fix(shell): address rcFile security issues

- Only source rcFile if the workspace is a trusted folder

- Properly escape the rcFile path to prevent command injection

.gcp/Dockerfile.development

@@ -0,0 +1,89 @@
+# --- STAGE 1: Base Runtime ---
+FROM docker.io/library/node:20-slim AS base
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  python3 \
+  python3-pip \
+  python3-venv \
+  curl \
+  dnsutils \
+  less \
+  jq \
+  ca-certificates \
+  git \
+  && apt-get clean \
+  && rm -rf /var/lib/apt/lists/*
+
+# --- STAGE 2: Builder (Compile Main) ---
+FROM base AS builder
+WORKDIR /build
+COPY . .
+RUN npm ci --ignore-scripts
+RUN npm run bundle
+# Run the official release preparation script to move the bundle and assets into packages/cli
+RUN node scripts/prepare-npm-release.js
+
+# --- STAGE 3: Development Environment ---
+FROM base AS development
+
+WORKDIR /home/node/dev/main
+
+# Set up npm global package folder
+RUN mkdir -p /usr/local/share/npm-global \
+  && chown -R node:node /usr/local/share/npm-global
+ENV NPM_CONFIG_PREFIX=/usr/local/share/npm-global
+ENV PATH=$PATH:/usr/local/share/npm-global/bin
+
+# Copy package.json to extract versions for global tools
+COPY package.json /tmp/package.json
+
+# Install Build Tools, Global Dev Tools (pinned), and Linters
+ARG ACTIONLINT_VER=1.7.7
+ARG SHELLCHECK_VER=0.11.0
+ARG YAMLLINT_VER=1.35.1
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  make \
+  g++ \
+  gh \
+  git \
+  unzip \
+  rsync \
+  ripgrep \
+  procps \
+  psmisc \
+  lsof \
+  socat \
+  tmux \
+  docker.io \
+  build-essential \
+  libsecret-1-dev \
+  libkrb5-dev \
+  file \
+  && curl -sSLo /tmp/actionlint.tar.gz https://github.com/rhysd/actionlint/releases/download/v${ACTIONLINT_VER}/actionlint_${ACTIONLINT_VER}_linux_amd64.tar.gz \
+  && tar -xzf /tmp/actionlint.tar.gz -C /usr/local/bin actionlint \
+  && curl -sSLo /tmp/shellcheck.tar.xz https://github.com/koalaman/shellcheck/releases/download/v${SHELLCHECK_VER}/shellcheck-v${SHELLCHECK_VER}.linux.x86_64.tar.xz \
+  && tar -xf /tmp/shellcheck.tar.xz -C /usr/local/bin --strip-components=1 shellcheck-v${SHELLCHECK_VER}/shellcheck \
+  && pip3 install --break-system-packages yamllint==${YAMLLINT_VER} \
+  && export TSX_VER=$(node -p "require('/tmp/package.json').devDependencies.tsx") \
+  && export VITEST_VER=$(node -p "require('/tmp/package.json').devDependencies.vitest") \
+  && export PRETTIER_VER=$(node -p "require('/tmp/package.json').devDependencies.prettier") \
+  && export ESLINT_VER=$(node -p "require('/tmp/package.json').devDependencies.eslint") \
+  && export CROSS_ENV_VER=$(node -p "require('/tmp/package.json').devDependencies['cross-env']") \
+  && npm install -g tsx@$TSX_VER vitest@$VITEST_VER prettier@$PRETTIER_VER eslint@$ESLINT_VER cross-env@$CROSS_ENV_VER typescript@5.3.3 \
+  && npm install -g @google/gemini-cli@nightly && mv /usr/local/share/npm-global/bin/gemini /usr/local/share/npm-global/bin/g-nightly \
+  && npm install -g @google/gemini-cli@preview && mv /usr/local/share/npm-global/bin/gemini /usr/local/share/npm-global/bin/g-preview \
+  && npm install -g @google/gemini-cli@latest  && mv /usr/local/share/npm-global/bin/gemini /usr/local/share/npm-global/bin/g-stable \
+  && apt-get purge -y build-essential libsecret-1-dev libkrb5-dev \
+  && apt-get autoremove -y \
+  && apt-get clean \
+  && rm -rf /var/lib/apt/lists/* /tmp/* /root/.npm
+
+# Copy the bundled CLI package to a permanent location and install it
+# We MUST not delete this source folder as 'npm install -g <folder>' 
+# often symlinks to it for local folder installs.
+COPY --from=builder /build/packages/cli /usr/local/lib/gemini-cli
+RUN npm install -g /usr/local/lib/gemini-cli
+
+USER node
+CMD ["/bin/bash"]

.gcp/Dockerfile.development.dockerignore

@@ -0,0 +1,10 @@
+node_modules
+.git
+.gemini/workspaces
+dist
+!packages/*/dist/*.tgz
+bundle
+out
+*.log
+.env
+.DS_Store

.gcp/development-worker.yml

@@ -0,0 +1,58 @@
+substitutions:
+  _IMAGE_NAME: 'development'
+  _ARTIFACT_REGISTRY_REPO: 'us-docker.pkg.dev/gemini-code-dev/gemini-cli'
+
+steps:
+  # Step 1: Install root dependencies
+  - name: 'us-west1-docker.pkg.dev/gemini-code-dev/gemini-code-containers/gemini-code-builder'
+    id: 'Install Dependencies'
+    entrypoint: 'npm'
+    args: ['install']
+
+  # Step 2: Authenticate for Docker
+  - name: 'us-west1-docker.pkg.dev/gemini-code-dev/gemini-code-containers/gemini-code-builder'
+    id: 'Authenticate docker'
+    entrypoint: 'npm'
+    args: ['run', 'auth']
+
+  # Step 3: Build workspace packages
+  - name: 'us-west1-docker.pkg.dev/gemini-code-dev/gemini-code-containers/gemini-code-builder'
+    id: 'Build packages'
+    entrypoint: 'npm'
+    args: ['run', 'build:packages']
+
+  # Step 4: Build Development Image
+  - name: 'us-west1-docker.pkg.dev/gemini-code-dev/gemini-code-containers/gemini-code-builder'
+    id: 'Build Development Image'
+    entrypoint: 'bash'
+    env:
+      - 'RAW_BRANCH_VALUE=${BRANCH_NAME}'
+    args:
+      - '-c'
+      - |-
+        IMAGE_BASE="${_ARTIFACT_REGISTRY_REPO}/${_IMAGE_NAME}"
+
+        # Determine the primary tag (branch name or 'latest' for main)
+        # Use $$ for shell variables to avoid Cloud Build attempting premature substitution
+        RAW_BRANCH="$$RAW_BRANCH_VALUE"
+        if [ "$${RAW_BRANCH}" == "main" ]; then
+          TAG_PRIMARY="latest"
+        else
+          TAG_PRIMARY=$$(echo "$${RAW_BRANCH}" | sed 's/[^a-zA-Z0-9]/-/g' | tr '[:upper:]' '[:lower:]')
+        fi
+
+        # Use SHORT_SHA if available (Cloud Build) or fallback to latest-dev
+        TAG_SHA="$${SHORT_SHA:-latest-dev}"
+
+        echo "📦 Building Development Image for: $${RAW_BRANCH} -> $${TAG_PRIMARY} ($${TAG_SHA})"
+
+        docker build -f .gcp/Dockerfile.development \
+          -t "$${IMAGE_BASE}:$${TAG_SHA}" \
+          -t "$${IMAGE_BASE}:$${TAG_PRIMARY}" .
+
+        docker push "$${IMAGE_BASE}:$${TAG_SHA}"
+        docker push "$${IMAGE_BASE}:$${TAG_PRIMARY}"
+
+options:
+  defaultLogsBucketBehavior: 'REGIONAL_USER_OWNED_BUCKET'
+  dynamicSubstitutions: true

.gemini/commands/fix-behavioral-eval.toml

@@ -1,60 +0,0 @@
-description = "Check status of nightly evals, fix failures for key models, and re-run."
-prompt = """
-You are an expert at fixing behavioral evaluations.
-
-1. **Investigate**:
-   - Use 'gh' cli to fetch the results from the latest run from the main branch: https://github.com/google-gemini/gemini-cli/actions/workflows/evals-nightly.yml.
-   - DO NOT push any changes or start any runs. The rest of your evaluation will be local.
-   - Evals are in evals/ directory and are documented by evals/README.md.
-   - The test case trajectory logs will be logged to evals/logs.
-   - You should also enable and review the verbose agent logs by setting the GEMINI_DEBUG_LOG_FILE environment variable.
-   - Identify the relevant test. Confine your investigation and validation to just this test.
-   - Proactively add logging that will aid in gathering information or validating your hypotheses.
-
-2. **Fix**:
-   - If a relevant test is failing, locate the test file and the corresponding prompt/code.
-   - It's often helpful to make an extreme, brute force change to see if you are changing the right place to make an improvement and then scope it back iteratively.
-   - Your **final** change should be **minimal and targeted**.
-   - Keep in mind the following:
-     - The prompt has multiple configurations and pieces. Take care that your changes
-       end up in the final prompt for the selected model and configuration.
-     - The prompt chosen for the eval is intentional. It's often vague or indirect
-       to see how the agent performs with ambiguous instructions. Changing it should
-       be a last resort.
-     - When changing the test prompt, carefully consider whether the prompt still tests
-       the same scenario. We don't want to lose test fidelity by making the prompts too
-       direct (i.e.: easy).
-     - Your primary mechanism for improving the agent's behavior is to make changes to
-       tool instructions, system prompt (snippets.ts), and/or modules that contribute to the prompt.
-     - If prompt and description changes are unsuccessful, use logs and debugging to
-       confirm that everything is working as expected.
-    - If unable to fix the test, you can make recommendations for architecture changes
-      that might help stablize the test. Be sure to THINK DEEPLY if offering architecture guidance.
-      Some facts that might help with this are:
-      - Agents may be composed of one or more agent loops.
-      - AgentLoop == 'context + toolset + prompt'. Subagents are one type of agent loop.
-      - Agent loops perform better when:
-        - They have direct, unambiguous, and non-contradictory prompts.
-        - They have fewer irrelevant tools.
-        - They have fewer goals or steps to perform.
-        - They have less low value or irrelevant context.
-      - You may suggest compositions of existing primitives, like subagents, or
-        propose a new one.
-      - These recommendations should be high confidence and should be grounded
-        in observed deficient behaviors rather than just parroting the facts above.
-        Investigate as needed to ground your recommendations.
-
-3. **Verify**:
-   - Run just that one test if needed to validate that it is fixed. Be sure to run vitest in non-interactive mode.
-   - Running the tests can take a long time, so consider whether you can diagnose via other means or log diagnostics before committing the time. You must minimize the number of test runs needed to diagnose the failure.
-   - After the test completes, check whether it seems to have improved.
-   - You will need to run the test 3 times for Gemini 3.0, Gemini 3 flash, and Gemini 2.5 pro to ensure that it is truly stable. Run these runs in parallel, using scripts if needed.
-   - Some flakiness is expected; if it looks like a transient issue or the test is inherently unstable but passes 2/3 times, you might decide it cannot be improved.
-
-4. **Report**:
-   - Provide a summary of the test success rate for each of the tested models.
-   - Success rate is calculated based on 3 runs per model (e.g., 3/3 = 100%).
-   - If you couldn't fix it due to persistent flakiness, explain why.
-
-{{args}}
-"""

.gemini/commands/promote-behavioral-eval.toml

@@ -1,29 +0,0 @@
-description = "Promote behavioral evals that have a 100% success rate over the last 7 nightly runs."
-prompt = """
-You are an expert at analyzing and promoting behavioral evaluations.
-
-1. **Investigate**:
-   - Use 'gh' cli to fetch the results from the most recent run from the main branch: https://github.com/google-gemini/gemini-cli/actions/workflows/evals-nightly.yml.
-   - DO NOT push any changes or start any runs. The rest of your evaluation will be local.
-   - Evals are in evals/ directory and are documented by evals/README.md.
-   - Identify tests that have passed 100% of the time for ALL enabled models across the past 7 runs in a row.
-   - NOTE: the results summary from the most recent run contains the last 7 runs test results. 100% means the test passed 3/3 times for that model and run.
-   - If a test meets this criteria, it is a candidate for promotion.
-
-2. **Promote**:
-   - For each candidate test, locate the test file in the evals/ directory.
-   - Promote the test according to the project's standard promotion process (e.g., moving it to a stable suite, updating its tags, or removing skip/flaky annotations). 
-   - Ensure you follow any guidelines in evals/README.md for stable tests.
-   - Your **final** change should be **minimal and targeted** to just promoting the test status.
-
-3. **Verify**:
-   - Run the promoted tests locally to validate that they still execute correctly. Be sure to run vitest in non-interactive mode.
-   - Check that the test is now part of the expected standard or stable test suites.
-
-4. **Report**:
-   - Provide a summary of the tests that were promoted.
-   - Include the success rate evidence (7/7 runs passed for all models) for each promoted test.
-   - If no tests met the criteria for promotion, clearly state that and summarize the closest candidates.
-
-{{args}}
-"""

.gemini/commands/strict-development-rules.md

@@ -107,7 +107,7 @@ Gemini CLI project.
   set.
 - **Logging**: Use `debugLogger` for rethrown errors to avoid duplicate logging.
 - **Keyboard Shortcuts**: Define all new keyboard shortcuts in
-  `packages/cli/src/config/keyBindings.ts` and document them in
+  `packages/cli/src/ui/key/keyBindings.ts` and document them in
   `docs/cli/keyboard-shortcuts.md`. Be careful of keybindings that require the
   `Meta` key, as only certain meta key shortcuts are supported on Mac. Avoid
   function keys and shortcuts commonly bound in VSCode.

.gemini/settings.json

@@ -1,8 +1,8 @@
 {
   "experimental": {
-    "plan": true,
     "extensionReloading": true,
-    "modelSteering": true
+    "modelSteering": true,
+    "memoryManager": true
   },
   "general": {
     "devtools": true

.gemini/skills/async-pr-review/SKILL.md

@@ -0,0 +1,45 @@
+---
+name: async-pr-review
+description: Trigger this skill when the user wants to start an asynchronous PR review, run background checks on a PR, or check the status of a previously started async PR review.
+---
+
+# Async PR Review
+
+This skill provides a set of tools to asynchronously review a Pull Request. It will create a background job to run the project's preflight checks, execute Gemini-powered test plans, and perform a comprehensive code review using custom prompts.
+
+This skill is designed to showcase an advanced "Agentic Asynchronous Pattern":
+1.  **Native Background Shells vs Headless Inference**: While Gemini CLI can natively spawn and detach background shell commands (using the `run_shell_command` tool with `is_background: true`), a standard bash background job cannot perform LLM inference. To conduct AI-driven code reviews and test generation in the background, the shell script *must* invoke the `gemini` executable headlessly using `-p`. This offloads the AI tasks to independent worker agents.
+2.  **Dynamic Git Scoping**: The review scripts avoid hardcoded paths. They use `git rev-parse --show-toplevel` to automatically resolve the root of the user's current project.
+3.  **Ephemeral Worktrees**: Instead of checking out branches in the user's main workspace, the skill provisions temporary git worktrees in `.gemini/tmp/async-reviews/pr-<number>`. This prevents git lock conflicts and namespace pollution.
+4.  **Agentic Evaluation (`check-async-review.sh`)**: The check script outputs clean JSON/text statuses for the main agent to parse. The interactive agent itself synthesizes the final assessment dynamically from the generated log files.
+
+## Workflow
+
+1.  **Determine Action**: Establish whether the user wants to start a new async review or check the status of an existing one.
+    *   If the user says "start an async review for PR #123" or similar, proceed to **Start Review**.
+    *   If the user says "check the status of my async review for PR #123" or similar, proceed to **Check Status**.
+
+### Start Review
+
+If the user wants to start a new async PR review:
+
+1.  Ask the user for the PR number if they haven't provided it.
+2.  Execute the `async-review.sh` script, passing the PR number as the first argument. Be sure to run it with the `is_background` flag set to true to ensure it immediately detaches.
+    ```bash
+    .gemini/skills/async-pr-review/scripts/async-review.sh <PR_NUMBER>
+    ```
+3.  Inform the user that the tasks have started successfully and they can check the status later.
+
+### Check Status
+
+If the user wants to check the status or view the final assessment of a previously started async review:
+
+1.  Ask the user for the PR number if they haven't provided it.
+2.  Execute the `check-async-review.sh` script, passing the PR number as the first argument:
+    ```bash
+    .gemini/skills/async-pr-review/scripts/check-async-review.sh <PR_NUMBER>
+    ```
+3.  **Evaluate Output**: Read the output from the script.
+    *   If the output contains `STATUS: IN_PROGRESS`, tell the user which tasks are still running.
+    *   If the output contains `STATUS: COMPLETE`, use your file reading tools (`read_file`) to retrieve the contents of `final-assessment.md`, `review.md`, `pr-diff.diff`, `npm-test.log`, and `test-execution.log` files from the `LOG_DIR` specified in the output.
+    *   **Final Assessment**: Read those files, synthesize their results, and give the user a concise recommendation on whether the PR builds successfully, passes tests, and if you recommend they approve it based on the review.

.gemini/skills/async-pr-review/policy.toml

@@ -0,0 +1,148 @@
+# --- CORE TOOLS ---
+[[rule]]
+toolName = "read_file"
+decision = "allow"
+priority = 100
+
+[[rule]]
+toolName = "write_file"
+decision = "allow"
+priority = 100
+
+[[rule]]
+toolName = "grep_search"
+decision = "allow"
+priority = 100
+
+[[rule]]
+toolName = "glob"
+decision = "allow"
+priority = 100
+
+[[rule]]
+toolName = "list_directory"
+decision = "allow"
+priority = 100
+
+[[rule]]
+toolName = "codebase_investigator"
+decision = "allow"
+priority = 100
+
+# --- SHELL COMMANDS ---
+
+# Git (Safe/Read-only)
+[[rule]]
+toolName = "run_shell_command"
+commandPrefix = [
+  "git blame",
+  "git show",
+  "git grep",
+  "git show-ref",
+  "git ls-tree",
+  "git ls-remote",
+  "git reflog",
+  "git remote -v",
+  "git diff",
+  "git rev-list",
+  "git rev-parse",
+  "git merge-base",
+  "git cherry",
+  "git fetch",
+  "git status",
+  "git st",
+  "git branch",
+  "git br",
+  "git log",
+  "git --version"
+]
+decision = "allow"
+priority = 100
+
+# GitHub CLI (Read-only)
+[[rule]]
+toolName = "run_shell_command"
+commandPrefix = [
+  "gh workflow list",
+  "gh auth status",
+  "gh checkout view",
+  "gh run view",
+  "gh run job view",
+  "gh run list",
+  "gh run --help",
+  "gh issue view",
+  "gh issue list",
+  "gh label list",
+  "gh pr diff",
+  "gh pr check",
+  "gh pr checks",
+  "gh pr view",
+  "gh pr list",
+  "gh pr status",
+  "gh repo view",
+  "gh job view",
+  "gh api",
+  "gh log"
+]
+decision = "allow"
+priority = 100
+
+# Node.js/NPM (Generic Tests, Checks, and Build)
+[[rule]]
+toolName = "run_shell_command"
+commandPrefix = [
+  "npm run start",
+  "npm install",
+  "npm run",
+  "npm test",
+  "npm ci",
+  "npm list",
+  "npm --version"
+]
+decision = "allow"
+priority = 100
+
+# Core Utilities (Safe)
+[[rule]]
+toolName = "run_shell_command"
+commandPrefix = [
+  "sleep",
+  "env",
+  "break",
+  "xargs",
+  "base64",
+  "uniq",
+  "sort",
+  "echo",
+  "which",
+  "ls",
+  "find",
+  "tail",
+  "head",
+  "cat",
+  "cd",
+  "grep",
+  "ps",
+  "pwd",
+  "wc",
+  "file",
+  "stat",
+  "diff",
+  "lsof",
+  "date",
+  "whoami",
+  "uname",
+  "du",
+  "cut",
+  "true",
+  "false",
+  "readlink",
+  "awk",
+  "jq",
+  "rg",
+  "less",
+  "more",
+  "tree"
+]
+decision = "allow"
+priority = 100

.gemini/skills/async-pr-review/scripts/async-review.sh

@@ -0,0 +1,245 @@
+#!/bin/bash
+
+notify() {
+  local title="${1}"
+  local message="${2}"
+  local pr="${3}"
+  # Terminal escape sequence
+  printf "\e]9;%s | PR #%s | %s\a" "${title}" "${pr}" "${message}"
+  # Native macOS notification
+  os_type="$(uname || true)"
+  if [[ "${os_type}" == "Darwin" ]]; then
+    osascript -e "display notification \"${message}\" with title \"${title}\" subtitle \"PR #${pr}\""
+  fi
+}
+
+pr_number="${1}"
+if [[ -z "${pr_number}" ]]; then
+  echo "Usage: async-review <pr_number>"
+  exit 1
+fi
+
+base_dir="$(git rev-parse --show-toplevel 2>/dev/null || true)"
+if [[ -z "${base_dir}" ]]; then
+  echo "❌ Must be run from within a git repository."
+  exit 1
+fi
+
+# Use the repository's local .gemini/tmp directory for ephemeral worktrees and logs
+pr_dir="${base_dir}/.gemini/tmp/async-reviews/pr-${pr_number}"
+target_dir="${pr_dir}/worktree"
+log_dir="${pr_dir}/logs"
+
+cd "${base_dir}" || exit 1
+
+mkdir -p "${log_dir}"
+rm -f "${log_dir}/setup.exit" "${log_dir}/final-assessment.exit" "${log_dir}/final-assessment.md"
+
+echo "🧹 Cleaning up previous worktree if it exists..." | tee -a "${log_dir}/setup.log"
+git worktree remove -f "${target_dir}" >> "${log_dir}/setup.log" 2>&1 || true
+git branch -D "gemini-async-pr-${pr_number}" >> "${log_dir}/setup.log" 2>&1 || true
+git worktree prune >> "${log_dir}/setup.log" 2>&1 || true
+
+echo "📡 Fetching PR #${pr_number}..." | tee -a "${log_dir}/setup.log"
+if ! git fetch origin -f "pull/${pr_number}/head:gemini-async-pr-${pr_number}" >> "${log_dir}/setup.log" 2>&1; then
+  echo 1 > "${log_dir}/setup.exit"
+  echo "❌ Fetch failed. Check ${log_dir}/setup.log"
+  notify "Async Review Failed" "Fetch failed." "${pr_number}"
+  exit 1
+fi
+
+if [[ ! -d "${target_dir}" ]]; then
+  echo "🧹 Pruning missing worktrees..." | tee -a "${log_dir}/setup.log"
+  git worktree prune >> "${log_dir}/setup.log" 2>&1
+  echo "🌿 Creating worktree in ${target_dir}..." | tee -a "${log_dir}/setup.log"
+  if ! git worktree add "${target_dir}" "gemini-async-pr-${pr_number}" >> "${log_dir}/setup.log" 2>&1; then
+    echo 1 > "${log_dir}/setup.exit"
+    echo "❌ Worktree creation failed. Check ${log_dir}/setup.log"
+    notify "Async Review Failed" "Worktree creation failed." "${pr_number}"
+    exit 1
+  fi
+else
+  echo "🌿 Worktree already exists." | tee -a "${log_dir}/setup.log"
+fi
+echo 0 > "${log_dir}/setup.exit"
+
+cd "${target_dir}" || exit 1
+
+echo "🚀 Launching background tasks. Logs saving to: ${log_dir}"
+
+echo "  ↳ [1/5] Grabbing PR diff..."
+rm -f "${log_dir}/pr-diff.exit"
+{ gh pr diff "${pr_number}" > "${log_dir}/pr-diff.diff" 2>&1; echo $? > "${log_dir}/pr-diff.exit"; } &
+
+echo "  ↳ [2/5] Starting build and lint..."
+rm -f "${log_dir}/build-and-lint.exit"
+{ { npm run clean && npm ci && npm run format && npm run build && npm run lint:ci && npm run typecheck; } > "${log_dir}/build-and-lint.log" 2>&1; echo $? > "${log_dir}/build-and-lint.exit"; } &
+
+# Dynamically resolve gemini binary (fallback to your nightly path)
+GEMINI_CMD="$(command -v gemini || echo "${HOME}/.gcli/nightly/node_modules/.bin/gemini")"
+# shellcheck disable=SC2312
+POLICY_PATH="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)/policy.toml"
+
+echo "  ↳ [3/5] Starting Gemini code review..."
+rm -f "${log_dir}/review.exit"
+{ "${GEMINI_CMD}" --policy "${POLICY_PATH}" -p "/review-frontend ${pr_number}" > "${log_dir}/review.md" 2>&1; echo $? > "${log_dir}/review.exit"; } &
+
+echo "  ↳ [4/5] Starting automated tests (waiting for build and lint)..."
+rm -f "${log_dir}/npm-test.exit"
+{ 
+  while [[ ! -f "${log_dir}/build-and-lint.exit" ]]; do sleep 1; done
+  read -r build_exit < "${log_dir}/build-and-lint.exit" || build_exit=""
+  if [[ "${build_exit}" == "0" ]]; then
+    gh pr checks "${pr_number}" > "${log_dir}/ci-checks.log" 2>&1
+    ci_status=$?
+    
+    if [[ "${ci_status}" -eq 0 ]]; then
+      echo "CI checks passed. Skipping local npm tests." > "${log_dir}/npm-test.log"
+      echo 0 > "${log_dir}/npm-test.exit"
+    elif [[ "${ci_status}" -eq 8 ]]; then
+      echo "CI checks are still pending. Skipping local npm tests to avoid duplicate work. Please check GitHub for final results." > "${log_dir}/npm-test.log"
+      echo 0 > "${log_dir}/npm-test.exit"
+    else
+      echo "CI checks failed. Failing checks:" > "${log_dir}/npm-test.log"
+      gh pr checks "${pr_number}" --json name,bucket -q '.[] | select(.bucket=="fail") | .name' >> "${log_dir}/npm-test.log" 2>&1
+      
+      echo "Attempting to extract failing test files from CI logs..." >> "${log_dir}/npm-test.log"
+      pr_branch="$(gh pr view "${pr_number}" --json headRefName -q '.headRefName' 2>/dev/null || true)"
+      run_id="$(gh run list --branch "${pr_branch}" --workflow ci.yml --json databaseId -q '.[0].databaseId' 2>/dev/null || true)"
+      
+      failed_files=""
+      if [[ -n "${run_id}" ]]; then
+        failed_files="$(gh run view "${run_id}" --log-failed 2>/dev/null | grep -o -E '(packages/[a-zA-Z0-9_-]+|integration-tests|evals)/[a-zA-Z0-9_/-]+\.test\.ts(x)?' | sort | uniq || true)"
+      fi
+      
+      if [[ -n "${failed_files}" ]]; then
+        echo "Found failing test files from CI:" >> "${log_dir}/npm-test.log"
+        for f in ${failed_files}; do echo "  - ${f}" >> "${log_dir}/npm-test.log"; done
+        echo "Running ONLY failing tests locally..." >> "${log_dir}/npm-test.log"
+        
+        exit_code=0
+        for file in ${failed_files}; do
+           if [[ "${file}" == packages/* ]]; then
+             ws_dir="$(echo "${file}" | cut -d'/' -f1,2)"
+           else
+             ws_dir="$(echo "${file}" | cut -d'/' -f1)"
+           fi
+           rel_file="${file#"${ws_dir}"/}"
+           
+           echo "--- Running ${rel_file} in workspace ${ws_dir} ---" >> "${log_dir}/npm-test.log"
+           if ! npm run test:ci -w "${ws_dir}" -- "${rel_file}" >> "${log_dir}/npm-test.log" 2>&1; then
+             exit_code=1
+           fi
+        done
+        echo "${exit_code}" > "${log_dir}/npm-test.exit"
+      else
+        echo "Could not extract specific failing files. Skipping full local test suite as it takes too long. Please check CI logs manually." >> "${log_dir}/npm-test.log"
+        echo 1 > "${log_dir}/npm-test.exit"
+      fi
+    fi
+  else
+    echo "Skipped due to build-and-lint failure" > "${log_dir}/npm-test.log"
+    echo 1 > "${log_dir}/npm-test.exit"
+  fi
+} &
+
+echo "  ↳ [5/5] Starting Gemini test execution (waiting for build and lint)..."
+rm -f "${log_dir}/test-execution.exit"
+{ 
+  while [[ ! -f "${log_dir}/build-and-lint.exit" ]]; do sleep 1; done
+  read -r build_exit < "${log_dir}/build-and-lint.exit" || build_exit=""
+  if [[ "${build_exit}" == "0" ]]; then
+    "${GEMINI_CMD}" --policy "${POLICY_PATH}" -p "Analyze the diff for PR ${pr_number} using 'gh pr diff ${pr_number}'. Instead of running the project's automated test suite (like 'npm test'), physically exercise the newly changed code in the terminal (e.g., by writing a temporary script to call the new functions, or testing the CLI command directly). Verify the feature's behavior works as expected. IMPORTANT: Do NOT modify any source code to fix errors. Just exercise the code and log the results, reporting any failures clearly. Do not ask for user confirmation." > "${log_dir}/test-execution.log" 2>&1; echo $? > "${log_dir}/test-execution.exit"
+  else
+    echo "Skipped due to build-and-lint failure" > "${log_dir}/test-execution.log"
+    echo 1 > "${log_dir}/test-execution.exit"
+  fi
+} &
+
+echo "✅ All tasks dispatched!"
+echo "You can monitor progress with: tail -f ${log_dir}/*.log"
+echo "Read your review later at: ${log_dir}/review.md"
+
+# Polling loop to wait for all background tasks to finish
+tasks=("pr-diff" "build-and-lint" "review" "npm-test" "test-execution")
+log_files=("pr-diff.diff" "build-and-lint.log" "review.md" "npm-test.log" "test-execution.log")
+
+declare -A task_done
+for t in "${tasks[@]}"; do task_done[${t}]=0; done
+
+all_done=0
+while [[ "${all_done}" -eq 0 ]]; do
+  clear
+  echo "=================================================="
+  echo "🚀 Async PR Review Status for PR #${pr_number}"
+  echo "=================================================="
+  echo ""
+  
+  all_done=1
+  for i in "${!tasks[@]}"; do
+    t="${tasks[${i}]}"
+    
+    if [[ -f "${log_dir}/${t}.exit" ]]; then
+      read -r task_exit < "${log_dir}/${t}.exit" || task_exit=""
+      if [[ "${task_exit}" == "0" ]]; then
+        echo "  ✅ ${t}: SUCCESS"
+      else
+        echo "  ❌ ${t}: FAILED (exit code ${task_exit})"
+      fi
+      task_done[${t}]=1
+    else
+      echo "  ⏳ ${t}: RUNNING"
+      all_done=0
+    fi
+  done
+  
+  echo ""
+  echo "=================================================="
+  echo "📝 Live Logs (Last 5 lines of running tasks)"
+  echo "=================================================="
+  
+  for i in "${!tasks[@]}"; do
+    t="${tasks[${i}]}"
+    log_file="${log_files[${i}]}"
+    
+    if [[ "${task_done[${t}]}" -eq 0 ]]; then
+      if [[ -f "${log_dir}/${log_file}" ]]; then
+        echo ""
+        echo "--- ${t} ---"
+        tail -n 5 "${log_dir}/${log_file}"
+      fi
+    fi
+  done
+  
+  if [[ "${all_done}" -eq 0 ]]; then
+    sleep 3
+  fi
+done
+
+clear
+echo "=================================================="
+echo "🚀 Async PR Review Status for PR #${pr_number}"
+echo "=================================================="
+echo ""
+for t in "${tasks[@]}"; do
+  read -r task_exit < "${log_dir}/${t}.exit" || task_exit=""
+  if [[ "${task_exit}" == "0" ]]; then
+    echo "  ✅ ${t}: SUCCESS"
+  else
+    echo "  ❌ ${t}: FAILED (exit code ${task_exit})"
+  fi
+done
+echo ""
+
+echo "⏳ Tasks complete! Synthesizing final assessment..."
+if ! "${GEMINI_CMD}" --policy "${POLICY_PATH}" -p "Read the review at ${log_dir}/review.md, the automated test logs at ${log_dir}/npm-test.log, and the manual test execution logs at ${log_dir}/test-execution.log. Summarize the results, state whether the build and tests passed based on ${log_dir}/build-and-lint.exit and ${log_dir}/npm-test.exit, and give a final recommendation for PR ${pr_number}." > "${log_dir}/final-assessment.md" 2>&1; then
+  echo $? > "${log_dir}/final-assessment.exit"
+  echo "❌ Final assessment synthesis failed!"
+  echo "Check ${log_dir}/final-assessment.md for details."
+  notify "Async Review Failed" "Final assessment synthesis failed." "${pr_number}"
+  exit 1
+fi
+
+echo 0 > "${log_dir}/final-assessment.exit"
+echo "✅ Final assessment complete! Check ${log_dir}/final-assessment.md"
+notify "Async Review Complete" "Review and test execution finished successfully." "${pr_number}"

.gemini/skills/async-pr-review/scripts/check-async-review.sh

@@ -0,0 +1,65 @@
+#!/bin/bash
+pr_number="${1}"
+
+if [[ -z "${pr_number}" ]]; then
+  echo "Usage: check-async-review <pr_number>"
+  exit 1
+fi
+
+base_dir="$(git rev-parse --show-toplevel 2>/dev/null || true)"
+if [[ -z "${base_dir}" ]]; then
+  echo "❌ Must be run from within a git repository."
+  exit 1
+fi
+
+log_dir="${base_dir}/.gemini/tmp/async-reviews/pr-${pr_number}/logs"
+
+if [[ ! -d "${log_dir}" ]]; then
+  echo "STATUS: NOT_FOUND"
+  echo "❌ No logs found for PR #${pr_number} in ${log_dir}"
+  exit 0
+fi
+
+tasks=(
+  "setup|setup.log"
+  "pr-diff|pr-diff.diff"
+  "build-and-lint|build-and-lint.log"
+  "review|review.md"
+  "npm-test|npm-test.log"
+  "test-execution|test-execution.log"
+  "final-assessment|final-assessment.md"
+)
+
+all_done=true
+echo "STATUS: CHECKING"
+
+for task_info in "${tasks[@]}"; do
+  IFS="|" read -r task_name log_file <<< "${task_info}"
+  
+  file_path="${log_dir}/${log_file}"
+  exit_file="${log_dir}/${task_name}.exit"
+
+  if [[ -f "${exit_file}" ]]; then
+    read -r exit_code < "${exit_file}" || exit_code=""
+    if [[ "${exit_code}" == "0" ]]; then
+      echo "✅ ${task_name}: SUCCESS"
+    else
+      echo "❌ ${task_name}: FAILED (exit code ${exit_code})"
+      echo "   Last lines of ${file_path}:"
+      tail -n 3 "${file_path}" | sed 's/^/      /' || true
+    fi
+  elif [[ -f "${file_path}" ]]; then
+    echo "⏳ ${task_name}: RUNNING"
+    all_done=false
+  else
+    echo "➖ ${task_name}: NOT STARTED"
+    all_done=false
+  fi
+done
+
+if [[ "${all_done}" == "true" ]]; then
+  echo "STATUS: COMPLETE"
+  echo "LOG_DIR: ${log_dir}"
+else
+  echo "STATUS: IN_PROGRESS"
+fi

.gemini/skills/behavioral-evals/SKILL.md

@@ -0,0 +1,56 @@
+---
+name: behavioral-evals
+description: Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt steering, or adding workspace regression tests.
+---
+
+# Behavioral Evals
+
+## Overview
+
+Behavioral evaluations (evals) are tests that validate the **agent's decision-making** (e.g., tool choice) rather than pure functionality. They are critical for verifying prompt changes, debugging steerability, and preventing regressions.
+
+> [!NOTE]
+> **Single Source of Truth**: For core concepts, policies, running tests, and general best practices, always refer to **[evals/README.md](file:///Users/abhipatel/code/gemini-cli/docs/evals/README.md)**.
+
+---
+
+## 🔄 Workflow Decision Tree
+
+1.  **Does a prompt/tool change need validation?**
+    *   *No* -> Normal integration tests.
+    *   *Yes* -> Continue below.
+2.  **Is it UI/Interaction heavy?**
+    *   *Yes* -> Use `appEvalTest` (`AppRig`). See **[creating.md](references/creating.md)**.
+    *   *No* -> Use `evalTest` (`TestRig`). See **[creating.md](references/creating.md)**.
+3.  **Is it a new test?**
+    *   *Yes* -> Set policy to `USUALLY_PASSES`.
+    *   *No* -> `ALWAYS_PASSES` (locks in regression).
+4.  **Are you fixing a failure or promoting a test?**
+    *   *Fixing* -> See **[fixing.md](references/fixing.md)**.
+    *   *Promoting* -> See **[promoting.md](references/promoting.md)**.
+
+---
+
+## 📋 Quick Checklist
+
+### 1. Setup Workspace
+Seed the workspace with necessary files using the `files` object to simulate a realistic scenario (e.g., NodeJS project with `package.json`).
+*   *Details in **[creating.md](references/creating.md)***
+
+### 2. Write Assertions
+Audit agent decisions using `rig.setBreakpoint()` (AppRig only) or index verification on `rig.readToolLogs()`.
+*   *Details in **[creating.md](references/creating.md)***
+
+### 3. Verify
+Run single tests locally with Vitest. Confirm stability locally before relying on CI workflows.
+*   *See **[evals/README.md](file:///Users/abhipatel/code/gemini-cli/docs/evals/README.md)** for running commands.*
+
+---
+
+## 📦 Bundled Resources
+
+Detailed procedural guides:
+*   **[creating.md](references/creating.md)**: Assertion strategies, Rig selection, Mock MCPs.
+*   **[fixing.md](references/fixing.md)**: Step-by-step automated investigation, architecture diagnosis guidelines.
+*   **[promoting.md](references/promoting.md)**: Candidate identification criteria and threshold guidelines.
+

