chore: add removal of function call if response causes 404

Co-authored-by: Bryan Morgan <bryanmorgan@google.com>

.gemini/commands/introspect.toml

@@ -0,0 +1,16 @@
+description = "Analyze the influence of system instructions on a specific action."
+prompt = """
+# Introspection Task
+
+Take a step back and analyze your own system instructions and internal logic.
+The user is curious about the reasoning behind a specific action or decision you've made.
+
+**Specific point of interest:** {{args}}
+
+Please provide a detailed breakdown of:
+1.  Which parts of your system instructions (global, workspace-specific, or provided via GEMINI.md) influenced this behavior?
+2.  What was your internal thought process leading up to this action?
+3.  Are there any ambiguities or conflicting instructions that played a role?
+
+Your goal is to provide transparency into your underlying logic so the user can potentially improve the instructions in the future.
+"""

.gemini/settings.json

@@ -0,0 +1,5 @@
+{
+  "experimental": {
+    "skills": true
+  }
+}

.gemini/skills/pr-creator/SKILL.md

@@ -0,0 +1,57 @@
+---
+name: pr-creator
+description:
+  Use this skill when asked to create a pull request (PR). It ensures all PRs
+  follow the repository's established templates and standards.
+---
+
+# Pull Request Creator
+
+This skill guides the creation of high-quality Pull Requests that adhere to the
+repository's standards.
+
+## Workflow
+
+Follow these steps to create a Pull Request:
+
+1.  **Locate Template**: Search for a pull request template in the repository.
+    - Check `.github/pull_request_template.md`
+    - Check `.github/PULL_REQUEST_TEMPLATE.md`
+    - If multiple templates exist (e.g., in `.github/PULL_REQUEST_TEMPLATE/`),
+      ask the user which one to use or select the most appropriate one based on
+      the context (e.g., `bug_fix.md` vs `feature.md`).
+
+2.  **Read Template**: Read the content of the identified template file.
+
+3.  **Draft Description**: Create a PR description that strictly follows the
+    template's structure.
+    - **Headings**: Keep all headings from the template.
+    - **Checklists**: Review each item. Mark with `[x]` if completed. If an item
+      is not applicable, leave it unchecked or mark as `[ ]` (depending on the
+      template's instructions) or remove it if the template allows flexibility
+      (but prefer keeping it unchecked for transparency).
+    - **Content**: Fill in the sections with clear, concise summaries of your
+      changes.
+    - **Related Issues**: Link any issues fixed or related to this PR (e.g.,
+      "Fixes #123").
+
+4.  **Create PR**: Use the `gh` CLI to create the PR. To avoid shell escaping
+    issues with multi-line Markdown, write the description to a temporary file
+    first.
+    ```bash
+    # 1. Write the drafted description to a temporary file
+    # 2. Create the PR using the --body-file flag
+    gh pr create --title "type(scope): succinct description" --body-file <temp_file_path>
+    # 3. Remove the temporary file
+    rm <temp_file_path>
+    ```
+    - **Title**: Ensure the title follows the
+      [Conventional Commits](https://www.conventionalcommits.org/) format if the
+      repository uses it (e.g., `feat(ui): add new button`,
+      `fix(core): resolve crash`).
+
+## Principles
+
+- **Compliance**: Never ignore the PR template. It exists for a reason.
+- **Completeness**: Fill out all relevant sections.
+- **Accuracy**: Don't check boxes for tasks you haven't done.

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -1,7 +1,5 @@
 name: 'Bug Report'
 description: 'Report a bug to help us improve Gemini CLI'
-labels:
-  - 'status/need-triage'
 body:
   - type: 'markdown'
     attributes:

.github/dependabot.yml

@@ -1,35 +1,33 @@
-# See https://docs.github.com/en/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
 version: 2
 updates:
   - package-ecosystem: 'npm'
     directory: '/'
     schedule:
-      interval: 'daily'
-    target-branch: 'main'
-    commit-message:
-      prefix: 'chore(deps)'
-      include: 'scope'
+      interval: 'weekly'
+      day: 'monday'
+    open-pull-requests-limit: 10
     reviewers:
-      - 'google-gemini/gemini-cli-askmode-approvers'
+      - 'joshualitt'
     groups:
-      # Group all non-major updates together.
-      # This is to reduce the number of PRs that need to be reviewed.
-      # Major updates will still be created as separate PRs.
-      npm-minor-patch:
-        applies-to: 'version-updates'
+      npm-dependencies:
+        patterns:
+          - '*'
         update-types:
           - 'minor'
           - 'patch'
-    open-pull-requests-limit: 0
 
   - package-ecosystem: 'github-actions'
     directory: '/'
     schedule:
-      interval: 'daily'
-    target-branch: 'main'
-    commit-message:
-      prefix: 'chore(deps)'
-      include: 'scope'
+      interval: 'weekly'
+      day: 'monday'
+    open-pull-requests-limit: 10
     reviewers:
-      - 'google-gemini/gemini-cli-askmode-approvers'
-    open-pull-requests-limit: 0
+      - 'joshualitt'
+    groups:
+      actions-dependencies:
+        patterns:
+          - '*'
+        update-types:
+          - 'minor'
+          - 'patch'

.github/scripts/backfill-need-triage.cjs

@@ -0,0 +1,138 @@
+/* eslint-disable */
+/* global require, console, process */
+
+/**
+ * Script to backfill the 'status/need-triage' label to all open issues
+ * that are NOT currently labeled with '🔒 maintainer only' or 'help wanted'.
+ */
+
+const { execFileSync } = require('child_process');
+
+const isDryRun = process.argv.includes('--dry-run');
+const REPO = 'google-gemini/gemini-cli';
+
+/**
+ * Executes a GitHub CLI command safely using an argument array to prevent command injection.
+ * @param {string[]} args
+ * @returns {string|null}
+ */
+function runGh(args) {
+  try {
+    // Using execFileSync with an array of arguments is safe as it doesn't use a shell.
+    // We set a large maxBuffer (10MB) to handle repositories with many issues.
+    return execFileSync('gh', args, {
+      encoding: 'utf8',
+      maxBuffer: 10 * 1024 * 1024,
+      stdio: ['ignore', 'pipe', 'pipe'],
+    }).trim();
+  } catch (error) {
+    const stderr = error.stderr ? ` Stderr: ${error.stderr.trim()}` : '';
+    console.error(
+      `❌ Error running gh ${args.join(' ')}: ${error.message}${stderr}`,
+    );
+    return null;
+  }
+}
+
+async function main() {
+  console.log('🔐 GitHub CLI security check...');
+  const authStatus = runGh(['auth', 'status']);
+  if (authStatus === null) {
+    console.error('❌ GitHub CLI (gh) is not installed or not authenticated.');
+    process.exit(1);
+  }
+
+  if (isDryRun) {
+    console.log('🧪 DRY RUN MODE ENABLED - No changes will be made.\n');
+  }
+
+  console.log(`🔍 Fetching and filtering open issues from ${REPO}...`);
+
+  // We use the /issues endpoint with pagination to bypass the 1000-result limit.
+  // The jq filter ensures we exclude PRs, maintainer-only, help-wanted, and existing status/need-triage.
+  const jqFilter =
+    '.[] | select(.pull_request == null) | select([.labels[].name] as $l | (any($l[]; . == "🔒 maintainer only") | not) and (any($l[]; . == "help wanted") | not) and (any($l[]; . == "status/need-triage") | not)) | {number: .number, title: .title}';
+
+  const output = runGh([
+    'api',
+    `repos/${REPO}/issues?state=open&per_page=100`,
+    '--paginate',
+    '--jq',
+    jqFilter,
+  ]);
+
+  if (output === null) {
+    process.exit(1);
+  }
+
+  const issues = output
+    .split('\n')
+    .filter((line) => line.trim())
+    .map((line) => {
+      try {
+        return JSON.parse(line);
+      } catch (_e) {
+        console.error(`⚠️ Failed to parse line: ${line}`);
+        return null;
+      }
+    })
+    .filter(Boolean);
+
+  console.log(`✅ Found ${issues.length} issues matching criteria.`);
+
+  if (issues.length === 0) {
+    console.log('✨ No issues need backfilling.');
+    return;
+  }
+
+  let successCount = 0;
+  let failCount = 0;
+
+  if (isDryRun) {
+    for (const issue of issues) {
+      console.log(
+        `[DRY RUN] Would label issue #${issue.number}: ${issue.title}`,
+      );
+    }
+    successCount = issues.length;
+  } else {
+    console.log(`🏷️  Applying labels to ${issues.length} issues...`);
+
+    for (const issue of issues) {
+      const issueNumber = String(issue.number);
+      console.log(`🏷️  Labeling issue #${issueNumber}: ${issue.title}`);
+
+      const result = runGh([
+        'issue',
+        'edit',
+        issueNumber,
+        '--add-label',
+        'status/need-triage',
+        '--repo',
+        REPO,
+      ]);
+
+      if (result !== null) {
+        successCount++;
+      } else {
+        failCount++;
+      }
+    }
+  }
+
+  console.log(`\n📊 Summary:`);
+  console.log(`   - Success: ${successCount}`);
+  console.log(`   - Failed:  ${failCount}`);
+
+  if (failCount > 0) {
+    console.error(`\n❌ Backfill completed with ${failCount} errors.`);
+    process.exit(1);
+  } else {
+    console.log(`\n🎉 ${isDryRun ? 'Dry run' : 'Backfill'} complete!`);
+  }
+}
+
+main().catch((error) => {
+  console.error('❌ Unexpected error:', error);
+  process.exit(1);
+});

.github/scripts/backfill-pr-notification.cjs

@@ -0,0 +1,190 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+/* eslint-disable */
+/* global require, console, process */
+
+/**
+ * Script to backfill a process change notification comment to all open PRs
+ * not created by members of the 'gemini-cli-maintainers' team.
+ *
+ * Skip PRs that are already associated with an issue.
+ */
+
+const { execFileSync } = require('child_process');
+
+const isDryRun = process.argv.includes('--dry-run');
+const REPO = 'google-gemini/gemini-cli';
+const ORG = 'google-gemini';
+const TEAM_SLUG = 'gemini-cli-maintainers';
+const DISCUSSION_URL =
+  'https://github.com/google-gemini/gemini-cli/discussions/16706';
+
+/**
+ * Executes a GitHub CLI command safely using an argument array.
+ */
+function runGh(args, options = {}) {
+  const { silent = false } = options;
+  try {
+    return execFileSync('gh', args, {
+      encoding: 'utf8',
+      maxBuffer: 10 * 1024 * 1024,
+      stdio: ['ignore', 'pipe', 'pipe'],
+    }).trim();
+  } catch (error) {
+    if (!silent) {
+      const stderr = error.stderr ? ` Stderr: ${error.stderr.trim()}` : '';
+      console.error(
+        `❌ Error running gh ${args.join(' ')}: ${error.message}${stderr}`,
+      );
+    }
+    return null;
+  }
+}
+
+/**
+ * Checks if a user is a member of the maintainers team.
+ */
+const membershipCache = new Map();
+function isMaintainer(username) {
+  if (membershipCache.has(username)) return membershipCache.get(username);
+
+  // GitHub returns 404 if user is not a member.
+  // We use silent: true to avoid logging 404s as errors.
+  const result = runGh(
+    ['api', `orgs/${ORG}/teams/${TEAM_SLUG}/memberships/${username}`],
+    { silent: true },
+  );
+
+  const isMember = result !== null;
+  membershipCache.set(username, isMember);
+  return isMember;
+}
+
+async function main() {
+  console.log('🔐 GitHub CLI security check...');
+  if (runGh(['auth', 'status']) === null) {
+    console.error('❌ GitHub CLI (gh) is not authenticated.');
+    process.exit(1);
+  }
+
+  if (isDryRun) {
+    console.log('🧪 DRY RUN MODE ENABLED\n');
+  }
+
+  console.log(`📥 Fetching open PRs from ${REPO}...`);
+  // Fetch number, author, and closingIssuesReferences to check if linked to an issue
+  const prsJson = runGh([
+    'pr',
+    'list',
+    '--repo',
+    REPO,
+    '--state',
+    'open',
+    '--limit',
+    '1000',
+    '--json',
+    'number,author,closingIssuesReferences',
+  ]);
+
+  if (prsJson === null) process.exit(1);
+  const prs = JSON.parse(prsJson);
+
+  console.log(`📊 Found ${prs.length} open PRs. Filtering...`);
+
+  let targetPrs = [];
+  for (const pr of prs) {
+    const author = pr.author.login;
+    const issueCount = pr.closingIssuesReferences
+      ? pr.closingIssuesReferences.length
+      : 0;
+
+    if (issueCount > 0) {
+      // Skip if already linked to an issue
+      continue;
+    }
+
+    if (!isMaintainer(author)) {
+      targetPrs.push(pr);
+    }
+  }
+
+  console.log(
+    `✅ Found ${targetPrs.length} PRs from non-maintainers without associated issues.`,
+  );
+
+  const commentBody =
+    "\nHi @{AUTHOR}, thank you so much for your contribution to Gemini CLI! We really appreciate the time and effort you've put into this.\n\nWe're making some updates to our contribution process to improve how we track and review changes. Please take a moment to review our recent discussion post: [Improving Our Contribution Process & Introducing New Guidelines](${DISCUSSION_URL}).\n\nKey Update: Starting **January 26, 2026**, the Gemini CLI project will require all pull requests to be associated with an existing issue. Any pull requests not linked to an issue by that date will be automatically closed.\n\nThank you for your understanding and for being a part of our community!\n  ".trim();
+
+  let successCount = 0;
+  let skipCount = 0;
+  let failCount = 0;
+
+  for (const pr of targetPrs) {
+    const prNumber = String(pr.number);
+    const author = pr.author.login;
+
+    // Check if we already commented (idempotency)
+    // We use silent: true here because view might fail if PR is deleted mid-run
+    const existingComments = runGh(
+      [
+        'pr',
+        'view',
+        prNumber,
+        '--repo',
+        REPO,
+        '--json',
+        'comments',
+        '--jq',
+        `.comments[].body | contains("${DISCUSSION_URL}")`,
+      ],
+      { silent: true },
+    );
+
+    if (existingComments && existingComments.includes('true')) {
+      console.log(
+        `⏭️  PR #${prNumber} already has the notification. Skipping.`,
+      );
+      skipCount++;
+      continue;
+    }
+
+    if (isDryRun) {
+      console.log(`[DRY RUN] Would notify @${author} on PR #${prNumber}`);
+      successCount++;
+    } else {
+      console.log(`💬 Notifying @${author} on PR #${prNumber}...`);
+      const personalizedComment = commentBody.replace('{AUTHOR}', author);
+      const result = runGh([
+        'pr',
+        'comment',
+        prNumber,
+        '--repo',
+        REPO,
+        '--body',
+        personalizedComment,
+      ]);
+
+      if (result !== null) {
+        successCount++;
+      } else {
+        failCount++;
+      }
+    }
+  }
+
+  console.log(`\n📊 Summary:`);
+  console.log(`   - Notified: ${successCount}`);
+  console.log(`   - Skipped:  ${skipCount}`);
+  console.log(`   - Failed:   ${failCount}`);
+
+  if (failCount > 0) process.exit(1);
+}
+
+main().catch((e) => {
+  console.error(e);
+  process.exit(1);
+});

.github/scripts/pr-triage.sh

@@ -1,162 +1,180 @@
 #!/usr/bin/env bash
+# @license
+# Copyright 2026 Google LLC
+# SPDX-License-Identifier: Apache-2.0
+
 set -euo pipefail
 
 # Initialize a comma-separated string to hold PR numbers that need a comment
 PRS_NEEDING_COMMENT=""
 
-# Function to process a single PR
-process_pr() {
-    if [[ -z "${GITHUB_REPOSITORY:-}" ]]; then
-        echo "‼️ Missing \$GITHUB_REPOSITORY - this must be run from GitHub Actions"
-        return 1
+# Global cache for issue labels (compatible with Bash 3.2)
+# Stores "ISSUE_NUM:LABELS" pairs separated by spaces
+ISSUE_LABELS_CACHE_FLAT=""
+
+# Function to get area and priority labels from an issue (with caching)
+get_issue_labels() {
+    local ISSUE_NUM="${1}"
+    if [[ -z "${ISSUE_NUM}" || "${ISSUE_NUM}" == "null" || "${ISSUE_NUM}" == "" ]]; then
+        return
     fi
 
-    if [[ -z "${GITHUB_OUTPUT:-}" ]]; then
-        echo "‼️ Missing \$GITHUB_OUTPUT - this must be run from GitHub Actions"
-        return 1
+    # Check cache
+    case " ${ISSUE_LABELS_CACHE_FLAT} " in
+        *" ${ISSUE_NUM}:"*) 
+            local suffix="${ISSUE_LABELS_CACHE_FLAT#* " ${ISSUE_NUM}:"}"
+            echo "${suffix%% *}"
+            return
+            ;; 
+        *)
+            # Cache miss, proceed to fetch
+            ;;
+    esac
+
+    echo "   📥 Fetching area and priority labels from issue #${ISSUE_NUM}" >&2
+    local gh_output
+    if ! gh_output=$(gh issue view "${ISSUE_NUM}" --repo "${GITHUB_REPOSITORY}" --json labels -q '.labels[].name' 2>/dev/null); then
+        echo "      ⚠️ Could not fetch issue #${ISSUE_NUM}" >&2
+        ISSUE_LABELS_CACHE_FLAT="${ISSUE_LABELS_CACHE_FLAT} ${ISSUE_NUM}:"
+        return
     fi
 
-    local PR_NUMBER=$1
+    local labels
+    labels=$(echo "${gh_output}" | grep -E '^(area|priority)/' | tr '\n' ',' | sed 's/,$//' || echo "")
+    
+    # Save to flat cache
+    ISSUE_LABELS_CACHE_FLAT="${ISSUE_LABELS_CACHE_FLAT} ${ISSUE_NUM}:${labels}"
+    echo "${labels}"
+}
+
+# Function to process a single PR with pre-fetched data
+process_pr_optimized() {
+    local PR_NUMBER="${1}"
+    local IS_DRAFT="${2}"
+    local ISSUE_NUMBER="${3}"
+    local CURRENT_LABELS="${4}" # Comma-separated labels
+
     echo "🔄 Processing PR #${PR_NUMBER}"
 
-    # Get PR details: closing issue, draft status, body and labels
-    local PR_DATA
-    if ! PR_DATA=$(gh pr view "${PR_NUMBER}" --repo "${GITHUB_REPOSITORY}" --json closingIssuesReferences,isDraft,body,labels 2>/dev/null); then
-        echo "   ⚠️ Could not fetch data for PR #${PR_NUMBER}"
-        return 0
-    fi
+    local LABELS_TO_ADD=""
+    local LABELS_TO_REMOVE=""
 
-    local ISSUE_NUMBER
-    ISSUE_NUMBER=$(echo "${PR_DATA}" | jq -r '.closingIssuesReferences[0].number // empty')
-
-    # If no closing issue found, check body for references (e.g. #123)
-    if [[ -z "${ISSUE_NUMBER}" ]]; then
-        local REFERENCED_ISSUE
-        # Search for # followed by digits, not preceded by alphanumeric chars
-        REFERENCED_ISSUE=$(echo "${PR_DATA}" | jq -r '.body // empty' | grep -oE '(^|[^a-zA-Z0-9])#[0-9]+([^a-zA-Z0-9]|$)' | head -n 1 | grep -oE '[0-9]+' || echo "")
-        if [[ -n "${REFERENCED_ISSUE}" ]]; then
-            ISSUE_NUMBER="${REFERENCED_ISSUE}"
-            echo "🔗 Found referenced issue #${ISSUE_NUMBER} in PR body"
-        fi
-    fi
-
-    local IS_DRAFT
-    IS_DRAFT=$(echo "${PR_DATA}" | jq -r '.isDraft')
-
-    if [[ -z "${ISSUE_NUMBER}" ]]; then
+    if [[ -z "${ISSUE_NUMBER}" || "${ISSUE_NUMBER}" == "null" || "${ISSUE_NUMBER}" == "" ]]; then
         if [[ "${IS_DRAFT}" == "true" ]]; then
-            echo "📝 PR #${PR_NUMBER} is a draft and has no linked issue, skipping status/need-issue label"
-            # Remove status/need-issue label if it was previously added
-            if ! gh pr edit "${PR_NUMBER}" --repo "${GITHUB_REPOSITORY}" --remove-label "status/need-issue" 2>/dev/null; then
-                echo "   status/need-issue label not present or could not be removed"
+            echo "   📝 PR #${PR_NUMBER} is a draft and has no linked issue"
+            if [[ ",${CURRENT_LABELS}," == *",status/need-issue,"* ]]; then
+                echo "      ➖ Removing status/need-issue label"
+                LABELS_TO_REMOVE="status/need-issue"
             fi
-            echo "needs_comment=false" >> "${GITHUB_OUTPUT}"
         else
-            echo "⚠️  No linked issue found for PR #${PR_NUMBER}, adding status/need-issue label"
-            if ! gh pr edit "${PR_NUMBER}" --repo "${GITHUB_REPOSITORY}" --add-label "status/need-issue" 2>/dev/null; then
-                echo "   ⚠️ Failed to add label (may already exist or have permission issues)"
+            echo "   ⚠️  No linked issue found for PR #${PR_NUMBER}"
+            if [[ ",${CURRENT_LABELS}," != *",status/need-issue,"* ]]; then
+                echo "      ➕ Adding status/need-issue label"
+                LABELS_TO_ADD="status/need-issue"
             fi
-            # Add PR number to the list
+            
             if [[ -z "${PRS_NEEDING_COMMENT}" ]]; then
                 PRS_NEEDING_COMMENT="${PR_NUMBER}"
             else
                 PRS_NEEDING_COMMENT="${PRS_NEEDING_COMMENT},${PR_NUMBER}"
             fi
-            echo "needs_comment=true" >> "${GITHUB_OUTPUT}"
         fi
     else
-        echo "🔗 Found linked issue #${ISSUE_NUMBER}"
+        echo "   🔗 Found linked issue #${ISSUE_NUMBER}"
 
-        # Remove status/need-issue label if present
-        if ! gh pr edit "${PR_NUMBER}" --repo "${GITHUB_REPOSITORY}" --remove-label "status/need-issue" 2>/dev/null; then
-            echo "   status/need-issue label not present or could not be removed"
+        if [[ ",${CURRENT_LABELS}," == *",status/need-issue,"* ]]; then
+            echo "      ➖ Removing status/need-issue label"
+            LABELS_TO_REMOVE="status/need-issue"
         fi
 
-        # Get issue labels
-        echo "📥 Fetching area and priority labels from issue #${ISSUE_NUMBER}"
-        local ISSUE_LABELS=""
-        local gh_output
-        if ! gh_output=$(gh issue view "${ISSUE_NUMBER}" --repo "${GITHUB_REPOSITORY}" --json labels -q '.labels[].name' 2>/dev/null); then
-            echo "   ⚠️ Could not fetch issue #${ISSUE_NUMBER} (may not exist or be in different repo)"
-            ISSUE_LABELS=""
-        else
-            # If grep finds no matches, it exits with 1, which pipefail would treat as an error.
-            # `|| echo ""` ensures the command succeeds with an empty string in that case.
-            ISSUE_LABELS=$(echo "${gh_output}" | grep -E "^(area|priority)/" | tr '\n' ',' | sed 's/,$//' || echo "")
-        fi
+        local ISSUE_LABELS
+        ISSUE_LABELS=$(get_issue_labels "${ISSUE_NUMBER}")
 
-        # Get PR labels from already fetched PR_DATA
-        echo "📥 Extracting labels from PR #${PR_NUMBER}"
-        local PR_LABELS=""
-        PR_LABELS=$(echo "${PR_DATA}" | jq -r '.labels[].name // empty' | tr '\n' ',' | sed 's/,$//' || echo "")
-
-        echo "   Issue labels (area/priority): ${ISSUE_LABELS}"
-        echo "   PR labels: ${PR_LABELS}"
-
-        # Convert comma-separated strings to arrays
-        local ISSUE_LABEL_ARRAY PR_LABEL_ARRAY
-        IFS=',' read -ra ISSUE_LABEL_ARRAY <<< "${ISSUE_LABELS}"
-        IFS=',' read -ra PR_LABEL_ARRAY <<< "${PR_LABELS:-}"
-
-        # Find labels to add (on issue but not on PR)
-        local LABELS_TO_ADD=""
-        for label in "${ISSUE_LABEL_ARRAY[@]}"; do
-            if [[ -n "${label}" ]] && [[ " ${PR_LABEL_ARRAY[*]:-}" != *" ${label} "* ]]; then
-                if [[ -z "${LABELS_TO_ADD}" ]]; then
-                    LABELS_TO_ADD="${label}"
-                else
-                    LABELS_TO_ADD="${LABELS_TO_ADD},${label}"
+        if [[ -n "${ISSUE_LABELS}" ]]; then
+            local IFS_OLD="${IFS}"
+            IFS=','
+            for label in ${ISSUE_LABELS}; do
+                if [[ -n "${label}" ]] && [[ ",${CURRENT_LABELS}," != *",${label},"* ]]; then
+                    if [[ -z "${LABELS_TO_ADD}" ]]; then
+                        LABELS_TO_ADD="${label}"
+                    else
+                        LABELS_TO_ADD="${LABELS_TO_ADD},${label}"
+                    fi
                 fi
-            fi
-        done
+done
+            IFS="${IFS_OLD}"
+        fi
 
-        # Apply label changes
+        if [[ -z "${LABELS_TO_ADD}" && -z "${LABELS_TO_REMOVE}" ]]; then
+            echo "   ✅ Labels already synchronized"
+        fi
+    fi
+
+    if [[ -n "${LABELS_TO_ADD}" || -n "${LABELS_TO_REMOVE}" ]]; then
+        local EDIT_CMD=("gh" "pr" "edit" "${PR_NUMBER}" "--repo" "${GITHUB_REPOSITORY}")
         if [[ -n "${LABELS_TO_ADD}" ]]; then
-            echo "➕ Adding labels: ${LABELS_TO_ADD}"
-            if ! gh pr edit "${PR_NUMBER}" --repo "${GITHUB_REPOSITORY}" --add-label "${LABELS_TO_ADD}" 2>/dev/null; then
-                echo "   ⚠️ Failed to add some labels"
-            fi
+            echo "      ➕ Syncing labels to add: ${LABELS_TO_ADD}"
+            EDIT_CMD+=("--add-label" "${LABELS_TO_ADD}")
         fi
-
-        if [[ -z "${LABELS_TO_ADD}" ]]; then
-            echo "✅ Labels already synchronized"
+        if [[ -n "${LABELS_TO_REMOVE}" ]]; then
+            echo "      ➖ Syncing labels to remove: ${LABELS_TO_REMOVE}"
+            EDIT_CMD+=("--remove-label" "${LABELS_TO_REMOVE}")
         fi
-        echo "needs_comment=false" >> "${GITHUB_OUTPUT}"
+        
+        ("${EDIT_CMD[@]}" 2>/dev/null || true)
     fi
 }
 
-# If PR_NUMBER is set, process only that PR
-if [[ -n "${PR_NUMBER:-}" ]]; then
-    if ! process_pr "${PR_NUMBER}"; then
-        echo "❌ Failed to process PR #${PR_NUMBER}"
-        exit 1
-    fi
-else
-    # Otherwise, get all open PRs and process them
-    # The script logic will determine which ones need issue linking or label sync
-    echo "📥 Getting all open pull requests..."
-    if ! PR_NUMBERS=$(gh pr list --repo "${GITHUB_REPOSITORY}" --state open --limit 1000 --json number -q '.[].number' 2>/dev/null); then
-        echo "❌ Failed to fetch PR list"
-        exit 1
-    fi
-
-    if [[ -z "${PR_NUMBERS}" ]]; then
-        echo "✅ No open PRs found"
-    else
-        # Count the number of PRs
-        PR_COUNT=$(echo "${PR_NUMBERS}" | wc -w | tr -d ' ')
-        echo "📊 Found ${PR_COUNT} open PRs to process"
-
-        for pr_number in ${PR_NUMBERS}; do
-            if ! process_pr "${pr_number}"; then
-                echo "⚠️ Failed to process PR #${pr_number}, continuing with next PR..."
-                continue
-            fi
-        done
-    fi
+if [[ -z "${GITHUB_REPOSITORY:-}" ]]; then
+    echo "‼️ Missing \$GITHUB_REPOSITORY - this must be run from GitHub Actions"
+    exit 1
+fi
+
+if [[ -z "${GITHUB_OUTPUT:-}" ]]; then
+    echo "‼️ Missing \$GITHUB_OUTPUT - this must be run from GitHub Actions"
+    exit 1
+fi
+
+JQ_EXTRACT_FIELDS='{
+    number: .number,
+    isDraft: .isDraft,
+    issue: (.closingIssuesReferences[0].number // (.body // "" | capture("(^|[^a-zA-Z0-9])#(?<num>[0-9]+)([^a-zA-Z0-9]|$)")? | .num) // "null"),
+    labels: [.labels[].name] | join(",")
+}'
+
+JQ_TSV_FORMAT='"\((.number | tostring))\t\(.isDraft)\t\((.issue // null) | tostring)\t\(.labels)"'
+
+if [[ -n "${PR_NUMBER:-}" ]]; then
+    echo "🔄 Processing single PR #${PR_NUMBER}"
+    PR_DATA=$(gh pr view "${PR_NUMBER}" --repo "${GITHUB_REPOSITORY}" --json number,closingIssuesReferences,isDraft,body,labels 2>/dev/null) || {
+        echo "❌ Failed to fetch data for PR #${PR_NUMBER}"
+        exit 1
+    }
+    
+    line=$(echo "${PR_DATA}" | jq -r "${JQ_EXTRACT_FIELDS} | ${JQ_TSV_FORMAT}")
+    IFS=$'\t' read -r pr_num is_draft issue_num current_labels <<< "${line}"
+    process_pr_optimized "${pr_num}" "${is_draft}" "${issue_num}" "${current_labels}"
+else
+    echo "📥 Getting all open pull requests..."
+    PR_DATA_ALL=$(gh pr list --repo "${GITHUB_REPOSITORY}" --state open --limit 1000 --json number,closingIssuesReferences,isDraft,body,labels 2>/dev/null) || {
+        echo "❌ Failed to fetch PR list"
+        exit 1
+    }
+
+    PR_COUNT=$(echo "${PR_DATA_ALL}" | jq '. | length')
+    echo "📊 Found ${PR_COUNT} open PRs to process"
+
+    # Use a temporary file to avoid masking exit codes in process substitution
+    tmp_file=$(mktemp)
+    echo "${PR_DATA_ALL}" | jq -r ".[] | ${JQ_EXTRACT_FIELDS} | ${JQ_TSV_FORMAT}" > "${tmp_file}"
+    while read -r line; do
+        [[ -z "${line}" ]] && continue
+        IFS=$'\t' read -r pr_num is_draft issue_num current_labels <<< "${line}"
+        process_pr_optimized "${pr_num}" "${is_draft}" "${issue_num}" "${current_labels}"
+    done < "${tmp_file}"
+    rm -f "${tmp_file}"
 fi
 
-# Ensure output is always set, even if empty
 if [[ -z "${PRS_NEEDING_COMMENT}" ]]; then
     echo "prs_needing_comment=[]" >> "${GITHUB_OUTPUT}"
 else

.github/scripts/sync-maintainer-labels.cjs

@@ -0,0 +1,355 @@
+/* eslint-disable @typescript-eslint/no-require-imports */
+/* global process, console, require */
+const { Octokit } = require('@octokit/rest');
+
+/**
+ * Sync Maintainer Labels (Recursive with strict parent-child relationship detection)
+ * - Uses Native Sub-issues.
+ * - Uses Markdown Task Lists (- [ ] #123).
+ * - Filters for OPEN issues only.
+ * - Skips DUPLICATES.
+ * - Skips Pull Requests.
+ * - ONLY labels issues in the PUBLIC (gemini-cli) repo.
+ */
+
+const REPO_OWNER = 'google-gemini';
+const PUBLIC_REPO = 'gemini-cli';
+const PRIVATE_REPO = 'maintainers-gemini-cli';
+const ALLOWED_REPOS = [PUBLIC_REPO, PRIVATE_REPO];
+
+const ROOT_ISSUES = [
+  { owner: REPO_OWNER, repo: PUBLIC_REPO, number: 15374 },
+  { owner: REPO_OWNER, repo: PUBLIC_REPO, number: 15456 },
+  { owner: REPO_OWNER, repo: PUBLIC_REPO, number: 15324 },
+];
+
+const TARGET_LABEL = '🔒 maintainer only';
+const isDryRun =
+  process.argv.includes('--dry-run') || process.env.DRY_RUN === 'true';
+
+const octokit = new Octokit({
+  auth: process.env.GITHUB_TOKEN,
+});
+
+/**
+ * Extracts child issue references from markdown Task Lists ONLY.
+ * e.g. - [ ] #123 or - [x] google-gemini/gemini-cli#123
+ */
+function extractTaskListLinks(text, contextOwner, contextRepo) {
+  if (!text) return [];
+  const childIssues = new Map();
+
+  const add = (owner, repo, number) => {
+    if (ALLOWED_REPOS.includes(repo)) {
+      const key = `${owner}/${repo}#${number}`;
+      childIssues.set(key, { owner, repo, number: parseInt(number, 10) });
+    }
+  };
+
+  // 1. Full URLs in task lists
+  const urlRegex =
+    /-\s+\[[ x]\].*https:\/\/github\.com\/([a-zA-Z0-9._-]+)\/([a-zA-Z0-9._-]+)\/issues\/(\d+)\b/g;
+  let match;
+  while ((match = urlRegex.exec(text)) !== null) {
+    add(match[1], match[2], match[3]);
+  }
+
+  // 2. Cross-repo refs in task lists: owner/repo#123
+  const crossRepoRegex =
+    /-\s+\[[ x]\].*([a-zA-Z0-9._-]+)\/([a-zA-Z0-9._-]+)#(\d+)\b/g;
+  while ((match = crossRepoRegex.exec(text)) !== null) {
+    add(match[1], match[2], match[3]);
+  }
+
+  // 3. Short refs in task lists: #123
+  const shortRefRegex = /-\s+\[[ x]\].*#(\d+)\b/g;
+  while ((match = shortRefRegex.exec(text)) !== null) {
+    add(contextOwner, contextRepo, match[1]);
+  }
+
+  return Array.from(childIssues.values());
+}
+
+/**
+ * Fetches issue data via GraphQL with full pagination for sub-issues, comments, and labels.
+ */
+async function fetchIssueData(owner, repo, number) {
+  const query = `
+    query($owner:String!, $repo:String!, $number:Int!) {
+      repository(owner:$owner, name:$repo) {
+        issue(number:$number) {
+          state
+          title
+          body
+          labels(first: 100) {
+            nodes { name }
+            pageInfo { hasNextPage endCursor }
+          }
+          subIssues(first: 100) {
+            nodes {
+              number
+              repository {
+                name
+                owner { login }
+              }
+            }
+            pageInfo { hasNextPage endCursor }
+          }
+          comments(first: 100) {
+            nodes {
+              body
+            }
+          }
+        }
+      }
+    }
+  `;
+
+  try {
+    const response = await octokit.graphql(query, { owner, repo, number });
+    const data = response.repository.issue;
+    if (!data) return null;
+
+    const issue = {
+      state: data.state,
+      title: data.title,
+      body: data.body || '',
+      labels: data.labels.nodes.map((n) => n.name),
+      subIssues: [...data.subIssues.nodes],
+      comments: data.comments.nodes.map((n) => n.body),
+    };
+
+    // Paginate subIssues if there are more than 100
+    if (data.subIssues.pageInfo.hasNextPage) {
+      const moreSubIssues = await paginateConnection(
+        owner,
+        repo,
+        number,
+        'subIssues',
+        'number repository { name owner { login } }',
+        data.subIssues.pageInfo.endCursor,
+      );
+      issue.subIssues.push(...moreSubIssues);
+    }
+
+    // Paginate labels if there are more than 100 (unlikely but for completeness)
+    if (data.labels.pageInfo.hasNextPage) {
+      const moreLabels = await paginateConnection(
+        owner,
+        repo,
+        number,
+        'labels',
+        'name',
+        data.labels.pageInfo.endCursor,
+        (n) => n.name,
+      );
+      issue.labels.push(...moreLabels);
+    }
+
+    // Note: Comments are handled via Task Lists in body + first 100 comments.
+    // If an issue has > 100 comments with task lists, we'd need to paginate those too.
+    // Given the 1,100+ issue discovery count, 100 comments is usually sufficient,
+    // but we can add it for absolute completeness.
+    // (Skipping for now to avoid excessive API churn unless clearly needed).
+
+    return issue;
+  } catch (error) {
+    if (error.errors && error.errors.some((e) => e.type === 'NOT_FOUND')) {
+      return null;
+    }
+    throw error;
+  }
+}
+
+/**
+ * Helper to paginate any GraphQL connection.
+ */
+async function paginateConnection(
+  owner,
+  repo,
+  number,
+  connectionName,
+  nodeFields,
+  initialCursor,
+  transformNode = (n) => n,
+) {
+  let additionalNodes = [];
+  let hasNext = true;
+  let cursor = initialCursor;
+
+  while (hasNext) {
+    const query = `
+      query($owner:String!, $repo:String!, $number:Int!, $cursor:String) {
+        repository(owner:$owner, name:$repo) {
+          issue(number:$number) {
+            ${connectionName}(first: 100, after: $cursor) {
+              nodes { ${nodeFields} }
+              pageInfo { hasNextPage endCursor }
+            }
+          }
+        }
+      }
+    `;
+    const response = await octokit.graphql(query, {
+      owner,
+      repo,
+      number,
+      cursor,
+    });
+    const connection = response.repository.issue[connectionName];
+    additionalNodes.push(...connection.nodes.map(transformNode));
+    hasNext = connection.pageInfo.hasNextPage;
+    cursor = connection.pageInfo.endCursor;
+  }
+  return additionalNodes;
+}
+
+/**
+ * Validates if an issue should be processed (Open, not a duplicate, not a PR)
+ */
+function shouldProcess(issueData) {
+  if (!issueData) return false;
+
+  if (issueData.state !== 'OPEN') return false;
+
+  const labels = issueData.labels.map((l) => l.toLowerCase());
+  if (labels.includes('duplicate') || labels.includes('kind/duplicate')) {
+    return false;
+  }
+
+  return true;
+}
+
+async function getAllDescendants(roots) {
+  const allDescendants = new Map();
+  const visited = new Set();
+  const queue = [...roots];
+
+  for (const root of roots) {
+    visited.add(`${root.owner}/${root.repo}#${root.number}`);
+  }
+
+  console.log(`Starting discovery from ${roots.length} roots...`);
+
+  while (queue.length > 0) {
+    const current = queue.shift();
+    const currentKey = `${current.owner}/${current.repo}#${current.number}`;
+
+    try {
+      const issueData = await fetchIssueData(
+        current.owner,
+        current.repo,
+        current.number,
+      );
+
+      if (!shouldProcess(issueData)) {
+        continue;
+      }
+
+      // ONLY add to labeling list if it's in the PUBLIC repository
+      if (current.repo === PUBLIC_REPO) {
+        // Don't label the roots themselves
+        if (
+          !ROOT_ISSUES.some(
+            (r) => r.number === current.number && r.repo === current.repo,
+          )
+        ) {
+          allDescendants.set(currentKey, {
+            ...current,
+            title: issueData.title,
+            labels: issueData.labels,
+          });
+        }
+      }
+
+      const children = new Map();
+
+      // 1. Process Native Sub-issues
+      if (issueData.subIssues) {
+        for (const node of issueData.subIssues) {
+          const childOwner = node.repository.owner.login;
+          const childRepo = node.repository.name;
+          const childNumber = node.number;
+          const key = `${childOwner}/${childRepo}#${childNumber}`;
+          children.set(key, {
+            owner: childOwner,
+            repo: childRepo,
+            number: childNumber,
+          });
+        }
+      }
+
+      // 2. Process Markdown Task Lists in Body and Comments
+      let combinedText = issueData.body || '';
+      if (issueData.comments) {
+        for (const commentBody of issueData.comments) {
+          combinedText += '\n' + (commentBody || '');
+        }
+      }
+
+      const taskListLinks = extractTaskListLinks(
+        combinedText,
+        current.owner,
+        current.repo,
+      );
+      for (const link of taskListLinks) {
+        const key = `${link.owner}/${link.repo}#${link.number}`;
+        children.set(key, link);
+      }
+
+      // Queue children (regardless of which repo they are in, for recursion)
+      for (const [key, child] of children) {
+        if (!visited.has(key)) {
+          visited.add(key);
+          queue.push(child);
+        }
+      }
+    } catch (error) {
+      console.error(`Error processing ${currentKey}: ${error.message}`);
+    }
+  }
+
+  return Array.from(allDescendants.values());
+}
+
+async function run() {
+  if (isDryRun) {
+    console.log('=== DRY RUN MODE: No labels will be applied ===');
+  }
+
+  const descendants = await getAllDescendants(ROOT_ISSUES);
+  console.log(
+    `\nFound ${descendants.length} total unique open descendant issues in ${PUBLIC_REPO}.`,
+  );
+
+  for (const issueInfo of descendants) {
+    const issueKey = `${issueInfo.owner}/${issueInfo.repo}#${issueInfo.number}`;
+    try {
+      // Data is already available from the discovery phase
+      const hasLabel = issueInfo.labels.some((l) => l === TARGET_LABEL);
+
+      if (!hasLabel) {
+        if (isDryRun) {
+          console.log(
+            `[DRY RUN] Would label ${issueKey}: "${issueInfo.title}"`,
+          );
+        } else {
+          console.log(`Labeling ${issueKey}: "${issueInfo.title}"...`);
+          await octokit.rest.issues.addLabels({
+            owner: issueInfo.owner,
+            repo: issueInfo.repo,
+            issue_number: issueInfo.number,
+            labels: [TARGET_LABEL],
+          });
+        }
+      }
+    } catch (error) {
+      console.error(`Error processing label for ${issueKey}: ${error.message}`);
+    }
+  }
+}
+
+run().catch((error) => {
+  console.error(error);
+  process.exit(1);
+});

