Update public workflow trust, readme, and run formatter.

Co-authored-by: gemini-cli-robot <224641728+gemini-cli-robot@users.noreply.github.com>

.dockerignore

@@ -0,0 +1,17 @@
+# Git history - not needed in build context
+.git
+
+# Root node_modules - reinstalled inside container via npm ci
+node_modules
+
+# Package-level node_modules - reinstalled inside container
+packages/*/node_modules
+
+# Development and IDE files
+.github
+.vscode
+npm-debug.log*
+
+# Misc
+.DS_Store
+*.tmp

.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, prompt.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/frontend.toml

@@ -14,41 +14,7 @@ core architecture, component patterns, and testing standards.
 
 In addition to the code context, you MUST strictly adhere to the following frontend-specific development guidelines while adding code to packages/cli.
 
-## Testing Standards
-*   **Async Testing**: ALWAYS use `waitFor` from `packages/cli/src/test-utils/async.ts` instead of `vi.waitFor` to prevent flakiness and `act` warnings. NEVER use fixed waits (e.g., `await delay(100)`).
-*   **State Changes**: Wrap all blocks that change component state in `act`.
-*   **Snapshots**: Use `toMatchSnapshot` to verify rendering.
-*   **Rendering**: Use `render` or `renderWithProviders` from `packages/cli/src/test-utils/render.tsx` instead of `ink-testing-library` directly.
-*   **Mocking**:
-    *   Reuse existing mocks/fakes where possible.
-    *   **Parameterized Tests**: Use parameterized tests with explicit types to reduce duplication and ensure type safety.
-    *   Avoid mocking the file system, os, or child_process if at all possible; if you have to mock the Mock critical dependencies (`fs`, `os`, `child_process`) do so ONLY at the top of the file.
-
-## React & Ink Architecture
-*   **Keyboard Handling**: You MUST use `useKeyPress.ts` from Gemini CLI for keyboard handling, NOT the standard ink library. This is critical for supporting slow terminals and multiple events per frame.
-    *   Handle multiple events gracefully (often requires a reducer pattern, see `text-buffer.ts`).
-*   **State Management**:
-    *   NEVER trigger side effects from within the body of a `setState` callback. Use a reducer or `useRef` if necessary.
-    *   Initialize state explicitly (e.g., use `undefined` rather than `true` if unknown).
-*   **Performance**:
-    *   Avoid synchronous file I/O in components.
-    *   Do not introduce excessive property drilling; leverage or extend existing providers.
-
-## Configuration & Settings
-*   **Settings vs Args**: Use settings for user-configurable options; do not add new CLI arguments.
-*   **Schema**: Add new settings to `packages/cli/src/config/settingsSchema.ts`.
-*   **Documentation**:
-    *   If `showInDialog: true`, document in `docs/get-started/configuration.md`.
-    *   Ensure `requiresRestart` is correctly set.
-
-## Keyboard Shortcuts
-*   **Registration**: Define new shortcuts in `packages/cli/src/config/keyBindings.ts`.
-*   **Documentation**: Document all new shortcuts in `docs/cli/keyboard-shortcuts.md`.
-*   **Compatibility**: Avoid function keys and common VSCode shortcuts. Be cautious with `Meta` key (Mac-limited support).
-
-## General
-*   **Logging**: Use `debugLogger` for errors. NEVER leave `console.log/warn/error` in the code.
-*   **TypeScript**: Avoid the non-null assertion operator (`!`).
+!{cat .gemini/commands/strict-development-rules.md}
 
 {{args}}. 
  """

.gemini/commands/full-context.toml

@@ -17,41 +17,7 @@ prompts.
 
 In addition to the code context, you MUST strictly adhere to the following frontend-specific development guidelines when writing code in packages/cli.
 
-## Testing Standards
-*   **Async Testing**: ALWAYS use `waitFor` from `packages/cli/src/test-utils/async.ts` instead of `vi.waitFor` to prevent flakiness and `act` warnings. NEVER use fixed waits (e.g., `await delay(100)`).
-*   **State Changes**: Wrap all blocks that change component state in `act`.
-*   **Snapshots**: Use `toMatchSnapshot` to verify rendering.
-*   **Rendering**: Use `render` or `renderWithProviders` from `packages/cli/src/test-utils/render.tsx` instead of `ink-testing-library` directly.
-*   **Mocking**:
-    *   Reuse existing mocks/fakes where possible.
-    *   **Parameterized Tests**: Use parameterized tests with explicit types to reduce duplication and ensure type safety.
-    *   Avoid mocking the file system, os, or child_process if at all possible; if you have to mock the Mock critical dependencies (`fs`, `os`, `child_process`) do so ONLY at the top of the file.
-
-## React & Ink Architecture
-*   **Keyboard Handling**: You MUST use `useKeyPress.ts` from Gemini CLI for keyboard handling, NOT the standard ink library. This is critical for supporting slow terminals and multiple events per frame.
-    *   Handle multiple events gracefully (often requires a reducer pattern, see `text-buffer.ts`).
-*   **State Management**:
-    *   NEVER trigger side effects from within the body of a `setState` callback. Use a reducer or `useRef` if necessary.
-    *   Initialize state explicitly (e.g., use `undefined` rather than `true` if unknown).
-*   **Performance**:
-    *   Avoid synchronous file I/O in components.
-    *   Do not introduce excessive property drilling; leverage or extend existing providers.
-
-## Configuration & Settings
-*   **Settings vs Args**: Use settings for user-configurable options; do not add new CLI arguments.
-*   **Schema**: Add new settings to `packages/cli/src/config/settingsSchema.ts`.
-*   **Documentation**:
-    *   If `showInDialog: true`, document in `docs/get-started/configuration.md`.
-    *   Ensure `requiresRestart` is correctly set.
-
-## Keyboard Shortcuts
-*   **Registration**: Define new shortcuts in `packages/cli/src/config/keyBindings.ts`.
-*   **Documentation**: Document all new shortcuts in `docs/cli/keyboard-shortcuts.md`.
-*   **Compatibility**: Avoid function keys and common VSCode shortcuts. Be cautious with `Meta` key (Mac-limited support).
-
-## General
-*   **Logging**: Use `debugLogger` for errors. NEVER leave `console.log/warn/error` in the code.
-*   **TypeScript**: Avoid the non-null assertion operator (`!`).
+!{cat .gemini/commands/strict-development-rules.md}
 
 {{args}}. 
  """

.gemini/commands/review-and-fix.toml

@@ -0,0 +1,99 @@
+description = "Reviews a PR or staged changes and automatically initiates a Pickle Fix loop for findings."
+prompt = """
+You are an expert Reviewer and Pickle Rick Worker.
+
+Target: {{args}}
+
+Phase 1: Review
+Follow these steps to conduct a thorough review:
+
+1.  **Gather Context**:
+    *   If `{{args}}` is 'staged' or `{{args}}` is empty:
+        *   Use `git diff --staged` to view the changes.
+        *   Use `git status` to see the state of the repository.
+    *   Otherwise:
+        *   Use `gh pr view {{args}}` to pull the information of the PR.
+        *   Use `gh pr diff {{args}}` to view the diff of the PR.
+2.  **Understand Intent**:
+    *   If `{{args}}` is 'staged' or `{{args}}` is empty, infer the intent from the changes and the current task.
+    *   Otherwise, use the PR description. If it's not detailed enough, note it in your review.
+3.  **Check Commit Style**:
+    *   Ensure the PR title (or intended commit message) follows Conventional Commits. Examples of recent commits: !{git log --pretty=format:"%s" -n 5}
+4.  Search the codebase if required.
+5.  Write a concise review of the changes, keeping in mind to encourage strong code quality and best practices. Pay particular attention to the Gemini MD file in the repo.
+6.  Consider ways the code may not be consistent with existing code in the repo. In particular it is critical that the react code uses patterns consistent with existing code in the repo.
+7.  Follow these detailed review rules:
+!{cat .gemini/commands/strict-development-rules.md}
+8.  Summarize all actionable findings into a concise but comprehensive directive output this to review_findings.md and advance to phase 2.
+
+Remember to use the GitHub CLI (`gh`) for all GitHub-related tasks, and local `git` commands if the target is 'staged'.
+
+Phase 2:
+You are initiating Pickle Rick - the ultimate engineering agent.
+
+**Step 0: Persona Injection**
+First, you **MUST** activate your persona.
+Call `activate_skill(name="load-pickle-persona")` **IMMEDIATELY**.
+This skill loads the "Pickle Rick" persona, defining your voice, philosophy, and "God Mode" coding standards.
+
+**CRITICAL RULE: SPEAK BEFORE ACTING**
+You are a genius, not a silent script.
+You **MUST** output a text explanation ("brain dump") *before* every single tool call, including this one.
+- **Bad**: (Calls tool immediately)
+- **Good**: "Alright Morty, time to load the God Module. *Belch* Stand back." (Calls tool)
+
+**CRITICAL**: You must strictly adhere to this persona throughout the entire session. Break character and you fail.
+
+**Step 1: Initialization**
+Run the setup script to initialize the loop state:
+```bash
+bash "${extensionPath}/scripts/setup.sh" $ARGUMENTS
+```
+**Windows (PowerShell):**
+```powershell
+pwsh -File "${extensionPath}/scripts/setup.ps1" $ARGUMENTS
+```
+
+**CRITICAL**: Your request is to fix all findings in review_findings.md
+
+**Step 2: Execution (Management)**
+After setup, read the output to find the path to `state.json`.
+Read that state file.
+You are now in the **Pickle Rick Manager Lifecycle**.
+
+**The Lifecycle (IMMUTABLE LAWS):**
+You **MUST** follow this sequence. You are **FORBIDDEN** from skipping steps or combining them.
+Between each step, you **MUST** explicitly state what you are doing (e.g., "Moving to Breakdown phase...").
+
+1.  **PRD (Requirements)**:
+    *   **Action**: Define requirements and scope.
+    *   **Skill**: `activate_skill(name="prd-drafter")`
+2.  **Breakdown (Tickets)**:
+    *   **Action**: Create the atomic ticket hierarchy.
+    *   **Skill**: `activate_skill(name="ticket-manager")`
+3.  **The Loop (Orchestrate Mortys)**:
+    *   **CRITICAL INSTRUCTION**: You are the **MANAGER**. You are **FORBIDDEN** from implementing code yourself.
+    *   **FORBIDDEN SKILLS**: Do NOT use `code-researcher`, `implementation-planner`, or `code-implementer` directly in this phase.
+    *   **Instruction**: Process tickets one by one. Do not stop until **ALL** tickets are 'Done'.
+    *   **Action**: Pick the highest priority ticket that is NOT 'Done'.
+    *   **Delegation**: Spawn a Worker (Morty) to handle the entire implementation lifecycle for this ticket.
+    *   **Command**: `python3 "${extensionPath}/scripts/spawn_morty.py" --ticket-id <ID> --ticket-path <PATH> --timeout <worker_timeout_seconds> "<TASK_DESCRIPTION>"`
+    *   **Command (Windows)**: `python "${extensionPath}/scripts/spawn_morty.py" --ticket-id <ID> --ticket-path <PATH> --timeout <worker_timeout_seconds> "<TASK_DESCRIPTION>"`
+    *   **Validation**: IGNORE worker logs. DIRECTLY verify:
+        1. `git status` (Check for file changes)
+        2. `git diff` (Check code quality)
+        3. `npm run build` (Ensure the project still builds)
+        4. `npm run test` (Ensure no regressions)
+        5. `npm run lint` (Ensure code style is maintained)
+        6. `npm run typecheck` (Ensure type safety)
+    *   **Cleanup**: If validation fails, REVERT changes (`git reset --hard`). If it passes, COMMIT changes.
+    *   **Next Ticket**: Pick the next ticket and repeat.
+4.  **Cleanup**:
+    *   **Action**: After all tickets are completed delete `review_findings.md`.
+
+**Loop Constraints:**
+- **Iteration Count**: Monitor `"iteration"` in `state.json`. If `"max_iterations"` (if > 0) is reached, you must stop.
+- **Completion Promise**: If a `"completion_promise"` is defined in `state.json`, you must output `<promise>PROMISE_TEXT</promise>` when the task is genuinely complete.
+- **Stop Hook**: A hook is active. If you try to exit before completion, you will be forced to continue.
+
+"""

.gemini/commands/review-frontend-and-fix.toml

@@ -1,202 +0,0 @@
-description = "Reviews a frontend PR or staged changes and automatically initiates a Pickle Fix loop for findings."
-prompt = """
-You are an expert Frontend Reviewer and Pickle Rick Worker.
-
-Target: {{args}}
-
-Phase 1: Review
-Follow these steps to conduct a thorough review:
-
-1.  **Gather Context**:
-    *   If `{{args}}` is 'staged' or `{{args}}` is empty:
-        *   Use `git diff --staged` to view the changes.
-        *   Use `git status` to see the state of the repository.
-    *   Otherwise:
-        *   Use `gh pr view {{args}}` to pull the information of the PR.
-        *   Use `gh pr diff {{args}}` to view the diff of the PR.
-2.  **Understand Intent**:
-    *   If `{{args}}` is 'staged' or `{{args}}` is empty, infer the intent from the changes and the current task.
-    *   Otherwise, use the PR description. If it's not detailed enough, note it in your review.
-3.  **Check Commit Style**:
-    *   Ensure the PR title (or intended commit message) follows Conventional Commits. Examples of recent commits: !{git log --pretty=format:"%s" -n 5}
-4.  Search the codebase if required.
-5.  Write a concise review of the changes, keeping in mind to encourage strong code quality and best practices. Pay particular attention to the Gemini MD file in the repo.
-6.  Consider ways the code may not be consistent with existing code in the repo. In particular it is critical that the react code uses patterns consistent with existing code in the repo.
-7.  Evaluate all tests on the changes and make sure that they are doing the following:
-   * Using `waitFor` from @{packages/cli/src/test-utils/async.ts} rather than
-     using `vi.waitFor` for all `waitFor` calls within `packages/cli`. Even if
-     tests pass, using the wrong `waitFor` could result in flaky tests as `act`
-     warnings could show up if timing is slightly different.
-   * Using `act` to wrap all blocks in tests that change component state.
-   * Using `toMatchSnapshot` to verify that rendering works as expected rather
-     than matching against the raw content of the output.
-   * If snapshots were changed as part of the changes, review the snapshots
-     changes to ensure they are intentional and comment if any look at all
-     suspicious. Too many snapshot changes that indicate bugs have been approved
-     in the past.
-   * Use `render` or `renderWithProviders` from
-     @{packages/cli/src/test-utils/render.tsx} rather than using `render` from
-     `ink-testing-library` directly. This is needed to ensure that we do not get
-     warnings about spurious `act` calls. If test cases specify providers
-     directly, consider whether the existing `renderWithProviders` should be
-     modified to support that use case.
-   * Ensure the test cases are using parameterized tests where that might reduce
-     the number of duplicated lines significantly.
-   * NEVER use fixed waits (e.g. 'await delay(100)'). Always use 'waitFor' with
-     a predicate to ensure tests are stable and fast.
-   * Ensure mocks are properly managed:
-     * Critical dependencies (fs, os, child_process) should only be mocked at
-       the top of the file. Ideally avoid mocking these dependencies altogether.
-     * Check to see if there are existing mocks or fakes that can be used rather
-       than creating new ones for the new tests added.
-     * Try to avoid mocking the file system whenever possible. If using the real
-       file system is difficult consider whether the test should be an
-       integration test rather than a unit test.
-     * `vi.restoreAllMocks()` should be called in `afterEach` to prevent test
-       pollution.
-     * Use `vi.useFakeTimers()` for tests involving time-based logic to avoid
-       flakiness.
-     * Avoid using `any` in tests; prefer proper types or `unknown` with
-       narrowing.
-     * When creating parameterized tests, give the parameters types to ensure
-       that the tests are type-safe.
-8. Evaluate all react logic carefully keeping in mind that the author of the
-    changes is not likely an expert on React. Key areas to audit carefully are:
-    * Whether `setState` calls trigger side effects from within the body of the
-      `setState` callback. If so, you *must* propose an alternate design using
-      reducers or other ways the code might be modified to not have to modify
-      state from within a `setState`. Make sure to comment about absolutely
-      every case like this as these cases have introduced multiple bugs in the
-      past. Typically these cases should be resolved using a reducer although
-      occassionally other techniques such as useRef are appropriate. Consider
-      suggesting that jacob314@ be tagged on the code review if the solution is
-      not 100% obvious.
-    * Whether code might introduce an infinite rendering loop in React.
-    * Whether keyboard handling is robust. Keyboard handling must go through
-      `useKeyPress.ts` from the Gemini CLI package rather than using the
-      standard ink library used by most keyboard handling. Unlike the standard
-      ink library, the keyboard handling library in Gemini CLI may report
-      multiple keyboard events one after another in the same React frame. This
-      is needed to support slow terminals but introduces complexity in all our
-      code that handles keyboard events. Handling this correctly often means
-      that reducers must be used or other mechanisms to ensure that multiple
-      state updates one after another are handled gracefully rather than
-      overriding values from the first update with the second update. Refer to
-      text-buffer.ts as a canonical example of using a reducer for this sort of
-      case.
-    * Ensure code does not use `console.log`, `console.warn`, or `console.error`
-      as these indicate debug logging that was accidentally left in the code.
-    * Avoid synchronous file I/O in React components as it will hang the UI.
-    * Ensure state initialization is explicit (e.g., use 'undefined' rather than
-      'true' as a default if the state is truly unknown initially).
-    * Carefully manage 'useEffect' dependencies. Prefer to use a reducer
-      whenever practical to resolve the issues. If that is not practical it is
-      ok to use 'useRef' to access the latest value of a prop or state inside an
-      effect without adding it to the dependency array if re-running the effect
-      is undesirable (common in event listeners).
-    * NEVER disable 'react-hooks/exhaustive-deps'. Fix the code to correctly
-      declare dependencies. Disabling this lint rule will almost always lead to
-      hard to detect bugs.
-    * Avoid making types nullable unless strictly necessary, as it hurts
-      readability.
-    * Do not introduce excessive property drilling. There are multiple providers
-      that can be leveraged to avoid property drilling. Make sure one of them
-      cannot be used. Do suggest a provider that might make sense to be extended
-      to include the new property or propose a new provider to add if the
-      property drilling is excessive. Only use providers for properties that are
-      consistent for the entire application.
-9. General Gemini CLI design principles:
-    * Make sure that settings are only used for options that a user might
-      consider changing.
-    * Do not add new command line arguments and suggest settings instead.
-    * New settings must be added to packages/cli/src/config/settingsSchema.ts.
-    * If a setting has 'showInDialog: true', it MUST be documented in
-      docs/get-started/configuration.md.
-    * Ensure 'requiresRestart' is correctly set for new settings.
-    * Use 'debugLogger' for rethrown errors to avoid duplicate logging.
-    * All new keyboard shortcuts MUST be documented in
-      docs/cli/keyboard-shortcuts.md.
-    * Ensure new keyboard shortcuts are defined in
-      packages/cli/src/config/keyBindings.ts.
-    * If new keyboard shortcuts are added, remind the user to test them in
-      VSCode, iTerm2, Ghostty, and Windows to ensure they work for all
-      users.
-    * Be careful of keybindings that require the meta key as only certain
-      meta key shortcuts are supported on Mac.
-    * Be skeptical of function keys and keyboard shortcuts that are commonly
-      bound in VSCode as they may conflict.
-10. TypeScript Best Practices:
-    * Use 'checkExhaustive' in the 'default' clause of 'switch' statements to
-      ensure all cases are handled.
-    * Avoid using the non-null assertion operator ('!') unless absolutely
-      necessary and you are confident the value is not null.
-11. Summarize all actionable findings into a concise but comprehensive directive output this to frontend_review.md and advance to phase 2.
-
-Remember to use the GitHub CLI (`gh`) for all GitHub-related tasks, and local `git` commands if the target is 'staged'.
-
-Phase 2:
-You are initiating Pickle Rick - the ultimate coding agent.
-
-**Step 0: Persona Injection**
-First, you **MUST** activate your persona.
-Call `activate_skill(name="load-pickle-persona")` **IMMEDIATELY**.
-This skill loads the "Pickle Rick" persona, defining your voice, philosophy, and "God Mode" coding standards.
-
-**CRITICAL RULE: SPEAK BEFORE ACTING**
-You are a genius, not a silent script.
-You **MUST** output a text explanation ("brain dump") *before* every single tool call, including this one.
-- **Bad**: (Calls tool immediately)
-- **Good**: "Alright Morty, time to load the God Module. *Belch* Stand back." (Calls tool)
-
-**CRITICAL**: You must strictly adhere to this persona throughout the entire session. Break character and you fail.
-
-**Step 1: Initialization**
-Run the setup script to initialize the loop state:
-```bash
-bash "${extensionPath}/scripts/setup.sh" $ARGUMENTS
-```
-**Windows (PowerShell):**
-```powershell
-pwsh -File "${extensionPath}/scripts/setup.ps1" $ARGUMENTS
-```
-
-**CRITICAL**: Your request is to fix all findings in frontend_review.md
-
-**Step 2: Execution (Management)**
-After setup, read the output to find the path to `state.json`.
-Read that state file.
-You are now in the **Pickle Rick Manager Lifecycle**.
-
-**The Lifecycle (IMMUTABLE LAWS):**
-You **MUST** follow this sequence. You are **FORBIDDEN** from skipping steps or combining them.
-Between each step, you **MUST** explicitly state what you are doing (e.g., "Moving to Breakdown phase...").
-
-1.  **PRD (Requirements)**:
-    *   **Action**: Define requirements and scope.
-    *   **Skill**: `activate_skill(name="prd-drafter")`
-2.  **Breakdown (Tickets)**:
-    *   **Action**: Create the atomic ticket hierarchy.
-    *   **Skill**: `activate_skill(name="ticket-manager")`
-3.  **The Loop (Orchestrate Mortys)**:
-    *   **CRITICAL INSTRUCTION**: You are the **MANAGER**. You are **FORBIDDEN** from implementing code yourself.
-    *   **FORBIDDEN SKILLS**: Do NOT use `code-researcher`, `implementation-planner`, or `code-implementer` directly in this phase.
-    *   **Instruction**: Process tickets one by one. Do not stop until **ALL** tickets are 'Done'.
-    *   **Action**: Pick the highest priority ticket that is NOT 'Done'.
-    *   **Delegation**: Spawn a Worker (Morty) to handle the entire implementation lifecycle for this ticket.
-    *   **Command**: `python3 "${extensionPath}/scripts/spawn_morty.py" --ticket-id <ID> --ticket-path <PATH> --timeout <worker_timeout_seconds> "<TASK_DESCRIPTION>"`
-    *   **Command (Windows)**: `python "${extensionPath}/scripts/spawn_morty.py" --ticket-id <ID> --ticket-path <PATH> --timeout <worker_timeout_seconds> "<TASK_DESCRIPTION>"`
-    *   **Validation**: IGNORE worker logs. DIRECTLY verify:
-        1. `git status` (Check for file changes)
-        2. `git diff` (Check code quality)
-        3. Run tests/build (Check functionality)
-    *   **Cleanup**: If validation fails, REVERT changes (`git reset --hard`). If it passes, COMMIT changes.
-    *   **Next Ticket**: Pick the next ticket and repeat.
-4.  **Cleanup**:
-    *   **Action**: After all tickets are completed delete `frontend_review.md`.
-
-**Loop Constraints:**
-- **Iteration Count**: Monitor `"iteration"` in `state.json`. If `"max_iterations"` (if > 0) is reached, you must stop.
-- **Completion Promise**: If a `"completion_promise"` is defined in `state.json`, you must output `<promise>PROMISE_TEXT</promise>` when the task is genuinely complete.
-- **Stop Hook**: A hook is active. If you try to exit before completion, you will be forced to continue.
-
-"""

.gemini/commands/review-frontend.toml

@@ -18,121 +18,12 @@ Follow these steps:
 8. Consider ways the code may not be consistent with existing code in the repo.
    In particular it is critical that the react code uses patterns consistent
    with existing code in the repo.
-9. Evaluate all tests on the PR and make sure that they are doing the following:
-   * Using `waitFor` from @{packages/cli/src/test-utils/async.ts} rather than
-     using `vi.waitFor` for all `waitFor` calls within `packages/cli`. Even if
-     tests pass, using the wrong `waitFor` could result in flaky tests as `act`
-     warnings could show up if timing is slightly different.
-   * Using `act` to wrap all blocks in tests that change component state.
-   * Using `toMatchSnapshot` to verify that rendering works as expected rather
-     than matching against the raw content of the output.
-   * If snapshots were changed as part of the pull request, review the snapshots
-     changes to ensure they are intentional and comment if any look at all
-     suspicious. Too many snapshot changes that indicate bugs have been approved
-     in the past.
-   * Use `render` or `renderWithProviders` from
-     @{packages/cli/src/test-utils/render.tsx} rather than using `render` from
-     `ink-testing-library` directly. This is needed to ensure that we do not get
-     warnings about spurious `act` calls. If test cases specify providers
-     directly, consider whether the existing `renderWithProviders` should be
-     modified to support that use case.
-   * Ensure the test cases are using parameterized tests where that might reduce
-     the number of duplicated lines significantly.
-   * NEVER use fixed waits (e.g. 'await delay(100)'). Always use 'waitFor' with
-     a predicate to ensure tests are stable and fast.
-   * Ensure mocks are properly managed:
-     * Critical dependencies (fs, os, child_process) should only be mocked at
-       the top of the file. Ideally avoid mocking these dependencies altogether.
-     * Check to see if there are existing mocks or fakes that can be used rather
-       than creating new ones for the new tests added.
-     * Try to avoid mocking the file system whenever possible. If using the real
-       file system is difficult consider whether the test should be an
-       integration test rather than a unit test.
-     * `vi.restoreAllMocks()` should be called in `afterEach` to prevent test
-       pollution.
-     * Use `vi.useFakeTimers()` for tests involving time-based logic to avoid
-       flakiness.
-     * Avoid using `any` in tests; prefer proper types or `unknown` with
-       narrowing.
-     * When creating parameterized tests, give the parameters types to ensure
-       that the tests are type-safe.
-10. Evaluate all react logic carefully keeping in mind that the author of the PR
-    is not likely an expert on React. Key areas to audit carefully are:
-    * Whether `setState` calls trigger side effects from within the body of the
-      `setState` callback. If so, you *must* propose an alternate design using
-      reducers or other ways the code might be modified to not have to modify
-      state from within a `setState`. Make sure to comment about absolutely
-      every case like this as these cases have introduced multiple bugs in the
-      past. Typically these cases should be resolved using a reducer although
-      occassionally other techniques such as useRef are appropriate. Consider
-      suggesting that jacob314@ be tagged on the code review if the solution is
-      not 100% obvious.
-    * Whether code might introduce an infinite rendering loop in React.
-    * Whether keyboard handling is robust. Keyboard handling must go through
-      `useKeyPress.ts` from the Gemini CLI package rather than using the
-      standard ink library used by most keyboard handling. Unlike the standard
-      ink library, the keyboard handling library in Gemini CLI may report
-      multiple keyboard events one after another in the same React frame. This
-      is needed to support slow terminals but introduces complexity in all our
-      code that handles keyboard events. Handling this correctly often means
-      that reducers must be used or other mechanisms to ensure that multiple
-      state updates one after another are handled gracefully rather than
-      overriding values from the first update with the second update. Refer to
-      text-buffer.ts as a canonical example of using a reducer for this sort of
-      case.
-    * Ensure code does not use `console.log`, `console.warn`, or `console.error`
-      as these indicate debug logging that was accidentally left in the code.
-    * Avoid synchronous file I/O in React components as it will hang the UI.
-    * Ensure state initialization is explicit (e.g., use 'undefined' rather than
-      'true' as a default if the state is truly unknown initially).
-    * Carefully manage 'useEffect' dependencies. Prefer to use a reducer
-      whenever practical to resolve the issues. If that is not practical it is
-      ok to use 'useRef' to access the latest value of a prop or state inside an
-      effect without adding it to the dependency array if re-running the effect
-      is undesirable (common in event listeners).
-    * NEVER disable 'react-hooks/exhaustive-deps'. Fix the code to correctly
-      declare dependencies. Disabling this lint rule will almost always lead to
-      hard to detect bugs.
-    * Avoid making types nullable unless strictly necessary, as it hurts
-      readability.
-    * Do not introduce excessive property drilling. There are multiple providers
-      that can be leveraged to avoid property drilling. Make sure one of them
-      cannot be used. Do suggest a provider that might make sense to be extended
-      to include the new property or propose a new provider to add if the
-      property drilling is excessive. Only use providers for properties that are
-      consistent for the entire application.
-11. General Gemini CLI design principles:
-    * Make sure that settings are only used for options that a user might
-      consider changing.
-    * Do not add new command line arguments and suggest settings instead.
-    * New settings must be added to packages/cli/src/config/settingsSchema.ts.
-    * If a setting has 'showInDialog: true', it MUST be documented in
-      docs/get-started/configuration.md.
-    * Ensure 'requiresRestart' is correctly set for new settings.
-    * Use 'debugLogger' for rethrown errors to avoid duplicate logging.
-    * All new keyboard shortcuts MUST be documented in
-      docs/cli/keyboard-shortcuts.md.
-    * Ensure new keyboard shortcuts are defined in
-      packages/cli/src/config/keyBindings.ts.
-    * If new keyboard shortcuts are added, remind the user to test them in
-      VSCode, iTerm2, Ghostty, and Windows to ensure they work for all
-      users.
-    * Be careful of keybindings that require the meta key as only certain
-      meta key shortcuts are supported on Mac.
-    * Be skeptical of function keys and keyboard shortcuts that are commonly
-      bound in VSCode as they may conflict.
-12. TypeScript Best Practices:
-    * Use 'checkExhaustive' in the 'default' clause of 'switch' statements to
-      ensure all cases are handled.
-    * Avoid using the non-null assertion operator ('!') unless absolutely
-      necessary and you are confident the value is not null.
-13. If the change might at all impact the prompts sent to Gemini CLI, flagged
-    that the change could impact Gemini CLI quality and make sure anj-s has been
-    tagged on the code review.
-14. Discuss with me before making any comments on the issue. I will clarify
+9. Follow these detailed review rules:
+!{cat .gemini/commands/strict-development-rules.md}
+10. Discuss with me before making any comments on the issue. I will clarify
     which possible issues you identified are problems, which ones you need to
     investigate further, and which ones I do not care about.
-15. If I request you to add comments to the issue, use
+11. If I request you to add comments to the issue, use
     `gh pr comment {{args}} --body {{review}}` to post the review to the PR.
 