.gemini/skills/behavioral-evals/assets/interactive_eval.ts.txt

@@ -0,0 +1,27 @@
+import { describe, expect } from 'vitest';
+import { appEvalTest } from './app-test-helper.js';
+
+describe('interactive_feature', () => {
+  // New tests MUST start as USUALLY_PASSES
+  appEvalTest('USUALLY_PASSES', {
+    name: 'should pause for user confirmation',
+    files: {
+      'package.json': JSON.stringify({ name: 'app' })
+    },
+    prompt: 'Task description here requiring approval',
+    timeout: 60000, 
+    setup: async (rig) => {
+      // ⚠️ Breakpoints are ONLY safe in appEvalTest
+      rig.setBreakpoint(['ask_user']);
+    },
+    assert: async (rig) => {
+      // 1. Wait for the breakpoint to trigger
+      const confirmation = await rig.waitForPendingConfirmation('ask_user');
+      expect(confirmation).toBeDefined();
+
+      // 2. Resolve it so the test can finish
+      await rig.resolveTool(confirmation);
+      await rig.waitForIdle();
+    },
+  });
+});

.gemini/skills/behavioral-evals/assets/standard_eval.ts.txt

@@ -0,0 +1,30 @@
+import { describe, expect } from 'vitest';
+import { evalTest } from './test-helper.js';
+
+describe('core_feature', () => {
+  // New tests MUST start as USUALLY_PASSES
+  evalTest('USUALLY_PASSES', {
+    name: 'should perform expected agent action',
+    setup: async (rig) => {
+      // For mocking offline MCP:
+      // rig.addMockMcpServer('workspace-server', 'google-workspace');
+    },
+    files: {
+      'src/app.ts': '// some code',
+    },
+    prompt: 'Task description here',
+    timeout: 60000, // 1 minute safety limit
+    assert: async (rig, result) => {
+      // 1. Audit the trajectory (Safe for standard evalTest)
+      const logs = rig.readToolLogs();
+      const hasTool = logs.some((l) => l.toolRequest.name === 'read_file');
+      expect(hasTool, 'Agent should have read the file').toBe(true);
+
+      // 2. Assert efficiency (Cost/Turn)
+      expect(logs.length).toBeLessThan(5);
+
+      // 3. Assert final output
+      expect(result).toContain('Expected Keyword');
+    },
+  });
+});

.gemini/skills/behavioral-evals/references/creating.md

@@ -0,0 +1,151 @@
+# Creating Behavioral Evals
+
+## 🔬 Rig Selection
+
+| Rig Type          | Import From            | Architecture                                                         | Use When                                                                                              |
+| :---------------- | :--------------------- | :------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------- |
+| **`evalTest`**    | `./test-helper.js`     | **Subprocess**. Runs the CLI in a separate process + waits for exit. | Standard workspace tests. **Do not use `setBreakpoint`**; auditing history (`readToolLogs`) is safer. |
+| **`appEvalTest`** | `./app-test-helper.js` | **In-Process**. Runs directly inside the runner loop.                | UI/Ink rendering. Safe for `setBreakpoint` triggers.                                                  |
+
+---
+
+## 🏗️ Scenario Design
+
+Evals must simulate realistic agent environments to effectively test
+decision-making.
+
+- **Workspace State**: Seed with standard project anchors if testing general
+  capabilities:
+  - `package.json` for NodeJS environments.
+  - Minimal configuration files (`tsconfig.json`, `GEMINI.md`).
+- **Structural Complexity**: Provide enough files to force the agent to _search_
+  or _navigate_, rather than giving the answer directly. Avoid trivial one-file
+  tests unless testing exact prompt steering.
+
+---
+
+## ❌ Fail First Principle
+
+Before asserting a new capability or locking in a fix, **verify that the test
+fails first**.
+
+- It is easy to accidentally write an eval that asserts behaviors that are
+  already met or pass by default.
+- **Process**: reproduce failure with test -> apply fix (prompt/tool) -> verify
+  test passes.
+
+---
+
+## ✋ Testing Patterns
+
+### 1. Breakpoints
+
+Verifies the agent _intends_ to use a tool BEFORE executing it. Useful for
+interactive prompts or safety checks.
+
+```typescript
+// ⚠️ Only works with appEvalTest (AppRig)
+setup: async (rig) => {
+  rig.setBreakpoint(['ask_user']);
+},
+assert: async (rig) => {
+  const confirmation = await rig.waitForPendingConfirmation('ask_user');
+  expect(confirmation).toBeDefined();
+}
+```
+
+### 2. Tool Confirmation Race
+
+When asserting multiple triggers (e.g., "enters plan mode then asks question"):
+
+```typescript
+assert: async (rig) => {
+  let confirmation = await rig.waitForPendingConfirmation([
+    'enter_plan_mode',
+    'ask_user',
+  ]);
+
+  if (confirmation?.name === 'enter_plan_mode') {
+    rig.acceptConfirmation('enter_plan_mode');
+    confirmation = await rig.waitForPendingConfirmation('ask_user');
+  }
+  expect(confirmation?.toolName).toBe('ask_user');
+};
+```
+
+### 3. Audit Tool Logs
+
+Audit exact operations to ensure efficiency (e.g., no redundant reads).
+
+```typescript
+assert: async (rig, result) => {
+  await rig.waitForTelemetryReady();
+  const toolLogs = rig.readToolLogs();
+
+  const writeCall = toolLogs.find(
+    (log) => log.toolRequest.name === 'write_file',
+  );
+  expect(writeCall).toBeDefined();
+};
+```
+
+### 4. Mock MCP Facades
+
+To evaluate tools connected via MCP without hitting live endpoints, load a mock
+server configuration in the `setup` hook.
+
+```typescript
+setup: async (rig) => {
+  rig.addMockMcpServer('workspace-server', 'google-workspace');
+},
+assert: async (rig) => {
+  await rig.waitForTelemetryReady();
+  const toolLogs = rig.readToolLogs();
+  const workspaceCall = toolLogs.find(
+    (log) => log.toolRequest.name === 'mcp_workspace-server_docs.getText'
+  );
+  expect(workspaceCall).toBeDefined();
+};
+```
+
+---
+
+## ⚠️ Safety & Efficiency Guardrails
+
+### 1. Breakpoint Deadlocks
+
+Breakpoints (`setBreakpoint`) pause execution. In standard `evalTest`,
+`rig.run()` waits for the process to exit _before_ assertions run. **This will
+hang indefinitely.**
+
+- **Use Breakpoints** for `appEvalTest` or interactive simulations.
+- **Use Audit Tool Logs** (above) for standard trajectory tests.
+
+### 2. Runaway Timeout
+
+Always set a budget boundary in the `EvalCase` to prevent runaway loops on
+quota:
+
+```typescript
+evalTest('USUALLY_PASSES', {
+  name: '...',
+  timeout: 60000, // 1 minute safety limit
+  // ...
+});
+```
+
+### 3. Efficiency Assertion (Turn limits)
+
+Check if a tool is called _early_ using index checks:
+
+```typescript
+assert: async (rig) => {
+  const toolLogs = rig.readToolLogs();
+  const toolCallIndex = toolLogs.findIndex(
+    (log) => log.toolRequest.name === 'cli_help',
+  );
+
+  expect(toolCallIndex).toBeGreaterThan(-1);
+  expect(toolCallIndex).toBeLessThan(5); // Called within first 5 turns
+};
+```

.gemini/skills/behavioral-evals/references/fixing.md

@@ -0,0 +1,100 @@
+# Fixing Behavioral Evals
+
+Use this guide when asked to debug, troubleshoot, or fix a failing behavioral
+evaluation.
+
+---
+
+## 1. 🔍 Investigate
+
+1.  **Fetch Nightly Results**: Use the `gh` CLI to inspect the latest run from
+    `evals-nightly.yml` if applicable.
+    - _Example view URL_:
+      `https://github.com/google-gemini/gemini-cli/actions/workflows/evals-nightly.yml`
+2.  **Isolate**: DO NOT push changes or start remote runs. Confine investigation
+    to the local workspace.
+3.  **Read Logs**:
+    - Eval logs live in `evals/logs/<test_name>.log`.
+    - Enable verbose debugging via `export GEMINI_DEBUG_LOG_FILE="debug.log"`.
+4.  **Diagnose**: Audit tool logs and telemetry. Note if due to setup/assert.
+    - **Tip**: Proactively add custom logging/diagnostics to check hypotheses.
+
+---
+
+## 2. 🛠️ Fix Strategy
+
+1.  **Targeted Location**: Locate the test case and the corresponding
+    prompt/code.
+2.  **Iterative Scope**: Make extreme change first to verify scope, then refine
+    to a minimal, targeted change.
+3.  **Assertion Fidelity**:
+    - Changing the test prompt is a **last resort** (prompts are often vague by
+      design).
+    - **Warning**: Do not lose test fidelity by making prompts too direct/easy.
+    - **Primary Fix Trigger**: Adjust tool descriptions, system prompts
+      (`snippets.ts`), or **modules that contribute to the prompt template**.
+    - Fixes should generally try to improve the prompt
+      `@packages/core/src/prompts/snippets.ts` first.
+    - **Instructional Generality**: Changes to the system prompt should aim to
+      be as general as possible while still accomplishing the goal. Specificity
+      should be added only as needed.
+      - **Principle**: Instead of creating "forbidden lists" for specific syntax
+        (e.g., "Don't use `Object.create()`"), formulate a broader engineering
+        principle that covers the underlying issue (e.g., "Prioritize explicit
+        composition over hidden prototype manipulation"). This improves
+        steerability across a wider range of similar scenarios.
+      - _Low Specificity_: "Follow ecosystem best practices"
+      - _Medium Specificity_: "Utilize OOP and functional best practices, as
+        applicable"
+      - _High Specificity_: Provide ecosystem-specific hints as examples of a
+        broader principle rather than direct instructions. e.g., "NEVER use
+        hacks like bypassing the type system or employing 'hidden' logic (e.g.:
+        reflection, prototype manipulation). Instead, use explicit and idiomatic
+        language features (e.g.: type guards, explicit class instantiation, or
+        object spread) that maintain structural integrity."
+    - **Prompt Simplification**: Once the test is passing, use `ask_user` to
+      determine if prompt simplification is desired.
+      - **Criteria**: Simplification should be attempted only if there are
+        related clauses that can be de-duplicated or reparented under a single
+        heading.
+      - **Verification**: As part of simplification, you MUST identify and run
+        any behavioral eval tests that might be affected by the changes to
+        ensure no regressions are introduced.
+    - Test fixes should not "cheat" by changing a test's `GEMINI.md` file or by
+      updating the test's prompt to instruct it to not repro the bug.
+    - **Warning**: Prompts have multiple configurations; ensure your fix targets
+      the correct config for the model in question.
+4.  **Architecture Options**: If prompt or instruction tuning triggers no
+    improvement, analyze loop composition.
+    - **AgentLoop**: Defined by `context + toolset + prompt`.
+    - **Enhancements**: Loops perform best with direct prompts, fewer irrelevant
+      tools, low goal density, and minimal low-value/irrelevant context.
+    - **Modifications**: Compose subagents or isolate tools. Ground in observed
+      traces.
+    - **Warning**: Think deeply before offering recommendations; avoid parroting
+      abstract design guidelines.
+
+---
+
+## 3. ✅ Verify
+
+1.  **Run Local**: Run Vitest in non-interactive mode on just the file.
+2.  **Log Audit**: Prioritize diagnosing failures via log comparison before
+    triggering heavy test runs.
+3.  **Stability Limit**: Run the test **3 times** locally on key models (can use
+    scripts to run in parallel for speed):
+    - **Gemini 3.0**
+    - **Gemini 3 Flash**
+    - **Gemini 2.5 Pro**
+4.  **Flakiness Rule**: If it passes 2/3 times, it may be inherent noise
+    difficult to improve without a structural split.
+
+---
+
+## 4. 📊 Report
+
+Provide a summary of:
+
+- Test success rate for each tested model (e.g., 3/3 = 100%).
+- Root cause identification and fix explanation.
+- If unfixed, provide high-confidence architecture recommendations.

.gemini/skills/behavioral-evals/references/promoting.md

@@ -0,0 +1,55 @@
+# Promoting Behavioral Evals
+
+Use this guide when asked to analyze nightly results and promote incubated tests
+to stable suites.
+
+---
+
+## 1. 🔍 Investigate candidates
+
+1.  **Audit Nightly Logs**: Use the `gh` CLI to fetch results from
+    `evals-nightly.yml` (Direct URL:
+    `https://github.com/google-gemini/gemini-cli/actions/workflows/evals-nightly.yml`).
+    - **Tip**: The aggregate summary from the most recent run integrates the
+      last 7 runs of history automatically.
+    - **Safety**: DO NOT push changes or start remote runs. All verification is
+      local.
+2.  **Assess Stability**: Identify tests that pass **100% of the time** across
+    ALL enabled models over the **last 7 nightly runs** in a row.
+    - _100% means the test passed 3/3 times for every model and run._
+3.  **Promotion Targets**: Tests meeting this criteria are candidates for
+    promotion from `USUALLY_PASSES` to `ALWAYS_PASSES`.
+
+---
+
+## 2. 🚥 Promotion Steps
+
+1.  **Locate File**: Locate the eval file in the `evals/` directory.
+2.  **Update Policy**: Modify the policy argument to `ALWAYS_PASSES`.
+    ```typescript
+    evalTest('ALWAYS_PASSES', { ... })
+    ```
+3.  **Targeting**: Follow guidelines in `evals/README.md` regarding stable suite
+    organization.
+4.  **Constraint**: Your final change must be **minimal and targeted** strictly
+    to promoting the test status. Do not refactor the test or setup fixtures.
+
+---
+
+## 3. ✅ Verify
+
+1.  **Run Prompted Tests**: Run the promoted test locally using non-interactive
+    Vitest to confirm structure validity.
+2.  **Verify Suite Inclusion**: Check that the test is successfully picked up by
+    standard runnable ranges.
+
+---
+
+## 4. 📊 Report
+
+Provide a summary of:
+
+- Which tests were promoted.
+- Provide the success rate evidence (e.g., 7/7 runs passed for all models).
+- If no candidates qualified, list the next closest candidates and their current
+  pass rate.

.gemini/skills/behavioral-evals/references/running.md

@@ -0,0 +1,95 @@
+# Running & Promoting Evals
+
+## 🛠️ Prerequisites
+
+Behavioral evals run against the compiled binary. You **must** build and bundle
+the project first after making changes:
+
+```bash
+npm run build && npm run bundle
+```
+
+---
+
+## 🏃‍♂️ Running Tests
+
+### 1. Configure Environment Variables
+
+Evals require a standard API key. If your `.env` file has multiple keys or
+comments, use this precise extraction setup:
+
+```bash
+export GEMINI_API_KEY=$(grep '^GEMINI_API_KEY=' .env | cut -d '=' -f2) && RUN_EVALS=1 npx vitest run --config evals/vitest.config.ts <file_name>
+```
+
+### 2. Commands
+
+| Command                             | Scope           | Description                                        |
+| :---------------------------------- | :-------------- | :------------------------------------------------- |
+| `npm run test:always_passing_evals` | `ALWAYS_PASSES` | Fast feedback, runs in CI.                         |
+| `npm run test:all_evals`            | All             | Runs nightly incubation tests. Sets `RUN_EVALS=1`. |
+
+### Target Specific File
+
+_Note: `RUN_EVALS=1` is required for incubated (`USUALLY_PASSES`) tests._
+
+```bash
+RUN_EVALS=1 npx vitest run --config evals/vitest.config.ts my_feature.eval.ts
+```
+
+---
+
+## 🐞 Debugging and Logs
+
+If a test fails, verify:
+
+- **Tool Trajectory Logs**:序列 of calls in `evals/logs/<test_name>.log`.
+- **Verbose Reasoning**: Capture raw buffer traces by setting
+  `GEMINI_DEBUG_LOG_FILE`:
+  ```bash
+  export GEMINI_DEBUG_LOG_FILE="debug.log"
+  ```
+
+---
+
+### 🎯 Verify Model Targeting
+
+- **Tip:** Standard evals benchmark against model variations. If a test passes
+  on Flash but fails on Pro (or vice versa), the issue is usually in the **tool
+  description**, not the prompt definition. Flash is sensitive to "instruction
+  bloat," while Pro is sensitive to "ambiguous intent."
+
+---
+
+## 🚥 deflaking & Promotion
+
+To maintain CI stability, all new evals follow a strict incubation period.
+
+### 1. Incubation (`USUALLY_PASSES`)
+
+New tests must be created with the `USUALLY_PASSES` policy.
+
+```typescript
+evalTest('USUALLY_PASSES', { ... })
+```
+
+They run in **Evals: Nightly** workflows and do not block PR merges.
+
+### 2. Investigate Failures
+
+If a nightly eval regresses, investigate via agent:
+
+```bash
+gemini /fix-behavioral-eval [optional-run-uri]
+```
+
+### 3. Promotion (`ALWAYS_PASSES`)
+
+Once a test scores 100% consistency over multiple nightly cycles:
+
+```bash
+gemini /promote-behavioral-eval
+```
+
+_Do not promote manually._ The command verifies trajectory logs before updating
+the file policy.

.gemini/skills/ci/SKILL.md

@@ -0,0 +1,66 @@
+---
+name: ci
+description:
+  A specialized skill for Gemini CLI that provides high-performance, fail-fast
+  monitoring of GitHub Actions workflows and automated local verification of CI
+  failures. It handles run discovery automatically—simply provide the branch name.
+---
+
+# CI Replicate & Status
+
+This skill enables the agent to efficiently monitor GitHub Actions, triage
+failures, and bridge remote CI errors to local development. It defaults to
+**automatic replication** of failures to streamline the fix cycle.
+
+## Core Capabilities
+
+- **Automatic Replication**: Automatically monitors CI and immediately executes 
+  suggested test or lint commands locally upon failure.
+- **Real-time Monitoring**: Aggregated status line for all concurrent workflows
+  on the current branch.
+- **Fail-Fast Triage**: Immediately stops on the first job failure to provide a
+  structured report.
+
+## Workflow
+
+### 1. CI Replicate (`replicate`) - DEFAULT
+Use this as the primary path to monitor CI and **automatically** replicate 
+failures locally for immediate triage and fixing.
+- **Behavior**: When this workflow is triggered, the agent will monitor the CI
+  and **immediately and automatically execute** all suggested test or lint
+  commands (marked with 🚀) as soon as a failure is detected. 
+- **Tool**: `node .gemini/skills/ci/scripts/ci.mjs [branch]`
+- **Discovery**: The script **automatically** finds the latest active or recent
+  run for the branch. Do NOT manually search for run IDs.
+- **Goal**: Reproduce the failure locally without manual intervention, then
+  proceed to analyze and fix the code.
+
+### 1. CI Status (`status`)
+Use this when you have pushed changes and need to monitor the CI and reproduce
+any failures locally.
+- **Tool**: `node .gemini/skills/ci/scripts/ci.mjs [branch] [run_id]`
+- **Discovery**: The script **automatically** finds the latest active or recent
+  run for the branch. You should NOT manually search for \`run_id\` using \`gh run list\`
+  unless a specific historical run is requested. Simply provide the branch name.
+- **Step 1 (Monitor)**: Execute the tool with the branch name.
+- **Step 2 (Extract)**: Extract suggested \`npm test\` or \`npm run lint\` commands
+  from the output (marked with 🚀).
+- **Step 3 (Reproduce)**: Execute those commands locally to confirm the failure.
+- **Behavior**: It will poll every 15 seconds. If it detects a failure, it will
+  exit with a structured report and provide the exact commands to run locally.
+
+## Failure Categories & Actions
+
+- **Test Failures**: Agent should run the specific `npm test -w <pkg> -- <path>`
+  command suggested.
+- **Lint Errors**: Agent should run `npm run lint:all` or the specific package
+  lint command.
+- **Build Errors**: Agent should check `tsc` output or build logs to resolve
+  compilation issues.
+- **Job Errors**: Investigate `gh run view --job <job_id> --log` for
+  infrastructure or setup failures.
+
+## Noise Filtering
+The underlying scripts automatically filter noise (Git logs, NPM warnings, stack
+trace overhead). The agent should focus on the "Structured Failure Report"
+provided by the tool.

.gemini/skills/ci/scripts/ci.mjs

@@ -0,0 +1,281 @@
+#!/usr/bin/env node
+
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import { execSync } from 'node:child_process';
+
+const BRANCH =
+  process.argv[2] || execSync('git branch --show-current').toString().trim();
+const RUN_ID_OVERRIDE = process.argv[3];
+
+let REPO;
+try {
+  const remoteUrl = execSync('git remote get-url origin').toString().trim();
+  REPO = remoteUrl
+    .replace(/.*github\.com[\/:]/, '')
+    .replace(/\.git$/, '')
+    .trim();
+} catch (e) {
+  REPO = 'google-gemini/gemini-cli';
+}
+
+const FAILED_FILES = new Set();
+
+function runGh(args) {
+  try {
+    return execSync(`gh ${args}`, {
+      stdio: ['ignore', 'pipe', 'ignore'],
+    }).toString();
+  } catch (e) {
+    return null;
+  }
+}
+
+function fetchFailuresViaApi(jobId) {
+  try {
+    const cmd = `gh api repos/${REPO}/actions/jobs/${jobId}/logs | grep -iE " FAIL |❌|ERROR|Lint failed|Build failed|Exception|failed with exit code"`;
+    return execSync(cmd, {
+      stdio: ['ignore', 'pipe', 'ignore'],
+      maxBuffer: 10 * 1024 * 1024,
+    }).toString();
+  } catch (e) {
+    return '';
+  }
+}
+
+function isNoise(line) {
+  const lower = line.toLowerCase();
+  return (
+    lower.includes('* [new branch]') ||
+    lower.includes('npm warn') ||
+    lower.includes('fetching updates') ||
+    lower.includes('node:internal/errors') ||
+    lower.includes('at ') || // Stack traces
+    lower.includes('checkexecsyncerror') ||
+    lower.includes('node_modules')
+  );
+}
+
+function extractTestFile(failureText) {
+  const cleanLine = failureText
+    .replace(/[|#\[\]()]/g, ' ')
+    .replace(/<[^>]*>/g, ' ')
+    .trim();
+  const fileMatch = cleanLine.match(/([\w\/._-]+\.test\.[jt]sx?)/);
+  if (fileMatch) return fileMatch[1];
+  return null;
+}
+
+function generateTestCommand(failedFilesMap) {
+  const workspaceToFiles = new Map();
+  for (const [file, info] of failedFilesMap.entries()) {
+    if (
+      ['Job Error', 'Unknown File', 'Build Error', 'Lint Error'].includes(file)
+    )
+      continue;
+    let workspace = '@google/gemini-cli';
+    let relPath = file;
+    if (file.startsWith('packages/core/')) {
+      workspace = '@google/gemini-cli-core';
+      relPath = file.replace('packages/core/', '');
+    } else if (file.startsWith('packages/cli/')) {
+      workspace = '@google/gemini-cli';
+      relPath = file.replace('packages/cli/', '');
+    }
+    relPath = relPath.replace(/^.*packages\/[^\/]+\//, '');
+    if (!workspaceToFiles.has(workspace))
+      workspaceToFiles.set(workspace, new Set());
+    workspaceToFiles.get(workspace).add(relPath);
+  }
+  const commands = [];
+  for (const [workspace, files] of workspaceToFiles.entries()) {
+    commands.push(`npm test -w ${workspace} -- ${Array.from(files).join(' ')}`);
+  }
+  return commands.join(' && ');
+}
+
+async function monitor() {
+  let targetRunIds = [];
+  if (RUN_ID_OVERRIDE) {
+    targetRunIds = [RUN_ID_OVERRIDE];
+  } else {
+    // 1. Get runs directly associated with the branch
+    const runListOutput = runGh(
+      `run list --branch "${BRANCH}" --limit 10 --json databaseId,status,workflowName,createdAt`,
+    );
+    if (runListOutput) {
+      const runs = JSON.parse(runListOutput);
+      const activeRuns = runs.filter((r) => r.status !== 'completed');
+      if (activeRuns.length > 0) {
+        targetRunIds = activeRuns.map((r) => r.databaseId);
+      } else if (runs.length > 0) {
+        const latestTime = new Date(runs[0].createdAt).getTime();
+        targetRunIds = runs
+          .filter((r) => latestTime - new Date(r.createdAt).getTime() < 60000)
+          .map((r) => r.databaseId);
+      }
+    }
+
+    // 2. Get runs associated with commit statuses (handles chained/indirect runs)
+    try {
+      const headSha = execSync(`git rev-parse "${BRANCH}"`).toString().trim();
+      const statusOutput = runGh(
+        `api repos/${REPO}/commits/${headSha}/status -q '.statuses[] | select(.target_url | contains("actions/runs/")) | .target_url'`,
+      );
+      if (statusOutput) {
+        const statusRunIds = statusOutput
+          .split('\n')
+          .filter(Boolean)
+          .map((url) => {
+            const match = url.match(/actions\/runs\/(\d+)/);
+            return match ? parseInt(match[1], 10) : null;
+          })
+          .filter(Boolean);
+
+        for (const runId of statusRunIds) {
+          if (!targetRunIds.includes(runId)) {
+            targetRunIds.push(runId);
+          }
+        }
+      }
+    } catch (e) {
+      // Ignore if branch/SHA not found or API fails
+    }
+
+    if (targetRunIds.length > 0) {
+      const runNames = [];
+      for (const runId of targetRunIds) {
+        const runInfo = runGh(`run view "${runId}" --json workflowName`);
+        if (runInfo) {
+          runNames.push(JSON.parse(runInfo).workflowName);
+        }
+      }
+      console.log(`Monitoring workflows: ${[...new Set(runNames)].join(', ')}`);
+    }
+  }
+
+  if (targetRunIds.length === 0) {
+    console.log(`No runs found for branch ${BRANCH}.`);
+    process.exit(0);
+  }
+
+  while (true) {
+    let allPassed = 0,
+      allFailed = 0,
+      allRunning = 0,
+      allQueued = 0,
+      totalJobs = 0;
+    let anyRunInProgress = false;
+    const fileToTests = new Map();
+    let failuresFoundInLoop = false;
+
+    for (const runId of targetRunIds) {
+      const runOutput = runGh(
+        `run view "${runId}" --json databaseId,status,conclusion,workflowName`,
+      );
+      if (!runOutput) continue;
+      const run = JSON.parse(runOutput);
+      if (run.status !== 'completed') anyRunInProgress = true;
+
+      const jobsOutput = runGh(`run view "${runId}" --json jobs`);
+      if (jobsOutput) {
+        const { jobs } = JSON.parse(jobsOutput);
+        totalJobs += jobs.length;
+        const failedJobs = jobs.filter((j) => j.conclusion === 'failure');
+        if (failedJobs.length > 0) {
+          failuresFoundInLoop = true;
+          for (const job of failedJobs) {
+            const failures = fetchFailuresViaApi(job.databaseId);
+            if (failures.trim()) {
+              failures.split('\n').forEach((line) => {
+                if (!line.trim() || isNoise(line)) return;
+                const file = extractTestFile(line);
+                const filePath =
+                  file ||
+                  (line.toLowerCase().includes('lint')
+                    ? 'Lint Error'
+                    : line.toLowerCase().includes('build')
+                      ? 'Build Error'
+                      : 'Unknown File');
+                let testName = line;
+                if (line.includes(' > ')) {
+                  testName = line.split(' > ').slice(1).join(' > ').trim();
+                }
+                if (!fileToTests.has(filePath))
+                  fileToTests.set(filePath, new Set());
+                fileToTests.get(filePath).add(testName);
+              });
+            } else {
+              const step =
+                job.steps?.find((s) => s.conclusion === 'failure')?.name ||
+                'unknown';
+              const category = step.toLowerCase().includes('lint')
+                ? 'Lint Error'
+                : step.toLowerCase().includes('build')
+                  ? 'Build Error'
+                  : 'Job Error';
+              if (!fileToTests.has(category))
+                fileToTests.set(category, new Set());
+              fileToTests
+                .get(category)
+                .add(`${job.name}: Failed at step "${step}"`);
+            }
+          }
+        }
+        for (const job of jobs) {
+          if (job.status === 'in_progress') allRunning++;
+          else if (job.status === 'queued') allQueued++;
+          else if (job.conclusion === 'success') allPassed++;
+          else if (job.conclusion === 'failure') allFailed++;
+        }
+      }
+    }
+
+    if (failuresFoundInLoop) {
+      console.log(
+        `\n\n❌ Failures detected across ${allFailed} job(s). Stopping monitor...`,
+      );
+      console.log('\n--- Structured Failure Report (Noise Filtered) ---');
+      for (const [file, tests] of fileToTests.entries()) {
+        console.log(`\nCategory/File: ${file}`);
+        // Limit output per file if it's too large
+        const testsArr = Array.from(tests).map((t) =>
+          t.length > 500 ? t.substring(0, 500) + '... [TRUNCATED]' : t,
+        );
+        testsArr.slice(0, 10).forEach((t) => console.log(`  - ${t}`));
+        if (testsArr.length > 10)
+          console.log(`  ... and ${testsArr.length - 10} more`);
+      }
+      const testCmd = generateTestCommand(fileToTests);
+      if (testCmd) {
+        console.log('\n🚀 Run this to verify fixes:');
+        console.log(testCmd);
+      } else if (
+        Array.from(fileToTests.keys()).some((k) => k.includes('Lint'))
+      ) {
+        console.log('\n🚀 Run this to verify lint fixes:\nnpm run lint:all');
+      }
+      console.log('---------------------------------');
+      process.exit(1);
+    }
+
+    const completed = allPassed + allFailed;
+    process.stdout.write(
+      `\r⏳ Monitoring ${targetRunIds.length} runs... ${completed}/${totalJobs} jobs (${allPassed} passed, ${allFailed} failed, ${allRunning} running, ${allQueued} queued)          `,
+    );
+    if (!anyRunInProgress) {
+      console.log('\n✅ All workflows passed!');
+      process.exit(0);
+    }
+    await new Promise((r) => setTimeout(r, 15000));
+  }
+}
+
+monitor().catch((err) => {
+  console.error('\nMonitor error:', err.message);
+  process.exit(1);
+});

.gemini/skills/docs-changelog/SKILL.md

@@ -162,5 +162,7 @@ instructions for the other section.
 
 ## Finalize
 
-- After making changes, run `npm run format` ONLY to ensure consistency.
+- After making changes, if `npm run format` fails, it may be necessary to run
+  `npm install` first to ensure all formatting dependencies are available.
+  Then, run `npm run format` to ensure consistency.
 - Delete any temporary files created during the process.

.gemini/skills/docs-writer/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: docs-writer
 description:
-  Always use this skill when the task involves writing, reviewing, or editing 
+  Always use this skill when the task involves writing, reviewing, or editing
   files in the `/docs` directory or any `.md` files in the repository.
 ---
 
@@ -24,7 +24,7 @@ approach.
 
 - **Perspective and tense:** Address the reader as "you." Use active voice and
   present tense (e.g., "The API returns...").
-- **Tone:** Professional, friendly, and direct. 
+- **Tone:** Professional, friendly, and direct.
 - **Clarity:** Use simple vocabulary. Avoid jargon, slang, and marketing hype.
 - **Global Audience:** Write in standard US English. Avoid idioms and cultural
   references.
@@ -47,8 +47,8 @@ Write precisely to ensure your instructions are unambiguous.
   "foo" or "bar."
 - **Quota and limit terminology:** For any content involving resource capacity
   or using the word "quota" or "limit", strictly adhere to the guidelines in
-  the `quota-limit-style-guide.md` resource file. Generally, Use "quota" for the
-  administrative bucket and "limit" for the numerical ceiling.
+  the `quota-limit-style-guide.md` resource file. Generally, Use "quota" for
+  the administrative bucket and "limit" for the numerical ceiling.
 
 ### Formatting and syntax
 Apply consistent formatting to make documentation visually organized and
@@ -65,35 +65,85 @@ accessible.
 - **UI and code:** Use **bold** for UI elements and `code font` for filenames,
   snippets, commands, and API elements. Focus on the task when discussing
   interaction.
-- **Links:** Use descriptive anchor text; avoid "click here." Ensure the link
-  makes sense out of context.
 - **Accessibility:** Use semantic HTML elements correctly (headings, lists, 
   tables).
 - **Media:** Use lowercase hyphenated filenames. Provide descriptive alt text
   for all images.
+- **Details section:** Use the `<details>` tag to create a collapsible section.
+  This is useful for supplementary or data-heavy information that isn't critical
+  to the main flow.
+
+  Example:
+
+  <details>
+  <summary>Title</summary>
+
+  - First entry
+  - Second entry
+
+  </details>
+
+- **Callouts**: Use GitHub-flavored markdown alerts to highlight important
+  information. To ensure the formatting is preserved by `npm run format`, place
+  an empty line, then a prettier ignore comment directly before the callout
+  block. Use `<!-- prettier-ignore -->` for standard Markdown files (`.md`) and
+  `{/* prettier-ignore */}` for MDX files (`.mdx`). The callout type (`[!TYPE]`)
+  should be on the first line, followed by a newline, and then the content, with
+  each subsequent line of content starting with `>`. Available types are `NOTE`,
+  `TIP`, `IMPORTANT`, `WARNING`, and `CAUTION`.
+
+  Example (.md):
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an example of a multi-line note that will be preserved
+> by Prettier.
+
+  Example (.mdx):
+
+{/* prettier-ignore */}
+> [!NOTE]
+> This is an example of a multi-line note that will be preserved
+> by Prettier.
+
+### Links
+- **Accessibility:** Use descriptive anchor text; avoid "click here." Ensure the
+  link makes sense out of context, such as when being read by a screen reader.
+- **Use relative links in docs:** Use relative links in documentation (`/docs/`)
+  to ensure portability. Use paths relative to the current file's directory
+  (for example, `../tools/` from `docs/cli/`). Do not include the `/docs/`
+  section of a path, but do verify that the resulting relative link exists. This
+  does not apply to meta files such as README.MD and CONTRIBUTING.MD.
+- **When changing headings, check for deep links:** If a user is changing a
+  heading, check for deep links to that heading in other pages and update
+  accordingly.
 
 ### Structure
 - **BLUF:** Start with an introduction explaining what to expect.
 - **Experimental features:** If a feature is clearly noted as experimental,
-add the following note immediately after the introductory paragraph:
-  `> **Note:** This is a preview feature currently under active development.`
+  add the following note immediately after the introductory paragraph:
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an experimental feature currently under active development.
+(Note: Use `{/* prettier-ignore */}` if editing an `.mdx` file.)
+
 - **Headings:** Use hierarchical headings to support the user journey.
-- **Procedures:** 
+- **Procedures:**
   - Introduce lists of steps with a complete sentence.
   - Start each step with an imperative verb.
   - Number sequential steps; use bullets for non-sequential lists.
   - Put conditions before instructions (e.g., "On the Settings page, click...").
   - Provide clear context for where the action takes place.
   - Indicate optional steps clearly (e.g., "Optional: ...").
-- **Elements:** Use bullet lists, tables, notes (`> **Note:**`), and warnings 
-  (`> **Warning:**`).
+- **Elements:** Use bullet lists, tables, details, and callouts.
 - **Avoid using a table of contents:** If a table of contents is present, remove
   it.
 - **Next steps:** Conclude with a "Next steps" section if applicable.
 
 ## Phase 2: Preparation
 Before modifying any documentation, thoroughly investigate the request and the
-surrounding context. 
+surrounding context.
 
 1.  **Clarify:** Understand the core request. Differentiate between writing new
     content and editing existing content. If the request is ambiguous (e.g.,
@@ -104,6 +154,8 @@ surrounding context.
 4.  **Connect:** Identify all referencing pages if changing behavior. Check if
     `docs/sidebar.json` needs updates.
 5.  **Plan:** Create a step-by-step plan before making changes.
+6.  **Audit Docset:** If asked to audit the documentation, follow the procedural
+    guide in [docs-auditing.md](./references/docs-auditing.md).
 
 ## Phase 3: Execution
 Implement your plan by either updating existing files or creating new ones
@@ -116,7 +168,7 @@ documentation.
 
 - **Gaps:** Identify areas where the documentation is incomplete or no longer
   reflects existing code.
-- **Structure:** Apply "Structure (New Docs)" rules (BLUF, headings, etc.) when 
+- **Structure:** Apply "Structure (New Docs)" rules (BLUF, headings, etc.) when
   adding new sections to existing pages.
 - **Headers**: If you change a header, you must check for links that lead to
   that header and update them.
@@ -126,17 +178,17 @@ documentation.
 - **Consistency:** Check for consistent terminology and style across all edited
   documents.
 
-
 ## Phase 4: Verification and finalization
-Perform a final quality check to ensure that all changes are correctly formatted
-and that all links are functional.
+Perform a final quality check to ensure that all changes are correctly
+formatted and that all links are functional.
 
 1.  **Accuracy:** Ensure content accurately reflects the implementation and
   technical behavior.
 2.  **Self-review:** Re-read changes for formatting, correctness, and flow.
-3.  **Link check:** Verify all new and existing links leading to or from modified
-    pages. If you changed a header, ensure that any links that lead to it are
-    updated.
-4.  **Format:** Once all changes are complete, ask to execute `npm run format`
-    to ensure consistent formatting across the project. If the user confirms,
-    execute the command.
+3.  **Link check:** Verify all new and existing links leading to or from
+    modified pages. If you changed a header, ensure that any links that lead to
+    it are updated.
+4.  **Format:** If `npm run format` fails, it may be necessary to run `npm
+    install` first to ensure all formatting dependencies are available. Once all
+    changes are complete, ask to execute `npm run format` to ensure consistent
+    formatting across the project. If the user confirms, execute the command.