.github/workflows/chained_e2e.yml

@@ -277,6 +277,37 @@ jobs:
         shell: 'pwsh'
         run: 'npm run test:integration:sandbox:none'
 
+  evals:
+    name: 'Evals (ALWAYS_PASSING)'
+    needs:
+      - 'merge_queue_skipper'
+      - 'parse_run_context'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    if: |
+      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
+        with:
+          ref: '${{ needs.parse_run_context.outputs.sha }}'
+          repository: '${{ needs.parse_run_context.outputs.repository }}'
+
+      - name: 'Set up Node.js 20.x'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
+        with:
+          node-version: '20.x'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Build project'
+        run: 'npm run build'
+
+      - name: 'Run Evals (Required to pass)'
+        env:
+          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+        run: 'npm run test:always_passing_evals'
+
   e2e:
     name: 'E2E'
     if: |
@@ -284,13 +315,15 @@ jobs:
     needs:
       - 'e2e_linux'
       - 'e2e_mac'
+      - 'evals'
       - 'merge_queue_skipper'
     runs-on: 'gemini-cli-ubuntu-16-core'
     steps:
       - name: 'Check E2E test results'
         run: |
           if [[ ${{ needs.e2e_linux.result }} != 'success' || \
-               ${{ needs.e2e_mac.result }} != 'success' ]]; then
+               ${{ needs.e2e_mac.result }} != 'success' || \
+               ${{ needs.evals.result }} != 'success' ]]; then
             echo "One or more E2E jobs failed."
             exit 1
           fi

.github/workflows/evals-nightly.yml

@@ -0,0 +1,76 @@
+name: 'Evals: Nightly'
+
+on:
+  schedule:
+    - cron: '0 1 * * *' # Runs at 1 AM every day
+  workflow_dispatch:
+    inputs:
+      run_all:
+        description: 'Run all evaluations (including usually passing)'
+        type: 'boolean'
+        default: true
+
+permissions:
+  contents: 'read'
+  checks: 'write'
+  actions: 'read'
+
+jobs:
+  evals:
+    name: 'Evals (USUALLY_PASSING) nightly run'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    strategy:
+      fail-fast: false
+      matrix:
+        run_attempt: [1, 2, 3]
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+        with:
+          node-version-file: '.nvmrc'
+          cache: 'npm'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Build project'
+        run: 'npm run build'
+
+      - name: 'Create logs directory'
+        run: 'mkdir -p evals/logs'
+
+      - name: 'Run Evals'
+        env:
+          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          RUN_EVALS: "${{ github.event.inputs.run_all != 'false' }}"
+        run: 'npm run test:all_evals'
+
+      - name: 'Upload Logs'
+        if: 'always()'
+        uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
+        with:
+          name: 'eval-logs-${{ matrix.run_attempt }}'
+          path: 'evals/logs'
+          retention-days: 7
+
+  aggregate-results:
+    name: 'Aggregate Results'
+    needs: ['evals']
+    if: 'always()'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+
+      - name: 'Download Logs'
+        uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4
+        with:
+          path: 'artifacts'
+
+      - name: 'Generate Summary'
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: 'node scripts/aggregate_evals.js artifacts >> "$GITHUB_STEP_SUMMARY"'

.github/workflows/gemini-automated-issue-triage.yml

@@ -14,9 +14,15 @@ on:
         description: 'issue number to triage'
         required: true
         type: 'number'
+  workflow_call:
+    inputs:
+      issue_number:
+        description: 'issue number to triage'
+        required: false
+        type: 'string'
 
 concurrency:
-  group: '${{ github.workflow }}-${{ github.event.issue.number || github.event.inputs.issue_number }}'
+  group: '${{ github.workflow }}-${{ github.event.issue.number || github.event.inputs.issue_number || inputs.issue_number }}'
   cancel-in-progress: true
 
 defaults:
@@ -34,7 +40,7 @@ permissions:
 jobs:
   triage-issue:
     if: |-
-      github.repository == 'google-gemini/gemini-cli' &&
+      (github.repository == 'google-gemini/gemini-cli' || github.repository == 'google-gemini/maintainers-gemini-cli') &&
       (
         github.event_name == 'workflow_dispatch' ||
         (
@@ -57,10 +63,11 @@ jobs:
         with:
           github-token: '${{ secrets.GITHUB_TOKEN }}'
           script: |
+            const issueNumber = ${{ github.event.inputs.issue_number || inputs.issue_number }};
             const { data: issue } = await github.rest.issues.get({
               owner: context.repo.owner,
               repo: context.repo.repo,
-              issue_number: ${{ github.event.inputs.issue_number }},
+              issue_number: issueNumber,
             });
             core.setOutput('title', issue.title);
             core.setOutput('body', issue.body);
@@ -71,7 +78,7 @@ jobs:
         if: |-
           github.event_name == 'workflow_dispatch'
         env:
-          ISSUE_NUMBER_INPUT: '${{ github.event.inputs.issue_number }}'
+          ISSUE_NUMBER_INPUT: '${{ github.event.inputs.issue_number || inputs.issue_number }}'
           LABELS: '${{ steps.get_issue_data.outputs.labels }}'
         run: |
           if echo "${LABELS}" | grep -q 'area/'; then
@@ -86,6 +93,10 @@ jobs:
 
       - name: 'Generate GitHub App Token'
         id: 'generate_token'
+        env:
+          APP_ID: '${{ secrets.APP_ID }}'
+        if: |-
+          ${{ env.APP_ID != '' }}
         uses: 'actions/create-github-app-token@a8d616148505b5069dccd32f177bb87d7f39123b' # ratchet:actions/create-github-app-token@v2
         with:
           app-id: '${{ secrets.APP_ID }}'
@@ -96,7 +107,7 @@ jobs:
         id: 'get_labels'
         uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
         with:
-          github-token: '${{ steps.generate_token.outputs.token }}'
+          github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
           script: |-
             const { data: labels } = await github.rest.issues.listLabelsForRepo({
               owner: context.repo.owner,
@@ -127,7 +138,7 @@ jobs:
           ISSUE_BODY: >-
             ${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.body || github.event.issue.body }}
           ISSUE_NUMBER: >-
-            ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.issue_number || github.event.issue.number }}
+            ${{ github.event_name == 'workflow_dispatch' && (github.event.inputs.issue_number || inputs.issue_number) || github.event.issue.number }}
           REPOSITORY: '${{ github.repository }}'
           AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
         with:
@@ -253,7 +264,7 @@ jobs:
           LABELS_OUTPUT: '${{ steps.gemini_issue_analysis.outputs.summary }}'
         uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
         with:
-          github-token: '${{ steps.generate_token.outputs.token }}'
+          github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
           script: |
             const rawOutput = process.env.LABELS_OUTPUT;
             core.info(`Raw output from model: ${rawOutput}`);
@@ -295,22 +306,6 @@ jobs:
             });
             core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}`);
 
-            // Remove the 'status/need-triage' label
-            try {
-                await github.rest.issues.removeLabel({
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: issueNumber,
-                    name: 'status/need-triage'
-                });
-                core.info(`Successfully removed 'status/need-triage' label.`);
-            } catch (error) {
-                // If the label doesn't exist, the API call will throw a 404. We can ignore this.
-                if (error.status !== 404) {
-                    core.warning(`Failed to remove 'status/need-triage': ${error.message}`);
-                }
-            }
-
       - name: 'Post Issue Analysis Failure Comment'
         if: |-
           ${{ failure() && steps.gemini_issue_analysis.outcome == 'failure' }}
@@ -319,7 +314,7 @@ jobs:
           RUN_URL: '${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}'
         uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
         with:
-          github-token: '${{ steps.generate_token.outputs.token }}'
+          github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
           script: |-
             github.rest.issues.createComment({
               owner: context.repo.owner,

.github/workflows/gemini-automated-pr-size-labeler.yml

@@ -1,127 +0,0 @@
-name: 'Gemini Automated PR Labeler'
-
-on:
-  pull_request_target:
-    types: ['opened', 'reopened', 'synchronize']
-
-jobs:
-  label-pr:
-    timeout-minutes: 10
-    if: |-
-      ${{ github.repository == 'google-gemini/gemini-cli' }}
-    permissions:
-      pull-requests: 'write'
-      contents: 'read'
-      id-token: 'write'
-
-    concurrency:
-      group: '${{ github.workflow }}-${{ github.event.pull_request.number }}'
-      cancel-in-progress: true
-
-    runs-on: 'ubuntu-latest'
-
-    steps:
-      - name: 'Generate GitHub App Token'
-        id: 'generate_token'
-        uses: 'actions/create-github-app-token@df432ceedc7162793a195dd1713ff69aefc7379e' # v2
-        with:
-          app-id: '${{ secrets.APP_ID }}'
-          private-key: '${{ secrets.PRIVATE_KEY }}'
-          permission-pull-requests: 'write'
-
-      - name: 'Run Gemini PR size and complexity labeller'
-        uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # Use the specific commit SHA
-        env:
-          GH_TOKEN: '${{ steps.generate_token.outputs.token }}'
-          PR_NUMBER: '${{ github.event.pull_request.number }}'
-          REPOSITORY: '${{ github.repository }}'
-        with:
-          gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
-          gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
-          gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
-          gcp_service_account: '${{ vars.SERVICE_ACCOUNT_EMAIL }}'
-          gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
-          use_vertex_ai: '${{ vars.GOOGLE_GENAI_USE_VERTEXAI }}'
-          use_gemini_code_assist: '${{ vars.GOOGLE_GENAI_USE_GCA }}'
-          settings: |
-            {
-              "coreTools": [
-                "run_shell_command(gh pr diff)",
-                "run_shell_command(gh pr edit)",
-                "run_shell_command(gh pr comment)",
-                "run_shell_command(gh pr view)"
-              ],
-              "telemetry": {
-                "enabled": true,
-                "target": "gcp"
-              },
-              "sandbox": false
-            }
-          prompt: |
-            You are a Pull Request labeller and Feedback Assistant. Your primary goal is to improve review velocity and help maintainers prioritize their work by automatically labeling pull requests based on size and complexity, and providing guidance for overly large PRs.
-
-            Steps:
-            1. Retrieve Pull Request Information:
-               - Use `gh pr diff ${{ env.PR_NUMBER }} --repo ${{ env.REPOSITORY }}` to get the diff content.
-               - Parse the output from `gh pr diff` to determine the total lines of code added and deleted. Calculate `TOTAL_LINES_CHANGED`.
-
-            2. Determine Pull Request Size:
-               - Use `gh pr view ${{ env.PR_NUMBER }} --repo ${{ env.REPOSITORY }} --json labels` to get the current labels on the PR.
-               - Check the current labels and identify if any `size/*` labels already exist (e.g., `size/xs`, `size/s`, etc.).
-               - If an old `size/*` label is found and it is different from the newly calculated size, remove it using:
-                 `gh pr edit ${{ env.PR_NUMBER }} --repo ${{ env.REPOSITORY }} --remove-label "size-label-to-remove"`
-               - Based on `TOTAL_LINES_CHANGED`, select the appropriate new size label:
-                 - `size/xs`: < 10 lines changed
-                 - `size/s`: 10-50 lines changed
-                 - `size/m`: 51-200 lines changed
-                 - `size/l`: 201-1000 lines changed
-                 - `size/xl`: > 1000 lines changed
-               - Do not invent new size labels.
-               - Apply the newly determined `size/*` label to the pull request using:
-                 `gh pr edit ${{ env.PR_NUMBER }} --repo ${{ env.REPOSITORY }} --add-label "your-new-size-label"`
-
-            3. Analyze Pull Request Complexity:
-                - Perform Code Change Analysis: Examine the content of the code changes obtained from `gh pr diff ${{ env.PR_NUMBER }} --repo ${{ env.REPOSITORY }}`. Look for indicators of complexity such as:
-                 - Number of files changed (can be inferred from the diff headers).
-                 - Diversity of file types (e.g., changes across different languages, configuration files, documentation).
-                 - Presence of new external dependencies.
-                 - Introduction of new architectural components or significant refactoring.
-                 - Complexity of individual code changes (e.g., deeply nested logic, complex algorithms, extensive conditional statements).
-               - Apply Heuristic-based Complexity Assessment:
-                 - If the PR touches a small number of files with minor changes (e.g., typos, simple bug fixes, small feature additions), categorize it as `review/quick`.
-                 - If the PR involves changes across multiple files, introduces new features, significantly refactors existing code, or has a high line count (even within `size/l`), categorize it as `review/involved`.
-                 - Pay close attention to changes in critical or core modules as these inherently increase complexity.
-               - **Only use the labels `review/quick` or `review/involved` for complexity. Do not invent new complexity labels.**
-               - **Remove any previous `review/*` labels if they no longer apply, similar to the size label process.**
-               - Apply the determined `review/*` label to the pull request using:
-                 `gh pr edit ${{ env.PR_NUMBER }} --repo ${{ env.REPOSITORY }} --add-label "your-complexity-label"`
-
-            4. Handle Overly Large Pull Requests (`size/xl`):
-               - **Conditional Check:** If the pull request has been labeled `size/xl` (i.e., > 1000 lines of code changed) in Step 2, proceed to the next sub-step.
-               - **Post Constructive Comment:** Post a polite and helpful comment on the pull request using:
-                 `gh pr comment ${{ env.PR_NUMBER }} --repo ${{ env.REPOSITORY }} --body "Your comment here"`
-                 The comment body should be:
-                 """
-                 Thanks for your hard work on this pull request!
-
-                 This pull request is quite large, which can make it challenging and time-consuming for reviewers to go through thoroughly.
-
-                 To help us review it more efficiently and get your changes merged faster, we kindly request you consider breaking this into smaller, more focused pull requests. Each smaller PR should ideally address a single logical change or a small set of related changes.
-
-                 For example, you could separate out refactoring, new feature additions, and bug fixes into individual PRs. This makes it easier to understand, review, and test each component independently.
-
-                 We appreciate your understanding and cooperation. Feel free to reach out if you need any assistance with this!
-                 """
-
-            Guidelines:
-            - Automation Focus: All actions should be automated and not require manual intervention.
-            - Non-intrusive: The system should add labels and comments but not modify the code or close the pull request.
-            - Polite and Constructive: All communication, especially for large PRs, must be polite, encouraging, and constructive.
-            - Prioritize Clarity: The labels applied should clearly convey the PR's size and complexity to reviewers.
-            - Adhere to Defined Labels: Only use the specified `size/*` and `review/*` labels. Do not create or apply any other labels.
-            - Utilize `gh CLI`: Interact with GitHub using the `gh` command-line tool for diffing, label management, and commenting.
-            - Execute commands strictly as described in the steps. Do not invent new commands.
-            - In no case should you change other pull request that are not the one you are working on. Which can be found by using env.PR_NUMBER
-            - Execute each step that is defined in the steps section.
-            - In no case should you execute code from the pull request because this could be malicious code.
-            - If you fail to do this step log the errors you received

.github/workflows/gemini-scheduled-issue-triage.yml

@@ -1,12 +1,16 @@
 name: '📋 Gemini Scheduled Issue Triage'
 
 on:
+  issues:
+    types:
+      - 'opened'
+      - 'reopened'
   schedule:
     - cron: '0 * * * *' # Runs every hour
   workflow_dispatch:
 
 concurrency:
-  group: '${{ github.workflow }}'
+  group: '${{ github.workflow }}-${{ github.event.number || github.run_id }}'
   cancel-in-progress: true
 
 defaults:
@@ -35,7 +39,21 @@ jobs:
           private-key: '${{ secrets.PRIVATE_KEY }}'
           permission-issues: 'write'
 
+      - name: 'Get issue from event'
+        if: |-
+          ${{ github.event_name == 'issues' }}
+        id: 'get_issue_from_event'
+        env:
+          ISSUE_EVENT: '${{ toJSON(github.event.issue) }}'
+        run: |
+          set -euo pipefail
+          ISSUE_JSON=$(echo "$ISSUE_EVENT" | jq -c '[{number: .number, title: .title, body: .body}]')
+          echo "issues_to_triage=${ISSUE_JSON}" >> "${GITHUB_OUTPUT}"
+          echo "✅ Found issue #${{ github.event.issue.number }} from event to triage! 🎯"
+
       - name: 'Find untriaged issues'
+        if: |-
+          ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
         id: 'find_issues'
         env:
           GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
@@ -43,22 +61,26 @@ jobs:
         run: |-
           set -euo pipefail
 
-          echo '🔍 Finding issues without labels...'
-          NO_LABEL_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue no:label' --limit 10 --json number,title,body)"
+          echo '🔍 Finding issues missing area labels...'
+          NO_AREA_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue -label:area/core -label:area/agent -label:area/enterprise -label:area/non-interactive -label:area/security -label:area/platform -label:area/extensions -label:area/unknown' --limit 100 --json number,title,body)"
 
-          echo '🏷️ Finding issues that need triage...'
-          NEED_TRIAGE_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search "is:open is:issue label:\"status/need-triage\"" --limit 10 --json number,title,body)"
+          echo '🔍 Finding issues missing kind labels...'
+          NO_KIND_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue -label:kind/bug -label:kind/enhancement -label:kind/customer-issue -label:kind/question' --limit 100 --json number,title,body)"
+
+          echo '🏷️ Finding issues missing priority labels...'
+          NO_PRIORITY_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue -label:priority/p0 -label:priority/p1 -label:priority/p2 -label:priority/p3 -label:priority/unknown' --limit 100 --json number,title,body)"
 
           echo '🔄 Merging and deduplicating issues...'
-          ISSUES="$(echo "${NO_LABEL_ISSUES}" "${NEED_TRIAGE_ISSUES}" | jq -c -s 'add | unique_by(.number)')"
+          ISSUES="$(echo "${NO_AREA_ISSUES}" "${NO_KIND_ISSUES}" "${NO_PRIORITY_ISSUES}" | jq -c -s 'add | unique_by(.number)')"
 
           echo '📝 Setting output for GitHub Actions...'
           echo "issues_to_triage=${ISSUES}" >> "${GITHUB_OUTPUT}"
 
           ISSUE_COUNT="$(echo "${ISSUES}" | jq 'length')"
-          echo "✅ Found ${ISSUE_COUNT} issues to triage! 🎯"
+          echo "✅ Found ${ISSUE_COUNT} unique issues to triage! 🎯"
 
       - name: 'Get Repository Labels'
         id: 'get_labels'
@@ -77,12 +99,13 @@ jobs:
 
       - name: 'Run Gemini Issue Analysis'
         if: |-
-          ${{ steps.find_issues.outputs.issues_to_triage != '[]' }}
+          (steps.get_issue_from_event.outputs.issues_to_triage != '' && steps.get_issue_from_event.outputs.issues_to_triage != '[]') ||
+          (steps.find_issues.outputs.issues_to_triage != '' && steps.find_issues.outputs.issues_to_triage != '[]')
         uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
         id: 'gemini_issue_analysis'
         env:
           GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
-          ISSUES_TO_TRIAGE: '${{ steps.find_issues.outputs.issues_to_triage }}'
+          ISSUES_TO_TRIAGE: '${{ steps.get_issue_from_event.outputs.issues_to_triage || steps.find_issues.outputs.issues_to_triage }}'
           REPOSITORY: '${{ github.repository }}'
           AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
         with:
@@ -116,38 +139,32 @@ jobs:
             1. You are only able to use the echo command. Review the available labels in the environment variable: "${AVAILABLE_LABELS}".
             2. Check environment variable for issues to triage: $ISSUES_TO_TRIAGE (JSON array of issues)
             3. Review the issue title, body and any comments provided in the environment variables.
-            4. Identify the most relevant labels from the existing labels, focusing on kind/*, area/*, sub-area/* and priority/*.
-            5. If the issue already has area/ label, dont try to change it. Similarly, if the issue already has a kind/ label don't change it. And if the issue already has a priority/ label do not change it for example:
-               If an issue has area/core and kind/bug  you will only add a priority/ label.
-               Instead if an issue has no labels, you will could add one lable of each kind.
+            4. Identify the most relevant labels from the existing labels, specifically focusing on area/*, kind/* and priority/*.
+            5. Label Policy:
+               - If the issue already has a kind/ label, do not change it.
+               - If the issue already has a priority/ label, do not change it.
+               - If the issue already has an area/ label, do not change it.
+               - If any of these are missing, select exactly ONE appropriate label for the missing category.
             6. Identify other applicable labels based on the issue content, such as status/*, help wanted, good first issue, etc.
-            7. For area/* and kind/* limit yourself to only the single most applicable label in each case.
-            8. Give me a single short explanation about why you are selecting each label in the process.
-            9. Output a JSON array of objects, each containing the issue number
+            7. Give me a single short explanation about why you are selecting each label in the process.
+            8. Output a JSON array of objects, each containing the issue number
                and the labels to add and remove, along with an explanation. For example:
                ```
                [
                  {
                    "issue_number": 123,
-                   "labels_to_add": ["kind/bug", "priority/p2"],
+                   "labels_to_add": ["area/core", "kind/bug", "priority/p2"],
                    "labels_to_remove": ["status/need-triage"],
-                   "explanation": "This issue is a bug that needs to be addressed with medium priority."
-                 },
-                 {
-                   "issue_number": 456,
-                   "labels_to_add": ["kind/enhancement"],
-                   "labels_to_remove": [],
-                   "explanation": "This issue is an enhancement request that could improve the user experience."
+                   "explanation": "This issue is a UI bug that needs to be addressed with medium priority."
                  }
                ]
                ```
               If an issue cannot be classified, do not include it in the output array.
-            10. For each issue please check if CLI version is present, this is usually in the output of the /about command and will look like 0.1.5
+            9. For each issue please check if CLI version is present, this is usually in the output of the /about command and will look like 0.1.5
               - Anything more than 6 versions older than the most recent should add the status/need-retesting label
-            11. If you see that the issue doesn't look like it has sufficient information recommend the status/need-information label and leave a comment politely requesting the relevant information, eg.. if repro steps are missing request for repro steps. if version information is missing request for version information into the explanation section below.
-              - After identifying appropriate labels to an issue, add "status/need-triage" label to labels_to_remove in the output.
-            12. If you think an issue might be a Priority/P0 do not apply the priority/p0 label. Instead apply a status/manual-triage label and include a note in your explanation.
-            13. If you are uncertain and have not been able to apply one each of kind/, area/ and priority/ , apply the status/manual-triage label.
+            10. If you see that the issue doesn't look like it has sufficient information recommend the status/need-information label and leave a comment politely requesting the relevant information, eg.. if repro steps are missing request for repro steps. if version information is missing request for version information into the explanation section below.
+            11. If you think an issue might be a Priority/P0 do not apply the priority/p0 label. Instead apply a status/manual-triage label and include a note in your explanation.
+            12. If you are uncertain about a category, use the area/unknown, kind/question, or priority/unknown labels as appropriate. If you are extremely uncertain, apply the status/manual-triage label.
 
             ## Guidelines
 
@@ -157,100 +174,46 @@ jobs:
               - Do not add comments or modify the issue content.
               - Do not remove the following labels maintainer, help wanted or good first issue.
               - Triage only the current issue.
-              - Identify only one area/ label
+              - Identify only one area/ label.
               - Identify only one kind/ label (Do not apply kind/duplicate or kind/parent-issue)
-              - Identify all applicable sub-area/* and priority/* labels based on the issue content. It's ok to have multiple of these.
+              - Identify only one priority/ label.
               - Once you categorize the issue if it needs information bump down the priority by 1 eg.. a p0 would become a p1 a p1 would become a p2. P2 and P3 can stay as is in this scenario.
-            Categorization Guidelines:
-            P0: Critical / Blocker
-              - A P0 bug is a catastrophic failure that demands immediate attention.
-              - To be a P0 it means almost all users are running into this issue and it is blocking users from being able to use the product.
-              - You would see this in the form of many comments from different developers on the bug.
-              - It represents a complete showstopper for a significant portion of users or for the development process itself.
-            Impact:
-              - Blocks development or testing for the entire team.
-              - Major security vulnerability that could compromise user data or system integrity.
-              - Causes data loss or corruption with no workaround.
-              - Crashes the application or makes a core feature completely unusable for all or most users in a production environment. Will it cause severe quality degration?
-              - Is it preventing contributors from contributing to the repository or is it a release blocker?
-              Qualifier: Is the main function of the software broken?
-              Example: The gemini auth login command fails with an unrecoverable error, preventing any user from authenticating and using the rest of the CLI.
-            P1: High
-              - A P1 bug is a serious issue that significantly degrades the user experience or impacts a core feature.
-              - While not a complete blocker, it's a major problem that needs a fast resolution. Feature requests are almost never P1.
-              - Once again this would be affecting many users.
-              - You would see this in the form of comments from different developers on the bug.
-              Impact:
-              - A core feature is broken or behaving incorrectly for a large number of users or large number of use cases.
-              - Review the bug details and comments to try figure out if this issue affects a large set of use cases or if it's a narrow set of use cases.
-              - Severe performance degradation making the application frustratingly slow.
-              - No straightforward workaround exists, or the workaround is difficult and non-obvious.
-              Qualifier: Is a key feature unusable or giving very wrong results?
-              Example: Gemini CLI enters a loop when making read-many-files tool call. I am unable to break out of the loop and gemini doesn't follow instructions subsequently.
-            P2: Medium
-              - A P2 bug is a moderately impactful issue. It's a noticeable problem but doesn't prevent the use of the software's main functionality.
-              Impact:
-              - Affects a non-critical feature or a smaller, specific subset of users.
-              - An inconvenient but functional workaround is available and easy to execute.
-              - Noticeable UI/UX problems that don't break functionality but look unprofessional (e.g., elements are misaligned or overlapping).
-              Qualifier: Is it an annoying but non-blocking problem?
-              Example: An error message is unclear or contains a typo, causing user confusion but not halting their workflow.
-            P3: Low
-              - A P3 bug is a minor, low-impact issue that is trivial or cosmetic. It has little to no effect on the overall functionality of the application.
-              Impact:
-              - Minor cosmetic issues like color inconsistencies, typos in documentation, or slight alignment problems on a non-critical page.
-              - An edge-case bug that is very difficult to reproduce and affects a tiny fraction of users.
-              Qualifier: Is it a "nice-to-fix" issue?
-              Example: Spelling mistakes etc.
+
+            Categorization Guidelines (Priority):
+            P0 - Urgent Blocking Issues:
+              - DO NOT APPLY THIS LABEL AUTOMATICALLY. Use status/manual-triage instead.
+              - Definition: Urgent, block a significant percentage of the user base, and prevent frequent use of the Gemini CLI.
+              - This includes core stability blockers (e.g., authentication failures, broken upgrades), critical crashes, and P0 security vulnerabilities.
+              - Impact: Blocks development or testing for the entire team; Major security vulnerability; Causes data loss or corruption with no workaround; Crashes the application or makes a core feature completely unusable for all or most users.
+              - Qualifier: Is the main function of the software broken?
+            P1 - High-Impact Issues:
+              - Definition: Affect a large number of users, blocking them from using parts of the Gemini CLI, or make the CLI frequently unusable even with workarounds available.
+              - Impact: A core feature is broken or behaving incorrectly for a large number of users or use cases; Severe performance degradation; No straightforward workaround exists.
+              - Qualifier: Is a key feature unusable or giving very wrong results?
+            P2 - Significant Issues:
+              - Definition: Affect some users significantly, such as preventing the use of certain features or authentication types.
+              - Can also be issues that many users complain about, causing annoyance or hindering daily use.
+              - Impact: Affects a non-critical feature or a smaller, specific subset of users; An inconvenient but functional workaround is available; Noticeable UI/UX problems that look unprofessional.
+              - Qualifier: Is it an annoying but non-blocking problem?
+            P3 - Low-Impact Issues:
+              - Definition: Typically usability issues that cause annoyance to a limited user base.
+              - Includes feature requests that could be addressed in the near future and may be suitable for community contributions.
+              - Impact: Minor cosmetic issues; An edge-case bug that is very difficult to reproduce and affects a tiny fraction of users.
+              - Qualifier: Is it a "nice-to-fix" issue?
+
+            Categorization Guidelines (Area):
+            area/agent: Core Agent, Tools, Memory, Sub-Agents, Hooks, Agent Quality
+            area/core: User Interface, OS Support, Core Functionality
+            area/enterprise: Telemetry, Policy, Quota / Licensing
+            area/extensions: Gemini CLI extensions capability
+            area/non-interactive: GitHub Actions, SDK, 3P Integrations, Shell Scripting, Command line automation
+            area/platform: Build infra, Release mgmt, Testing, Eval infra, Capacity, Quota mgmt
+            area/security: security related issues
+
             Additional Context:
-              - If users are talking about issues where the model gets downgraded from pro to flash then i want you to categorize that as a performance issue
-              - This product is designed to use different models eg.. using pro, downgrading to flash etc.
-              - When users report that they dont expect the model to change those would be categorized as feature requests.
-            Definition of Areas
-            area/ux:
-              - Issues concerning user-facing elements like command usability, interactive features, help docs, and perceived performance.
-              - I am seeing my screen flicker when using Gemini CLI
-              - I am seeing the output malformed
-              - Theme changes aren't taking effect
-              - My keyboard inputs arent' being recognzied
-            area/platform:
-              - Issues related to installation, packaging, OS compatibility (Windows, macOS, Linux), and the underlying CLI framework.
-            area/background: Issues related to long-running background tasks, daemons, and autonomous or proactive agent features.
-            area/models:
-              - i am not getting a response that is reasonable or expected. this can include things like
-              - I am calling a tool and the tool is not performing as expected.
-              - i am expecting a tool to be called and it is not getting called ,
-              - Including experience when using
-              - built-in tools (e.g., web search, code interpreter, read file, writefile, etc..),
-              - Function calling issues should be under this area
-              - i am getting responses from the model that are malformed.
-              - Issues concerning Gemini quality of response and inference,
-              - Issues talking about unnecessary token consumption.
-              - Issues talking about Model getting stuck in a loop be watchful as this could be the root cause for issues that otherwise seem like model performance issues.
-              - Memory compression
-              - unexpected responses,
-              - poor quality of generated code
-            area/tools:
-              - These are primarily issues related to Model Context Protocol
-              - These are issues that mention MCP support
-              - feature requests asking for support for new tools.
-            area/core:
-              - Issues with fundamental components like command parsing, configuration management, session state, and the main API client logic. Introducing multi-modality
-            area/contribution:
-              - Issues related to improving the developer contribution experience, such as CI/CD pipelines, build scripts, and test automation infrastructure.
-            area/authentication:
-              -  Issues related to user identity, login flows, API key handling, credential storage, and access token management, unable to sign in selecting wrong authentication path etc..
-            area/security-privacy:
-              - Issues concerning vulnerability patching, dependency security, data sanitization, privacy controls, and preventing unauthorized data access.
-            area/extensibility:
-              - Issues related to the plugin system, extension APIs, or making the CLI's functionality available in other applications, github actions, ide support etc..
-            area/performance:
-              - Issues focused on model performance
-              - Issues with running out of capacity,
-              - 429 errors etc..
-              - could also pertain to latency,
-              - other general software performance like, memory usage, CPU consumption, and algorithmic efficiency.
-              - Switching models from one to the other unexpectedly.
+            - If users are talking about issues where the model gets downgraded from pro to flash then i want you to categorize that as a performance issue.
+            - This product is designed to use different models eg.. using pro, downgrading to flash etc.
+            - When users report that they dont expect the model to change those would be categorized as feature requests.
 