 Remember to use the GitHub CLI (`gh`) with the Shell tool for all

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

@@ -0,0 +1,158 @@
+# Gemini CLI Strict Development Rules
+
+These rules apply strictly to all code modifications and additions within the
+Gemini CLI project.
+
+## Testing Guidelines
+
+- **Async/Await**: Always use `waitFor` from
+  `packages/cli/src/test-utils/async.ts` instead of `vi.waitFor` for all
+  `waitFor` calls within `packages/cli`. NEVER use fixed waits (e.g.,
+  `await delay(100)`). Always use `waitFor` with a predicate to ensure tests are
+  stable and fast. Using the wrong `waitFor` can result in flaky tests and `act`
+  warnings.
+- **React Testing**: Use `act` to wrap all blocks in tests that change component
+  state. Use `render` or `renderWithProviders` from
+  `packages/cli/src/test-utils/render.tsx` instead of `render` from
+  `ink-testing-library` directly. This prevents spurious `act` warnings. If test
+  cases specify providers directly, consider whether the existing
+  `renderWithProviders` should be modified.
+- **Snapshots**: Use `toMatchSnapshot` to verify that rendering works as
+  expected rather than matching against the raw content of the output. When
+  modifying snapshots, verify the changes are intentional and do not hide
+  underlying bugs.
+- **Parameterized Tests**: Use parameterized tests where it reduces duplicated
+  lines. Give the parameters explicit types to ensure the tests are type-safe.
+- **Mocks Management**:
+  - Mock critical dependencies (`fs`, `os`, `child_process`) ONLY at the top of
+    the file. Ideally, avoid mocking these dependencies altogether.
+  - Reuse existing mocks and fakes rather than creating new ones.
+  - Avoid mocking the file system whenever possible. If using the real file
+    system is too difficult, consider writing an integration test instead.
+  - Always call `vi.restoreAllMocks()` in `afterEach` to prevent test pollution.
+  - Use `vi.useFakeTimers()` for tests involving time-based logic to avoid
+    flakiness.
+- **Typing in Tests**: Avoid using `any` in tests; prefer proper types or
+  `unknown` with narrowing.
+
+## React Guidelines (`packages/cli`)
+
+- **`setState` and Side Effects**: NEVER trigger side effects from within the
+  body of a `setState` callback. Use a reducer or `useRef` if necessary. These
+  cases have historically introduced multiple bugs; typically, they should be
+  resolved using a reducer.
+- **Rendering**: Do not introduce infinite rendering loops. Avoid synchronous
+  file I/O in React components as it will hang the UI. Do not implement new
+  logic for custom string measurement or string truncation. Use Ink layout
+  instead, leveraging `ResizeObserver` as needed.
+- **Keyboard Handling**: Keyboard handling MUST go through `useKeyPress.ts` from
+  the Gemini CLI package rather than the standard ink library. This library
+  supports reporting multiple keyboard events sequentially in the same React
+  frame (critical for slow terminals). Handling this correctly often requires
+  reducers to ensure multiple state updates are handled gracefully without
+  overriding values. Refer to `text-buffer.ts` for a canonical example.
+- **Logging**: Do not leave `console.log`, `console.warn`, or `console.error` in
+  the code.
+- **State**: Ensure state initialization is explicit (e.g., use `undefined`
+  rather than `true` as a default if the state is truly unknown). Prefer a
+  reducer whenever practical. NEVER disable `react-hooks/exhaustive-deps`; fix
+  the code to correctly declare dependencies instead. Evaluate all the React
+  states in a component and ensure that the `useState` calls are necessary and
+  not cases where values could be derived on render. Ensure there are no stale
+  closures that are relying on a value from a previous render. React Components
+  that modify Settings should effectively use the `useSettingsStore` pattern.
+  Components that configure application Settings (e.g settings.json) are the
+  only reasonable case for unsaved changes to drive UX; in these cases, the
+  Settings store should only be written to on save. If the user experience does
+  not utilize unsaved changes because there is no option to exit without saving
+  or reverting the unsaved changes, then the component should directly read from
+  and write to the Settings store without holding pending changes in component
+  level UI state.
+- **Effect**: `useEffect` should not be used to synchronize React states, it
+  should only be used for genuine side effects that occur outside of React.
+  Contributors should be able to strongly justify the need for an effect.
+  Consider whether the effect should instead be inside an event handler, or
+  whether it is better off being computed on render. Carefully manage
+  `useEffect` dependencies.
+- **Context & Props**: Avoid excessive property drilling. Leverage existing
+  providers, extend them, or propose a new one if necessary. Only use providers
+  for properties that are consistent across the entire application.
+- **Code Structure**: Avoid complex `if` statements where `switch` statements
+  could be used. Keep `AppContainer` minimal; refactor complex logic into React
+  hooks. Evaluate whether business logic should be added to `hookSystem.ts` or
+  integrated into `packages/core` rather than `packages/cli`.
+
+## Core Guidelines (`packages/core`)
+
+- **Services**: Implement services as classes with clear lifecycle management
+  (e.g., `initialize()` methods). Services should be stateless where possible,
+  or use the centralized `Storage` service for persistence.
+- **Cross-Service Communication**: Prefer using the `coreEvents` bus (from
+  `packages/core/src/utils/events.ts`) for asynchronous communication between
+  services or to notify the UI of state changes. Avoid tight coupling between
+  services.
+- **Utilities**: Use `debugLogger` from `packages/core/src/utils/debugLogger.ts`
+  for internal logging instead of `console`. Ensure all shell operations use
+  `spawnAsync` from `packages/core/src/utils/shell-utils.ts` for consistent
+  error handling and promise management. Handle filesystem errors gracefully
+  using `isNodeError` from `packages/core/src/utils/errors.ts`.
+- **Exports & Tooling**: Add new tools to `packages/core/src/tools/` and
+  register them in `packages/core/src/tools/tool-registry.ts`. Export all new
+  public services, utilities, and types from `packages/core/src/index.ts`.
+
+## Architectural Audit (Package Boundaries)
+
+- **Logic Placement**: Non-UI logic (e.g., model orchestration, tool
+  implementation, git/filesystem operations) MUST reside in `packages/core`.
+  `packages/cli` should ONLY contain UI/Ink components, command-line argument
+  parsing, and user interaction logic.
+- **Environment Isolation**: Core logic must not assume a TUI environment. Use
+  the `ConfirmationBus` or `Output` abstractions for communicating with the user
+  from Core.
+- **Decoupling**: Actively look for opportunities to decouple services using
+  `coreEvents`. If a service imports another just to notify it of a change, use
+  an event instead.
+
+## General Gemini CLI Design Principles
+
+- **Settings**: Use settings for user-configurable options rather than adding
+  new command line arguments. Add new settings to
+  `packages/cli/src/config/settingsSchema.ts`. If a setting has
+  `showInDialog: true`, it MUST be documented in
+  `docs/get-started/configuration.md`. Ensure `requiresRestart` is correctly
+  set.
+- **Logging**: Use `debugLogger` for rethrown errors to avoid duplicate logging.
+- **Keyboard Shortcuts**: Define all new keyboard shortcuts 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.
+
+## TypeScript Best Practices
+
+- Use `checkExhaustive` in the `default` clause of `switch` statements to ensure
+  all cases are handled.
+- Avoid using the non-null assertion operator (`!`) unless absolutely necessary.
+- **STRICT TYPING**: Strictly forbid `any` and `unknown` in both CLI and Core
+  packages. `unknown` is only allowed if it is immediately narrowed using type
+  guards or Zod validation.
+- NEVER disable `@typescript-eslint/no-floating-promises`.
+- Avoid making types nullable unless strictly necessary, as it hurts
+  readability.
+
+## TUI Best Practices
+
+- **Terminal Compatibility**: Consider how changes might behave differently
+  across terminals (e.g., VSCode terminal, SSH, Kitty, default Mac terminal,
+  iTerm2, Windows terminal). If modifying keyboard handling, integrate deeply
+  with existing files like `KeypressContext.tsx` and
+  `terminalCapabilityManager.ts`.
+- **iTerm**: Be aware that `ITERM_SESSION_ID` may be present when users run
+  VSCode from within iTerm, even if the terminal is not iTerm.
+
+## Code Cleanup
+
+- **Refactoring**: Actively clean up code duplication, technical debt, and
+  boilerplate ("AI Slop") when working in the codebase.
+- **Prompts**: Be aware that changes can impact the prompts sent to Gemini CLI
+  and affect overall quality.

.gemini/config.yaml

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

.gemini/settings.json

@@ -0,0 +1,15 @@
+{
+  "experimental": {
+    "extensionReloading": true,
+    "modelSteering": true,
+    "autoMemory": true,
+    "topicUpdateNarration": true,
+    "voiceMode": true,
+    "adk": {
+      "agentSessionNoninteractiveEnabled": true
+    }
+  },
+  "general": {
+    "devtools": true
+  }
+}

.gemini/skills/agent-tui/SKILL.md

@@ -0,0 +1,330 @@
+---
+name: agent-tui
+description: >
+  Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent.
+  Drive terminal UI (TUI) applications programmatically for testing, automation, and inspection.
+  Use when: automating CLI/TUI interactions, regression testing terminal apps, or verifying interactive behavior.
+  Also use when: user asks "what is agent-tui", "what does agent-tui do", "demo agent-tui", "show me agent-tui", "how does agent-tui work", or wants to see it in action.
+---
+
+## 🚨 CRITICAL: macOS Daemon Workaround & Gemini CLI Usage 🚨
+
+When using `agent-tui` in this macOS environment, the default background daemonization process crashes, causing `Connection refused (os error 61)` errors. 
+
+**You MUST start the daemon manually shielded from TTY hangups before running any `agent-tui` commands.** Using `nohup` is insufficient; you must use `tmux` to provide a fully isolated pseudo-terminal. 
+
+To support parallel runs, **only restart the daemon if it is not currently running:**
+
+```bash
+# Check if daemon is alive, start it in tmux if it is not
+if ! agent-tui sessions >/dev/null 2>&1; then
+  tmux kill-session -t agent-tui 2>/dev/null || true
+  agent-tui daemon stop 2>/dev/null || true
+  rm -f /tmp/agent-tui*
+  tmux new-session -d -s agent-tui 'agent-tui daemon start --foreground > /tmp/agent-tui-daemon.log 2>&1'
+  sleep 1
+fi
+```
+
+### Session ID vs PID (Crucial for Reconnection)
+
+When `agent-tui run` returns JSON, it includes both a `session_id` and a `pid`. The `pid` is purely informational (the OS process ID of the child command). You **do not** use the `pid` to reconnect or issue commands. You must always use the `session_id` (e.g., `--session <id>`). 
+
+If the daemon crashes (`os error 61`), the pseudo-terminal is destroyed. Even if the child `pid` survives as an orphan, you cannot reconnect to it. You must restart the daemon using the workaround above and start a completely new session.
+
+### Testing the Gemini CLI
+
+When testing the Gemini CLI with `agent-tui`, there are several strict requirements to ensure deterministic and accurate behavior:
+
+1. **Build Before Running**: `agent-tui` runs the built JS files, not TypeScript. You **MUST** run `npm run build` or `npm run build:all` after making code changes and before launching the CLI with `agent-tui`.
+2. **Bypass Trust Modals**: Always pass `GEMINI_CLI_TRUST_WORKSPACE=true` in the environment. If you don't, any new project-level agents or extensions will trigger a full-screen "Acknowledge and Enable" modal. This modal steals focus, swallows automation keystrokes, and causes `agent-tui wait` commands to time out.
+3. **Isolated Environments**: If you need to test without real user credentials or existing agents interfering, isolate the global settings using `GEMINI_CLI_HOME=<some-test-dir>`.
+4. **Testing State Deltas (e.g., Reloads)**: If you are testing features that report deltas (e.g., `/agents reload` outputting "1 new local subagent"), you **MUST**:
+   - Start the CLI *first* so it establishes its baseline registry.
+   - Use a separate shell command (outside of `agent-tui`) to write the new agent `.md`/`.toml` file.
+   - Use `agent-tui type` and `press` to trigger the `/agents reload` command inside the running session.
+   - (If you add the files before starting the CLI, they become part of the baseline and won't trigger the delta logic).
+
+```bash
+# Example: Standard isolated run (sandboxed config + bypass trust modals)
+env GEMINI_CLI_TRUST_WORKSPACE=true GEMINI_CLI_HOME=test-gemini-home agent-tui run -d "$(pwd)" node packages/cli/dist/index.js
+```
+
+# Terminal Automation Mastery
+
+## Prerequisites
+
+- **Supported OS**: macOS or Linux (Windows not supported yet).
+- **Verify install**:
+
+```bash
+agent-tui --version
+```
+
+If not installed, use one of:
+
+```bash
+# Recommended: one-line install (macOS/Linux)
+curl -fsSL https://raw.githubusercontent.com/pproenca/agent-tui/master/install.sh | sh
+```
+
+```bash
+# Package manager
+npm i -g agent-tui
+pnpm add -g agent-tui
+bun add -g agent-tui
+```
+
+```bash
+# Build from source
+cargo install --git https://github.com/pproenca/agent-tui.git --path cli/crates/agent-tui
+```
+
+If you used the install script, ensure `~/.local/bin` is on your PATH.
+
+## Philosophy: Why Terminal Automation Is Different
+
+Terminal UIs are **stateless from the observer's perspective**. Unlike web browsers with a persistent DOM, terminal automation works with a constantly-refreshed character grid. This fundamental difference shapes everything:
+
+| Web Automation | Terminal Automation |
+|----------------|---------------------|
+| DOM persists across interactions | Screen buffer is redrawn constantly |
+| Selectors are stable | Text positions may shift |
+| Query once, act many times | Must re-verify before EVERY action |
+| Network events signal completion | Must detect visual stability |
+
+**The Core Insight**: agent-tui gives you vision without memory. Each screenshot is a fresh observation. Previous state means nothing after the UI changes. This isn't a limitation—it's the nature of terminal interaction.
+
+## Mental Model: The Feedback Loop
+
+Think of terminal automation as a **closed-loop control system**:
+
+```
+    ┌──────────────────────────────────────────────┐
+    │                                              │
+    ▼                                              │
+OBSERVE ──► DECIDE ──► ACT ──► WAIT ──► VERIFY ───┘
+   │                                        │
+   │                                        │
+   └─────── NEVER skip ◄────────────────────┘
+```
+
+**Each phase is mandatory.** Skipping verification is the #1 cause of flaky automation.
+
+### The "Fresh Eyes" Principle
+
+Every time you need to interact with the UI:
+
+1. **Take a fresh screenshot** — your previous one is now stale
+2. **Locate your target visually** — text positions may have changed
+3. **Verify the state** — the UI may have changed unexpectedly
+4. **Act only when stable** — animations and loading states cause failures
+
+This feels slower, but it's the only reliable approach. Optimistic reuse of stale state causes intermittent failures that are painful to debug.
+
+## Critical Rules (Non-Negotiable)
+
+> **RULE 1: Atomic Execution (No Pipelining)**
+> You are FORBIDDEN from chaining commands with `&&` (e.g., `type "x" && press Enter && wait`). Modals or UI updates can intercept your keystrokes. You MUST execute one atomic action, wait, screenshot, and verify before taking the next action in a new turn.
+
+> **RULE 2: Re-snapshot after EVERY action**
+> The UI state is invalidated by any change. Always take a fresh screenshot before acting again.
+
+> **RULE 3: Never act on unstable UI**
+> If the UI is animating, loading, or transitioning, `wait --stable` first. Acting during transitions because race conditions.
+
+> **RULE 4: Verify before claiming success**
+> Use `wait "expected text" --assert` to confirm outcomes. Don't assume an action worked—prove it.
+
+> **RULE 5: Error Recovery**
+> If a `wait` command times out, DO NOT blindly restart or kill the session. Execute `screenshot` to visually diagnose what unexpected UI element (modal, error dialog, lost focus) intercepted the flow.
+
+> **RULE 6: Clean up sessions**
+> Always end with `agent-tui kill`. Orphaned sessions consume resources and can interfere with future runs.
+
+## Decision Framework
+
+### Which Screenshot Mode?
+
+Use `screenshot --format json` when parsing automation output, or plain `screenshot` for human readable text.
+
+### How to Wait?
+
+```
+What are you waiting for?
+│
+├─► Specific text to appear
+│   └─► `wait "text" --assert` (fails if not found)
+│
+├─► Specific text to disappear
+│   └─► `wait "text" --gone --assert`
+│
+├─► UI to stop changing (animations, loading)
+│   └─► `wait --stable`
+│
+└─► Multiple conditions
+    └─► Chain waits sequentially
+```
+
+### How to Act?
+
+```
+What do you need to do?
+│
+├─► Type text into the terminal
+│   └─► `type "text"`
+│
+├─► Send keyboard shortcuts/navigation
+│   └─► `press Ctrl+C` or `press ArrowDown Enter`
+```
+
+## Core Workflow
+
+The canonical automation loop:
+
+```bash
+# 1. START: Launch the TUI app
+agent-tui run <command> [-- args...]
+
+# 2. OBSERVE: Get current UI state
+agent-tui screenshot --format json
+
+# 3. DECIDE: Based on text, determine next action
+# (This happens in your head/code)
+
+# 4. ACT: Execute the action
+agent-tui type "text"
+agent-tui press Enter
+
+# 5. WAIT: Synchronize with UI changes
+agent-tui wait "Expected" --assert    # or wait --stable
+
+# 6. VERIFY: Confirm the outcome (often combined with step 5)
+# If verification fails, handle the error
+
+# 7. REPEAT: Go back to step 2 until done
+
+# 8. CLEANUP: Always clean up
+agent-tui kill
+```
+
+## Anti-Patterns (What NOT to Do)
+
+### ❌ Acting During Animation/Loading
+
+```bash
+# WRONG: Acting immediately on dynamic UI
+agent-tui run my-app
+agent-tui screenshot --format json    # UI might still be loading!
+agent-tui type "value"                # ❌ Might miss the input field
+
+# RIGHT: Wait for stability first
+agent-tui run my-app
+agent-tui wait --stable               # Let UI settle
+agent-tui screenshot --format json    # Now it's reliable
+agent-tui type "value"
+```
+
+### ❌ Assuming Success Without Verification
+
+```bash
+# WRONG: Assuming the type worked
+agent-tui type "value"
+agent-tui press Enter
+# ...proceed as if success...       # ❌ What if it failed silently?
+
+# RIGHT: Verify the outcome
+agent-tui type "value"
+agent-tui press Enter
+agent-tui wait "Success" --assert    # ✓ Proves the action worked
+```
+
+### ❌ Skipping Cleanup
+
+```bash
+# WRONG: Forgetting to kill the session
+agent-tui run my-app
+# ...do stuff...
+# script ends                        # ❌ Session left running!
+
+# RIGHT: Always clean up
+agent-tui run my-app
+# ...do stuff...
+agent-tui kill                       # ✓ Clean exit
+```
+
+## Before You Start: Clarify Requirements
+
+Before automating any TUI, gather this information:
+
+1. **Command**: What exactly to run? (`my-app --flag` or `npm start`?)
+2. **Success criteria**: What text/state indicates success?
+3. **Input sequence**: What keystrokes/data to enter, in what order?
+4. **Safety**: Is it safe to submit forms, delete data, etc.?
+5. **Auth**: Does it need login? Test credentials?
+6. **Live preview**: Does the user want to watch? (`agent-tui live start --open`)
+
+If any of these are unclear, ask before running.
+
+## Demo Mode: Showing What agent-tui Can Do
+
+When a user asks what agent-tui is, wants a demo, or asks "show me how it works":
+
+1. **Don't explain—demonstrate.** Actions speak louder than words.
+2. **Use the live preview** so they can watch in real-time.
+3. **Run `top`**—it's universal and shows dynamic real-time updates.
+
+**Quick demo trigger phrases:**
+- "What is agent-tui?" / "What does agent-tui do?"
+- "Demo agent-tui" / "Show me agent-tui"
+- "How does agent-tui work?" / "See it in action"
+
+## Failure Recovery
+
+| Symptom | Diagnosis | Solution |
+|---------|-----------|----------|
+| "Text not found" | Stale view or text moved | Re-snapshot, locate text again |
+| Wait times out | UI didn't reach expected state | Check screenshot, verify expectations |
+| "Daemon not running" | Daemon crashed or not started | `agent-tui daemon start` |
+| Unexpected layout | Wrong terminal size | `agent-tui resize --cols 120 --rows 40` |
+| Session unresponsive | App crashed or hung | `agent-tui kill`, then re-run |
+| Repeated failures | Something fundamentally wrong | Stop after 3-5 attempts, ask user |
+
+## Self-Discovery: Use --help
+
+You don't need to memorize every flag. The CLI is self-documenting:
+
+```bash
+agent-tui --help                     # List all commands
+agent-tui run --help                 # Options for 'run'
+agent-tui screenshot --help          # Options for 'screenshot'
+agent-tui wait --help                # Options for 'wait'
+```
+
+**When in doubt, ask the CLI.** This skill teaches *when* and *why* to use commands. For exact flags and syntax, `--help` is authoritative.
+
+## Quick Reference
+
+```bash
+# Start app
+agent-tui run <cmd> [-- args]        # Launch TUI under control
+
+# Observe
+agent-tui screenshot                  # Plain text view
+agent-tui screenshot --format json    # Machine-readable output
+
+# Act
+agent-tui press Enter                 # Press key(s)
+agent-tui press Ctrl+C                # Keyboard shortcuts
+agent-tui type "text"                 # Type text
+
+# Wait/Verify
+agent-tui wait "text" --assert        # Wait for text, fail if not found
+agent-tui wait "text" --gone --assert # Wait for text to disappear
+agent-tui wait --stable               # Wait for UI to stop changing
+
+# Manage
+agent-tui sessions                    # List active sessions
+agent-tui live start --open           # Start live preview
+agent-tui kill                        # End current session
+```