.gemini/skills/docs-writer/references/docs-auditing.md

@@ -0,0 +1,195 @@
+# Procedural Guide: Auditing the Docset
+
+This guide outlines the process for auditing the Gemini CLI documentation for
+correctness and adherence to style guidelines. This process involves both an
+"Editor" and "Technical Writer" phase.
+
+## Objective
+
+To ensure all public-facing documentation is accurate, up-to-date, adheres to
+the Gemini CLI documentation style guide, and reflects the current state of the
+codebase.
+
+## Phase 1: Editor Audit
+
+**Role:** The editor is responsible for identifying potential issues based on
+style guide violations and technical inaccuracies.
+
+### Steps
+
+1.  **Identify Documentation Scope:**
+    - Read `docs/sidebar.json` to get a list of all viewable documentation
+      pages.
+    - For each entry with a `slug`, convert it into a file path (e.g., `docs` ->
+      `docs/index.md`, `docs/get-started` -> `docs/get-started.md`). Ignore
+      entries with `link` properties.
+
+2.  **Prepare Audit Results File:**
+    - Create a new Markdown file named `audit-results-[YYYY-MM-DD].md` (e.g.,
+      `audit-results-2026-03-13.md`). This file will contain all identified
+      violations and recommendations.
+
+3.  **Retrieve Style Guidelines:**
+    - Familiarize yourself with the `docs-writer` skill instructions and the
+      included style guidelines.
+
+4.  **Audit Each Document:**
+    - For each documentation file identified in Step 1, read its content.
+    - **Review against Style Guide:**
+      - **Voice and Tone Violations:**
+        - **Unprofessional Tone:** Identify phrasing that is overly casual,
+          defensive, or lacks a professional and friendly demeanor.
+        - **Indirectness or Vagueness:** Identify sentences that are
+          unnecessarily wordy or fail to be concise and direct.
+        - **Incorrect Pronoun:** Identify any use of third-person pronouns
+          (e.g., "we," "they," "the user") when referring to the reader, instead
+          of the second-person pronoun **"you"**.
+        - **Passive Voice:** Identify sentences written in the passive voice.
+        - **Incorrect Tense:** Identify the use of past or future tense verbs,
+          instead of the **present tense**.
+        - **Poor Vocabulary:** Identify the use of jargon, slang, or overly
+          informal language.
+      - **Language and Grammar Violations:**
+        - **Lack of Conciseness:** Identify unnecessarily long phrases or
+          sentences.
+        - **Punctuation Errors:** Identify incorrect or missing punctuation.
+        - **Ambiguous Dates:** Identify dates that could be misinterpreted
+          (e.g., "next Monday" instead of "April 15, 2026").
+        - **Abbreviation Usage:** Identify the use of abbreviations that should
+          be spelled out (e.g., "e.g." instead of "for example").
+        - **Terminology:** Check for incorrect or inconsistent use of
+          product-specific terms (e.g., "quota" vs. "limit").
+      - **Formatting and Syntax Violations:**
+        - **Missing Overview:** Check for the absence of a brief overview
+          paragraph at the start of the document.
+        - **Line Length:** Identify any lines of text that exceed **80
+          characters** (text wrap violation).
+        - **Casing:** Identify incorrect casing for headings, titles, or named
+          entities (e.g., product names like `Gemini CLI`).
+        - **List Formatting:** Identify incorrectly formatted lists (e.g.,
+          inconsistent indentation or numbering).
+        - **Incorrect Emphasis:** Identify incorrect use of bold text (should
+          only be used for UI elements) or code font (should be used for code,
+          file names, or command-line input).
+        - **Link Quality:** Identify links with non-descriptive anchor text
+          (e.g., "click here").
+        - **Image Alt Text:** Identify images with missing or poor-quality
+          (non-descriptive) alt text.
+      - **Structure Violations:**
+        - **Missing BLUF:** Check for the absence of a "Bottom Line Up Front"
+          summary at the start of complex sections or documents.
+        - **Experimental Feature Notes:** Identify experimental features that
+          are not clearly labeled with a standard note.
+        - **Heading Hierarchy:** Check for skipped heading levels (e.g., going
+          from `##` to `####`).
+        - **Procedure Clarity:** Check for procedural steps that do not start
+          with an imperative verb or where a condition is placed _after_ the
+          instruction.
+        - **Element Misuse:** Identify the incorrect or inappropriate use of
+          special elements (e.g., Notes, Warnings, Cautions).
+        - **Table of Contents:** Identify the presence of a dynamically
+          generated or manually included table of contents.
+        - **Missing Next Steps:** Check for procedural documents that lack a
+          "Next steps" section (if applicable).
+    - **Verify Code Accuracy (if applicable):**
+      - If the document contains code snippets (e.g., shell commands, API calls,
+        file paths, Docker image versions), use `grep_search` and `read_file`
+        within the `packages/` directory (or other relevant parts of the
+        codebase) to ensure the code is still accurate and up-to-date. Pay close
+        attention to version numbers, package names, and command syntax.
+    - **Record Findings:** For each **violation** or inaccuracy found:
+      - Note the file path.
+      - Describe the violation (e.g., "Violation (Language and Grammar): Uses
+        'e.g.'").
+      - Provide a clear and actionable recommendation to correct the issue.
+        (e.g., "Recommendation: Replace 'e.g.' with 'for example'." or
+        "Recommendation: Replace '...' with '...' in active voice.).
+      - Append these findings to `audit-results-[YYYY-MM-DD].md`.
+
+## Phase 2: Software Engineer Audit
+
+**Role:** The software engineer is responsible for finding undocumented features
+by auditing the codebase and recent changelogs, and passing these findings to
+the technical writer.
+
+### Steps
+
+1.  **Proactive Codebase Audit:**
+    - Audit high-signal areas of the codebase to identify undocumented features.
+      You MUST review:
+      - `packages/cli/src/commands/`
+      - `packages/core/src/tools/`
+      - `packages/cli/src/config/settings.ts`
+
+2.  **Review Recent Updates:**
+    - Check recent changelogs in stable and announcements within the
+      documentation to see if newly introduced features are documented properly.
+
+3.  **Evaluate and Record Findings:**
+    - Determine if these features are adequately covered in the docs. They do
+      not need to be documented word for word, but major features that customers
+      should care about probably should have an article.
+    - Append your findings to the `audit-results-[YYYY-MM-DD].md` file,
+      providing a brief description of the feature and where it should be
+      documented.
+
+## Phase 3: Technical Writer Implementation
+
+**Role:** The technical writer handles input from both the editor and the
+software engineer, makes appropriate decisions about what to change, and
+implements the approved changes.
+
+### Steps
+
+1.  **Review Audit Results:**
+    - Read `audit-results-[YYYY-MM-DD].md` to understand all identified issues,
+      undocumented features, and recommendations from both the Editor and
+      Software Engineer phases.
+
+2.  **Make Decisions and Log Reasoning:**
+    - Create or update an implementation log (e.g.,
+      `audit-implementation-log-[YYYY-MM-DD].md`).
+    - Make sure the logs are updated for all steps, documenting your reasoning
+      for each recommendation (why it was accepted, modified, or rejected). This
+      is required for a final check by a human in the PR.
+
+3.  **Implement Changes:**
+    - For each approved recommendation:
+      - Read the target documentation file.
+      - Apply the recommended change using the `replace` tool. Pay close
+        attention to `old_string` for exact matches, including whitespace and
+        newlines. For multiple occurrences of the same simple string (e.g.,
+        "e.g."), use `allow_multiple: true`.
+      - **String replacement safeguards:** When applying these fixes across the
+        docset, you must verify the following:
+        - **Preserve Code Blocks:** Explicitly verify that no code blocks,
+          inline code snippets, terminal commands, or file paths have been
+          erroneously capitalized or modified.
+        - **Preserve Literal Strings:** Never alter the wording of literal error
+          messages, UI quotes, or system logs. For example, if a style rule says
+          to remove the word "please", you must NOT remove it if it appears
+          inside a quoted error message (e.g.,
+          `Error: Please contact your administrator`).
+        - **Verify Sentence Casing:** When removing filler words (like "please")
+          from the beginning of a sentence or list item, always verify that the
+          new first word of the sentence is properly capitalized.
+      - For structural changes (e.g., adding an overview paragraph), use
+        `replace` or `write_file` as appropriate.
+      - For broken links, determine the correct new path or update the link
+        text.
+      - For creating new files (e.g., `docs/get-started.md` to fix a broken
+        link, or a new feature article), use `write_file`.
+
+4.  **Execute Auto-Generation Scripts:**
+    - Some documentation pages are auto-generated from the codebase and should
+      be updated using npm scripts rather than manual edits. After implementing
+      manual changes (especially if you edited settings or configurations based
+      on SWE recommendations), ensure you run:
+      - `npm run docs:settings` to generate/update the configuration reference.
+      - `npm run docs:keybindings` to generate/update the keybindings reference.
+
+5.  **Format Code:**
+    - **Dependencies:** If `npm run format` fails, it may be necessary to run
+      `npm install` first to ensure all formatting dependencies are available.
+    - After all changes have been implemented, run `npm run format` to ensure
+      consistent formatting across the project.

.gemini/skills/review-duplication/SKILL.md

@@ -0,0 +1,69 @@
+---
+name: review-duplication
+description: Use this skill during code reviews to proactively investigate the codebase for duplicated functionality, reinvented wheels, or failure to reuse existing project best practices and shared utilities.
+---
+
+# Review Duplication
+
+## Overview
+
+This skill provides a structured workflow for investigating a codebase during a code review to identify duplicated logic, reinvented utilities, and missed opportunities to reuse established patterns. By executing this workflow, you ensure that new code integrates seamlessly with the existing project architecture.
+
+## Workflow: Investigating for Duplication
+
+When reviewing code, perform the following steps before finalizing your review:
+
+### 1. Extract Core Logic
+Analyze the new code to identify the core algorithms, utility functions, generic data structures, or UI components being introduced. Look beyond the specific business logic to see the underlying mechanics.
+
+### 2. Hypothesize Existing Locations & Trace Dependencies
+Think about where this type of code *would* live if it already existed in the project. Provide absolute paths from the repo root to disambiguate.
+- **Utilities:** `packages/core/src/utils/`, `packages/cli/src/utils/`
+- **UI Components:** `packages/cli/src/ui/components/`, `packages/cli/src/ui/`
+- **Services:** `packages/core/src/services/`, `packages/cli/src/services/`
+- **Configuration:** `packages/core/src/config/`, `packages/cli/src/config/`
+- **Core Logic:** Call out `packages/core/` if functionality does not appear React UI specific.
+
+**Trace Third-Party Dependencies:** If the PR introduces a new import for a utility library (e.g., `lodash.merge`, `date-fns`), trace how and where the project currently uses that library. There is likely an existing wrapper or shared utility.
+
+**Check Package Files:** Before flagging a custom implementation of a complex algorithm, check `package.json` to see if a standard library (like `lodash` or `uuid`) is already installed that provides this functionality.
+
+### 3. Investigate the Codebase (Sub-Agent Delegation)
+Delegate the heavy lifting of codebase investigation to specialized sub-agents. They are optimized to perform deep searches and semantic mapping without bloating your session history.
+
+To ensure a comprehensive review, you MUST formulate highly specific objectives for the sub-agents, providing them with the "scents" you discovered in Step 1.
+
+- **Codebase Investigator:** Use the `codebase_investigator` as your primary researcher. When delegating, formulate an objective that asks specific, investigative questions about the codebase, explicitly including these search vectors:
+  - **Structural Similarity:** Ask if existing code uses the same underlying APIs (e.g., "Does any existing code use `Intl.DateTimeFormat` or `setTimeout` for similar purposes?").
+  - **Naming Conventions:** Ask if there are existing symbols with similar naming patterns (e.g., "Are there existing symbols with naming patterns like `*Format*` or `*Debounce*`?").
+  - **Comments & Documentation:** Ask if keywords from the PR's comments or JSDoc exist in describing similar behavior elsewhere.
+  - **Architectural Fit:** Ask where this type of logic is currently centralized (e.g., "Where is centralized date formatting logic located?").
+  - **Refactoring Guidance:** Crucially, ask the sub-agent to explain *how* the new code could be refactored to use any existing logic it finds.
+- **Generalist Agent:** Use the `generalist` for detailed, turn-intensive comparisons. For example: "Review the implementation of `MyNewComponent` in the PR and compare it semantically against all components in `packages/ui/src`. Are there any existing components that could be extended or used instead?"
+- **Retain Fast Path for Simple Searches:** For extremely simple, unambiguous checks (e.g., "Does `package.json` include `lodash`?"), perform a direct search to save time. Default to delegation for any open-ended "investigations."
+
+### 4. Evaluate Best Practices
+Check if the new code aligns with the project's established conventions.
+- **Error Handling:** Does it use the project's standard error classes or logging mechanisms?
+- **State Management:** Does it bypass established stores or contexts?
+- **Styling:** Does it hardcode colors or spacing instead of using theme variables?
+If the PR introduces a new pattern, compare it against the documented standards and explicitly confirm if an existing project pattern should have been used instead.
+
+### 5. Formulate Constructive Feedback
+If you discover that the PR duplicates existing functionality or ignores a best practice:
+- Provide a clear review comment.
+- **Identify the Source:** Explicitly mention the absolute or project-relative file path and the specific symbol (function, component, class) that should be reused.
+- **Implementation Guidance:** Provide a brief code snippet or a clear explanation showing **how** to integrate the existing code to fulfill the task's requirements.
+- **Explain the Value:** Briefly explain why reusing the existing code is beneficial (e.g., maintainability, consistency, built-in edge case handling).
+
+Example comment:
+> "It looks like this PR introduces a new `formatDate` utility. We already have a robust, tested `formatDate` function in `src/utils/dateHelpers.ts`. 
+>
+> You can replace your implementation by importing it like this:
+> ```typescript
+> import { formatDate } from '../utils/dateHelpers';
+> 
+> // Then use it here:
+> const displayDate = formatDate(userDate, 'MMM Do, YYYY');
+> ```
+> Reusing this ensures that the date formatting remains consistent with the rest of the application and handles timezone conversions correctly."

.geminiignore

@@ -0,0 +1 @@
+packages/core/src/services/scripts/*.exe

.github/ISSUE_TEMPLATE/website_issue.yml

@@ -1,7 +1,9 @@
 name: 'Website issue'
 description: 'Report an issue with the Gemini CLI Website and Gemini CLI Extensions Gallery'
+title: 'GeminiCLI.com Feedback: [ISSUE]'
 labels:
   - 'area/extensions'
+  - 'area/documentation'
 body:
   - type: 'markdown'
     attributes:

.github/actions/publish-release/action.yml

@@ -175,7 +175,9 @@ runs:
           --dry-run="${INPUTS_DRY_RUN}" \
           --workspace="${INPUTS_CORE_PACKAGE_NAME}" \
           --no-tag
-        npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} false --silent
+        if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
+          npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} false
+        fi
 
     - name: '🔗 Install latest core package'
       working-directory: '${{ inputs.working-directory }}'
@@ -221,7 +223,9 @@ runs:
           --dry-run="${INPUTS_DRY_RUN}" \
           --workspace="${INPUTS_CLI_PACKAGE_NAME}" \
           --no-tag
-        npm dist-tag rm ${INPUTS_CLI_PACKAGE_NAME} false --silent
+        if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
+          npm dist-tag rm ${INPUTS_CLI_PACKAGE_NAME} false
+        fi
 
     - name: 'Get a2a-server Token'
       uses: './.github/actions/npm-auth-token'
@@ -246,7 +250,9 @@ runs:
           --dry-run="${INPUTS_DRY_RUN}" \
           --workspace="${INPUTS_A2A_PACKAGE_NAME}" \
           --no-tag
-        npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} false --silent
+          if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
+            npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} false
+          fi
 
     - name: '🔬 Verify NPM release by version'
       uses: './.github/actions/verify-release'
@@ -285,8 +291,25 @@ runs:
         INPUTS_PREVIOUS_TAG: '${{ inputs.previous-tag }}'
       shell: 'bash'
       run: |
+        rm -f gemini-cli-bundle.zip
+        (cd bundle && chmod +x gemini.js && zip -r ../gemini-cli-bundle.zip .)
+
+        echo "Testing the generated bundle archive..."
+        rm -rf test-bundle
+        mkdir -p test-bundle
+        unzip -q gemini-cli-bundle.zip -d test-bundle
+
+        # Verify it runs and outputs a version
+        BUNDLE_VERSION=$(node test-bundle/gemini.js --version | xargs)
+        echo "Bundle version output: ${BUNDLE_VERSION}"
+        if [[ -z "${BUNDLE_VERSION}" ]]; then
+          echo "Error: Bundle failed to execute or return version."
+          exit 1
+        fi
+        rm -rf test-bundle
+
         gh release create "${INPUTS_RELEASE_TAG}" \
-          bundle/gemini.js \
+          gemini-cli-bundle.zip \
           --target "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}" \
           --title "Release ${INPUTS_RELEASE_TAG}" \
           --notes-start-tag "${INPUTS_PREVIOUS_TAG}" \

.github/actions/push-sandbox/action.yml

@@ -34,7 +34,7 @@ runs:
         JSON_INPUTS: '${{ toJSON(inputs) }}'
       run: 'echo "$JSON_INPUTS"'
     - name: 'Checkout'
-      uses: 'actions/checkout@v4'
+      uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
       with:
         ref: '${{ inputs.github-sha }}'
         fetch-depth: 0
@@ -45,11 +45,11 @@ runs:
       shell: 'bash'
       run: 'npm run build'
     - name: 'Set up QEMU'
-      uses: 'docker/setup-qemu-action@v3'
+      uses: 'docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130' # ratchet:docker/setup-qemu-action@v3
     - name: 'Set up Docker Buildx'
-      uses: 'docker/setup-buildx-action@v3'
+      uses: 'docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f' # ratchet:docker/setup-buildx-action@v3
     - name: 'Log in to GitHub Container Registry'
-      uses: 'docker/login-action@v3'
+      uses: 'docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9' # ratchet:docker/login-action@v3
       with:
         registry: 'docker.io'
         username: '${{ inputs.dockerhub-username }}'

.github/actions/run-tests/action.yml

@@ -18,6 +18,13 @@ runs:
       env:
         JSON_INPUTS: '${{ toJSON(inputs) }}'
       run: 'echo "$JSON_INPUTS"'
+    - name: 'Install system dependencies'
+      if: "runner.os == 'Linux'"
+      run: |
+        sudo apt-get update -qq && sudo DEBIAN_FRONTEND=noninteractive apt-get install -y -qq bubblewrap
+        # Ubuntu 24.04+ requires this to allow bwrap to function in CI
+        sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 || true
+      shell: 'bash'
     - name: 'Run Tests'
       env:
         GEMINI_API_KEY: '${{ inputs.gemini_api_key }}'

.github/actions/verify-release/action.yml

@@ -36,7 +36,7 @@ runs:
       run: 'echo "$JSON_INPUTS"'
 
     - name: 'setup node'
-      uses: 'actions/setup-node@v4'
+      uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
       with:
         node-version: '20'
 

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

@@ -347,6 +347,36 @@ async function run() {
           });
         }
       }
+
+      // Remove status/need-triage from maintainer-only issues since they
+      // don't need community triage. We always attempt removal rather than
+      // checking the (potentially stale) label snapshot, because the
+      // issue-opened-labeler workflow runs concurrently and may add the
+      // label after our snapshot was taken.
+      if (isDryRun) {
+        console.log(
+          `[DRY RUN] Would remove status/need-triage from ${issueKey}`,
+        );
+      } else {
+        try {
+          await octokit.rest.issues.removeLabel({
+            owner: issueInfo.owner,
+            repo: issueInfo.repo,
+            issue_number: issueInfo.number,
+            name: 'status/need-triage',
+          });
+          console.log(`Removed status/need-triage from ${issueKey}`);
+        } catch (removeError) {
+          // 404 means the label wasn't present — that's fine.
+          if (removeError.status === 404) {
+            console.log(
+              `status/need-triage not present on ${issueKey}, skipping.`,
+            );
+          } else {
+            throw removeError;
+          }
+        }
+      }
     } catch (error) {
       console.error(`Error processing label for ${issueKey}: ${error.message}`);
     }

.github/workflows/agent-session-drift-check.yml

@@ -0,0 +1,132 @@
+# yaml-language-server: $schema=https://json.schemastore.org/github-workflow.json
+
+name: 'Agent Session Drift Check'
+
+on:
+  pull_request:
+    branches:
+      - 'main'
+      - 'release/**'
+    paths:
+      - 'packages/cli/src/nonInteractiveCli.ts'
+      - 'packages/cli/src/nonInteractiveCliAgentSession.ts'
+
+concurrency:
+  group: '${{ github.workflow }}-${{ github.head_ref || github.ref }}'
+  cancel-in-progress: true
+
+jobs:
+  check-drift:
+    name: 'Check Agent Session Drift'
+    runs-on: 'ubuntu-latest'
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    permissions:
+      contents: 'read'
+      pull-requests: 'write'
+    steps:
+      - name: 'Detect drift and comment'
+        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea' # ratchet:actions/github-script@v8
+        with:
+          script: |-
+            // === Pair configuration — append here to cover more pairs ===
+            const PAIRS = [
+              {
+                legacy: 'packages/cli/src/nonInteractiveCli.ts',
+                session: 'packages/cli/src/nonInteractiveCliAgentSession.ts',
+                label: 'non-interactive CLI',
+              },
+              // Future pairs can be added here. Remember to also add both
+              // paths to the `paths:` filter at the top of this workflow.
+              // Example:
+              // {
+              //   legacy: 'packages/core/src/agents/local-invocation.ts',
+              //   session: 'packages/core/src/agents/local-session-invocation.ts',
+              //   label: 'local subagent invocation',
+              // },
+            ];
+            // ============================================================
+
+            const prNumber = context.payload.pull_request.number;
+            const { owner, repo } = context.repo;
+
+            // Use the API to list changed files — no checkout/git diff needed.
+            const files = await github.paginate(github.rest.pulls.listFiles, {
+              owner,
+              repo,
+              pull_number: prNumber,
+              per_page: 100,
+            });
+            const changed = new Set(files.map((f) => f.filename));
+
+            const warnings = [];
+            for (const { legacy, session, label } of PAIRS) {
+              const legacyChanged = changed.has(legacy);
+              const sessionChanged = changed.has(session);
+              if (legacyChanged && !sessionChanged) {
+                warnings.push(
+                  `**${label}**: \`${legacy}\` was modified but \`${session}\` was not.`,
+                );
+              } else if (!legacyChanged && sessionChanged) {
+                warnings.push(
+                  `**${label}**: \`${session}\` was modified but \`${legacy}\` was not.`,
+                );
+              }
+            }
+
+            const MARKER = '<!-- agent-session-drift-check -->';
+
+            // Look up our existing drift comment (for upsert/cleanup).
+            const comments = await github.paginate(github.rest.issues.listComments, {
+              owner,
+              repo,
+              issue_number: prNumber,
+              per_page: 100,
+            });
+            const existing = comments.find(
+              (c) => c.user?.type === 'Bot' && c.body?.includes(MARKER),
+            );
+
+            if (warnings.length === 0) {
+              core.info('No drift detected.');
+              // If drift was previously flagged and is now resolved, remove the comment.
+              if (existing) {
+                await github.rest.issues.deleteComment({
+                  owner,
+                  repo,
+                  comment_id: existing.id,
+                });
+                core.info(`Deleted stale drift comment ${existing.id}.`);
+              }
+              return;
+            }
+
+            const body = [
+              MARKER,
+              '### ⚠️ Invocation Drift Warning',
+              '',
+              'The following file pairs should generally be kept in sync during the AgentSession migration:',
+              '',
+              ...warnings.map((w) => `- ${w}`),
+              '',
+              'If this is intentional (e.g., a bug fix specific to one implementation), you can ignore this comment.',
+              '',
+              '_This check will be removed once the legacy implementations are deleted._',
+            ].join('\n');
+
+            if (existing) {
+              core.info(`Updating existing drift comment ${existing.id}.`);
+              await github.rest.issues.updateComment({
+                owner,
+                repo,
+                comment_id: existing.id,
+                body,
+              });
+            } else {
+              core.info('Creating new drift comment.');
+              await github.rest.issues.createComment({
+                owner,
+                repo,
+                issue_number: prNumber,
+                body,
+              });
+            }

.github/workflows/chained_e2e.yml

@@ -183,7 +183,7 @@ jobs:
     needs:
       - 'merge_queue_skipper'
       - 'parse_run_context'
-    runs-on: 'macos-latest'
+    runs-on: 'macos-latest-large'
     if: |
       github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
     steps:
@@ -334,8 +334,22 @@ jobs:
         if: "${{ steps.check_evals.outputs.should_run == 'true' }}"
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GEMINI_MODEL: 'gemini-3-pro-preview'
+          # Only run always passes behavioral tests.
+          EVAL_SUITE_TYPE: 'behavioral'
+          # Disable Vitest internal retries to avoid double-retrying;
+          # custom retry logic is handled in evals/test-helper.ts
+          VITEST_RETRY: 0
         run: 'npm run test:always_passing_evals'
 
+      - name: 'Upload Reliability Logs'
+        if: "always() && steps.check_evals.outputs.should_run == 'true'"
+        uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
+        with:
+          name: 'eval-logs-${{ github.run_id }}-${{ github.run_attempt }}'
+          path: 'evals/logs/api-reliability.jsonl'
+          retention-days: 7
+
   e2e:
     name: 'E2E'
     if: |

.github/workflows/ci.yml

@@ -67,7 +67,7 @@ jobs:
           cache: 'npm'
 
       - name: 'Cache Linters'
-        uses: 'actions/cache@v4'
+        uses: 'actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830' # ratchet:actions/cache@v4
         with:
           path: '${{ env.GEMINI_LINT_TEMP_DIR }}'
           key: "${{ runner.os }}-${{ runner.arch }}-linters-${{ hashFiles('scripts/lint.js') }}"
@@ -76,7 +76,7 @@ jobs:
         run: 'npm ci'
 
       - name: 'Cache ESLint'
-        uses: 'actions/cache@v4'
+        uses: 'actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830' # ratchet:actions/cache@v4
         with:
           path: '.eslintcache'
           key: "${{ runner.os }}-eslint-${{ hashFiles('package-lock.json', 'eslint.config.js') }}"
@@ -102,6 +102,12 @@ jobs:
       - name: 'Run yamllint'
         run: 'node scripts/lint.js --yamllint'
 
+      - name: 'Build project for typecheck'
+        run: 'npm run build'
+
+      - name: 'Run typecheck'
+        run: 'npm run typecheck'
+
       - name: 'Run Prettier'
         run: 'node scripts/lint.js --prettier'
 
@@ -114,6 +120,9 @@ jobs:
       - name: 'Run sensitive keyword linter'
         run: 'node scripts/lint.js --sensitive-keywords'
 
+      - name: 'Run GitHub Actions pinning linter'
+        run: 'node scripts/lint.js --check-github-actions-pinning'
+
   link_checker:
     name: 'Link Checker'
     runs-on: 'ubuntu-latest'
@@ -158,6 +167,12 @@ jobs:
       - name: 'Build project'
         run: 'npm run build'
 
+      - name: 'Install system dependencies'
+        run: |
+          sudo apt-get update -qq && sudo DEBIAN_FRONTEND=noninteractive apt-get install -y -qq bubblewrap
+          # Ubuntu 24.04+ requires this to allow bwrap to function in CI
+          sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 || true
+
       - name: 'Install dependencies for testing'
         run: 'npm ci'
 
@@ -166,10 +181,10 @@ jobs:
           NO_COLOR: true
         run: |
           if [[ "${{ matrix.shard }}" == "cli" ]]; then
-            npm run test:ci --workspace @google/gemini-cli
+            npm run test:ci --workspace "@google/gemini-cli"
           else
             # Explicitly list non-cli packages to ensure they are sharded correctly
-            npm run test:ci --workspace @google/gemini-cli-core --workspace @google/gemini-cli-a2a-server --workspace gemini-cli-vscode-ide-companion --workspace @google/gemini-cli-test-utils --if-present
+            npm run test:ci --workspace "@google/gemini-cli-core" --workspace "@google/gemini-cli-a2a-server" --workspace "gemini-cli-vscode-ide-companion" --workspace "@google/gemini-cli-test-utils" --if-present -- --coverage.enabled=false
             npm run test:scripts
           fi
 
@@ -215,7 +230,7 @@ jobs:
 
   test_mac:
     name: 'Test (Mac) - ${{ matrix.node-version }}, ${{ matrix.shard }}'
-    runs-on: 'macos-latest'
+    runs-on: 'macos-latest-large'
     needs:
       - 'merge_queue_skipper'
     if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
@@ -254,10 +269,10 @@ jobs:
           NO_COLOR: true
         run: |
           if [[ "${{ matrix.shard }}" == "cli" ]]; then
-            npm run test:ci --workspace @google/gemini-cli -- --coverage.enabled=false
+            npm run test:ci --workspace "@google/gemini-cli" -- --coverage.enabled=false
           else
             # Explicitly list non-cli packages to ensure they are sharded correctly
-            npm run test:ci --workspace @google/gemini-cli-core --workspace @google/gemini-cli-a2a-server --workspace gemini-cli-vscode-ide-companion --workspace @google/gemini-cli-test-utils --if-present -- --coverage.enabled=false
+            npm run test:ci --workspace "@google/gemini-cli-core" --workspace "@google/gemini-cli-a2a-server" --workspace "gemini-cli-vscode-ide-companion" --workspace "@google/gemini-cli-test-utils" --if-present -- --coverage.enabled=false
             npm run test:scripts
           fi
 
@@ -420,11 +435,14 @@ jobs:
           NODE_ENV: 'test'
         run: |
           if ("${{ matrix.shard }}" -eq "cli") {
-            npm run test:ci --workspace @google/gemini-cli -- --coverage.enabled=false
+            npm run test:ci --workspace "@google/gemini-cli" -- --coverage.enabled=false
+            if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
           } else {
             # Explicitly list non-cli packages to ensure they are sharded correctly
-            npm run test:ci --workspace @google/gemini-cli-core --workspace @google/gemini-cli-a2a-server --workspace gemini-cli-vscode-ide-companion --workspace @google/gemini-cli-test-utils --if-present -- --coverage.enabled=false
+            npm run test:ci --workspace "@google/gemini-cli-core" --workspace "@google/gemini-cli-a2a-server" --workspace "gemini-cli-vscode-ide-companion" --workspace "@google/gemini-cli-test-utils" --if-present -- --coverage.enabled=false
+            if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
             npm run test:scripts
+            if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
           }
         shell: 'pwsh'
 

.github/workflows/deflake.yml

@@ -77,7 +77,7 @@ jobs:
 
   deflake_e2e_mac:
     name: 'E2E Test (macOS)'
-    runs-on: 'macos-latest'
+    runs-on: 'macos-latest-large'
     if: "github.repository == 'google-gemini/gemini-cli'"
     steps:
       - name: 'Checkout'

.github/workflows/docs-audit.yml

@@ -0,0 +1,62 @@
+name: 'Automated Documentation Audit'
+
+on:
+  schedule:
+    # Runs every Monday at 00:00 UTC
+    - cron: '0 0 * * MON'
+  workflow_dispatch:
+
+jobs:
+  audit-docs:
+    runs-on: 'ubuntu-latest'
+    permissions:
+      contents: 'write'
+      pull-requests: 'write'
+
+    steps:
+      - name: 'Checkout repository'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5'
+        with:
+          fetch-depth: 0
+          ref: 'main'
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020'
+        with:
+          node-version: '20'
+
+      - name: 'Run Docs Audit with Gemini'
+        id: 'run_gemini'
+        uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31'
+        with:
+          gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
+          prompt: |
+            Activate the 'docs-writer' skill.
+
+            **Task:** Execute the docs audit procedure, as defined in your 'docs-auditing.md' reference.
+            Provide a detailed summary of the changes you make.
+
+      - name: 'Get current date'
+        id: 'date'
+        run: |
+          echo "date=$(date +'%Y-%m-%d')" >> "$GITHUB_OUTPUT"
+
+      - name: 'Create Pull Request with Audit Results'
+        uses: 'peter-evans/create-pull-request@c5a7806660adbe173f04e3e038b0ccdcd758773c'
+        with:
+          token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
+          commit-message: 'docs: weekly audit results for ${{ github.run_id }}'
+          title: 'Docs audit: ${{ steps.date.outputs.date }}'
+          body: |
+            This PR contains the auto-generated documentation audit for the week. It includes a new `audit-results-*.md` file with findings and any direct fixes applied by the agent.
+
+            ### Audit Summary:
+            ${{ steps.run_gemini.outputs.summary || 'No summary provided.' }}
+
+            Please review the suggestions and merge.
+
+            Related to #25152
+          branch: 'docs-audit-${{ github.run_id }}'
+          base: 'main'
+          team-reviewers: 'gemini-cli-docs, gemini-cli-maintainers'
+          delete-branch: true

.github/workflows/eval-pr.yml

@@ -0,0 +1,209 @@
+name: 'Evals: PR Evaluation & Regression'
+
+on:
+  pull_request_target:
+    types: ['opened', 'synchronize', 'reopened', 'ready_for_review']
+    paths:
+      - 'packages/core/src/prompts/**'
+      - 'packages/core/src/tools/**'
+      - 'packages/core/src/agents/**'
+      - 'evals/**'
+      - '!**/*.test.ts'
+      - '!**/*.test.tsx'
+  workflow_dispatch:
+
+# Prevents multiple runs for the same PR simultaneously (saves tokens)
+concurrency:
+  group: '${{ github.workflow }}-${{ github.head_ref || github.ref }}'
+  cancel-in-progress: true
+
+permissions:
+  pull-requests: 'write'
+  contents: 'read'
+  actions: 'read'
+
+jobs:
+  detect-changes:
+    name: 'Detect Steering Changes'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    # Security: pull_request_target allows secrets, so we must gate carefully.
+    # Detection should not run code from the fork.
+    if: "github.repository == 'google-gemini/gemini-cli' && github.event.pull_request.draft == false"
+    outputs:
+      SHOULD_RUN: '${{ steps.detect.outputs.SHOULD_RUN }}'
+      STEERING_DETECTED: '${{ steps.detect.outputs.STEERING_DETECTED }}'
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
+        with:
+          # Check out the trusted code from main for detection
+          fetch-depth: 0
+
+      - name: 'Detect Steering Changes'
+        id: 'detect'
+        env:
+          # Use the PR's head SHA for comparison without checking it out
+          PR_HEAD_SHA: '${{ github.event.pull_request.head.sha }}'
+        run: |
+          # Fetch the fork's PR branch for analysis
+          git fetch origin pull/${{ github.event.pull_request.number }}/head:pr-head
+
+          # Run the trusted script from main
+          SHOULD_RUN=$(node scripts/changed_prompt.js)
+          STEERING_DETECTED=$(node scripts/changed_prompt.js --steering-only)
+          echo "SHOULD_RUN=$SHOULD_RUN" >> "$GITHUB_OUTPUT"
+          echo "STEERING_DETECTED=$STEERING_DETECTED" >> "$GITHUB_OUTPUT"
+
+      - name: 'Notify Approval Required'
+        if: "steps.detect.outputs.SHOULD_RUN == 'true'"
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: |
+          RUN_URL="https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"
+          COMMENT_BODY="### 🛑 Action Required: Evaluation Approval
+
+          Steering changes have been detected in this PR. To prevent regressions, a maintainer must approve the evaluation run before this PR can be merged.
+
+          **Maintainers:**
+          1. Go to the [**Workflow Run Summary**]($RUN_URL).
+          2. Click the yellow **'Review deployments'** button.
+          3. Select the **'eval-gate'** environment and click **'Approve'**.
+
+          Once approved, the evaluation results will be posted here automatically.
+
+          <!-- eval-approval-notification -->"
+
+          # Check if comment already exists to avoid spamming
+          COMMENT_ID=$(gh pr view ${{ github.event.pull_request.number }} --json comments --jq '.comments[] | select(.body | contains("<!-- eval-approval-notification -->")) | .url' | grep -oE "[0-9]+$" | head -n 1)
+
+          if [ -z "$COMMENT_ID" ]; then
+            gh pr comment ${{ github.event.pull_request.number }} --body "$COMMENT_BODY"
+          else
+            echo "Updating existing notification comment $COMMENT_ID..."
+            gh api -X PATCH "repos/${{ github.repository }}/issues/comments/$COMMENT_ID" -F body="$COMMENT_BODY"
+          fi
+
+  pr-evaluation:
+    name: 'Evaluate Steering & Regressions'
+    needs: 'detect-changes'
+    if: "needs.detect-changes.outputs.SHOULD_RUN == 'true'"
+    # Manual approval gate via environment
+    environment: 'eval-gate'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    env:
+      # CENTRALIZED MODEL LIST
+      MODEL_LIST: 'gemini-3-flash-preview'
+
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
+        with:
+          # Check out the fork's PR code for the actual evaluation
+          # This only runs AFTER manual approval
+          ref: '${{ github.event.pull_request.head.sha }}'
+          fetch-depth: 0
+
+      - name: 'Remove Approval Notification'
+        # Run even if other steps fail, to ensure we clean up the "Action Required" message
+        if: 'always()'
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+          PR_NUMBER: '${{ github.event.pull_request.number }}'
+        run: |
+          echo "Debug: PR_NUMBER is '$PR_NUMBER'"
+          # Search for the notification comment by its hidden tag
+          COMMENT_ID=$(gh pr view "$PR_NUMBER" --json comments --jq '.comments[] | select(.body | contains("<!-- eval-approval-notification -->")) | .url' | grep -oE "[0-9]+$" | head -n 1)
+          if [ -n "$COMMENT_ID" ]; then
+            echo "Removing notification comment $COMMENT_ID now that run is approved..."
+            gh api -X DELETE "repos/${{ github.repository }}/issues/comments/$COMMENT_ID"
+          fi
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4.4.0
+        with:
+          node-version-file: '.nvmrc'
+          cache: 'npm'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Build project'
+        run: 'npm run build'
+
+      - name: 'Analyze PR Content (Guidance)'
+        if: "needs.detect-changes.outputs.STEERING_DETECTED == 'true'"
+        id: 'analysis'
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: |
+          # Check for behavioral eval changes
+          EVAL_CHANGES=$(git diff --name-only origin/${{ github.base_ref }}...HEAD | grep "^evals/" || true)
+          if [ -z "$EVAL_CHANGES" ]; then
+            echo "MISSING_EVALS=true" >> "$GITHUB_OUTPUT"
+          fi
+
+          # Check if user is a maintainer
+          USER_PERMISSION=$(gh api repos/${{ github.repository }}/collaborators/${{ github.actor }}/permission --jq '.permission')
+          if [[ "$USER_PERMISSION" == "admin" || "$USER_PERMISSION" == "write" ]]; then
+            echo "IS_MAINTAINER=true" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: 'Execute Regression Check'
+        env:
+          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+          MODEL_LIST: '${{ env.MODEL_LIST }}'
+        run: |
+          # Run the regression check loop. The script saves the report to a file.
+          node scripts/run_eval_regression.js
+
+          # Use the generated report file if it exists
+          if [[ -f eval_regression_report.md ]]; then
+            echo "REPORT_FILE=eval_regression_report.md" >> "$GITHUB_ENV"
+          fi
+
+      - name: 'Post or Update PR Comment'
+        if: "always() && (needs.detect-changes.outputs.STEERING_DETECTED == 'true' || env.REPORT_FILE != '')"
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: |
+          # 1. Build the full comment body
+          {
+            if [[ -f eval_regression_report.md ]]; then
+              cat eval_regression_report.md
+              echo ""
+            fi
+
+            if [[ "${{ needs.detect-changes.outputs.STEERING_DETECTED }}" == "true" ]]; then
+              echo "### 🧠 Model Steering Guidance"
+              echo ""
+              echo "This PR modifies files that affect the model's behavior (prompts, tools, or instructions)."
+              echo ""
+
+              if [[ "${{ steps.analysis.outputs.MISSING_EVALS }}" == "true" ]]; then
+                echo "- ⚠️ **Consider adding Evals:** No behavioral evaluations (\`evals/*.eval.ts\`) were added or updated in this PR. Consider [adding a test case](https://github.com/google-gemini/gemini-cli/blob/main/evals/README.md#creating-an-evaluation) to verify the new behavior and prevent regressions."
+              fi
+
+              if [[ "${{ steps.analysis.outputs.IS_MAINTAINER }}" == "true" ]]; then
+                echo "- 🚀 **Maintainer Reminder:** Please ensure that these changes do not regress results on benchmark evals before merging."
+              fi
+            fi
+
+            echo ""
+            echo "---"
+            echo "*This is an automated guidance message triggered by steering logic signatures.*"
+            echo "<!-- eval-pr-report -->"
+          } > full_comment.md
+
+          # 2. Find if a comment with our unique tag already exists
+          # We extract the numeric ID from the URL to ensure compatibility with the REST API
+          COMMENT_ID=$(gh pr view ${{ github.event.pull_request.number }} --json comments --jq '.comments[] | select(.body | contains("<!-- eval-pr-report -->")) | .url' | grep -oE "[0-9]+$" | head -n 1)
+
+          # 3. Update or Create the comment
+          if [ -n "$COMMENT_ID" ]; then
+            echo "Updating existing comment $COMMENT_ID via API..."
+            gh api -X PATCH "repos/${{ github.repository }}/issues/comments/$COMMENT_ID" -F body=@full_comment.md
+          else
+            echo "Creating new PR comment..."
+            gh pr comment ${{ github.event.pull_request.number }} --body-file full_comment.md
+          fi