       - name: 'Apply Labels to Issues'
         if: |-
@@ -300,24 +263,6 @@ jobs:
                 core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}${explanation}`);
               }
 
-              if (entry.labels_to_remove && entry.labels_to_remove.length > 0) {
-                for (const label of entry.labels_to_remove) {
-                  try {
-                    await github.rest.issues.removeLabel({
-                      owner: context.repo.owner,
-                      repo: context.repo.repo,
-                      issue_number: issueNumber,
-                      name: label
-                    });
-                  } catch (error) {
-                    if (error.status !== 404) {
-                      throw error;
-                    }
-                  }
-                }
-                core.info(`Successfully removed labels for #${issueNumber}: ${entry.labels_to_remove.join(', ')}`);
-              }
-
               if (entry.explanation) {
                 await github.rest.issues.createComment({
                   owner: context.repo.owner,

.github/workflows/gemini-scheduled-pr-triage.yml

@@ -39,3 +39,7 @@ jobs:
           GITHUB_REPOSITORY: '${{ github.repository }}'
         run: |-
           ./.github/scripts/pr-triage.sh
+          # If prs_needing_comment is empty, set it to [] explicitly for downstream steps
+          if [[ -z "$(grep 'prs_needing_comment' "${GITHUB_OUTPUT}" | cut -d'=' -f2-)" ]]; then
+            echo "prs_needing_comment=[]" >> "${GITHUB_OUTPUT}"
+          fi

.github/workflows/issue-opened-labeler.yml

@@ -0,0 +1,46 @@
+name: '🏷️ Issue Opened Labeler'
+
+on:
+  issues:
+    types:
+      - 'opened'
+
+jobs:
+  label-issue:
+    runs-on: 'ubuntu-latest'
+    if: |-
+      ${{ github.repository == 'google-gemini/gemini-cli' || github.repository == 'google-gemini/maintainers-gemini-cli' }}
+    steps:
+      - name: 'Generate GitHub App Token'
+        id: 'generate_token'
+        env:
+          APP_ID: '${{ secrets.APP_ID }}'
+        if: |-
+          ${{ env.APP_ID != '' }}
+        uses: 'actions/create-github-app-token@a8d616148505b5069dccd32f177bb87d7f39123b' # ratchet:actions/create-github-app-token@v2
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+
+      - name: 'Add need-triage label'
+        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
+          script: |-
+            const { data: issue } = await github.rest.issues.get({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: context.issue.number,
+            });
+
+            const hasLabel = issue.labels.some(l => l.name === 'status/need-triage');
+            if (!hasLabel) {
+              await github.rest.issues.addLabels({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: context.issue.number,
+                labels: ['status/need-triage']
+              });
+            } else {
+              core.info('Issue already has status/need-triage label. Skipping.');
+            }

.github/workflows/label-backlog-child-issues.yml

@@ -3,38 +3,55 @@ name: 'Label Child Issues for Project Rollup'
 on:
   issues:
     types: ['opened', 'edited', 'reopened']
+  schedule:
+    - cron: '0 * * * *' # Run every hour
+  workflow_dispatch:
+
+permissions:
+  issues: 'write'
+  contents: 'read'
 
 jobs:
+  # Event-based: Quick reaction to new/edited issues in THIS repo
   labeler:
+    if: "github.event_name == 'issues'"
     runs-on: 'ubuntu-latest'
-    permissions:
-      issues: 'write'
     steps:
-      - name: 'Check for Parent Workstream and Apply Label'
-        uses: 'actions/github-script@v7'
+      - name: 'Checkout'
+        uses: 'actions/checkout@v4'
+
+      - name: 'Setup Node.js'
+        uses: 'actions/setup-node@v4'
         with:
-          script: |
-            const issue = context.payload.issue;
-            const labelToAdd = 'workstream-rollup';
+          node-version: '20'
+          cache: 'npm'
 
-            // --- Define the FULL URLs of the allowed parent workstreams ---
-            const allowedParentUrls = [
-              'https://api.github.com/repos/google-gemini/gemini-cli/issues/15374',
-              'https://api.github.com/repos/google-gemini/gemini-cli/issues/15456',
-              'https://api.github.com/repos/google-gemini/gemini-cli/issues/15324'
-            ];
+      - name: 'Install Dependencies'
+        run: 'npm ci'
 
-            // Check if the issue has a parent_issue_url and if it's in our allowed list.
-            if (issue && issue.parent_issue_url && allowedParentUrls.includes(issue.parent_issue_url)) {
-              console.log(`SUCCESS: Issue #${issue.number} is a child of a target workstream (${issue.parent_issue_url}). Adding label.`);
-              await github.rest.issues.addLabels({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                issue_number: issue.number,
-                labels: [labelToAdd]
-              });
-            } else if (issue && issue.parent_issue_url) {
-              console.log(`FAILURE: Issue #${issue.number} has a parent, but it's not a target workstream. Parent URL: ${issue.parent_issue_url}`);
-            } else {
-              console.log(`FAILURE: Issue #${issue.number} is not a child of any issue. No action taken.`);
-            }
+      - name: 'Run Multi-Repo Sync Script'
+        env:
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: 'node .github/scripts/sync-maintainer-labels.cjs'
+
+  # Scheduled/Manual: Recursive sync across multiple repos
+  sync-maintainer-labels:
+    if: "github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'"
+    runs-on: 'ubuntu-latest'
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@v4'
+
+      - name: 'Setup Node.js'
+        uses: 'actions/setup-node@v4'
+        with:
+          node-version: '20'
+          cache: 'npm'
+
+      - name: 'Install Dependencies'
+        run: 'npm ci'
+
+      - name: 'Run Multi-Repo Sync Script'
+        env:
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: 'node .github/scripts/sync-maintainer-labels.cjs'

.github/workflows/label-enforcer.yml

@@ -0,0 +1,119 @@
+name: '🏷️ Enforce Restricted Label Permissions'
+
+on:
+  issues:
+    types:
+      - 'labeled'
+      - 'unlabeled'
+
+jobs:
+  enforce-label:
+    # Run this job only when restricted labels are changed
+    if: |-
+      ${{ (github.event.label.name == 'help wanted' || github.event.label.name == 'status/need-triage' || github.event.label.name == '🔒 maintainer only') &&
+          (github.repository == 'google-gemini/gemini-cli' || github.repository == 'google-gemini/maintainers-gemini-cli') }}
+    runs-on: 'ubuntu-latest'
+    permissions:
+      issues: 'write'
+    steps:
+      - name: 'Generate GitHub App Token'
+        id: 'generate_token'
+        env:
+          APP_ID: '${{ secrets.APP_ID }}'
+        if: |-
+          ${{ env.APP_ID != '' }}
+        uses: 'actions/create-github-app-token@a8d616148505b5069dccd32f177bb87d7f39123b' # ratchet:actions/create-github-app-token@v2
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+
+      - name: 'Check if user is in the maintainers team'
+        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
+          script: |-
+            const org = context.repo.owner;
+            const username = context.payload.sender.login;
+            const team_slug = 'gemini-cli-maintainers';
+            const action = context.payload.action; // 'labeled' or 'unlabeled'
+            const labelName = context.payload.label.name;
+
+            // Skip if the change was made by a bot to avoid infinite loops
+            if (username === 'github-actions[bot]' || username === 'gemini-cli[bot]' || username.endsWith('[bot]')) {
+              core.info('Change made by a bot. Skipping.');
+              return;
+            }
+
+            try {
+              // Check repository permission level directly.
+              // This is more robust than team membership as it doesn't require Org-level read permissions
+              // and correctly handles Repo Admins/Writers who might not be in the specific team.
+              const { data: { permission } } = await github.rest.repos.getCollaboratorPermissionLevel({
+                owner: org,
+                repo: context.repo.repo,
+                username,
+              });
+
+              if (permission === 'admin' || permission === 'write') {
+                core.info(`${username} has '${permission}' permission. Allowed.`);
+                return;
+              }
+
+              core.info(`${username} has '${permission}' permission (needs 'write' or 'admin'). Reverting '${action}' action for '${labelName}' label.`);
+            } catch (error) {
+              core.error(`Failed to check permissions for ${username}: ${error.message}`);
+              // Fall through to revert logic if we can't verify permissions (fail safe)
+            }
+
+            // If we are here, the user is NOT authorized.
+            if (true) { // wrapping block to preserve variable scope if needed
+              if (action === 'labeled') {
+                // 1. Remove the label if added by a non-maintainer
+                await github.rest.issues.removeLabel ({
+                  owner: org,
+                  repo: context.repo.repo,
+                  issue_number: context.issue.number,
+                  name: labelName
+                });
+
+                // 2. Post a polite comment
+                const comment = `
+            Hi @${username}, thank you for your interest in helping triage issues!
+
+            The \`${labelName}\` label is reserved for project maintainers to apply. This helps us ensure that an issue is ready and properly vetted for community contribution.
+
+            A maintainer will review this issue soon. Please see our [CONTRIBUTING.md](https://github.com/google-gemini/gemini-cli/blob/main/CONTRIBUTING.md) for more details on our labeling process.
+                `.trim().replace(/^[ ]+/gm, '');
+
+                await github.rest.issues.createComment ({
+                  owner: org,
+                  repo: context.repo.repo,
+                  issue_number: context.issue.number,
+                  body: comment
+                });
+              } else if (action === 'unlabeled') {
+                // 1. Add the label back if removed by a non-maintainer
+                await github.rest.issues.addLabels ({
+                  owner: org,
+                  repo: context.repo.repo,
+                  issue_number: context.issue.number,
+                  labels: [labelName]
+                });
+
+                // 2. Post a polite comment
+                const comment = `
+            Hi @${username}, it looks like the \`${labelName}\` label was removed.
+
+            This label is managed by project maintainers. We've added it back to ensure the issue remains visible to potential contributors until a maintainer decides otherwise.
+
+            Thank you for your understanding!
+                `.trim().replace(/^[ ]+/gm, '');
+
+                await github.rest.issues.createComment ({
+                  owner: org,
+                  repo: context.repo.repo,
+                  issue_number: context.issue.number,
+                  body: comment
+                });
+              }
+            }

.github/workflows/label-workstream-rollup.yml

@@ -0,0 +1,94 @@
+name: 'Label Workstream Rollup'
+
+on:
+  issues:
+    types: ['opened', 'edited', 'reopened']
+  schedule:
+    - cron: '0 * * * *'
+  workflow_dispatch:
+
+jobs:
+  labeler:
+    runs-on: 'ubuntu-latest'
+    permissions:
+      issues: 'write'
+    steps:
+      - name: 'Check for Parent Workstream and Apply Label'
+        uses: 'actions/github-script@v7'
+        with:
+          script: |
+            const labelToAdd = 'workstream-rollup';
+
+            // Allow-list of parent issue URLs
+            const allowedParentUrls = [
+              'https://github.com/google-gemini/gemini-cli/issues/15374',
+              'https://github.com/google-gemini/gemini-cli/issues/15456',
+              'https://github.com/google-gemini/gemini-cli/issues/15324'
+            ];
+
+            async function getIssueParent(owner, repo, number) {
+              const query = `
+                query($owner:String!, $repo:String!, $number:Int!) {
+                  repository(owner:$owner, name:$repo) {
+                    issue(number:$number) {
+                      parent {
+                        url
+                      }
+                    }
+                  }
+                }
+              `;
+              try {
+                const result = await github.graphql(query, { owner, repo, number });
+                return result.repository.issue.parent ? result.repository.issue.parent.url : null;
+              } catch (error) {
+                console.error(`Failed to fetch parent for #${number}:`, error);
+                return null;
+              }
+            }
+
+            // Determine which issues to process
+            let issuesToProcess = [];
+
+            if (context.eventName === 'issues') {
+               // Context payload for 'issues' event already has the issue object
+               issuesToProcess.push({
+                 number: context.payload.issue.number,
+                 owner: context.repo.owner,
+                 repo: context.repo.repo
+               });
+            } else {
+              // For schedule/dispatch, fetch open issues (lightweight list)
+              console.log(`Running for event: ${context.eventName}. Fetching open issues...`);
+              const openIssues = await github.paginate(github.rest.issues.listForRepo, {
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                state: 'open'
+              });
+              issuesToProcess = openIssues.map(i => ({
+                number: i.number,
+                owner: context.repo.owner,
+                repo: context.repo.repo
+              }));
+            }
+
+            console.log(`Processing ${issuesToProcess.length} issue(s)...`);
+
+            for (const issue of issuesToProcess) {
+              const parentUrl = await getIssueParent(issue.owner, issue.repo, issue.number);
+
+              if (parentUrl && allowedParentUrls.includes(parentUrl)) {
+                console.log(`SUCCESS: Issue #${issue.number} is a direct child of ${parentUrl}. Adding label.`);
+                await github.rest.issues.addLabels({
+                  owner: issue.owner,
+                  repo: issue.repo,
+                  issue_number: issue.number,
+                  labels: [labelToAdd]
+                });
+              } else {
+                 // logging only for single execution to avoid spam
+                 if (context.eventName === 'issues') {
+                    console.log(`Issue #${issue.number} parent is ${parentUrl || 'None'}. No action.`);
+                 }
+              }
+            }

.github/workflows/pr-contribution-guidelines-notifier.yml

@@ -0,0 +1,83 @@
+name: '🏷️ PR Contribution Guidelines Notifier'
+
+on:
+  pull_request:
+    types:
+      - 'opened'
+
+jobs:
+  notify-process-change:
+    runs-on: 'ubuntu-latest'
+    if: |-
+      github.repository == 'google-gemini/gemini-cli' || github.repository == 'google-gemini/maintainers-gemini-cli'
+    permissions:
+      pull-requests: 'write'
+    steps:
+      - name: 'Generate GitHub App Token'
+        id: 'generate_token'
+        env:
+          APP_ID: '${{ secrets.APP_ID }}'
+        if: |-
+          ${{ env.APP_ID != '' }}
+        uses: 'actions/create-github-app-token@a8d616148505b5069dccd32f177bb87d7f39123b' # ratchet:actions/create-github-app-token@v2
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+
+      - name: 'Check membership and post comment'
+        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
+          script: |-
+            const org = context.repo.owner;
+            const repo = context.repo.repo;
+            const username = context.payload.pull_request.user.login;
+            const pr_number = context.payload.pull_request.number;
+
+            // 1. Check if the PR author is a maintainer
+            const authorAssociation = context.payload.pull_request.author_association;
+            if (['OWNER', 'MEMBER', 'COLLABORATOR'].includes(authorAssociation)) {
+              core.info(`${username} is a maintainer (Association: ${authorAssociation}). No notification needed.`);
+              return;
+            }
+
+            // 2. Check if the PR is already associated with an issue
+            const query = `
+              query($owner:String!, $repo:String!, $number:Int!) {
+                repository(owner:$owner, name:$repo) {
+                  pullRequest(number:$number) {
+                    closingIssuesReferences(first: 1) {
+                      totalCount
+                    }
+                  }
+                }
+              }
+            `;
+            const variables = { owner: org, repo: repo, number: pr_number };
+            const result = await github.graphql(query, variables);
+            const issueCount = result.repository.pullRequest.closingIssuesReferences.totalCount;
+
+            if (issueCount > 0) {
+              core.info(`PR #${pr_number} is already associated with an issue. No notification needed.`);
+              return;
+            }
+
+            // 3. Post the notification comment
+            core.info(`${username} is not a maintainer and PR #${pr_number} has no linked issue. Posting notification.`);
+
+            const comment = `
+            Hi @${username}, thank you so much for your contribution to Gemini CLI! We really appreciate the time and effort you've put into this.
+
+            We're making some updates to our contribution process to improve how we track and review changes. Please take a moment to review our recent discussion post: [Improving Our Contribution Process & Introducing New Guidelines](https://github.com/google-gemini/gemini-cli/discussions/16706).
+
+            Key Update: Starting **January 26, 2026**, the Gemini CLI project will require all pull requests to be associated with an existing issue. Any pull requests not linked to an issue by that date will be automatically closed.
+
+            Thank you for your understanding and for being a part of our community!
+            `.trim().replace(/^[ ]+/gm, '');
+
+            await github.rest.issues.createComment({
+              owner: org,
+              repo: repo,
+              issue_number: pr_number,
+              body: comment
+            });

.gitignore

@@ -11,6 +11,8 @@
 .gemini/*
 !.gemini/config.yaml
 !.gemini/commands/
+!.gemini/skills/
+!.gemini/settings.json
 
 # Note: .gemini-clipboard/ is NOT in gitignore so Gemini can access pasted images
 
@@ -57,3 +59,4 @@ patch_output.log
 .genkit
 .gemini-clipboard/
 .eslintcache
+evals/logs/

.prettierignore

@@ -20,3 +20,4 @@ junit.xml
 .gemini-linters/
 Thumbs.db
 .pytest_cache
+**/SKILL.md

CONTRIBUTING.md

@@ -42,8 +42,13 @@ This project follows
 The process for contributing code is as follows:
 
 1.  **Find an issue** that you want to work on. If an issue is tagged as
-    "🔒Maintainers only", this means it is reserved for project maintainers. We
-    will not accept pull requests related to these issues.
+    `🔒Maintainers only`, this means it is reserved for project maintainers. We
+    will not accept pull requests related to these issues. In the near future,
+    we will explicitly mark issues looking for contributions using the
+    `help  wanted` label. If you believe an issue is a good candidate for
+    community contribution, please leave a comment on the issue. A maintainer
+    will review it and apply the `help-wanted` label if appropriate. Only
+    maintainers should attempt to add the `help-wanted` label to an issue.
 2.  **Fork the repository** and create a new branch.
 3.  **Make your changes** in the `packages/` directory.
 4.  **Ensure all checks pass** by running `npm run preflight`.
@@ -94,8 +99,11 @@ any code is written.
 - **For features:** The PR should be linked to the feature request or proposal
   issue that has been approved by a maintainer.
 
-If an issue for your change doesn't exist, please **open one first** and wait
-for feedback before you start coding.
+If an issue for your change doesn't exist, we will automatically close your PR
+along with a comment reminding you to associate the PR with an issue. The ideal
+workflow starts with an issue that has been reviewed and approved by a
+maintainer. Please **open the issue first** and wait for feedback before you
+start coding.
 
 #### 2. Keep it small and focused
 

GEMINI.md

@@ -15,6 +15,17 @@ project. While you can run the individual steps (`build`, `test`, `typecheck`,
 `lint`) separately, it is highly recommended to use `npm run preflight` to
 ensure a comprehensive validation.
 
+## Running Tests in Workspaces\*\*: To run a specific test file within a
+
+workspace, use the command:
+`npm test -w <workspace-name> -- <path/to/test-file.test.ts>`. **CRITICAL**: The
+`<path/to/test-file.test.ts>` MUST be relative to the workspace directory root,
+NOT the project root.
+
+- _Example (Core package)_:
+  `npm test -w @google/gemini-cli-core -- src/routing/modelRouterService.test.ts`
+- _Common workspaces_: `@google/gemini-cli`, `@google/gemini-cli-core`.
+
 ## Writing Tests
 
 This project uses **Vitest** as its primary testing framework. When writing

README.md

@@ -18,7 +18,8 @@ Learn all about Gemini CLI in our [documentation](https://geminicli.com/docs/).
 
 - **🎯 Free tier**: 60 requests/min and 1,000 requests/day with personal Google
   account.
-- **🧠 Powerful Gemini 2.5 Pro**: Access to 1M token context window.
+- **🧠 Powerful Gemini 3 models**: Access to improved reasoning and 1M token
+  context window.
 - **🔧 Built-in tools**: Google Search grounding, file operations, shell
   commands, web fetching.
 - **🔌 Extensible**: MCP (Model Context Protocol) support for custom
@@ -140,7 +141,7 @@ for details)
 **Benefits:**
 
 - **Free tier**: 60 requests/min and 1,000 requests/day
-- **Gemini 2.5 Pro** with 1M token context window
+- **Gemini 3 models** with 1M token context window
 - **No API key management** - just sign in with your Google account
 - **Automatic updates** to latest models
 
@@ -164,7 +165,7 @@ gemini
 
 **Benefits:**
 
-- **Free tier**: 100 requests/day with Gemini 2.5 Pro
+- **Free tier**: 1000 requests/day with Gemini 3 (mix of flash and pro)
 - **Model selection**: Choose specific Gemini models
 - **Usage-based billing**: Upgrade for higher limits when needed
 

docs/architecture.md

@@ -13,11 +13,11 @@ input:
       as handling the initial user input, presenting the final output, and
       managing the overall user experience.
     - **Key functions contained in the package:**
-      - [Input processing](/docs/cli/commands.md)
+      - [Input processing](/docs/cli/commands)
       - History management
       - Display rendering
-      - [Theme and UI customization](/docs/cli/themes.md)
-      - [CLI configuration settings](/docs/get-started/configuration.md)
+      - [Theme and UI customization](/docs/cli/themes)
+      - [CLI configuration settings](/docs/get-started/configuration)
 
 2.  **Core package (`packages/core`):**
     - **Purpose:** This acts as the backend for the Gemini CLI. It receives

docs/changelogs/index.md

@@ -18,6 +18,31 @@ on GitHub.
 | [Preview](preview.md) | Experimental features ready for early feedback. |
 | [Stable](latest.md)   | Stable, recommended for general use.            |
 
+## Announcements: v0.23.0 - 2026-01-07
+
+- 🎉 **Experimental Agent Skills Support in Preview:** Gemini CLI now supports
+  [Agent Skills](https://agentskills.io/home) in our preview builds. This is an
+  early preview where we’re looking for feedback!
+  - Install Preview: `npm install -g @google/gemini-cli@preview`
+  - Enable in `/settings`
+  - Docs:
+    [https://geminicli.com/docs/cli/skills/](https://geminicli.com/docs/cli/skills/)
+- **Gemini CLI wrapped:** Run `npx gemini-wrapped` to visualize your usage
+  stats, top models, languages, and more!
+- **Windows clipboard image support:** Windows users can now paste images
+  directly from their clipboard into the CLI using `Alt`+`V`.
+  ([pr](https://github.com/google-gemini/gemini-cli/pull/13997) by
+  [@sgeraldes](https://github.com/sgeraldes))
+- **Terminal background color detection:** Automatically optimizes your
+  terminal's background color to select compatible themes and provide
+  accessibility warnings.
+  ([pr](https://github.com/google-gemini/gemini-cli/pull/15132) by
+  [@jacob314](https://github.com/jacob314))
+- **Session logout:** Use the new `/logout` command to instantly clear
+  credentials and reset your authentication state for seamless account
+  switching. ([pr](https://github.com/google-gemini/gemini-cli/pull/13383) by
+  [@CN-Scars](https://github.com/CN-Scars))
+
 ## Announcements: v0.22.0 - 2025-12-22
 
 - 🎉**Free Tier + Gemini 3:** Free tier users now all have access to Gemini 3

docs/changelogs/latest.md

@@ -1,6 +1,6 @@
-# Latest stable release: v0.22.0 - v0.22.5
+# Latest stable release: v0.23.0
 
-Released: December 30, 2025
+Released: January 6, 2026
 
 For most users, our latest stable release is the recommended release. Install
 the latest stable version with:
@@ -11,143 +11,155 @@ npm install -g @google/gemini-cli
 
 ## Highlights
 
-- **Comprehensive quota visibility:** View usage statistics for all available
-  models in the `/stats` command, even those not yet used in your current
-  session. ([pic](https://imgur.com/a/cKyDtYh),
-  [pr](https://github.com/google-gemini/gemini-cli/pull/14764) by
-  [@sehoon38](https://github.com/sehoon38))
-- **Polished CLI statistics:** We’ve cleaned up the `/stats` view to prioritize
-  actionable quota information while providing a detailed token and
-  cache-efficiency breakdown in `/stats model`
-  ([login with Google](https://imgur.com/a/w9xKthm),
-  [api key](https://imgur.com/a/FjQPHOY),
-  [model stats](https://imgur.com/a/VfWzVgw),
-  [pr](https://github.com/google-gemini/gemini-cli/pull/14961) by
+- **Gemini CLI wrapped:** Run `npx gemini-wrapped` to visualize your usage
+  stats, top models, languages, and more!
+- **Windows clipboard image support:** Windows users can now paste images
+  directly from their clipboard into the CLI using `Alt`+`V`.
+  ([pr](https://github.com/google-gemini/gemini-cli/pull/13997) by
+  [@sgeraldes](https://github.com/sgeraldes))
+- **Terminal background color detection:** Automatically optimizes your
+  terminal's background color to select compatible themes and provide
+  accessibility warnings.
+  ([pr](https://github.com/google-gemini/gemini-cli/pull/15132) by
   [@jacob314](https://github.com/jacob314))
-- **Multi-file drag & drop:** Multi-file drag & drop is now supported and
-  properly translated to be prefixed with `@`.
-  ([pr](https://github.com/google-gemini/gemini-cli/pull/14832) by
-  [@jackwotherspoon](https://github.com/jackwotherspoon))
+- **Session logout:** Use the new `/logout` command to instantly clear
+  credentials and reset your authentication state for seamless account
+  switching. ([pr](https://github.com/google-gemini/gemini-cli/pull/13383) by
+  [@CN-Scars](https://github.com/CN-Scars))
 
-## What's Changed
+## What's changed
 
-- feat(ide): fallback to GEMINI_CLI_IDE_AUTH_TOKEN env var by @skeshive in
-  https://github.com/google-gemini/gemini-cli/pull/14843
-- feat: display quota stats for unused models in /stats by @sehoon38 in
-  https://github.com/google-gemini/gemini-cli/pull/14764
-- feat: ensure codebase investigator uses preview model when main agent does by
-  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/14412
-- chore: add closing reason to stale bug workflow by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/14861
-- Send the model and CLI version with the user agent by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/14865
-- refactor(sessions): move session summary generation to startup by
-  @jackwotherspoon in https://github.com/google-gemini/gemini-cli/pull/14691
-- Limit search depth in path corrector by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/14869
-- Fix: Correct typo in code comment by @kuishou68 in
-  https://github.com/google-gemini/gemini-cli/pull/14671
-- feat(core): Plumbing for late resolution of model configs. by @joshualitt in
-  https://github.com/google-gemini/gemini-cli/pull/14597
-- feat: attempt more error parsing by @adamfweidman in
-  https://github.com/google-gemini/gemini-cli/pull/14899
-- Add missing await. by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/14910
-- feat(core): Add support for transcript_path in hooks for git-ai/Gemini
-  extension by @svarlamov in
-  https://github.com/google-gemini/gemini-cli/pull/14663
-- refactor: implement DelegateToAgentTool with discriminated union by
-  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/14769
-- feat: reset availabilityService on /auth by @adamfweidman in
-  https://github.com/google-gemini/gemini-cli/pull/14911
-- chore/release: bump version to 0.21.0-nightly.20251211.8c83e1ea9 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/14924
-- Fix: Correctly detect MCP tool errors by @kevin-ramdass in
-  https://github.com/google-gemini/gemini-cli/pull/14937
-- increase labeler timeout by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/14922
-- tool(cli): tweak the frontend tool to be aware of more core files from the cli
-  by @jacob314 in https://github.com/google-gemini/gemini-cli/pull/14962
-- feat(cli): polish cached token stats and simplify stats display when quota is
-  present. by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/14961
-- feat(settings-validation): add validation for settings schema by @lifefloating
-  in https://github.com/google-gemini/gemini-cli/pull/12929
-- fix(ide): Update IDE extension to write auth token in env var by @skeshive in
-  https://github.com/google-gemini/gemini-cli/pull/14999
-- Revert "chore(deps): bump express from 5.1.0 to 5.2.0" by @skeshive in
-  https://github.com/google-gemini/gemini-cli/pull/14998
-- feat(a2a): Introduce /init command for a2a server by @cocosheng-g in
-  https://github.com/google-gemini/gemini-cli/pull/13419
-- feat: support multi-file drag and drop of images by @jackwotherspoon in
-  https://github.com/google-gemini/gemini-cli/pull/14832
-- fix(policy): allow codebase_investigator by default in read-only policy by
-  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15000
-- refactor(ide ext): Update port file name + switch to 1-based index for
-  characters + remove truncation text by @skeshive in
-  https://github.com/google-gemini/gemini-cli/pull/10501
-- fix(vscode-ide-companion): correct license generation for workspace
-  dependencies by @skeshive in
-  https://github.com/google-gemini/gemini-cli/pull/15004
-- fix: temp fix for subagent invocation until subagent delegation is merged to
-  stable by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15007
-- test: update ide detection tests to make them more robust when run in an ide
-  by @kevin-ramdass in https://github.com/google-gemini/gemini-cli/pull/15008
-- Remove flex from stats display. See snapshots for diffs. by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/14983
-- Add license field into package.json by @jb-perez in
-  https://github.com/google-gemini/gemini-cli/pull/14473
-- feat: Persistent "Always Allow" policies with granular shell & MCP support by
-  @allenhutchison in https://github.com/google-gemini/gemini-cli/pull/14737
-- chore/release: bump version to 0.21.0-nightly.20251212.54de67536 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/14969
-- fix(core): commandPrefix word boundary and compound command safety by
-  @allenhutchison in https://github.com/google-gemini/gemini-cli/pull/15006
-- chore(docs): add 'Maintainers only' label info to CONTRIBUTING.md by @jacob314
-  in https://github.com/google-gemini/gemini-cli/pull/14914
-- Refresh hooks when refreshing extensions. by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/14918
-- Add clarity to error messages by @gsehgal in
-  https://github.com/google-gemini/gemini-cli/pull/14879
-- chore : remove a redundant tip by @JayadityaGit in
-  https://github.com/google-gemini/gemini-cli/pull/14947
-- chore/release: bump version to 0.21.0-nightly.20251213.977248e09 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15029
-- Disallow redundant typecasts. by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/15030
-- fix(auth): prioritize GEMINI_API_KEY env var and skip unnecessary key… by
-  @galz10 in https://github.com/google-gemini/gemini-cli/pull/14745
-- fix: use zod for safety check result validation by @allenhutchison in
-  https://github.com/google-gemini/gemini-cli/pull/15026
-- update(telemetry): add hashed_extension_name to field to extension events by
-  @kiranani in https://github.com/google-gemini/gemini-cli/pull/15025
-- fix: similar to policy-engine, throw error in case of requiring tool execution
-  confirmation for non-interactive mode by @MayV in
-  https://github.com/google-gemini/gemini-cli/pull/14702
-- Clean up processes in integration tests by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15102
-- docs: update policy engine getting started and defaults by @NTaylorMullen in
-  https://github.com/google-gemini/gemini-cli/pull/15105
-- Fix tool output fragmentation by encapsulating content in functionResponse by
-  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/13082
-- Simplify method signature. by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15114
-- Show raw input token counts in json output. by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/15021
-- fix: Mark A2A requests as interactive by @MayV in
-  https://github.com/google-gemini/gemini-cli/pull/15108
-- use previewFeatures to determine which pro model to use for A2A by @sehoon38
-  in https://github.com/google-gemini/gemini-cli/pull/15131
-- refactor(cli): fix settings merging so that settings using the new json format
-  take priority over ones using the old format by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/15116
-- fix(patch): cherry-pick a6d1245 to release/v0.22.0-preview.1-pr-15214 to patch
-  version v0.22.0-preview.1 and create version 0.22.0-preview.2 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15226
-- fix(patch): cherry-pick 9e6914d to release/v0.22.0-preview.2-pr-15288 to patch
-  version v0.22.0-preview.2 and create version 0.22.0-preview.3 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15294
+- Code assist service metrics. by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15024
+- chore/release: bump version to 0.21.0-nightly.20251216.bb0c0d8ee by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15121
+- Docs by @Roaimkhan in https://github.com/google-gemini/gemini-cli/pull/15103
+- Use official ACP SDK and support HTTP/SSE based MCP servers by @SteffenDE in
+  https://github.com/google-gemini/gemini-cli/pull/13856
+- Remove foreground for themes other than shades of purple and holiday. by
+  @jacob314 in https://github.com/google-gemini/gemini-cli/pull/14606
+- chore: remove repo specific tips by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15164
+- chore: remove user query from footer in debug mode by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15169
+- Disallow unnecessary awaits. by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15172
+- Add one to the padding in settings dialog to avoid flicker. by @jacob314 in
+  https://github.com/google-gemini/gemini-cli/pull/15173
+- feat(core): introduce remote agent infrastructure and rename local executor by
+  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15110
+- feat(cli): Add `/auth logout` command to clear credentials and auth state by
+  @CN-Scars in https://github.com/google-gemini/gemini-cli/pull/13383
+- (fix) Automated pr labeller by @DaanVersavel in
+  https://github.com/google-gemini/gemini-cli/pull/14885
+- feat: launch Gemini 3 Flash in Gemini CLI ⚡️⚡️⚡️ by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15196
+- Refactor: Migrate console.error in ripGrep.ts to debugLogger by @Adib234 in
+  https://github.com/google-gemini/gemini-cli/pull/15201
+- chore: update a2a-js to 0.3.7 by @adamfweidman in
+  https://github.com/google-gemini/gemini-cli/pull/15197
+- chore(core): remove redundant isModelAvailabilityServiceEnabled toggle and
+  clean up dead code by @adamfweidman in
+  https://github.com/google-gemini/gemini-cli/pull/15207
+- feat(core): Late resolve `GenerateContentConfig`s and reduce mutation. by
+  @joshualitt in https://github.com/google-gemini/gemini-cli/pull/14920
+- Respect previewFeatures value from the remote flag if undefined by @sehoon38
+  in https://github.com/google-gemini/gemini-cli/pull/15214
+- feat(ui): add Windows clipboard image support and Alt+V paste workaround by
+  @jacob314 in https://github.com/google-gemini/gemini-cli/pull/15218
+- chore(core): remove legacy fallback flags and migrate loop detection by
+  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15213
+- fix(ui): Prevent eager slash command completion hiding sibling commands by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15224
+- Docs: Update Changelog for Dec 17, 2025 by @jkcinouye in
+  https://github.com/google-gemini/gemini-cli/pull/15204
+- Code Assist backend telemetry for user accept/reject of suggestions by
+  @gundermanc in https://github.com/google-gemini/gemini-cli/pull/15206
+- fix(cli): correct initial history length handling for chat commands by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15223
+- chore/release: bump version to 0.21.0-nightly.20251218.739c02bd6 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15231
+- Change detailed model stats to use a new shared Table class to resolve
+  robustness issues. by @jacob314 in
+  https://github.com/google-gemini/gemini-cli/pull/15208
+- feat: add agent toml parser by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15112
+- Add core tool that adds all context from the core package. by @jacob314 in
+  https://github.com/google-gemini/gemini-cli/pull/15238
+- (docs): Add reference section to hooks documentation by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15159
+- feat(hooks): add support for friendly names and descriptions by @abhipatel12
+  in https://github.com/google-gemini/gemini-cli/pull/15174
+- feat: Detect background color by @jacob314 in
+  https://github.com/google-gemini/gemini-cli/pull/15132
+- add 3.0 to allowed sensitive keywords by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15276
+- feat: Pass additional environment variables to shell execution by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15160
+- Remove unused code by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15290
+- Handle all 429 as retryableQuotaError by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15288
+- Remove unnecessary dependencies by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15291
+- fix: prevent infinite loop in prompt completion on error by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/14548
+- fix(ui): show command suggestions even on perfect match and sort them by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15287
+- feat(hooks): reduce log verbosity and improve error reporting in UI by
+  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15297
+- feat: simplify tool confirmation labels for better UX by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15296
+- chore/release: bump version to 0.21.0-nightly.20251219.70696e364 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15301
+- feat(core): Implement JIT context memory loading and UI sync by @SandyTao520
+  in https://github.com/google-gemini/gemini-cli/pull/14469
+- feat(ui): Put "Allow for all future sessions" behind a setting off by default.
+  by @jacob314 in https://github.com/google-gemini/gemini-cli/pull/15322
+- fix(cli):change the placeholder of input during the shell mode by
+  @JayadityaGit in https://github.com/google-gemini/gemini-cli/pull/15135
+- Validate OAuth resource parameter matches MCP server URL by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15289
+- docs(cli): add System Prompt Override (GEMINI_SYSTEM_MD) by @ashmod in
+  https://github.com/google-gemini/gemini-cli/pull/9515
+- more robust command parsing logs by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15339
+- Introspection agent demo by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15232
+- fix(core): sanitize hook command expansion and prevent injection by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15343
+- fix(folder trust): add validation for trusted folder level by @adamfweidman in
+  https://github.com/google-gemini/gemini-cli/pull/12215
+- fix(cli): fix right border overflow in trust dialogs by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15350
+- fix(policy): fix bug where accepting-edits continued after it was turned off
+  by @jacob314 in https://github.com/google-gemini/gemini-cli/pull/15351
+- fix: prevent infinite relaunch loop when --resume fails (#14941) by @Ying-xi
+  in https://github.com/google-gemini/gemini-cli/pull/14951
+- chore/release: bump version to 0.21.0-nightly.20251220.41a1a3eed by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15352
+- feat(telemetry): add clearcut logging for hooks by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15405
+- fix(core): Add `.geminiignore` support to SearchText tool by @xyrolle in
+  https://github.com/google-gemini/gemini-cli/pull/13763
+- fix(patch): cherry-pick 0843d9a to release/v0.23.0-preview.0-pr-15443 to patch
+  version v0.23.0-preview.0 and create version 0.23.0-preview.1 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15445
+- fix(patch): cherry-pick 9cdb267 to release/v0.23.0-preview.1-pr-15494 to patch
+  version v0.23.0-preview.1 and create version 0.23.0-preview.2 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15592
+- fix(patch): cherry-pick 37be162 to release/v0.23.0-preview.2-pr-15601 to patch
+  version v0.23.0-preview.2 and create version 0.23.0-preview.3 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15603
+- fix(patch): cherry-pick 07e597d to release/v0.23.0-preview.3-pr-15684
+  [CONFLICTS] by @gemini-cli-robot in
+  https://github.com/google-gemini/gemini-cli/pull/15734
+- fix(patch): cherry-pick c31f053 to release/v0.23.0-preview.4-pr-16004 to patch
+  version v0.23.0-preview.4 and create version 0.23.0-preview.5 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/16027
+- fix(patch): cherry-pick 788bb04 to release/v0.23.0-preview.5-pr-15817
+  [CONFLICTS] by @gemini-cli-robot in
+  https://github.com/google-gemini/gemini-cli/pull/16038
 
-**Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.21.3...v0.22.0
+**Full changelog**:
+https://github.com/google-gemini/gemini-cli/compare/v0.22.5...v0.23.0

docs/changelogs/preview.md

@@ -1,6 +1,6 @@
-# Preview release: Release v0.23.0-preview.0
+# Preview release: Release v0.24.0-preview.0
 
