshStatic,
      reset,
      handleHintSubmit,
-      triggerExpandHint,
    ],
  );

  const handleClearScreen = useCallback(() => {
    reset();
    // Explicitly hide the expansion hint and clear its x-second timer when clearing the screen.
-    triggerExpandHint(null);
+    setShowIsExpandableHint(false);
+    if (expandHintTimerRef.current) {
+      clearTimeout(expandHintTimerRef.current);
+    }
    historyManager.clearItems();
    clearConsoleMessagesState();
    refreshStatic();
@@ -1345,7 +1345,7 @@ Logging in with Google... Restarting Gemini CLI to continue.
    clearConsoleMessagesState,
    refreshStatic,
    reset,
-    triggerExpandHint,
+    setShowIsExpandableHint,
  ]);

  const { handleInput: vimHandleInput } = useVim(buffer, handleFinalSubmit);
@@ -1632,6 +1632,17 @@ Logging in with Google... Restarting Gemini CLI to continue.
    }
  }, [ideNeedsRestart]);

+  useEffect(() => {
+    if (queueErrorMessage) {
+      const timer = setTimeout(() => {
+        setQueueErrorMessage(null);
+      }, QUEUE_ERROR_DISPLAY_DURATION_MS);
+
+      return () => clearTimeout(timer);
+    }
+    return undefined;
+  }, [queueErrorMessage, setQueueErrorMessage]);
+
  useEffect(() => {
    if (isInitialMount.current) {
      isInitialMount.current = false;
@@ -1689,7 +1700,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
    retryStatus,
    loadingPhrasesMode: settings.merged.ui.loadingPhrases,
    customWittyPhrases: settings.merged.ui.customWittyPhrases,
-    errorVerbosity: settings.merged.ui.errorVerbosity,
  });

  const handleGlobalKeypress = useCallback(
@@ -1738,7 +1748,13 @@ Logging in with Google... Restarting Gemini CLI to continue.
        setConstrainHeight(true);
        if (keyMatchers[Command.SHOW_MORE_LINES](key)) {
          // If the user manually collapses the view, show the hint and reset the x-second timer.
-          triggerExpandHint(true);
+          setShowIsExpandableHint(true);
+          if (expandHintTimerRef.current) {
+            clearTimeout(expandHintTimerRef.current);
+          }
+          expandHintTimerRef.current = setTimeout(() => {
+            setShowIsExpandableHint(false);
+          }, EXPAND_HINT_DURATION_MS);
        }
        if (!isAlternateBuffer) {
          refreshStatic();
@@ -1787,7 +1803,13 @@ Logging in with Google... Restarting Gemini CLI to continue.
      ) {
        setConstrainHeight(false);
        // If the user manually expands the view, show the hint and reset the x-second timer.
-        triggerExpandHint(true);
+        setShowIsExpandableHint(true);
+        if (expandHintTimerRef.current) {
+          clearTimeout(expandHintTimerRef.current);
+        }
+        expandHintTimerRef.current = setTimeout(() => {
+          setShowIsExpandableHint(false);
+        }, EXPAND_HINT_DURATION_MS);
        if (!isAlternateBuffer) {
          refreshStatic();
        }
@@ -1892,14 +1914,10 @@ Logging in with Google... Restarting Gemini CLI to continue.
      showTransientMessage,
      settings.merged.general.devtools,
      showErrorDetails,
-      triggerExpandHint,
    ],
  );

-  useKeypress(handleGlobalKeypress, {
-    isActive: true,
-    priority: KeypressPriority.Low,
-  });
+  useKeypress(handleGlobalKeypress, { isActive: true, priority: true });

  useKeypress(
    () => {
@@ -2038,8 +2056,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
    showIdeRestartPrompt ||
    !!proQuotaRequest ||
    !!validationRequest ||
-    !!overageMenuRequest ||
-    !!emptyWalletRequest ||
    isSessionBrowserOpen ||
    authState === AuthState.AwaitingApiKeyInput ||
    !!newAgents;
@@ -2067,8 +2083,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
    hasLoopDetectionConfirmationRequest ||
    !!proQuotaRequest ||
    !!validationRequest ||
-    !!overageMenuRequest ||
-    !!emptyWalletRequest ||
    !!customDialog;