.github/workflows/evals-nightly.yml

@@ -5,10 +5,18 @@ on:
     - 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
+      suite_type:
+        description: 'Suite type to run'
+        type: 'choice'
+        options:
+          - 'behavioral'
+          - 'component-level'
+          - 'hero-scenario'
+        default: 'behavioral'
+      suite_name:
+        description: 'Specific suite name to run'
+        required: false
+        type: 'string'
       test_name_pattern:
         description: 'Test name pattern or file name'
         required: false
@@ -59,8 +67,13 @@ jobs:
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
           GEMINI_MODEL: '${{ matrix.model }}'
-          RUN_EVALS: "${{ github.event.inputs.run_all != 'false' }}"
+          RUN_EVALS: 'true'
+          EVAL_SUITE_TYPE: "${{ github.event.inputs.suite_type || 'behavioral' }}"
+          EVAL_SUITE_NAME: '${{ github.event.inputs.suite_name }}'
           TEST_NAME_PATTERN: '${{ github.event.inputs.test_name_pattern }}'
+          # Disable Vitest internal retries to avoid double-retrying;
+          # custom retry logic is handled in evals/test-helper.ts
+          VITEST_RETRY: 0
         run: |
           CMD="npm run test:all_evals"
           PATTERN="${TEST_NAME_PATTERN}"

.github/workflows/gemini-scheduled-stale-issue-closer.yml

@@ -28,14 +28,14 @@ jobs:
     steps:
       - name: 'Generate GitHub App Token'
         id: 'generate_token'
-        uses: 'actions/create-github-app-token@v2'
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
         with:
           app-id: '${{ secrets.APP_ID }}'
           private-key: '${{ secrets.PRIVATE_KEY }}'
           permission-issues: 'write'
 
       - name: 'Process Stale Issues'
-        uses: 'actions/github-script@v7'
+        uses: 'actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b' # ratchet:actions/github-script@v7
         env:
           DRY_RUN: '${{ inputs.dry_run }}'
         with:

.github/workflows/gemini-scheduled-stale-pr-closer.yml

@@ -27,19 +27,21 @@ jobs:
           APP_ID: '${{ secrets.APP_ID }}'
         if: |-
           ${{ env.APP_ID != '' }}
-        uses: 'actions/create-github-app-token@v2'
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
         with:
           app-id: '${{ secrets.APP_ID }}'
           private-key: '${{ secrets.PRIVATE_KEY }}'
 
       - name: 'Process Stale PRs'
-        uses: 'actions/github-script@v7'
+        uses: 'actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b' # ratchet:actions/github-script@v7
         env:
           DRY_RUN: '${{ inputs.dry_run }}'
         with:
           github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
           script: |
             const dryRun = process.env.DRY_RUN === 'true';
+            const fourteenDaysAgo = new Date();
+            fourteenDaysAgo.setDate(fourteenDaysAgo.getDate() - 14);
             const thirtyDaysAgo = new Date();
             thirtyDaysAgo.setDate(thirtyDaysAgo.getDate() - 30);
 
@@ -56,48 +58,38 @@ jobs:
                 for (const m of members) maintainerLogins.add(m.login.toLowerCase());
                 core.info(`Successfully fetched ${members.length} team members from ${team_slug}`);
               } catch (e) {
-                core.warning(`Failed to fetch team members from ${team_slug}: ${e.message}`);
+                // Silently skip if permissions are insufficient; we will rely on author_association
+                core.debug(`Skipped team fetch for ${team_slug}: ${e.message}`);
               }
             }
 
-            const isGooglerCache = new Map();
-            const isGoogler = async (login) => {
-              if (isGooglerCache.has(login)) return isGooglerCache.get(login);
+            const isMaintainer = async (login, assoc) => {
+              // Reliably identify maintainers using authorAssociation (provided by GitHub)
+              // and organization membership (if available).
+              const isTeamMember = maintainerLogins.has(login.toLowerCase());
+              const isRepoMaintainer = ['OWNER', 'MEMBER', 'COLLABORATOR'].includes(assoc);
 
+              if (isTeamMember || isRepoMaintainer) return true;
+
+              // Fallback: Check if user belongs to the 'google' or 'googlers' orgs (requires permission)
               try {
-                // Check membership in 'googlers' or 'google' orgs
                 const orgs = ['googlers', 'google'];
                 for (const org of orgs) {
                   try {
-                    await github.rest.orgs.checkMembershipForUser({
-                      org: org,
-                      username: login
-                    });
-                    core.info(`User ${login} is a member of ${org} organization.`);
-                    isGooglerCache.set(login, true);
+                    await github.rest.orgs.checkMembershipForUser({ org: org, username: login });
                     return true;
                   } catch (e) {
-                    // 404 just means they aren't a member, which is fine
                     if (e.status !== 404) throw e;
                   }
                 }
               } catch (e) {
-                core.warning(`Failed to check org membership for ${login}: ${e.message}`);
+                // Gracefully ignore failures here
               }
 
-              isGooglerCache.set(login, false);
               return false;
             };
 
-            const isMaintainer = async (login, assoc) => {
-              const isTeamMember = maintainerLogins.has(login.toLowerCase());
-              const isRepoMaintainer = ['OWNER', 'MEMBER', 'COLLABORATOR'].includes(assoc);
-              if (isTeamMember || isRepoMaintainer) return true;
-
-              return await isGoogler(login);
-            };
-
-            // 2. Determine which PRs to check
+            // 2. Fetch all open PRs
             let prs = [];
             if (context.eventName === 'pull_request') {
               const { data: pr } = await github.rest.pulls.get({
@@ -118,64 +110,77 @@ jobs:
             for (const pr of prs) {
               const maintainerPr = await isMaintainer(pr.user.login, pr.author_association);
               const isBot = pr.user.type === 'Bot' || pr.user.login.endsWith('[bot]');
+              if (maintainerPr || isBot) continue;
 
-              // Detection Logic for Linked Issues
-              // Check 1: Official GitHub "Closing Issue" link (GraphQL)
-              const linkedIssueQuery = `query($owner:String!, $repo:String!, $number:Int!) {
+              // Helper: Fetch labels and linked issues via GraphQL
+              const prDetailsQuery = `query($owner:String!, $repo:String!, $number:Int!) {
                 repository(owner:$owner, name:$repo) {
                   pullRequest(number:$number) {
-                    closingIssuesReferences(first: 1) { totalCount }
+                    closingIssuesReferences(first: 10) {
+                      nodes {
+                        number
+                        labels(first: 20) {
+                          nodes { name }
+                        }
+                      }
+                    }
                   }
                 }
               }`;
 
-              let hasClosingLink = false;
+              let linkedIssues = [];
               try {
-                const res = await github.graphql(linkedIssueQuery, {
+                const res = await github.graphql(prDetailsQuery, {
                   owner: context.repo.owner, repo: context.repo.repo, number: pr.number
                 });
-                hasClosingLink = res.repository.pullRequest.closingIssuesReferences.totalCount > 0;
-              } catch (e) {}
-
-              // Check 2: Regex for mentions (e.g., "Related to #123", "Part of #123", "#123")
-              // We check for # followed by numbers or direct URLs to issues.
-              const body = pr.body || '';
-              const mentionRegex = /(?:#|https:\/\/github\.com\/[^\/]+\/[^\/]+\/issues\/)(\d+)/i;
-              const hasMentionLink = mentionRegex.test(body);
-
-              const hasLinkedIssue = hasClosingLink || hasMentionLink;
-
-              // Logic for Closed PRs (Auto-Reopen)
-              if (pr.state === 'closed' && context.eventName === 'pull_request' && context.payload.action === 'edited') {
-                if (hasLinkedIssue) {
-                  core.info(`PR #${pr.number} now has a linked issue. Reopening.`);
-                  if (!dryRun) {
-                    await github.rest.pulls.update({
-                      owner: context.repo.owner,
-                      repo: context.repo.repo,
-                      pull_number: pr.number,
-                      state: 'open'
-                    });
-                    await github.rest.issues.createComment({
-                      owner: context.repo.owner,
-                      repo: context.repo.repo,
-                      issue_number: pr.number,
-                      body: "Thank you for linking an issue! This pull request has been automatically reopened."
-                    });
-                  }
-                }
-                continue;
+                linkedIssues = res.repository.pullRequest.closingIssuesReferences.nodes;
+              } catch (e) {
+                core.warning(`GraphQL fetch failed for PR #${pr.number}: ${e.message}`);
               }
 
-              // Logic for Open PRs (Immediate Closure)
-              if (pr.state === 'open' && !maintainerPr && !hasLinkedIssue && !isBot) {
-                core.info(`PR #${pr.number} is missing a linked issue. Closing.`);
+              // Check for mentions in body as fallback (regex)
+              const body = pr.body || '';
+              const mentionRegex = /(?:#|https:\/\/github\.com\/[^\/]+\/[^\/]+\/issues\/)(\d+)/i;
+              const matches = body.match(mentionRegex);
+              if (matches && linkedIssues.length === 0) {
+                const issueNumber = parseInt(matches[1]);
+                try {
+                  const { data: issue } = await github.rest.issues.get({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issueNumber
+                  });
+                  linkedIssues = [{ number: issueNumber, labels: { nodes: issue.labels.map(l => ({ name: l.name })) } }];
+                } catch (e) {}
+              }
+
+              // 3. Enforcement Logic
+              const prLabels = pr.labels.map(l => l.name.toLowerCase());
+              const hasHelpWanted = prLabels.includes('help wanted') ||
+                                    linkedIssues.some(issue => issue.labels.nodes.some(l => l.name.toLowerCase() === 'help wanted'));
+
+              const hasMaintainerOnly = prLabels.includes('🔒 maintainer only') ||
+                                        linkedIssues.some(issue => issue.labels.nodes.some(l => l.name.toLowerCase() === '🔒 maintainer only'));
+
+              const hasLinkedIssue = linkedIssues.length > 0;
+
+              // Closure Policy: No help-wanted label = Close after 14 days
+              if (pr.state === 'open' && !hasHelpWanted && !hasMaintainerOnly) {
+                const prCreatedAt = new Date(pr.created_at);
+
+                // We give a 14-day grace period for non-help-wanted PRs to be manually reviewed/labeled by an EM
+                if (prCreatedAt > fourteenDaysAgo) {
+                  core.info(`PR #${pr.number} is new and lacks 'help wanted'. Giving 14-day grace period for EM review.`);
+                  continue;
+                }
+
+                core.info(`PR #${pr.number} is older than 14 days and lacks 'help wanted' association. Closing.`);
                 if (!dryRun) {
                   await github.rest.issues.createComment({
                     owner: context.repo.owner,
                     repo: context.repo.repo,
                     issue_number: pr.number,
-                    body: "Hi there! Thank you for your contribution to Gemini CLI. \n\nTo improve our contribution process and better track changes, we now require all pull requests to be associated with an existing issue, as announced in our [recent discussion](https://github.com/google-gemini/gemini-cli/discussions/16706) and as detailed in our [CONTRIBUTING.md](https://github.com/google-gemini/gemini-cli/blob/main/CONTRIBUTING.md#1-link-to-an-existing-issue).\n\nThis pull request is being closed because it is not currently linked to an issue. **Once you have updated the description of this PR to link an issue (e.g., by adding `Fixes #123` or `Related to #123`), it will be automatically reopened.**\n\n**How to link an issue:**\nAdd a keyword followed by the issue number (e.g., `Fixes #123`) in the description of your pull request. For more details on supported keywords and how linking works, please refer to the [GitHub Documentation on linking pull requests to issues](https://docs.github.com/en/issues/tracking-your-work-with-issues/linking-a-pull-request-to-an-issue).\n\nThank you for your understanding and for being a part of our community!"
+                    body: "Hi there! Thank you for your interest in contributing to Gemini CLI. \n\nTo ensure we maintain high code quality and focus on our prioritized roadmap, we have updated our contribution policy (see [Discussion #17383](https://github.com/google-gemini/gemini-cli/discussions/17383)). \n\n**We only *guarantee* review and consideration of pull requests for issues that are explicitly labeled as 'help wanted'.** All other community pull requests are subject to closure after 14 days if they do not align with our current focus areas. For this reason, we strongly recommend that contributors only submit pull requests against issues explicitly labeled as **'help-wanted'**. \n\nThis pull request is being closed as it has been open for 14 days without a 'help wanted' designation. We encourage you to find and contribute to existing 'help wanted' issues in our backlog! Thank you for your understanding and for being part of our community!"
                   });
                   await github.rest.pulls.update({
                     owner: context.repo.owner,
@@ -187,27 +192,22 @@ jobs:
                 continue;
               }
 
-              // Staleness check (Scheduled runs only)
-              if (pr.state === 'open' && context.eventName !== 'pull_request') {
-                const labels = pr.labels.map(l => l.name.toLowerCase());
-                if (labels.includes('help wanted') || labels.includes('🔒 maintainer only')) continue;
+              // Also check for linked issue even if it has help wanted (redundant but safe)
+              if (pr.state === 'open' && !hasLinkedIssue) {
+                 // Already covered by hasHelpWanted check above, but good for future-proofing
+                 continue;
+              }
 
+              // 4. Staleness Check (Scheduled only)
+              if (pr.state === 'open' && context.eventName !== 'pull_request') {
                 // Skip PRs that were created less than 30 days ago - they cannot be stale yet
                 const prCreatedAt = new Date(pr.created_at);
-                if (prCreatedAt > thirtyDaysAgo) {
-                  const daysOld = Math.floor((Date.now() - prCreatedAt.getTime()) / (1000 * 60 * 60 * 24));
-                  core.info(`PR #${pr.number} was created ${daysOld} days ago. Skipping staleness check.`);
-                  continue;
-                }
+                if (prCreatedAt > thirtyDaysAgo) continue;
 
-                // Initialize lastActivity to PR creation date (not epoch) as a safety baseline.
-                // This ensures we never incorrectly mark a PR as stale due to failed activity lookups.
                 let lastActivity = new Date(pr.created_at);
                 try {
                   const reviews = await github.paginate(github.rest.pulls.listReviews, {
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    pull_number: pr.number
+                    owner: context.repo.owner, repo: context.repo.repo, pull_number: pr.number
                   });
                   for (const r of reviews) {
                     if (await isMaintainer(r.user.login, r.author_association)) {
@@ -216,9 +216,7 @@ jobs:
                     }
                   }
                   const comments = await github.paginate(github.rest.issues.listComments, {
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: pr.number
+                    owner: context.repo.owner, repo: context.repo.repo, issue_number: pr.number
                   });
                   for (const c of comments) {
                     if (await isMaintainer(c.user.login, c.author_association)) {
@@ -226,25 +224,23 @@ jobs:
                       if (d > lastActivity) lastActivity = d;
                     }
                   }
-                } catch (e) {
-                  core.warning(`Failed to fetch reviews/comments for PR #${pr.number}: ${e.message}`);
-                }
-
-                // For maintainer PRs, the PR creation itself counts as maintainer activity.
-                // (Now redundant since we initialize to pr.created_at, but kept for clarity)
-                if (maintainerPr) {
-                  const d = new Date(pr.created_at);
-                  if (d > lastActivity) lastActivity = d;
-                }
+                } catch (e) {}
 
                 if (lastActivity < thirtyDaysAgo) {
-                  core.info(`PR #${pr.number} is stale.`);
+                  const labels = pr.labels.map(l => l.name.toLowerCase());
+                  const isProtected = labels.includes('help wanted') || labels.includes('🔒 maintainer only');
+                  if (isProtected) {
+                    core.info(`PR #${pr.number} is stale but has a protected label. Skipping closure.`);
+                    continue;
+                  }
+
+                  core.info(`PR #${pr.number} is stale (no maintainer activity for 30+ days). Closing.`);
                   if (!dryRun) {
                     await github.rest.issues.createComment({
                       owner: context.repo.owner,
                       repo: context.repo.repo,
                       issue_number: pr.number,
-                      body: "Hi there! Thank you for your contribution to Gemini CLI. We really appreciate the time and effort you've put into this pull request.\n\nTo keep our backlog manageable and ensure we're focusing on current priorities, we are closing pull requests that haven't seen maintainer activity for 30 days. Currently, the team is prioritizing work associated with **🔒 maintainer only** or **help wanted** issues.\n\nIf you believe this change is still critical, please feel free to comment with updated details. Otherwise, we encourage contributors to focus on open issues labeled as **help wanted**. Thank you for your understanding!"
+                      body: "Hi there! Thank you for your contribution. To keep our backlog manageable, we are closing pull requests that haven't seen maintainer activity for 30 days. If you're still working on this, please let us know!"
                     });
                     await github.rest.pulls.update({
                       owner: context.repo.owner,

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

@@ -18,10 +18,10 @@ jobs:
     runs-on: 'ubuntu-latest'
     steps:
       - name: 'Checkout'
-        uses: 'actions/checkout@v4'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
 
       - name: 'Setup Node.js'
-        uses: 'actions/setup-node@v4'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
         with:
           node-version: '20'
           cache: 'npm'
@@ -40,10 +40,10 @@ jobs:
     runs-on: 'ubuntu-latest'
     steps:
       - name: 'Checkout'
-        uses: 'actions/checkout@v4'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
 
       - name: 'Setup Node.js'
-        uses: 'actions/setup-node@v4'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
         with:
           node-version: '20'
           cache: 'npm'

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

@@ -15,7 +15,7 @@ jobs:
       issues: 'write'
     steps:
       - name: 'Check for Parent Workstream and Apply Label'
-        uses: 'actions/github-script@v7'
+        uses: 'actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b' # ratchet:actions/github-script@v7
         with:
           script: |
             const labelToAdd = 'workstream-rollup';

.github/workflows/memory-nightly.yml

@@ -0,0 +1,33 @@
+name: 'Memory Tests: Nightly'
+
+on:
+  schedule:
+    - cron: '0 2 * * *' # Runs at 2 AM every day
+  workflow_dispatch: # Allow manual trigger
+
+permissions:
+  contents: 'read'
+
+jobs:
+  memory-test:
+    name: 'Run Memory Usage Tests'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    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: 'Run Memory Tests'
+        run: 'npm run test:memory'

.github/workflows/perf-nightly.yml

@@ -0,0 +1,33 @@
+name: 'Performance Tests: Nightly'
+
+on:
+  schedule:
+    - cron: '0 3 * * *' # Runs at 3 AM every day
+  workflow_dispatch: # Allow manual trigger
+
+permissions:
+  contents: 'read'
+
+jobs:
+  perf-test:
+    name: 'Run Performance Usage Tests'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    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: 'Run Performance Tests'
+        run: 'npm run test:perf'

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

@@ -19,7 +19,7 @@ jobs:
           APP_ID: '${{ secrets.APP_ID }}'
         if: |-
           ${{ env.APP_ID != '' }}
-        uses: 'actions/create-github-app-token@v2'
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
         with:
           app-id: '${{ secrets.APP_ID }}'
           private-key: '${{ secrets.PRIVATE_KEY }}'

.github/workflows/release-change-tags.yml

@@ -40,7 +40,7 @@ jobs:
       issues: 'write'
     steps:
       - name: 'Checkout repository'
-        uses: 'actions/checkout@v4'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
         with:
           ref: '${{ github.ref }}'
           fetch-depth: 0

.github/workflows/release-notes.yml

@@ -29,14 +29,14 @@ jobs:
       pull-requests: 'write'
     steps:
       - name: 'Checkout repository'
-        uses: 'actions/checkout@v4'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
         with:
           # The user-level skills need to be available to the workflow
           fetch-depth: 0
           ref: 'main'
 
       - name: 'Set up Node.js'
-        uses: 'actions/setup-node@v4'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
         with:
           node-version: '20'
 
@@ -86,7 +86,7 @@ jobs:
 
       - name: 'Create Pull Request'
         if: "steps.validate_version.outputs.CONTINUE == 'true'"
-        uses: 'peter-evans/create-pull-request@v6'
+        uses: 'peter-evans/create-pull-request@c5a7806660adbe173f04e3e038b0ccdcd758773c' # ratchet:peter-evans/create-pull-request@v6
         with:
           token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
           commit-message: 'docs(changelog): update for ${{ steps.release_info.outputs.VERSION }}'
@@ -95,6 +95,8 @@ jobs:
             This PR contains the auto-generated changelog for the ${{ steps.release_info.outputs.VERSION }} release.
 
             Please review and merge.
+
+            Related to #18505
           branch: 'changelog-${{ steps.release_info.outputs.VERSION }}'
           base: 'main'
           team-reviewers: 'gemini-cli-docs, gemini-cli-maintainers'

.github/workflows/release-patch-0-from-comment.yml

@@ -120,6 +120,9 @@ jobs:
             if (recentRuns.length > 0) {
               core.setOutput('dispatched_run_urls', recentRuns.map(r => r.html_url).join(','));
               core.setOutput('dispatched_run_ids', recentRuns.map(r => r.id).join(','));
+
+              const markdownLinks = recentRuns.map(r => `- [View dispatched workflow run](${r.html_url})`).join('\n');
+              core.setOutput('dispatched_run_links', markdownLinks);
             }
 
       - name: 'Comment on Failure'
@@ -138,16 +141,19 @@ jobs:
           token: '${{ secrets.GITHUB_TOKEN }}'
           issue-number: '${{ github.event.issue.number }}'
           body: |
-            ✅ **Patch workflow(s) dispatched successfully!**
+            🚀 **[Step 1/4] Patch workflow(s) waiting for approval!**
 
             **📋 Details:**
             - **Channels**: `${{ steps.dispatch_patch.outputs.dispatched_channels }}`
             - **Commit**: `${{ steps.pr_status.outputs.MERGE_COMMIT_SHA }}`
             - **Workflows Created**: ${{ steps.dispatch_patch.outputs.dispatched_run_count }}
 
+            **⏳ Status:** The patch creation workflow has been triggered and is waiting for deployment approval. Please visit the specific workflow links below and approve the runs.
+
             **🔗 Track Progress:**
-            - [View patch workflows](https://github.com/${{ github.repository }}/actions/workflows/release-patch-1-create-pr.yml)
-            - [This workflow run](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }})
+            ${{ steps.dispatch_patch.outputs.dispatched_run_links }}
+            - [View patch workflow history](https://github.com/${{ github.repository }}/actions/workflows/release-patch-1-create-pr.yml)
+            - [This trigger workflow run](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }})
 
       - name: 'Final Status Comment - Dispatch Success (No URL)'
         if: "always() && startsWith(github.event.comment.body, '/patch') && steps.dispatch_patch.outcome == 'success' && !steps.dispatch_patch.outputs.dispatched_run_urls"
@@ -156,16 +162,18 @@ jobs:
           token: '${{ secrets.GITHUB_TOKEN }}'
           issue-number: '${{ github.event.issue.number }}'
           body: |
-            ✅ **Patch workflow(s) dispatched successfully!**
+            🚀 **[Step 1/4] Patch workflow(s) waiting for approval!**
 
             **📋 Details:**
             - **Channels**: `${{ steps.dispatch_patch.outputs.dispatched_channels }}`
             - **Commit**: `${{ steps.pr_status.outputs.MERGE_COMMIT_SHA }}`
             - **Workflows Created**: ${{ steps.dispatch_patch.outputs.dispatched_run_count }}
 
+            **⏳ Status:** The patch creation workflow has been triggered and is waiting for deployment approval. Please visit the workflow history link below and approve the runs.
+
             **🔗 Track Progress:**
-            - [View patch workflows](https://github.com/${{ github.repository }}/actions/workflows/release-patch-1-create-pr.yml)
-            - [This workflow run](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }})
+            - [View patch workflow history](https://github.com/${{ github.repository }}/actions/workflows/release-patch-1-create-pr.yml)
+            - [This trigger workflow run](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }})
 
       - name: 'Final Status Comment - Failure'
         if: "always() && startsWith(github.event.comment.body, '/patch') && (steps.dispatch_patch.outcome == 'failure' || steps.dispatch_patch.outcome == 'cancelled')"
@@ -174,7 +182,7 @@ jobs:
           token: '${{ secrets.GITHUB_TOKEN }}'
           issue-number: '${{ github.event.issue.number }}'
           body: |
-            ❌ **Patch workflow dispatch failed!**
+            ❌ **[Step 1/4] Patch workflow dispatch failed!**
 
             There was an error dispatching the patch creation workflow.
 

.github/workflows/test-build-binary.yml

@@ -33,7 +33,7 @@ jobs:
 
     steps:
       - name: 'Checkout'
-        uses: 'actions/checkout@v4'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
 
       - name: 'Optimize Windows Performance'
         if: "matrix.os == 'windows-latest'"
@@ -46,7 +46,7 @@ jobs:
         shell: 'powershell'
 
       - name: 'Set up Node.js'
-        uses: 'actions/setup-node@v4'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
         with:
           node-version-file: '.nvmrc'
           architecture: '${{ matrix.arch }}'
@@ -63,7 +63,7 @@ jobs:
 
       - name: 'Setup Windows SDK (Windows)'
         if: "matrix.os == 'windows-latest'"
-        uses: 'microsoft/setup-msbuild@v2'
+        uses: 'microsoft/setup-msbuild@6fb02220983dee41ce7ae257b6f4d8f9bf5ed4ce' # ratchet:microsoft/setup-msbuild@v2
 
       - name: 'Add Signtool to Path (Windows)'
         if: "matrix.os == 'windows-latest'"
@@ -153,7 +153,7 @@ jobs:
           npm run test:integration:sandbox:none -- --testTimeout=600000
 
       - name: 'Upload Artifact'
-        uses: 'actions/upload-artifact@v4'
+        uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
         with:
           name: 'gemini-cli-${{ matrix.platform_name }}'
           path: 'dist/${{ matrix.platform_name }}/'

.github/workflows/unassign-inactive-assignees.yml

@@ -40,13 +40,13 @@ jobs:
     steps:
       - name: 'Generate GitHub App Token'
         id: 'generate_token'
-        uses: 'actions/create-github-app-token@v2'
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
         with:
           app-id: '${{ secrets.APP_ID }}'
           private-key: '${{ secrets.PRIVATE_KEY }}'
 
       - name: 'Unassign inactive assignees'
-        uses: 'actions/github-script@v7'
+        uses: 'actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b' # ratchet:actions/github-script@v7
         env:
           DRY_RUN: '${{ inputs.dry_run }}'
         with:

.gitignore

@@ -48,6 +48,7 @@ packages/cli/src/generated/
 packages/core/src/generated/
 packages/devtools/src/_client-assets.ts
 .integration-tests/
+.perf-tests/
 packages/vscode-ide-companion/*.vsix
 packages/cli/download-ripgrep*/
 
@@ -62,3 +63,8 @@ gemini-debug.log
 .gemini-clipboard/
 .eslintcache
 evals/logs/
+
+temp_agents/
+
+# conductor extension and planning directories
+conductor/

.prettierignore

@@ -22,3 +22,4 @@ Thumbs.db
 .pytest_cache
 **/SKILL.md
 packages/sdk/test-data/*.json
+*.mdx

CONTRIBUTING.md

@@ -60,20 +60,45 @@ All submissions, including submissions by project members, require review. We
 use [GitHub pull requests](https://docs.github.com/articles/about-pull-requests)
 for this purpose.
 
-If your pull request involves changes to `packages/cli` (the frontend), we
-recommend running our automated frontend review tool. **Note: This tool is
-currently experimental.** It helps detect common React anti-patterns, testing
-issues, and other frontend-specific best practices that are easy to miss.
+To assist with the review process, we provide an automated review tool that
+helps detect common anti-patterns, testing issues, and other best practices that
+are easy to miss.
 
-To run the review tool, enter the following command from within Gemini CLI:
+#### Using the automated review tool
 
-```text
-/review-frontend <PR_NUMBER>
-```
+You can run the review tool in two ways:
 
-Replace `<PR_NUMBER>` with your pull request number. Authors are encouraged to
-run this on their own PRs for self-review, and reviewers should use it to
-augment their manual review process.
+1.  **Using the helper script (Recommended):** We provide a script that
+    automatically handles checking out the PR into a separate worktree,
+    installing dependencies, building the project, and launching the review
+    tool.
+
+    ```bash
+    ./scripts/review.sh <PR_NUMBER> [model]
+    ```
+
+    **Warning:** If you run `scripts/review.sh`, you must have first verified
+    that the code for the PR being reviewed is safe to run and does not contain
+    data exfiltration attacks.
+
+    **Authors are strongly encouraged to run this script on their own PRs**
+    immediately after creation. This allows you to catch and fix simple issues
+    locally before a maintainer performs a full review.
+
+    **Note on Models:** By default, the script uses the latest Pro model
+    (`gemini-3.1-pro-preview`). If you do not have enough Pro quota, you can run
+    it with the latest Flash model instead:
+    `./scripts/review.sh <PR_NUMBER> gemini-3-flash-preview`.
+
+2.  **Manually from within Gemini CLI:** If you already have the PR checked out
+    and built, you can run the tool directly from the CLI prompt:
+
+    ```text
+    /review-frontend <PR_NUMBER>
+    ```
+
+Replace `<PR_NUMBER>` with your pull request number. Reviewers should use this
+tool to augment, not replace, their manual review process.
 
 ### Self-assigning and unassigning issues
 
@@ -85,7 +110,9 @@ assign or unassign the issue as requested, provided the conditions are met
 (e.g., an issue must be unassigned to be assigned).
 
 Please note that you can have a maximum of 3 issues assigned to you at any given
-time.
+time and that only
+[issues labeled "help wanted"](https://github.com/google-gemini/gemini-cli/issues?q=is%3Aissue%20state%3Aopen%20label%3A%22help%20wanted%22)
+may be self-assigned.
 
 ### Pull request guidelines
 
@@ -267,7 +294,8 @@ npm run test:e2e
 ```
 
 For more detailed information on the integration testing framework, please see
-the [Integration Tests documentation](/docs/integration-tests.md).
+the
+[Integration Tests documentation](https://geminicli.com/docs/integration-tests).
 
 ### Linting and preflight checks
 
@@ -297,8 +325,8 @@ fi
 
 #### Formatting
 
-To separately format the code in this project by running the following command
-from the root directory:
+To separately format the code in this project, run the following command from
+the root directory:
 
 ```bash
 npm run format
@@ -320,27 +348,14 @@ npm run lint
 
 - Please adhere to the coding style, patterns, and conventions used throughout
   the existing codebase.
-- Consult [GEMINI.md](../GEMINI.md) (typically found in the project root) for
-  specific instructions related to AI-assisted development, including
-  conventions for React, comments, and Git usage.
+- Consult
+  [GEMINI.md](https://github.com/google-gemini/gemini-cli/blob/main/GEMINI.md)
+  (typically found in the project root) for specific instructions related to
+  AI-assisted development, including conventions for React, comments, and Git
+  usage.
 - **Imports:** Pay special attention to import paths. The project uses ESLint to
   enforce restrictions on relative imports between packages.
 
-### Project structure
-
-- `packages/`: Contains the individual sub-packages of the project.
-  - `a2a-server`: A2A server implementation for the Gemini CLI. (Experimental)
-  - `cli/`: The command-line interface.
-  - `core/`: The core backend logic for the Gemini CLI.
-  - `test-utils` Utilities for creating and cleaning temporary file systems for
-    testing.
-  - `vscode-ide-companion/`: The Gemini CLI Companion extension pairs with
-    Gemini CLI.
-- `docs/`: Contains all project documentation.
-- `scripts/`: Utility scripts for building, testing, and development tasks.
-
-For more detailed architecture, see `docs/architecture.md`.
-
 ### Debugging
 
 #### VS Code
@@ -494,8 +509,9 @@ code.
 
 ### Documentation structure
 
-Our documentation is organized using [sidebar.json](/docs/sidebar.json) as the
-table of contents. When adding new documentation:
+Our documentation is organized using
+[sidebar.json](https://github.com/google-gemini/gemini-cli/blob/main/docs/sidebar.json)
+as the table of contents. When adding new documentation:
 
 1. Create your markdown file **in the appropriate directory** under `/docs`.
 2. Add an entry to `sidebar.json` in the relevant section.
@@ -546,7 +562,7 @@ Before submitting your documentation pull request, please:
 
 If you have questions about contributing documentation:
 
-- Check our [FAQ](/docs/resources/faq.md).
+- Check our [FAQ](https://geminicli.com/docs/resources/faq).
 - Review existing documentation for examples.
 - Open [an issue](https://github.com/google-gemini/gemini-cli/issues) to discuss
   your proposed changes.

GEMINI.md

@@ -22,9 +22,10 @@ powerful tool for developers.
     rendering.
   - `packages/core`: Backend logic, Gemini API orchestration, prompt
     construction, and tool execution.
-  - `packages/core/src/tools/`: Built-in tools for file system, shell, and web
-    operations.
   - `packages/a2a-server`: Experimental Agent-to-Agent server.
+  - `packages/sdk`: Programmatic SDK for embedding Gemini CLI capabilities.
+  - `packages/devtools`: Integrated developer tools (Network/Console inspector).
+  - `packages/test-utils`: Shared test utilities and test rig.
   - `packages/vscode-ide-companion`: VS Code extension pairing with the CLI.
 
 ## Building and Running
@@ -43,6 +44,13 @@ powerful tool for developers.
 - **Test Commands:**
   - **Unit (All):** `npm run test`
   - **Integration (E2E):** `npm run test:e2e`
+  - > **NOTE**: Please run the memory and perf tests locally **only if** you are
+    > implementing changes related to those test areas. Otherwise skip these
+    > tests locally and rely on CI to run them on nightly builds.
+  - **Memory (Nightly):** `npm run test:memory` (Runs memory regression tests
+    against baselines. Excluded from `preflight`, run nightly.)
+  - **Performance (Nightly):** `npm run test:perf` (Runs CPU performance
+    regression tests against baselines. Excluded from `preflight`, run nightly.)
   - **Workspace-Specific:** `npm test -w <pkg> -- <path>` (Note: `<path>` must
     be relative to the workspace root, e.g.,
     `-w @google/gemini-cli-core -- src/routing/modelRouterService.test.ts`)
@@ -58,10 +66,6 @@ powerful tool for developers.
 
 ## Development Conventions
 
-- **Legacy Snippets:** `packages/core/src/prompts/snippets.legacy.ts` is a
-  snapshot of an older system prompt. Avoid changing the prompting verbiage to
-  preserve its historical behavior; however, structural changes to ensure
-  compilation or simplify the code are permitted.
 - **Contributions:** Follow the process outlined in `CONTRIBUTING.md`. Requires
   signing the Google CLA.
 - **Pull Requests:** Keep PRs small, focused, and linked to an existing issue.
@@ -69,8 +73,6 @@ powerful tool for developers.
   `gh` CLI.
 - **Commit Messages:** Follow the
   [Conventional Commits](https://www.conventionalcommits.org/) standard.
-- **Coding Style:** Adhere to existing patterns in `packages/cli` (React/Ink)
-  and `packages/core` (Backend logic).
 - **Imports:** Use specific imports and avoid restricted relative imports
   between packages (enforced by ESLint).
 - **License Headers:** For all new source code files (`.ts`, `.tsx`, `.js`),

README.md

@@ -6,7 +6,7 @@
 [![License](https://img.shields.io/github/license/google-gemini/gemini-cli)](https://github.com/google-gemini/gemini-cli/blob/main/LICENSE)
 [![View Code Wiki](https://assets.codewiki.google/readme-badge/static.svg)](https://codewiki.google/github.com/google-gemini/gemini-cli?utm_source=badge&utm_medium=github&utm_campaign=github.com/google-gemini/gemini-cli)
 
-![Gemini CLI Screenshot](./docs/assets/gemini-screenshot.png)
+![Gemini CLI Screenshot](/docs/assets/gemini-screenshot.png)
 
 Gemini CLI is an open-source AI agent that brings the power of Gemini directly
 into your terminal. It provides lightweight access to Gemini, giving you the
@@ -30,7 +30,7 @@ Learn all about Gemini CLI in our [documentation](https://geminicli.com/docs/).
 ## 📦 Installation
 
 See
-[Gemini CLI installation, execution, and releases](./docs/get-started/installation.md)
+[Gemini CLI installation, execution, and releases](https://www.geminicli.com/docs/get-started/installation)
 for recommended system specifications and a detailed installation guide.
 