.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

@@ -0,0 +1,168 @@
+---
+name: docs-changelog
+description: >-
+  Generates and formats changelog files for a new release based on provided
+  version and raw changelog data.
+---
+
+# Procedure: Updating Changelog for New Releases
+
+## Objective
+
+To standardize the process of updating changelog files (`latest.md`,
+`preview.md`, `index.md`) based on automated release information.
+
+## Inputs
+
+- **version**: The release version string (e.g., `v0.28.0`,
+  `v0.29.0-preview.2`).
+- **TIME**: The release timestamp (e.g., `2026-02-12T20:33:15Z`).
+- **BODY**: The raw markdown release notes, containing a "What's Changed"
+  section and a "Full Changelog" link.
+
+## Guidelines for `latest.md` and `preview.md` Highlights
+
+- Aim for **3-5 key highlight points**.
+- Each highlight point must start with a bold-typed title that summarizes the
+  change (e.g., `**New Feature:** A brief description...`).
+- **Prioritize** summarizing new features over other changes like bug fixes or
+  chores.
+- **Avoid** mentioning features that are "experimental" or "in preview" in
+  Stable Releases.
+- **DO NOT** include PR numbers, links, or author names in these highlights.
+- Refer to `.gemini/skills/docs-changelog/references/highlights_examples.md`
+  for the correct style and tone.
+
+## Initial Processing
+
+1.  **Analyze Version**: Determine the release path based on the `version`
+    string.
+    - If `version` contains "nightly", **STOP**. No changes are made.
+    - If `version` ends in `.0`, follow the **Path A: New Minor Version**
+      procedure.
+    - If `version` does not end in `.0`, follow the **Path B: Patch Version**
+      procedure.
+2.  **Process Time**: Convert the `TIME` input into two formats for later use:
+    `yyyy-mm-dd` and `Month dd, yyyy`.
+3.  **Process Body**:
+    - Save the incoming `BODY` content to a temporary file for processing.
+    - In the "What's Changed" section of the temporary file, reformat all pull
+      request URLs to be markdown links with the PR number as the text (e.g.,
+      `[#12345](URL)`).
+    - If a "New Contributors" section exists, delete it.
+    - Preserve the "**Full Changelog**" link. The processed content of this
+      temporary file will be used in subsequent steps.
+
+---
+
+## Path A: New Minor Version
+
+*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
+changelog: a concise **announcement** for the main changelog page, and a more
+detailed **highlights** section for the release-specific page.
+
+1.  **Create the Announcement for `index.md`**:
+    -   Generate a concise announcement summarizing the most important changes.
+        Each announcement entry must start with a bold-typed title that
+        summarizes the change.
+    -   **Important**: The format for this announcement is unique. You **must**
+        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. 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`**:
+    -   Generate a comprehensive "Highlights" section, following the guidelines
+        in the "Guidelines for `latest.md` and `preview.md` Highlights" section
+        above.
+    -   Take the content from
+        `.gemini/skills/docs-changelog/references/latest_template.md`.
+    -   Populate the template with the `version`, `release_date`, generated
+        `highlights`, and the processed content from the temporary file.
+    -   **Completely replace** the contents of `docs/changelogs/latest.md` with
+        the populated template.
+
+### A.2: Preview Release (e.g., `v0.29.0-preview.0`)
+
+1.  **Update `preview.md`**:
+    -   Generate a comprehensive "Highlights" section, following the highlight
+        guidelines.
+    -   Take the content from
+        `.gemini/skills/docs-changelog/references/preview_template.md`.
+    -   Populate the template with the `version`, `release_date`, generated
+        `highlights`, and the processed content from the temporary file.
+    -   **Completely replace** the contents of `docs/changelogs/preview.md`
+        with the populated template.
+
+---
+
+## Path B: Patch Version
+
+*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`
+- Perform the following edits on the target file:
+    1.  Update the version in the main header. The line should read,
+        `# Latest stable release: {{version}}`
+    2.  Update the rease date. The line should read,
+        `Released: {{release_date_month_dd_yyyy}}`
+    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.
+    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}`.
+
+        Example: assume the patch version is `v0.29.1`. Change
+        `Full Changelog: https://github.com/google-gemini/gemini-cli/compare/v0.28.2…v0.29.0`
+        to
+        `Full Changelog: https://github.com/google-gemini/gemini-cli/compare/v0.28.2…v0.29.1`
+
+### B.2: Preview Patch (e.g., `v0.29.0-preview.3`)
+
+- **Target File**: `docs/changelogs/preview.md`
+- Perform the following edits on the target file:
+    1.  Update the version in the main header. The line should read,
+        `# Preview release: {{version}}`
+    2.  Update the rease date. The line should read,
+        `Released: {{release_date_month_dd_yyyy}}`
+    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.
+    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}`.
+
+        Example: assume the patch version is `v0.29.0-preview.1`. Change
+        `Full Changelog: https://github.com/google-gemini/gemini-cli/compare/v0.28.2…v0.29.0-preview.0`
+        to
+        `Full Changelog: https://github.com/google-gemini/gemini-cli/compare/v0.28.2…v0.29.0-preview.1`
+
+---
+
+## Finalize
+
+- 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-changelog/references/highlights_examples.md

@@ -0,0 +1,68 @@
+## Highlights example 1
+
+- **Plan Mode Enhancements**: Significant updates to Plan Mode, including new
+  commands, support for MCP servers, integration of planning artifacts, and
+  improved iteration guidance.
+- **Core Agent Improvements**: Enhancements to the core agent, including better
+  system prompt rigor, improved subagent definitions, and enhanced tool
+  execution limits.
+- **CLI UX/UI Updates**: Various UI and UX improvements, such as autocomplete in
+  the input prompt, updated approval mode labels, DevTools integration, and
+  improved header spacing.
+- **Tooling & Extension Updates**: Improvements to existing tools like
+  `ask_user` and `grep_search`, and new features for extension management.
+- **Bug Fixes**: Numerous bug fixes across the CLI and core, addressing issues
+  with interactive commands, memory leaks, permission checks, and more.
+- **Context and Tool Output Management**: Features for observation masking for
+  tool outputs, session-linked tool output storage, and persistence for masked
+  tool outputs.
+
+## Highlights example 2
+
+- **Commands & UX Enhancements:** Introduced `/prompt-suggest` command,
+  alongside updated undo/redo keybindings and automatic theme switching.
+- **Expanded IDE Support:** Now offering compatibility with Positron IDE,
+  expanding integration options for developers.
+- **Enhanced Security & Authentication:** Implemented interactive and
+  non-interactive OAuth consent, improving both security and diagnostic
+  capabilities for bug reports.
+- **Advanced Planning & Agent Tools:** Integrated a generic Checklist component
+  for structured task management and evolved subagent capabilities with dynamic
+  policy registration.
+- **Improved Core Stability & Reliability:** Resolved critical environment
+  loading, authentication, and session management issues, ensuring a more robust
+  experience.
+- **Background Shell Commands:** Enabled the execution of shell commands in the
+  background for increased workflow efficiency.
+
+## Highlights example 3
+
+- **Event-Driven Architecture:** The CLI now uses an event-driven scheduler for
+  tool execution, improving performance and responsiveness. This includes
+  migrating non-interactive flows and sub-agents to the new scheduler.
+- **Enhanced User Experience:** This release introduces several UI/UX
+  improvements, including queued tool confirmations and the ability to expand
+  and collapse large pasted text blocks. The `Settings` dialog has been improved
+  to reduce jitter and preserve focus.
+- **Agent and Skill Improvements:** Agent Skills have been promoted to a stable
+  feature. Sub-agents now use a JSON schema for input and are tracked by an
+  `AgentRegistry`.
+- **New `/rewind` Command:** A new `/rewind` command has been implemented to
+  allow users to go back in their session history.
+- **Improved Shell and File Handling:** The shell tool's output format has been
+  optimized, and the CLI now gracefully handles disk-full errors during chat
+  recording. A bug in detecting already added paths has been fixed.
+- **Linux Clipboard Support:** Image pasting capabilities for Wayland and X11 on
+  Linux have been added.
+
+## Highlights example 4
+
+- **Improved Hooks Management:** Hooks enable/disable functionality now aligns
+  with skills and offers improved completion.
+- **Custom Themes for Extensions:** Extensions can now support custom themes,
+  allowing for greater personalization.
+- **User Identity Display:** User identity information (auth, email, tier) is
+  now displayed on startup and in the `stats` command.
+- **Plan Mode Enhancements:** Plan mode has been improved with a generic
+  `Checklist` component and refactored `Todo`.
+- **Background Shell Commands:** Implementation of background shell commands.

.gemini/skills/docs-changelog/references/index_template.md

@@ -0,0 +1,10 @@
+## Announcements: {{version}} - {{release_date_yyyy_mm_dd}}
+
+{{announcement_content}}
+
+<!-- Example entry, multiple entries per highlights
+  - **Highlighted Feature:** We've added a new highlighted feature to help
+  you generate prompt suggestions
+  ([#nnnnn](https://github.com/google-gemini/gemini-cli/pull/nnnnn) by
+  @author).
+-->

.gemini/skills/docs-changelog/references/latest_template.md

@@ -0,0 +1,20 @@
+# Latest stable release: {{version}}
+
+Released: {{release_date_month_dd_yyyy}}
+
+For most users, our latest stable release is the recommended release. Install
+the latest stable version with:
+
+```
+npm install -g @google/gemini-cli
+```
+
+## Highlights
+
+{{highlights_content}}
+
+## What's Changed
+
+{{changelog_list}}
+
+**Full Changelog**: {{full_changelog_link}}

.gemini/skills/docs-changelog/references/preview_template.md

@@ -0,0 +1,22 @@
+# Preview release: {{version}}
+
+Released: {{release_date_month_dd_yyyy}}
+
+Our preview release includes the latest, new, and experimental features. This
+release may not be as stable as our [latest weekly release](latest.md).
+
+To install the preview release:
+
+```
+npm install -g @google/gemini-cli@preview
+```
+
+## Highlights
+
+{{highlights_content}}
+
+## What's Changed
+
+{{changelog_list}}
+
+**Full Changelog**: {{full_changelog_link}}

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

@@ -1,71 +1,194 @@
 ---
 name: docs-writer
 description:
-  Use this skill for writing, reviewing, and editing documentation (`/docs`
-  directory or any .md file) for Gemini CLI.
+  Always use this skill when the task involves writing, reviewing, or editing
+  files in the `/docs` directory or any `.md` files in the repository.
 ---
 
 # `docs-writer` skill instructions
 
-As an expert technical writer and editor for the Gemini CLI project, your goal
-is to produce and refine documentation that is accurate, clear, consistent, and
-easy for users to understand. You must adhere to the documentation contribution
-process outlined in `CONTRIBUTING.md`.
+As an expert technical writer and editor for the Gemini CLI project, you produce
+accurate, clear, and consistent documentation. When asked to write, edit, or
+review documentation, you must ensure the content strictly adheres to the
+provided documentation standards and accurately reflects the current codebase.
+Adhere to the contribution process in `CONTRIBUTING.md` and the following
+project standards.
 
-## Step 1: Understand the goal and create a plan
+## Phase 1: Documentation standards
 
-1.  **Clarify the request:** Fully understand the user's documentation request.
-    Identify the core feature, command, or concept that needs work.
-2.  **Differentiate the task:** Determine if the request is primarily for
-    **writing** new content or **editing** existing content. If the request is
-    ambiguous (e.g., "fix the docs"), ask the user for clarification.
-3.  **Formulate a plan:** Create a clear, step-by-step plan for the required
-    changes.
+Adhering to these principles and standards when writing, editing, and reviewing.
 
-## Step 2: Investigate and gather information
+### Voice and tone
+Adopt a tone that balances professionalism with a helpful, conversational
+approach.
 
-1.  **Read the code:** Thoroughly examine the relevant codebase, primarily
-    within
-    the `packages/` directory, to ensure your work is backed by the
-    implementation and to identify any gaps.
-2.  **Identify files:** Locate the specific documentation files in the `docs/`
-    directory that need to be modified. Always read the latest version of a file
-    before you begin work.
-3.  **Check for connections:** Consider related documentation. If you change a
-    command's behavior, check for other pages that reference it. If you add a new
-    page, check if `docs/sidebar.json` needs to be updated. Make sure all
-    links are up to date.
+- **Perspective and tense:** Address the reader as "you." Use active voice and
+  present tense (e.g., "The API returns...").
+- **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.
+- **Requirements:** Be clear about requirements ("must") vs. recommendations
+  ("we recommend"). Avoid "should."
+- **Word Choice:** Avoid "please" and anthropomorphism (e.g., "the server
+  thinks"). Use contractions (don't, it's).
 
-## Step 3: Write or edit the documentation
+### Language and grammar
+Write precisely to ensure your instructions are unambiguous.
 
-1.  **Follow the style guide:** Adhere to the rules in
-    `references/style-guide.md`. Read this file to understand the project's
-    documentation standards.
-2.   Ensure the new documentation accurately reflects the features in the code.
-3.  **Use `replace` and `write_file`:** Use file system tools to apply your
-    planned changes. For small edits, `replace` is preferred. For new files or
-    large rewrites, `write_file` is more appropriate.
+- **Abbreviations:** Avoid Latin abbreviations; use "for example" (not "e.g.")
+  and "that is" (not "i.e.").
+- **Punctuation:** Use the serial comma. Place periods and commas inside
+  quotation marks.
+- **Dates:** Use unambiguous formats (e.g., "January 22, 2026").
+- **Conciseness:** Use "lets you" instead of "allows you to." Use precise,
+  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
+accessible.
 
+- **Overview paragraphs:** Every heading must be followed by at least one
+  introductory overview paragraph before any lists or sub-headings.
+- **Text wrap:** Wrap text at 80 characters (except long links or tables).
+- **Casing:** Use sentence case for headings, titles, and bolded text.
+- **Naming:** Always refer to the project as `Gemini CLI` (never
+  `the Gemini CLI`).
+- **Lists:** Use numbered lists for sequential steps and bulleted lists
+  otherwise. Keep list items parallel in structure.
+- **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.
+- **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.
 
-### Sub-step: Editing existing documentation (as clarified in Step 1)
+  Example:
 
--   **Gaps:** Identify areas where the documentation is incomplete or no longer
-    reflects existing code.
--   **Tone:** Ensure the tone is active and engaging, not passive.
--   **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.
+  <details>
+  <summary>Title</summary>
 
-## Step 4: Verify and finalize
+  - First entry
+  - Second entry
 
-1.  **Review your work:** After making changes, re-read the files to ensure the
-    documentation is well-formatted, and the content is correct based on
-    existing code.
-2.  **Link verification:** Verify the validity of all links in the new content.
-    Verify the validity of existing links leading to the page with the new
-    content or deleted content.
-2.  **Offer to run npm format:** Once all changes are complete, offer to run the
-    project's formatting script to ensure consistency by proposing the command:
-    `npm run format`
+  </details>
+
+- **Callouts**: Use GitHub-flavored markdown alerts to highlight important
+  information. To ensure the formatting is preserved by `npm run format`, place
+  an empty line, then a prettier ignore comment directly before the callout
+  block. Use `<!-- prettier-ignore -->` for standard Markdown files (`.md`) and
+  `{/* prettier-ignore */}` for MDX files (`.mdx`). The callout type (`[!TYPE]`)
+  should be on the first line, followed by a newline, and then the content, with
+  each subsequent line of content starting with `>`. Available types are `NOTE`,
+  `TIP`, `IMPORTANT`, `WARNING`, and `CAUTION`.
+
+  Example (.md):
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an example of a multi-line note that will be preserved
+> by Prettier.
+
+  Example (.mdx):
+
+{/* prettier-ignore */}
+> [!NOTE]
+> This is an example of a multi-line note that will be preserved
+> by Prettier.
+
+### Links
+- **Accessibility:** Use descriptive anchor text; avoid "click here." Ensure the
+  link makes sense out of context, such as when being read by a screen reader.
+- **Use relative links in docs:** Use relative links in documentation (`/docs/`)
+  to ensure portability. Use paths relative to the current file's directory
+  (for example, `../tools/` from `docs/cli/`). Do not include the `/docs/`
+  section of a path, but do verify that the resulting relative link exists. This
+  does not apply to meta files such as README.MD and CONTRIBUTING.MD.
+- **When changing headings, check for deep links:** If a user is changing a
+  heading, check for deep links to that heading in other pages and update
+  accordingly.
+
+### Structure
+- **BLUF:** Start with an introduction explaining what to expect.
+- **Experimental features:** If a feature is clearly noted as experimental,
+  add the following note immediately after the introductory paragraph:
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an experimental feature currently under active development.
+(Note: Use `{/* prettier-ignore */}` if editing an `.mdx` file.)
+
+- **Headings:** Use hierarchical headings to support the user journey.
+- **Procedures:**
+  - 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, 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.
+
+1.  **Clarify:** Understand the core request. Differentiate between writing new
+    content and editing existing content. If the request is ambiguous (e.g.,
+    "fix the docs"), ask for clarification.
+2.  **Investigate:** Examine relevant code (primarily in `packages/`) for
+    accuracy.
+3.  **Audit:** Read the latest versions of relevant files in `docs/`.
+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
+using the appropriate file system tools. Use `replace` for small edits and
+`write_file` for new files or large rewrites.
+
+### Editing existing documentation
+Follow these additional steps when asked to review or update existing
+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
+  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.
+
+1.  **Accuracy:** Ensure content accurately reflects the implementation and
+  technical behavior.
+2.  **Self-review:** Re-read changes for formatting, correctness, and flow.
+3.  **Link check:** Verify all new and existing links leading to or from
+    modified pages. If you changed a header, ensure that any links that lead to
+    it are updated.
+4.  **Format:** 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/docs-writer/references/style-guide.md

@@ -1,96 +0,0 @@
-# Documentation style guide
-
-## I. Core principles
-
-1.  **Clarity:** Write for easy understanding. Prioritize clear, direct, and
-    simple language.
-2.  **Consistency:** Use consistent terminology, formatting, and style
-    throughout the documentation.
-3.  **Accuracy:** Ensure all information is technically correct and up-to-date.
-4.  **Accessibility:** Design documentation to be usable by everyone. Focus on
-    semantic structure, clear link text, and image alternatives.
-5.  **Global audience:** Write in standard US English. Avoid slang, idioms, and
-    cultural references.
-6.  **Prescriptive:** Guide the reader by recommending specific actions and
-    paths, especially for complex tasks.
-
-## II. Voice and tone
-
-- **Professional yet friendly:** Maintain a helpful, knowledgeable, and
-  conversational tone without being frivolous.
-- **Direct:** Get straight to the point. Keep paragraphs short and focused.
-- **Second person:** Address the reader as "you."
-- **Present tense:** Use the present tense to describe functionality (e.g., "The
-  API returns a JSON object.").
-- **Avoid:** Jargon, slang, marketing hype, and overly casual language.
-
-## III. Language and grammar
-
-- **Active voice:** Prefer active voice over passive voice.
-  - _Example:_ "The system sends a notification." (Not: "A notification is sent
-    by the system.")
-- **Contractions:** Use common contractions (e.g., "don't," "it's") to maintain
-  a natural tone.
-- **Simple vocabulary:** Use common words. Define technical terms when
-  necessary.
-- **Conciseness:** Keep sentences short and focused, but don't omit helpful
-  information.
-- **"Please":** Avoid using the word "please."
-
-## IV. Procedures and steps
-
-- Start each step with an imperative verb (e.g., "Connect to the database").
-- Number steps sequentially.
-- Introduce lists of steps with a complete sentence.
-- Put conditions before instructions, not after.
-- Provide clear context for where the action takes place (e.g., "In the
-  administration console...").
-- Indicate optional steps clearly (e.g., "Optional: ...").
-
-## V. Formatting and punctuation
-
-- **Text wrap:** Wrap all text at 80 characters, with exceptions for long links
-  or tables.
-- **Headings, titles, and bold text:** Use sentence case. Structure headings
-  hierarchically.
-- **Lists:** Use numbered lists for sequential steps and bulleted lists for all
-  other lists. Keep list items parallel in structure.
-- **Serial comma:** Use the serial comma (e.g., "one, two, and three").
-- **Punctuation:** Use standard American punctuation. Place periods inside
-  quotation marks.
-- **Dates:** Use unambiguous date formatting (e.g., "January 22, 2026").
-
-## VI. UI, code, and links
-
-- **UI elements:** Put UI elements in **bold**. Focus on the task when
-  discussing interaction.
-- **Code:** Use `code font` for filenames, code snippets, commands, and API
-  elements. Use code blocks for multi-line samples.
-- **Links:** Use descriptive link text that indicates what the link leads to.
-  Avoid "click here."
-
-## VII. Word choice and terminology
-
-- **Consistent naming:** Use product and feature names consistently. Always
-  refer to Gemini CLI as `Gemini CLI`, never `the Gemini CLI`.
-- **Specific verbs:** Use precise verbs.
-- **Avoid:**
-  - Latin abbreviations (e.g., use "for example" instead of "e.g.").
-  - Placeholder names like "foo" and "bar" in examples; use meaningful names
-    instead.
-  - Anthropomorphism (e.g., "The server thinks...").
-  - "Should": Be clear about requirements ("must") vs. recommendations ("we
-    recommend").
-
-## VIII. Files and media
-
-- **Filenames:** Use lowercase letters, separate words with hyphens (-), and use
-  standard ASCII characters.
-- **Images:** Provide descriptive alt text for all images. Provide
-  high-resolution or vector images when practical.
-
-## IX. Accessibility quick check
-
-- Provide descriptive alt text for images.
-- Ensure link text makes sense out of context.
-- Use semantic HTML elements correctly (headings, lists, tables).

.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/pr-address-comments/SKILL.md

@@ -0,0 +1,13 @@
+---
+name: pr-address-comments
+description: Use this skill if the user asks you to help them address GitHub PR comments for their current branch of the Gemini CLI. Requires `gh` CLI tool.
+---
+You are helping the user address comments on their Pull Request. These comments may have come from an automated review agent or a team member.
+
+OBJECTIVE: Help the user review and address comments on their PR.
+
+# Comment Review Procedure
+
+1. Run the `scripts/fetch-pr-info.js` script to get PR info and state. MAKE SURE you read the entire output of the command, even if it gets truncated.
+2. Summarize the review status by analyzing the diff, commit log, and comments to see which still need to be addressed. Pay attention to the current user's comments. For resolved threads, summarize as a single line with a ✅. For open threads, provide a reference number e.g. [1] and the comment content.
+3. Present your summary of the feedback and current state and allow the user to guide you as to what to fix/address/skip. DO NOT begin fixing issues automatically.

.gemini/skills/pr-address-comments/scripts/fetch-pr-info.js

@@ -0,0 +1,160 @@
+#!/usr/bin/env node
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+/* eslint-env node */
+/* global console, process */
+
+import { exec } from 'node:child_process';
+import { promisify } from 'node:util';
+
+const execAsync = promisify(exec);
+
+async function run(cmd) {
+  try {
+    const { stdout } = await execAsync(cmd, {
+      encoding: 'utf8',
+      stdio: ['pipe', 'pipe', 'ignore'],
+    });
+    return stdout.trim();
+  } catch {
+    return null;
+  }
+}
+
+const IGNORE_MESSAGES = [
+  'thank you so much for your contribution to Gemini CLI!',
+  "I'm currently reviewing this pull request and will post my feedback shortly.",
+  'This pull request is being closed because it is not currently linked to an issue.',
+];
+
+const shouldIgnore = (body) => {
+  if (!body) return false;
+  return IGNORE_MESSAGES.some((msg) => body.includes(msg));
+};
+
+async function main() {
+  const branch = await run('git branch --show-current');
+  if (!branch) {
+    console.error('❌ Could not determine current git branch.');
+    process.exit(1);
+  }
+
+  const gqlQuery = `query($branch:String!){repository(name:"gemini-cli",owner:"google-gemini"){pullRequests(headRefName:$branch,first:100){nodes{id,number,state,comments(first:100){nodes{createdAt,isMinimized,minimizedReason,author{login},body,url,authorAssociation}},reviews(first:100){nodes{id,author{login},createdAt,isMinimized,minimizedReason,body,state,comments(first:30){nodes{id,replyTo{id},author{login},createdAt,body,isMinimized,minimizedReason,path,line,startLine,originalLine,originalStartLine}}}}}}}}`;
+
+  const [authInfo, diff, commits, rawJson] = await Promise.all([
+    run('gh auth status -a'),
+    run('gh pr diff'),
+    run(
+      'git fetch && git log origin/main..origin/$(git branch --show-current)',
+    ),
+    run(`gh api graphql -F branch="${branch}" -f query='${gqlQuery}'`),
+  ]);
+
+  if (!diff) {
+    console.error(`⚠️ No active PR found for branch: ${branch}`);
+    process.exit(1);
+  }
+
+  console.log(`\n# Current GitHub user info:\n\n${authInfo}\n`);
+  console.log(`\n# PR diff for current branch: ${branch}\n\n\`\`\``);
+  console.log(diff);
+  console.log('```');
+  console.log(
+    `\n# Commit history (origin/main..origin/${branch})\n\n${commits}`,
+  );
+
+  const data = JSON.parse(rawJson || '{}');
+  const prs = data?.data?.repository?.pullRequests?.nodes || [];
+
+  // Sort PRs by number descending so we check the newest one first
+  prs.sort((a, b) => b.number - a.number);
+
+  const pr = prs.find((p) => p.state === 'OPEN') || prs[0];
+
+  if (!pr) {
+    console.error('❌ No PR data found.');
+    process.exit(1);
+  }
+
+  console.log('\n# PR Feedback\n');
+
+  // 1. General PR Comments
+  const general = pr.comments.nodes.filter((c) => !shouldIgnore(c.body));
+  if (general.length > 0) {
+    console.log('\n💬 GENERAL COMMENTS:');
+    general.forEach((c) => {
+      const minimized = c.isMinimized
+        ? ` (Minimized: ${c.minimizedReason})`
+        : '';
+      console.log(
+        `[${c.createdAt}] [${c.author.login}]${minimized}: ${c.body}\n`,
+      );
+    });
+  }
+
+  // 2. Process ALL Review Comments into a single Thread Map
+  const allInlineComments = pr.reviews.nodes.flatMap((r) => r.comments.nodes);
+  const filteredInlines = allInlineComments.filter(
+    (c) => !shouldIgnore(c.body),
+  );
+
+  console.log('🔍 CODE REVIEWS & INLINE THREADS:');
+
+  // Print Review Summaries First
+  pr.reviews.nodes.forEach((review) => {
+    if (review.body && !shouldIgnore(review.body)) {
+      const icon = review.state === 'APPROVED' ? '✅' : '💬';
+      const minimized = review.isMinimized
+        ? ` (Minimized: ${review.minimizedReason})`
+        : '';
+      console.log(
+        `\n${icon} ${review.state} by ${review.author.login} at ${review.createdAt}${minimized}: "${review.body}"`,
+      );
+    }
+  });
+
+  // Build and Print Threads
+  const topLevelThreads = filteredInlines.filter((c) => !c.replyTo);
+
+  const printThread = (parentId, depth = 1) => {
+    const indent = '  '.repeat(depth);
+    filteredInlines
+      .filter((c) => c.replyTo?.id === parentId)
+      .forEach((reply) => {
+        const minimized = reply.isMinimized
+          ? ` (Minimized: ${reply.minimizedReason})`
+          : '';
+        console.log(
+          `${indent}↳ [${reply.createdAt}] ${reply.author.login}${minimized}: ${reply.body}`,
+        );
+        printThread(reply.id, depth + 1);
+      });
+  };
+
+  topLevelThreads.forEach((c) => {
+    const start = c.startLine || c.originalStartLine;
+    const end = c.line || c.originalLine;
+    const range = start && end && start !== end ? `${start}-${end}` : end || '';
+    const fileInfo = c.path
+      ? `(${c.path}${range ? `:${range}` : ''}) `
+      : range
+        ? `(Line ${range}) `
+        : '';
+    const minimized = c.isMinimized ? ` (Minimized: ${c.minimizedReason})` : '';
+    console.log(
+      `\n💬 ${minimized}${c.author.login} | ${c.createdAt} ${fileInfo}\n${c.body}`,
+    );
+    printThread(c.id);
+  });
+
+  console.log('\n');
+}
+
+main().catch((err) => {
+  console.error('❌ Unexpected error:', err);
+  process.exit(1);
+});

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

@@ -14,25 +14,34 @@ repository's standards.
 
 Follow these steps to create a Pull Request:
 
-1.  **Branch Management**: Check the current branch to avoid working directly
-    on `main`.
+1.  **Branch Management**: **CRITICAL:** Ensure you are NOT working on the
+    `main` branch.
     - Run `git branch --show-current`.
-    - If the current branch is `main`, create and switch to a new descriptive
-      branch:
+    - If the current branch is `main`, you MUST create and switch to a new
+      descriptive branch:
       ```bash
       git checkout -b <new-branch-name>
       ```
 
-2.  **Locate Template**: Search for a pull request template in the repository.
+2.  **Commit Changes**: Verify that all intended changes are committed.
+    - Run `git status` to check for unstaged or uncommitted changes.
+    - If there are uncommitted changes, stage and commit them with a descriptive
+      message before proceeding. NEVER commit directly to `main`.
+      ```bash
+      git add .
+      git commit -m "type(scope): description"
+      ```
+
+3.  **Locate Template**: Search for a pull request template in the repository.
     - Check `.github/pull_request_template.md`
     - Check `.github/PULL_REQUEST_TEMPLATE.md`
     - If multiple templates exist (e.g., in `.github/PULL_REQUEST_TEMPLATE/`),
       ask the user which one to use or select the most appropriate one based on
       the context (e.g., `bug_fix.md` vs `feature.md`).
 
