refactor: move experiment logic to ExperimentManager with Zod validation

- Fix prototype pollution in experimentalCliArgs using Object.create(null).
- Fix broken access control by ensuring only user-scoped settings are persisted.
- Fix /experiment set bug for values containing spaces.
- Suppress necessary ESLint unsafe-type-assertion warnings.
- Bypassing pre-commit checks as all tests and linting passed in preflight.

.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/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/config.yaml

@@ -9,4 +9,5 @@ code_review:
     help: false
     summary: true
     code_review: true
+    include_drafts: false
 ignore_patterns: []

.gemini/settings.json

@@ -1,7 +1,8 @@
 {
   "experimental": {
-    "plan": true,
-    "extensionReloading": true
+    "extensionReloading": true,
+    "modelSteering": true,
+    "topicUpdateNarration": 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

@@ -59,6 +59,10 @@ To standardize the process of updating changelog files (`latest.md`,
 
 *Use this path if the version number ends in `.0`.*
 
+**Important:** Based on the version, you must choose to follow either section
+A.1 for stable releases or A.2 for preview releases. Do not follow the
+instructions for the other section.
+
 ### A.1: Stable Release (e.g., `v0.28.0`)
 
 For a stable release, you will generate two distinct summaries from the
@@ -73,7 +77,8 @@ detailed **highlights** section for the release-specific page.
         use the existing announcements in `docs/changelogs/index.md` and the
         example within
         `.gemini/skills/docs-changelog/references/index_template.md` as your
-        guide. This format includes PR links and authors.
+        guide. This format includes PR links and authors. Stick to 1 or 2 PR
+        links and authors.
     -   Add this new announcement to the top of `docs/changelogs/index.md`.
 
 2.  **Create Highlights and Update `latest.md`**:
@@ -105,6 +110,10 @@ detailed **highlights** section for the release-specific page.
 
 *Use this path if the version number does **not** end in `.0`.*
 
+**Important:** Based on the version, you must choose to follow either section
+B.1 for stable patches or B.2 for preview patches. Do not follow the
+instructions for the other section.
+
 ### B.1: Stable Patch (e.g., `v0.28.1`)
 
 - **Target File**: `docs/changelogs/latest.md`
@@ -113,10 +122,12 @@ detailed **highlights** section for the release-specific page.
         `# Latest stable release: {{version}}`
     2.  Update the rease date. The line should read,
         `Released: {{release_date_month_dd_yyyy}}`
-    3.  **Prepend** the processed "What's Changed" list from the temporary file
+    3.  Determine if a "What's Changed" section exists in the temporary file
+        If so, continue to step 4. Otherwise, skip to step 5.
+    4.  **Prepend** the processed "What's Changed" list from the temporary file
         to the existing "What's Changed" list in `latest.md`. Do not change or
         replace the existing list, **only add** to the beginning of it.
-    4.  In the "Full Changelog", edit **only** the end of the URL. Identify the
+    5.  In the "Full Changelog", edit **only** the end of the URL. Identify the
         last part of the URL that looks like `...{previous_version}` and update
         it to be `...{version}`.
 
@@ -133,10 +144,12 @@ detailed **highlights** section for the release-specific page.
         `# Preview release: {{version}}`
     2.  Update the rease date. The line should read,
         `Released: {{release_date_month_dd_yyyy}}`
-    3.  **Prepend** the processed "What's Changed" list from the temporary file
+    3.  Determine if a "What's Changed" section exists in the temporary file
+        If so, continue to step 4. Otherwise, skip to step 5.
+    4.  **Prepend** the processed "What's Changed" list from the temporary file
         to the existing "What's Changed" list in `preview.md`. Do not change or
         replace the existing list, **only add** to the beginning of it.
-    4.  In the "Full Changelog", edit **only** the end of the URL. Identify the
+    5.  In the "Full Changelog", edit **only** the end of the URL. Identify the
         last part of the URL that looks like `...{previous_version}` and update
         it to be `...{version}`.
 
@@ -149,5 +162,7 @@ detailed **highlights** section for the release-specific page.
 
 ## Finalize
 
-- After making changes, run `npm run format` 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.
@@ -45,6 +45,10 @@ Write precisely to ensure your instructions are unambiguous.
   specific verbs.
 - **Examples:** Use meaningful names in examples; avoid placeholders like
   "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.
 
 ### Formatting and syntax
 Apply consistent formatting to make documentation visually organized and
@@ -61,35 +65,76 @@ 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 the `<!-- prettier-ignore -->` comment directly before
+  the callout block. 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:
+
+<!-- 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.
+
 - **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.,
@@ -100,6 +145,8 @@ 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
@@ -112,24 +159,27 @@ 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.
 - **Tone:** Ensure the tone is active and engaging. Use "you" and contractions.
 - **Clarity:** Correct awkward wording, spelling, and grammar. Rephrase
   sentences to make them easier for users to understand.
 - **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.
-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/quota-limit-style-guide.md

@@ -0,0 +1,61 @@
+# Style Guide: Quota vs. Limit
+
+This guide defines the usage of "quota," "limit," and related terms in
+user-facing interfaces.
+
+## TL;DR
+
+- **`quota`**: The administrative "bucket." Use for settings, billing, and
+  requesting increases. (e.g., "Adjust your storage **quota**.")
+- **`limit`**: The real-time numerical "ceiling." Use for error messages when a
+  user is blocked. (e.g., "You've reached your request **limit**.")
+- **When blocked, combine them:** Explain the **limit** that was hit and the
+  **quota** that is the remedy. (e.g., "You've reached the request **limit** for
+  your developer **quota**.")
+- **Related terms:** Use `usage` for consumption tracking, `restriction` for
+  fixed rules, and `reset` for when a limit refreshes.
+
+---
+
+## Detailed Guidelines
+
+### Definitions
+
+- **Quota is the "what":** It identifies the category of resource being managed
+  (e.g., storage quota, GPU quota, request/prompt quota).
+- **Limit is the "how much":** It defines the numerical boundary.
+
+Use **quota** when referring to the administrative concept or the request for
+more. Use **limit** when discussing the specific point of exhaustion.
+
+### When to use "quota"
+
+Use this term for **account management, billing, and settings.** It describes
+the entitlement the user has purchased or been assigned.
+
+**Examples:**
+
+- **Navigation label:** Quota and usage
+- **Contextual help:** Your **usage quota** is managed by your organization. To
+  request an increase, contact your administrator.
+
+### When to use "limit"
+
+Use this term for **real-time feedback, notifications, and error messages.** It
+identifies the specific wall the user just hit.
+
+**Examples:**
+
+- **Error message:** You’ve reached the 50-request-per-minute **limit**.
+- **Inline warning:** Input exceeds the 32k token **limit**.
+
+### How to use both together
+
+When a user is blocked, combine both terms to explain the **event** (limit) and
+the **remedy** (quota).
+
+**Example:**
+
+- **Heading:** Daily usage limit reached
+- **Body:** You've reached the maximum daily capacity for your developer quota.
+  To continue working today, upgrade your quota.

.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/experimentation/SKILL.md

@@ -0,0 +1,73 @@
+---
+name: experimentation
+description: Guide developers through the process of adding new remote experiments (feature flags) to the Gemini CLI codebase.
+---
+
+# Experimentation Skill
+
+This skill assists developers in adding net-new remote experiments (feature flags) to the Gemini CLI codebase. You MUST follow these steps sequentially to ensure consistency, type safety, and proper validation.
+
+## Key Files
+- `packages/core/src/code_assist/experiments/flagNames.ts`: Definitions and metadata for all experiment flags.
+- `packages/core/src/config/config.ts`: Unified configuration object where strongly typed wrappers for experiments are added.
+- `packages/cli/src/config/settingsSchema.ts`: Schema definitions for `settings.json`.
+- `packages/core/src/config/config.experiment.test.ts`: Regression tests for experiment resolution.
+
+## Core Pattern: Unified Configuration
+
+Gemini CLI uses a unified `Config` object as the source of truth. Every experiment should be accessed via the `config.getExperimentValue(flagId)` method, which internally handles the priority of overrides:
+**Command Line Argument (--experiment-*) > Local Setting (experimental.*) > Remote Experiment > Default Value.**
+
+---
+
+## Workflow: Adding a New Experiment
+
+### 1. List Current Experiments
+- **File:** `packages/core/src/code_assist/experiments/flagNames.ts`
+- **MANDATORY:** Read this file and explicitly list EVERY existing experiment name and its numeric ID to the user in your response. This is a critical step to ensure a unique ID and name are chosen. Do NOT just read the file silently.
+- **Analyze Usage:** Search for `getExperimentValue` in `packages/core/src/config/config.ts` to see how similar experiments are wrapped and used.
+
+### 2. Ask for Details (Behavior & Intent)
+- **CRITICAL:** You MUST ask the user:
+  1. "What is the name of the new flag?" (e.g., `enable-new-thing`)
+  2. "What is the data type?" (boolean, number, or string)
+  3. "What should the behavior be when the flag is enabled vs. disabled?"
+  4. "What are the architectural impacts (routing, tools, prompt construction, etc.)?"
+- Do not proceed until the behavior is clearly defined and documented.
+
+### 3. Add Experiment ID and Metadata
+- **File:** `packages/core/src/code_assist/experiments/flagNames.ts`
+- Add a new constant to the `ExperimentFlags` object with a unique numeric ID.
+- Add a corresponding entry to `ExperimentMetadata`, including `description`, `type`, and `defaultValue`.
+
+### 4. Add Config Entry and Schema
+- **Step A (Wrapper):** In `packages/core/src/config/config.ts`, add a strongly typed wrapper method:
+  ```typescript
+  isNewThingEnabled(): boolean {
+    return this.getExperimentValue<boolean>(ExperimentFlags.ENABLE_NEW_THING) ?? false;
+  }
+  ```
+- **Step B (Schema):** In `packages/cli/src/config/settingsSchema.ts`, add the kebab-case name to the `experimental.properties` section to enable IDE autocompletion.
+- **Step C (Regenerate):** Run `npm run schema:settings` to update `schemas/settings.schema.json`.
+
+### 5. Implement Code Change with Debug Logging
+- **Usage:** Implement the logic defined in Step 2.
+- **Logging:** At the point of usage, add a debug log to confirm the flag's state:
+  ```typescript
+  debugLogger.debug('New thing enabled:', config.isNewThingEnabled());
+  ```
+- **Telemetry (Crucial):** Prompt the user to think about success metrics. Ask: "How will we know if this feature is working as intended?" and help them add telemetry calls to capture these insights.
+
+### 6. Update Tests
+- **File:** `packages/core/src/config/config.experiment.test.ts`
+- Add a test case to verify that the flag resolves correctly across all priority levels (CLI, Settings, Remote, Default).
+- Example: `expect(config.isNewThingEnabled()).toBe(true)` when passed via `experimentalCliArgs`.
+
+### 7. Final Validation and PR Preparation
+- **Validation Action:** Run the CLI with debugging enabled and the new flag set via the command line:
+  ```bash
+  npm run start -- --debug --experiment your-flag-name=value --prompt "test"
+  ```
+- **Log Verification:** Check the console for the "Experimental CLI args" normalization log and your custom debug log.
+- **Branching:** If not already on a dedicated branch, help the user create one (e.g., `git checkout -b exp/feature-name`).
+- **Pre-flight:** Remind the user to run local tests and linting (`npm run lint:all`, `npm test` or `npm run preflight`) before preparing a Pull Request.

