Compare commits

..

158 Commits

Author SHA1 Message Date
mkorwel 99573ec504 fix(workspaces): finalize path portability and lint fixes 2026-03-23 11:27:05 -07:00
mkorwel 61034f4bc8 fix(workspaces): complete removal of legacy npm-based workflow and redundant skills 2026-03-23 11:20:15 -07:00
mkorwel 9a19cd67ea fix(workspaces): clean up distractors and fix ESM runtime errors 2026-03-23 11:15:57 -07:00
mkorwel b2fe426d90 revert: move extension manager fixes to separate branch 2026-03-19 16:44:15 -07:00
mkorwel ad14cd4466 fix(cli): add back github shorthand support 2026-03-19 16:36:36 -07:00
mkorwel 01e937fedb fix(cli): ensure git clone is used when --ref is provided 2026-03-19 16:36:28 -07:00
mkorwel bedb8552a8 fix(workspaces): use ${extensionPath} for absolute script paths in skill 2026-03-19 15:58:27 -07:00
mkorwel a03eb159e4 chore: remove old location of gemini-extension.json 2026-03-19 15:56:50 -07:00
mkorwel fc5e289f81 fix(workspaces): move gemini-extension.json back to root for git install 2026-03-19 15:53:09 -07:00
mkorwel b3848043f1 revert: remove github shorthand fix from this branch 2026-03-19 15:37:28 -07:00
mkorwel 400a0020e2 fix(workspaces): correct extension structure and portable script paths 2026-03-19 15:32:55 -07:00
mkorwel c9cc49f62f fix(cli): recognize github: and gitlab: shorthand in extension install 2026-03-19 15:20:16 -07:00
mkorwel f380aedbf8 fix(cli): move default query command to end of yargs chain to prevent subcommand shadowing 2026-03-19 11:54:53 -07:00
mkorwel 8d9c7b90e9 fix(workspaces): update setup policy sync path 2026-03-19 10:19:07 -07:00
mkorwel 0218d885a1 fix(workspaces): move skill and policy to root for extension discovery 2026-03-19 10:13:12 -07:00
mkorwel df2ac184dd feat(workspaces): transform workspaces feature into a distributable extension 2026-03-19 09:53:51 -07:00
mkorwel 8cdd22d27d feat(workspaces): unify host and container paths in startup script 2026-03-19 08:07:34 -07:00
mkorwel 98913642cf feat(workspaces): use GIT_CONFIG env vars to bypass safe.directory on read-only FS 2026-03-19 01:16:22 -07:00
mkorwel bb1137d0fa feat(workspaces): enforce UID 1000 ownership and use sudo for host git ops 2026-03-19 01:15:10 -07:00
mkorwel 4591d4177a feat(workspaces): dynamically detect remote user for git operations 2026-03-19 01:14:23 -07:00
mkorwel b8343150bb feat(workspaces): unify paths and remove redundant worktree repair 2026-03-19 01:07:38 -07:00
mkorwel 80a54318ec feat(workspaces): revert shell to global gemini command 2026-03-19 01:00:20 -07:00
mkorwel f575231ab4 feat(workspaces): use local binary for shell and fix iTerm2 quoting 2026-03-19 00:58:45 -07:00
mkorwel a3350a0ade feat(workspaces): silence auto-updates and improve sandbox/host info in footer 2026-03-19 00:55:49 -07:00
mkorwel c33c128568 feat(workspaces): hide tmux footer and inject local settings into remote worktree 2026-03-19 00:52:49 -07:00
mkorwel 368b80d461 fix(workspaces): restore authEnv variable in orchestrator 2026-03-19 00:50:32 -07:00
mkorwel 8ffa185949 feat(workspaces): enable true color support in remote sessions 2026-03-19 00:49:24 -07:00
mkorwel 9bb8e702b9 feat(workspaces): sync local theme and UI settings to remote worker 2026-03-19 00:44:39 -07:00
mkorwel c2022d1651 fix(workspaces): disable folder trust and auto-updates on remote worker 2026-03-19 00:41:29 -07:00
mkorwel e82781ca7d scdript 2026-03-19 00:25:25 -07:00
mkorwel 7d11fdeb8c feat(workspaces): implement unified scripts/workspaces.ts entry point and simplify commands 2026-03-19 00:21:41 -07:00
mkorwel 0df26997b4 feat(workspaces): support --open flag for terminal target selection 2026-03-19 00:09:16 -07:00
mkorwel a8b48c0572 feat(workspaces): implement workspace:shell command for ad-hoc interactive sessions 2026-03-19 00:06:08 -07:00
mkorwel 864090313f feat(workspaces): mount gh config for secure authentication 2026-03-18 23:57:12 -07:00
mkorwel 63faf92440 feat(workspaces): implement remote worktree repair and .env injection 2026-03-18 23:56:35 -07:00
mkorwel 2f1175b9fe feat(workspaces): consolidate cleanup commands and add safety confirmations 2026-03-18 23:42:51 -07:00
mkorwel f42f366ca4 fix(workspaces): add workspace:prune alias for cleanup 2026-03-18 23:36:52 -07:00
mkorwel a4ba716281 feat(workspaces): include docker and image pruning in bulk cleanup 2026-03-18 23:32:59 -07:00
mkorwel ba824a1aba fix(workspaces): update cleanup paths for unified architecture 2026-03-18 23:31:52 -07:00
mkorwel 48fe995b55 feat(workspaces): darken tmux status bar and add pruning docs 2026-03-18 23:30:40 -07:00
mkorwel 8228b6518e feat(workspaces): customize tmux status bar for better UX and session ID 2026-03-18 23:27:20 -07:00
mkorwel 6414594a4c fix(workspaces): restore tmux for persistent sessions 2026-03-18 23:22:00 -07:00
mkorwel da36bb8d01 docs(workspaces): add npx tsx constraint to SKILL.md 2026-03-18 23:11:21 -07:00
mkorwel 4e19e9ac56 fix(workspaces): clean up setup prompt UX 2026-03-18 23:07:45 -07:00
mkorwel 8530083a98 fix(workspaces): link workspace:status directly to local script and clean up fleet.ts 2026-03-18 23:03:00 -07:00
mkorwel f3b4256812 fix(workspaces): correct remote path for fleet status 2026-03-18 22:58:57 -07:00
mkorwel 08d3646ace fix(workspaces): add missing frontmatter to SKILL.md for discovery 2026-03-18 22:06:46 -07:00
mkorwel dfbe583050 docs(workspaces): update onboarding to reflect unified architecture and npx usage 2026-03-18 21:57:27 -07:00
mkorwel 8cd24bf667 fix(workspaces): resolve auth and path issues for remote reviews 2026-03-18 21:52:41 -07:00
mkorwel c4c5d4e956 feat(workspaces): unify architecture and improve auth UX 2026-03-18 21:43:07 -07:00
mkorwel a1763a3e44 feat(workspaces): improve prompt UX for sensitive defaults and mask API keys 2026-03-18 13:41:47 -07:00
mkorwel 466867b593 feat(workspaces): implement intelligent authentication switching and restore sync logic 2026-03-18 13:38:50 -07:00
mkorwel 85dd66e749 fix(workspaces): resolve setup variable scope and initialization order issues 2026-03-18 12:47:05 -07:00
mkorwel 911466bd03 feat(workspaces): implement resume logic and environment-based auth for faster setup 2026-03-18 12:41:36 -07:00
mkorwel 15db44f9ec fix(workspaces): apply sudo to all remote sync calls in setup 2026-03-18 12:39:36 -07:00
mkorwel fd8755d292 fix(workspaces): implement sudo support for rsync to resolve remote permission issues 2026-03-18 12:35:46 -07:00
mkorwel 489b36d5b2 fix(workspaces): sync credentials into isolated config directory for remote auth 2026-03-18 12:32:35 -07:00
mkorwel 496a85f46b fix(workspaces): ensure container user owns configuration directories 2026-03-18 12:28:34 -07:00
mkorwel c6915fbfc1 fix(workspaces): add missing os import in setup.ts 2026-03-18 12:20:19 -07:00
mkorwel e23cbdc258 fix(workspaces): fix invalid gemini args and initialize remote auth settings 2026-03-18 12:16:59 -07:00
mkorwel f3a2457af3 feat(workspaces): ask for existing PAT before suggesting creation 2026-03-18 12:00:50 -07:00
mkorwel 93b58feb9b fix(workspaces): move git setup to host and fix path pluralization 2026-03-18 11:56:44 -07:00
mkorwel fe79087d7a perf(workspaces): use GraphQL for instantaneous fork discovery 2026-03-18 11:38:39 -07:00
mkorwel c63c0d0422 fix(workspaces): improve fork discovery using GitHub API for accurate identification 2026-03-18 11:32:29 -07:00
mkorwel c91e00e0ed feat(workspaces): implement interactive fork selection and management 2026-03-18 11:27:30 -07:00
mkorwel d20923953a feat(workspaces): add interactive fork creation to setup 2026-03-18 11:26:19 -07:00
mkorwel 0bf765bae0 feat(workspaces): implement foreground, background, and iterm2 UI targets 2026-03-18 11:23:29 -07:00
mkorwel d28188bf12 feat(workspaces): transform offload into repository-agnostic Gemini Workspaces 2026-03-18 11:18:53 -07:00
mkorwel 494425cdc4 feat(offload): implement phased, turn-key configuration and onboarding 2026-03-18 11:03:56 -07:00
mkorwel 5dfc91cca5 fix(offload): implement robust fork detection and refine boot disk allocation 2026-03-18 11:01:40 -07:00
mkorwel 32e3d3e68e fix(offload): add missing os import in GceCosProvider 2026-03-18 10:52:22 -07:00
mkorwel 82bf2e6d5f fix(offload): use metadata-from-file for robust startup script deployment 2026-03-18 10:50:33 -07:00
mkorwel 822f478d9b fix(offload): switch to global gemini binary for remote execution 2026-03-18 10:42:05 -07:00
mkorwel 7f8bd31b08 feat(offload): bundle full dev toolset including nightly gemini into image 2026-03-17 22:02:41 -07:00
mkorwel 0fac6b9ecf fix(offload): add binary validation logging to remote worker 2026-03-17 21:59:43 -07:00
mkorwel ae387866c5 fix(offload): increase entrypoint verbosity for easier debugging 2026-03-17 21:56:25 -07:00
mkorwel 51f1ebecbd fix(offload): resolve rsync permission errors and refine remote ownership 2026-03-17 21:48:23 -07:00
mkorwel e7d3860d40 fix(offload): use OSC 8 for magic link rendering to prevent line splitting 2026-03-17 21:44:34 -07:00
mkorwel cf86172c14 Merge remote-tracking branch 'origin/main' into mk-offload 2026-03-17 21:30:23 -07:00
mkorwel 16dd840215 fix(offload): correct script extensions for remote execution 2026-03-17 21:22:23 -07:00
mkorwel 70b3e7c786 fix(offload): restore path consistency with ~/.offload mounts 2026-03-17 15:34:13 -07:00
mkorwel bdf00c1d8c fix(offload): implement auto-update for stale containers 2026-03-17 15:25:39 -07:00
mkorwel ff56c33f64 feat(offload): add tmux and docker to maintainer image 2026-03-17 15:05:51 -07:00
mkorwel 934ee8baf7 fix(offload): implement self-healing container health checks and fortified startup 2026-03-17 14:50:29 -07:00
mkorwel 35e358535c feat(offload): finalize verified single-command onboarding flow 2026-03-17 14:46:49 -07:00
mkorwel 38f1627e9b fix(offload): add sudo to docker commands for COS compatibility 2026-03-17 14:03:30 -07:00
mkorwel 0c3f836682 fix(offload): run persistent sessions inside the container 2026-03-17 13:36:39 -07:00
mkorwel fe285a93c6 feat(offload): restore and enhance iTerm2 auto-launch UI 2026-03-17 13:23:15 -07:00
mkorwel e937681cd3 docs(offload): document persistence and fix status script orchestrator 2026-03-17 13:03:40 -07:00
mkorwel bc9f0fbbd8 feat(offload): silence provisioning warnings and add --yes flag for setup 2026-03-17 10:28:18 -07:00
mkorwel 9c027a7924 feat(offload): unify onboarding flow and improve logging UX 2026-03-17 10:26:59 -07:00
mkorwel 7d3a856a1a feat(offload): finalize e2e automation and corporate routing fixes 2026-03-17 10:14:27 -07:00
mkorwel 62b9b03962 docs(offload): document network research and final configuration 2026-03-16 20:03:42 -07:00
mkorwel 7c66e7e427 chore(offload): organize configuration into .gemini/offload sub-folder 2026-03-16 15:48:11 -07:00
mkorwel 0ee5d0823e feat(offload): make system project-agnostic and update docs 2026-03-16 15:42:23 -07:00
mkorwel a77f1f5e24 docs(offload): update maintainer onboarding for provider architecture 2026-03-16 15:40:59 -07:00
mkorwel cc7b7e2fbc feat(offload): implement WorkerProvider abstraction and robust IAP fallback 2026-03-16 15:33:40 -07:00
mkorwel 5786dc675d fix(offload): apply empirically verified nic0 hostname construction to setup 2026-03-16 11:23:51 -07:00
mkorwel e4db5931f4 fix(offload): ensure leading dot in DNS suffix for project isolation 2026-03-16 11:19:13 -07:00
mkorwel 3b95667e33 fix(offload): restore high-performance direct internal routing with nic0 prefix 2026-03-16 00:16:26 -07:00
mkorwel 959bb5dc9b fix(offload): add pre-sync connectivity check to trigger SSO prompts 2026-03-15 23:49:10 -07:00
mkorwel 6d81c5ece1 fix(offload): ensure leading dot in DNS suffix and use absolute container paths 2026-03-15 23:47:41 -07:00
mkorwel 31b50f9413 fix(offload): resolve ReferenceError and harden setup SSH commands 2026-03-15 23:46:27 -07:00
mkorwel 2f8caea6a4 feat(offload): implement project-isolated SSH configuration for cleaner orchestration 2026-03-15 23:44:54 -07:00
mkorwel 0edc2623a4 fix(offload): temporarily disable fork management for streamlined setup 2026-03-15 23:27:27 -07:00
mkorwel 4d791904d4 fix(offload): resolve syntax error and finalize setup script 2026-03-15 20:17:23 -07:00
mkorwel de50780ab9 fix(offload): corrected github token magic link and instructions 2026-03-15 20:15:47 -07:00
mkorwel 826f66e25b fix(offload): prevent branch/config bleeding and restore missing rsync logic 2026-03-15 18:37:56 -07:00
mkorwel 1ae0ff0508 fix(offload): finalize fork discovery and Magic Link formatting for clean setup 2026-03-15 16:41:08 -07:00
mkorwel aa6c1625c1 fix(offload): improve fork detection logic and Magic Link clickability 2026-03-15 16:31:22 -07:00
mkorwel b9b94e57ca feat(offload): implement high-performance internal routing with IAP fallback 2026-03-15 16:20:31 -07:00
mkorwel bb36fc4486 feat(offload): implement internal-only network architecture and disable external IPs 2026-03-15 13:18:15 -07:00
mkorwel 7b9a8294ee feat(offload): inject SSH keys and add disk expansion logic to provisioning 2026-03-15 13:16:28 -07:00
mkorwel fb4c413412 feat(offload): rename container to maintainer-worker and finalize COS integration 2026-03-15 12:36:48 -07:00
mkorwel db5a00489a feat(offload): restore Invisible VM architecture using Container-Optimized OS and high-performance disk 2026-03-15 12:33:45 -07:00
mkorwel edc8bfdfe4 feat(offload): address provisioning warnings and implement high-performance startup-script container 2026-03-15 12:32:22 -07:00
mkorwel b5c1b9f77b docs(offload): move architectural rationale to user-facing documentation 2026-03-15 12:13:11 -07:00
mkorwel fb8ec967c1 feat(offload): update status command for container-aware job discovery 2026-03-15 12:09:59 -07:00
mkorwel e2ad7f4ecb feat(offload): implement persistent container workstation model 2026-03-15 12:07:50 -07:00
mkorwel 0a99550c6d feat(offload): re-center on persistent workstation model and archive container logic 2026-03-15 12:06:33 -07:00
mkorwel 084eee061d feat(offload): implement Isolation 2.0 with ephemeral containers and surgical RO/RW mounts 2026-03-15 12:03:38 -07:00
mkorwel b7db77e938 feat(offload): unify host/container paths and mounts for seamless orchestration 2026-03-15 10:45:59 -07:00
mkorwel 4d063015eb feat(offload): implement full container-native support with COS and docker exec 2026-03-15 10:42:07 -07:00
mkorwel 71c5b807a3 feat(build): implement two-trigger strategy for maintainer image builds 2026-03-15 10:01:46 -07:00
mkorwel 5f26de9eae docs(offload): implement maintainer onboarding guide and link from contributing 2026-03-15 09:54:27 -07:00
mkorwel e7cf6a4baa docs(offload): mark Phase 1 as verified in mission dossier 2026-03-15 09:45:32 -07:00
mkorwel 3a0c5eef9c feat(build): implement dual-tagging strategy and update next mission dossier 2026-03-15 09:41:50 -07:00
mkorwel 3a813171f9 feat(build): isolate maintainer build logic to a dedicated pipeline file 2026-03-15 09:40:05 -07:00
mkorwel f7837d4d42 feat(build): decouple maintainer image into dedicated Dockerfile 2026-03-15 09:17:54 -07:00
mkorwel f7d5510b8b feat(build): implement multi-stage maintainer parent image and dual-tag cloud build 2026-03-15 09:16:01 -07:00
mkorwel 162ac93f81 feat(offload): implement continuous golden image pipeline and robust fork discovery 2026-03-14 11:59:41 -07:00
mkorwel 369241d271 feat(offload): implement unified control plane with log tailing and flexible attachment 2026-03-14 11:02:27 -07:00
mkorwel 7ee56e7cfd feat(offload): finalize high-performance architecture with fast-path SSH and worktrees 2026-03-14 09:23:40 -07:00
mkorwel b13fe22582 feat(offload): implement dynamic remote home resolution for reliable rsync 2026-03-14 01:47:05 -07:00
mkorwel af9dc5be58 feat(offload): refine for OS Login and add stop command 2026-03-14 01:31:15 -07:00
mkorwel fc1b5c0247 feat(offload): remove auto-deletion and transition to persistent one-worker model 2026-03-14 00:55:18 -07:00
mkorwel 1f14f609ee feat(offload): finalize GCE-only architecture and secure fleet management 2026-03-14 00:43:53 -07:00
mkorwel 45902f5e8a feat(offload): make setup script dynamic based on remote state 2026-03-13 20:08:30 -07:00
mkorwel 12824cb21c feat(policy): remove gh pr review from allow list to ensure manual confirmation 2026-03-13 20:00:16 -07:00
mkorwel cd1699fcda feat(offload): remove browser opener and make review-pr actionable 2026-03-13 19:56:52 -07:00
mkorwel b545670bbc docs: overhaul offload README with 'why' context and add skill-specific guides 2026-03-13 19:50:13 -07:00
mkorwel d4a386c4ed chore: final cleanup of offload configuration paths and test assertions 2026-03-13 19:47:02 -07:00
mkorwel 7113c5093d docs: remove future roadmap section from offload README 2026-03-13 19:41:06 -07:00
mkorwel 295831105b feat: add 'review-pr' skill and sunset 'async-pr-review' 2026-03-13 19:39:41 -07:00
mkorwel 8692b347f0 feat(offload): modularize playbooks with TaskRunner and integrate agentic fix-pr loop 2026-03-13 19:31:32 -07:00
mkorwel 3649059a28 feat: add 'fix-pr' skill for agentic iterative PR fixing 2026-03-13 19:25:03 -07:00
mkorwel 7d85e84d17 refactor: rename deep-review to offload and generalize capabilities 2026-03-13 19:03:30 -07:00
mkorwel f7ec958a69 feat(deep-review): finalize orchestration tests and integrate into main test suite 2026-03-13 18:51:48 -07:00
mkorwel 879ad72390 feat(deep-review): add tmux check to setup and expand test suite 2026-03-13 18:48:02 -07:00
mkorwel ee4fb24004 test(deep-review): add comprehensive orchestration tests and refactor for testability 2026-03-13 18:45:06 -07:00
mkorwel d1aba65cb0 feat(deep-review): allow choice between pre-existing and isolated instances for Gemini and GH CLI 2026-03-13 18:40:14 -07:00
mkorwel 824225bfa3 feat(deep-review): improve setup script robustness and quoting 2026-03-13 18:05:46 -07:00
mkorwel 187f2afb62 refactor: remove redundant shell scripts in favor of Node-based orchestration 2026-03-13 18:04:17 -07:00
mkorwel d5434f21d5 docs: clarify setup with pre-existing environments and isolation benefits 2026-03-13 17:57:00 -07:00
mkorwel 350f4dcd5c docs: add 'why' section to deep-review README 2026-03-13 17:52:10 -07:00
mkorwel ddc1522501 docs: move deep-review guide to skill folder as README 2026-03-13 17:51:31 -07:00
mkorwel 1f8e0a3d2e docs: add documentation for deep-review maintainer skill 2026-03-13 17:49:35 -07:00
mkorwel 0de1fb3f62 feat: add deep-review maintainer skill with node-based orchestration 2026-03-13 17:41:05 -07:00
1996 changed files with 52946 additions and 1042120 deletions
-17
View File
@@ -1,17 +0,0 @@
# Git history - not needed in build context
.git
# Root node_modules - reinstalled inside container via npm ci
node_modules
# Package-level node_modules - reinstalled inside container
packages/*/node_modules
# Development and IDE files
.github
.vscode
npm-debug.log*
# Misc
.DS_Store
*.tmp
-89
View File
@@ -1,89 +0,0 @@
# --- 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"]
-10
View File
@@ -1,10 +0,0 @@
node_modules
.git
.gemini/workspaces
dist
!packages/*/dist/*.tgz
bundle
out
*.log
.env
.DS_Store
+54
View File
@@ -0,0 +1,54 @@
# --- STAGE 1: Base Runtime ---
FROM docker.io/library/node:20-slim AS base
ARG CLI_VERSION_ARG
ENV CLI_VERSION=$CLI_VERSION_ARG
RUN apt-get update && apt-get install -y --no-install-recommends \
python3 \
curl \
dnsutils \
less \
jq \
ca-certificates \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
# --- STAGE 2: Maintainer ---
FROM base AS maintainer
# Install "Maintainer Bloat" - tools needed for development and offloading
RUN apt-get update && apt-get install -y --no-install-recommends \
make \
g++ \
gh \
git \
unzip \
rsync \
ripgrep \
procps \
psmisc \
lsof \
socat \
tmux \
docker.io \
build-essential \
libsecret-1-dev \
libkrb5-dev \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
# Install global dev tools
RUN npm install -g tsx vitest @google/gemini-cli@nightly prettier eslint typescript cross-env
# Set up npm global package folder
RUN mkdir -p /usr/local/share/npm-global \
&& chown -R node:node /usr/local/share/npm-global
ENV NPM_CONFIG_PREFIX=/usr/local/share/npm-global
ENV PATH=$PATH:/usr/local/share/npm-global/bin
# Switch to non-root user node
USER node
# Default entrypoint
CMD ["/bin/bash"]
@@ -1,7 +1,3 @@
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'
@@ -21,35 +17,31 @@ steps:
entrypoint: 'npm'
args: ['run', 'build:packages']
# Step 4: Build Development Image
# Step 4: Build Maintainer Image
- name: 'us-west1-docker.pkg.dev/gemini-code-dev/gemini-code-containers/gemini-code-builder'
id: 'Build Development Image'
id: 'Build Maintainer Image'
entrypoint: 'bash'
env:
- 'RAW_BRANCH_VALUE=${BRANCH_NAME}'
args:
- '-c'
- |-
IMAGE_BASE="${_ARTIFACT_REGISTRY_REPO}/${_IMAGE_NAME}"
IMAGE_BASE="us-docker.pkg.dev/gemini-code-dev/gemini-cli/maintainer"
# 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"
RAW_BRANCH="${_HEAD_BRANCH:-${BRANCH_NAME}}"
if [ "$${RAW_BRANCH}" == "main" ]; then
TAG_PRIMARY="latest"
else
TAG_PRIMARY=$$(echo "$${RAW_BRANCH}" | sed 's/[^a-zA-Z0-9]/-/g' | tr '[:upper:]' '[:lower:]')
TAG_PRIMARY=$(echo "$${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 \
TAG_SHA="${SHORT_SHA}"
echo "📦 Building Maintainer Image for: $${RAW_BRANCH} -> $${TAG_PRIMARY}"
docker build -f .gcp/Dockerfile.maintainer \
-t "$${IMAGE_BASE}:$${TAG_SHA}" \
-t "$${IMAGE_BASE}:$${TAG_PRIMARY}" .
docker push "$${IMAGE_BASE}:$${TAG_SHA}"
docker push "$${IMAGE_BASE}:$${TAG_PRIMARY}"
+60
View File
@@ -0,0 +1,60 @@
description = "Check status of nightly evals, fix failures for key models, and re-run."
prompt = """
You are an expert at fixing behavioral evaluations.