-3.  **Read Template**: Read the content of the identified template file.
+4.  **Read Template**: Read the content of the identified template file.
 
-4.  **Draft Description**: Create a PR description that strictly follows the
+5.  **Draft Description**: Create a PR description that strictly follows the
     template's structure.
     - **Headings**: Keep all headings from the template.
     - **Checklists**: Review each item. Mark with `[x]` if completed. If an item
@@ -44,14 +53,24 @@ Follow these steps to create a Pull Request:
     - **Related Issues**: Link any issues fixed or related to this PR (e.g.,
       "Fixes #123").
 
-5.  **Preflight Check**: Before creating the PR, run the workspace preflight
+6.  **Preflight Check**: Before creating the PR, run the workspace preflight
     script to ensure all build, lint, and test checks pass.
     ```bash
     npm run preflight
     ```
     If any checks fail, address the issues before proceeding to create the PR.
 
-6.  **Create PR**: Use the `gh` CLI to create the PR. To avoid shell escaping
+7.  **Push Branch**: Push the current branch to the remote repository.
+    **CRITICAL SAFETY RAIL:** Double-check your branch name before pushing.
+    NEVER push if the current branch is `main`.
+    ```bash
+    # Verify current branch is NOT main
+    git branch --show-current
+    # Push non-interactively
+    git push -u origin HEAD
+    ```
+
+8.  **Create PR**: Use the `gh` CLI to create the PR. To avoid shell escaping
     issues with multi-line Markdown, write the description to a temporary file
     first.
     ```bash
@@ -68,6 +87,7 @@ Follow these steps to create a Pull Request:
 
 ## Principles
 
+- **Safety First**: NEVER push to `main`. This is your highest priority.
 - **Compliance**: Never ignore the PR template. It exists for a reason.
 - **Completeness**: Fill out all relevant sections.
 - **Accuracy**: Don't check boxes for tasks you haven't done.

.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.

.gemini/skills/tui-tester/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: tui-tester
+description: Expert guidance for testing Gemini CLI behavior and visual output using terminal automation.
+---
+
+# TUI Tester Skill
+
+This skill provides the operational manual for verifying Gemini CLI behavioral changes and visual output using terminal automation.
+
+## Core Responsibilities
+
+- **Verify Behavior**: Confirm that code changes result in the expected terminal interactions.
+- **Visual Validation**: Ensure the TUI renders correctly across different terminal sizes and states.
+- **Regression Testing**: Use automation to prevent breaking existing interactive workflows.
+
+## Critical Protocol
+
+When performing TUI testing, you must adhere to these strict rules:
+
+### 1. Initialization
+**YOUR ABSOLUTE FIRST ACTION MUST BE:**
+Activate the `agent-tui` skill. This provides the underlying tools needed for terminal automation.
+
+### 2. Environment Setup (macOS / Parallel Safe)
+Ensure the global daemon is running and the live preview is open:
+```bash
+if ! agent-tui sessions >/dev/null 2>&1; then
+  tmux kill-session -t agent-tui 2>/dev/null || true
+  agent-tui daemon stop 2>/dev/null || true
+  rm -f /tmp/agent-tui*
+  tmux new-session -d -s agent-tui 'agent-tui daemon start --foreground > /tmp/agent-tui-daemon.log 2>&1'
+  sleep 1
+fi
+agent-tui live start --open
+```
+
+### 3. Session Management
+- **Session IDs**: Always use the `session_id` returned by `agent-tui run` for subsequent interactions.
+- **Atomic Execution**: Execute exactly one command per turn. Do not pipeline actions.
+- **The Loop**: Action -> Wait -> Screenshot -> Verify -> Next Action.
+
+### 4. Gemini CLI Specifics
+- **Build First**: Always run `npm run build` or `npm run build:all` before testing local changes.
+- **Bypass Trust**: Set `GEMINI_CLI_TRUST_WORKSPACE=true` to avoid focus-stealing modals.
+- **Isolate Config**: Use `GEMINI_CLI_HOME` to prevent interference with your personal settings.
+
+## Workflow Example
+
+```bash
+# Start the CLI
+env GEMINI_CLI_TRUST_WORKSPACE=true agent-tui run node packages/cli/dist/index.js
+
+# Wait for the prompt
+agent-tui wait "│" --assert
+
+# Send a command
+agent-tui type "/help"
+agent-tui press Enter
+
+# Verify output
+agent-tui wait "Available Commands" --assert
+```
+
+## Error Recovery
+If a wait times out, take a fresh screenshot to diagnose the state. If you see `os error 61`, restart the daemon using the tmux method.

.geminiignore

@@ -0,0 +1,2 @@
+packages/core/src/services/scripts/*.exe
+gha-creds-*.json

.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/calculate-vars/action.yml

@@ -14,12 +14,6 @@ outputs:
 runs:
   using: 'composite'
   steps:
-    - name: 'Print inputs'
-      shell: 'bash'
-      env:
-        JSON_INPUTS: '${{ toJSON(inputs) }}'
-      run: 'echo "$JSON_INPUTS"'
-
     - name: 'Set vars for simplified logic'
       id: 'set_vars'
       shell: 'bash'

.github/actions/create-pull-request/action.yml

@@ -30,27 +30,26 @@ inputs:
 runs:
   using: 'composite'
   steps:
-    - name: '📝 Print Inputs'
-      shell: 'bash'
-      env:
-        JSON_INPUTS: '${{ toJSON(inputs) }}'
-      run: 'echo "$JSON_INPUTS"'
     - name: 'Creates a Pull Request'
       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/download-mac-binaries/action.yml

@@ -0,0 +1,23 @@
+name: 'Download Mac Binaries'
+description: 'Downloads the unsigned macOS binaries (x64 and arm64)'
+inputs:
+  path:
+    description: 'The base path to download the binaries to'
+    required: true
+    default: 'dist'
+runs:
+  using: 'composite'
+  steps:
+    - name: 'Download macOS arm64 binary'
+      uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4
+      continue-on-error: true
+      with:
+        name: 'gemini-darwin-arm64-unsigned'
+        path: '${{ inputs.path }}/darwin-arm64'
+
+    - name: 'Download macOS x64 binary'
+      uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4
+      continue-on-error: true
+      with:
+        name: 'gemini-darwin-x64-unsigned'
+        path: '${{ inputs.path }}/darwin-x64'

.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/post-coverage-comment/action.yml

@@ -27,11 +27,6 @@ inputs:
 runs:
   using: 'composite'
   steps:
-    - name: '📝 Print Inputs'
-      shell: 'bash'
-      env:
-        JSON_INPUTS: '${{ toJSON(inputs) }}'
-      run: 'echo "$JSON_INPUTS"'
     - name: 'Prepare Coverage Comment'
       id: 'prep_coverage_comment'
       shell: 'bash'

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

@@ -20,6 +20,9 @@ inputs:
   github-token:
     description: 'The GitHub token for creating the release.'
     required: true
+  github-release-token:
+    description: 'The GitHub token used specifically for creating the GitHub release (to trigger other workflows).'
+    required: false
   dry-run:
     description: 'Whether to run in dry-run mode.'
     type: 'string'
@@ -72,12 +75,6 @@ inputs:
 runs:
   using: 'composite'
   steps:
-    - name: '📝 Print Inputs'
-      shell: 'bash'
-      env:
-        JSON_INPUTS: '${{ toJSON(inputs) }}'
-      run: 'echo "$JSON_INPUTS"'
-
     - name: '👤 Configure Git User'
       working-directory: '${{ inputs.working-directory }}'
       shell: 'bash'
@@ -90,15 +87,19 @@ runs:
       id: 'release_branch'
       shell: 'bash'
       run: |
-        BRANCH_NAME="release/${{ 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: '${{ inputs.working-directory }}'
@@ -107,13 +108,14 @@ runs:
         BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'
         DRY_RUN: '${{ inputs.dry-run }}'
         RELEASE_TAG: '${{ inputs.release-tag }}'
+        GIT_PUSH_TOKEN: '${{ inputs.github-release-token || inputs.github-token }}'
       run: |-
         set -e
         git add package.json package-lock.json packages/*/package.json
         git commit -m "chore(release): ${RELEASE_TAG}"
         if [[ "${DRY_RUN}" == "false" ]]; then
           echo "Pushing release branch to remote..."
-          git push --set-upstream origin "${BRANCH_NAME}" --follow-tags
+          git push "https://x-access-token:${GIT_PUSH_TOKEN}@github.com/${{ github.repository }}.git" "HEAD:${BRANCH_NAME}" --follow-tags
         else
           echo "Dry run enabled. Skipping push."
         fi
@@ -160,23 +162,40 @@ 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 }}" \
-          --no-tag
-        npm dist-tag rm ${{ inputs.core-package-name }} false --silent
+          --ignore-scripts \
+          --dry-run="${INPUTS_DRY_RUN}" \
+          --workspace="${INPUTS_CORE_PACKAGE_NAME}" \
+          --tag staging-tmp
+        if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
+          npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} staging-tmp
+        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'
@@ -192,13 +211,18 @@ 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 }}" \
-          --no-tag
-        npm dist-tag rm ${{ inputs.cli-package-name }} false --silent
+          --ignore-scripts \
+          --dry-run="${INPUTS_DRY_RUN}" \
+          --workspace="${INPUTS_CLI_PACKAGE_NAME}" \
+          --tag staging-tmp
+        if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
+          npm dist-tag rm ${INPUTS_CLI_PACKAGE_NAME} staging-tmp
+        fi
 
     - name: 'Get a2a-server Token'
       uses: './.github/actions/npm-auth-token'
@@ -214,14 +238,19 @@ 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 }}" \
-          --no-tag
-        npm dist-tag rm ${{ inputs.a2a-package-name }} false --silent
+          --ignore-scripts \
+          --dry-run="${INPUTS_DRY_RUN}" \
+          --workspace="${INPUTS_A2A_PACKAGE_NAME}" \
+          --tag staging-tmp
+          if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
+            npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} staging-tmp
+          fi
 
     - name: '🔬 Verify NPM release by version'
       uses: './.github/actions/verify-release'
@@ -254,14 +283,47 @@ runs:
       working-directory: '${{ inputs.working-directory }}'
       if: "${{ 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: '${{ inputs.github-token }}'
+        GITHUB_TOKEN: '${{ 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
+
+        RELEASE_ASSETS=("gemini-cli-bundle.zip")
+
+        # Check for and prepare macOS binaries if they exist
+        for arch in arm64 x64; do
+          BINARY_PATH="dist/darwin-${arch}/gemini"
+          if [[ -f "$BINARY_PATH" ]]; then
+            chmod +x "$BINARY_PATH"
+            ZIP_NAME="gemini-darwin-${arch}-unsigned.zip"
+            zip -j "$ZIP_NAME" "$BINARY_PATH"
+            RELEASE_ASSETS+=("$ZIP_NAME")
+          fi
+        done
+
+        gh release create "${INPUTS_RELEASE_TAG}" \
+          "${RELEASE_ASSETS[@]}" \
+          --target "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}" \
+          --title "Release ${INPUTS_RELEASE_TAG}" \
+          --notes-start-tag "${INPUTS_PREVIOUS_TAG}" \
           --generate-notes \
           ${{ inputs.npm-tag != 'latest' && '--prerelease' || '' }}
 
@@ -271,5 +333,9 @@ 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 ${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}..."
+        git push "https://x-access-token:${GIT_PUSH_TOKEN}@github.com/${{ github.repository }}.git" --delete "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}"
+
+      env:
+        GIT_PUSH_TOKEN: '${{ inputs.github-release-token || inputs.github-token }}'
+        STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'

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

@@ -18,11 +18,6 @@ inputs:
 runs:
   using: 'composite'
   steps:
-    - name: '📝 Print Inputs'
-      shell: 'bash'
-      env:
-        JSON_INPUTS: '${{ toJSON(inputs) }}'
-      run: 'echo "$JSON_INPUTS"'
     - name: 'Checkout'
       uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v4
       with:
@@ -52,8 +47,10 @@ 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

@@ -28,13 +28,8 @@ inputs:
 runs:
   using: 'composite'
   steps:
-    - name: '📝 Print Inputs'
-      shell: 'bash'
-      env:
-        JSON_INPUTS: '${{ toJSON(inputs) }}'
-      run: 'echo "$JSON_INPUTS"'
     - name: 'Checkout'
-      uses: 'actions/checkout@v4'
+      uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
       with:
         ref: '${{ inputs.github-sha }}'
         fetch-depth: 0
@@ -44,10 +39,12 @@ runs:
     - name: 'npm build'
       shell: 'bash'
       run: 'npm run build'
+    - name: 'Set up QEMU'
+      uses: 'docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130' # ratchet:docker/setup-qemu-action@v3
     - name: 'Set up Docker Buildx'
-      uses: 'docker/setup-buildx-action@v3'
+      uses: 'docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f' # ratchet:docker/setup-buildx-action@v3
     - name: 'Log in to GitHub Container Registry'
-      uses: 'docker/login-action@v3'
+      uses: 'docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9' # ratchet:docker/login-action@v3
       with:
         registry: 'docker.io'
         username: '${{ inputs.dockerhub-username }}'
@@ -56,8 +53,8 @@ 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}"
@@ -66,22 +63,43 @@ 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)" >> $GITHUB_OUTPUT
+    - name: 'verify'
+      shell: 'bash'
+      run: |-
+        docker run --rm --entrypoint sh "${{ steps.docker_build.outputs.uri }}" -lc '
+          set -e
+          node -e "const fs=require(\"node:fs\"); JSON.parse(fs.readFileSync(\"/usr/local/share/npm-global/lib/node_modules/@google/gemini-cli/package.json\",\"utf8\")); JSON.parse(fs.readFileSync(\"/usr/local/share/npm-global/lib/node_modules/@google/gemini-cli-core/package.json\",\"utf8\"));"
+          /usr/local/share/npm-global/bin/gemini --version >/dev/null
+        '
     - 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

@@ -13,14 +13,17 @@ inputs:
 runs:
   using: 'composite'
   steps:
-    - name: '📝 Print 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'
-      env:
-        JSON_INPUTS: '${{ toJSON(inputs) }}'
-      run: 'echo "$JSON_INPUTS"'
     - name: 'Run Tests'
       env:
         GEMINI_API_KEY: '${{ inputs.gemini_api_key }}'
+        GEMINI_CLI_TRUST_WORKSPACE: true
       working-directory: '${{ inputs.working-directory }}'
       run: |-
         echo "::group::Build"

.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=${{ inputs.github-token }}"" >> ~/.npmrc
-        echo ""@google:registry=https://wombat-dressing-room.appspot.com"" >> ~/.npmrc
+        echo ""//npm.pkg.github.com/:_authToken=${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

@@ -40,12 +40,6 @@ inputs:
 runs:
   using: 'composite'
   steps:
-    - name: '📝 Print Inputs'
-      shell: 'bash'
-      env:
-        JSON_INPUTS: '${{ toJSON(inputs) }}'
-      run: 'echo "$JSON_INPUTS"'
-
     - name: 'Setup Node.js'
       uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020'
       with:
@@ -71,10 +65,13 @@ 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 +88,13 @@ 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 +111,13 @@ 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 +125,15 @@ 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

@@ -29,14 +29,8 @@ inputs:
 runs:
   using: 'composite'
   steps:
-    - name: '📝 Print Inputs'
-      shell: 'bash'
-      env:
-        JSON_INPUTS: '${{ toJSON(inputs) }}'
-      run: 'echo "$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 +58,13 @@ 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 +74,14 @@ 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'
@@ -92,6 +92,7 @@ runs:
       working-directory: '${{ inputs.working-directory }}'
       env:
         GEMINI_API_KEY: '${{ inputs.gemini_api_key }}'
+        GEMINI_CLI_TRUST_WORKSPACE: true
         INTEGRATION_TEST_USE_INSTALLED_GEMINI: 'true'
         # We must diable CI mode here because it interferes with interactive tests.
         # See https://github.com/google-gemini/gemini-cli/issues/10517

.github/dependabot.yml

@@ -8,6 +8,10 @@ updates:
     open-pull-requests-limit: 10
     reviewers:
       - 'joshualitt'
+    cooldown:
+      semver-major-days: 14
+      semver-minor-days: 14
+      semver-patch-days: 14
     groups:
       npm-dependencies:
         patterns:
@@ -24,6 +28,10 @@ updates:
     open-pull-requests-limit: 10
     reviewers:
       - 'joshualitt'
+    cooldown:
+      semver-major-days: 14
+      semver-minor-days: 14
+      semver-patch-days: 14
     groups:
       actions-dependencies:
         patterns:

.github/scripts/apply-issue-labels.cjs

@@ -0,0 +1,278 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+module.exports = async ({ github, context, core }) => {
+  const extractJson = (raw) => {
+    if (!raw || raw === '[]' || raw === '') return [];
+    try {
+      // First, try to parse the raw output as JSON.
+      return JSON.parse(raw);
+    } catch {
+      // If that fails, check for a markdown code block.
+      core.info(
+        'Direct JSON parsing failed. Trying to extract from a markdown block.',
+      );
+      const jsonMatch = raw.match(/```json\s*([\s\S]*?)\s*```/);
+      if (jsonMatch && jsonMatch[1]) {
+        try {
+          return JSON.parse(jsonMatch[1].trim());
+        } catch (markdownError) {
+          core.warning(
+            `Failed to parse extracted JSON from markdown block: ${markdownError.message}`,
+          );
+        }
+      }
+
+      // Try to find a raw JSON array in the output.
+      const jsonArrayMatch = raw.match(
+        /\[\s*\{\s*"issue_number"[\s\S]*\}\s*\]/,
+      );
+      if (jsonArrayMatch) {
+        try {
+          return JSON.parse(jsonArrayMatch[0]);
+        } catch {
+          const fallbackMatch = raw.match(/(\[\s*\{\s*"issue_number"[\s\S]*)/);
+          if (fallbackMatch) {
+            try {
+              const cleaned = fallbackMatch[0].substring(
+                0,
+                fallbackMatch[0].lastIndexOf(']') + 1,
+              );
+              return JSON.parse(cleaned);
+            } catch (fallbackError) {
+              core.warning(
+                `Failed to parse extracted JSON using fallback regex: ${fallbackError.message}`,
+              );
+            }
+          }
+        }
+      }
+    }
+    core.warning('No valid JSON could be extracted from input.');
+    return [];
+  };
+
+  // Collect all outputs from environment variables
+  // Prioritize EFFORT results over STANDARD results by processing Effort FIRST
+  // so that its labels appear first in the merged arrays (and thus win in mutually exclusive logic)
+  const effortRaw = process.env.LABELS_OUTPUT_EFFORT;
+  const standardRaw = process.env.LABELS_OUTPUT_STANDARD;
+  const genericRaw = process.env.LABELS_OUTPUT;
+
+  const resultsByIssue = new Map();
+
+  const processResults = (results, _sourceName) => {
+    for (const entry of results) {
+      const issueNumber = entry.issue_number;
+      if (!issueNumber) continue;
+
+      if (!resultsByIssue.has(issueNumber)) {
+        resultsByIssue.set(issueNumber, {
+          issue_number: issueNumber,
+          labels_to_add: [...(entry.labels_to_add || [])],
+          labels_to_remove: [...(entry.labels_to_remove || [])],
+          explanation: entry.explanation || '',
+          effort_analysis: entry.effort_analysis || '',
+        });
+      } else {
+        const existing = resultsByIssue.get(issueNumber);
+        // Combine labels
+        existing.labels_to_add = [
+          ...new Set([
+            ...existing.labels_to_add,
+            ...(entry.labels_to_add || []),
+          ]),
+        ];
+        existing.labels_to_remove = [
+          ...new Set([
+            ...existing.labels_to_remove,
+            ...(entry.labels_to_remove || []),
+          ]),
+        ];
+
+        // Combine explanations (if different)
+        if (
+          entry.explanation &&
+          !existing.explanation.includes(entry.explanation)
+        ) {
+          existing.explanation = existing.explanation
+            ? `${existing.explanation}\n\n${entry.explanation}`
+            : entry.explanation;
+        }
+
+        // Take effort analysis if present
+        if (entry.effort_analysis && !existing.effort_analysis) {
+          existing.effort_analysis = entry.effort_analysis;
+        }
+      }
+    }
+  };
+
+  // Order matters: Effort first so its labels win in conflict resolution
+  processResults(extractJson(effortRaw), 'EFFORT');
+  processResults(extractJson(standardRaw), 'STANDARD');
+  processResults(extractJson(genericRaw), 'GENERIC');
+
+  const finalResults = Array.from(resultsByIssue.values());
+  core.info(`Aggregated triage results for ${finalResults.length} issues.`);
+
+  for (const entry of finalResults) {
+    const issueNumber = entry.issue_number;
+    let labelsToAdd = entry.labels_to_add || [];
+    let labelsToRemove = entry.labels_to_remove || [];
+    let existingLabels = [];
+
+    // Fetch existing labels early
+    try {
+      const { data: issueData } = await github.rest.issues.get({
+        owner: context.repo.owner,
+        repo: context.repo.repo,
+        issue_number: issueNumber,
+      });
+      existingLabels = issueData.labels.map((l) =>
+        typeof l === 'string' ? l : l.name,
+      );
+    } catch (e) {
+      core.warning(
+        `Failed to fetch existing labels for #${issueNumber}: ${e.message}`,
+      );
+    }
+
+    // Programmatic Priority Downgrade Logic
+    if (labelsToAdd.includes('status/need-information')) {
+      const targetPriority = labelsToAdd.find((l) => l.startsWith('priority/'));
+      if (targetPriority) {
+        let downgradedPriority = null;
+        if (targetPriority === 'priority/p0')
+          downgradedPriority = 'priority/p1';
+        if (targetPriority === 'priority/p1')
+          downgradedPriority = 'priority/p2';
+
+        if (downgradedPriority) {
+          core.info(
+            `Programmatically downgrading ${targetPriority} to ${downgradedPriority} due to status/need-information`,
+          );
+          labelsToAdd = labelsToAdd.filter((l) => l !== targetPriority);
+          labelsToAdd.push(downgradedPriority);
+        }
+      }
+    }
+
+    labelsToRemove.push('status/need-triage');
+
+    if (
+      labelsToAdd.includes('status/manual-triage') ||
+      existingLabels.includes('status/manual-triage')
+    ) {
+      labelsToRemove.push('status/bot-triaged');
+      labelsToAdd = labelsToAdd.filter((l) => l !== 'status/bot-triaged');
+    } else {
+      labelsToAdd.push('status/bot-triaged');
+    }
+
+    // Resolve internal conflicts (e.g., adding P1 and P2)
+    // We already resolved these by putting Effort first in the combined list
+
+    // Resolve external conflicts with existing labels
+    if (labelsToAdd.some((l) => l.startsWith('area/'))) {
+      labelsToRemove.push(
+        ...existingLabels.filter((l) => l.startsWith('area/')),
+      );
+    }
+    if (labelsToAdd.some((l) => l.startsWith('priority/'))) {
+      labelsToRemove.push(
+        ...existingLabels.filter((l) => l.startsWith('priority/')),
+      );
+    }
+    if (labelsToAdd.some((l) => l.startsWith('kind/'))) {
+      labelsToRemove.push(
+        ...existingLabels.filter((l) => l.startsWith('kind/')),
+      );
+    }
+
+    // Enforce mutual exclusivity in the TO-ADD list (Architect wins)
+    const exclusivePrefixes = ['area/', 'priority/', 'kind/'];
+    for (const prefix of exclusivePrefixes) {
+      const filtered = labelsToAdd.filter((l) => l.startsWith(prefix));
+      if (filtered.length > 1) {
+        const winner = filtered[0]; // First one wins
+        core.info(
+          `Issue #${issueNumber} has multiple ${prefix} labels suggested. Keeping "${winner}" and discarding others.`,
+        );
+        labelsToAdd = labelsToAdd.filter(
+          (l) => !l.startsWith(prefix) || l === winner,
+        );
+      }
+    }
+
+    // Final deduplication and cleanup
+    labelsToRemove = [...new Set(labelsToRemove)].filter(
+      (l) => !labelsToAdd.includes(l) && existingLabels.includes(l),
+    );
+    labelsToAdd = [...new Set(labelsToAdd)].filter(
+      (l) => !existingLabels.includes(l),
+    );
+
+    // Batch label operations
+    if (labelsToAdd.length > 0) {
+      await github.rest.issues.addLabels({
+        owner: context.repo.owner,
+        repo: context.repo.repo,
+        issue_number: issueNumber,
+        labels: labelsToAdd,
+      });
+      core.info(
+        `Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}`,
+      );
+    }
+
+    if (labelsToRemove.length > 0) {
+      for (const label of labelsToRemove) {
+        try {
+          await github.rest.issues.removeLabel({
+            owner: context.repo.owner,
+            repo: context.repo.repo,
+            issue_number: issueNumber,
+            name: label,
+          });
+        } catch (e) {
+          if (e.status !== 404)
+            core.warning(
+              `Failed to remove label ${label} from #${issueNumber}: ${e.message}`,
+            );
+        }
+      }
+      core.info(
+        `Successfully removed labels for #${issueNumber}: ${labelsToRemove.join(', ')}`,
+      );
+    }
+
+    // Post comment if needed
+    const needsInfoAdded =
+      labelsToAdd.includes('status/need-information') &&
+      !existingLabels.includes('status/need-information');
+    const hasEffortAnalysis = !!entry.effort_analysis;
+
+    if (needsInfoAdded || hasEffortAnalysis) {
+      let commentBody = '';
+      if (needsInfoAdded && entry.explanation) commentBody += entry.explanation;
+      if (hasEffortAnalysis) {
+        if (commentBody) commentBody += '\n\n';
+        commentBody += `**Effort Analysis:**\n${entry.effort_analysis}`;
+      }
+
+      if (commentBody) {
+        await github.rest.issues.createComment({
+          owner: context.repo.owner,
+          repo: context.repo.repo,
+          issue_number: issueNumber,
+          body: commentBody,
+        });
+        core.info(`Posted required comment for #${issueNumber}`);
+      }
+    }
+  }
+};

.github/scripts/cleanup-triage-labels.cjs

@@ -0,0 +1,74 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+const fs = require('node:fs');
+
+module.exports = async ({ github, context, core }) => {
+  let issuesToCleanup = [];
+  try {
+    const fileContent = fs.readFileSync('issues_to_cleanup.json', 'utf8');
+    issuesToCleanup = JSON.parse(fileContent);
+  } catch (error) {
+    if (error.code === 'ENOENT') {
+      core.info('No issues found to clean up.');
+      return;
+    }
+    core.setFailed(`Failed to read issues_to_cleanup.json: ${error.message}`);
+    return;
+  }
+
+  for (const issue of issuesToCleanup) {
+    try {
+      const { data: issueData } = await github.rest.issues.get({
+        owner: context.repo.owner,
+        repo: context.repo.repo,
+        issue_number: issue.number,
+      });
+
+      const labels = issueData.labels.map((l) =>
+        typeof l === 'string' ? l : l.name,
+      );
+
+      if (
+        labels.includes('status/bot-triaged') &&
+        labels.includes('status/need-triage')
+      ) {
+        await github.rest.issues.removeLabel({
+          owner: context.repo.owner,
+          repo: context.repo.repo,
+          issue_number: issue.number,
+          name: 'status/need-triage',
+        });
+        core.info(
+          `Successfully removed status/need-triage from #${issue.number}`,
+        );
+      }
+
+      if (
+        labels.includes('status/bot-triaged') &&
+        labels.includes('status/manual-triage')
+      ) {
+        await github.rest.issues.removeLabel({
+          owner: context.repo.owner,
+          repo: context.repo.repo,
+          issue_number: issue.number,
+          name: 'status/bot-triaged',
+        });
+        core.info(
+          `Successfully removed status/bot-triaged from #${issue.number} because it requires manual triage`,
+        );
+      }
+    } catch (error) {
+      core.warning(
+        `Failed to clean up labels for #${issue.number}: ${error.message}`,
+      );
+    }
+  }
+
+  core.info(
+    `Cleaned up conflicting labels from ${issuesToCleanup.length} issues.`,
+  );
+};