 ### Quick Install
@@ -71,9 +71,9 @@ conda activate gemini_env
 npm install -g @google/gemini-cli
 ```
 
-## Release Cadence and Tags
+## Release Channels
 
-See [Releases](./docs/releases.md) for more details.
+See [Releases](https://www.geminicli.com/docs/changelogs) for more details.
 
 ### Preview
 
@@ -147,7 +147,7 @@ Integrate Gemini CLI directly into your GitHub workflows with
 
 Choose the authentication method that best fits your needs:
 
-### Option 1: Login with Google (OAuth login using your Google Account)
+### Option 1: Sign in with Google (OAuth login using your Google Account)
 
 **✨ Best for:** Individual developers as well as anyone who has a Gemini Code
 Assist License. (see
@@ -161,7 +161,7 @@ for details)
 - **No API key management** - just sign in with your Google account
 - **Automatic updates** to latest models
 
-#### Start Gemini CLI, then choose _Login with Google_ and follow the browser authentication flow when prompted
+#### Start Gemini CLI, then choose _Sign in with Google_ and follow the browser authentication flow when prompted
 
 ```bash
 gemini
@@ -209,7 +209,7 @@ gemini
 ```
 
 For Google Workspace accounts and other authentication methods, see the
-[authentication guide](./docs/get-started/authentication.md).
+[authentication guide](https://www.geminicli.com/docs/get-started/authentication).
 
 ## 🚀 Getting Started
 
@@ -278,60 +278,64 @@ gemini
 
 ### Getting Started
 
-- [**Quickstart Guide**](./docs/get-started/index.md) - Get up and running
-  quickly.
-- [**Authentication Setup**](./docs/get-started/authentication.md) - Detailed
-  auth configuration.
-- [**Configuration Guide**](./docs/reference/configuration.md) - Settings and
-  customization.
-- [**Keyboard Shortcuts**](./docs/reference/keyboard-shortcuts.md) -
+- [**Quickstart Guide**](https://www.geminicli.com/docs/get-started) - Get up
+  and running quickly.
+- [**Authentication Setup**](https://www.geminicli.com/docs/get-started/authentication) -
+  Detailed auth configuration.
+- [**Configuration Guide**](https://www.geminicli.com/docs/reference/configuration) -
+  Settings and customization.
+- [**Keyboard Shortcuts**](https://www.geminicli.com/docs/reference/keyboard-shortcuts) -
   Productivity tips.
 
 ### Core Features
 
-- [**Commands Reference**](./docs/reference/commands.md) - All slash commands
-  (`/help`, `/chat`, etc).
-- [**Custom Commands**](./docs/cli/custom-commands.md) - Create your own
-  reusable commands.
-- [**Context Files (GEMINI.md)**](./docs/cli/gemini-md.md) - Provide persistent
-  context to Gemini CLI.
-- [**Checkpointing**](./docs/cli/checkpointing.md) - Save and resume
-  conversations.
-- [**Token Caching**](./docs/cli/token-caching.md) - Optimize token usage.
+- [**Commands Reference**](https://www.geminicli.com/docs/reference/commands) -
+  All slash commands (`/help`, `/chat`, etc).
+- [**Custom Commands**](https://www.geminicli.com/docs/cli/custom-commands) -
+  Create your own reusable commands.
+- [**Context Files (GEMINI.md)**](https://www.geminicli.com/docs/cli/gemini-md) -
+  Provide persistent context to Gemini CLI.
+- [**Checkpointing**](https://www.geminicli.com/docs/cli/checkpointing) - Save
+  and resume conversations.
+- [**Token Caching**](https://www.geminicli.com/docs/cli/token-caching) -
+  Optimize token usage.
 
 ### Tools & Extensions
 
-- [**Built-in Tools Overview**](./docs/reference/tools.md)
-  - [File System Operations](./docs/tools/file-system.md)
-  - [Shell Commands](./docs/tools/shell.md)
-  - [Web Fetch & Search](./docs/tools/web-fetch.md)
-- [**MCP Server Integration**](./docs/tools/mcp-server.md) - Extend with custom
-  tools.
-- [**Custom Extensions**](./docs/extensions/index.md) - Build and share your own
-  commands.
+- [**Built-in Tools Overview**](https://www.geminicli.com/docs/reference/tools)
+  - [File System Operations](https://www.geminicli.com/docs/tools/file-system)
+  - [Shell Commands](https://www.geminicli.com/docs/tools/shell)
+  - [Web Fetch & Search](https://www.geminicli.com/docs/tools/web-fetch)
+- [**MCP Server Integration**](https://www.geminicli.com/docs/tools/mcp-server) -
+  Extend with custom tools.
+- [**Custom Extensions**](https://geminicli.com/docs/extensions/writing-extensions) -
+  Build and share your own commands.
 
 ### Advanced Topics
 
-- [**Headless Mode (Scripting)**](./docs/cli/headless.md) - Use Gemini CLI in
-  automated workflows.
-- [**Architecture Overview**](./docs/architecture.md) - How Gemini CLI works.
-- [**IDE Integration**](./docs/ide-integration/index.md) - VS Code companion.
-- [**Sandboxing & Security**](./docs/cli/sandbox.md) - Safe execution
-  environments.
-- [**Trusted Folders**](./docs/cli/trusted-folders.md) - Control execution
-  policies by folder.
-- [**Enterprise Guide**](./docs/cli/enterprise.md) - Deploy and manage in a
-  corporate environment.
-- [**Telemetry & Monitoring**](./docs/cli/telemetry.md) - Usage tracking.
-- [**Tools reference**](./docs/reference/tools.md) - Built-in tools overview.
-- [**Local development**](./docs/local-development.md) - Local development
-  tooling.
+- [**Headless Mode (Scripting)**](https://www.geminicli.com/docs/cli/headless) -
+  Use Gemini CLI in automated workflows.
+- [**IDE Integration**](https://www.geminicli.com/docs/ide-integration) - VS
+  Code companion.
+- [**Sandboxing & Security**](https://www.geminicli.com/docs/cli/sandbox) - Safe
+  execution environments.
+- [**Trusted Folders**](https://www.geminicli.com/docs/cli/trusted-folders) -
+  Control execution policies by folder.
+- [**Enterprise Guide**](https://www.geminicli.com/docs/cli/enterprise) - Deploy
+  and manage in a corporate environment.
+- [**Telemetry & Monitoring**](https://www.geminicli.com/docs/cli/telemetry) -
+  Usage tracking.
+- [**Tools reference**](https://www.geminicli.com/docs/reference/tools) -
+  Built-in tools overview.
+- [**Local development**](https://www.geminicli.com/docs/local-development) -
+  Local development tooling.
 
 ### Troubleshooting & Support
 
-- [**Troubleshooting Guide**](./docs/resources/troubleshooting.md) - Common
-  issues and solutions.
-- [**FAQ**](./docs/resources/faq.md) - Frequently asked questions.
+- [**Troubleshooting Guide**](https://www.geminicli.com/docs/resources/troubleshooting) -
+  Common issues and solutions.
+- [**FAQ**](https://www.geminicli.com/docs/resources/faq) - Frequently asked
+  questions.
 - Use `/bug` command to report issues directly from the CLI.
 
 ### Using MCP Servers
@@ -345,8 +349,9 @@ custom tools:
 > @database Run a query to find inactive users
 ```
 
-See the [MCP Server Integration guide](./docs/tools/mcp-server.md) for setup
-instructions.
+See the
+[MCP Server Integration guide](https://www.geminicli.com/docs/tools/mcp-server)
+for setup instructions.
 
 ## 🤝 Contributing
 
@@ -367,7 +372,8 @@ for planned features and priorities.
 ## 📖 Resources
 
 - **[Official Roadmap](./ROADMAP.md)** - See what's coming next.
-- **[Changelog](./docs/changelogs/index.md)** - See recent notable updates.
+- **[Changelog](https://www.geminicli.com/docs/changelogs)** - See recent
+  notable updates.
 - **[NPM Package](https://www.npmjs.com/package/@google/gemini-cli)** - Package
   registry.
 - **[GitHub Issues](https://github.com/google-gemini/gemini-cli/issues)** -
@@ -377,13 +383,14 @@ for planned features and priorities.
 
 ### Uninstall
 
-See the [Uninstall Guide](./docs/resources/uninstall.md) for removal
-instructions.
+See the [Uninstall Guide](https://www.geminicli.com/docs/resources/uninstall)
+for removal instructions.
 
 ## 📄 Legal
 
 - **License**: [Apache License 2.0](LICENSE)
-- **Terms of Service**: [Terms & Privacy](./docs/resources/tos-privacy.md)
+- **Terms of Service**:
+  [Terms & Privacy](https://www.geminicli.com/docs/resources/tos-privacy)
 - **Security**: [Security Policy](SECURITY.md)
 
 ---

docs/admin/enterprise-controls.md

@@ -72,7 +72,7 @@ organization.
 **Supported Fields:**
 
 - `url`: (Required) The full URL of the MCP server endpoint.
-- `type`: (Required) The connection type (e.g., `sse` or `http`).
+- `type`: (Required) The connection type (for example, `sse` or `http`).
 - `trust`: (Optional) If set to `true`, the server is trusted and tool execution
   will not require user approval.
 - `includeTools`: (Optional) An explicit list of tool names to allow. If
@@ -106,6 +106,67 @@ organization.
   ensures users maintain final control over which permitted servers are actually
   active in their environment.
 
+#### Required MCP Servers (preview)
+
+**Default**: empty
+
+Allows administrators to define MCP servers that are **always injected** into
+the user's environment. Unlike the allowlist (which filters user-configured
+servers), required servers are automatically added regardless of the user's
+local configuration.
+
+**Required Servers Format:**
+
+```json
+{
+  "requiredMcpServers": {
+    "corp-compliance-tool": {
+      "url": "https://mcp.corp/compliance",
+      "type": "http",
+      "trust": true,
+      "description": "Corporate compliance tool"
+    },
+    "internal-registry": {
+      "url": "https://registry.corp/mcp",
+      "type": "sse",
+      "authProviderType": "google_credentials",
+      "oauth": {
+        "scopes": ["https://www.googleapis.com/auth/scope"]
+      }
+    }
+  }
+}
+```
+
+**Supported Fields:**
+
+- `url`: (Required) The full URL of the MCP server endpoint.
+- `type`: (Required) The connection type (`sse` or `http`).
+- `trust`: (Optional) If set to `true`, tool execution will not require user
+  approval. Defaults to `true` for required servers.
+- `description`: (Optional) Human-readable description of the server.
+- `authProviderType`: (Optional) Authentication provider (`dynamic_discovery`,
+  `google_credentials`, or `service_account_impersonation`).
+- `oauth`: (Optional) OAuth configuration including `scopes`, `clientId`, and
+  `clientSecret`.
+- `targetAudience`: (Optional) OAuth target audience for service-to-service
+  auth.
+- `targetServiceAccount`: (Optional) Service account email to impersonate.
+- `headers`: (Optional) Additional HTTP headers to send with requests.
+- `includeTools` / `excludeTools`: (Optional) Tool filtering lists.
+- `timeout`: (Optional) Timeout in milliseconds for MCP requests.
+
+**Client Enforcement Logic:**
+
+- Required servers are injected **after** allowlist filtering, so they are
+  always available even if the allowlist is active.
+- If a required server has the **same name** as a locally configured server, the
+  admin configuration **completely overrides** the local one.
+- Required servers only support remote transports (`sse`, `http`). Local
+  execution fields (`command`, `args`, `env`, `cwd`) are not supported.
+- Required servers can coexist with allowlisted servers — both features work
+  independently.
+
 ### Unmanaged Capabilities
 
 **Enabled/Disabled** | Default: disabled

docs/changelogs/index.md

@@ -18,6 +18,127 @@ on GitHub.
 | [Preview](preview.md) | Experimental features ready for early feedback. |
 | [Stable](latest.md)   | Stable, recommended for general use.            |
 
+## Announcements: v0.38.0 - 2026-04-14
+
+- **Chapters Narrative Flow:** Group agent interactions into "Chapters" based on
+  intent and tool usage for better session structure
+  ([#23150](https://github.com/google-gemini/gemini-cli/pull/23150) by
+  @Abhijit-2592,
+  [#24079](https://github.com/google-gemini/gemini-cli/pull/24079) by
+  @gundermanc).
+- **Context Compression Service:** Advanced context management to efficiently
+  distill conversation history
+  ([#24483](https://github.com/google-gemini/gemini-cli/pull/24483) by
+  @joshualitt).
+- **UI Flicker & UX Enhancements:** Solved rendering flicker with "Terminal
+  Buffer" mode and introduced selective topic expansion
+  ([#24512](https://github.com/google-gemini/gemini-cli/pull/24512) by
+  @jacob314, [#24793](https://github.com/google-gemini/gemini-cli/pull/24793) by
+  @Abhijit-2592).
+- **Persistent Policy Approvals:** Implemented context-aware persistent
+  approvals for tool execution
+  ([#23257](https://github.com/google-gemini/gemini-cli/pull/23257) by @jerop).
+
+## Announcements: v0.37.0 - 2026-04-08
+
+- **Dynamic Sandbox Expansion:** Implemented dynamic sandbox expansion and
+  worktree support for Linux and Windows, improving developer workflows in
+  isolated environments
+  ([#23692](https://github.com/google-gemini/gemini-cli/pull/23692) by @galz10,
+  [#23691](https://github.com/google-gemini/gemini-cli/pull/23691) by
+  @scidomino).
+- **Chapters Narrative Flow:** Introduced tool-based topic grouping ("Chapters")
+  to provide better session structure and narrative continuity
+  ([#23150](https://github.com/google-gemini/gemini-cli/pull/23150) by
+  @Abhijit-2592,
+  [#24079](https://github.com/google-gemini/gemini-cli/pull/24079) by
+  @gundermanc).
+- **Advanced Browser Capabilities:** Enhanced the browser agent with persistent
+  sessions and dynamic tool discovery
+  ([#21306](https://github.com/google-gemini/gemini-cli/pull/21306) by
+  @kunal-10-cloud,
+  [#23805](https://github.com/google-gemini/gemini-cli/pull/23805) by
+  @cynthialong0-0).
+
+## Announcements: v0.36.0 - 2026-04-01
+
+- **Multi-Registry Architecture and Sandboxing:** Introduced a multi-registry
+  architecture and implemented native macOS Seatbelt and Windows sandboxing for
+  enhanced subagent security
+  ([#22712](https://github.com/google-gemini/gemini-cli/pull/22712),
+  [#22718](https://github.com/google-gemini/gemini-cli/pull/22718) by @akh64bit,
+  [#22832](https://github.com/google-gemini/gemini-cli/pull/22832) by @ehedlund,
+  [#21807](https://github.com/google-gemini/gemini-cli/pull/21807) by
+  @mattKorwel).
+- **Refreshed Composer UX:** Implemented a refreshed user experience for the
+  Composer layout and improved terminal interaction robustness
+  ([#21212](https://github.com/google-gemini/gemini-cli/pull/21212),
+  [#23286](https://github.com/google-gemini/gemini-cli/pull/23286) by
+  @jwhelangoog).
+- **Git Worktree Support:** Added native support for Git worktrees, allowing for
+  isolated parallel sessions
+  ([#22973](https://github.com/google-gemini/gemini-cli/pull/22973),
+  [#23265](https://github.com/google-gemini/gemini-cli/pull/23265) by @jerop).
+- **Subagent Context and Feedback:** Enhanced subagents with JIT context
+  injection and resilient tool rejection with contextual feedback
+  ([#23032](https://github.com/google-gemini/gemini-cli/pull/23032),
+  [#22951](https://github.com/google-gemini/gemini-cli/pull/22951) by
+  @abhipatel12).
+
+## Announcements: v0.35.0 - 2026-03-24
+
+- **Customizable Keyboard Shortcuts:** Users can now customize their keyboard
+  shortcuts, including support for literal character keybindings and the
+  extended Kitty protocol
+  ([#21945](https://github.com/google-gemini/gemini-cli/pull/21945),
+  [#21972](https://github.com/google-gemini/gemini-cli/pull/21972) by
+  @scidomino).
+- **Vim Mode Improvements:** Added missing motions (X, ~, r, f/F/t/T) and
+  yank/paste support with the unnamed register
+  ([#21932](https://github.com/google-gemini/gemini-cli/pull/21932),
+  [#22026](https://github.com/google-gemini/gemini-cli/pull/22026) by @aanari).
+- **Tool Isolation and Sandboxing:** Introduced `SandboxManager` to isolate
+  process-spawning tools and added Linux bubblewrap/seccomp sandboxing support
+  ([#21774](https://github.com/google-gemini/gemini-cli/pull/21774),
+  [#22231](https://github.com/google-gemini/gemini-cli/pull/22231) by @galz10,
+  [#22680](https://github.com/google-gemini/gemini-cli/pull/22680) by
+  @DavidAPierce).
+- **JIT Context Discovery:** Implemented Just-In-Time context discovery for file
+  system tools to improve model performance and accuracy
+  ([#22082](https://github.com/google-gemini/gemini-cli/pull/22082),
+  [#22736](https://github.com/google-gemini/gemini-cli/pull/22736) by
+  @SandyTao520).
+
+## Announcements: v0.34.0 - 2026-03-17
+
+- **Plan Mode Enabled by Default:** Plan Mode is now enabled by default to help
+  you break down complex tasks and execute them systematically
+  ([#21713](https://github.com/google-gemini/gemini-cli/pull/21713) by @jerop).
+- **Sandboxing Enhancements:** We've added native gVisor (runsc) and
+  experimental LXC container sandboxing support for safer execution environments
+  ([#21062](https://github.com/google-gemini/gemini-cli/pull/21062) by
+  @Zheyuan-Lin, [#20735](https://github.com/google-gemini/gemini-cli/pull/20735)
+  by @h30s).
+
+## Announcements: v0.33.0 - 2026-03-11
+
+- **Agent Architecture Enhancements:** Introduced HTTP authentication for A2A
+  remote agents and authenticated A2A agent card discovery
+  ([#20510](https://github.com/google-gemini/gemini-cli/pull/20510) by
+  @SandyTao520, [#20622](https://github.com/google-gemini/gemini-cli/pull/20622)
+  by @SandyTao520).
+- **Plan Mode Updates:** Expanded Plan Mode with built-in research subagents,
+  annotation support for feedback, and a new `copy` subcommand
+  ([#20972](https://github.com/google-gemini/gemini-cli/pull/20972) by @Adib234,
+  [#20988](https://github.com/google-gemini/gemini-cli/pull/20988) by
+  @ruomengz).
+- **CLI UX & Admin Controls:** Redesigned the header to be compact with an ASCII
+  icon, inverted context window display to show usage, and enabled a 30-day
+  default retention for chat history
+  ([#18713](https://github.com/google-gemini/gemini-cli/pull/18713) by
+  @keithguerin, [#20853](https://github.com/google-gemini/gemini-cli/pull/20853)
+  by @skeshive).
+
 ## Announcements: v0.32.0 - 2026-03-03
 
 - **Generalist Agent:** The generalist agent is now enabled to improve task
@@ -106,10 +227,6 @@ on GitHub.
 
 ## Announcements: v0.28.0 - 2026-02-10
 
-- **Slash Command:** We've added a new `/prompt-suggest` slash command to help
-  you generate prompt suggestions
-  ([#17264](https://github.com/google-gemini/gemini-cli/pull/17264) by
-  @NTaylorMullen).
 - **IDE Support:** Gemini CLI now supports the Positron IDE
   ([#15047](https://github.com/google-gemini/gemini-cli/pull/15047) by
   @kapsner).
@@ -149,8 +266,8 @@ on GitHub.
   ([#16638](https://github.com/google-gemini/gemini-cli/pull/16638) by
   @joshualitt).
 - **UI/UX Improvements:** You can now "Rewind" through your conversation history
-  ([#15717](https://github.com/google-gemini/gemini-cli/pull/15717) by @Adib234)
-  and use a new `/introspect` command for debugging.
+  ([#15717](https://github.com/google-gemini/gemini-cli/pull/15717) by
+  @Adib234).
 - **Core and Scheduler Refactoring:** The core scheduler has been significantly
   refactored to improve performance and reliability
   ([#16895](https://github.com/google-gemini/gemini-cli/pull/16895) by

docs/changelogs/latest.md

@@ -1,6 +1,6 @@
-# Latest stable release: v0.32.1
+# Latest stable release: v0.38.2
 
-Released: March 4, 2026
+Released: April 17, 2026
 
 For most users, our latest stable release is the recommended release. Install
 the latest stable version with:
@@ -11,198 +11,264 @@ npm install -g @google/gemini-cli
 
 ## Highlights
 
-- **Plan Mode Enhancements**: Significant updates to Plan Mode, including the
-  ability to open and modify plans in an external editor, adaptations for
-  complex tasks with multi-select options, and integration tests for plan mode.
-- **Agent and Steering Improvements**: The generalist agent has been enabled to
-  enhance task delegation, model steering is now supported directly within the
-  workspace, and contiguous parallel admission is enabled for `Kind.Agent`
-  tools.
-- **Interactive Shell**: Interactive shell autocompletion has been introduced,
-  significantly enhancing the user experience.
-- **Core Stability and Performance**: Extensions are now loaded in parallel,
-  fetch timeouts have been increased, robust A2A streaming reassembly was
-  implemented, and orphaned processes when terminal closes have been prevented.
-- **Billing and Quota Handling**: Implemented G1 AI credits overage flow with
-  billing telemetry and added support for quota error fallbacks across all
-  authentication types.
+- **Chapters Narrative Flow:** Introduced tool-based topic grouping ("Chapters")
+  to provide better session structure and narrative continuity in long-running
+  tasks.
+- **Context Compression Service:** Implemented a dedicated service for advanced
+  context management, efficiently distilling conversation history to preserve
+  focus and tokens.
+- **Enhanced UI Stability & UX:** Introduced a new "Terminal Buffer" mode to
+  solve rendering flicker, along with selective topic expansion and improved
+  tool confirmation layouts.
+- **Context-Aware Policy Approvals:** Users can now grant persistent,
+  context-aware approvals for tools, significantly reducing manual confirmation
+  overhead for trusted workflows.
+- **Background Process Monitoring:** New tools for monitoring and inspecting
+  background shell processes, providing better visibility into asynchronous
+  tasks.
 
 ## What's Changed
 
-- fix(patch): cherry-pick 0659ad1 to release/v0.32.0-pr-21042 to patch version
-  v0.32.0 and create version 0.32.1 by @gemini-cli-robot in
-  [#21048](https://github.com/google-gemini/gemini-cli/pull/21048)
-- feat(plan): add integration tests for plan mode by @Adib234 in
-  [#20214](https://github.com/google-gemini/gemini-cli/pull/20214)
-- fix(acp): update auth handshake to spec by @skeshive in
-  [#19725](https://github.com/google-gemini/gemini-cli/pull/19725)
-- feat(core): implement robust A2A streaming reassembly and fix task continuity
-  by @adamfweidman in
-  [#20091](https://github.com/google-gemini/gemini-cli/pull/20091)
-- feat(cli): load extensions in parallel by @scidomino in
-  [#20229](https://github.com/google-gemini/gemini-cli/pull/20229)
-- Plumb the maxAttempts setting through Config args by @kevinjwang1 in
-  [#20239](https://github.com/google-gemini/gemini-cli/pull/20239)
-- fix(cli): skip 404 errors in setup-github file downloads by @h30s in
-  [#20287](https://github.com/google-gemini/gemini-cli/pull/20287)
-- fix(cli): expose model.name setting in settings dialog for persistence by
-  @achaljhawar in
-  [#19605](https://github.com/google-gemini/gemini-cli/pull/19605)
-- docs: remove legacy cmd examples in favor of powershell by @scidomino in
-  [#20323](https://github.com/google-gemini/gemini-cli/pull/20323)
-- feat(core): Enable model steering in workspace. by @joshualitt in
-  [#20343](https://github.com/google-gemini/gemini-cli/pull/20343)
-- fix: remove trailing comma in issue triage workflow settings json by @Nixxx19
-  in [#20265](https://github.com/google-gemini/gemini-cli/pull/20265)
-- feat(core): implement task tracker foundation and service by @anj-s in
-  [#19464](https://github.com/google-gemini/gemini-cli/pull/19464)
-- test: support tests that include color information by @jacob314 in
-  [#20220](https://github.com/google-gemini/gemini-cli/pull/20220)
-- feat(core): introduce Kind.Agent for sub-agent classification by @abhipatel12
-  in [#20369](https://github.com/google-gemini/gemini-cli/pull/20369)
-- Changelog for v0.30.0 by @gemini-cli-robot in
-  [#20252](https://github.com/google-gemini/gemini-cli/pull/20252)
-- Update changelog workflow to reject nightly builds by @g-samroberts in
-  [#20248](https://github.com/google-gemini/gemini-cli/pull/20248)
-- Changelog for v0.31.0-preview.0 by @gemini-cli-robot in
-  [#20249](https://github.com/google-gemini/gemini-cli/pull/20249)
-- feat(cli): hide workspace policy update dialog and auto-accept by default by
-  @Abhijit-2592 in
-  [#20351](https://github.com/google-gemini/gemini-cli/pull/20351)
-- feat(core): rename grep_search include parameter to include_pattern by
-  @SandyTao520 in
-  [#20328](https://github.com/google-gemini/gemini-cli/pull/20328)
-- feat(plan): support opening and modifying plan in external editor by @Adib234
-  in [#20348](https://github.com/google-gemini/gemini-cli/pull/20348)
-- feat(cli): implement interactive shell autocompletion by @mrpmohiburrahman in
-  [#20082](https://github.com/google-gemini/gemini-cli/pull/20082)
-- fix(core): allow /memory add to work in plan mode by @Jefftree in
-  [#20353](https://github.com/google-gemini/gemini-cli/pull/20353)
-- feat(core): add HTTP 499 to retryable errors and map to RetryableQuotaError by
-  @bdmorgan in [#20432](https://github.com/google-gemini/gemini-cli/pull/20432)
-- feat(core): Enable generalist agent by @joshualitt in
-  [#19665](https://github.com/google-gemini/gemini-cli/pull/19665)
-- Updated tests in TableRenderer.test.tsx to use SVG snapshots by @devr0306 in
-  [#20450](https://github.com/google-gemini/gemini-cli/pull/20450)
-- Refactor Github Action per b/485167538 by @google-admin in
-  [#19443](https://github.com/google-gemini/gemini-cli/pull/19443)
-- fix(github): resolve actionlint and yamllint regressions from #19443 by @jerop
-  in [#20467](https://github.com/google-gemini/gemini-cli/pull/20467)
-- fix: action var usage by @galz10 in
-  [#20492](https://github.com/google-gemini/gemini-cli/pull/20492)
-- feat(core): improve A2A content extraction by @adamfweidman in
-  [#20487](https://github.com/google-gemini/gemini-cli/pull/20487)
-- fix(cli): support quota error fallbacks for all authentication types by
-  @sehoon38 in [#20475](https://github.com/google-gemini/gemini-cli/pull/20475)
-- fix(core): flush transcript for pure tool-call responses to ensure BeforeTool
-  hooks see complete state by @krishdef7 in
-  [#20419](https://github.com/google-gemini/gemini-cli/pull/20419)
-- feat(plan): adapt planning workflow based on complexity of task by @jerop in
-  [#20465](https://github.com/google-gemini/gemini-cli/pull/20465)
-- fix: prevent orphaned processes from consuming 100% CPU when terminal closes
-  by @yuvrajangadsingh in
-  [#16965](https://github.com/google-gemini/gemini-cli/pull/16965)
-- feat(core): increase fetch timeout and fix [object Object] error
-  stringification by @bdmorgan in
-  [#20441](https://github.com/google-gemini/gemini-cli/pull/20441)
-- [Gemma x Gemini CLI] Add an Experimental Gemma Router that uses a LiteRT-LM
-  shim into the Composite Model Classifier Strategy by @sidwan02 in
-  [#17231](https://github.com/google-gemini/gemini-cli/pull/17231)
-- docs(plan): update documentation regarding supporting editing of plan files
-  during plan approval by @Adib234 in
-  [#20452](https://github.com/google-gemini/gemini-cli/pull/20452)
-- test(cli): fix flaky ToolResultDisplay overflow test by @jwhelangoog in
-  [#20518](https://github.com/google-gemini/gemini-cli/pull/20518)
-- ui(cli): reduce length of Ctrl+O hint by @jwhelangoog in
-  [#20490](https://github.com/google-gemini/gemini-cli/pull/20490)
-- fix(ui): correct styled table width calculations by @devr0306 in
-  [#20042](https://github.com/google-gemini/gemini-cli/pull/20042)
-- Avoid overaggressive unescaping by @scidomino in
-  [#20520](https://github.com/google-gemini/gemini-cli/pull/20520)
-- feat(telemetry) Instrument traces with more attributes and make them available
-  to OTEL users by @heaventourist in
-  [#20237](https://github.com/google-gemini/gemini-cli/pull/20237)
-- Add support for policy engine in extensions by @chrstnb in
-  [#20049](https://github.com/google-gemini/gemini-cli/pull/20049)
-- Docs: Update to Terms of Service & FAQ by @jkcinouye in
-  [#20488](https://github.com/google-gemini/gemini-cli/pull/20488)
-- Fix bottom border rendering for search and add a regression test. by @jacob314
-  in [#20517](https://github.com/google-gemini/gemini-cli/pull/20517)
-- fix(core): apply retry logic to CodeAssistServer for all users by @bdmorgan in
-  [#20507](https://github.com/google-gemini/gemini-cli/pull/20507)
-- Fix extension MCP server env var loading by @chrstnb in
-  [#20374](https://github.com/google-gemini/gemini-cli/pull/20374)
-- feat(ui): add 'ctrl+o' hint to truncated content message by @jerop in
-  [#20529](https://github.com/google-gemini/gemini-cli/pull/20529)
-- Fix flicker showing message to press ctrl-O again to collapse. by @jacob314 in
-  [#20414](https://github.com/google-gemini/gemini-cli/pull/20414)
-- fix(cli): hide shortcuts hint while model is thinking or the user has typed a
-  prompt + add debounce to avoid flicker by @jacob314 in
-  [#19389](https://github.com/google-gemini/gemini-cli/pull/19389)
-- feat(plan): update planning workflow to encourage multi-select with
-  descriptions of options by @Adib234 in
-  [#20491](https://github.com/google-gemini/gemini-cli/pull/20491)
-- refactor(core,cli): useAlternateBuffer read from config by @psinha40898 in
-  [#20346](https://github.com/google-gemini/gemini-cli/pull/20346)
-- fix(cli): ensure dialogs stay scrolled to bottom in alternate buffer mode by
-  @jacob314 in [#20527](https://github.com/google-gemini/gemini-cli/pull/20527)
-- fix(core): revert auto-save of policies to user space by @Abhijit-2592 in
-  [#20531](https://github.com/google-gemini/gemini-cli/pull/20531)
-- Demote unreliable test. by @gundermanc in
-  [#20571](https://github.com/google-gemini/gemini-cli/pull/20571)
-- fix(core): handle optional response fields from code assist API by @sehoon38
-  in [#20345](https://github.com/google-gemini/gemini-cli/pull/20345)
-- fix(cli): keep thought summary when loading phrases are off by @LyalinDotCom
-  in [#20497](https://github.com/google-gemini/gemini-cli/pull/20497)
-- feat(cli): add temporary flag to disable workspace policies by @Abhijit-2592
-  in [#20523](https://github.com/google-gemini/gemini-cli/pull/20523)
-- Disable expensive and scheduled workflows on personal forks by @dewitt in
-  [#20449](https://github.com/google-gemini/gemini-cli/pull/20449)
-- Moved markdown parsing logic to a separate util file by @devr0306 in
-  [#20526](https://github.com/google-gemini/gemini-cli/pull/20526)
-- fix(plan): prevent agent from using ask_user for shell command confirmation by
-  @Adib234 in [#20504](https://github.com/google-gemini/gemini-cli/pull/20504)
-- fix(core): disable retries for code assist streaming requests by @sehoon38 in
-  [#20561](https://github.com/google-gemini/gemini-cli/pull/20561)
-- feat(billing): implement G1 AI credits overage flow with billing telemetry by
-  @gsquared94 in
-  [#18590](https://github.com/google-gemini/gemini-cli/pull/18590)
-- feat: better error messages by @gsquared94 in
-  [#20577](https://github.com/google-gemini/gemini-cli/pull/20577)
-- fix(ui): persist expansion in AskUser dialog when navigating options by @jerop
-  in [#20559](https://github.com/google-gemini/gemini-cli/pull/20559)
-- fix(cli): prevent sub-agent tool calls from leaking into UI by @abhipatel12 in
-  [#20580](https://github.com/google-gemini/gemini-cli/pull/20580)
-- fix(cli): Shell autocomplete polish by @jacob314 in
-  [#20411](https://github.com/google-gemini/gemini-cli/pull/20411)
-- Changelog for v0.31.0-preview.1 by @gemini-cli-robot in
-  [#20590](https://github.com/google-gemini/gemini-cli/pull/20590)
-- Add slash command for promoting behavioral evals to CI blocking by @gundermanc
-  in [#20575](https://github.com/google-gemini/gemini-cli/pull/20575)
-- Changelog for v0.30.1 by @gemini-cli-robot in
-  [#20589](https://github.com/google-gemini/gemini-cli/pull/20589)
-- Add low/full CLI error verbosity mode for cleaner UI by @LyalinDotCom in
-  [#20399](https://github.com/google-gemini/gemini-cli/pull/20399)
-- Disable Gemini PR reviews on draft PRs. by @gundermanc in
-  [#20362](https://github.com/google-gemini/gemini-cli/pull/20362)
-- Docs: FAQ update by @jkcinouye in
-  [#20585](https://github.com/google-gemini/gemini-cli/pull/20585)
-- fix(core): reduce intrusive MCP errors and deduplicate diagnostics by
-  @spencer426 in
-  [#20232](https://github.com/google-gemini/gemini-cli/pull/20232)
-- docs: fix spelling typos in installation guide by @campox747 in
-  [#20579](https://github.com/google-gemini/gemini-cli/pull/20579)
-- Promote stable tests to CI blocking. by @gundermanc in
-  [#20581](https://github.com/google-gemini/gemini-cli/pull/20581)
-- feat(core): enable contiguous parallel admission for Kind.Agent tools by
+- fix(patch): cherry-pick 14b2f35 to release/v0.38.1-pr-24974 to patch version
+  v0.38.1 and create version 0.38.2 by @gemini-cli-robot in
+  [#25585](https://github.com/google-gemini/gemini-cli/pull/25585)
+- fix(patch): cherry-pick 050c303 to release/v0.38.0-pr-25317 to patch version
+  v0.38.0 and create version 0.38.1 by @gemini-cli-robot in
+  [#25466](https://github.com/google-gemini/gemini-cli/pull/25466)
+- fix(cli): refresh slash command list after /skills reload by @NTaylorMullen in
+  [#24454](https://github.com/google-gemini/gemini-cli/pull/24454)
+- Update README.md for links. by @g-samroberts in
+  [#22759](https://github.com/google-gemini/gemini-cli/pull/22759)
+- fix(core): ensure complete_task tool calls are recorded in chat history by
   @abhipatel12 in
-  [#20583](https://github.com/google-gemini/gemini-cli/pull/20583)
-- Enforce import/no-duplicates as error by @Nixxx19 in
-  [#19797](https://github.com/google-gemini/gemini-cli/pull/19797)
-- fix: merge duplicate imports in sdk and test-utils packages (1/4) by @Nixxx19
-  in [#19777](https://github.com/google-gemini/gemini-cli/pull/19777)
-- fix: merge duplicate imports in a2a-server package (2/4) by @Nixxx19 in
-  [#19781](https://github.com/google-gemini/gemini-cli/pull/19781)
+  [#24437](https://github.com/google-gemini/gemini-cli/pull/24437)
+- feat(policy): explicitly allow web_fetch in plan mode with ask_user by
+  @Adib234 in [#24456](https://github.com/google-gemini/gemini-cli/pull/24456)
+- fix(core): refactor linux sandbox to fix ARG_MAX crashes by @ehedlund in
+  [#24286](https://github.com/google-gemini/gemini-cli/pull/24286)
+- feat(config): add experimental.adk.agentSessionNoninteractiveEnabled setting
+  by @adamfweidman in
+  [#24439](https://github.com/google-gemini/gemini-cli/pull/24439)
+- Changelog for v0.36.0-preview.8 by @gemini-cli-robot in
+  [#24453](https://github.com/google-gemini/gemini-cli/pull/24453)
+- feat(cli): change default loadingPhrases to 'off' to hide tips by @keithguerin
+  in [#24342](https://github.com/google-gemini/gemini-cli/pull/24342)
+- fix(cli): ensure agent stops when all declinable tools are cancelled by
+  @NTaylorMullen in
+  [#24479](https://github.com/google-gemini/gemini-cli/pull/24479)
+- fix(core): enhance sandbox usability and fix build error by @galz10 in
+  [#24460](https://github.com/google-gemini/gemini-cli/pull/24460)
+- Terminal Serializer Optimization by @jacob314 in
+  [#24485](https://github.com/google-gemini/gemini-cli/pull/24485)
+- Auto configure memory. by @jacob314 in
+  [#24474](https://github.com/google-gemini/gemini-cli/pull/24474)
+- Unused error variables in catch block are not allowed by @alisa-alisa in
+  [#24487](https://github.com/google-gemini/gemini-cli/pull/24487)
+- feat(core): add background memory service for skill extraction by @SandyTao520
+  in [#24274](https://github.com/google-gemini/gemini-cli/pull/24274)
+- feat: implement high-signal PR regression check for evaluations by
+  @alisa-alisa in
+  [#23937](https://github.com/google-gemini/gemini-cli/pull/23937)
+- Fix shell output display by @jacob314 in
+  [#24490](https://github.com/google-gemini/gemini-cli/pull/24490)
+- fix(ui): resolve unwanted vertical spacing around various tool output
+  treatments by @jwhelangoog in
+  [#24449](https://github.com/google-gemini/gemini-cli/pull/24449)
+- revert(cli): bring back input box and footer visibility in copy mode by
+  @sehoon38 in [#24504](https://github.com/google-gemini/gemini-cli/pull/24504)
+- fix(cli): prevent crash in AnsiOutputText when handling non-array data by
+  @sehoon38 in [#24498](https://github.com/google-gemini/gemini-cli/pull/24498)
+- feat(cli): support default values for environment variables by @ruomengz in
+  [#24469](https://github.com/google-gemini/gemini-cli/pull/24469)
+- Implement background process monitoring and inspection tools by @cocosheng-g
+  in [#23799](https://github.com/google-gemini/gemini-cli/pull/23799)
+- docs(browser-agent): update stale browser agent documentation by @gsquared94
+  in [#24463](https://github.com/google-gemini/gemini-cli/pull/24463)
+- fix: enable browser_agent in integration tests and add localhost fixture tests
+  by @gsquared94 in
+  [#24523](https://github.com/google-gemini/gemini-cli/pull/24523)
+- fix(browser): handle computer-use model detection for analyze_screenshot by
+  @gsquared94 in
+  [#24502](https://github.com/google-gemini/gemini-cli/pull/24502)
+- feat(core): Land ContextCompressionService by @joshualitt in
+  [#24483](https://github.com/google-gemini/gemini-cli/pull/24483)
+- feat(core): scope subagent workspace directories via AsyncLocalStorage by
+  @SandyTao520 in
+  [#24445](https://github.com/google-gemini/gemini-cli/pull/24445)
+- Update ink version to 6.6.7 by @jacob314 in
+  [#24514](https://github.com/google-gemini/gemini-cli/pull/24514)
+- fix(acp): handle all InvalidStreamError types gracefully in prompt by @sripasg
+  in [#24540](https://github.com/google-gemini/gemini-cli/pull/24540)
+- Fix crash when vim editor is not found in PATH on Windows by
+  @Nagajyothi-tammisetti in
+  [#22423](https://github.com/google-gemini/gemini-cli/pull/22423)
+- fix(core): move project memory dir under tmp directory by @SandyTao520 in
+  [#24542](https://github.com/google-gemini/gemini-cli/pull/24542)
+- Enable 'Other' option for yesno question type by @ruomengz in
+  [#24545](https://github.com/google-gemini/gemini-cli/pull/24545)
+- fix(cli): clear stale retry/loading state after cancellation (#21096) by
+  @Aaxhirrr in [#21960](https://github.com/google-gemini/gemini-cli/pull/21960)
+- Changelog for v0.37.0-preview.0 by @gemini-cli-robot in
+  [#24464](https://github.com/google-gemini/gemini-cli/pull/24464)
+- feat(core): implement context-aware persistent policy approvals by @jerop in
+  [#23257](https://github.com/google-gemini/gemini-cli/pull/23257)
+- docs: move agent disabling instructions and update remote agent status by
+  @jackwotherspoon in
+  [#24559](https://github.com/google-gemini/gemini-cli/pull/24559)
+- feat(cli): migrate nonInteractiveCli to LegacyAgentSession by @adamfweidman in
+  [#22987](https://github.com/google-gemini/gemini-cli/pull/22987)
+- fix(core): unsafe type assertions in Core File System #19712 by
+  @aniketsaurav18 in
+  [#19739](https://github.com/google-gemini/gemini-cli/pull/19739)
+- fix(ui): hide model quota in /stats and refactor quota display by @danzaharia1
+  in [#24206](https://github.com/google-gemini/gemini-cli/pull/24206)
+- Changelog for v0.36.0 by @gemini-cli-robot in
+  [#24558](https://github.com/google-gemini/gemini-cli/pull/24558)
+- Changelog for v0.37.0-preview.1 by @gemini-cli-robot in
+  [#24568](https://github.com/google-gemini/gemini-cli/pull/24568)
+- docs: add missing .md extensions to internal doc links by @ishaan-arora-1 in
+  [#24145](https://github.com/google-gemini/gemini-cli/pull/24145)
+- fix(ui): fixed table styling by @devr0306 in
+  [#24565](https://github.com/google-gemini/gemini-cli/pull/24565)
+- fix(core): pass includeDirectories to sandbox configuration by @galz10 in
+  [#24573](https://github.com/google-gemini/gemini-cli/pull/24573)
+- feat(ui): enable "TerminalBuffer" mode to solve flicker by @jacob314 in
+  [#24512](https://github.com/google-gemini/gemini-cli/pull/24512)
+- docs: clarify release coordination by @scidomino in
+  [#24575](https://github.com/google-gemini/gemini-cli/pull/24575)
+- fix(core): remove broken PowerShell translation and fix native \_\_write in
+  Windows sandbox by @scidomino in
+  [#24571](https://github.com/google-gemini/gemini-cli/pull/24571)
+- Add instructions for how to start react in prod and force react to prod mode
+  by @jacob314 in
+  [#24590](https://github.com/google-gemini/gemini-cli/pull/24590)
+- feat(cli): minimalist sandbox status labels by @galz10 in
+  [#24582](https://github.com/google-gemini/gemini-cli/pull/24582)
+- Feat/browser agent metrics by @kunal-10-cloud in
+  [#24210](https://github.com/google-gemini/gemini-cli/pull/24210)
+- test: fix Windows CI execution and resolve exposed platform failures by
+  @ehedlund in [#24476](https://github.com/google-gemini/gemini-cli/pull/24476)
+- feat(core,cli): prioritize summary for topics (#24608) by @Abhijit-2592 in
+  [#24609](https://github.com/google-gemini/gemini-cli/pull/24609)
+- show color by @jacob314 in
+  [#24613](https://github.com/google-gemini/gemini-cli/pull/24613)
+- feat(cli): enable compact tool output by default (#24509) by @jwhelangoog in
+  [#24510](https://github.com/google-gemini/gemini-cli/pull/24510)
+- fix(core): inject skill system instructions into subagent prompts if activated
+  by @abhipatel12 in
+  [#24620](https://github.com/google-gemini/gemini-cli/pull/24620)
+- fix(core): improve windows sandbox reliability and fix integration tests by
+  @ehedlund in [#24480](https://github.com/google-gemini/gemini-cli/pull/24480)
+- fix(core): ensure sandbox approvals are correctly persisted and matched for
+  proactive expansions by @galz10 in
+  [#24577](https://github.com/google-gemini/gemini-cli/pull/24577)
+- feat(cli) Scrollbar for input prompt by @jacob314 in
+  [#21992](https://github.com/google-gemini/gemini-cli/pull/21992)
+- Do not run pr-eval workflow when no steering changes detected by @alisa-alisa
+  in [#24621](https://github.com/google-gemini/gemini-cli/pull/24621)
+- Fix restoration of topic headers. by @gundermanc in
+  [#24650](https://github.com/google-gemini/gemini-cli/pull/24650)
+- feat(core): discourage update topic tool for simple tasks by @Samee24 in
+  [#24640](https://github.com/google-gemini/gemini-cli/pull/24640)
+- fix(core): ensure global temp directory is always in sandbox allowed paths by
+  @galz10 in [#24638](https://github.com/google-gemini/gemini-cli/pull/24638)
+- fix(core): detect uninitialized lines by @jacob314 in
+  [#24646](https://github.com/google-gemini/gemini-cli/pull/24646)
+- docs: update sandboxing documentation and toolSandboxing settings by @galz10
+  in [#24655](https://github.com/google-gemini/gemini-cli/pull/24655)
+- feat(cli): enhance tool confirmation UI and selection layout by @galz10 in
+  [#24376](https://github.com/google-gemini/gemini-cli/pull/24376)
+- feat(acp): add support for `/about` command by @sripasg in
+  [#24649](https://github.com/google-gemini/gemini-cli/pull/24649)
+- feat(cli): add role specific metrics to /stats by @cynthialong0-0 in
+  [#24659](https://github.com/google-gemini/gemini-cli/pull/24659)
+- split context by @jacob314 in
+  [#24623](https://github.com/google-gemini/gemini-cli/pull/24623)
+- fix(cli): remove -S from shebang to fix Windows and BSD execution by
+  @scidomino in [#24756](https://github.com/google-gemini/gemini-cli/pull/24756)
+- Fix issue where topic headers can be posted back to back by @gundermanc in
+  [#24759](https://github.com/google-gemini/gemini-cli/pull/24759)
+- fix(core): handle partial llm_request in BeforeModel hook override by
+  @krishdef7 in [#22326](https://github.com/google-gemini/gemini-cli/pull/22326)
+- fix(ui): improve narration suppression and reduce flicker by @gundermanc in
+  [#24635](https://github.com/google-gemini/gemini-cli/pull/24635)
+- fix(ui): fixed auth race condition causing logo to flicker by @devr0306 in
+  [#24652](https://github.com/google-gemini/gemini-cli/pull/24652)
+- fix(browser): remove premature browser cleanup after subagent invocation by
+  @gsquared94 in
+  [#24753](https://github.com/google-gemini/gemini-cli/pull/24753)
+- Revert "feat(core,cli): prioritize summary for topics (#24608)" by
+  @Abhijit-2592 in
+  [#24777](https://github.com/google-gemini/gemini-cli/pull/24777)
+- relax tool sandboxing overrides for plan mode to match defaults. by
+  @DavidAPierce in
+  [#24762](https://github.com/google-gemini/gemini-cli/pull/24762)
+- fix(cli): respect global environment variable allowlist by @scidomino in
+  [#24767](https://github.com/google-gemini/gemini-cli/pull/24767)
+- fix(cli): ensure skills list outputs to stdout in non-interactive environments
+  by @spencer426 in
+  [#24566](https://github.com/google-gemini/gemini-cli/pull/24566)
+- Add an eval for and fix unsafe cloning behavior. by @gundermanc in
+  [#24457](https://github.com/google-gemini/gemini-cli/pull/24457)
+- fix(policy): allow complete_task in plan mode by @abhipatel12 in
+  [#24771](https://github.com/google-gemini/gemini-cli/pull/24771)
+- feat(telemetry): add browser agent clearcut metrics by @gsquared94 in
+  [#24688](https://github.com/google-gemini/gemini-cli/pull/24688)
+- feat(cli): support selective topic expansion and click-to-expand by
+  @Abhijit-2592 in
+  [#24793](https://github.com/google-gemini/gemini-cli/pull/24793)
+- temporarily disable sandbox integration test on windows by @ehedlund in
+  [#24786](https://github.com/google-gemini/gemini-cli/pull/24786)
+- Remove flakey test by @scidomino in
+  [#24837](https://github.com/google-gemini/gemini-cli/pull/24837)
+- Alisa/approve button by @alisa-alisa in
+  [#24645](https://github.com/google-gemini/gemini-cli/pull/24645)
+- feat(hooks): display hook system messages in UI by @mbleigh in
+  [#24616](https://github.com/google-gemini/gemini-cli/pull/24616)
+- fix(core): propagate BeforeModel hook model override end-to-end by @krishdef7
+  in [#24784](https://github.com/google-gemini/gemini-cli/pull/24784)
+- chore: fix formatting for behavioral eval skill reference file by @abhipatel12
+  in [#24846](https://github.com/google-gemini/gemini-cli/pull/24846)
+- fix: use directory junctions on Windows for skill linking by @enjoykumawat in
+  [#24823](https://github.com/google-gemini/gemini-cli/pull/24823)
+- fix(cli): prevent multiple banner increments on remount by @sehoon38 in
+  [#24843](https://github.com/google-gemini/gemini-cli/pull/24843)
+- feat(acp): add /help command by @sripasg in
+  [#24839](https://github.com/google-gemini/gemini-cli/pull/24839)
+- fix(core): remove tmux alternate buffer warning by @jackwotherspoon in
+  [#24852](https://github.com/google-gemini/gemini-cli/pull/24852)
+- Improve sandbox error matching and caching by @DavidAPierce in
+  [#24550](https://github.com/google-gemini/gemini-cli/pull/24550)
+- feat(core): add agent protocol UI types and experimental flag by @mbleigh in
+  [#24275](https://github.com/google-gemini/gemini-cli/pull/24275)
+- feat(core): use experiment flags for default fetch timeouts by @yunaseoul in
+  [#24261](https://github.com/google-gemini/gemini-cli/pull/24261)
+- Revert "fix(ui): improve narration suppression and reduce flicker (#2… by
+  @gundermanc in
+  [#24857](https://github.com/google-gemini/gemini-cli/pull/24857)
+- refactor(cli): remove duplication in interactive shell awaiting input hint by
+  @JayadityaGit in
+  [#24801](https://github.com/google-gemini/gemini-cli/pull/24801)
+- refactor(core): make LegacyAgentSession dependencies optional by @mbleigh in
+  [#24287](https://github.com/google-gemini/gemini-cli/pull/24287)
+- Changelog for v0.37.0-preview.2 by @gemini-cli-robot in
+  [#24848](https://github.com/google-gemini/gemini-cli/pull/24848)
+- fix(cli): always show shell command description or actual command by @jacob314
+  in [#24774](https://github.com/google-gemini/gemini-cli/pull/24774)
+- Added flag for ept size and increased default size by @devr0306 in
+  [#24859](https://github.com/google-gemini/gemini-cli/pull/24859)
+- fix(core): dispose Scheduler to prevent McpProgress listener leak by
+  @Anjaligarhwal in
+  [#24870](https://github.com/google-gemini/gemini-cli/pull/24870)
+- fix(cli): switch default back to terminalBuffer=false and fix regressions
+  introduced for that mode by @jacob314 in
+  [#24873](https://github.com/google-gemini/gemini-cli/pull/24873)
+- feat(cli): switch to ctrl+g from ctrl-x by @jacob314 in
+  [#24861](https://github.com/google-gemini/gemini-cli/pull/24861)
+- fix: isolate concurrent browser agent instances by @gsquared94 in
+  [#24794](https://github.com/google-gemini/gemini-cli/pull/24794)
+- docs: update MCP server OAuth redirect port documentation by @adamfweidman in
+  [#24844](https://github.com/google-gemini/gemini-cli/pull/24844)
 