1. **Investigate**:
- Use 'gh' cli to fetch the results from the latest run from the main branch: https://github.com/google-gemini/gemini-cli/actions/workflows/evals-nightly.yml.
- DO NOT push any changes or start any runs. The rest of your evaluation will be local.
- Evals are in evals/ directory and are documented by evals/README.md.
- The test case trajectory logs will be logged to evals/logs.
- You should also enable and review the verbose agent logs by setting the GEMINI_DEBUG_LOG_FILE environment variable.
- Identify the relevant test. Confine your investigation and validation to just this test.
- Proactively add logging that will aid in gathering information or validating your hypotheses.
2. **Fix**:
- If a relevant test is failing, locate the test file and the corresponding prompt/code.
- It's often helpful to make an extreme, brute force change to see if you are changing the right place to make an improvement and then scope it back iteratively.
- Your **final** change should be **minimal and targeted**.
- Keep in mind the following:
- The prompt has multiple configurations and pieces. Take care that your changes
end up in the final prompt for the selected model and configuration.
- The prompt chosen for the eval is intentional. It's often vague or indirect
to see how the agent performs with ambiguous instructions. Changing it should
be a last resort.
- When changing the test prompt, carefully consider whether the prompt still tests
the same scenario. We don't want to lose test fidelity by making the prompts too
direct (i.e.: easy).
- Your primary mechanism for improving the agent's behavior is to make changes to
tool instructions, system prompt (snippets.ts), and/or modules that contribute to the prompt.
- If prompt and description changes are unsuccessful, use logs and debugging to
confirm that everything is working as expected.
- If unable to fix the test, you can make recommendations for architecture changes
that might help stablize the test. Be sure to THINK DEEPLY if offering architecture guidance.
Some facts that might help with this are:
- Agents may be composed of one or more agent loops.
- AgentLoop == 'context + toolset + prompt'. Subagents are one type of agent loop.
- Agent loops perform better when:
- They have direct, unambiguous, and non-contradictory prompts.
- They have fewer irrelevant tools.
- They have fewer goals or steps to perform.
- They have less low value or irrelevant context.
- You may suggest compositions of existing primitives, like subagents, or
propose a new one.
- These recommendations should be high confidence and should be grounded
in observed deficient behaviors rather than just parroting the facts above.
Investigate as needed to ground your recommendations.
3. **Verify**:
- Run just that one test if needed to validate that it is fixed. Be sure to run vitest in non-interactive mode.
- Running the tests can take a long time, so consider whether you can diagnose via other means or log diagnostics before committing the time. You must minimize the number of test runs needed to diagnose the failure.
- After the test completes, check whether it seems to have improved.
- You will need to run the test 3 times for Gemini 3.0, Gemini 3 flash, and Gemini 2.5 pro to ensure that it is truly stable. Run these runs in parallel, using scripts if needed.
- Some flakiness is expected; if it looks like a transient issue or the test is inherently unstable but passes 2/3 times, you might decide it cannot be improved.
4. **Report**:
- Provide a summary of the test success rate for each of the tested models.
- Success rate is calculated based on 3 runs per model (e.g., 3/3 = 100%).
- If you couldn't fix it due to persistent flakiness, explain why.
{{args}}
"""
@@ -0,0 +1,29 @@
description = "Promote behavioral evals that have a 100% success rate over the last 7 nightly runs."
prompt = """
You are an expert at analyzing and promoting behavioral evaluations.
1. **Investigate**:
- Use 'gh' cli to fetch the results from the most recent run from the main branch: https://github.com/google-gemini/gemini-cli/actions/workflows/evals-nightly.yml.
- DO NOT push any changes or start any runs. The rest of your evaluation will be local.
- Evals are in evals/ directory and are documented by evals/README.md.
- Identify tests that have passed 100% of the time for ALL enabled models across the past 7 runs in a row.
- NOTE: the results summary from the most recent run contains the last 7 runs test results. 100% means the test passed 3/3 times for that model and run.
- If a test meets this criteria, it is a candidate for promotion.
2. **Promote**:
- For each candidate test, locate the test file in the evals/ directory.
- Promote the test according to the project's standard promotion process (e.g., moving it to a stable suite, updating its tags, or removing skip/flaky annotations).
- Ensure you follow any guidelines in evals/README.md for stable tests.
- Your **final** change should be **minimal and targeted** to just promoting the test status.
3. **Verify**:
- Run the promoted tests locally to validate that they still execute correctly. Be sure to run vitest in non-interactive mode.
- Check that the test is now part of the expected standard or stable test suites.
4. **Report**:
- Provide a summary of the tests that were promoted.
- Include the success rate evidence (7/7 runs passed for all models) for each promoted test.
- If no tests met the criteria for promotion, clearly state that and summarize the closest candidates.
{{args}}
"""
+5 -21
View File
@@ -53,27 +53,11 @@ Gemini CLI project.
overriding values. Refer to `text-buffer.ts` for a canonical example.
- **Logging**: Do not leave `console.log`, `console.warn`, or `console.error` in
the code.
- **State**: Ensure state initialization is explicit (e.g., use `undefined`
rather than `true` as a default if the state is truly unknown). Prefer a
reducer whenever practical. NEVER disable `react-hooks/exhaustive-deps`; fix
the code to correctly declare dependencies instead. Evaluate all the React
states in a component and ensure that the `useState` calls are necessary and
not cases where values could be derived on render. Ensure there are no stale
closures that are relying on a value from a previous render. React Components
that modify Settings should effectively use the `useSettingsStore` pattern.
Components that configure application Settings (e.g settings.json) are the
only reasonable case for unsaved changes to drive UX; in these cases, the
Settings store should only be written to on save. If the user experience does
not utilize unsaved changes because there is no option to exit without saving
or reverting the unsaved changes, then the component should directly read from
and write to the Settings store without holding pending changes in component
level UI state.
- **Effect**: `useEffect` should not be used to synchronize React states, it
should only be used for genuine side effects that occur outside of React.
Contributors should be able to strongly justify the need for an effect.
Consider whether the effect should instead be inside an event handler, or
whether it is better off being computed on render. Carefully manage
`useEffect` dependencies.
- **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.
+2 -7
View File
@@ -1,13 +1,8 @@
{
"experimental": {
"plan": true,
"extensionReloading": true,
"modelSteering": true,
"autoMemory": true,
"topicUpdateNarration": true,
"voiceMode": true,
"adk": {
"agentSessionNoninteractiveEnabled": true
}
"modelSteering": true
},
"general": {
"devtools": true
-330
View File
@@ -1,330 +0,0 @@
---
name: agent-tui
description: >
Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent.
Drive terminal UI (TUI) applications programmatically for testing, automation, and inspection.
Use when: automating CLI/TUI interactions, regression testing terminal apps, or verifying interactive behavior.
Also use when: user asks "what is agent-tui", "what does agent-tui do", "demo agent-tui", "show me agent-tui", "how does agent-tui work", or wants to see it in action.
---
## 🚨 CRITICAL: macOS Daemon Workaround & Gemini CLI Usage 🚨
When using `agent-tui` in this macOS environment, the default background daemonization process crashes, causing `Connection refused (os error 61)` errors.
**You MUST start the daemon manually shielded from TTY hangups before running any `agent-tui` commands.** Using `nohup` is insufficient; you must use `tmux` to provide a fully isolated pseudo-terminal.
To support parallel runs, **only restart the daemon if it is not currently running:**
```bash
# Check if daemon is alive, start it in tmux if it is not
if ! agent-tui sessions >/dev/null 2>&1; then
tmux kill-session -t agent-tui 2>/dev/null || true
agent-tui daemon stop 2>/dev/null || true
rm -f /tmp/agent-tui*
tmux new-session -d -s agent-tui 'agent-tui daemon start --foreground > /tmp/agent-tui-daemon.log 2>&1'
sleep 1
fi
```
### Session ID vs PID (Crucial for Reconnection)
When `agent-tui run` returns JSON, it includes both a `session_id` and a `pid`. The `pid` is purely informational (the OS process ID of the child command). You **do not** use the `pid` to reconnect or issue commands. You must always use the `session_id` (e.g., `--session <id>`).
If the daemon crashes (`os error 61`), the pseudo-terminal is destroyed. Even if the child `pid` survives as an orphan, you cannot reconnect to it. You must restart the daemon using the workaround above and start a completely new session.
### Testing the Gemini CLI
When testing the Gemini CLI with `agent-tui`, there are several strict requirements to ensure deterministic and accurate behavior:
1. **Build Before Running**: `agent-tui` runs the built JS files, not TypeScript. You **MUST** run `npm run build` or `npm run build:all` after making code changes and before launching the CLI with `agent-tui`.
2. **Bypass Trust Modals**: Always pass `GEMINI_CLI_TRUST_WORKSPACE=true` in the environment. If you don't, any new project-level agents or extensions will trigger a full-screen "Acknowledge and Enable" modal. This modal steals focus, swallows automation keystrokes, and causes `agent-tui wait` commands to time out.
3. **Isolated Environments**: If you need to test without real user credentials or existing agents interfering, isolate the global settings using `GEMINI_CLI_HOME=<some-test-dir>`.
4. **Testing State Deltas (e.g., Reloads)**: If you are testing features that report deltas (e.g., `/agents reload` outputting "1 new local subagent"), you **MUST**:
- Start the CLI *first* so it establishes its baseline registry.
- Use a separate shell command (outside of `agent-tui`) to write the new agent `.md`/`.toml` file.
- Use `agent-tui type` and `press` to trigger the `/agents reload` command inside the running session.
- (If you add the files before starting the CLI, they become part of the baseline and won't trigger the delta logic).
```bash
# Example: Standard isolated run (sandboxed config + bypass trust modals)
env GEMINI_CLI_TRUST_WORKSPACE=true GEMINI_CLI_HOME=test-gemini-home agent-tui run -d "$(pwd)" node packages/cli/dist/index.js
```
# Terminal Automation Mastery
## Prerequisites
- **Supported OS**: macOS or Linux (Windows not supported yet).
- **Verify install**:
```bash
agent-tui --version
```
If not installed, use one of:
```bash
# Recommended: one-line install (macOS/Linux)
curl -fsSL https://raw.githubusercontent.com/pproenca/agent-tui/master/install.sh | sh
```
```bash
# Package manager
npm i -g agent-tui
pnpm add -g agent-tui
bun add -g agent-tui
```
```bash
# Build from source
cargo install --git https://github.com/pproenca/agent-tui.git --path cli/crates/agent-tui
```
If you used the install script, ensure `~/.local/bin` is on your PATH.
## Philosophy: Why Terminal Automation Is Different
Terminal UIs are **stateless from the observer's perspective**. Unlike web browsers with a persistent DOM, terminal automation works with a constantly-refreshed character grid. This fundamental difference shapes everything:
| Web Automation | Terminal Automation |
|----------------|---------------------|
| DOM persists across interactions | Screen buffer is redrawn constantly |
| Selectors are stable | Text positions may shift |
| Query once, act many times | Must re-verify before EVERY action |
| Network events signal completion | Must detect visual stability |
**The Core Insight**: agent-tui gives you vision without memory. Each screenshot is a fresh observation. Previous state means nothing after the UI changes. This isn't a limitation—it's the nature of terminal interaction.
## Mental Model: The Feedback Loop
Think of terminal automation as a **closed-loop control system**:
```
┌──────────────────────────────────────────────┐
│ │
▼ │
OBSERVE ──► DECIDE ──► ACT ──► WAIT ──► VERIFY ───┘
│ │
│ │
└─────── NEVER skip ◄────────────────────┘
```
**Each phase is mandatory.** Skipping verification is the #1 cause of flaky automation.
### The "Fresh Eyes" Principle
Every time you need to interact with the UI:
1. **Take a fresh screenshot** — your previous one is now stale
2. **Locate your target visually** — text positions may have changed
3. **Verify the state** — the UI may have changed unexpectedly
4. **Act only when stable** — animations and loading states cause failures
This feels slower, but it's the only reliable approach. Optimistic reuse of stale state causes intermittent failures that are painful to debug.
## Critical Rules (Non-Negotiable)
> **RULE 1: Atomic Execution (No Pipelining)**
> You are FORBIDDEN from chaining commands with `&&` (e.g., `type "x" && press Enter && wait`). Modals or UI updates can intercept your keystrokes. You MUST execute one atomic action, wait, screenshot, and verify before taking the next action in a new turn.
> **RULE 2: Re-snapshot after EVERY action**
> The UI state is invalidated by any change. Always take a fresh screenshot before acting again.
> **RULE 3: Never act on unstable UI**
> If the UI is animating, loading, or transitioning, `wait --stable` first. Acting during transitions because race conditions.
> **RULE 4: Verify before claiming success**
> Use `wait "expected text" --assert` to confirm outcomes. Don't assume an action worked—prove it.
> **RULE 5: Error Recovery**
> If a `wait` command times out, DO NOT blindly restart or kill the session. Execute `screenshot` to visually diagnose what unexpected UI element (modal, error dialog, lost focus) intercepted the flow.
> **RULE 6: Clean up sessions**
> Always end with `agent-tui kill`. Orphaned sessions consume resources and can interfere with future runs.
## Decision Framework
### Which Screenshot Mode?
Use `screenshot --format json` when parsing automation output, or plain `screenshot` for human readable text.
### How to Wait?
```
What are you waiting for?
├─► Specific text to appear
│ └─► `wait "text" --assert` (fails if not found)
├─► Specific text to disappear
│ └─► `wait "text" --gone --assert`
├─► UI to stop changing (animations, loading)
│ └─► `wait --stable`
└─► Multiple conditions
└─► Chain waits sequentially
```
### How to Act?
```
What do you need to do?
├─► Type text into the terminal
│ └─► `type "text"`
├─► Send keyboard shortcuts/navigation
│ └─► `press Ctrl+C` or `press ArrowDown Enter`
```
## Core Workflow
The canonical automation loop:
```bash
# 1. START: Launch the TUI app
agent-tui run <command> [-- args...]
# 2. OBSERVE: Get current UI state
agent-tui screenshot --format json
# 3. DECIDE: Based on text, determine next action
# (This happens in your head/code)
# 4. ACT: Execute the action
agent-tui type "text"
agent-tui press Enter
# 5. WAIT: Synchronize with UI changes
agent-tui wait "Expected" --assert # or wait --stable
# 6. VERIFY: Confirm the outcome (often combined with step 5)
# If verification fails, handle the error
# 7. REPEAT: Go back to step 2 until done
# 8. CLEANUP: Always clean up
agent-tui kill
```
## Anti-Patterns (What NOT to Do)
### ❌ Acting During Animation/Loading
```bash
# WRONG: Acting immediately on dynamic UI
agent-tui run my-app
agent-tui screenshot --format json # UI might still be loading!
agent-tui type "value" # ❌ Might miss the input field
# RIGHT: Wait for stability first
agent-tui run my-app
agent-tui wait --stable # Let UI settle
agent-tui screenshot --format json # Now it's reliable
agent-tui type "value"
```
### ❌ Assuming Success Without Verification
```bash
# WRONG: Assuming the type worked
agent-tui type "value"
agent-tui press Enter
# ...proceed as if success... # ❌ What if it failed silently?
# RIGHT: Verify the outcome
agent-tui type "value"
agent-tui press Enter
agent-tui wait "Success" --assert # ✓ Proves the action worked
```
### ❌ Skipping Cleanup
```bash
# WRONG: Forgetting to kill the session
agent-tui run my-app
# ...do stuff...
# script ends # ❌ Session left running!
# RIGHT: Always clean up
agent-tui run my-app
# ...do stuff...
agent-tui kill # ✓ Clean exit
```
## Before You Start: Clarify Requirements
Before automating any TUI, gather this information:
1. **Command**: What exactly to run? (`my-app --flag` or `npm start`?)
2. **Success criteria**: What text/state indicates success?
3. **Input sequence**: What keystrokes/data to enter, in what order?
4. **Safety**: Is it safe to submit forms, delete data, etc.?
5. **Auth**: Does it need login? Test credentials?
6. **Live preview**: Does the user want to watch? (`agent-tui live start --open`)
If any of these are unclear, ask before running.
## Demo Mode: Showing What agent-tui Can Do
When a user asks what agent-tui is, wants a demo, or asks "show me how it works":
1. **Don't explain—demonstrate.** Actions speak louder than words.
2. **Use the live preview** so they can watch in real-time.
3. **Run `top`**—it's universal and shows dynamic real-time updates.
**Quick demo trigger phrases:**
- "What is agent-tui?" / "What does agent-tui do?"
- "Demo agent-tui" / "Show me agent-tui"
- "How does agent-tui work?" / "See it in action"
## Failure Recovery
| Symptom | Diagnosis | Solution |
|---------|-----------|----------|
| "Text not found" | Stale view or text moved | Re-snapshot, locate text again |
| Wait times out | UI didn't reach expected state | Check screenshot, verify expectations |
| "Daemon not running" | Daemon crashed or not started | `agent-tui daemon start` |
| Unexpected layout | Wrong terminal size | `agent-tui resize --cols 120 --rows 40` |
| Session unresponsive | App crashed or hung | `agent-tui kill`, then re-run |
| Repeated failures | Something fundamentally wrong | Stop after 3-5 attempts, ask user |
## Self-Discovery: Use --help
You don't need to memorize every flag. The CLI is self-documenting:
```bash
agent-tui --help # List all commands
agent-tui run --help # Options for 'run'
agent-tui screenshot --help # Options for 'screenshot'
agent-tui wait --help # Options for 'wait'
```
**When in doubt, ask the CLI.** This skill teaches *when* and *why* to use commands. For exact flags and syntax, `--help` is authoritative.
## Quick Reference
```bash
# Start app
agent-tui run <cmd> [-- args] # Launch TUI under control
# Observe
agent-tui screenshot # Plain text view
agent-tui screenshot --format json # Machine-readable output
# Act
agent-tui press Enter # Press key(s)
agent-tui press Ctrl+C # Keyboard shortcuts
agent-tui type "text" # Type text
# Wait/Verify
agent-tui wait "text" --assert # Wait for text, fail if not found
agent-tui wait "text" --gone --assert # Wait for text to disappear
agent-tui wait --stable # Wait for UI to stop changing
# Manage
agent-tui sessions # List active sessions
agent-tui live start --open # Start live preview
agent-tui kill # End current session
```
-45
View File
@@ -1,45 +0,0 @@
---
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.
@@ -1,245 +0,0 @@
#!/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}"
@@ -1,65 +0,0 @@
#!/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
-56
View File
@@ -1,56 +0,0 @@
---
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.
@@ -1,27 +0,0 @@
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();
},
});
});
@@ -1,30 +0,0 @@
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');
},
});
});
@@ -1,151 +0,0 @@
# 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
};
```
@@ -1,100 +0,0 @@
# 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.
@@ -1,55 +0,0 @@
# 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.
@@ -1,95 +0,0 @@
# 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.
-66
View File
@@ -1,66 +0,0 @@
---
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.
-281
View File
@@ -1,281 +0,0 @@
#!/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);
});
+1 -3
View File
@@ -162,7 +162,5 @@ instructions for the other section.
## 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.
- After making changes, run `npm run format` ONLY to ensure consistency.
- Delete any temporary files created during the process.
+22 -74
View File
@@ -1,7 +1,7 @@
---
name: docs-writer
description:
Always use this skill when the task involves writing, reviewing, or editing
Always use this skill when the task involves writing, reviewing, or editing
files in the `/docs` directory or any `.md` files in the repository.
---
@@ -24,7 +24,7 @@ approach.
- **Perspective and tense:** Address the reader as "you." Use active voice and
present tense (e.g., "The API returns...").
- **Tone:** Professional, friendly, and direct.
- **Tone:** Professional, friendly, and direct.
- **Clarity:** Use simple vocabulary. Avoid jargon, slang, and marketing hype.
- **Global Audience:** Write in standard US English. Avoid idioms and cultural
references.
@@ -47,8 +47,8 @@ Write precisely to ensure your instructions are unambiguous.
"foo" or "bar."
- **Quota and limit terminology:** For any content involving resource capacity
or using the word "quota" or "limit", strictly adhere to the guidelines in
the `quota-limit-style-guide.md` resource file. Generally, Use "quota" for
the administrative bucket and "limit" for the numerical ceiling.
the `quota-limit-style-guide.md` resource file. Generally, Use "quota" for the
administrative bucket and "limit" for the numerical ceiling.
### Formatting and syntax
Apply consistent formatting to make documentation visually organized and
@@ -65,85 +65,35 @@ accessible.
- **UI and code:** Use **bold** for UI elements and `code font` for filenames,
snippets, commands, and API elements. Focus on the task when discussing
interaction.
- **Links:** Use descriptive anchor text; avoid "click here." Ensure the link
makes sense out of context.
- **Accessibility:** Use semantic HTML elements correctly (headings, lists,
tables).
- **Media:** Use lowercase hyphenated filenames. Provide descriptive alt text
for all images.
- **Details section:** Use the `<details>` tag to create a collapsible section.
This is useful for supplementary or data-heavy information that isn't critical
to the main flow.
Example:
<details>
<summary>Title</summary>
- First entry
- Second entry
</details>
- **Callouts**: Use GitHub-flavored markdown alerts to highlight important
information. To ensure the formatting is preserved by `npm run format`, place
an empty line, then a prettier ignore comment directly before the callout
block. Use `<!-- prettier-ignore -->` for standard Markdown files (`.md`) and
`{/* prettier-ignore */}` for MDX files (`.mdx`). The callout type (`[!TYPE]`)
should be on the first line, followed by a newline, and then the content, with
each subsequent line of content starting with `>`. Available types are `NOTE`,
`TIP`, `IMPORTANT`, `WARNING`, and `CAUTION`.
Example (.md):
<!-- prettier-ignore -->
> [!NOTE]
> This is an example of a multi-line note that will be preserved
> by Prettier.
Example (.mdx):
{/* prettier-ignore */}
> [!NOTE]
> This is an example of a multi-line note that will be preserved
> by Prettier.
### Links
- **Accessibility:** Use descriptive anchor text; avoid "click here." Ensure the
link makes sense out of context, such as when being read by a screen reader.
- **Use relative links in docs:** Use relative links in documentation (`/docs/`)
to ensure portability. Use paths relative to the current file's directory
(for example, `../tools/` from `docs/cli/`). Do not include the `/docs/`
section of a path, but do verify that the resulting relative link exists. This
does not apply to meta files such as README.MD and CONTRIBUTING.MD.
- **When changing headings, check for deep links:** If a user is changing a
heading, check for deep links to that heading in other pages and update
accordingly.
### Structure
- **BLUF:** Start with an introduction explaining what to expect.
- **Experimental features:** If a feature is clearly noted as experimental,
add the following note immediately after the introductory paragraph:
<!-- prettier-ignore -->
> [!NOTE]
> This is an experimental feature currently under active development.
(Note: Use `{/* prettier-ignore */}` if editing an `.mdx` file.)
add the following note immediately after the introductory paragraph:
`> **Note:** This is a preview feature currently under active development.`
- **Headings:** Use hierarchical headings to support the user journey.
- **Procedures:**
- **Procedures:**
- Introduce lists of steps with a complete sentence.
- Start each step with an imperative verb.
- Number sequential steps; use bullets for non-sequential lists.
- Put conditions before instructions (e.g., "On the Settings page, click...").
- Provide clear context for where the action takes place.
- Indicate optional steps clearly (e.g., "Optional: ...").
- **Elements:** Use bullet lists, tables, details, and callouts.
- **Elements:** Use bullet lists, tables, notes (`> **Note:**`), and warnings
(`> **Warning:**`).
- **Avoid using a table of contents:** If a table of contents is present, remove
it.
- **Next steps:** Conclude with a "Next steps" section if applicable.
## Phase 2: Preparation
Before modifying any documentation, thoroughly investigate the request and the
surrounding context.
surrounding context.
1. **Clarify:** Understand the core request. Differentiate between writing new
content and editing existing content. If the request is ambiguous (e.g.,
@@ -154,8 +104,6 @@ surrounding context.
4. **Connect:** Identify all referencing pages if changing behavior. Check if
`docs/sidebar.json` needs updates.
5. **Plan:** Create a step-by-step plan before making changes.
6. **Audit Docset:** If asked to audit the documentation, follow the procedural
guide in [docs-auditing.md](./references/docs-auditing.md).
## Phase 3: Execution
Implement your plan by either updating existing files or creating new ones
@@ -168,7 +116,7 @@ documentation.
- **Gaps:** Identify areas where the documentation is incomplete or no longer
reflects existing code.
- **Structure:** Apply "Structure (New Docs)" rules (BLUF, headings, etc.) when
- **Structure:** Apply "Structure (New Docs)" rules (BLUF, headings, etc.) when
adding new sections to existing pages.