  const allowPlanMode =
@@ -2209,7 +2223,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
      isAuthenticating,
      isConfigInitialized,
      authError,
-      accountSuspensionInfo,
      isAuthDialogOpen,
      isAwaitingApiKeyInput: authState === AuthState.AwaitingApiKeyInput,
      apiKeyDefaultValue,
@@ -2280,9 +2293,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
        stats: quotaStats,
        proQuotaRequest,
        validationRequest,
-        // G1 AI Credits dialog state
-        overageMenuRequest,
-        emptyWalletRequest,
      },
      contextFileNames,
      errorCount,
@@ -2341,7 +2351,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
      isAuthenticating,
      isConfigInitialized,
      authError,
-      accountSuspensionInfo,
      isAuthDialogOpen,
      editorError,
      isEditorDialogOpen,
@@ -2408,8 +2417,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
      quotaStats,
      proQuotaRequest,
      validationRequest,
-      overageMenuRequest,
-      emptyWalletRequest,
      contextFileNames,
      errorCount,
      availableTerminalHeight,
@@ -2491,9 +2498,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
      handleClearScreen,
      handleProQuotaChoice,
      handleValidationChoice,
-      // G1 AI Credits handlers
-      handleOverageMenuChoice,
-      handleEmptyWalletChoice,
      openSessionBrowser,
      closeSessionBrowser,
      handleResumeSession,
@@ -2551,10 +2555,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
        setNewAgents(null);
      },
      getPreferredEditor,
-      clearAccountSuspension: () => {
-        setAccountSuspensionInfo(null);
-        setAuthState(AuthState.Updating);
-      },
    }),
    [
      handleThemeSelect,
@@ -2584,8 +2584,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
      handleClearScreen,
      handleProQuotaChoice,
      handleValidationChoice,
-      handleOverageMenuChoice,
-      handleEmptyWalletChoice,
      openSessionBrowser,
      closeSessionBrowser,
      handleResumeSession,
@@ -2605,7 +2603,6 @@ Logging in with Google... Restarting Gemini CLI to continue.
      setActiveBackgroundShellPid,
      setIsBackgroundShellListOpen,
      setAuthContext,
-      setAccountSuspensionInfo,
      newAgents,
      config,
      historyManager,
@@ -1,241 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import { describe, it, expect, vi, beforeEach, type Mock } from 'vitest';
-import { renderWithProviders } from '../../test-utils/render.js';
-import { waitFor } from '../../test-utils/async.js';
-import { BannedAccountDialog } from './BannedAccountDialog.js';
-import { RadioButtonSelect } from '../components/shared/RadioButtonSelect.js';
-import { useKeypress } from '../hooks/useKeypress.js';
-import {
-  openBrowserSecurely,
-  shouldLaunchBrowser,
-} from '@google/gemini-cli-core';
-import { Text } from 'ink';
-import { runExitCleanup } from '../../utils/cleanup.js';
-import type { AccountSuspensionInfo } from '../contexts/UIStateContext.js';
-
-vi.mock('@google/gemini-cli-core', async (importOriginal) => {
-  const actual =
-    await importOriginal<typeof import('@google/gemini-cli-core')>();
-  return {
-    ...actual,
-    openBrowserSecurely: vi.fn(),
-    shouldLaunchBrowser: vi.fn().mockReturnValue(true),
-  };
-});
-
-vi.mock('../../utils/cleanup.js', () => ({
-  runExitCleanup: vi.fn().mockResolvedValue(undefined),
-}));
-
-vi.mock('../hooks/useKeypress.js', () => ({
-  useKeypress: vi.fn(),
-}));
-
-vi.mock('../components/shared/RadioButtonSelect.js', () => ({
-  RadioButtonSelect: vi.fn(({ items }) => (
-    <>
-      {items.map((item: { value: string; label: string }) => (
-        <Text key={item.value}>{item.label}</Text>
-      ))}
-    </>
-  )),
-}));
-
-const mockedRadioButtonSelect = RadioButtonSelect as Mock;
-const mockedUseKeypress = useKeypress as Mock;
-const mockedOpenBrowser = openBrowserSecurely as Mock;
-const mockedShouldLaunchBrowser = shouldLaunchBrowser as Mock;
-const mockedRunExitCleanup = runExitCleanup as Mock;
-
-const DEFAULT_SUSPENSION_INFO: AccountSuspensionInfo = {
-  message:
-    'This service has been disabled in this account for violation of Terms of Service. Please submit an appeal to continue using this product.',
-  appealUrl: 'https://example.com/appeal',
-  appealLinkText: 'Appeal Here',
-};
-
-describe('BannedAccountDialog', () => {
-  let onExit: Mock;
-  let onChangeAuth: Mock;
-
-  beforeEach(() => {
-    vi.resetAllMocks();
-    mockedShouldLaunchBrowser.mockReturnValue(true);
-    mockedOpenBrowser.mockResolvedValue(undefined);
-    mockedRunExitCleanup.mockResolvedValue(undefined);
-    onExit = vi.fn();
-    onChangeAuth = vi.fn();
-  });
-
-  it('renders the suspension message from accountSuspensionInfo', async () => {
-    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
-      <BannedAccountDialog
-        accountSuspensionInfo={DEFAULT_SUSPENSION_INFO}
-        onExit={onExit}
-        onChangeAuth={onChangeAuth}
-      />,
-    );
-    await waitUntilReady();
-    const frame = lastFrame();
-    expect(frame).toContain('Account Suspended');
-    expect(frame).toContain('violation of Terms of Service');
-    expect(frame).toContain('Escape to exit');
-    unmount();
-  });
-
-  it('renders menu options with appeal link text from response', async () => {
-    const { waitUntilReady, unmount } = renderWithProviders(
-      <BannedAccountDialog
-        accountSuspensionInfo={DEFAULT_SUSPENSION_INFO}
-        onExit={onExit}
-        onChangeAuth={onChangeAuth}
-      />,
-    );
-    await waitUntilReady();
-    const items = mockedRadioButtonSelect.mock.calls[0][0].items;
-    expect(items).toHaveLength(3);
-    expect(items[0].label).toBe('Appeal Here');
-    expect(items[1].label).toBe('Change authentication');
-    expect(items[2].label).toBe('Exit');
-    unmount();
-  });
-
-  it('hides form option when no appealUrl is provided', async () => {
-    const infoWithoutUrl: AccountSuspensionInfo = {
-      message: 'Account suspended.',
-    };
-    const { waitUntilReady, unmount } = renderWithProviders(
-      <BannedAccountDialog
-        accountSuspensionInfo={infoWithoutUrl}
-        onExit={onExit}
-        onChangeAuth={onChangeAuth}
-      />,
-    );
-    await waitUntilReady();
-    const items = mockedRadioButtonSelect.mock.calls[0][0].items;
-    expect(items).toHaveLength(2);
-    expect(items[0].label).toBe('Change authentication');
-    expect(items[1].label).toBe('Exit');
-    unmount();
-  });
-
-  it('uses default label when appealLinkText is not provided', async () => {
-    const infoWithoutLinkText: AccountSuspensionInfo = {
-      message: 'Account suspended.',
-      appealUrl: 'https://example.com/appeal',
-    };
-    const { waitUntilReady, unmount } = renderWithProviders(
-      <BannedAccountDialog
-        accountSuspensionInfo={infoWithoutLinkText}
-        onExit={onExit}
-        onChangeAuth={onChangeAuth}
-      />,
-    );
-    await waitUntilReady();
-    const items = mockedRadioButtonSelect.mock.calls[0][0].items;
-    expect(items[0].label).toBe('Open the Google Form');
-    unmount();
-  });
-
-  it('opens browser when appeal option is selected', async () => {
-    const { waitUntilReady, unmount } = renderWithProviders(
-      <BannedAccountDialog
-        accountSuspensionInfo={DEFAULT_SUSPENSION_INFO}
-        onExit={onExit}
-        onChangeAuth={onChangeAuth}
-      />,
-    );
-    await waitUntilReady();
-    const { onSelect } = mockedRadioButtonSelect.mock.calls[0][0];
-    await onSelect('open_form');
-    expect(mockedOpenBrowser).toHaveBeenCalledWith(
-      'https://example.com/appeal',
-    );
-    expect(onExit).not.toHaveBeenCalled();
-    unmount();
-  });
-
-  it('shows URL when browser cannot be launched', async () => {
-    mockedShouldLaunchBrowser.mockReturnValue(false);
-    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
-      <BannedAccountDialog
-        accountSuspensionInfo={DEFAULT_SUSPENSION_INFO}
-        onExit={onExit}
-        onChangeAuth={onChangeAuth}
-      />,
-    );
-    await waitUntilReady();
-    const { onSelect } = mockedRadioButtonSelect.mock.calls[0][0];
-    onSelect('open_form');
-    await waitFor(() => {
-      expect(lastFrame()).toContain('Please open this URL in a browser');
-    });
-    expect(mockedOpenBrowser).not.toHaveBeenCalled();
-    unmount();
-  });
-
-  it('calls onExit when "Exit" is selected', async () => {
-    const { waitUntilReady, unmount } = renderWithProviders(
-      <BannedAccountDialog
-        accountSuspensionInfo={DEFAULT_SUSPENSION_INFO}
-        onExit={onExit}
-        onChangeAuth={onChangeAuth}
-      />,
-    );
-    await waitUntilReady();
-    const { onSelect } = mockedRadioButtonSelect.mock.calls[0][0];
-    await onSelect('exit');
-    expect(mockedRunExitCleanup).toHaveBeenCalled();
-    expect(onExit).toHaveBeenCalled();
-    unmount();
-  });
-
-  it('calls onChangeAuth when "Change authentication" is selected', async () => {
-    const { waitUntilReady, unmount } = renderWithProviders(
-      <BannedAccountDialog
-        accountSuspensionInfo={DEFAULT_SUSPENSION_INFO}
-        onExit={onExit}
-        onChangeAuth={onChangeAuth}
-      />,
-    );
-    await waitUntilReady();
-    const { onSelect } = mockedRadioButtonSelect.mock.calls[0][0];
-    onSelect('change_auth');
-    expect(onChangeAuth).toHaveBeenCalled();
-    expect(onExit).not.toHaveBeenCalled();
-    unmount();
-  });
-
-  it('exits on escape key', async () => {
-    const { waitUntilReady, unmount } = renderWithProviders(
-      <BannedAccountDialog
-        accountSuspensionInfo={DEFAULT_SUSPENSION_INFO}
-        onExit={onExit}
-        onChangeAuth={onChangeAuth}
-      />,
-    );
-    await waitUntilReady();
-    const keypressHandler = mockedUseKeypress.mock.calls[0][0];
-    const result = keypressHandler({ name: 'escape' });
-    expect(result).toBe(true);
-    unmount();
-  });
-
-  it('renders snapshot correctly', async () => {
-    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
-      <BannedAccountDialog
-        accountSuspensionInfo={DEFAULT_SUSPENSION_INFO}
-        onExit={onExit}
-        onChangeAuth={onChangeAuth}
-      />,
-    );
-    await waitUntilReady();
-    expect(lastFrame()).toMatchSnapshot();
-    unmount();
-  });
-});
@@ -1,138 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import type React from 'react';
-import { useCallback, useMemo, useState } from 'react';
-import { Box, Text } from 'ink';
-import { theme } from '../semantic-colors.js';
-import { RadioButtonSelect } from '../components/shared/RadioButtonSelect.js';
-import { useKeypress } from '../hooks/useKeypress.js';
-import {
-  openBrowserSecurely,
-  shouldLaunchBrowser,
-} from '@google/gemini-cli-core';
-import { runExitCleanup } from '../../utils/cleanup.js';
-import type { AccountSuspensionInfo } from '../contexts/UIStateContext.js';
-
-interface BannedAccountDialogProps {
-  accountSuspensionInfo: AccountSuspensionInfo;
-  onExit: () => void;
-  onChangeAuth: () => void;
-}
-
-export function BannedAccountDialog({
-  accountSuspensionInfo,
-  onExit,
-  onChangeAuth,
-}: BannedAccountDialogProps): React.JSX.Element {
-  const [errorMessage, setErrorMessage] = useState<string | null>(null);
-
-  const appealUrl = accountSuspensionInfo.appealUrl;
-  const appealLinkText =
-    accountSuspensionInfo.appealLinkText ?? 'Open the Google Form';
-
-  const items = useMemo(() => {
-    const menuItems = [];
-    if (appealUrl) {
-      menuItems.push({
-        label: appealLinkText,
-        value: 'open_form' as const,
-        key: 'open_form',
-      });
-    }
-    menuItems.push(
-      {
-        label: 'Change authentication',
-        value: 'change_auth' as const,
-        key: 'change_auth',
-      },
-      {
-        label: 'Exit',
-        value: 'exit' as const,
-        key: 'exit',
-      },
-    );
-    return menuItems;
-  }, [appealUrl, appealLinkText]);
-
-  useKeypress(
-    (key) => {
-      if (key.name === 'escape') {
-        void handleExit();
-        return true;
-      }
-      return false;
-    },
-    { isActive: true },
-  );
-
-  const handleExit = useCallback(async () => {
-    await runExitCleanup();
-    onExit();
-  }, [onExit]);
-
-  const handleSelect = useCallback(
-    async (choice: string) => {
-      if (choice === 'open_form' && appealUrl) {
-        if (!shouldLaunchBrowser()) {
-          setErrorMessage(`Please open this URL in a browser: ${appealUrl}`);
-          return;
-        }
-
-        try {
-          await openBrowserSecurely(appealUrl);
-        } catch {
-          setErrorMessage(`Failed to open browser. Please visit: ${appealUrl}`);
-        }
-      } else if (choice === 'change_auth') {
-        onChangeAuth();
-      } else {
-        await handleExit();
-      }
-    },
-    [handleExit, onChangeAuth, appealUrl],
-  );
-
-  return (
-    <Box flexDirection="column" padding={1}>
-      <Text bold color={theme.status.error}>
-        Error: Account Suspended
-      </Text>
-
-      <Box marginTop={1}>
-        <Text>{accountSuspensionInfo.message}</Text>
-      </Box>
-
-      {appealUrl && (
-        <>
-          <Box marginTop={1}>
-            <Text>Appeal URL:</Text>
-          </Box>
-          <Box>
-            <Text color={theme.text.link}>[{appealUrl}]</Text>
-          </Box>
-        </>
-      )}
-
-      {errorMessage && (
-        <Box marginTop={1}>
-          <Text color={theme.status.error}>{errorMessage}</Text>
-        </Box>
-      )}
-
-      <Box marginTop={1}>
-        <RadioButtonSelect
-          items={items}
-          onSelect={(choice) => void handleSelect(choice)}
-        />
-      </Box>
-
-      <Box marginTop={1}>
-        <Text dimColor>Escape to exit</Text>
-      </Box>
-    </Box>
-  );
-}
@@ -1,17 +0,0 @@
-// Vitest Snapshot v1, https://vitest.dev/guide/snapshot.html
-
-exports[`BannedAccountDialog > renders snapshot correctly 1`] = `
-"
- Error: Account Suspended
-
- This service has been disabled in this account for violation of Terms of Service. Please submit an
- appeal to continue using this product.
-
- Appeal URL:
- [https://example.com/appeal]
-
- Appeal HereChange authenticationExit
-
- Escape to exit
-"
-`;
@@ -11,7 +11,6 @@ import {
  type Config,
  loadApiKey,
  debugLogger,
-  isAccountSuspendedError,
 } from '@google/gemini-cli-core';
 import { getErrorMessage } from '@google/gemini-cli-core';
 import { AuthState } from '../types.js';
@@ -35,21 +34,16 @@ export function validateAuthMethodWithSettings(
  return validateAuthMethod(authType);
 }

-import type { AccountSuspensionInfo } from '../contexts/UIStateContext.js';
-
 export const useAuthCommand = (
  settings: LoadedSettings,
  config: Config,
  initialAuthError: string | null = null,
-  initialAccountSuspensionInfo: AccountSuspensionInfo | null = null,
 ) => {
  const [authState, setAuthState] = useState<AuthState>(
    initialAuthError ? AuthState.Updating : AuthState.Unauthenticated,
  );

  const [authError, setAuthError] = useState<string | null>(initialAuthError);
-  const [accountSuspensionInfo, setAccountSuspensionInfo] =
-    useState<AccountSuspensionInfo | null>(initialAccountSuspensionInfo);
  const [apiKeyDefaultValue, setApiKeyDefaultValue] = useState<
    string | undefined
  >(undefined);
@@ -136,16 +130,7 @@ export const useAuthCommand = (
        setAuthError(null);
        setAuthState(AuthState.Authenticated);
      } catch (e) {
-        const suspendedError = isAccountSuspendedError(e);
-        if (suspendedError) {
-          setAccountSuspensionInfo({
-            message: suspendedError.message,
-            appealUrl: suspendedError.appealUrl,
-            appealLinkText: suspendedError.appealLinkText,
-          });
-        } else {
-          onAuthError(`Failed to login. Message: ${getErrorMessage(e)}`);
-        }
+        onAuthError(`Failed to login. Message: ${getErrorMessage(e)}`);
      }
    })();
  }, [
@@ -165,7 +150,5 @@ export const useAuthCommand = (
    onAuthError,
    apiKeyDefaultValue,
    reloadApiKey,
-    accountSuspensionInfo,
-    setAccountSuspensionInfo,
  };
 };
@@ -4,7 +4,7 @@
 * SPDX-License-Identifier: Apache-2.0
 */