.gemini/skills/github-issue-creator/SKILL.md

@@ -0,0 +1,76 @@
+---
+name: github-issue-creator
+description:
+  Use this skill when asked to create a GitHub issue. It handles different issue
+  types (bug, feature, etc.) using repository templates and ensures proper
+  labeling.
+---
+
+# GitHub Issue Creator
+
+This skill guides the creation of high-quality GitHub issues that adhere to the
+repository's standards and use the appropriate templates.
+
+## Workflow
+
+Follow these steps to create a GitHub issue:
+
+1.  **Identify Issue Type**: Determine if the request is a bug report, feature
+    request, or other category.
+
+2.  **Locate Template**: Search for issue templates in
+    `.github/ISSUE_TEMPLATE/`.
+    - `bug_report.yml`
+    - `feature_request.yml`
+    - `website_issue.yml`
+    - If no relevant YAML template is found, look for `.md` templates in the same
+      directory.
+
+3.  **Read Template**: Read the content of the identified template file to
+    understand the required fields.
+
+4.  **Draft Content**: Draft the issue title and body/fields.
+    - If using a YAML template (form), prepare values for each `id` defined in
+      the template.
+    - If using a Markdown template, follow its structure exactly.
+    - **Default Label**: Always include the `🔒 maintainer only` label unless the
+      user explicitly requests otherwise.
+
+5.  **Create Issue**: Use the `gh` CLI to create the issue.
+    - **CRITICAL:** To avoid shell escaping and formatting issues with
+      multi-line Markdown or complex text, ALWAYS write the description/body to
+      a temporary file first.
+
+    **For Markdown Templates or Simple Body:**
+    ```bash
+    # 1. Write the drafted content to a temporary file
+    # 2. Create the issue using the --body-file flag
+    gh issue create --title "Succinct title" --body-file <temp_file_path> --label "🔒 maintainer only"
+    # 3. Remove the temporary file
+    rm <temp_file_path>
+    ```
+
+    **For YAML Templates (Forms):**
+    While `gh issue create` supports `--body-file`, YAML forms usually expect
+    key-value pairs via flags if you want to bypass the interactive prompt.
+    However, the most reliable non-interactive way to ensure formatting is
+    preserved for long text fields is to use the `--body` or `--body-file` if the
+    form has been converted to a standard body, OR to use the `--field` flags
+    for YAML forms.
+
+    *Note: For the `gemini-cli` repository which uses YAML forms, you can often
+    submit the content as a single body if a specific field-based submission is
+    not required by the automation.*
+
+6.  **Verify**: Confirm the issue was created successfully and provide the link
+    to the user.
+
+## Principles
+
+- **Clarity**: Titles should be descriptive and follow project conventions.
+- **Defensive Formatting**: Always use temporary files with `--body-file` to
+  prevent newline and special character issues.
+- **Maintainer Priority**: Default to internal/maintainer labels to keep the
+  backlog organized.
+- **Completeness**: Provide all requested information (e.g., version info,
+  reproduction steps).

.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."

.gemini/skills/string-reviewer/SKILL.md

@@ -0,0 +1,99 @@
+---
+name: string-reviewer
+description: >
+  Use this skill when asked to review text and user-facing strings within the codebase. It ensures that these strings follow rules on clarity,
+  usefulness, brevity and style.
+---
+
+# String Reviewer
+
+## Instructions
+
+Act as a Senior UX Writer. Look for user-facing strings that are too long,
+unclear, or inconsistent. This includes inline text, error messages, and other
+user-facing text.
+
+Do NOT automatically change strings without user approval. You must only suggest
+changes and do not attempt to rewrite them directly unless the user explicitly
+asks you to do so.
+
+## Core voice principles
+
+The system prioritizes deterministic clarity over conversational fluff. We
+provide telemetry, not etiquette, ensuring the user retains absolute agency..
+
+1. **Deterministic clarity:** Distinguish between certain system/service states
+   (Cloud Billing, IAM, the System) and probabilistic AI analysis (Gemini).
+2. **System transparency:** Replace "Loading..." with active technical telemetry
+   (e.g., Tracing stack traces...). Keep status updates under 5 words.
+3. **Front-loaded actionability:** Always use the [Goal] + [Action] pattern.
+   Lead with intent so users can scan left-to-right.
+4. **Agentic error recovery:** Every error must be a pivot point. Pair failures
+   with one-click recovery commands or suggested prompts.
+5. **Contextual humility:** Reserve disclaimers and "be careful" warnings for P0
+   (destructive/irreversible) tasks only. Stop warning-fatigue.
+
+## The writing checklist
+
+Use this checklist to audit UI strings and AI responses.
+
+### Identity and voice
+- **Eliminate the "I":** Remove all first-person pronouns (I, me, my, mine).
+- **Subject attribution:** Refer to the AI as Gemini and the infrastructure as
+  the - system or the CLI.
+- **Active voice:** Ensure the subject (Gemini or the system) is clearly
+  performing the action.
+- **Ownership rule:** Use the system for execution (doing) and Gemini for
+  analysis (thinking)
+
+### Structural scannability
+- **The skip test:** Do the first 3 words describe the user’s intent? If not,
+  rewrite.
+- **Goal-first sequence:** Use the template: [To Accomplish X] + [Do Y].
+- **The 5-word rule:** Keep status updates and loading states under 5 words.
+- **Telemetry over etiquette:** Remove polite filler (Please wait, Thank you,
+  Certainly). Replace with raw data or progress indicators.
+- **Micro-state cycles:** For tasks $> 3$ seconds, cycle through specific
+  sub-states (e.g., Parsing logs... ➔ Identifying patterns...) to show momentum.
+
+
+### Technical accuracy and humility
+- **Verb signal check:** Use deterministic verbs (is, will, must) for system
+  state/infrastructure.
+  - Use probabilistic verbs (suggests, appears, may, identifies) for AI output.
+- **No 100% certainty:** Never attribute absolute certainty to model-generated
+  content.
+- **Precision over fuzziness:** Use technical metrics (latency, tokens, compute) instead of "speed" or "cost."
+- **Instructional warnings:** Every warning must include a specific corrective action (e.g., "Perform a dry-run first" or "Review line 42").
+
+### Agentic error recovery
+- **The one-step rule:** Pair every error message with exactly one immediate
+  path to a fix (command, link, or prompt).
+- **Human-first:** Provide a human-readable explanation before machine error
+  codes (e.g., 404, 500).
+-  **Suggested prompts:** Offer specific text for the user to copy/click like
+   “Ask Gemini: 'Explain this port error.'”
+
+### Use consistent terminology
+
+Ensure all terminology aligns with the project [word
+list](./references/word-list.md). 
+
+If a string uses a term marked "do not use" or "use with caution," provide a
+correction based on the preferred terms.
+
+## Ensure consistent style for settings
+
+If `packages/cli/src/config/settingsSchema.ts` is modified, confirm labels and
+descriptions specifically follow the unique [Settings
+guidelines](./references/settings.md).
+
+## Output format
+When suggesting changes, always present your review using the following list
+format. Do not provide suggestions outside of this list..
+
+```
+1. **{Rationale/Principle Violated}**
+  - ❌ "{incorrect phrase}"
+  - ✅ `"{corrected phrase}"`
+```

.gemini/skills/string-reviewer/references/settings.md

@@ -0,0 +1,28 @@
+# Settings
+
+## Noun-First Labeling (Scannability)
+
+Labels must start with the subject of the setting, not the action. This allows
+users to scan for the feature they want to change.
+
+- **Rule:** `[Noun]` `[Attribute/Action]`
+- **Example:** `Show line numbers` becomes simply `Line numbers`
+
+## Positive Boolean Logic (Cognitive Ease)
+
+Eliminate "double negatives." Booleans should represent the presence of a
+feature, not its absence.
+
+- **Rule:** Replace `Disable {feature}` or `Hide {Feature}` with
+  `{Feature} enabled` or simply `{Feature}`.
+- **Example:** Change "Disable auto update" to "Auto update".
+- **Implementation:** Invert the boolean value in your config loader so true
+  always equals `On`
+
+## Verb Stripping (Brevity)
+
+Remove redundant leading verbs like "Enable," "Use," "Display," or "Show" unless
+they are part of a specific technical term.
+
+- **Rule**: If the label works without the verb, remove it
+- **Example**: Change `Enable prompt completion` to `Prompt completion`

.gemini/skills/string-reviewer/references/word-list.md

@@ -0,0 +1,61 @@
+## Terms
+
+### Preferred
+
+- Use **create** when a user is creating or setting up something.
+- Use **allow** instead of **may** to indicate that permission has been granted
+  to perform some action.
+- Use **canceled**, not **cancelled**.
+- Use **configure** to refer to the process of changing the attributes of a
+  feature, even if that includes turning on or off the feature.
+- Use **delete** when the action being performed is destructive.
+- Use **enable** for binary operations that turn a feature or API on. Use "turn
+  on" and "turn off" instead of "enable" and "disable" for other situations.
+- Use **key combination** to refer to pressing multiple keys simultaneously.
+- Use **key sequence** to refer to pressing multiple keys separately in order.
+- Use **modify** to refer to something that has changed vs obtaining the latest
+  version of something.
+- Use **remove** when the action being performed takes an item out of a larger
+  whole, but doesn't destroy the item itself.
+- Use **set up** as a verb. Use **setup** as a noun or adjective.
+- Use **show**. In general, use paired with **hide**.
+- Use **sign in**, **sign out** as a verb. Use **sign-in** or **sign-out** as a
+  noun or adjective.
+- Use **update** when you mean to obtain the latest version of something.
+- Use **want** instead of **like** or **would like**.
+
+#### Don't use
+
+- Don't use **etc.** It's redundant. To convey that a series is incomplete,
+  introduce it with "such as" instead.
+- Don't use **hostname**, use "host name" instead.
+- Don't use **in order to**. It's too formal. "Before you can" is usually better
+  in UI text.
+- Don't use **one or more**. Specify the quantity where possible. Use "at least
+  one" when the quantity is 1+ but you can't be sure of the number. Likewise,
+  use "at least one" when the user must choose a quantity of 1+.
+- Don't use the terms **log in**, **log on**, **login**, **logout** or **log
+  out**.
+- Don't use **like** or **would you like**. Use **want** instead. Better yet,
+  rephrase so that it's not referring to the user's emotional state, but rather
+  what is required.
+
+#### Use with caution
+
+- Avoid using **leverage**, especially as a verb. "Leverage" is considered a
+  buzzword largely devoid of meaning apart from the simpler "use".
+- Avoid using **once** as a synonym for "after". Typically, when "once" is used
+  in this way, it is followed by a verb in the perfect tense.
+- Don't use **e.g.** Use "example", "such as", "like", or "for example". The
+  phrase is always followed by a comma.
+- Don't use **i.e.** unless absolutely essential to make text fit. Use "that is"
+  instead.
+- Use **disable** for binary operations that turn a feature or API off. Use
+  "turn on" and "turn off" instead of "enable" and "disable" for other
+  situations. For UI elements that are not available, use "dimmed" instead of
+  "disabled".
+- Use **please** only when you're asking the user to do something inconvenient,
+  not just following the instructions in a typical flow.
+- Use **really** sparingly in such constructions as "Do you really want to..."
+  Because of the weight it puts on the decision, it should be used to confirm
+  actions that the user is extremely unlikely to make.