- **Headers**: If you change a header, you must check for links that lead to
that header and update them.
@@ -178,17 +126,17 @@ documentation.
- **Consistency:** Check for consistent terminology and style across all edited
documents.
## Phase 4: Verification and finalization
Perform a final quality check to ensure that all changes are correctly
formatted and that all links are functional.
Perform a final quality check to ensure that all changes are correctly formatted
and that all links are functional.
1. **Accuracy:** Ensure content accurately reflects the implementation and
technical behavior.
2. **Self-review:** Re-read changes for formatting, correctness, and flow.
3. **Link check:** Verify all new and existing links leading to or from
modified pages. If you changed a header, ensure that any links that lead to
it are updated.
4. **Format:** 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.
3. **Link check:** Verify all new and existing links leading to or from modified
pages. If you changed a header, ensure that any links that lead to it are
updated.
4. **Format:** Once all changes are complete, ask to execute `npm run format`
to ensure consistent formatting across the project. If the user confirms,
execute the command.
@@ -1,195 +0,0 @@
# 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.
+31
View File
@@ -0,0 +1,31 @@
# Fix PR Skill
The `fix-pr` skill enables the Gemini CLI agent to autonomously and iteratively
fix a pull request until it is mergeable and passes all quality checks.
## When to use fix-pr
- **Autonomous fixing**: Move a PR from failing to green without manual
intervention.
- **Iterative loops**: Automatically handle the "fix -> push -> wait for CI"
cycle.
- **Context preservation**: Maintain context across multiple fix attempts.
## Sync vs Offload
This skill is designed to be versatile:
- **Synchronous mode**: Activate the skill in your current terminal for
quick fixes or conflict resolution.
- **Offloaded mode**: Use `npm run offload <PR> fix` to launch an iterative
fix loop on a remote workstation, keeping your local machine free.
## Objective
The goal is to move a PR from its current state (failing tests, merge conflicts,
or unaddressed comments) to a "Ready to Merge" state.
## Technical details
The skill uses the `gh` CLI and a specialized `wait-for-ci` utility to monitor
remote status. It is governed by the project's standard security policies.
+60
View File
@@ -0,0 +1,60 @@
# Fix PR Skill
This skill enables the agent to autonomously and iteratively fix a Pull Request until it is mergeable and passes all quality checks. It is designed to be run in a dedicated, non-blocking environment (like an offloaded remote session).
## Objective
The goal is to move a PR from its current state (failing tests, merge conflicts, or unaddressed comments) to a "Ready to Merge" state.
## Iterative Fix Loop
The agent must follow this loop until the PR is green and mergeable:
### 1. Synchronization & Merge Conflicts
- Fetch latest main: `git fetch origin main`.
- Attempt to merge: `git merge origin/main`.
- **If conflicts occur**:
- Use `git status` to identify conflicted files.
- Resolve the conflict markers (`<<<<<<<`, `=======`, `>>>>>>>`) based on the project's architectural direction.
- `git add` and `git commit` the resolution.
### 2. CI Failure Analysis
- Check current status: `gh pr checks`.
- **If CI is failing**:
- Download failing logs: `gh run view --log-failed`.
- Analyze the specific error (lint, typecheck, or test failure).
- Reproduce the failure locally (e.g., `npm run lint`, `npm test -- <path>`).
- Apply a targeted fix.
### 3. Comment Resolution
- Fetch all comments: Use `scripts/fetch-pr-info.js` or `gh pr view --json reviews,comments`.
- Analyze:
- **Line-level comments**: Fix the specific logic requested.
- **Review rejections**: Address the high-level architectural concerns.
- **General comments**: Respond or implement requested changes.
- For each fixed item, summarize the change in a commit message.
### 4. Verification & Push
- Verify the fix locally: `npm run build` and relevant tests.
- **If local verification fails**: Re-analyze and apply a new fix.
- **If local verification passes**:
- `git add .`
- `git commit -m "fix: address <issue/comment>"`
- `git push origin HEAD`
### 5. Wait for CI
- Run the blocker tool: `npx tsx .gemini/skills/fix-pr/scripts/wait-for-ci.ts`.
- **If CI passes**: Move to final check.
- **If CI fails**: Repeat the loop from step 2.
## Final Check
The PR is considered "Fix Complete" when:
1. `gh pr checks` returns success for all required jobs.
2. There are no outstanding merge conflicts with `main`.
3. All critical review comments have been addressed via code changes.
## Best Practices
- **Reason about failures**: Don't just guess. Read the stack traces and log files.
- **Incremental commits**: Make small, focused commits for different fixes.
- **Verify before pushing**: Always run the build/test locally before pushing to CI to save time.
- **Be Autonomous**: In an offloaded session, you have full permission to iterate until successful.
@@ -0,0 +1,41 @@
/**
* CI Waiter Utility for Fix PR Skill
* Blocks until GitHub checks for the current branch are complete.
*/
import { spawnSync } from 'child_process';
async function wait(ms: number) {
return new Promise(resolve => setTimeout(resolve, ms));
}
async function main() {
console.log('🔍 Waiting for GitHub Checks to complete...');
let attempts = 0;
const maxAttempts = 30; // 15 minutes total
while (attempts < maxAttempts) {
const checkStatus = spawnSync('gh', ['pr', 'checks'], { shell: true });
const output = checkStatus.stdout.toString();
if (output.includes('fail')) {
console.log('❌ CI Failed.');
process.exit(1);
} else if (output.includes('pending')) {
console.log(`⏳ CI still pending... (check ${attempts + 1}/${maxAttempts})`);
await wait(30000); // 30 seconds
} else if (output.trim() === '') {
console.log('⚠️ No checks found yet, waiting...');
await wait(10000);
} else {
console.log('✅ CI Passed!');
process.exit(0);
}
attempts++;
}
console.error('⏰ Timeout waiting for CI.');
process.exit(1);
}
main().catch(console.error);
@@ -1,69 +0,0 @@
---
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."
+34
View File
@@ -0,0 +1,34 @@
# Review PR Skill
The `review-pr` skill enables the Gemini CLI agent to conduct high-fidelity,
behavioral code reviews that go beyond simple static analysis.
## When to use review-pr
- **Deep verification**: Verify that a feature actually works by executing
it in a live environment.
- **Infrastructure awareness**: Leverage build and CI results to focus on
empirical proof of functionality.
- **Interactive collaboration**: Discuss findings and explore edge cases
with the agent in real-time.
## Sync vs Offload
This skill supports two primary modes:
- **Synchronous mode**: Activate the skill locally for quick, high-level
analysis of a peer's PR.
- **Offloaded mode**: Use `npm run offload <PR> review` to conduct a
full-scale behavioral review on a remote workstation with parallelized
infrastructure validation.
## Objective
Conduct a thorough review that involves physically proving the feature works
through terminal scripts and command execution.
## Technical details
The skill assumes the infrastructure (build and CI) is already being validated
and focuses on empirical proofs. It uses the `extract-failures.ts` utility to
automatically identify regressions in CI logs.
+67
View File
@@ -0,0 +1,67 @@
# Review PR Skill
This skill enables the agent to conduct a high-fidelity, behavioral code review
for a Pull Request. It is designed to be run in a dedicated, workspace remote
session where parallel infrastructure validation (build, CI check) is already
underway.
## Objective
Conduct a thorough review that goes beyond static analysis. The agent must
**physically prove** the feature works and that all regressions are caught by
exercising the code in a live terminal.
## Workflow: Verify then Synthesize
The agent must follow these steps to conduct the review:
### 1. Context Acquisition
- Read the PR description: `gh pr view <PR_NUMBER>`.
- Read the intent from the description and map it against the diff.
- Run `/review-frontend <PR_NUMBER>` to get an initial static analysis report.
### 2. Infrastructure Validation
- Trust the parallel worker results in `.gemini/logs/workspace-<PR_NUMBER>/`.
- Read `build.log` to ensure the environment is stable for testing.
- Read `ci-status.exit`.
- **If CI is failing**: Use the extractor to identify failing tests:
`npx tsx .gemini/skills/review-pr/scripts/extract-failures.ts <PR_NUMBER>`
- Reproduce the failing tests locally and analyze the output.
### 3. Behavioral Verification (The "Proof")
- Do NOT just trust that tests pass.
- Physically exercise the new code in the terminal.
- Examples of "Proof":
- If it's a new CLI command, run it with various flags.
- If it's a new service, write a small `.ts` script to call the functions.
- If it's a UI component, verify the Ink layout renders correctly.
- Log these proof steps and results in your conversation.
### 4. Synthesis
- Combine all data points:
- **Static Analysis** (Code quality, style).
- **Infrastructure** (Build status, CI status).
- **Behavioral Proof** (Empirical verification).
- Check for merge conflicts with `main`.
## Final Assessment
Provide a final recommendation with four sections:
1. **Summary**: High-level verdict (Approve / Needs Work / Reject).
2. **Verified Behavior**: Describe the scripts/commands you ran to prove the
feature works.
3. **Findings**: List Critical issues, Improvements, and Nitpicks.
4. **Actionable URL**: Explicitly print the PR URL: `gh pr view --web`.
### Approval Protocol
After presenting the synthesis, the agent MUST determine the all-up recommendation and ask the user for confirmation:
* "Based on the verification, I recommend **[APPROVE / COMMENT / REJECT]**. Would you like me to post this review to GitHub?"
* If the user agrees, execute the appropriate `gh pr review` command (e.g., `gh pr review <PR_NUMBER> --approve --body "<Summary>"`).
## Best Practices
- **Be Skeptical**: Just because CI is green doesn't mean the feature is complete. Look for missing edge cases.
- **Collaborate**: If you find a bug during verification, tell the user immediately in the main window.
- **Don't Fix**: Your role is to **review**, not to fix. If the PR is failing, summarize the causes and request changes.
@@ -0,0 +1,59 @@
/**
* CI Failure Extraction Utility
*
* Analyzes remote CI logs to identify specific failing test files.
* Used by the review-pr and fix-pr skills to minimize local repro noise.
*/
import { spawnSync } from 'child_process';
async function main() {
const prNumber = process.argv[2];
if (!prNumber) {
console.error('Usage: npx tsx extract-failures.ts <PR_NUMBER>');
process.exit(1);
}
console.log(`🔍 Investigating CI failures for PR #${prNumber}...`);
// 1. Get branch name
const branchView = spawnSync('gh', ['pr', 'view', prNumber, '--json', 'headRefName', '-q', '.headRefName'], { shell: true });
const branchName = branchView.stdout.toString().trim();
// 2. Get latest CI run ID
const runList = spawnSync('gh', ['run', 'list', '--branch', branchName, '--workflow', 'ci.yml', '--json', 'databaseId', '-q', '.[0].databaseId'], { shell: true });
const runId = runList.stdout.toString().trim();
if (!runId) {
console.log('⚠️ No recent CI runs found for this branch.');
process.exit(0);
}
// 3. Extract failing files from logs
// Pattern matches common test locations in the monorepo
const logView = spawnSync('gh', ['run', 'view', runId, '--log-failed'], { shell: true });
const logOutput = logView.stdout.toString();
const testPattern = /(packages\/[a-zA-Z0-9_-]+|integration-tests|evals)\/[a-zA-Z0-9_\/-]+\.test\.ts(x)?/g;
const matches = logOutput.match(testPattern);
if (!matches || matches.length === 0) {
console.log('✅ No specific failing test files detected in logs.');
process.exit(0);
}
const uniqueFiles = Array.from(new Set(matches)).sort();
console.log('\n❌ Found failing test files:');
uniqueFiles.forEach(f => console.log(` - ${f}`));
console.log('\n👉 Recommendation: Run these tests locally using:');
uniqueFiles.forEach(file => {
let wsDir = file.split('/')[0];
if (wsDir === 'packages') {
wsDir = file.split('/').slice(0, 2).join('/');
}
const relFile = file.replace(`${wsDir}/`, '');
console.log(` npm run test:ci -w ${wsDir} -- ${relFile}`);
});
}
main().catch(console.error);
-65
View File
@@ -1,65 +0,0 @@
---
name: tui-tester
description: Expert guidance for testing Gemini CLI behavior and visual output using terminal automation.
---
# TUI Tester Skill
This skill provides the operational manual for verifying Gemini CLI behavioral changes and visual output using terminal automation.
## Core Responsibilities
- **Verify Behavior**: Confirm that code changes result in the expected terminal interactions.
- **Visual Validation**: Ensure the TUI renders correctly across different terminal sizes and states.
- **Regression Testing**: Use automation to prevent breaking existing interactive workflows.
## Critical Protocol
When performing TUI testing, you must adhere to these strict rules:
### 1. Initialization
**YOUR ABSOLUTE FIRST ACTION MUST BE:**
Activate the `agent-tui` skill. This provides the underlying tools needed for terminal automation.
### 2. Environment Setup (macOS / Parallel Safe)
Ensure the global daemon is running and the live preview is open:
```bash
if ! agent-tui sessions >/dev/null 2>&1; then
tmux kill-session -t agent-tui 2>/dev/null || true
agent-tui daemon stop 2>/dev/null || true
rm -f /tmp/agent-tui*
tmux new-session -d -s agent-tui 'agent-tui daemon start --foreground > /tmp/agent-tui-daemon.log 2>&1'
sleep 1
fi
agent-tui live start --open
```
### 3. Session Management
- **Session IDs**: Always use the `session_id` returned by `agent-tui run` for subsequent interactions.
- **Atomic Execution**: Execute exactly one command per turn. Do not pipeline actions.
- **The Loop**: Action -> Wait -> Screenshot -> Verify -> Next Action.
### 4. Gemini CLI Specifics
- **Build First**: Always run `npm run build` or `npm run build:all` before testing local changes.
- **Bypass Trust**: Set `GEMINI_CLI_TRUST_WORKSPACE=true` to avoid focus-stealing modals.
- **Isolate Config**: Use `GEMINI_CLI_HOME` to prevent interference with your personal settings.
## Workflow Example
```bash
# Start the CLI
env GEMINI_CLI_TRUST_WORKSPACE=true agent-tui run node packages/cli/dist/index.js
# Wait for the prompt
agent-tui wait "│" --assert
# Send a command
agent-tui type "/help"
agent-tui press Enter
# Verify output
agent-tui wait "Available Commands" --assert
```
## Error Recovery
If a wait times out, take a fresh screenshot to diagnose the state. If you see `os error 61`, restart the daemon using the tmux method.
-2
View File
@@ -1,2 +0,0 @@
packages/core/src/services/scripts/*.exe
gha-creds-*.json
-2
View File
@@ -1,9 +1,7 @@
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:
@@ -14,6 +14,12 @@ outputs:
runs:
using: 'composite'
steps:
- name: 'Print inputs'
shell: 'bash'
env:
JSON_INPUTS: '${{ toJSON(inputs) }}'
run: 'echo "$JSON_INPUTS"'
- name: 'Set vars for simplified logic'
id: 'set_vars'
shell: 'bash'
@@ -30,6 +30,11 @@ inputs:
runs:
using: 'composite'
steps:
- name: '📝 Print Inputs'
shell: 'bash'
env:
JSON_INPUTS: '${{ toJSON(inputs) }}'
run: 'echo "$JSON_INPUTS"'
- name: 'Creates a Pull Request'
if: "inputs.dry-run != 'true'"
env:
@@ -1,23 +0,0 @@
name: 'Download Mac Binaries'
description: 'Downloads the unsigned macOS binaries (x64 and arm64)'
inputs:
path:
description: 'The base path to download the binaries to'
required: true
default: 'dist'
runs:
using: 'composite'
steps:
- name: 'Download macOS arm64 binary'
uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4
continue-on-error: true
with:
name: 'gemini-darwin-arm64-unsigned'
path: '${{ inputs.path }}/darwin-arm64'
- name: 'Download macOS x64 binary'
uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4
continue-on-error: true
with:
name: 'gemini-darwin-x64-unsigned'
path: '${{ inputs.path }}/darwin-x64'
@@ -27,6 +27,11 @@ inputs:
runs:
using: 'composite'
steps:
- name: '📝 Print Inputs'
shell: 'bash'
env:
JSON_INPUTS: '${{ toJSON(inputs) }}'
run: 'echo "$JSON_INPUTS"'
- name: 'Prepare Coverage Comment'
id: 'prep_coverage_comment'
shell: 'bash'
+29 -82
View File
@@ -75,6 +75,12 @@ inputs:
runs:
using: 'composite'
steps:
- name: '📝 Print Inputs'
shell: 'bash'
env:
JSON_INPUTS: '${{ toJSON(inputs) }}'
run: 'echo "$JSON_INPUTS"'
- name: '👤 Configure Git User'
working-directory: '${{ inputs.working-directory }}'
shell: 'bash'
@@ -108,14 +114,13 @@ runs:
BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'
DRY_RUN: '${{ inputs.dry-run }}'
RELEASE_TAG: '${{ inputs.release-tag }}'
GIT_PUSH_TOKEN: '${{ inputs.github-release-token || inputs.github-token }}'
run: |-
set -e
git add package.json package-lock.json packages/*/package.json
git commit -m "chore(release): ${RELEASE_TAG}"
if [[ "${DRY_RUN}" == "false" ]]; then
echo "Pushing release branch to remote..."
git push "https://x-access-token:${GIT_PUSH_TOKEN}@github.com/${{ github.repository }}.git" "HEAD:${BRANCH_NAME}" --follow-tags
git push --set-upstream origin "${BRANCH_NAME}" --follow-tags
else
echo "Dry run enabled. Skipping push."
fi
@@ -167,13 +172,10 @@ runs:
shell: 'bash'
run: |
npm publish \
--ignore-scripts \
--dry-run="${INPUTS_DRY_RUN}" \
--workspace="${INPUTS_CORE_PACKAGE_NAME}" \
--tag staging-tmp
if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} staging-tmp
fi
--no-tag
npm dist-tag rm ${INPUTS_CORE_PACKAGE_NAME} false --silent
- name: '🔗 Install latest core package'
working-directory: '${{ inputs.working-directory }}'
@@ -191,35 +193,12 @@ runs:
INPUTS_A2A_PACKAGE_NAME: '${{ inputs.a2a-package-name }}'
- name: '📦 Prepare bundled CLI for npm release'
if: "inputs.npm-registry-url != 'https://npm.pkg.github.com/'"
if: "inputs.npm-registry-url != 'https://npm.pkg.github.com/' && inputs.npm-tag != 'latest'"
working-directory: '${{ inputs.working-directory }}'
shell: 'bash'
run: |
node ${{ github.workspace }}/scripts/prepare-npm-release.js
- name: '📦 Pack CLI for verification'
if: "inputs.dry-run != 'true' && inputs.force-skip-tests != 'true'"
working-directory: '${{ inputs.working-directory }}'
shell: 'bash'
run: |
npm pack --workspace="${INPUTS_CLI_PACKAGE_NAME}"
# We restore the package.json so that `npm ci` in verify-release doesn't fail due to deleted dependencies
git checkout packages/cli/package.json
env:
INPUTS_CLI_PACKAGE_NAME: '${{ inputs.cli-package-name }}'
- name: '🔬 Verify NPM release by version'
uses: './.github/actions/verify-release'
if: "${{ inputs.dry-run != 'true' && inputs.force-skip-tests != 'true' }}"
with:
npm-package: './google-gemini-cli-${{ inputs.release-version }}.tgz'
expected-version: '${{ inputs.release-version }}'
working-directory: '${{ inputs.working-directory }}'
gemini_api_key: '${{ inputs.gemini_api_key }}'
github-token: '${{ inputs.github-token }}'
npm-registry-url: '${{ inputs.npm-registry-url }}'
npm-registry-scope: '${{ inputs.npm-registry-scope }}'
- name: 'Get CLI Token'
uses: './.github/actions/npm-auth-token'
id: 'cli-token'
@@ -236,23 +215,13 @@ runs:
NODE_AUTH_TOKEN: '${{ steps.cli-token.outputs.auth-token }}'
INPUTS_DRY_RUN: '${{ inputs.dry-run }}'
INPUTS_CLI_PACKAGE_NAME: '${{ inputs.cli-package-name }}'
INPUTS_RELEASE_VERSION: '${{ inputs.release-version }}'
shell: 'bash'
run: |
if [ -f "google-gemini-cli-${INPUTS_RELEASE_VERSION}.tgz" ]; then
PUBLISH_TARGET="google-gemini-cli-${INPUTS_RELEASE_VERSION}.tgz"
else
PUBLISH_TARGET="--workspace=${INPUTS_CLI_PACKAGE_NAME}"
fi
npm publish \
--ignore-scripts \
--dry-run="${INPUTS_DRY_RUN}" \
${PUBLISH_TARGET} \
--tag staging-tmp
if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
npm dist-tag rm ${INPUTS_CLI_PACKAGE_NAME} staging-tmp
fi
--workspace="${INPUTS_CLI_PACKAGE_NAME}" \
--no-tag
npm dist-tag rm ${INPUTS_CLI_PACKAGE_NAME} false --silent
- name: 'Get a2a-server Token'
uses: './.github/actions/npm-auth-token'
@@ -274,13 +243,22 @@ runs:
# Tag staging for initial release
run: |
npm publish \
--ignore-scripts \
--dry-run="${INPUTS_DRY_RUN}" \
--workspace="${INPUTS_A2A_PACKAGE_NAME}" \
--tag staging-tmp
if [[ "${INPUTS_DRY_RUN}" == "false" ]]; then
npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} staging-tmp
fi
--no-tag
npm dist-tag rm ${INPUTS_A2A_PACKAGE_NAME} false --silent
- name: '🔬 Verify NPM release by version'
uses: './.github/actions/verify-release'
if: "${{ inputs.dry-run != 'true' && inputs.force-skip-tests != 'true' }}"
with:
npm-package: '${{ inputs.cli-package-name }}@${{ inputs.release-version }}'
expected-version: '${{ inputs.release-version }}'
working-directory: '${{ inputs.working-directory }}'
gemini_api_key: '${{ inputs.gemini_api_key }}'
github-token: '${{ inputs.github-token }}'
npm-registry-url: '${{ inputs.npm-registry-url }}'
npm-registry-scope: '${{ inputs.npm-registry-scope }}'
- name: '🏷️ Tag release'
uses: './.github/actions/tag-npm-release'
@@ -307,38 +285,8 @@ runs:
INPUTS_PREVIOUS_TAG: '${{ inputs.previous-tag }}'
shell: 'bash'
run: |
rm -f gemini-cli-bundle.zip
(cd bundle && chmod +x gemini.js && zip -r ../gemini-cli-bundle.zip .)
echo "Testing the generated bundle archive..."
rm -rf test-bundle
mkdir -p test-bundle
unzip -q gemini-cli-bundle.zip -d test-bundle
# Verify it runs and outputs a version
BUNDLE_VERSION=$(node test-bundle/gemini.js --version | xargs)
echo "Bundle version output: ${BUNDLE_VERSION}"
if [[ -z "${BUNDLE_VERSION}" ]]; then
echo "Error: Bundle failed to execute or return version."
exit 1
fi
rm -rf test-bundle
RELEASE_ASSETS=("gemini-cli-bundle.zip")
# Check for and prepare macOS binaries if they exist
for arch in arm64 x64; do
BINARY_PATH="dist/darwin-${arch}/gemini"
if [[ -f "$BINARY_PATH" ]]; then
chmod +x "$BINARY_PATH"
ZIP_NAME="gemini-darwin-${arch}-unsigned.zip"
zip -j "$ZIP_NAME" "$BINARY_PATH"
RELEASE_ASSETS+=("$ZIP_NAME")
fi
done
gh release create "${INPUTS_RELEASE_TAG}" \
"${RELEASE_ASSETS[@]}" \
bundle/gemini.js \
--target "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}" \
--title "Release ${INPUTS_RELEASE_TAG}" \
--notes-start-tag "${INPUTS_PREVIOUS_TAG}" \
@@ -352,8 +300,7 @@ runs:
shell: 'bash'
run: |
echo "Cleaning up release branch ${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}..."