-import { vi, describe, it, expect, beforeEach, afterEach } from 'vitest';
+import { vi, describe, it, expect, beforeEach } from 'vitest';
 import { mcpCommand } from './mcpCommand.js';
 import { createMockCommandContext } from '../../test-utils/mockCommandContext.js';
 import {
@@ -77,8 +77,6 @@ describe('mcpCommand', () => {
    getGeminiClient: ReturnType<typeof vi.fn>;
    getMcpClientManager: ReturnType<typeof vi.fn>;
    getResourceRegistry: ReturnType<typeof vi.fn>;
-    setUserInteractedWithMcp: ReturnType<typeof vi.fn>;
-    getLastMcpError: ReturnType<typeof vi.fn>;
  };

  beforeEach(() => {
@@ -106,15 +104,12 @@ describe('mcpCommand', () => {
      }),
      getGeminiClient: vi.fn(),
      getMcpClientManager: vi.fn().mockImplementation(() => ({
-        getBlockedMcpServers: vi.fn().mockReturnValue([]),
-        getMcpServers: vi.fn().mockReturnValue({}),
-        getLastError: vi.fn().mockReturnValue(undefined),
+        getBlockedMcpServers: vi.fn(),
+        getMcpServers: vi.fn(),
      })),
      getResourceRegistry: vi.fn().mockReturnValue({
        getAllResources: vi.fn().mockReturnValue([]),
      }),
-      setUserInteractedWithMcp: vi.fn(),
-      getLastMcpError: vi.fn().mockReturnValue(undefined),
    };

    mockContext = createMockCommandContext({
@@ -124,10 +119,6 @@ describe('mcpCommand', () => {
    });
  });

-  afterEach(() => {
-    vi.restoreAllMocks();
-  });
-
  describe('basic functionality', () => {
    it('should show an error if config is not available', async () => {
      const contextWithoutConfig = createMockCommandContext({
@@ -170,7 +161,6 @@ describe('mcpCommand', () => {
      mockConfig.getMcpClientManager = vi.fn().mockReturnValue({
        getMcpServers: vi.fn().mockReturnValue(mockMcpServers),
        getBlockedMcpServers: vi.fn().mockReturnValue([]),
-        getLastError: vi.fn().mockReturnValue(undefined),
      });
    });

@@ -52,8 +52,6 @@ const authCommand: SlashCommand = {
      };
    }

-    config.setUserInteractedWithMcp();
-
    const mcpServers = config.getMcpClientManager()?.getMcpServers() ?? {};

    if (!serverName) {
@@ -186,8 +184,6 @@ const listAction = async (
    };
  }

-  config.setUserInteractedWithMcp();
-
  const toolRegistry = config.getToolRegistry();
  if (!toolRegistry) {
    return {
@@ -254,13 +250,6 @@ const listAction = async (
    enablementState[serverName] =
      await enablementManager.getDisplayState(serverName);
  }
-  const errors: Record<string, string> = {};
-  for (const serverName of serverNames) {
-    const error = config.getMcpClientManager()?.getLastError(serverName);
-    if (error) {
-      errors[serverName] = error;
-    }
-  }

  const mcpStatusItem: HistoryItemMcpStatus = {
    type: MessageType.MCP_STATUS,
@@ -285,19 +274,16 @@ const listAction = async (
    })),
    authStatus,
    enablementState,
-    errors,
-    blockedServers: blockedMcpServers.map((s) => ({
-      name: s.name,
-      extensionName: s.extensionName,
-    })),
+    blockedServers: blockedMcpServers,
    discoveryInProgress,
    connectingServers,
-    showDescriptions: Boolean(showDescriptions),
-    showSchema: Boolean(showSchema),
+    showDescriptions,
+    showSchema,
  };

  context.ui.addItem(mcpStatusItem);
 };
+
 const listCommand: SlashCommand = {
  name: 'list',
  altNames: ['ls', 'nodesc', 'nodescription'],
@@ -386,8 +372,6 @@ async function handleEnableDisable(
    };
  }

-  config.setUserInteractedWithMcp();
-
  const parts = args.trim().split(/\s+/);
  const isSession = parts.includes('--session');
  const serverName = parts.filter((p) => p !== '--session')[0];
@@ -39,18 +39,11 @@ describe('statsCommand', () => {
    mockContext.session.stats.sessionStartTime = startTime;
  });

-  it('should display general session stats when run with no subcommand', async () => {
+  it('should display general session stats when run with no subcommand', () => {
    if (!statsCommand.action) throw new Error('Command has no action');

-    mockContext.services.config = {
-      refreshUserQuota: vi.fn(),
-      refreshAvailableCredits: vi.fn(),
-      getUserTierName: vi.fn(),
-      getUserPaidTier: vi.fn(),
-      getModel: vi.fn(),
-    } as unknown as Config;
-
-    await statsCommand.action(mockContext, '');
+    // eslint-disable-next-line @typescript-eslint/no-floating-promises
+    statsCommand.action(mockContext, '');

    const expectedDuration = formatDuration(
      endTime.getTime() - startTime.getTime(),
@@ -62,7 +55,6 @@ describe('statsCommand', () => {
      tier: undefined,
      userEmail: 'mock@example.com',
      currentModel: undefined,
-      creditBalance: undefined,
    });
  });

@@ -86,8 +78,6 @@ describe('statsCommand', () => {
      getQuotaRemaining: mockGetQuotaRemaining,
      getQuotaLimit: mockGetQuotaLimit,
      getQuotaResetTime: mockGetQuotaResetTime,
-      getUserPaidTier: vi.fn(),
-      refreshAvailableCredits: vi.fn(),
    } as unknown as Config;

    await statsCommand.action(mockContext, '');
@@ -11,10 +11,7 @@ import type {
 } from '../types.js';
 import { MessageType } from '../types.js';
 import { formatDuration } from '../utils/formatters.js';
-import {
-  UserAccountManager,
-  getG1CreditBalance,
-} from '@google/gemini-cli-core';
+import { UserAccountManager } from '@google/gemini-cli-core';
 import {
  type CommandContext,
  type SlashCommand,
@@ -30,10 +27,8 @@ function getUserIdentity(context: CommandContext) {
  const userEmail = cachedAccount ?? undefined;

  const tier = context.services.config?.getUserTierName();
-  const paidTier = context.services.config?.getUserPaidTier();
-  const creditBalance = getG1CreditBalance(paidTier) ?? undefined;

-  return { selectedAuthType, userEmail, tier, creditBalance };
+  return { selectedAuthType, userEmail, tier };
 }

 async function defaultSessionView(context: CommandContext) {
@@ -48,8 +43,7 @@ async function defaultSessionView(context: CommandContext) {
  }
  const wallDuration = now.getTime() - sessionStartTime.getTime();

-  const { selectedAuthType, userEmail, tier, creditBalance } =
-    getUserIdentity(context);
+  const { selectedAuthType, userEmail, tier } = getUserIdentity(context);
  const currentModel = context.services.config?.getModel();

  const statsItem: HistoryItemStats = {
@@ -59,14 +53,10 @@ async function defaultSessionView(context: CommandContext) {
    userEmail,
    tier,
    currentModel,
-    creditBalance,
  };

  if (context.services.config) {
-    const [quota] = await Promise.all([
-      context.services.config.refreshUserQuota(),
-      context.services.config.refreshAvailableCredits(),
-    ]);
+    const quota = await context.services.config.refreshUserQuota();
    if (quota) {
      statsItem.quotas = quota;
      statsItem.pooledRemaining = context.services.config.getQuotaRemaining();
@@ -6,8 +6,8 @@

 import { beforeEach, afterEach, describe, it, expect, vi } from 'vitest';
 import { render } from '../../test-utils/render.js';
-import { act, useEffect } from 'react';
 import { Box, Text } from 'ink';
+import { useEffect } from 'react';
 import { Composer } from './Composer.js';
 import { UIStateContext, type UIState } from '../contexts/UIStateContext.js';
 import {
@@ -34,7 +34,6 @@ import { StreamingState } from '../types.js';
 import { TransientMessageType } from '../../utils/events.js';
 import type { LoadedSettings } from '../../config/settings.js';
 import type { SessionMetrics } from '../contexts/SessionContext.js';
-import type { TextBuffer } from './shared/text-buffer.js';

 const composerTestControls = vi.hoisted(() => ({
  suggestionsVisible: false,
@@ -264,26 +263,16 @@ const renderComposer = async (
    </ConfigContext.Provider>,
  );
  await result.waitUntilReady();
-
-  // Wait for shortcuts hint debounce if using fake timers
-  if (vi.isFakeTimers()) {
-    await act(async () => {
-      await vi.advanceTimersByTimeAsync(250);
-    });
-  }
-
  return result;
 };

 describe('Composer', () => {
  beforeEach(() => {
-    vi.useFakeTimers();
    composerTestControls.suggestionsVisible = false;
    composerTestControls.isAlternateBuffer = false;
  });

  afterEach(() => {
-    vi.useRealTimers();
    vi.restoreAllMocks();
  });

@@ -402,7 +391,7 @@ describe('Composer', () => {
      expect(output).not.toContain('ShortcutsHint');
    });