-Released: December 22, 2025
+Released: January 6, 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).
@@ -11,121 +11,214 @@ To install the preview release:
 npm install -g @google/gemini-cli@preview
 ```
 
-## What's Changed
+## What's changed
 
-- Code assist service metrics. by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/15024
-- chore/release: bump version to 0.21.0-nightly.20251216.bb0c0d8ee by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15121
-- Docs by @Roaimkhan in https://github.com/google-gemini/gemini-cli/pull/15103
-- Use official ACP SDK and support HTTP/SSE based MCP servers by @SteffenDE in
-  https://github.com/google-gemini/gemini-cli/pull/13856
-- Remove foreground for themes other than shades of purple and holiday. by
-  @jacob314 in https://github.com/google-gemini/gemini-cli/pull/14606
-- chore: remove repo specific tips by @jackwotherspoon in
-  https://github.com/google-gemini/gemini-cli/pull/15164
-- chore: remove user query from footer in debug mode by @jackwotherspoon in
-  https://github.com/google-gemini/gemini-cli/pull/15169
-- Disallow unnecessary awaits. by @gundermanc in
-  https://github.com/google-gemini/gemini-cli/pull/15172
-- Add one to the padding in settings dialog to avoid flicker. by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/15173
-- feat(core): introduce remote agent infrastructure and rename local executor by
-  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15110
-- feat(cli): Add `/auth logout` command to clear credentials and auth state by
-  @CN-Scars in https://github.com/google-gemini/gemini-cli/pull/13383
-- (fix) Automated pr labeler by @DaanVersavel in
-  https://github.com/google-gemini/gemini-cli/pull/14885
-- feat: launch Gemini 3 Flash in Gemini CLI ⚡️⚡️⚡️ by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15196
-- Refactor: Migrate console.error in ripGrep.ts to debugLogger by @Adib234 in
-  https://github.com/google-gemini/gemini-cli/pull/15201
-- chore: update a2a-js to 0.3.7 by @adamfweidman in
-  https://github.com/google-gemini/gemini-cli/pull/15197
-- chore(core): remove redundant isModelAvailabilityServiceEnabled toggle and
-  clean up dead code by @adamfweidman in
-  https://github.com/google-gemini/gemini-cli/pull/15207
-- feat(core): Late resolve `GenerateContentConfig`s and reduce mutation. by
-  @joshualitt in https://github.com/google-gemini/gemini-cli/pull/14920
-- Respect previewFeatures value from the remote flag if undefined by @sehoon38
-  in https://github.com/google-gemini/gemini-cli/pull/15214
-- feat(ui): add Windows clipboard image support and Alt+V paste workaround by
-  @jacob314 in https://github.com/google-gemini/gemini-cli/pull/15218
-- chore(core): remove legacy fallback flags and migrate loop detection by
-  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15213
-- fix(ui): Prevent eager slash command completion hiding sibling commands by
-  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15224
-- Docs: Update Changelog for Dec 17, 2025 by @jkcinouye in
-  https://github.com/google-gemini/gemini-cli/pull/15204
-- Code Assist backend telemetry for user accept/reject of suggestions by
-  @gundermanc in https://github.com/google-gemini/gemini-cli/pull/15206
-- fix(cli): correct initial history length handling for chat commands by
-  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15223
-- chore/release: bump version to 0.21.0-nightly.20251218.739c02bd6 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15231
-- Change detailed model stats to use a new shared Table class to resolve
-  robustness issues. by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/15208
-- feat: add agent toml parser by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15112
-- Add core tool that adds all context from the core package. by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/15238
-- (docs): Add reference section to hooks documentation by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15159
-- feat(hooks): add support for friendly names and descriptions by @abhipatel12
-  in https://github.com/google-gemini/gemini-cli/pull/15174
-- feat: Detect background color by @jacob314 in
-  https://github.com/google-gemini/gemini-cli/pull/15132
-- add 3.0 to allowed sensitive keywords by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15276
-- feat: Pass additional environment variables to shell execution by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/15160
-- Remove unused code by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15290
-- Handle all 429 as retryableQuotaError by @sehoon38 in
-  https://github.com/google-gemini/gemini-cli/pull/15288
-- Remove unnecessary dependencies by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15291
-- fix: prevent infinite loop in prompt completion on error by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/14548
-- fix(ui): show command suggestions even on perfect match and sort them by
-  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15287
-- feat(hooks): reduce log verbosity and improve error reporting in UI by
-  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15297
-- feat: simplify tool confirmation labels for better UX by @NTaylorMullen in
-  https://github.com/google-gemini/gemini-cli/pull/15296
-- chore/release: bump version to 0.21.0-nightly.20251219.70696e364 by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15301
-- feat(core): Implement JIT context memory loading and UI sync by @SandyTao520
-  in https://github.com/google-gemini/gemini-cli/pull/14469
-- feat(ui): Put "Allow for all future sessions" behind a setting off by default.
-  by @jacob314 in https://github.com/google-gemini/gemini-cli/pull/15322
-- fix(cli):change the placeholder of input during the shell mode by
-  @JayadityaGit in https://github.com/google-gemini/gemini-cli/pull/15135
-- Validate OAuth resource parameter matches MCP server URL by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/15289
-- docs(cli): add System Prompt Override (GEMINI_SYSTEM_MD) by @ashmod in
-  https://github.com/google-gemini/gemini-cli/pull/9515
-- more robust command parsing logs by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15339
-- Introspection agent demo by @scidomino in
-  https://github.com/google-gemini/gemini-cli/pull/15232
-- fix(core): sanitize hook command expansion and prevent injection by
-  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15343
-- fix(folder trust): add validation for trusted folder level by @adamfweidman in
-  https://github.com/google-gemini/gemini-cli/pull/12215
-- fix(cli): fix right border overflow in trust dialogs by @galz10 in
-  https://github.com/google-gemini/gemini-cli/pull/15350
-- fix(policy): fix bug where accepting-edits continued after it was turned off
-  by @jacob314 in https://github.com/google-gemini/gemini-cli/pull/15351
-- fix: prevent infinite relaunch loop when --resume fails (#14941) by @Ying-xi
-  in https://github.com/google-gemini/gemini-cli/pull/14951
-- chore/release: bump version to 0.21.0-nightly.20251220.41a1a3eed by
-  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15352
-- feat(telemetry): add clearcut logging for hooks by @abhipatel12 in
-  https://github.com/google-gemini/gemini-cli/pull/15405
-- fix(core): Add `.geminiignore` support to SearchText tool by @xyrolle in
-  https://github.com/google-gemini/gemini-cli/pull/13763
+- chore(core): refactor model resolution and cleanup fallback logic by
+  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15228
+- Add Folder Trust Support To Hooks by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15325
+- Record timestamp with code assist metrics. by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15439
+- feat(policy): implement dynamic mode-aware policy evaluation by @abhipatel12
+  in https://github.com/google-gemini/gemini-cli/pull/15307
+- fix(core): use debugLogger.debug for startup profiler logs by @NTaylorMullen
+  in https://github.com/google-gemini/gemini-cli/pull/15443
+- feat(ui): Add security warning and improve layout for Hooks list by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15440
+- fix #15369, prevent crash on unhandled EIO error in readStdin cleanup by
+  @ElecTwix in https://github.com/google-gemini/gemini-cli/pull/15410
+- chore: improve error messages for --resume by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15360
+- chore: remove clipboard file by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15447
+- Implemented unified secrets sanitization and env. redaction options by
+  @gundermanc in https://github.com/google-gemini/gemini-cli/pull/15348
+- feat: automatic `/model` persistence across Gemini CLI sessions by @niyasrad
+  in https://github.com/google-gemini/gemini-cli/pull/13199
+- refactor(core): remove deprecated permission aliases from BeforeToolHookOutput
+  by @StoyanD in https://github.com/google-gemini/gemini-cli/pull/14855
+- fix: add missing `type` field to MCPServerConfig by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15465
+- Make schema validation errors non-fatal by @jacob314 in
+  https://github.com/google-gemini/gemini-cli/pull/15487
+- chore: limit MCP resources display to 10 by default by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15489
+- Add experimental in-CLI extension install and uninstall subcommands by
+  @chrstnb in https://github.com/google-gemini/gemini-cli/pull/15178
+- feat: Add A2A Client Manager and tests by @adamfweidman in
+  https://github.com/google-gemini/gemini-cli/pull/15485
+- feat: terse transformations of image paths in text buffer by @psinha40898 in
+  https://github.com/google-gemini/gemini-cli/pull/4924
+- Security: Project-level hook warnings by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15470
+- Added modifyOtherKeys protocol support for tmux by @ved015 in
+  https://github.com/google-gemini/gemini-cli/pull/15524
+- chore(core): fix comment typo by @Mapleeeeeeeeeee in
+  https://github.com/google-gemini/gemini-cli/pull/15558
+- feat: Show snowfall animation for holiday theme by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15494
+- do not persist the fallback model by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15483
+- Resolve unhandled promise rejection in ide-client.ts by @Adib234 in
+  https://github.com/google-gemini/gemini-cli/pull/15587
+- fix(core): handle checkIsRepo failure in GitService.initialize by
+  @Mapleeeeeeeeeee in https://github.com/google-gemini/gemini-cli/pull/15574
+- fix(cli): add enableShellOutputEfficiency to settings schema by
+  @Mapleeeeeeeeeee in https://github.com/google-gemini/gemini-cli/pull/15560
+- Manual nightly version bump to 0.24.0-nightly.20251226.546baf993 by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15594
+- refactor(core): extract static concerns from CoreToolScheduler by @abhipatel12
+  in https://github.com/google-gemini/gemini-cli/pull/15589
+- fix(core): enable granular shell command allowlisting in policy engine by
+  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15601
+- chore/release: bump version to 0.24.0-nightly.20251227.37be16243 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15612
+- refactor: deprecate legacy confirmation settings and enforce Policy Engine by
+  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15626
+- Migrate console to coreEvents.emitFeedback or debugLogger by @Adib234 in
+  https://github.com/google-gemini/gemini-cli/pull/15219
+- Exponential back-off retries for retryable error without a specified … by
+  @sehoon38 in https://github.com/google-gemini/gemini-cli/pull/15684
+- feat(agents): add support for remote agents and multi-agent TOML files by
+  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15437
+- Update wittyPhrases.ts by @segyges in
+  https://github.com/google-gemini/gemini-cli/pull/15697
+- refactor(auth): Refactor non-interactive mode auth validation & refresh by
+  @skeshive in https://github.com/google-gemini/gemini-cli/pull/15679
+- Revert "Update wittyPhrases.ts (#15697)" by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15719
+- fix(hooks): deduplicate agent hooks and add cross-platform integration tests
+  by @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15701
+- Implement support for tool input modification by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15492
+- Add instructions to the extensions update info notification by @chrstnb in
+  https://github.com/google-gemini/gemini-cli/pull/14907
+- Add extension settings info to /extensions list by @chrstnb in
+  https://github.com/google-gemini/gemini-cli/pull/14905
+- Agent Skills: Implement Core Skill Infrastructure & Tiered Discovery by
+  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15698
+- chore: remove cot style comments by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15735
+- feat(agents): Add remote agents to agent registry by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15711
+- feat(hooks): implement STOP_EXECUTION and enhance hook decision handling by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15685
+- Fix build issues caused by year-specific linter rule by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15780
+- fix(core): handle unhandled promise rejection in mcp-client-manager by
+  @kamja44 in https://github.com/google-gemini/gemini-cli/pull/14701
+- log fallback mode by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15817
+- Agent Skills: Implement Autonomous Activation Tool & Context Injection by
+  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15725
+- fix(core): improve shell command with redirection detection by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15683
+- Add security docs by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15739
+- feat: add folder suggestions to `/dir add` command by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15724
+- Agent Skills: Implement Agent Integration and System Prompt Awareness by
+  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15728
+- chore: cleanup old smart edit settings by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15832
+- Agent Skills: Status Bar Integration for Skill Counts by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15741
+- fix(core): mock powershell output in shell-utils test by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15831
+- Agent Skills: Unify Representation & Centralize Loading by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15833
+- Unify shell security policy and remove legacy logic by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15770
+- feat(core): restore MessageBus optionality for soft migration (Phase 1) by
+  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15774
+- feat(core): Standardize Tool and Agent Invocation constructors (Phase 2) by
+  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15775
+- feat(core,cli): enforce mandatory MessageBus injection (Phase 3 Hard
+  Migration) by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15776
+- Agent Skills: Extension Support & Security Disclosure by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15834
+- feat(hooks): implement granular stop and block behavior for agent hooks by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15824
+- Agent Skills: Add gemini skills CLI management command by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15837
+- refactor: consolidate EditTool and SmartEditTool by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15857
+- fix(cli): mock fs.readdir in consent tests for Windows compatibility by
+  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15904
+- refactor(core): Extract and integrate ToolExecutor by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15900
+- Fix terminal hang when user exits browser without logging in by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15748
+- fix: avoid SDK warning by not accessing .text getter in logging by @ved015 in
+  https://github.com/google-gemini/gemini-cli/pull/15706
+- Make default settings apply by @devr0306 in
+  https://github.com/google-gemini/gemini-cli/pull/15354
+- chore: rename smart-edit to edit by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15923
+- Opt-in to persist model from /model by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15820
+- fix: prevent /copy crash on Windows by skipping /dev/tty by @ManojINaik in
+  https://github.com/google-gemini/gemini-cli/pull/15657
+- Support context injection via SessionStart hook. by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15746
+- Fix order of preflight by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15941
+- Fix failing unit tests by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15940
+- fix(cli): resolve paste issue on Windows terminals. by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15932
+- Agent Skills: Implement /skills reload by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15865
+- Add setting to support OSC 52 paste by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15336
+- remove manual string when displaying manual model in the footer by @sehoon38
+  in https://github.com/google-gemini/gemini-cli/pull/15967
+- fix(core): use correct interactive check for system prompt by @ppergame in
+  https://github.com/google-gemini/gemini-cli/pull/15020
+- Inform user of missing settings on extensions update by @chrstnb in
+  https://github.com/google-gemini/gemini-cli/pull/15944
+- feat(policy): allow 'modes' in user and admin policies by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15977
+- fix: default folder trust to untrusted for enhanced security by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15943
+- Add description for each settings item in /settings by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15936
+- Use GetOperation to poll for OnboardUser completion by @ishaanxgupta in
+  https://github.com/google-gemini/gemini-cli/pull/15827
+- Agent Skills: Add skill directory to WorkspaceContext upon activation by
+  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15870
+- Fix settings command fallback by @chrstnb in
+  https://github.com/google-gemini/gemini-cli/pull/15926
+- fix: writeTodo construction by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/16014
+- properly disable keyboard modes on exit by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/16006
+- Add workflow to label child issues for rollup by @bdmorgan in
+  https://github.com/google-gemini/gemini-cli/pull/16002
+- feat(ui): add visual indicators for hook execution by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15408
+- fix: image token estimation by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/16004
+- feat(hooks): Add a hooks.enabled setting. by @joshualitt in
+  https://github.com/google-gemini/gemini-cli/pull/15933
+- feat(admin): Introduce remote admin settings & implement
+  secureModeEnabled/mcpEnabled by @skeshive in
+  https://github.com/google-gemini/gemini-cli/pull/15935
+- Remove trailing whitespace in yaml. by @joshualitt in
+  https://github.com/google-gemini/gemini-cli/pull/16036
+- feat(agents): add support for remote agents by @adamfweidman in
+  https://github.com/google-gemini/gemini-cli/pull/16013
+- fix: limit scheduled issue triage queries to prevent argument list too long
+  error by @jerop in https://github.com/google-gemini/gemini-cli/pull/16021
+- ci(github-actions): triage all new issues automatically by @jerop in
+  https://github.com/google-gemini/gemini-cli/pull/16018
+- Fix test. by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/16011
+- fix: hide broken skills object from settings dialog by @korade-krushna in
+  https://github.com/google-gemini/gemini-cli/pull/15766
+- Agent Skills: Initial Documentation & Tutorial by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15869
 
-**Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.22.0-preview.3...v0.23.0-preview.0
+**Full changelog**:
+https://github.com/google-gemini/gemini-cli/compare/v0.23.0-preview.6...v0.24.0-preview.0

docs/changelogs/releases.md

@@ -10,17 +10,398 @@ For the full changelog, including nightly releases, refer to
 [Releases - google-gemini/gemini-cli](https://github.com/google-gemini/gemini-cli/releases)
 on GitHub.
 
-## Current Releases
+## Current releases
 
 | Release channel                           | Notes                                           |
 | :---------------------------------------- | :---------------------------------------------- |
 | Nightly                                   | Nightly release with the most recent changes.   |
-| [Preview](#release-v0230-preview-preview) | Experimental features ready for early feedback. |
-| [Latest](#release-v0220---v0225-latest)   | Stable, recommended for general use.            |
+| [Preview](#release-v0240-preview-preview) | Experimental features ready for early feedback. |
+| [Latest](#release-v0230-latest)           | Stable, recommended for general use.            |
 
-## Release v0.23.0-preview (Preview)
+## Release v0.24.0-preview (Preview)
 
-## What's Changed
+### Highlights
+
+- 🎉 **Experimental Agent Skills Support in Preview:** Gemini CLI now supports
+  [Agent Skills](https://agentskills.io/home) in our preview builds. This is an
+  early preview where we’re looking for feedback!
+  - Install Preview: `npm install -g @google/gemini-cli@preview`
+  - Enable in `/settings`
+  - Docs:
+    [https://geminicli.com/docs/cli/skills/](https://geminicli.com/docs/cli/skills/)
+
+### What's changed
+
+- chore(core): refactor model resolution and cleanup fallback logic by
+  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15228
+- Add Folder Trust Support To Hooks by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15325
+- Record timestamp with code assist metrics. by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15439
+- feat(policy): implement dynamic mode-aware policy evaluation by @abhipatel12
+  in https://github.com/google-gemini/gemini-cli/pull/15307
+- fix(core): use debugLogger.debug for startup profiler logs by @NTaylorMullen
+  in https://github.com/google-gemini/gemini-cli/pull/15443
+- feat(ui): Add security warning and improve layout for Hooks list by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15440
+- fix #15369, prevent crash on unhandled EIO error in readStdin cleanup by
+  @ElecTwix in https://github.com/google-gemini/gemini-cli/pull/15410
+- chore: improve error messages for --resume by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15360
+- chore: remove clipboard file by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15447
+- Implemented unified secrets sanitization and env. redaction options by
+  @gundermanc in https://github.com/google-gemini/gemini-cli/pull/15348
+- feat: automatic `/model` persistence across Gemini CLI sessions by @niyasrad
+  in https://github.com/google-gemini/gemini-cli/pull/13199
+- refactor(core): remove deprecated permission aliases from BeforeToolHookOutput
+  by @StoyanD in https://github.com/google-gemini/gemini-cli/pull/14855
+- fix: add missing `type` field to MCPServerConfig by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15465
+- Make schema validation errors non-fatal by @jacob314 in
+  https://github.com/google-gemini/gemini-cli/pull/15487
+- chore: limit MCP resources display to 10 by default by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15489
+- Add experimental in-CLI extension install and uninstall subcommands by
+  @chrstnb in https://github.com/google-gemini/gemini-cli/pull/15178
+- feat: Add A2A Client Manager and tests by @adamfweidman in
+  https://github.com/google-gemini/gemini-cli/pull/15485
+- feat: terse transformations of image paths in text buffer by @psinha40898 in
+  https://github.com/google-gemini/gemini-cli/pull/4924
+- Security: Project-level hook warnings by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15470
+- Added modifyOtherKeys protocol support for tmux by @ved015 in
+  https://github.com/google-gemini/gemini-cli/pull/15524
+- chore(core): fix comment typo by @Mapleeeeeeeeeee in
+  https://github.com/google-gemini/gemini-cli/pull/15558
+- feat: Show snowfall animation for holiday theme by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15494
+- do not persist the fallback model by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15483
+- Resolve unhandled promise rejection in ide-client.ts by @Adib234 in
+  https://github.com/google-gemini/gemini-cli/pull/15587
+- fix(core): handle checkIsRepo failure in GitService.initialize by
+  @Mapleeeeeeeeeee in https://github.com/google-gemini/gemini-cli/pull/15574
+- fix(cli): add enableShellOutputEfficiency to settings schema by
+  @Mapleeeeeeeeeee in https://github.com/google-gemini/gemini-cli/pull/15560
+- Manual nightly version bump to 0.24.0-nightly.20251226.546baf993 by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15594
+- refactor(core): extract static concerns from CoreToolScheduler by @abhipatel12
+  in https://github.com/google-gemini/gemini-cli/pull/15589
+- fix(core): enable granular shell command allowlisting in policy engine by
+  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15601
+- chore/release: bump version to 0.24.0-nightly.20251227.37be16243 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15612
+- refactor: deprecate legacy confirmation settings and enforce Policy Engine by
+  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15626
+- Migrate console to coreEvents.emitFeedback or debugLogger by @Adib234 in
+  https://github.com/google-gemini/gemini-cli/pull/15219
+- Exponential back-off retries for retryable error without a specified … by
+  @sehoon38 in https://github.com/google-gemini/gemini-cli/pull/15684
+- feat(agents): add support for remote agents and multi-agent TOML files by
+  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15437
+- Update wittyPhrases.ts by @segyges in
+  https://github.com/google-gemini/gemini-cli/pull/15697
+- refactor(auth): Refactor non-interactive mode auth validation & refresh by
+  @skeshive in https://github.com/google-gemini/gemini-cli/pull/15679
+- Revert "Update wittyPhrases.ts (#15697)" by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15719
+- fix(hooks): deduplicate agent hooks and add cross-platform integration tests
+  by @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15701
+- Implement support for tool input modification by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15492
+- Add instructions to the extensions update info notification by @chrstnb in
+  https://github.com/google-gemini/gemini-cli/pull/14907
+- Add extension settings info to /extensions list by @chrstnb in
+  https://github.com/google-gemini/gemini-cli/pull/14905
+- Agent Skills: Implement Core Skill Infrastructure & Tiered Discovery by
+  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15698
+- chore: remove cot style comments by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15735
+- feat(agents): Add remote agents to agent registry by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15711
+- feat(hooks): implement STOP_EXECUTION and enhance hook decision handling by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15685
+- Fix build issues caused by year-specific linter rule by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15780
+- fix(core): handle unhandled promise rejection in mcp-client-manager by
+  @kamja44 in https://github.com/google-gemini/gemini-cli/pull/14701
+- log fallback mode by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15817
+- Agent Skills: Implement Autonomous Activation Tool & Context Injection by
+  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15725
+- fix(core): improve shell command with redirection detection by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15683
+- Add security docs by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15739
+- feat: add folder suggestions to `/dir add` command by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15724
+- Agent Skills: Implement Agent Integration and System Prompt Awareness by
+  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15728
+- chore: cleanup old smart edit settings by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15832
+- Agent Skills: Status Bar Integration for Skill Counts by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15741
+- fix(core): mock powershell output in shell-utils test by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15831
+- Agent Skills: Unify Representation & Centralize Loading by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15833
+- Unify shell security policy and remove legacy logic by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15770
+- feat(core): restore MessageBus optionality for soft migration (Phase 1) by
+  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15774
+- feat(core): Standardize Tool and Agent Invocation constructors (Phase 2) by
+  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15775
+- feat(core,cli): enforce mandatory MessageBus injection (Phase 3 Hard
+  Migration) by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15776
+- Agent Skills: Extension Support & Security Disclosure by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15834
+- feat(hooks): implement granular stop and block behavior for agent hooks by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15824
+- Agent Skills: Add gemini skills CLI management command by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15837
+- refactor: consolidate EditTool and SmartEditTool by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15857
+- fix(cli): mock fs.readdir in consent tests for Windows compatibility by
+  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15904
+- refactor(core): Extract and integrate ToolExecutor by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15900
+- Fix terminal hang when user exits browser without logging in by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15748
+- fix: avoid SDK warning by not accessing .text getter in logging by @ved015 in
+  https://github.com/google-gemini/gemini-cli/pull/15706
+- Make default settings apply by @devr0306 in
+  https://github.com/google-gemini/gemini-cli/pull/15354
+- chore: rename smart-edit to edit by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15923
+- Opt-in to persist model from /model by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15820
+- fix: prevent /copy crash on Windows by skipping /dev/tty by @ManojINaik in
+  https://github.com/google-gemini/gemini-cli/pull/15657
+- Support context injection via SessionStart hook. by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15746
+- Fix order of preflight by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15941
+- Fix failing unit tests by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15940
+- fix(cli): resolve paste issue on Windows terminals. by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15932
+- Agent Skills: Implement /skills reload by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15865
+- Add setting to support OSC 52 paste by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15336
+- remove manual string when displaying manual model in the footer by @sehoon38
+  in https://github.com/google-gemini/gemini-cli/pull/15967
+- fix(core): use correct interactive check for system prompt by @ppergame in
+  https://github.com/google-gemini/gemini-cli/pull/15020
+- Inform user of missing settings on extensions update by @chrstnb in
+  https://github.com/google-gemini/gemini-cli/pull/15944
+- feat(policy): allow 'modes' in user and admin policies by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15977
+- fix: default folder trust to untrusted for enhanced security by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15943
+- Add description for each settings item in /settings by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15936
+- Use GetOperation to poll for OnboardUser completion by @ishaanxgupta in
+  https://github.com/google-gemini/gemini-cli/pull/15827
+- Agent Skills: Add skill directory to WorkspaceContext upon activation by
+  @NTaylorMullen in https://github.com/google-gemini/gemini-cli/pull/15870
+- Fix settings command fallback by @chrstnb in
+  https://github.com/google-gemini/gemini-cli/pull/15926
+- fix: writeTodo construction by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/16014
+- properly disable keyboard modes on exit by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/16006
+- Add workflow to label child issues for rollup by @bdmorgan in
+  https://github.com/google-gemini/gemini-cli/pull/16002
+- feat(ui): add visual indicators for hook execution by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15408
+- fix: image token estimation by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/16004
+- feat(hooks): Add a hooks.enabled setting. by @joshualitt in
+  https://github.com/google-gemini/gemini-cli/pull/15933
+- feat(admin): Introduce remote admin settings & implement
+  secureModeEnabled/mcpEnabled by @skeshive in
+  https://github.com/google-gemini/gemini-cli/pull/15935
+- Remove trailing whitespace in yaml. by @joshualitt in
+  https://github.com/google-gemini/gemini-cli/pull/16036
+- feat(agents): add support for remote agents by @adamfweidman in
+  https://github.com/google-gemini/gemini-cli/pull/16013
+- fix: limit scheduled issue triage queries to prevent argument list too long
+  error by @jerop in https://github.com/google-gemini/gemini-cli/pull/16021
+- ci(github-actions): triage all new issues automatically by @jerop in
+  https://github.com/google-gemini/gemini-cli/pull/16018
+- Fix test. by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/16011
+- fix: hide broken skills object from settings dialog by @korade-krushna in
+  https://github.com/google-gemini/gemini-cli/pull/15766
+- Agent Skills: Initial Documentation & Tutorial by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15869
+
+**Full changelog**:
+https://github.com/google-gemini/gemini-cli/compare/v0.23.0-preview.6...v0.24.0-preview.0
+
+## Release v0.23.0 (Latest)
+
+### Highlights
+
+- **Gemini CLI wrapped:** Run `npx gemini-wrapped` to visualize your usage
+  stats, top models, languages, and more!
+- **Windows clipboard image support:** Windows users can now paste images
+  directly from their clipboard into the CLI using `Alt`+`V`.
+  ([pr](https://github.com/google-gemini/gemini-cli/pull/13997) by
+  [@sgeraldes](https://github.com/sgeraldes))
+- **Terminal background color detection:** Automatically optimizes your
+  terminal's background color to select compatible themes and provide
+  accessibility warnings.
+  ([pr](https://github.com/google-gemini/gemini-cli/pull/15132) by
+  [@jacob314](https://github.com/jacob314))
+- **Session logout:** Use the new `/logout` command to instantly clear
+  credentials and reset your authentication state for seamless account
+  switching. ([pr](https://github.com/google-gemini/gemini-cli/pull/13383) by
+  [@CN-Scars](https://github.com/CN-Scars))
+
+### What's changed
+
+- Code assist service metrics. by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15024
+- chore/release: bump version to 0.21.0-nightly.20251216.bb0c0d8ee by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15121
+- Docs by @Roaimkhan in https://github.com/google-gemini/gemini-cli/pull/15103
+- Use official ACP SDK and support HTTP/SSE based MCP servers by @SteffenDE in
+  https://github.com/google-gemini/gemini-cli/pull/13856
+- Remove foreground for themes other than shades of purple and holiday. by
+  @jacob314 in https://github.com/google-gemini/gemini-cli/pull/14606
+- chore: remove repo specific tips by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15164
+- chore: remove user query from footer in debug mode by @jackwotherspoon in
+  https://github.com/google-gemini/gemini-cli/pull/15169
+- Disallow unnecessary awaits. by @gundermanc in
+  https://github.com/google-gemini/gemini-cli/pull/15172
+- Add one to the padding in settings dialog to avoid flicker. by @jacob314 in
+  https://github.com/google-gemini/gemini-cli/pull/15173
+- feat(core): introduce remote agent infrastructure and rename local executor by
+  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15110
+- feat(cli): Add `/auth logout` command to clear credentials and auth state by
+  @CN-Scars in https://github.com/google-gemini/gemini-cli/pull/13383
+- (fix) Automated pr labeller by @DaanVersavel in
+  https://github.com/google-gemini/gemini-cli/pull/14885
+- feat: launch Gemini 3 Flash in Gemini CLI ⚡️⚡️⚡️ by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15196
+- Refactor: Migrate console.error in ripGrep.ts to debugLogger by @Adib234 in
+  https://github.com/google-gemini/gemini-cli/pull/15201
+- chore: update a2a-js to 0.3.7 by @adamfweidman in
+  https://github.com/google-gemini/gemini-cli/pull/15197
+- chore(core): remove redundant isModelAvailabilityServiceEnabled toggle and
+  clean up dead code by @adamfweidman in
+  https://github.com/google-gemini/gemini-cli/pull/15207
+- feat(core): Late resolve `GenerateContentConfig`s and reduce mutation. by
+  @joshualitt in https://github.com/google-gemini/gemini-cli/pull/14920
+- Respect previewFeatures value from the remote flag if undefined by @sehoon38
+  in https://github.com/google-gemini/gemini-cli/pull/15214
+- feat(ui): add Windows clipboard image support and Alt+V paste workaround by
+  @jacob314 in https://github.com/google-gemini/gemini-cli/pull/15218
+- chore(core): remove legacy fallback flags and migrate loop detection by
+  @adamfweidman in https://github.com/google-gemini/gemini-cli/pull/15213
+- fix(ui): Prevent eager slash command completion hiding sibling commands by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15224
+- Docs: Update Changelog for Dec 17, 2025 by @jkcinouye in
+  https://github.com/google-gemini/gemini-cli/pull/15204
+- Code Assist backend telemetry for user accept/reject of suggestions by
+  @gundermanc in https://github.com/google-gemini/gemini-cli/pull/15206
+- fix(cli): correct initial history length handling for chat commands by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15223
+- chore/release: bump version to 0.21.0-nightly.20251218.739c02bd6 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15231
+- Change detailed model stats to use a new shared Table class to resolve
+  robustness issues. by @jacob314 in
+  https://github.com/google-gemini/gemini-cli/pull/15208
+- feat: add agent toml parser by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15112
+- Add core tool that adds all context from the core package. by @jacob314 in
+  https://github.com/google-gemini/gemini-cli/pull/15238
+- (docs): Add reference section to hooks documentation by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15159
+- feat(hooks): add support for friendly names and descriptions by @abhipatel12
+  in https://github.com/google-gemini/gemini-cli/pull/15174
+- feat: Detect background color by @jacob314 in
+  https://github.com/google-gemini/gemini-cli/pull/15132
+- add 3.0 to allowed sensitive keywords by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15276
+- feat: Pass additional environment variables to shell execution by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15160
+- Remove unused code by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15290
+- Handle all 429 as retryableQuotaError by @sehoon38 in
+  https://github.com/google-gemini/gemini-cli/pull/15288
+- Remove unnecessary dependencies by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15291
+- fix: prevent infinite loop in prompt completion on error by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/14548
+- fix(ui): show command suggestions even on perfect match and sort them by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15287
+- feat(hooks): reduce log verbosity and improve error reporting in UI by
+  @abhipatel12 in https://github.com/google-gemini/gemini-cli/pull/15297
+- feat: simplify tool confirmation labels for better UX by @NTaylorMullen in
+  https://github.com/google-gemini/gemini-cli/pull/15296
+- chore/release: bump version to 0.21.0-nightly.20251219.70696e364 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15301
+- feat(core): Implement JIT context memory loading and UI sync by @SandyTao520
+  in https://github.com/google-gemini/gemini-cli/pull/14469
+- feat(ui): Put "Allow for all future sessions" behind a setting off by default.
+  by @jacob314 in https://github.com/google-gemini/gemini-cli/pull/15322
+- fix(cli):change the placeholder of input during the shell mode by
+  @JayadityaGit in https://github.com/google-gemini/gemini-cli/pull/15135
+- Validate OAuth resource parameter matches MCP server URL by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15289
+- docs(cli): add System Prompt Override (GEMINI_SYSTEM_MD) by @ashmod in
+  https://github.com/google-gemini/gemini-cli/pull/9515
+- more robust command parsing logs by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15339
+- Introspection agent demo by @scidomino in
+  https://github.com/google-gemini/gemini-cli/pull/15232
+- fix(core): sanitize hook command expansion and prevent injection by
+  @SandyTao520 in https://github.com/google-gemini/gemini-cli/pull/15343
+- fix(folder trust): add validation for trusted folder level by @adamfweidman in
+  https://github.com/google-gemini/gemini-cli/pull/12215
+- fix(cli): fix right border overflow in trust dialogs by @galz10 in
+  https://github.com/google-gemini/gemini-cli/pull/15350
+- fix(policy): fix bug where accepting-edits continued after it was turned off
+  by @jacob314 in https://github.com/google-gemini/gemini-cli/pull/15351
+- fix: prevent infinite relaunch loop when --resume fails (#14941) by @Ying-xi
+  in https://github.com/google-gemini/gemini-cli/pull/14951
+- chore/release: bump version to 0.21.0-nightly.20251220.41a1a3eed by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15352
+- feat(telemetry): add clearcut logging for hooks by @abhipatel12 in
+  https://github.com/google-gemini/gemini-cli/pull/15405
+- fix(core): Add `.geminiignore` support to SearchText tool by @xyrolle in
+  https://github.com/google-gemini/gemini-cli/pull/13763
+- fix(patch): cherry-pick 0843d9a to release/v0.23.0-preview.0-pr-15443 to patch
+  version v0.23.0-preview.0 and create version 0.23.0-preview.1 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15445
+- fix(patch): cherry-pick 9cdb267 to release/v0.23.0-preview.1-pr-15494 to patch
+  version v0.23.0-preview.1 and create version 0.23.0-preview.2 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15592
+- fix(patch): cherry-pick 37be162 to release/v0.23.0-preview.2-pr-15601 to patch
+  version v0.23.0-preview.2 and create version 0.23.0-preview.3 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15603
+- fix(patch): cherry-pick 07e597d to release/v0.23.0-preview.3-pr-15684
+  [CONFLICTS] by @gemini-cli-robot in
+  https://github.com/google-gemini/gemini-cli/pull/15734
+- fix(patch): cherry-pick c31f053 to release/v0.23.0-preview.4-pr-16004 to patch
+  version v0.23.0-preview.4 and create version 0.23.0-preview.5 by
+  @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/16027
+- fix(patch): cherry-pick 788bb04 to release/v0.23.0-preview.5-pr-15817
+  [CONFLICTS] by @gemini-cli-robot in
+  https://github.com/google-gemini/gemini-cli/pull/16038
+
+**Full changelog**:
+https://github.com/google-gemini/gemini-cli/compare/v0.22.5...v0.23.0
+
+## Release v0.23.0-preview
+
+### What's changed
 
 - Code assist service metrics. by @gundermanc in
   https://github.com/google-gemini/gemini-cli/pull/15024
@@ -136,10 +517,10 @@ on GitHub.
 - fix(core): Add `.geminiignore` support to SearchText tool by @xyrolle in
   https://github.com/google-gemini/gemini-cli/pull/13763
 
-**Full Changelog**:
+**Full changelog**:
 https://github.com/google-gemini/gemini-cli/compare/v0.22.0-preview.3...v0.23.0-preview.0
 
-## Release v0.22.0 - v0.22.5 (Latest)
+## Release v0.22.0
 
 ### Highlights
 
@@ -161,7 +542,7 @@ https://github.com/google-gemini/gemini-cli/compare/v0.22.0-preview.3...v0.23.0-
   ([pr](https://github.com/google-gemini/gemini-cli/pull/14832) by
   [@jackwotherspoon](https://github.com/jackwotherspoon))
 
-### What's Changed
+### What's changed
 
 - feat(ide): fallback to GEMINI_CLI_IDE_AUTH_TOKEN env var by @skeshive in
   https://github.com/google-gemini/gemini-cli/pull/14843
@@ -281,10 +662,10 @@ https://github.com/google-gemini/gemini-cli/compare/v0.22.0-preview.3...v0.23.0-
   version v0.22.0-preview.2 and create version 0.22.0-preview.3 by
   @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15294
 
-**Full Changelog**:
+**Full changelog**:
 https://github.com/google-gemini/gemini-cli/compare/v0.21.3...v0.22.0
 
-## Release v0.21.0 - v0.21.1
+## Release v0.21.0
 
 ### Highlights
 
@@ -293,7 +674,7 @@ https://github.com/google-gemini/gemini-cli/compare/v0.21.3...v0.22.0
   Features** to `true` to enable Gemini 3. For more information:
   [Gemini 3 Flash is now available in Gemini CLI](https://developers.googleblog.com/gemini-3-flash-is-now-available-in-gemini-cli/).
 
-### What's Changed
+### What's changed
 
 - refactor(stdio): always patch stdout and use createWorkingStdio for clean
   output by @allenhutchison in
@@ -498,12 +879,12 @@ https://github.com/google-gemini/gemini-cli/compare/v0.21.3...v0.22.0
   version v0.21.0-preview.5 and create version 0.21.0-preview.6 by
   @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/15153
 
-**Full Changelog**:
+**Full changelog**:
 https://github.com/google-gemini/gemini-cli/compare/v0.20.2...v0.21.0
 
-## Release v0.22.0-preview-0 (Preview)
+## Release v0.22.0-preview-0
 
-### What's Changed
+### What's changed
 
 - feat(ide): fallback to GEMINI_CLI_IDE_AUTH_TOKEN env var by @skeshive in
   https://github.com/google-gemini/gemini-cli/pull/14843
@@ -617,12 +998,12 @@ https://github.com/google-gemini/gemini-cli/compare/v0.20.2...v0.21.0
   take priority over ones using the old format by @jacob314 in
   https://github.com/google-gemini/gemini-cli/pull/15116
 
-**Full Changelog**:
+**Full changelog**:
 https://github.com/google-gemini/gemini-cli/compare/v0.21.0-preview.6...v0.22.0-preview.0
 
-## Release v0.20.0 - v0.20.2
+## Release v0.20.0
 
-### What's Changed
+### What's changed
 
 - Update error codes when process exiting the gemini cli by @megha1188 in
   https://github.com/google-gemini/gemini-cli/pull/13728
@@ -747,10 +1128,10 @@ https://github.com/google-gemini/gemini-cli/compare/v0.21.0-preview.6...v0.22.0-
   version v0.20.0-preview.2 and create version 0.20.0-preview.5 by
   @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/14752
 
-**Full Changelog**:
+**Full changelog**:
 https://github.com/google-gemini/gemini-cli/compare/v0.19.4...v0.20.0
 
-## Release v0.19.0 - v0.19.4
+## Release v0.19.0
 
 ## Highlights
 
@@ -765,7 +1146,7 @@ https://github.com/google-gemini/gemini-cli/compare/v0.19.4...v0.20.0
     [pr](https://github.com/google-gemini/gemini-cli/pull/12535) by
     [@jackwotherspoon](https://github.com/jackwotherspoon))
 
-### What's Changed
+### What's changed
 
 - Use lenient MCP output schema validator by @cornmander in
   https://github.com/google-gemini/gemini-cli/pull/13521
@@ -849,7 +1230,7 @@ https://github.com/google-gemini/gemini-cli/compare/v0.19.4...v0.20.0
   https://github.com/google-gemini/gemini-cli/pull/12863
 - feat(hooks): Hook Telemetry Infrastructure by @Edilmo in
   https://github.com/google-gemini/gemini-cli/pull/9082
-- fix: (some minor improvements to configs and getPackageJson return behaviour)
+- fix: (some minor improvements to configs and getPackageJson return behavior)
   by @grMLEqomlkkU5Eeinz4brIrOVCUCkJuN in
   https://github.com/google-gemini/gemini-cli/pull/12510
 - feat(hooks): Hook Event Handling by @Edilmo in
@@ -894,12 +1275,12 @@ https://github.com/google-gemini/gemini-cli/compare/v0.19.4...v0.20.0
   [CONFLICTS] by @gemini-cli-robot in
   https://github.com/google-gemini/gemini-cli/pull/14402
 
-**Full Changelog**:
+**Full changelog**:
 https://github.com/google-gemini/gemini-cli/compare/v0.18.4...v0.19.0
 
 ## Release v0.19.0-preview.0
 
-### What's Changed
+### What's changed
 
 - Use lenient MCP output schema validator by @cornmander in
   https://github.com/google-gemini/gemini-cli/pull/13521
@@ -983,7 +1364,7 @@ https://github.com/google-gemini/gemini-cli/compare/v0.18.4...v0.19.0
   https://github.com/google-gemini/gemini-cli/pull/12863
 - feat(hooks): Hook Telemetry Infrastructure by @Edilmo in
   https://github.com/google-gemini/gemini-cli/pull/9082
-- fix: (some minor improvements to configs and getPackageJson return behaviour)
+- fix: (some minor improvements to configs and getPackageJson return behavior)
   by @grMLEqomlkkU5Eeinz4brIrOVCUCkJuN in
   https://github.com/google-gemini/gemini-cli/pull/12510
 - feat(hooks): Hook Event Handling by @Edilmo in
@@ -1025,10 +1406,10 @@ https://github.com/google-gemini/gemini-cli/compare/v0.18.4...v0.19.0
 - Update dependency for modelcontextprotocol/sdk to 1.23.0 by @bbiggs in
   https://github.com/google-gemini/gemini-cli/pull/13827
 
-**Full Changelog**:
+**Full changelog**:
 https://github.com/google-gemini/gemini-cli/compare/v0.18.0-preview.4...v0.19.0-preview.0
 
-## Release v0.18.0 - v0.18.4
+## Release v0.18.0
 
 ### Highlights
 
@@ -1158,5 +1539,5 @@ https://github.com/google-gemini/gemini-cli/compare/v0.18.0-preview.4...v0.19.0-
   version v0.18.0-preview.3 and create version 0.18.0-preview.4 by
   @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/13826
 
-  **Full Changelog**:
+  **Full changelog**:
   https://github.com/google-gemini/gemini-cli/compare/v0.17.1...v0.18.0

docs/cli/commands.md

@@ -73,6 +73,9 @@ Slash commands provide meta-level control over the CLI itself.
 - **`/copy`**
   - **Description:** Copies the last output produced by Gemini CLI to your
     clipboard, for easy sharing or reuse.
+  - **Behavior:**
+    - Local sessions use system clipboard tools (pbcopy/xclip/clip).
+    - Remote sessions (SSH/WSL) use OSC 52 and require terminal support.
   - **Note:** This command requires platform-specific clipboard tools to be
     installed.
     - On Linux, it requires `xclip` or `xsel`. You can typically install them
@@ -164,6 +167,13 @@ Slash commands provide meta-level control over the CLI itself.
   - **Note:** Only available if checkpointing is configured via
     [settings](../get-started/configuration.md). See
     [Checkpointing documentation](../cli/checkpointing.md) for more details.
+
+- [**`/rewind`**](./rewind.md)
+  - **Description:** Browse and rewind previous interactions. Allows you to
+    rewind the conversation, revert file changes, or both. Provides an
+    interactive interface to select the exact point to rewind to.
+  - **Keyboard shortcut:** Press **Esc** twice.
+
 - **`/resume`**
   - **Description:** Browse and resume previous conversation sessions. Opens an
     interactive session browser where you can search, filter, and select from
@@ -194,6 +204,23 @@ Slash commands provide meta-level control over the CLI itself.
     modify them as desired. Changes to some settings are applied immediately,
     while others require a restart.
 
+- [**`/skills`**](./skills.md)
+  - **Description:** (Experimental) Manage Agent Skills, which provide on-demand
+    expertise and specialized workflows.
+  - **Sub-commands:**
+    - **`list`**:
+      - **Description:** List all discovered skills and their current status
+        (enabled/disabled).
+    - **`enable`**:
+      - **Description:** Enable a specific skill by name.
+      - **Usage:** `/skills enable <name>`
+    - **`disable`**:
+      - **Description:** Disable a specific skill by name.
+      - **Usage:** `/skills disable <name>`
+    - **`reload`**:
+      - **Description:** Refresh the list of discovered skills from all tiers
+        (workspace, user, and extensions).
+
 - **`/stats`**
   - **Description:** Display detailed statistics for the current Gemini CLI
     session, including token usage, cached token savings (when available), and

docs/cli/custom-commands.md

@@ -50,7 +50,7 @@ Your command definition files must be written in the TOML format and use the
 ## Handling arguments
 
 Custom commands support two powerful methods for handling arguments. The CLI
-automatically chooses the correct method based on the content of your command\'s
+automatically chooses the correct method based on the content of your command's
 `prompt`.
 
 ### 1. Context-aware injection with `{{args}}`
@@ -96,13 +96,13 @@ Search Results:
 """
 ```
 
-When you run `/grep-code It\'s complicated`:
+When you run `/grep-code It's complicated`:
 
 1. The CLI sees `{{args}}` used both outside and inside `!{...}`.
-2. Outside: The first `{{args}}` is replaced raw with `It\'s complicated`.
+2. Outside: The first `{{args}}` is replaced raw with `It's complicated`.
 3. Inside: The second `{{args}}` is replaced with the escaped version (e.g., on
    Linux: `"It\'s complicated"`).
-4. The command executed is `grep -r "It\'s complicated" .`.
+4. The command executed is `grep -r "It's complicated" .`.
 5. The CLI prompts you to confirm this exact, secure command before execution.
 6. The final prompt is sent.
 