git push "https://x-access-token:${GIT_PUSH_TOKEN}@github.com/${{ github.repository }}.git" --delete "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}"
git push origin --delete "${STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME}"
env:
GIT_PUSH_TOKEN: '${{ inputs.github-release-token || inputs.github-token }}'
STEPS_RELEASE_BRANCH_OUTPUTS_BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'
+5
View File
@@ -18,6 +18,11 @@ inputs:
runs:
using: 'composite'
steps:
- name: '📝 Print Inputs'
shell: 'bash'
env:
JSON_INPUTS: '${{ toJSON(inputs) }}'
run: 'echo "$JSON_INPUTS"'
- name: 'Checkout'
uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v4
with:
+9 -4
View File
@@ -28,8 +28,13 @@ inputs:
runs:
using: 'composite'
steps:
- name: '📝 Print Inputs'
shell: 'bash'
env:
JSON_INPUTS: '${{ toJSON(inputs) }}'
run: 'echo "$JSON_INPUTS"'
- name: 'Checkout'
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
uses: 'actions/checkout@v4'
with:
ref: '${{ inputs.github-sha }}'
fetch-depth: 0
@@ -40,11 +45,11 @@ runs:
shell: 'bash'
run: 'npm run build'
- name: 'Set up QEMU'
uses: 'docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130' # ratchet:docker/setup-qemu-action@v3
uses: 'docker/setup-qemu-action@v3'
- name: 'Set up Docker Buildx'
uses: 'docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f' # ratchet:docker/setup-buildx-action@v3
uses: 'docker/setup-buildx-action@v3'
- name: 'Log in to GitHub Container Registry'
uses: 'docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9' # ratchet:docker/login-action@v3
uses: 'docker/login-action@v3'
with:
registry: 'docker.io'
username: '${{ inputs.dockerhub-username }}'
+4 -7
View File
@@ -13,17 +13,14 @@ inputs:
runs:
using: 'composite'
steps:
- name: 'Install system dependencies'
if: "runner.os == 'Linux'"
run: |
sudo apt-get update -qq && sudo DEBIAN_FRONTEND=noninteractive apt-get install -y -qq bubblewrap
# Ubuntu 24.04+ requires this to allow bwrap to function in CI
sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 || true
- name: '📝 Print Inputs'
shell: 'bash'
env:
JSON_INPUTS: '${{ toJSON(inputs) }}'
run: 'echo "$JSON_INPUTS"'
- name: 'Run Tests'
env:
GEMINI_API_KEY: '${{ inputs.gemini_api_key }}'
GEMINI_CLI_TRUST_WORKSPACE: true
working-directory: '${{ inputs.working-directory }}'
run: |-
echo "::group::Build"
@@ -40,6 +40,12 @@ inputs:
runs:
using: 'composite'
steps:
- name: '📝 Print Inputs'
shell: 'bash'
env:
JSON_INPUTS: '${{ toJSON(inputs) }}'
run: 'echo "$JSON_INPUTS"'
- name: 'Setup Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020'
with:
+10 -7
View File
@@ -29,8 +29,14 @@ inputs:
runs:
using: 'composite'
steps:
- name: '📝 Print Inputs'
shell: 'bash'
env:
JSON_INPUTS: '${{ toJSON(inputs) }}'
run: 'echo "$JSON_INPUTS"'
- name: 'setup node'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
uses: 'actions/setup-node@v4'
with:
node-version: '20'
@@ -74,7 +80,7 @@ runs:
shell: 'bash'
working-directory: '${{ inputs.working-directory }}'
run: |-
gemini_version=$(npx --yes --prefer-online "${INPUTS_NPM_PACKAGE}" --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 ${INPUTS_EXPECTED_VERSION}"
exit 1
@@ -86,18 +92,15 @@ runs:
- name: 'Install dependencies for integration tests'
shell: 'bash'
working-directory: '${{ inputs.working-directory }}'
run: 'npm ci --ignore-scripts'
run: 'npm ci'
- name: '🔬 Run integration tests against NPM release'
working-directory: '${{ inputs.working-directory }}'
env:
GEMINI_API_KEY: '${{ inputs.gemini_api_key }}'
GEMINI_CLI_TRUST_WORKSPACE: true
INTEGRATION_TEST_USE_INSTALLED_GEMINI: 'true'
# We must diable CI mode here because it interferes with interactive tests.
# See https://github.com/google-gemini/gemini-cli/issues/10517
CI: 'false'
shell: 'bash'
run: |
export INTEGRATION_TEST_GEMINI_BINARY_PATH=$(which gemini)
npm run test:integration:sandbox:none
run: 'npm run test:integration:sandbox:none'
-8
View File
@@ -8,10 +8,6 @@ updates:
open-pull-requests-limit: 10
reviewers:
- 'joshualitt'
cooldown:
semver-major-days: 14
semver-minor-days: 14
semver-patch-days: 14
groups:
npm-dependencies:
patterns:
@@ -28,10 +24,6 @@ updates:
open-pull-requests-limit: 10
reviewers:
- 'joshualitt'
cooldown:
semver-major-days: 14
semver-minor-days: 14
semver-patch-days: 14
groups:
actions-dependencies:
patterns:
-278
View File
@@ -1,278 +0,0 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
module.exports = async ({ github, context, core }) => {
const extractJson = (raw) => {
if (!raw || raw === '[]' || raw === '') return [];
try {
// First, try to parse the raw output as JSON.
return JSON.parse(raw);
} catch {
// If that fails, check for a markdown code block.
core.info(
'Direct JSON parsing failed. Trying to extract from a markdown block.',
);
const jsonMatch = raw.match(/```json\s*([\s\S]*?)\s*```/);
if (jsonMatch && jsonMatch[1]) {
try {
return JSON.parse(jsonMatch[1].trim());
} catch (markdownError) {
core.warning(
`Failed to parse extracted JSON from markdown block: ${markdownError.message}`,
);
}
}
// Try to find a raw JSON array in the output.
const jsonArrayMatch = raw.match(
/\[\s*\{\s*"issue_number"[\s\S]*\}\s*\]/,
);
if (jsonArrayMatch) {
try {
return JSON.parse(jsonArrayMatch[0]);
} catch {
const fallbackMatch = raw.match(/(\[\s*\{\s*"issue_number"[\s\S]*)/);
if (fallbackMatch) {
try {
const cleaned = fallbackMatch[0].substring(
0,
fallbackMatch[0].lastIndexOf(']') + 1,
);
return JSON.parse(cleaned);
} catch (fallbackError) {
core.warning(
`Failed to parse extracted JSON using fallback regex: ${fallbackError.message}`,
);
}
}
}
}
}
core.warning('No valid JSON could be extracted from input.');
return [];
};
// Collect all outputs from environment variables
// Prioritize EFFORT results over STANDARD results by processing Effort FIRST
// so that its labels appear first in the merged arrays (and thus win in mutually exclusive logic)
const effortRaw = process.env.LABELS_OUTPUT_EFFORT;
const standardRaw = process.env.LABELS_OUTPUT_STANDARD;
const genericRaw = process.env.LABELS_OUTPUT;
const resultsByIssue = new Map();
const processResults = (results, _sourceName) => {
for (const entry of results) {
const issueNumber = entry.issue_number;
if (!issueNumber) continue;
if (!resultsByIssue.has(issueNumber)) {
resultsByIssue.set(issueNumber, {
issue_number: issueNumber,
labels_to_add: [...(entry.labels_to_add || [])],
labels_to_remove: [...(entry.labels_to_remove || [])],
explanation: entry.explanation || '',
effort_analysis: entry.effort_analysis || '',
});
} else {
const existing = resultsByIssue.get(issueNumber);
// Combine labels
existing.labels_to_add = [
...new Set([
...existing.labels_to_add,
...(entry.labels_to_add || []),
]),
];
existing.labels_to_remove = [
...new Set([
...existing.labels_to_remove,
...(entry.labels_to_remove || []),
]),
];
// Combine explanations (if different)
if (
entry.explanation &&
!existing.explanation.includes(entry.explanation)
) {
existing.explanation = existing.explanation
? `${existing.explanation}\n\n${entry.explanation}`
: entry.explanation;
}
// Take effort analysis if present
if (entry.effort_analysis && !existing.effort_analysis) {
existing.effort_analysis = entry.effort_analysis;
}
}
}
};
// Order matters: Effort first so its labels win in conflict resolution
processResults(extractJson(effortRaw), 'EFFORT');
processResults(extractJson(standardRaw), 'STANDARD');
processResults(extractJson(genericRaw), 'GENERIC');
const finalResults = Array.from(resultsByIssue.values());
core.info(`Aggregated triage results for ${finalResults.length} issues.`);
for (const entry of finalResults) {
const issueNumber = entry.issue_number;
let labelsToAdd = entry.labels_to_add || [];
let labelsToRemove = entry.labels_to_remove || [];
let existingLabels = [];
// Fetch existing labels early
try {
const { data: issueData } = await github.rest.issues.get({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
});
existingLabels = issueData.labels.map((l) =>
typeof l === 'string' ? l : l.name,
);
} catch (e) {
core.warning(
`Failed to fetch existing labels for #${issueNumber}: ${e.message}`,
);
}
// Programmatic Priority Downgrade Logic
if (labelsToAdd.includes('status/need-information')) {
const targetPriority = labelsToAdd.find((l) => l.startsWith('priority/'));
if (targetPriority) {
let downgradedPriority = null;
if (targetPriority === 'priority/p0')
downgradedPriority = 'priority/p1';
if (targetPriority === 'priority/p1')
downgradedPriority = 'priority/p2';
if (downgradedPriority) {
core.info(
`Programmatically downgrading ${targetPriority} to ${downgradedPriority} due to status/need-information`,
);
labelsToAdd = labelsToAdd.filter((l) => l !== targetPriority);
labelsToAdd.push(downgradedPriority);
}
}
}
labelsToRemove.push('status/need-triage');
if (
labelsToAdd.includes('status/manual-triage') ||
existingLabels.includes('status/manual-triage')
) {
labelsToRemove.push('status/bot-triaged');
labelsToAdd = labelsToAdd.filter((l) => l !== 'status/bot-triaged');
} else {
labelsToAdd.push('status/bot-triaged');
}
// Resolve internal conflicts (e.g., adding P1 and P2)
// We already resolved these by putting Effort first in the combined list
// Resolve external conflicts with existing labels
if (labelsToAdd.some((l) => l.startsWith('area/'))) {
labelsToRemove.push(
...existingLabels.filter((l) => l.startsWith('area/')),
);
}
if (labelsToAdd.some((l) => l.startsWith('priority/'))) {
labelsToRemove.push(
...existingLabels.filter((l) => l.startsWith('priority/')),
);
}
if (labelsToAdd.some((l) => l.startsWith('kind/'))) {
labelsToRemove.push(
...existingLabels.filter((l) => l.startsWith('kind/')),
);
}
// Enforce mutual exclusivity in the TO-ADD list (Architect wins)
const exclusivePrefixes = ['area/', 'priority/', 'kind/'];
for (const prefix of exclusivePrefixes) {
const filtered = labelsToAdd.filter((l) => l.startsWith(prefix));
if (filtered.length > 1) {
const winner = filtered[0]; // First one wins
core.info(
`Issue #${issueNumber} has multiple ${prefix} labels suggested. Keeping "${winner}" and discarding others.`,
);
labelsToAdd = labelsToAdd.filter(
(l) => !l.startsWith(prefix) || l === winner,
);
}
}
// Final deduplication and cleanup
labelsToRemove = [...new Set(labelsToRemove)].filter(
(l) => !labelsToAdd.includes(l) && existingLabels.includes(l),
);
labelsToAdd = [...new Set(labelsToAdd)].filter(
(l) => !existingLabels.includes(l),
);
// Batch label operations
if (labelsToAdd.length > 0) {
await github.rest.issues.addLabels({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
labels: labelsToAdd,
});
core.info(
`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}`,
);
}
if (labelsToRemove.length > 0) {
for (const label of labelsToRemove) {
try {
await github.rest.issues.removeLabel({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
name: label,
});
} catch (e) {
if (e.status !== 404)
core.warning(
`Failed to remove label ${label} from #${issueNumber}: ${e.message}`,
);
}
}
core.info(
`Successfully removed labels for #${issueNumber}: ${labelsToRemove.join(', ')}`,
);
}
// Post comment if needed
const needsInfoAdded =
labelsToAdd.includes('status/need-information') &&
!existingLabels.includes('status/need-information');
const hasEffortAnalysis = !!entry.effort_analysis;
if (needsInfoAdded || hasEffortAnalysis) {
let commentBody = '';
if (needsInfoAdded && entry.explanation) commentBody += entry.explanation;
if (hasEffortAnalysis) {
if (commentBody) commentBody += '\n\n';
commentBody += `**Effort Analysis:**\n${entry.effort_analysis}`;
}
if (commentBody) {
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
body: commentBody,
});
core.info(`Posted required comment for #${issueNumber}`);
}
}
}
};
-74
View File
@@ -1,74 +0,0 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
const fs = require('node:fs');
module.exports = async ({ github, context, core }) => {
let issuesToCleanup = [];
try {
const fileContent = fs.readFileSync('issues_to_cleanup.json', 'utf8');
issuesToCleanup = JSON.parse(fileContent);
} catch (error) {
if (error.code === 'ENOENT') {
core.info('No issues found to clean up.');
return;
}
core.setFailed(`Failed to read issues_to_cleanup.json: ${error.message}`);
return;
}
for (const issue of issuesToCleanup) {
try {
const { data: issueData } = await github.rest.issues.get({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
});
const labels = issueData.labels.map((l) =>
typeof l === 'string' ? l : l.name,
);
if (
labels.includes('status/bot-triaged') &&
labels.includes('status/need-triage')
) {
await github.rest.issues.removeLabel({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
name: 'status/need-triage',
});
core.info(
`Successfully removed status/need-triage from #${issue.number}`,
);
}
if (
labels.includes('status/bot-triaged') &&
labels.includes('status/manual-triage')
) {
await github.rest.issues.removeLabel({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
name: 'status/bot-triaged',
});
core.info(
`Successfully removed status/bot-triaged from #${issue.number} because it requires manual triage`,
);
}
} catch (error) {
core.warning(
`Failed to clean up labels for #${issue.number}: ${error.message}`,
);
}
}
core.info(
`Cleaned up conflicting labels from ${issuesToCleanup.length} issues.`,
);
};
@@ -1,380 +0,0 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
/**
* Gemini Scheduled Lifecycle Manager Script
* @param {object} param0
* @param {import('@octokit/rest').Octokit} param0.github
* @param {import('@actions/github/lib/context').Context} param0.context
* @param {import('@actions/core')} param0.core
*/
module.exports = async ({ github, context, core }) => {
const dryRun = process.env.DRY_RUN === 'true';
const owner = context.repo.owner;
const repo = context.repo.repo;
core.info(`Running in ${dryRun ? 'DRY RUN' : 'PRODUCTION'} mode.`);
const STALE_LABEL = 'stale';
const NEED_INFO_LABEL = 'status/need-information';
const EXEMPT_LABELS = [
'pinned',
'security',
'🔒 maintainer only',
'help wanted',
'🗓️ Public Roadmap',
];
const STALE_DAYS = 60;
const CLOSE_DAYS = 14;
const NO_RESPONSE_DAYS = 14;
const now = new Date();
const staleThreshold = new Date(
now.getTime() - STALE_DAYS * 24 * 60 * 60 * 1000,
);
const closeThreshold = new Date(
now.getTime() - CLOSE_DAYS * 24 * 60 * 60 * 1000,
);
const noResponseThreshold = new Date(
now.getTime() - NO_RESPONSE_DAYS * 24 * 60 * 60 * 1000,
);
const maintainerCache = new Map();
async function isMaintainer(user, association) {
if (user?.type === 'Bot') return true;
if (['OWNER', 'MEMBER', 'COLLABORATOR'].includes(association)) return true;
const username = user?.login;
if (!username) return false;
if (maintainerCache.has(username)) {
return maintainerCache.get(username);
}
try {
const { data } = await github.rest.repos.getCollaboratorPermissionLevel({
owner,
repo,
username,
});
// Permission can be admin, write, read, none.
// Roles like 'maintain' or 'triage' often map to 'write' or 'read' in the top-level field.
const isM =
['admin', 'write'].includes(data.permission) ||
['admin', 'maintain', 'write'].includes(data.role_name);
maintainerCache.set(username, isM);
return isM;
} catch (err) {
core.warning(
`Could not check permissions for ${username}: ${err.message}`,
);
maintainerCache.set(username, false);
return false;
}
}
async function processItems(query, callback) {
core.info(`Searching: ${query}`);
try {
let items = await github.paginate(
github.rest.search.issuesAndPullRequests,
{
q: query,
per_page: 100,
sort: 'updated',
order: 'asc',
},
);
core.info(`Found ${items.length} items.`);
for (const item of items) {
try {
await callback(item);
} catch (err) {
core.error(`Error processing #${item.number}: ${err.message}`);
}
}
} catch (err) {
core.error(`Search failed: ${err.message}`);
}
}
// 1. Handle No-Response (status/need-information)
// Removal: Check issues updated in the last 48h that have the label
const twoDaysAgo = new Date(now.getTime() - 2 * 24 * 60 * 60 * 1000);
await processItems(
`repo:${owner}/${repo} is:open label:"${NEED_INFO_LABEL}" updated:>${twoDaysAgo.toISOString()}`,
async (item) => {
const { data: comments } = await github.rest.issues.listComments({
owner,
repo,
issue_number: item.number,
sort: 'created',
direction: 'desc',
per_page: 5,
});
// Check if the last comment is from a non-maintainer and not a bot
const lastComment = comments[0];
if (
lastComment &&
lastComment.user?.type !== 'Bot' &&
!(await isMaintainer(lastComment.user, lastComment.author_association))
) {
if (dryRun) {
core.info(
`[DRY RUN] Would remove ${NEED_INFO_LABEL} from #${item.number} due to contributor response.`,
);
} else {
core.info(
`Removing ${NEED_INFO_LABEL} from #${item.number} due to contributor response.`,
);
await github.rest.issues
.removeLabel({
owner,
repo,
issue_number: item.number,
name: NEED_INFO_LABEL,
})
.catch(() => {});
}
}
},
);
// Closure: Check issues with the label that haven't been updated in 14 days
await processItems(
`repo:${owner}/${repo} is:open label:"${NEED_INFO_LABEL}" updated:<${noResponseThreshold.toISOString()}`,
async (item) => {
if (dryRun) {
core.info(
`[DRY RUN] Would close #${item.number} due to no response for ${NO_RESPONSE_DAYS} days.`,
);
} else {
core.info(
`Closing #${item.number} due to no response for ${NO_RESPONSE_DAYS} days.`,
);
await github.rest.issues.createComment({
owner,
repo,
issue_number: item.number,
body: `This item was marked as needing more information and has not received a response in ${NO_RESPONSE_DAYS} days. Closing it for now. If you still face this problem, feel free to reopen with more details. Thank you!`,
});
await github.rest.issues.update({
owner,
repo,
issue_number: item.number,
state: 'closed',
state_reason: 'not_planned',
});
}
},
);
// 2. Handle Stale Mark (60 days inactivity, no stale label)
const exemptQuery = EXEMPT_LABELS.map((l) => `-label:"${l}"`).join(' ');
await processItems(
`repo:${owner}/${repo} is:open -label:"${STALE_LABEL}" ${exemptQuery} updated:<${staleThreshold.toISOString()}`,
async (item) => {
const isBug = item.labels.some((l) =>
(typeof l === 'string' ? l : l.name).toLowerCase().includes('bug'),
);
const bodyText = isBug
? `This bug report has been automatically marked as stale due to ${STALE_DAYS} days of inactivity. Many issues are resolved in newer releases. Please verify if the issue persists in the latest Gemini CLI version. If it does, please leave a comment to keep this open. It will be closed in ${CLOSE_DAYS} days if no further activity occurs. Thank you!`
: `This item has been automatically marked as stale due to ${STALE_DAYS} days of inactivity. It will be closed in ${CLOSE_DAYS} days if no further activity occurs. Thank you!`;
if (dryRun) {
core.info(`[DRY RUN] Would mark #${item.number} as stale.`);
} else {
core.info(`Marking #${item.number} as stale.`);
await github.rest.issues.addLabels({
owner,
repo,
issue_number: item.number,
labels: [STALE_LABEL],
});
await github.rest.issues.createComment({
owner,
repo,
issue_number: item.number,
body: bodyText,
});
}
},
);
// 3. Handle Stale Removal & Close
await processItems(
`repo:${owner}/${repo} is:open label:"${STALE_LABEL}" ${exemptQuery}`,
async (item) => {
// Fetch full timeline to see events and comments
const timeline = await github.paginate(
github.rest.issues.listEventsForTimeline,
{
owner,
repo,
issue_number: item.number,
per_page: 100,
},
);
// Find exactly when the Stale label was added
// We look for the last 'labeled' event for STALE_LABEL
const staleEventIndex = timeline.findLastIndex(
(e) =>
e.event === 'labeled' &&
e.label?.name?.toLowerCase() === STALE_LABEL.toLowerCase(),
);
if (staleEventIndex === -1) return; // Fallback if no event found
const staleEvent = timeline[staleEventIndex];
const eventsAfterStale = timeline.slice(staleEventIndex + 1);
// Check for meaningful activity after the Stale label was applied
const meaningfulEvents = eventsAfterStale.filter((e) => {
const actor = e.actor?.login || '';
const isBot =
actor.includes('[bot]') || actor.includes('github-actions');
if (isBot) return false;
// Explicit whitelist of meaningful events for humans
if (
[
'commented',
'cross-referenced',
'connected',
'reopened',
'assigned',
].includes(e.event)
) {
return true;
}
return false;
});
if (meaningfulEvents.length > 0) {
// Activity detected, remove Stale label
if (dryRun) {
core.info(
`[DRY RUN] Would remove ${STALE_LABEL} from #${item.number} due to meaningful activity (e.g., comment or PR).`,
);
} else {
core.info(
`Removing ${STALE_LABEL} from #${item.number} due to meaningful activity (e.g., comment or PR).`,
);
await github.rest.issues
.removeLabel({
owner,
repo,
issue_number: item.number,
name: STALE_LABEL,
})
.catch(() => {});
}
return;
}
// No meaningful activity. Check if 14 days have passed.
const labeledDate = new Date(staleEvent.created_at);
if (labeledDate > closeThreshold) {
// Has not been 14 days since it was ACTUALLY marked stale
return;
}
if (dryRun) {
core.info(`[DRY RUN] Would close stale item #${item.number}.`);
} else {
core.info(`Closing stale item #${item.number}.`);
await github.rest.issues.createComment({
owner,
repo,
issue_number: item.number,
body: `This item has been closed due to ${CLOSE_DAYS} additional days of inactivity after being marked as stale. If you believe this is still relevant, feel free to comment or reopen. Thank you!`,
});
await github.rest.issues.update({
owner,
repo,
issue_number: item.number,
state: 'closed',
state_reason: 'not_planned',
});
}
},
);
// 4. Handle PR Contribution Policy (Nudge at 7d, Close at 14d)
const PR_NUDGE_DAYS = 7;
const PR_CLOSE_DAYS = 14;
const nudgeThreshold = new Date(
now.getTime() - PR_NUDGE_DAYS * 24 * 60 * 60 * 1000,
);
const prCloseThreshold = new Date(
now.getTime() - PR_CLOSE_DAYS * 24 * 60 * 60 * 1000,
);
// Nudge
await processItems(
`repo:${owner}/${repo} is:open is:pr -label:"help wanted" -label:"🔒 maintainer only" -label:"status/pr-nudge-sent" created:${prCloseThreshold.toISOString()}..${nudgeThreshold.toISOString()}`,
async (pr) => {
if (await isMaintainer(pr.user, pr.author_association)) return;
if (dryRun) {
core.info(
`[DRY RUN] Would nudge PR #${pr.number} for contribution policy.`,
);
} else {
core.info(`Nudging PR #${pr.number} for contribution policy.`);
await github.rest.issues.addLabels({
owner,
repo,
issue_number: pr.number,
labels: ['status/pr-nudge-sent'],
});
await github.rest.issues.createComment({
owner,
repo,
issue_number: pr.number,
body: "Hi there! Thank you for your interest in contributing to Gemini CLI. \n\nTo ensure we maintain high code quality and focus on our prioritized roadmap, we only guarantee review and consideration of pull requests for issues that are explicitly labeled as 'help wanted'. \n\nThis PR will be closed in 7 days if it remains without that designation. We encourage you to find and contribute to existing 'help wanted' issues in our backlog! Thank you for your understanding.",
});
}
},
);
// Close
await processItems(
`repo:${owner}/${repo} is:open is:pr -label:"help wanted" -label:"🔒 maintainer only" created:<${prCloseThreshold.toISOString()}`,
async (pr) => {
if (await isMaintainer(pr.user, pr.author_association)) return;
if (dryRun) {
core.info(
`[DRY RUN] Would close PR #${pr.number} per contribution policy (no 'help wanted').`,
);
} else {
core.info(
`Closing PR #${pr.number} per contribution policy (no 'help wanted').`,
);
await github.rest.issues.createComment({
owner,
repo,
issue_number: pr.number,
body: "This pull request is being closed as it has been open for 14 days without a 'help wanted' designation. We encourage you to find and contribute to existing 'help wanted' issues in our backlog! Thank you for your understanding.",
});
await github.rest.pulls.update({
owner,
repo,
pull_number: pr.number,
state: 'closed',
});
}
},
);
};
-99
View File
@@ -1,99 +0,0 @@
/**
* @license
* Copyright 2026 Google LLC
* SPDX-License-Identifier: Apache-2.0
*/
const fs = require('node:fs');
module.exports = async ({ github, context, core }) => {
const query = `
query($owner: String!, $repo: String!) {
repository(owner: $owner, name: $repo) {
issues(first: 50, states: OPEN, orderBy: {field: UPDATED_AT, direction: DESC}) {
nodes {
id
number
title
body
issueType {
name
}
labels(first: 20) {
nodes {
name
}
}
}
}
}
}
`;
try {
const result = await github.graphql(query, {
owner: context.repo.owner,
repo: context.repo.repo,
});
const issues = result.repository.issues.nodes;
const issuesNeedingAnalysis = [];
let syncedCount = 0;
for (const issue of issues) {
if (issue.issueType === null) {
const labelNames = issue.labels.nodes.map((l) => l.name);
const hasBug = labelNames.includes('kind/bug');
const hasFeature =
labelNames.includes('kind/feature') ||
labelNames.includes('kind/enhancement');
let issueTypeId = null;
if (hasBug) {
issueTypeId = 'IT_kwDOCaSVvs4BR7vP'; // Bug
} else if (hasFeature) {
issueTypeId = 'IT_kwDOCaSVvs4BR7vQ'; // Feature
}
if (issueTypeId) {
await github.graphql(
`
mutation($issueId: ID!, $issueTypeId: ID!) {
updateIssue(input: {id: $issueId, issueTypeId: $issueTypeId}) {
issue {
id
}
}
}
`,
{
issueId: issue.id,
issueTypeId: issueTypeId,
},
);
core.info(`Successfully synced Issue Type for #${issue.number}`);
syncedCount++;
} else {
// Needs analysis to determine kind/type
issuesNeedingAnalysis.push({
number: issue.number,
title: issue.title,
body: issue.body,
});
}
}
}
// Write issues needing analysis to a file so the AI can process them
fs.writeFileSync(
'no_type_issues.json',
JSON.stringify(issuesNeedingAnalysis),
);
core.info(`Synced ${syncedCount} issues from labels.`);
core.info(
`Found ${issuesNeedingAnalysis.length} issues missing both type and kind label to be analyzed.`,
);
} catch (error) {
core.setFailed(`Failed to sync issue types: ${error.message}`);
}
};
@@ -1,132 +0,0 @@
# yaml-language-server: $schema=https://json.schemastore.org/github-workflow.json
name: 'Agent Session Drift Check'
on:
pull_request:
branches:
- 'main'
- 'release/**'
paths:
- 'packages/cli/src/nonInteractiveCli.ts'
- 'packages/cli/src/nonInteractiveCliAgentSession.ts'
concurrency:
group: '${{ github.workflow }}-${{ github.head_ref || github.ref }}'
cancel-in-progress: true
jobs:
check-drift:
name: 'Check Agent Session Drift'
runs-on: 'ubuntu-latest'
if: "github.repository == 'google-gemini/gemini-cli'"
permissions:
contents: 'read'
pull-requests: 'write'
steps:
- name: 'Detect drift and comment'
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea' # ratchet:actions/github-script@v8
with:
script: |-
// === Pair configuration — append here to cover more pairs ===
const PAIRS = [
{
legacy: 'packages/cli/src/nonInteractiveCli.ts',
session: 'packages/cli/src/nonInteractiveCliAgentSession.ts',
label: 'non-interactive CLI',
},
// Future pairs can be added here. Remember to also add both
// paths to the `paths:` filter at the top of this workflow.