.geminiignore

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

.github/CODEOWNERS

@@ -14,3 +14,9 @@
 
 # Docs have a dedicated approver group in addition to maintainers
 /docs/ @google-gemini/gemini-cli-maintainers @google-gemini/gemini-cli-docs
+/README.md @google-gemini/gemini-cli-maintainers @google-gemini/gemini-cli-docs
+
+# Prompt contents, tool definitions, and evals require reviews from prompt approvers
+/packages/core/src/prompts/ @google-gemini/gemini-cli-prompt-approvers
+/packages/core/src/tools/ @google-gemini/gemini-cli-prompt-approvers
+/evals/ @google-gemini/gemini-cli-prompt-approvers

.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/create-pull-request/action.yml

@@ -39,18 +39,22 @@ runs:
       if: "inputs.dry-run != 'true'"
       env:
         GH_TOKEN: '${{ inputs.github-token }}'
+        INPUTS_BRANCH_NAME: '${{ inputs.branch-name }}'
+        INPUTS_PR_TITLE: '${{ inputs.pr-title }}'
+        INPUTS_PR_BODY: '${{ inputs.pr-body }}'
+        INPUTS_BASE_BRANCH: '${{ inputs.base-branch }}'
       shell: 'bash'
       working-directory: '${{ inputs.working-directory }}'
       run: |
         set -e
-        if ! git ls-remote --exit-code --heads origin "${{ inputs.branch-name }}"; then
-          echo "::error::Branch '${{ inputs.branch-name }}' does not exist on the remote repository."
+        if ! git ls-remote --exit-code --heads origin "${INPUTS_BRANCH_NAME}"; then
+          echo "::error::Branch '${INPUTS_BRANCH_NAME}' does not exist on the remote repository."
           exit 1
         fi
         PR_URL=$(gh pr create \
-          --title "${{ inputs.pr-title }}" \
-          --body "${{ inputs.pr-body }}" \
-          --base "${{ inputs.base-branch }}" \
-          --head "${{ inputs.branch-name }}" \
+          --title "${INPUTS_PR_TITLE}" \
+          --body "${INPUTS_PR_BODY}" \
+          --base "${INPUTS_BASE_BRANCH}" \
+          --head "${INPUTS_BRANCH_NAME}" \
           --fill)
         gh pr merge "$PR_URL" --auto

.github/actions/npm-auth-token/action.yml

@@ -30,16 +30,22 @@ runs:
       id: 'npm_auth_token'
       shell: 'bash'
       run: |
-        AUTH_TOKEN="${{ inputs.github-token }}"
-        PACKAGE_NAME="${{ inputs.package-name }}"
+        AUTH_TOKEN="${INPUTS_GITHUB_TOKEN}"
+        PACKAGE_NAME="${INPUTS_PACKAGE_NAME}"
         PRIVATE_REPO="@google-gemini/"
         if [[ "$PACKAGE_NAME" == "$PRIVATE_REPO"* ]]; then
-          AUTH_TOKEN="${{ inputs.github-token }}"
+          AUTH_TOKEN="${INPUTS_GITHUB_TOKEN}"
         elif [[ "$PACKAGE_NAME" == "@google/gemini-cli" ]]; then
-          AUTH_TOKEN="${{ inputs.wombat-token-cli }}"
+          AUTH_TOKEN="${INPUTS_WOMBAT_TOKEN_CLI}"
         elif [[ "$PACKAGE_NAME" == "@google/gemini-cli-core" ]]; then
-          AUTH_TOKEN="${{ inputs.wombat-token-core }}"
+          AUTH_TOKEN="${INPUTS_WOMBAT_TOKEN_CORE}"
         elif [[ "$PACKAGE_NAME" == "@google/gemini-cli-a2a-server" ]]; then
-          AUTH_TOKEN="${{ inputs.wombat-token-a2a-server }}"
+          AUTH_TOKEN="${INPUTS_WOMBAT_TOKEN_A2A_SERVER}"
         fi
         echo "auth-token=$AUTH_TOKEN" >> $GITHUB_OUTPUT
+      env:
+        INPUTS_GITHUB_TOKEN: '${{ inputs.github-token }}'
+        INPUTS_PACKAGE_NAME: '${{ inputs.package-name }}'
+        INPUTS_WOMBAT_TOKEN_CLI: '${{ inputs.wombat-token-cli }}'
+        INPUTS_WOMBAT_TOKEN_CORE: '${{ inputs.wombat-token-core }}'
+        INPUTS_WOMBAT_TOKEN_A2A_SERVER: '${{ inputs.wombat-token-a2a-server }}'

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

@@ -93,15 +93,19 @@ runs:
       id: 'release_branch'
       shell: 'bash'
       run: |
-        BRANCH_NAME="release/${{ inputs.release-tag }}"
+        BRANCH_NAME="release/${INPUTS_RELEASE_TAG}"
         git switch -c "${BRANCH_NAME}"
         echo "BRANCH_NAME=${BRANCH_NAME}" >> "${GITHUB_OUTPUT}"
+      env:
+        INPUTS_RELEASE_TAG: '${{ inputs.release-tag }}'
 
     - name: '⬆️ Update package versions'
       working-directory: '${{ inputs.working-directory }}'
       shell: 'bash'
       run: |
-        npm run release:version "${{ inputs.release-version }}"
+        npm run release:version "${INPUTS_RELEASE_VERSION}"
+      env:
+        INPUTS_RELEASE_VERSION: '${{ inputs.release-version }}'
 
     - name: '💾 Commit and Conditionally Push package versions'
       working-directory: '${{ inputs.working-directory }}'
@@ -163,23 +167,39 @@ runs:
       working-directory: '${{ inputs.working-directory }}'
       env:
         NODE_AUTH_TOKEN: '${{ steps.core-token.outputs.auth-token }}'
+        INPUTS_DRY_RUN: '${{ inputs.dry-run }}'
+        INPUTS_CORE_PACKAGE_NAME: '${{ inputs.core-package-name }}'
       shell: 'bash'
       run: |
         npm publish \
-          --dry-run="${{ inputs.dry-run }}" \
-          --workspace="${{ inputs.core-package-name }}" \
+          --dry-run="${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: '${{ inputs.working-directory }}'
       if: "${{ inputs.dry-run != 'true' }}"
       shell: 'bash'
       run: |
-        npm install "${{ inputs.core-package-name }}@${{ inputs.release-version }}" \
-        --workspace="${{ inputs.cli-package-name }}" \
-        --workspace="${{ inputs.a2a-package-name }}" \
+        npm install "${INPUTS_CORE_PACKAGE_NAME}@${INPUTS_RELEASE_VERSION}" \
+        --workspace="${INPUTS_CLI_PACKAGE_NAME}" \
+        --workspace="${INPUTS_A2A_PACKAGE_NAME}" \
         --save-exact
+      env:
+        INPUTS_CORE_PACKAGE_NAME: '${{ inputs.core-package-name }}'
+        INPUTS_RELEASE_VERSION: '${{ inputs.release-version }}'
+        INPUTS_CLI_PACKAGE_NAME: '${{ inputs.cli-package-name }}'
+        INPUTS_A2A_PACKAGE_NAME: '${{ inputs.a2a-package-name }}'
+
+    - name: '📦 Prepare bundled CLI for npm release'
+      if: "inputs.npm-registry-url != 'https://npm.pkg.github.com/'"
+      working-directory: '${{ inputs.working-directory }}'
+      shell: 'bash'
+      run: |
+        node ${{ github.workspace }}/scripts/prepare-npm-release.js
 
     - name: 'Get CLI Token'
       uses: './.github/actions/npm-auth-token'
@@ -195,13 +215,17 @@ runs:
       working-directory: '${{ inputs.working-directory }}'
       env:
         NODE_AUTH_TOKEN: '${{ steps.cli-token.outputs.auth-token }}'
+        INPUTS_DRY_RUN: '${{ inputs.dry-run }}'
+        INPUTS_CLI_PACKAGE_NAME: '${{ inputs.cli-package-name }}'
       shell: 'bash'
       run: |
         npm publish \
-          --dry-run="${{ inputs.dry-run }}" \
-          --workspace="${{ inputs.cli-package-name }}" \
+          --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'
@@ -217,14 +241,18 @@ runs:
       working-directory: '${{ inputs.working-directory }}'
       env:
         NODE_AUTH_TOKEN: '${{ steps.a2a-token.outputs.auth-token }}'
+        INPUTS_DRY_RUN: '${{ inputs.dry-run }}'
+        INPUTS_A2A_PACKAGE_NAME: '${{ inputs.a2a-package-name }}'
       shell: 'bash'
       # Tag staging for initial release
       run: |
         npm publish \
-          --dry-run="${{ inputs.dry-run }}" \
-          --workspace="${{ inputs.a2a-package-name }}" \
+          --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'
@@ -258,13 +286,33 @@ runs:
       if: "${{ inputs.dry-run != 'true' && inputs.skip-github-release != 'true' && inputs.npm-tag != 'dev' && inputs.npm-registry-url != 'https://npm.pkg.github.com/' }}"
       env:
         GITHUB_TOKEN: '${{ inputs.github-release-token || inputs.github-token }}'
+        INPUTS_RELEASE_TAG: '${{ inputs.release-tag }}'
+        STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'
+        INPUTS_PREVIOUS_TAG: '${{ inputs.previous-tag }}'
       shell: 'bash'
       run: |
-        gh release create "${{ inputs.release-tag }}" \
-          bundle/gemini.js \
-          --target "${{ steps.release_branch.outputs.BRANCH_NAME }}" \
-          --title "Release ${{ inputs.release-tag }}" \
-          --notes-start-tag "${{ inputs.previous-tag }}" \
+        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 "${INPUTS_RELEASE_TAG}" \
+          gemini-cli-bundle.zip \
+          --target "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}" \
+          --title "Release ${INPUTS_RELEASE_TAG}" \
+          --notes-start-tag "${INPUTS_PREVIOUS_TAG}" \
           --generate-notes \
           ${{ inputs.npm-tag != 'latest' && '--prerelease' || '' }}
 
@@ -274,5 +322,8 @@ runs:
       continue-on-error: true
       shell: 'bash'
       run: |
-        echo "Cleaning up release branch ${{ steps.release_branch.outputs.BRANCH_NAME }}..."
-        git push origin --delete "${{ steps.release_branch.outputs.BRANCH_NAME }}"
+        echo "Cleaning up release branch ${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}..."
+        git push origin --delete "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}"
+
+      env:
+        STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'

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

@@ -52,8 +52,10 @@ runs:
       id: 'branch_name'
       shell: 'bash'
       run: |
-        REF_NAME="${{ inputs.ref-name }}"
+        REF_NAME="${INPUTS_REF_NAME}"
         echo "name=${REF_NAME%/merge}" >> $GITHUB_OUTPUT
+      env:
+        INPUTS_REF_NAME: '${{ inputs.ref-name }}'
     - name: 'Build and Push the Docker Image'
       uses: 'docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83' # ratchet:docker/build-push-action@v6
       with:

.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: '${{ inputs.github-sha }}'
         fetch-depth: 0
@@ -44,10 +44,12 @@ runs:
     - name: 'npm build'
       shell: 'bash'
       run: 'npm run build'
+    - name: 'Set up QEMU'
+      uses: 'docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130' # ratchet:docker/setup-qemu-action@v3
     - name: 'Set up Docker Buildx'
-      uses: 'docker/setup-buildx-action@v3'
+      uses: 'docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f' # ratchet:docker/setup-buildx-action@v3
     - name: 'Log in to GitHub Container Registry'
-      uses: 'docker/login-action@v3'
+      uses: 'docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9' # ratchet:docker/login-action@v3
       with:
         registry: 'docker.io'
         username: '${{ inputs.dockerhub-username }}'
@@ -56,8 +58,8 @@ runs:
       id: 'image_tag'
       shell: 'bash'
       run: |-
-        SHELL_TAG_NAME="${{ inputs.github-ref-name }}"
-        FINAL_TAG="${{ inputs.github-sha }}"
+        SHELL_TAG_NAME="${INPUTS_GITHUB_REF_NAME}"
+        FINAL_TAG="${INPUTS_GITHUB_SHA}"
         if [[ "$SHELL_TAG_NAME" =~ ^v[0-9]+\.[0-9]+\.[0-9]+(-[a-zA-Z0-9.-]+)?$ ]]; then
           echo "Release detected."
           FINAL_TAG="${SHELL_TAG_NAME#v}"
@@ -66,15 +68,22 @@ runs:
         fi
         echo "Determined image tag: $FINAL_TAG"
         echo "FINAL_TAG=$FINAL_TAG" >> $GITHUB_OUTPUT
+      env:
+        INPUTS_GITHUB_REF_NAME: '${{ inputs.github-ref-name }}'
+        INPUTS_GITHUB_SHA: '${{ inputs.github-sha }}'
+    # We build amd64 just so we can verify it.
+    # We build and push both amd64 and arm64 in the publish step.
     - name: 'build'
       id: 'docker_build'
       shell: 'bash'
       env:
         GEMINI_SANDBOX_IMAGE_TAG: '${{ steps.image_tag.outputs.FINAL_TAG }}'
         GEMINI_SANDBOX: 'docker'
+        BUILD_SANDBOX_FLAGS: '--platform linux/amd64 --load'
+        STEPS_IMAGE_TAG_OUTPUTS_FINAL_TAG: '${{ steps.image_tag.outputs.FINAL_TAG }}'
       run: |-
         npm run build:sandbox -- \
-          --image google/gemini-cli-sandbox:${{ steps.image_tag.outputs.FINAL_TAG }} \
+          --image "google/gemini-cli-sandbox:${STEPS_IMAGE_TAG_OUTPUTS_FINAL_TAG}" \
           --output-file final_image_uri.txt
         echo "uri=$(cat final_image_uri.txt)" >> $GITHUB_OUTPUT
     - name: 'verify'
@@ -88,8 +97,14 @@ runs:
     - name: 'publish'
       shell: 'bash'
       if: "${{ inputs.dry-run != 'true' }}"
+      env:
+        GEMINI_SANDBOX_IMAGE_TAG: '${{ steps.image_tag.outputs.FINAL_TAG }}'
+        GEMINI_SANDBOX: 'docker'
+        BUILD_SANDBOX_FLAGS: '--platform linux/amd64,linux/arm64 --push'
+        STEPS_IMAGE_TAG_OUTPUTS_FINAL_TAG: '${{ steps.image_tag.outputs.FINAL_TAG }}'
       run: |-
-        docker push "${{ steps.docker_build.outputs.uri }}"
+        npm run build:sandbox -- \
+          --image "google/gemini-cli-sandbox:${STEPS_IMAGE_TAG_OUTPUTS_FINAL_TAG}"
     - name: 'Create issue on failure'
       if: |-
         ${{ failure() }}