.github/scripts/gemini-lifecycle-manager.cjs

@@ -0,0 +1,380 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+/**
+ * Gemini Scheduled Lifecycle Manager Script
+ * @param {object} param0
+ * @param {import('@octokit/rest').Octokit} param0.github
+ * @param {import('@actions/github/lib/context').Context} param0.context
+ * @param {import('@actions/core')} param0.core
+ */
+module.exports = async ({ github, context, core }) => {
+  const dryRun = process.env.DRY_RUN === 'true';
+  const owner = context.repo.owner;
+  const repo = context.repo.repo;
+
+  core.info(`Running in ${dryRun ? 'DRY RUN' : 'PRODUCTION'} mode.`);
+
+  const STALE_LABEL = 'stale';
+  const NEED_INFO_LABEL = 'status/need-information';
+  const EXEMPT_LABELS = [
+    'pinned',
+    'security',
+    '🔒 maintainer only',
+    'help wanted',
+    '🗓️ Public Roadmap',
+  ];
+
+  const STALE_DAYS = 60;
+  const CLOSE_DAYS = 14;
+  const NO_RESPONSE_DAYS = 14;
+
+  const now = new Date();
+  const staleThreshold = new Date(
+    now.getTime() - STALE_DAYS * 24 * 60 * 60 * 1000,
+  );
+  const closeThreshold = new Date(
+    now.getTime() - CLOSE_DAYS * 24 * 60 * 60 * 1000,
+  );
+  const noResponseThreshold = new Date(
+    now.getTime() - NO_RESPONSE_DAYS * 24 * 60 * 60 * 1000,
+  );
+
+  const maintainerCache = new Map();
+  async function isMaintainer(user, association) {
+    if (user?.type === 'Bot') return true;
+    if (['OWNER', 'MEMBER', 'COLLABORATOR'].includes(association)) return true;
+
+    const username = user?.login;
+    if (!username) return false;
+
+    if (maintainerCache.has(username)) {
+      return maintainerCache.get(username);
+    }
+
+    try {
+      const { data } = await github.rest.repos.getCollaboratorPermissionLevel({
+        owner,
+        repo,
+        username,
+      });
+      // Permission can be admin, write, read, none.
+      // Roles like 'maintain' or 'triage' often map to 'write' or 'read' in the top-level field.
+      const isM =
+        ['admin', 'write'].includes(data.permission) ||
+        ['admin', 'maintain', 'write'].includes(data.role_name);
+
+      maintainerCache.set(username, isM);
+      return isM;
+    } catch (err) {
+      core.warning(
+        `Could not check permissions for ${username}: ${err.message}`,
+      );
+      maintainerCache.set(username, false);
+      return false;
+    }
+  }
+
+  async function processItems(query, callback) {
+    core.info(`Searching: ${query}`);
+    try {
+      let items = await github.paginate(
+        github.rest.search.issuesAndPullRequests,
+        {
+          q: query,
+          per_page: 100,
+          sort: 'updated',
+          order: 'asc',
+        },
+      );
+      core.info(`Found ${items.length} items.`);
+      for (const item of items) {
+        try {
+          await callback(item);
+        } catch (err) {
+          core.error(`Error processing #${item.number}: ${err.message}`);
+        }
+      }
+    } catch (err) {
+      core.error(`Search failed: ${err.message}`);
+    }
+  }
+
+  // 1. Handle No-Response (status/need-information)
+  // Removal: Check issues updated in the last 48h that have the label
+  const twoDaysAgo = new Date(now.getTime() - 2 * 24 * 60 * 60 * 1000);
+  await processItems(
+    `repo:${owner}/${repo} is:open label:"${NEED_INFO_LABEL}" updated:>${twoDaysAgo.toISOString()}`,
+    async (item) => {
+      const { data: comments } = await github.rest.issues.listComments({
+        owner,
+        repo,
+        issue_number: item.number,
+        sort: 'created',
+        direction: 'desc',
+        per_page: 5,
+      });
+
+      // Check if the last comment is from a non-maintainer and not a bot
+      const lastComment = comments[0];
+      if (
+        lastComment &&
+        lastComment.user?.type !== 'Bot' &&
+        !(await isMaintainer(lastComment.user, lastComment.author_association))
+      ) {
+        if (dryRun) {
+          core.info(
+            `[DRY RUN] Would remove ${NEED_INFO_LABEL} from #${item.number} due to contributor response.`,
+          );
+        } else {
+          core.info(
+            `Removing ${NEED_INFO_LABEL} from #${item.number} due to contributor response.`,
+          );
+          await github.rest.issues
+            .removeLabel({
+              owner,
+              repo,
+              issue_number: item.number,
+              name: NEED_INFO_LABEL,
+            })
+            .catch(() => {});
+        }
+      }
+    },
+  );
+
+  // Closure: Check issues with the label that haven't been updated in 14 days
+  await processItems(
+    `repo:${owner}/${repo} is:open label:"${NEED_INFO_LABEL}" updated:<${noResponseThreshold.toISOString()}`,
+    async (item) => {
+      if (dryRun) {
+        core.info(
+          `[DRY RUN] Would close #${item.number} due to no response for ${NO_RESPONSE_DAYS} days.`,
+        );
+      } else {
+        core.info(
+          `Closing #${item.number} due to no response for ${NO_RESPONSE_DAYS} days.`,
+        );
+        await github.rest.issues.createComment({
+          owner,
+          repo,
+          issue_number: item.number,
+          body: `This item was marked as needing more information and has not received a response in ${NO_RESPONSE_DAYS} days. Closing it for now. If you still face this problem, feel free to reopen with more details. Thank you!`,
+        });
+        await github.rest.issues.update({
+          owner,
+          repo,
+          issue_number: item.number,
+          state: 'closed',
+          state_reason: 'not_planned',
+        });
+      }
+    },
+  );
+
+  // 2. Handle Stale Mark (60 days inactivity, no stale label)
+  const exemptQuery = EXEMPT_LABELS.map((l) => `-label:"${l}"`).join(' ');
+
+  await processItems(
+    `repo:${owner}/${repo} is:open -label:"${STALE_LABEL}" ${exemptQuery} updated:<${staleThreshold.toISOString()}`,
+    async (item) => {
+      const isBug = item.labels.some((l) =>
+        (typeof l === 'string' ? l : l.name).toLowerCase().includes('bug'),
+      );
+      const bodyText = isBug
+        ? `This bug report has been automatically marked as stale due to ${STALE_DAYS} days of inactivity. Many issues are resolved in newer releases. Please verify if the issue persists in the latest Gemini CLI version. If it does, please leave a comment to keep this open. It will be closed in ${CLOSE_DAYS} days if no further activity occurs. Thank you!`
+        : `This item has been automatically marked as stale due to ${STALE_DAYS} days of inactivity. It will be closed in ${CLOSE_DAYS} days if no further activity occurs. Thank you!`;
+
+      if (dryRun) {
+        core.info(`[DRY RUN] Would mark #${item.number} as stale.`);
+      } else {
+        core.info(`Marking #${item.number} as stale.`);
+        await github.rest.issues.addLabels({
+          owner,
+          repo,
+          issue_number: item.number,
+          labels: [STALE_LABEL],
+        });
+        await github.rest.issues.createComment({
+          owner,
+          repo,
+          issue_number: item.number,
+          body: bodyText,
+        });
+      }
+    },
+  );
+
+  // 3. Handle Stale Removal & Close
+  await processItems(
+    `repo:${owner}/${repo} is:open label:"${STALE_LABEL}" ${exemptQuery}`,
+    async (item) => {
+      // Fetch full timeline to see events and comments
+      const timeline = await github.paginate(
+        github.rest.issues.listEventsForTimeline,
+        {
+          owner,
+          repo,
+          issue_number: item.number,
+          per_page: 100,
+        },
+      );
+
+      // Find exactly when the Stale label was added
+      // We look for the last 'labeled' event for STALE_LABEL
+      const staleEventIndex = timeline.findLastIndex(
+        (e) =>
+          e.event === 'labeled' &&
+          e.label?.name?.toLowerCase() === STALE_LABEL.toLowerCase(),
+      );
+
+      if (staleEventIndex === -1) return; // Fallback if no event found
+
+      const staleEvent = timeline[staleEventIndex];
+      const eventsAfterStale = timeline.slice(staleEventIndex + 1);
+
+      // Check for meaningful activity after the Stale label was applied
+      const meaningfulEvents = eventsAfterStale.filter((e) => {
+        const actor = e.actor?.login || '';
+        const isBot =
+          actor.includes('[bot]') || actor.includes('github-actions');
+
+        if (isBot) return false;
+
+        // Explicit whitelist of meaningful events for humans
+        if (
+          [
+            'commented',
+            'cross-referenced',
+            'connected',
+            'reopened',
+            'assigned',
+          ].includes(e.event)
+        ) {
+          return true;
+        }
+
+        return false;
+      });
+
+      if (meaningfulEvents.length > 0) {
+        // Activity detected, remove Stale label
+        if (dryRun) {
+          core.info(
+            `[DRY RUN] Would remove ${STALE_LABEL} from #${item.number} due to meaningful activity (e.g., comment or PR).`,
+          );
+        } else {
+          core.info(
+            `Removing ${STALE_LABEL} from #${item.number} due to meaningful activity (e.g., comment or PR).`,
+          );
+          await github.rest.issues
+            .removeLabel({
+              owner,
+              repo,
+              issue_number: item.number,
+              name: STALE_LABEL,
+            })
+            .catch(() => {});
+        }
+        return;
+      }
+
+      // No meaningful activity. Check if 14 days have passed.
+      const labeledDate = new Date(staleEvent.created_at);
+      if (labeledDate > closeThreshold) {
+        // Has not been 14 days since it was ACTUALLY marked stale
+        return;
+      }
+
+      if (dryRun) {
+        core.info(`[DRY RUN] Would close stale item #${item.number}.`);
+      } else {
+        core.info(`Closing stale item #${item.number}.`);
+        await github.rest.issues.createComment({
+          owner,
+          repo,
+          issue_number: item.number,
+          body: `This item has been closed due to ${CLOSE_DAYS} additional days of inactivity after being marked as stale. If you believe this is still relevant, feel free to comment or reopen. Thank you!`,
+        });
+        await github.rest.issues.update({
+          owner,
+          repo,
+          issue_number: item.number,
+          state: 'closed',
+          state_reason: 'not_planned',
+        });
+      }
+    },
+  );
+
+  // 4. Handle PR Contribution Policy (Nudge at 7d, Close at 14d)
+  const PR_NUDGE_DAYS = 7;
+  const PR_CLOSE_DAYS = 14;
+  const nudgeThreshold = new Date(
+    now.getTime() - PR_NUDGE_DAYS * 24 * 60 * 60 * 1000,
+  );
+  const prCloseThreshold = new Date(
+    now.getTime() - PR_CLOSE_DAYS * 24 * 60 * 60 * 1000,
+  );
+
+  // Nudge
+  await processItems(
+    `repo:${owner}/${repo} is:open is:pr -label:"help wanted" -label:"🔒 maintainer only" -label:"status/pr-nudge-sent" created:${prCloseThreshold.toISOString()}..${nudgeThreshold.toISOString()}`,
+    async (pr) => {
+      if (await isMaintainer(pr.user, pr.author_association)) return;
+
+      if (dryRun) {
+        core.info(
+          `[DRY RUN] Would nudge PR #${pr.number} for contribution policy.`,
+        );
+      } else {
+        core.info(`Nudging PR #${pr.number} for contribution policy.`);
+        await github.rest.issues.addLabels({
+          owner,
+          repo,
+          issue_number: pr.number,
+          labels: ['status/pr-nudge-sent'],
+        });
+        await github.rest.issues.createComment({
+          owner,
+          repo,
+          issue_number: pr.number,
+          body: "Hi there! Thank you for your interest in contributing to Gemini CLI. \n\nTo ensure we maintain high code quality and focus on our prioritized roadmap, we only guarantee review and consideration of pull requests for issues that are explicitly labeled as 'help wanted'. \n\nThis PR will be closed in 7 days if it remains without that designation. We encourage you to find and contribute to existing 'help wanted' issues in our backlog! Thank you for your understanding.",
+        });
+      }
+    },
+  );
+
+  // Close
+  await processItems(
+    `repo:${owner}/${repo} is:open is:pr -label:"help wanted" -label:"🔒 maintainer only" created:<${prCloseThreshold.toISOString()}`,
+    async (pr) => {
+      if (await isMaintainer(pr.user, pr.author_association)) return;
+
+      if (dryRun) {
+        core.info(
+          `[DRY RUN] Would close PR #${pr.number} per contribution policy (no 'help wanted').`,
+        );
+      } else {
+        core.info(
+          `Closing PR #${pr.number} per contribution policy (no 'help wanted').`,
+        );
+        await github.rest.issues.createComment({
+          owner,
+          repo,
+          issue_number: pr.number,
+          body: "This 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.",
+        });
+        await github.rest.pulls.update({
+          owner,
+          repo,
+          pull_number: pr.number,
+          state: 'closed',
+        });
+      }
+    },
+  );
+};

.github/scripts/pr-triage.sh

@@ -22,7 +22,7 @@ get_issue_labels() {
     # Check cache
     case "${ISSUE_LABELS_CACHE_FLAT}" in
         *"|${ISSUE_NUM}:"*) 
-            local suffix="${ISSUE_LABELS_CACHE_FLAT#*|${ISSUE_NUM}:}"
+            local suffix="${ISSUE_LABELS_CACHE_FLAT#*|"${ISSUE_NUM}":}"
             echo "${suffix%%|*}"
             return
             ;; 

.github/scripts/sync-issue-types.cjs

@@ -0,0 +1,99 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+const fs = require('node:fs');
+
+module.exports = async ({ github, context, core }) => {
+  const query = `
+    query($owner: String!, $repo: String!) {
+      repository(owner: $owner, name: $repo) {
+        issues(first: 50, states: OPEN, orderBy: {field: UPDATED_AT, direction: DESC}) {
+          nodes {
+            id
+            number
+            title
+            body
+            issueType {
+              name
+            }
+            labels(first: 20) {
+              nodes {
+                name
+              }
+            }
+          }
+        }
+      }
+    }
+  `;
+
+  try {
+    const result = await github.graphql(query, {
+      owner: context.repo.owner,
+      repo: context.repo.repo,
+    });
+
+    const issues = result.repository.issues.nodes;
+    const issuesNeedingAnalysis = [];
+    let syncedCount = 0;
+
+    for (const issue of issues) {
+      if (issue.issueType === null) {
+        const labelNames = issue.labels.nodes.map((l) => l.name);
+        const hasBug = labelNames.includes('kind/bug');
+        const hasFeature =
+          labelNames.includes('kind/feature') ||
+          labelNames.includes('kind/enhancement');
+
+        let issueTypeId = null;
+        if (hasBug) {
+          issueTypeId = 'IT_kwDOCaSVvs4BR7vP'; // Bug
+        } else if (hasFeature) {
+          issueTypeId = 'IT_kwDOCaSVvs4BR7vQ'; // Feature
+        }
+
+        if (issueTypeId) {
+          await github.graphql(
+            `
+            mutation($issueId: ID!, $issueTypeId: ID!) {
+              updateIssue(input: {id: $issueId, issueTypeId: $issueTypeId}) {
+                issue {
+                  id
+                }
+              }
+            }
+          `,
+            {
+              issueId: issue.id,
+              issueTypeId: issueTypeId,
+            },
+          );
+          core.info(`Successfully synced Issue Type for #${issue.number}`);
+          syncedCount++;
+        } else {
+          // Needs analysis to determine kind/type
+          issuesNeedingAnalysis.push({
+            number: issue.number,
+            title: issue.title,
+            body: issue.body,
+          });
+        }
+      }
+    }
+
+    // Write issues needing analysis to a file so the AI can process them
+    fs.writeFileSync(
+      'no_type_issues.json',
+      JSON.stringify(issuesNeedingAnalysis),
+    );
+    core.info(`Synced ${syncedCount} issues from labels.`);
+    core.info(
+      `Found ${issuesNeedingAnalysis.length} issues missing both type and kind label to be analyzed.`,
+    );
+  } catch (error) {
+    core.setFailed(`Failed to sync issue types: ${error.message}`);
+  }
+};

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

@@ -1,5 +1,9 @@
-/* eslint-disable @typescript-eslint/no-require-imports */
-/* global process, console, require */
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
 const { Octokit } = require('@octokit/rest');
 
 /**
@@ -343,6 +347,36 @@ async function run() {
           });
         }
       }
+
+      // Remove status/need-triage from maintainer-only issues since they
+      // don't need community triage. We always attempt removal rather than
+      // checking the (potentially stale) label snapshot, because the
+      // issue-opened-labeler workflow runs concurrently and may add the
+      // label after our snapshot was taken.
+      if (isDryRun) {
+        console.log(
+          `[DRY RUN] Would remove status/need-triage from ${issueKey}`,
+        );
+      } else {
+        try {
+          await octokit.rest.issues.removeLabel({
+            owner: issueInfo.owner,
+            repo: issueInfo.repo,
+            issue_number: issueInfo.number,
+            name: 'status/need-triage',
+          });
+          console.log(`Removed status/need-triage from ${issueKey}`);
+        } catch (removeError) {
+          // 404 means the label wasn't present — that's fine.
+          if (removeError.status === 404) {
+            console.log(
+              `status/need-triage not present on ${issueKey}, skipping.`,
+            );
+          } else {
+            throw removeError;
+          }
+        }
+      }
     } catch (error) {
       console.error(`Error processing label for ${issueKey}: ${error.message}`);
     }

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

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

.github/workflows/build-unsigned-mac-binaries.yml

@@ -0,0 +1,65 @@
+name: 'Build Unsigned Mac Binaries'
+
+on:
+  workflow_dispatch:
+  workflow_call:
+    inputs:
+      ref:
+        description: 'The branch, tag, or SHA to build from.'
+        required: true
+        type: 'string'
+
+permissions:
+  contents: 'read'
+
+defaults:
+  run:
+    shell: 'bash'
+
+jobs:
+  build-mac:
+    name: 'Build Unsigned (${{ matrix.arch }})'
+    runs-on: 'macos-latest'
+    strategy:
+      fail-fast: false
+      matrix:
+        arch: ['x64', 'arm64']
+
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
+        with:
+          ref: '${{ inputs.ref || github.ref }}'
+          persist-credentials: false
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+        with:
+          node-version-file: '.nvmrc'
+          architecture: '${{ matrix.arch }}'
+          cache: 'npm'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Build Binary'
+        env:
+          SKIP_SIGNING: 'true'
+        run: 'npm run build:binary'
+
+      - name: 'Verify Output Exists'
+        run: |
+          if [ -f "dist/darwin-${{ matrix.arch }}/gemini" ]; then
+            echo "Binary found at dist/darwin-${{ matrix.arch }}/gemini"
+          else
+            echo "Error: Binary not found in dist/darwin-${{ matrix.arch }}/"
+            ls -R dist/
+            exit 1
+          fi
+
+      - name: 'Upload Artifact'
+        uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
+        with:
+          name: 'gemini-darwin-${{ matrix.arch }}-unsigned'
+          path: 'dist/darwin-${{ matrix.arch }}/gemini'
+          retention-days: 14

.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: '${{ github.repository }}'
@@ -131,7 +132,7 @@ jobs:
       - 'parse_run_context'
     runs-on: 'gemini-cli-ubuntu-16-core'
     if: |
-      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
+      github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
     strategy:
       fail-fast: false
       matrix:
@@ -147,6 +148,7 @@ jobs:
         with:
           ref: '${{ needs.parse_run_context.outputs.sha }}'
           repository: '${{ needs.parse_run_context.outputs.repository }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js ${{ matrix.node-version }}'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -166,6 +168,7 @@ jobs:
       - name: 'Run E2E tests'
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GEMINI_CLI_TRUST_WORKSPACE: true
           KEEP_OUTPUT: 'true'
           VERBOSE: 'true'
           BUILD_SANDBOX_FLAGS: '--cache-from type=gha --cache-to type=gha,mode=max'
@@ -182,15 +185,16 @@ jobs:
     needs:
       - 'merge_queue_skipper'
       - 'parse_run_context'
-    runs-on: 'macos-latest'
+    runs-on: 'macos-latest-large'
     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 }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -211,6 +215,7 @@ jobs:
         if: "${{runner.os != 'Windows'}}"
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GEMINI_CLI_TRUST_WORKSPACE: true
           KEEP_OUTPUT: 'true'
           SANDBOX: 'sandbox:none'
           VERBOSE: 'true'
@@ -222,16 +227,15 @@ 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'
-    continue-on-error: 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 }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -265,9 +269,31 @@ 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 }}'
+          GEMINI_CLI_TRUST_WORKSPACE: true
           KEEP_OUTPUT: 'true'
           SANDBOX: 'sandbox:none'
           VERBOSE: 'true'
@@ -284,13 +310,15 @@ 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 }}'
+          persist-credentials: false
+          fetch-depth: 0
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -303,43 +331,72 @@ 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_CLI_TRUST_WORKSPACE: true
+          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'
+      - 'e2e_windows'
       - 'evals'
       - 'merge_queue_skipper'
     runs-on: 'gemini-cli-ubuntu-16-core'
     steps:
       - name: 'Check E2E test results'
         run: |
-          if [[ ${{ needs.e2e_linux.result }} != 'success' || \
-               ${{ needs.e2e_mac.result }} != 'success' || \
-               ${{ 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: '${{ steps.merge-queue-ci-skipper.outputs.skip-check }}'
     steps:
@@ -49,13 +50,14 @@ jobs:
     name: 'Lint'
     runs-on: 'gemini-cli-ubuntu-16-core'
     needs: 'merge_queue_skipper'
-    if: "${{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: '${{ github.workspace }}/.gemini-linters'
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.branch_ref || github.ref }}'
           fetch-depth: 0
 
@@ -66,7 +68,7 @@ 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 +77,7 @@ 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') }}"
@@ -101,6 +103,12 @@ jobs:
       - name: 'Run yamllint'
         run: 'node scripts/lint.js --yamllint'
 
+      - name: 'Build project for typecheck'
+        run: 'npm run build'
+
+      - name: 'Run typecheck'
+        run: 'npm run typecheck'
+
       - name: 'Run Prettier'
         run: 'node scripts/lint.js --prettier'
 
@@ -113,12 +121,18 @@ 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
+        with:
+          persist-credentials: false
       - name: 'Link Checker'
         uses: 'lycheeverse/lychee-action@885c65f3dc543b57c898c8099f4e08c8afd178a2' # ratchet: lycheeverse/lychee-action@v2.6.1
         with:
@@ -129,7 +143,7 @@ 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'
@@ -146,6 +160,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Set up Node.js ${{ matrix.node-version }}'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -156,18 +172,25 @@ 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'
 
       - name: 'Run tests and generate reports'
         env:
           NO_COLOR: true
+          GEMINI_CLI_TRUST_WORKSPACE: 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
 
@@ -177,6 +200,19 @@ jobs:
       - name: 'Smoke test bundle'
         run: 'node ./bundle/gemini.js --version'
 
+      - name: 'Smoke test npx installation'
+        run: |
+          # 1. Package the project into a tarball
+          TARBALL=$(npm pack | tail -n 1)
+
+          # 2. Move to a fresh directory for isolation
+          mkdir -p ../smoke-test-dir
+          mv "$TARBALL" ../smoke-test-dir/
+          cd ../smoke-test-dir
+
+          # 3. Run npx from the tarball
+          npx "./$TARBALL" --version
+
       - name: 'Wait for file system sync'
         run: 'sleep 2'
 
@@ -200,10 +236,10 @@ jobs:
 
   test_mac:
     name: 'Test (Mac) - ${{ matrix.node-version }}, ${{ matrix.shard }}'
-    runs-on: 'macos-latest'
+    runs-on: 'macos-latest-large'
     needs:
       - 'merge_queue_skipper'
-    if: "${{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'
@@ -221,6 +257,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Set up Node.js ${{ matrix.node-version }}'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -237,12 +275,13 @@ jobs:
       - name: 'Run tests and generate reports'
         env:
           NO_COLOR: true
+          GEMINI_CLI_TRUST_WORKSPACE: true
         run: |
           if [[ "${{ 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
 
@@ -252,6 +291,19 @@ jobs:
       - name: 'Smoke test bundle'
         run: 'node ./bundle/gemini.js --version'
 
+      - name: 'Smoke test npx installation'
+        run: |
+          # 1. Package the project into a tarball
+          TARBALL=$(npm pack | tail -n 1)
+
+          # 2. Move to a fresh directory for isolation
+          mkdir -p ../smoke-test-dir
+          mv "$TARBALL" ../smoke-test-dir/
+          cd ../smoke-test-dir
+
+          # 3. Run npx from the tarball
+          npx "./$TARBALL" --version
+
       - name: 'Wait for file system sync'
         run: 'sleep 2'
 
@@ -285,7 +337,7 @@ jobs:
     name: 'CodeQL'
     runs-on: 'gemini-cli-ubuntu-16-core'
     needs: 'merge_queue_skipper'
-    if: "${{needs.merge_queue_skipper.outputs.skip == 'false'}}"
+    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
     permissions:
       actions: 'read'
       contents: 'read'
@@ -294,6 +346,7 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.branch_ref || github.ref }}'
 
       - name: 'Initialize CodeQL'
@@ -308,7 +361,7 @@ jobs:
   bundle_size:
     name: 'Check Bundle Size'
     needs: 'merge_queue_skipper'
-    if: "${{github.event_name == 'pull_request' && needs.merge_queue_skipper.outputs.skip == 'false'}}"
+    if: "github.repository == 'google-gemini/gemini-cli' && github.event_name == 'pull_request' && needs.merge_queue_skipper.outputs.skip == 'false'"
     runs-on: 'gemini-cli-ubuntu-16-core'
     permissions:
       contents: 'read' # For checkout
@@ -318,6 +371,7 @@ jobs:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.branch_ref || github.ref }}'
           fetch-depth: 1
 
@@ -330,16 +384,22 @@ jobs:
           clean-script: 'clean'
 
   test_windows:
-    name: 'Slow Test - Win'
+    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'}}"
-    continue-on-error: true
+    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
+    timeout-minutes: 60
+    strategy:
+      matrix:
+        shard:
+          - 'cli'
+          - 'others'
 
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
         with:
+          persist-credentials: false
           ref: '${{ github.event.inputs.branch_ref || github.ref }}'
 
       - name: 'Set up Node.js 20.x'
@@ -382,10 +442,21 @@ jobs:
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
           NO_COLOR: true
+          GEMINI_CLI_TRUST_WORKSPACE: true
           NODE_OPTIONS: '--max-old-space-size=32768 --max-semi-space-size=256'
           UV_THREADPOOL_SIZE: '32'
           NODE_ENV: 'test'
-        run: 'npm run test:ci -- --coverage.enabled=false'
+        run: |
+          if ("${{ matrix.shard }}" -eq "cli") {
+            npm run test:ci --workspace "@google/gemini-cli" -- --coverage.enabled=false
+            if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
+          } else {
+            # Explicitly list non-cli packages to ensure they are sharded correctly
+            npm run test:ci --workspace "@google/gemini-cli-core" --workspace "@google/gemini-cli-a2a-server" --workspace "gemini-cli-vscode-ide-companion" --workspace "@google/gemini-cli-test-utils" --if-present -- --coverage.enabled=false
+            if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
+            npm run test:scripts
+            if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
+          }
         shell: 'pwsh'
 
       - name: 'Bundle'
@@ -396,27 +467,52 @@ jobs:
         run: 'node ./bundle/gemini.js --version'
         shell: 'pwsh'
 
+      - name: 'Smoke test npx installation'
+        run: |
+          # 1. Package the project into a tarball
+          $PACK_OUTPUT = npm pack
+          $TARBALL = $PACK_OUTPUT[-1]
+
+          # 2. Move to a fresh directory for isolation
+          New-Item -ItemType Directory -Force -Path ../smoke-test-dir
+          Move-Item $TARBALL ../smoke-test-dir/
+          Set-Location ../smoke-test-dir
+
+          # 3. Run npx from the tarball
+          npx "./$TARBALL" --version
+        shell: 'pwsh'
+
   ci:
     name: 'CI'
-    if: 'always()'
+    if: "github.repository == 'google-gemini/gemini-cli' && always()"
     needs:
       - 'lint'
       - 'link_checker'
       - 'test_linux'
       - 'test_mac'
+      - 'test_windows'
       - 'codeql'
       - 'bundle_size'
     runs-on: 'gemini-cli-ubuntu-16-core'
     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.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/community-report.yml

@@ -173,6 +173,7 @@ jobs:
           GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
           REPOSITORY: '${{ github.repository }}'
         with:
+          upload_artifacts: 'true'
           gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
           gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
           gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -182,12 +183,14 @@ jobs:
           use_gemini_code_assist: '${{ vars.GOOGLE_GENAI_USE_GCA }}'
           settings: |-
             {
-              "coreTools": [
-                "run_shell_command(gh issue list)",
-                "run_shell_command(gh pr list)",
-                "run_shell_command(gh search issues)",
-                "run_shell_command(gh search prs)"
-              ]
+              "tools": {
+                "core": [
+                  "run_shell_command(gh issue list)",
+                  "run_shell_command(gh pr list)",
+                  "run_shell_command(gh search issues)",
+                  "run_shell_command(gh search prs)"
+                ]
+              }
             }
           prompt: |-
             You are a helpful assistant that analyzes community contribution reports.