// Example:
// {
// legacy: 'packages/core/src/agents/local-invocation.ts',
// session: 'packages/core/src/agents/local-session-invocation.ts',
// label: 'local subagent invocation',
// },
];
// ============================================================
const prNumber = context.payload.pull_request.number;
const { owner, repo } = context.repo;
// Use the API to list changed files — no checkout/git diff needed.
const files = await github.paginate(github.rest.pulls.listFiles, {
owner,
repo,
pull_number: prNumber,
per_page: 100,
});
const changed = new Set(files.map((f) => f.filename));
const warnings = [];
for (const { legacy, session, label } of PAIRS) {
const legacyChanged = changed.has(legacy);
const sessionChanged = changed.has(session);
if (legacyChanged && !sessionChanged) {
warnings.push(
`**${label}**: \`${legacy}\` was modified but \`${session}\` was not.`,
);
} else if (!legacyChanged && sessionChanged) {
warnings.push(
`**${label}**: \`${session}\` was modified but \`${legacy}\` was not.`,
);
}
}
const MARKER = '<!-- agent-session-drift-check -->';
// Look up our existing drift comment (for upsert/cleanup).
const comments = await github.paginate(github.rest.issues.listComments, {
owner,
repo,
issue_number: prNumber,
per_page: 100,
});
const existing = comments.find(
(c) => c.user?.type === 'Bot' && c.body?.includes(MARKER),
);
if (warnings.length === 0) {
core.info('No drift detected.');
// If drift was previously flagged and is now resolved, remove the comment.
if (existing) {
await github.rest.issues.deleteComment({
owner,
repo,
comment_id: existing.id,
});
core.info(`Deleted stale drift comment ${existing.id}.`);
}
return;
}
const body = [
MARKER,
'### ⚠️ Invocation Drift Warning',
'',
'The following file pairs should generally be kept in sync during the AgentSession migration:',
'',
...warnings.map((w) => `- ${w}`),
'',
'If this is intentional (e.g., a bug fix specific to one implementation), you can ignore this comment.',
'',
'_This check will be removed once the legacy implementations are deleted._',
].join('\n');
if (existing) {
core.info(`Updating existing drift comment ${existing.id}.`);
await github.rest.issues.updateComment({
owner,
repo,
comment_id: existing.id,
body,
});
} else {
core.info('Creating new drift comment.');
await github.rest.issues.createComment({
owner,
repo,
issue_number: prNumber,
body,
});
}
@@ -1,65 +0,0 @@
name: 'Build Unsigned Mac Binaries'
on:
workflow_dispatch:
workflow_call:
inputs:
ref:
description: 'The branch, tag, or SHA to build from.'
required: true
type: 'string'
permissions:
contents: 'read'
defaults:
run:
shell: 'bash'
jobs:
build-mac:
name: 'Build Unsigned (${{ matrix.arch }})'
runs-on: 'macos-latest'
strategy:
fail-fast: false
matrix:
arch: ['x64', 'arm64']
steps:
- name: 'Checkout'
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
with:
ref: '${{ inputs.ref || github.ref }}'
persist-credentials: false
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
with:
node-version-file: '.nvmrc'
architecture: '${{ matrix.arch }}'
cache: 'npm'
- name: 'Install dependencies'
run: 'npm ci'
- name: 'Build Binary'
env:
SKIP_SIGNING: 'true'
run: 'npm run build:binary'
- name: 'Verify Output Exists'
run: |
if [ -f "dist/darwin-${{ matrix.arch }}/gemini" ]; then
echo "Binary found at dist/darwin-${{ matrix.arch }}/gemini"
else
echo "Error: Binary not found in dist/darwin-${{ matrix.arch }}/"
ls -R dist/
exit 1
fi
- name: 'Upload Artifact'
uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
with:
name: 'gemini-darwin-${{ matrix.arch }}-unsigned'
path: 'dist/darwin-${{ matrix.arch }}/gemini'
retention-days: 14
+1 -23
View File
@@ -148,7 +148,6 @@ jobs:
with:
ref: '${{ needs.parse_run_context.outputs.sha }}'
repository: '${{ needs.parse_run_context.outputs.repository }}'
persist-credentials: false
- name: 'Set up Node.js ${{ matrix.node-version }}'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -168,7 +167,6 @@ jobs:
- name: 'Run E2E tests'
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
GEMINI_CLI_TRUST_WORKSPACE: true
KEEP_OUTPUT: 'true'
VERBOSE: 'true'
BUILD_SANDBOX_FLAGS: '--cache-from type=gha --cache-to type=gha,mode=max'
@@ -185,7 +183,7 @@ jobs:
needs:
- 'merge_queue_skipper'
- 'parse_run_context'
runs-on: 'macos-latest-large'
runs-on: 'macos-latest'
if: |
github.repository == 'google-gemini/gemini-cli' && always() && (needs.merge_queue_skipper.result !='success' || needs.merge_queue_skipper.outputs.skip != 'true')
steps:
@@ -194,7 +192,6 @@ jobs:
with:
ref: '${{ needs.parse_run_context.outputs.sha }}'
repository: '${{ needs.parse_run_context.outputs.repository }}'
persist-credentials: false
- name: 'Set up Node.js 20.x'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -215,7 +212,6 @@ jobs:
if: "${{runner.os != 'Windows'}}"
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
GEMINI_CLI_TRUST_WORKSPACE: true
KEEP_OUTPUT: 'true'
SANDBOX: 'sandbox:none'
VERBOSE: 'true'
@@ -235,7 +231,6 @@ jobs:
with:
ref: '${{ needs.parse_run_context.outputs.sha }}'
repository: '${{ needs.parse_run_context.outputs.repository }}'
persist-credentials: false
- name: 'Set up Node.js 20.x'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -293,7 +288,6 @@ jobs:
- name: 'Run E2E tests'
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
GEMINI_CLI_TRUST_WORKSPACE: true
KEEP_OUTPUT: 'true'
SANDBOX: 'sandbox:none'
VERBOSE: 'true'
@@ -317,7 +311,6 @@ jobs:
with:
ref: '${{ needs.parse_run_context.outputs.sha }}'
repository: '${{ needs.parse_run_context.outputs.repository }}'
persist-credentials: false
fetch-depth: 0
- name: 'Set up Node.js 20.x'
@@ -341,23 +334,8 @@ jobs:
if: "${{ steps.check_evals.outputs.should_run == 'true' }}"
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
GEMINI_CLI_TRUST_WORKSPACE: true
GEMINI_MODEL: 'gemini-3-pro-preview'
# Only run always passes behavioral tests.
EVAL_SUITE_TYPE: 'behavioral'
# Disable Vitest internal retries to avoid double-retrying;
# custom retry logic is handled in evals/test-helper.ts
VITEST_RETRY: 0
run: 'npm run test:always_passing_evals'
- name: 'Upload Reliability Logs'
if: "always() && steps.check_evals.outputs.should_run == 'true'"
uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
with:
name: 'eval-logs-${{ github.run_id }}-${{ github.run_attempt }}'
path: 'evals/logs/api-reliability.jsonl'
retention-days: 7
e2e:
name: 'E2E'
if: |
+9 -40
View File
@@ -57,7 +57,6 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
ref: '${{ github.event.inputs.branch_ref || github.ref }}'
fetch-depth: 0
@@ -68,7 +67,7 @@ jobs:
cache: 'npm'
- name: 'Cache Linters'
uses: 'actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830' # ratchet:actions/cache@v4
uses: 'actions/cache@v4'
with:
path: '${{ env.GEMINI_LINT_TEMP_DIR }}'
key: "${{ runner.os }}-${{ runner.arch }}-linters-${{ hashFiles('scripts/lint.js') }}"
@@ -77,7 +76,7 @@ jobs:
run: 'npm ci'
- name: 'Cache ESLint'
uses: 'actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830' # ratchet:actions/cache@v4
uses: 'actions/cache@v4'
with:
path: '.eslintcache'
key: "${{ runner.os }}-eslint-${{ hashFiles('package-lock.json', 'eslint.config.js') }}"
@@ -103,12 +102,6 @@ jobs:
- name: 'Run yamllint'
run: 'node scripts/lint.js --yamllint'
- name: 'Build project for typecheck'
run: 'npm run build'
- name: 'Run typecheck'
run: 'npm run typecheck'
- name: 'Run Prettier'
run: 'node scripts/lint.js --prettier'
@@ -121,9 +114,6 @@ 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'
@@ -131,8 +121,6 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Link Checker'
uses: 'lycheeverse/lychee-action@885c65f3dc543b57c898c8099f4e08c8afd178a2' # ratchet: lycheeverse/lychee-action@v2.6.1
with:
@@ -160,8 +148,6 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Set up Node.js ${{ matrix.node-version }}'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -172,25 +158,18 @@ jobs:
- name: 'Build project'
run: 'npm run build'
- name: 'Install system dependencies'
run: |
sudo apt-get update -qq && sudo DEBIAN_FRONTEND=noninteractive apt-get install -y -qq bubblewrap
# Ubuntu 24.04+ requires this to allow bwrap to function in CI
sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 || true
- name: 'Install dependencies for testing'
run: 'npm ci'
- name: 'Run tests and generate reports'
env:
NO_COLOR: true
GEMINI_CLI_TRUST_WORKSPACE: true
run: |
if [[ "${{ matrix.shard }}" == "cli" ]]; then
npm run test:ci --workspace "@google/gemini-cli"
npm run test:ci --workspace @google/gemini-cli
else
# Explicitly list non-cli packages to ensure they are sharded correctly
npm run test:ci --workspace "@google/gemini-cli-core" --workspace "@google/gemini-cli-a2a-server" --workspace "gemini-cli-vscode-ide-companion" --workspace "@google/gemini-cli-test-utils" --if-present -- --coverage.enabled=false
npm run test:ci --workspace @google/gemini-cli-core --workspace @google/gemini-cli-a2a-server --workspace gemini-cli-vscode-ide-companion --workspace @google/gemini-cli-test-utils --if-present -- --coverage.enabled=false
npm run test:scripts
fi
@@ -236,7 +215,7 @@ jobs:
test_mac:
name: 'Test (Mac) - ${{ matrix.node-version }}, ${{ matrix.shard }}'
runs-on: 'macos-latest-large'
runs-on: 'macos-latest'
needs:
- 'merge_queue_skipper'
if: "github.repository == 'google-gemini/gemini-cli' && needs.merge_queue_skipper.outputs.skip == 'false'"
@@ -257,8 +236,6 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Set up Node.js ${{ matrix.node-version }}'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -275,13 +252,12 @@ jobs:
- name: 'Run tests and generate reports'
env:
NO_COLOR: true
GEMINI_CLI_TRUST_WORKSPACE: true
run: |
if [[ "${{ matrix.shard }}" == "cli" ]]; then
npm run test:ci --workspace "@google/gemini-cli" -- --coverage.enabled=false
npm run test:ci --workspace @google/gemini-cli -- --coverage.enabled=false
else
# Explicitly list non-cli packages to ensure they are sharded correctly
npm run test:ci --workspace "@google/gemini-cli-core" --workspace "@google/gemini-cli-a2a-server" --workspace "gemini-cli-vscode-ide-companion" --workspace "@google/gemini-cli-test-utils" --if-present -- --coverage.enabled=false
npm run test:ci --workspace @google/gemini-cli-core --workspace @google/gemini-cli-a2a-server --workspace gemini-cli-vscode-ide-companion --workspace @google/gemini-cli-test-utils --if-present -- --coverage.enabled=false
npm run test:scripts
fi
@@ -346,7 +322,6 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
ref: '${{ github.event.inputs.branch_ref || github.ref }}'
- name: 'Initialize CodeQL'
@@ -371,7 +346,6 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
ref: '${{ github.event.inputs.branch_ref || github.ref }}'
fetch-depth: 1
@@ -399,7 +373,6 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
ref: '${{ github.event.inputs.branch_ref || github.ref }}'
- name: 'Set up Node.js 20.x'
@@ -442,20 +415,16 @@ jobs:
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
NO_COLOR: true
GEMINI_CLI_TRUST_WORKSPACE: true
NODE_OPTIONS: '--max-old-space-size=32768 --max-semi-space-size=256'
UV_THREADPOOL_SIZE: '32'
NODE_ENV: 'test'
run: |
if ("${{ matrix.shard }}" -eq "cli") {
npm run test:ci --workspace "@google/gemini-cli" -- --coverage.enabled=false
if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
npm run test:ci --workspace @google/gemini-cli -- --coverage.enabled=false
} else {
# Explicitly list non-cli packages to ensure they are sharded correctly
npm run test:ci --workspace "@google/gemini-cli-core" --workspace "@google/gemini-cli-a2a-server" --workspace "gemini-cli-vscode-ide-companion" --workspace "@google/gemini-cli-test-utils" --if-present -- --coverage.enabled=false
if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
npm run test:ci --workspace @google/gemini-cli-core --workspace @google/gemini-cli-a2a-server --workspace gemini-cli-vscode-ide-companion --workspace @google/gemini-cli-test-utils --if-present -- --coverage.enabled=false
npm run test:scripts
if ($LASTEXITCODE -ne 0) { exit $LASTEXITCODE }
}
shell: 'pwsh'
+6 -9
View File
@@ -173,7 +173,6 @@ jobs:
GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
REPOSITORY: '${{ github.repository }}'
with:
upload_artifacts: 'true'
gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -183,14 +182,12 @@ jobs:
use_gemini_code_assist: '${{ vars.GOOGLE_GENAI_USE_GCA }}'
settings: |-
{
"tools": {
"core": [
"run_shell_command(gh issue list)",
"run_shell_command(gh pr list)",
"run_shell_command(gh search issues)",
"run_shell_command(gh search prs)"
]
}
"coreTools": [
"run_shell_command(gh issue list)",
"run_shell_command(gh pr list)",
"run_shell_command(gh search issues)",
"run_shell_command(gh search prs)"
]
}
prompt: |-
You are a helpful assistant that analyzes community contribution reports.
+1 -7
View File
@@ -43,7 +43,6 @@ jobs:
with:
ref: '${{ github.event.pull_request.head.sha }}'
repository: '${{ github.repository }}'
persist-credentials: false
- name: 'Set up Node.js ${{ matrix.node-version }}'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -63,7 +62,6 @@ jobs:
- name: 'Run E2E tests'
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
GEMINI_CLI_TRUST_WORKSPACE: true
IS_DOCKER: "${{ matrix.sandbox == 'sandbox:docker' }}"
KEEP_OUTPUT: 'true'
RUNS: '${{ github.event.inputs.runs }}'
@@ -79,7 +77,7 @@ jobs:
deflake_e2e_mac:
name: 'E2E Test (macOS)'
runs-on: 'macos-latest-large'
runs-on: 'macos-latest'
if: "github.repository == 'google-gemini/gemini-cli'"
steps:
- name: 'Checkout'
@@ -87,7 +85,6 @@ jobs:
with:
ref: '${{ github.event.pull_request.head.sha }}'
repository: '${{ github.repository }}'
persist-credentials: false
- name: 'Set up Node.js 20.x'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -108,7 +105,6 @@ jobs:
if: "runner.os != 'Windows'"
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
GEMINI_CLI_TRUST_WORKSPACE: true
KEEP_OUTPUT: 'true'
RUNS: '${{ github.event.inputs.runs }}'
SANDBOX: 'sandbox:none'
@@ -127,7 +123,6 @@ jobs:
with:
ref: '${{ github.event.pull_request.head.sha }}'
repository: '${{ github.repository }}'
persist-credentials: false
- name: 'Set up Node.js 20.x'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -164,7 +159,6 @@ jobs:
- name: 'Run E2E tests'
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
GEMINI_CLI_TRUST_WORKSPACE: true
KEEP_OUTPUT: 'true'
SANDBOX: 'sandbox:none'
VERBOSE: 'true'
-66
View File
@@ -1,66 +0,0 @@
name: 'Automated Documentation Audit'
on:
schedule:
# Runs every Monday at 00:00 UTC
- cron: '0 0 * * MON'
workflow_dispatch:
jobs:
audit-docs:
runs-on: 'ubuntu-latest'
permissions:
contents: 'write'
pull-requests: 'write'
steps:
- name: 'Checkout repository'
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5'
with:
fetch-depth: 0
ref: 'main'
persist-credentials: false
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020'
with:
node-version: '20'
- name: 'Run Docs Audit with Gemini'
id: 'run_gemini'
uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31'
env:
GEMINI_CLI_TRUST_WORKSPACE: true
with:
upload_artifacts: 'true'
gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
prompt: |
Activate the 'docs-writer' skill.
**Task:** Execute the docs audit procedure, as defined in your 'docs-auditing.md' reference.
Provide a detailed summary of the changes you make.
- name: 'Get current date'
id: 'date'
run: |
echo "date=$(date +'%Y-%m-%d')" >> "$GITHUB_OUTPUT"
- name: 'Create Pull Request with Audit Results'
uses: 'peter-evans/create-pull-request@c5a7806660adbe173f04e3e038b0ccdcd758773c'
with:
token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
commit-message: 'docs: weekly audit results for ${{ github.run_id }}'
title: 'Docs audit: ${{ steps.date.outputs.date }}'
body: |
This PR contains the auto-generated documentation audit for the week. It includes a new `audit-results-*.md` file with findings and any direct fixes applied by the agent.
### Audit Summary:
${{ steps.run_gemini.outputs.summary || 'No summary provided.' }}
Please review the suggestions and merge.
Related to #25152
branch: 'docs-audit-${{ github.run_id }}'
base: 'main'
team-reviewers: 'gemini-cli-docs, gemini-cli-maintainers'
delete-branch: true
-2
View File
@@ -24,8 +24,6 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Setup Pages'
uses: 'actions/configure-pages@983d7736d9b0ae728b81ab479565c72886d7745b' # ratchet:actions/configure-pages@v5
-211
View File
@@ -1,211 +0,0 @@
name: 'Evals: PR Evaluation & Regression'
on:
pull_request_target:
types: ['opened', 'synchronize', 'reopened', 'ready_for_review']
paths:
- 'packages/core/src/prompts/**'
- 'packages/core/src/tools/**'
- 'packages/core/src/agents/**'
- 'evals/**'
- '!**/*.test.ts'
- '!**/*.test.tsx'
workflow_dispatch:
# Prevents multiple runs for the same PR simultaneously (saves tokens)
concurrency:
group: '${{ github.workflow }}-${{ github.head_ref || github.ref }}'
cancel-in-progress: true
permissions:
pull-requests: 'write'
contents: 'read'
actions: 'read'
jobs:
detect-changes:
name: 'Detect Steering Changes'
runs-on: 'gemini-cli-ubuntu-16-core'
# Security: pull_request_target allows secrets, so we must gate carefully.
# Detection should not run code from the fork.
if: "github.repository == 'google-gemini/gemini-cli' && github.event.pull_request.draft == false"
outputs:
SHOULD_RUN: '${{ steps.detect.outputs.SHOULD_RUN }}'
STEERING_DETECTED: '${{ steps.detect.outputs.STEERING_DETECTED }}'
steps:
- name: 'Checkout'
uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
with:
# Check out the trusted code from main for detection
fetch-depth: 0
persist-credentials: false
- name: 'Detect Steering Changes'
id: 'detect'
env:
# Use the PR's head SHA for comparison without checking it out
PR_HEAD_SHA: '${{ github.event.pull_request.head.sha }}'
run: |
# Fetch the fork's PR branch for analysis
git fetch origin pull/${{ github.event.pull_request.number }}/head:pr-head
# Run the trusted script from main
SHOULD_RUN=$(node scripts/changed_prompt.js)
STEERING_DETECTED=$(node scripts/changed_prompt.js --steering-only)
echo "SHOULD_RUN=$SHOULD_RUN" >> "$GITHUB_OUTPUT"
echo "STEERING_DETECTED=$STEERING_DETECTED" >> "$GITHUB_OUTPUT"
- name: 'Notify Approval Required'
if: "steps.detect.outputs.SHOULD_RUN == 'true'"
env:
GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
run: |
RUN_URL="https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"
COMMENT_BODY="### 🛑 Action Required: Evaluation Approval
Steering changes have been detected in this PR. To prevent regressions, a maintainer must approve the evaluation run before this PR can be merged.
**Maintainers:**
1. Go to the [**Workflow Run Summary**]($RUN_URL).
2. Click the yellow **'Review deployments'** button.
3. Select the **'eval-gate'** environment and click **'Approve'**.
Once approved, the evaluation results will be posted here automatically.
