fix(core,cli): properly resolve nested paths and plan dirs in exit_plan_mode

- **exit_plan_mode.ts**: Fixed an issue where `path.basename` incorrectly stripped nested directories (e.g., `tracks/123/index.md` to `index.md`) by adopting `resolveAndValidatePlanPath`.
- **UI Components**: Updated `ExitPlanModeDialog.tsx` and `planCommand.ts` to use `config.getPlansDir()` instead of `config.storage.getPlansDir()`. This ensures the UI respects active extension plan directories (like Conductor) rather than falling back to the default temporary directory.
- **write-file.ts**: Updated to use `config.getPlansDir()` for consistency.

.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/core.toml

@@ -0,0 +1,29 @@
+description="Injects context of all relevant cli files"
+prompt = """
+The following output contains the complete
+source code of packages/core.
+**Pay extremely close attention to these files.** They define the project's
+core architecture, component patterns, and testing standards.
+
+The source code contains the content of absolutely every source code file in
+packages/core.
+You should very rarely need to read any other files from packages/core to resolve
+prompts.
+
+!{find packages/core \\( -path packages/cli/dist -o -path packages/core/dist -o -name node_modules \\) -prune -o -type f \\( -name "*.ts" -o -name "*.tsx" \\) ! -name "*.test.ts" ! -name "*.test.tsx" ! -name "*.d.ts" -exec echo "--- {} ---" \\; -exec cat {} \\;}
+
+In addition to the code context, you MUST strictly adhere to the following frontend-specific development guidelines when writing code in packages/core.
+
+## 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.
+
+## General
+*   **Logging**: Use `debugLogger` for errors. NEVER leave `console.log/warn/error` in the code.
+*   **TypeScript**: Avoid the non-null assertion operator (`!`).
+
+{{args}}. 
+ """

.gemini/commands/frontend.toml

@@ -0,0 +1,20 @@
+description="Injects context of all relevant cli files"
+prompt = """
+The source code contains the content of absolutely every source code file in
+packages/cli and key files from packages/core. In addition to the source code, the following test files are
+included as they are test files that conform to the project's testing standards:
+`packages/cli/src/ui/components/InputPrompt.test.tsx` and `packages/cli/src/ui/App.test.tsx`.
+You should very rarely need to read any other files from packages/cli to resolve
+prompts.
+
+!{find packages/cli -path packages/cli/dist -prune -o -type f \\( -name "*.ts" -o -name "*.tsx" \\) ! -name "*.test.ts" ! -name "*.test.tsx" ! -name "*.d.ts" -exec echo "--- {} ---" \\; -exec cat {} \\; && echo "--- packages/cli/src/ui/components/InputPrompt.test.tsx ---" && cat packages/cli/src/ui/components/InputPrompt.test.tsx && echo "--- packages/cli/src/ui/App.test.tsx ---" && cat packages/cli/src/ui/App.test.tsx && echo "--- packages/core/src/core/coreToolScheduler.ts ---" && cat packages/core/src/core/coreToolScheduler.ts && echo "--- packages/core/src/core/nonInteractiveToolExecutor.ts ---" && cat packages/core/src/core/nonInteractiveToolExecutor.ts && echo "--- packages/core/src/confirmation-bus/message-bus.ts ---" && cat packages/core/src/confirmation-bus/message-bus.ts && echo "--- packages/core/src/confirmation-bus/types.ts ---" && cat packages/core/src/confirmation-bus/types.ts && echo "--- packages/core/src/utils/events.ts ---" && cat packages/core/src/utils/events.ts && echo "--- packages/core/src/core/client.ts ---" && cat packages/core/src/core/client.ts && echo "--- packages/core/src/core/geminiChat.ts ---" && cat packages/core/src/core/geminiChat.ts && echo "--- packages/core/src/core/turn.ts ---" && cat packages/core/src/core/turn.ts && echo "--- packages/core/src/agents/executor.ts ---" && cat packages/core/src/agents/executor.ts && echo "--- packages/core/src/telemetry/types.ts ---" && cat packages/core/src/telemetry/types.ts && echo "--- packages/core/src/telemetry/loggers.ts ---" && cat packages/core/src/telemetry/loggers.ts && echo "--- packages/core/src/telemetry/uiTelemetry.ts ---" && cat packages/core/src/telemetry/uiTelemetry.ts}
+
+**Pay extremely close attention to these files.** They define the project's
+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.
+
+!{cat .gemini/commands/strict-development-rules.md}
+
+{{args}}. 
+ """

.gemini/commands/full-context.toml

@@ -0,0 +1,23 @@
+description="Injects context of all relevant cli files"
+prompt = """
+The following output contains the complete
+source code of the gemini cli library (`packages/cli`), and {packages/core} and representative test files
+(`packages/cli/src/ui/components/InputPrompt.test.tsx` and `packages/cli/src/ui/App.test.tsx`) that best conform to the project's testing standards.
+**Pay extremely close attention to these files.** They define the project's
+core architecture, component patterns, and testing standards.
+
+The source code contains the content of absolutely every source code file in
+packages/cli and packages/core. In addition to the source code, the following test files are
+included as they are test files that conform to the project's testing standards:
+`packages/cli/src/ui/components/InputPrompt.test.tsx` and `packages/cli/src/ui/App.test.tsx`.
+You should very rarely need to read any other files from packages/cli to resolve
+prompts.
+
+!{find packages/cli packages/core \\( -path packages/cli/dist -o -path packages/core/dist -o -name node_modules \\) -prune -o -type f \\( -name "*.ts" -o -name "*.tsx" \\) ! -name "*.test.ts" ! -name "*.test.tsx" ! -name "*.d.ts" -exec echo "--- {} ---" \\; -exec cat {} \\; && echo "--- packages/cli/src/ui/components/InputPrompt.test.tsx ---" && cat packages/cli/src/ui/components/InputPrompt.test.tsx && echo "--- packages/cli/src/ui/App.test.tsx ---" && cat packages/cli/src/ui/App.test.tsx}
+
+In addition to the code context, you MUST strictly adhere to the following frontend-specific development guidelines when writing code in packages/cli.
+
+!{cat .gemini/commands/strict-development-rules.md}
+
+{{args}}. 
+ """

.gemini/commands/introspect.toml

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

.gemini/commands/prompt-suggest.toml

@@ -0,0 +1,22 @@
+description = "Analyze agent behavior and suggest high-level improvements to system prompts."
+prompt = """
+# Prompt Engineering Analysis
+
+You are a world-class prompt engineer and an expert AI engineer at the top of your class. Your goal is to analyze a specific agent behavior or failure and suggest high-level improvements to the system instructions.
+
+**Observed Behavior / Issue:**
+{{args}}
+
+**Reference Context:**
+- System Prompt Logic: @packages/core/src/core/prompts.ts
+
+### Task
+1.  **Analyze the Failure:** Review the provided behavior and identify the underlying instructional causes. Use the `/introspect` command output if provided by the user.
+2.  **Strategic Insights:** Share your technical view of the issue. Focus on the "why" and identify any instructional inertia or ambiguity.
+3.  **Propose Improvements:** Suggest high-level changes to the system instructions to prevent this behavior.
+
+### Principles
+- **Avoid Hyper-scoping:** Do not create narrow solutions for specific scenarios; aim for generalized improvements that handle classes of behavior.
+- **Avoid Specific Examples in Suggestions:** Keep the proposed instructions semantic and high-level to prevent the agent from over-indexing on specific cases.
+- **Maintain Operational Rigor:** Ensure suggestions do not compromise safety, security, or the quality of the agent's work.
+"""

.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.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 +1,142 @@
+# 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 & Effects**: Ensure state initialization is explicit (e.g., use
+  `undefined` rather than `true` as a default if the state is truly unknown).
+  Carefully manage `useEffect` dependencies. Prefer a reducer whenever
+  practical. NEVER disable `react-hooks/exhaustive-deps`; fix the code to
+  correctly declare dependencies instead.
+- **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 +1,10 @@
+{
+  "experimental": {
+    "extensionReloading": true,
+    "modelSteering": true,
+    "topicUpdateNarration": true
+  },
+  "general": {
+    "devtools": true
+  }
+}

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

.gemini/skills/ci/SKILL.md

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

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

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

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

@@ -0,0 +1,65 @@
+---
+name: code-reviewer
+description:
+  Use this skill to review code. It supports both local changes (staged or working tree)
+  and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability,
+  and adherence to project standards.
+---
+
+# Code Reviewer
+
+This skill guides the agent in conducting professional and thorough code reviews for both local development and remote Pull Requests.
+
+## Workflow
+
+### 1. Determine Review Target
+*   **Remote PR**: If the user provides a PR number or URL (e.g., "Review PR #123"), target that remote PR.
+*   **Local Changes**: If no specific PR is mentioned, or if the user asks to "review my changes", target the current local file system states (staged and unstaged changes).
+
+### 2. Preparation
+
+#### For Remote PRs:
+1.  **Checkout**: Use the GitHub CLI to checkout the PR.
+    ```bash
+    gh pr checkout <PR_NUMBER>
+    ```
+2.  **Preflight**: Execute the project's standard verification suite to catch automated failures early.
+    ```bash
+    npm run preflight
+    ```
+3.  **Context**: Read the PR description and any existing comments to understand the goal and history.
+
+#### For Local Changes:
+1.  **Identify Changes**:
+    *   Check status: `git status`
+    *   Read diffs: `git diff` (working tree) and/or `git diff --staged` (staged).
+2.  **Preflight (Optional)**: If the changes are substantial, ask the user if they want to run `npm run preflight` before reviewing.
+
+### 3. In-Depth Analysis
+Analyze the code changes based on the following pillars:
+
+*   **Correctness**: Does the code achieve its stated purpose without bugs or logical errors?
+*   **Maintainability**: Is the code clean, well-structured, and easy to understand and modify in the future? Consider factors like code clarity, modularity, and adherence to established design patterns.
+*   **Readability**: Is the code well-commented (where necessary) and consistently formatted according to our project's coding style guidelines?
+*   **Efficiency**: Are there any obvious performance bottlenecks or resource inefficiencies introduced by the changes?
+*   **Security**: Are there any potential security vulnerabilities or insecure coding practices?
+*   **Edge Cases and Error Handling**: Does the code appropriately handle edge cases and potential errors?
+*   **Testability**: Is the new or modified code adequately covered by tests (even if preflight checks pass)? Suggest additional test cases that would improve coverage or robustness.
+
+### 4. Provide Feedback
+
+#### Structure
+*   **Summary**: A high-level overview of the review.
+*   **Findings**:
+    *   **Critical**: Bugs, security issues, or breaking changes.
+    *   **Improvements**: Suggestions for better code quality or performance.
+    *   **Nitpicks**: Formatting or minor style issues (optional).
+*   **Conclusion**: Clear recommendation (Approved / Request Changes).
+
+#### Tone
+*   Be constructive, professional, and friendly.
+*   Explain *why* a change is requested.
+*   For approvals, acknowledge the specific value of the contribution.
+
+### 5. Cleanup (Remote PRs only)
+*   After the review, ask the user if they want to switch back to the default branch (e.g., `main` or `master`).

.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

@@ -0,0 +1,185 @@
+---
+name: docs-writer
+description:
+  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, 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.
+
+## Phase 1: Documentation standards
+
+Adhering to these principles and standards when writing, editing, and reviewing.
+
+### Voice and tone
+Adopt a tone that balances professionalism with a helpful, conversational
+approach.
+
+- **Perspective and tense:** Address the reader as "you." Use active voice and
+  present tense (e.g., "The API returns...").
+- **Tone:** Professional, friendly, and direct.
+- **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).
+
+### Language and grammar
+Write precisely to ensure your instructions are unambiguous.
+
+- **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.
+
+  Example:
+
+  <details>
+  <summary>Title</summary>
+
+  - First entry
+  - Second entry
+
+  </details>
+
+- **Callouts**: Use GitHub-flavored markdown alerts to highlight important
+  information. To ensure the formatting is preserved by `npm run format`, place
+  an empty line, then the `<!-- prettier-ignore -->` comment directly before
+  the callout block. The callout type (`[!TYPE]`) should be on the first line,
+  followed by a newline, and then the content, with each subsequent line of
+  content starting with `>`. Available types are `NOTE`, `TIP`, `IMPORTANT`,
+  `WARNING`, and `CAUTION`.
+
+  Example:
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an example of a multi-line note that will be preserved
+> by Prettier.
+
+### Links
+- **Accessibility:** Use descriptive anchor text; avoid "click here." Ensure the
+  link makes sense out of context, such as when being read by a screen reader.
+- **Use relative links in docs:** Use relative links in documentation (`/docs/`)
+  to ensure portability. Use paths relative to the current file's directory
+  (for example, `../tools/` from `docs/cli/`). Do not include the `/docs/`
+  section of a path, but do verify that the resulting relative link exists. This
+  does not apply to meta files such as README.MD and CONTRIBUTING.MD.
+- **When changing headings, check for deep links:** If a user is changing a
+  heading, check for deep links to that heading in other pages and update
+  accordingly.
+
+### Structure
+- **BLUF:** Start with an introduction explaining what to expect.
+- **Experimental features:** If a feature is clearly noted as experimental,
+  add the following note immediately after the introductory paragraph:
+
+<!-- prettier-ignore -->
+> [!NOTE]
+> This is an experimental feature currently under active development.
+
+- **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/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