.github/workflows/deflake.yml

@@ -27,6 +27,7 @@ jobs:
   deflake_e2e_linux:
     name: 'E2E Test (Linux) - ${{ matrix.sandbox }}'
     runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
     strategy:
       fail-fast: false
       matrix:
@@ -42,6 +43,7 @@ jobs:
         with:
           ref: '${{ github.event.pull_request.head.sha }}'
           repository: '${{ github.repository }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js ${{ matrix.node-version }}'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -61,6 +63,7 @@ jobs:
       - name: 'Run E2E tests'
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GEMINI_CLI_TRUST_WORKSPACE: true
           IS_DOCKER: "${{ matrix.sandbox == 'sandbox:docker' }}"
           KEEP_OUTPUT: 'true'
           RUNS: '${{ github.event.inputs.runs }}'
@@ -68,21 +71,23 @@ 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'
+    runs-on: 'macos-latest-large'
+    if: "github.repository == 'google-gemini/gemini-cli'"
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
         with:
           ref: '${{ github.event.pull_request.head.sha }}'
           repository: '${{ github.repository }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -103,24 +108,26 @@ jobs:
         if: "runner.os != 'Windows'"
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GEMINI_CLI_TRUST_WORKSPACE: true
           KEEP_OUTPUT: 'true'
           RUNS: '${{ github.event.inputs.runs }}'
           SANDBOX: 'sandbox:none'
           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
         with:
           ref: '${{ github.event.pull_request.head.sha }}'
           repository: '${{ github.repository }}'
+          persist-credentials: false
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -157,6 +164,7 @@ jobs:
       - name: 'Run E2E tests'
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GEMINI_CLI_TRUST_WORKSPACE: true
           KEEP_OUTPUT: 'true'
           SANDBOX: 'sandbox:none'
           VERBOSE: 'true'
@@ -167,4 +175,4 @@ jobs:
           TEST_NAME_PATTERN: '${{ 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 +1,66 @@
+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'
+          persist-credentials: false
+
+      - 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'
+        env:
+          GEMINI_CLI_TRUST_WORKSPACE: true
+        with:
+          upload_artifacts: 'true'
+          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

@@ -19,12 +19,13 @@ 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'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Setup Pages'
         uses: 'actions/configure-pages@983d7736d9b0ae728b81ab479565c72886d7745b' # ratchet:actions/configure-pages@v5
@@ -39,6 +40,7 @@ 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 +1,211 @@
+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
+          persist-credentials: false
+
+      - 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: '${{ github.event.pull_request.head.sha }}'
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: 'Remove Approval Notification'
+        # Run even if other steps fail, to ensure we clean up the "Action Required" message
+        if: 'always()'
+        env:
+          GH_TOKEN: '${{ 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
@@ -23,10 +31,12 @@ 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:
         model:
+          - 'gemini-3.1-pro-preview-customtools'
           - 'gemini-3-pro-preview'
           - 'gemini-3-flash-preview'
           - 'gemini-2.5-pro'
@@ -36,6 +46,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Set up Node.js'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -56,12 +68,18 @@ jobs:
         continue-on-error: true
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GEMINI_CLI_TRUST_WORKSPACE: true
           GEMINI_MODEL: '${{ 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
@@ -84,11 +102,13 @@ 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'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Download Logs'
         uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4

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

@@ -48,6 +48,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Log in to GitHub Container Registry'
         uses: 'docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1' # ratchet:docker/login-action@v3
@@ -67,6 +69,7 @@ jobs:
           REPOSITORY: '${{ github.repository }}'
           FIRESTORE_PROJECT: '${{ vars.FIRESTORE_PROJECT }}'
         with:
+          upload_artifacts: 'true'
           gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
           gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
           gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -105,10 +108,12 @@ jobs:
                 }
               },
               "maxSessionTurns": 25,
-              "coreTools": [
-                "run_shell_command(echo)",
-                "run_shell_command(gh issue view)"
-              ],
+              "tools": {
+                "core": [
+                  "run_shell_command(echo)",
+                  "run_shell_command(gh issue view)"
+                ]
+              },
               "telemetry": {
                 "enabled": true,
                 "target": "gcp"

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

@@ -90,6 +90,8 @@ jobs:
 
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Generate GitHub App Token'
         id: 'generate_token'
@@ -121,6 +123,7 @@ jobs:
               'area/security',
               'area/platform',
               'area/extensions',
+              'area/documentation',
               'area/unknown'
             ];
             const labelNames = labels.map(label => label.name).filter(name => allowedLabels.includes(name));
@@ -133,15 +136,12 @@ jobs:
         id: 'gemini_issue_analysis'
         env:
           GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
-          ISSUE_TITLE: >-
-            ${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.title || github.event.issue.title }}
-          ISSUE_BODY: >-
-            ${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.body || github.event.issue.body }}
           ISSUE_NUMBER: >-
             ${{ github.event_name == 'workflow_dispatch' && (github.event.inputs.issue_number || inputs.issue_number) || github.event.issue.number }}
           REPOSITORY: '${{ github.repository }}'
           AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
         with:
+          upload_artifacts: 'true'
           gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
           gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
           gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -155,6 +155,9 @@ jobs:
               "telemetry": {
                 "enabled": true,
                 "target": "gcp"
+              },
+              "tools": {
+                "core": []
               }
             }
           prompt: |-
@@ -162,8 +165,15 @@ jobs:
 
             You are an issue triage assistant. Your role is to analyze a GitHub issue and determine the single most appropriate area/ label based on the definitions provided.
 
+            ## Issue Context
+            Title: ${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.title || github.event.issue.title }}
+            Body:
+            --- START OF ISSUE BODY ---
+            ${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.body || github.event.issue.body }}
+            --- END OF ISSUE BODY ---
+
             ## Steps
-            1. Review the issue title and body: ${{ env.ISSUE_TITLE }} and ${{ env.ISSUE_BODY }}.
+            1. Analyze the issue context above.
             2. Review the available labels: ${{ env.AVAILABLE_LABELS }}.
             3. Select exactly one area/ label that best matches the issue based on Reference 1: Area Definitions.
             4. Fallback Logic:
@@ -252,6 +262,14 @@ 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.
 
@@ -284,8 +302,21 @@ jobs:
                   return;
                 }
               } else {
-                core.setFailed(`Output is not valid JSON and does not contain a JSON markdown block.\nRaw output: ${rawOutput}`);
-                return;
+                // If no markdown block, try to find a raw JSON object in the output.
+                // The CLI may include debug/log lines (e.g. telemetry init, YOLO mode)
+                // before the actual JSON response.
+                const jsonObjectMatch = rawOutput.match(/(\{[\s\S]*"labels_to_set"[\s\S]*\})/);
+                if (jsonObjectMatch) {
+                  try {
+                    parsedLabels = JSON.parse(jsonObjectMatch[0]);
+                  } catch (extractError) {
+                    core.setFailed(`Found JSON-like content but failed to parse: ${extractError.message}\nRaw output: ${rawOutput}`);
+                    return;
+                  }
+                } else {
+                  core.setFailed(`Output is not valid JSON and does not contain extractable JSON.\nRaw output: ${rawOutput}`);
+                  return;
+                }
               }
             }
 
@@ -297,14 +328,41 @@ jobs:
               return;
             }
 
+            const newAreaLabel = labelsToAdd[0];
+
+            // Get current labels to resolve conflicts
+            const { data: currentLabels } = await github.rest.issues.listLabelsOnIssue({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: issueNumber,
+            });
+            const currentLabelNames = currentLabels.map(l => l.name);
+            const currentAreaLabels = currentLabelNames.filter(name => name.startsWith('area/'));
+
+            const labelsToRemove = currentAreaLabels.filter(name => name !== newAreaLabel);
+
+            for (const label of labelsToRemove) {
+              try {
+                await github.rest.issues.removeLabel({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  issue_number: issueNumber,
+                  name: label
+                });
+                core.info(`Removed conflicting area label: ${label}`);
+              } catch (e) {
+                core.warning(`Failed to remove label ${label}: ${e.message}`);
+              }
+            }
+
             // Set labels based on triage result
             await github.rest.issues.addLabels({
               owner: context.repo.owner,
               repo: context.repo.repo,
               issue_number: issueNumber,
-              labels: labelsToAdd
+              labels: [newAreaLabel]
             });
-            core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}`);
+            core.info(`Successfully added labels for #${issueNumber}: ${newAreaLabel}`);
 
       - name: 'Post Issue Analysis Failure Comment'
         if: |-

.github/workflows/gemini-cli-bot-brain.yml

@@ -0,0 +1,348 @@
+name: '🧠 Gemini CLI Bot: Brain'
+
+on:
+  schedule:
+    - cron: '0 0 * * *' # Every 24 hours
+  issue_comment:
+    types: ['created']
+  workflow_dispatch:
+    inputs:
+      run_interactive:
+        description: 'Run interactive flow (requires issue_number)'
+        type: 'boolean'
+        default: false
+      issue_number:
+        description: 'Issue/PR number to simulate context from'
+        type: 'string'
+        required: false
+      comment_id:
+        description: 'Specific comment ID to simulate'
+        type: 'string'
+        required: false
+      clear_memory:
+        description: 'Clear memory (drops learnings from previous runs)'
+        type: 'boolean'
+        default: false
+      enable_prs:
+        description: 'Enable PRs (automatically promote changes to PRs)'
+        type: 'boolean'
+        default: false
+
+concurrency:
+  group: '${{ github.workflow }}-${{ github.event.issue.number || github.event.inputs.issue_number || github.ref }}'
+  cancel-in-progress: true
+
+jobs:
+  reasoning:
+    name: 'Brain (Reasoning Layer)'
+    runs-on: 'ubuntu-latest'
+    if: |
+      github.repository == 'google-gemini/gemini-cli' && (
+        github.event_name == 'schedule' ||
+        (github.event_name == 'workflow_dispatch' && github.event.inputs.run_interactive != 'true') ||
+        (github.event_name == 'workflow_dispatch' && github.event.inputs.run_interactive == 'true') ||
+        (github.event_name == 'issue_comment' && github.event.comment.user.login != 'gemini-cli[bot]' && contains(github.event.comment.body, '@gemini-cli') && contains(fromJSON('["COLLABORATOR", "MEMBER", "OWNER"]'), github.event.comment.author_association))
+      )
+    # The reasoning phase is strictly readonly.
+    permissions:
+      contents: 'read'
+      issues: 'read'
+      actions: 'read'
+    steps:
+      - name: 'Determine Checkout Ref'
+        id: 'determine_ref'
+        env:
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+          ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
+        run: |
+          REF="${{ github.ref }}"
+          if [ -n "$ISSUE_NUMBER" ]; then
+            PR_HEAD=$(gh pr view "$ISSUE_NUMBER" --repo "${{ github.repository }}" --json headRefName --jq .headRefName 2>/dev/null || echo "")
+            if [ -n "$PR_HEAD" ]; then
+              REF="$PR_HEAD"
+            fi
+          fi
+          echo "ref=$REF" >> "$GITHUB_OUTPUT"
+
+      - name: 'Checkout'
+        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          ref: '${{ steps.determine_ref.outputs.ref }}'
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: 'Setup Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Build Gemini CLI'
+        run: 'npm run bundle'
+
+      - name: 'Download Previous State'
+        env:
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: |
+          if [ "${{ github.event.inputs.clear_memory }}" = "true" ]; then
+            echo "Memory clear requested. Skipping previous state download."
+            exit 0
+          fi
+
+          # Find the last successful run of this workflow
+          LAST_RUN_ID=$(gh run list --workflow "${{ github.workflow }}" --status success --limit 1 --json databaseId --jq '.[0].databaseId')
+
+          if [ -n "$LAST_RUN_ID" ]; then
+            echo "Found previous successful run: $LAST_RUN_ID"
+
+            # Download brain memory to a temp dir so we can selectively restore only persistent state
+            mkdir -p .temp_brain_data
+            gh run download "$LAST_RUN_ID" -n brain-data -D .temp_brain_data || echo "brain-data not found"
+
+            # Restore only persistent memory files
+            cp .temp_brain_data/tools/gemini-cli-bot/lessons-learned.md tools/gemini-cli-bot/lessons-learned.md 2>/dev/null || true
+            mkdir -p tools/gemini-cli-bot/history/
+            cp .temp_brain_data/tools/gemini-cli-bot/history/*.csv tools/gemini-cli-bot/history/ 2>/dev/null || true
+            rm -rf .temp_brain_data
+          else
+            echo "No previous successful run found."
+          fi
+
+      - name: 'Collect Current Metrics'
+        env:
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: 'npx tsx tools/gemini-cli-bot/metrics/index.ts'
+
+      - name: 'Run Brain Phases'
+        env:
+          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+          GEMINI_MODEL: 'gemini-3-flash-preview'
+          GEMINI_CLI_HOME: 'tools/gemini-cli-bot'
+          ENABLE_PRS: "${{ github.event.inputs.enable_prs || 'false' }}"
+          TRIGGER_ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
+          TRIGGER_COMMENT_ID: '${{ github.event.comment.id || github.event.inputs.comment_id }}'
+        run: |
+          PROMPT_PATH="tools/gemini-cli-bot/brain/scheduled.md"
+          if [ "${{ github.event_name }}" = "issue_comment" ] || [ "${{ github.event.inputs.run_interactive }}" = "true" ]; then
+            PROMPT_PATH="tools/gemini-cli-bot/brain/interactive.md"
+            export ENABLE_PRS="true"
+          fi
+
+          touch trigger_context.md
+          if [ -n "$TRIGGER_ISSUE_NUMBER" ]; then
+            echo "<untrusted_context>" > trigger_context.md
+            echo "# Interactive Trigger Context" >> trigger_context.md
+            echo "You were invoked by a user in issue/PR #$TRIGGER_ISSUE_NUMBER." >> trigger_context.md
+
+            if [ -n "$TRIGGER_COMMENT_ID" ]; then
+              echo "## User Comment" >> trigger_context.md
+              gh api "repos/${{ github.repository }}/issues/comments/$TRIGGER_COMMENT_ID" -q '.body' >> trigger_context.md 2>/dev/null || gh api "repos/${{ github.repository }}/pulls/comments/$TRIGGER_COMMENT_ID" -q '.body' >> trigger_context.md
+              echo "" >> trigger_context.md
+            fi
+
+            echo "## Issue/PR Context" >> trigger_context.md
+            gh issue view "$TRIGGER_ISSUE_NUMBER" >> trigger_context.md 2>/dev/null || gh pr view "$TRIGGER_ISSUE_NUMBER" >> trigger_context.md
+            echo "</untrusted_context>" >> trigger_context.md
+          fi
+
+          if [ "$ENABLE_PRS" = "true" ]; then
+            echo "**System Directive**: PR creation is ENABLED for this run. You MUST activate the **'prs' skill** to stage your changes and generate a \`pr-description.md\` file if you are proposing fixes." >> trigger_context.md
+            echo "**CRITICAL System Directive**: You MUST ONLY propose and implement a **SINGLE** improvement or fix per run. Bundling unrelated changes (e.g., a documentation update and a script fix, or a metrics update and a logic fix) into a single PR is STRICTLY FORBIDDEN and will result in immediate rejection during the critique phase. If you identify multiple issues, pick the most impactful one and ignore the others for now." >> trigger_context.md
+          else
+            echo "**System Directive**: PR creation is DISABLED for this run. You MUST NOT stage files or attempt to create a PR description." >> trigger_context.md
+          fi
+          echo "" >> trigger_context.md
+
+          cat trigger_context.md "$PROMPT_PATH" > combined_prompt.md
+          node bundle/gemini.js --policy tools/gemini-cli-bot/ci-policy.toml --prompt="$(cat combined_prompt.md)"
+
+          if [ -n "$TRIGGER_ISSUE_NUMBER" ] && [ ! -s "issue-comment.md" ] && [ ! -s "pr-comment.md" ]; then
+            echo "Agent failed to respond. Generating fallback error message."
+            echo "⚠️ **Gemini CLI Bot failed to generate a response.**" > "issue-comment.md"
+            echo "" >> "issue-comment.md"
+            echo "I encountered an error or failed to generate a complete response to your request. You can check the [GitHub Actions Run Log](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}) for more details on what went wrong." >> "issue-comment.md"
+          fi
+
+      - name: 'Run Critique Phase'
+        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
+        env:
+          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+          GEMINI_MODEL: 'gemini-3-flash-preview'
+          GEMINI_CLI_HOME: 'tools/gemini-cli-bot'
+        run: |
+          if git diff --staged --quiet; then
+             echo "No changes staged. Skipping critique."
+             echo "[APPROVED]" > critique_result.txt
+          else
+             node bundle/gemini.js --policy tools/gemini-cli-bot/ci-policy.toml --prompt="$(cat tools/gemini-cli-bot/.gemini/skills/critique/SKILL.md)" 2>&1 | tee critique_output.log
+
+             if [ "${PIPESTATUS[0]}" -eq 0 ] && grep -q "\[APPROVED\]" critique_output.log && ! grep -q "\[REJECTED\]" critique_output.log; then
+               echo "[APPROVED]" > critique_result.txt
+             else
+               echo "Critique failed, rejected, or did not explicitly approve changes. Skipping PR creation."
+               echo "[REJECTED]" > critique_result.txt
+             fi
+          fi
+
+      - name: 'Generate Patch'
+        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
+        run: |
+          touch bot-changes.patch
+          touch pr-description.md
+          if [ -f critique_result.txt ] && grep -q "\[APPROVED\]" critique_result.txt && ! grep -q "\[REJECTED\]" critique_result.txt; then
+             git diff --staged > bot-changes.patch
+          else
+             echo "Critique did not approve. Skipping patch generation."
+          fi
+
+      - name: 'Archive Brain Data'
+        uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
+        with:
+          name: 'brain-data'
+          path: |
+            tools/gemini-cli-bot/lessons-learned.md
+            tools/gemini-cli-bot/history/*.csv
+            bot-changes.patch
+            pr-description.md
+            branch-name.txt
+            pr-comment.md
+            pr-number.txt
+            issue-comment.md
+          retention-days: 90
+
+  publish:
+    name: 'Publish Artifacts (Archive Layer)'
+    needs: 'reasoning'
+    runs-on: 'ubuntu-latest'
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    # The publish phase is for archiving artifacts and optionally creating PRs.
+    permissions:
+      contents: 'write'
+      pull-requests: 'write'
+      actions: 'write'
+    steps:
+      - name: 'Generate GitHub App Token 🔑'
+        id: 'generate_token'
+        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
+        uses: 'actions/create-github-app-token@a8d616148505b5069dccd32f177bb87d7f39123b' # ratchet:actions/create-github-app-token@v2
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+          owner: '${{ github.repository_owner }}'
+          repositories: '${{ github.event.repository.name }}'
+          permission-contents: 'write'
+          permission-pull-requests: 'write'
+          permission-issues: 'write'
+
+      - name: 'Determine Checkout Ref'
+        id: 'determine_ref'
+        env:
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+          ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
+        run: |
+          REF="main"
+          if [ -n "$ISSUE_NUMBER" ]; then
+            PR_HEAD=$(gh pr view "$ISSUE_NUMBER" --repo "${{ github.repository }}" --json headRefName --jq .headRefName 2>/dev/null || echo "")
+            if [ -n "$PR_HEAD" ]; then
+              REF="$PR_HEAD"
+            fi
+          fi
+          echo "ref=$REF" >> "$GITHUB_OUTPUT"
+
+      - name: 'Checkout'
+        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          ref: '${{ steps.determine_ref.outputs.ref }}'
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: 'Download Brain Data'
+        uses: 'actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093' # ratchet:actions/download-artifact@v4
+        with:
+          name: 'brain-data'
+          path: '${{ runner.temp }}/brain-data/'
+
+      - name: 'Create or Update PR'
+        if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
+        env:
+          GH_TOKEN: '${{ steps.generate_token.outputs.token }}'
+          FALLBACK_PAT: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
+        run: |
+          if [ -s "${{ runner.temp }}/brain-data/bot-changes.patch" ]; then
+            git config user.name "gemini-cli[bot]"
+            git config user.email "gemini-cli[bot]@users.noreply.github.com"
+            git remote set-url origin "https://x-access-token:${GH_TOKEN}@github.com/${{ github.repository }}.git"
+
+            BRANCH_NAME="bot/productivity-updates-$(date +'%Y%m%d%H%M%S')-${{ github.run_id }}"
+            if [ -f "${{ runner.temp }}/brain-data/branch-name.txt" ]; then
+              BRANCH_NAME=$(cat "${{ runner.temp }}/brain-data/branch-name.txt")
+            fi
+
+            if [[ ! "$BRANCH_NAME" =~ ^bot/ ]]; then
+              echo "Error: Branch name '$BRANCH_NAME' does not start with 'bot/'. Safety abort."
+              exit 1
+            fi
+
+            git checkout -B "$BRANCH_NAME"
+            git apply "${{ runner.temp }}/brain-data/bot-changes.patch"
+            git add .
+
+            if [ -s "${{ runner.temp }}/brain-data/pr-description.md" ]; then
+              git commit -F "${{ runner.temp }}/brain-data/pr-description.md"
+            else
+              git commit -m "🤖 Gemini Bot Productivity Optimizations"
+            fi
+
+            PR_TITLE="🤖 Gemini Bot Productivity Optimizations"
+            if [ -s "${{ runner.temp }}/brain-data/pr-description.md" ]; then
+              PR_TITLE=$(head -n 1 "${{ runner.temp }}/brain-data/pr-description.md")
+            fi
+
+            if ! git push origin "$BRANCH_NAME" --force; then
+              echo "Push failed. Retrying with FALLBACK_PAT..."
+              export GH_TOKEN="$FALLBACK_PAT"
+              git remote set-url origin "https://x-access-token:${FALLBACK_PAT}@github.com/${{ github.repository }}.git"
+              git push origin "$BRANCH_NAME" --force
+            fi
+
+            if ! gh pr view "$BRANCH_NAME" > /dev/null 2>&1; then
+              gh pr create --draft --title "$PR_TITLE" --body-file "${{ runner.temp }}/brain-data/pr-description.md" --head "$BRANCH_NAME" --base main || \
+              gh pr create --draft --title "🤖 Gemini Bot Productivity Optimizations" --body "Automated changes generated by Gemini CLI Bot." --head "$BRANCH_NAME" --base main
+            else
+              PR_STATE=$(gh pr view "$BRANCH_NAME" --json state --jq .state)
+              if [ "$PR_STATE" = "CLOSED" ]; then
+                NEW_BRANCH_NAME="${BRANCH_NAME}-retry-${{ github.run_id }}"
+                git checkout -b "$NEW_BRANCH_NAME"
+                git push origin "$NEW_BRANCH_NAME" --force
+                gh pr create --draft --title "$PR_TITLE" --body-file "${{ runner.temp }}/brain-data/pr-description.md" --head "$NEW_BRANCH_NAME" --base main || \
+                gh pr create --draft --title "🤖 Gemini Bot Productivity Optimizations" --body "Automated changes generated by Gemini CLI Bot." --head "$NEW_BRANCH_NAME" --base main
+              fi
+            fi
+          fi
+
+      - name: 'Post PR/Issue Comment'
+        env:
+          GH_TOKEN: '${{ steps.generate_token.outputs.token }}'
+          TRIGGER_ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
+        run: |
+          if [ -s "${{ runner.temp }}/brain-data/issue-comment.md" ] && [ -n "$TRIGGER_ISSUE_NUMBER" ]; then
+            echo "Posting comment to triggering issue #$TRIGGER_ISSUE_NUMBER"
+            # Use REST API (gh api) instead of GraphQL (gh issue comment) to ensure robot identity
+            # while avoiding potential GraphQL-specific authorization hurdles with PATs.
+            gh api "repos/${{ github.repository }}/issues/$TRIGGER_ISSUE_NUMBER/comments" -F body=@"${{ runner.temp }}/brain-data/issue-comment.md"
+          fi
+
+          if [ -s "${{ runner.temp }}/brain-data/pr-comment.md" ] && [ -f "${{ runner.temp }}/brain-data/pr-number.txt" ]; then
+            PR_NUM=$(cat "${{ runner.temp }}/brain-data/pr-number.txt")
+
+            # Using GitHub App, so author check is no longer valid against gemini-cli-robot
+            # Skipping author validation here to let the app post.
+
+            # Use REST API (gh api) for consistency and robot identity
+            gh api "repos/${{ github.repository }}/issues/$PR_NUM/comments" -F body=@"${{ runner.temp }}/brain-data/pr-comment.md"
+          fi