<!-- eval-approval-notification -->"
# Check if comment already exists to avoid spamming
COMMENT_ID=$(gh pr view ${{ github.event.pull_request.number }} --json comments --jq '.comments[] | select(.body | contains("<!-- eval-approval-notification -->")) | .url' | grep -oE "[0-9]+$" | head -n 1)
if [ -z "$COMMENT_ID" ]; then
gh pr comment ${{ github.event.pull_request.number }} --body "$COMMENT_BODY"
else
echo "Updating existing notification comment $COMMENT_ID..."
gh api -X PATCH "repos/${{ github.repository }}/issues/comments/$COMMENT_ID" -F body="$COMMENT_BODY"
fi
pr-evaluation:
name: 'Evaluate Steering & Regressions'
needs: 'detect-changes'
if: "needs.detect-changes.outputs.SHOULD_RUN == 'true'"
# Manual approval gate via environment
environment: 'eval-gate'
runs-on: 'gemini-cli-ubuntu-16-core'
env:
# CENTRALIZED MODEL LIST
MODEL_LIST: 'gemini-3-flash-preview'
steps:
- name: 'Checkout'
uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v5
with:
# Check out the fork's PR code for the actual evaluation
# This only runs AFTER manual approval
ref: '${{ github.event.pull_request.head.sha }}'
fetch-depth: 0
persist-credentials: false
- name: 'Remove Approval Notification'
# Run even if other steps fail, to ensure we clean up the "Action Required" message
if: 'always()'
env:
GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
PR_NUMBER: '${{ github.event.pull_request.number }}'
run: |
echo "Debug: PR_NUMBER is '$PR_NUMBER'"
# Search for the notification comment by its hidden tag
COMMENT_ID=$(gh pr view "$PR_NUMBER" --json comments --jq '.comments[] | select(.body | contains("<!-- eval-approval-notification -->")) | .url' | grep -oE "[0-9]+$" | head -n 1)
if [ -n "$COMMENT_ID" ]; then
echo "Removing notification comment $COMMENT_ID now that run is approved..."
gh api -X DELETE "repos/${{ github.repository }}/issues/comments/$COMMENT_ID"
fi
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4.4.0
with:
node-version-file: '.nvmrc'
cache: 'npm'
- name: 'Install dependencies'
run: 'npm ci'
- name: 'Build project'
run: 'npm run build'
- name: 'Analyze PR Content (Guidance)'
if: "needs.detect-changes.outputs.STEERING_DETECTED == 'true'"
id: 'analysis'
env:
GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
run: |
# Check for behavioral eval changes
EVAL_CHANGES=$(git diff --name-only origin/${{ github.base_ref }}...HEAD | grep "^evals/" || true)
if [ -z "$EVAL_CHANGES" ]; then
echo "MISSING_EVALS=true" >> "$GITHUB_OUTPUT"
fi
# Check if user is a maintainer
USER_PERMISSION=$(gh api repos/${{ github.repository }}/collaborators/${{ github.actor }}/permission --jq '.permission')
if [[ "$USER_PERMISSION" == "admin" || "$USER_PERMISSION" == "write" ]]; then
echo "IS_MAINTAINER=true" >> "$GITHUB_OUTPUT"
fi
- name: 'Execute Regression Check'
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
MODEL_LIST: '${{ env.MODEL_LIST }}'
run: |
# Run the regression check loop. The script saves the report to a file.
node scripts/run_eval_regression.js
# Use the generated report file if it exists
if [[ -f eval_regression_report.md ]]; then
echo "REPORT_FILE=eval_regression_report.md" >> "$GITHUB_ENV"
fi
- name: 'Post or Update PR Comment'
if: "always() && (needs.detect-changes.outputs.STEERING_DETECTED == 'true' || env.REPORT_FILE != '')"
env:
GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
run: |
# 1. Build the full comment body
{
if [[ -f eval_regression_report.md ]]; then
cat eval_regression_report.md
echo ""
fi
if [[ "${{ needs.detect-changes.outputs.STEERING_DETECTED }}" == "true" ]]; then
echo "### 🧠 Model Steering Guidance"
echo ""
echo "This PR modifies files that affect the model's behavior (prompts, tools, or instructions)."
echo ""
if [[ "${{ steps.analysis.outputs.MISSING_EVALS }}" == "true" ]]; then
echo "- ⚠️ **Consider adding Evals:** No behavioral evaluations (\`evals/*.eval.ts\`) were added or updated in this PR. Consider [adding a test case](https://github.com/google-gemini/gemini-cli/blob/main/evals/README.md#creating-an-evaluation) to verify the new behavior and prevent regressions."
fi
if [[ "${{ steps.analysis.outputs.IS_MAINTAINER }}" == "true" ]]; then
echo "- 🚀 **Maintainer Reminder:** Please ensure that these changes do not regress results on benchmark evals before merging."
fi
fi
echo ""
echo "---"
echo "*This is an automated guidance message triggered by steering logic signatures.*"
echo "<!-- eval-pr-report -->"
} > full_comment.md
# 2. Find if a comment with our unique tag already exists
# We extract the numeric ID from the URL to ensure compatibility with the REST API
COMMENT_ID=$(gh pr view ${{ github.event.pull_request.number }} --json comments --jq '.comments[] | select(.body | contains("<!-- eval-pr-report -->")) | .url' | grep -oE "[0-9]+$" | head -n 1)
# 3. Update or Create the comment
if [ -n "$COMMENT_ID" ]; then
echo "Updating existing comment $COMMENT_ID via API..."
gh api -X PATCH "repos/${{ github.repository }}/issues/comments/$COMMENT_ID" -F body=@full_comment.md
else
echo "Creating new PR comment..."
gh pr comment ${{ github.event.pull_request.number }} --body-file full_comment.md
fi
+5 -23
View File
@@ -5,18 +5,10 @@ on:
- cron: '0 1 * * *' # Runs at 1 AM every day
workflow_dispatch:
inputs:
suite_type:
description: 'Suite type to run'
type: 'choice'
options:
- 'behavioral'
- 'component-level'
- 'hero-scenario'
default: 'behavioral'
suite_name:
description: 'Specific suite name to run'
required: false
type: 'string'
run_all:
description: 'Run all evaluations (including usually passing)'
type: 'boolean'
default: true
test_name_pattern:
description: 'Test name pattern or file name'
required: false
@@ -46,8 +38,6 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -68,15 +58,9 @@ jobs:
continue-on-error: true
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
GEMINI_CLI_TRUST_WORKSPACE: true
GEMINI_MODEL: '${{ matrix.model }}'
RUN_EVALS: 'true'
EVAL_SUITE_TYPE: "${{ github.event.inputs.suite_type || 'behavioral' }}"
EVAL_SUITE_NAME: '${{ github.event.inputs.suite_name }}'
RUN_EVALS: "${{ github.event.inputs.run_all != 'false' }}"
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}"
@@ -107,8 +91,6 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Download Logs'
uses: 'actions/download-artifact@cc203385981b70ca67e1cc392babf9cc229d5806' # ratchet:actions/download-artifact@v4
@@ -48,8 +48,6 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Log in to GitHub Container Registry'
uses: 'docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1' # ratchet:docker/login-action@v3
@@ -68,9 +66,7 @@ jobs:
ISSUE_NUMBER: '${{ github.event.issue.number }}'
REPOSITORY: '${{ github.repository }}'
FIRESTORE_PROJECT: '${{ vars.FIRESTORE_PROJECT }}'
GEMINI_CLI_TRUST_WORKSPACE: 'true'
with:
upload_artifacts: 'true'
gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -109,12 +105,10 @@ jobs:
}
},
"maxSessionTurns": 25,
"tools": {
"core": [
"run_shell_command(echo)",
"run_shell_command(gh issue view)"
]
},
"coreTools": [
"run_shell_command(echo)",
"run_shell_command(gh issue view)"
],
"telemetry": {
"enabled": true,
"target": "gcp"
@@ -90,8 +90,6 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Generate GitHub App Token'
id: 'generate_token'
@@ -131,31 +129,20 @@ jobs:
core.info(`Found ${labelNames.length} labels: ${labelNames.join(', ')}`);
return labelNames;
- name: 'Prepare Issue Data'
id: 'prepare_issue_data'
env:
ISSUE_TITLE: >-
${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.title || github.event.issue.title }}
ISSUE_BODY: >-
${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.body || github.event.issue.body }}
run: |
set -euo pipefail
echo "Title: ${ISSUE_TITLE}" > issue_context.md
echo "Body:" >> issue_context.md
echo "${ISSUE_BODY}" >> issue_context.md
- name: 'Run Gemini Issue Analysis'
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
ISSUE_TITLE: >-
${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.title || github.event.issue.title }}
ISSUE_BODY: >-
${{ github.event_name == 'workflow_dispatch' && steps.get_issue_data.outputs.body || github.event.issue.body }}
ISSUE_NUMBER: >-
${{ github.event_name == 'workflow_dispatch' && (github.event.inputs.issue_number || inputs.issue_number) || github.event.issue.number }}
REPOSITORY: '${{ github.repository }}'
AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
GEMINI_CLI_TRUST_WORKSPACE: 'true'
with:
upload_artifacts: 'true'
gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -170,12 +157,9 @@ jobs:
"enabled": true,
"target": "gcp"
},
"tools": {
"core": [
"run_shell_command(echo)",
"read_file"
]
}
"coreTools": [
"run_shell_command(echo)"
]
}
prompt: |-
## Role
@@ -183,7 +167,7 @@ jobs:
You are an issue triage assistant. Your role is to analyze a GitHub issue and determine the single most appropriate area/ label based on the definitions provided.
## Steps
1. Use the read_file tool to read the file "issue_context.md" which contains the issue title and body.
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. Fallback Logic:
@@ -338,41 +322,14 @@ jobs:
return;
}
const newAreaLabel = labelsToAdd[0];
// Get current labels to resolve conflicts
const { data: currentLabels } = await github.rest.issues.listLabelsOnIssue({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
});
const currentLabelNames = currentLabels.map(l => l.name);
const currentAreaLabels = currentLabelNames.filter(name => name.startsWith('area/'));
const labelsToRemove = currentAreaLabels.filter(name => name !== newAreaLabel);
for (const label of labelsToRemove) {
try {
await github.rest.issues.removeLabel({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
name: label
});
core.info(`Removed conflicting area label: ${label}`);
} catch (e) {
core.warning(`Failed to remove label ${label}: ${e.message}`);
}
}
// Set labels based on triage result
await github.rest.issues.addLabels({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
labels: [newAreaLabel]
labels: labelsToAdd
});
core.info(`Successfully added labels for #${issueNumber}: ${newAreaLabel}`);
core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}`);
- name: 'Post Issue Analysis Failure Comment'
if: |-
-350
View File
@@ -1,350 +0,0 @@
name: '🧠 Gemini CLI Bot: Brain'
on:
schedule:
- cron: '0 0 * * *' # Every 24 hours
issue_comment:
types: ['created']
workflow_dispatch:
inputs:
run_interactive:
description: 'Run interactive flow (requires issue_number)'
type: 'boolean'
default: false
issue_number:
description: 'Issue/PR number to simulate context from'
type: 'string'
required: false
comment_id:
description: 'Specific comment ID to simulate'
type: 'string'
required: false
clear_memory:
description: 'Clear memory (drops learnings from previous runs)'
type: 'boolean'
default: false
enable_prs:
description: 'Enable PRs (automatically promote changes to PRs)'
type: 'boolean'
default: false
concurrency:
group: '${{ github.workflow }}-${{ github.event.issue.number || github.event.inputs.issue_number || github.ref }}'
cancel-in-progress: true
jobs:
reasoning:
name: 'Brain (Reasoning Layer)'
runs-on: 'ubuntu-latest'
if: |
github.repository == 'google-gemini/gemini-cli' && (
github.event_name == 'schedule' ||
(github.event_name == 'workflow_dispatch' && github.event.inputs.run_interactive != 'true') ||
(github.event_name == 'workflow_dispatch' && github.event.inputs.run_interactive == 'true') ||
(github.event_name == 'issue_comment' && github.event.comment.user.login != 'gemini-cli[bot]' && contains(github.event.comment.body, '@gemini-cli') && contains(fromJSON('["COLLABORATOR", "MEMBER", "OWNER"]'), github.event.comment.author_association))
)
# The reasoning phase is strictly readonly.
permissions:
contents: 'read'
issues: 'read'
actions: 'read'
env:
GEMINI_CLI_TRUST_WORKSPACE: 'true'
steps:
- name: 'Determine Checkout Ref'
id: 'determine_ref'
env:
GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
run: |
REF="${{ github.ref }}"
if [ -n "$ISSUE_NUMBER" ]; then
PR_HEAD=$(gh pr view "$ISSUE_NUMBER" --repo "${{ github.repository }}" --json headRefName --jq .headRefName 2>/dev/null || echo "")
if [ -n "$PR_HEAD" ]; then
REF="$PR_HEAD"
fi
fi
echo "ref=$REF" >> "$GITHUB_OUTPUT"
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
ref: '${{ steps.determine_ref.outputs.ref }}'
fetch-depth: 0
persist-credentials: false
- name: 'Setup Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
with:
node-version: '20'
cache: 'npm'
- name: 'Install dependencies'
run: 'npm ci'
- name: 'Build Gemini CLI'
run: 'npm run bundle'
- name: 'Download Previous State'
env:
GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
run: |
if [ "${{ github.event.inputs.clear_memory }}" = "true" ]; then
echo "Memory clear requested. Skipping previous state download."
exit 0
fi
# Find the last successful run of this workflow
LAST_RUN_ID=$(gh run list --workflow "${{ github.workflow }}" --status success --limit 1 --json databaseId --jq '.[0].databaseId')
if [ -n "$LAST_RUN_ID" ]; then
echo "Found previous successful run: $LAST_RUN_ID"
# Download brain memory to a temp dir so we can selectively restore only persistent state
mkdir -p .temp_brain_data
gh run download "$LAST_RUN_ID" -n brain-data -D .temp_brain_data || echo "brain-data not found"
# Restore only persistent memory files
cp .temp_brain_data/tools/gemini-cli-bot/lessons-learned.md tools/gemini-cli-bot/lessons-learned.md 2>/dev/null || true
mkdir -p tools/gemini-cli-bot/history/
cp .temp_brain_data/tools/gemini-cli-bot/history/*.csv tools/gemini-cli-bot/history/ 2>/dev/null || true
rm -rf .temp_brain_data
else
echo "No previous successful run found."
fi
- name: 'Collect Current Metrics'
env:
GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
run: 'npx tsx tools/gemini-cli-bot/metrics/index.ts'
- name: 'Run Brain Phases'
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
GEMINI_MODEL: 'gemini-3-flash-preview'
GEMINI_CLI_HOME: 'tools/gemini-cli-bot'
ENABLE_PRS: "${{ github.event.inputs.enable_prs || 'false' }}"
TRIGGER_ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
TRIGGER_COMMENT_ID: '${{ github.event.comment.id || github.event.inputs.comment_id }}'
run: |
PROMPT_PATH="tools/gemini-cli-bot/brain/scheduled.md"
if [ "${{ github.event_name }}" = "issue_comment" ] || [ "${{ github.event.inputs.run_interactive }}" = "true" ]; then
PROMPT_PATH="tools/gemini-cli-bot/brain/interactive.md"
export ENABLE_PRS="true"
fi
touch trigger_context.md
if [ -n "$TRIGGER_ISSUE_NUMBER" ]; then
echo "<untrusted_context>" > trigger_context.md
echo "# Interactive Trigger Context" >> trigger_context.md
echo "You were invoked by a user in issue/PR #$TRIGGER_ISSUE_NUMBER." >> trigger_context.md
if [ -n "$TRIGGER_COMMENT_ID" ]; then
echo "## User Comment" >> trigger_context.md
gh api "repos/${{ github.repository }}/issues/comments/$TRIGGER_COMMENT_ID" -q '.body' >> trigger_context.md 2>/dev/null || gh api "repos/${{ github.repository }}/pulls/comments/$TRIGGER_COMMENT_ID" -q '.body' >> trigger_context.md
echo "" >> trigger_context.md
fi
echo "## Issue/PR Context" >> trigger_context.md
gh issue view "$TRIGGER_ISSUE_NUMBER" >> trigger_context.md 2>/dev/null || gh pr view "$TRIGGER_ISSUE_NUMBER" >> trigger_context.md
echo "</untrusted_context>" >> trigger_context.md
fi
if [ "$ENABLE_PRS" = "true" ]; then
echo "**System Directive**: PR creation is ENABLED for this run. You MUST activate the **'prs' skill** to stage your changes and generate a \`pr-description.md\` file if you are proposing fixes." >> trigger_context.md
echo "**CRITICAL System Directive**: You MUST ONLY propose and implement a **SINGLE** improvement or fix per run. Bundling unrelated changes (e.g., a documentation update and a script fix, or a metrics update and a logic fix) into a single PR is STRICTLY FORBIDDEN and will result in immediate rejection during the critique phase. If you identify multiple issues, pick the most impactful one and ignore the others for now." >> trigger_context.md
else
echo "**System Directive**: PR creation is DISABLED for this run. You MUST NOT stage files or attempt to create a PR description." >> trigger_context.md
fi
echo "" >> trigger_context.md
cat trigger_context.md "$PROMPT_PATH" > combined_prompt.md
node bundle/gemini.js --policy tools/gemini-cli-bot/ci-policy.toml --prompt="$(cat combined_prompt.md)"
if [ -n "$TRIGGER_ISSUE_NUMBER" ] && [ ! -s "issue-comment.md" ] && [ ! -s "pr-comment.md" ]; then
echo "Agent failed to respond. Generating fallback error message."
echo "⚠️ **Gemini CLI Bot failed to generate a response.**" > "issue-comment.md"
echo "" >> "issue-comment.md"
echo "I encountered an error or failed to generate a complete response to your request. You can check the [GitHub Actions Run Log](https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}) for more details on what went wrong." >> "issue-comment.md"
fi
- name: 'Run Critique Phase'
if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
GEMINI_MODEL: 'gemini-3-flash-preview'
GEMINI_CLI_HOME: 'tools/gemini-cli-bot'
run: |
if git diff --staged --quiet; then
echo "No changes staged. Skipping critique."
echo "[APPROVED]" > critique_result.txt
else
node bundle/gemini.js --policy tools/gemini-cli-bot/ci-policy.toml --prompt="$(cat tools/gemini-cli-bot/.gemini/skills/critique/SKILL.md)" 2>&1 | tee critique_output.log
if [ "${PIPESTATUS[0]}" -eq 0 ] && grep -q "\[APPROVED\]" critique_output.log && ! grep -q "\[REJECTED\]" critique_output.log; then
echo "[APPROVED]" > critique_result.txt
else
echo "Critique failed, rejected, or did not explicitly approve changes. Skipping PR creation."
echo "[REJECTED]" > critique_result.txt
fi
fi
- name: 'Generate Patch'
if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
run: |
touch bot-changes.patch
touch pr-description.md
if [ -f critique_result.txt ] && grep -q "\[APPROVED\]" critique_result.txt && ! grep -q "\[REJECTED\]" critique_result.txt; then
git diff --staged > bot-changes.patch
else
echo "Critique did not approve. Skipping patch generation."
fi
- name: 'Archive Brain Data'
uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
with:
name: 'brain-data'
path: |
tools/gemini-cli-bot/lessons-learned.md
tools/gemini-cli-bot/history/*.csv
bot-changes.patch
pr-description.md
branch-name.txt
pr-comment.md
pr-number.txt
issue-comment.md
retention-days: 90
publish:
name: 'Publish Artifacts (Archive Layer)'
needs: 'reasoning'
runs-on: 'ubuntu-latest'
if: "github.repository == 'google-gemini/gemini-cli'"
# The publish phase is for archiving artifacts and optionally creating PRs.
permissions:
contents: 'write'
pull-requests: 'write'
actions: 'write'
steps:
- name: 'Generate GitHub App Token 🔑'
id: 'generate_token'
if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
uses: 'actions/create-github-app-token@a8d616148505b5069dccd32f177bb87d7f39123b' # ratchet:actions/create-github-app-token@v2
with:
app-id: '${{ secrets.APP_ID }}'
private-key: '${{ secrets.PRIVATE_KEY }}'
owner: '${{ github.repository_owner }}'
repositories: '${{ github.event.repository.name }}'
permission-contents: 'write'
permission-pull-requests: 'write'
permission-issues: 'write'
- name: 'Determine Checkout Ref'
id: 'determine_ref'
env:
GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
run: |
REF="main"
if [ -n "$ISSUE_NUMBER" ]; then
PR_HEAD=$(gh pr view "$ISSUE_NUMBER" --repo "${{ github.repository }}" --json headRefName --jq .headRefName 2>/dev/null || echo "")
if [ -n "$PR_HEAD" ]; then
REF="$PR_HEAD"
fi
fi
echo "ref=$REF" >> "$GITHUB_OUTPUT"
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
ref: '${{ steps.determine_ref.outputs.ref }}'
fetch-depth: 0
persist-credentials: false
- name: 'Download Brain Data'
uses: 'actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093' # ratchet:actions/download-artifact@v4
with:
name: 'brain-data'
path: '${{ runner.temp }}/brain-data/'
- name: 'Create or Update PR'
if: "${{ github.event.inputs.enable_prs == 'true' || github.event_name == 'issue_comment' || github.event.inputs.run_interactive == 'true' }}"
env:
GH_TOKEN: '${{ steps.generate_token.outputs.token }}'
FALLBACK_PAT: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
run: |
if [ -s "${{ runner.temp }}/brain-data/bot-changes.patch" ]; then
git config user.name "gemini-cli[bot]"
git config user.email "gemini-cli[bot]@users.noreply.github.com"
git remote set-url origin "https://x-access-token:${GH_TOKEN}@github.com/${{ github.repository }}.git"
BRANCH_NAME="bot/productivity-updates-$(date +'%Y%m%d%H%M%S')-${{ github.run_id }}"
if [ -f "${{ runner.temp }}/brain-data/branch-name.txt" ]; then
BRANCH_NAME=$(cat "${{ runner.temp }}/brain-data/branch-name.txt")
fi
if [[ ! "$BRANCH_NAME" =~ ^bot/ ]]; then
echo "Error: Branch name '$BRANCH_NAME' does not start with 'bot/'. Safety abort."
exit 1
fi
git checkout -B "$BRANCH_NAME"
git apply "${{ runner.temp }}/brain-data/bot-changes.patch"
git add .
if [ -s "${{ runner.temp }}/brain-data/pr-description.md" ]; then
git commit -F "${{ runner.temp }}/brain-data/pr-description.md"
else
git commit -m "🤖 Gemini Bot Productivity Optimizations"
fi
PR_TITLE="🤖 Gemini Bot Productivity Optimizations"
if [ -s "${{ runner.temp }}/brain-data/pr-description.md" ]; then
PR_TITLE=$(head -n 1 "${{ runner.temp }}/brain-data/pr-description.md")
fi
if ! git push origin "$BRANCH_NAME" --force; then
echo "Push failed. Retrying with FALLBACK_PAT..."
export GH_TOKEN="$FALLBACK_PAT"
git remote set-url origin "https://x-access-token:${FALLBACK_PAT}@github.com/${{ github.repository }}.git"
git push origin "$BRANCH_NAME" --force
fi
if ! gh pr view "$BRANCH_NAME" > /dev/null 2>&1; then
gh pr create --draft --title "$PR_TITLE" --body-file "${{ runner.temp }}/brain-data/pr-description.md" --head "$BRANCH_NAME" --base main || \
gh pr create --draft --title "🤖 Gemini Bot Productivity Optimizations" --body "Automated changes generated by Gemini CLI Bot." --head "$BRANCH_NAME" --base main
else
PR_STATE=$(gh pr view "$BRANCH_NAME" --json state --jq .state)
if [ "$PR_STATE" = "CLOSED" ]; then
NEW_BRANCH_NAME="${BRANCH_NAME}-retry-${{ github.run_id }}"
git checkout -b "$NEW_BRANCH_NAME"
git push origin "$NEW_BRANCH_NAME" --force
gh pr create --draft --title "$PR_TITLE" --body-file "${{ runner.temp }}/brain-data/pr-description.md" --head "$NEW_BRANCH_NAME" --base main || \
gh pr create --draft --title "🤖 Gemini Bot Productivity Optimizations" --body "Automated changes generated by Gemini CLI Bot." --head "$NEW_BRANCH_NAME" --base main
fi
fi
fi
- name: 'Post PR/Issue Comment'
env:
GH_TOKEN: '${{ steps.generate_token.outputs.token }}'
TRIGGER_ISSUE_NUMBER: '${{ github.event.issue.number || github.event.inputs.issue_number }}'
run: |
if [ -s "${{ runner.temp }}/brain-data/issue-comment.md" ] && [ -n "$TRIGGER_ISSUE_NUMBER" ]; then
echo "Posting comment to triggering issue #$TRIGGER_ISSUE_NUMBER"
# Use REST API (gh api) instead of GraphQL (gh issue comment) to ensure robot identity
# while avoiding potential GraphQL-specific authorization hurdles with PATs.
gh api "repos/${{ github.repository }}/issues/$TRIGGER_ISSUE_NUMBER/comments" -F body=@"${{ runner.temp }}/brain-data/issue-comment.md"
fi
if [ -s "${{ runner.temp }}/brain-data/pr-comment.md" ] && [ -f "${{ runner.temp }}/brain-data/pr-number.txt" ]; then
PR_NUM=$(cat "${{ runner.temp }}/brain-data/pr-number.txt")
# Using GitHub App, so author check is no longer valid against gemini-cli-robot
# Skipping author validation here to let the app post.
# Use REST API (gh api) for consistency and robot identity
gh api "repos/${{ github.repository }}/issues/$PR_NUM/comments" -F body=@"${{ runner.temp }}/brain-data/pr-comment.md"
fi
@@ -1,49 +0,0 @@
name: '🔄 Gemini CLI Bot: Pulse'
on:
schedule:
- cron: '*/30 * * * *' # Every 30 minutes
workflow_dispatch:
concurrency:
group: '${{ github.workflow }}-${{ github.ref }}'
cancel-in-progress: true
permissions:
contents: 'write'
issues: 'write'
pull-requests: 'write'
jobs:
pulse:
name: 'Pulse (Reflex Layer)'
runs-on: 'ubuntu-latest'
if: "github.repository == 'google-gemini/gemini-cli'"
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
fetch-depth: 0
- name: 'Setup Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
with:
node-version: '20'
cache: 'npm'
- name: 'Install dependencies'
run: 'npm ci'
- name: 'Run Reflex Processes'
env:
GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
run: |
if [ -d "tools/gemini-cli-bot/reflexes/scripts" ] && [ "$(ls -A tools/gemini-cli-bot/reflexes/scripts)" ]; then
for script in tools/gemini-cli-bot/reflexes/scripts/*.ts; do
echo "Running reflex script: $script"
npx tsx "$script"
done
else
echo "No reflex scripts found."