-    it('renders LoadingIndicator with thought when loadingPhrases is off', async () => {
+    it('renders LoadingIndicator without thought when loadingPhrases is off', async () => {
      const uiState = createMockUIState({
        streamingState: StreamingState.Responding,
        thought: { subject: 'Hidden', description: 'Should not show' },
@@ -415,7 +404,7 @@ describe('Composer', () => {

      const output = lastFrame();
      expect(output).toContain('LoadingIndicator');
-      expect(output).toContain('LoadingIndicator: Hidden');
+      expect(output).not.toContain('Should not show');
    });

    it('does not render LoadingIndicator when waiting for confirmation', async () => {
@@ -820,28 +809,6 @@ describe('Composer', () => {
  });

  describe('Shortcuts Hint', () => {
-    it('restores shortcuts hint after 200ms debounce when buffer is empty', async () => {
-      const { lastFrame } = await renderComposer(
-        createMockUIState({
-          buffer: { text: '' } as unknown as TextBuffer,
-          cleanUiDetailsVisible: false,
-        }),
-      );
-
-      expect(lastFrame({ allowEmpty: true })).toContain('ShortcutsHint');
-    });
-
-    it('does not show shortcuts hint immediately when buffer has text', async () => {
-      const uiState = createMockUIState({
-        buffer: { text: 'hello' } as unknown as TextBuffer,
-        cleanUiDetailsVisible: false,
-      });
-
-      const { lastFrame } = await renderComposer(uiState);
-
-      expect(lastFrame()).not.toContain('ShortcutsHint');
-    });
-
    it('hides shortcuts hint when showShortcutsHint setting is false', async () => {
      const uiState = createMockUIState();
      const settings = createMockSettings({
@@ -890,27 +857,6 @@ describe('Composer', () => {
      expect(lastFrame()).toContain('ShortcutsHint');
    });

-    it('hides shortcuts hint while loading when full UI details are visible', async () => {
-      const uiState = createMockUIState({
-        cleanUiDetailsVisible: true,
-        streamingState: StreamingState.Responding,
-      });
-
-      const { lastFrame } = await renderComposer(uiState);
-
-      expect(lastFrame()).not.toContain('ShortcutsHint');
-    });
-
-    it('hides shortcuts hint when text is typed in buffer', async () => {
-      const uiState = createMockUIState({
-        buffer: { text: 'hello' } as unknown as TextBuffer,
-      });
-
-      const { lastFrame } = await renderComposer(uiState);
-
-      expect(lastFrame()).not.toContain('ShortcutsHint');
-    });
-
    it('hides shortcuts hint while loading in minimal mode', async () => {
      const uiState = createMockUIState({
        cleanUiDetailsVisible: false,
@@ -984,10 +930,9 @@ describe('Composer', () => {
        streamingState: StreamingState.Idle,
      });

-      const { lastFrame, unmount } = await renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);

      expect(lastFrame()).toContain('ShortcutsHelp');
-      unmount();
    });

    it('hides shortcuts help while streaming', async () => {
@@ -996,10 +941,9 @@ describe('Composer', () => {
        streamingState: StreamingState.Responding,
      });

-      const { lastFrame, unmount } = await renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);

      expect(lastFrame()).not.toContain('ShortcutsHelp');
-      unmount();
    });

    it('hides shortcuts help when action is required', async () => {
@@ -1012,10 +956,9 @@ describe('Composer', () => {
        ),
      });

-      const { lastFrame, unmount } = await renderComposer(uiState);
+      const { lastFrame } = await renderComposer(uiState);

      expect(lastFrame()).not.toContain('ShortcutsHelp');
-      unmount();
    });
  });

@@ -151,30 +151,11 @@ export const Composer = ({ isFocused = true }: { isFocused?: boolean }) => {
        : undefined,
    );
  const hideShortcutsHintForSuggestions = hideUiDetailsForSuggestions;
-  const isModelIdle = uiState.streamingState === StreamingState.Idle;
-  const isBufferEmpty = uiState.buffer.text.length === 0;
-  const canShowShortcutsHint =
-    isModelIdle && isBufferEmpty && !hasPendingActionRequired;
-  const [showShortcutsHintDebounced, setShowShortcutsHintDebounced] =
-    useState(canShowShortcutsHint);
-
-  useEffect(() => {
-    if (!canShowShortcutsHint) {
-      setShowShortcutsHintDebounced(false);
-      return;
-    }
-
-    const timeout = setTimeout(() => {
-      setShowShortcutsHintDebounced(true);
-    }, 200);
-
-    return () => clearTimeout(timeout);
-  }, [canShowShortcutsHint]);
-
  const showShortcutsHint =
    settings.merged.ui.showShortcutsHint &&
    !hideShortcutsHintForSuggestions &&
-    showShortcutsHintDebounced;
+    !hideMinimalModeHintWhileBusy &&
+    !hasPendingActionRequired;
  const showMinimalModeBleedThrough =
    !hideUiDetailsForSuggestions && Boolean(minimalModeBleedThrough);
  const showMinimalInlineLoading = !showUiDetails && showLoadingIndicator;
@@ -229,7 +210,8 @@ export const Composer = ({ isFocused = true }: { isFocused?: boolean }) => {
                inline
                thought={
                  uiState.streamingState ===
-                  StreamingState.WaitingForConfirmation
+                    StreamingState.WaitingForConfirmation ||
+                  settings.merged.ui.loadingPhrases === 'off'
                    ? undefined
                    : uiState.thought
                }
@@ -272,7 +254,8 @@ export const Composer = ({ isFocused = true }: { isFocused?: boolean }) => {
                  inline
                  thought={
                    uiState.streamingState ===
-                    StreamingState.WaitingForConfirmation
+                      StreamingState.WaitingForConfirmation ||
+                    settings.merged.ui.loadingPhrases === 'off'
                      ? undefined
                      : uiState.thought
                  }
@@ -4,13 +4,12 @@
 * SPDX-License-Identifier: Apache-2.0
 */

-import { renderWithProviders } from '../../test-utils/render.js';
+import { render } from '../../test-utils/render.js';
 import { DetailedMessagesDisplay } from './DetailedMessagesDisplay.js';
 import { describe, it, expect, vi } from 'vitest';
 import type { ConsoleMessageItem } from '../types.js';
 import { Box } from 'ink';
 import type React from 'react';
-import { createMockSettings } from '../../test-utils/settings.js';

 vi.mock('./shared/ScrollableList.js', () => ({
  ScrollableList: ({
@@ -30,18 +29,13 @@ vi.mock('./shared/ScrollableList.js', () => ({

 describe('DetailedMessagesDisplay', () => {
  it('renders nothing when messages are empty', async () => {
-    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = render(
      <DetailedMessagesDisplay
        messages={[]}
        maxHeight={10}
        width={80}
        hasFocus={false}
      />,
-      {
-        settings: createMockSettings({
-          merged: { ui: { errorVerbosity: 'full' } },
-        }),
-      },
    );
    await waitUntilReady();
    expect(lastFrame({ allowEmpty: true })).toBe('');
@@ -56,18 +50,13 @@ describe('DetailedMessagesDisplay', () => {
      { type: 'debug', content: 'Debug message', count: 1 },
    ];

-    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = render(
      <DetailedMessagesDisplay
        messages={messages}
        maxHeight={20}
        width={80}
        hasFocus={true}
      />,
-      {
-        settings: createMockSettings({
-          merged: { ui: { errorVerbosity: 'full' } },
-        }),
-      },
    );
    await waitUntilReady();
    const output = lastFrame();
@@ -76,69 +65,18 @@ describe('DetailedMessagesDisplay', () => {
    unmount();
  });

-  it('hides the F12 hint in low error verbosity mode', async () => {
-    const messages: ConsoleMessageItem[] = [
-      { type: 'error', content: 'Error message', count: 1 },
-    ];
-
-    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
-      <DetailedMessagesDisplay
-        messages={messages}
-        maxHeight={20}
-        width={80}
-        hasFocus={true}
-      />,
-      {
-        settings: createMockSettings({
-          merged: { ui: { errorVerbosity: 'low' } },
-        }),
-      },
-    );
-    await waitUntilReady();
-    expect(lastFrame()).not.toContain('(F12 to close)');
-    unmount();
-  });
-
-  it('shows the F12 hint in full error verbosity mode', async () => {
-    const messages: ConsoleMessageItem[] = [
-      { type: 'error', content: 'Error message', count: 1 },
-    ];
-
-    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
-      <DetailedMessagesDisplay
-        messages={messages}
-        maxHeight={20}
-        width={80}
-        hasFocus={true}
-      />,
-      {
-        settings: createMockSettings({
-          merged: { ui: { errorVerbosity: 'full' } },
-        }),
-      },
-    );
-    await waitUntilReady();
-    expect(lastFrame()).toContain('(F12 to close)');
-    unmount();
-  });
-
  it('renders message counts', async () => {
    const messages: ConsoleMessageItem[] = [
      { type: 'log', content: 'Repeated message', count: 5 },
    ];

-    const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
+    const { lastFrame, waitUntilReady, unmount } = render(
      <DetailedMessagesDisplay
        messages={messages}
        maxHeight={10}
        width={80}
        hasFocus={false}
      />,
-      {
-        settings: createMockSettings({
-          merged: { ui: { errorVerbosity: 'full' } },
-        }),
-      },
    );
    await waitUntilReady();
    const output = lastFrame();
@@ -13,8 +13,6 @@ import {
  ScrollableList,
  type ScrollableListRef,
 } from './shared/ScrollableList.js';
-import { useConfig } from '../contexts/ConfigContext.js';
-import { useSettings } from '../contexts/SettingsContext.js';

 interface DetailedMessagesDisplayProps {
  messages: ConsoleMessageItem[];
@@ -29,10 +27,6 @@ export const DetailedMessagesDisplay: React.FC<
  DetailedMessagesDisplayProps
 > = ({ messages, maxHeight, width, hasFocus }) => {
  const scrollableListRef = useRef<ScrollableListRef<ConsoleMessageItem>>(null);
-  const config = useConfig();
-  const settings = useSettings();
-  const showHotkeyHint =
-    settings.merged.ui.errorVerbosity === 'full' || config.getDebugMode();

  const borderAndPadding = 3;