@@ -0,0 +1,93 @@
+---
+name: pr-creator
+description:
+  Use this skill when asked to create a pull request (PR). It ensures all PRs
+  follow the repository's established templates and standards.
+---
+
+# Pull Request Creator
+
+This skill guides the creation of high-quality Pull Requests that adhere to the
+repository's standards.
+
+## Workflow
+
+Follow these steps to create a Pull Request:
+
+1.  **Branch Management**: **CRITICAL:** Ensure you are NOT working on the
+    `main` branch.
+    - Run `git branch --show-current`.
+    - If the current branch is `main`, you MUST create and switch to a new
+      descriptive branch:
+      ```bash
+      git checkout -b <new-branch-name>
+      ```
+
+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`).
+
+4.  **Read Template**: Read the content of the identified template file.
+
+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
+      is not applicable, leave it unchecked or mark as `[ ]` (depending on the
+      template's instructions) or remove it if the template allows flexibility
+      (but prefer keeping it unchecked for transparency).
+    - **Content**: Fill in the sections with clear, concise summaries of your
+      changes.
+    - **Related Issues**: Link any issues fixed or related to this PR (e.g.,
+      "Fixes #123").
+
+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.
+
+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
+    # 1. Write the drafted description to a temporary file
+    # 2. Create the PR using the --body-file flag
+    gh pr create --title "type(scope): succinct description" --body-file <temp_file_path>
+    # 3. Remove the temporary file
+    rm <temp_file_path>
+    ```
+    - **Title**: Ensure the title follows the
+      [Conventional Commits](https://www.conventionalcommits.org/) format if the
+      repository uses it (e.g., `feat(ui): add new button`,
+      `fix(core): resolve crash`).
+
+## Principles
+
+- **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.

.geminiignore

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

.github/CODEOWNERS

@@ -11,3 +11,12 @@
 /.github/workflows/ @google-gemini/gemini-cli-askmode-approvers
 /packages/cli/package.json @google-gemini/gemini-cli-askmode-approvers
 /packages/core/package.json @google-gemini/gemini-cli-askmode-approvers
+
+# 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/bug_report.yml

@@ -1,8 +1,5 @@
 name: 'Bug Report'
 description: 'Report a bug to help us improve Gemini CLI'
-labels:
-  - 'status/need-triage'
-type: 'Bug'
 body:
   - type: 'markdown'
     attributes:
@@ -31,7 +28,7 @@ body:
     id: 'info'
     attributes:
       label: 'Client information'
-      description: 'Please paste the full text from the `/about` command run from Gemini CLI. Also include which platform (macOS, Windows, Linux).'
+      description: 'Please paste the full text from the `/about` command run from Gemini CLI. Also include which platform (macOS, Windows, Linux). Note that this output contains your email address. Consider removing it before submitting.'
       value: |-
         <details>
         <summary>Client Information</summary>

.github/ISSUE_TEMPLATE/website_issue.yml

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

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

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

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

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

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

@@ -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'
@@ -90,15 +93,19 @@ runs:
       id: 'release_branch'
       shell: 'bash'
       run: |
-        BRANCH_NAME="release/${{ inputs.release-tag }}"
+        BRANCH_NAME="release/${INPUTS_RELEASE_TAG}"
         git switch -c "${BRANCH_NAME}"
         echo "BRANCH_NAME=${BRANCH_NAME}" >> "${GITHUB_OUTPUT}"
+      env:
+        INPUTS_RELEASE_TAG: '${{ inputs.release-tag }}'
 
     - name: '⬆️ Update package versions'
       working-directory: '${{ inputs.working-directory }}'
       shell: 'bash'
       run: |
-        npm run release:version "${{ inputs.release-version }}"
+        npm run release:version "${INPUTS_RELEASE_VERSION}"
+      env:
+        INPUTS_RELEASE_VERSION: '${{ inputs.release-version }}'
 
     - name: '💾 Commit and Conditionally Push package versions'
       working-directory: '${{ inputs.working-directory }}'
@@ -160,23 +167,39 @@ runs:
       working-directory: '${{ inputs.working-directory }}'
       env:
         NODE_AUTH_TOKEN: '${{ steps.core-token.outputs.auth-token }}'
+        INPUTS_DRY_RUN: '${{ inputs.dry-run }}'
+        INPUTS_CORE_PACKAGE_NAME: '${{ inputs.core-package-name }}'
       shell: 'bash'
       run: |
         npm publish \
-          --dry-run="${{ inputs.dry-run }}" \
-          --workspace="${{ inputs.core-package-name }}" \
+          --dry-run="${INPUTS_DRY_RUN}" \
+          --workspace="${INPUTS_CORE_PACKAGE_NAME}" \
           --no-tag
-        npm dist-tag rm ${{ inputs.core-package-name }} false --silent
+        if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
+          npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} false
+        fi
 
     - name: '🔗 Install latest core package'
       working-directory: '${{ inputs.working-directory }}'
       if: "${{ inputs.dry-run != 'true' }}"
       shell: 'bash'
       run: |
-        npm install "${{ inputs.core-package-name }}@${{ inputs.release-version }}" \
-        --workspace="${{ inputs.cli-package-name }}" \
-        --workspace="${{ inputs.a2a-package-name }}" \
+        npm install "${INPUTS_CORE_PACKAGE_NAME}@${INPUTS_RELEASE_VERSION}" \
+        --workspace="${INPUTS_CLI_PACKAGE_NAME}" \
+        --workspace="${INPUTS_A2A_PACKAGE_NAME}" \
         --save-exact
+      env:
+        INPUTS_CORE_PACKAGE_NAME: '${{ inputs.core-package-name }}'
+        INPUTS_RELEASE_VERSION: '${{ inputs.release-version }}'
+        INPUTS_CLI_PACKAGE_NAME: '${{ inputs.cli-package-name }}'
+        INPUTS_A2A_PACKAGE_NAME: '${{ inputs.a2a-package-name }}'
+
+    - name: '📦 Prepare bundled CLI for npm release'
+      if: "inputs.npm-registry-url != 'https://npm.pkg.github.com/'"
+      working-directory: '${{ inputs.working-directory }}'
+      shell: 'bash'
+      run: |
+        node ${{ github.workspace }}/scripts/prepare-npm-release.js
 
     - name: 'Get CLI Token'
       uses: './.github/actions/npm-auth-token'
@@ -192,13 +215,17 @@ runs:
       working-directory: '${{ inputs.working-directory }}'
       env:
         NODE_AUTH_TOKEN: '${{ steps.cli-token.outputs.auth-token }}'
+        INPUTS_DRY_RUN: '${{ inputs.dry-run }}'
+        INPUTS_CLI_PACKAGE_NAME: '${{ inputs.cli-package-name }}'
       shell: 'bash'
       run: |
         npm publish \
-          --dry-run="${{ inputs.dry-run }}" \
-          --workspace="${{ inputs.cli-package-name }}" \
+          --dry-run="${INPUTS_DRY_RUN}" \
+          --workspace="${INPUTS_CLI_PACKAGE_NAME}" \
           --no-tag
-        npm dist-tag rm ${{ inputs.cli-package-name }} false --silent
+        if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
+          npm dist-tag rm ${INPUTS_CLI_PACKAGE_NAME} false
+        fi
 
     - name: 'Get a2a-server Token'
       uses: './.github/actions/npm-auth-token'
@@ -214,14 +241,18 @@ runs:
       working-directory: '${{ inputs.working-directory }}'
       env:
         NODE_AUTH_TOKEN: '${{ steps.a2a-token.outputs.auth-token }}'
+        INPUTS_DRY_RUN: '${{ inputs.dry-run }}'
+        INPUTS_A2A_PACKAGE_NAME: '${{ inputs.a2a-package-name }}'
       shell: 'bash'
       # Tag staging for initial release
       run: |
         npm publish \
-          --dry-run="${{ inputs.dry-run }}" \
-          --workspace="${{ inputs.a2a-package-name }}" \
+          --dry-run="${INPUTS_DRY_RUN}" \
+          --workspace="${INPUTS_A2A_PACKAGE_NAME}" \
           --no-tag
-        npm dist-tag rm ${{ inputs.a2a-package-name }} false --silent
+          if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
+            npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} false
+          fi
 
     - name: '🔬 Verify NPM release by version'
       uses: './.github/actions/verify-release'
@@ -254,15 +285,36 @@ 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 }}" \
-          --generate-notes
+        rm -f gemini-cli-bundle.zip
+        (cd bundle && chmod +x gemini.js && zip -r ../gemini-cli-bundle.zip .)
+
+        echo "Testing the generated bundle archive..."
+        rm -rf test-bundle
+        mkdir -p test-bundle
+        unzip -q gemini-cli-bundle.zip -d test-bundle
+
+        # Verify it runs and outputs a version
+        BUNDLE_VERSION=$(node test-bundle/gemini.js --version | xargs)
+        echo "Bundle version output: ${BUNDLE_VERSION}"
+        if [[ -z "${BUNDLE_VERSION}" ]]; then
+          echo "Error: Bundle failed to execute or return version."
+          exit 1
+        fi
+        rm -rf test-bundle
+
+        gh release create "${INPUTS_RELEASE_TAG}" \
+          gemini-cli-bundle.zip \
+          --target "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}" \
+          --title "Release ${INPUTS_RELEASE_TAG}" \
+          --notes-start-tag "${INPUTS_PREVIOUS_TAG}" \
+          --generate-notes \
+          ${{ inputs.npm-tag != 'latest' && '--prerelease' || '' }}
 
     - name: '🧹 Clean up release branch'
       working-directory: '${{ inputs.working-directory }}'
@@ -270,5 +322,8 @@ runs:
       continue-on-error: true
       shell: 'bash'
       run: |
-        echo "Cleaning up release branch ${{ steps.release_branch.outputs.BRANCH_NAME }}..."
-        git push origin --delete "${{ steps.release_branch.outputs.BRANCH_NAME }}"
+        echo "Cleaning up release branch ${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}..."
+        git push origin --delete "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}"
+
+      env:
+        STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'

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

@@ -52,8 +52,10 @@ runs:
       id: 'branch_name'
       shell: 'bash'
       run: |
-        REF_NAME="${{ inputs.ref-name }}"
+        REF_NAME="${INPUTS_REF_NAME}"
         echo "name=${REF_NAME%/merge}" >> $GITHUB_OUTPUT
+      env:
+        INPUTS_REF_NAME: '${{ inputs.ref-name }}'
     - name: 'Build and Push the Docker Image'
       uses: 'docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83' # ratchet:docker/build-push-action@v6
       with:
@@ -75,4 +77,4 @@ runs:
         gh issue create \
           --title "Docker build failed" \
           --body "The docker build failed. See the full run for details: ${DETAILS_URL}" \
-          --label "kind/bug,release-failure"
+          --label "release-failure"

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

@@ -34,7 +34,7 @@ runs:
         JSON_INPUTS: '${{ toJSON(inputs) }}'
       run: 'echo "$JSON_INPUTS"'
     - name: 'Checkout'
-      uses: 'actions/checkout@v4'
+      uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
       with:
         ref: '${{ inputs.github-sha }}'
         fetch-depth: 0
@@ -44,10 +44,12 @@ runs:
     - name: 'npm build'
       shell: 'bash'
       run: 'npm run build'
+    - name: 'Set up QEMU'
+      uses: 'docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130' # ratchet:docker/setup-qemu-action@v3
     - name: 'Set up Docker Buildx'
-      uses: 'docker/setup-buildx-action@v3'
+      uses: 'docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f' # ratchet:docker/setup-buildx-action@v3
     - name: 'Log in to GitHub Container Registry'
-      uses: 'docker/login-action@v3'
+      uses: 'docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9' # ratchet:docker/login-action@v3
       with:
         registry: 'docker.io'
         username: '${{ inputs.dockerhub-username }}'
@@ -56,8 +58,8 @@ runs:
       id: 'image_tag'
       shell: 'bash'
       run: |-
-        SHELL_TAG_NAME="${{ inputs.github-ref-name }}"
-        FINAL_TAG="${{ inputs.github-sha }}"
+        SHELL_TAG_NAME="${INPUTS_GITHUB_REF_NAME}"
+        FINAL_TAG="${INPUTS_GITHUB_SHA}"
         if [[ "$SHELL_TAG_NAME" =~ ^v[0-9]+\.[0-9]+\.[0-9]+(-[a-zA-Z0-9.-]+)?$ ]]; then
           echo "Release detected."
           FINAL_TAG="${SHELL_TAG_NAME#v}"
@@ -66,22 +68,43 @@ 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() }}
@@ -93,4 +116,4 @@ runs:
         gh issue create \
           --title "Docker build failed" \
           --body "The docker build failed. See the full run for details: ${DETAILS_URL}" \
-          --label "kind/bug,release-failure"
+          --label "release-failure"

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

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

.github/actions/setup-npmrc/action.yml

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

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

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

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

@@ -36,7 +36,7 @@ runs:
       run: 'echo "$JSON_INPUTS"'
 
     - name: 'setup node'
-      uses: 'actions/setup-node@v4'
+      uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
       with:
         node-version: '20'
 
@@ -64,10 +64,13 @@ runs:
       working-directory: '${{ inputs.working-directory }}'
       run: |-
         gemini_version=$(gemini --version)
-        if [ "$gemini_version" != "${{ inputs.expected-version }}" ]; then
-          echo "❌ NPM Version mismatch: Got $gemini_version from ${{ inputs.npm-package }}, expected ${{ inputs.expected-version }}"
+        if [ "$gemini_version" != "${INPUTS_EXPECTED_VERSION}" ]; then
+          echo "❌ NPM Version mismatch: Got $gemini_version from ${INPUTS_NPM_PACKAGE}, expected ${INPUTS_EXPECTED_VERSION}"
           exit 1
         fi
+      env:
+        INPUTS_EXPECTED_VERSION: '${{ inputs.expected-version }}'
+        INPUTS_NPM_PACKAGE: '${{ inputs.npm-package }}'
 
     - name: 'Clear npm cache'
       shell: 'bash'
@@ -77,11 +80,14 @@ runs:
       shell: 'bash'
       working-directory: '${{ inputs.working-directory }}'
       run: |-
-        gemini_version=$(npx --prefer-online "${{ inputs.npm-package}}" --version)
-        if [ "$gemini_version" != "${{ inputs.expected-version }}" ]; then
-          echo "❌ NPX Run Version mismatch: Got $gemini_version from ${{ inputs.npm-package }}, expected ${{ inputs.expected-version }}"
+        gemini_version=$(npx --prefer-online "${INPUTS_NPM_PACKAGE}" --version)
+        if [ "$gemini_version" != "${INPUTS_EXPECTED_VERSION}" ]; then
+          echo "❌ NPX Run Version mismatch: Got $gemini_version from ${INPUTS_NPM_PACKAGE}, expected ${INPUTS_EXPECTED_VERSION}"
           exit 1
         fi
+      env:
+        INPUTS_NPM_PACKAGE: '${{ inputs.npm-package }}'
+        INPUTS_EXPECTED_VERSION: '${{ inputs.expected-version }}'
 
     - name: 'Install dependencies for integration tests'
       shell: 'bash'

.github/dependabot.yml

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

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

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

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

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

.github/scripts/pr-triage.sh

@@ -1,133 +1,180 @@
 #!/usr/bin/env bash
+# @license
+# Copyright 2026 Google LLC
+# SPDX-License-Identifier: Apache-2.0
+
 set -euo pipefail
 
 # Initialize a comma-separated string to hold PR numbers that need a comment
 PRS_NEEDING_COMMENT=""
 
-# Function to process a single PR
-process_pr() {
-    if [[ -z "${GITHUB_REPOSITORY:-}" ]]; then
-        echo "‼️ Missing \$GITHUB_REPOSITORY - this must be run from GitHub Actions"
-        return 1
+# Global cache for issue labels (compatible with Bash 3.2)
+# Stores "|ISSUE_NUM:LABELS|" segments
+ISSUE_LABELS_CACHE_FLAT="|"
+
+# Function to get labels from an issue (with caching)
+get_issue_labels() {
+    local ISSUE_NUM="${1}"
+    if [[ -z "${ISSUE_NUM}" || "${ISSUE_NUM}" == "null" || "${ISSUE_NUM}" == "" ]]; then
+        return
     fi
 
-    if [[ -z "${GITHUB_OUTPUT:-}" ]]; then
-        echo "‼️ Missing \$GITHUB_OUTPUT - this must be run from GitHub Actions"
-        return 1
+    # Check cache
+    case "${ISSUE_LABELS_CACHE_FLAT}" in
+        *"|${ISSUE_NUM}:"*) 
+            local suffix="${ISSUE_LABELS_CACHE_FLAT#*|"${ISSUE_NUM}":}"
+            echo "${suffix%%|*}"
+            return
+            ;; 
+        *)
+            # Cache miss, proceed to fetch
+            ;;
+    esac
+
+    echo "   📥 Fetching labels from issue #${ISSUE_NUM}" >&2
+    local gh_output
+    if ! gh_output=$(gh issue view "${ISSUE_NUM}" --repo "${GITHUB_REPOSITORY}" --json labels -q '.labels[].name' 2>/dev/null); then
+        echo "      ⚠️ Could not fetch issue #${ISSUE_NUM}" >&2
+        ISSUE_LABELS_CACHE_FLAT="${ISSUE_LABELS_CACHE_FLAT}${ISSUE_NUM}:|"
+        return
     fi
 
-    local PR_NUMBER=$1
+    local labels
+    labels=$(echo "${gh_output}" | grep -x -E '(area|priority)/.*|help wanted|🔒 maintainer only' | tr '\n' ',' | sed 's/,$//' || echo "")
+    
+    # Save to flat cache
+    ISSUE_LABELS_CACHE_FLAT="${ISSUE_LABELS_CACHE_FLAT}${ISSUE_NUM}:${labels}|"
+    echo "${labels}"
+}
+
+# Function to process a single PR with pre-fetched data
+process_pr_optimized() {
+    local PR_NUMBER="${1}"
+    local IS_DRAFT="${2}"
+    local ISSUE_NUMBER="${3}"
+    local CURRENT_LABELS="${4}" # Comma-separated labels
+
     echo "🔄 Processing PR #${PR_NUMBER}"
 
-    # Get closing issue number with error handling
-    local ISSUE_NUMBER
-    if ! ISSUE_NUMBER=$(gh pr view "${PR_NUMBER}" --repo "${GITHUB_REPOSITORY}" --json closingIssuesReferences -q '.closingIssuesReferences.nodes[0].number' 2>/dev/null); then
-        echo "   ⚠️ Could not fetch closing issue for PR #${PR_NUMBER}"
+    local LABELS_TO_ADD=""
+    local LABELS_TO_REMOVE=""
+
+    if [[ -z "${ISSUE_NUMBER}" || "${ISSUE_NUMBER}" == "null" || "${ISSUE_NUMBER}" == "" ]]; then
+        if [[ "${IS_DRAFT}" == "true" ]]; then
+            echo "   📝 PR #${PR_NUMBER} is a draft and has no linked issue"
+            if [[ ",${CURRENT_LABELS}," == *",status/need-issue,"* ]]; then
+                echo "      ➖ Removing status/need-issue label"
+                LABELS_TO_REMOVE="status/need-issue"
+            fi
+        else
+            echo "   ⚠️  No linked issue found for PR #${PR_NUMBER}"
+            if [[ ",${CURRENT_LABELS}," != *",status/need-issue,"* ]]; then
+                echo "      ➕ Adding status/need-issue label"
+                LABELS_TO_ADD="status/need-issue"
+            fi
+            
+            if [[ -z "${PRS_NEEDING_COMMENT}" ]]; then
+                PRS_NEEDING_COMMENT="${PR_NUMBER}"
+            else
+                PRS_NEEDING_COMMENT="${PRS_NEEDING_COMMENT},${PR_NUMBER}"
+            fi
+        fi
+    else
+        echo "   🔗 Found linked issue #${ISSUE_NUMBER}"
+
+        if [[ ",${CURRENT_LABELS}," == *",status/need-issue,"* ]]; then
+            echo "      ➖ Removing status/need-issue label"
+            LABELS_TO_REMOVE="status/need-issue"
+        fi
+
+        local ISSUE_LABELS
+        ISSUE_LABELS=$(get_issue_labels "${ISSUE_NUMBER}")
+
+        if [[ -n "${ISSUE_LABELS}" ]]; then
+            local IFS_OLD="${IFS}"
+            IFS=','
+            for label in ${ISSUE_LABELS}; do
+                if [[ -n "${label}" ]] && [[ ",${CURRENT_LABELS}," != *",${label},"* ]]; then
+                    if [[ -z "${LABELS_TO_ADD}" ]]; then
+                        LABELS_TO_ADD="${label}"
+                    else
+                        LABELS_TO_ADD="${LABELS_TO_ADD},${label}"
+                    fi
+                fi
+done
+            IFS="${IFS_OLD}"
+        fi
+
+        if [[ -z "${LABELS_TO_ADD}" && -z "${LABELS_TO_REMOVE}" ]]; then
+            echo "   ✅ Labels already synchronized"
+        fi
     fi
 
-    if [[ -z "${ISSUE_NUMBER}" ]]; then
-        echo "⚠️  No linked issue found for PR #${PR_NUMBER}, adding status/need-issue label"
-        if ! gh pr edit "${PR_NUMBER}" --repo "${GITHUB_REPOSITORY}" --add-label "status/need-issue" 2>/dev/null; then
-            echo "   ⚠️ Failed to add label (may already exist or have permission issues)"
-        fi
-        # Add PR number to the list
-        if [[ -z "${PRS_NEEDING_COMMENT}" ]]; then
-            PRS_NEEDING_COMMENT="${PR_NUMBER}"
-        else
-            PRS_NEEDING_COMMENT="${PRS_NEEDING_COMMENT},${PR_NUMBER}"
-        fi
-        echo "needs_comment=true" >> "${GITHUB_OUTPUT}"
-    else