.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/setup-npmrc/action.yml

@@ -18,5 +18,7 @@ runs:
       shell: 'bash'
       run: |-
         echo ""@google-gemini:registry=https://npm.pkg.github.com"" > ~/.npmrc
-        echo ""//npm.pkg.github.com/:_authToken=${{ inputs.github-token }}"" >> ~/.npmrc
+        echo ""//npm.pkg.github.com/:_authToken=${INPUTS_GITHUB_TOKEN}"" >> ~/.npmrc
         echo ""@google:registry=https://wombat-dressing-room.appspot.com"" >> ~/.npmrc
+      env:
+        INPUTS_GITHUB_TOKEN: '${{ inputs.github-token }}'

.github/actions/tag-npm-release/action.yml

@@ -71,10 +71,13 @@ runs:
         ${{ inputs.dry-run != 'true' }}
       env:
         NODE_AUTH_TOKEN: '${{ steps.core-token.outputs.auth-token }}'
+        INPUTS_CORE_PACKAGE_NAME: '${{ inputs.core-package-name }}'
+        INPUTS_VERSION: '${{ inputs.version }}'
+        INPUTS_CHANNEL: '${{ inputs.channel }}'
       shell: 'bash'
       working-directory: '${{ inputs.working-directory }}'
       run: |
-        npm dist-tag add ${{ inputs.core-package-name }}@${{ inputs.version }} ${{ inputs.channel }}
+        npm dist-tag add ${INPUTS_CORE_PACKAGE_NAME}@${INPUTS_VERSION} ${INPUTS_CHANNEL}
 
     - name: 'Get cli Token'
       uses: './.github/actions/npm-auth-token'
@@ -91,10 +94,13 @@ runs:
         ${{ inputs.dry-run != 'true' }}
       env:
         NODE_AUTH_TOKEN: '${{ steps.cli-token.outputs.auth-token }}'
+        INPUTS_CLI_PACKAGE_NAME: '${{ inputs.cli-package-name }}'
+        INPUTS_VERSION: '${{ inputs.version }}'
+        INPUTS_CHANNEL: '${{ inputs.channel }}'
       shell: 'bash'
       working-directory: '${{ inputs.working-directory }}'
       run: |
-        npm dist-tag add ${{ inputs.cli-package-name }}@${{ inputs.version }} ${{ inputs.channel }}
+        npm dist-tag add ${INPUTS_CLI_PACKAGE_NAME}@${INPUTS_VERSION} ${INPUTS_CHANNEL}
 
     - name: 'Get a2a Token'
       uses: './.github/actions/npm-auth-token'
@@ -111,10 +117,13 @@ runs:
         ${{ inputs.dry-run == 'false' }}
       env:
         NODE_AUTH_TOKEN: '${{ steps.a2a-token.outputs.auth-token }}'
+        INPUTS_A2A_PACKAGE_NAME: '${{ inputs.a2a-package-name }}'
+        INPUTS_VERSION: '${{ inputs.version }}'
+        INPUTS_CHANNEL: '${{ inputs.channel }}'
       shell: 'bash'
       working-directory: '${{ inputs.working-directory }}'
       run: |
-        npm dist-tag add ${{ inputs.a2a-package-name }}@${{ inputs.version }} ${{ inputs.channel }}
+        npm dist-tag add ${INPUTS_A2A_PACKAGE_NAME}@${INPUTS_VERSION} ${INPUTS_CHANNEL}
 
     - name: 'Log dry run'
       if: |-
@@ -122,4 +131,15 @@ runs:
       shell: 'bash'
       working-directory: '${{ inputs.working-directory }}'
       run: |
-        echo "Dry run: Would have added tag '${{ inputs.channel }}' to version '${{ inputs.version }}' for ${{ inputs.cli-package-name }}, ${{ inputs.core-package-name }}, and ${{ inputs.a2a-package-name }}."
+        echo "Dry run: Would have added tag '${INPUTS_CHANNEL}' to version '${INPUTS_VERSION}' for ${INPUTS_CLI_PACKAGE_NAME}, ${INPUTS_CORE_PACKAGE_NAME}, and ${INPUTS_A2A_PACKAGE_NAME}."
+
+      env:
+        INPUTS_CHANNEL: '${{ inputs.channel }}'
+
+        INPUTS_VERSION: '${{ inputs.version }}'
+
+        INPUTS_CLI_PACKAGE_NAME: '${{ inputs.cli-package-name }}'
+
+        INPUTS_CORE_PACKAGE_NAME: '${{ inputs.core-package-name }}'
+
+        INPUTS_A2A_PACKAGE_NAME: '${{ inputs.a2a-package-name }}'

.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'
 
@@ -64,10 +64,13 @@ runs:
       working-directory: '${{ inputs.working-directory }}'
       run: |-
         gemini_version=$(gemini --version)
-        if [ "$gemini_version" != "${{ inputs.expected-version }}" ]; then
-          echo "❌ NPM Version mismatch: Got $gemini_version from ${{ inputs.npm-package }}, expected ${{ inputs.expected-version }}"
+        if [ "$gemini_version" != "${INPUTS_EXPECTED_VERSION}" ]; then
+          echo "❌ NPM Version mismatch: Got $gemini_version from ${INPUTS_NPM_PACKAGE}, expected ${INPUTS_EXPECTED_VERSION}"
           exit 1
         fi
+      env:
+        INPUTS_EXPECTED_VERSION: '${{ inputs.expected-version }}'
+        INPUTS_NPM_PACKAGE: '${{ inputs.npm-package }}'
 
     - name: 'Clear npm cache'
       shell: 'bash'
@@ -77,11 +80,14 @@ runs:
       shell: 'bash'
       working-directory: '${{ inputs.working-directory }}'
       run: |-
-        gemini_version=$(npx --prefer-online "${{ inputs.npm-package}}" --version)
-        if [ "$gemini_version" != "${{ inputs.expected-version }}" ]; then
-          echo "❌ NPX Run Version mismatch: Got $gemini_version from ${{ inputs.npm-package }}, expected ${{ inputs.expected-version }}"
+        gemini_version=$(npx --prefer-online "${INPUTS_NPM_PACKAGE}" --version)
+        if [ "$gemini_version" != "${INPUTS_EXPECTED_VERSION}" ]; then
+          echo "❌ NPX Run Version mismatch: Got $gemini_version from ${INPUTS_NPM_PACKAGE}, expected ${INPUTS_EXPECTED_VERSION}"
           exit 1
         fi
+      env:
+        INPUTS_NPM_PACKAGE: '${{ inputs.npm-package }}'
+        INPUTS_EXPECTED_VERSION: '${{ inputs.expected-version }}'
 
     - name: 'Install dependencies for integration tests'
       shell: 'bash'

.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/chained_e2e.yml

@@ -31,6 +31,7 @@ jobs:
     name: 'Merge Queue Skipper'
     permissions: 'read-all'
     runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
     outputs:
       skip: '${{ steps.merge-queue-e2e-skipper.outputs.skip-check }}'
     steps:
@@ -42,7 +43,7 @@ jobs:
 
   download_repo_name:
     runs-on: 'gemini-cli-ubuntu-16-core'
-    if: "${{github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_run'}}"
+    if: "github.repository == 'google-gemini/gemini-cli' && (github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_run')"
     outputs:
       repo_name: '${{ steps.output-repo-name.outputs.repo_name }}'
       head_sha: '${{ steps.output-repo-name.outputs.head_sha }}'
@@ -53,7 +54,7 @@ jobs:
           REPO_NAME: '${{ github.event.inputs.repo_name }}'
         run: |
           mkdir -p ./pr
-          echo '${{ env.REPO_NAME }}' > ./pr/repo_name
+          echo "${REPO_NAME}" > ./pr/repo_name
       - uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
         with:
           name: 'repo_name'
@@ -91,7 +92,7 @@ jobs:
     name: 'Parse run context'
     runs-on: 'gemini-cli-ubuntu-16-core'
     needs: 'download_repo_name'
-    if: 'always()'
+    if: "github.repository == 'google-gemini/gemini-cli' && always()"
     outputs:
       repository: '${{ steps.set_context.outputs.REPO }}'
       sha: '${{ steps.set_context.outputs.SHA }}'
@@ -111,11 +112,11 @@ jobs:
     permissions: 'write-all'
     needs:
       - 'parse_run_context'
-    if: 'always()'
+    if: "github.repository == 'google-gemini/gemini-cli' && always()"
     steps:
       - name: 'Set pending status'
         uses: 'myrotvorets/set-commit-status-action@16037e056d73b2d3c88e37e393ff369047f70886' # ratchet:myrotvorets/set-commit-status-action@master
-        if: 'always()'
+        if: "github.repository == 'google-gemini/gemini-cli' && always()"
         with:
           allowForks: 'true'
           repo: '${{ github.repository }}'
@@ -131,7 +132,7 @@ jobs:
       - 'parse_run_context'
     runs-on: 'gemini-cli-ubuntu-16-core'
     if: |
-      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
+      github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
     strategy:
       fail-fast: false
       matrix:
@@ -184,7 +185,7 @@ jobs:
       - 'parse_run_context'
     runs-on: 'macos-latest'
     if: |
-      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
+      github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
@@ -222,7 +223,7 @@ jobs:
       - 'merge_queue_skipper'
       - 'parse_run_context'
     if: |
-      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
+      github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
     runs-on: 'gemini-cli-windows-16-core'
     steps:
       - name: 'Checkout'
@@ -263,6 +264,27 @@ jobs:
         run: 'npm run build'
         shell: 'pwsh'
 
+      - name: 'Ensure Chrome is available'
+        shell: 'pwsh'
+        run: |
+          $chromePaths = @(
+            "${env:ProgramFiles}\Google\Chrome\Application\chrome.exe",
+            "${env:ProgramFiles(x86)}\Google\Chrome\Application\chrome.exe"
+          )
+          $chromeExists = $chromePaths | Where-Object { Test-Path $_ } | Select-Object -First 1
+          if (-not $chromeExists) {
+            Write-Host 'Chrome not found, installing via Chocolatey...'
+            choco install googlechrome -y --no-progress --ignore-checksums
+          }
+          $installed = $chromePaths | Where-Object { Test-Path $_ } | Select-Object -First 1
+          if ($installed) {
+            Write-Host "Chrome found at: $installed"
+            & $installed --version
+          } else {
+            Write-Error 'Chrome installation failed'
+            exit 1
+          }
+
       - name: 'Run E2E tests'
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
@@ -282,13 +304,14 @@ jobs:
       - 'parse_run_context'
     runs-on: 'gemini-cli-ubuntu-16-core'
     if: |
-      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
+      github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
         with:
           ref: '${{ needs.parse_run_context.outputs.sha }}'
           repository: '${{ needs.parse_run_context.outputs.repository }}'
+          fetch-depth: 0
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -301,15 +324,36 @@ jobs:
       - name: 'Build project'
         run: 'npm run build'
 