@@ -71,10 +65,7 @@ export const DetailedMessagesDisplay: React.FC<
    >
      <Box marginBottom={1}>
        <Text bold color={theme.text.primary}>
-          Debug Console{' '}
-          {showHotkeyHint && (
-            <Text color={theme.text.secondary}>(F12 to close)</Text>
-          )}
+          Debug Console <Text color={theme.text.secondary}>(F12 to close)</Text>
        </Text>
      </Box>
      <Box height={maxHeight} width={width - borderAndPadding}>
@@ -80,8 +80,6 @@ describe('DialogManager', () => {
      stats: undefined,
      proQuotaRequest: null,
      validationRequest: null,
-      overageMenuRequest: null,
-      emptyWalletRequest: null,
    },
    shouldShowIdePrompt: false,
    isFolderTrustDialogOpen: false,
@@ -134,8 +132,6 @@ describe('DialogManager', () => {
            resolve: vi.fn(),
          },
          validationRequest: null,
-          overageMenuRequest: null,
-          emptyWalletRequest: null,
        },
      },
      'ProQuotaDialog',
@@ -13,14 +13,11 @@ import { ThemeDialog } from './ThemeDialog.js';
 import { SettingsDialog } from './SettingsDialog.js';
 import { AuthInProgress } from '../auth/AuthInProgress.js';
 import { AuthDialog } from '../auth/AuthDialog.js';
-import { BannedAccountDialog } from '../auth/BannedAccountDialog.js';
 import { ApiAuthDialog } from '../auth/ApiAuthDialog.js';
 import { EditorSettingsDialog } from './EditorSettingsDialog.js';
 import { PrivacyNotice } from '../privacy/PrivacyNotice.js';
 import { ProQuotaDialog } from './ProQuotaDialog.js';
 import { ValidationDialog } from './ValidationDialog.js';
-import { OverageMenuDialog } from './OverageMenuDialog.js';
-import { EmptyWalletDialog } from './EmptyWalletDialog.js';
 import { runExitCleanup } from '../../utils/cleanup.js';
 import { RELAUNCH_EXIT_CODE } from '../../utils/processUtils.js';
 import { SessionBrowser } from './SessionBrowser.js';
@@ -138,7 +135,6 @@ export const DialogManager = ({
        isModelNotFoundError={
          !!uiState.quota.proQuotaRequest.isModelNotFoundError
        }
-        authType={uiState.quota.proQuotaRequest.authType}
        onChoice={uiActions.handleProQuotaChoice}
      />
    );
@@ -155,28 +151,6 @@ export const DialogManager = ({
      />
    );
  }
-  if (uiState.quota.overageMenuRequest) {
-    return (
-      <OverageMenuDialog
-        failedModel={uiState.quota.overageMenuRequest.failedModel}
-        fallbackModel={uiState.quota.overageMenuRequest.fallbackModel}
-        resetTime={uiState.quota.overageMenuRequest.resetTime}
-        creditBalance={uiState.quota.overageMenuRequest.creditBalance}
-        onChoice={uiActions.handleOverageMenuChoice}
-      />
-    );
-  }
-  if (uiState.quota.emptyWalletRequest) {
-    return (
-      <EmptyWalletDialog
-        failedModel={uiState.quota.emptyWalletRequest.failedModel}
-        fallbackModel={uiState.quota.emptyWalletRequest.fallbackModel}
-        resetTime={uiState.quota.emptyWalletRequest.resetTime}
-        onGetCredits={uiState.quota.emptyWalletRequest.onGetCredits}
-        onChoice={uiActions.handleEmptyWalletChoice}
-      />
-    );
-  }
  if (uiState.shouldShowIdePrompt) {
    return (
      <IdeIntegrationNudge
@@ -321,21 +295,6 @@ export const DialogManager = ({
      </Box>
    );
  }
-  if (uiState.accountSuspensionInfo) {
-    return (
-      <Box flexDirection="column">
-        <BannedAccountDialog
-          accountSuspensionInfo={uiState.accountSuspensionInfo}
-          onExit={() => {
-            process.exit(1);
-          }}
-          onChangeAuth={() => {
-            uiActions.clearAccountSuspension();
-          }}
-        />
-      </Box>
-    );
-  }
  if (uiState.isAuthenticating) {
    return (
      <AuthInProgress
@@ -358,7 +317,6 @@ export const DialogManager = ({
      </Box>
    );
  }
-
  if (uiState.isAuthDialogOpen) {
    return (
      <Box flexDirection="column">
@@ -1,218 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import { renderWithProviders } from '../../test-utils/render.js';
-import { waitFor } from '../../test-utils/async.js';
-import { act } from 'react';
-import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
-import { EmptyWalletDialog } from './EmptyWalletDialog.js';
-
-const writeKey = (stdin: { write: (data: string) => void }, key: string) => {
-  act(() => {
-    stdin.write(key);
-  });
-};
-
-describe('EmptyWalletDialog', () => {
-  const mockOnChoice = vi.fn();
-  const mockOnGetCredits = vi.fn();
-
-  beforeEach(() => {
-    vi.clearAllMocks();
-  });
-
-  afterEach(() => {
-    vi.restoreAllMocks();
-  });
-
-  describe('rendering', () => {
-    it('should match snapshot with fallback available', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <EmptyWalletDialog
-          failedModel="gemini-2.5-pro"
-          fallbackModel="gemini-3-flash-preview"
-          resetTime="2:00 PM"
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      expect(lastFrame()).toMatchSnapshot();
-      unmount();
-    });
-
-    it('should match snapshot without fallback', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <EmptyWalletDialog
-          failedModel="gemini-2.5-pro"
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      expect(lastFrame()).toMatchSnapshot();
-      unmount();
-    });
-
-    it('should display the model name and usage limit message', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <EmptyWalletDialog
-          failedModel="gemini-2.5-pro"
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      const output = lastFrame() ?? '';
-      expect(output).toContain('gemini-2.5-pro');
-      expect(output).toContain('Usage limit reached');
-      unmount();
-    });
-
-    it('should display purchase prompt and credits update notice', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <EmptyWalletDialog
-          failedModel="gemini-2.5-pro"
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      const output = lastFrame() ?? '';
-      expect(output).toContain('purchase more AI Credits');
-      expect(output).toContain(
-        'Newly purchased AI credits may take a few minutes to update',
-      );
-      unmount();
-    });
-
-    it('should display reset time when provided', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <EmptyWalletDialog
-          failedModel="gemini-2.5-pro"
-          resetTime="3:45 PM"
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      const output = lastFrame() ?? '';
-      expect(output).toContain('3:45 PM');
-      expect(output).toContain('Access resets at');
-      unmount();
-    });
-
-    it('should not display reset time when not provided', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <EmptyWalletDialog
-          failedModel="gemini-2.5-pro"
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      const output = lastFrame() ?? '';
-      expect(output).not.toContain('Access resets at');
-      unmount();
-    });
-
-    it('should display slash command hints', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <EmptyWalletDialog
-          failedModel="gemini-2.5-pro"
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      const output = lastFrame() ?? '';
-      expect(output).toContain('/stats');
-      expect(output).toContain('/model');
-      expect(output).toContain('/auth');
-      unmount();
-    });
-  });
-
-  describe('onChoice handling', () => {
-    it('should call onGetCredits and onChoice when get_credits is selected', async () => {
-      // get_credits is the first item, so just press Enter
-      const { unmount, stdin, waitUntilReady } = renderWithProviders(
-        <EmptyWalletDialog
-          failedModel="gemini-2.5-pro"
-          onChoice={mockOnChoice}
-          onGetCredits={mockOnGetCredits}
-        />,
-      );
-      await waitUntilReady();
-
-      writeKey(stdin, '\r');
-
-      await waitFor(() => {
-        expect(mockOnGetCredits).toHaveBeenCalled();
-        expect(mockOnChoice).toHaveBeenCalledWith('get_credits');
-      });
-      unmount();
-    });
-
-    it('should call onChoice without onGetCredits when onGetCredits is not provided', async () => {
-      const { unmount, stdin, waitUntilReady } = renderWithProviders(
-        <EmptyWalletDialog
-          failedModel="gemini-2.5-pro"
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      writeKey(stdin, '\r');
-
-      await waitFor(() => {
-        expect(mockOnChoice).toHaveBeenCalledWith('get_credits');
-      });
-      unmount();
-    });
-
-    it('should call onChoice with use_fallback when selected', async () => {
-      // With fallback: items are [get_credits, use_fallback, stop]
-      // use_fallback is the second item: Down + Enter
-      const { unmount, stdin, waitUntilReady } = renderWithProviders(
-        <EmptyWalletDialog
-          failedModel="gemini-2.5-pro"
-          fallbackModel="gemini-3-flash-preview"
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      writeKey(stdin, '\x1b[B'); // Down arrow
-      writeKey(stdin, '\r');
-
-      await waitFor(() => {
-        expect(mockOnChoice).toHaveBeenCalledWith('use_fallback');
-      });
-      unmount();
-    });
-
-    it('should call onChoice with stop when selected', async () => {
-      // Without fallback: items are [get_credits, stop]
-      // stop is the second item: Down + Enter
-      const { unmount, stdin, waitUntilReady } = renderWithProviders(
-        <EmptyWalletDialog
-          failedModel="gemini-2.5-pro"
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      writeKey(stdin, '\x1b[B'); // Down arrow
-      writeKey(stdin, '\r');
-
-      await waitFor(() => {
-        expect(mockOnChoice).toHaveBeenCalledWith('stop');
-      });
-      unmount();
-    });
-  });
-});
@@ -1,110 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import type React from 'react';
-import { Box, Text } from 'ink';
-import { RadioButtonSelect } from './shared/RadioButtonSelect.js';
-import { theme } from '../semantic-colors.js';
-
-/** Available choices in the empty wallet dialog */
-export type EmptyWalletChoice = 'get_credits' | 'use_fallback' | 'stop';
-
-interface EmptyWalletDialogProps {
-  /** The model that hit the quota limit */
-  failedModel: string;
-  /** The fallback model to offer (omit if none available) */
-  fallbackModel?: string;
-  /** Time when access resets (human-readable) */
-  resetTime?: string;
-  /** Callback to log click and open the browser for purchasing credits */
-  onGetCredits?: () => void;
-  /** Callback when user makes a selection */
-  onChoice: (choice: EmptyWalletChoice) => void;
-}
-
-export function EmptyWalletDialog({
-  failedModel,
-  fallbackModel,
-  resetTime,
-  onGetCredits,
-  onChoice,
-}: EmptyWalletDialogProps): React.JSX.Element {
-  const items: Array<{
-    label: string;
-    value: EmptyWalletChoice;
-    key: string;
-  }> = [
-    {
-      label: 'Get AI Credits - Open browser to purchase credits',
-      value: 'get_credits',
-      key: 'get_credits',
-    },
-  ];
-
-  if (fallbackModel) {
-    items.push({
-      label: `Switch to ${fallbackModel}`,
-      value: 'use_fallback',
-      key: 'use_fallback',
-    });
-  }
-
-  items.push({
-    label: 'Stop - Abort request',
-    value: 'stop',
-    key: 'stop',
-  });
-
-  const handleSelect = (choice: EmptyWalletChoice) => {
-    if (choice === 'get_credits') {
-      onGetCredits?.();
-    }
-    onChoice(choice);
-  };
-
-  return (
-    <Box borderStyle="round" flexDirection="column" padding={1}>
-      <Box marginBottom={1} flexDirection="column">
-        <Text color={theme.status.warning}>
-          Usage limit reached for {failedModel}.
-        </Text>
-        {resetTime && <Text>Access resets at {resetTime}.</Text>}
-        <Text>
-          <Text bold color={theme.text.accent}>
-            /stats
-          </Text>{' '}
-          model for usage details
-        </Text>
-        <Text>
-          <Text bold color={theme.text.accent}>
-            /model
-          </Text>{' '}
-          to switch models.
-        </Text>
-        <Text>
-          <Text bold color={theme.text.accent}>
-            /auth
-          </Text>{' '}
-          to switch to API key.
-        </Text>
-      </Box>
-      <Box marginBottom={1}>
-        <Text>To continue using this model now, purchase more AI Credits.</Text>
-      </Box>
-      <Box marginBottom={1}>
-        <Text dimColor>
-          Newly purchased AI credits may take a few minutes to update.
-        </Text>
-      </Box>
-      <Box marginBottom={1}>
-        <Text>How would you like to proceed?</Text>
-      </Box>
-      <Box marginTop={1} marginBottom={1}>
-        <RadioButtonSelect items={items} onSelect={handleSelect} />
-      </Box>
-    </Box>
-  );
-}
@@ -167,7 +167,6 @@ Implement a comprehensive authentication system with multiple providers.
            readTextFile: vi.fn(),
            writeTextFile: vi.fn(),
          }),
-          getUseAlternateBuffer: () => options?.useAlternateBuffer ?? true,
        } as unknown as import('@google/gemini-cli-core').Config,
      },
    );
@@ -444,7 +443,6 @@ Implement a comprehensive authentication system with multiple providers.
                readTextFile: vi.fn(),
                writeTextFile: vi.fn(),
              }),
-              getUseAlternateBuffer: () => useAlternateBuffer ?? true,
            } as unknown as import('@google/gemini-cli-core').Config,
          },
        );
@@ -8,11 +8,7 @@ import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
 import { renderWithProviders } from '../../test-utils/render.js';
 import { createMockSettings } from '../../test-utils/settings.js';
 import { Footer } from './Footer.js';
-import {
-  makeFakeConfig,
-  tildeifyPath,
-  ToolCallDecision,
-} from '@google/gemini-cli-core';
+import { tildeifyPath, ToolCallDecision } from '@google/gemini-cli-core';
 import type { SessionStatsState } from '../contexts/SessionContext.js';