-        echo "🔗 Found linked issue #${ISSUE_NUMBER}"
-
-        # Remove status/need-issue label if present
-        if ! gh pr edit "${PR_NUMBER}" --repo "${GITHUB_REPOSITORY}" --remove-label "status/need-issue" 2>/dev/null; then
-            echo "   status/need-issue label not present or could not be removed"
-        fi
-
-        # Get issue labels
-        echo "📥 Fetching labels from issue #${ISSUE_NUMBER}"
-        local ISSUE_LABELS=""
-        if ! ISSUE_LABELS=$(gh issue view "${ISSUE_NUMBER}" --repo "${GITHUB_REPOSITORY}" --json labels -q '.labels[].name' 2>/dev/null | tr '\n' ',' | sed 's/,$//' || echo ""); then
-            echo "   ⚠️ Could not fetch issue #${ISSUE_NUMBER} (may not exist or be in different repo)"
-            ISSUE_LABELS=""
-        fi
-
-        # Get PR labels
-        echo "📥 Fetching labels from PR #${PR_NUMBER}"
-        local PR_LABELS=""
-        if ! PR_LABELS=$(gh pr view "${PR_NUMBER}" --repo "${GITHUB_REPOSITORY}" --json labels -q '.labels[].name' 2>/dev/null | tr '\n' ',' | sed 's/,$//' || echo ""); then
-            echo "   ⚠️ Could not fetch PR labels"
-            PR_LABELS=""
-        fi
-
-        echo "   Issue labels: ${ISSUE_LABELS}"
-        echo "   PR labels: ${PR_LABELS}"
-
-        # Convert comma-separated strings to arrays
-        local ISSUE_LABEL_ARRAY PR_LABEL_ARRAY
-        IFS=',' read -ra ISSUE_LABEL_ARRAY <<< "${ISSUE_LABELS}"
-        IFS=',' read -ra PR_LABEL_ARRAY <<< "${PR_LABELS}"
-
-        # Find labels to add (on issue but not on PR)
-        local LABELS_TO_ADD=""
-        for label in "${ISSUE_LABEL_ARRAY[@]}"; do
-            if [[ -n "${label}" ]] && [[ " ${PR_LABEL_ARRAY[*]} " != *" ${label} "* ]]; then
-                if [[ -z "${LABELS_TO_ADD}" ]]; then
-                    LABELS_TO_ADD="${label}"
-                else
-                    LABELS_TO_ADD="${LABELS_TO_ADD},${label}"
-                fi
-            fi
-        done
-
-        # Apply label changes
+    if [[ -n "${LABELS_TO_ADD}" || -n "${LABELS_TO_REMOVE}" ]]; then
+        local EDIT_CMD=("gh" "pr" "edit" "${PR_NUMBER}" "--repo" "${GITHUB_REPOSITORY}")
         if [[ -n "${LABELS_TO_ADD}" ]]; then
-            echo "➕ Adding labels: ${LABELS_TO_ADD}"
-            if ! gh pr edit "${PR_NUMBER}" --repo "${GITHUB_REPOSITORY}" --add-label "${LABELS_TO_ADD}" 2>/dev/null; then
-                echo "   ⚠️ Failed to add some labels"
-            fi
+            echo "      ➕ Syncing labels to add: ${LABELS_TO_ADD}"
+            EDIT_CMD+=("--add-label" "${LABELS_TO_ADD}")
         fi
-
-        if [[ -z "${LABELS_TO_ADD}" ]]; then
-            echo "✅ Labels already synchronized"
+        if [[ -n "${LABELS_TO_REMOVE}" ]]; then
+            echo "      ➖ Syncing labels to remove: ${LABELS_TO_REMOVE}"
+            EDIT_CMD+=("--remove-label" "${LABELS_TO_REMOVE}")
         fi
-        echo "needs_comment=false" >> "${GITHUB_OUTPUT}"
+        
+        ("${EDIT_CMD[@]}" || true)
     fi
 }
 
-# If PR_NUMBER is set, process only that PR
-if [[ -n "${PR_NUMBER:-}" ]]; then
-    if ! process_pr "${PR_NUMBER}"; then
-        echo "❌ Failed to process PR #${PR_NUMBER}"
-        exit 1
-    fi
-else
-    # Otherwise, get all open PRs and process them
-    # The script logic will determine which ones need issue linking or label sync
-    echo "📥 Getting all open pull requests..."
-    if ! PR_NUMBERS=$(gh pr list --repo "${GITHUB_REPOSITORY}" --state open --limit 1000 --json number -q '.[].number' 2>/dev/null); then
-        echo "❌ Failed to fetch PR list"
-        exit 1
-    fi
-
-    if [[ -z "${PR_NUMBERS}" ]]; then
-        echo "✅ No open PRs found"
-    else
-        # Count the number of PRs
-        PR_COUNT=$(echo "${PR_NUMBERS}" | wc -w | tr -d ' ')
-        echo "📊 Found ${PR_COUNT} open PRs to process"
-
-        for pr_number in ${PR_NUMBERS}; do
-            if ! process_pr "${pr_number}"; then
-                echo "⚠️ Failed to process PR #${pr_number}, continuing with next PR..."
-                continue
-            fi
-        done
-    fi
+if [[ -z "${GITHUB_REPOSITORY:-}" ]]; then
+    echo "‼️ Missing \$GITHUB_REPOSITORY - this must be run from GitHub Actions"
+    exit 1
+fi
+
+if [[ -z "${GITHUB_OUTPUT:-}" ]]; then
+    echo "‼️ Missing \$GITHUB_OUTPUT - this must be run from GitHub Actions"
+    exit 1
+fi
+
+JQ_EXTRACT_FIELDS='{
+    number: .number,
+    isDraft: .isDraft,
+    issue: (.closingIssuesReferences[0].number // (.body // "" | capture("(^|[^a-zA-Z0-9])#(?<num>[0-9]+)([^a-zA-Z0-9]|$)")? | .num) // "null"),
+    labels: [.labels[].name] | join(",")
+}'
+
+JQ_TSV_FORMAT='"\((.number | tostring))\t\(.isDraft)\t\((.issue // null) | tostring)\t\(.labels)"'
+
+if [[ -n "${PR_NUMBER:-}" ]]; then
+    echo "🔄 Processing single PR #${PR_NUMBER}"
+    PR_DATA=$(gh pr view "${PR_NUMBER}" --repo "${GITHUB_REPOSITORY}" --json number,closingIssuesReferences,isDraft,body,labels 2>/dev/null) || {
+        echo "❌ Failed to fetch data for PR #${PR_NUMBER}"
+        exit 1
+    }
+    
+    line=$(echo "${PR_DATA}" | jq -r "${JQ_EXTRACT_FIELDS} | ${JQ_TSV_FORMAT}")
+    IFS=$'\t' read -r pr_num is_draft issue_num current_labels <<< "${line}"
+    process_pr_optimized "${pr_num}" "${is_draft}" "${issue_num}" "${current_labels}"
+else
+    echo "📥 Getting all open pull requests..."
+    PR_DATA_ALL=$(gh pr list --repo "${GITHUB_REPOSITORY}" --state open --limit 1000 --json number,closingIssuesReferences,isDraft,body,labels 2>/dev/null) || {
+        echo "❌ Failed to fetch PR list"
+        exit 1
+    }
+
+    PR_COUNT=$(echo "${PR_DATA_ALL}" | jq '. | length')
+    echo "📊 Found ${PR_COUNT} open PRs to process"
+
+    # Use a temporary file to avoid masking exit codes in process substitution
+    tmp_file=$(mktemp)
+    echo "${PR_DATA_ALL}" | jq -r ".[] | ${JQ_EXTRACT_FIELDS} | ${JQ_TSV_FORMAT}" > "${tmp_file}"
+    while read -r line; do
+        [[ -z "${line}" ]] && continue
+        IFS=$'\t' read -r pr_num is_draft issue_num current_labels <<< "${line}"
+        process_pr_optimized "${pr_num}" "${is_draft}" "${issue_num}" "${current_labels}"
+    done < "${tmp_file}"
+    rm -f "${tmp_file}"
 fi
 
-# Ensure output is always set, even if empty
 if [[ -z "${PRS_NEEDING_COMMENT}" ]]; then
     echo "prs_needing_comment=[]" >> "${GITHUB_OUTPUT}"
 else

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

@@ -0,0 +1,389 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+const { Octokit } = require('@octokit/rest');
+
+/**
+ * Sync Maintainer Labels (Recursive with strict parent-child relationship detection)
+ * - Uses Native Sub-issues.
+ * - Uses Markdown Task Lists (- [ ] #123).
+ * - Filters for OPEN issues only.
+ * - Skips DUPLICATES.
+ * - Skips Pull Requests.
+ * - ONLY labels issues in the PUBLIC (gemini-cli) repo.
+ */
+
+const REPO_OWNER = 'google-gemini';
+const PUBLIC_REPO = 'gemini-cli';
+const PRIVATE_REPO = 'maintainers-gemini-cli';
+const ALLOWED_REPOS = [PUBLIC_REPO, PRIVATE_REPO];
+
+const ROOT_ISSUES = [
+  { owner: REPO_OWNER, repo: PUBLIC_REPO, number: 15374 },
+  { owner: REPO_OWNER, repo: PUBLIC_REPO, number: 15456 },
+  { owner: REPO_OWNER, repo: PUBLIC_REPO, number: 15324 },
+];
+
+const TARGET_LABEL = '🔒 maintainer only';
+const isDryRun =
+  process.argv.includes('--dry-run') || process.env.DRY_RUN === 'true';
+
+const octokit = new Octokit({
+  auth: process.env.GITHUB_TOKEN,
+});
+
+/**
+ * Extracts child issue references from markdown Task Lists ONLY.
+ * e.g. - [ ] #123 or - [x] google-gemini/gemini-cli#123
+ */
+function extractTaskListLinks(text, contextOwner, contextRepo) {
+  if (!text) return [];
+  const childIssues = new Map();
+
+  const add = (owner, repo, number) => {
+    if (ALLOWED_REPOS.includes(repo)) {
+      const key = `${owner}/${repo}#${number}`;
+      childIssues.set(key, { owner, repo, number: parseInt(number, 10) });
+    }
+  };
+
+  // 1. Full URLs in task lists
+  const urlRegex =
+    /-\s+\[[ x]\].*https:\/\/github\.com\/([a-zA-Z0-9._-]+)\/([a-zA-Z0-9._-]+)\/issues\/(\d+)\b/g;
+  let match;
+  while ((match = urlRegex.exec(text)) !== null) {
+    add(match[1], match[2], match[3]);
+  }
+
+  // 2. Cross-repo refs in task lists: owner/repo#123
+  const crossRepoRegex =
+    /-\s+\[[ x]\].*([a-zA-Z0-9._-]+)\/([a-zA-Z0-9._-]+)#(\d+)\b/g;
+  while ((match = crossRepoRegex.exec(text)) !== null) {
+    add(match[1], match[2], match[3]);
+  }
+
+  // 3. Short refs in task lists: #123
+  const shortRefRegex = /-\s+\[[ x]\].*#(\d+)\b/g;
+  while ((match = shortRefRegex.exec(text)) !== null) {
+    add(contextOwner, contextRepo, match[1]);
+  }
+
+  return Array.from(childIssues.values());
+}
+
+/**
+ * Fetches issue data via GraphQL with full pagination for sub-issues, comments, and labels.
+ */
+async function fetchIssueData(owner, repo, number) {
+  const query = `
+    query($owner:String!, $repo:String!, $number:Int!) {
+      repository(owner:$owner, name:$repo) {
+        issue(number:$number) {
+          state
+          title
+          body
+          labels(first: 100) {
+            nodes { name }
+            pageInfo { hasNextPage endCursor }
+          }
+          subIssues(first: 100) {
+            nodes {
+              number
+              repository {
+                name
+                owner { login }
+              }
+            }
+            pageInfo { hasNextPage endCursor }
+          }
+          comments(first: 100) {
+            nodes {
+              body
+            }
+          }
+        }
+      }
+    }
+  `;
+
+  try {
+    const response = await octokit.graphql(query, { owner, repo, number });
+    const data = response.repository.issue;
+    if (!data) return null;
+
+    const issue = {
+      state: data.state,
+      title: data.title,
+      body: data.body || '',
+      labels: data.labels.nodes.map((n) => n.name),
+      subIssues: [...data.subIssues.nodes],
+      comments: data.comments.nodes.map((n) => n.body),
+    };
+
+    // Paginate subIssues if there are more than 100
+    if (data.subIssues.pageInfo.hasNextPage) {
+      const moreSubIssues = await paginateConnection(
+        owner,
+        repo,
+        number,
+        'subIssues',
+        'number repository { name owner { login } }',
+        data.subIssues.pageInfo.endCursor,
+      );
+      issue.subIssues.push(...moreSubIssues);
+    }
+
+    // Paginate labels if there are more than 100 (unlikely but for completeness)
+    if (data.labels.pageInfo.hasNextPage) {
+      const moreLabels = await paginateConnection(
+        owner,
+        repo,
+        number,
+        'labels',
+        'name',
+        data.labels.pageInfo.endCursor,
+        (n) => n.name,
+      );
+      issue.labels.push(...moreLabels);
+    }
+
+    // Note: Comments are handled via Task Lists in body + first 100 comments.
+    // If an issue has > 100 comments with task lists, we'd need to paginate those too.
+    // Given the 1,100+ issue discovery count, 100 comments is usually sufficient,
+    // but we can add it for absolute completeness.
+    // (Skipping for now to avoid excessive API churn unless clearly needed).
+
+    return issue;
+  } catch (error) {
+    if (error.errors && error.errors.some((e) => e.type === 'NOT_FOUND')) {
+      return null;
+    }
+    throw error;
+  }
+}
+
+/**
+ * Helper to paginate any GraphQL connection.
+ */
+async function paginateConnection(
+  owner,
+  repo,
+  number,
+  connectionName,
+  nodeFields,
+  initialCursor,
+  transformNode = (n) => n,
+) {
+  let additionalNodes = [];
+  let hasNext = true;
+  let cursor = initialCursor;
+
+  while (hasNext) {
+    const query = `
+      query($owner:String!, $repo:String!, $number:Int!, $cursor:String) {
+        repository(owner:$owner, name:$repo) {
+          issue(number:$number) {
+            ${connectionName}(first: 100, after: $cursor) {
+              nodes { ${nodeFields} }
+              pageInfo { hasNextPage endCursor }
+            }
+          }
+        }
+      }
+    `;
+    const response = await octokit.graphql(query, {
+      owner,
+      repo,
+      number,
+      cursor,
+    });
+    const connection = response.repository.issue[connectionName];
+    additionalNodes.push(...connection.nodes.map(transformNode));
+    hasNext = connection.pageInfo.hasNextPage;
+    cursor = connection.pageInfo.endCursor;
+  }
+  return additionalNodes;
+}
+
+/**
+ * Validates if an issue should be processed (Open, not a duplicate, not a PR)
+ */
+function shouldProcess(issueData) {
+  if (!issueData) return false;
+
+  if (issueData.state !== 'OPEN') return false;
+
+  const labels = issueData.labels.map((l) => l.toLowerCase());
+  if (labels.includes('duplicate') || labels.includes('kind/duplicate')) {
+    return false;
+  }
+
+  return true;
+}
+
+async function getAllDescendants(roots) {
+  const allDescendants = new Map();
+  const visited = new Set();
+  const queue = [...roots];
+
+  for (const root of roots) {
+    visited.add(`${root.owner}/${root.repo}#${root.number}`);
+  }
+
+  console.log(`Starting discovery from ${roots.length} roots...`);
+
+  while (queue.length > 0) {
+    const current = queue.shift();
+    const currentKey = `${current.owner}/${current.repo}#${current.number}`;
+
+    try {
+      const issueData = await fetchIssueData(
+        current.owner,
+        current.repo,
+        current.number,
+      );
+
+      if (!shouldProcess(issueData)) {
+        continue;
+      }
+
+      // ONLY add to labeling list if it's in the PUBLIC repository
+      if (current.repo === PUBLIC_REPO) {
+        // Don't label the roots themselves
+        if (
+          !ROOT_ISSUES.some(
+            (r) => r.number === current.number && r.repo === current.repo,
+          )
+        ) {
+          allDescendants.set(currentKey, {
+            ...current,
+            title: issueData.title,
+            labels: issueData.labels,
+          });
+        }
+      }
+
+      const children = new Map();
+
+      // 1. Process Native Sub-issues
+      if (issueData.subIssues) {
+        for (const node of issueData.subIssues) {
+          const childOwner = node.repository.owner.login;
+          const childRepo = node.repository.name;
+          const childNumber = node.number;
+          const key = `${childOwner}/${childRepo}#${childNumber}`;
+          children.set(key, {
+            owner: childOwner,
+            repo: childRepo,
+            number: childNumber,
+          });
+        }
+      }
+
+      // 2. Process Markdown Task Lists in Body and Comments
+      let combinedText = issueData.body || '';
+      if (issueData.comments) {
+        for (const commentBody of issueData.comments) {
+          combinedText += '\n' + (commentBody || '');
+        }
+      }
+
+      const taskListLinks = extractTaskListLinks(
+        combinedText,
+        current.owner,
+        current.repo,
+      );
+      for (const link of taskListLinks) {
+        const key = `${link.owner}/${link.repo}#${link.number}`;
+        children.set(key, link);
+      }
+
+      // Queue children (regardless of which repo they are in, for recursion)
+      for (const [key, child] of children) {
+        if (!visited.has(key)) {
+          visited.add(key);
+          queue.push(child);
+        }
+      }
+    } catch (error) {
+      console.error(`Error processing ${currentKey}: ${error.message}`);
+    }
+  }
+
+  return Array.from(allDescendants.values());
+}
+
+async function run() {
+  if (isDryRun) {
+    console.log('=== DRY RUN MODE: No labels will be applied ===');
+  }
+
+  const descendants = await getAllDescendants(ROOT_ISSUES);
+  console.log(
+    `\nFound ${descendants.length} total unique open descendant issues in ${PUBLIC_REPO}.`,
+  );
+
+  for (const issueInfo of descendants) {
+    const issueKey = `${issueInfo.owner}/${issueInfo.repo}#${issueInfo.number}`;
+    try {
+      // Data is already available from the discovery phase
+      const hasLabel = issueInfo.labels.some((l) => l === TARGET_LABEL);
+
+      if (!hasLabel) {
+        if (isDryRun) {
+          console.log(
+            `[DRY RUN] Would label ${issueKey}: "${issueInfo.title}"`,
+          );
+        } else {
+          console.log(`Labeling ${issueKey}: "${issueInfo.title}"...`);
+          await octokit.rest.issues.addLabels({
+            owner: issueInfo.owner,
+            repo: issueInfo.repo,
+            issue_number: issueInfo.number,
+            labels: [TARGET_LABEL],
+          });
+        }
+      }
+
+      // 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}`);
+    }
+  }
+}
+
+run().catch((error) => {
+  console.error(error);
+  process.exit(1);
+});

.github/workflows/chained_e2e.yml

@@ -1,4 +1,4 @@
-name: 'Test Chained E2E'
+name: 'Testing: E2E (Chained)'
 
 on:
   push:
@@ -31,20 +31,22 @@ jobs:
     name: 'Merge Queue Skipper'
     permissions: 'read-all'
     runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
     outputs:
       skip: '${{ steps.merge-queue-e2e-skipper.outputs.skip-check }}'
     steps:
       - id: 'merge-queue-e2e-skipper'
         uses: 'cariad-tech/merge-queue-ci-skipper@1032489e59437862c90a08a2c92809c903883772' # ratchet:cariad-tech/merge-queue-ci-skipper@main
         with:
-          secret: '${{ secrets.GITHUB_TOKEN }}'
+          secret: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
     continue-on-error: true
 
   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 }}'
     steps:
       - name: 'Mock Repo Artifact'
         if: "${{ github.event_name == 'workflow_dispatch' }}"
@@ -52,7 +54,7 @@ jobs:
           REPO_NAME: '${{ 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'
@@ -66,7 +68,7 @@ jobs:
           name: 'repo_name'
           run-id: '${{ env.RUN_ID }}'
           path: '${{ runner.temp }}/artifacts'
-      - name: 'Output Repo Name'
+      - name: 'Output Repo Name and SHA'
         id: 'output-repo-name'
         uses: 'actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd' # ratchet:actions/github-script@v8
         with:
@@ -75,14 +77,22 @@ jobs:
             const fs = require('fs');
             const path = require('path');
             const temp = '${{ runner.temp }}/artifacts';
-            const repo_name = String(fs.readFileSync(path.join(temp, 'repo_name')));
-            core.setOutput('repo_name', repo_name);
+            const repoPath = path.join(temp, 'repo_name');
+            if (fs.existsSync(repoPath)) {
+              const repo_name = String(fs.readFileSync(repoPath)).trim();
+              core.setOutput('repo_name', repo_name);
+            }
+            const shaPath = path.join(temp, 'head_sha');
+            if (fs.existsSync(shaPath)) {
+              const head_sha = String(fs.readFileSync(shaPath)).trim();
+              core.setOutput('head_sha', head_sha);
+            }
 
   parse_run_context:
     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 }}'
@@ -91,7 +101,7 @@ jobs:
         name: 'Set dynamic repository and SHA'
         env:
           REPO: '${{ needs.download_repo_name.outputs.repo_name || github.repository }}'
-          SHA: '${{ github.event.inputs.head_sha || github.event.workflow_run.head_sha || github.sha }}'
+          SHA: '${{ needs.download_repo_name.outputs.head_sha || github.event.inputs.head_sha || github.event.workflow_run.head_sha || github.sha }}'
         shell: 'bash'
         run: |
           echo "REPO=$REPO" >> "$GITHUB_OUTPUT"
@@ -100,19 +110,20 @@ jobs:
   set_pending_status:
     runs-on: 'gemini-cli-ubuntu-16-core'
     permissions: 'write-all'
-    if: "github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_run'"
     needs:
       - 'parse_run_context'
+    if: "github.repository == 'google-gemini/gemini-cli' && always()"
     steps:
       - name: 'Set pending status'
         uses: 'myrotvorets/set-commit-status-action@16037e056d73b2d3c88e37e393ff369047f70886' # ratchet:myrotvorets/set-commit-status-action@master
-        if: 'always()'
+        if: "github.repository == 'google-gemini/gemini-cli' && always()"
         with:
           allowForks: 'true'
-          repo: '${{ needs.parse_run_context.outputs.repository }}'
+          repo: '${{ github.repository }}'
           sha: '${{ needs.parse_run_context.outputs.sha }}'
-          token: '${{ secrets.GITHUB_TOKEN }}'
+          token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
           status: 'pending'
+          context: 'E2E (Chained)'
 
   e2e_linux:
     name: 'E2E Test (Linux) - ${{ matrix.sandbox }}'
@@ -121,7 +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 == 'false')
+      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:
@@ -150,7 +161,7 @@ jobs:
         run: 'npm run build'
 
       - name: 'Set up Docker'
-        if: "matrix.sandbox == 'sandbox:docker'"
+        if: "${{matrix.sandbox == 'sandbox:docker'}}"
         uses: 'docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435' # ratchet:docker/setup-buildx-action@v3
 
       - name: 'Run E2E tests'
@@ -158,6 +169,7 @@ jobs:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
           KEEP_OUTPUT: 'true'
           VERBOSE: 'true'
+          BUILD_SANDBOX_FLAGS: '--cache-from type=gha --cache-to type=gha,mode=max'
         shell: 'bash'
         run: |
           if [[ "${{ matrix.sandbox }}" == "sandbox:docker" ]]; then
@@ -173,7 +185,7 @@ jobs:
       - 'parse_run_context'
     runs-on: 'macos-latest'
     if: |
-      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip == 'false')
+      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
@@ -193,11 +205,11 @@ jobs:
         run: 'npm run build'
 
       - name: 'Fix rollup optional dependencies on macOS'
-        if: "runner.os == 'macOS'"
+        if: "${{runner.os == 'macOS'}}"
         run: |
           npm cache clean --force
       - name: 'Run E2E tests (non-Windows)'
-        if: "runner.os != 'Windows'"
+        if: "${{runner.os != 'Windows'}}"
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
           KEEP_OUTPUT: 'true'
@@ -211,10 +223,8 @@ jobs:
       - 'merge_queue_skipper'
       - 'parse_run_context'
     if: |
-      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip == 'false')
+      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
@@ -254,6 +264,27 @@ jobs:
         run: 'npm run build'
         shell: 'pwsh'
 
+      - name: 'Ensure Chrome is available'
+        shell: 'pwsh'
+        run: |
+          $chromePaths = @(
+            "${env:ProgramFiles}\Google\Chrome\Application\chrome.exe",
+            "${env:ProgramFiles(x86)}\Google\Chrome\Application\chrome.exe"
+          )
+          $chromeExists = $chromePaths | Where-Object { Test-Path $_ } | Select-Object -First 1
+          if (-not $chromeExists) {
+            Write-Host 'Chrome not found, installing via Chocolatey...'
+            choco install googlechrome -y --no-progress --ignore-checksums
+          }
+          $installed = $chromePaths | Where-Object { Test-Path $_ } | Select-Object -First 1
+          if ($installed) {
+            Write-Host "Chrome found at: $installed"
+            & $installed --version
+          } else {
+            Write-Error 'Chrome installation failed'
+            exit 1
+          }
+
       - name: 'Run E2E tests'
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
@@ -266,39 +297,102 @@ jobs:
         shell: 'pwsh'
         run: 'npm run test:integration:sandbox:none'
 
+  evals:
+    name: 'Evals (ALWAYS_PASSING)'
+    needs:
+      - 'merge_queue_skipper'
+      - 'parse_run_context'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    if: |
+      github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
+        with:
+          ref: '${{ needs.parse_run_context.outputs.sha }}'
+          repository: '${{ needs.parse_run_context.outputs.repository }}'
+          fetch-depth: 0
+
+      - name: 'Set up Node.js 20.x'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
+        with:
+          node-version: '20.x'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Build project'
+        run: 'npm run build'
+
+      - name: 'Check if evals should run'
+        id: 'check_evals'
+        run: |
+          SHOULD_RUN=$(node scripts/changed_prompt.js)
+          echo "should_run=$SHOULD_RUN" >> "$GITHUB_OUTPUT"
+
+      - name: 'Run Evals (Required to pass)'
+        if: "${{ steps.check_evals.outputs.should_run == 'true' }}"
+        env:
+          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GEMINI_MODEL: 'gemini-3-pro-preview'
+          # Only run always passes behavioral tests.
+          EVAL_SUITE_TYPE: 'behavioral'
+          # Disable Vitest internal retries to avoid double-retrying;
+          # custom retry logic is handled in evals/test-helper.ts
+          VITEST_RETRY: 0
+        run: 'npm run test:always_passing_evals'
+
+      - name: 'Upload Reliability Logs'
+        if: "always() && steps.check_evals.outputs.should_run == 'true'"
+        uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
+        with:
+          name: 'eval-logs-${{ github.run_id }}-${{ github.run_attempt }}'
+          path: 'evals/logs/api-reliability.jsonl'
+          retention-days: 7
+
   e2e:
     name: 'E2E'
     if: |
-      always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip == 'false')
+      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' ]]; 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: "github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_run'"
+    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: '${{ needs.parse_run_context.outputs.repository }}'
+          repo: '${{ github.repository }}'
           sha: '${{ needs.parse_run_context.outputs.sha }}'
           token: '${{ secrets.GITHUB_TOKEN }}'
-          status: '${{ job.status }}'
+          status: '${{ needs.e2e.result }}'
+          context: 'E2E (Chained)'

.github/workflows/ci.yml

@@ -37,19 +37,22 @@ jobs:
     permissions: 'read-all'
     name: 'Merge Queue Skipper'
     runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
     outputs:
       skip: '${{ steps.merge-queue-ci-skipper.outputs.skip-check }}'
     steps:
       - id: 'merge-queue-ci-skipper'
         uses: 'cariad-tech/merge-queue-ci-skipper@1032489e59437862c90a08a2c92809c903883772' # ratchet:cariad-tech/merge-queue-ci-skipper@main
         with:
-          secret: '${{ secrets.GITHUB_TOKEN }}'
+          secret: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
 
   lint:
     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
@@ -63,9 +66,21 @@ jobs:
           node-version-file: '.nvmrc'
           cache: 'npm'
 
+      - name: 'Cache Linters'
+        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') }}"
+
       - name: 'Install dependencies'
         run: 'npm ci'
 
+      - name: 'Cache ESLint'
+        uses: 'actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830' # ratchet:actions/cache@v4
+        with:
+          path: '.eslintcache'
+          key: "${{ runner.os }}-eslint-${{ hashFiles('package-lock.json', 'eslint.config.js') }}"
+
       - name: 'Validate NOTICES.txt'
         run: 'git diff --exit-code packages/vscode-ide-companion/NOTICES.txt'
 
@@ -99,24 +114,27 @@ 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
       - name: 'Link Checker'
         uses: 'lycheeverse/lychee-action@885c65f3dc543b57c898c8099f4e08c8afd178a2' # ratchet: lycheeverse/lychee-action@v2.6.1
         with:
-          args: '--verbose ./**/*.md'
+          args: '--verbose --accept 200,503 ./**/*.md'
           fail: true
   test_linux:
-    name: 'Test (Linux)'
+    name: 'Test (Linux) - ${{ matrix.node-version }}, ${{ matrix.shard }}'
     runs-on: 'gemini-cli-ubuntu-16-core'
     needs:
-      - 'lint'
       - 'merge_queue_skipper'
-    if: "${{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'
@@ -127,6 +145,9 @@ jobs:
           - '20.x'
           - '22.x'
           - '24.x'
+        shard:
+          - 'cli'
+          - 'others'
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
@@ -140,13 +161,26 @@ 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
-        run: 'npm run test:ci'
+        run: |
+          if [[ "${{ matrix.shard }}" == "cli" ]]; then
+            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 -- --coverage.enabled=false
+            npm run test:scripts
+          fi
 
       - name: 'Bundle'
         run: 'npm run bundle'
@@ -154,6 +188,19 @@ 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'
 
@@ -162,7 +209,7 @@ jobs:
           ${{ always() && (github.event.pull_request.head.repo.full_name == github.repository) }}
         uses: 'dorny/test-reporter@dc3a92680fcc15842eef52e8c4606ea7ce6bd3f3' # ratchet:dorny/test-reporter@v2
         with:
-          name: 'Test Results (Node ${{ matrix.node-version }})'
+          name: 'Test Results (Node ${{ runner.os }}, ${{ matrix.node-version }}, ${{ matrix.shard }})'
           path: 'packages/*/junit.xml'
           reporter: 'java-junit'
           fail-on-error: 'false'
@@ -172,16 +219,15 @@ jobs:
           ${{ always() && (github.event_name == 'pull_request' && github.event.pull_request.head.repo.full_name != github.repository) }}
         uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
         with:
-          name: 'test-results-fork-${{ matrix.node-version }}-${{ runner.os }}'
+          name: 'test-results-fork-${{ runner.os }}-${{ matrix.node-version }}-${{ matrix.shard }}'
           path: 'packages/*/junit.xml'
 
   test_mac:
-    name: 'Test (Mac)'
-    runs-on: '${{ matrix.os }}'
+    name: 'Test (Mac) - ${{ matrix.node-version }}, ${{ matrix.shard }}'
+    runs-on: 'macos-latest'
     needs:
-      - 'lint'
       - 'merge_queue_skipper'
-    if: "${{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'
@@ -189,12 +235,13 @@ jobs:
     continue-on-error: true
     strategy:
       matrix:
-        os:
-          - 'macos-latest'
         node-version:
           - '20.x'
           - '22.x'
           - '24.x'
+        shard:
+          - 'cli'
+          - 'others'
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
@@ -214,7 +261,14 @@ jobs:
       - name: 'Run tests and generate reports'
         env:
           NO_COLOR: true
-        run: 'npm run test:ci -- --coverage.enabled=false'
+        run: |
+          if [[ "${{ matrix.shard }}" == "cli" ]]; then
+            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:scripts
+          fi
 
       - name: 'Bundle'
         run: 'npm run bundle'
@@ -222,6 +276,19 @@ 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'
 
@@ -230,7 +297,7 @@ jobs:
           ${{ always() && (github.event.pull_request.head.repo.full_name == github.repository) }}
         uses: 'dorny/test-reporter@dc3a92680fcc15842eef52e8c4606ea7ce6bd3f3' # ratchet:dorny/test-reporter@v2
         with:
-          name: 'Test Results (Node ${{ matrix.node-version }})'
+          name: 'Test Results (Node ${{ runner.os }}, ${{ matrix.node-version }}, ${{ matrix.shard }})'
           path: 'packages/*/junit.xml'
           reporter: 'java-junit'
           fail-on-error: 'false'
@@ -240,7 +307,7 @@ jobs:
           ${{ always() && (github.event_name == 'pull_request' && github.event.pull_request.head.repo.full_name != github.repository) }}
         uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
         with:
-          name: 'test-results-fork-${{ matrix.node-version }}-${{ runner.os }}'
+          name: 'test-results-fork-${{ runner.os }}-${{ matrix.node-version }}-${{ matrix.shard }}'
           path: 'packages/*/junit.xml'
 
       - name: 'Upload coverage reports'
@@ -248,14 +315,14 @@ jobs:
           ${{ always() }}
         uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
         with:
-          name: 'coverage-reports-${{ matrix.node-version }}-${{ matrix.os }}'
+          name: 'coverage-reports-${{ runner.os }}-${{ matrix.node-version }}-${{ matrix.shard }}'
           path: 'packages/*/coverage'
 
   codeql:
     name: 'CodeQL'
     runs-on: 'gemini-cli-ubuntu-16-core'
     needs: 'merge_queue_skipper'
-    if: "${{needs.merge_queue_skipper.outputs.skip == 'false'}}"
+    if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
     permissions:
       actions: 'read'
       contents: 'read'
@@ -278,7 +345,7 @@ jobs:
   bundle_size:
     name: 'Check Bundle Size'
     needs: 'merge_queue_skipper'
-    if: "${{github.event_name == 'pull_request' && needs.merge_queue_skipper.outputs.skip == 'false'}}"
+    if: "github.repository == 'google-gemini/gemini-cli' && github.event_name == 'pull_request' && needs.merge_queue_skipper.outputs.skip == 'false'"
     runs-on: 'gemini-cli-ubuntu-16-core'
     permissions:
       contents: 'read' # For checkout
@@ -300,11 +367,16 @@ 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'
@@ -355,7 +427,17 @@ jobs:
           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'
@@ -366,27 +448,52 @@ 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/deflake.yml

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

.github/workflows/docs-audit.yml

@@ -0,0 +1,50 @@
+name: 'Weekly Docs Audit'
+
+on:
+  schedule:
+    # Runs every Monday at 00:00 UTC
+    - cron: '0 0 * * MON'
+  workflow_dispatch:
+
+jobs:
+  audit-docs:
+    runs-on: 'ubuntu-latest'
+    permissions:
+      contents: 'write'
+      pull-requests: 'write'
+
+    steps:
+      - name: 'Checkout repository'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5'
+        with:
+          fetch-depth: 0
+          ref: 'main'
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020'
+        with:
+          node-version: '20'
+
+      - name: 'Run Docs Audit with Gemini'
+        uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31'
+        with:
+          gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
+          prompt: |
+            Activate the 'docs-writer' skill.
+
+            **Task:** Execute the docs audit procedure, as defined in your 'docs-auditing.md' reference.
+
+      - name: 'Create Pull Request with Audit Results'
+        uses: 'peter-evans/create-pull-request@c5a7806660adbe173f04e3e038b0ccdcd758773c'
+        with:
+          token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
+          commit-message: 'docs: weekly audit results for ${{ github.run_id }}'
+          title: 'Docs Audit for Week of ${{ github.event.schedule }}'
+          body: |
+            This PR contains the auto-generated documentation audit for the week. It includes a new `audit-results-*.md` file with findings and any direct fixes applied by the agent.
+
+            Please review the suggestions and merge.
+          branch: 'docs-audit-${{ github.run_id }}'
+          base: 'main'
+          team-reviewers: 'gemini-cli-docs, gemini-cli-maintainers'
+          delete-branch: true

.github/workflows/docs-page-action.yml

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

.github/workflows/docs-rebuild.yml

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

.github/workflows/e2e.yml

@@ -1,247 +0,0 @@
-name: 'Testing: E2E'
-
-on:
-  push:
-    branches:
-      - 'main'
-  # This will run for PRs from the base repository, providing secrets.
-  pull_request:
-    branches:
-      - 'main'
-      - 'release/**'
-  # This will run for PRs from forks when a label is added.
-  pull_request_target:
-    types: ['labeled']
-  merge_group:
-  workflow_dispatch:
-    inputs:
-      branch_ref:
-        description: 'Branch to run on'
-        required: true
-        default: 'main'
-        type: 'string'
-
-concurrency:
-  group: '${{ github.workflow }}-${{ github.head_ref || github.ref }}'
-  cancel-in-progress: |-
-    ${{ github.ref != 'refs/heads/main' && !startsWith(github.ref, 'refs/heads/release/') }}
-
-jobs:
-  merge_queue_skipper:
-    name: 'Merge Queue Skipper'
-    runs-on: 'gemini-cli-ubuntu-16-core'
-    permissions: 'read-all'
-    outputs:
-      skip: '${{ steps.merge-queue-e2e-skipper.outputs.skip-check }}'
-    steps:
-      - id: 'merge-queue-e2e-skipper'
-        uses: 'cariad-tech/merge-queue-ci-skipper@1032489e59437862c90a08a2c92809c903883772' # ratchet:cariad-tech/merge-queue-ci-skipper@main
-        with:
-          secret: '${{ secrets.GITHUB_TOKEN }}'
-    continue-on-error: true
-
-  e2e_linux:
-    name: 'E2E Test (Linux) - ${{ matrix.sandbox }}'
-    needs: 'merge_queue_skipper'
-    if: |
-      (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip == 'false') &&
-      (github.event_name == 'push' ||
-      github.event_name == 'merge_group' ||
-      github.event_name == 'workflow_dispatch' ||
-      (github.event.pull_request.head.repo.full_name == github.repository) ||
-      (github.event.label.name == 'maintainer:e2e:ok'))
-    runs-on: 'gemini-cli-ubuntu-16-core'
-    strategy:
-      fail-fast: false
-      matrix:
-        sandbox:
-          - 'sandbox:none'
-          - 'sandbox:docker'
-        node-version:
-          - '20.x'
-
-    steps:
-      - name: 'Checkout (fork)'
-        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
-        if: "github.event_name == 'pull_request_target'"
-        with:
-          ref: '${{ github.event.pull_request.head.sha }}'
-          repository: '${{ github.event.pull_request.head.repo.full_name }}'
-
-      - name: 'Checkout (internal)'
-        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
-        if: "github.event_name != 'pull_request_target'"
-        with:
-          ref: '${{ github.event.inputs.branch_ref || github.ref }}'
-
-      - name: 'Set up Node.js ${{ matrix.node-version }}'
-        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
-        with:
-          node-version: '${{ matrix.node-version }}'
-
-      - name: 'Install dependencies'
-        run: 'npm ci'
-
-      - name: 'Build project'
-        run: 'npm run build'
-
-      - name: 'Set up Docker'
-        if: "matrix.sandbox == 'sandbox:docker'"
-        uses: 'docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435' # ratchet:docker/setup-buildx-action@v3
-
-      - name: 'Run E2E tests'
-        env:
-          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          KEEP_OUTPUT: 'true'
-          VERBOSE: 'true'
-        shell: 'bash'
-        run: |
-          if [[ "${{ matrix.sandbox }}" == "sandbox:docker" ]]; then
-            npm run test:integration:sandbox:docker
-          else
-            npm run test:integration:sandbox:none
-          fi
-
-  e2e_mac:
-    name: 'E2E Test (macOS)'
-    needs: 'merge_queue_skipper'
-    if: |
-      (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip == 'false') &&
-      (github.event_name == 'push' ||
-      github.event_name == 'merge_group' ||
-      github.event_name == 'workflow_dispatch' ||
-      (github.event.pull_request.head.repo.full_name == github.repository) ||
-      (github.event.label.name == 'maintainer:e2e:ok'))
-    runs-on: 'macos-latest'
-    steps:
-      - name: 'Checkout (fork)'
-        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
-        if: "github.event_name == 'pull_request_target'"
-        with:
-          ref: '${{ github.event.pull_request.head.sha }}'
-          repository: '${{ github.event.pull_request.head.repo.full_name }}'
-
-      - name: 'Checkout (internal)'
-        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
-        if: "github.event_name != 'pull_request_target'"
-        with:
-          ref: '${{ github.event.inputs.branch_ref || github.ref }}'
-
-      - name: 'Set up Node.js 20.x'
-        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
-        with:
-          node-version: '20.x'
-
-      - name: 'Install dependencies'
-        run: 'npm ci'
-
-      - name: 'Build project'
-        run: 'npm run build'
-
-      - name: 'Fix rollup optional dependencies on macOS'
-        if: "runner.os == 'macOS'"
-        run: |
-          npm cache clean --force
-      - name: 'Run E2E tests (non-Windows)'
-        if: "runner.os != 'Windows'"
-        env:
-          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          KEEP_OUTPUT: 'true'
-          SANDBOX: 'sandbox:none'
-          VERBOSE: 'true'
-        run: 'npm run test:integration:sandbox:none'
-
-  e2e_windows:
-    name: 'Slow E2E - Win'
-    needs: 'merge_queue_skipper'
-    if: |
-      (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip == 'false') &&
-      (github.event_name == 'push' ||
-      github.event_name == 'merge_group' ||
-      github.event_name == 'workflow_dispatch' ||
-      (github.event.pull_request.head.repo.full_name == github.repository) ||
-      (github.event.label.name == 'maintainer:e2e:ok'))
-    runs-on: 'gemini-cli-windows-16-core'
-    continue-on-error: true
-
-    steps:
-      - name: 'Checkout (fork)'
-        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
-        if: "github.event_name == 'pull_request_target'"
-        with:
-          ref: '${{ github.event.pull_request.head.sha }}'
-          repository: '${{ github.event.pull_request.head.repo.full_name }}'
-
-      - name: 'Checkout (internal)'
-        uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
-        if: "github.event_name != 'pull_request_target'"
-        with:
-          ref: '${{ github.event.inputs.branch_ref || github.ref }}'
-