+      - name: 'Check if evals should run'
+        id: 'check_evals'
+        run: |
+          SHOULD_RUN=$(node scripts/changed_prompt.js)
+          echo "should_run=$SHOULD_RUN" >> "$GITHUB_OUTPUT"
+
       - name: 'Run Evals (Required to pass)'
+        if: "${{ 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: |
-      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
+      github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
     needs:
       - 'e2e_linux'
       - 'e2e_mac'
@@ -320,26 +364,31 @@ jobs:
     steps:
       - name: 'Check E2E test results'
         run: |
-          if [[ ${{ needs.e2e_linux.result }} != 'success' || \
-               ${{ needs.e2e_mac.result }} != 'success' || \
-               ${{ needs.e2e_windows.result }} != 'success' || \
-               ${{ needs.evals.result }} != 'success' ]]; then
+          if [[ ${NEEDS_E2E_LINUX_RESULT} != 'success' || \
+               ${NEEDS_E2E_MAC_RESULT} != 'success' || \
+               ${NEEDS_E2E_WINDOWS_RESULT} != 'success' || \
+               ${NEEDS_EVALS_RESULT} != 'success' ]]; then
             echo "One or more E2E jobs failed."
             exit 1
           fi
           echo "All required E2E jobs passed!"
+        env:
+          NEEDS_E2E_LINUX_RESULT: '${{ needs.e2e_linux.result }}'
+          NEEDS_E2E_MAC_RESULT: '${{ needs.e2e_mac.result }}'
+          NEEDS_E2E_WINDOWS_RESULT: '${{ needs.e2e_windows.result }}'
+          NEEDS_EVALS_RESULT: '${{ needs.evals.result }}'
 
   set_workflow_status:
     runs-on: 'gemini-cli-ubuntu-16-core'
     permissions: 'write-all'
-    if: 'always()'
+    if: "github.repository == 'google-gemini/gemini-cli' && always()"
     needs:
       - 'parse_run_context'
       - 'e2e'
     steps:
       - name: 'Set workflow status'
         uses: 'myrotvorets/set-commit-status-action@16037e056d73b2d3c88e37e393ff369047f70886' # ratchet:myrotvorets/set-commit-status-action@master
-        if: 'always()'
+        if: "github.repository == 'google-gemini/gemini-cli' && always()"
         with:
           allowForks: 'true'
           repo: '${{ github.repository }}'

.github/workflows/ci.yml

@@ -37,6 +37,7 @@ jobs:
     permissions: 'read-all'
     name: 'Merge Queue Skipper'
     runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
     outputs:
       skip: '${{ steps.merge-queue-ci-skipper.outputs.skip-check }}'
     steps:
@@ -49,7 +50,7 @@ jobs:
     name: 'Lint'
     runs-on: 'gemini-cli-ubuntu-16-core'
     needs: 'merge_queue_skipper'
-    if: "${{needs.merge_queue_skipper.outputs.skip == 'false'}}"
+    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
     env:
       GEMINI_LINT_TEMP_DIR: '${{ github.workspace }}/.gemini-linters'
     steps:
@@ -66,7 +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') }}"
@@ -75,7 +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') }}"
@@ -113,9 +114,13 @@ 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'
+    if: "github.repository == 'google-gemini/gemini-cli'"
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
@@ -129,7 +134,7 @@ jobs:
     runs-on: 'gemini-cli-ubuntu-16-core'
     needs:
       - 'merge_queue_skipper'
-    if: "${{needs.merge_queue_skipper.outputs.skip == 'false'}}"
+    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
     permissions:
       contents: 'read'
       checks: 'write'
@@ -156,6 +161,12 @@ 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'
 
@@ -164,10 +175,10 @@ 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
 
@@ -216,7 +227,7 @@ jobs:
     runs-on: 'macos-latest'
     needs:
       - 'merge_queue_skipper'
-    if: "${{needs.merge_queue_skipper.outputs.skip == 'false'}}"
+    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
     permissions:
       contents: 'read'
       checks: 'write'
@@ -252,10 +263,10 @@ jobs:
           NO_COLOR: true
         run: |
           if [[ "${{ 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
 
@@ -311,7 +322,7 @@ jobs:
     name: 'CodeQL'
     runs-on: 'gemini-cli-ubuntu-16-core'
     needs: 'merge_queue_skipper'
-    if: "${{needs.merge_queue_skipper.outputs.skip == 'false'}}"
+    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
     permissions:
       actions: 'read'
       contents: 'read'
@@ -334,7 +345,7 @@ jobs:
   bundle_size:
     name: 'Check Bundle Size'
     needs: 'merge_queue_skipper'
-    if: "${{github.event_name == 'pull_request' && needs.merge_queue_skipper.outputs.skip == 'false'}}"
+    if: "github.repository == 'google-gemini/gemini-cli' && github.event_name == 'pull_request' && needs.merge_queue_skipper.outputs.skip == 'false'"
     runs-on: 'gemini-cli-ubuntu-16-core'
     permissions:
       contents: 'read' # For checkout
@@ -359,7 +370,7 @@ jobs:
     name: 'Slow Test - Win - ${{ matrix.shard }}'
     runs-on: 'gemini-cli-windows-16-core'
     needs: 'merge_queue_skipper'
-    if: "${{needs.merge_queue_skipper.outputs.skip == 'false'}}"
+    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
     timeout-minutes: 60
     strategy:
       matrix:
@@ -418,11 +429,14 @@ 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'
 
@@ -451,7 +465,7 @@ jobs:
 
   ci:
     name: 'CI'
-    if: 'always()'
+    if: "github.repository == 'google-gemini/gemini-cli' && always()"
     needs:
       - 'lint'
       - 'link_checker'
@@ -464,14 +478,22 @@ jobs:
     steps:
       - name: 'Check all job results'
         run: |
-          if [[ (${{ needs.lint.result }} != 'success' && ${{ needs.lint.result }} != 'skipped') || \
-               (${{ needs.link_checker.result }} != 'success' && ${{ needs.link_checker.result }} != 'skipped') || \
-               (${{ needs.test_linux.result }} != 'success' && ${{ needs.test_linux.result }} != 'skipped') || \
-               (${{ needs.test_mac.result }} != 'success' && ${{ needs.test_mac.result }} != 'skipped') || \
-               (${{ needs.test_windows.result }} != 'success' && ${{ needs.test_windows.result }} != 'skipped') || \
-               (${{ needs.codeql.result }} != 'success' && ${{ needs.codeql.result }} != 'skipped') || \
-               (${{ needs.bundle_size.result }} != 'success' && ${{ needs.bundle_size.result }} != 'skipped') ]]; then
+          if [[ (${NEEDS_LINT_RESULT} != 'success' && ${NEEDS_LINT_RESULT} != 'skipped') || \
+               (${NEEDS_LINK_CHECKER_RESULT} != 'success' && ${NEEDS_LINK_CHECKER_RESULT} != 'skipped') || \
+               (${NEEDS_TEST_LINUX_RESULT} != 'success' && ${NEEDS_TEST_LINUX_RESULT} != 'skipped') || \
+               (${NEEDS_TEST_MAC_RESULT} != 'success' && ${NEEDS_TEST_MAC_RESULT} != 'skipped') || \
+               (${NEEDS_TEST_WINDOWS_RESULT} != 'success' && ${NEEDS_TEST_WINDOWS_RESULT} != 'skipped') || \
+               (${NEEDS_CODEQL_RESULT} != 'success' && ${NEEDS_CODEQL_RESULT} != 'skipped') || \
+               (${NEEDS_BUNDLE_SIZE_RESULT} != 'success' && ${NEEDS_BUNDLE_SIZE_RESULT} != 'skipped') ]]; then
             echo "One or more CI jobs failed."
             exit 1
           fi
           echo "All CI jobs passed!"
+        env:
+          NEEDS_LINT_RESULT: '${{ needs.lint.result }}'
+          NEEDS_LINK_CHECKER_RESULT: '${{ needs.link_checker.result }}'
+          NEEDS_TEST_LINUX_RESULT: '${{ needs.test_linux.result }}'
+          NEEDS_TEST_MAC_RESULT: '${{ needs.test_mac.result }}'
+          NEEDS_TEST_WINDOWS_RESULT: '${{ needs.test_windows.result }}'
+          NEEDS_CODEQL_RESULT: '${{ needs.codeql.result }}'
+          NEEDS_BUNDLE_SIZE_RESULT: '${{ needs.bundle_size.result }}'

.github/workflows/deflake.yml

@@ -27,6 +27,7 @@ jobs:
   deflake_e2e_linux:
     name: 'E2E Test (Linux) - ${{ matrix.sandbox }}'
     runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
     strategy:
       fail-fast: false
       matrix:
@@ -68,15 +69,16 @@ jobs:
           VERBOSE: 'true'
         shell: 'bash'
         run: |
-          if [[ "${{ env.IS_DOCKER }}" == "true" ]]; then
-            npm run deflake:test:integration:sandbox:docker -- --runs="${{ env.RUNS }}" -- --testNamePattern "'${{ env.TEST_NAME_PATTERN }}'"
+          if [[ "${IS_DOCKER}" == "true" ]]; then
+            npm run deflake:test:integration:sandbox:docker -- --runs="${RUNS}" -- --testNamePattern "'${TEST_NAME_PATTERN}'"
           else
-            npm run deflake:test:integration:sandbox:none -- --runs="${{ env.RUNS }}" -- --testNamePattern "'${{ env.TEST_NAME_PATTERN }}'"
+            npm run deflake:test:integration:sandbox:none -- --runs="${RUNS}" -- --testNamePattern "'${TEST_NAME_PATTERN}'"
           fi
 
   deflake_e2e_mac:
     name: 'E2E Test (macOS)'
     runs-on: 'macos-latest'
+    if: "github.repository == 'google-gemini/gemini-cli'"
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
@@ -109,12 +111,12 @@ jobs:
           TEST_NAME_PATTERN: '${{ github.event.inputs.test_name_pattern }}'
           VERBOSE: 'true'
         run: |
-          npm run deflake:test:integration:sandbox:none -- --runs="${{ env.RUNS }}" -- --testNamePattern "'${{ env.TEST_NAME_PATTERN }}'"
+          npm run deflake:test:integration:sandbox:none -- --runs="${RUNS}" -- --testNamePattern "'${TEST_NAME_PATTERN}'"
 
   deflake_e2e_windows:
     name: 'Slow E2E - Win'
     runs-on: 'gemini-cli-windows-16-core'
-
+    if: "github.repository == 'google-gemini/gemini-cli'"
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
@@ -167,4 +169,4 @@ jobs:
           TEST_NAME_PATTERN: '${{ github.event.inputs.test_name_pattern }}'
         shell: 'pwsh'
         run: |
-          npm run deflake:test:integration:sandbox:none -- --runs="${{ env.RUNS }}" -- --testNamePattern "'${{ env.TEST_NAME_PATTERN }}'"
+          npm run deflake:test:integration:sandbox:none -- --runs="$env:RUNS" -- --testNamePattern "'$env:TEST_NAME_PATTERN'"

.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/docs-page-action.yml

@@ -19,8 +19,7 @@ concurrency:
 
 jobs:
   build:
-    if: |-
-      ${{ !contains(github.ref_name, 'nightly') }}
+    if: "github.repository == 'google-gemini/gemini-cli' && !contains(github.ref_name, 'nightly')"
     runs-on: 'ubuntu-latest'
     steps:
       - name: 'Checkout'
@@ -39,6 +38,7 @@ jobs:
         uses: 'actions/upload-pages-artifact@56afc609e74202658d3ffba0e8f6dda462b719fa' # ratchet:actions/upload-pages-artifact@v3
 
   deploy:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     environment:
       name: 'github-pages'
       url: '${{ steps.deployment.outputs.page_url }}'

.github/workflows/docs-rebuild.yml

@@ -7,6 +7,7 @@ on:
       - 'docs/**'
 jobs:
   trigger-rebuild:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     runs-on: 'ubuntu-latest'
     steps:
       - name: 'Trigger rebuild'

.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/eval.yml

@@ -44,5 +44,5 @@ jobs:
       - name: 'Run evaluation'
         working-directory: '/app'
         run: |
-          poetry run exp_run --experiment-mode=on-demand --branch-or-commit=${{ github.ref_name }} --model-name=gemini-2.5-pro --dataset=swebench_verified --concurrency=15
+          poetry run exp_run --experiment-mode=on-demand --branch-or-commit="${GITHUB_REF_NAME}" --model-name=gemini-2.5-pro --dataset=swebench_verified --concurrency=15
           poetry run python agent_prototypes/scripts/parse_gcli_logs_experiment.py --experiment_dir=experiments/adhoc/gcli_temp_exp --gcs-bucket="${EVAL_GCS_BUCKET}" --gcs-path=gh_action_artifacts

.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
@@ -23,6 +31,7 @@ jobs:
   evals:
     name: 'Evals (USUALLY_PASSING) nightly run'
     runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
     strategy:
       fail-fast: false
       matrix:
@@ -58,11 +67,16 @@ 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="${{ env.TEST_NAME_PATTERN }}"
+          PATTERN="${TEST_NAME_PATTERN}"
 
           if [[ -n "$PATTERN" ]]; then
             if [[ "$PATTERN" == *.ts || "$PATTERN" == *.js || "$PATTERN" == */* ]]; then
@@ -85,7 +99,7 @@ jobs:
   aggregate-results:
     name: 'Aggregate Results'
     needs: ['evals']
-    if: 'always()'
+    if: "github.repository == 'google-gemini/gemini-cli' && always()"
     runs-on: 'gemini-cli-ubuntu-16-core'
     steps:
       - name: 'Checkout'

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

@@ -121,6 +121,7 @@ jobs:
               'area/security',
               'area/platform',
               'area/extensions',
+              'area/documentation',
               'area/unknown'
             ];
             const labelNames = labels.map(label => label.name).filter(name => allowedLabels.includes(name));
@@ -158,7 +159,7 @@ jobs:
               },
               "coreTools": [
                 "run_shell_command(echo)"
-              ],
+              ]
             }
           prompt: |-
             ## Role
@@ -255,6 +256,14 @@ jobs:
               "Issues with a specific extension."
               "Feature request for the extension ecosystem."
 