fi
@@ -1,47 +0,0 @@
name: '🔄 Gemini Scheduled Lifecycle Manager'
on:
schedule:
- cron: '30 1 * * *' # Once a day
workflow_dispatch:
inputs:
dry_run:
description: 'Run in dry-run mode (no changes applied)'
required: false
default: false
type: 'boolean'
concurrency:
group: '${{ github.workflow }}'
cancel-in-progress: true
permissions:
issues: 'write'
pull-requests: 'write'
jobs:
manage-lifecycle:
if: "github.repository == 'google-gemini/gemini-cli'"
runs-on: 'ubuntu-latest'
steps:
- name: 'Generate GitHub App Token'
id: 'generate_token'
uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
with:
app-id: '${{ secrets.APP_ID }}'
private-key: '${{ secrets.PRIVATE_KEY }}'
- name: 'Checkout repository'
uses: 'actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683' # ratchet:actions/checkout@v4
with:
persist-credentials: false
- name: 'Lifecycle Management'
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
env:
DRY_RUN: '${{ inputs.dry_run }}'
with:
github-token: '${{ steps.generate_token.outputs.token }}'
script: |
const script = require('./.github/scripts/gemini-lifecycle-manager.cjs');
await script({github, context, core});
@@ -28,8 +28,6 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Log in to GitHub Container Registry'
uses: 'docker/login-action@184bdaa0721073962dff0199f1fb9940f07167d1' # ratchet:docker/login-action@v3
@@ -49,7 +47,6 @@ jobs:
REPOSITORY: '${{ github.repository }}'
FIRESTORE_PROJECT: '${{ vars.FIRESTORE_PROJECT }}'
with:
upload_artifacts: 'true'
gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -88,11 +85,9 @@ jobs:
}
},
"maxSessionTurns": 25,
"tools": {
"core": [
"run_shell_command(echo)"
]
},
"coreTools": [
"run_shell_command(echo)"
],
"telemetry": {
"enabled": true,
"target": "gcp"
@@ -1,6 +1,10 @@
name: '📋 Gemini Scheduled Issue Triage'
on:
issues:
types:
- 'opened'
- 'reopened'
schedule:
- cron: '0 * * * *' # Runs every hour
workflow_dispatch:
@@ -19,27 +23,13 @@ permissions:
jobs:
triage-issues:
timeout-minutes: 60
timeout-minutes: 10
if: |-
${{ github.repository == 'google-gemini/gemini-cli' }}
runs-on: 'ubuntu-latest'
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Install Utilities'
run: |
sudo apt-get update
sudo apt-get install -y ripgrep
- name: 'Get Current Version'
id: 'get_version'
run: |
VERSION=$(jq -r .version package.json | cut -d'-' -f1)
echo "version=${VERSION}" >> "${GITHUB_OUTPUT}"
echo "🚀 Current CLI Version: ${VERSION}"
- name: 'Generate GitHub App Token'
id: 'generate_token'
@@ -57,38 +47,10 @@ jobs:
ISSUE_EVENT: '${{ toJSON(github.event.issue) }}'
run: |
set -euo pipefail
echo "$ISSUE_EVENT" | jq -c '[{number: .number, title: .title, body: .body}]' > issues_to_triage.json
echo "has_issues=true" >> "${GITHUB_OUTPUT}"
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: 'Sync Issue Types'
if: |-
${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
with:
github-token: '${{ steps.generate_token.outputs.token }}'
script: |-
const syncIssueTypes = require('./.github/scripts/sync-issue-types.cjs');
await syncIssueTypes({ github, context, core });
- name: 'Find Issues with Conflicting Labels'
if: |-
${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
env:
GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
GITHUB_REPOSITORY: '${{ github.repository }}'
run: |-
set -euo pipefail
echo '🔍 Fetching open issues to find conflicts...'
# Fetch up to 2000 open issues in one quick GraphQL-backed query
gh issue list --repo "${GITHUB_REPOSITORY}" --search "is:issue is:open" --limit 2000 --json number,title,body,labels > all_open_issues.json
echo '🧹 Filtering issues with multiple area/ or priority/ labels...'
jq -c '[ .[] | select( (.labels | map(select(.name | startswith("area/"))) | length) > 1 or (.labels | map(select(.name | startswith("priority/"))) | length) > 1 ) ] | .[0:50]' all_open_issues.json > conflicting_labels_issues.json
CONFLICT_COUNT=$(jq 'length' conflicting_labels_issues.json)
echo "Found ${CONFLICT_COUNT} issues with conflicting labels (capped at 50 for processing)."
- name: 'Find untriaged issues'
if: |-
${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
@@ -100,56 +62,25 @@ jobs:
set -euo pipefail
echo '🔍 Finding issues missing area labels...'
gh issue list --repo "${GITHUB_REPOSITORY}" \
--search 'is:open is:issue -label:area/core -label:area/agent -label:area/enterprise -label:area/non-interactive -label:area/security -label:area/platform -label:area/extensions -label:area/documentation -label:area/unknown' --limit 50 --json number,title,body,labels > no_area_issues.json
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 missing kind labels...'
gh issue list --repo "${GITHUB_REPOSITORY}" \
--search 'is:open is:issue -label:kind/bug -label:kind/enhancement -label:kind/customer-issue -label:kind/question' --limit 50 --json number,title,body,labels > no_kind_issues.json
NO_KIND_ISSUES="$(gh issue list --repo "${GITHUB_REPOSITORY}" \
--search 'is:open is:issue -label:kind/bug -label:kind/enhancement -label:kind/customer-issue -label:kind/question' --limit 100 --json number,title,body)"
echo '🏷️ Finding issues missing priority labels...'
gh issue list --repo "${GITHUB_REPOSITORY}" \
--search 'is:open is:issue -label:priority/p0 -label:priority/p1 -label:priority/p2 -label:priority/p3 -label:priority/unknown' --limit 50 --json number,title,body,labels > no_priority_issues.json
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 '📏 Finding issues missing effort labels...'
gh issue list --repo "${GITHUB_REPOSITORY}" \
--search 'is:open is:issue -label:effort/small -label:effort/medium -label:effort/large label:area/core,area/extensions,area/site,area/non-interactive' --limit 20 --json number,title,body,labels > no_effort_issues.json
echo '🔄 Merging and deduplicating issues...'
ISSUES="$(echo "${NO_AREA_ISSUES}" "${NO_KIND_ISSUES}" "${NO_PRIORITY_ISSUES}" | jq -c -s 'add | unique_by(.number)')"
echo '🔄 Merging and deduplicating standard triage issues...'
if [ ! -f conflicting_labels_issues.json ]; then echo "[]" > conflicting_labels_issues.json; fi
jq -c -s 'add | unique_by(.number)' no_area_issues.json no_kind_issues.json no_priority_issues.json conflicting_labels_issues.json > standard_issues_to_triage.json
echo '📝 Setting output for GitHub Actions...'
echo "issues_to_triage=${ISSUES}" >> "${GITHUB_OUTPUT}"
echo '📏 Deduplicating effort issues...'
jq -c -s 'add | unique_by(.number)' no_effort_issues.json > effort_issues_to_triage.json
STANDARD_COUNT="$(jq 'length' standard_issues_to_triage.json)"
EFFORT_COUNT="$(jq 'length' effort_issues_to_triage.json)"
if [ "$STANDARD_COUNT" -gt 0 ] || [ "$EFFORT_COUNT" -gt 0 ]; then
echo "has_issues=true" >> "${GITHUB_OUTPUT}"
echo "has_standard_issues=$([ "$STANDARD_COUNT" -gt 0 ] && echo 'true' || echo 'false')" >> "${GITHUB_OUTPUT}"
echo "has_effort_issues=$([ "$EFFORT_COUNT" -gt 0 ] && echo 'true' || echo 'false')" >> "${GITHUB_OUTPUT}"
else
echo "has_issues=false" >> "${GITHUB_OUTPUT}"
echo "has_standard_issues=false" >> "${GITHUB_OUTPUT}"
echo "has_effort_issues=false" >> "${GITHUB_OUTPUT}"
fi
echo "✅ Found ${STANDARD_COUNT} standard issues and ${EFFORT_COUNT} effort issues to triage! 🎯"
- name: 'Create Gemini CLI Experiments Override'
if: |-
steps.get_issue_from_event.outputs.has_issues == 'true' || steps.find_issues.outputs.has_issues == 'true'
run: |
cat << 'EOF' > gemini_exp.json
{
"flags": [
{
"flagId": 45750526,
"boolValue": false
}
],
"experimentIds": []
}
EOF
ISSUE_COUNT="$(echo "${ISSUES}" | jq 'length')"
echo "✅ Found ${ISSUE_COUNT} unique issues to triage! 🎯"
- name: 'Get Repository Labels'
id: 'get_labels'
@@ -166,22 +97,18 @@ jobs:
core.info(`Found ${labelNames.length} labels: ${labelNames.join(', ')}`);
return labelNames;
- name: 'Run Standard Triage Analysis'
- name: 'Run Gemini Issue Analysis'
if: |-
steps.get_issue_from_event.outputs.has_issues == 'true' || steps.find_issues.outputs.has_standard_issues == 'true'
(steps.get_issue_from_event.outputs.issues_to_triage != '' && steps.get_issue_from_event.outputs.issues_to_triage != '[]') ||
(steps.find_issues.outputs.issues_to_triage != '' && steps.find_issues.outputs.issues_to_triage != '[]')
uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
id: 'gemini_standard_issue_analysis'
id: 'gemini_issue_analysis'
env:
GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
ISSUES_TO_TRIAGE: '${{ steps.get_issue_from_event.outputs.issues_to_triage || steps.find_issues.outputs.issues_to_triage }}'
REPOSITORY: '${{ github.repository }}'
AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
CLI_VERSION: '${{ steps.get_version.outputs.version }}'
GEMINI_CLI_TRUST_WORKSPACE: 'true'
GEMINI_EXP: 'gemini_exp.json'
GEMINI_STRICT_TELEMETRY_LIMITS: 'true'
GEMINI_MODEL: 'gemini-3-flash-preview'
with:
upload_artifacts: 'true'
gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
@@ -192,14 +119,11 @@ jobs:
settings: |-
{
"maxSessionTurns": 25,
"tools": {
"core": [
"run_shell_command(echo)",
"read_file"
]
},
"coreTools": [
"run_shell_command(echo)"
],
"telemetry": {
"enabled": false,
"enabled": true,
"target": "gcp"
}
}
@@ -212,16 +136,14 @@ jobs:
## Steps
1. You are only able to use the echo and read_file commands. Review the available labels in the environment variable: "${AVAILABLE_LABELS}".
2. Use the read_file tool to read the file "standard_issues_to_triage.json" which contains the JSON array of issues to triage (including their current labels).
3. Review the issue title, body, current labels, and any comments provided in the JSON file.
4. Identify the most relevant labels from the existing labels, specifically focusing on area/*, kind/*, and priority/*.
1. You are only able to use the echo command. Review the available labels in the environment variable: "${AVAILABLE_LABELS}".
2. Check environment variable for issues to triage: $ISSUES_TO_TRIAGE (JSON array of issues)
3. Review the issue title, body and any comments provided in the environment variables.
4. Identify the most relevant labels from the existing labels, specifically focusing on area/*, kind/* and priority/*.
5. Label Policy:
- If the issue already has a kind/ label, do not change it.
- If the issue has exactly ONE priority/ label, do not change it (unless you are explicitly re-evaluating an ambiguous priority).
- If the issue is missing a priority/ label, OR if the issue currently has MULTIPLE priority/ labels, you must evaluate the issue's impact to determine exactly ONE priority level (priority/p0, priority/p1, priority/p2, priority/p3, or priority/unknown) based the guidelines. If you are fixing an issue with multiple priority/ labels, put the correct one in `labels_to_add` and put all the incorrect ones in `labels_to_remove`.
- If the issue has exactly ONE area/ label, do not change it.
- If the issue is missing an area/ label, OR if the issue currently has MULTIPLE area/ labels, select exactly ONE area/ label that best fits the issue. Issues MUST NOT have multiple area/ labels. If you are fixing an issue with multiple area/ labels, put the correct one in `labels_to_add` and put all the incorrect ones in `labels_to_remove`.
- If 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. Give me a single short explanation about why you are selecting each label in the process.
@@ -238,12 +160,11 @@ jobs:
]
```
If an issue cannot be classified, do not include it in the output array.
9. For each issue, carefully check if the CLI version is present. It is usually found under the "### Client information" header, as a bullet point (e.g., "• CLI Version: 0.33.1", "* **CLI Version:** 0.42.0"), or in the output of the `/about` command.
- **Only for issues classified as kind/bug:** If the version is provided but is more than 6 minor versions older than the most recent release (current version is ${{ steps.get_version.outputs.version }}), apply the status/need-information label and leave a comment politely asking the user to verify if the issue persists in the latest version.
10. **Only for issues classified as kind/bug:** If the issue does not have sufficient information, recommend the status/need-information label and leave a comment politely requesting the missing details. For example, if repro steps are missing, ask for them; if the CLI version is completely missing, ask for the version information in the explanation section below. Do not ask for version info if it is already in the issue body. (Check both bullet points and bold text). For features and enhancements, the CLI version is NOT required.
11. If you think an issue is a Priority/P0, you MUST apply the priority/p1 label AND the status/manual-triage label, and include a note in your explanation that it likely requires P0 escalation.
12. If the issue is highly ambiguous, completely lacks a description, or you are torn between two lower priorities (like P2 vs P3), you MUST retain the existing priority label if one is already present. Do not toggle the priority if you do not have enough information to make a definitive change.
13. If you are uncertain about a category, use the area/unknown, kind/question, or priority/unknown labels as appropriate. If you are extremely uncertain, apply the status/manual-triage label.
9. For each issue please check if CLI version is present, this is usually in the output of the /about command and will look like 0.1.5
- Anything more than 6 versions older than the most recent should add the status/need-retesting label
10. If you see that the issue doesn't look like it has sufficient information recommend the status/need-information label and leave a comment politely requesting the relevant information, eg.. if repro steps are missing request for repro steps. if version information is missing request for version information into the explanation section below.
11. If you think an issue might be a Priority/P0 do not apply the priority/p0 label. Instead apply a status/manual-triage label and include a note in your explanation.
12. If you are uncertain about a category, use the area/unknown, kind/question, or priority/unknown labels as appropriate. If you are extremely uncertain, apply the status/manual-triage label.
## Guidelines
@@ -253,127 +174,10 @@ 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 exactly ONE area/ label. Do NOT assign multiple area/ labels to a single issue.
- Identify only one area/ label.
- Identify only one kind/ label (Do not apply kind/duplicate or kind/parent-issue)
- Identify exactly ONE priority/ label. Do NOT assign multiple priority/ labels to a single issue.
- **Do not manually downgrade the priority.** Always assign the true priority based on the guidelines. The system will handle downgrades programmatically if information is missing.
- **NEVER mention label names, label removals, or label additions in your `explanation`.** The explanation must be purely written for the user (e.g., "Please provide your CLI version.") without exposing internal triage mechanics (e.g., do NOT say "Removing area/unknown to leave only area/core").
Categorization Guidelines (Priority):
P0 - Urgent Blocking Issues:
- DO NOT APPLY THE priority/p0 LABEL AUTOMATICALLY. Instead apply priority/p1 and status/manual-triage.
- Definition: Critical failures breaking core functionality for a large portion of users. Examples: CLI fails to launch globally, core commands (gemini run) crash on valid input, unhandled promise rejections on boot, critical security vulnerability.
- Note: You must apply priority/p1 and status/manual-triage instead of priority/p0.
P1 - Critical but Workable:
- Definition: Severe issues without a reasonable workaround, significantly degrading the developer experience but not globally blocking. Examples: Specific tools failing consistently (e.g., `web_search` returns 500s), persistent PTY streaming hangs, memory leaks leading to OOM after short use.
P2 - Significant Issues:
- Definition: Affect some workflows but a clear workaround exists, or non-critical bugs. Examples: Theme flickering, confusing error messages, minor UI misalignment, failing to read deeply nested config files correctly.
P3 - Minor/Enhancements:
- Definition: Trivial bugs, typos, documentation requests, or feature requests.
Categorization Guidelines (Kind):
kind/bug: The issue is describing an unexpected behavior or failure in the application.
kind/enhancement: The issue is describing a feature request or an improvement to an existing feature.
kind/question: The issue is asking a question about how to use the CLI or about a specific feature.
Categorization Guidelines (Area):
area/agent: The "brain" of the CLI. Core agent logic, model quality, tool/function calling, memory, web search, generated code quality, sub-agents.
area/core: The fundamental CLI app. UI/UX, installation, OS compatibility, performance, command parsing, theming, flickering.
area/documentation: Website docs, READMEs, inline help text.
area/enterprise: Telemetry, Policy, Quota / Licensing
area/extensions: Gemini CLI extensions capability
area/non-interactive: GitHub Actions, SDK, 3P Integrations, Shell Scripting, Command line automation
area/platform: Platform specific behavior
area/security: Authentication, authorization, privacy, data leaks, credential storage.
- name: 'Stop Telemetry Collector'
if: |-
steps.find_issues.outputs.has_effort_issues == 'true'
run: 'docker rm -f gemini-telemetry-collector || true'
- name: 'Run Effort Triage Analysis'
if: |-
steps.find_issues.outputs.has_effort_issues == 'true'
uses: 'google-github-actions/run-gemini-cli@a3bf79042542528e91937b3a3a6fbc4967ee3c31' # ratchet:google-github-actions/run-gemini-cli@v0
id: 'gemini_effort_issue_analysis'
env:
GITHUB_TOKEN: '' # Do not pass any auth token here since this runs on untrusted inputs
REPOSITORY: '${{ github.repository }}'
AVAILABLE_LABELS: '${{ steps.get_labels.outputs.available_labels }}'
CLI_VERSION: '${{ steps.get_version.outputs.version }}'
GEMINI_CLI_TRUST_WORKSPACE: 'true'
GEMINI_EXP: 'gemini_exp.json'
GEMINI_STRICT_TELEMETRY_LIMITS: 'true'
GEMINI_MODEL: 'gemini-3-flash-preview'
with:
upload_artifacts: 'true'
gcp_workload_identity_provider: '${{ vars.GCP_WIF_PROVIDER }}'
gcp_project_id: '${{ vars.GOOGLE_CLOUD_PROJECT }}'
gcp_location: '${{ vars.GOOGLE_CLOUD_LOCATION }}'
gcp_service_account: '${{ vars.SERVICE_ACCOUNT_EMAIL }}'
gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
use_vertex_ai: '${{ vars.GOOGLE_GENAI_USE_VERTEXAI }}'
use_gemini_code_assist: '${{ vars.GOOGLE_GENAI_USE_GCA }}'
settings: |-
{
"maxSessionTurns": 30,
"tools": {
"core": [
"run_shell_command(echo)",
"grep_search",
"glob",
"read_file"
]
},
"telemetry": {
"enabled": false,
"target": "gcp"
}
}
prompt: |-
## Role
You are an expert software architect. Analyze the provided GitHub issues and assign the correct `effort/*` label based on the codebase complexity.
## Steps
1. Use the read_file tool to read "effort_issues_to_triage.json".
2. For each issue in the array:
- You must evaluate the architectural complexity to determine the effort level. You MUST NOT guess the root cause. You MUST actively use your codebase search tools (grep_search and glob) to search for keywords from the issue and explore the codebase. You must identify the specific files and components involved before deciding the effort.
3. Output a JSON array of objects, each containing the issue number and the effort label to add, along with an explanation and an effort_analysis field. This effort_analysis must be highly detailed, technical, and empirical. It MUST NOT contain vague guesses (e.g., avoid words like "likely points to" or "possibly"). You must explicitly cite the specific file paths and architectural mechanisms you discovered using your search tools, explain the root cause, and then explicitly state how that complexity maps to the chosen effort level guidelines. For example:
```
[
{
"issue_number": 123,
"labels_to_add": ["effort/small"],
"explanation": "This is a simple logic fix.",
"effort_analysis": "The `vscode-ide-companion` extension indiscriminately tracks active text editors via `vscode.window.onDidChangeActiveTextEditor` in `open-files-manager.ts`. When a user opens `.vscode/settings.json`, its content is sent to the CLI's context. The fix is highly localized to the VS Code companion extension's event listener. It involves adding a simple conditional check to exclude specific configuration files from the active editor tracking logic, which is a trivial logic adjustment with a clear root cause."
}
]
```
## Guidelines
- Output only valid JSON format
- Do not include any explanation or additional text, just the JSON
- Triage only the current issue.
Categorization Guidelines (Effort):
effort/small (1 day or less):
- Trivial Logic & Config: Schema updates (Zod), feature flag toggles, adding missing fields to package.json or settings.json.
- UI/Aesthetic Adjustments: Fixing minor layout bugs in Ink components (e.g., adding flexShrink, correcting padding in a single Box), text color changes.
- Documentation & Strings: Typos, log message updates, CLI argument descriptions.
- Localized Bug Fixes: Single-file logic errors, straightforward promise rejections (e.g., wrapping a known failure in a try/catch), simple regex or string parsing fixes.
effort/medium (2-3 days):
- React/Ink State Management: Debugging useState/useEffect/useReducer bugs, component lifecycle issues (memory leaks in the UI), terminal redraw flickering, or state synchronization between the CLI's internal input buffer and the interactive React components.
- Asynchronous Flow & Integration: Resolving complex Promise chains, ERR_STREAM_PREMATURE_CLOSE, debugging IDE companion extensions (VS Code, Android Studio) or resolving hanging HTTP requests/IPC between the CLI and external plugins, timeouts in non-interactive/ACP modes.
- Tooling & Output Parsers: Modifying how tools parse streaming stdout/stderr buffers, adding new built-in tools that don't require native bindings.
- Cross-Component Refactors: Changes that span across packages/cli and packages/core to pass new data models or telemetry state.
effort/large (3+ days):
- Platform-Specific Complexities (PTY/Signals): Any issue involving node-pty, child_process.spawn, OS-level shell behavior (Windows vs Linux vs macOS), pseudo-terminal exhaustion (ENXIO), raw mode terminal desyncs, or POSIX signal forwarding (SIGINT/SIGTERM).
- Core Architecture & Protocols: Refactoring the Scheduler, Agent-to-Agent (A2A) protocol implementation, low-level MCP (Model Context Protocol) transport mechanisms.
- Performance & Memory: Diagnosing massive disk/memory leaks, severe boot time regressions, high-throughput streaming optimizations (e.g., voice streaming pipelines).
Note: Any bug that is described as intermittent, flickering, difficult to reproduce, platform-specific, or requiring cross-environment setups (e.g., involving the VS Code IDE companion, GCA plugin, or Android Studio) MUST NOT be rated as effort/small because of the increased overhead of testing and reproducing.
- 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 (Priority):
P0 - Urgent Blocking Issues:
@@ -412,52 +216,64 @@ jobs:
- This product is designed to use different models eg.. using pro, downgrading to flash etc.
- When users report that they dont expect the model to change those would be categorized as feature requests.