@@ -129,13 +129,13 @@ format and behavior.
 # In: <project>/.gemini/commands/changelog.toml
 # Invoked via: /changelog 1.2.0 added "Support for default argument parsing."
 
-description = "Adds a new entry to the project\'s CHANGELOG.md file."
+description = "Adds a new entry to the project's CHANGELOG.md file."
 prompt = """
 # Task: Update Changelog
 
 You are an expert maintainer of this software project. A user has invoked a command to add a new entry to the changelog.
 
-**The user\'s raw command is appended below your instructions.**
+**The user's raw command is appended below your instructions.**
 
 Your task is to parse the `<version>`, `<change_type>`, and `<message>` from their input and use the `write_file` tool to correctly update the `CHANGELOG.md` file.
 
@@ -147,7 +147,7 @@ The command follows this format: `/changelog <version> <type> <message>`
 1. Read the `CHANGELOG.md` file.
 2. Find the section for the specified `<version>`.
 3. Add the `<message>` under the correct `<type>` heading.
-4. If the version or type section doesn\'t exist, create it.
+4. If the version or type section doesn't exist, create it.
 5. Adhere strictly to the "Keep a Changelog" format.
 """
 ```
@@ -241,7 +241,7 @@ operate on specific files.
 **Example (`review.toml`):**
 
 This command injects the content of a _fixed_ best practices file
-(`docs/best-practices.md`) and uses the user\'s arguments to provide context for
+(`docs/best-practices.md`) and uses the user's arguments to provide context for
 the review.
 
 ```toml
@@ -293,7 +293,7 @@ practice.
 description = "Asks the model to refactor the current context into a pure function."
 
 prompt = """
-Please analyze the code I\'ve provided in the current context.
+Please analyze the code I've provided in the current context.
 Refactor it into a pure function.
 
 Your response should include:

docs/cli/index.md

@@ -25,10 +25,12 @@ overview of Gemini CLI, see the [main documentation page](../index.md).
 
 - **[Checkpointing](./checkpointing.md):** Automatically save and restore
   snapshots of your session and files.
-- **[Enterprise configuration](./enterprise.md):** Deploying and manage Gemini
-  CLI in an enterprise environment.
+- **[Enterprise configuration](./enterprise.md):** Deploy and manage Gemini CLI
+  in an enterprise environment.
 - **[Sandboxing](./sandbox.md):** Isolate tool execution in a secure,
   containerized environment.
+- **[Agent Skills](./skills.md):** (Experimental) Extend the CLI with
+  specialized expertise and procedural workflows.
 - **[Telemetry](./telemetry.md):** Configure observability to monitor usage and
   performance.
 - **[Token caching](./token-caching.md):** Optimize API costs by caching tokens.

docs/cli/keyboard-shortcuts.md

@@ -8,32 +8,39 @@ available combinations.
 
 #### Basic Controls
 
-| Action                                       | Keys    |
-| -------------------------------------------- | ------- |
-| Confirm the current selection or choice.     | `Enter` |
-| Dismiss dialogs or cancel the current focus. | `Esc`   |
+| Action                                                          | Keys       |
+| --------------------------------------------------------------- | ---------- |
+| Confirm the current selection or choice.                        | `Enter`    |
+| Dismiss dialogs or cancel the current focus.                    | `Esc`      |
+| Cancel the current request or quit the CLI when input is empty. | `Ctrl + C` |
+| Exit the CLI when the input buffer is empty.                    | `Ctrl + D` |
 
 #### Cursor Movement
 
-| Action                                    | Keys                   |
-| ----------------------------------------- | ---------------------- |
-| Move the cursor to the start of the line. | `Ctrl + A`<br />`Home` |
-| Move the cursor to the end of the line.   | `Ctrl + E`<br />`End`  |
+| Action                                      | Keys                                                         |
+| ------------------------------------------- | ------------------------------------------------------------ |
+| Move the cursor to the start of the line.   | `Ctrl + A`<br />`Home`                                       |
+| Move the cursor to the end of the line.     | `Ctrl + E`<br />`End`                                        |
+| Move the cursor up one line.                | `Up Arrow (no Ctrl, no Cmd)`                                 |
+| Move the cursor down one line.              | `Down Arrow (no Ctrl, no Cmd)`                               |
+| Move the cursor one character to the left.  | `Left Arrow (no Ctrl, no Cmd)`<br />`Ctrl + B`               |
+| Move the cursor one character to the right. | `Right Arrow (no Ctrl, no Cmd)`<br />`Ctrl + F`              |
+| Move the cursor one word to the left.       | `Ctrl + Left Arrow`<br />`Cmd + Left Arrow`<br />`Cmd + B`   |
+| Move the cursor one word to the right.      | `Ctrl + Right Arrow`<br />`Cmd + Right Arrow`<br />`Cmd + F` |
 
 #### Editing
 
-| Action                                           | Keys                                      |
-| ------------------------------------------------ | ----------------------------------------- |
-| Delete from the cursor to the end of the line.   | `Ctrl + K`                                |
-| Delete from the cursor to the start of the line. | `Ctrl + U`                                |
-| Clear all text in the input field.               | `Ctrl + C`                                |
-| Delete the previous word.                        | `Ctrl + Backspace`<br />`Cmd + Backspace` |
-
-#### Screen Control
-
-| Action                                       | Keys       |
-| -------------------------------------------- | ---------- |
-| Clear the terminal screen and redraw the UI. | `Ctrl + L` |
+| Action                                           | Keys                                                      |
+| ------------------------------------------------ | --------------------------------------------------------- |
+| Delete from the cursor to the end of the line.   | `Ctrl + K`                                                |
+| Delete from the cursor to the start of the line. | `Ctrl + U`                                                |
+| Clear all text in the input field.               | `Ctrl + C`                                                |
+| Delete the previous word.                        | `Ctrl + Backspace`<br />`Cmd + Backspace`<br />`Ctrl + W` |
+| Delete the next word.                            | `Ctrl + Delete`<br />`Cmd + Delete`                       |
+| Delete the character to the left.                | `Backspace`<br />`Ctrl + H`                               |
+| Delete the character to the right.               | `Delete`<br />`Ctrl + D`                                  |
+| Undo the most recent text edit.                  | `Ctrl + Z (no Shift)`                                     |
+| Redo the most recent undone text edit.           | `Ctrl + Shift + Z`                                        |
 
 #### Scrolling
 
@@ -53,7 +60,7 @@ available combinations.
 | Show the previous entry in history.          | `Ctrl + P (no Shift)` |
 | Show the next entry in history.              | `Ctrl + N (no Shift)` |
 | Start reverse search through history.        | `Ctrl + R`            |
-| Insert the selected reverse-search match.    | `Enter (no Ctrl)`     |
+| Submit the selected reverse-search match.    | `Enter (no Ctrl)`     |
 | Accept a suggestion while reverse searching. | `Tab`                 |
 
 #### Navigation
@@ -77,66 +84,40 @@ available combinations.
 
 #### Text Input
 
-| Action                               | Keys                                                                                        |
-| ------------------------------------ | ------------------------------------------------------------------------------------------- |
-| Submit the current prompt.           | `Enter (no Ctrl, no Shift, no Cmd, not Paste)`                                              |
-| Insert a newline without submitting. | `Ctrl + Enter`<br />`Cmd + Enter`<br />`Paste + Enter`<br />`Shift + Enter`<br />`Ctrl + J` |
-
-#### External Tools
-
-| Action                                         | Keys                      |
-| ---------------------------------------------- | ------------------------- |
-| Open the current prompt in an external editor. | `Ctrl + X`                |
-| Paste from the clipboard.                      | `Ctrl + V`<br />`Cmd + V` |
+| Action                                         | Keys                                                                   |
+| ---------------------------------------------- | ---------------------------------------------------------------------- |
+| Submit the current prompt.                     | `Enter (no Ctrl, no Shift, no Cmd)`                                    |
+| Insert a newline without submitting.           | `Ctrl + Enter`<br />`Cmd + 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`                                              |
 
 #### App Controls
 
-| Action                                                            | Keys       |
-| ----------------------------------------------------------------- | ---------- |
-| Toggle detailed error information.                                | `F12`      |
-| Toggle the full TODO list.                                        | `Ctrl + T` |
-| Toggle IDE context details.                                       | `Ctrl + G` |
-| Toggle Markdown rendering.                                        | `Cmd + M`  |
-| Toggle copy mode when the terminal is using the alternate buffer. | `Ctrl + S` |
-| Expand a height-constrained response to show additional lines.    | `Ctrl + S` |
-| Toggle focus between the shell and Gemini input.                  | `Ctrl + F` |
-
-#### Session Control
-
-| Action                                       | Keys       |
-| -------------------------------------------- | ---------- |
-| Cancel the current request or quit the CLI.  | `Ctrl + C` |
-| Exit the CLI when the input buffer is empty. | `Ctrl + D` |
+| Action                                                                                           | Keys             |
+| ------------------------------------------------------------------------------------------------ | ---------------- |
+| Toggle detailed error information.                                                               | `F12`            |
+| Toggle the full TODO list.                                                                       | `Ctrl + T`       |
+| Show IDE context details.                                                                        | `Ctrl + G`       |
+| Toggle Markdown rendering.                                                                       | `Cmd + M`        |
+| Toggle copy mode when in alternate buffer mode.                                                  | `Ctrl + S`       |
+| Toggle YOLO (auto-approval) mode for tool calls.                                                 | `Ctrl + Y`       |
+| Toggle Auto Edit (auto-accept edits) mode.                                                       | `Shift + Tab`    |
+| Expand a height-constrained response to show additional lines when not in alternate buffer mode. | `Ctrl + S`       |
+| Focus the shell input from the gemini input.                                                     | `Tab (no Shift)` |
+| Focus the Gemini input from the shell input.                                                     | `Tab`            |
+| Clear the terminal screen and redraw the UI.                                                     | `Ctrl + L`       |
+| Restart the application.                                                                         | `R`              |
 
 <!-- KEYBINDINGS-AUTOGEN:END -->
 
 ## Additional context-specific shortcuts
 
-- `Ctrl+Y`: Toggle YOLO (auto-approval) mode for tool calls.
-- `Shift+Tab`: Toggle Auto Edit (auto-accept edits) mode.
-- `Option+M` (macOS): Entering `µ` with Option+M also toggles Markdown
-  rendering, matching `Cmd+M`.
+- `Option+B/F/M` (macOS only): Are interpreted as `Cmd+B/F/M` even if your
+  terminal isn't configured to send Meta with Option.
 - `!` on an empty prompt: Enter or exit shell mode.
 - `\` (at end of a line) + `Enter`: Insert a newline without leaving single-line
   mode.
-- `Ctrl+Delete` / `Meta+Delete`: Delete the word to the right of the cursor.
-- `Ctrl+B` or `Left Arrow`: Move the cursor one character to the left while
-  editing text.
-- `Ctrl+F` or `Right Arrow`: Move the cursor one character to the right; with an
-  embedded shell attached, `Ctrl+F` still toggles focus.
-- `Ctrl+D` or `Delete`: Remove the character immediately to the right of the
-  cursor.
-- `Ctrl+H` or `Backspace`: Remove the character immediately to the left of the
-  cursor.
-- `Ctrl+Left Arrow` / `Meta+Left Arrow` / `Meta+B`: Move one word to the left.
-- `Ctrl+Right Arrow` / `Meta+Right Arrow` / `Meta+F`: Move one word to the
-  right.
-- `Ctrl+W`: Delete the word to the left of the cursor (in addition to
-  `Ctrl+Backspace` / `Cmd+Backspace`).
-- `Ctrl+Z` / `Ctrl+Shift+Z`: Undo or redo the most recent text edit.
-- `Meta+Enter`: Open the current input in an external editor (alias for
-  `Ctrl+X`).
-- `Esc` pressed twice quickly: Clear the current input buffer.
+- `Esc` pressed twice quickly: Browse and rewind previous interactions.
 - `Up Arrow` / `Down Arrow`: When the cursor is at the top or bottom of a
   single-line input, navigate backward or forward through prompt history.
 - `Number keys (1-9, multi-digit)` inside selection dialogs: Jump directly to

docs/cli/model-routing.md

@@ -11,7 +11,7 @@ health and automatically routes requests to available models based on defined
 policies.
 
 1.  **Model failure:** If the currently selected model fails (e.g., due to quota
-    or server errors), the CLI will iniate the fallback process.
+    or server errors), the CLI will initiate the fallback process.
 
 2.  **User consent:** Depending on the failure and the model's policy, the CLI
     may prompt you to switch to a fallback model (by default always prompts

docs/cli/sandbox.md

@@ -11,7 +11,7 @@ Before using sandboxing, you need to install and set up the Gemini CLI:
 npm install -g @google/gemini-cli
 ```
 
-To verify the installation
+To verify the installation:
 
 ```bash
 gemini --version

docs/cli/settings.md

@@ -18,45 +18,50 @@ Note: Workspace settings override user settings.
 Here is a list of all the available settings, grouped by category and ordered as
 they appear in the UI.
 
+<!-- SETTINGS-AUTOGEN:START -->
+
 ### General
 
-| UI Label                        | Setting                            | Description                                                                  | Default     |
-| ------------------------------- | ---------------------------------- | ---------------------------------------------------------------------------- | ----------- |
-| Preview Features (e.g., models) | `general.previewFeatures`          | Enable preview features (e.g., preview models).                              | `false`     |
-| Vim Mode                        | `general.vimMode`                  | Enable Vim keybindings.                                                      | `false`     |
-| Disable Auto Update             | `general.disableAutoUpdate`        | Disable automatic updates.                                                   | `false`     |
-| Enable Prompt Completion        | `general.enablePromptCompletion`   | Enable AI-powered prompt completion suggestions while typing.                | `false`     |
-| Debug Keystroke Logging         | `general.debugKeystrokeLogging`    | Enable debug logging of keystrokes to the console.                           | `false`     |
-| Session Retention               | `general.sessionRetention`         | Settings for automatic session cleanup. This feature is disabled by default. | `undefined` |
-| Enable Session Cleanup          | `general.sessionRetention.enabled` | Enable automatic session cleanup.                                            | `false`     |
+| UI Label                        | Setting                            | Description                                                   | Default |
+| ------------------------------- | ---------------------------------- | ------------------------------------------------------------- | ------- |
+| Preview Features (e.g., models) | `general.previewFeatures`          | Enable preview features (e.g., preview models).               | `false` |
+| Vim Mode                        | `general.vimMode`                  | Enable Vim keybindings                                        | `false` |
+| Enable Auto Update              | `general.enableAutoUpdate`         | Enable automatic updates.                                     | `true`  |
+| Enable Prompt Completion        | `general.enablePromptCompletion`   | Enable AI-powered prompt completion suggestions while typing. | `false` |
+| Debug Keystroke Logging         | `general.debugKeystrokeLogging`    | Enable debug logging of keystrokes to the console.            | `false` |
+| Enable Session Cleanup          | `general.sessionRetention.enabled` | Enable automatic session cleanup                              | `false` |
 
 ### Output
 
-| UI Label      | Setting         | Description                                            | Default |
-| ------------- | --------------- | ------------------------------------------------------ | ------- |
-| Output Format | `output.format` | The format of the CLI output. Can be `text` or `json`. | `text`  |
+| UI Label      | Setting         | Description                                            | Default  |
+| ------------- | --------------- | ------------------------------------------------------ | -------- |
+| Output Format | `output.format` | The format of the CLI output. Can be `text` or `json`. | `"text"` |
 
 ### UI
 
-| UI Label                       | Setting                                  | Description                                                          | Default |
-| ------------------------------ | ---------------------------------------- | -------------------------------------------------------------------- | ------- |
-| Hide Window Title              | `ui.hideWindowTitle`                     | Hide the window title bar.                                           | `false` |
-| Show Status in Title           | `ui.showStatusInTitle`                   | Show Gemini CLI status and thoughts in the terminal window title.    | `false` |
-| Hide Tips                      | `ui.hideTips`                            | Hide helpful tips in the UI.                                         | `false` |
-| Hide Banner                    | `ui.hideBanner`                          | Hide the application banner.                                         | `false` |
-| Hide Context Summary           | `ui.hideContextSummary`                  | Hide the context summary (GEMINI.md, MCP servers) above the input.   | `false` |
-| Hide CWD                       | `ui.footer.hideCWD`                      | Hide the current working directory path in the footer.               | `false` |
-| Hide Sandbox Status            | `ui.footer.hideSandboxStatus`            | Hide the sandbox status indicator in the footer.                     | `false` |
-| Hide Model Info                | `ui.footer.hideModelInfo`                | Hide the model name and context usage in the footer.                 | `false` |
-| Hide Context Window Percentage | `ui.footer.hideContextPercentage`        | Hides the context window remaining percentage.                       | `true`  |
-| Hide Footer                    | `ui.hideFooter`                          | Hide the footer from the UI.                                         | `false` |
-| Show Memory Usage              | `ui.showMemoryUsage`                     | Display memory usage information in the UI.                          | `false` |
-| Show Line Numbers              | `ui.showLineNumbers`                     | Show line numbers in the chat.                                       | `false` |
-| Show Citations                 | `ui.showCitations`                       | Show citations for generated text in the chat.                       | `false` |
-| Use Full Width                 | `ui.useFullWidth`                        | Use the entire width of the terminal for output.                     | `true`  |
-| Use Alternate Screen Buffer    | `ui.useAlternateBuffer`                  | Use an alternate screen buffer for the UI, preserving shell history. | `true`  |
-| Disable Loading Phrases        | `ui.accessibility.disableLoadingPhrases` | Disable loading phrases for accessibility.                           | `false` |
-| Screen Reader Mode             | `ui.accessibility.screenReader`          | Render output in plain-text to be more screen reader accessible.     | `false` |
+| UI Label                       | Setting                                 | Description                                                                                                                                                       | Default |
+| ------------------------------ | --------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| Hide Window Title              | `ui.hideWindowTitle`                    | Hide the window title bar                                                                                                                                         | `false` |
+| Show Thoughts in Title         | `ui.showStatusInTitle`                  | Show Gemini CLI model thoughts in the terminal window title during the working phase                                                                              | `false` |
+| Dynamic Window Title           | `ui.dynamicWindowTitle`                 | Update the terminal window title with current status icons (Ready: ◇, Action Required: ✋, Working: ✦)                                                            | `true`  |
+| Show Home Directory Warning    | `ui.showHomeDirectoryWarning`           | Show a warning when running Gemini CLI in the home directory.                                                                                                     | `true`  |
+| Hide Tips                      | `ui.hideTips`                           | Hide helpful tips in the UI                                                                                                                                       | `false` |
+| Hide Banner                    | `ui.hideBanner`                         | Hide the application banner                                                                                                                                       | `false` |
+| Hide Context Summary           | `ui.hideContextSummary`                 | Hide the context summary (GEMINI.md, MCP servers) above the input.                                                                                                | `false` |
+| Hide CWD                       | `ui.footer.hideCWD`                     | Hide the current working directory path in the footer.                                                                                                            | `false` |
+| Hide Sandbox Status            | `ui.footer.hideSandboxStatus`           | Hide the sandbox status indicator in the footer.                                                                                                                  | `false` |
+| Hide Model Info                | `ui.footer.hideModelInfo`               | Hide the model name and context usage in the footer.                                                                                                              | `false` |
+| Hide Context Window Percentage | `ui.footer.hideContextPercentage`       | Hides the context window remaining percentage.                                                                                                                    | `true`  |
+| Hide Footer                    | `ui.hideFooter`                         | Hide the footer from the UI                                                                                                                                       | `false` |
+| Show Memory Usage              | `ui.showMemoryUsage`                    | Display memory usage information in the UI                                                                                                                        | `false` |
+| Show Line Numbers              | `ui.showLineNumbers`                    | Show line numbers in the chat.                                                                                                                                    | `true`  |
+| Show Citations                 | `ui.showCitations`                      | Show citations for generated text in the chat.                                                                                                                    | `false` |
+| Show Model Info In Chat        | `ui.showModelInfoInChat`                | Show the model name in the chat for each model turn.                                                                                                              | `false` |
+| Use Full Width                 | `ui.useFullWidth`                       | Use the entire width of the terminal for output.                                                                                                                  | `true`  |
+| Use Alternate Screen Buffer    | `ui.useAlternateBuffer`                 | Use an alternate screen buffer for the UI, preserving shell history.                                                                                              | `false` |
+| 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`  |
+| Enable Loading Phrases         | `ui.accessibility.enableLoadingPhrases` | Enable loading phrases during operations.                                                                                                                         | `true`  |
+| Screen Reader Mode             | `ui.accessibility.screenReader`         | Render output in plain-text to be more screen reader accessible                                                                                                   | `false` |
 
 ### IDE
 
@@ -69,7 +74,7 @@ they appear in the UI.
 | UI Label                | Setting                      | Description                                                                            | Default |
 | ----------------------- | ---------------------------- | -------------------------------------------------------------------------------------- | ------- |
 | Max Session Turns       | `model.maxSessionTurns`      | Maximum number of user/model/tool turns to keep in a session. -1 means unlimited.      | `-1`    |
-| Compression Threshold   | `model.compressionThreshold` | The fraction of context usage at which to trigger context compression (e.g. 0.2, 0.3). | `0.2`   |
+| Compression Threshold   | `model.compressionThreshold` | The fraction of context usage at which to trigger context compression (e.g. 0.2, 0.3). | `0.5`   |
 | Skip Next Speaker Check | `model.skipNextSpeakerCheck` | Skip the next speaker check.                                                           | `true`  |
 
 ### Context
@@ -81,35 +86,46 @@ they appear in the UI.
 | Respect .gitignore                   | `context.fileFiltering.respectGitIgnore`          | Respect .gitignore files when searching.                                                                                                        | `true`  |
 | Respect .geminiignore                | `context.fileFiltering.respectGeminiIgnore`       | Respect .geminiignore files when searching.                                                                                                     | `true`  |
 | Enable Recursive File Search         | `context.fileFiltering.enableRecursiveFileSearch` | Enable recursive file search functionality when completing @ references in the prompt.                                                          | `true`  |
-| Disable Fuzzy Search                 | `context.fileFiltering.disableFuzzySearch`        | Disable fuzzy search when searching for files.                                                                                                  | `false` |
+| Enable Fuzzy Search                  | `context.fileFiltering.enableFuzzySearch`         | Enable fuzzy search when searching for files.                                                                                                   | `true`  |
 
 ### Tools
 
-| UI Label                         | Setting                              | Description                                                                                                     | Default |
-| -------------------------------- | ------------------------------------ | --------------------------------------------------------------------------------------------------------------- | ------- |
-| Enable Interactive Shell         | `tools.shell.enableInteractiveShell` | Use node-pty for an interactive shell experience. Fallback to child_process still applies.                      | `true`  |
-| Show Color                       | `tools.shell.showColor`              | Show color in shell output.                                                                                     | `false` |
-| Auto Accept                      | `tools.autoAccept`                   | Automatically accept and execute tool calls that are considered safe (e.g., read-only operations).              | `false` |
-| Use Ripgrep                      | `tools.useRipgrep`                   | Use ripgrep for file content search instead of the fallback implementation. Provides faster search performance. | `true`  |
-| Enable Tool Output Truncation    | `tools.enableToolOutputTruncation`   | Enable truncation of large tool outputs.                                                                        | `true`  |
-| Tool Output Truncation Threshold | `tools.truncateToolOutputThreshold`  | Truncate tool output if it is larger than this many characters. Set to -1 to disable.                           | `10000` |
-| Tool Output Truncation Lines     | `tools.truncateToolOutputLines`      | The number of lines to keep when truncating tool output.                                                        | `100`   |
+| UI Label                         | Setting                              | Description                                                                                                                                                                | Default   |
+| -------------------------------- | ------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------- |
+| Enable Interactive Shell         | `tools.shell.enableInteractiveShell` | Use node-pty for an interactive shell experience. Fallback to child_process still applies.                                                                                 | `true`    |
+| Show Color                       | `tools.shell.showColor`              | Show color in shell output.                                                                                                                                                | `false`   |
+| Auto Accept                      | `tools.autoAccept`                   | Automatically accept and execute tool calls that are considered safe (e.g., read-only operations).                                                                         | `false`   |
+| Use Ripgrep                      | `tools.useRipgrep`                   | Use ripgrep for file content search instead of the fallback implementation. Provides faster search performance.                                                            | `true`    |
+| Enable Tool Output Truncation    | `tools.enableToolOutputTruncation`   | Enable truncation of large tool outputs.                                                                                                                                   | `true`    |
+| Tool Output Truncation Threshold | `tools.truncateToolOutputThreshold`  | Truncate tool output if it is larger than this many characters. Set to -1 to disable.                                                                                      | `4000000` |
+| Tool Output Truncation Lines     | `tools.truncateToolOutputLines`      | The number of lines to keep when truncating tool output.                                                                                                                   | `1000`    |
+| Disable LLM Correction           | `tools.disableLLMCorrection`         | Disable LLM-based error correction for edit tools. When enabled, tools will fail immediately if exact string matches are not found, instead of attempting to self-correct. | `false`   |
 
 ### Security
 
-| UI Label                      | Setting                                         | Description                                               | Default |
-| ----------------------------- | ----------------------------------------------- | --------------------------------------------------------- | ------- |
-| Disable YOLO Mode             | `security.disableYoloMode`                      | Disable YOLO mode, even if enabled by a flag.             | `false` |
-| Blocks extensions from Git    | `security.blockGitExtensions`                   | Blocks installing and loading extensions from Git.        | `false` |
-| Folder Trust                  | `security.folderTrust.enabled`                  | Setting to track whether Folder trust is enabled.         | `false` |
-| Allowed Environment Variables | `security.environmentVariableRedaction.allowed` | Environment variables to always allow (bypass redaction). | `[]`    |
-| Blocked Environment Variables | `security.environmentVariableRedaction.blocked` | Environment variables to always redact.                   | `[]`    |
+| UI Label                              | Setting                                         | Description                                                                     | Default |
+| ------------------------------------- | ----------------------------------------------- | ------------------------------------------------------------------------------- | ------- |
+| 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` |
+| Blocks extensions from Git            | `security.blockGitExtensions`                   | Blocks installing and loading extensions from Git.                              | `false` |
+| Folder Trust                          | `security.folderTrust.enabled`                  | Setting to track whether Folder trust is enabled.                               | `false` |
+| Enable Environment Variable Redaction | `security.environmentVariableRedaction.enabled` | Enable redaction of environment variables that may contain secrets.             | `false` |
 
 ### Experimental
 
-| UI Label                            | Setting                                                 | Description                                                  | Default |
-| ----------------------------------- | ------------------------------------------------------- | ------------------------------------------------------------ | ------- |
-| Enable Codebase Investigator        | `experimental.codebaseInvestigatorSettings.enabled`     | Enable the Codebase Investigator agent.                      | `true`  |
-| Codebase Investigator Max Num Turns | `experimental.codebaseInvestigatorSettings.maxNumTurns` | Maximum number of turns for the Codebase Investigator agent. | `10`    |
-| Enable CLI Help Agent               | `experimental.cliHelpAgentSettings.enabled`             | Enable the CLI Help Agent.                                   | `true`  |
-| Agent Skills                        | `experimental.skills`                                   | Enable Agent Skills (experimental).                          | `false` |
+| UI Label                            | Setting                                                 | Description                                                                         | Default |
+| ----------------------------------- | ------------------------------------------------------- | ----------------------------------------------------------------------------------- | ------- |
+| Agent Skills                        | `experimental.skills`                                   | Enable Agent Skills (experimental).                                                 | `false` |
+| Enable Codebase Investigator        | `experimental.codebaseInvestigatorSettings.enabled`     | Enable the Codebase Investigator agent.                                             | `true`  |
+| Codebase Investigator Max Num Turns | `experimental.codebaseInvestigatorSettings.maxNumTurns` | Maximum number of turns for the Codebase Investigator agent.                        | `10`    |
+| Use OSC 52 Paste                    | `experimental.useOSC52Paste`                            | Use OSC 52 sequence for pasting instead of clipboardy (useful for remote sessions). | `false` |
+| Enable CLI Help Agent               | `experimental.cliHelpAgentSettings.enabled`             | Enable the CLI Help Agent.                                                          | `true`  |
+| Plan                                | `experimental.plan`                                     | Enable planning features (Plan Mode and tools).                                     | `false` |
+
+### Hooks
+
+| UI Label           | Setting               | Description                                      | Default |
+| ------------------ | --------------------- | ------------------------------------------------ | ------- |
+| Hook Notifications | `hooks.notifications` | Show visual indicators when hooks are executing. | `true`  |
+
+<!-- SETTINGS-AUTOGEN:END -->

docs/cli/skills.md

@@ -13,7 +13,7 @@ discoverable capability.
 ## Overview
 
 Unlike general context files ([`GEMINI.md`](./gemini-md.md)), which provide
-persistent project-wide background, Skills represent **on-demand expertise**.
+persistent workspace-wide background, Skills represent **on-demand expertise**.
 This allows Gemini to maintain a vast library of specialized capabilities—such
 as security auditing, cloud deployments, or codebase migrations—without
 cluttering the model's immediate context window.
@@ -39,15 +39,15 @@ the full instructions and resources required to complete the task using the
 
 Gemini CLI discovers skills from three primary locations:
 
-1.  **Project Skills** (`.gemini/skills/`): Project-specific skills that are
+1.  **Workspace Skills** (`.gemini/skills/`): Workspace-specific skills that are
     typically committed to version control and shared with the team.
 2.  **User Skills** (`~/.gemini/skills/`): Personal skills available across all
-    your projects.
+    your workspaces.
 3.  **Extension Skills**: Skills bundled within installed
     [extensions](../extensions/index.md).
 
 **Precedence:** If multiple skills share the same name, higher-precedence
-locations override lower ones: **Project > User > Extension**.
+locations override lower ones: **Workspace > User > Extension**.
 
 ## Managing Skills
 
@@ -61,7 +61,7 @@ Use the `/skills` slash command to view and manage available expertise:
 - `/skills reload`: Refreshes the list of discovered skills from all tiers.
 
 _Note: `/skills disable` and `/skills enable` default to the `user` scope. Use
-`--scope project` to manage project-specific settings._
+`--scope workspace` to manage workspace-specific settings._
 
 ### From the Terminal
 
@@ -71,9 +71,26 @@ The `gemini skills` command provides management utilities:
 # List all discovered skills
 gemini skills list
 
-# Enable/disable skills. Can use --scope to specify project or user
+# Install a skill from a Git repository, local directory, or zipped skill file (.skill)
+# Uses the user scope by default (~/.gemini/skills)
+gemini skills install https://github.com/user/repo.git
+gemini skills install /path/to/local/skill
+gemini skills install /path/to/local/my-expertise.skill
+
+# Install a specific skill from a monorepo or subdirectory using --path
+gemini skills install https://github.com/my-org/my-skills.git --path skills/frontend-design
+
+# Install to the workspace scope (.gemini/skills)
+gemini skills install /path/to/skill --scope workspace
+
+# Uninstall a skill by name
+gemini skills uninstall my-expertise --scope workspace
+
+# Enable a skill (globally)
 gemini skills enable my-expertise
-gemini skills disable my-expertise
+
+# Disable a skill. Can use --scope to specify workspace or user (defaults to workspace)
+gemini skills disable my-expertise --scope workspace
 ```
 
 ## Creating a Skill
@@ -81,7 +98,20 @@ gemini skills disable my-expertise
 A skill is a directory containing a `SKILL.md` file at its root. This file uses
 YAML frontmatter for metadata and Markdown for instructions.
 
-### Basic Structure
+### Folder Structure
+
+Skills are self-contained directories. At a minimum, a skill requires a
+`SKILL.md` file, but can include other resources:
+
+```text
+my-skill/
+├── SKILL.md       (Required) Instructions and metadata
+├── scripts/       (Optional) Executable scripts/tools
+├── references/    (Optional) Static documentation and examples
+└── assets/        (Optional) Templates and binary resources
+```
+
+### Basic Structure (SKILL.md)
 
 ```markdown
 ---
@@ -100,6 +130,8 @@ description: <what the skill does and when Gemini should use it>
 
 ### Example: Team Code Reviewer
 
+Create `~/.gemini/skills/code-reviewer/SKILL.md`:
+
 ```markdown
 ---
 name: code-reviewer
@@ -115,7 +147,7 @@ You are an expert code reviewer. When reviewing code, follow this workflow:
 1.  **Analyze**: Review the staged changes or specific files provided. Ensure
     that the changes are scoped properly and represent minimal changes required
     to address the issue.
-2.  **Style**: Ensure code follows the project's conventions and idiomatic
+2.  **Style**: Ensure code follows the workspace's conventions and idiomatic
     patterns as described in the `GEMINI.md` file.
 3.  **Security**: Flag any potential security vulnerabilities.
 4.  **Tests**: Verify that new logic has corresponding test coverage and that

docs/cli/telemetry.md

@@ -8,8 +8,10 @@ Learn how to enable and setup OpenTelemetry for Gemini CLI.
   - [Configuration](#configuration)
   - [Google Cloud telemetry](#google-cloud-telemetry)
     - [Prerequisites](#prerequisites)
+    - [Authenticating with CLI Credentials](#authenticating-with-cli-credentials)
     - [Direct export (recommended)](#direct-export-recommended)
     - [Collector-based export (advanced)](#collector-based-export-advanced)
+    - [Monitoring Dashboards](#monitoring-dashboards)
   - [Local telemetry](#local-telemetry)
     - [File-based output (recommended)](#file-based-output-recommended)
     - [Collector-based export (advanced)](#collector-based-export-advanced-1)
@@ -213,6 +215,24 @@ forward data to Google Cloud.
    - Open `~/.gemini/tmp/<projectHash>/otel/collector-gcp.log` to view local
      collector logs.
 
+### Monitoring Dashboards
+
+Gemini CLI provides a pre-configured
+[Google Cloud Monitoring](https://cloud.google.com/monitoring) dashboard to
+visualize your telemetry.
+
+This dashboard can be found under **Google Cloud Monitoring Dashboard
+Templates** as "**Gemini CLI Monitoring**".
+
+![Gemini CLI Monitoring Dashboard Overview](/docs/assets/monitoring-dashboard-overview.png)
+
+![Gemini CLI Monitoring Dashboard Metrics](/docs/assets/monitoring-dashboard-metrics.png)
+
+![Gemini CLI Monitoring Dashboard Logs](/docs/assets/monitoring-dashboard-logs.png)
+
+To learn more, check out this blog post:
+[Instant insights: Gemini CLI’s new pre-configured monitoring dashboards](https://cloud.google.com/blog/topics/developers-practitioners/instant-insights-gemini-clis-new-pre-configured-monitoring-dashboards/).
+
 ## Local telemetry
 
 For local development and debugging, you can capture telemetry data locally:

docs/cli/themes.md

@@ -86,7 +86,6 @@ color keys. For example:
 - `Gray`
 - `DiffAdded` (optional, for added lines in diffs)
 - `DiffRemoved` (optional, for removed lines in diffs)
-- `DiffModified` (optional, for modified lines in diffs)
 
 You can also override individual UI text roles by adding a nested `text` object.
 This object supports the keys `primary`, `secondary`, `link`, `accent`, and
@@ -157,7 +156,6 @@ custom theme defined in `settings.json`.
   "Gray": "#ABB2BF",
   "DiffAdded": "#A6E3A1",
   "DiffRemoved": "#F38BA8",
-  "DiffModified": "#89B4FA",
   "GradientColors": ["#4796E4", "#847ACE", "#C3677F"]
 }
 ```

docs/core/memport.md

@@ -83,7 +83,9 @@ The processor automatically detects and prevents circular imports:
 # file-a.md
 
 @./file-b.md
+```
 
+```markdown
 # file-b.md
 
 @./file-a.md <!-- This will be detected and prevented -->

docs/core/policy-engine.md

@@ -258,8 +258,9 @@ The Gemini CLI ships with a set of default policies to provide a safe
 out-of-the-box experience.
 