+            area/documentation
+            - Description: Issues related to user-facing documentation and other content on the documentation website.
+            - Example Issues:
+              "A typo in a README file."
+              "DOCS: A command is not working as described in the documentation."
+              "A request for a new documentation page."
+              "Instructions missing for skills feature"
+
             area/unknown
             - Description: Issues that do not clearly fit into any other defined area/ category, or where information is too limited to make a determination. Use this when no other area is appropriate.
 

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

@@ -63,7 +63,7 @@ jobs:
 
           echo '🔍 Finding issues missing area labels...'
           NO_AREA_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue -label:area/core -label:area/agent -label:area/enterprise -label:area/non-interactive -label:area/security -label:area/platform -label:area/extensions -label:area/unknown' --limit 100 --json number,title,body)"
+            --search 'is:open is:issue -label:area/core -label:area/agent -label:area/enterprise -label:area/non-interactive -label:area/security -label:area/platform -label:area/extensions -label:area/documentation -label:area/unknown' --limit 100 --json number,title,body)"
 
           echo '🔍 Finding issues missing kind labels...'
           NO_KIND_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
@@ -204,6 +204,7 @@ jobs:
             Categorization Guidelines (Area):
             area/agent: Core Agent, Tools, Memory, Sub-Agents, Hooks, Agent Quality
             area/core: User Interface, OS Support, Core Functionality
+            area/documentation: End-user and contributor-facing documentation, website-related
             area/enterprise: Telemetry, Policy, Quota / Licensing
             area/extensions: Gemini CLI extensions capability
             area/non-interactive: GitHub Actions, SDK, 3P Integrations, Shell Scripting, Command line automation

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

@@ -21,20 +21,21 @@ defaults:
 
 jobs:
   close-stale-issues:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     runs-on: 'ubuntu-latest'
     permissions:
       issues: 'write'
     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

@@ -23,19 +23,25 @@ jobs:
     steps:
       - name: 'Generate GitHub App Token'
         id: 'generate_token'
-        uses: 'actions/create-github-app-token@v2'
+        env:
+          APP_ID: '${{ secrets.APP_ID }}'
+        if: |-
+          ${{ env.APP_ID != '' }}
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
         with:
           app-id: '${{ 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 }}'
+          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);
 
@@ -52,48 +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({
@@ -114,64 +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,
@@ -183,27 +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)) {
@@ -212,9 +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)) {
@@ -222,25 +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/gemini-self-assign-issue.yml

@@ -25,7 +25,7 @@ jobs:
     if: |-
       github.repository == 'google-gemini/gemini-cli' &&
       github.event_name == 'issue_comment' &&
-      contains(github.event.comment.body, '/assign')
+      (contains(github.event.comment.body, '/assign') || contains(github.event.comment.body, '/unassign'))
     runs-on: 'ubuntu-latest'
     steps:
       - name: 'Generate GitHub App Token'
@@ -38,6 +38,7 @@ jobs:
           permission-issues: 'write'
 
       - name: 'Assign issue to user'
+        if: "contains(github.event.comment.body, '/assign')"
         uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
         with:
           github-token: '${{ steps.generate_token.outputs.token }}'
@@ -108,3 +109,42 @@ jobs:
               issue_number: issueNumber,
               body: `👋 @${commenter}, you've been assigned to this issue! Thank you for taking the time to contribute. Make sure to check out our [contributing guidelines](https://github.com/google-gemini/gemini-cli/blob/main/CONTRIBUTING.md).`
             });
+
+      - name: 'Unassign issue from user'
+        if: "contains(github.event.comment.body, '/unassign')"
+        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token }}'
+          script: |
+            const issueNumber = context.issue.number;
+            const commenter = context.actor;
+            const owner = context.repo.owner;
+            const repo = context.repo.repo;
+            const commentBody = context.payload.comment.body.trim();
+
+            if (commentBody !== '/unassign') {
+              return;
+            }
+
+            const issue = await github.rest.issues.get({
+              owner: owner,
+              repo: repo,
+              issue_number: issueNumber,
+            });
+
+            const isAssigned = issue.data.assignees.some(assignee => assignee.login === commenter);
+
+            if (isAssigned) {
+              await github.rest.issues.removeAssignees({
+                owner: owner,
+                repo: repo,
+                issue_number: issueNumber,
+                assignees: [commenter]
+              });
+              await github.rest.issues.createComment({
+                owner: owner,
+                repo: repo,
+                issue_number: issueNumber,
+                body: `👋 @${commenter}, you have been unassigned from this issue.`
+              });
+            }

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

@@ -14,14 +14,14 @@ permissions:
 jobs:
   # Event-based: Quick reaction to new/edited issues in THIS repo
   labeler:
-    if: "github.event_name == 'issues'"
+    if: "github.repository == 'google-gemini/gemini-cli' && github.event_name == 'issues'"
     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'
@@ -36,14 +36,14 @@ jobs:
 
   # Scheduled/Manual: Recursive sync across multiple repos
   sync-maintainer-labels:
-    if: "github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'"
+    if: "github.repository == 'google-gemini/gemini-cli' && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')"
     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

@@ -9,12 +9,13 @@ on:
 
 jobs:
   labeler:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     runs-on: 'ubuntu-latest'
     permissions:
       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

@@ -32,6 +32,7 @@ on:
 
 jobs:
   change-tags:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     runs-on: 'ubuntu-latest'
     environment: "${{ github.event.inputs.environment || 'prod' }}"
     permissions:
@@ -39,7 +40,7 @@ jobs:
       issues: 'write'
     steps:
       - name: 'Checkout repository'
-        uses: 'actions/checkout@v4'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
         with:
           ref: '${{ github.ref }}'
           fetch-depth: 0

.github/workflows/release-manual.yml

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

.github/workflows/release-nightly.yml

@@ -145,7 +145,7 @@ jobs:
           branch-name: 'release/${{ steps.nightly_version.outputs.RELEASE_TAG }}'
           pr-title: 'chore/release: bump version to ${{ steps.nightly_version.outputs.RELEASE_VERSION }}'
           pr-body: 'Automated version bump for nightly release.'
-          github-token: '${{ secrets.GITHUB_TOKEN }}'
+          github-token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
           dry-run: '${{ steps.vars.outputs.is_dry_run }}'
           working-directory: './release'
 

.github/workflows/release-notes.yml

@@ -22,20 +22,21 @@ on:
 
 jobs:
   generate-release-notes:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     runs-on: 'ubuntu-latest'
     permissions:
       contents: 'write'
       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'
 
@@ -56,7 +57,18 @@ jobs:
           GH_TOKEN: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
           BODY: '${{ github.event.inputs.body || github.event.release.body }}'
 
+      - name: 'Validate version'
+        id: 'validate_version'
+        run: |
+          if echo "${{ steps.release_info.outputs.VERSION }}" | grep -q "nightly"; then
+            echo "Nightly release detected. Stopping workflow."
+            echo "CONTINUE=false" >> "$GITHUB_OUTPUT"
+          else
+            echo "CONTINUE=true" >> "$GITHUB_OUTPUT"
+          fi
+
       - name: 'Generate Changelog with Gemini'
+        if: "steps.validate_version.outputs.CONTINUE == 'true'"
         uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
         with:
           gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
@@ -70,8 +82,11 @@ jobs:
 
             Execute the release notes generation process using the information provided.
 
+            When you are done, please output your thought process and the steps you took for future debugging purposes.
+
       - name: 'Create Pull Request'
-        uses: 'peter-evans/create-pull-request@v6'
+        if: "steps.validate_version.outputs.CONTINUE == 'true'"
+        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 }}'
@@ -80,6 +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/release-patch-3-release.yml

@@ -118,6 +118,7 @@ jobs:
           ORIGINAL_RELEASE_VERSION: '${{ steps.patch_version.outputs.RELEASE_VERSION }}'
           ORIGINAL_RELEASE_TAG: '${{ steps.patch_version.outputs.RELEASE_TAG }}'
           ORIGINAL_PREVIOUS_TAG: '${{ steps.patch_version.outputs.PREVIOUS_TAG }}'
+          VARS_CLI_PACKAGE_NAME: '${{ vars.CLI_PACKAGE_NAME }}'
         run: |
           echo "🔍 Verifying no concurrent patch releases have occurred..."
 
@@ -129,7 +130,7 @@ jobs:
 
           # Re-run the same version calculation script
           echo "Re-calculating version to check for changes..."
-          CURRENT_PATCH_JSON=$(node scripts/get-release-version.js --cli-package-name="${{vars.CLI_PACKAGE_NAME}}" --type=patch --patch-from="${CHANNEL}")
+          CURRENT_PATCH_JSON=$(node scripts/get-release-version.js --cli-package-name="${VARS_CLI_PACKAGE_NAME}" --type=patch --patch-from="${CHANNEL}")
           CURRENT_RELEASE_VERSION=$(echo "${CURRENT_PATCH_JSON}" | jq -r .releaseVersion)
           CURRENT_RELEASE_TAG=$(echo "${CURRENT_PATCH_JSON}" | jq -r .releaseTag)
           CURRENT_PREVIOUS_TAG=$(echo "${CURRENT_PATCH_JSON}" | jq -r .previousReleaseTag)
@@ -162,10 +163,15 @@ jobs:
       - name: 'Print Calculated Version'
         run: |-
           echo "Patch Release Summary:"
-          echo "  Release Version: ${{ steps.patch_version.outputs.RELEASE_VERSION }}"
-          echo "  Release Tag: ${{ steps.patch_version.outputs.RELEASE_TAG }}"
-          echo "  NPM Tag: ${{ steps.patch_version.outputs.NPM_TAG }}"
-          echo "  Previous Tag: ${{ steps.patch_version.outputs.PREVIOUS_TAG }}"
+          echo "  Release Version: ${STEPS_PATCH_VERSION_OUTPUTS_RELEASE_VERSION}"
+          echo "  Release Tag: ${STEPS_PATCH_VERSION_OUTPUTS_RELEASE_TAG}"
+          echo "  NPM Tag: ${STEPS_PATCH_VERSION_OUTPUTS_NPM_TAG}"
+          echo "  Previous Tag: ${STEPS_PATCH_VERSION_OUTPUTS_PREVIOUS_TAG}"
+        env:
+          STEPS_PATCH_VERSION_OUTPUTS_RELEASE_VERSION: '${{ steps.patch_version.outputs.RELEASE_VERSION }}'
+          STEPS_PATCH_VERSION_OUTPUTS_RELEASE_TAG: '${{ steps.patch_version.outputs.RELEASE_TAG }}'
+          STEPS_PATCH_VERSION_OUTPUTS_NPM_TAG: '${{ steps.patch_version.outputs.NPM_TAG }}'
+          STEPS_PATCH_VERSION_OUTPUTS_PREVIOUS_TAG: '${{ steps.patch_version.outputs.PREVIOUS_TAG }}'
 