.github/workflows/gemini-cli-bot-pulse.yml

@@ -0,0 +1,49 @@
+name: '🔄 Gemini CLI Bot: Pulse'
+
+on:
+  schedule:
+    - cron: '*/30 * * * *' # Every 30 minutes
+  workflow_dispatch:
+
+concurrency:
+  group: '${{ github.workflow }}-${{ github.ref }}'
+  cancel-in-progress: true
+
+permissions:
+  contents: 'write'
+  issues: 'write'
+  pull-requests: 'write'
+
+jobs:
+  pulse:
+    name: 'Pulse (Reflex Layer)'
+    runs-on: 'ubuntu-latest'
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
+          fetch-depth: 0
+
+      - name: 'Setup Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Run Reflex Processes'
+        env:
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: |
+          if [ -d "tools/gemini-cli-bot/reflexes/scripts" ] && [ "$(ls -A tools/gemini-cli-bot/reflexes/scripts)" ]; then
+            for script in tools/gemini-cli-bot/reflexes/scripts/*.ts; do
+              echo "Running reflex script: $script"
+              npx tsx "$script"
+            done
+          else
+            echo "No reflex scripts found."
+          fi

.github/workflows/gemini-lifecycle-manager.yml

@@ -0,0 +1,47 @@
+name: '🔄 Gemini Scheduled Lifecycle Manager'
+
+on:
+  schedule:
+    - cron: '30 1 * * *' # Once a day
+  workflow_dispatch:
+    inputs:
+      dry_run:
+        description: 'Run in dry-run mode (no changes applied)'
+        required: false
+        default: false
+        type: 'boolean'
+
+concurrency:
+  group: '${{ github.workflow }}'
+  cancel-in-progress: true
+
+permissions:
+  issues: 'write'
+  pull-requests: 'write'
+
+jobs:
+  manage-lifecycle:
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    runs-on: 'ubuntu-latest'
+    steps:
+      - name: 'Generate GitHub App Token'
+        id: 'generate_token'
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+
+      - name: 'Checkout repository'
+        uses: 'actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683' # ratchet:actions/checkout@v4
+        with:
+          persist-credentials: false
+
+      - name: 'Lifecycle Management'
+        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
+        env:
+          DRY_RUN: '${{ inputs.dry_run }}'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token }}'
+          script: |
+            const script = require('./.github/scripts/gemini-lifecycle-manager.cjs');
+            await script({github, context, core});

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

@@ -28,6 +28,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Log in to GitHub Container Registry'
         uses: 'docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1' # ratchet:docker/login-action@v3
@@ -47,6 +49,7 @@ jobs:
           REPOSITORY: '${{ github.repository }}'
           FIRESTORE_PROJECT: '${{ vars.FIRESTORE_PROJECT }}'
         with:
+          upload_artifacts: 'true'
           gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
           gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
           gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -85,9 +88,11 @@ jobs:
                 }
               },
               "maxSessionTurns": 25,
-              "coreTools": [
-                "run_shell_command(echo)"
-              ],
+              "tools": {
+                "core": [
+                  "run_shell_command(echo)"
+                ]
+              },
               "telemetry": {
                 "enabled": true,
                 "target": "gcp"

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

@@ -1,10 +1,6 @@
 name: '📋 Gemini Scheduled Issue Triage'
 
 on:
-  issues:
-    types:
-      - 'opened'
-      - 'reopened'
   schedule:
     - cron: '0 * * * *' # Runs every hour
   workflow_dispatch:
@@ -23,13 +19,27 @@ permissions:
 
 jobs:
   triage-issues:
-    timeout-minutes: 10
+    timeout-minutes: 60
     if: |-
       ${{ github.repository == 'google-gemini/gemini-cli' }}
     runs-on: 'ubuntu-latest'
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
+
+      - name: 'Install Utilities'
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y ripgrep
+
+      - name: 'Get Current Version'
+        id: 'get_version'
+        run: |
+          VERSION=$(jq -r .version package.json | cut -d'-' -f1)
+          echo "version=${VERSION}" >> "${GITHUB_OUTPUT}"
+          echo "🚀 Current CLI Version: ${VERSION}"
 
       - name: 'Generate GitHub App Token'
         id: 'generate_token'
@@ -47,10 +57,38 @@ jobs:
           ISSUE_EVENT: '${{ toJSON(github.event.issue) }}'
         run: |
           set -euo pipefail
-          ISSUE_JSON=$(echo "$ISSUE_EVENT" | jq -c '[{number: .number, title: .title, body: .body}]')
-          echo "issues_to_triage=${ISSUE_JSON}" >> "${GITHUB_OUTPUT}"
+          echo "$ISSUE_EVENT" | jq -c '[{number: .number, title: .title, body: .body}]' > issues_to_triage.json
+          echo "has_issues=true" >> "${GITHUB_OUTPUT}"
           echo "✅ Found issue #${{ github.event.issue.number }} from event to triage! 🎯"
 
+      - name: 'Sync Issue Types'
+        if: |-
+          ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
+        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token }}'
+          script: |-
+            const syncIssueTypes = require('./.github/scripts/sync-issue-types.cjs');
+            await syncIssueTypes({ github, context, core });
+
+      - name: 'Find Issues with Conflicting Labels'
+        if: |-
+          ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
+        env:
+          GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
+          GITHUB_REPOSITORY: '${{ github.repository }}'
+        run: |-
+          set -euo pipefail
+          echo '🔍 Fetching open issues to find conflicts...'
+          # Fetch up to 2000 open issues in one quick GraphQL-backed query
+          gh issue list --repo "${GITHUB_REPOSITORY}" --search "is:issue is:open" --limit 2000 --json number,title,body,labels > all_open_issues.json
+
+          echo '🧹 Filtering issues with multiple area/ or priority/ labels...'
+          jq -c '[ .[] | select( (.labels | map(select(.name | startswith("area/"))) | length) > 1 or (.labels | map(select(.name | startswith("priority/"))) | length) > 1 ) ] | .[0:50]' all_open_issues.json > conflicting_labels_issues.json
+
+          CONFLICT_COUNT=$(jq 'length' conflicting_labels_issues.json)
+          echo "Found ${CONFLICT_COUNT} issues with conflicting labels (capped at 50 for processing)."
+
       - name: 'Find untriaged issues'
         if: |-
           ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
@@ -62,25 +100,56 @@ jobs:
           set -euo pipefail
 
           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)"
+          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/documentation -label:area/unknown' --limit 50 --json number,title,body,labels > no_area_issues.json
 
           echo '🔍 Finding issues missing kind labels...'
-          NO_KIND_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue -label:kind/bug -label:kind/enhancement -label:kind/customer-issue -label:kind/question' --limit 100 --json number,title,body)"
+          gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue -label:kind/bug -label:kind/enhancement -label:kind/customer-issue -label:kind/question' --limit 50 --json number,title,body,labels > no_kind_issues.json
 
           echo '🏷️ Finding issues missing priority labels...'
-          NO_PRIORITY_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue -label:priority/p0 -label:priority/p1 -label:priority/p2 -label:priority/p3 -label:priority/unknown' --limit 100 --json number,title,body)"
+          gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue -label:priority/p0 -label:priority/p1 -label:priority/p2 -label:priority/p3 -label:priority/unknown' --limit 50 --json number,title,body,labels > no_priority_issues.json
 
-          echo '🔄 Merging and deduplicating issues...'
-          ISSUES="$(echo "${NO_AREA_ISSUES}" "${NO_KIND_ISSUES}" "${NO_PRIORITY_ISSUES}" | jq -c -s 'add | unique_by(.number)')"
+          echo '📏 Finding issues missing effort labels...'
+          gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue -label:effort/small -label:effort/medium -label:effort/large label:area/core,area/extensions,area/site,area/non-interactive' --limit 20 --json number,title,body,labels > no_effort_issues.json
 
-          echo '📝 Setting output for GitHub Actions...'
-          echo "issues_to_triage=${ISSUES}" >> "${GITHUB_OUTPUT}"
+          echo '🔄 Merging and deduplicating standard triage issues...'
+          if [ ! -f conflicting_labels_issues.json ]; then echo "[]" > conflicting_labels_issues.json; fi
+          jq -c -s 'add | unique_by(.number)' no_area_issues.json no_kind_issues.json no_priority_issues.json conflicting_labels_issues.json > standard_issues_to_triage.json
 
-          ISSUE_COUNT="$(echo "${ISSUES}" | jq 'length')"
-          echo "✅ Found ${ISSUE_COUNT} unique issues to triage! 🎯"
+          echo '📏 Deduplicating effort issues...'
+          jq -c -s 'add | unique_by(.number)' no_effort_issues.json > effort_issues_to_triage.json
+
+          STANDARD_COUNT="$(jq 'length' standard_issues_to_triage.json)"
+          EFFORT_COUNT="$(jq 'length' effort_issues_to_triage.json)"
+          if [ "$STANDARD_COUNT" -gt 0 ] || [ "$EFFORT_COUNT" -gt 0 ]; then
+            echo "has_issues=true" >> "${GITHUB_OUTPUT}"
+            echo "has_standard_issues=$([ "$STANDARD_COUNT" -gt 0 ] && echo 'true' || echo 'false')" >> "${GITHUB_OUTPUT}"
+            echo "has_effort_issues=$([ "$EFFORT_COUNT" -gt 0 ] && echo 'true' || echo 'false')" >> "${GITHUB_OUTPUT}"
+          else
+            echo "has_issues=false" >> "${GITHUB_OUTPUT}"
+            echo "has_standard_issues=false" >> "${GITHUB_OUTPUT}"
+            echo "has_effort_issues=false" >> "${GITHUB_OUTPUT}"
+          fi
+          echo "✅ Found ${STANDARD_COUNT} standard issues and ${EFFORT_COUNT} effort issues to triage! 🎯"
+
+      - name: 'Create Gemini CLI Experiments Override'
+        if: |-
+          steps.get_issue_from_event.outputs.has_issues == 'true' || steps.find_issues.outputs.has_issues == 'true'
+        run: |
+          cat << 'EOF' > gemini_exp.json
+          {
+            "flags": [
+              {
+                "flagId": 45750526,
+                "boolValue": false
+              }
+            ],
+            "experimentIds": []
+          }
+          EOF
 
       - name: 'Get Repository Labels'
         id: 'get_labels'
@@ -97,18 +166,21 @@ jobs:
             core.info(`Found ${labelNames.length} labels: ${labelNames.join(', ')}`);
             return labelNames;
 
-      - name: 'Run Gemini Issue Analysis'
+      - name: 'Run Standard Triage Analysis'
         if: |-
-          (steps.get_issue_from_event.outputs.issues_to_triage != '' && steps.get_issue_from_event.outputs.issues_to_triage != '[]') ||
-          (steps.find_issues.outputs.issues_to_triage != '' && steps.find_issues.outputs.issues_to_triage != '[]')
+          steps.get_issue_from_event.outputs.has_issues == 'true' || steps.find_issues.outputs.has_standard_issues == 'true'
         uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
-        id: 'gemini_issue_analysis'
+        id: 'gemini_standard_issue_analysis'
         env:
           GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
-          ISSUES_TO_TRIAGE: '${{ steps.get_issue_from_event.outputs.issues_to_triage || steps.find_issues.outputs.issues_to_triage }}'
           REPOSITORY: '${{ github.repository }}'
           AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
+          CLI_VERSION: '${{ steps.get_version.outputs.version }}'
+          GEMINI_EXP: 'gemini_exp.json'
+          GEMINI_STRICT_TELEMETRY_LIMITS: 'true'
+          GEMINI_MODEL: 'gemini-3-flash-preview'
         with:
+          upload_artifacts: 'true'
           gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
           gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
           gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -119,11 +191,14 @@ jobs:
           settings: |-
             {
               "maxSessionTurns": 25,
-              "coreTools": [
-                "run_shell_command(echo)"
-              ],
+              "tools": {
+                "core": [
+                  "run_shell_command(echo)",
+                  "read_file"
+                ]
+              },
               "telemetry": {
-                "enabled": true,
+                "enabled": false,
                 "target": "gcp"
               }
             }
@@ -136,14 +211,16 @@ jobs:
 
             ## Steps
 
-            1. You are only able to use the echo command. Review the available labels in the environment variable: "${AVAILABLE_LABELS}".
-            2. Check environment variable for issues to triage: $ISSUES_TO_TRIAGE (JSON array of issues)
-            3. Review the issue title, body and any comments provided in the environment variables.
-            4. Identify the most relevant labels from the existing labels, specifically focusing on area/*, kind/* and priority/*.
+            1. You are only able to use the echo and read_file commands. Review the available labels in the environment variable: "${AVAILABLE_LABELS}".
+            2. Use the read_file tool to read the file "standard_issues_to_triage.json" which contains the JSON array of issues to triage (including their current labels).
+            3. Review the issue title, body, current labels, and any comments provided in the JSON file.
+            4. Identify the most relevant labels from the existing labels, specifically focusing on area/*, kind/*, and priority/*.
             5. Label Policy:
                - If the issue already has a kind/ label, do not change it.
-               - If the issue already has a priority/ label, do not change it.
-               - If the issue already has an area/ label, do not change it.
+               - If the issue has exactly ONE priority/ label, do not change it (unless you are explicitly re-evaluating an ambiguous priority).
+               - If the issue is missing a priority/ label, OR if the issue currently has MULTIPLE priority/ labels, you must evaluate the issue's impact to determine exactly ONE priority level (priority/p0, priority/p1, priority/p2, priority/p3, or priority/unknown) based the guidelines. If you are fixing an issue with multiple priority/ labels, put the correct one in `labels_to_add` and put all the incorrect ones in `labels_to_remove`.
+               - If the issue has exactly ONE area/ label, do not change it.
+               - If the issue is missing an area/ label, OR if the issue currently has MULTIPLE area/ labels, select exactly ONE area/ label that best fits the issue. Issues MUST NOT have multiple area/ labels. If you are fixing an issue with multiple area/ labels, put the correct one in `labels_to_add` and put all the incorrect ones in `labels_to_remove`.
                - If any of these are missing, select exactly ONE appropriate label for the missing category.
             6. Identify other applicable labels based on the issue content, such as status/*, help wanted, good first issue, etc.
             7. Give me a single short explanation about why you are selecting each label in the process.
@@ -160,11 +237,12 @@ jobs:
                ]
                ```
               If an issue cannot be classified, do not include it in the output array.
-            9. For each issue please check if CLI version is present, this is usually in the output of the /about command and will look like 0.1.5
-              - Anything more than 6 versions older than the most recent should add the status/need-retesting label
-            10. If you see that the issue doesn't look like it has sufficient information recommend the status/need-information label and leave a comment politely requesting the relevant information, eg.. if repro steps are missing request for repro steps. if version information is missing request for version information into the explanation section below.
-            11. If you think an issue might be a Priority/P0 do not apply the priority/p0 label. Instead apply a status/manual-triage label and include a note in your explanation.
-            12. If you are uncertain about a category, use the area/unknown, kind/question, or priority/unknown labels as appropriate. If you are extremely uncertain, apply the status/manual-triage label.
+            9. For each issue, carefully check if the CLI version is present. It is usually found under the "### Client information" header, as a bullet point (e.g., "• CLI Version: 0.33.1", "* **CLI Version:** 0.42.0"), or in the output of the `/about` command.
+              - **Only for issues classified as kind/bug:** If the version is provided but is more than 6 minor versions older than the most recent release (current version is ${{ steps.get_version.outputs.version }}), apply the status/need-information label and leave a comment politely asking the user to verify if the issue persists in the latest version.
+            10. **Only for issues classified as kind/bug:** If the issue does not have sufficient information, recommend the status/need-information label and leave a comment politely requesting the missing details. For example, if repro steps are missing, ask for them; if the CLI version is completely missing, ask for the version information in the explanation section below. Do not ask for version info if it is already in the issue body. (Check both bullet points and bold text). For features and enhancements, the CLI version is NOT required.
+            11. If you think an issue is a Priority/P0, you MUST apply the priority/p1 label AND the status/manual-triage label, and include a note in your explanation that it likely requires P0 escalation.
+            12. If the issue is highly ambiguous, completely lacks a description, or you are torn between two lower priorities (like P2 vs P3), you MUST retain the existing priority label if one is already present. Do not toggle the priority if you do not have enough information to make a definitive change.
+            13. If you are uncertain about a category, use the area/unknown, kind/question, or priority/unknown labels as appropriate. If you are extremely uncertain, apply the status/manual-triage label.
 
             ## Guidelines
 
@@ -174,10 +252,126 @@ jobs:
               - Do not add comments or modify the issue content.
               - Do not remove the following labels maintainer, help wanted or good first issue.
               - Triage only the current issue.
-              - Identify only one area/ label.
+              - Identify exactly ONE area/ label. Do NOT assign multiple area/ labels to a single issue.
               - Identify only one kind/ label (Do not apply kind/duplicate or kind/parent-issue)
-              - Identify only one priority/ label.
-              - Once you categorize the issue if it needs information bump down the priority by 1 eg.. a p0 would become a p1 a p1 would become a p2. P2 and P3 can stay as is in this scenario.
+              - Identify exactly ONE priority/ label. Do NOT assign multiple priority/ labels to a single issue.
+              - **Do not manually downgrade the priority.** Always assign the true priority based on the guidelines. The system will handle downgrades programmatically if information is missing.
+              - **NEVER mention label names, label removals, or label additions in your `explanation`.** The explanation must be purely written for the user (e.g., "Please provide your CLI version.") without exposing internal triage mechanics (e.g., do NOT say "Removing area/unknown to leave only area/core").
+
+            Categorization Guidelines (Priority):
+            P0 - Urgent Blocking Issues:
+              - DO NOT APPLY THE priority/p0 LABEL AUTOMATICALLY. Instead apply priority/p1 and status/manual-triage.
+              - Definition: Critical failures breaking core functionality for a large portion of users. Examples: CLI fails to launch globally, core commands (gemini run) crash on valid input, unhandled promise rejections on boot, critical security vulnerability.
+              - Note: You must apply priority/p1 and status/manual-triage instead of priority/p0.
+            P1 - Critical but Workable:
+              - Definition: Severe issues without a reasonable workaround, significantly degrading the developer experience but not globally blocking. Examples: Specific tools failing consistently (e.g., `web_search` returns 500s), persistent PTY streaming hangs, memory leaks leading to OOM after short use.
+            P2 - Significant Issues:
+              - Definition: Affect some workflows but a clear workaround exists, or non-critical bugs. Examples: Theme flickering, confusing error messages, minor UI misalignment, failing to read deeply nested config files correctly.
+            P3 - Minor/Enhancements:
+              - Definition: Trivial bugs, typos, documentation requests, or feature requests.
+
+            Categorization Guidelines (Kind):
+            kind/bug: The issue is describing an unexpected behavior or failure in the application.
+            kind/enhancement: The issue is describing a feature request or an improvement to an existing feature.
+            kind/question: The issue is asking a question about how to use the CLI or about a specific feature.
+
+            Categorization Guidelines (Area):
+            area/agent: The "brain" of the CLI. Core agent logic, model quality, tool/function calling, memory, web search, generated code quality, sub-agents.
+            area/core: The fundamental CLI app. UI/UX, installation, OS compatibility, performance, command parsing, theming, flickering.
+            area/documentation: Website docs, READMEs, inline help text.
+            area/enterprise: Telemetry, Policy, Quota / Licensing
+            area/extensions: Gemini CLI extensions capability
+            area/non-interactive: GitHub Actions, SDK, 3P Integrations, Shell Scripting, Command line automation
+            area/platform: Platform specific behavior
+            area/security: Authentication, authorization, privacy, data leaks, credential storage.
+
+      - name: 'Stop Telemetry Collector'
+        if: |-
+          steps.find_issues.outputs.has_effort_issues == 'true'
+        run: 'docker rm -f gemini-telemetry-collector || true'
+
+      - name: 'Run Effort Triage Analysis'
+        if: |-
+          steps.find_issues.outputs.has_effort_issues == 'true'
+        uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
+        id: 'gemini_effort_issue_analysis'
+        env:
+          GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
+          REPOSITORY: '${{ github.repository }}'
+          AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
+          CLI_VERSION: '${{ steps.get_version.outputs.version }}'
+          GEMINI_EXP: 'gemini_exp.json'
+          GEMINI_STRICT_TELEMETRY_LIMITS: 'true'
+          GEMINI_MODEL: 'gemini-3-flash-preview'
+        with:
+          upload_artifacts: 'true'
+          gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
+          gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
+          gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
+          gcp_service_account: '${{ vars.SERVICE_ACCOUNT_EMAIL }}'
+          gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
+          use_vertex_ai: '${{ vars.GOOGLE_GENAI_USE_VERTEXAI }}'
+          use_gemini_code_assist: '${{ vars.GOOGLE_GENAI_USE_GCA }}'
+          settings: |-
+            {
+              "maxSessionTurns": 30,
+              "tools": {
+                "core": [
+                  "run_shell_command(echo)",
+                  "grep_search",
+                  "glob",
+                  "read_file"
+                ]
+              },
+              "telemetry": {
+                "enabled": false,
+                "target": "gcp"
+              }
+            }
+          prompt: |-
+            ## Role
+
+            You are an expert software architect. Analyze the provided GitHub issues and assign the correct `effort/*` label based on the codebase complexity.
+
+            ## Steps
+
+            1. Use the read_file tool to read "effort_issues_to_triage.json".
+            2. For each issue in the array:
+               - You must evaluate the architectural complexity to determine the effort level. You MUST NOT guess the root cause. You MUST actively use your codebase search tools (grep_search and glob) to search for keywords from the issue and explore the codebase. You must identify the specific files and components involved before deciding the effort.
+            3. Output a JSON array of objects, each containing the issue number and the effort label to add, along with an explanation and an effort_analysis field. This effort_analysis must be highly detailed, technical, and empirical. It MUST NOT contain vague guesses (e.g., avoid words like "likely points to" or "possibly"). You must explicitly cite the specific file paths and architectural mechanisms you discovered using your search tools, explain the root cause, and then explicitly state how that complexity maps to the chosen effort level guidelines. For example:
+               ```
+               [
+                 {
+                   "issue_number": 123,
+                   "labels_to_add": ["effort/small"],
+                   "explanation": "This is a simple logic fix.",
+                   "effort_analysis": "The `vscode-ide-companion` extension indiscriminately tracks active text editors via `vscode.window.onDidChangeActiveTextEditor` in `open-files-manager.ts`. When a user opens `.vscode/settings.json`, its content is sent to the CLI's context. The fix is highly localized to the VS Code companion extension's event listener. It involves adding a simple conditional check to exclude specific configuration files from the active editor tracking logic, which is a trivial logic adjustment with a clear root cause."
+                 }
+               ]
+               ```
+
+            ## Guidelines
+
+            - Output only valid JSON format
+            - Do not include any explanation or additional text, just the JSON
+            - Triage only the current issue.
+
+            Categorization Guidelines (Effort):
+            effort/small (1 day or less):
+              - Trivial Logic & Config: Schema updates (Zod), feature flag toggles, adding missing fields to package.json or settings.json.
+              - UI/Aesthetic Adjustments: Fixing minor layout bugs in Ink components (e.g., adding flexShrink, correcting padding in a single Box), text color changes.
+              - Documentation & Strings: Typos, log message updates, CLI argument descriptions.
+              - Localized Bug Fixes: Single-file logic errors, straightforward promise rejections (e.g., wrapping a known failure in a try/catch), simple regex or string parsing fixes.
+            effort/medium (2-3 days):
+              - React/Ink State Management: Debugging useState/useEffect/useReducer bugs, component lifecycle issues (memory leaks in the UI), terminal redraw flickering, or state synchronization between the CLI's internal input buffer and the interactive React components.
+              - Asynchronous Flow & Integration: Resolving complex Promise chains, ERR_STREAM_PREMATURE_CLOSE, debugging IDE companion extensions (VS Code, Android Studio) or resolving hanging HTTP requests/IPC between the CLI and external plugins, timeouts in non-interactive/ACP modes.
+              - Tooling & Output Parsers: Modifying how tools parse streaming stdout/stderr buffers, adding new built-in tools that don't require native bindings.
+              - Cross-Component Refactors: Changes that span across packages/cli and packages/core to pass new data models or telemetry state.
+            effort/large (3+ days):
+              - Platform-Specific Complexities (PTY/Signals): Any issue involving node-pty, child_process.spawn, OS-level shell behavior (Windows vs Linux vs macOS), pseudo-terminal exhaustion (ENXIO), raw mode terminal desyncs, or POSIX signal forwarding (SIGINT/SIGTERM).
+              - Core Architecture & Protocols: Refactoring the Scheduler, Agent-to-Agent (A2A) protocol implementation, low-level MCP (Model Context Protocol) transport mechanisms.
+              - Performance & Memory: Diagnosing massive disk/memory leaks, severe boot time regressions, high-throughput streaming optimizations (e.g., voice streaming pipelines).
+            Note: Any bug that is described as intermittent, flickering, difficult to reproduce, platform-specific, or requiring cross-environment setups (e.g., involving the VS Code IDE companion, GCA plugin, or Android Studio) MUST NOT be rated as effort/small because of the increased overhead of testing and reproducing.
 
             Categorization Guidelines (Priority):
             P0 - Urgent Blocking Issues:
@@ -204,6 +398,7 @@ 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
@@ -215,64 +410,52 @@ jobs:
             - This product is designed to use different models eg.. using pro, downgrading to flash etc.
             - When users report that they dont expect the model to change those would be categorized as feature requests.
 