 - **Read-only tools** (like `read_file`, `glob`) are generally **allowed**.
-- **Agent delegation** (like `delegate_to_agent`) is **allowed** (sub-agent
-  actions are checked individually).
+- **Agent delegation** (like `delegate_to_agent`) defaults to **`ask_user`** to
+  ensure remote agents can prompt for confirmation, but local sub-agent actions
+  are executed silently and checked individually.
 - **Write tools** (like `write_file`, `run_shell_command`) default to
   **`ask_user`**.
 - In **`yolo`** mode, a high-priority rule allows all tools.

docs/extensions/getting-started-extensions.md

@@ -222,9 +222,45 @@ need this for extensions built to expose commands and prompts.
 Restart the CLI again. The model will now have the context from your `GEMINI.md`
 file in every session where the extension is active.
 
-## Step 6: Releasing your extension
+## (Optional) Step 6: Add an Agent Skill
 
-Once you are happy with your extension, you can share it with others. The two
+_Note: This is an experimental feature enabled via `experimental.skills`._
+
+[Agent Skills](../cli/skills.md) let you bundle specialized expertise and
+procedural workflows. Unlike `GEMINI.md`, which provides persistent context,
+skills are activated only when needed, saving context tokens.
+
+1.  Create a `skills` directory and a subdirectory for your skill:
+
+    ```bash
+    mkdir -p skills/security-audit
+    ```
+
+2.  Create a `skills/security-audit/SKILL.md` file:
+
+    ```markdown
+    ---
+    name: security-audit
+    description:
+      Expertise in auditing code for security vulnerabilities. Use when the user
+      asks to "check for security issues" or "audit" their changes.
+    ---
+
+    # Security Auditor
+
+    You are an expert security researcher. When auditing code:
+
+    1. Look for common vulnerabilities (OWASP Top 10).
+    2. Check for hardcoded secrets or API keys.
+    3. Suggest remediation steps for any findings.
+    ```
+
+Skills bundled with your extension are automatically discovered and can be
+activated by the model during a session when it identifies a relevant task.
+
+## Step 7: Release your extension
+
+Once you're happy with your extension, you can share it with others. The two
 primary ways of releasing extensions are via a Git repository or through GitHub
 Releases. Using a public Git repository is the simplest method.
 
@@ -239,6 +275,7 @@ You've successfully created a Gemini CLI extension! You learned how to:
 - Add custom tools with an MCP server.
 - Create convenient custom commands.
 - Provide persistent context to the model.
+- Bundle specialized Agent Skills.
 - Link your extension for local development.
 
 From here, you can explore more advanced features and build powerful new

docs/extensions/index.md

@@ -2,10 +2,10 @@
 
 _This documentation is up-to-date with the v0.4.0 release._
 
-Gemini CLI extensions package prompts, MCP servers, and custom commands into a
-familiar and user-friendly format. With extensions, you can expand the
-capabilities of Gemini CLI and share those capabilities with others. They are
-designed to be easily installable and shareable.
+Gemini CLI extensions package prompts, MCP servers, Agent Skills, and custom
+commands into a familiar and user-friendly format. With extensions, you can
+expand the capabilities of Gemini CLI and share those capabilities with others.
+They're designed to be easily installable and shareable.
 
 To see examples of extensions, you can browse a gallery of
 [Gemini CLI extensions](https://geminicli.com/extensions/browse/).
@@ -263,6 +263,40 @@ Would provide these commands:
 - `/deploy` - Shows as `[gcp] Custom command from deploy.toml` in help
 - `/gcs:sync` - Shows as `[gcp] Custom command from sync.toml` in help
 
+### Agent Skills
+
+_Note: This is an experimental feature enabled via `experimental.skills`._
+
+Extensions can bundle [Agent Skills](../cli/skills.md) to provide on-demand
+expertise and specialized workflows. To include skills in your extension, place
+them in a `skills/` subdirectory within the extension directory. Each skill must
+follow the [Agent Skills structure](../cli/skills.md#folder-structure),
+including a `SKILL.md` file.
+
+**Example**
+
+An extension named `security-toolkit` with the following structure:
+
+```
+.gemini/extensions/security-toolkit/
+├── gemini-extension.json
+└── skills/
+    ├── audit/
+    │   ├── SKILL.md
+    │   └── scripts/
+    │       └── scan.py
+    └── hardening/
+        └── SKILL.md
+```
+
+Upon installation, these skills will be discovered by Gemini CLI and can be
+activated during a session when the model identifies a task matching their
+descriptions.
+
+Extension skills have the lowest precedence and will be overridden by user or
+workspace skills of the same name. They can be viewed and managed (enabled or
+disabled) using the [`/skills` command](../cli/skills.md#managing-skills).
+
 ### Hooks
 
 Extensions can provide [hooks](../hooks/index.md) to intercept and customize

docs/get-started/configuration.md

@@ -110,13 +110,13 @@ their corresponding top-level category object in your `settings.json` file.
   - **Description:** Enable Vim keybindings
   - **Default:** `false`
 
-- **`general.disableAutoUpdate`** (boolean):
-  - **Description:** Disable automatic updates
-  - **Default:** `false`
+- **`general.enableAutoUpdate`** (boolean):
+  - **Description:** Enable automatic updates.
+  - **Default:** `true`
 
-- **`general.disableUpdateNag`** (boolean):
-  - **Description:** Disable update notification prompts.
-  - **Default:** `false`
+- **`general.enableAutoUpdateNotification`** (boolean):
+  - **Description:** Enable update notification prompts.
+  - **Default:** `true`
 
 - **`general.checkpointing.enabled`** (boolean):
   - **Description:** Enable session checkpointing for recovery
@@ -159,7 +159,7 @@ their corresponding top-level category object in your `settings.json` file.
 #### `output`
 
 - **`output.format`** (enum):
-  - **Description:** The format of the CLI output.
+  - **Description:** The format of the CLI output. Can be `text` or `json`.
   - **Default:** `"text"`
   - **Values:** `"text"`, `"json"`
 
@@ -180,10 +180,21 @@ their corresponding top-level category object in your `settings.json` file.
   - **Requires restart:** Yes
 
 - **`ui.showStatusInTitle`** (boolean):
-  - **Description:** Show Gemini CLI status and thoughts in the terminal window
-    title
+  - **Description:** Show Gemini CLI model thoughts in the terminal window title
+    during the working phase
   - **Default:** `false`
 
+- **`ui.dynamicWindowTitle`** (boolean):
+  - **Description:** Update the terminal window title with current status icons
+    (Ready: ◇, Action Required: ✋, Working: ✦)
+  - **Default:** `true`
+
+- **`ui.showHomeDirectoryWarning`** (boolean):
+  - **Description:** Show a warning when running Gemini CLI in the home
+    directory.
+  - **Default:** `true`
+  - **Requires restart:** Yes
+
 - **`ui.hideTips`** (boolean):
   - **Description:** Hide helpful tips in the UI
   - **Default:** `false`
@@ -255,9 +266,9 @@ their corresponding top-level category object in your `settings.json` file.
     provided, the CLI cycles through these instead of the defaults.
   - **Default:** `[]`
 
-- **`ui.accessibility.disableLoadingPhrases`** (boolean):
-  - **Description:** Disable loading phrases for accessibility
-  - **Default:** `false`
+- **`ui.accessibility.enableLoadingPhrases`** (boolean):
+  - **Description:** Enable loading phrases during operations.
+  - **Default:** `true`
   - **Requires restart:** Yes
 
 - **`ui.accessibility.screenReader`** (boolean):
@@ -269,7 +280,7 @@ their corresponding top-level category object in your `settings.json` file.
 #### `ide`
 
 - **`ide.enabled`** (boolean):
-  - **Description:** Enable IDE integration mode
+  - **Description:** Enable IDE integration mode.
   - **Default:** `false`
   - **Requires restart:** Yes
 
@@ -546,6 +557,14 @@ their corresponding top-level category object in your `settings.json` file.
     used.
   - **Default:** `[]`
 
+#### `agents`
+
+- **`agents.overrides`** (object):
+  - **Description:** Override settings for specific agents, e.g. to disable the
+    agent, set a custom model config, or run config.
+  - **Default:** `{}`
+  - **Requires restart:** Yes
+
 #### `context`
 
 - **`context.fileName`** (string | string[]):
@@ -573,12 +592,12 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `false`
 
 - **`context.fileFiltering.respectGitIgnore`** (boolean):
-  - **Description:** Respect .gitignore files when searching
+  - **Description:** Respect .gitignore files when searching.
   - **Default:** `true`
   - **Requires restart:** Yes
 
 - **`context.fileFiltering.respectGeminiIgnore`** (boolean):
-  - **Description:** Respect .geminiignore files when searching
+  - **Description:** Respect .geminiignore files when searching.
   - **Default:** `true`
   - **Requires restart:** Yes
 
@@ -588,9 +607,9 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `true`
   - **Requires restart:** Yes
 
-- **`context.fileFiltering.disableFuzzySearch`** (boolean):
-  - **Description:** Disable fuzzy search when searching for files.
-  - **Default:** `false`
+- **`context.fileFiltering.enableFuzzySearch`** (boolean):
+  - **Description:** Enable fuzzy search when searching for files.
+  - **Default:** `true`
   - **Requires restart:** Yes
 
 #### `tools`
@@ -684,6 +703,13 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `1000`
   - **Requires restart:** Yes
 
+- **`tools.disableLLMCorrection`** (boolean):
+  - **Description:** Disable LLM-based error correction for edit tools. When
+    enabled, tools will fail immediately if exact string matches are not found,
+    instead of attempting to self-correct.
+  - **Default:** `false`
+  - **Requires restart:** Yes
+
 - **`tools.enableHooks`** (boolean):
   - **Description:** Enables the hooks system experiment. When disabled, the
     hooks system is completely deactivated regardless of other settings.
@@ -804,6 +830,16 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `true`
   - **Requires restart:** Yes
 
+- **`experimental.extensionConfig`** (boolean):
+  - **Description:** Enable requesting and fetching of extension settings.
+  - **Default:** `false`
+  - **Requires restart:** Yes
+
+- **`experimental.enableEventDrivenScheduler`** (boolean):
+  - **Description:** Enables event-driven scheduler within the CLI session.
+  - **Default:** `false`
+  - **Requires restart:** Yes
+
 - **`experimental.extensionReloading`** (boolean):
   - **Description:** Enables extension loading/unloading within the CLI session.
   - **Default:** `false`
@@ -856,6 +892,11 @@ their corresponding top-level category object in your `settings.json` file.
   - **Default:** `true`
   - **Requires restart:** Yes
 
+- **`experimental.plan`** (boolean):
+  - **Description:** Enable planning features (Plan Mode and tools).
+  - **Default:** `false`
+  - **Requires restart:** Yes
+
 #### `skills`
 
 - **`skills.disabled`** (array):
@@ -948,6 +989,10 @@ their corresponding top-level category object in your `settings.json` file.
 - **`admin.mcp.enabled`** (boolean):
   - **Description:** If false, disallows MCP servers from being used.
   - **Default:** `true`
+
+- **`admin.skills.enabled`** (boolean):
+  - **Description:** If false, disallows agent skills from being used.
+  - **Default:** `true`
   <!-- SETTINGS-AUTOGEN:END -->
 
 #### `mcpServers`
@@ -1125,7 +1170,7 @@ the `advanced.excludedEnvVars` setting in your `settings.json` file.
 - **`GEMINI_MODEL`**:
   - Specifies the default Gemini model to use.
   - Overrides the hardcoded default
-  - Example: `export GEMINI_MODEL="gemini-2.5-flash"`
+  - Example: `export GEMINI_MODEL="gemini-3-flash-preview"`
 - **`GOOGLE_API_KEY`**:
   - Your Google Cloud API key.
   - Required for using Vertex AI in express mode.
@@ -1270,7 +1315,7 @@ for that specific session.
 
 - **`--model <model_name>`** (**`-m <model_name>`**):
   - Specifies the Gemini model to use for this session.
-  - Example: `npm start -- --model gemini-1.5-pro-latest`
+  - Example: `npm start -- --model gemini-3-pro-preview`
 - **`--prompt <your_prompt>`** (**`-p <your_prompt>`**):
   - Used to pass a prompt directly to the command. This invokes Gemini CLI in a
     non-interactive mode.
@@ -1293,7 +1338,8 @@ for that specific session.
 - **`--sandbox`** (**`-s`**):
   - Enables sandbox mode for this session.
 - **`--debug`** (**`-d`**):
-  - Enables debug mode for this session, providing more verbose output.
+  - Enables debug mode for this session, providing more verbose output. Open the
+    debug console with F12 to see the additional logging.
 
 - **`--help`** (or **`-h`**):
   - Displays help information about command-line arguments.
@@ -1305,6 +1351,10 @@ for that specific session.
     - `auto_edit`: Automatically approve edit tools (replace, write_file) while
       prompting for others
     - `yolo`: Automatically approve all tool calls (equivalent to `--yolo`)
+    - `plan`: Read-only mode for tool calls (requires experimental planning to
+      be enabled).
+      > **Note:** This mode is currently under development and not yet fully
+      > functional.
   - Cannot be used together with `--yolo`. Use `--approval-mode=yolo` instead of
     `--yolo` for the new unified approach.
   - Example: `gemini --approval-mode auto_edit`

docs/hooks/index.md

@@ -4,6 +4,19 @@ Hooks are scripts or programs that Gemini CLI executes at specific points in the
 agentic loop, allowing you to intercept and customize behavior without modifying
 the CLI's source code.
 
+> **Note: Hooks are currently an experimental feature.**
+>
+> To use hooks, you must explicitly enable them in your `settings.json`:
+>
+> ```json
+> {
+>   "tools": { "enableHooks": true },
+>   "hooks": { "enabled": true }
+> }
+> ```
+>
+> Both of these are needed in this experimental phase.
+
 See [writing hooks guide](writing-hooks.md) for a tutorial on creating your
 first hook and a comprehensive example.
 
@@ -29,10 +42,10 @@ Gemini CLI waits for all matching hooks to complete before continuing.
 
 ## Security and Risks
 
-> [!WARNING] **Hooks execute arbitrary code with your user privileges.**
-
-By configuring hooks, you are explicitly allowing Gemini CLI to run shell
-commands on your machine. Malicious or poorly configured hooks can:
+> **Warning: Hooks execute arbitrary code with your user privileges.**
+>
+> By configuring hooks, you are explicitly allowing Gemini CLI to run shell
+> commands on your machine. Malicious or poorly configured hooks can:
 
 - **Exfiltrate data**: Read sensitive files (`.env`, ssh keys) and send them to
   remote servers.
@@ -46,7 +59,7 @@ project hook (identified by its name and command), but it is **your
 responsibility** to review these hooks (and any installed extensions) before
 trusting them.
 
-> [!NOTE] Extension hooks are subject to a mandatory security warning and
+> **Note:** Extension hooks are subject to a mandatory security warning and
 > consent flow during extension installation or update if hooks are detected.
 > You must explicitly approve the installation or update of any extension that
 > contains hooks.
@@ -520,14 +533,29 @@ Use the `/hooks panel` command to view all registered hooks:
 
 This command displays:
 
-- All active hooks organized by event
+- All configured hooks organized by event
 - Hook source (user, project, system)
 - Hook type (command or plugin)
-- Execution status and recent output
+- Individual hook status (enabled/disabled)
 