 vi.mock('@google/gemini-cli-core', async (importOriginal) => {
@@ -181,8 +177,6 @@ describe('<Footer />', () => {
            },
            proQuotaRequest: null,
            validationRequest: null,
-            overageMenuRequest: null,
-            emptyWalletRequest: null,
          },
        },
      },
@@ -209,8 +203,6 @@ describe('<Footer />', () => {
            },
            proQuotaRequest: null,
            validationRequest: null,
-            overageMenuRequest: null,
-            emptyWalletRequest: null,
          },
        },
      },
@@ -237,8 +229,6 @@ describe('<Footer />', () => {
            },
            proQuotaRequest: null,
            validationRequest: null,
-            overageMenuRequest: null,
-            emptyWalletRequest: null,
          },
        },
      },
@@ -507,75 +497,6 @@ describe('<Footer />', () => {
      unmount();
    });
  });
-
-  describe('error summary visibility', () => {
-    it('hides error summary in low verbosity mode', async () => {
-      const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
-        <Footer />,
-        {
-          width: 120,
-          uiState: {
-            sessionStats: mockSessionStats,
-            errorCount: 2,
-            showErrorDetails: false,
-          },
-          settings: createMockSettings({
-            merged: { ui: { errorVerbosity: 'low' } },
-          }),
-        },
-      );
-      await waitUntilReady();
-      expect(lastFrame()).not.toContain('F12 for details');
-      expect(lastFrame()).not.toContain('2 errors');
-      unmount();
-    });
-
-    it('shows error summary in full verbosity mode', async () => {
-      const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
-        <Footer />,
-        {
-          width: 120,
-          uiState: {
-            sessionStats: mockSessionStats,
-            errorCount: 2,
-            showErrorDetails: false,
-          },
-          settings: createMockSettings({
-            merged: { ui: { errorVerbosity: 'full' } },
-          }),
-        },
-      );
-      await waitUntilReady();
-      expect(lastFrame()).toContain('F12 for details');
-      expect(lastFrame()).toContain('2 errors');
-      unmount();
-    });
-
-    it('shows error summary in debug mode even when verbosity is low', async () => {
-      const debugConfig = makeFakeConfig();
-      vi.spyOn(debugConfig, 'getDebugMode').mockReturnValue(true);
-
-      const { lastFrame, waitUntilReady, unmount } = renderWithProviders(
-        <Footer />,
-        {
-          width: 120,
-          config: debugConfig,
-          uiState: {
-            sessionStats: mockSessionStats,
-            errorCount: 1,
-            showErrorDetails: false,
-          },
-          settings: createMockSettings({
-            merged: { ui: { errorVerbosity: 'low' } },
-          }),
-        },
-      );
-      await waitUntilReady();
-      expect(lastFrame()).toContain('F12 for details');
-      expect(lastFrame()).toContain('1 error');
-      unmount();
-    });
-  });
 });

 describe('fallback mode display', () => {
@@ -60,9 +60,6 @@ export const Footer: React.FC = () => {