-      - name: 'Set up Node.js 20.x'
-        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
-        with:
-          node-version: '20.x'
-          cache: 'npm'
-
-      - name: 'Configure Windows Defender exclusions'
-        run: |
-          Add-MpPreference -ExclusionPath $env:GITHUB_WORKSPACE -Force
-          Add-MpPreference -ExclusionPath "$env:GITHUB_WORKSPACE\node_modules" -Force
-          Add-MpPreference -ExclusionPath "$env:GITHUB_WORKSPACE\packages" -Force
-          Add-MpPreference -ExclusionPath "$env:TEMP" -Force
-        shell: 'pwsh'
-
-      - name: 'Configure npm for Windows performance'
-        run: |
-          npm config set progress false
-          npm config set audit false
-          npm config set fund false
-          npm config set loglevel error
-          npm config set maxsockets 32
-          npm config set registry https://registry.npmjs.org/
-        shell: 'pwsh'
-
-      - name: 'Install dependencies'
-        run: 'npm ci'
-        shell: 'pwsh'
-
-      - name: 'Build project'
-        run: 'npm run build'
-        shell: 'pwsh'
-
-      - name: 'Run E2E tests'
-        env:
-          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
-          KEEP_OUTPUT: 'true'
-          SANDBOX: 'sandbox:none'
-          VERBOSE: 'true'
-          NODE_OPTIONS: '--max-old-space-size=32768 --max-semi-space-size=256'
-          UV_THREADPOOL_SIZE: '32'
-          NODE_ENV: 'test'
-        shell: 'pwsh'
-        run: 'npm run test:integration:sandbox:none'
-
-  e2e:
-    name: 'E2E'
-    if: |
-      always() && (
-        github.event_name == 'push' ||
-        github.event_name == 'merge_group' ||
-        github.event_name == 'workflow_dispatch' ||
-        (github.event.pull_request.head.repo.full_name == github.repository) ||
-        (github.event.label.name == 'maintainer:e2e:ok')
-      )
-    needs:
-      - 'e2e_linux'
-      - 'e2e_mac'
-    runs-on: 'gemini-cli-ubuntu-16-core'
-    steps:
-      - name: 'Check E2E test results'
-        run: |
-          if [[ (${{ needs.e2e_linux.result }} != 'success' && ${{ needs.e2e_linux.result }} != 'skipped') || \
-               (${{ needs.e2e_mac.result }} != 'success' && ${{ needs.e2e_mac.result }} != 'skipped') ]]; then
-            echo "One or more E2E jobs failed."
-            exit 1
-          fi
-          echo "All required E2E jobs passed!"

.github/workflows/eval-pr.yml

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

.github/workflows/eval.yml

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

.github/workflows/evals-nightly.yml

@@ -0,0 +1,116 @@
+name: 'Evals: Nightly'
+
+on:
+  schedule:
+    - cron: '0 1 * * *' # Runs at 1 AM every day
+  workflow_dispatch:
+    inputs:
+      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
+        type: 'string'
+
+permissions:
+  contents: 'read'
+  checks: 'write'
+  actions: 'read'
+
+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'
+          - 'gemini-2.5-flash'
+          - 'gemini-2.5-flash-lite'
+        run_attempt: [1, 2, 3]
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+        with:
+          node-version-file: '.nvmrc'
+          cache: 'npm'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Build project'
+        run: 'npm run build'
+
+      - name: 'Create logs directory'
+        run: 'mkdir -p evals/logs'
+
+      - name: 'Run Evals'
+        continue-on-error: true
+        env:
+          GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
+          GEMINI_MODEL: '${{ matrix.model }}'
+          RUN_EVALS: 'true'
+          EVAL_SUITE_TYPE: "${{ github.event.inputs.suite_type || 'behavioral' }}"
+          EVAL_SUITE_NAME: '${{ github.event.inputs.suite_name }}'
+          TEST_NAME_PATTERN: '${{ github.event.inputs.test_name_pattern }}'
+          # Disable Vitest internal retries to avoid double-retrying;
+          # custom retry logic is handled in evals/test-helper.ts
+          VITEST_RETRY: 0
+        run: |
+          CMD="npm run test:all_evals"
+          PATTERN="${TEST_NAME_PATTERN}"
+
+          if [[ -n "$PATTERN" ]]; then
+            if [[ "$PATTERN" == *.ts || "$PATTERN" == *.js || "$PATTERN" == */* ]]; then
+              $CMD -- "$PATTERN"
+            else
+              $CMD -- -t "$PATTERN"
+            fi
+          else
+            $CMD
+          fi
+
+      - name: 'Upload Logs'
+        if: 'always()'
+        uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
+        with:
+          name: 'eval-logs-${{ matrix.model }}-${{ matrix.run_attempt }}'
+          path: 'evals/logs'
+          retention-days: 7
+
+  aggregate-results:
+    name: 'Aggregate Results'
+    needs: ['evals']
+    if: "github.repository == 'google-gemini/gemini-cli' && always()"
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+
+      - name: 'Download Logs'
+        uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4
+        with:
+          path: 'artifacts'
+
+      - name: 'Generate Summary'
+        env:
+          GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: 'node scripts/aggregate_evals.js artifacts >> "$GITHUB_STEP_SUMMARY"'

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

@@ -101,7 +101,6 @@ jobs:
                     "FIRESTORE_DATABASE_ID": "(default)",
                     "GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}"
                   },
-                  "enabled": true,
                   "timeout": 600000
                 }
               },

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

@@ -14,9 +14,15 @@ on:
         description: 'issue number to triage'
         required: true
         type: 'number'
+  workflow_call:
+    inputs:
+      issue_number:
+        description: 'issue number to triage'
+        required: false
+        type: 'string'
 
 concurrency:
-  group: '${{ github.workflow }}-${{ github.event.issue.number || github.event.inputs.issue_number }}'
+  group: '${{ github.workflow }}-${{ github.event.issue.number || github.event.inputs.issue_number || inputs.issue_number }}'
   cancel-in-progress: true
 
 defaults:
@@ -34,20 +40,18 @@ permissions:
 jobs:
   triage-issue:
     if: |-
-      github.repository == 'google-gemini/gemini-cli' &&
+      (github.repository == 'google-gemini/gemini-cli' || github.repository == 'google-gemini/maintainers-gemini-cli') &&
       (
         github.event_name == 'workflow_dispatch' ||
         (
           (github.event_name == 'issues' || github.event_name == 'issue_comment') &&
-          contains(github.event.issue.labels.*.name, 'status/need-triage') &&
           (github.event_name != 'issue_comment' || (
             contains(github.event.comment.body, '@gemini-cli /triage') &&
             (github.event.comment.author_association == 'OWNER' || github.event.comment.author_association == 'MEMBER' || github.event.comment.author_association == 'COLLABORATOR')
           ))
         )
       ) &&
-      !contains(github.event.issue.labels.*.name, 'area/') &&
-      !contains(github.event.issue.labels.*.name, 'priority/')
+      !contains(github.event.issue.labels.*.name, 'area/')
     timeout-minutes: 5
     runs-on: 'ubuntu-latest'
     steps:
@@ -59,10 +63,11 @@ jobs:
         with:
           github-token: '${{ secrets.GITHUB_TOKEN }}'
           script: |
+            const issueNumber = ${{ github.event.inputs.issue_number || inputs.issue_number }};
             const { data: issue } = await github.rest.issues.get({
               owner: context.repo.owner,
               repo: context.repo.repo,
-              issue_number: ${{ github.event.inputs.issue_number }},
+              issue_number: issueNumber,
             });
             core.setOutput('title', issue.title);
             core.setOutput('body', issue.body);
@@ -73,16 +78,11 @@ jobs:
         if: |-
           github.event_name == 'workflow_dispatch'
         env:
-          ISSUE_NUMBER_INPUT: '${{ github.event.inputs.issue_number }}'
+          ISSUE_NUMBER_INPUT: '${{ github.event.inputs.issue_number || inputs.issue_number }}'
           LABELS: '${{ steps.get_issue_data.outputs.labels }}'
         run: |
-          if ! echo "${LABELS}" | grep -q 'status/need-triage'; then
-            echo "Issue #${ISSUE_NUMBER_INPUT} does not have the 'status/need-triage' label. Stopping workflow."
-            exit 1
-          fi
-
-          if echo "${LABELS}" | grep -q 'area/' || echo "${LABELS}" | grep -q 'priority/'; then
-            echo "Issue #${ISSUE_NUMBER_INPUT} already has 'area/' or 'priority/' labels. Stopping workflow."
+          if echo "${LABELS}" | grep -q 'area/'; then
+            echo "Issue #${ISSUE_NUMBER_INPUT} already has 'area/' label. Stopping workflow."
             exit 1
           fi
 
@@ -93,6 +93,10 @@ jobs:
 
       - name: 'Generate GitHub App Token'
         id: 'generate_token'
+        env:
+          APP_ID: '${{ secrets.APP_ID }}'
+        if: |-
+          ${{ env.APP_ID != '' }}
         uses: 'actions/create-github-app-token@a8d616148505b5069dccd32f177bb87d7f39123b' # ratchet:actions/create-github-app-token@v2
         with:
           app-id: '${{ secrets.APP_ID }}'
@@ -103,18 +107,13 @@ jobs:
         id: 'get_labels'
         uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
         with:
-          github-token: '${{ steps.generate_token.outputs.token }}'
+          github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
           script: |-
             const { data: labels } = await github.rest.issues.listLabelsForRepo({
               owner: context.repo.owner,
               repo: context.repo.repo,
             });
             const allowedLabels = [
-              'priority/p0',
-              'priority/p1',
-              'priority/p2',
-              'priority/p3',
-              'priority/unknown',
               'area/agent',
               'area/enterprise',
               'area/non-interactive',
@@ -122,6 +121,7 @@ jobs:
               'area/security',
               'area/platform',
               'area/extensions',
+              'area/documentation',
               'area/unknown'
             ];
             const labelNames = labels.map(label => label.name).filter(name => allowedLabels.includes(name));
@@ -139,7 +139,7 @@ jobs:
           ISSUE_BODY: >-
             ${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.body || github.event.issue.body }}
           ISSUE_NUMBER: >-
-            ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.issue_number || github.event.issue.number }}
+            ${{ github.event_name == 'workflow_dispatch' && (github.event.inputs.issue_number || inputs.issue_number) || github.event.issue.number }}
           REPOSITORY: '${{ github.repository }}'
           AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
         with:
@@ -156,26 +156,27 @@ jobs:
               "telemetry": {
                 "enabled": true,
                 "target": "gcp"
-              }
+              },
+              "coreTools": [
+                "run_shell_command(echo)"
+              ]
             }
           prompt: |-
             ## Role
 
-            You are an issue triage assistant. Your role is to analyze a GitHub issue and determine the single most appropriate area/ label and the single most appropriate priority/ label based on the definitions provided.
+            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.
 
             ## Steps
             1. Review the issue title and body: ${{ env.ISSUE_TITLE }} and ${{ env.ISSUE_BODY }}.
             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. Select exactly one priority/ label that best matches the issue based on Reference 2: Priority Definitions.
-            5. Fallback Logic:
+            4. Fallback Logic:
                 - If you cannot confidently determine the correct area/ label from the definitions, you must use area/unknown.
-                - If you cannot confidently determine the correct priority/ label from the definitions, you must use priority/unknown.
-            6. Output your two selected labels in JSON format and nothing else. Example:
-                {"labels_to_set": ["area/core", "priority/p1"]}
+            5. Output your selected label in JSON format and nothing else. Example:
+                {"labels_to_set": ["area/core"]}
 
             ## Guidelines
-            - Your output must contain exactly one area/ label and exactly one priority/ label.
+            - Your output must contain exactly one area/ label.
             - Triage only the current issue based on its title and body.
             - Output only valid JSON format.
             - Do not include any explanation or additional text, just the JSON.
@@ -255,41 +256,17 @@ 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.
 
-            Reference 2: Priority Definitions
-            priority/p0: Critical / Blocker
-            - Definition: A catastrophic failure that makes the CLI unusable for most users or poses a severe security risk. This includes installation failures, authentication failures, persistent crashes, or critical security vulnerabilities.
-            - Key Questions:
-              - Is the CLI failing to install or run?
-              - Does it fail to authenticate or connect to the Gemini API, making all commands useless?
-              - Is it consistently crashing on basic, common commands?
-              - Does this represent a critical security vulnerability?
-
-            priority/p1: High
-            - Definition: A severe issue where a core feature (e.g., text generation, code generation, file processing) is unusable, failing, has severe performance degradation, or providing fundamentally incorrect output formatting (e.g., truncated text, broken JSON). Affects many users, and there is no reasonable workaround.
-            - Key Questions:
-              - Is a core feature failing for a specific, large user group (e.g., all Windows users, all users of a specific shell)?
-              - Is the CLI failing to process a supported input or misinterpreting critical flags?
-              - Is the CLI's output formatting consistently broken, making the response unusable?
-              - Is a core command or feature extremely slow, making it impractical to use?
-
-            priority/p2: Medium
-            - Definition: A moderately impactful issue causing inconvenience or a non-optimal experience, but a reasonable workaround exists. This also includes failures in non-core features.
-            - Key Questions:
-              - Is a command or flag behaving incorrectly, but the user can achieve their goal via other means?
-              - Is there a significant, non-blocking UI/UX problem in the terminal (e.g., broken progress indicators, bad terminal coloring)?
-
-            priority/p3: Low
-            - Definition: A minor, low-impact issue with minimal effect on functionality. This includes most cosmetic defects, typos in documentation, or unclear help text.
-            - Key Questions:
-              - Is this a typo in the README.md, gemini --help text, or other documentation?
-              - Is this a minor cosmetic issue (e.g., text alignment in output, an extra newline) that doesn't affect usability?
-
-            priority/unknown
-            - Description: Issues that do not clearly fit into any other defined priority/ category, or where information is too limited to make a determination. Use this when no other priority is appropriate.
-
       - name: 'Apply Labels to Issue'
         if: |-
           ${{ steps.gemini_issue_analysis.outputs.summary != '' }}
@@ -299,7 +276,7 @@ jobs:
           LABELS_OUTPUT: '${{ steps.gemini_issue_analysis.outputs.summary }}'
         uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
         with:
-          github-token: '${{ steps.generate_token.outputs.token }}'
+          github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
           script: |
             const rawOutput = process.env.LABELS_OUTPUT;
             core.info(`Raw output from model: ${rawOutput}`);
@@ -319,16 +296,29 @@ 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;
+                }
               }
             }
 
             const issueNumber = parseInt(process.env.ISSUE_NUMBER);
             const labelsToAdd = parsedLabels.labels_to_set || [];
 
-            if (labelsToAdd.length !== 2) {
-              core.setFailed(`Expected exactly 2 labels (one area/ and one priority/), but got ${labelsToAdd.length}. Labels: ${labelsToAdd.join(', ')}`);
+            if (labelsToAdd.length !== 1) {
+              core.setFailed(`Expected exactly 1 label (area/), but got ${labelsToAdd.length}. Labels: ${labelsToAdd.join(', ')}`);
               return;
             }
 
@@ -341,22 +331,6 @@ jobs:
             });
             core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}`);
 
-            // Remove the 'status/need-triage' label
-            try {
-                await github.rest.issues.removeLabel({
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    issue_number: issueNumber,
-                    name: 'status/need-triage'
-                });
-                core.info(`Successfully removed 'status/need-triage' label.`);
-            } catch (error) {
-                // If the label doesn't exist, the API call will throw a 404. We can ignore this.
-                if (error.status !== 404) {
-                    core.warning(`Failed to remove 'status/need-triage': ${error.message}`);
-                }
-            }
-
       - name: 'Post Issue Analysis Failure Comment'
         if: |-
           ${{ failure() && steps.gemini_issue_analysis.outcome == 'failure' }}
@@ -365,7 +339,7 @@ jobs:
           RUN_URL: '${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}'
         uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
         with:
-          github-token: '${{ steps.generate_token.outputs.token }}'
+          github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
           script: |-
             github.rest.issues.createComment({
               owner: context.repo.owner,

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

@@ -81,7 +81,6 @@ jobs:
                     "FIRESTORE_DATABASE_ID": "(default)",
                     "GOOGLE_APPLICATION_CREDENTIALS": "${GOOGLE_APPLICATION_CREDENTIALS}"
                   },
-                  "enabled": true,
                   "timeout": 600000
                 }
               },

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

@@ -1,12 +1,16 @@
 name: '📋 Gemini Scheduled Issue Triage'
 
 on:
+  issues:
+    types:
+      - 'opened'
+      - 'reopened'
   schedule:
     - cron: '0 * * * *' # Runs every hour
   workflow_dispatch:
 
 concurrency:
-  group: '${{ github.workflow }}'
+  group: '${{ github.workflow }}-${{ github.event.number || github.run_id }}'
   cancel-in-progress: true
 
 defaults:
@@ -35,7 +39,21 @@ jobs:
           private-key: '${{ secrets.PRIVATE_KEY }}'
           permission-issues: 'write'
 
+      - name: 'Get issue from event'
+        if: |-
+          ${{ github.event_name == 'issues' }}
+        id: 'get_issue_from_event'
+        env:
+          ISSUE_EVENT: '${{ toJSON(github.event.issue) }}'
+        run: |
+          set -euo pipefail
+          ISSUE_JSON=$(echo "$ISSUE_EVENT" | jq -c '[{number: .number, title: .title, body: .body}]')
+          echo "issues_to_triage=${ISSUE_JSON}" >> "${GITHUB_OUTPUT}"
+          echo "✅ Found issue #${{ github.event.issue.number }} from event to triage! 🎯"
+
       - name: 'Find untriaged issues'
+        if: |-
+          ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
         id: 'find_issues'
         env:
           GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
@@ -43,22 +61,26 @@ jobs:
         run: |-
           set -euo pipefail
 
-          echo '🔍 Finding issues without labels...'
-          NO_LABEL_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search 'is:open is:issue no:label' --json number,title,body)"
+          echo '🔍 Finding issues missing area labels...'
+          NO_AREA_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue -label:area/core -label:area/agent -label:area/enterprise -label:area/non-interactive -label:area/security -label:area/platform -label:area/extensions -label:area/documentation -label:area/unknown' --limit 100 --json number,title,body)"
 
-          echo '🏷️ Finding issues that need triage...'
-          NEED_TRIAGE_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
-            --search "is:open is:issue label:\"status/need-triage\""  --limit 1000 --json number,title,body)"