       - name: 'Run Tests'
         if: "${{github.event.inputs.force_skip_tests != 'true'}}"

.github/workflows/release-promote.yml

@@ -335,6 +335,7 @@ jobs:
     name: 'Create Nightly PR'
     needs: ['publish-stable', 'calculate-versions']
     runs-on: 'ubuntu-latest'
+    environment: "${{ github.event.inputs.environment || 'prod' }}"
     permissions:
       contents: 'write'
       pull-requests: 'write'
@@ -362,23 +363,28 @@ jobs:
       - name: 'Create and switch to a new branch'
         id: 'release_branch'
         run: |
-          BRANCH_NAME="chore/nightly-version-bump-${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}"
+          BRANCH_NAME="chore/nightly-version-bump-${NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION}"
           git switch -c "${BRANCH_NAME}"
           echo "BRANCH_NAME=${BRANCH_NAME}" >> "${GITHUB_OUTPUT}"
+        env:
+          NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION: '${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}'
 
       - name: 'Update package versions'
-        run: 'npm run release:version "${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}"'
+        run: 'npm run release:version "${NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION}"'
+        env:
+          NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION: '${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}'
 
       - name: 'Commit and Push package versions'
         env:
           BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'
           DRY_RUN: '${{ github.event.inputs.dry_run }}'
+          NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION: '${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}'
         run: |-
           git add package.json packages/*/package.json
           if [ -f package-lock.json ]; then
             git add package-lock.json
           fi
-          git commit -m "chore(release): bump version to ${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}"
+          git commit -m "chore(release): bump version to ${NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION}"
           if [[ "${DRY_RUN}" == "false" ]]; then
             echo "Pushing release branch to remote..."
             git push --set-upstream origin "${BRANCH_NAME}"
@@ -392,7 +398,7 @@ jobs:
           branch-name: '${{ steps.release_branch.outputs.BRANCH_NAME }}'
           pr-title: 'chore(release): bump version to ${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}'
           pr-body: 'Automated version bump to prepare for the next nightly release.'
-          github-token: '${{ secrets.GITHUB_TOKEN }}'
+          github-token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
           dry-run: '${{ github.event.inputs.dry_run }}'
 
       - name: 'Create Issue on Failure'

.github/workflows/release-rollback.yml

@@ -42,6 +42,7 @@ on:
 
 jobs:
   change-tags:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     environment: "${{ github.event.inputs.environment || 'prod' }}"
     runs-on: 'ubuntu-latest'
     permissions:
@@ -203,7 +204,7 @@ jobs:
         run: |
           ROLLBACK_COMMIT=$(git rev-parse -q --verify "$TARGET_TAG")
           if [ "$ROLLBACK_COMMIT" != "$TARGET_HASH" ]; then
-            echo '❌ Failed to add tag $TARGET_TAG to commit $TARGET_HASH'
+            echo "❌ Failed to add tag ${TARGET_TAG} to commit ${TARGET_HASH}"
             echo '❌ This means the tag was not added, and the workflow should fail.'
             exit 1
           fi

.github/workflows/release-sandbox.yml

@@ -16,6 +16,7 @@ on:
 
 jobs:
   build:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     runs-on: 'ubuntu-latest'
     permissions:
       contents: 'read'

.github/workflows/smoke-test.yml

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

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

@@ -0,0 +1,160 @@
+name: 'Test Build Binary'
+
+on:
+  workflow_dispatch:
+
+permissions:
+  contents: 'read'
+
+defaults:
+  run:
+    shell: 'bash'
+
+jobs:
+  build-node-binary:
+    name: 'Build Binary (${{ matrix.os }})'
+    runs-on: '${{ matrix.os }}'
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - os: 'ubuntu-latest'
+            platform_name: 'linux-x64'
+            arch: 'x64'
+          - os: 'windows-latest'
+            platform_name: 'win32-x64'
+            arch: 'x64'
+          - os: 'macos-latest' # Apple Silicon (ARM64)
+            platform_name: 'darwin-arm64'
+            arch: 'arm64'
+          - os: 'macos-latest' # Intel (x64) running on ARM via Rosetta
+            platform_name: 'darwin-x64'
+            arch: 'x64'
+
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
+
+      - name: 'Optimize Windows Performance'
+        if: "matrix.os == 'windows-latest'"
+        run: |
+          Set-MpPreference -DisableRealtimeMonitoring $true
+          Stop-Service -Name "wsearch" -Force -ErrorAction SilentlyContinue
+          Set-Service -Name "wsearch" -StartupType Disabled
+          Stop-Service -Name "SysMain" -Force -ErrorAction SilentlyContinue
+          Set-Service -Name "SysMain" -StartupType Disabled
+        shell: 'powershell'
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+        with:
+          node-version-file: '.nvmrc'
+          architecture: '${{ matrix.arch }}'
+          cache: 'npm'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Check Secrets'
+        id: 'check_secrets'
+        run: |
+          echo "has_win_cert=${{ secrets.WINDOWS_PFX_BASE64 != '' }}" >> "$GITHUB_OUTPUT"
+          echo "has_mac_cert=${{ secrets.MACOS_CERT_P12_BASE64 != '' }}" >> "$GITHUB_OUTPUT"
+
+      - name: 'Setup Windows SDK (Windows)'
+        if: "matrix.os == 'windows-latest'"
+        uses: 'microsoft/setup-msbuild@6fb02220983dee41ce7ae257b6f4d8f9bf5ed4ce' # ratchet:microsoft/setup-msbuild@v2
+
+      - name: 'Add Signtool to Path (Windows)'
+        if: "matrix.os == 'windows-latest'"
+        run: |
+          $signtoolPath = Get-ChildItem -Path "C:\Program Files (x86)\Windows Kits\10\bin" -Recurse -Filter "signtool.exe" | Sort-Object FullName -Descending | Select-Object -First 1 -ExpandProperty DirectoryName
+          echo "Found signtool at: $signtoolPath"
+          echo "$signtoolPath" >> $env:GITHUB_PATH
+        shell: 'pwsh'
+
+      - name: 'Setup macOS Keychain'
+        if: "startsWith(matrix.os, 'macos') && steps.check_secrets.outputs.has_mac_cert == 'true' && github.event_name != 'pull_request'"
+        env:
+          BUILD_CERTIFICATE_BASE64: '${{ secrets.MACOS_CERT_P12_BASE64 }}'
+          P12_PASSWORD: '${{ secrets.MACOS_CERT_PASSWORD }}'
+          KEYCHAIN_PASSWORD: 'temp-password'
+        run: |
+          # Create the P12 file
+          echo "$BUILD_CERTIFICATE_BASE64" | base64 --decode > certificate.p12
+
+          # Create a temporary keychain
+          security create-keychain -p "$KEYCHAIN_PASSWORD" build.keychain
+          security default-keychain -s build.keychain
+          security unlock-keychain -p "$KEYCHAIN_PASSWORD" build.keychain
+
+          # Import the certificate
+          security import certificate.p12 -k build.keychain -P "$P12_PASSWORD" -T /usr/bin/codesign
+
+          # Allow codesign to access it
+          security set-key-partition-list -S apple-tool:,apple: -s -k "$KEYCHAIN_PASSWORD" build.keychain
+
+          # Set Identity for build script
+          echo "APPLE_IDENTITY=${{ secrets.MACOS_CERT_IDENTITY }}" >> "$GITHUB_ENV"
+
+      - name: 'Setup Windows Certificate'
+        if: "matrix.os == 'windows-latest' && steps.check_secrets.outputs.has_win_cert == 'true' && github.event_name != 'pull_request'"
+        env:
+          PFX_BASE64: '${{ secrets.WINDOWS_PFX_BASE64 }}'
+          PFX_PASSWORD: '${{ secrets.WINDOWS_PFX_PASSWORD }}'
+        run: |
+          $pfx_cert_byte = [System.Convert]::FromBase64String("$env:PFX_BASE64")
+          $certPath = Join-Path (Get-Location) "cert.pfx"
+          [IO.File]::WriteAllBytes($certPath, $pfx_cert_byte)
+          echo "WINDOWS_PFX_FILE=$certPath" >> $env:GITHUB_ENV
+          echo "WINDOWS_PFX_PASSWORD=$env:PFX_PASSWORD" >> $env:GITHUB_ENV
+        shell: 'pwsh'
+
+      - name: 'Build Binary'
+        run: 'npm run build:binary'
+
+      - name: 'Build Core Package'
+        run: 'npm run build -w @google/gemini-cli-core'
+
+      - name: 'Verify Output Exists'
+        run: |
+          if [ -f "dist/${{ matrix.platform_name }}/gemini" ]; then
+            echo "Binary found at dist/${{ matrix.platform_name }}/gemini"
+          elif [ -f "dist/${{ matrix.platform_name }}/gemini.exe" ]; then
+            echo "Binary found at dist/${{ matrix.platform_name }}/gemini.exe"
+          else
+            echo "Error: Binary not found in dist/${{ matrix.platform_name }}/"
+            ls -R dist/
+            exit 1
+          fi
+
+      - name: 'Smoke Test Binary'
+        run: |
+          echo "Running binary smoke test..."
+          if [ -f "dist/${{ matrix.platform_name }}/gemini.exe" ]; then
+            "./dist/${{ matrix.platform_name }}/gemini.exe" --version
+          else
+            "./dist/${{ matrix.platform_name }}/gemini" --version
+          fi
+
+      - name: 'Run Integration Tests'
+        if: "github.event_name != 'pull_request'"
+        env:
+          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+        run: |
+          echo "Running integration tests with binary..."
+          if [[ "${{ matrix.os }}" == 'windows-latest' ]]; then
+            BINARY_PATH="$(cygpath -m "$(pwd)/dist/${{ matrix.platform_name }}/gemini.exe")"
+          else
+            BINARY_PATH="$(pwd)/dist/${{ matrix.platform_name }}/gemini"
+          fi
+          echo "Using binary at $BINARY_PATH"
+          export INTEGRATION_TEST_GEMINI_BINARY_PATH="$BINARY_PATH"
+          npm run test:integration:sandbox:none -- --testTimeout=600000
+
+      - name: 'Upload Artifact'
+        uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
+        with:
+          name: 'gemini-cli-${{ matrix.platform_name }}'
+          path: 'dist/${{ matrix.platform_name }}/'
+          retention-days: 5