  const showMemoryUsage =
    config.getDebugMode() || settings.merged.ui.showMemoryUsage;
-  const isFullErrorVerbosity = settings.merged.ui.errorVerbosity === 'full';
-  const showErrorSummary =
-    !showErrorDetails && errorCount > 0 && (isFullErrorVerbosity || debugMode);
  const hideCWD = settings.merged.ui.footer.hideCWD;
  const hideSandboxStatus = settings.merged.ui.footer.hideSandboxStatus;
  const hideModelInfo = settings.merged.ui.footer.hideModelInfo;
@@ -183,7 +180,7 @@ export const Footer: React.FC = () => {
                </Text>
              </Box>
            )}
-            {showErrorSummary && (
+            {!showErrorDetails && errorCount > 0 && (
              <Box paddingLeft={1} flexDirection="row">
                <Text color={theme.ui.comment}>| </Text>
                <ConsoleSummaryDisplay errorCount={errorCount} />
@@ -146,7 +146,6 @@ export const HistoryItemDisplay: React.FC<HistoryItemDisplayProps> = ({
                }
              : undefined
          }
-          creditBalance={itemForDisplay.creditBalance}
        />
      )}
      {itemForDisplay.type === 'model_stats' && (
@@ -895,9 +895,7 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
        completion.isPerfectMatch &&
        keyMatchers[Command.SUBMIT](key) &&
        recentUnsafePasteTime === null &&
-        (!completion.showSuggestions ||
-          (completion.activeSuggestionIndex <= 0 &&
-            !hasUserNavigatedSuggestions.current))
+        (!completion.showSuggestions || completion.activeSuggestionIndex <= 0)
      ) {
        handleSubmit(buffer.text);
        return true;
@@ -1,228 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import { renderWithProviders } from '../../test-utils/render.js';
-import { waitFor } from '../../test-utils/async.js';
-import { act } from 'react';
-import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
-import { OverageMenuDialog } from './OverageMenuDialog.js';
-
-const writeKey = (stdin: { write: (data: string) => void }, key: string) => {
-  act(() => {
-    stdin.write(key);
-  });
-};
-
-describe('OverageMenuDialog', () => {
-  const mockOnChoice = vi.fn();
-
-  beforeEach(() => {
-    vi.clearAllMocks();
-  });
-
-  afterEach(() => {
-    vi.restoreAllMocks();
-  });
-
-  describe('rendering', () => {
-    it('should match snapshot with fallback available', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <OverageMenuDialog
-          failedModel="gemini-2.5-pro"
-          fallbackModel="gemini-3-flash-preview"
-          resetTime="2:00 PM"
-          creditBalance={500}
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      expect(lastFrame()).toMatchSnapshot();
-      unmount();
-    });
-
-    it('should match snapshot without fallback', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <OverageMenuDialog
-          failedModel="gemini-2.5-pro"
-          creditBalance={500}
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      expect(lastFrame()).toMatchSnapshot();
-      unmount();
-    });
-
-    it('should display the credit balance', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <OverageMenuDialog
-          failedModel="gemini-2.5-pro"
-          creditBalance={200}
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      const output = lastFrame() ?? '';
-      expect(output).toContain('200');
-      expect(output).toContain('AI Credits available');
-      unmount();
-    });
-
-    it('should display the model name', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <OverageMenuDialog
-          failedModel="gemini-2.5-pro"
-          creditBalance={100}
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      const output = lastFrame() ?? '';
-      expect(output).toContain('gemini-2.5-pro');
-      expect(output).toContain('Usage limit reached');
-      unmount();
-    });
-
-    it('should display reset time when provided', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <OverageMenuDialog
-          failedModel="gemini-2.5-pro"
-          resetTime="3:45 PM"
-          creditBalance={100}
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      const output = lastFrame() ?? '';
-      expect(output).toContain('3:45 PM');
-      expect(output).toContain('Access resets at');
-      unmount();
-    });
-
-    it('should not display reset time when not provided', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <OverageMenuDialog
-          failedModel="gemini-2.5-pro"
-          creditBalance={100}
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      const output = lastFrame() ?? '';
-      expect(output).not.toContain('Access resets at');
-      unmount();
-    });
-
-    it('should display slash command hints', async () => {
-      const { lastFrame, unmount, waitUntilReady } = renderWithProviders(
-        <OverageMenuDialog
-          failedModel="gemini-2.5-pro"
-          creditBalance={100}
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      const output = lastFrame() ?? '';
-      expect(output).toContain('/stats');
-      expect(output).toContain('/model');
-      expect(output).toContain('/auth');
-      unmount();
-    });
-  });
-
-  describe('onChoice handling', () => {
-    it('should call onChoice with use_credits when selected', async () => {
-      // use_credits is the first item, so just press Enter
-      const { unmount, stdin, waitUntilReady } = renderWithProviders(
-        <OverageMenuDialog
-          failedModel="gemini-2.5-pro"
-          creditBalance={100}
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      writeKey(stdin, '\r');
-
-      await waitFor(() => {
-        expect(mockOnChoice).toHaveBeenCalledWith('use_credits');
-      });
-      unmount();
-    });
-
-    it('should call onChoice with manage when selected', async () => {
-      // manage is the second item: Down + Enter
-      const { unmount, stdin, waitUntilReady } = renderWithProviders(
-        <OverageMenuDialog
-          failedModel="gemini-2.5-pro"
-          creditBalance={100}
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      writeKey(stdin, '\x1b[B'); // Down arrow
-      writeKey(stdin, '\r');
-
-      await waitFor(() => {
-        expect(mockOnChoice).toHaveBeenCalledWith('manage');
-      });
-      unmount();
-    });
-
-    it('should call onChoice with use_fallback when selected', async () => {
-      // With fallback: items are [use_credits, manage, use_fallback, stop]
-      // use_fallback is the third item: Down x2 + Enter
-      const { unmount, stdin, waitUntilReady } = renderWithProviders(
-        <OverageMenuDialog
-          failedModel="gemini-2.5-pro"
-          fallbackModel="gemini-3-flash-preview"
-          creditBalance={100}
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      writeKey(stdin, '\x1b[B'); // Down arrow
-      writeKey(stdin, '\x1b[B'); // Down arrow
-      writeKey(stdin, '\r');
-
-      await waitFor(() => {
-        expect(mockOnChoice).toHaveBeenCalledWith('use_fallback');
-      });
-      unmount();
-    });
-
-    it('should call onChoice with stop when selected', async () => {
-      // Without fallback: items are [use_credits, manage, stop]
-      // stop is the third item: Down x2 + Enter
-      const { unmount, stdin, waitUntilReady } = renderWithProviders(
-        <OverageMenuDialog
-          failedModel="gemini-2.5-pro"
-          creditBalance={100}
-          onChoice={mockOnChoice}
-        />,
-      );
-      await waitUntilReady();
-
-      writeKey(stdin, '\x1b[B'); // Down arrow
-      writeKey(stdin, '\x1b[B'); // Down arrow
-      writeKey(stdin, '\r');
-
-      await waitFor(() => {
-        expect(mockOnChoice).toHaveBeenCalledWith('stop');
-      });
-      unmount();
-    });
-  });
-});
@@ -1,113 +0,0 @@
-/**
- * @license
- * Copyright 2026 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import type React from 'react';
-import { Box, Text } from 'ink';
-import { RadioButtonSelect } from './shared/RadioButtonSelect.js';
-import { theme } from '../semantic-colors.js';
-
-/** Available choices in the overage menu dialog */
-export type OverageMenuChoice =
-  | 'use_credits'
-  | 'use_fallback'
-  | 'manage'
-  | 'stop';
-
-interface OverageMenuDialogProps {
-  /** The model that hit the quota limit */
-  failedModel: string;
-  /** The fallback model to offer (omit if none available) */
-  fallbackModel?: string;
-  /** Time when access resets (human-readable) */
-  resetTime?: string;
-  /** Available G1 AI credit balance */
-  creditBalance: number;
-  /** Callback when user makes a selection */
-  onChoice: (choice: OverageMenuChoice) => void;
-}
-
-export function OverageMenuDialog({
-  failedModel,
-  fallbackModel,
-  resetTime,
-  creditBalance,
-  onChoice,
-}: OverageMenuDialogProps): React.JSX.Element {
-  const items: Array<{
-    label: string;
-    value: OverageMenuChoice;
-    key: string;
-  }> = [
-    {
-      label: 'Use AI Credits - Continue this request (Overage)',
-      value: 'use_credits',
-      key: 'use_credits',
-    },
-    {
-      label: 'Manage - View balance and purchase more credits',
-      value: 'manage',
-      key: 'manage',
-    },
-  ];
-
-  if (fallbackModel) {
-    items.push({
-      label: `Switch to ${fallbackModel}`,
-      value: 'use_fallback',
-      key: 'use_fallback',
-    });
-  }
-
-  items.push({
-    label: 'Stop - Abort request',
-    value: 'stop',
-    key: 'stop',
-  });
-
-  return (
-    <Box borderStyle="round" flexDirection="column" padding={1}>
-      <Box marginBottom={1} flexDirection="column">
-        <Text color={theme.status.warning}>
-          Usage limit reached for {failedModel}.
-        </Text>
-        {resetTime && <Text>Access resets at {resetTime}.</Text>}
-        <Text>
-          <Text bold color={theme.text.accent}>
-            /stats
-          </Text>{' '}
-          model for usage details
-        </Text>
-        <Text>
-          <Text bold color={theme.text.accent}>
-            /model
-          </Text>{' '}
-          to switch models.
-        </Text>
-        <Text>
-          <Text bold color={theme.text.accent}>
-            /auth
-          </Text>{' '}
-          to switch to API key.
-        </Text>
-      </Box>
-      <Box marginBottom={1}>
-        <Text>
-          You have{' '}
-          <Text bold color={theme.status.success}>
-            {creditBalance}
-          </Text>{' '}
-          AI Credits available.
-        </Text>
-      </Box>
-      <Box marginBottom={1}>
-        <Text>How would you like to proceed?</Text>
-      </Box>
-      <Box marginTop={1} marginBottom={1}>
-        <RadioButtonSelect items={items} onSelect={onChoice} />
-      </Box>
-    </Box>
-  );
-}
@@ -13,7 +13,6 @@ import { RadioButtonSelect } from './shared/RadioButtonSelect.js';
 import {
  PREVIEW_GEMINI_MODEL,
  DEFAULT_GEMINI_FLASH_MODEL,
-  AuthType,
 } from '@google/gemini-cli-core';

 // Mock the child component to make it easier to test the parent
@@ -63,7 +62,7 @@ describe('ProQuotaDialog', () => {

  describe('for non-flash model failures', () => {
    describe('when it is a terminal quota error', () => {
-      it('should render switch, upgrade, and stop options for LOGIN_WITH_GOOGLE', () => {
+      it('should render switch, upgrade, and stop options for paid tiers', () => {
        const { unmount } = render(
          <ProQuotaDialog
            failedModel="gemini-2.5-pro"
@@ -71,7 +70,6 @@ describe('ProQuotaDialog', () => {
            message="paid tier quota error"
            isTerminalQuotaError={true}
            isModelNotFoundError={false}
-            authType={AuthType.LOGIN_WITH_GOOGLE}
            onChoice={mockOnChoice}
          />,
        );
@@ -101,39 +99,6 @@ describe('ProQuotaDialog', () => {
        unmount();
      });

-      it('should NOT render upgrade option for USE_GEMINI', () => {
-        const { unmount } = render(
-          <ProQuotaDialog
-            failedModel="gemini-2.5-pro"
-            fallbackModel="gemini-2.5-flash"
-            message="paid tier quota error"
-            isTerminalQuotaError={true}
-            isModelNotFoundError={false}
-            authType={AuthType.USE_GEMINI}
-            onChoice={mockOnChoice}
-          />,
-        );
-
-        expect(RadioButtonSelect).toHaveBeenCalledWith(
-          expect.objectContaining({
-            items: [
-              {
-                label: 'Switch to gemini-2.5-flash',
-                value: 'retry_always',
-                key: 'retry_always',
-              },
-              {
-                label: 'Stop',
-                value: 'retry_later',
-                key: 'retry_later',
-              },
-            ],
-          }),
-          undefined,
-        );
-        unmount();
-      });
-
      it('should render "Keep trying" and "Stop" options when failed model and fallback model are the same', () => {
        const { unmount } = render(
          <ProQuotaDialog
@@ -165,7 +130,7 @@ describe('ProQuotaDialog', () => {
        unmount();
      });

-      it('should render switch, upgrade, and stop options for LOGIN_WITH_GOOGLE (free tier)', () => {
+      it('should render switch, upgrade, and stop options for free tier', () => {
        const { unmount } = render(
          <ProQuotaDialog
            failedModel="gemini-2.5-pro"
@@ -173,7 +138,6 @@ describe('ProQuotaDialog', () => {
            message="free tier quota error"
            isTerminalQuotaError={true}
            isModelNotFoundError={false}
-            authType={AuthType.LOGIN_WITH_GOOGLE}
            onChoice={mockOnChoice}
          />,
        );
@@ -240,7 +204,7 @@ describe('ProQuotaDialog', () => {
    });

    describe('when it is a model not found error', () => {
-      it('should render switch, upgrade, and stop options for LOGIN_WITH_GOOGLE', () => {
+      it('should render switch and stop options regardless of tier', () => {
        const { unmount } = render(
          <ProQuotaDialog
            failedModel="gemini-3-pro-preview"
@@ -248,7 +212,6 @@ describe('ProQuotaDialog', () => {
            message="You don't have access to gemini-3-pro-preview yet."
            isTerminalQuotaError={false}
            isModelNotFoundError={true}
-            authType={AuthType.LOGIN_WITH_GOOGLE}
            onChoice={mockOnChoice}
          />,
        );
@@ -278,7 +241,7 @@ describe('ProQuotaDialog', () => {
        unmount();
      });

-      it('should NOT render upgrade option for USE_GEMINI', () => {
+      it('should render switch and stop options for paid tier as well', () => {
        const { unmount } = render(
          <ProQuotaDialog
            failedModel="gemini-3-pro-preview"
@@ -286,7 +249,6 @@ describe('ProQuotaDialog', () => {
            message="You don't have access to gemini-3-pro-preview yet."
            isTerminalQuotaError={false}
            isModelNotFoundError={true}
-            authType={AuthType.USE_GEMINI}
            onChoice={mockOnChoice}
          />,
        );
@@ -299,6 +261,11 @@ describe('ProQuotaDialog', () => {
                value: 'retry_always',
                key: 'retry_always',
              },
+              {
+                label: 'Upgrade for higher limits',
+                value: 'upgrade',
+                key: 'upgrade',
+              },
              {
                label: 'Stop',
                value: 'retry_later',
@@ -8,7 +8,6 @@ import type React from 'react';
 import { Box, Text } from 'ink';
 import { RadioButtonSelect } from './shared/RadioButtonSelect.js';
 import { theme } from '../semantic-colors.js';
-import { AuthType } from '@google/gemini-cli-core';