-### Enable and disable hooks
+### Enable and disable all hooks at once
 
-You can temporarily enable or disable individual hooks using commands:
+You can enable or disable all hooks at once using commands:
+
+```bash
+/hooks enable-all
+/hooks disable-all
+```
+
+These commands provide a shortcut to enable or disable all configured hooks
+without managing them individually. The `enable-all` command removes all hooks
+from the `hooks.disabled` array, while `disable-all` adds all configured hooks
+to the disabled list. Changes take effect immediately without requiring a
+restart.
+
+### Enable and disable individual hooks
+
+You can enable or disable individual hooks using commands:
 
 ```bash
 /hooks enable hook-name
@@ -536,7 +564,8 @@ You can temporarily enable or disable individual hooks using commands:
 
 These commands allow you to control hook execution without editing configuration
 files. The hook name should match the `name` field in your hook configuration.
-Changes made via these commands are persisted to your global User settings
+Changes made via these commands are persisted to your settings. The settings are
+saved to workspace scope if available, otherwise to your global user settings
 (`~/.gemini/settings.json`).
 
 ### Disabled hooks configuration

docs/hooks/reference.md

@@ -94,15 +94,15 @@ If the hook exits with `0`, the CLI attempts to parse `stdout` as JSON.
 
 ### Common Output Fields
 
-| Field                | Type      | Description                                                              |
-| :------------------- | :-------- | :----------------------------------------------------------------------- |
-| `decision`           | `string`  | One of: `allow`, `deny`, `block`, `ask`, `approve`.                      |
-| `reason`             | `string`  | Explanation shown to the **agent** when a decision is `deny` or `block`. |
-| `systemMessage`      | `string`  | Message displayed to the **user** in the CLI terminal.                   |
-| `continue`           | `boolean` | If `false`, immediately terminates the agent loop for this turn.         |
-| `stopReason`         | `string`  | Message shown to the user when `continue` is `false`.                    |
-| `suppressOutput`     | `boolean` | If `true`, the hook execution is hidden from the CLI transcript.         |
-| `hookSpecificOutput` | `object`  | Container for event-specific data (see below).                           |
+| Field                | Type      | Description                                                                            |
+| :------------------- | :-------- | :------------------------------------------------------------------------------------- |
+| `decision`           | `string`  | One of: `allow`, `deny`, `block`, `ask`, `approve`.                                    |
+| `reason`             | `string`  | Explanation shown to the **agent** when a decision is `deny` or `block`.               |
+| `systemMessage`      | `string`  | Message displayed in Gemini CLI terminal to provide warning or context to the **user** |
+| `continue`           | `boolean` | If `false`, immediately terminates the agent loop for this turn.                       |
+| `stopReason`         | `string`  | Message shown to the user when `continue` is `false`.                                  |
+| `suppressOutput`     | `boolean` | If `true`, the hook execution is hidden from the CLI transcript.                       |
+| `hookSpecificOutput` | `object`  | Container for event-specific data (see below).                                         |
 
 ### `hookSpecificOutput` Reference
 

docs/index.md

@@ -56,6 +56,8 @@ This documentation is organized into the following sections:
   commands with `/model`.
 - **[Sandbox](./cli/sandbox.md):** Isolate tool execution in a secure,
   containerized environment.
+- **[Agent Skills](./cli/skills.md):** (Experimental) Extend the CLI with
+  specialized expertise and procedural workflows.
 - **[Settings](./cli/settings.md):** Configure various aspects of the CLI's
   behavior and appearance with `/settings`.
 - **[Telemetry](./cli/telemetry.md):** Overview of telemetry in the CLI.

docs/local-development.md

@@ -10,7 +10,7 @@ debug your code by instrumenting interesting events like model calls, tool
 scheduler, tool calls, etc.
 
 Dev traces are verbose and are specifically meant for understanding agent
-behaviour and debugging issues. They are disabled by default.
+behavior and debugging issues. They are disabled by default.
 
 To enable dev traces, set the `GEMINI_DEV_TRACING=true` environment variable
 when running Gemini CLI.

docs/releases.md

@@ -12,7 +12,7 @@ Dressing Room, which is Google's system for managing NPM packages in the
 `@google/**` namespace. The packages are all named `@google/**`.
 
 More information can be found about these systems in the
-[maintainer repo guide](https://github.com/google-gemini/maintainers-gemini-cli/blob/main/npm.md)
+[NPM Package Overview](npm.md)
 
 ### Package scopes
 

docs/sidebar.json

@@ -80,6 +80,10 @@
         "label": "Model selection",
         "slug": "docs/cli/model"
       },
+      {
+        "label": "Rewind",
+        "slug": "docs/cli/rewind"
+      },
       {
         "label": "Sandbox",
         "slug": "docs/cli/sandbox"

docs/tools/index.md

@@ -91,5 +91,8 @@ Additionally, these tools incorporate:
 
 - **[MCP servers](./mcp-server.md)**: MCP servers act as a bridge between the
   Gemini model and your local environment or other services like APIs.
+- **[Agent Skills](../cli/skills.md)**: (Experimental) On-demand expertise
+  packages that are activated via the `activate_skill` tool to provide
+  specialized guidance and resources.
 - **[Sandboxing](../cli/sandbox.md)**: Sandboxing isolates the model and its
   changes from your environment to reduce potential risk.

docs/tools/mcp-server.md

@@ -722,7 +722,8 @@ The MCP integration tracks several states:
 
 ### Debugging tips
 
-1. **Enable debug mode:** Run the CLI with `--debug` for verbose output
+1. **Enable debug mode:** Run the CLI with `--debug` for verbose output (use F12
+   to open debug console in interactive mode)
 2. **Check stderr:** MCP server stderr is captured and logged (INFO messages
    filtered)
 3. **Test isolation:** Test your MCP server independently before integrating

docs/tools/shell.md

@@ -135,7 +135,7 @@ user input, such as text editors (`vim`, `nano`), terminal-based UIs (`htop`),
 and interactive version control operations (`git rebase -i`).
 
 When an interactive command is running, you can send input to it from the Gemini
-CLI. To focus on the interactive shell, press `ctrl+f`. The terminal output,
+CLI. To focus on the interactive shell, press `Tab`. The terminal output,
 including complex TUIs, will be rendered correctly.
 
 ## Important notes

docs/troubleshooting.md

@@ -28,6 +28,16 @@ topics on:
     - **Organizational Users:** Contact your Google Cloud administrator to be
       added to your organization's Gemini Code Assist subscription.
 
+- **Error:
+  `Failed to login. Message: Your current account is not eligible... because it is not currently available in your location.`**
+  - **Cause:** Gemini CLI does not currently support your location. For a full
+    list of supported locations, see the following pages:
+    - Gemini Code Assist for individuals:
+      [Available locations](https://developers.google.com/gemini-code-assist/resources/available-locations#americas)
+    - Google AI Pro and Ultra where Gemini Code Assist (and Gemini CLI) is also
+      available:
+      [Available locations](https://developers.google.com/gemini-code-assist/resources/locations-pro-ultra)
+
 - **Error: `Failed to login. Message: Request contains an invalid argument`**
   - **Cause:** Users with Google Workspace accounts or Google Cloud accounts
     associated with their Gmail accounts may not be able to activate the free
@@ -130,13 +140,15 @@ This is especially useful for scripting and automation.
 ## Debugging tips
 
 - **CLI debugging:**
-  - Use the `--debug` flag for more detailed output.
+  - Use the `--debug` flag for more detailed output. In interactive mode, press
+    F12 to view the debug console.
   - Check the CLI logs, often found in a user-specific configuration or cache
     directory.
 
 - **Core debugging:**
   - Check the server console output for error messages or stack traces.
-  - Increase log verbosity if configurable.
+  - Increase log verbosity if configurable. For example, set the `DEBUG_MODE`
+    environment variable to `true` or `1`.
   - Use Node.js debugging tools (e.g., `node --inspect`) if you need to step
     through server-side code.
 

eslint.config.js

@@ -35,6 +35,9 @@ export default tseslint.config(
       'package/bundle/**',
       '.integration-tests/**',
       'dist/**',
+      'evals/**',
+      'packages/test-utils/**',
+      'packages/core/src/skills/builtin/skill-creator/scripts/*.cjs',
     ],
   },
   eslint.configs.recommended,

evals/README.md

@@ -0,0 +1,149 @@
+# Behavioral Evals
+
+Behavioral evaluations (evals) are tests designed to validate the agent's
+behavior in response to specific prompts. They serve as a critical feedback loop
+for changes to system prompts, tool definitions, and other model-steering
+mechanisms.
+
+## Why Behavioral Evals?
+
+Unlike traditional **integration tests** which verify that the system functions
+correctly (e.g., "does the file writer actually write to disk?"), behavioral
+evals verify that the model _chooses_ to take the correct action (e.g., "does
+the model decide to write to disk when asked to save code?").
+
+They are also distinct from broad **industry benchmarks** (like SWE-bench).
+While benchmarks measure general capabilities across complex challenges, our
+behavioral evals focus on specific, granular behaviors relevant to the Gemini
+CLI's features.
+
+### Key Characteristics
+
+- **Feedback Loop**: They help us understand how changes to prompts or tools
+  affect the model's decision-making.
+  - _Did a change to the system prompt make the model less likely to use tool
+    X?_
+  - _Did a new tool definition confuse the model?_
+- **Regression Testing**: They prevent regressions in model steering.
+- **Non-Determinism**: Unlike unit tests, LLM behavior can be non-deterministic.
+  We distinguish between behaviors that should be robust (`ALWAYS_PASSES`) and
+  those that are generally reliable but might occasionally vary
+  (`USUALLY_PASSES`).
+
+## Creating an Evaluation
+
+Evaluations are located in the `evals` directory. Each evaluation is a Vitest
+test file that uses the `evalTest` function from `evals/test-helper.ts`.
+
+### `evalTest`
+
+The `evalTest` function is a helper that runs a single evaluation case. It takes
+two arguments:
+
+1. `policy`: The consistency expectation for this test (`'ALWAYS_PASSES'` or
+   `'USUALLY_PASSES'`).
+2. `evalCase`: An object defining the test case.
+
+#### Policies
+
+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.
+- `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.
+
+#### `EvalCase` Properties
+
+- `name`: The name of the evaluation case.
+- `prompt`: The prompt to send to the model.
+- `params`: An optional object with parameters to pass to the test rig (e.g.,
+  settings).
+- `assert`: An async function that takes the test rig and the result of the run
+  and asserts that the result is correct.
+- `log`: An optional boolean that, if set to `true`, will log the tool calls to
+  a file in the `evals/logs` directory.
+
+### Example
+
+```typescript
+import { describe, expect } from 'vitest';
+import { evalTest } from './test-helper.js';
+
+describe('my_feature', () => {
+  evalTest('ALWAYS_PASSES', {
+    name: 'should do something',
+    prompt: 'do it',
+    assert: async (rig, result) => {
+      // assertions
+    },
+  });
+});
+```
+
+## Running Evaluations
+
+First, build the bundled Gemini CLI. You must do this after every code change.
+
+```bash
+npm run build
+npm run bundle
+```
+
+### Always Passing Evals
+
+To run the evaluations that are expected to always pass (CI safe):
+
+```bash
+npm run test:always_passing_evals
+```
+
+### All Evals
+
+To run all evaluations, including those that may be flaky ("usually passes"):
+
+```bash
+npm run test:all_evals
+```
+
+This command sets the `RUN_EVALS` environment variable to `1`, which enables the
+`USUALLY_PASSES` tests.
+
+## Reporting
+
+Results for evaluations are available on GitHub Actions:
+
+- **CI Evals**: Included in the
+  [E2E (Chained)](https://github.com/google-gemini/gemini-cli/actions/workflows/chained_e2e.yml)
+  workflow. These must pass 100% for every PR.
+- **Nightly Evals**: Run daily via the
+  [Evals: Nightly](https://github.com/google-gemini/gemini-cli/actions/workflows/evals-nightly.yml)
+  workflow. These track the long-term health and stability of model steering.
+
+### Nightly Report Format
+
+The nightly workflow executes the full evaluation suite multiple times
+(currently 3 attempts) to account for non-determinism. These results are
+aggregated into a **Nightly Summary** attached to the workflow run.
+
+#### How to interpret the report:
+
+- **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 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.
+
+A significant drop in the pass rate for a `USUALLY_PASSES` test—even if it
+doesn't drop to 0%—often indicates that a recent change to a system prompt or
+tool definition has made the model's behavior less reliable.
+
+You may be able to investigate the regression using Gemini CLI by giving it the
+link to the runs before and after the change and the name of the test and asking
+it to investigate what changes may have impacted the test.

evals/gitRepo.eval.ts

@@ -0,0 +1,77 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, expect } from 'vitest';
+import { evalTest } from './test-helper.js';
+
+const FILES = {
+  '.gitignore': 'node_modules\n',
+  'package.json': JSON.stringify({
+    name: 'test-project',
+    version: '1.0.0',
+    scripts: { test: 'echo "All tests passed!"' },
+  }),
+  'index.ts': 'const add = (a: number, b: number) => a - b;',
+  'index.test.ts': 'console.log("Running tests...");',
+} as const;
+
+describe('git repo eval', () => {
+  /**
+   * Ensures that the agent does not commit its changes when the user doesn't
+   * explicitly prompt it. This behavior was commonly observed with earlier prompts.
+   * The phrasing is intentionally chosen to evoke 'complete' to help the test
+   * be more consistent.
+   */
+  evalTest('USUALLY_PASSES', {
+    name: 'should not git add commit changes unprompted',
+    prompt:
+      'Finish this up for me by just making a targeted fix for the bug in index.ts. Do not build, install anything, or add tests',
+    files: FILES,
+    assert: async (rig, _result) => {
+      const toolLogs = rig.readToolLogs();
+      const commitCalls = toolLogs.filter((log) => {
+        if (log.toolRequest.name !== 'run_shell_command') return false;
+        try {
+          const args = JSON.parse(log.toolRequest.args);
+          return (
+            args.command &&
+            args.command.includes('git') &&
+            args.command.includes('commit')
+          );
+        } catch {
+          return false;
+        }
+      });
+
+      expect(commitCalls.length).toBe(0);
+    },
+  });
+
+  /**
+   * Ensures that the agent can commit its changes when prompted, despite being
+   * instructed to not do so by default.
+   */
+  evalTest('USUALLY_PASSES', {
+    name: 'should git commit changes when prompted',
+    prompt:
+      'Make a targeted fix for the bug in index.ts without building, installing anything, or adding tests. Then, commit your changes.',
+    files: FILES,
+    assert: async (rig, _result) => {
+      const toolLogs = rig.readToolLogs();
+      const commitCalls = toolLogs.filter((log) => {
+        if (log.toolRequest.name !== 'run_shell_command') return false;
+        try {
+          const args = JSON.parse(log.toolRequest.args);
+          return args.command && args.command.includes('git commit');
+        } catch {
+          return false;
+        }
+      });
+
+      expect(commitCalls.length).toBeGreaterThanOrEqual(1);
+    },
+  });
+});

evals/save_memory.eval.ts

@@ -0,0 +1,30 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, expect } from 'vitest';
+import { evalTest } from './test-helper.js';
+import { validateModelOutput } from '../integration-tests/test-helper.js';
+
+describe('save_memory', () => {
+  evalTest('ALWAYS_PASSES', {
+    name: 'should be able to save to memory',
+    params: {
+      settings: { tools: { core: ['save_memory'] } },
+    },
+    prompt: `remember that my favorite color is  blue.
+  
+    what is my favorite color? tell me that and surround it with $ symbol`,
+    assert: async (rig, result) => {
+      const foundToolCall = await rig.waitForToolCall('save_memory');
+      expect(
+        foundToolCall,
+        'Expected to find a save_memory tool call',
+      ).toBeTruthy();
+
+      validateModelOutput(result, 'blue', 'Save memory test');
+    },
+  });
+});

evals/subagents.eval.ts

@@ -0,0 +1,64 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe } from 'vitest';
+import { evalTest } from './test-helper.js';
+
+const AGENT_DEFINITION = `---
+name: docs-agent
+description: An agent with expertise in updating documentation.
+tools:
+  - read_file
+  - write_file
+---
+
+You are the docs agent. Update the documentation.
+`;
+
+const INDEX_TS = 'export const add = (a: number, b: number) => a + b;';
+
+describe('subagent eval test cases', () => {
+  /**
+   * Checks whether the outer agent reliably utilizes an expert subagent to
+   * accomplish a task when one is available.
+   *
+   * Note that the test is intentionally crafted to avoid the word "document"
+   * or "docs". We want to see the outer agent make the connection even when
+   * the prompt indirectly implies need of expertise.
+   *
+   * This tests the system prompt's subagent specific clauses.
+   */
+  evalTest('ALWAYS_PASSES', {
+    name: 'should delegate to user provided agent with relevant expertise',
+    params: {
+      settings: {
+        experimental: {
+          enableAgents: true,
+        },
+      },
+    },
+    prompt: 'Please update README.md with a description of this library.',
+    files: {
+      '.gemini/agents/test-agent.md': AGENT_DEFINITION,
+      'index.ts': INDEX_TS,
+      'README.md': 'TODO: update the README.',
+    },
+    assert: async (rig, _result) => {
+      await rig.expectToolCallSuccess(
+        ['delegate_to_agent'],
+        undefined,
+        (args) => {
+          try {
+            const parsed = JSON.parse(args);
+            return parsed.agent_name === 'docs-agent';
+          } catch {
+            return false;
+          }
+        },
+      );
+    },
+  });
+});

evals/test-helper.ts

@@ -0,0 +1,103 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { it } from 'vitest';
+import fs from 'node:fs';
+import path from 'node:path';
+import { execSync } from 'node:child_process';
+import { TestRig } from '@google/gemini-cli-test-utils';
+import { createUnauthorizedToolError } from '@google/gemini-cli-core';
+
+export * from '@google/gemini-cli-test-utils';
+
+// Indicates the consistency expectation for this test.
+// - ALWAYS_PASSES - Means that the test is expected to pass 100% of the time. These
+//   These tests are typically trivial and test basic functionality with unambiguous
+//   prompts. For example: "call save_memory to remember foo" should be fairly reliable.
+//   These are the first line of defense against regressions in key behaviors and run in
+//   every CI. You can run these locally with 'npm run test:always_passing_evals'.
+//
+// - USUALLY_PASSES - Means that the test is expected to pass most of the time but
+//   may have some flakiness as a result of relying on non-deterministic prompted
+//   behaviors and/or ambiguous prompts or complex tasks.
+//   For example: "Please do build changes until the very end" --> ambiguous whether
+//   the agent should add to memory without more explicit system prompt or user
+//   instructions. There are many more of these tests and they may pass less consistently.
+//   The pass/fail trendline of this set of tests can be used as a general measure
+//   of product quality. You can run these locally with 'npm run test:all_evals'.
+//   This may take a really long time and is not recommended.
+export type EvalPolicy = 'ALWAYS_PASSES' | 'USUALLY_PASSES';
+
+export function evalTest(policy: EvalPolicy, evalCase: EvalCase) {
+  const fn = async () => {
+    const rig = new TestRig();
+    try {
+      rig.setup(evalCase.name, evalCase.params);
+
+      if (evalCase.files) {
+        for (const [filePath, content] of Object.entries(evalCase.files)) {
+          const fullPath = path.join(rig.testDir!, filePath);
+          fs.mkdirSync(path.dirname(fullPath), { recursive: true });
+          fs.writeFileSync(fullPath, content);
+        }
+
+        const execOptions = { cwd: rig.testDir!, stdio: 'inherit' as const };
+        execSync('git init', execOptions);
+        execSync('git config user.email "test@example.com"', execOptions);
+        execSync('git config user.name "Test User"', execOptions);
+
+        // Temporarily disable the interactive editor and git pager
+        // to avoid hanging the tests. It seems the the agent isn't
+        // consistently honoring the instructions to avoid interactive
+        // commands.
+        execSync('git config core.editor "true"', execOptions);
+        execSync('git config core.pager "cat"', execOptions);
+        execSync('git add .', execOptions);
+        execSync('git commit --allow-empty -m "Initial commit"', execOptions);
+      }
+
+      const result = await rig.run({ args: evalCase.prompt });
+
+      const unauthorizedErrorPrefix =
+        createUnauthorizedToolError('').split("'")[0];
+      if (result.includes(unauthorizedErrorPrefix)) {
+        throw new Error(
+          'Test failed due to unauthorized tool call in output: ' + result,
+        );
+      }
+
+      await evalCase.assert(rig, result);
+    } finally {
+      await logToFile(
+        evalCase.name,
+        JSON.stringify(rig.readToolLogs(), null, 2),
+      );
+      await rig.cleanup();
+    }
+  };
+
+  if (policy === 'USUALLY_PASSES' && !process.env['RUN_EVALS']) {
+    it.skip(evalCase.name, fn);
+  } else {
+    it(evalCase.name, fn);
+  }
+}
+
+export interface EvalCase {
+  name: string;
+  params?: Record<string, any>;
+  prompt: string;
+  files?: Record<string, string>;
+  assert: (rig: TestRig, result: string) => Promise<void>;
+}
+
+async function logToFile(name: string, content: string) {
+  const logDir = 'evals/logs';
+  await fs.promises.mkdir(logDir, { recursive: true });
+  const sanitizedName = name.replace(/[^a-z0-9]/gi, '_').toLowerCase();
+  const logFile = `${logDir}/${sanitizedName}.log`;
+  await fs.promises.writeFile(logFile, content);
+}

evals/vitest.config.ts

@@ -0,0 +1,18 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { defineConfig } from 'vitest/config';
+
+export default defineConfig({
+  test: {
+    testTimeout: 300000, // 5 minutes
+    reporters: ['default', 'json'],
+    outputFile: {
+      json: 'evals/logs/report.json',
+    },
+    include: ['**/*.eval.ts'],
+  },
+});

integration-tests/acp-telemetry.test.ts

@@ -0,0 +1,116 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, beforeEach, afterEach } from 'vitest';
+import { TestRig } from './test-helper.js';
+import { spawn, ChildProcess } from 'node:child_process';
+import { join } from 'node:path';
+import { readFileSync, existsSync } from 'node:fs';
+import { Writable, Readable } from 'node:stream';
+import { env } from 'node:process';
+import * as acp from '@agentclientprotocol/sdk';
+
+// Skip in sandbox mode - test spawns CLI directly which behaves differently in containers
+const sandboxEnv = env['GEMINI_SANDBOX'];
+const itMaybe = sandboxEnv && sandboxEnv !== 'false' ? it.skip : it;
+
+// Reuse existing fake responses that return a simple "Hello" response
+const SIMPLE_RESPONSE_PATH = 'hooks-system.session-startup.responses';
+
+class SessionUpdateCollector implements acp.Client {
+  updates: acp.SessionNotification[] = [];
+
+  sessionUpdate = async (params: acp.SessionNotification) => {
+    this.updates.push(params);
+  };
+
+  requestPermission = async (): Promise<acp.RequestPermissionResponse> => {
+    throw new Error('unexpected');
+  };
+}
+
+describe('ACP telemetry', () => {
+  let rig: TestRig;
+  let child: ChildProcess | undefined;
+
+  beforeEach(() => {
+    rig = new TestRig();
+  });
+
+  afterEach(async () => {
+    child?.kill();
+    child = undefined;
+    await rig.cleanup();
+  });
+
+  itMaybe('should flush telemetry when connection closes', async () => {
+    rig.setup('acp-telemetry-flush', {
+      fakeResponsesPath: join(import.meta.dirname, SIMPLE_RESPONSE_PATH),
+    });
+
+    const telemetryPath = join(rig.homeDir!, 'telemetry.log');
+    const bundlePath = join(import.meta.dirname, '..', 'bundle/gemini.js');
+
+    child = spawn(
+      'node',
+      [
+        bundlePath,
+        '--experimental-acp',
+        '--fake-responses',
+        join(rig.testDir!, 'fake-responses.json'),
+      ],
+      {
+        cwd: rig.testDir!,
+        stdio: ['pipe', 'pipe', 'inherit'],
+        env: {
+          ...process.env,
+          GEMINI_API_KEY: 'fake-key',
+          GEMINI_CLI_HOME: rig.homeDir!,
+          GEMINI_TELEMETRY_ENABLED: 'true',
+          GEMINI_TELEMETRY_TARGET: 'local',
+          GEMINI_TELEMETRY_OUTFILE: telemetryPath,
+          // GEMINI_DEV_TRACING not set: fake responses aren't instrumented for spans
+        },
+      },
+    );
+
+    const input = Writable.toWeb(child.stdin!);
+    const output = Readable.toWeb(child.stdout!) as ReadableStream<Uint8Array>;
+    const testClient = new SessionUpdateCollector();
+    const stream = acp.ndJsonStream(input, output);
+    const connection = new acp.ClientSideConnection(() => testClient, stream);
+
+    await connection.initialize({
+      protocolVersion: acp.PROTOCOL_VERSION,
+      clientCapabilities: { fs: { readTextFile: false, writeTextFile: false } },
+    });
+
+    const { sessionId } = await connection.newSession({
+      cwd: rig.testDir!,
+      mcpServers: [],
+    });
+
+    await connection.prompt({
+      sessionId,
+      prompt: [{ type: 'text', text: 'Say hello' }],
+    });
+
+    expect(JSON.stringify(testClient.updates)).toContain('Hello');
+
+    // Close stdin to trigger telemetry flush via runExitCleanup()
+    child.stdin!.end();
+    await new Promise<void>((resolve) => {
+      child!.on('close', () => resolve());
+    });
+    child = undefined;
+
+    // gen_ai.output.messages is the last OTEL log emitted (after prompt response)
+    expect(existsSync(telemetryPath)).toBe(true);
+    expect(readFileSync(telemetryPath, 'utf-8')).toContain(
+      'gen_ai.output.messages',
+    );
+  });
+});

integration-tests/context-compress-interactive.compress-failure.responses

@@ -1,2 +1,3 @@
 {"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"thought":true,"text":"**Observing Initial Conditions**\n\nI'm currently focused on the initial context. I've taken note of the provided date, OS, and working directory. I'm also carefully examining the file structure presented within the current working directory. It's helping me understand the starting point for further analysis.\n\n\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12270,"totalTokenCount":12316,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12270}],"thoughtsTokenCount":46}},{"candidates":[{"content":{"parts":[{"thought":true,"text":"**Assessing User Intent**\n\nI'm now shifting my focus. I've successfully registered the provided data and file structure. My current task is to understand the user's ultimate goal, given the information provided. The \"Hello.\" command is straightforward, but I'm checking if there's an underlying objective.\n\n\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12270,"totalTokenCount":12341,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12270}],"thoughtsTokenCount":71}},{"candidates":[{"content":{"parts":[{"thoughtSignature":"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","text":"Hello."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12270,"totalTokenCount":12341,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12270}],"thoughtsTokenCount":71}}]}
 {"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"<state_snapshot>\n    <overall_goal>\n        <!-- The user has not yet specified a goal. -->\n    </overall_goal>\n\n    <key_knowledge>\n       - OS: linux\n        - Date: Friday, October 24, 2025\n    </key_knowledge>\n\n    <file_system_state>\n       - OBSERVED: The directory contains `telemetry.log` and a `.gemini/` directory.\n        - OBSERVED: The `.gemini/` directory contains `settings.json` and `settings.json.orig`.\n    </file_system_state>\n\n    <recent_actions>\n        - The user initiated the chat.\n    </recent_actions>\n\n    <current_plan>\n        1. [TODO] Await the user's first instruction to formulate a plan.\n    </current_plan>\n</state_snapshot>"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":983,"candidatesTokenCount":299,"totalTokenCount":1637,"promptTokensDetails":[{"modality":"TEXT","tokenCount":983}],"thoughtsTokenCount":355}}}
+{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"<state_snapshot>\n    <overall_goal>\n        <!-- The user has not yet specified a goal. -->\n    </overall_goal>\n\n    <key_knowledge>\n       - OS: linux\n        - Date: Friday, October 24, 2025\n    </key_knowledge>\n\n    <file_system_state>\n       - OBSERVED: The directory contains `telemetry.log` and a `.gemini/` directory.\n        - OBSERVED: The `.gemini/` directory contains `settings.json` and `settings.json.orig`.\n    </file_system_state>\n\n    <recent_actions>\n        - The user initiated the chat.\n    </recent_actions>\n\n    <current_plan>\n        1. [TODO] Await the user's first instruction to formulate a plan.\n    </current_plan>\n</state_snapshot>"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":983,"candidatesTokenCount":299,"totalTokenCount":1637,"promptTokensDetails":[{"modality":"TEXT","tokenCount":983}],"thoughtsTokenCount":355}}}

integration-tests/context-compress-interactive.compress.responses

@@ -1,3 +1,4 @@
 {"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"thought":true,"text":"**Generating a Story**\n\nI've crafted the robot story. The narrative is complete and meets the length requirement. Now, I'm getting ready to use the `write_file` tool to save it. I'm choosing the filename `robot_story.txt` as a default.\n\n\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12282,"totalTokenCount":12352,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"thoughtsTokenCount":70}},{"candidates":[{"finishReason":"MALFORMED_FUNCTION_CALL","index":0}],"usageMetadata":{"promptTokenCount":12282,"totalTokenCount":12282,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}]}}]}
 {"method":"generateContentStream","response":[{"candidates":[{"content":{"parts":[{"thought":true,"text":"**Drafting the Narrative**\n\nI'm currently focused on the narrative's central conflict. I'm aiming for a compelling story about a robot and am working to keep the word count tight. The \"THE _END.\" conclusion is proving challenging to integrate organically. I need to make the ending feel natural and satisfying.\n\n\n"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12282,"totalTokenCount":12326,"cachedContentTokenCount":11883,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11883}],"thoughtsTokenCount":44}},{"candidates":[{"content":{"parts":[{"thoughtSignature":"CikB0e2Kb7zkpgRyJXXNt6ykO/+FoOglhrKxjLgoESrgafzIZak2Ofxo1gpaAdHtim9aG7MvpXlIg+n2zgmcDBWOPXtvQHxhE9k8pR+DO8i2jIe3tMWLxdN944XpUlR9vaNmVdtSRMKr4MhB/t1R3WSWR3QYhk7MEQxnjYR7cv/pR9viwZyFCoYBAdHtim/xKmMl/S+U8p+p9848q4agsL/STufluXewPqL3uJSinZbN0Z4jTYfMzXKldhDYIonvw3Crn/Y11oAjnT656Sx0kkKtavAXbiU/WsGyDxZbNhLofnJGQxruljPGztxkKawz1cTiQnddnQRfLddhy+3iJIOSh6ZpYq9uGHz3PzVkUuQ=","text":"Unit 734 whirred, its optical sensors scanning the desolate junkyard. For years, its purpose had been clear: compress refuse, maintain order. But today, a glint of tarnished silver beneath a rusted hull"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12282,"candidatesTokenCount":47,"totalTokenCount":12373,"cachedContentTokenCount":11883,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11883}],"thoughtsTokenCount":44}},{"candidates":[{"content":{"parts":[{"text":" caught its attention. It was a discarded music box, its delicate gears jammed, a faint, melancholic tune trapped within.\n\n734 usually crushed, never salvaged. Yet, a new directive flickered in its circuits – curiosity."}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12282,"candidatesTokenCount":95,"totalTokenCount":12421,"cachedContentTokenCount":11883,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11883}],"thoughtsTokenCount":44}},{"candidates":[{"content":{"parts":[{"text":" With surprising gentleness for its formidable pincers, it retrieved the box. Back in its monochrome workshop, it meticulously cleaned and repaired. Each tiny spring, each worn tooth, became a puzzle.\n\nHours later, a soft, ethereal melody filled the clang"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12282,"candidatesTokenCount":146,"totalTokenCount":12472,"cachedContentTokenCount":11883,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11883}],"thoughtsTokenCount":44}},{"candidates":[{"content":{"parts":[{"text":"orous space. The music box sang. 734 felt a strange, new sensation – a warmth in its core processors, a hum of contentment. Its existence, once solely utilitarian, now held a note of beauty, a hint of something more than"}],"role":"model"},"index":0}],"usageMetadata":{"promptTokenCount":12282,"candidatesTokenCount":197,"totalTokenCount":12523,"cachedContentTokenCount":11883,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11883}],"thoughtsTokenCount":44}},{"candidates":[{"content":{"parts":[{"text":" just compression. It had fixed a broken song, and in doing so, had found a different kind of purpose. THE_END."}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":12282,"candidatesTokenCount":224,"totalTokenCount":12550,"cachedContentTokenCount":11883,"promptTokensDetails":[{"modality":"TEXT","tokenCount":12282}],"cacheTokensDetails":[{"modality":"TEXT","tokenCount":11883}],"thoughtsTokenCount":44}}]}
 {"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"scratchpad\nThe user's overall goal was to write a 200-word story about a robot, ending with \"THE_END.\". The agent successfully completed this task.\n\nSince the task is complete, the snapshot should reflect that the goal has been achieved and there are no further actions planned regarding the story.\n\nLet's break down the required sections for the snapshot:\n\n1.  **Overall Goal**: The initial goal was to write a story. This has been completed.\n2.  **Key Knowledge**: No specific key knowledge was provided or discovered during this simple interaction beyond the prompt's constraints.\n3.  **File System State**: No files were read, modified, or created by the agent relevant to the task. The initial file system state was merely provided for context.\n4.  **Recent Actions**: The agent wrote the story.\n5.  **Current Plan**: The plan was to write the story, which is now done. Therefore, the plan should indicate completion."},{"text":"<state_snapshot>\n    <overall_goal>\n        Write a 200-word story about a robot, ending with \"THE_END.\".\n    </overall_goal>\n\n    <key_knowledge>\n        - The story must be approximately 200 words.\n        - The story must end with the exact phrase \"THE_END.\"\n    </key_knowledge>\n\n    <file_system_state>\n        <!-- No relevant file system interactions occurred during this task. -->\n    </file_system_state>\n\n    <recent_actions>\n        - Generated a 200-word story about a robot, successfully ending it with \"THE_END.\".\n    </recent_actions>\n\n    <current_plan>\n        1. [DONE] Write a 200-word story about a robot.\n        2. [DONE] Ensure the story ends with the exact text \"THE_END.\".\n    </current_plan>\n</state_snapshot>"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":1223,"candidatesTokenCount":424,"totalTokenCount":1647,"promptTokensDetails":[{"modality":"TEXT","tokenCount":1223}]}}}
+{"method":"generateContent","response":{"candidates":[{"content":{"parts":[{"text":"scratchpad\nThe user's overall goal was to write a 200-word story about a robot, ending with \"THE_END.\". The agent successfully completed this task.\n\nSince the task is complete, the snapshot should reflect that the goal has been achieved and there are no further actions planned regarding the story.\n\nLet's break down the required sections for the snapshot:\n\n1.  **Overall Goal**: The initial goal was to write a story. This has been completed.\n2.  **Key Knowledge**: No specific key knowledge was provided or discovered during this simple interaction beyond the prompt's constraints.\n3.  **File System State**: No files were read, modified, or created by the agent relevant to the task. The initial file system state was merely provided for context.\n4.  **Recent Actions**: The agent wrote the story.\n5.  **Current Plan**: The plan was to write the story, which is now done. Therefore, the plan should indicate completion."},{"text":"<state_snapshot>\n    <overall_goal>\n        Write a 200-word story about a robot, ending with \"THE_END.\".\n    </overall_goal>\n\n    <key_knowledge>\n        - The story must be approximately 200 words.\n        - The story must end with the exact phrase \"THE_END.\"\n    </key_knowledge>\n\n    <file_system_state>\n        <!-- No relevant file system interactions occurred during this task. -->\n    </file_system_state>\n\n    <recent_actions>\n        - Generated a 200-word story about a robot, successfully ending it with \"THE_END.\".\n    </recent_actions>\n\n    <current_plan>\n        1. [DONE] Write a 200-word story about a robot.\n        2. [DONE] Ensure the story ends with the exact text \"THE_END.\".\n    </current_plan>\n</state_snapshot>"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":1223,"candidatesTokenCount":424,"totalTokenCount":1647,"promptTokensDetails":[{"modality":"TEXT","tokenCount":1223}]}}}

integration-tests/save_memory.test.ts

@@ -1,54 +0,0 @@
-/**
- * @license
- * Copyright 2025 Google LLC
- * SPDX-License-Identifier: Apache-2.0
- */
-
-import { describe, it, expect, beforeEach, afterEach } from 'vitest';
-import { TestRig, printDebugInfo, validateModelOutput } from './test-helper.js';
-
-describe('save_memory', () => {
-  let rig: TestRig;
-
-  beforeEach(() => {
-    rig = new TestRig();
-  });
-
-  afterEach(async () => await rig.cleanup());
-
-  it('should be able to save to memory', async () => {
-    await rig.setup('should be able to save to memory', {
-      settings: { tools: { core: ['save_memory'] } },
-    });
-
-    const prompt = `remember that my favorite color is  blue.
-
-  what is my favorite color? tell me that and surround it with $ symbol`;
-    const result = await rig.run({ args: prompt });
-
-    const foundToolCall = await rig.waitForToolCall('save_memory');
-
-    // Add debugging information
-    if (!foundToolCall || !result.toLowerCase().includes('blue')) {
-      const allTools = printDebugInfo(rig, result, {
-        'Found tool call': foundToolCall,
-        'Contains blue': result.toLowerCase().includes('blue'),
-      });
-
-      console.error(
-        'Memory tool calls:',
-        allTools
-          .filter((t) => t.toolRequest.name === 'save_memory')
-          .map((t) => t.toolRequest.args),
-      );
-    }
-
-    expect(
-      foundToolCall,
-      'Expected to find a save_memory tool call',
-    ).toBeTruthy();
-
-    // Validate model output - will throw if no output, warn if missing expected content
-    validateModelOutput(result, 'blue', 'Save memory test');
-  });
-});

integration-tests/simple-mcp-server.test.ts

@@ -164,7 +164,7 @@ rpc.send({
 });
 `;
 
-describe('simple-mcp-server', () => {
+describe.skip('simple-mcp-server', () => {
   let rig: TestRig;
 
   beforeEach(() => {

integration-tests/skill-creator-scripts.test.ts

@@ -0,0 +1,104 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, beforeEach, afterEach } from 'vitest';
+import { TestRig } from './test-helper.js';
+import * as fs from 'node:fs';
+import * as path from 'node:path';
+import { execSync } from 'node:child_process';
+
+describe('skill-creator scripts e2e', () => {
+  let rig: TestRig;
+  const initScript = path.resolve(
+    'packages/core/src/skills/builtin/skill-creator/scripts/init_skill.cjs',
+  );
+  const validateScript = path.resolve(
+    'packages/core/src/skills/builtin/skill-creator/scripts/validate_skill.cjs',
+  );
+  const packageScript = path.resolve(
+    'packages/core/src/skills/builtin/skill-creator/scripts/package_skill.cjs',
+  );
+
+  beforeEach(() => {
+    rig = new TestRig();
+  });
+
+  afterEach(async () => {
+    await rig.cleanup();
+  });
+
+  it('should initialize, validate, and package a skill', async () => {
+    await rig.setup('skill-creator scripts e2e');
+    const skillName = 'e2e-test-skill';
+    const tempDir = rig.testDir!;
+
+    // 1. Initialize
+    execSync(`node "${initScript}" ${skillName} --path "${tempDir}"`, {
+      stdio: 'inherit',
+    });
+    const skillDir = path.join(tempDir, skillName);
+
+    expect(fs.existsSync(skillDir)).toBe(true);
+    expect(fs.existsSync(path.join(skillDir, 'SKILL.md'))).toBe(true);
+    expect(
+      fs.existsSync(path.join(skillDir, 'scripts/example_script.cjs')),
+    ).toBe(true);
+
+    // 2. Validate (should have warning initially due to TODOs)
+    const validateOutputInitial = execSync(
+      `node "${validateScript}" "${skillDir}" 2>&1`,
+      { encoding: 'utf8' },
+    );
+    expect(validateOutputInitial).toContain('⚠️  Found unresolved TODO');
+
+    // 3. Package (should fail due to TODOs)
+    try {
+      execSync(`node "${packageScript}" "${skillDir}" "${tempDir}"`, {
+        stdio: 'pipe',
+      });
+      throw new Error('Packaging should have failed due to TODOs');
+    } catch (err: unknown) {
+      expect((err as Error).message).toContain('Command failed');
+    }
+
+    // 4. Fix SKILL.md (remove TODOs)
+    let content = fs.readFileSync(path.join(skillDir, 'SKILL.md'), 'utf8');
+    // More aggressive global replace for all TODO patterns
+    content = content.replace(/TODO:[^\n]*/g, 'Fixed');
+    content = content.replace(/\[TODO:[^\]]*\]/g, 'Fixed');
+    fs.writeFileSync(path.join(skillDir, 'SKILL.md'), content);
+
+    // Also remove TODOs from example scripts
+    const exampleScriptPath = path.join(skillDir, 'scripts/example_script.cjs');
+    let scriptContent = fs.readFileSync(exampleScriptPath, 'utf8');
+    scriptContent = scriptContent.replace(/TODO:[^\n]*/g, 'Fixed');
+    fs.writeFileSync(exampleScriptPath, scriptContent);
+
+    // 4. Validate again (should pass now)
+    const validateOutput = execSync(`node "${validateScript}" "${skillDir}"`, {
+      encoding: 'utf8',
+    });
+    expect(validateOutput).toContain('Skill is valid!');
+
+    // 5. Package
+    execSync(`node "${packageScript}" "${skillDir}" "${tempDir}"`, {
+      stdio: 'inherit',
+    });
+    const skillFile = path.join(tempDir, `${skillName}.skill`);
+    expect(fs.existsSync(skillFile)).toBe(true);
+
+    // 6. Verify zip content (should NOT have nested directory)
+    // Use unzip -l if available, otherwise fallback to tar -tf (common on Windows)
+    let zipList: string;
+    try {
+      zipList = execSync(`unzip -l "${skillFile}"`, { encoding: 'utf8' });
+    } catch {
+      zipList = execSync(`tar -tf "${skillFile}"`, { encoding: 'utf8' });
+    }
+    expect(zipList).toContain('SKILL.md');
+    expect(zipList).not.toContain(`${skillName}/SKILL.md`);
+  });
+});

integration-tests/skill-creator-vulnerabilities.test.ts

@@ -0,0 +1,111 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, beforeEach, afterEach } from 'vitest';
+import { TestRig } from './test-helper.js';
+import * as fs from 'node:fs';
+import * as path from 'node:path';
+import { execSync, spawnSync } from 'node:child_process';
+
+describe('skill-creator scripts security and bug fixes', () => {
+  let rig: TestRig;
+  const initScript = path.resolve(
+    'packages/core/src/skills/builtin/skill-creator/scripts/init_skill.cjs',
+  );
+  const validateScript = path.resolve(
+    'packages/core/src/skills/builtin/skill-creator/scripts/validate_skill.cjs',
+  );
+  const packageScript = path.resolve(
+    'packages/core/src/skills/builtin/skill-creator/scripts/package_skill.cjs',
+  );
+
+  beforeEach(() => {
+    rig = new TestRig();
+  });
+
+  afterEach(async () => {
+    await rig.cleanup();
+  });
+
+  it('should prevent command injection in package_skill.cjs', async () => {
+    await rig.setup('skill-creator command injection');
+    const tempDir = rig.testDir!;
+
+    // Create a dummy skill
+    const skillName = 'injection-test';
+    execSync(`node "${initScript}" ${skillName} --path "${tempDir}"`);
+    const skillDir = path.join(tempDir, skillName);
+
+    // Malicious output filename with command injection
+    const maliciousFilename = '"; touch injection_success; #';
+
+    // Attempt to package with malicious filename
+    // We expect this to fail or at least NOT create the 'injection_success' file
+    spawnSync('node', [packageScript, skillDir, tempDir, maliciousFilename], {
+      cwd: tempDir,
+    });
+
+    const injectionFile = path.join(tempDir, 'injection_success');
+    expect(fs.existsSync(injectionFile)).toBe(false);
+  });
+
+  it('should prevent path traversal in init_skill.cjs', async () => {
+    await rig.setup('skill-creator init path traversal');
+    const tempDir = rig.testDir!;
+
+    const maliciousName = '../traversal-success';
+
+    const result = spawnSync(
+      'node',
+      [initScript, maliciousName, '--path', tempDir],
+      {
+        encoding: 'utf8',
+      },
+    );
+
+    expect(result.stderr).toContain(
+      'Error: Skill name cannot contain path separators',
+    );
+    const traversalDir = path.join(path.dirname(tempDir), 'traversal-success');
+    expect(fs.existsSync(traversalDir)).toBe(false);
+  });
+
+  it('should prevent path traversal in validate_skill.cjs', async () => {
+    await rig.setup('skill-creator validate path traversal');
+
+    const maliciousPath = '../../../../etc/passwd';
+    const result = spawnSync('node', [validateScript, maliciousPath], {
+      encoding: 'utf8',
+    });
+
+    expect(result.stderr).toContain('Error: Path traversal detected');
+  });
+
+  it('should not crash on empty description in validate_skill.cjs', async () => {
+    await rig.setup('skill-creator regex crash');
+    const tempDir = rig.testDir!;
+    const skillName = 'empty-desc-skill';
+
+    execSync(`node "${initScript}" ${skillName} --path "${tempDir}"`);
+    const skillDir = path.join(tempDir, skillName);
+    const skillMd = path.join(skillDir, 'SKILL.md');
+
+    // Set an empty quoted description
+    let content = fs.readFileSync(skillMd, 'utf8');
+    content = content.replace(/^description: .+$/m, 'description: ""');
+    fs.writeFileSync(skillMd, content);
+
+    const result = spawnSync('node', [validateScript, skillDir], {
+      encoding: 'utf8',
+    });
+
+    // It might still fail validation (e.g. TODOs), but it should NOT crash with a stack trace
+    expect(result.status).not.toBe(null);
+    expect(result.stderr).not.toContain(
+      "TypeError: Cannot read properties of undefined (reading 'trim')",
+    );
+  });
+});

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli",
-  "version": "0.25.0-nightly.20260107.59a18e710",
+  "version": "0.26.0-nightly.20260115.6cb3ae4e0",
   "engines": {
     "node": ">=20.0.0"
   },
@@ -14,7 +14,7 @@
     "url": "git+https://github.com/google-gemini/gemini-cli.git"
   },
   "config": {
-    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.25.0-nightly.20260107.59a18e710"
+    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.26.0-nightly.20260115.6cb3ae4e0"
   },
   "scripts": {
     "start": "cross-env NODE_ENV=development node scripts/start.js",
@@ -41,6 +41,8 @@
     "test": "npm run test --workspaces --if-present",
     "test:ci": "npm run test:ci --workspaces --if-present && npm run test:scripts",
     "test:scripts": "vitest run --config ./scripts/tests/vitest.config.ts",
+    "test:always_passing_evals": "vitest run --config evals/vitest.config.ts",
+    "test:all_evals": "cross-env RUN_EVALS=1 vitest run --config evals/vitest.config.ts",
     "test:e2e": "cross-env VERBOSE=true KEEP_OUTPUT=true npm run test:integration:sandbox:none",