+          echo '🔍 Finding issues missing kind labels...'
+          NO_KIND_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue -label:kind/bug -label:kind/enhancement -label:kind/customer-issue -label:kind/question' --limit 100 --json number,title,body)"
+
+          echo '🏷️ Finding issues missing priority labels...'
+          NO_PRIORITY_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
+            --search 'is:open is:issue -label:priority/p0 -label:priority/p1 -label:priority/p2 -label:priority/p3 -label:priority/unknown' --limit 100 --json number,title,body)"
 
           echo '🔄 Merging and deduplicating issues...'
-          ISSUES="$(echo "${NO_LABEL_ISSUES}" "${NEED_TRIAGE_ISSUES}" | jq -c -s 'add | unique_by(.number)')"
+          ISSUES="$(echo "${NO_AREA_ISSUES}" "${NO_KIND_ISSUES}" "${NO_PRIORITY_ISSUES}" | jq -c -s 'add | unique_by(.number)')"
 
           echo '📝 Setting output for GitHub Actions...'
           echo "issues_to_triage=${ISSUES}" >> "${GITHUB_OUTPUT}"
 
           ISSUE_COUNT="$(echo "${ISSUES}" | jq 'length')"
-          echo "✅ Found ${ISSUE_COUNT} issues to triage! 🎯"
+          echo "✅ Found ${ISSUE_COUNT} unique issues to triage! 🎯"
 
       - name: 'Get Repository Labels'
         id: 'get_labels'
@@ -77,12 +99,13 @@ jobs:
 
       - name: 'Run Gemini Issue Analysis'
         if: |-
-          ${{ steps.find_issues.outputs.issues_to_triage != '[]' }}
+          (steps.get_issue_from_event.outputs.issues_to_triage != '' && steps.get_issue_from_event.outputs.issues_to_triage != '[]') ||
+          (steps.find_issues.outputs.issues_to_triage != '' && steps.find_issues.outputs.issues_to_triage != '[]')
         uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
         id: 'gemini_issue_analysis'
         env:
           GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
-          ISSUES_TO_TRIAGE: '${{ steps.find_issues.outputs.issues_to_triage }}'
+          ISSUES_TO_TRIAGE: '${{ steps.get_issue_from_event.outputs.issues_to_triage || steps.find_issues.outputs.issues_to_triage }}'
           REPOSITORY: '${{ github.repository }}'
           AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
         with:
@@ -116,38 +139,32 @@ jobs:
             1. You are only able to use the echo command. Review the available labels in the environment variable: "${AVAILABLE_LABELS}".
             2. Check environment variable for issues to triage: $ISSUES_TO_TRIAGE (JSON array of issues)
             3. Review the issue title, body and any comments provided in the environment variables.
-            4. Identify the most relevant labels from the existing labels, focusing on kind/*, area/*, sub-area/* and priority/*.
-            5. If the issue already has area/ label, dont try to change it. Similarly, if the issue already has a kind/ label don't change it. And if the issue already has a priority/ label do not change it for example:
-               If an issue has area/core and kind/bug  you will only add a priority/ label.
-               Instead if an issue has no labels, you will could add one lable of each kind.
+            4. Identify the most relevant labels from the existing labels, specifically focusing on area/*, kind/* and priority/*.
+            5. Label Policy:
+               - If the issue already has a kind/ label, do not change it.
+               - If the issue already has a priority/ label, do not change it.
+               - If the issue already has an area/ label, do not change it.
+               - If any of these are missing, select exactly ONE appropriate label for the missing category.
             6. Identify other applicable labels based on the issue content, such as status/*, help wanted, good first issue, etc.
-            7. For area/* and kind/* limit yourself to only the single most applicable label in each case.
-            8. Give me a single short explanation about why you are selecting each label in the process.
-            9. Output a JSON array of objects, each containing the issue number
+            7. Give me a single short explanation about why you are selecting each label in the process.
+            8. Output a JSON array of objects, each containing the issue number
                and the labels to add and remove, along with an explanation. For example:
                ```
                [
                  {
                    "issue_number": 123,
-                   "labels_to_add": ["kind/bug", "priority/p2"],
+                   "labels_to_add": ["area/core", "kind/bug", "priority/p2"],
                    "labels_to_remove": ["status/need-triage"],
-                   "explanation": "This issue is a bug that needs to be addressed with medium priority."
-                 },
-                 {
-                   "issue_number": 456,
-                   "labels_to_add": ["kind/enhancement"],
-                   "labels_to_remove": [],
-                   "explanation": "This issue is an enhancement request that could improve the user experience."
+                   "explanation": "This issue is a UI bug that needs to be addressed with medium priority."
                  }
                ]
                ```
               If an issue cannot be classified, do not include it in the output array.
-            10. For each issue please check if CLI version is present, this is usually in the output of the /about command and will look like 0.1.5
+            9. For each issue please check if CLI version is present, this is usually in the output of the /about command and will look like 0.1.5
               - Anything more than 6 versions older than the most recent should add the status/need-retesting label
-            11. If you see that the issue doesn't look like it has sufficient information recommend the status/need-information label and leave a comment politely requesting the relevant information, eg.. if repro steps are missing request for repro steps. if version information is missing request for version information into the explanation section below.
-              - After identifying appropriate labels to an issue, add "status/need-triage" label to labels_to_remove in the output.
-            12. If you think an issue might be a Priority/P0 do not apply the priority/p0 label. Instead apply a status/manual-triage label and include a note in your explanation.
-            13. If you are uncertain and have not been able to apply one each of kind/, area/ and priority/ , apply the status/manual-triage label.
+            10. If you see that the issue doesn't look like it has sufficient information recommend the status/need-information label and leave a comment politely requesting the relevant information, eg.. if repro steps are missing request for repro steps. if version information is missing request for version information into the explanation section below.
+            11. If you think an issue might be a Priority/P0 do not apply the priority/p0 label. Instead apply a status/manual-triage label and include a note in your explanation.
+            12. If you are uncertain about a category, use the area/unknown, kind/question, or priority/unknown labels as appropriate. If you are extremely uncertain, apply the status/manual-triage label.
 
             ## Guidelines
 
@@ -157,100 +174,47 @@ jobs:
               - Do not add comments or modify the issue content.
               - Do not remove the following labels maintainer, help wanted or good first issue.
               - Triage only the current issue.
-              - Identify only one area/ label
+              - Identify only one area/ label.
               - Identify only one kind/ label (Do not apply kind/duplicate or kind/parent-issue)
-              - Identify all applicable sub-area/* and priority/* labels based on the issue content. It's ok to have multiple of these.
+              - Identify only one priority/ label.
               - Once you categorize the issue if it needs information bump down the priority by 1 eg.. a p0 would become a p1 a p1 would become a p2. P2 and P3 can stay as is in this scenario.
-            Categorization Guidelines:
-            P0: Critical / Blocker
-              - A P0 bug is a catastrophic failure that demands immediate attention.
-              - To be a P0 it means almost all users are running into this issue and it is blocking users from being able to use the product.
-              - You would see this in the form of many comments from different developers on the bug.
-              - It represents a complete showstopper for a significant portion of users or for the development process itself.
-            Impact:
-              - Blocks development or testing for the entire team.
-              - Major security vulnerability that could compromise user data or system integrity.
-              - Causes data loss or corruption with no workaround.
-              - Crashes the application or makes a core feature completely unusable for all or most users in a production environment. Will it cause severe quality degration?
-              - Is it preventing contributors from contributing to the repository or is it a release blocker?
-              Qualifier: Is the main function of the software broken?
-              Example: The gemini auth login command fails with an unrecoverable error, preventing any user from authenticating and using the rest of the CLI.
-            P1: High
-              - A P1 bug is a serious issue that significantly degrades the user experience or impacts a core feature.
-              - While not a complete blocker, it's a major problem that needs a fast resolution. Feature requests are almost never P1.
-              - Once again this would be affecting many users.
-              - You would see this in the form of comments from different developers on the bug.
-              Impact:
-              - A core feature is broken or behaving incorrectly for a large number of users or large number of use cases.
-              - Review the bug details and comments to try figure out if this issue affects a large set of use cases or if it's a narrow set of use cases.
-              - Severe performance degradation making the application frustratingly slow.
-              - No straightforward workaround exists, or the workaround is difficult and non-obvious.
-              Qualifier: Is a key feature unusable or giving very wrong results?
-              Example: Gemini CLI enters a loop when making read-many-files tool call. I am unable to break out of the loop and gemini doesn't follow instructions subsequently.
-            P2: Medium
-              - A P2 bug is a moderately impactful issue. It's a noticeable problem but doesn't prevent the use of the software's main functionality.
-              Impact:
-              - Affects a non-critical feature or a smaller, specific subset of users.
-              - An inconvenient but functional workaround is available and easy to execute.
-              - Noticeable UI/UX problems that don't break functionality but look unprofessional (e.g., elements are misaligned or overlapping).
-              Qualifier: Is it an annoying but non-blocking problem?
-              Example: An error message is unclear or contains a typo, causing user confusion but not halting their workflow.
-            P3: Low
-              - A P3 bug is a minor, low-impact issue that is trivial or cosmetic. It has little to no effect on the overall functionality of the application.
-              Impact:
-              - Minor cosmetic issues like color inconsistencies, typos in documentation, or slight alignment problems on a non-critical page.
-              - An edge-case bug that is very difficult to reproduce and affects a tiny fraction of users.
-              Qualifier: Is it a "nice-to-fix" issue?
-              Example: Spelling mistakes etc.
+
+            Categorization Guidelines (Priority):
+            P0 - Urgent Blocking Issues:
+              - DO NOT APPLY THIS LABEL AUTOMATICALLY. Use status/manual-triage instead.
+              - Definition: Urgent, block a significant percentage of the user base, and prevent frequent use of the Gemini CLI.
+              - This includes core stability blockers (e.g., authentication failures, broken upgrades), critical crashes, and P0 security vulnerabilities.
+              - Impact: Blocks development or testing for the entire team; Major security vulnerability; Causes data loss or corruption with no workaround; Crashes the application or makes a core feature completely unusable for all or most users.
+              - Qualifier: Is the main function of the software broken?
+            P1 - High-Impact Issues:
+              - Definition: Affect a large number of users, blocking them from using parts of the Gemini CLI, or make the CLI frequently unusable even with workarounds available.
+              - Impact: A core feature is broken or behaving incorrectly for a large number of users or use cases; Severe performance degradation; No straightforward workaround exists.
+              - Qualifier: Is a key feature unusable or giving very wrong results?
+            P2 - Significant Issues:
+              - Definition: Affect some users significantly, such as preventing the use of certain features or authentication types.
+              - Can also be issues that many users complain about, causing annoyance or hindering daily use.
+              - Impact: Affects a non-critical feature or a smaller, specific subset of users; An inconvenient but functional workaround is available; Noticeable UI/UX problems that look unprofessional.
+              - Qualifier: Is it an annoying but non-blocking problem?
+            P3 - Low-Impact Issues:
+              - Definition: Typically usability issues that cause annoyance to a limited user base.
+              - Includes feature requests that could be addressed in the near future and may be suitable for community contributions.
+              - Impact: Minor cosmetic issues; An edge-case bug that is very difficult to reproduce and affects a tiny fraction of users.
+              - Qualifier: Is it a "nice-to-fix" issue?
+
+            Categorization Guidelines (Area):
+            area/agent: Core Agent, Tools, Memory, Sub-Agents, Hooks, Agent Quality
+            area/core: User Interface, OS Support, Core Functionality
+            area/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
+            area/platform: Build infra, Release mgmt, Testing, Eval infra, Capacity, Quota mgmt
+            area/security: security related issues
+
             Additional Context:
-              - If users are talking about issues where the model gets downgraded from pro to flash then i want you to categorize that as a performance issue
-              - This product is designed to use different models eg.. using pro, downgrading to flash etc.
-              - When users report that they dont expect the model to change those would be categorized as feature requests.
-            Definition of Areas
-            area/ux:
-              - Issues concerning user-facing elements like command usability, interactive features, help docs, and perceived performance.
-              - I am seeing my screen flicker when using Gemini CLI
-              - I am seeing the output malformed
-              - Theme changes aren't taking effect
-              - My keyboard inputs arent' being recognzied
-            area/platform:
-              - Issues related to installation, packaging, OS compatibility (Windows, macOS, Linux), and the underlying CLI framework.
-            area/background: Issues related to long-running background tasks, daemons, and autonomous or proactive agent features.
-            area/models:
-              - i am not getting a response that is reasonable or expected. this can include things like
-              - I am calling a tool and the tool is not performing as expected.
-              - i am expecting a tool to be called and it is not getting called ,
-              - Including experience when using
-              - built-in tools (e.g., web search, code interpreter, read file, writefile, etc..),
-              - Function calling issues should be under this area
-              - i am getting responses from the model that are malformed.
-              - Issues concerning Gemini quality of response and inference,
-              - Issues talking about unnecessary token consumption.
-              - Issues talking about Model getting stuck in a loop be watchful as this could be the root cause for issues that otherwise seem like model performance issues.
-              - Memory compression
-              - unexpected responses,
-              - poor quality of generated code
-            area/tools:
-              - These are primarily issues related to Model Context Protocol
-              - These are issues that mention MCP support
-              - feature requests asking for support for new tools.
-            area/core:
-              - Issues with fundamental components like command parsing, configuration management, session state, and the main API client logic. Introducing multi-modality
-            area/contribution:
-              - Issues related to improving the developer contribution experience, such as CI/CD pipelines, build scripts, and test automation infrastructure.
-            area/authentication:
-              -  Issues related to user identity, login flows, API key handling, credential storage, and access token management, unable to sign in selecting wrong authentication path etc..
-            area/security-privacy:
-              - Issues concerning vulnerability patching, dependency security, data sanitization, privacy controls, and preventing unauthorized data access.
-            area/extensibility:
-              - Issues related to the plugin system, extension APIs, or making the CLI's functionality available in other applications, github actions, ide support etc..
-            area/performance:
-              - Issues focused on model performance
-              - Issues with running out of capacity,
-              - 429 errors etc..
-              - could also pertain to latency,
-              - other general software performance like, memory usage, CPU consumption, and algorithmic efficiency.
-              - Switching models from one to the other unexpectedly.
+            - If users are talking about issues where the model gets downgraded from pro to flash then i want you to categorize that as a performance issue.
+            - This product is designed to use different models eg.. using pro, downgrading to flash etc.
+            - When users report that they dont expect the model to change those would be categorized as feature requests.
 
       - name: 'Apply Labels to Issues'
         if: |-
@@ -300,24 +264,6 @@ jobs:
                 core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}${explanation}`);
               }
 
-              if (entry.labels_to_remove && entry.labels_to_remove.length > 0) {
-                for (const label of entry.labels_to_remove) {
-                  try {
-                    await github.rest.issues.removeLabel({
-                      owner: context.repo.owner,
-                      repo: context.repo.repo,
-                      issue_number: issueNumber,
-                      name: label
-                    });
-                  } catch (error) {
-                    if (error.status !== 404) {
-                      throw error;
-                    }
-                  }
-                }
-                core.info(`Successfully removed labels for #${issueNumber}: ${entry.labels_to_remove.join(', ')}`);
-              }
-
               if (entry.explanation) {
                 await github.rest.issues.createComment({
                   owner: context.repo.owner,

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

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

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

@@ -0,0 +1,159 @@
+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: '${{ github.workflow }}'
+  cancel-in-progress: true
+
+defaults:
+  run:
+    shell: 'bash'
+
+jobs:
+  close-stale-issues:
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    runs-on: 'ubuntu-latest'
+    permissions:
+      issues: 'write'
+    steps:
+      - name: 'Generate GitHub App Token'
+        id: 'generate_token'
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+          permission-issues: 'write'
+