 interface ProQuotaDialogProps {
  failedModel: string;
@@ -16,7 +15,6 @@ interface ProQuotaDialogProps {
  message: string;
  isTerminalQuotaError: boolean;
  isModelNotFoundError?: boolean;
-  authType?: AuthType;
  onChoice: (
    choice: 'retry_later' | 'retry_once' | 'retry_always' | 'upgrade',
  ) => void;
@@ -28,7 +26,6 @@ export function ProQuotaDialog({
  message,
  isTerminalQuotaError,
  isModelNotFoundError,
-  authType,
  onChoice,
 }: ProQuotaDialogProps): React.JSX.Element {
  let items;
@@ -54,15 +51,11 @@ export function ProQuotaDialog({
        value: 'retry_always' as const,
        key: 'retry_always',
      },
-      ...(authType === AuthType.LOGIN_WITH_GOOGLE
-        ? [
-            {
-              label: 'Upgrade for higher limits',
-              value: 'upgrade' as const,
-              key: 'upgrade',
-            },
-          ]
-        : []),
+      {
+        label: 'Upgrade for higher limits',
+        value: 'upgrade' as const,
+        key: 'upgrade',
+      },
      {
        label: `Stop`,
        value: 'retry_later' as const,
@@ -395,7 +395,6 @@ interface StatsDisplayProps {
  tier?: string;
  currentModel?: string;
  quotaStats?: QuotaStats;
-  creditBalance?: number;
 }

 export const StatsDisplay: React.FC<StatsDisplayProps> = ({
@@ -408,7 +407,6 @@ export const StatsDisplay: React.FC<StatsDisplayProps> = ({
  tier,
  currentModel,
  quotaStats,
-  creditBalance,
 }) => {
  const { stats } = useSessionStats();
  const { metrics } = stats;
@@ -490,17 +488,6 @@ export const StatsDisplay: React.FC<StatsDisplayProps> = ({
            <Text color={theme.text.primary}>{tier}</Text>
          </StatRow>
        )}
-        {showUserIdentity && creditBalance != null && creditBalance >= 0 && (
-          <StatRow title="Google AI Credits:">
-            <Text
-              color={
-                creditBalance > 0 ? theme.text.primary : theme.text.secondary
-              }
-            >
-              {creditBalance.toLocaleString()}
-            </Text>
-          </StatRow>
-        )}
        <StatRow title="Tool Calls:">
          <Text color={theme.text.primary}>
            {tools.totalCalls} ({' '}
@@ -187,9 +187,7 @@ describe('ToastDisplay', () => {
      constrainHeight: true,
    });
    await waitUntilReady();
-    expect(lastFrame()).toContain(
-      'Ctrl+O to show more lines of the last response',
-    );
+    expect(lastFrame()).toContain('Press Ctrl+O to show more lines');
  });

  it('renders collapse hint when showIsExpandableHint is true and constrainHeight is false', async () => {
@@ -198,8 +196,6 @@ describe('ToastDisplay', () => {
      constrainHeight: false,
    });
    await waitUntilReady();
-    expect(lastFrame()).toContain(
-      'Ctrl+O to collapse lines of the last response',
-    );
+    expect(lastFrame()).toContain('Press Ctrl+O to collapse lines');
  });
 });
@@ -78,7 +78,7 @@ export const ToastDisplay: React.FC = () => {
    const action = uiState.constrainHeight ? 'show more' : 'collapse';
    return (
      <Text color={theme.text.accent}>
-        Ctrl+O to {action} lines of the last response
+        Press Ctrl+O to {action} lines for the most recent response
      </Text>
    );
  }
@@ -51,7 +51,6 @@ describe('ToolConfirmationQueue', () => {
    storage: {
      getPlansDir: () => '/mock/temp/plans',
    },
-    getUseAlternateBuffer: () => false,
  } as unknown as Config;

  beforeEach(() => {
@@ -228,7 +227,7 @@ describe('ToolConfirmationQueue', () => {
    // availableContentHeight = Math.max(9 - 6, 4) = 4
    // MaxSizedBox in ToolConfirmationMessage will use 4
    // It should show truncation message
-    await waitFor(() => expect(lastFrame()).toContain('49 hidden (Ctrl+O)'));
+    await waitFor(() => expect(lastFrame()).toContain('first 49 lines hidden'));
    expect(lastFrame()).toMatchSnapshot();
    unmount();
  });
@@ -35,7 +35,7 @@ Footer
 `;

 exports[`Composer > Snapshots > matches snapshot while streaming 1`] = `
-" LoadingIndicator: Thinking
+" LoadingIndicator: Thinking                                                            ShortcutsHint
 ────────────────────────────────────────────────────────────────────────────────────────────────────
 ApprovalModeIndicator
 InputPrompt:   Type your message or @path/to/file
@@ -1,49 +0,0 @@
-// Vitest Snapshot v1, https://vitest.dev/guide/snapshot.html
-
-exports[`EmptyWalletDialog > rendering > should match snapshot with fallback available 1`] = `
-"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
-│                                                                                                  │
-│ Usage limit reached for gemini-2.5-pro.                                                          │
-│ Access resets at 2:00 PM.                                                                        │
-│ /stats model for usage details                                                                   │
-│ /model to switch models.                                                                         │
-│ /auth to switch to API key.                                                                      │
-│                                                                                                  │
-│ To continue using this model now, purchase more AI Credits.                                      │
-│                                                                                                  │
-│ Newly purchased AI credits may take a few minutes to update.                                     │
-│                                                                                                  │
-│ How would you like to proceed?                                                                   │
-│                                                                                                  │
-│                                                                                                  │
-│ ● 1. Get AI Credits - Open browser to purchase credits                                           │
-│   2. Switch to gemini-3-flash-preview                                                            │
-│   3. Stop - Abort request                                                                        │
-│                                                                                                  │
-│                                                                                                  │
-╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
-"
-`;
-
-exports[`EmptyWalletDialog > rendering > should match snapshot without fallback 1`] = `
-"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
-│                                                                                                  │
-│ Usage limit reached for gemini-2.5-pro.                                                          │
-│ /stats model for usage details                                                                   │
-│ /model to switch models.                                                                         │
-│ /auth to switch to API key.                                                                      │
-│                                                                                                  │
-│ To continue using this model now, purchase more AI Credits.                                      │
-│                                                                                                  │
-│ Newly purchased AI credits may take a few minutes to update.                                     │
-│                                                                                                  │
-│ How would you like to proceed?                                                                   │
-│                                                                                                  │
-│                                                                                                  │
-│ ● 1. Get AI Credits - Open browser to purchase credits                                           │
-│   2. Stop - Abort request                                                                        │
-│                                                                                                  │
-│                                                                                                  │
-╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
-"
-`;
@@ -74,7 +74,7 @@ Implementation Steps
 6. Add LDAP provider support in src/auth/providers/LDAPProvider.ts
 7. Create token refresh mechanism in src/auth/TokenManager.ts
 8. Add multi-factor authentication in src/auth/MFAService.ts
-... last 22 lines hidden (Ctrl+O to show) ...
+... last 22 lines hidden ...

 ● 1.  Yes, automatically accept edits
      Approves plan and allows tools to run automatically
@@ -112,7 +112,7 @@ exports[`<HistoryItemDisplay /> > gemini items (alternateBuffer=false) > should

 exports[`<HistoryItemDisplay /> > gemini items (alternateBuffer=false) > should render a truncated gemini item 1`] = `
 "✦ Example code block:
-   ... 42 hidden (Ctrl+O) ...
+   ... first 42 lines hidden ...
   43 Line 43
   44 Line 44
   45 Line 45
@@ -126,7 +126,7 @@ exports[`<HistoryItemDisplay /> > gemini items (alternateBuffer=false) > should

 exports[`<HistoryItemDisplay /> > gemini items (alternateBuffer=false) > should render a truncated gemini_content item 1`] = `
 "  Example code block:
-   ... 42 hidden (Ctrl+O) ...
+   ... first 42 lines hidden ...
   43 Line 43
   44 Line 44
   45 Line 45
@@ -49,7 +49,7 @@ exports[`MainContent > MainContent Tool Output Height Logic > 'Normal mode - Con
 ╭──────────────────────────────────────────────────────────────────────────────────────────────╮
 │ ⊷  Shell Command Running a long command...                                                   │
 │                                                                                              │
-│ ... first 11 lines hidden (Ctrl+O to show) ...                                               │
+│ ... first 11 lines hidden ...                                                                │
 │ Line 12                                                                                      │
 │ Line 13                                                                                      │
 │ Line 14                                                                                      │
@@ -1,47 +0,0 @@
-// Vitest Snapshot v1, https://vitest.dev/guide/snapshot.html
-
-exports[`OverageMenuDialog > rendering > should match snapshot with fallback available 1`] = `
-"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
-│                                                                                                  │
-│ Usage limit reached for gemini-2.5-pro.                                                          │
-│ Access resets at 2:00 PM.                                                                        │
-│ /stats model for usage details                                                                   │
-│ /model to switch models.                                                                         │
-│ /auth to switch to API key.                                                                      │
-│                                                                                                  │
-│ You have 500 AI Credits available.                                                               │
-│                                                                                                  │
-│ How would you like to proceed?                                                                   │
-│                                                                                                  │
-│                                                                                                  │
-│ ● 1. Use AI Credits - Continue this request (Overage)                                            │
-│   2. Manage - View balance and purchase more credits                                             │
-│   3. Switch to gemini-3-flash-preview                                                            │
-│   4. Stop - Abort request                                                                        │
-│                                                                                                  │
-│                                                                                                  │
-╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
-"
-`;
-
-exports[`OverageMenuDialog > rendering > should match snapshot without fallback 1`] = `
-"╭──────────────────────────────────────────────────────────────────────────────────────────────────╮
-│                                                                                                  │
-│ Usage limit reached for gemini-2.5-pro.                                                          │
-│ /stats model for usage details                                                                   │
-│ /model to switch models.                                                                         │
-│ /auth to switch to API key.                                                                      │
-│                                                                                                  │
-│ You have 500 AI Credits available.                                                               │
-│                                                                                                  │
-│ How would you like to proceed?                                                                   │
-│                                                                                                  │
-│                                                                                                  │
-│ ● 1. Use AI Credits - Continue this request (Overage)                                            │
-│   2. Manage - View balance and purchase more credits                                             │
-│   3. Stop - Abort request                                                                        │
-│                                                                                                  │
-│                                                                                                  │
-╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
-"
-`;
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Aishanee Shah	a8d4d944e8	test: update local-executor tests for relative path preference	2026-02-26 20:42:26 +00:00
Aishanee Shah	358ca8092a	revert: documentation changes for path preference	2026-02-26 20:33:17 +00:00
Aishanee Shah	69028570ed	docs: prefer relative paths in tool documentation and system prompt	2026-02-26 20:26:08 +00:00
Aishanee Shah	f593928cd6	feat(tools): prefer relative paths in tool descriptions and interfaces	2026-02-26 20:24:22 +00:00