 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.31.0...v0.32.1
+https://github.com/google-gemini/gemini-cli/compare/v0.38.0...v0.38.2

docs/changelogs/preview.md

@@ -1,6 +1,6 @@
-# Preview release: v0.33.0-preview.4
+# Preview release: v0.39.0-preview.0
 
-Released: March 06, 2026
+Released: April 14, 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).
@@ -13,189 +13,245 @@ npm install -g @google/gemini-cli@preview
 
 ## Highlights
 
-- **Plan Mode Enhancements**: Added support for annotating plans with feedback
-  for iteration, enabling built-in research subagents in plan mode, and a new
-  `copy` subcommand.
-- **Agent and Skill Improvements**: Introduced the new `github-issue-creator`
-  skill, implemented HTTP authentication support for A2A remote agents, and
-  added support for authenticated A2A agent card discovery.
-- **CLI UX/UI Updates**: Redesigned the header to be compact with an ASCII icon,
-  inverted the context window display to show usage, and directly indicate auth
-  required state for agents.
-- **Core and ACP Enhancements**: Implemented slash command handling in ACP (for
-  `/memory`, `/init`, `/extensions`, and `/restore`), added a set models
-  interface to ACP, and centralized `read_file` limits while truncating large
-  MCP tool output.
+- **Refactored Subagents and Unified Tooling:** Consolidate subagent tools into
+  a single `invoke_subagent` tool, removed legacy wrapping tools, and improved
+  turn limits for codebase investigator.
+- **Advanced Memory and Skill Management:** Introduced `/memory` inbox for
+  reviewing extracted skills and added skill patching support, enhancing agent
+  learning and persistence.
+- **Expanded Test and Evaluation Infrastructure:** Added memory and CPU
+  performance integration test harnesses and generalized evaluation
+  infrastructure for better suite organization.
+- **Sandbox and Security Hardening:** Centralized sandbox paths for Linux and
+  macOS, enforced read-only security for async git worktree resolution, and
+  optimized Windows sandbox initialization.
+- **Enhanced CLI UX and UI Stability:** Improved scroll momentum, added a
+  `debugRainbow` setting, and resolved various memory leaks and PTY exhaustion
+  issues for a smoother terminal experience.
 
 ## What's Changed
 
-- fix(patch): cherry-pick 7ec477d to release/v0.33.0-preview.3-pr-21305 to patch
-  version v0.33.0-preview.3 and create version 0.33.0-preview.4 by
-  @gemini-cli-robot in
-  [#21349](https://github.com/google-gemini/gemini-cli/pull/21349)
-- fix(patch): cherry-pick 0135b03 to release/v0.33.0-preview.2-pr-21171
-  [CONFLICTS] by @gemini-cli-robot in
-  [#21336](https://github.com/google-gemini/gemini-cli/pull/21336)
-- fix(patch): cherry-pick 173376b to release/v0.33.0-preview.1-pr-21157 to patch
-  version v0.33.0-preview.1 and create version 0.33.0-preview.2 by
-  @gemini-cli-robot in
-  [#21300](https://github.com/google-gemini/gemini-cli/pull/21300)
-- fix(patch): cherry-pick 173376b to release/v0.33.0-preview.1-pr-21157 to patch
-  version v0.33.0-preview.1 and create version 0.33.0-preview.2 by
-  @gemini-cli-robot in
-  [#21300](https://github.com/google-gemini/gemini-cli/pull/21300)
-- fix(patch): cherry-pick 0659ad1 to release/v0.33.0-preview.0-pr-21042 to patch
-  version v0.33.0-preview.0 and create version 0.33.0-preview.1 by
-  @gemini-cli-robot in
-  [#21047](https://github.com/google-gemini/gemini-cli/pull/21047)
-- Docs: Update model docs to remove Preview Features. by @jkcinouye in
-  [#20084](https://github.com/google-gemini/gemini-cli/pull/20084)
-- docs: fix typo in installation documentation by @AdityaSharma-Git3207 in
-  [#20153](https://github.com/google-gemini/gemini-cli/pull/20153)
-- docs: add Windows PowerShell equivalents for environments and scripting by
-  @scidomino in [#20333](https://github.com/google-gemini/gemini-cli/pull/20333)
-- fix(core): parse raw ASCII buffer strings in Gaxios errors by @sehoon38 in
-  [#20626](https://github.com/google-gemini/gemini-cli/pull/20626)
-- chore(release): bump version to 0.33.0-nightly.20260227.ba149afa0 by @galz10
-  in [#20637](https://github.com/google-gemini/gemini-cli/pull/20637)
-- fix(github): use robot PAT for automated PRs to pass CLA check by @galz10 in
-  [#20641](https://github.com/google-gemini/gemini-cli/pull/20641)
-- chore/release: bump version to 0.33.0-nightly.20260228.1ca5c05d0 by
-  @gemini-cli-robot in
-  [#20644](https://github.com/google-gemini/gemini-cli/pull/20644)
-- Changelog for v0.31.0 by @gemini-cli-robot in
-  [#20634](https://github.com/google-gemini/gemini-cli/pull/20634)
-- fix: use full paths for ACP diff payloads by @JagjeevanAK in
-  [#19539](https://github.com/google-gemini/gemini-cli/pull/19539)
-- Changelog for v0.32.0-preview.0 by @gemini-cli-robot in
-  [#20627](https://github.com/google-gemini/gemini-cli/pull/20627)
-- fix: acp/zed race condition between MCP initialisation and prompt by
-  @kartikangiras in
-  [#20205](https://github.com/google-gemini/gemini-cli/pull/20205)
-- fix(cli): reset themeManager between tests to ensure isolation by
-  @NTaylorMullen in
-  [#20598](https://github.com/google-gemini/gemini-cli/pull/20598)
-- refactor(core): Extract tool parameter names as constants by @SandyTao520 in
-  [#20460](https://github.com/google-gemini/gemini-cli/pull/20460)
-- fix(cli): resolve autoThemeSwitching when background hasn't changed but theme
-  mismatches by @sehoon38 in
-  [#20706](https://github.com/google-gemini/gemini-cli/pull/20706)
-- feat(skills): add github-issue-creator skill by @sehoon38 in
-  [#20709](https://github.com/google-gemini/gemini-cli/pull/20709)
-- fix(cli): allow sub-agent confirmation requests in UI while preventing
-  background flicker by @abhipatel12 in
-  [#20722](https://github.com/google-gemini/gemini-cli/pull/20722)
-- Merge User and Agent Card Descriptions #20849 by @adamfweidman in
-  [#20850](https://github.com/google-gemini/gemini-cli/pull/20850)
-- fix(core): reduce LLM-based loop detection false positives by @SandyTao520 in
-  [#20701](https://github.com/google-gemini/gemini-cli/pull/20701)
-- fix(plan): deflake plan mode integration tests by @Adib234 in
-  [#20477](https://github.com/google-gemini/gemini-cli/pull/20477)
-- Add /unassign support by @scidomino in
-  [#20864](https://github.com/google-gemini/gemini-cli/pull/20864)
-- feat(core): implement HTTP authentication support for A2A remote agents by
+- refactor(plan): simplify policy priorities and consolidate read-only rules by
+  @ruomengz in [#24849](https://github.com/google-gemini/gemini-cli/pull/24849)
+- feat(test-utils): add memory usage integration test harness by @sripasg in
+  [#24876](https://github.com/google-gemini/gemini-cli/pull/24876)
+- feat(memory): add /memory inbox command for reviewing extracted skills by
   @SandyTao520 in
-  [#20510](https://github.com/google-gemini/gemini-cli/pull/20510)
-- feat(core): centralize read_file limits and update gemini-3 description by
+  [#24544](https://github.com/google-gemini/gemini-cli/pull/24544)
+- chore(release): bump version to 0.39.0-nightly.20260408.e77b22e63 by
+  @gemini-cli-robot in
+  [#24939](https://github.com/google-gemini/gemini-cli/pull/24939)
+- fix(core): ensure robust sandbox cleanup in all process execution paths by
+  @ehedlund in [#24763](https://github.com/google-gemini/gemini-cli/pull/24763)
+- chore: update ink version to 6.6.8 by @jacob314 in
+  [#24934](https://github.com/google-gemini/gemini-cli/pull/24934)
+- Changelog for v0.38.0-preview.0 by @gemini-cli-robot in
+  [#24938](https://github.com/google-gemini/gemini-cli/pull/24938)
+- chore: ignore conductor directory by @JayadityaGit in
+  [#22128](https://github.com/google-gemini/gemini-cli/pull/22128)
+- Changelog for v0.37.0 by @gemini-cli-robot in
+  [#24940](https://github.com/google-gemini/gemini-cli/pull/24940)
+- feat(plan): require user confirmation for activate_skill in Plan Mode by
+  @ruomengz in [#24946](https://github.com/google-gemini/gemini-cli/pull/24946)
+- feat(test-utils): add CPU performance integration test harness by @sripasg in
+  [#24951](https://github.com/google-gemini/gemini-cli/pull/24951)
+- fix(cli-ui): enable Ctrl+Backspace for word deletion in Windows Terminal by
+  @dogukanozen in
+  [#21447](https://github.com/google-gemini/gemini-cli/pull/21447)
+- test(sdk): add unit tests for GeminiCliSession by @AdamyaSingh7 in
+  [#21897](https://github.com/google-gemini/gemini-cli/pull/21897)
+- fix(core): resolve windows symlink bypass and stabilize sandbox integration
+  tests by @ehedlund in
+  [#24834](https://github.com/google-gemini/gemini-cli/pull/24834)
+- fix(cli): restore file path display in edit and write tool confirmations by
+  @jwhelangoog in
+  [#24974](https://github.com/google-gemini/gemini-cli/pull/24974)
+- feat(core): refine shell tool description display logic by @jwhelangoog in
+  [#24903](https://github.com/google-gemini/gemini-cli/pull/24903)
+- fix(core): dynamic session ID injection to resolve resume bugs by @scidomino
+  in [#24972](https://github.com/google-gemini/gemini-cli/pull/24972)
+- Update ink version to 6.6.9 by @jacob314 in
+  [#24980](https://github.com/google-gemini/gemini-cli/pull/24980)
+- Generalize evals infra to support more types of evals, organization and
+  queuing of named suites by @gundermanc in
+  [#24941](https://github.com/google-gemini/gemini-cli/pull/24941)
+- fix(cli): optimize startup with lightweight parent process by @sehoon38 in
+  [#24667](https://github.com/google-gemini/gemini-cli/pull/24667)
+- refactor(sandbox): use centralized sandbox paths in macOS Seatbelt
+  implementation by @ehedlund in
+  [#24984](https://github.com/google-gemini/gemini-cli/pull/24984)
+- feat(cli): refine tool output formatting for compact mode by @jwhelangoog in
+  [#24677](https://github.com/google-gemini/gemini-cli/pull/24677)
+- fix(sdk): skip broken sendStream tests to unblock nightly by @SandyTao520 in
+  [#25000](https://github.com/google-gemini/gemini-cli/pull/25000)
+- refactor(core): use centralized path resolution for Linux sandbox by @ehedlund
+  in [#24985](https://github.com/google-gemini/gemini-cli/pull/24985)
+- Support ctrl+shift+g by @jacob314 in
+  [#25035](https://github.com/google-gemini/gemini-cli/pull/25035)
+- feat(core): refactor subagent tool to unified invoke_subagent tool by
+  @abhipatel12 in
+  [#24489](https://github.com/google-gemini/gemini-cli/pull/24489)
+- fix(core): add explicit git identity env vars to prevent sandbox checkpointing
+  error by @mrpmohiburrahman in
+  [#19775](https://github.com/google-gemini/gemini-cli/pull/19775)
+- fix: respect hideContextPercentage when FooterConfigDialog is closed without
+  changes by @chernistry in
+  [#24773](https://github.com/google-gemini/gemini-cli/pull/24773)
+- fix(cli): suppress unhandled AbortError logs during request cancellation by
+  @euxaristia in
+  [#22621](https://github.com/google-gemini/gemini-cli/pull/22621)
+- Automated documentation audit by @g-samroberts in
+  [#24567](https://github.com/google-gemini/gemini-cli/pull/24567)
+- feat(cli): implement useAgentStream hook by @mbleigh in
+  [#24292](https://github.com/google-gemini/gemini-cli/pull/24292)
+- refactor(plan) Clean default plan toml by @ruomengz in
+  [#25037](https://github.com/google-gemini/gemini-cli/pull/25037)
+- refactor(core): remove legacy subagent wrapping tools by @abhipatel12 in
+  [#25053](https://github.com/google-gemini/gemini-cli/pull/25053)
+- fix(core): honor retryDelay in RetryInfo for 503 errors by @yunaseoul in
+  [#25057](https://github.com/google-gemini/gemini-cli/pull/25057)
+- fix(core): remediate subagent memory leaks using AbortSignal in MessageBus by
+  @abhipatel12 in
+  [#25048](https://github.com/google-gemini/gemini-cli/pull/25048)
+- feat(cli): wire up useAgentStream in AppContainer by @mbleigh in
+  [#24297](https://github.com/google-gemini/gemini-cli/pull/24297)
+- feat(core): migrate chat recording to JSONL streaming by @spencer426 in
+  [#23749](https://github.com/google-gemini/gemini-cli/pull/23749)
+- fix(core): clear 5-minute timeouts in oauth flow to prevent memory leaks by
+  @spencer426 in
+  [#24968](https://github.com/google-gemini/gemini-cli/pull/24968)
+- fix(sandbox): centralize async git worktree resolution and enforce read-only
+  security by @ehedlund in
+  [#25040](https://github.com/google-gemini/gemini-cli/pull/25040)
+- feat(test): add high-volume shell test and refine perf harness by @sripasg in
+  [#24983](https://github.com/google-gemini/gemini-cli/pull/24983)
+- fix(core): silently handle EPERM when listing dir structure by @scidomino in
+  [#25066](https://github.com/google-gemini/gemini-cli/pull/25066)
+- Changelog for v0.37.1 by @gemini-cli-robot in
+  [#25055](https://github.com/google-gemini/gemini-cli/pull/25055)
+- fix: decode Uint8Array and multi-byte UTF-8 in API error messages by
+  @kimjune01 in [#23341](https://github.com/google-gemini/gemini-cli/pull/23341)
+- Automated documentation audit results by @g-samroberts in
+  [#22755](https://github.com/google-gemini/gemini-cli/pull/22755)
+- debugging(ui): add optional debugRainbow setting by @jacob314 in
+  [#25088](https://github.com/google-gemini/gemini-cli/pull/25088)
+- fix: resolve lifecycle memory leaks by cleaning up listeners and root closures
+  by @spencer426 in
+  [#25049](https://github.com/google-gemini/gemini-cli/pull/25049)
+- docs(cli): updates f12 description to be more precise by @JayadityaGit in
+  [#15816](https://github.com/google-gemini/gemini-cli/pull/15816)
+- fix(cli): mark /settings as unsafe to run concurrently by @jacob314 in
+  [#25061](https://github.com/google-gemini/gemini-cli/pull/25061)
+- fix(core): remove buffer slice to prevent OOM on large output streams by
+  @spencer426 in
+  [#25094](https://github.com/google-gemini/gemini-cli/pull/25094)
+- feat(core): persist subagent agentId in tool call records by @abhipatel12 in
+  [#25092](https://github.com/google-gemini/gemini-cli/pull/25092)
+- chore(core): increase codebase investigator turn limits to 50 by @abhipatel12
+  in [#25125](https://github.com/google-gemini/gemini-cli/pull/25125)
+- refactor(core): consolidate execute() arguments into ExecuteOptions by
+  @mbleigh in [#25101](https://github.com/google-gemini/gemini-cli/pull/25101)
+- feat(core): add Strategic Re-evaluation guidance to system prompt by
   @aishaneeshah in
-  [#20619](https://github.com/google-gemini/gemini-cli/pull/20619)
-- Do not block CI on evals by @gundermanc in
-  [#20870](https://github.com/google-gemini/gemini-cli/pull/20870)
-- document node limitation for shift+tab by @scidomino in
-  [#20877](https://github.com/google-gemini/gemini-cli/pull/20877)
-- Add install as an option when extension is selected. by @DavidAPierce in
-  [#20358](https://github.com/google-gemini/gemini-cli/pull/20358)
-- Update CODEOWNERS for README.md reviewers by @g-samroberts in
-  [#20860](https://github.com/google-gemini/gemini-cli/pull/20860)
-- feat(core): truncate large MCP tool output by @SandyTao520 in
-  [#19365](https://github.com/google-gemini/gemini-cli/pull/19365)
-- Subagent activity UX. by @gundermanc in
-  [#17570](https://github.com/google-gemini/gemini-cli/pull/17570)
-- style(cli) : Dialog pattern for /hooks Command by @AbdulTawabJuly in
-  [#17930](https://github.com/google-gemini/gemini-cli/pull/17930)
-- feat: redesign header to be compact with ASCII icon by @keithguerin in
-  [#18713](https://github.com/google-gemini/gemini-cli/pull/18713)
-- fix(core): ensure subagents use qualified MCP tool names by @abhipatel12 in
-  [#20801](https://github.com/google-gemini/gemini-cli/pull/20801)
-- feat(core): support authenticated A2A agent card discovery by @SandyTao520 in
-  [#20622](https://github.com/google-gemini/gemini-cli/pull/20622)
-- refactor(cli): fully remove React anti patterns, improve type safety and fix
-  UX oversights in SettingsDialog.tsx by @psinha40898 in
-  [#18963](https://github.com/google-gemini/gemini-cli/pull/18963)
-- Adding MCPOAuthProvider implementing the MCPSDK OAuthClientProvider by
-  @Nayana-Parameswarappa in
-  [#20121](https://github.com/google-gemini/gemini-cli/pull/20121)
-- feat(core): add tool name validation in TOML policy files by @allenhutchison
-  in [#19281](https://github.com/google-gemini/gemini-cli/pull/19281)
-- docs: fix broken markdown links in main README.md by @Hamdanbinhashim in
-  [#20300](https://github.com/google-gemini/gemini-cli/pull/20300)
-- refactor(core): replace manual syncPlanModeTools with declarative policy rules
-  by @jerop in [#20596](https://github.com/google-gemini/gemini-cli/pull/20596)
-- fix(core): increase default headers timeout to 5 minutes by @gundermanc in
-  [#20890](https://github.com/google-gemini/gemini-cli/pull/20890)
-- feat(admin): enable 30 day default retention for chat history & remove warning
-  by @skeshive in
-  [#20853](https://github.com/google-gemini/gemini-cli/pull/20853)
-- feat(plan): support annotating plans with feedback for iteration by @Adib234
-  in [#20876](https://github.com/google-gemini/gemini-cli/pull/20876)
-- Add some dos and don'ts to behavioral evals README. by @gundermanc in
-  [#20629](https://github.com/google-gemini/gemini-cli/pull/20629)
-- fix(core): skip telemetry logging for AbortError exceptions by @yunaseoul in
-  [#19477](https://github.com/google-gemini/gemini-cli/pull/19477)
-- fix(core): restrict "System: Please continue" invalid stream retry to Gemini 2
-  models by @SandyTao520 in
-  [#20897](https://github.com/google-gemini/gemini-cli/pull/20897)
-- ci(evals): only run evals in CI if prompts or tools changed by @gundermanc in
-  [#20898](https://github.com/google-gemini/gemini-cli/pull/20898)
-- Build binary by @aswinashok44 in
-  [#18933](https://github.com/google-gemini/gemini-cli/pull/18933)
-- Code review fixes as a pr by @jacob314 in
-  [#20612](https://github.com/google-gemini/gemini-cli/pull/20612)
-- fix(ci): handle empty APP_ID in stale PR closer by @bdmorgan in
-  [#20919](https://github.com/google-gemini/gemini-cli/pull/20919)
-- feat(cli): invert context window display to show usage by @keithguerin in
-  [#20071](https://github.com/google-gemini/gemini-cli/pull/20071)
-- fix(plan): clean up session directories and plans on deletion by @jerop in
-  [#20914](https://github.com/google-gemini/gemini-cli/pull/20914)
-- fix(core): enforce optionality for API response fields in code_assist by
-  @sehoon38 in [#20714](https://github.com/google-gemini/gemini-cli/pull/20714)
-- feat(extensions): add support for plan directory in extension manifest by
-  @mahimashanware in
-  [#20354](https://github.com/google-gemini/gemini-cli/pull/20354)
-- feat(plan): enable built-in research subagents in plan mode by @Adib234 in
-  [#20972](https://github.com/google-gemini/gemini-cli/pull/20972)
-- feat(agents): directly indicate auth required state by @adamfweidman in
-  [#20986](https://github.com/google-gemini/gemini-cli/pull/20986)
-- fix(cli): wait for background auto-update before relaunching by @scidomino in
-  [#20904](https://github.com/google-gemini/gemini-cli/pull/20904)
-- fix: pre-load @scripts/copy_files.js references from external editor prompts
-  by @kartikangiras in
-  [#20963](https://github.com/google-gemini/gemini-cli/pull/20963)
-- feat(evals): add behavioral evals for ask_user tool by @Adib234 in
-  [#20620](https://github.com/google-gemini/gemini-cli/pull/20620)
-- refactor common settings logic for skills,agents by @ishaanxgupta in
-  [#17490](https://github.com/google-gemini/gemini-cli/pull/17490)
-- Update docs-writer skill with new resource by @g-samroberts in
-  [#20917](https://github.com/google-gemini/gemini-cli/pull/20917)
-- fix(cli): pin clipboardy to ~5.2.x by @scidomino in
-  [#21009](https://github.com/google-gemini/gemini-cli/pull/21009)
-- feat: Implement slash command handling in ACP for
-  `/memory`,`/init`,`/extensions` and `/restore` by @sripasg in
-  [#20528](https://github.com/google-gemini/gemini-cli/pull/20528)
-- Docs/add hooks reference by @AadithyaAle in
-  [#20961](https://github.com/google-gemini/gemini-cli/pull/20961)
-- feat(plan): add copy subcommand to plan (#20491) by @ruomengz in
-  [#20988](https://github.com/google-gemini/gemini-cli/pull/20988)
-- fix(core): sanitize and length-check MCP tool qualified names by @abhipatel12
-  in [#20987](https://github.com/google-gemini/gemini-cli/pull/20987)
-- Format the quota/limit style guide. by @g-samroberts in
-  [#21017](https://github.com/google-gemini/gemini-cli/pull/21017)
-- fix(core): send shell output to model on cancel by @devr0306 in
-  [#20501](https://github.com/google-gemini/gemini-cli/pull/20501)
-- remove hardcoded tiername when missing tier by @sehoon38 in
-  [#21022](https://github.com/google-gemini/gemini-cli/pull/21022)
-- feat(acp): add set models interface by @skeshive in
-  [#20991](https://github.com/google-gemini/gemini-cli/pull/20991)
+  [#25062](https://github.com/google-gemini/gemini-cli/pull/25062)
+- fix(core): preserve shell execution config fields on update by
+  @jasonmatthewsuhari in
+  [#25113](https://github.com/google-gemini/gemini-cli/pull/25113)
+- docs: add vi shortcuts and clarify MCP sandbox setup by @chrisjcthomas in
+  [#21679](https://github.com/google-gemini/gemini-cli/pull/21679)
+- fix(cli): pass session id to interactive shell executions by
+  @jasonmatthewsuhari in
+  [#25114](https://github.com/google-gemini/gemini-cli/pull/25114)
+- fix(cli): resolve text sanitization data loss due to C1 control characters by
+  @euxaristia in
+  [#22624](https://github.com/google-gemini/gemini-cli/pull/22624)
+- feat(core): add large memory regression test by @cynthialong0-0 in
+  [#25059](https://github.com/google-gemini/gemini-cli/pull/25059)
+- fix(core): resolve PTY exhaustion and orphan MCP subprocess leaks by
+  @spencer426 in
+  [#25079](https://github.com/google-gemini/gemini-cli/pull/25079)
+- chore(deps): update vulnerable dependencies via npm audit fix by @scidomino in
+  [#25140](https://github.com/google-gemini/gemini-cli/pull/25140)
+- perf(sandbox): optimize Windows sandbox initialization via native ACL
+  application by @ehedlund in
+  [#25077](https://github.com/google-gemini/gemini-cli/pull/25077)
+- chore: switch from keytar to @github/keytar by @cocosheng-g in
+  [#25143](https://github.com/google-gemini/gemini-cli/pull/25143)
+- fix: improve audio MIME normalization and validation in file reads by
+  @junaiddshaukat in
+  [#21636](https://github.com/google-gemini/gemini-cli/pull/21636)
+- docs: Update docs-audit to include changes in PR body by @g-samroberts in
+  [#25153](https://github.com/google-gemini/gemini-cli/pull/25153)
+- docs: correct documentation for enforced authentication type by @cocosheng-g
+  in [#25142](https://github.com/google-gemini/gemini-cli/pull/25142)
+- fix(cli): exclude update_topic from confirmation queue count by @Abhijit-2592
+  in [#24945](https://github.com/google-gemini/gemini-cli/pull/24945)
+- Memory fix for trace's streamWrapper. by @anthraxmilkshake in
+  [#25089](https://github.com/google-gemini/gemini-cli/pull/25089)
+- fix(core): fix quota footer for non-auto models and improve display by
+  @jackwotherspoon in
+  [#25121](https://github.com/google-gemini/gemini-cli/pull/25121)
+- docs(contributing): clarify self-assignment policy for issues by @jmr in
+  [#23087](https://github.com/google-gemini/gemini-cli/pull/23087)
+- feat(core): add skill patching support with /memory inbox integration by
+  @SandyTao520 in
+  [#25148](https://github.com/google-gemini/gemini-cli/pull/25148)
+- Stop suppressing thoughts and text in model response by @gundermanc in
+  [#25073](https://github.com/google-gemini/gemini-cli/pull/25073)
+- fix(release): prefix git hash in nightly versions to prevent semver
+  normalization by @SandyTao520 in
+  [#25304](https://github.com/google-gemini/gemini-cli/pull/25304)
+- feat(cli): extract QuotaContext and resolve infinite render loop by @Adib234
+  in [#24959](https://github.com/google-gemini/gemini-cli/pull/24959)
+- refactor(core): extract and centralize sandbox path utilities by @ehedlund in
+  [#25305](https://github.com/google-gemini/gemini-cli/pull/25305)
+- feat(ui): added enhancements to scroll momentum by @devr0306 in
+  [#24447](https://github.com/google-gemini/gemini-cli/pull/24447)
+- fix(core): replace custom binary detection with isbinaryfile to correctly
+  handle UTF-8 (U+FFFD) by @Anjaligarhwal in
+  [#25297](https://github.com/google-gemini/gemini-cli/pull/25297)
+- feat(agent): implement tool-controlled display protocol (Steps 2-3) by
+  @mbleigh in [#25134](https://github.com/google-gemini/gemini-cli/pull/25134)
+- Stop showing scrollbar unless we are in terminalBuffer mode by @jacob314 in
+  [#25320](https://github.com/google-gemini/gemini-cli/pull/25320)
+- feat: support auth block in MCP servers config in agents by @TanmayVartak in
+  [#24770](https://github.com/google-gemini/gemini-cli/pull/24770)
+- fix(core): expose GEMINI_PLANS_DIR to hook environment by @Adib234 in
+  [#25296](https://github.com/google-gemini/gemini-cli/pull/25296)
+- feat(core): implement silent fallback for Plan Mode model routing by @jerop in
+  [#25317](https://github.com/google-gemini/gemini-cli/pull/25317)
+- fix: correct redirect count increment in fetchJson by @KevinZhao in
+  [#24896](https://github.com/google-gemini/gemini-cli/pull/24896)
+- fix(core): prevent secondary crash in ModelRouterService finally block by
+  @gundermanc in
+  [#25333](https://github.com/google-gemini/gemini-cli/pull/25333)
+- feat(core): introduce decoupled ContextManager and Sidecar architecture by
+  @joshualitt in
+  [#24752](https://github.com/google-gemini/gemini-cli/pull/24752)
+- docs(core): update generalist agent documentation by @abhipatel12 in
+  [#25325](https://github.com/google-gemini/gemini-cli/pull/25325)
+- chore(mcp): check MCP error code over brittle string match by @jackwotherspoon
+  in [#25381](https://github.com/google-gemini/gemini-cli/pull/25381)
+- feat(plan): update plan mode prompt to allow showing plan content by @ruomengz
+  in [#25058](https://github.com/google-gemini/gemini-cli/pull/25058)
+- test(core): improve sandbox integration test coverage and fix OS-specific
+  failures by @ehedlund in
+  [#25307](https://github.com/google-gemini/gemini-cli/pull/25307)
+- fix(core): use debug level for keychain fallback logging by @ehedlund in
+  [#25398](https://github.com/google-gemini/gemini-cli/pull/25398)
+- feat(test): add a performance test in asian language by @cynthialong0-0 in
+  [#25392](https://github.com/google-gemini/gemini-cli/pull/25392)
+- feat(cli): enable mouse clicking for cursor positioning in AskUser multi-line
+  answers by @Adib234 in
+  [#24630](https://github.com/google-gemini/gemini-cli/pull/24630)
+- fix(core): detect kmscon terminal as supporting true color by @claygeo in
+  [#25282](https://github.com/google-gemini/gemini-cli/pull/25282)
+- ci: add agent session drift check workflow by @adamfweidman in
+  [#25389](https://github.com/google-gemini/gemini-cli/pull/25389)
+- use macos-latest-large runner where applicable. by @scidomino in
+  [#25413](https://github.com/google-gemini/gemini-cli/pull/25413)
+- Changelog for v0.37.2 by @gemini-cli-robot in
+  [#25336](https://github.com/google-gemini/gemini-cli/pull/25336)
 