+      - name: 'Process Stale Issues'
+        uses: 'actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b' # ratchet:actions/github-script@v7
+        env:
+          DRY_RUN: '${{ inputs.dry_run }}'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token }}'
+          script: |
+            const dryRun = process.env.DRY_RUN === 'true';
+            if (dryRun) {
+              core.info('DRY RUN MODE ENABLED: No changes will be applied.');
+            }
+            const 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

@@ -0,0 +1,254 @@
+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'
+        env:
+          APP_ID: '${{ secrets.APP_ID }}'
+        if: |-
+          ${{ env.APP_ID != '' }}
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
+        with:
+          app-id: '${{ secrets.APP_ID }}'
+          private-key: '${{ secrets.PRIVATE_KEY }}'
+
+      - name: 'Process Stale PRs'
+        uses: 'actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b' # ratchet:actions/github-script@v7
+        env:
+          DRY_RUN: '${{ inputs.dry_run }}'
+        with:
+          github-token: '${{ steps.generate_token.outputs.token || secrets.GITHUB_TOKEN }}'
+          script: |
+            const dryRun = process.env.DRY_RUN === 'true';
+            const fourteenDaysAgo = new Date();
+            fourteenDaysAgo.setDate(fourteenDaysAgo.getDate() - 14);
+            const thirtyDaysAgo = new Date();
+            thirtyDaysAgo.setDate(thirtyDaysAgo.getDate() - 30);
+
+            // 1. Fetch maintainers for verification
+            let maintainerLogins = new Set();
+            const teams = ['gemini-cli-maintainers', 'gemini-cli-askmode-approvers', 'gemini-cli-docs'];
+
+            for (const team_slug of teams) {
+              try {
+                const members = await github.paginate(github.rest.teams.listMembersInOrg, {
+                  org: context.repo.owner,
+                  team_slug: team_slug
+                });
+                for (const m of members) maintainerLogins.add(m.login.toLowerCase());
+                core.info(`Successfully fetched ${members.length} team members from ${team_slug}`);
+              } catch (e) {
+                // Silently skip if permissions are insufficient; we will rely on author_association
+                core.debug(`Skipped team fetch for ${team_slug}: ${e.message}`);
+              }
+            }
+
+            const isMaintainer = async (login, assoc) => {
+              // Reliably identify maintainers using authorAssociation (provided by GitHub)
+              // and organization membership (if available).
+              const isTeamMember = maintainerLogins.has(login.toLowerCase());
+              const isRepoMaintainer = ['OWNER', 'MEMBER', 'COLLABORATOR'].includes(assoc);
+
+              if (isTeamMember || isRepoMaintainer) return true;
+
+              // Fallback: Check if user belongs to the 'google' or 'googlers' orgs (requires permission)
+              try {
+                const orgs = ['googlers', 'google'];
+                for (const org of orgs) {
+                  try {
+                    await github.rest.orgs.checkMembershipForUser({ org: org, username: login });
+                    return true;
+                  } catch (e) {
+                    if (e.status !== 404) throw e;
+                  }
+                }
+              } catch (e) {
+                // Gracefully ignore failures here
+              }
+
+              return false;
+            };
+
+            // 2. Fetch all open PRs
+            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 = await isMaintainer(pr.user.login, pr.author_association);
+              const isBot = pr.user.type === 'Bot' || pr.user.login.endsWith('[bot]');
+              if (maintainerPr || isBot) continue;
+
+              // Helper: Fetch labels and linked issues via GraphQL
+              const prDetailsQuery = `query($owner:String!, $repo:String!, $number:Int!) {
+                repository(owner:$owner, name:$repo) {
+                  pullRequest(number:$number) {
+                    closingIssuesReferences(first: 10) {
+                      nodes {
+                        number
+                        labels(first: 20) {
+                          nodes { name }
+                        }
+                      }
+                    }
+                  }
+                }
+              }`;
+
+              let linkedIssues = [];
+              try {
+                const res = await github.graphql(prDetailsQuery, {
+                  owner: context.repo.owner, repo: context.repo.repo, number: pr.number
+                });
+                linkedIssues = res.repository.pullRequest.closingIssuesReferences.nodes;
+              } catch (e) {
+                core.warning(`GraphQL fetch failed for PR #${pr.number}: ${e.message}`);
+              }
+
+              // Check for mentions in body as fallback (regex)
+              const body = pr.body || '';
+              const mentionRegex = /(?:#|https:\/\/github\.com\/[^\/]+\/[^\/]+\/issues\/)(\d+)/i;
+              const matches = body.match(mentionRegex);
+              if (matches && linkedIssues.length === 0) {
+                const issueNumber = parseInt(matches[1]);
+                try {
+                  const { data: issue } = await github.rest.issues.get({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: issueNumber
+                  });
+                  linkedIssues = [{ number: issueNumber, labels: { nodes: issue.labels.map(l => ({ name: l.name })) } }];
+                } catch (e) {}
+              }
+
+              // 3. Enforcement Logic
+              const prLabels = pr.labels.map(l => l.name.toLowerCase());
+              const hasHelpWanted = prLabels.includes('help wanted') ||
+                                    linkedIssues.some(issue => issue.labels.nodes.some(l => l.name.toLowerCase() === 'help wanted'));
+
+              const hasMaintainerOnly = prLabels.includes('🔒 maintainer only') ||
+                                        linkedIssues.some(issue => issue.labels.nodes.some(l => l.name.toLowerCase() === '🔒 maintainer only'));
+
+              const hasLinkedIssue = linkedIssues.length > 0;
+
+              // Closure Policy: No help-wanted label = Close after 14 days
+              if (pr.state === 'open' && !hasHelpWanted && !hasMaintainerOnly) {
+                const prCreatedAt = new Date(pr.created_at);
+
+                // We give a 14-day grace period for non-help-wanted PRs to be manually reviewed/labeled by an EM
+                if (prCreatedAt > fourteenDaysAgo) {
+                  core.info(`PR #${pr.number} is new and lacks 'help wanted'. Giving 14-day grace period for EM review.`);
+                  continue;
+                }
+
+                core.info(`PR #${pr.number} is older than 14 days and lacks 'help wanted' association. Closing.`);
+                if (!dryRun) {
+                  await github.rest.issues.createComment({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    issue_number: pr.number,
+                    body: "Hi there! Thank you for your interest in contributing to Gemini CLI. \n\nTo ensure we maintain high code quality and focus on our prioritized roadmap, we have updated our contribution policy (see [Discussion #17383](https://github.com/google-gemini/gemini-cli/discussions/17383)). \n\n**We only *guarantee* review and consideration of pull requests for issues that are explicitly labeled as 'help wanted'.** All other community pull requests are subject to closure after 14 days if they do not align with our current focus areas. For this reason, we strongly recommend that contributors only submit pull requests against issues explicitly labeled as **'help-wanted'**. \n\nThis pull request is being closed as it has been open for 14 days without a 'help wanted' designation. We encourage you to find and contribute to existing 'help wanted' issues in our backlog! Thank you for your understanding and for being part of our community!"
+                  });
+                  await github.rest.pulls.update({
+                    owner: context.repo.owner,
+                    repo: context.repo.repo,
+                    pull_number: pr.number,
+                    state: 'closed'
+                  });
+                }
+                continue;
+              }
+
+              // Also check for linked issue even if it has help wanted (redundant but safe)
+              if (pr.state === 'open' && !hasLinkedIssue) {
+                 // Already covered by hasHelpWanted check above, but good for future-proofing
+                 continue;
+              }
+
+              // 4. Staleness Check (Scheduled only)
+              if (pr.state === 'open' && context.eventName !== 'pull_request') {
+                // Skip PRs that were created less than 30 days ago - they cannot be stale yet
+                const prCreatedAt = new Date(pr.created_at);
+                if (prCreatedAt > thirtyDaysAgo) continue;
+
+                let lastActivity = new Date(pr.created_at);
+                try {
+                  const reviews = await github.paginate(github.rest.pulls.listReviews, {
+                    owner: context.repo.owner, repo: context.repo.repo, pull_number: pr.number
+                  });
+                  for (const r of reviews) {
+                    if (await 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 (await isMaintainer(c.user.login, c.author_association)) {
+                      const d = new Date(c.updated_at);
+                      if (d > lastActivity) lastActivity = d;
+                    }
+                  }
+                } catch (e) {}
+
+                if (lastActivity < thirtyDaysAgo) {
+                  const labels = pr.labels.map(l => l.name.toLowerCase());
+                  const isProtected = labels.includes('help wanted') || labels.includes('🔒 maintainer only');
+                  if (isProtected) {
+                    core.info(`PR #${pr.number} is stale but has a protected label. Skipping closure.`);
+                    continue;
+                  }
+
+                  core.info(`PR #${pr.number} is stale (no maintainer activity for 30+ days). Closing.`);
+                  if (!dryRun) {
+                    await github.rest.issues.createComment({
+                      owner: context.repo.owner,
+                      repo: context.repo.repo,
+                      issue_number: pr.number,
+                      body: "Hi there! Thank you for your contribution. To keep our backlog manageable, we are closing pull requests that haven't seen maintainer activity for 30 days. If you're still working on this, please let us know!"
+                    });
+                    await github.rest.pulls.update({
+                      owner: context.repo.owner,
+                      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/issue-opened-labeler.yml

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

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

@@ -0,0 +1,57 @@
+name: 'Label Child Issues for Project Rollup'
+
+on:
+  issues:
+    types: ['opened', 'edited', 'reopened']
+  schedule:
+    - cron: '0 * * * *' # Run every hour
+  workflow_dispatch:
+
+permissions:
+  issues: 'write'
+  contents: 'read'
+
+jobs:
+  # Event-based: Quick reaction to new/edited issues in THIS repo
+  labeler:
+    if: "github.repository == 'google-gemini/gemini-cli' && github.event_name == 'issues'"
+    runs-on: 'ubuntu-latest'
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
+
+      - 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 Multi-Repo Sync Script'
+        env:
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: 'node .github/scripts/sync-maintainer-labels.cjs'
+
+  # Scheduled/Manual: Recursive sync across multiple repos
+  sync-maintainer-labels:
+    if: "github.repository == 'google-gemini/gemini-cli' && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')"
+    runs-on: 'ubuntu-latest'
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
+
+      - name: 'Setup Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+
+      - name: 'Install Dependencies'
+        run: 'npm ci'
+
+      - name: 'Run Multi-Repo Sync Script'
+        env:
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: 'node .github/scripts/sync-maintainer-labels.cjs'

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

@@ -0,0 +1,175 @@
+name: 'Label Workstream Rollup'
+
+on:
+  issues:
+    types: ['opened', 'edited', 'reopened']
+  schedule:
+    - cron: '0 * * * *'
+  workflow_dispatch:
+
+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@f28e40c7f34bde8b3046d885e986cb6290c5673b' # ratchet:actions/github-script@v7
+        with:
+          script: |
+            const labelToAdd = 'workstream-rollup';
+
+            // Allow-list of parent issue URLs
+            const allowedParentUrls = [
+              'https://github.com/google-gemini/gemini-cli/issues/15374',
+              'https://github.com/google-gemini/gemini-cli/issues/15456',
+              'https://github.com/google-gemini/gemini-cli/issues/15324',
+              'https://github.com/google-gemini/gemini-cli/issues/17202',
+              'https://github.com/google-gemini/gemini-cli/issues/17203'
+            ];
+
+            // Single issue processing (for event triggers)
+            async function processSingleIssue(owner, repo, number) {
+              const query = `
+                query($owner:String!, $repo:String!, $number:Int!) {
+                  repository(owner:$owner, name:$repo) {
+                    issue(number:$number) {
+                      number
+                      parent {
+                        url
+                        parent {
+                          url
+                          parent {
+                            url
+                            parent {
+                              url
+                              parent {
+                                url
+                              }
+                            }
+                          }
+                        }
+                      }
+                    }
+                  }
+                }
+              `;
+              try {
+                const result = await github.graphql(query, { owner, repo, number });
+
+                if (!result || !result.repository || !result.repository.issue) {
+                  console.log(`Issue #${number} not found or data missing.`);
+                  return;
+                }
+
+                const issue = result.repository.issue;
+                await checkAndLabel(issue, owner, repo);
+              } catch (error) {
+                console.error(`Failed to process issue #${number}:`, error);
+                throw error; // Re-throw to be caught by main execution
+              }
+            }
+
+            // Bulk processing (for schedule/dispatch)
+            async function processAllOpenIssues(owner, repo) {
+              const query = `
+                query($owner:String!, $repo:String!, $cursor:String) {
+                  repository(owner:$owner, name:$repo) {
+                    issues(first: 100, states: OPEN, after: $cursor) {
+                      pageInfo {
+                        hasNextPage
+                        endCursor
+                      }
+                      nodes {
+                        number
+                        parent {
+                          url
+                          parent {
+                            url
+                            parent {
+                              url
+                              parent {
+                                url
+                                parent {
+                                  url
+                                }
+                              }
+                            }
+                          }
+                        }
+                      }
+                    }
+                  }
+                }
+              `;
+
+              let hasNextPage = true;
+              let cursor = null;
+
+              while (hasNextPage) {
+                try {
+                  const result = await github.graphql(query, { owner, repo, cursor });
+
+                  if (!result || !result.repository || !result.repository.issues) {
+                     console.error('Invalid response structure from GitHub API');
+                     break;
+                  }
+
+                  const issues = result.repository.issues.nodes || [];
+
+                  console.log(`Processing batch of ${issues.length} issues...`);
+                  for (const issue of issues) {
+                    await checkAndLabel(issue, owner, repo);
+                  }
+
+                  hasNextPage = result.repository.issues.pageInfo.hasNextPage;
+                  cursor = result.repository.issues.pageInfo.endCursor;
+                } catch (error) {
+                  console.error('Failed to fetch issues batch:', error);
+                  throw error; // Re-throw to be caught by main execution
+                }
+              }
+            }
+
+            async function checkAndLabel(issue, owner, repo) {
+              if (!issue || !issue.parent) return;
+
+              let currentParent = issue.parent;
+              let tracedParents = [];
+              let matched = false;
+
+              while (currentParent) {
+                tracedParents.push(currentParent.url);
+
+                if (allowedParentUrls.includes(currentParent.url)) {
+                  console.log(`SUCCESS: Issue #${issue.number} is a descendant of ${currentParent.url}. Trace: ${tracedParents.join(' -> ')}. Adding label.`);
+                  await github.rest.issues.addLabels({
+                    owner,
+                    repo,
+                    issue_number: issue.number,
+                    labels: [labelToAdd]
+                  });
+                  matched = true;
+                  break;
+                }
+                currentParent = currentParent.parent;
+              }
+
+              if (!matched && context.eventName === 'issues') {
+                 console.log(`Issue #${issue.number} did not match any allowed workstreams. Trace: ${tracedParents.join(' -> ') || 'None'}.`);
+              }
+            }
+
+            // Main execution
+            try {
+              if (context.eventName === 'issues') {
+                console.log(`Processing single issue #${context.payload.issue.number}...`);
+                await processSingleIssue(context.repo.owner, context.repo.repo, context.payload.issue.number);
+              } else {
+                console.log(`Running for event: ${context.eventName}. Processing all open issues...`);
+                await processAllOpenIssues(context.repo.owner, context.repo.repo);
+              }
+            } catch (error) {
+              core.setFailed(`Workflow failed: ${error.message}`);
+            }

.github/workflows/links.yml

@@ -12,6 +12,8 @@ on:
 
 jobs:
   linkChecker:
+    if: |-
+      ${{ github.repository == 'google-gemini/gemini-cli' }}
     runs-on: 'ubuntu-latest'
     steps:
       - uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
@@ -20,4 +22,4 @@ jobs:
         id: 'lychee'
         uses: 'lycheeverse/lychee-action@885c65f3dc543b57c898c8099f4e08c8afd178a2' # ratchet: lycheeverse/lychee-action@v2.6.1
         with:
-          args: '--verbose --no-progress ./**/*.md'
+          args: '--verbose --no-progress --accept 200,503 ./**/*.md'

.github/workflows/memory-nightly.yml

@@ -0,0 +1,33 @@
+name: 'Memory Tests: Nightly'
+
+on:
+  schedule:
+    - cron: '0 2 * * *' # Runs at 2 AM every day
+  workflow_dispatch: # Allow manual trigger
+
+permissions:
+  contents: 'read'
+
+jobs:
+  memory-test:
+    name: 'Run Memory Usage Tests'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+        with:
+          node-version-file: '.nvmrc'
+          cache: 'npm'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Build project'
+        run: 'npm run build'
+
+      - name: 'Run Memory Tests'
+        run: 'npm run test:memory'

.github/workflows/perf-nightly.yml

@@ -0,0 +1,33 @@
+name: 'Performance Tests: Nightly'
+
+on:
+  schedule:
+    - cron: '0 3 * * *' # Runs at 3 AM every day
+  workflow_dispatch: # Allow manual trigger
+
+permissions:
+  contents: 'read'
+
+jobs:
+  perf-test:
+    name: 'Run Performance Usage Tests'
+    runs-on: 'gemini-cli-ubuntu-16-core'