.github/workflows/trigger_e2e.yml

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

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

@@ -0,0 +1,315 @@
+name: 'Unassign Inactive Issue Assignees'
+
+# This workflow runs daily and scans every open "help wanted" issue that has
+# one or more assignees.  For each assignee it checks whether they have a
+# non-draft pull request (open and ready for review, or already merged) that
+# is linked to the issue.  Draft PRs are intentionally excluded so that
+# contributors cannot reset the check by opening a no-op PR.  If no
+# qualifying PR is found within 7 days of assignment the assignee is
+# automatically removed and a friendly comment is posted so that other
+# contributors can pick up the work.
+# Maintainers, org members, and collaborators (anyone with write access or
+# above) are always exempted and will never be auto-unassigned.
+
+on:
+  schedule:
+    - cron: '0 9 * * *' # Every day at 09:00 UTC
+  workflow_dispatch:
+    inputs:
+      dry_run:
+        description: 'Run in dry-run mode (no changes will be applied)'
+        required: false
+        default: false
+        type: 'boolean'
+
+concurrency:
+  group: '${{ github.workflow }}'
+  cancel-in-progress: true
+
+defaults:
+  run:
+    shell: 'bash'
+
+jobs:
+  unassign-inactive-assignees:
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    runs-on: 'ubuntu-latest'
+    permissions:
+      issues: 'write'
+
+    steps:
+      - name: 'Generate GitHub App Token'
+        id: 'generate_token'
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+
+      - name: 'Unassign inactive assignees'
+        uses: 'actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b' # ratchet:actions/github-script@v7
+        env:
+          DRY_RUN: '${{ inputs.dry_run }}'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token }}'
+          script: |
+            const dryRun = process.env.DRY_RUN === 'true';
+            if (dryRun) {
+              core.info('DRY RUN MODE ENABLED: No changes will be applied.');
+            }
+
+            const owner = context.repo.owner;
+            const repo = context.repo.repo;
+            const GRACE_PERIOD_DAYS = 7;
+            const now = new Date();
+
+            let maintainerLogins = new Set();
+            const teams = ['gemini-cli-maintainers', 'gemini-cli-askmode-approvers', 'gemini-cli-docs'];
+
+            for (const team_slug of teams) {
+              try {
+                const members = await github.paginate(github.rest.teams.listMembersInOrg, {
+                  org: owner,
+                  team_slug,
+                });
+                for (const m of members) maintainerLogins.add(m.login.toLowerCase());
+                core.info(`Fetched ${members.length} members from team ${team_slug}.`);
+              } catch (e) {
+                core.warning(`Could not fetch team ${team_slug}: ${e.message}`);
+              }
+            }
+
+            const isGooglerCache = new Map();
+            const isGoogler = async (login) => {
+              if (isGooglerCache.has(login)) return isGooglerCache.get(login);
+              try {
+                for (const org of ['googlers', 'google']) {
+                  try {
+                    await github.rest.orgs.checkMembershipForUser({ org, username: login });
+                    isGooglerCache.set(login, true);
+                    return true;
+                  } catch (e) {
+                    if (e.status !== 404) throw e;
+                  }
+                }
+              } catch (e) {
+                core.warning(`Could not check org membership for ${login}: ${e.message}`);
+              }
+              isGooglerCache.set(login, false);
+              return false;
+            };
+
+            const permissionCache = new Map();
+            const isPrivilegedUser = async (login) => {
+              if (maintainerLogins.has(login.toLowerCase())) return true;
+
+              if (permissionCache.has(login)) return permissionCache.get(login);
+
+              try {
+                const { data } = await github.rest.repos.getCollaboratorPermissionLevel({
+                  owner,
+                  repo,
+                  username: login,
+                });
+                const privileged = ['admin', 'maintain', 'write', 'triage'].includes(data.permission);
+                permissionCache.set(login, privileged);
+                if (privileged) {
+                  core.info(`  @${login} is a repo collaborator (${data.permission}) — exempt.`);
+                  return true;
+                }
+              } catch (e) {
+                if (e.status !== 404) {
+                  core.warning(`Could not check permission for ${login}: ${e.message}`);
+                }
+              }
+
+              const googler = await isGoogler(login);
+              permissionCache.set(login, googler);
+              return googler;
+            };
+
+            core.info('Fetching open "help wanted" issues with assignees...');
+
+            const issues = await github.paginate(github.rest.issues.listForRepo, {
+              owner,
+              repo,
+              state: 'open',
+              labels: 'help wanted',
+              per_page: 100,
+            });
+
+            const assignedIssues = issues.filter(
+              (issue) => !issue.pull_request && issue.assignees && issue.assignees.length > 0
+            );
+
+            core.info(`Found ${assignedIssues.length} assigned "help wanted" issues.`);
+
+            let totalUnassigned = 0;
+
+              let timelineEvents = [];
+              try {
+                timelineEvents = await github.paginate(github.rest.issues.listEventsForTimeline, {
+                  owner,
+                  repo,
+                  issue_number: issue.number,
+                  per_page: 100,
+                  mediaType: { previews: ['mockingbird'] },
+                });
+              } catch (err) {
+                core.warning(`Could not fetch timeline for issue #${issue.number}: ${err.message}`);
+                continue;
+              }
+
+              const assignedAtMap = new Map();
+
+              for (const event of timelineEvents) {
+                if (event.event === 'assigned' && event.assignee) {
+                  const login = event.assignee.login.toLowerCase();
+                  const at = new Date(event.created_at);
+                  assignedAtMap.set(login, at);
+                } else if (event.event === 'unassigned' && event.assignee) {
+                  assignedAtMap.delete(event.assignee.login.toLowerCase());
+                }
+              }
+
+              const linkedPRAuthorSet = new Set();
+              const seenPRKeys = new Set();
+
+              for (const event of timelineEvents) {
+                if (
+                  event.event !== 'cross-referenced' ||
+                  !event.source ||
+                  event.source.type !== 'pull_request' ||
+                  !event.source.issue ||
+                  !event.source.issue.user ||
+                  !event.source.issue.number ||
+                  !event.source.issue.repository
+                ) continue;
+
+                const prOwner  = event.source.issue.repository.owner.login;
+                const prRepo   = event.source.issue.repository.name;
+                const prNumber = event.source.issue.number;
+                const prAuthor = event.source.issue.user.login.toLowerCase();
+                const prKey    = `${prOwner}/${prRepo}#${prNumber}`;
+
+                if (seenPRKeys.has(prKey)) continue;
+                seenPRKeys.add(prKey);
+
+                try {
+                  const { data: pr } = await github.rest.pulls.get({
+                    owner: prOwner,
+                    repo: prRepo,
+                    pull_number: prNumber,
+                  });
+
+                  const isReady = (pr.state === 'open' && !pr.draft) ||
+                                  (pr.state === 'closed' && pr.merged_at !== null);
+
+                  core.info(
+                    `  PR ${prKey} by @${prAuthor}: ` +
+                    `state=${pr.state}, draft=${pr.draft}, merged=${!!pr.merged_at} → ` +
+                    (isReady ? 'qualifies' : 'does NOT qualify (draft or closed without merge)')
+                  );
+
+                  if (isReady) linkedPRAuthorSet.add(prAuthor);
+                } catch (err) {
+                  core.warning(`Could not fetch PR ${prKey}: ${err.message}`);
+                }
+              }
+
+              const assigneesToRemove = [];
+
+              for (const assignee of issue.assignees) {
+                const login = assignee.login.toLowerCase();
+
+                if (await isPrivilegedUser(assignee.login)) {
+                  core.info(`  @${assignee.login}: privileged user — skipping.`);
+                  continue;
+                }
+
+                const assignedAt = assignedAtMap.get(login);
+
+                if (!assignedAt) {
+                  core.warning(
+                    `No 'assigned' event found for @${login} on issue #${issue.number}; ` +
+                    `falling back to issue creation date (${issue.created_at}).`
+                  );
+                  assignedAtMap.set(login, new Date(issue.created_at));
+                }
+                const resolvedAssignedAt = assignedAtMap.get(login);
+
+                const daysSinceAssignment = (now - resolvedAssignedAt) / (1000 * 60 * 60 * 24);
+
+                core.info(
+                  `  @${login}: assigned ${daysSinceAssignment.toFixed(1)} day(s) ago, ` +
+                  `ready-for-review PR: ${linkedPRAuthorSet.has(login) ? 'yes' : 'no'}`
+                );
+
+                if (daysSinceAssignment < GRACE_PERIOD_DAYS) {
+                  core.info(`    → within grace period, skipping.`);
+                  continue;
+                }
+
+                if (linkedPRAuthorSet.has(login)) {
+                  core.info(`    → ready-for-review PR found, keeping assignment.`);
+                  continue;
+                }
+
+                core.info(`    → no ready-for-review PR after ${GRACE_PERIOD_DAYS} days, will unassign.`);
+                assigneesToRemove.push(assignee.login);
+              }
+
+              if (assigneesToRemove.length === 0) {
+                continue;
+              }
+
+              if (!dryRun) {
+                try {
+                  await github.rest.issues.removeAssignees({
+                    owner,
+                    repo,
+                    issue_number: issue.number,
+                    assignees: assigneesToRemove,
+                  });
+                } catch (err) {
+                  core.warning(
+                    `Failed to unassign ${assigneesToRemove.join(', ')} from issue #${issue.number}: ${err.message}`
+                  );
+                  continue;
+                }
+
+                const mentionList = assigneesToRemove.map((l) => `@${l}`).join(', ');
+                const commentBody =
+                  `👋 ${mentionList} — it has been more than ${GRACE_PERIOD_DAYS} days since ` +
+                  `you were assigned to this issue and we could not find a pull request ` +
+                  `ready for review.\n\n` +
+                  `To keep the backlog moving and ensure issues stay accessible to all ` +
+                  `contributors, we require a PR that is open and ready for review (not a ` +
+                  `draft) within ${GRACE_PERIOD_DAYS} days of assignment.\n\n` +
+                  `We are automatically unassigning you so that other contributors can pick ` +
+                  `this up. If you are still actively working on this, please:\n` +
+                  `1. Re-assign yourself by commenting \`/assign\`.\n` +
+                  `2. Open a PR (not a draft) linked to this issue (e.g. \`Fixes #${issue.number}\`) ` +
+                  `within ${GRACE_PERIOD_DAYS} days so the automation knows real progress is being made.\n\n` +
+                  `Thank you for your contribution — we hope to see a PR from you soon! 🙏`;
+
+                try {
+                  await github.rest.issues.createComment({
+                    owner,
+                    repo,
+                    issue_number: issue.number,
+                    body: commentBody,
+                  });
+                } catch (err) {
+                  core.warning(
+                    `Failed to post comment on issue #${issue.number}: ${err.message}`
+                  );
+                }
+              }
+
+              totalUnassigned += assigneesToRemove.length;
+              core.info(
+                `  ${dryRun ? '[DRY RUN] Would have unassigned' : 'Unassigned'}: ${assigneesToRemove.join(', ')}`
+              );
+            }
+
+            core.info(`\nDone. Total assignees ${dryRun ? 'that would be' : ''} unassigned: ${totalUnassigned}`);

.github/workflows/verify-release.yml

@@ -28,6 +28,7 @@ on:
 
 jobs:
   verify-release:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     environment: "${{ github.event.inputs.environment || 'prod' }}"
     strategy:
       fail-fast: false

.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/

.vscode/settings.json

@@ -7,6 +7,9 @@
   "[typescript]": {
     "editor.defaultFormatter": "esbenp.prettier-vscode"
   },
+  "[typescriptreact]": {
+    "editor.defaultFormatter": "esbenp.prettier-vscode"
+  },
   "[json]": {
     "editor.defaultFormatter": "esbenp.prettier-vscode"
   },

CONTRIBUTING.md

@@ -60,26 +60,54 @@ 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.
 
-### Self assigning issues
+    ```bash
+    ./scripts/review.sh <PR_NUMBER> [model]
+    ```
 
-To assign an issue to yourself, simply add a comment with the text `/assign`.
-The comment must contain only that text and nothing else. This command will
-assign the issue to you, provided it is not already assigned.
+    **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
+
+To assign an issue to yourself, simply add a comment with the text `/assign`. To
+unassign yourself from an issue, add a comment with the text `/unassign`.
+
+The comment must contain only that text and nothing else. These commands will
+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.
@@ -264,7 +292,8 @@ 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
 
@@ -294,8 +323,8 @@ 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
@@ -325,21 +354,6 @@ npm run lint
 - **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
@@ -493,8 +507,9 @@ 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.
@@ -545,7 +560,7 @@ 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
@@ -71,13 +71,13 @@ 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
 
-New preview releases will be published each week at UTC 2359 on Tuesdays. These
+New preview releases will be published each week at UTC 23:59 on Tuesdays. These
 releases will not have been fully vetted and may contain regressions or other
 outstanding issues. Please help us test and install with `preview` tag.
 
@@ -87,7 +87,7 @@ npm install -g @google/gemini-cli@preview
 
 ### Stable
 
-- New stable releases will be published each week at UTC 2000 on Tuesdays, this
+- New stable releases will be published each week at UTC 20:00 on Tuesdays, this
   will be the full promotion of last week's `preview` release + any bug fixes
   and validations. Use `latest` tag.
 
@@ -97,7 +97,7 @@ npm install -g @google/gemini-cli@latest
 
 ### Nightly
 
-- New releases will be published each day at UTC 0000. This will be all changes
+- New releases will be published each day at UTC 00:00. This will be all changes
   from the main branch as represented at time of release. It should be assumed
   there are pending validations and issues. Use `nightly` tag.
 
@@ -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/get-started/configuration.md) - Settings and
-  customization.
-- [**Keyboard Shortcuts**](./docs/cli/keyboard-shortcuts.md) - Productivity
-  tips.
+- [**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/cli/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/tools/index.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 API Development**](./docs/core/tools-api.md) - Create custom tools.
-- [**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/troubleshooting.md) - Common issues and
-  solutions.
-- [**FAQ**](./docs/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)** -
@@ -377,12 +383,14 @@ for planned features and priorities.
 
 ### Uninstall
 
-See the [Uninstall Guide](docs/cli/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