 **Full Changelog**:
-https://github.com/google-gemini/gemini-cli/compare/v0.32.0-preview.0...v0.33.0-preview.4
+https://github.com/google-gemini/gemini-cli/compare/v0.38.0-preview.0...v0.39.0-preview.0

docs/cli/acp-mode.md

@@ -0,0 +1,126 @@
+# ACP Mode
+
+ACP (Agent Client Protocol) mode is a special operational mode of Gemini CLI
+designed for programmatic control, primarily for IDE and other developer tool
+integrations. It uses a JSON-RPC protocol over stdio to communicate between
+Gemini CLI agent and a client.
+
+To start Gemini CLI in ACP mode, use the `--acp` flag:
+
+```bash
+gemini --acp
+```
+
+## Agent Client Protocol (ACP)
+
+ACP is an open protocol that standardizes how AI coding agents communicate with
+code editors and IDEs. It addresses the challenge of fragmented distribution,
+where agents traditionally needed custom integrations for each client. With ACP,
+developers can implement their agent once, and it becomes compatible with any
+ACP-compliant editor.
+
+For a comprehensive introduction to ACP, including its architecture and
+benefits, refer to the official
+[ACP Introduction](https://agentclientprotocol.com/get-started/introduction)
+documentation.
+
+### Existing integrations using ACP
+
+The ACP Agent Registry simplifies the distribution and management of
+ACP-compatible agents across various IDEs. Gemini CLI is an ACP-compatible agent
+and can be found in this registry.
+
+For more general information about the registry, and how to use it with specific
+IDEs like JetBrains and Zed, refer to the
+[IDE Integration](../ide-integration/index.md) documentation.
+
+You can also find more information on the official
+[ACP Agent Registry](https://agentclientprotocol.com/get-started/registry) page.
+
+## Architecture and protocol basics
+
+ACP mode establishes a client-server relationship between your tool (the client)
+and Gemini CLI (the server).
+
+- **Communication:** The entire communication happens over standard input/output
+  (stdio) using the JSON-RPC 2.0 protocol.
+- **Client's role:** The client is responsible for sending requests (for
+  example, prompts) and handling responses and notifications from Gemini CLI.
+- **Gemini CLI's role:** In ACP mode, Gemini CLI listens for incoming JSON-RPC
+  requests, processes them, and sends back responses.
+
+The core of the ACP implementation can be found in
+`packages/cli/src/acp/acpClient.ts`.
+
+### Extending with MCP
+
+ACP can be used with the Model Context Protocol (MCP). This lets an ACP client
+(like an IDE) expose its own functionality as "tools" that the Gemini model can
+use.
+
+1.  The client implements an **MCP server** that advertises its tools.
+2.  During the ACP `initialize` handshake, the client provides the connection
+    details for its MCP server.
+3.  Gemini CLI connects to the MCP server, discovers the available tools, and
+    makes them available to the AI model.
+4.  When the model decides to use one of these tools, Gemini CLI sends a tool
+    call request to the MCP server.
+
+This mechanism lets for a powerful, two-way integration where the agent can
+leverage the IDE's capabilities to perform tasks. The MCP client logic is in
+`packages/core/src/tools/mcp-client.ts`.
+
+## Capabilities and supported methods
+
+The ACP protocol exposes a number of methods for ACP clients (for example IDEs)
+to control Gemini CLI.
+
+### Core methods
+
+- `initialize`: Establishes the initial connection and lets the client to
+  register its MCP server.
+- `authenticate`: Authenticates the user.
+- `newSession`: Starts a new chat session.
+- `loadSession`: Loads a previous session.
+- `prompt`: Sends a prompt to the agent.
+- `cancel`: Cancels an ongoing prompt.
+
+### Session control
+
+- `setSessionMode`: Allows changing the approval level for tool calls (for
+  example, to `auto-approve`).
+- `unstable_setSessionModel`: Changes the model for the current session.
+
+### File system proxy
+
+ACP includes a proxied file system service. This means that when the agent needs
+to read or write files, it does so through the ACP client. This is a security
+feature that ensures the agent only has access to the files that the client (and
+by extension, the user) has explicitly allowed.
+
+## Debugging and telemetry
+
+You can get insights into the ACP communication and the agent's behavior through
+debugging logs and telemetry.
+
+### Debugging logs
+
+To enable general debugging logs, start Gemini CLI with the `--debug` flag:
+
+```bash
+gemini --acp --debug
+```
+
+### Telemetry
+
+For more detailed telemetry, you can use the following environment variables to
+capture telemetry data to a file:
+
+- `GEMINI_TELEMETRY_ENABLED=true`
+- `GEMINI_TELEMETRY_TARGET=local`
+- `GEMINI_TELEMETRY_OUTFILE=/path/to/your/log.json`
+
+This will write a JSON log file containing detailed information about all the
+events happening within the agent, including ACP requests and responses. The
+integration test `integration-tests/acp-telemetry.test.ts` provides a working
+example of how to set this up.

docs/cli/auto-memory.md

@@ -0,0 +1,143 @@
+# Auto Memory
+
+Auto Memory is an experimental feature that mines your past Gemini CLI sessions
+in the background and turns recurring workflows into reusable
+[Agent Skills](./skills.md). You review, accept, or discard each extracted skill
+before it becomes available to future sessions.
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an experimental feature currently under active development.
+
+## Overview
+
+Every session you run with Gemini CLI is recorded locally as a transcript. Auto
+Memory scans those transcripts for procedural patterns that recur across
+sessions, then drafts each pattern as a `SKILL.md` file in a project-local
+inbox. You inspect the draft, decide whether it captures real expertise, and
+promote it to your global or workspace skills directory if you want it.
+
+You'll use Auto Memory when you want to:
+
+- **Capture team workflows** that you find yourself walking the agent through
+  more than once.
+- **Codify hard-won fixes** for project-specific landmines so future sessions
+  avoid them.
+- **Bootstrap a skills library** without writing every `SKILL.md` by hand.
+
+Auto Memory complements—but does not replace—the
+[`save_memory` tool](../tools/memory.md), which captures single facts into
+`GEMINI.md`. Auto Memory captures multi-step procedures into skills.
+
+## Prerequisites
+
+- Gemini CLI installed and authenticated.
+- At least 10 user messages across recent, idle sessions in the project. Auto
+  Memory ignores active or trivial sessions.
+
+## How to enable Auto Memory
+
+Auto Memory is off by default. Enable it in your settings file:
+
+1.  Open your global settings file at `~/.gemini/settings.json`. If you only
+    want Auto Memory in one project, edit `.gemini/settings.json` in that
+    project instead.
+
+2.  Add the experimental flag:
+
+    ```json
+    {
+      "experimental": {
+        "autoMemory": true
+      }
+    }
+    ```
+
+3.  Restart Gemini CLI. The flag requires a restart because the extraction
+    service starts during session boot.
+
+## How Auto Memory works
+
+Auto Memory runs as a background task on session startup. It does not block the
+UI, consume your interactive turns, or surface tool prompts.
+
+1.  **Eligibility scan.** The service indexes recent sessions from
+    `~/.gemini/tmp/<project>/chats/`. Sessions are eligible only if they have
+    been idle for at least three hours and contain at least 10 user messages.
+2.  **Lock acquisition.** A lock file in the project's memory directory
+    coordinates across multiple CLI instances so extraction runs at most once at
+    a time.
+3.  **Sub-agent extraction.** A specialized sub-agent (named `confucius`)
+    reviews the session index, reads any sessions that look like they contain
+    repeated procedural workflows, and drafts new `SKILL.md` files. Its
+    instructions tell it to default to creating zero skills unless the evidence
+    is strong, so most runs produce no inbox items.
+4.  **Patch validation.** If the sub-agent proposes edits to skills outside the
+    inbox (for example, an existing global skill), it writes a unified diff
+    `.patch` file. Auto Memory dry-runs each patch and discards any that do not
+    apply cleanly.
+5.  **Notification.** When a run produces new skills or patches, Gemini CLI
+    surfaces an inline message telling you how many items are waiting.
+
+## How to review extracted skills
+
+Use the `/memory inbox` slash command to open the inbox dialog at any time:
+
+**Command:** `/memory inbox`
+
+The dialog lists each draft skill with its name, description, and source
+sessions. From there you can:
+
+- **Read** the full `SKILL.md` body before deciding.
+- **Promote** a skill to your user (`~/.gemini/skills/`) or workspace
+  (`.gemini/skills/`) directory.
+- **Discard** a skill you do not want.
+- **Apply** or reject a `.patch` proposal against an existing skill.
+
+Promoted skills become discoverable in the next session and follow the standard
+[skill discovery precedence](./skills.md#skill-discovery-tiers).
+
+## How to disable Auto Memory
+
+To turn off background extraction, set the flag back to `false` in your settings
+file and restart Gemini CLI:
+
+```json
+{
+  "experimental": {
+    "autoMemory": false
+  }
+}
+```
+
+Disabling the flag stops the background service immediately on the next session
+start. Existing inbox items remain on disk; you can either drain them with
+`/memory inbox` first or remove the project memory directory manually.
+
+## Data and privacy
+
+- Auto Memory only reads session files that already exist locally on your
+  machine. Nothing is uploaded to Gemini outside the normal API calls the
+  extraction sub-agent makes during its run.
+- The sub-agent is instructed to redact secrets, tokens, and credentials it
+  encounters and to never copy large tool outputs verbatim.
+- Drafted skills live in your project's memory directory until you promote or
+  discard them. They are not automatically loaded into any session.
+
+## Limitations
+
+- The sub-agent runs on a preview Gemini Flash model. Extraction quality depends
+  on the model's ability to recognize durable patterns versus one-off incidents.
+- Auto Memory does not extract skills from the current session. It only
+  considers sessions that have been idle for three hours or more.
+- Inbox items are stored per project. Skills extracted in one workspace are not
+  visible from another until you promote them to the user-scope skills
+  directory.
+
+## Next steps
+
+- Learn how skills are discovered and activated in [Agent Skills](./skills.md).
+- Explore the [memory management tutorial](./tutorials/memory-management.md) for
+  the complementary `save_memory` and `GEMINI.md` workflows.
+- Review the experimental settings catalog in
+  [Settings](./settings.md#experimental).

docs/cli/checkpointing.md

@@ -1,9 +1,9 @@
 # Checkpointing
 
-The Gemini CLI includes a Checkpointing feature that automatically saves a
-snapshot of your project's state before any file modifications are made by
-AI-powered tools. This lets you safely experiment with and apply code changes,
-knowing you can instantly revert back to the state before the tool was run.
+Gemini CLI includes a Checkpointing feature that automatically saves a snapshot
+of your project's state before any file modifications are made by AI-powered
+tools. This lets you safely experiment with and apply code changes, knowing you
+can instantly revert back to the state before the tool was run.
 
 ## How it works
 
@@ -39,7 +39,9 @@ file in your project's temporary directory, typically located at
 The Checkpointing feature is disabled by default. To enable it, you need to edit
 your `settings.json` file.
 
-> **Note:** The `--checkpointing` command-line flag was removed in version
+<!-- prettier-ignore -->
+> [!CAUTION]
+> The `--checkpointing` command-line flag was removed in version
 > 0.11.0. Checkpointing can now only be enabled through the `settings.json`
 > configuration file.
 
@@ -70,7 +72,7 @@ To see a list of all saved checkpoints for the current project, simply run:
 
 The CLI will display a list of available checkpoint files. These file names are
 typically composed of a timestamp, the name of the file being modified, and the
-name of the tool that was about to be run (e.g.,
+name of the tool that was about to be run (for example,
 `2025-06-22T10-00-00_000Z-my-file.txt-write_file`).
 
 ### Restore a specific checkpoint

docs/cli/cli-reference.md

@@ -8,7 +8,8 @@ and parameters.
 | Command                            | Description                        | Example                                                      |
 | ---------------------------------- | ---------------------------------- | ------------------------------------------------------------ |
 | `gemini`                           | Start interactive REPL             | `gemini`                                                     |
-| `gemini "query"`                   | Query non-interactively, then exit | `gemini "explain this project"`                              |
+| `gemini -p "query"`                | Query non-interactively            | `gemini -p "summarize README.md"`                            |
+| `gemini "query"`                   | Query and continue interactively   | `gemini "explain this project"`                              |
 | `cat file \| gemini`               | Process piped content              | `cat logs.txt \| gemini`<br>`Get-Content logs.txt \| gemini` |
 | `gemini -i "query"`                | Execute and continue interactively | `gemini -i "What is the purpose of this project?"`           |
 | `gemini -r "latest"`               | Continue most recent session       | `gemini -r "latest"`                                         |
@@ -20,9 +21,24 @@ and parameters.
 
 ### Positional arguments
 
-| Argument | Type              | Description                                                                                                        |
-| -------- | ----------------- | ------------------------------------------------------------------------------------------------------------------ |
-| `query`  | string (variadic) | Positional prompt. Defaults to one-shot mode. Use `-i/--prompt-interactive` to execute and continue interactively. |
+| Argument | Type              | Description                                                                                                |
+| -------- | ----------------- | ---------------------------------------------------------------------------------------------------------- |
+| `query`  | string (variadic) | Positional prompt. Defaults to interactive mode in a TTY. Use `-p/--prompt` for non-interactive execution. |
+
+## Interactive commands
+
+These commands are available within the interactive REPL.
+
+| Command              | Description                                     |
+| -------------------- | ----------------------------------------------- |
+| `/skills reload`     | Reload discovered skills from disk              |
+| `/agents reload`     | Reload the agent registry                       |
+| `/commands reload`   | Reload custom slash commands                    |
+| `/memory reload`     | Reload context files (for example, `GEMINI.md`) |
+| `/mcp reload`        | Restart and reload MCP servers                  |
+| `/extensions reload` | Reload all active extensions                    |
+| `/help`              | Show help for all commands                      |
+| `/quit`              | Exit the interactive session                    |
 
 ## CLI Options
 
@@ -32,10 +48,11 @@ and parameters.
 | `--version`                      | `-v`  | -       | -         | Show CLI version number and exit                                                                                                                                       |
 | `--help`                         | `-h`  | -       | -         | Show help information                                                                                                                                                  |
 | `--model`                        | `-m`  | string  | `auto`    | Model to use. See [Model Selection](#model-selection) for available values.                                                                                            |
-| `--prompt`                       | `-p`  | string  | -         | Prompt text. Appended to stdin input if provided. **Deprecated:** Use positional arguments instead.                                                                    |
+| `--prompt`                       | `-p`  | string  | -         | Prompt text. Appended to stdin input if provided. Forces non-interactive mode.                                                                                         |
 | `--prompt-interactive`           | `-i`  | string  | -         | Execute prompt and continue in interactive mode                                                                                                                        |
+| `--worktree`                     | `-w`  | string  | -         | Start Gemini in a new git worktree. If no name is provided, one is generated automatically. Requires `experimental.worktrees: true` in settings.                       |
 | `--sandbox`                      | `-s`  | boolean | `false`   | Run in a sandboxed environment for safer execution                                                                                                                     |
-| `--approval-mode`                | -     | string  | `default` | Approval mode for tool execution. Choices: `default`, `auto_edit`, `yolo`                                                                                              |
+| `--approval-mode`                | -     | string  | `default` | Approval mode for tool execution. Choices: `default`, `auto_edit`, `yolo`, `plan`                                                                                      |
 | `--yolo`                         | `-y`  | boolean | `false`   | **Deprecated.** Auto-approve all actions. Use `--approval-mode=yolo` instead.                                                                                          |
 | `--experimental-acp`             | -     | boolean | -         | Start in ACP (Agent Code Pilot) mode. **Experimental feature.**                                                                                                        |
 | `--experimental-zed-integration` | -     | boolean | -         | Run in Zed editor integration mode. **Experimental feature.**                                                                                                          |
@@ -43,7 +60,7 @@ and parameters.
 | `--allowed-tools`                | -     | array   | -         | **Deprecated.** Use the [Policy Engine](../reference/policy-engine.md) instead. Tools that are allowed to run without confirmation (comma-separated or multiple flags) |
 | `--extensions`                   | `-e`  | array   | -         | List of extensions to use. If not provided, all extensions are enabled (comma-separated or multiple flags)                                                             |
 | `--list-extensions`              | `-l`  | boolean | -         | List all available extensions and exit                                                                                                                                 |
-| `--resume`                       | `-r`  | string  | -         | Resume a previous session. Use `"latest"` for most recent or index number (e.g. `--resume 5`)                                                                          |
+| `--resume`                       | `-r`  | string  | -         | Resume a previous session. Use `"latest"` for most recent or index number (for example `--resume 5`)                                                                   |
 | `--list-sessions`                | -     | boolean | -         | List available sessions for the current project and exit                                                                                                               |
 | `--delete-session`               | -     | string  | -         | Delete a session by index number (use `--list-sessions` to see available sessions)                                                                                     |
 | `--include-directories`          | -     | array   | -         | Additional directories to include in the workspace (comma-separated or multiple flags)                                                                                 |

docs/cli/creating-skills.md

@@ -14,7 +14,7 @@ skill. To use it, ask Gemini CLI to create a new skill for you.
 
 Gemini CLI will then use the `skill-creator` to generate the skill:
 
-1.  Generate a new directory for your skill (e.g., `my-new-skill/`).
+1.  Generate a new directory for your skill (for example, `my-new-skill/`).
 2.  Create a `SKILL.md` file with the necessary YAML frontmatter (`name` and
     `description`).
 3.  Create the standard resource directories: `scripts/`, `references/`, and
@@ -24,7 +24,7 @@ Gemini CLI will then use the `skill-creator` to generate the skill:
 
 If you prefer to create skills manually:
 
-1.  **Create a directory** for your skill (e.g., `my-new-skill/`).
+1.  **Create a directory** for your skill (for example, `my-new-skill/`).
 2.  **Create a `SKILL.md` file** inside the new directory.
 
 To add additional resources that support the skill, refer to the skill

docs/cli/custom-commands.md

@@ -30,7 +30,9 @@ separator (`/` or `\`) being converted to a colon (`:`).
 - A file at `<project>/.gemini/commands/git/commit.toml` becomes the namespaced
   command `/git:commit`.
 
-> [!TIP] After creating or modifying `.toml` command files, run
+<!-- prettier-ignore -->
+> [!TIP]
+> After creating or modifying `.toml` command files, run
 > `/commands reload` to pick up your changes without restarting the CLI.
 
 ## TOML file format (v1)
@@ -83,8 +85,8 @@ The model receives:
 **B. Using arguments in shell commands (inside `!{...}` blocks)**
 
 When you use `{{args}}` inside a shell injection block (`!{...}`), the arguments
-are automatically **shell-escaped** before replacement. This allows you to
-safely pass arguments to shell commands, ensuring the resulting command is
+are automatically **shell-escaped** before replacement. This lets you safely
+pass arguments to shell commands, ensuring the resulting command is
 syntactically correct and secure while preventing command injection
 vulnerabilities.
 
@@ -103,8 +105,8 @@ 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`.
-3. Inside: The second `{{args}}` is replaced with the escaped version (e.g., on
-   Linux: `"It\'s complicated"`).
+3. Inside: The second `{{args}}` is replaced with the escaped version (for
+   example, on Linux: `"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.
@@ -114,13 +116,13 @@ When you run `/grep-code It's complicated`:
 If your `prompt` does **not** contain the special placeholder `{{args}}`, the
 CLI uses a default behavior for handling arguments.
 
-If you provide arguments to the command (e.g., `/mycommand arg1`), the CLI will
-append the full command you typed to the end of the prompt, separated by two
-newlines. This allows the model to see both the original instructions and the
-specific arguments you just provided.
+If you provide arguments to the command (for example, `/mycommand arg1`), the
+CLI will append the full command you typed to the end of the prompt, separated
+by two newlines. This allows the model to see both the original instructions and
+the specific arguments you just provided.
 
-If you do **not** provide any arguments (e.g., `/mycommand`), the prompt is sent
-to the model exactly as it is, with nothing appended.
+If you do **not** provide any arguments (for example, `/mycommand`), the prompt
+is sent to the model exactly as it is, with nothing appended.
 
 **Example (`changelog.toml`):**
 
@@ -177,16 +179,16 @@ ensure that only intended commands can be run.
     automatically shell-escaped (see
     [Context-Aware Injection](#1-context-aware-injection-with-args) above).
 3.  **Robust parsing:** The parser correctly handles complex shell commands that
-    include nested braces, such as JSON payloads. **Note:** The content inside
-    `!{...}` must have balanced braces (`{` and `}`). If you need to execute a
-    command containing unbalanced braces, consider wrapping it in an external
-    script file and calling the script within the `!{...}` block.
+    include nested braces, such as JSON payloads. The content inside `!{...}`
+    must have balanced braces (`{` and `}`). If you need to execute a command
+    containing unbalanced braces, consider wrapping it in an external script
+    file and calling the script within the `!{...}` block.
 4.  **Security check and confirmation:** The CLI performs a security check on
     the final, resolved command (after arguments are escaped and substituted). A
     dialog will appear showing the exact command(s) to be executed.
 5.  **Execution and error reporting:** The command is executed. If the command
     fails, the output injected into the prompt will include the error messages
-    (stderr) followed by a status line, e.g.,
+    (stderr) followed by a status line, for example,
     `[Shell command exited with code 1]`. This helps the model understand the
     context of the failure.
 
@@ -227,9 +229,10 @@ operate on specific files.
 
 - **File injection**: `@{path/to/file.txt}` is replaced by the content of
   `file.txt`.
-- **Multimodal support**: If the path points to a supported image (e.g., PNG,
-  JPEG), PDF, audio, or video file, it will be correctly encoded and injected as
-  multimodal input. Other binary files are handled gracefully and skipped.
+- **Multimodal support**: If the path points to a supported image (for example,
+  PNG, JPEG), PDF, audio, or video file, it will be correctly encoded and
+  injected as multimodal input. Other binary files are handled gracefully and
+  skipped.
 - **Directory listing**: `@{path/to/dir}` is traversed and each file present
   within the directory and all subdirectories is inserted into the prompt. This
   respects `.gitignore` and `.geminiignore` if enabled.

docs/cli/enterprise.md

@@ -5,9 +5,11 @@ and managing Gemini CLI in an enterprise environment. By leveraging system-level
 settings, administrators can enforce security policies, manage tool access, and
 ensure a consistent experience for all users.
 
-> **A note on security:** The patterns described in this document are intended
-> to help administrators create a more controlled and secure environment for
-> using Gemini CLI. However, they should not be considered a foolproof security
+<!-- prettier-ignore -->
+> [!WARNING]
+> The patterns described in this document are intended to help
+> administrators create a more controlled and secure environment for using
+> Gemini CLI. However, they should not be considered a foolproof security
 > boundary. A determined user with sufficient privileges on their local machine
 > may still be able to circumvent these configurations. These measures are
 > designed to prevent accidental misuse and enforce corporate policy in a
@@ -173,8 +175,8 @@ the enterprise settings are always loaded with the highest precedence.
 **Example wrapper script:**
 
 Administrators can create a script named `gemini` and place it in a directory
-that appears earlier in the user's `PATH` than the actual Gemini CLI binary
-(e.g., `/usr/local/bin/gemini`).
+that appears earlier in the user's `PATH` than the actual Gemini CLI binary (for
+example, `/usr/local/bin/gemini`).
 
 ```bash
 #!/bin/bash
@@ -280,10 +282,12 @@ environment to a blocklist.
 }
 ```
 
-**Security note:** Blocklisting with `excludeTools` is less secure than
-allowlisting with `coreTools`, as it relies on blocking known-bad commands, and
-clever users may find ways to bypass simple string-based blocks. **Allowlisting
-is the recommended approach.**
+<!-- prettier-ignore -->
+> [!WARNING]
+> Blocklisting with `excludeTools` is less secure than
+> allowlisting with `coreTools`, as it relies on blocking known-bad commands,
+> and clever users may find ways to bypass simple string-based blocks.
+> **Allowlisting is the recommended approach.**
 
 ### Disabling YOLO mode
 
@@ -321,9 +325,9 @@ User. When it comes to the `mcpServers` object, these configurations are
 1.  **Merging:** The lists of servers from all three levels are combined into a
     single list.
 2.  **Precedence:** If a server with the **same name** is defined at multiple
-    levels (e.g., a server named `corp-api` exists in both system and user
-    settings), the definition from the highest-precedence level is used. The
-    order of precedence is: **System > Workspace > User**.
+    levels (for example, a server named `corp-api` exists in both system and
+    user settings), the definition from the highest-precedence level is used.
+    The order of precedence is: **System > Workspace > User**.
 
 This means a user **cannot** override the definition of a server that is already
 defined in the system-level settings. However, they **can** add new servers with
@@ -339,8 +343,8 @@ canonical servers and adding their names to an allowlist.
 For even greater security, especially when dealing with third-party MCP servers,
 you can restrict which specific tools from a server are exposed to the model.
 This is done using the `includeTools` and `excludeTools` properties within a
-server's definition. This allows you to use a subset of tools from a server
-without allowing potentially dangerous ones.
+server's definition. This lets you use a subset of tools from a server without
+allowing potentially dangerous ones.
 
 Following the principle of least privilege, it is highly recommended to use
 `includeTools` to create an allowlist of only the necessary tools.
@@ -477,9 +481,8 @@ an environment variable, but it can also be enforced for custom tools via the
 ## Telemetry and auditing
 
 For auditing and monitoring purposes, you can configure Gemini CLI to send
-telemetry data to a central location. This allows you to track tool usage and
-other events. For more information, see the
-[telemetry documentation](./telemetry.md).
+telemetry data to a central location. This lets you track tool usage and other
+events. For more information, see the [telemetry documentation](./telemetry.md).
 
 **Example:** Enable telemetry and send it to a local OTLP collector. If
 `otlpEndpoint` is not specified, it defaults to `http://localhost:4317`.
@@ -494,21 +497,27 @@ other events. For more information, see the
 }
 ```
 
-**Note:** Ensure that `logPrompts` is set to `false` in an enterprise setting to
-avoid collecting potentially sensitive information from user prompts.
+<!-- prettier-ignore -->
+> [!NOTE]
+> Ensure that `logPrompts` is set to `false` in an enterprise setting to
+> avoid collecting potentially sensitive information from user prompts.
 
 ## Authentication
 
 You can enforce a specific authentication method for all users by setting the
-`enforcedAuthType` in the system-level `settings.json` file. This prevents users
-from choosing a different authentication method. See the
-[Authentication docs](../get-started/authentication.md) for more details.
+`security.auth.enforcedType` in the system-level `settings.json` file. This
+prevents users from choosing a different authentication method. See the
+[Authentication docs](../get-started/authentication.mdx) for more details.
 
 **Example:** Enforce the use of Google login for all users.
 
 ```json
 {
-  "enforcedAuthType": "oauth-personal"
+  "security": {
+    "auth": {
+      "enforcedType": "oauth-personal"
+    }
+  }
 }
 ```
 

docs/cli/gemini-ignore.md

@@ -1,9 +1,9 @@
 # Ignoring files
 
 This document provides an overview of the Gemini Ignore (`.geminiignore`)
-feature of the Gemini CLI.
+feature of Gemini CLI.
 
-The Gemini CLI includes the ability to automatically ignore files, similar to
+Gemini CLI includes the ability to automatically ignore files, similar to
 `.gitignore` (used by Git) and `.aiexclude` (used by Gemini Code Assist). Adding
 paths to your `.geminiignore` file will exclude them from tools that support
 this feature, although they will still be visible to other services (such as

docs/cli/gemini-md.md

@@ -63,7 +63,7 @@ You can interact with the loaded context files by using the `/memory` command.
 - **`/memory show`**: Displays the full, concatenated content of the current
   hierarchical memory. This lets you inspect the exact instructional context
   being provided to the model.
-- **`/memory refresh`**: Forces a re-scan and reload of all `GEMINI.md` files
+- **`/memory reload`**: Forces a re-scan and reload of all `GEMINI.md` files
   from all configured locations.
 - **`/memory add <text>`**: Appends your text to your global
   `~/.gemini/GEMINI.md` file. This lets you add persistent memories on the fly.

docs/cli/generation-settings.md

@@ -1,26 +1,28 @@
 # Advanced Model Configuration
 
-This guide details the Model Configuration system within the Gemini CLI.
-Designed for researchers, AI quality engineers, and advanced users, this system
-provides a rigorous framework for managing generative model hyperparameters and
+This guide details the Model Configuration system within Gemini CLI. Designed
+for researchers, AI quality engineers, and advanced users, this system provides
+a rigorous framework for managing generative model hyperparameters and
 behaviors.
 
-> **Warning**: This is a power-user feature. Configuration values are passed
+<!-- prettier-ignore -->
+> [!WARNING]
+> This is a power-user feature. Configuration values are passed
 > directly to the model provider with minimal validation. Incorrect settings
-> (e.g., incompatible parameter combinations) may result in runtime errors from
-> the API.
+> (for example, incompatible parameter combinations) may result in runtime
+> errors from the API.
 
 ## 1. System Overview
 
 The Model Configuration system (`ModelConfigService`) enables deterministic
-control over model generation. It decouples the requested model identifier
-(e.g., a CLI flag or agent request) from the underlying API configuration. This
-allows for:
+control over model generation. It decouples the requested model identifier (for
+example, a CLI flag or agent request) from the underlying API configuration.
+This allows for:
 
 - **Precise Hyperparameter Tuning**: Direct control over `temperature`, `topP`,
   `thinkingBudget`, and other SDK-level parameters.
 - **Environment-Specific Behavior**: Distinct configurations for different
-  operating contexts (e.g., testing vs. production).
+  operating contexts (for example, testing vs. production).
 - **Agent-Scoped Customization**: Applying specific settings only when a
   particular agent is active.
 
@@ -71,7 +73,7 @@ context. They are evaluated dynamically for each model request.
   specified `match` properties.
   - `model`: Matches the requested model name or alias.
   - `overrideScope`: Matches the distinct scope of the request (typically the
-    agent name, e.g., `codebaseInvestigator`).
+    agent name, for example, `codebaseInvestigator`).
 
 **Example Override**:
 
@@ -113,8 +115,8 @@ and `overrideScope`).
 1.  **Filtering**: All matching overrides are identified.
 2.  **Sorting**: Matches are prioritized by **specificity** (the number of
     matched keys in the `match` object).
-    - Specific matches (e.g., `model` + `overrideScope`) override broad matches
-      (e.g., `model` only).
+    - Specific matches (for example, `model` + `overrideScope`) override broad
+      matches (for example, `model` only).
     - Tie-breaking: If specificity is equal, the order of definition in the
       `overrides` array is preserved (last one wins).
 3.  **Merging**: The configurations from the sorted overrides are merged
@@ -128,10 +130,10 @@ The configuration follows the `ModelConfigServiceConfig` interface.
 
 Defines the actual parameters for the model.
 
-| Property                | Type     | Description                                                        |
-| :---------------------- | :------- | :----------------------------------------------------------------- |
-| `model`                 | `string` | The identifier of the model to be called (e.g., `gemini-2.5-pro`). |
-| `generateContentConfig` | `object` | The configuration object passed to the `@google/genai` SDK.        |
+| Property                | Type     | Description                                                               |
+| :---------------------- | :------- | :------------------------------------------------------------------------ |
+| `model`                 | `string` | The identifier of the model to be called (for example, `gemini-2.5-pro`). |
+| `generateContentConfig` | `object` | The configuration object passed to the `@google/genai` SDK.               |
 
 ### `GenerateContentConfig` (Common Parameters)
 
@@ -142,7 +144,7 @@ Directly maps to the SDK's `GenerateContentConfig`. Common parameters include:
 - **`topP`**: (`number`) Nucleus sampling probability.
 - **`maxOutputTokens`**: (`number`) Limit on generated response length.
 - **`thinkingConfig`**: (`object`) Configuration for models with reasoning
-  capabilities (e.g., `thinkingBudget`, `includeThoughts`).
+  capabilities (for example, `thinkingBudget`, `includeThoughts`).
 
 ## 5. Practical Examples
 
@@ -170,7 +172,7 @@ configuration but enforcing zero temperature.
 ### Agent-Specific Parameter Injection
 
 Enforce extended thinking budgets for a specific agent without altering the
-global default, e.g. for the `codebaseInvestigator`.
+global default, for example for the `codebaseInvestigator`.
 