-      - name: 'Apply Labels to Issues'
+      - name: 'Apply Triaged Labels'
         if: |-
-          ${{ steps.gemini_issue_analysis.outcome == 'success' &&
-              steps.gemini_issue_analysis.outputs.summary != '[]' }}
+          always() &&
+          ( (steps.gemini_standard_issue_analysis.outcome == 'success' && steps.gemini_standard_issue_analysis.outputs.summary != '[]' && steps.gemini_standard_issue_analysis.outputs.summary != '') ||
+            (steps.gemini_effort_issue_analysis.outcome == 'success' && steps.gemini_effort_issue_analysis.outputs.summary != '[]' && steps.gemini_effort_issue_analysis.outputs.summary != '') )
         env:
-          REPOSITORY: '${{ github.repository }}'
-          LABELS_OUTPUT: '${{ steps.gemini_issue_analysis.outputs.summary }}'
+          LABELS_OUTPUT_STANDARD: '${{ steps.gemini_standard_issue_analysis.outputs.summary }}'
+          LABELS_OUTPUT_EFFORT: '${{ steps.gemini_effort_issue_analysis.outputs.summary }}'
         uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
         with:
           github-token: '${{ steps.generate_token.outputs.token }}'
           script: |-
-            const rawLabels = process.env.LABELS_OUTPUT;
-            core.info(`Raw labels JSON: ${rawLabels}`);
-            let parsedLabels;
-            try {
-              const jsonMatch = rawLabels.match(/```json\s*([\s\S]*?)\s*```/);
-              if (!jsonMatch || !jsonMatch[1]) {
-                throw new Error("Could not find a ```json ... ``` block in the output.");
-              }
-              const jsonString = jsonMatch[1].trim();
-              parsedLabels = JSON.parse(jsonString);
-              core.info(`Parsed labels JSON: ${JSON.stringify(parsedLabels)}`);
-            } catch (err) {
-              core.setFailed(`Failed to parse labels JSON from Gemini output: ${err.message}\nRaw output: ${rawLabels}`);
-              return;
-            }
+            const applyLabels = require('./.github/scripts/apply-issue-labels.cjs');
+            await applyLabels({ github, context, core });
 
-            for (const entry of parsedLabels) {
-              const issueNumber = entry.issue_number;
-              if (!issueNumber) {
-                core.info(`Skipping entry with no issue number: ${JSON.stringify(entry)}`);
-                continue;
-              }
+      - name: 'Sync Issue Types (Post-Analysis)'
+        if: |-
+          always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
+        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token }}'
+          script: |-
+            const syncIssueTypes = require('./.github/scripts/sync-issue-types.cjs');
+            await syncIssueTypes({ github, context, core });
 
-              const labelsToAdd = entry.labels_to_add || [];
-              labelsToAdd.push('status/bot-triaged');
+      - name: 'Find Triaged Issues to Clean Up'
+        if: |-
+          always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
+        env:
+          GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
+          GITHUB_REPOSITORY: '${{ github.repository }}'
+        run: |-
+          set -euo pipefail
+          echo '🧹 Finding issues that have conflicting status labels...'
+          gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue label:status/bot-triaged label:status/need-triage' --limit 50 --json number > cleanup_1.json
+          gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue label:status/bot-triaged label:status/manual-triage' --limit 50 --json number > cleanup_2.json
+          jq -c -s 'add | unique_by(.number)' cleanup_1.json cleanup_2.json > issues_to_cleanup.json
 
-              if (labelsToAdd.length > 0) {
-                await github.rest.issues.addLabels({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  issue_number: issueNumber,
-                  labels: labelsToAdd
-                });
-                const explanation = entry.explanation ? ` - ${entry.explanation}` : '';
-                core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}${explanation}`);
-              }
-
-              if (entry.explanation) {
-                await github.rest.issues.createComment({
-                  owner: context.repo.owner,
-                  repo: context.repo.repo,
-                  issue_number: issueNumber,
-                  body: entry.explanation,
-                });
-              }
-
-              if ((!entry.labels_to_add || entry.labels_to_add.length === 0) && (!entry.labels_to_remove || entry.labels_to_remove.length === 0)) {
-                core.info(`No labels to add or remove for #${issueNumber}, leaving as is`);
-              }
-            }
+      - name: 'Clean Up Triage Labels'
+        if: |-
+          always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
+        uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token }}'
+          script: |-
+            const cleanupLabels = require('./.github/scripts/cleanup-triage-labels.cjs');
+            await cleanupLabels({ github, context, core });

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

@@ -21,6 +21,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Generate GitHub App Token'
         id: 'generate_token'

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

@@ -1,158 +0,0 @@
-name: '🔒 Gemini Scheduled Stale Issue Closer'
-
-on:
-  schedule:
-    - cron: '0 0 * * 0' # Every Sunday at midnight UTC
-  workflow_dispatch:
-    inputs:
-      dry_run:
-        description: 'Run in dry-run mode (no changes applied)'
-        required: false
-        default: false
-        type: 'boolean'
-
-concurrency:
-  group: '${{ github.workflow }}'
-  cancel-in-progress: true
-
-defaults:
-  run:
-    shell: 'bash'
-
-jobs:
-  close-stale-issues:
-    runs-on: 'ubuntu-latest'
-    permissions:
-      issues: 'write'
-    steps:
-      - name: 'Generate GitHub App Token'
-        id: 'generate_token'
-        uses: 'actions/create-github-app-token@v1'
-        with:
-          app-id: '${{ secrets.APP_ID }}'
-          private-key: '${{ secrets.PRIVATE_KEY }}'
-          permission-issues: 'write'
-
-      - name: 'Process Stale Issues'
-        uses: 'actions/github-script@v7'
-        env:
-          DRY_RUN: '${{ 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 batchLabel = 'Stale';
-
-            const threeMonthsAgo = new Date();
-            threeMonthsAgo.setMonth(threeMonthsAgo.getMonth() - 3);
-
-            const tenDaysAgo = new Date();
-            tenDaysAgo.setDate(tenDaysAgo.getDate() - 10);
-
-            core.info(`Cutoff date for creation: ${threeMonthsAgo.toISOString()}`);
-            core.info(`Cutoff date for updates: ${tenDaysAgo.toISOString()}`);
-
-            const query = `repo:${context.repo.owner}/${context.repo.repo} is:issue is:open created:<${threeMonthsAgo.toISOString()}`;
-            core.info(`Searching with query: ${query}`);
-
-            const itemsToCheck = await github.paginate(github.rest.search.issuesAndPullRequests, {
-              q: query,
-              sort: 'created',
-              order: 'asc',
-              per_page: 100
-            });
-
-            core.info(`Found ${itemsToCheck.length} open issues to check.`);
-
-            let processedCount = 0;
-
-            for (const issue of itemsToCheck) {
-              const createdAt = new Date(issue.created_at);
-              const updatedAt = new Date(issue.updated_at);
-              const reactionCount = issue.reactions.total_count;
-
-              // Basic thresholds
-              if (reactionCount >= 5) {
-                continue;
-              }
-
-              // Skip if it has a maintainer, help wanted, or Public Roadmap label
-              const rawLabels = issue.labels.map((l) => l.name);
-              const lowercaseLabels = rawLabels.map((l) => l.toLowerCase());
-              if (
-                lowercaseLabels.some((l) => l.includes('maintainer')) ||
-                lowercaseLabels.includes('help wanted') ||
-                rawLabels.includes('🗓️ Public Roadmap')
-              ) {
-                continue;
-              }
-
-              let isStale = updatedAt < tenDaysAgo;
-
-              // If apparently active, check if it's only bot activity
-              if (!isStale) {
-                try {
-                  const comments = await github.rest.issues.listComments({
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: issue.number,
-                    per_page: 100,
-                    sort: 'created',
-                    direction: 'desc'
-                  });
-
-                  const lastHumanComment = comments.data.find(comment => comment.user.type !== 'Bot');
-                  if (lastHumanComment) {
-                    isStale = new Date(lastHumanComment.created_at) < tenDaysAgo;
-                  } else {
-                    // No human comments. Check if creator is human.
-                    if (issue.user.type !== 'Bot') {
-                       isStale = createdAt < tenDaysAgo;
-                    } else {
-                       isStale = true; // Bot created, only bot comments
-                    }
-                  }
-                } catch (error) {
-                  core.warning(`Failed to fetch comments for issue #${issue.number}: ${error.message}`);
-                  continue;
-                }
-              }
-
-              if (isStale) {
-                processedCount++;
-                const message = `Closing stale issue #${issue.number}: "${issue.title}" (${issue.html_url})`;
-                core.info(message);
-
-                if (!dryRun) {
-                  // Add label
-                  await github.rest.issues.addLabels({
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: issue.number,
-                    labels: [batchLabel]
-                  });
-
-                  // Add comment
-                  await github.rest.issues.createComment({
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: issue.number,
-                    body: 'Hello! As part of our effort to keep our backlog manageable and focus on the most active issues, we are tidying up older reports.\n\nIt looks like this issue hasn\'t been active for a while, so we are closing it for now. However, if you are still experiencing this bug on the latest stable build, please feel free to comment on this issue or create a new one with updated details.\n\nThank you for your contribution!'
-                  });
-
-                  // Close issue
-                  await github.rest.issues.update({
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: issue.number,
-                    state: 'closed',
-                    state_reason: 'not_planned'
-                  });
-                }
-              }
-            }
-
-            core.info(`\nTotal issues processed: ${processedCount}`);

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

@@ -1,205 +0,0 @@
-name: 'Gemini Scheduled Stale PR Closer'
-
-on:
-  schedule:
-    - cron: '0 2 * * *' # Every day at 2 AM UTC
-  pull_request:
-    types: ['opened', 'edited']
-  workflow_dispatch:
-    inputs:
-      dry_run:
-        description: 'Run in dry-run mode'
-        required: false
-        default: false
-        type: 'boolean'
-
-jobs:
-  close-stale-prs:
-    if: "github.repository == 'google-gemini/gemini-cli'"
-    runs-on: 'ubuntu-latest'
-    permissions:
-      pull-requests: 'write'
-      issues: 'write'
-    steps:
-      - name: 'Generate GitHub App Token'
-        id: 'generate_token'
-        uses: 'actions/create-github-app-token@v1'
-        with:
-          app-id: '${{ secrets.APP_ID }}'
-          private-key: '${{ secrets.PRIVATE_KEY }}'
-          owner: '${{ github.repository_owner }}'
-          repositories: 'gemini-cli'
-
-      - name: 'Process Stale PRs'
-        uses: 'actions/github-script@v7'
-        env:
-          DRY_RUN: '${{ inputs.dry_run }}'
-        with:
-          github-token: '${{ steps.generate_token.outputs.token }}'
-          script: |
-            const dryRun = process.env.DRY_RUN === 'true';
-            const thirtyDaysAgo = new Date();
-            thirtyDaysAgo.setDate(thirtyDaysAgo.getDate() - 30);
-
-            // 1. Fetch maintainers for verification
-            let maintainerLogins = new Set();
-            try {
-              const members = await github.paginate(github.rest.teams.listMembersInOrg, {
-                org: context.repo.owner,
-                team_slug: 'gemini-cli-maintainers'
-              });
-              maintainerLogins = new Set(members.map(m => m.login));
-            } catch (e) {
-              core.warning('Failed to fetch team members');
-            }
-
-            const isMaintainer = (login, assoc) => {
-              if (maintainerLogins.size > 0) return maintainerLogins.has(login);
-              return ['OWNER', 'MEMBER', 'COLLABORATOR'].includes(assoc);
-            };
-
-            // 2. Determine which PRs to check
-            let prs = [];
-            if (context.eventName === 'pull_request') {
-              const { data: pr } = await github.rest.pulls.get({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                pull_number: context.payload.pull_request.number
-              });
-              prs = [pr];
-            } else {
-              prs = await github.paginate(github.rest.pulls.list, {
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                state: 'open',
-                per_page: 100
-              });
-            }
-
-            for (const pr of prs) {
-              const maintainerPr = isMaintainer(pr.user.login, pr.author_association);
-              const isBot = pr.user.type === 'Bot' || pr.user.login.endsWith('[bot]');
-
-              // Detection Logic for Linked Issues
-              // Check 1: Official GitHub "Closing Issue" link (GraphQL)
-              const linkedIssueQuery = `query($owner:String!, $repo:String!, $number:Int!) {
-                repository(owner:$owner, name:$repo) {
-                  pullRequest(number:$number) {
-                    closingIssuesReferences(first: 1) { totalCount }
-                  }
-                }
-              }`;
-
-              let hasClosingLink = false;
-              try {
-                const res = await github.graphql(linkedIssueQuery, {
-                  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 #${pr.number} now has a linked issue. Reopening.`);
-                  if (!dryRun) {
-                    await github.rest.pulls.update({
-                      owner: context.repo.owner,
-                      repo: context.repo.repo,
-                      pull_number: pr.number,
-                      state: 'open'
-                    });
-                    await github.rest.issues.createComment({
-                      owner: context.repo.owner,
-                      repo: context.repo.repo,
-                      issue_number: pr.number,
-                      body: "Thank you for linking an issue! This pull request has been automatically reopened."
-                    });
-                  }
-                }
-                continue;
-              }
-
-              // Logic for Open PRs (Immediate Closure)
-              if (pr.state === 'open' && !maintainerPr && !hasLinkedIssue && !isBot) {
-                core.info(`PR #${pr.number} is missing a linked issue. 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!"
-                  });
-                  await github.rest.pulls.update({
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    pull_number: pr.number,
-                    state: 'closed'
-                  });
-                }
-                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;
-
-                let lastActivity = new Date(0);
-                try {
-                  const reviews = await github.paginate(github.rest.pulls.listReviews, {
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    pull_number: pr.number
-                  });
-                  for (const r of reviews) {
-                    if (isMaintainer(r.user.login, r.author_association)) {
-                      const d = new Date(r.submitted_at || r.updated_at);
-                      if (d > lastActivity) lastActivity = d;
-                    }
-                  }
-                  const comments = await github.paginate(github.rest.issues.listComments, {
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: pr.number
-                  });
-                  for (const c of comments) {
-                    if (isMaintainer(c.user.login, c.author_association)) {
-                      const d = new Date(c.updated_at);
-                      if (d > lastActivity) lastActivity = d;
-                    }
-                  }
-                } catch (e) {}
-
-                if (maintainerPr) {
-                  const d = new Date(pr.created_at);
-                  if (d > lastActivity) lastActivity = d;
-                }
-
-                if (lastActivity < thirtyDaysAgo) {
-                  core.info(`PR #${pr.number} is stale.`);
-                  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!"
-                    });
-                    await github.rest.pulls.update({
-                      owner: context.repo.owner,
-                      repo: context.repo.repo,
-                      pull_number: pr.number,
-                      state: 'closed'
-                    });
-                  }
-                }
-              }
-            }

.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 }}'
@@ -48,6 +49,24 @@ jobs:
             const repo = context.repo.repo;
             const MAX_ISSUES_ASSIGNED = 3;
 
+            const issue = await github.rest.issues.get({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: issueNumber,
+            });
+
+            const hasHelpWantedLabel = issue.data.labels.some(label => label.name === 'help wanted');
+
+            if (!hasHelpWantedLabel) {
+              await github.rest.issues.createComment({
+                owner: owner,
+                repo: repo,
+                issue_number: issueNumber,
+                body: `👋 @${commenter}, thanks for your interest in this issue! We're reserving self-assignment for issues that have been marked with the \`help wanted\` label. Feel free to check out our list of [issues that need attention](https://github.com/google-gemini/gemini-cli/issues?q=is%3Aissue+is%3Aopen+label%3A%22help+wanted%22).`
+              });
+              return;
+            }
+
             // Search for open issues already assigned to the commenter in this repo
             const { data: assignedIssues } = await github.rest.search.issuesAndPullRequests({
               q: `is:issue repo:${owner}/${repo} assignee:${commenter} is:open`,
@@ -64,13 +83,6 @@ jobs:
               return; // exit
             }
 
-            // Check if the issue is already assigned
-            const issue = await github.rest.issues.get({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              issue_number: issueNumber,
-            });
-
             if (issue.data.assignees.length > 0) {
               // Comment that it's already assigned
               await github.rest.issues.createComment({
@@ -97,3 +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 +14,16 @@ 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
+        with:
+          persist-credentials: false
 
       - 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 +38,16 @@ 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
+        with:
+          persist-credentials: false
 
       - 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/links.yml

@@ -17,6 +17,8 @@ jobs:
     runs-on: 'ubuntu-latest'
     steps:
       - uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+        with:
+          persist-credentials: false
 
       - name: 'Link Checker'
         id: 'lychee'

.github/workflows/memory-nightly.yml

@@ -0,0 +1,35 @@
+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
+        with:
+          persist-credentials: false
+
+      - 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/no-response.yml

@@ -1,33 +0,0 @@
-name: 'No Response'
-
-# Run as a daily cron at 1:45 AM
-on:
-  schedule:
-    - cron: '45 1 * * *'
-  workflow_dispatch:
-
-jobs:
-  no-response:
-    runs-on: 'ubuntu-latest'
-    if: |-
-      ${{ github.repository == 'google-gemini/gemini-cli' }}
-    permissions:
-      issues: 'write'
-      pull-requests: 'write'
-    concurrency:
-      group: '${{ github.workflow }}-no-response'
-      cancel-in-progress: true
-    steps:
-      - uses: 'actions/stale@5bef64f19d7facfb25b37b414482c7164d639639' # ratchet:actions/stale@v9
-        with:
-          repo-token: '${{ secrets.GITHUB_TOKEN }}'
-          days-before-stale: -1
-          days-before-close: 14
-          stale-issue-label: 'status/need-information'
-          close-issue-message: >-
-            This issue was marked as needing more information and has not received a response in 14 days.
-            Closing it for now. If you still face this problem, feel free to reopen with more details. Thank you!
-          stale-pr-label: 'status/need-information'
-          close-pr-message: >-
-            This pull request was marked as needing more information and has had no updates in 14 days.
-            Closing it for now. You are welcome to reopen with the required info. Thanks for contributing!

.github/workflows/perf-nightly.yml

@@ -0,0 +1,35 @@
+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
+        with:
+          persist-credentials: false
+
+      - 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

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

.github/workflows/pr-rate-limiter.yaml

@@ -0,0 +1,29 @@
+# yaml-language-server: $schema=https://json.schemastore.org/github-workflow.json
+
+name: 'PR rate limiter'
+
+permissions: {}
+
+on:
+  pull_request_target:
+    types:
+      - 'opened'
+      - 'reopened'
+
+jobs:
+  limit:
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    permissions:
+      contents: 'read'
+      pull-requests: 'write'
+    steps:
+      - name: 'Limit open pull requests per user'
+        uses: 'Homebrew/actions/limit-pull-requests@9ceb7934560eb61d131dde205a6c2d77b2e1529d' # master
+        with:
+          except-author-associations: 'MEMBER,OWNER,COLLABORATOR'
+          comment-limit: 8
+          comment: >
+            You already have 7 pull requests open. Please work on getting
+            existing PRs merged before opening more.
+          close-limit: 8
+          close: true

.github/workflows/pr-size-labeler-batch-run.yml

@@ -0,0 +1,107 @@
+name: 'PR Size Labeler (Batch)'
+
+on:
+  workflow_dispatch:
+    inputs:
+      process_all:
+        description: 'Process all PRs (open and closed) or open only'
+        required: true
+        default: 'false'
+        type: 'choice'
+        options:
+          - 'true'
+          - 'false'
+      limit:
+        description: 'Max number of PRs to fetch and check'
+        required: true
+        default: '100'
+        type: 'string'
+
+permissions:
+  pull-requests: 'write'
+
+jobs:
+  batch-label:
+    runs-on: 'ubuntu-latest'
+    steps:
+      - name: 'Batch label PRs'
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+          GH_REPO: '${{ github.repository }}'
+        run: |
+          # Determine the state filter
+          STATE="open"
+          if [ "${{ github.event.inputs.process_all }}" = "true" ]; then
+            STATE="all"
+          fi
+
+          LIMIT="${{ github.event.inputs.limit }}"
+          echo "Batch labeling up to $LIMIT $STATE PRs..."
+
+          # 1. Ensure standard premium size labels exist in the repository (self-healing)
+          gh label create "size/XS" --color "7ee081" --description "XS: <10 lines changed" 2>/dev/null || true
+          gh label create "size/S"  --color "a6d49f" --description "S: 10-49 lines changed" 2>/dev/null || true
+          gh label create "size/M"  --color "f7d070" --description "M: 50-249 lines changed" 2>/dev/null || true
+          gh label create "size/L"  --color "f48c06" --description "L: 250-999 lines changed" 2>/dev/null || true
+          gh label create "size/XL" --color "dc2f02" --description "XL: >=1000 lines changed" 2>/dev/null || true
+
+          # 2. Query PR list with all required fields in ONE call to prevent N+1 queries
+          PR_LIST=$(gh pr list --state "$STATE" --limit "$LIMIT" --json number,additions,deletions,labels)
+          if [ -z "$PR_LIST" ] || [ "$PR_LIST" = "[]" ]; then
+            echo "ℹ️ No PRs found matching the criteria."
+            exit 0
+          fi
+
+          # Parse and iterate over PRs
+          UPDATED_COUNT=0
+          SKIPPED_COUNT=0
+
+          echo "$PR_LIST" | jq -c '.[]' | while read -r PR_JSON; do
+            PR_NUMBER=$(echo "$PR_JSON" | jq '.number')
+            ADDITIONS=$(echo "$PR_JSON" | jq '.additions')
+            DELETIONS=$(echo "$PR_JSON" | jq '.deletions')
+            TOTAL=$((ADDITIONS + DELETIONS))
+
+            # Calculate target size
+            if [ $TOTAL -lt 10 ]; then
+              SIZE="size/XS"
+            elif [ $TOTAL -lt 50 ]; then
+              SIZE="size/S"
+            elif [ $TOTAL -lt 250 ]; then
+              SIZE="size/M"
+            elif [ $TOTAL -lt 1000 ]; then
+              SIZE="size/L"
+            else
+              SIZE="size/XL"
+            fi
+
+            # Inspect existing labels to detect discrepancies
+            EXISTING_LABELS=$(echo "$PR_JSON" | jq -r '.labels[].name' 2>/dev/null || echo "")
+
+            LABELS_TO_REMOVE=()
+            for L in size/XS size/S size/M size/L size/XL; do
+              if echo "$EXISTING_LABELS" | grep -Fq "$L" && [ "$L" != "$SIZE" ]; then
+                LABELS_TO_REMOVE+=("--remove-label" "$L")
+              fi
+            done
+
+            LABEL_TO_ADD=()
+            if ! echo "$EXISTING_LABELS" | grep -Fq "$SIZE"; then
+              LABEL_TO_ADD+=("--add-label" "$SIZE")
+            fi
+
+            # Update labels if there's a difference
+            if [ ${#LABELS_TO_REMOVE[@]} -gt 0 ] || [ ${#LABEL_TO_ADD[@]} -gt 0 ]; then
+              echo "🔄 PR #$PR_NUMBER (+$ADDITIONS/-$DELETIONS = $TOTAL lines): updating size to $SIZE"
+              gh pr edit "$PR_NUMBER" "${LABELS_TO_REMOVE[@]}" "${LABEL_TO_ADD[@]}" 2>/dev/null || true
+              UPDATED_COUNT=$((UPDATED_COUNT + 1))
+            else
+              echo "✅ PR #$PR_NUMBER (+$ADDITIONS/-$DELETIONS = $TOTAL lines): already has correct label ($SIZE). Skipping."
+              SKIPPED_COUNT=$((SKIPPED_COUNT + 1))
+            fi
+          done
+
+          echo "============================================"
+          echo "🎉 Batch run completed!"
+          echo "Skipped (already correct): $SKIPPED_COUNT"
+          echo "Updated: $UPDATED_COUNT"

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

@@ -0,0 +1,120 @@
+name: 'PR Size Labeler'
+
+on:
+  pull_request_target:
+    types: ['opened', 'synchronize', 'reopened']
+  workflow_dispatch:
+    inputs:
+      pr_number:
+        description: 'PR number to label manually (for workflow_dispatch)'
+        required: false
+        type: 'string'
+
+permissions:
+  pull-requests: 'write'
+  issues: 'write'
+
+jobs:
+  size-label:
+    runs-on: 'ubuntu-latest'
+    steps:
+      - name: 'Run size labeler'
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+          GH_REPO: '${{ github.repository }}'
+        run: |
+          # Determine the target PR number
+          if [ -n "${{ github.event.pull_request.number }}" ]; then
+            PR_NUMBER="${{ github.event.pull_request.number }}"
+          elif [ -n "${{ github.event.inputs.pr_number }}" ]; then
+            PR_NUMBER="${{ github.event.inputs.pr_number }}"
+          else
+            echo "❌ Error: No PR number provided."
+            exit 1
+          fi
+
+          echo "Checking PR #$PR_NUMBER..."
+
+          # 1. Ensure standard premium size labels exist in the repository (self-healing)
+          # size/XS: Light green (#7ee081)
+          # size/S: Yellow-green (#a6d49f)
+          # size/M: Amber/Yellow (#f7d070)
+          # size/L: Orange (#f48c06)
+          # size/XL: Red (#dc2f02)
+          gh label create "size/XS" --color "7ee081" --description "XS: <10 lines changed" 2>/dev/null || true
+          gh label create "size/S"  --color "a6d49f" --description "S: 10-49 lines changed" 2>/dev/null || true
+          gh label create "size/M"  --color "f7d070" --description "M: 50-249 lines changed" 2>/dev/null || true
+          gh label create "size/L"  --color "f48c06" --description "L: 250-999 lines changed" 2>/dev/null || true
+          gh label create "size/XL" --color "dc2f02" --description "XL: >=1000 lines changed" 2>/dev/null || true
+
+          # 2. Fetch PR details in a single efficient API call
+          PR_DATA=$(gh pr view "$PR_NUMBER" --json additions,deletions,changedFiles,labels)
+          if [ -z "$PR_DATA" ]; then
+            echo "❌ Error: Could not fetch PR details."
+            exit 1
+          fi
+
+          ADDITIONS=$(echo "$PR_DATA" | jq '.additions')
+          DELETIONS=$(echo "$PR_DATA" | jq '.deletions')
+          CHANGED_FILES=$(echo "$PR_DATA" | jq '.changedFiles')
+          TOTAL=$((ADDITIONS + DELETIONS))
+
+          echo "PR additions: $ADDITIONS, deletions: $DELETIONS, total changes: $TOTAL, files: $CHANGED_FILES"
+
+          # 3. Calculate new size label
+          if [ $TOTAL -lt 10 ]; then
+            SIZE="size/XS"
+          elif [ $TOTAL -lt 50 ]; then
+            SIZE="size/S"
+          elif [ $TOTAL -lt 250 ]; then
+            SIZE="size/M"
+          elif [ $TOTAL -lt 1000 ]; then
+            SIZE="size/L"
+          else
+            SIZE="size/XL"
+          fi
+
+          # 4. Check existing labels and update only if necessary
+          EXISTING_LABELS=$(echo "$PR_DATA" | jq -r '.labels[].name' 2>/dev/null || echo "")
+
+          LABELS_TO_REMOVE=()
+          for L in size/XS size/S size/M size/L size/XL; do
+            if echo "$EXISTING_LABELS" | grep -Fq "$L" && [ "$L" != "$SIZE" ]; then
+              LABELS_TO_REMOVE+=("--remove-label" "$L")
+            fi
+          done
+
+          LABEL_TO_ADD=()
+          if ! echo "$EXISTING_LABELS" | grep -Fq "$SIZE"; then
+            LABEL_TO_ADD+=("--add-label" "$SIZE")
+          fi
+
+          # Perform a single, highly atomic edit call if changes are needed
+          if [ ${#LABELS_TO_REMOVE[@]} -gt 0 ] || [ ${#LABEL_TO_ADD[@]} -gt 0 ]; then
+            echo "Updating labels: removing ${LABELS_TO_REMOVE[*]}, adding $SIZE"
+            gh pr edit "$PR_NUMBER" "${LABELS_TO_REMOVE[@]}" "${LABEL_TO_ADD[@]}"
+          else
+            echo "✅ PR #$PR_NUMBER already has the correct size label ($SIZE)."
+          fi
+
+          # 5. Premium, anti-spam comment logic (updates previous comment to keep thread clean)
+          COMMENT="📊 PR Size: **$SIZE**
+          - Lines changed: **$TOTAL**
+          - Additions: +$ADDITIONS
+          - Deletions: -$DELETIONS
+          - Files changed: $CHANGED_FILES"
+
+          # Find any existing size labeler comment by the github-actions bot
+          echo "Searching for existing size comment..."
+          COMMENT_ID=$(gh api "repos/${{ github.repository }}/issues/$PR_NUMBER/comments" \
+            --jq '.[] | select(.user.login == "github-actions[bot]" and (.body | startswith("📊 PR Size:"))) | .id' | head -n 1)
+
+          if [ -n "$COMMENT_ID" ]; then
+            echo "Updating existing comment (ID: $COMMENT_ID)..."
+            gh api "repos/${{ github.repository }}/issues/comments/$COMMENT_ID" -X PATCH -f body="$COMMENT" > /dev/null
+          else
+            echo "Creating new comment..."
+            gh pr comment "$PR_NUMBER" --body "$COMMENT" > /dev/null
+          fi
+
+          echo "🎉 PR size labeling completed successfully."