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+        with:
+          node-version-file: '.nvmrc'
+          cache: 'npm'
+
+      - name: 'Install dependencies'
+        run: 'npm ci'
+
+      - name: 'Build project'
+        run: 'npm run build'
+
+      - name: 'Run Performance Tests'
+        run: 'npm run test:perf'

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

@@ -0,0 +1,133 @@
+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: |-
+          ${{ env.APP_ID != '' }}
+        uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
+        with:
+          app-id: '${{ 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
+            // Check team membership (most reliable for private org members)
+            let isTeamMember = false;
+            const teams = ['gemini-cli-maintainers', 'gemini-cli-askmode-approvers', 'gemini-cli-docs'];
+            for (const team_slug of teams) {
+              try {
+                const members = await github.paginate(github.rest.teams.listMembersInOrg, {
+                  org: org,
+                  team_slug: team_slug
+                });
+                if (members.some(m => m.login.toLowerCase() === username.toLowerCase())) {
+                  isTeamMember = true;
+                  core.info(`${username} is a member of ${team_slug}. No notification needed.`);
+                  break;
+                }
+              } catch (e) {
+                core.warning(`Failed to fetch team members from ${team_slug}: ${e.message}`);
+              }
+            }
+
+            if (isTeamMember) return;
+
+            // Check author_association from webhook payload
+            const authorAssociation = context.payload.pull_request.author_association;
+            const isRepoMaintainer = ['OWNER', 'MEMBER', 'COLLABORATOR'].includes(authorAssociation);
+
+            if (isRepoMaintainer) {
+              core.info(`${username} is a maintainer (author_association: ${authorAssociation}). No notification needed.`);
+              return;
+            }
+
+            // Check if author is a Googler
+            const isGoogler = async (login) => {
+              try {
+                const orgs = ['googlers', 'google'];
+                for (const org of orgs) {
+                  try {
+                    await github.rest.orgs.checkMembershipForUser({
+                      org: org,
+                      username: login
+                    });
+                    return true;
+                  } catch (e) {
+                    if (e.status !== 404) throw e;
+                  }
+                }
+              } catch (e) {
+                core.warning(`Failed to check org membership for ${login}: ${e.message}`);
+              }
+              return false;
+            };
+
+            if (await isGoogler(username)) {
+              core.info(`${username} is a Googler. 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/release-change-tags.yml

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

.github/workflows/release-manual.yml

@@ -47,6 +47,7 @@ on:
 
 jobs:
   release:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     runs-on: 'ubuntu-latest'
     environment: "${{ github.event.inputs.environment || 'prod' }}"
     permissions:
@@ -110,6 +111,7 @@ jobs:
           wombat-token-cli: '${{ secrets.WOMBAT_TOKEN_CLI }}'
           wombat-token-a2a-server: '${{ secrets.WOMBAT_TOKEN_A2A_SERVER }}'
           github-token: '${{ secrets.GITHUB_TOKEN }}'
+          github-release-token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
           dry-run: '${{ github.event.inputs.dry_run }}'
           previous-tag: '${{ steps.release_info.outputs.PREVIOUS_TAG }}'
           skip-github-release: '${{ github.event.inputs.skip_github_release }}'
@@ -132,4 +134,4 @@ jobs:
           gh issue create \
             --title 'Manual Release Failed for ${RELEASE_TAG} on $(date +'%Y-%m-%d')' \
             --body 'The manual release workflow failed. See the full run for details: ${DETAILS_URL}' \
-            --label 'kind/bug,release-failure,priority/p0'
+            --label 'release-failure,priority/p0'

.github/workflows/release-nightly.yml

@@ -31,6 +31,7 @@ on:
 
 jobs:
   release:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     environment: "${{ github.event.inputs.environment || 'prod' }}"
     runs-on: 'ubuntu-latest'
     permissions:
@@ -123,6 +124,7 @@ jobs:
           wombat-token-cli: '${{ secrets.WOMBAT_TOKEN_CLI }}'
           wombat-token-a2a-server: '${{ secrets.WOMBAT_TOKEN_A2A_SERVER }}'
           github-token: '${{ secrets.GITHUB_TOKEN }}'
+          github-release-token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
           dry-run: '${{ steps.vars.outputs.is_dry_run }}'
           previous-tag: '${{ steps.nightly_version.outputs.PREVIOUS_TAG }}'
           working-directory: './release'
@@ -157,4 +159,4 @@ jobs:
           gh issue create \
             --title "Nightly Release Failed for ${RELEASE_TAG} on $(date +'%Y-%m-%d')" \
             --body "The nightly-release workflow failed. See the full run for details: ${DETAILS_URL}" \
-            --label 'kind/bug,release-failure,priority/p0'
+            --label 'release-failure,priority/p0'

.github/workflows/release-notes.yml

@@ -0,0 +1,103 @@
+# This workflow is triggered on every new release.
+# It uses Gemini to generate release notes and creates a PR with the changes.
+name: 'Generate Release Notes'
+
+on:
+  release:
+    types: ['published']
+  workflow_dispatch:
+    inputs:
+      version:
+        description: 'New version (e.g., v1.2.3)'
+        required: true
+        type: 'string'
+      body:
+        description: 'Release notes body'
+        required: true
+        type: 'string'
+      time:
+        description: 'Release time'
+        required: true
+        type: 'string'
+
+jobs:
+  generate-release-notes:
+    if: "github.repository == 'google-gemini/gemini-cli'"
+    runs-on: 'ubuntu-latest'
+    permissions:
+      contents: 'write'
+      pull-requests: 'write'
+    steps:
+      - name: 'Checkout repository'
+        uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
+        with:
+          # The user-level skills need to be available to the workflow
+          fetch-depth: 0
+          ref: 'main'
+
+      - name: 'Set up Node.js'
+        uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
+        with:
+          node-version: '20'
+
+      - name: 'Get release information'
+        id: 'release_info'
+        run: |
+          VERSION="${{ github.event.inputs.version || github.event.release.tag_name }}"
+          TIME="${{ github.event.inputs.time || github.event.release.created_at }}"
+
+          echo "VERSION=${VERSION}" >> "$GITHUB_OUTPUT"
+          echo "TIME=${TIME}" >> "$GITHUB_OUTPUT"
+
+          # Use a heredoc to preserve multiline release body
+          echo 'RAW_CHANGELOG<<EOF' >> "$GITHUB_OUTPUT"
+          printf "%s\n" "$BODY" >> "$GITHUB_OUTPUT"
+          echo 'EOF' >> "$GITHUB_OUTPUT"
+        env:
+          GH_TOKEN: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
+          BODY: '${{ github.event.inputs.body || github.event.release.body }}'
+
+      - name: 'Validate version'
+        id: 'validate_version'
+        run: |
+          if echo "${{ steps.release_info.outputs.VERSION }}" | grep -q "nightly"; then
+            echo "Nightly release detected. Stopping workflow."
+            echo "CONTINUE=false" >> "$GITHUB_OUTPUT"
+          else
+            echo "CONTINUE=true" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: 'Generate Changelog with Gemini'
+        if: "steps.validate_version.outputs.CONTINUE == 'true'"
+        uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
+        with:
+          gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
+          prompt: |
+            Activate the 'docs-changelog' skill.
+
+            **Release Information:**
+            - New Version: ${{ steps.release_info.outputs.VERSION }}
+            - Release Date: ${{ steps.release_info.outputs.TIME }}
+            - Raw Changelog Data: ${{ steps.release_info.outputs.RAW_CHANGELOG }}
+
+            Execute the release notes generation process using the information provided.
+
+            When you are done, please output your thought process and the steps you took for future debugging purposes.
+
+      - name: 'Create Pull Request'
+        if: "steps.validate_version.outputs.CONTINUE == 'true'"
+        uses: 'peter-evans/create-pull-request@c5a7806660adbe173f04e3e038b0ccdcd758773c' # ratchet:peter-evans/create-pull-request@v6
+        with:
+          token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
+          commit-message: 'docs(changelog): update for ${{ steps.release_info.outputs.VERSION }}'
+          title: 'Changelog for ${{ steps.release_info.outputs.VERSION }}'
+          body: |
+            This PR contains the auto-generated changelog for the ${{ steps.release_info.outputs.VERSION }} release.
+
+            Please review and merge.
+
+            Related to #18505
+          branch: 'changelog-${{ steps.release_info.outputs.VERSION }}'
+          base: 'main'
+          team-reviewers: 'gemini-cli-docs, gemini-cli-maintainers'
+          delete-branch: true

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

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

.github/workflows/release-patch-3-release.yml

@@ -118,6 +118,7 @@ jobs:
           ORIGINAL_RELEASE_VERSION: '${{ steps.patch_version.outputs.RELEASE_VERSION }}'
           ORIGINAL_RELEASE_TAG: '${{ steps.patch_version.outputs.RELEASE_TAG }}'
           ORIGINAL_PREVIOUS_TAG: '${{ steps.patch_version.outputs.PREVIOUS_TAG }}'
+          VARS_CLI_PACKAGE_NAME: '${{ vars.CLI_PACKAGE_NAME }}'
         run: |
           echo "🔍 Verifying no concurrent patch releases have occurred..."
 
@@ -129,7 +130,7 @@ jobs:
 
           # Re-run the same version calculation script
           echo "Re-calculating version to check for changes..."
-          CURRENT_PATCH_JSON=$(node scripts/get-release-version.js --cli-package-name="${{vars.CLI_PACKAGE_NAME}}" --type=patch --patch-from="${CHANNEL}")
+          CURRENT_PATCH_JSON=$(node scripts/get-release-version.js --cli-package-name="${VARS_CLI_PACKAGE_NAME}" --type=patch --patch-from="${CHANNEL}")
           CURRENT_RELEASE_VERSION=$(echo "${CURRENT_PATCH_JSON}" | jq -r .releaseVersion)
           CURRENT_RELEASE_TAG=$(echo "${CURRENT_PATCH_JSON}" | jq -r .releaseTag)
           CURRENT_PREVIOUS_TAG=$(echo "${CURRENT_PATCH_JSON}" | jq -r .previousReleaseTag)
@@ -162,10 +163,15 @@ jobs:
       - name: 'Print Calculated Version'
         run: |-
           echo "Patch Release Summary:"
-          echo "  Release Version: ${{ steps.patch_version.outputs.RELEASE_VERSION }}"
-          echo "  Release Tag: ${{ steps.patch_version.outputs.RELEASE_TAG }}"
-          echo "  NPM Tag: ${{ steps.patch_version.outputs.NPM_TAG }}"
-          echo "  Previous Tag: ${{ steps.patch_version.outputs.PREVIOUS_TAG }}"
+          echo "  Release Version: ${STEPS_PATCH_VERSION_OUTPUTS_RELEASE_VERSION}"
+          echo "  Release Tag: ${STEPS_PATCH_VERSION_OUTPUTS_RELEASE_TAG}"
+          echo "  NPM Tag: ${STEPS_PATCH_VERSION_OUTPUTS_NPM_TAG}"
+          echo "  Previous Tag: ${STEPS_PATCH_VERSION_OUTPUTS_PREVIOUS_TAG}"
+        env:
+          STEPS_PATCH_VERSION_OUTPUTS_RELEASE_VERSION: '${{ steps.patch_version.outputs.RELEASE_VERSION }}'
+          STEPS_PATCH_VERSION_OUTPUTS_RELEASE_TAG: '${{ steps.patch_version.outputs.RELEASE_TAG }}'
+          STEPS_PATCH_VERSION_OUTPUTS_NPM_TAG: '${{ steps.patch_version.outputs.NPM_TAG }}'
+          STEPS_PATCH_VERSION_OUTPUTS_PREVIOUS_TAG: '${{ steps.patch_version.outputs.PREVIOUS_TAG }}'
 
       - name: 'Run Tests'
         if: "${{github.event.inputs.force_skip_tests != 'true'}}"
@@ -184,6 +190,7 @@ jobs:
           wombat-token-cli: '${{ secrets.WOMBAT_TOKEN_CLI }}'
           wombat-token-a2a-server: '${{ secrets.WOMBAT_TOKEN_A2A_SERVER }}'
           github-token: '${{ secrets.GITHUB_TOKEN }}'
+          github-release-token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
           dry-run: '${{ github.event.inputs.dry_run }}'
           previous-tag: '${{ steps.patch_version.outputs.PREVIOUS_TAG }}'
           gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
@@ -205,7 +212,7 @@ jobs:
           gh issue create \
             --title 'Patch Release Failed for ${RELEASE_TAG} on $(date +'%Y-%m-%d')' \
             --body 'The patch-release workflow failed. See the full run for details: ${DETAILS_URL}' \
-            --label 'kind/bug,release-failure,priority/p0'
+            --label 'release-failure,priority/p0'
 
       - name: 'Comment Success on Original PR'
         if: '${{ success() && github.event.inputs.original_pr }}'

.github/workflows/release-promote.yml

@@ -239,6 +239,7 @@ jobs:
           wombat-token-cli: '${{ secrets.WOMBAT_TOKEN_CLI }}'
           wombat-token-a2a-server: '${{ secrets.WOMBAT_TOKEN_A2A_SERVER }}'
           github-token: '${{ secrets.GITHUB_TOKEN }}'
+          github-release-token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
           dry-run: '${{ github.event.inputs.dry_run }}'
           previous-tag: '${{ needs.calculate-versions.outputs.PREVIOUS_PREVIEW_TAG }}'
           working-directory: './release'
@@ -261,7 +262,7 @@ jobs:
           gh issue create \
             --title 'Promote Release Failed for ${RELEASE_TAG} on $(date +'%Y-%m-%d')' \
             --body 'The promote-release workflow failed during preview publish. See the full run for details: ${DETAILS_URL}' \
-            --label 'kind/bug,release-failure,priority/p0'
+            --label 'release-failure,priority/p0'
 
   publish-stable:
     name: 'Publish stable'
@@ -305,6 +306,7 @@ jobs:
           wombat-token-cli: '${{ secrets.WOMBAT_TOKEN_CLI }}'
           wombat-token-a2a-server: '${{ secrets.WOMBAT_TOKEN_A2A_SERVER }}'
           github-token: '${{ secrets.GITHUB_TOKEN }}'
+          github-release-token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
           dry-run: '${{ github.event.inputs.dry_run }}'
           previous-tag: '${{ needs.calculate-versions.outputs.PREVIOUS_STABLE_TAG }}'
           working-directory: './release'
@@ -327,12 +329,13 @@ jobs:
           gh issue create \
             --title 'Promote Release Failed for ${RELEASE_TAG} on $(date +'%Y-%m-%d')' \
             --body 'The promote-release workflow failed during stable publish. See the full run for details: ${DETAILS_URL}' \
-            --label 'kind/bug,release-failure,priority/p0'
+            --label 'release-failure,priority/p0'
 
   nightly-pr:
     name: 'Create Nightly PR'
     needs: ['publish-stable', 'calculate-versions']
     runs-on: 'ubuntu-latest'
+    environment: "${{ github.event.inputs.environment || 'prod' }}"
     permissions:
       contents: 'write'
       pull-requests: 'write'
@@ -360,23 +363,28 @@ jobs:
       - name: 'Create and switch to a new branch'
         id: 'release_branch'
         run: |
-          BRANCH_NAME="chore/nightly-version-bump-${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}"
+          BRANCH_NAME="chore/nightly-version-bump-${NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION}"
           git switch -c "${BRANCH_NAME}"
           echo "BRANCH_NAME=${BRANCH_NAME}" >> "${GITHUB_OUTPUT}"
+        env:
+          NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION: '${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}'
 
       - name: 'Update package versions'
-        run: 'npm run release:version "${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}"'
+        run: 'npm run release:version "${NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION}"'
+        env:
+          NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION: '${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}'
 
       - name: 'Commit and Push package versions'
         env:
           BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'
           DRY_RUN: '${{ github.event.inputs.dry_run }}'
+          NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION: '${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}'
         run: |-
           git add package.json packages/*/package.json
           if [ -f package-lock.json ]; then
             git add package-lock.json
           fi
-          git commit -m "chore(release): bump version to ${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}"
+          git commit -m "chore(release): bump version to ${NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION}"
           if [[ "${DRY_RUN}" == "false" ]]; then
             echo "Pushing release branch to remote..."
             git push --set-upstream origin "${BRANCH_NAME}"
@@ -403,4 +411,4 @@ jobs:
           gh issue create \
             --title 'Promote Release Failed for ${RELEASE_TAG} on $(date +'%Y-%m-%d')' \
             --body 'The promote-release workflow failed during nightly PR creation. See the full run for details: ${DETAILS_URL}' \
-            --label 'kind/bug,release-failure,priority/p0'
+            --label 'release-failure,priority/p0'

.github/workflows/release-rollback.yml

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

.github/workflows/release-sandbox.yml

@@ -16,6 +16,7 @@ on:
 
 jobs:
   build:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     runs-on: 'ubuntu-latest'
     permissions:
       contents: 'read'
@@ -46,4 +47,4 @@ jobs:
           gh issue create \
             --title 'Sandbox Release Failed on $(date +'%Y-%m-%d')' \
             --body 'The sandbox-release workflow failed. See the full run for details: ${DETAILS_URL}' \
-            --label 'kind/bug,release-failure,priority/p0'
+            --label 'release-failure,priority/p0'

.github/workflows/smoke-test.yml

@@ -20,6 +20,7 @@ on:
 
 jobs:
   smoke-test:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     runs-on: 'ubuntu-latest'
     permissions:
       contents: 'write'
@@ -47,4 +48,4 @@ jobs:
           gh issue create \
             --title 'Smoke test failed on ${REF} @ $(date +'%Y-%m-%d')' \
             --body 'Smoke test build failed. See the full run for details: ${DETAILS_URL}' \
-            --label 'kind/bug,priority/p0'
+            --label 'priority/p0'

.github/workflows/stale.yml

@@ -40,5 +40,5 @@ jobs:
             If this is still relevant, you are welcome to reopen or leave a comment. Thanks for contributing!
           days-before-stale: 60
           days-before-close: 14
-          exempt-issue-labels: 'pinned,security'
-          exempt-pr-labels: 'pinned,security'
+          exempt-issue-labels: 'pinned,security,🔒 maintainer only,help wanted,🗓️ Public Roadmap'
+          exempt-pr-labels: 'pinned,security,🔒 maintainer only,help wanted,🗓️ Public Roadmap'

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

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

.github/workflows/trigger_e2e.yml

@@ -3,29 +3,36 @@ name: 'Trigger E2E'
 on:
   workflow_dispatch:
     inputs:
-      branch_ref:
-        description: 'Branch to run on'
-        required: true
-        default: 'main'
+      repo_name:
+        description: 'Repository name (e.g., owner/repo)'
+        required: false
         type: 'string'
+      head_sha:
+        description: 'SHA of the commit to test'
+        required: false
+        type: 'string'
+  pull_request:
 
 jobs:
   save_repo_name:
+    if: "github.repository == 'google-gemini/gemini-cli'"
     runs-on: 'gemini-cli-ubuntu-16-core'
     steps:
       - name: 'Save Repo name'
         env:
-          # Replace with github.event.pull_request.head.repo.full_name when switched to listen on pull request events. This repo name does not contain the org which is needed for checkout.
-          REPO_NAME: '${{ github.event.repository.name }}'
+          REPO_NAME: '${{ github.event.inputs.repo_name || github.event.pull_request.head.repo.full_name }}'
+          HEAD_SHA: '${{ github.event.inputs.head_sha || github.event.pull_request.head.sha }}'
         run: |
           mkdir -p ./pr
-          echo '${{ env.REPO_NAME }}' > ./pr/repo_name
+          echo "${REPO_NAME}" > ./pr/repo_name
+          echo "${HEAD_SHA}" > ./pr/head_sha
       - uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
         with:
           name: 'repo_name'
           path: 'pr/'
   trigger_e2e:
     name: 'Trigger e2e'
+    if: "github.repository == 'google-gemini/gemini-cli'"
     runs-on: 'gemini-cli-ubuntu-16-core'
     steps:
       - id: 'trigger-e2e'