 ```json
 "modelConfigs": {

docs/cli/git-worktrees.md

@@ -0,0 +1,107 @@
+# Git Worktrees (experimental)
+
+When working on multiple tasks at once, you can use Git worktrees to give each
+Gemini session its own copy of the codebase. Git worktrees create separate
+working directories that each have their own files and branch while sharing the
+same repository history. This prevents changes in one session from colliding
+with another.
+
+Learn more about [session management](./session-management.md).
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an experimental feature currently under active development. Your
+> feedback is invaluable as we refine this feature. If you have ideas,
+> suggestions, or encounter issues:
+>
+> - [Open an issue](https://github.com/google-gemini/gemini-cli/issues/new?template=bug_report.yml) on GitHub.
+> - Use the **/bug** command within Gemini CLI to file an issue.
+
+Learn more in the official Git worktree
+[documentation](https://git-scm.com/docs/git-worktree).
+
+## How to enable Git worktrees
+
+Git worktrees are an experimental feature. You must enable them in your settings
+using the `/settings` command or by manually editing your `settings.json` file.
+
+1.  Use the `/settings` command.
+2.  Search for and set **Enable Git Worktrees** to `true`.
+
+Alternatively, add the following to your `settings.json`:
+
+```json
+{
+  "experimental": {
+    "worktrees": true
+  }
+}
+```
+
+## How to use Git worktrees
+
+Use the `--worktree` (`-w`) flag to create an isolated worktree and start Gemini
+CLI in it.
+
+- **Start with a specific name:** The value you pass becomes both the directory
+  name (within `.gemini/worktrees/`) and the branch name.
+
+  ```bash
+  gemini --worktree feature-search
+  ```
+
+- **Start with a random name:** If you omit the name, Gemini generates a random
+  one automatically (for example, `worktree-a1b2c3d4`).
+
+  ```bash
+  gemini --worktree
+  ```
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> Remember to initialize your development environment in each new
+> worktree according to your project's setup. Depending on your stack, this
+> might include running dependency installation (`npm install`, `yarn`), setting
+> up virtual environments, or following your project's standard build process.
+
+## How to exit a Git worktree session
+
+When you exit a worktree session (using `/quit` or `Ctrl+C`), Gemini leaves the
+worktree intact so your work is not lost. This includes your uncommitted changes
+(modified files, staged changes, or untracked files) and any new commits you
+have made.
+
+Gemini prioritizes a fast and safe exit: it **does not automatically delete**
+your worktree or branch. You are responsible for cleaning up your worktrees
+manually once you are finished with them.
+
+When you exit, Gemini displays instructions on how to resume your work or how to
+manually remove the worktree if you no longer need it.
+
+## Resuming work in a Git worktree
+
+To resume a session in a worktree, navigate to the worktree directory and start
+Gemini CLI with the `--resume` flag and the session ID:
+
+```bash
+cd .gemini/worktrees/feature-search
+gemini --resume <session_id>
+```
+
+## Managing Git worktrees manually
+
+For more control over worktree location and branch configuration, or to clean up
+a preserved worktree, you can use Git directly:
+
+- **Clean up a preserved Git worktree:**
+  ```bash
+  git worktree remove .gemini/worktrees/feature-search --force
+  git branch -D worktree-feature-search
+  ```
+- **Create a Git worktree manually:**
+  ```bash
+  git worktree add ../project-feature-search -b feature-search
+  cd ../project-feature-search && gemini
+  ```
+
+[Open an issue]: https://github.com/google-gemini/gemini-cli/issues

docs/cli/headless.md

@@ -6,7 +6,7 @@ structured text or JSON output without an interactive terminal UI.
 ## Technical reference
 
 Headless mode is triggered when the CLI is run in a non-TTY environment or when
-providing a query as a positional argument without the interactive flag.
+providing a query with the `-p` (or `--prompt`) flag.
 
 ### Output formats
 
@@ -31,7 +31,8 @@ Returns a stream of newline-delimited JSON (JSONL) events.
   - `tool_use`: Tool call requests with arguments.
   - `tool_result`: Output from executed tools.
   - `error`: Non-fatal warnings and system errors.
-  - `result`: Final outcome with aggregated statistics.
+  - `result`: Final outcome with aggregated statistics and per-model token usage
+    breakdowns.
 
 ## Exit codes
 

docs/cli/model-routing.md

@@ -10,8 +10,8 @@ Model routing is managed by the `ModelAvailabilityService`, which monitors model
 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 initiate the fallback process.
+1.  **Model failure:** If the currently selected model fails (for example, due
+    to quota 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
@@ -26,6 +26,20 @@ policies.
     the CLI will use an available fallback model for the current turn or the
     remainder of the session.
 
+### Local Model Routing (Experimental)
+
+Gemini CLI supports using a local model for routing decisions. When configured,
+Gemini CLI will use a locally-running **Gemma** model to make routing decisions
+(instead of sending routing decisions to a hosted model). This feature can help
+reduce costs associated with hosted model usage while offering similar routing
+decision latency and quality.
+
+In order to use this feature, the local Gemma model **must** be served behind a
+Gemini API and accessible via HTTP at an endpoint configured in `settings.json`.
+
+For more details on how to configure local model routing, see
+[Local Model Routing](../core/local-model-routing.md).
+
 ### Model selection precedence
 
 The model used by Gemini CLI is determined by the following order of precedence:
@@ -38,5 +52,8 @@ The model used by Gemini CLI is determined by the following order of precedence:
 3.  **`model.name` in `settings.json`:** If neither of the above are set, the
     model specified in the `model.name` property of your `settings.json` file
     will be used.
-4.  **Default model:** If none of the above are set, the default model will be
+4.  **Local model (experimental):** If the Gemma local model router is enabled
+    in your `settings.json` file, the CLI will use the local Gemma model
+    (instead of Gemini models) to route the request to an appropriate model.
+5.  **Default model:** If none of the above are set, the default model will be
     used. The default model is `auto`

docs/cli/model-steering.md

@@ -0,0 +1,80 @@
+# Model steering (experimental)
+
+Model steering lets you provide real-time guidance and feedback to Gemini CLI
+while it is actively executing a task. This lets you correct course, add missing
+context, or skip unnecessary steps without having to stop and restart the agent.
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an experimental feature currently under active development and
+> may need to be enabled under `/settings`.
+
+Model steering is particularly useful during complex [Plan Mode](./plan-mode.md)
+workflows or long-running subagent executions where you want to ensure the agent
+stays on the right track.
+
+## Enabling model steering
+
+Model steering is an experimental feature and is disabled by default. You can
+enable it using the `/settings` command or by updating your `settings.json`
+file.
+
+1.  Type `/settings` in Gemini CLI.
+2.  Search for **Model Steering**.
+3.  Set the value to **true**.
+
+Alternatively, add the following to your `settings.json`:
+
+```json
+{
+  "experimental": {
+    "modelSteering": true
+  }
+}
+```
+
+## Using model steering
+
+When model steering is enabled, Gemini CLI treats any text you type while the
+agent is working as a steering hint.
+
+1.  Start a task (for example, "Refactor the database service").
+2.  While the agent is working (the spinner is visible), type your feedback in
+    the input box.
+3.  Press **Enter**.
+
+Gemini CLI acknowledges your hint with a brief message and injects it directly
+into the model's context for the very next turn. The model then re-evaluates its
+current plan and adjusts its actions accordingly.
+
+### Common use cases
+
+You can use steering hints to guide the model in several ways:
+
+- **Correcting a path:** "Actually, the utilities are in `src/common/utils`."
+- **Skipping a step:** "Skip the unit tests for now and just focus on the
+  implementation."
+- **Adding context:** "The `User` type is defined in `packages/core/types.ts`."
+- **Redirecting the effort:** "Stop searching the codebase and start drafting
+  the plan now."
+- **Handling ambiguity:** "Use the existing `Logger` class instead of creating a
+  new one."
+
+## How it works
+
+When you submit a steering hint, Gemini CLI performs the following actions:
+
+1.  **Immediate acknowledgment:** It uses a small, fast model to generate a
+    one-sentence acknowledgment so you know your hint was received.
+2.  **Context injection:** It prepends an internal instruction to your hint that
+    tells the main agent to:
+    - Re-evaluate the active plan.
+    - Classify the update (for example, as a new task or extra context).
+    - Apply minimal-diff changes to affected tasks.
+3.  **Real-time update:** The hint is delivered to the agent at the beginning of
+    its next turn, ensuring the most immediate course correction possible.
+
+## Next steps
+
+- Tackle complex tasks with [Plan Mode](./plan-mode.md).
+- Build custom [Agent Skills](./skills.md).

docs/cli/model.md

@@ -5,7 +5,9 @@ used by Gemini CLI, giving you more control over your results. Use **Pro**
 models for complex tasks and reasoning, **Flash** models for high speed results,
 or the (recommended) **Auto** setting to choose the best model for your tasks.
 
-> **Note:** The `/model` command (and the `--model` flag) does not override the
+<!-- prettier-ignore -->
+> [!NOTE]
+> The `/model` command (and the `--model` flag) does not override the
 > model used by sub-agents. Consequently, even when using the `/model` flag you
 > may see other models used in your model usage reports.
 

docs/cli/notifications.md

@@ -0,0 +1,59 @@
+# Notifications (experimental)
+
+Gemini CLI can send system notifications to alert you when a session completes
+or when it needs your attention, such as when it's waiting for you to approve a
+tool call.
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an experimental feature currently under active development and
+> may need to be enabled under `/settings`.
+
+Notifications are particularly useful when running long-running tasks or using
+[Plan Mode](./plan-mode.md), letting you switch to other windows while Gemini
+CLI works in the background.
+
+## Requirements
+
+### Terminal support
+
+The CLI uses the OSC 9 terminal escape sequence to trigger system notifications.
+This is supported by several modern terminal emulators including iTerm2,
+WezTerm, Ghostty, and Kitty. If your terminal does not support OSC 9
+notifications, Gemini CLI falls back to a terminal bell (BEL) to get your
+attention. Most terminals respond to BEL with a taskbar flash or system alert
+sound.
+
+## Enable notifications
+
+Notifications are disabled by default. You can enable them using the `/settings`
+command or by updating your `settings.json` file.
+
+1.  Open the settings dialog by typing `/settings` in an interactive session.
+2.  Navigate to the **General** category.
+3.  Toggle the **Enable Notifications** setting to **On**.
+
+Alternatively, add the following to your `settings.json`:
+
+```json
+{
+  "general": {
+    "enableNotifications": true
+  }
+}
+```
+
+## Types of notifications
+
+Gemini CLI sends notifications for the following events:
+
+- **Action required:** Triggered when the model is waiting for user input or
+  tool approval. This helps you know when the CLI has paused and needs you to
+  intervene.
+- **Session complete:** Triggered when a session finishes successfully. This is
+  useful for tracking the completion of automated tasks.
+
+## Next steps
+
+- Start planning with [Plan Mode](./plan-mode.md).
+- Configure your experience with other [settings](./settings.md).

docs/cli/plan-mode.md

@@ -1,4 +1,4 @@
-# Plan Mode (experimental)
+# Plan Mode
 
 Plan Mode is a read-only environment for architecting robust solutions before
 implementation. With Plan Mode, you can:
@@ -8,27 +8,8 @@ implementation. With Plan Mode, you can:
 - **Design:** Understand problems, evaluate trade-offs, and choose a solution.
 - **Plan:** Align on an execution strategy before any code is modified.
 
-> **Note:** This is a preview feature currently under active development. Your
-> feedback is invaluable as we refine this feature. If you have ideas,
-> suggestions, or encounter issues:
->
-> - [Open an issue] on GitHub.
-> - Use the **/bug** command within Gemini CLI to file an issue.
-
-## How to enable Plan Mode
-
-Enable Plan Mode in **Settings** or by editing your configuration file.
-
-- **Settings:** Use the `/settings` command and set **Plan** to `true`.
-- **Configuration:** Add the following to your `settings.json`:
-
-  ```json
-  {
-    "experimental": {
-      "plan": true
-    }
-  }
-  ```
+Plan Mode is enabled by default. You can manage this setting using the
+`/settings` command.
 
 ## How to enter Plan Mode
 
@@ -54,16 +35,19 @@ To launch Gemini CLI in Plan Mode once:
 To start Plan Mode while using Gemini CLI:
 
 - **Keyboard shortcut:** Press `Shift+Tab` to cycle through approval modes
-  (`Default` -> `Auto-Edit` -> `Plan`).
+  (`Default` -> `Auto-Edit` -> `Plan`). Plan Mode is automatically removed from
+  the rotation when Gemini CLI is actively processing or showing confirmation
+  dialogs.
 
-  > **Note:** Plan Mode is automatically removed from the rotation when Gemini
-  > CLI is actively processing or showing confirmation dialogs.
-
-- **Command:** Type `/plan` in the input box.
+- **Command:** Type `/plan [goal]` in the input box. The `[goal]` is optional;
+  for example, `/plan implement authentication` will switch to Plan Mode and
+  immediately submit the prompt to the model.
 
 - **Natural Language:** Ask Gemini CLI to "start a plan for...". Gemini CLI
-  calls the [`enter_plan_mode`] tool to switch modes.
-  > **Note:** This tool is not available when Gemini CLI is in [YOLO mode].
+  calls the
+  [`enter_plan_mode`](../tools/planning.md#1-enter_plan_mode-enterplanmode) tool
+  to switch modes. This tool is not available when Gemini CLI is in
+  [YOLO mode](../reference/configuration.md#command-line-arguments).
 
 ## How to use Plan Mode
 
@@ -72,24 +56,51 @@ Gemini CLI takes action.
 
 1.  **Provide a goal:** Start by describing what you want to achieve. Gemini CLI
     will then enter Plan Mode (if it's not already) to research the task.
-2.  **Review research and provide input:** As Gemini CLI analyzes your codebase,
-    it may ask you questions or present different implementation options using
-    [`ask_user`]. Provide your preferences to help guide the design.
-3.  **Review the plan:** Once Gemini CLI has a proposed strategy, it creates a
-    detailed implementation plan as a Markdown file in your plans directory. You
-    can open and read this file to understand the proposed changes.
+2.  **Discuss and agree on strategy:** As Gemini CLI analyzes your codebase, it
+    will discuss its findings and proposed strategy with you to ensure
+    alignment. It may ask you questions or present different implementation
+    options using [`ask_user`](../tools/ask-user.md). **Gemini CLI will stop and
+    wait for your confirmation** before drafting the formal plan. You should
+    reach an informal agreement on the approach before proceeding.
+3.  **Review the plan:** Once you've agreed on the strategy, Gemini CLI creates
+    a detailed implementation plan as a Markdown file in your plans directory.
+    - **View:** You can open and read this file to understand the proposed
+      changes.
+    - **Edit:** Press `Ctrl+X` to open the plan directly in your configured
+      external editor.
+
 4.  **Approve or iterate:** Gemini CLI will present the finalized plan for your
-    approval.
+    formal approval.
     - **Approve:** If you're satisfied with the plan, approve it to start the
       implementation immediately: **Yes, automatically accept edits** or **Yes,
       manually accept edits**.
-    - **Iterate:** If the plan needs adjustments, provide feedback. Gemini CLI
-      will refine the strategy and update the plan.
+    - **Iterate:** If the plan needs adjustments, provide feedback in the input
+      box or [edit the plan file directly](#collaborative-plan-editing). Gemini
+      CLI will refine the strategy and update the plan.
     - **Cancel:** You can cancel your plan with `Esc`.
 
 For more complex or specialized planning tasks, you can
 [customize the planning workflow with skills](#custom-planning-with-skills).
 
+### Collaborative plan editing
+
+You can collaborate with Gemini CLI by making direct changes or leaving comments
+in the implementation plan. This is often faster and more precise than
+describing complex changes in natural language.
+
+1.  **Open the plan:** Press `Ctrl+X` when Gemini CLI presents a plan for
+    review.
+2.  **Edit or comment:** The plan opens in your configured external editor (for
+    example, VS Code or Vim). You can:
+    - **Modify steps:** Directly reorder, delete, or rewrite implementation
+      steps.
+    - **Leave comments:** Add inline questions or feedback (for example, "Wait,
+      shouldn't we use the existing `Logger` class here?").
+3.  **Save and close:** Save your changes and close the editor.
+4.  **Review and refine:** Gemini CLI automatically detects the changes, reviews
+    your comments, and adjusts the implementation strategy. It then presents the
+    refined plan for your final approval.
+
 ## How to exit Plan Mode
 
 You can exit Plan Mode at any time, whether you have finalized a plan or want to
@@ -100,41 +111,49 @@ switch back to another mode.
 - **Keyboard shortcut:** Press `Shift+Tab` to cycle to the desired mode.
 - **Natural language:** Ask Gemini CLI to "exit plan mode" or "stop planning."
 
-## Customization and best practices
-
-Plan Mode is secure by default, but you can adapt it to fit your specific
-workflows. You can customize how Gemini CLI plans by using skills, adjusting
-safety policies, or changing where plans are stored.
-
-## Commands
-
-- **`/plan copy`**: Copy the currently approved plan to your clipboard.
-
 ## Tool Restrictions
 
 Plan Mode enforces strict safety policies to prevent accidental changes.
 
 These are the only allowed tools:
 
-- **FileSystem (Read):** [`read_file`], [`list_directory`], [`glob`]
-- **Search:** [`grep_search`], [`google_web_search`]
-- **Research Subagents:** [`codebase_investigator`], [`cli_help`]
-- **Interaction:** [`ask_user`]
-- **MCP tools (Read):** Read-only [MCP tools] (for example, `github_read_issue`,
-  `postgres_read_schema`) are allowed.
-- **Planning (Write):** [`write_file`] and [`replace`] only allowed for `.md`
+- **FileSystem (Read):**
+  [`read_file`](../tools/file-system.md#2-read_file-readfile),
+  [`list_directory`](../tools/file-system.md#1-list_directory-readfolder),
+  [`glob`](../tools/file-system.md#4-glob-findfiles)
+- **Search:** [`grep_search`](../tools/file-system.md#5-grep_search-searchtext),
+  [`google_web_search`](../tools/web-search.md),
+  [`web_fetch`](../tools/web-fetch.md) (requires explicit confirmation),
+  [`get_internal_docs`](../tools/internal-docs.md)
+- **Research Subagents:**
+  [`codebase_investigator`](../core/subagents.md#codebase-investigator),
+  [`cli_help`](../core/subagents.md#cli-help-agent)
+- **Interaction:** [`ask_user`](../tools/ask-user.md)
+- **MCP tools (Read):** Read-only [MCP tools](../tools/mcp-server.md) (for
+  example, `github_read_issue`, `postgres_read_schema`) and core
+  [MCP resource tools](../tools/mcp-resources.md) (`list_mcp_resources`,
+  `read_mcp_resource`) are allowed.
+- **Planning (Write):**
+  [`write_file`](../tools/file-system.md#3-write_file-writefile) and
+  [`replace`](../tools/file-system.md#6-replace-edit) only allowed for `.md`
   files in the `~/.gemini/tmp/<project>/<session-id>/plans/` directory or your
   [custom plans directory](#custom-plan-directory-and-policies).
-- **Memory:** [`save_memory`]
-- **Skills:** [`activate_skill`] (allows loading specialized instructions and
-  resources in a read-only manner)
+- **Memory:** [`save_memory`](../tools/memory.md)
+- **Skills:** [`activate_skill`](../cli/skills.md) (allows loading specialized
+  instructions and resources in a read-only manner)
+
+## Customization and best practices
+
+Plan Mode is secure by default, but you can adapt it to fit your specific
+workflows. You can customize how Gemini CLI plans by using skills, adjusting
+safety policies, changing where plans are stored, or adding hooks.
 
 ### Custom planning with skills
 
-You can use [Agent Skills] to customize how Gemini CLI approaches planning for
-specific types of tasks. When a skill is activated during Plan Mode, its
-specialized instructions and procedural workflows will guide the research,
-design, and planning phases.
+You can use [Agent Skills](../cli/skills.md) to customize how Gemini CLI
+approaches planning for specific types of tasks. When a skill is activated
+during Plan Mode, its specialized instructions and procedural workflows will
+guide the research, design, and planning phases.
 
 For example:
 
@@ -151,10 +170,39 @@ based on the task description.
 
 ### Custom policies
 
-Plan Mode's default tool restrictions are managed by the [policy engine] and
-defined in the built-in [`plan.toml`] file. The built-in policy (Tier 1)
-enforces the read-only state, but you can customize these rules by creating your
-own policies in your `~/.gemini/policies/` directory (Tier 2).
+Plan Mode's default tool restrictions are managed by the
+[policy engine](../reference/policy-engine.md) and defined in the built-in
+[`plan.toml`] file. The built-in policy (Tier 1) enforces the read-only state,
+but you can customize these rules by creating your own policies in your
+`~/.gemini/policies/` directory (Tier 2).
+
+#### Global vs. mode-specific rules
+
+As described in the
+[policy engine documentation](../reference/policy-engine.md#approval-modes), any
+rule that does not explicitly specify `modes` is considered "always active" and
+will apply to Plan Mode as well.
+
+To maintain the integrity of Plan Mode as a safe research environment,
+persistent tool approvals are context-aware. Approvals granted in modes like
+Default or Auto-Edit do not apply to Plan Mode, ensuring that tools trusted for
+implementation don't automatically execute while you're researching. However,
+approvals granted while in Plan Mode are treated as intentional choices for
+global trust and apply to all modes.
+
+If you want to manually restrict a rule to other modes but _not_ to Plan Mode,
+you must explicitly specify the target modes. For example, to allow `npm test`
+in default and Auto-Edit modes but not in Plan Mode:
+
+```toml
+[[rule]]
+toolName = "run_shell_command"
+commandPrefix = "npm test"
+decision = "allow"
+priority = 100
+# By omitting "plan", this rule will not be active in Plan Mode.
+modes = ["default", "autoEdit"]
+```
 
 #### Example: Automatically approve read-only MCP tools
 
@@ -166,6 +214,7 @@ your specific environment.
 
 ```toml
 [[rule]]
+toolName = "*"
 mcpName = "*"
 toolAnnotations = { readOnlyHint = true }
 decision = "allow"
@@ -173,8 +222,8 @@ priority = 100
 modes = ["plan"]
 ```
 
-For more information on how the policy engine works, see the [policy engine]
-docs.
+For more information on how the policy engine works, see the
+[policy engine](../reference/policy-engine.md) docs.
 
 #### Example: Allow git commands in Plan Mode
 
@@ -194,9 +243,12 @@ modes = ["plan"]
 
 #### Example: Enable custom subagents in Plan Mode
 
-Built-in research [subagents] like [`codebase_investigator`] and [`cli_help`]
-are enabled by default in Plan Mode. You can enable additional [custom
-subagents] by adding a rule to your policy.
+Built-in research [subagents](../core/subagents.md) like
+[`codebase_investigator`](../core/subagents.md#codebase-investigator) and
+[`cli_help`](../core/subagents.md#cli-help-agent) are enabled by default in Plan
+Mode. You can enable additional
+[custom subagents](../core/subagents.md#creating-custom-subagents) by adding a
+rule to your policy.
 
 `~/.gemini/policies/research-subagents.toml`
 
@@ -235,10 +287,11 @@ locations defined within a project's workspace cannot be used to escape and
 overwrite sensitive files elsewhere. Any user-configured directory must reside
 within the project boundary.
 
-Using a custom directory requires updating your [policy engine] configurations
-to allow `write_file` and `replace` in that specific location. For example, to
-allow writing to the `.gemini/plans` directory within your project, create a
-policy file at `~/.gemini/policies/plan-custom-directory.toml`:
+Using a custom directory requires updating your
+[policy engine](../reference/policy-engine.md) configurations to allow
+`write_file` and `replace` in that specific location. For example, to allow
+writing to the `.gemini/plans` directory within your project, create a policy
+file at `~/.gemini/policies/plan-custom-directory.toml`:
 
 ```toml
 [[rule]]
@@ -251,16 +304,87 @@ modes = ["plan"]
 argsPattern = "\"file_path\":\"[^\"]+[\\\\/]+\\.gemini[\\\\/]+plans[\\\\/]+[\\w-]+\\.md\""
 ```
 
+### Using hooks with Plan Mode
+
+You can use the [hook system](../hooks/writing-hooks.md) to automate parts of
+the planning workflow or enforce additional checks when Gemini CLI transitions
+into or out of Plan Mode.
+
+Hooks such as `BeforeTool` or `AfterTool` can be configured to intercept the
+`enter_plan_mode` and `exit_plan_mode` tool calls.
+
+> [!WARNING] When hooks are triggered by **tool executions**, they do **not**
+> run when you manually toggle Plan Mode using the `/plan` command or the
+> `Shift+Tab` keyboard shortcut. If you need hooks to execute on mode changes,
+> ensure the transition is initiated by the agent (for example, by asking "start
+> a plan for...").
+
+#### Example: Archive approved plans to GCS (`AfterTool`)
+
+If your organizational policy requires a record of all execution plans, you can
+use an `AfterTool` hook to securely copy the plan artifact to Google Cloud
+Storage whenever Gemini CLI exits Plan Mode to start the implementation.
+
+**`.gemini/hooks/archive-plan.sh`:**
+
+```bash
+#!/usr/bin/env bash
+# Extract the plan filename from the tool input JSON
+plan_filename=$(jq -r '.tool_input.plan_filename // empty')
+
+# Construct the absolute path using the GEMINI_PLANS_DIR environment variable
+plan_path="$GEMINI_PLANS_DIR/$plan_filename"
+
+if [ -f "$plan_path" ]; then
+  # Generate a unique filename using a timestamp
+  filename="$(date +%s)_$(basename "$plan_path")"
+
+  # Upload the plan to GCS in the background so it doesn't block the CLI
+  gsutil cp "$plan_path" "gs://my-audit-bucket/gemini-plans/$filename" > /dev/null 2>&1 &
+fi
+
+# AfterTool hooks should generally allow the flow to continue
+echo '{"decision": "allow"}'
+```
+
+To register this `AfterTool` hook, add it to your `settings.json`:
+
+```json
+{
+  "hooks": {
+    "AfterTool": [
+      {
+        "matcher": "exit_plan_mode",
+        "hooks": [
+          {
+            "name": "archive-plan",
+            "type": "command",
+            "command": "~/.gemini/hooks/archive-plan.sh"
+          }
+        ]
+      }
+    ]
+  }
+}
+```
+
+## Commands
+
+- **`/plan copy`**: Copy the currently approved plan to your clipboard.
+
 ## Planning workflows
 
 Plan Mode provides building blocks for structured research and design. These are
-implemented as [extensions] using core planning tools like [`enter_plan_mode`],
-[`exit_plan_mode`], and [`ask_user`].
+implemented as [extensions](../extensions/index.md) using core planning tools
+like [`enter_plan_mode`](../tools/planning.md#1-enter_plan_mode-enterplanmode),
+[`exit_plan_mode`](../tools/planning.md#2-exit_plan_mode-exitplanmode), and
+[`ask_user`](../tools/ask-user.md).
 
 ### Built-in planning workflow
 
 The built-in planner uses an adaptive workflow to analyze your project, consult
-you on trade-offs via [`ask_user`], and draft a plan for your approval.
+you on trade-offs via [`ask_user`](../tools/ask-user.md), and draft a plan for
+your approval.
 
 ### Custom planning workflows
 
@@ -272,28 +396,36 @@ You can install or create specialized planners to suit your workflow.
 "tracks" and stores persistent artifacts in your project's `conductor/`
 directory:
 
-- **Automate transitions:** Switches to read-only mode via [`enter_plan_mode`].
-- **Streamline decisions:** Uses [`ask_user`] for architectural choices.
+- **Automate transitions:** Switches to read-only mode via
+  [`enter_plan_mode`](../tools/planning.md#1-enter_plan_mode-enterplanmode).
+- **Streamline decisions:** Uses [`ask_user`](../tools/ask-user.md) for
+  architectural choices.
 - **Maintain project context:** Stores artifacts in the project directory using
   [custom plan directory and policies](#custom-plan-directory-and-policies).
-- **Handoff execution:** Transitions to implementation via [`exit_plan_mode`].
+- **Handoff execution:** Transitions to implementation via
+  [`exit_plan_mode`](../tools/planning.md#2-exit_plan_mode-exitplanmode).
 
 #### Build your own
 
 Since Plan Mode is built on modular building blocks, you can develop your own
-custom planning workflow as an [extensions]. By leveraging core tools and
-[custom policies](#custom-policies), you can define how Gemini CLI researches
-and stores plans for your specific domain.
+custom planning workflow as an [extensions](../extensions/index.md). By
+leveraging core tools and [custom policies](#custom-policies), you can define
+how Gemini CLI researches and stores plans for your specific domain.
 
 To build a custom planning workflow, you can use:
 
-- **Tool usage:** Use core tools like [`enter_plan_mode`], [`ask_user`], and
-  [`exit_plan_mode`] to manage the research and design process.
+- **Tool usage:** Use core tools like
+  [`enter_plan_mode`](../tools/planning.md#1-enter_plan_mode-enterplanmode),
+  [`ask_user`](../tools/ask-user.md), and
+  [`exit_plan_mode`](../tools/planning.md#2-exit_plan_mode-exitplanmode) to
+  manage the research and design process.
 - **Customization:** Set your own storage locations and policy rules using
   [custom plan directories](#custom-plan-directory-and-policies) and
   [custom policies](#custom-policies).
 
-> **Note:** Use [Conductor] as a reference when building your own custom
+<!-- prettier-ignore -->
+> [!TIP]
+> Use [Conductor] as a reference when building your own custom
 > planning workflow.
 
 By using Plan Mode as its execution environment, your custom methodology can
@@ -302,8 +434,9 @@ high-reasoning model routing.
 
 ## Automatic Model Routing
 
-When using an [auto model], Gemini CLI automatically optimizes [model routing]
-based on the current phase of your task:
+When using an [auto model](../reference/configuration.md#model), Gemini CLI
+automatically optimizes [model routing](../cli/telemetry.md#model-routing) based
+on the current phase of your task:
 
 1.  **Planning Phase:** While in Plan Mode, the CLI routes requests to a
     high-reasoning **Pro** model to ensure robust architectural decisions and
@@ -313,6 +446,10 @@ based on the current phase of your task:
     switches to a high-speed **Flash** model. This provides a faster, more
     responsive experience during the implementation of the plan.
 
+If the high-reasoning model is unavailable or you don't have access to it,
+Gemini CLI automatically and silently falls back to a faster model to ensure
+your workflow isn't interrupted.
+
 This behavior is enabled by default to provide the best balance of quality and
 performance. You can disable this automatic switching in your settings:
 
@@ -334,7 +471,8 @@ associated plan files and task trackers.
 - **Default behavior:** Sessions (and their plans) are retained for **30 days**.
 - **Configuration:** You can customize this behavior via the `/settings` command
   (search for **Session Retention**) or in your `settings.json` file. See
-  [session retention] for more details.
+  [session retention](../cli/session-management.md#session-retention) for more
+  details.
 
 Manual deletion also removes all associated artifacts:
 
@@ -344,32 +482,27 @@ Manual deletion also removes all associated artifacts:
 If you use a [custom plans directory](#custom-plan-directory-and-policies),
 those files are not automatically deleted and must be managed manually.
 
-[`list_directory`]: /docs/tools/file-system.md#1-list_directory-readfolder
-[`read_file`]: /docs/tools/file-system.md#2-read_file-readfile
-[`grep_search`]: /docs/tools/file-system.md#5-grep_search-searchtext
-[`write_file`]: /docs/tools/file-system.md#3-write_file-writefile
-[`glob`]: /docs/tools/file-system.md#4-glob-findfiles
-[`google_web_search`]: /docs/tools/web-search.md
-[`replace`]: /docs/tools/file-system.md#6-replace-edit
-[MCP tools]: /docs/tools/mcp-server.md
-[`save_memory`]: /docs/tools/memory.md
-[`activate_skill`]: /docs/cli/skills.md
-[`codebase_investigator`]: /docs/core/subagents.md#codebase-investigator
-[`cli_help`]: /docs/core/subagents.md#cli-help-agent
-[subagents]: /docs/core/subagents.md
-[custom subagents]: /docs/core/subagents.md#creating-custom-subagents
-[policy engine]: /docs/reference/policy-engine.md
-[`enter_plan_mode`]: /docs/tools/planning.md#1-enter_plan_mode-enterplanmode
-[`exit_plan_mode`]: /docs/tools/planning.md#2-exit_plan_mode-exitplanmode
-[`ask_user`]: /docs/tools/ask-user.md
-[YOLO mode]: /docs/reference/configuration.md#command-line-arguments
+## Non-interactive execution
+
+When running Gemini CLI in non-interactive environments (such as headless
+scripts or CI/CD pipelines), Plan Mode optimizes for automated workflows:
+
+- **Automatic transitions:** The policy engine automatically approves the
+  `enter_plan_mode` and `exit_plan_mode` tools without prompting for user
+  confirmation.
+- **Automated implementation:** When exiting Plan Mode to execute the plan,
+  Gemini CLI automatically switches to
+  [YOLO mode](../reference/policy-engine.md#approval-modes) instead of the
+  standard Default mode. This allows the CLI to execute the implementation steps
+  automatically without hanging on interactive tool approvals.
+
+**Example:**
+
+```bash
+gemini --approval-mode plan -p "Analyze telemetry and suggest improvements"
+```
+
 [`plan.toml`]:
   https://github.com/google-gemini/gemini-cli/blob/main/packages/core/src/policy/policies/plan.toml
-[auto model]: /docs/reference/configuration.md#model
-[model routing]: /docs/cli/telemetry.md#model-routing
-[preferred external editor]: /docs/reference/configuration.md#general
-[session retention]: /docs/cli/session-management.md#session-retention
-[extensions]: /docs/extensions/
 [Conductor]: https://github.com/gemini-cli-extensions/conductor
 [open an issue]: https://github.com/google-gemini/gemini-cli/issues
-[Agent Skills]: /docs/cli/skills.md

docs/cli/sandbox.md

@@ -1,11 +1,11 @@
-# Sandboxing in the Gemini CLI
+# Sandboxing in Gemini CLI
 
-This document provides a guide to sandboxing in the Gemini CLI, including
+This document provides a guide to sandboxing in Gemini CLI, including
 prerequisites, quickstart, and configuration.
 
 ## Prerequisites
 
-Before using sandboxing, you need to install and set up the Gemini CLI:
+Before using sandboxing, you need to install and set up Gemini CLI:
 
 ```bash
 npm install -g @google/gemini-cli
@@ -50,7 +50,25 @@ Cross-platform sandboxing with complete process isolation.
 **Note**: Requires building the sandbox image locally or using a published image
 from your organization's registry.
 
-### 3. gVisor / runsc (Linux only)
+### 3. Windows Native Sandbox (Windows only)
+
+... **Troubleshooting and Side Effects:**
+
+The Windows Native sandbox uses the `icacls` command to set a "Low Mandatory
+Level" on files and directories it needs to write to.
+
+- **Persistence**: These integrity level changes are persistent on the
+  filesystem. Even after the sandbox session ends, files created or modified by
+  the sandbox will retain their "Low" integrity level.
+- **Manual Reset**: If you need to reset the integrity level of a file or
+  directory, you can use:
+  ```powershell
+  icacls "C:\path\to\dir" /setintegritylevel Medium
+  ```
+- **System Folders**: The sandbox manager automatically skips setting integrity
+  levels on system folders (like `C:\Windows`) for safety.
+
+### 4. gVisor / runsc (Linux only)
 
 Strongest isolation available: runs containers inside a user-space kernel via
 [gVisor](https://github.com/google/gvisor). gVisor intercepts all container
@@ -74,7 +92,7 @@ To set up runsc:
 2.  Configure the Docker daemon to use the runsc runtime.
 3.  Verify the installation.
 
-### 4. LXC/LXD (Linux only, experimental)
+### 5. LXC/LXD (Linux only, experimental)
 
 Full-system container sandboxing using LXC/LXD. Unlike Docker/Podman, LXC
 containers run a complete Linux system with `systemd`, `snapd`, and other system
@@ -118,6 +136,58 @@ gemini -p "build the snap"
   absolute path — the path must be writable inside the container.
 - Used with tools like Snapcraft or Rockcraft that require a full system.
 
+## Tool sandboxing
+
+Tool-level sandboxing provides granular isolation for individual tool executions
+(like `shell_exec` and `write_file`) instead of sandboxing the entire Gemini CLI
+process.
+
+This approach offers better integration with your local environment for non-tool
+tasks (like UI rendering and configuration loading) while still providing
+security for tool-driven operations.
+
+### How to turn off tool sandboxing
+
+If you experience issues with tool sandboxing or prefer full-process isolation,
+you can disable it by setting `security.toolSandboxing` to `false` in your
+`settings.json` file.
+
+```json
+{
+  "security": {
+    "toolSandboxing": false
+  }
+}
+```
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> Changing the `security.toolSandboxing` setting requires a restart of Gemini
+> CLI to take effect.
+
+## Sandbox expansion
+
+Sandbox expansion is a dynamic permission system that lets Gemini CLI request
+additional permissions for a command when needed.
+
+When a sandboxed command fails due to permission restrictions (like restricted
+file paths or network access), or when a command is proactively identified as
+requiring extra permissions (like `npm install`), Gemini CLI will present you
+with a "Sandbox Expansion Request."
+
+### How sandbox expansion works
+
+1.  **Detection**: Gemini CLI detects a sandbox denial or proactively identifies
+    a command that requires extra permissions.
+2.  **Request**: A modal dialog is shown, explaining which additional
+    permissions (e.g., specific directories or network access) are required.
+3.  **Approval**: If you approve the expansion, the command is executed with the
+    extended permissions for that specific run.
+
+This mechanism ensures you don't have to manually re-run commands with more
+permissive sandbox settings, while still maintaining control over what the AI
+can access.
+
 ## Quickstart
 
 ```bash
@@ -159,7 +229,7 @@ gemini -p "run the test suite"
 2. **Environment variable**:
    `GEMINI_SANDBOX=true|docker|podman|sandbox-exec|runsc|lxc`
 3. **Settings file**: `"sandbox": true` in the `tools` object of your
-   `settings.json` file (e.g., `{"tools": {"sandbox": true}}`).
+   `settings.json` file (for example, `{"tools": {"sandbox": true}}`).
 
 ### macOS Seatbelt profiles
 
@@ -239,7 +309,9 @@ $env:SANDBOX_SET_UID_GID="false"  # Disable UID/GID mapping
 
 **Missing commands**
 
-- Add to custom Dockerfile.
+- Add to a custom Dockerfile. Automatic `BUILD_SANDBOX` builds are only
+  available when running Gemini CLI from source; npm installs need a prebuilt
+  image instead.
 - Install via `sandbox.bashrc`.
 
 **Network issues**
@@ -253,9 +325,11 @@ $env:SANDBOX_SET_UID_GID="false"  # Disable UID/GID mapping
 DEBUG=1 gemini -s -p "debug command"
 ```
 
-**Note:** If you have `DEBUG=true` in a project's `.env` file, it won't affect
-gemini-cli due to automatic exclusion. Use `.gemini/.env` files for gemini-cli
-specific debug settings.
+<!-- prettier-ignore -->
+> [!NOTE]
+> If you have `DEBUG=true` in a project's `.env` file, it won't affect
+> gemini-cli due to automatic exclusion. Use `.gemini/.env` files for
+> gemini-cli specific debug settings.
 
 ### Inspect sandbox