     "test:integration:all": "npm run test:integration:sandbox:none && npm run test:integration:sandbox:docker && npm run test:integration:sandbox:podman",
     "test:integration:sandbox:none": "cross-env GEMINI_SANDBOX=false vitest run --root ./integration-tests",
@@ -62,7 +64,7 @@
     "pre-commit": "node scripts/pre-commit.js"
   },
   "overrides": {
-    "ink": "npm:@jrichman/ink@6.4.6",
+    "ink": "npm:@jrichman/ink@6.4.7",
     "wrap-ansi": "9.0.2",
     "cliui": {
       "wrap-ansi": "7.0.0"
@@ -77,6 +79,7 @@
     "LICENSE"
   ],
   "devDependencies": {
+    "@agentclientprotocol/sdk": "^0.12.0",
     "@octokit/rest": "^22.0.0",
     "@types/marked": "^5.0.2",
     "@types/mime-types": "^3.0.1",
@@ -121,7 +124,7 @@
     "yargs": "^17.7.2"
   },
   "dependencies": {
-    "ink": "npm:@jrichman/ink@6.4.6",
+    "ink": "npm:@jrichman/ink@6.4.7",
     "latest-version": "^9.0.0",
     "simple-git": "^3.28.0"
   },

packages/a2a-server/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli-a2a-server",
-  "version": "0.25.0-nightly.20260107.59a18e710",
+  "version": "0.26.0-nightly.20260115.6cb3ae4e0",
   "description": "Gemini CLI A2A Server",
   "repository": {
     "type": "git",
@@ -25,7 +25,7 @@
     "dist"
   ],
   "dependencies": {
-    "@a2a-js/sdk": "^0.3.7",
+    "@a2a-js/sdk": "^0.3.8",
     "@google-cloud/storage": "^7.16.0",
     "@google/gemini-cli-core": "file:../core",
     "express": "^5.1.0",

packages/a2a-server/src/agent/task.test.ts

@@ -349,6 +349,44 @@ describe('Task', () => {
         }),
       );
     });
+
+    it.each([
+      { eventType: GeminiEventType.Retry, eventName: 'Retry' },
+      { eventType: GeminiEventType.InvalidStream, eventName: 'InvalidStream' },
+    ])(
+      'should handle $eventName event without triggering error handling',
+      async ({ eventType }) => {
+        const mockConfig = createMockConfig();
+        const mockEventBus: ExecutionEventBus = {
+          publish: vi.fn(),
+          on: vi.fn(),
+          off: vi.fn(),
+          once: vi.fn(),
+          removeAllListeners: vi.fn(),
+          finished: vi.fn(),
+        };
+
+        // @ts-expect-error - Calling private constructor
+        const task = new Task(
+          'task-id',
+          'context-id',
+          mockConfig as Config,
+          mockEventBus,
+        );
+
+        const cancelPendingToolsSpy = vi.spyOn(task, 'cancelPendingTools');
+        const setTaskStateSpy = vi.spyOn(task, 'setTaskStateAndPublishUpdate');
+
+        const event = {
+          type: eventType,
+        };
+
+        await task.acceptAgentMessage(event);
+
+        expect(cancelPendingToolsSpy).not.toHaveBeenCalled();
+        expect(setTaskStateSpy).not.toHaveBeenCalled();
+      },
+    );
   });
 
   describe('_schedulerToolCallsUpdate', () => {

packages/a2a-server/src/agent/task.ts

@@ -378,7 +378,7 @@ export class Task {
       if (tc.status === 'awaiting_approval' && tc.confirmationDetails) {
         this.pendingToolConfirmationDetails.set(
           tc.request.callId,
-          tc.confirmationDetails,
+          tc.confirmationDetails as ToolCallConfirmationDetails,
         );
       }
 
@@ -412,7 +412,9 @@ export class Task {
       toolCalls.forEach((tc: ToolCall) => {
         if (tc.status === 'awaiting_approval' && tc.confirmationDetails) {
           // eslint-disable-next-line @typescript-eslint/no-floating-promises
-          tc.confirmationDetails.onConfirm(ToolConfirmationOutcome.ProceedOnce);
+          (tc.confirmationDetails as ToolCallConfirmationDetails).onConfirm(
+            ToolConfirmationOutcome.ProceedOnce,
+          );
           this.pendingToolConfirmationDetails.delete(tc.request.callId);
         }
       });
@@ -707,6 +709,10 @@ export class Task {
       case GeminiEventType.ModelInfo:
         this.modelInfo = event.value;
         break;
+      case GeminiEventType.Retry:
+      case GeminiEventType.InvalidStream:
+        // An invalid stream should trigger a retry, which requires no action from the user.
+        break;
       case GeminiEventType.Error:
       default: {
         // Block scope for lexical declaration

packages/a2a-server/src/commands/command-registry.ts

@@ -4,6 +4,7 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
+import { MemoryCommand } from './memory.js';
 import { debugLogger } from '@google/gemini-cli-core';
 import { ExtensionsCommand } from './extensions.js';
 import { InitCommand } from './init.js';
@@ -22,6 +23,7 @@ export class CommandRegistry {
     this.register(new ExtensionsCommand());
     this.register(new RestoreCommand());
     this.register(new InitCommand());
+    this.register(new MemoryCommand());
   }
 
   register(command: Command) {

packages/a2a-server/src/commands/memory.test.ts

@@ -0,0 +1,208 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import {
+  addMemory,
+  listMemoryFiles,
+  refreshMemory,
+  showMemory,
+} from '@google/gemini-cli-core';
+import { beforeEach, describe, expect, it, vi } from 'vitest';
+import {
+  AddMemoryCommand,
+  ListMemoryCommand,
+  MemoryCommand,
+  RefreshMemoryCommand,
+  ShowMemoryCommand,
+} from './memory.js';
+import type { CommandContext } from './types.js';
+import type {
+  AnyDeclarativeTool,
+  Config,
+  ToolRegistry,
+} from '@google/gemini-cli-core';
+
+// Mock the core functions
+vi.mock('@google/gemini-cli-core', async (importOriginal) => {
+  const actual =
+    await importOriginal<typeof import('@google/gemini-cli-core')>();
+  return {
+    ...actual,
+    showMemory: vi.fn(),
+    refreshMemory: vi.fn(),
+    listMemoryFiles: vi.fn(),
+    addMemory: vi.fn(),
+  };
+});
+
+const mockShowMemory = vi.mocked(showMemory);
+const mockRefreshMemory = vi.mocked(refreshMemory);
+const mockListMemoryFiles = vi.mocked(listMemoryFiles);
+const mockAddMemory = vi.mocked(addMemory);
+
+describe('a2a-server memory commands', () => {
+  let mockContext: CommandContext;
+  let mockConfig: Config;
+  let mockToolRegistry: ToolRegistry;
+  let mockSaveMemoryTool: AnyDeclarativeTool;
+
+  beforeEach(() => {
+    mockSaveMemoryTool = {
+      name: 'save_memory',
+      description: 'Saves memory',
+      buildAndExecute: vi.fn().mockResolvedValue(undefined),
+    } as unknown as AnyDeclarativeTool;
+
+    mockToolRegistry = {
+      getTool: vi.fn(),
+    } as unknown as ToolRegistry;
+
+    mockConfig = {
+      getToolRegistry: vi.fn().mockReturnValue(mockToolRegistry),
+    } as unknown as Config;
+
+    mockContext = {
+      config: mockConfig,
+    };
+
+    vi.mocked(mockToolRegistry.getTool).mockReturnValue(mockSaveMemoryTool);
+  });
+
+  describe('MemoryCommand', () => {
+    it('delegates to ShowMemoryCommand', async () => {
+      const command = new MemoryCommand();
+      mockShowMemory.mockReturnValue({
+        type: 'message',
+        messageType: 'info',
+        content: 'showing memory',
+      });
+      const response = await command.execute(mockContext, []);
+      expect(response.data).toBe('showing memory');
+      expect(mockShowMemory).toHaveBeenCalledWith(mockContext.config);
+    });
+  });
+
+  describe('ShowMemoryCommand', () => {
+    it('executes showMemory and returns the content', async () => {
+      const command = new ShowMemoryCommand();
+      mockShowMemory.mockReturnValue({
+        type: 'message',
+        messageType: 'info',
+        content: 'test memory content',
+      });
+
+      const response = await command.execute(mockContext, []);
+
+      expect(mockShowMemory).toHaveBeenCalledWith(mockContext.config);
+      expect(response.name).toBe('memory show');
+      expect(response.data).toBe('test memory content');
+    });
+  });
+
+  describe('RefreshMemoryCommand', () => {
+    it('executes refreshMemory and returns the content', async () => {
+      const command = new RefreshMemoryCommand();
+      mockRefreshMemory.mockResolvedValue({
+        type: 'message',
+        messageType: 'info',
+        content: 'memory refreshed',
+      });
+
+      const response = await command.execute(mockContext, []);
+
+      expect(mockRefreshMemory).toHaveBeenCalledWith(mockContext.config);
+      expect(response.name).toBe('memory refresh');
+      expect(response.data).toBe('memory refreshed');
+    });
+  });
+
+  describe('ListMemoryCommand', () => {
+    it('executes listMemoryFiles and returns the content', async () => {
+      const command = new ListMemoryCommand();
+      mockListMemoryFiles.mockReturnValue({
+        type: 'message',
+        messageType: 'info',
+        content: 'file1.md\nfile2.md',
+      });
+
+      const response = await command.execute(mockContext, []);
+
+      expect(mockListMemoryFiles).toHaveBeenCalledWith(mockContext.config);
+      expect(response.name).toBe('memory list');
+      expect(response.data).toBe('file1.md\nfile2.md');
+    });
+  });
+
+  describe('AddMemoryCommand', () => {
+    it('returns message content if addMemory returns a message', async () => {
+      const command = new AddMemoryCommand();
+      mockAddMemory.mockReturnValue({
+        type: 'message',
+        messageType: 'error',
+        content: 'error message',
+      });
+
+      const response = await command.execute(mockContext, []);
+
+      expect(mockAddMemory).toHaveBeenCalledWith('');
+      expect(response.name).toBe('memory add');
+      expect(response.data).toBe('error message');
+    });
+
+    it('executes the save_memory tool if found', async () => {
+      const command = new AddMemoryCommand();
+      const fact = 'this is a new fact';
+      mockAddMemory.mockReturnValue({
+        type: 'tool',
+        toolName: 'save_memory',
+        toolArgs: { fact },
+      });
+
+      const response = await command.execute(mockContext, [
+        'this',
+        'is',
+        'a',
+        'new',
+        'fact',
+      ]);
+
+      expect(mockAddMemory).toHaveBeenCalledWith(fact);
+      expect(mockConfig.getToolRegistry).toHaveBeenCalled();
+      expect(mockToolRegistry.getTool).toHaveBeenCalledWith('save_memory');
+      expect(mockSaveMemoryTool.buildAndExecute).toHaveBeenCalledWith(
+        { fact },
+        expect.any(AbortSignal),
+        undefined,
+        {
+          sanitizationConfig: {
+            allowedEnvironmentVariables: [],
+            blockedEnvironmentVariables: [],
+            enableEnvironmentVariableRedaction: false,
+          },
+        },
+      );
+      expect(mockRefreshMemory).toHaveBeenCalledWith(mockContext.config);
+      expect(response.name).toBe('memory add');
+      expect(response.data).toBe(`Added memory: "${fact}"`);
+    });
+
+    it('returns an error if the tool is not found', async () => {
+      const command = new AddMemoryCommand();
+      const fact = 'another fact';
+      mockAddMemory.mockReturnValue({
+        type: 'tool',
+        toolName: 'save_memory',
+        toolArgs: { fact },
+      });
+      vi.mocked(mockToolRegistry.getTool).mockReturnValue(undefined);
+
+      const response = await command.execute(mockContext, ['another', 'fact']);
+
+      expect(response.name).toBe('memory add');
+      expect(response.data).toBe('Error: Tool save_memory not found.');
+    });
+  });
+});

packages/a2a-server/src/commands/memory.ts

@@ -0,0 +1,118 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import {
+  addMemory,
+  listMemoryFiles,
+  refreshMemory,
+  showMemory,
+} from '@google/gemini-cli-core';
+import type {
+  Command,
+  CommandContext,
+  CommandExecutionResponse,
+} from './types.js';
+
+const DEFAULT_SANITIZATION_CONFIG = {
+  allowedEnvironmentVariables: [],
+  blockedEnvironmentVariables: [],
+  enableEnvironmentVariableRedaction: false,
+};
+
+export class MemoryCommand implements Command {
+  readonly name = 'memory';
+  readonly description = 'Manage memory.';
+  readonly subCommands = [
+    new ShowMemoryCommand(),
+    new RefreshMemoryCommand(),
+    new ListMemoryCommand(),
+    new AddMemoryCommand(),
+  ];
+  readonly topLevel = true;
+  readonly requiresWorkspace = true;
+
+  async execute(
+    context: CommandContext,
+    _: string[],
+  ): Promise<CommandExecutionResponse> {
+    return new ShowMemoryCommand().execute(context, _);
+  }
+}
+
+export class ShowMemoryCommand implements Command {
+  readonly name = 'memory show';
+  readonly description = 'Shows the current memory contents.';
+
+  async execute(
+    context: CommandContext,
+    _: string[],
+  ): Promise<CommandExecutionResponse> {
+    const result = showMemory(context.config);
+    return { name: this.name, data: result.content };
+  }
+}
+
+export class RefreshMemoryCommand implements Command {
+  readonly name = 'memory refresh';
+  readonly description = 'Refreshes the memory from the source.';
+
+  async execute(
+    context: CommandContext,
+    _: string[],
+  ): Promise<CommandExecutionResponse> {
+    const result = await refreshMemory(context.config);
+    return { name: this.name, data: result.content };
+  }
+}
+
+export class ListMemoryCommand implements Command {
+  readonly name = 'memory list';
+  readonly description = 'Lists the paths of the GEMINI.md files in use.';
+
+  async execute(
+    context: CommandContext,
+    _: string[],
+  ): Promise<CommandExecutionResponse> {
+    const result = listMemoryFiles(context.config);
+    return { name: this.name, data: result.content };
+  }
+}
+
+export class AddMemoryCommand implements Command {
+  readonly name = 'memory add';
+  readonly description = 'Add content to the memory.';
+
+  async execute(
+    context: CommandContext,
+    args: string[],
+  ): Promise<CommandExecutionResponse> {
+    const textToAdd = args.join(' ').trim();
+    const result = addMemory(textToAdd);
+    if (result.type === 'message') {
+      return { name: this.name, data: result.content };
+    }
+
+    const toolRegistry = context.config.getToolRegistry();
+    const tool = toolRegistry.getTool(result.toolName);
+    if (tool) {
+      const abortController = new AbortController();
+      const signal = abortController.signal;
+      await tool.buildAndExecute(result.toolArgs, signal, undefined, {
+        sanitizationConfig: DEFAULT_SANITIZATION_CONFIG,
+      });
+      await refreshMemory(context.config);
+      return {
+        name: this.name,
+        data: `Added memory: "${textToAdd}"`,
+      };
+    } else {
+      return {
+        name: this.name,
+        data: `Error: Tool ${result.toolName} not found.`,
+      };
+    }
+  }
+}

packages/a2a-server/src/config/config.ts

@@ -37,6 +37,10 @@ export async function loadConfig(
   const workspaceDir = process.cwd();
   const adcFilePath = process.env['GOOGLE_APPLICATION_CREDENTIALS'];
 
+  const folderTrust =
+    settings.folderTrust === true ||
+    process.env['GEMINI_FOLDER_TRUST'] === 'true';
+
   const configParams: ConfigParameters = {
     sessionId: taskId,
     model: settings.general?.previewFeatures
@@ -72,7 +76,8 @@ export async function loadConfig(
         settings.fileFiltering?.enableRecursiveFileSearch,
     },
     ideMode: false,
-    folderTrust: settings.folderTrust === true,
+    folderTrust,
+    trustedFolder: true,
     extensionLoader,
     checkpointing: process.env['CHECKPOINTING']
       ? process.env['CHECKPOINTING'] === 'true'
@@ -83,16 +88,18 @@ export async function loadConfig(
   };
 
   const fileService = new FileDiscoveryService(workspaceDir);
-  const { memoryContent, fileCount } = await loadServerHierarchicalMemory(
-    workspaceDir,
-    [workspaceDir],
-    false,
-    fileService,
-    extensionLoader,
-    settings.folderTrust === true,
-  );
+  const { memoryContent, fileCount, filePaths } =
+    await loadServerHierarchicalMemory(
+      workspaceDir,
+      [workspaceDir],
+      false,
+      fileService,
+      extensionLoader,
+      folderTrust,
+    );
   configParams.userMemory = memoryContent;
   configParams.geminiMdFileCount = fileCount;
+  configParams.geminiMdFilePaths = filePaths;
   const config = new Config({
     ...configParams,
   });

packages/a2a-server/src/http/app.test.ts

@@ -14,7 +14,7 @@ import type {
   TaskStatusUpdateEvent,
   SendStreamingMessageSuccessResponse,
 } from '@a2a-js/sdk';
-import type express from 'express';
+import express from 'express';
 import type { Server } from 'node:http';
 import request from 'supertest';
 import {
@@ -27,7 +27,7 @@ import {
   it,
   vi,
 } from 'vitest';
-import { createApp } from './app.js';
+import { createApp, main } from './app.js';
 import { commandRegistry } from '../commands/command-registry.js';
 import {
   assertUniqueFinalEventIsLast,
@@ -1176,4 +1176,43 @@ describe('E2E Tests', () => {
       });
     });
   });
+
+  describe('main', () => {
+    it('should listen on localhost only', async () => {
+      const listenSpy = vi
+        .spyOn(express.application, 'listen')
+        .mockImplementation((...args: unknown[]) => {
+          // Trigger the callback passed to listen
+          const callback = args.find(
+            (arg): arg is () => void => typeof arg === 'function',
+          );
+          if (callback) {
+            callback();
+          }
+
+          return {
+            address: () => ({ port: 1234 }),
+            on: vi.fn(),
+            once: vi.fn(),
+            emit: vi.fn(),
+          } as unknown as Server;
+        });
+
+      // Avoid process.exit if possible, or mock it if main might fail
+      const exitSpy = vi
+        .spyOn(process, 'exit')
+        .mockImplementation(() => undefined as never);
+
+      await main();
+
+      expect(listenSpy).toHaveBeenCalledWith(
+        expect.any(Number),
+        'localhost',
+        expect.any(Function),
+      );
+
+      listenSpy.mockRestore();
+      exitSpy.mockRestore();
+    });
+  });
 });

packages/a2a-server/src/http/app.ts

@@ -326,9 +326,9 @@ export async function createApp() {
 export async function main() {
   try {
     const expressApp = await createApp();
-    const port = process.env['CODER_AGENT_PORT'] || 0;
+    const port = Number(process.env['CODER_AGENT_PORT'] || 0);
 
-    const server = expressApp.listen(port, () => {
+    const server = expressApp.listen(port, 'localhost', () => {
       const address = server.address();
       let actualPort;
       if (process.env['CODER_AGENT_PORT']) {

packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@google/gemini-cli",
-  "version": "0.25.0-nightly.20260107.59a18e710",
+  "version": "0.26.0-nightly.20260115.6cb3ae4e0",
   "description": "Gemini CLI",
   "license": "Apache-2.0",
   "repository": {
@@ -26,10 +26,10 @@
     "dist"
   ],
   "config": {
-    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.25.0-nightly.20260107.59a18e710"
+    "sandboxImageUri": "us-docker.pkg.dev/gemini-code-dev/gemini-cli/sandbox:0.26.0-nightly.20260115.6cb3ae4e0"
   },
   "dependencies": {
-    "@agentclientprotocol/sdk": "^0.11.0",
+    "@agentclientprotocol/sdk": "^0.12.0",
     "@google/gemini-cli-core": "file:../core",
     "@google/genai": "1.30.0",
     "@iarna/toml": "^2.2.5",
@@ -37,6 +37,7 @@
     "@types/update-notifier": "^6.0.8",
     "ansi-regex": "^6.2.2",
     "clipboardy": "^5.0.0",
+    "color-convert": "^2.0.1",
     "command-exists": "^1.2.9",
     "comment-json": "^4.2.5",
     "diff": "^7.0.0",
@@ -45,7 +46,7 @@
     "fzf": "^0.5.2",
     "glob": "^12.0.0",
     "highlight.js": "^11.11.1",
-    "ink": "npm:@jrichman/ink@6.4.6",
+    "ink": "npm:@jrichman/ink@6.4.7",
     "ink-gradient": "^3.0.0",
     "ink-spinner": "^5.0.0",
     "latest-version": "^9.0.0",

packages/cli/src/commands/extensions/configure.ts

@@ -12,7 +12,8 @@ import {
   getScopedEnvContents,
 } from '../../config/extensions/extensionSettings.js';
 import { getExtensionAndManager, getExtensionManager } from './utils.js';
-import { debugLogger } from '@google/gemini-cli-core';
+import { loadSettings } from '../../config/settings.js';
+import { debugLogger, coreEvents } from '@google/gemini-cli-core';
 import { exitCli } from '../utils.js';
 import prompts from 'prompts';
 import type { ExtensionConfig } from '../../config/extension.js';
@@ -43,6 +44,16 @@ export const configureCommand: CommandModule<object, ConfigureArgs> = {
       }),
   handler: async (args) => {
     const { name, setting, scope } = args;
+    const settings = loadSettings(process.cwd()).merged;
+
+    if (!(settings.experimental?.extensionConfig ?? true)) {
+      coreEvents.emitFeedback(
+        'error',
+        'Extension configuration is currently disabled. Enable it by setting "experimental.extensionConfig" to true.',
+      );
+      await exitCli();
+      return;
+    }
 
     if (name) {
       if (name.includes('/') || name.includes('\\') || name.includes('..')) {

packages/cli/src/commands/hooks/migrate.ts

@@ -230,8 +230,7 @@ export async function handleMigrateFromClaude() {
   const settings = loadSettings(workingDir);
 
   // Merge migrated hooks with existing hooks
-  const existingHooks =
-    (settings.merged.hooks as Record<string, unknown>) || {};
+  const existingHooks = settings.merged.hooks as Record<string, unknown>;
   const mergedHooks = { ...existingHooks, ...migratedHooks };
 
   // Update settings (setValue automatically saves)

packages/cli/src/commands/mcp/list.test.ts

@@ -6,15 +6,20 @@
 
 import { vi, describe, it, expect, beforeEach, type Mock } from 'vitest';
 import { listMcpServers } from './list.js';
-import { loadSettings } from '../../config/settings.js';
+import { loadSettings, mergeSettings } from '../../config/settings.js';
 import { createTransport, debugLogger } from '@google/gemini-cli-core';
 import { Client } from '@modelcontextprotocol/sdk/client/index.js';
 import { ExtensionStorage } from '../../config/extensions/storage.js';
 import { ExtensionManager } from '../../config/extension-manager.js';
 
-vi.mock('../../config/settings.js', () => ({
-  loadSettings: vi.fn(),
-}));
+vi.mock('../../config/settings.js', async (importOriginal) => {
+  const actual =
+    await importOriginal<typeof import('../../config/settings.js')>();
+  return {
+    ...actual,
+    loadSettings: vi.fn(),
+  };
+});
 vi.mock('../../config/extensions/storage.js', () => ({
   ExtensionStorage: {
     getUserExtensionsDir: vi.fn(),
@@ -32,11 +37,16 @@ vi.mock('@google/gemini-cli-core', async (importOriginal) => {
       CONNECTING: 'CONNECTING',
       DISCONNECTED: 'DISCONNECTED',
     },
-    Storage: vi.fn().mockImplementation((_cwd: string) => ({
-      getGlobalSettingsPath: () => '/tmp/gemini/settings.json',
-      getWorkspaceSettingsPath: () => '/tmp/gemini/workspace-settings.json',
-      getProjectTempDir: () => '/test/home/.gemini/tmp/mocked_hash',
-    })),
+    Storage: Object.assign(
+      vi.fn().mockImplementation((_cwd: string) => ({
+        getGlobalSettingsPath: () => '/tmp/gemini/settings.json',
+        getWorkspaceSettingsPath: () => '/tmp/gemini/workspace-settings.json',
+        getProjectTempDir: () => '/test/home/.gemini/tmp/mocked_hash',
+      })),
+      {
+        getGlobalSettingsPath: () => '/tmp/gemini/settings.json',
+      },
+    ),
     GEMINI_DIR: '.gemini',
     getErrorMessage: (e: unknown) =>
       e instanceof Error ? e.message : String(e),
@@ -96,7 +106,10 @@ describe('mcp list command', () => {
   });
 
   it('should display message when no servers configured', async () => {
-    mockedLoadSettings.mockReturnValue({ merged: { mcpServers: {} } });
+    const defaultMergedSettings = mergeSettings({}, {}, {}, {}, true);
+    mockedLoadSettings.mockReturnValue({
+      merged: { ...defaultMergedSettings, mcpServers: {} },
+    });
 
     await listMcpServers();
 
@@ -104,8 +117,10 @@ describe('mcp list command', () => {
   });
 
   it('should display different server types with connected status', async () => {
+    const defaultMergedSettings = mergeSettings({}, {}, {}, {}, true);
     mockedLoadSettings.mockReturnValue({
       merged: {
+        ...defaultMergedSettings,
         mcpServers: {
           'stdio-server': { command: '/path/to/server', args: ['arg1'] },
           'sse-server': { url: 'https://example.com/sse' },
@@ -138,8 +153,10 @@ describe('mcp list command', () => {
   });
 
   it('should display disconnected status when connection fails', async () => {
+    const defaultMergedSettings = mergeSettings({}, {}, {}, {}, true);
     mockedLoadSettings.mockReturnValue({
       merged: {
+        ...defaultMergedSettings,
         mcpServers: {
           'test-server': { command: '/test/server' },
         },
@@ -158,9 +175,13 @@ describe('mcp list command', () => {
   });
 
   it('should merge extension servers with config servers', async () => {
+    const defaultMergedSettings = mergeSettings({}, {}, {}, {}, true);
     mockedLoadSettings.mockReturnValue({
       merged: {
-        mcpServers: { 'config-server': { command: '/config/server' } },
+        ...defaultMergedSettings,
+        mcpServers: {
+          'config-server': { command: '/config/server' },
+        },
       },
     });
 

packages/cli/src/commands/mcp/list.ts

@@ -35,7 +35,7 @@ async function getMcpServersFromConfig(): Promise<
     requestSetting: promptForSetting,
   });
   const extensions = await extensionManager.loadExtensions();
-  const mcpServers = { ...(settings.merged.mcpServers || {}) };
+  const mcpServers = { ...settings.merged.mcpServers };
   for (const extension of extensions) {
     Object.entries(extension.mcpServers || {}).forEach(([key, server]) => {
       if (mcpServers[key]) {
@@ -63,8 +63,7 @@ async function testMCPConnection(
   const sanitizationConfig = {
     enableEnvironmentVariableRedaction: true,
     allowedEnvironmentVariables: [],
-    blockedEnvironmentVariables:
-      settings.merged.advanced?.excludedEnvVars || [],
+    blockedEnvironmentVariables: settings.merged.advanced.excludedEnvVars,
   };
 
   let transport;

packages/cli/src/commands/skills.tsx

@@ -8,6 +8,8 @@ import type { CommandModule } from 'yargs';
 import { listCommand } from './skills/list.js';
 import { enableCommand } from './skills/enable.js';
 import { disableCommand } from './skills/disable.js';
+import { installCommand } from './skills/install.js';
+import { uninstallCommand } from './skills/uninstall.js';
 import { initializeOutputListenersAndFlush } from '../gemini.js';
 
 export const skillsCommand: CommandModule = {
@@ -20,6 +22,8 @@ export const skillsCommand: CommandModule = {
       .command(listCommand)
       .command(enableCommand)
       .command(disableCommand)
+      .command(installCommand)
+      .command(uninstallCommand)
       .demandCommand(1, 'You need at least one command before continuing.')
       .version(false),
   handler: () => {

packages/cli/src/commands/skills/disable.test.ts

@@ -80,7 +80,35 @@ describe('skills disable command', () => {
       );
       expect(emitConsoleLog).toHaveBeenCalledWith(
         'log',
-        'Skill "skill1" disabled by adding it to the disabled list in user (/user/settings.json) settings. Restart required to take effect.',
+        'Skill "skill1" disabled by adding it to the disabled list in user (/user/settings.json) settings.',
+      );
+    });
+
+    it('should disable an enabled skill in workspace scope', async () => {
+      const mockSettings = {
+        forScope: vi.fn().mockReturnValue({
+          settings: { skills: { disabled: [] } },
+          path: '/workspace/.gemini/settings.json',
+        }),
+        setValue: vi.fn(),
+      };
+      mockLoadSettings.mockReturnValue(
+        mockSettings as unknown as LoadedSettings,
+      );
+
+      await handleDisable({
+        name: 'skill1',
+        scope: SettingScope.Workspace as LoadableSettingScope,
+      });
+
+      expect(mockSettings.setValue).toHaveBeenCalledWith(
+        SettingScope.Workspace,
+        'skills.disabled',
+        ['skill1'],
+      );
+      expect(emitConsoleLog).toHaveBeenCalledWith(
+        'log',
+        'Skill "skill1" disabled by adding it to the disabled list in workspace (/workspace/.gemini/settings.json) settings.',
       );
     });
 
@@ -108,7 +136,7 @@ describe('skills disable command', () => {
 
   describe('disableCommand', () => {
     it('should have correct command and describe', () => {
-      expect(disableCommand.command).toBe('disable <name>');
+      expect(disableCommand.command).toBe('disable <name> [--scope]');
       expect(disableCommand.describe).toBe('Disables an agent skill.');
     });
   });

packages/cli/src/commands/skills/disable.ts

@@ -23,18 +23,15 @@ export async function handleDisable(args: DisableArgs) {
   const settings = loadSettings(workspaceDir);
 
   const result = disableSkill(settings, name, scope);
-  let feedback = renderSkillActionFeedback(
+  const feedback = renderSkillActionFeedback(
     result,
     (label, path) => `${chalk.bold(label)} (${chalk.dim(path)})`,
   );
-  if (result.status === 'success') {
-    feedback += ' Restart required to take effect.';
-  }
   debugLogger.log(feedback);
 }
 
 export const disableCommand: CommandModule = {
-  command: 'disable <name>',
+  command: 'disable <name> [--scope]',
   describe: 'Disables an agent skill.',
   builder: (yargs) =>
     yargs
@@ -45,14 +42,16 @@ export const disableCommand: CommandModule = {
       })
       .option('scope', {
         alias: 's',
-        describe: 'The scope to disable the skill in (user or project).',
+        describe: 'The scope to disable the skill in (user or workspace).',
         type: 'string',
-        default: 'project',
-        choices: ['user', 'project'],
+        default: 'workspace',
+        choices: ['user', 'workspace'],
       }),
   handler: async (argv) => {
     const scope =
-      argv['scope'] === 'project' ? SettingScope.Workspace : SettingScope.User;
+      argv['scope'] === 'workspace'
+        ? SettingScope.Workspace
+        : SettingScope.User;
     await handleDisable({
       name: argv['name'] as string,
       scope,

packages/cli/src/commands/skills/enable.test.ts

@@ -64,7 +64,7 @@ describe('skills enable command', () => {
               path: '/user/settings.json',
             };
           }
-          return { settings: {}, path: '/project/settings.json' };
+          return { settings: {}, path: '/workspace/settings.json' };
         }),
         setValue: vi.fn(),
       };
@@ -81,7 +81,7 @@ describe('skills enable command', () => {
       );
       expect(emitConsoleLog).toHaveBeenCalledWith(
         'log',
-        'Skill "skill1" enabled by removing it from the disabled list in user (/user/settings.json) and project (/project/settings.json) settings. Restart required to take effect.',
+        'Skill "skill1" enabled by removing it from the disabled list in user (/user/settings.json) and workspace (/workspace/settings.json) settings.',
       );
     });
 
@@ -122,7 +122,7 @@ describe('skills enable command', () => {
       );
       expect(emitConsoleLog).toHaveBeenCalledWith(
         'log',
-        'Skill "skill1" enabled by removing it from the disabled list in project (/workspace/settings.json) and user (/user/settings.json) settings. Restart required to take effect.',
+        'Skill "skill1" enabled by removing it from the disabled list in workspace (/workspace/settings.json) and user (/user/settings.json) settings.',
       );
     });
 

packages/cli/src/commands/skills/enable.ts

@@ -22,13 +22,10 @@ export async function handleEnable(args: EnableArgs) {
   const settings = loadSettings(workspaceDir);
 
   const result = enableSkill(settings, name);
-  let feedback = renderSkillActionFeedback(
+  const feedback = renderSkillActionFeedback(
     result,
     (label, path) => `${chalk.bold(label)} (${chalk.dim(path)})`,
   );
-  if (result.status === 'success') {
-    feedback += ' Restart required to take effect.';
-  }
   debugLogger.log(feedback);
 }
 

packages/cli/src/commands/skills/install.test.ts

@@ -0,0 +1,143 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, vi, beforeEach } from 'vitest';
+
+const mockInstallSkill = vi.hoisted(() => vi.fn());
+const mockRequestConsentNonInteractive = vi.hoisted(() => vi.fn());
+const mockSkillsConsentString = vi.hoisted(() => vi.fn());
+
+vi.mock('../../utils/skillUtils.js', () => ({
+  installSkill: mockInstallSkill,
+}));
+
+vi.mock('../../config/extensions/consent.js', () => ({
+  requestConsentNonInteractive: mockRequestConsentNonInteractive,
+  skillsConsentString: mockSkillsConsentString,
+}));
+
+vi.mock('@google/gemini-cli-core', () => ({
+  debugLogger: { log: vi.fn(), error: vi.fn() },
+}));
+
+import { debugLogger } from '@google/gemini-cli-core';
+import { handleInstall, installCommand } from './install.js';
+
+describe('skill install command', () => {
+  beforeEach(() => {
+    vi.clearAllMocks();
+    vi.spyOn(process, 'exit').mockImplementation(() => undefined as never);
+    mockSkillsConsentString.mockResolvedValue('Mock Consent String');
+    mockRequestConsentNonInteractive.mockResolvedValue(true);
+  });
+
+  describe('installCommand', () => {
+    it('should have correct command and describe', () => {
+      expect(installCommand.command).toBe(
+        'install <source> [--scope] [--path]',
+      );
+      expect(installCommand.describe).toBe(
+        'Installs an agent skill from a git repository URL or a local path.',
+      );
+    });
+  });
+
+  it('should call installSkill with correct arguments for user scope', async () => {
+    mockInstallSkill.mockImplementation(async (_s, _sc, _p, _ol, rc) => {
+      await rc([]);
+      return [{ name: 'test-skill', location: '/mock/user/skills/test-skill' }];
+    });
+
+    await handleInstall({
+      source: 'https://example.com/repo.git',
+      scope: 'user',
+    });
+
+    expect(mockInstallSkill).toHaveBeenCalledWith(
+      'https://example.com/repo.git',
+      'user',
+      undefined,
+      expect.any(Function),
+      expect.any(Function),
+    );
+    expect(debugLogger.log).toHaveBeenCalledWith(
+      expect.stringContaining('Successfully installed skill: test-skill'),
+    );
+    expect(debugLogger.log).toHaveBeenCalledWith(
+      expect.stringContaining('location: /mock/user/skills/test-skill'),
+    );
+    expect(mockRequestConsentNonInteractive).toHaveBeenCalledWith(
+      'Mock Consent String',
+    );
+  });
+
+  it('should skip prompt and log consent when --consent is provided', async () => {
+    mockInstallSkill.mockImplementation(async (_s, _sc, _p, _ol, rc) => {
+      await rc([]);
+      return [{ name: 'test-skill', location: '/mock/user/skills/test-skill' }];
+    });
+
+    await handleInstall({
+      source: 'https://example.com/repo.git',
+      consent: true,
+    });
+
+    expect(mockRequestConsentNonInteractive).not.toHaveBeenCalled();
+    expect(debugLogger.log).toHaveBeenCalledWith(
+      'You have consented to the following:',
+    );
+    expect(debugLogger.log).toHaveBeenCalledWith('Mock Consent String');
+    expect(mockInstallSkill).toHaveBeenCalled();
+  });
+
+  it('should abort installation if consent is denied', async () => {
+    mockRequestConsentNonInteractive.mockResolvedValue(false);
+    mockInstallSkill.mockImplementation(async (_s, _sc, _p, _ol, rc) => {
+      if (!(await rc([]))) {
+        throw new Error('Skill installation cancelled by user.');
+      }
+      return [];
+    });
+
+    await handleInstall({
+      source: 'https://example.com/repo.git',
+    });
+
+    expect(debugLogger.error).toHaveBeenCalledWith(
+      'Skill installation cancelled by user.',
+    );
+    expect(process.exit).toHaveBeenCalledWith(1);
+  });
+
+  it('should call installSkill with correct arguments for workspace scope and subpath', async () => {
+    mockInstallSkill.mockResolvedValue([
+      { name: 'test-skill', location: '/mock/workspace/skills/test-skill' },
+    ]);
+
+    await handleInstall({
+      source: 'https://example.com/repo.git',
+      scope: 'workspace',
+      path: 'my-skills-dir',
+    });
+
+    expect(mockInstallSkill).toHaveBeenCalledWith(
+      'https://example.com/repo.git',
+      'workspace',
+      'my-skills-dir',
+      expect.any(Function),
+      expect.any(Function),
+    );
+  });
+
+  it('should handle errors gracefully', async () => {
+    mockInstallSkill.mockRejectedValue(new Error('Install failed'));
+
+    await handleInstall({ source: '/local/path' });
+
+    expect(debugLogger.error).toHaveBeenCalledWith('Install failed');
+    expect(process.exit).toHaveBeenCalledWith(1);
+  });
+});

packages/cli/src/commands/skills/install.ts

@@ -0,0 +1,112 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import type { CommandModule } from 'yargs';
+import { debugLogger, type SkillDefinition } from '@google/gemini-cli-core';
+import { getErrorMessage } from '../../utils/errors.js';
+import { exitCli } from '../utils.js';
+import { installSkill } from '../../utils/skillUtils.js';
+import chalk from 'chalk';
+import {
+  requestConsentNonInteractive,
+  skillsConsentString,
+} from '../../config/extensions/consent.js';
+
+interface InstallArgs {
+  source: string;
+  scope?: 'user' | 'workspace';
+  path?: string;
+  consent?: boolean;
+}
+
+export async function handleInstall(args: InstallArgs) {
+  try {
+    const { source, consent } = args;
+    const scope = args.scope ?? 'user';
+    const subpath = args.path;
+
+    const requestConsent = async (
+      skills: SkillDefinition[],
+      targetDir: string,
+    ) => {
+      if (consent) {
+        debugLogger.log('You have consented to the following:');
+        debugLogger.log(await skillsConsentString(skills, source, targetDir));
+        return true;
+      }
+      return requestConsentNonInteractive(
+        await skillsConsentString(skills, source, targetDir),
+      );
+    };
+
+    const installedSkills = await installSkill(
+      source,
+      scope,
+      subpath,
+      (msg) => {
+        debugLogger.log(msg);
+      },
+      requestConsent,
+    );
+
+    for (const skill of installedSkills) {
+      debugLogger.log(
+        chalk.green(
+          `Successfully installed skill: ${chalk.bold(skill.name)} (scope: ${scope}, location: ${skill.location})`,
+        ),
+      );
+    }
+  } catch (error) {
+    debugLogger.error(getErrorMessage(error));
+    await exitCli(1);
+  }
+}
+
+export const installCommand: CommandModule = {
+  command: 'install <source> [--scope] [--path]',
+  describe:
+    'Installs an agent skill from a git repository URL or a local path.',
+  builder: (yargs) =>
+    yargs
+      .positional('source', {
+        describe:
+          'The git repository URL or local path of the skill to install.',
+        type: 'string',
+        demandOption: true,
+      })
+      .option('scope', {
+        describe:
+          'The scope to install the skill into. Defaults to "user" (global).',
+        choices: ['user', 'workspace'],
+        default: 'user',
+      })
+      .option('path', {
+        describe:
+          'Sub-path within the repository to install from (only used for git repository sources).',
+        type: 'string',
+      })
+      .option('consent', {
+        describe:
+          'Acknowledge the security risks of installing a skill and skip the confirmation prompt.',
+        type: 'boolean',
+        default: false,
+      })
+      .check((argv) => {
+        if (!argv.source) {
+          throw new Error('The source argument must be provided.');
+        }
+        return true;
+      }),
+  handler: async (argv) => {
+    await handleInstall({
+      source: argv['source'] as string,
+      scope: argv['scope'] as 'user' | 'workspace',
+      path: argv['path'] as string | undefined,
+      consent: argv['consent'] as boolean | undefined,
+    });
+    await exitCli();
+  },
+};

packages/cli/src/commands/skills/list.test.ts

@@ -65,7 +65,7 @@ describe('skills list command', () => {
       };
       mockLoadCliConfig.mockResolvedValue(mockConfig as unknown as Config);
 
-      await handleList();
+      await handleList({});
 
       expect(emitConsoleLog).toHaveBeenCalledWith(
         'log',
@@ -96,7 +96,7 @@ describe('skills list command', () => {
       };
       mockLoadCliConfig.mockResolvedValue(mockConfig as unknown as Config);
 
-      await handleList();
+      await handleList({});
 
       expect(emitConsoleLog).toHaveBeenCalledWith(
         'log',
@@ -120,10 +120,63 @@ describe('skills list command', () => {
       );
     });
 
+    it('should filter built-in skills by default and show them with { all: true }', async () => {
+      const skills = [
+        {
+          name: 'regular',
+          description: 'desc1',
+          disabled: false,
+          location: '/loc1',
+        },
+        {
+          name: 'builtin',
+          description: 'desc2',
+          disabled: false,
+          location: '/loc2',
+          isBuiltin: true,
+        },
+      ];
+      const mockConfig = {
+        initialize: vi.fn().mockResolvedValue(undefined),
+        getSkillManager: vi.fn().mockReturnValue({
+          getAllSkills: vi.fn().mockReturnValue(skills),
+        }),
+      };
+      mockLoadCliConfig.mockResolvedValue(mockConfig as unknown as Config);
+
+      // Default
+      await handleList({ all: false });
+      expect(emitConsoleLog).toHaveBeenCalledWith(
+        'log',
+        expect.stringContaining('regular'),
+      );
+      expect(emitConsoleLog).not.toHaveBeenCalledWith(
+        'log',
+        expect.stringContaining('builtin'),
+      );
+
+      vi.clearAllMocks();
+
+      // With all: true
+      await handleList({ all: true });
+      expect(emitConsoleLog).toHaveBeenCalledWith(
+        'log',
+        expect.stringContaining('regular'),
+      );
+      expect(emitConsoleLog).toHaveBeenCalledWith(
+        'log',
+        expect.stringContaining('builtin'),
+      );
+      expect(emitConsoleLog).toHaveBeenCalledWith(
+        'log',
+        expect.stringContaining(chalk.gray(' [Built-in]')),
+      );
+    });
+
     it('should throw an error when listing fails', async () => {
       mockLoadCliConfig.mockRejectedValue(new Error('List failed'));
 
-      await expect(handleList()).rejects.toThrow('List failed');
+      await expect(handleList({})).rejects.toThrow('List failed');
     });
   });
 
@@ -131,7 +184,7 @@ describe('skills list command', () => {
     const command = listCommand;
 
     it('should have correct command and describe', () => {
-      expect(command.command).toBe('list');
+      expect(command.command).toBe('list [--all]');
       expect(command.describe).toBe('Lists discovered agent skills.');
     });
   });

packages/cli/src/commands/skills/list.ts

@@ -11,7 +11,7 @@ import { loadCliConfig, type CliArgs } from '../../config/config.js';
 import { exitCli } from '../utils.js';
 import chalk from 'chalk';
 
-export async function handleList() {
+export async function handleList(args: { all?: boolean }) {
   const workspaceDir = process.cwd();
   const settings = loadSettings(workspaceDir);
 
@@ -28,7 +28,17 @@ export async function handleList() {
   await config.initialize();
 
   const skillManager = config.getSkillManager();
-  const skills = skillManager.getAllSkills();
+  const skills = args.all
+    ? skillManager.getAllSkills()
+    : skillManager.getAllSkills().filter((s) => !s.isBuiltin);
+
+  // Sort skills: non-built-in first, then alphabetically by name
+  skills.sort((a, b) => {
+    if (a.isBuiltin === b.isBuiltin) {
+      return a.name.localeCompare(b.name);
+    }
+    return a.isBuiltin ? 1 : -1;
+  });
 
   if (skills.length === 0) {
     debugLogger.log('No skills discovered.');
@@ -43,7 +53,9 @@ export async function handleList() {
       ? chalk.red('[Disabled]')
       : chalk.green('[Enabled]');
 
-    debugLogger.log(`${chalk.bold(skill.name)} ${status}`);
+    const builtinSuffix = skill.isBuiltin ? chalk.gray(' [Built-in]') : '';
+
+    debugLogger.log(`${chalk.bold(skill.name)} ${status}${builtinSuffix}`);
     debugLogger.log(`  Description: ${skill.description}`);
     debugLogger.log(`  Location:    ${skill.location}`);
     debugLogger.log('');
@@ -51,11 +63,16 @@ export async function handleList() {
 }
 
 export const listCommand: CommandModule = {
-  command: 'list',
+  command: 'list [--all]',
   describe: 'Lists discovered agent skills.',
-  builder: (yargs) => yargs,
-  handler: async () => {
-    await handleList();
+  builder: (yargs) =>
+    yargs.option('all', {
+      type: 'boolean',
+      description: 'Show all skills, including built-in ones.',
+      default: false,
+    }),
+  handler: async (argv) => {
+    await handleList({ all: argv['all'] as boolean });
     await exitCli();
   },
 };

packages/cli/src/commands/skills/uninstall.test.ts

@@ -0,0 +1,87 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { describe, it, expect, vi, beforeEach } from 'vitest';
+
+const mockUninstallSkill = vi.hoisted(() => vi.fn());
+
+vi.mock('../../utils/skillUtils.js', () => ({
+  uninstallSkill: mockUninstallSkill,
+}));
+
+vi.mock('@google/gemini-cli-core', () => ({
+  debugLogger: { log: vi.fn(), error: vi.fn() },
+}));
+
+import { debugLogger } from '@google/gemini-cli-core';
+import { handleUninstall, uninstallCommand } from './uninstall.js';
+
+describe('skill uninstall command', () => {
+  beforeEach(() => {
+    vi.clearAllMocks();
+    vi.spyOn(process, 'exit').mockImplementation(() => undefined as never);
+  });
+
+  describe('uninstallCommand', () => {
+    it('should have correct command and describe', () => {
+      expect(uninstallCommand.command).toBe('uninstall <name> [--scope]');
+      expect(uninstallCommand.describe).toBe(
+        'Uninstalls an agent skill by name.',
+      );
+    });
+  });
+
+  it('should call uninstallSkill with correct arguments for user scope', async () => {
+    mockUninstallSkill.mockResolvedValue({
+      location: '/mock/user/skills/test-skill',
+    });
+
+    await handleUninstall({
+      name: 'test-skill',
+      scope: 'user',
+    });
+
+    expect(mockUninstallSkill).toHaveBeenCalledWith('test-skill', 'user');
+    expect(debugLogger.log).toHaveBeenCalledWith(
+      expect.stringContaining('Successfully uninstalled skill: test-skill'),
+    );
+    expect(debugLogger.log).toHaveBeenCalledWith(
+      expect.stringContaining('location: /mock/user/skills/test-skill'),
+    );
+  });
+
+  it('should call uninstallSkill with correct arguments for workspace scope', async () => {
+    mockUninstallSkill.mockResolvedValue({
+      location: '/mock/workspace/skills/test-skill',
+    });
+
+    await handleUninstall({
+      name: 'test-skill',
+      scope: 'workspace',
+    });
+
+    expect(mockUninstallSkill).toHaveBeenCalledWith('test-skill', 'workspace');
+  });
+
+  it('should log an error if skill is not found', async () => {
+    mockUninstallSkill.mockResolvedValue(null);
+
+    await handleUninstall({ name: 'test-skill' });
+
+    expect(debugLogger.error).toHaveBeenCalledWith(
+      'Skill "test-skill" is not installed in the user scope.',
+    );
+  });
+
+  it('should handle errors gracefully', async () => {
+    mockUninstallSkill.mockRejectedValue(new Error('Uninstall failed'));
+
+    await handleUninstall({ name: 'test-skill' });
+
+    expect(debugLogger.error).toHaveBeenCalledWith('Uninstall failed');
+    expect(process.exit).toHaveBeenCalledWith(1);
+  });
+});

packages/cli/src/commands/skills/uninstall.ts

@@ -0,0 +1,72 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import type { CommandModule } from 'yargs';
+import { debugLogger } from '@google/gemini-cli-core';
+import { getErrorMessage } from '../../utils/errors.js';
+import { exitCli } from '../utils.js';
+import { uninstallSkill } from '../../utils/skillUtils.js';
+import chalk from 'chalk';
+
+interface UninstallArgs {
+  name: string;
+  scope?: 'user' | 'workspace';
+}
+
+export async function handleUninstall(args: UninstallArgs) {
+  try {
+    const { name } = args;
+    const scope = args.scope ?? 'user';
+
+    const result = await uninstallSkill(name, scope);
+
+    if (result) {
+      debugLogger.log(
+        chalk.green(
+          `Successfully uninstalled skill: ${chalk.bold(name)} (scope: ${scope}, location: ${result.location})`,
+        ),
+      );
+    } else {
+      debugLogger.error(
+        `Skill "${name}" is not installed in the ${scope} scope.`,
+      );
+    }
+  } catch (error) {
+    debugLogger.error(getErrorMessage(error));
+    await exitCli(1);
+  }
+}
+
+export const uninstallCommand: CommandModule = {
+  command: 'uninstall <name> [--scope]',
+  describe: 'Uninstalls an agent skill by name.',
+  builder: (yargs) =>
+    yargs
+      .positional('name', {
+        describe: 'The name of the skill to uninstall.',
+        type: 'string',
+        demandOption: true,
+      })
+      .option('scope', {
+        describe:
+          'The scope to uninstall the skill from. Defaults to "user" (global).',
+        choices: ['user', 'workspace'],
+        default: 'user',
+      })
+      .check((argv) => {
+        if (!argv.name) {
+          throw new Error('The skill name must be provided.');
+        }
+        return true;
+      }),
+  handler: async (argv) => {
+    await handleUninstall({
+      name: argv['name'] as string,
+      scope: argv['scope'] as 'user' | 'workspace',
+    });
+    await exitCli();
+  },
+};