- name: 'Apply Triaged Labels'
- name: 'Apply Labels to Issues'
if: |-
always() &&
( (steps.gemini_standard_issue_analysis.outcome == 'success' && steps.gemini_standard_issue_analysis.outputs.summary != '[]' && steps.gemini_standard_issue_analysis.outputs.summary != '') ||
(steps.gemini_effort_issue_analysis.outcome == 'success' && steps.gemini_effort_issue_analysis.outputs.summary != '[]' && steps.gemini_effort_issue_analysis.outputs.summary != '') )
${{ steps.gemini_issue_analysis.outcome == 'success' &&
steps.gemini_issue_analysis.outputs.summary != '[]' }}
env:
LABELS_OUTPUT_STANDARD: '${{ steps.gemini_standard_issue_analysis.outputs.summary }}'
LABELS_OUTPUT_EFFORT: '${{ steps.gemini_effort_issue_analysis.outputs.summary }}'
REPOSITORY: '${{ github.repository }}'
LABELS_OUTPUT: '${{ steps.gemini_issue_analysis.outputs.summary }}'
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
with:
github-token: '${{ steps.generate_token.outputs.token }}'
script: |-
const applyLabels = require('./.github/scripts/apply-issue-labels.cjs');
await applyLabels({ github, context, core });
const rawLabels = process.env.LABELS_OUTPUT;
core.info(`Raw labels JSON: ${rawLabels}`);
let parsedLabels;
try {
const jsonMatch = rawLabels.match(/```json\s*([\s\S]*?)\s*```/);
if (!jsonMatch || !jsonMatch[1]) {
throw new Error("Could not find a ```json ... ``` block in the output.");
}
const jsonString = jsonMatch[1].trim();
parsedLabels = JSON.parse(jsonString);
core.info(`Parsed labels JSON: ${JSON.stringify(parsedLabels)}`);
} catch (err) {
core.setFailed(`Failed to parse labels JSON from Gemini output: ${err.message}\nRaw output: ${rawLabels}`);
return;
}
- name: 'Sync Issue Types (Post-Analysis)'
if: |-
always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
with:
github-token: '${{ steps.generate_token.outputs.token }}'
script: |-
const syncIssueTypes = require('./.github/scripts/sync-issue-types.cjs');
await syncIssueTypes({ github, context, core });
for (const entry of parsedLabels) {
const issueNumber = entry.issue_number;
if (!issueNumber) {
core.info(`Skipping entry with no issue number: ${JSON.stringify(entry)}`);
continue;
}
- name: 'Find Triaged Issues to Clean Up'
if: |-
always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
env:
GITHUB_TOKEN: '${{ steps.generate_token.outputs.token }}'
GITHUB_REPOSITORY: '${{ github.repository }}'
run: |-
set -euo pipefail
echo '🧹 Finding issues that have conflicting status labels...'
gh issue list --repo "${GITHUB_REPOSITORY}" \
--search 'is:open is:issue label:status/bot-triaged label:status/need-triage' --limit 50 --json number > cleanup_1.json
gh issue list --repo "${GITHUB_REPOSITORY}" \
--search 'is:open is:issue label:status/bot-triaged label:status/manual-triage' --limit 50 --json number > cleanup_2.json
jq -c -s 'add | unique_by(.number)' cleanup_1.json cleanup_2.json > issues_to_cleanup.json
const labelsToAdd = entry.labels_to_add || [];
labelsToAdd.push('status/bot-triaged');
- name: 'Clean Up Triage Labels'
if: |-
always() && (github.event_name == 'schedule' || github.event_name == 'workflow_dispatch')
uses: 'actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea'
with:
github-token: '${{ steps.generate_token.outputs.token }}'
script: |-
const cleanupLabels = require('./.github/scripts/cleanup-triage-labels.cjs');
await cleanupLabels({ github, context, core });
if (labelsToAdd.length > 0) {
await github.rest.issues.addLabels({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
labels: labelsToAdd
});
const explanation = entry.explanation ? ` - ${entry.explanation}` : '';
core.info(`Successfully added labels for #${issueNumber}: ${labelsToAdd.join(', ')}${explanation}`);
}
if (entry.explanation) {
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issueNumber,
body: entry.explanation,
});
}
if ((!entry.labels_to_add || entry.labels_to_add.length === 0) && (!entry.labels_to_remove || entry.labels_to_remove.length === 0)) {
core.info(`No labels to add or remove for #${issueNumber}, leaving as is`);
}
}
@@ -21,8 +21,6 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Generate GitHub App Token'
id: 'generate_token'
@@ -0,0 +1,159 @@
name: '🔒 Gemini Scheduled Stale Issue Closer'
on:
schedule:
- cron: '0 0 * * 0' # Every Sunday at midnight UTC
workflow_dispatch:
inputs:
dry_run:
description: 'Run in dry-run mode (no changes applied)'
required: false
default: false
type: 'boolean'
concurrency:
group: '${{ 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@v2'
with:
app-id: '${{ secrets.APP_ID }}'
private-key: '${{ secrets.PRIVATE_KEY }}'
permission-issues: 'write'
- name: 'Process Stale Issues'
uses: 'actions/github-script@v7'
env:
DRY_RUN: '${{ inputs.dry_run }}'
with:
github-token: '${{ steps.generate_token.outputs.token }}'
script: |
const dryRun = process.env.DRY_RUN === 'true';
if (dryRun) {
core.info('DRY RUN MODE ENABLED: No changes will be applied.');
}
const batchLabel = 'Stale';
const threeMonthsAgo = new Date();
threeMonthsAgo.setMonth(threeMonthsAgo.getMonth() - 3);
const tenDaysAgo = new Date();
tenDaysAgo.setDate(tenDaysAgo.getDate() - 10);
core.info(`Cutoff date for creation: ${threeMonthsAgo.toISOString()}`);
core.info(`Cutoff date for updates: ${tenDaysAgo.toISOString()}`);
const query = `repo:${context.repo.owner}/${context.repo.repo} is:issue is:open created:<${threeMonthsAgo.toISOString()}`;
core.info(`Searching with query: ${query}`);
const itemsToCheck = await github.paginate(github.rest.search.issuesAndPullRequests, {
q: query,
sort: 'created',
order: 'asc',
per_page: 100
});
core.info(`Found ${itemsToCheck.length} open issues to check.`);
let processedCount = 0;
for (const issue of itemsToCheck) {
const createdAt = new Date(issue.created_at);
const updatedAt = new Date(issue.updated_at);
const reactionCount = issue.reactions.total_count;
// Basic thresholds
if (reactionCount >= 5) {
continue;
}
// Skip if it has a maintainer, help wanted, or Public Roadmap label
const rawLabels = issue.labels.map((l) => l.name);
const lowercaseLabels = rawLabels.map((l) => l.toLowerCase());
if (
lowercaseLabels.some((l) => l.includes('maintainer')) ||
lowercaseLabels.includes('help wanted') ||
rawLabels.includes('🗓️ Public Roadmap')
) {
continue;
}
let isStale = updatedAt < tenDaysAgo;
// If apparently active, check if it's only bot activity
if (!isStale) {
try {
const comments = await github.rest.issues.listComments({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
per_page: 100,
sort: 'created',
direction: 'desc'
});
const lastHumanComment = comments.data.find(comment => comment.user.type !== 'Bot');
if (lastHumanComment) {
isStale = new Date(lastHumanComment.created_at) < tenDaysAgo;
} else {
// No human comments. Check if creator is human.
if (issue.user.type !== 'Bot') {
isStale = createdAt < tenDaysAgo;
} else {
isStale = true; // Bot created, only bot comments
}
}
} catch (error) {
core.warning(`Failed to fetch comments for issue #${issue.number}: ${error.message}`);
continue;
}
}
if (isStale) {
processedCount++;
const message = `Closing stale issue #${issue.number}: "${issue.title}" (${issue.html_url})`;
core.info(message);
if (!dryRun) {
// Add label
await github.rest.issues.addLabels({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
labels: [batchLabel]
});
// Add comment
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
body: 'Hello! As part of our effort to keep our backlog manageable and focus on the most active issues, we are tidying up older reports.\n\nIt looks like this issue hasn\'t been active for a while, so we are closing it for now. However, if you are still experiencing this bug on the latest stable build, please feel free to comment on this issue or create a new one with updated details.\n\nThank you for your contribution!'
});
// Close issue
await github.rest.issues.update({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: issue.number,
state: 'closed',
state_reason: 'not_planned'
});
}
}
}
core.info(`\nTotal issues processed: ${processedCount}`);
@@ -0,0 +1,254 @@
name: 'Gemini Scheduled Stale PR Closer'
on:
schedule:
- cron: '0 2 * * *' # Every day at 2 AM UTC
pull_request:
types: ['opened', 'edited']
workflow_dispatch:
inputs:
dry_run:
description: 'Run in dry-run mode'
required: false
default: false
type: 'boolean'
jobs:
close-stale-prs:
if: "github.repository == 'google-gemini/gemini-cli'"
runs-on: 'ubuntu-latest'
permissions:
pull-requests: 'write'
issues: 'write'
steps:
- name: 'Generate GitHub App Token'
id: 'generate_token'
env:
APP_ID: '${{ secrets.APP_ID }}'
if: |-
${{ env.APP_ID != '' }}
uses: 'actions/create-github-app-token@v2'
with:
app-id: '${{ secrets.APP_ID }}'
private-key: '${{ secrets.PRIVATE_KEY }}'
- name: 'Process Stale PRs'
uses: 'actions/github-script@v7'
env:
DRY_RUN: '${{ 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'
});
}
}
}
}
@@ -18,12 +18,10 @@ jobs:
runs-on: 'ubuntu-latest'
steps:
- name: 'Checkout'
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
with:
persist-credentials: false
uses: 'actions/checkout@v4'
- name: 'Setup Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
uses: 'actions/setup-node@v4'
with:
node-version: '20'
cache: 'npm'
@@ -42,12 +40,10 @@ jobs:
runs-on: 'ubuntu-latest'
steps:
- name: 'Checkout'
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
with:
persist-credentials: false
uses: 'actions/checkout@v4'
- name: 'Setup Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
uses: 'actions/setup-node@v4'
with:
node-version: '20'
cache: 'npm'
@@ -15,7 +15,7 @@ jobs:
issues: 'write'
steps:
- name: 'Check for Parent Workstream and Apply Label'
uses: 'actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b' # ratchet:actions/github-script@v7
uses: 'actions/github-script@v7'
with:
script: |
const labelToAdd = 'workstream-rollup';
-2
View File
@@ -17,8 +17,6 @@ jobs:
runs-on: 'ubuntu-latest'
steps:
- uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Link Checker'
id: 'lychee'
-35
View File
@@ -1,35 +0,0 @@
name: 'Memory Tests: Nightly'
on:
schedule:
- cron: '0 2 * * *' # Runs at 2 AM every day
workflow_dispatch: # Allow manual trigger
permissions:
contents: 'read'
jobs:
memory-test:
name: 'Run Memory Usage Tests'
runs-on: 'gemini-cli-ubuntu-16-core'
if: "github.repository == 'google-gemini/gemini-cli'"
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
with:
node-version-file: '.nvmrc'
cache: 'npm'
- name: 'Install dependencies'
run: 'npm ci'
- name: 'Build project'
run: 'npm run build'
- name: 'Run Memory Tests'
run: 'npm run test:memory'
+33
View File
@@ -0,0 +1,33 @@
name: 'No Response'
# Run as a daily cron at 1:45 AM
on:
schedule:
- cron: '45 1 * * *'
workflow_dispatch:
jobs:
no-response:
runs-on: 'ubuntu-latest'
if: |-
${{ github.repository == 'google-gemini/gemini-cli' }}
permissions:
issues: 'write'
pull-requests: 'write'
concurrency:
group: '${{ github.workflow }}-no-response'
cancel-in-progress: true
steps:
- uses: 'actions/stale@5bef64f19d7facfb25b37b414482c7164d639639' # ratchet:actions/stale@v9
with:
repo-token: '${{ secrets.GITHUB_TOKEN }}'
days-before-stale: -1
days-before-close: 14
stale-issue-label: 'status/need-information'
close-issue-message: >-
This issue was marked as needing more information and has not received a response in 14 days.
Closing it for now. If you still face this problem, feel free to reopen with more details. Thank you!
stale-pr-label: 'status/need-information'
close-pr-message: >-
This pull request was marked as needing more information and has had no updates in 14 days.
Closing it for now. You are welcome to reopen with the required info. Thanks for contributing!
@@ -0,0 +1,41 @@
name: Offload Golden Image Update
on:
push:
branches:
- main
paths:
- '.gemini/skills/offload/scripts/provision-worker.sh'
- '.gemini/skills/offload/scripts/fleet.ts'
workflow_dispatch:
jobs:
update-image:
runs-on: ubuntu-latest
permissions:
contents: read
id-token: write
steps:
- name: Checkout Repository
uses: actions/checkout@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: 20
- name: Install Dependencies
run: npm install
- name: Authenticate to Google Cloud
uses: google-github-actions/auth@v2
with:
workload_identity_provider: ${{ secrets.GCP_WIP }}
service_account: ${{ secrets.GCP_SA }}
- name: Setup GCloud SDK
uses: google-github-actions/setup-gcloud@v2
- name: Build New Golden Image
run: npm run offload:fleet create-image
-35
View File
@@ -1,35 +0,0 @@
name: 'Performance Tests: Nightly'
on:
schedule:
- cron: '0 3 * * *' # Runs at 3 AM every day
workflow_dispatch: # Allow manual trigger
permissions:
contents: 'read'
jobs:
perf-test:
name: 'Run Performance Usage Tests'
runs-on: 'gemini-cli-ubuntu-16-core'
if: "github.repository == 'google-gemini/gemini-cli'"
steps:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8' # ratchet:actions/checkout@v5
with:
persist-credentials: false
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
with:
node-version-file: '.nvmrc'
cache: 'npm'
- name: 'Install dependencies'
run: 'npm ci'
- name: 'Build project'
run: 'npm run build'
- name: 'Run Performance Tests'
run: 'npm run test:perf'
@@ -0,0 +1,133 @@
name: '🏷️ PR Contribution Guidelines Notifier'
on:
pull_request:
types:
- 'opened'
jobs:
notify-process-change:
runs-on: 'ubuntu-latest'
if: |-
github.repository == 'google-gemini/gemini-cli' || github.repository == 'google-gemini/maintainers-gemini-cli'
permissions:
pull-requests: 'write'
steps:
- name: 'Generate GitHub App Token'
id: 'generate_token'
env:
APP_ID: '${{ secrets.APP_ID }}'
if: |-
${{ env.APP_ID != '' }}
uses: 'actions/create-github-app-token@v2'
with:
app-id: '${{ 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
});
@@ -1,107 +0,0 @@
name: 'PR Size Labeler (Batch)'
on:
workflow_dispatch:
inputs:
process_all:
description: 'Process all PRs (open and closed) or open only'
required: true
default: 'false'
type: 'choice'
options:
- 'true'
- 'false'
limit:
description: 'Max number of PRs to fetch and check'
required: true
default: '100'
type: 'string'
permissions:
pull-requests: 'write'
jobs:
batch-label:
runs-on: 'ubuntu-latest'
steps:
- name: 'Batch label PRs'
env:
GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
GH_REPO: '${{ github.repository }}'
run: |
# Determine the state filter
STATE="open"
if [ "${{ github.event.inputs.process_all }}" = "true" ]; then
STATE="all"
fi
LIMIT="${{ github.event.inputs.limit }}"
echo "Batch labeling up to $LIMIT $STATE PRs..."
# 1. Ensure standard premium size labels exist in the repository (self-healing)
gh label create "size/XS" --color "7ee081" --description "XS: <10 lines changed" 2>/dev/null || true
gh label create "size/S" --color "a6d49f" --description "S: 10-49 lines changed" 2>/dev/null || true
gh label create "size/M" --color "f7d070" --description "M: 50-249 lines changed" 2>/dev/null || true
gh label create "size/L" --color "f48c06" --description "L: 250-999 lines changed" 2>/dev/null || true
gh label create "size/XL" --color "dc2f02" --description "XL: >=1000 lines changed" 2>/dev/null || true
# 2. Query PR list with all required fields in ONE call to prevent N+1 queries
PR_LIST=$(gh pr list --state "$STATE" --limit "$LIMIT" --json number,additions,deletions,labels)
if [ -z "$PR_LIST" ] || [ "$PR_LIST" = "[]" ]; then
echo "️ No PRs found matching the criteria."
exit 0
fi
# Parse and iterate over PRs
UPDATED_COUNT=0
SKIPPED_COUNT=0
echo "$PR_LIST" | jq -c '.[]' | while read -r PR_JSON; do
PR_NUMBER=$(echo "$PR_JSON" | jq '.number')
ADDITIONS=$(echo "$PR_JSON" | jq '.additions')
DELETIONS=$(echo "$PR_JSON" | jq '.deletions')
TOTAL=$((ADDITIONS + DELETIONS))
# Calculate target size
if [ $TOTAL -lt 10 ]; then
SIZE="size/XS"
elif [ $TOTAL -lt 50 ]; then
SIZE="size/S"
elif [ $TOTAL -lt 250 ]; then
SIZE="size/M"
elif [ $TOTAL -lt 1000 ]; then
SIZE="size/L"
else
SIZE="size/XL"
fi
# Inspect existing labels to detect discrepancies
EXISTING_LABELS=$(echo "$PR_JSON" | jq -r '.labels[].name' 2>/dev/null || echo "")
LABELS_TO_REMOVE=()
for L in size/XS size/S size/M size/L size/XL; do
if echo "$EXISTING_LABELS" | grep -Fq "$L" && [ "$L" != "$SIZE" ]; then
LABELS_TO_REMOVE+=("--remove-label" "$L")
fi
done
LABEL_TO_ADD=()
if ! echo "$EXISTING_LABELS" | grep -Fq "$SIZE"; then
LABEL_TO_ADD+=("--add-label" "$SIZE")
fi
# Update labels if there's a difference
if [ ${#LABELS_TO_REMOVE[@]} -gt 0 ] || [ ${#LABEL_TO_ADD[@]} -gt 0 ]; then
echo "🔄 PR #$PR_NUMBER (+$ADDITIONS/-$DELETIONS = $TOTAL lines): updating size to $SIZE"
gh pr edit "$PR_NUMBER" "${LABELS_TO_REMOVE[@]}" "${LABEL_TO_ADD[@]}" 2>/dev/null || true
UPDATED_COUNT=$((UPDATED_COUNT + 1))
else
echo "✅ PR #$PR_NUMBER (+$ADDITIONS/-$DELETIONS = $TOTAL lines): already has correct label ($SIZE). Skipping."
SKIPPED_COUNT=$((SKIPPED_COUNT + 1))
fi
done
echo "============================================"
echo "🎉 Batch run completed!"
echo "Skipped (already correct): $SKIPPED_COUNT"
echo "Updated: $UPDATED_COUNT"
-120
View File
@@ -1,120 +0,0 @@
name: 'PR Size Labeler'
on:
pull_request_target:
types: ['opened', 'synchronize', 'reopened']
workflow_dispatch:
inputs:
pr_number:
description: 'PR number to label manually (for workflow_dispatch)'
required: false
type: 'string'
permissions:
pull-requests: 'write'
issues: 'write'
jobs:
size-label:
runs-on: 'ubuntu-latest'
steps:
- name: 'Run size labeler'
env:
GH_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
GH_REPO: '${{ github.repository }}'
run: |
# Determine the target PR number
if [ -n "${{ github.event.pull_request.number }}" ]; then
PR_NUMBER="${{ github.event.pull_request.number }}"
elif [ -n "${{ github.event.inputs.pr_number }}" ]; then
PR_NUMBER="${{ github.event.inputs.pr_number }}"
else
echo "❌ Error: No PR number provided."
exit 1
fi
echo "Checking PR #$PR_NUMBER..."
# 1. Ensure standard premium size labels exist in the repository (self-healing)
# size/XS: Light green (#7ee081)
# size/S: Yellow-green (#a6d49f)
# size/M: Amber/Yellow (#f7d070)
# size/L: Orange (#f48c06)
# size/XL: Red (#dc2f02)
gh label create "size/XS" --color "7ee081" --description "XS: <10 lines changed" 2>/dev/null || true
gh label create "size/S" --color "a6d49f" --description "S: 10-49 lines changed" 2>/dev/null || true
gh label create "size/M" --color "f7d070" --description "M: 50-249 lines changed" 2>/dev/null || true
gh label create "size/L" --color "f48c06" --description "L: 250-999 lines changed" 2>/dev/null || true
gh label create "size/XL" --color "dc2f02" --description "XL: >=1000 lines changed" 2>/dev/null || true
# 2. Fetch PR details in a single efficient API call
PR_DATA=$(gh pr view "$PR_NUMBER" --json additions,deletions,changedFiles,labels)
if [ -z "$PR_DATA" ]; then
echo "❌ Error: Could not fetch PR details."
exit 1
fi
ADDITIONS=$(echo "$PR_DATA" | jq '.additions')
DELETIONS=$(echo "$PR_DATA" | jq '.deletions')
CHANGED_FILES=$(echo "$PR_DATA" | jq '.changedFiles')
TOTAL=$((ADDITIONS + DELETIONS))
echo "PR additions: $ADDITIONS, deletions: $DELETIONS, total changes: $TOTAL, files: $CHANGED_FILES"
# 3. Calculate new size label
if [ $TOTAL -lt 10 ]; then
SIZE="size/XS"
elif [ $TOTAL -lt 50 ]; then
SIZE="size/S"
elif [ $TOTAL -lt 250 ]; then
SIZE="size/M"
elif [ $TOTAL -lt 1000 ]; then
SIZE="size/L"
else
SIZE="size/XL"
fi
# 4. Check existing labels and update only if necessary
EXISTING_LABELS=$(echo "$PR_DATA" | jq -r '.labels[].name' 2>/dev/null || echo "")
LABELS_TO_REMOVE=()
for L in size/XS size/S size/M size/L size/XL; do
if echo "$EXISTING_LABELS" | grep -Fq "$L" && [ "$L" != "$SIZE" ]; then
LABELS_TO_REMOVE+=("--remove-label" "$L")
fi
done
LABEL_TO_ADD=()
if ! echo "$EXISTING_LABELS" | grep -Fq "$SIZE"; then
LABEL_TO_ADD+=("--add-label" "$SIZE")
fi
# Perform a single, highly atomic edit call if changes are needed
if [ ${#LABELS_TO_REMOVE[@]} -gt 0 ] || [ ${#LABEL_TO_ADD[@]} -gt 0 ]; then
echo "Updating labels: removing ${LABELS_TO_REMOVE[*]}, adding $SIZE"
gh pr edit "$PR_NUMBER" "${LABELS_TO_REMOVE[@]}" "${LABEL_TO_ADD[@]}"
else
echo "✅ PR #$PR_NUMBER already has the correct size label ($SIZE)."
fi
# 5. Premium, anti-spam comment logic (updates previous comment to keep thread clean)
COMMENT="📊 PR Size: **$SIZE**
- Lines changed: **$TOTAL**
- Additions: +$ADDITIONS
- Deletions: -$DELETIONS
- Files changed: $CHANGED_FILES"
# Find any existing size labeler comment by the github-actions bot
echo "Searching for existing size comment..."
COMMENT_ID=$(gh api "repos/${{ github.repository }}/issues/$PR_NUMBER/comments" \
--jq '.[] | select(.user.login == "github-actions[bot]" and (.body | startswith("📊 PR Size:"))) | .id' | head -n 1)
if [ -n "$COMMENT_ID" ]; then
echo "Updating existing comment (ID: $COMMENT_ID)..."
gh api "repos/${{ github.repository }}/issues/comments/$COMMENT_ID" -X PATCH -f body="$COMMENT" > /dev/null
else
echo "Creating new comment..."
gh pr comment "$PR_NUMBER" --body "$COMMENT" > /dev/null
fi
echo "🎉 PR size labeling completed successfully."
+1 -2
View File
@@ -40,11 +40,10 @@ jobs:
issues: 'write'
steps:
- name: 'Checkout repository'
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
uses: 'actions/checkout@v4'
with:
ref: '${{ github.ref }}'
fetch-depth: 0
persist-credentials: false
- name: 'Setup Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020'
-14
View File
@@ -46,15 +46,8 @@ on:
default: 'prod'
jobs:
build-mac:
if: "github.repository == 'google-gemini/gemini-cli'"
uses: './.github/workflows/build-unsigned-mac-binaries.yml'
with:
ref: '${{ github.event.inputs.ref }}'
release:
if: "github.repository == 'google-gemini/gemini-cli'"
needs: ['build-mac']
runs-on: 'ubuntu-latest'
environment: "${{ github.event.inputs.environment || 'prod' }}"
permissions:
@@ -65,13 +58,11 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
fetch-depth: 0
- name: 'Checkout Release Code'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
path: 'release'
fetch-depth: 0
@@ -92,11 +83,6 @@ jobs:
working-directory: './release'
run: 'npm ci'
- name: 'Download macOS Binaries'
uses: './.github/actions/download-mac-binaries'
with:
path: 'release/dist'
- name: 'Prepare Release Info'
id: 'release_info'
working-directory: './release'
+7 -21
View File
@@ -30,16 +30,9 @@ on:
default: 'prod'
jobs:
build-mac:
if: "github.repository == 'google-gemini/gemini-cli'"
uses: './.github/workflows/build-unsigned-mac-binaries.yml'
with:
ref: '${{ github.event.inputs.ref }}'
release:
if: "github.repository == 'google-gemini/gemini-cli'"
needs: ['build-mac']
environment: "${{ github.event_name == 'schedule' && 'internal' || github.event.inputs.environment || 'prod' }}"
environment: "${{ github.event.inputs.environment || 'prod' }}"
runs-on: 'ubuntu-latest'
permissions:
contents: 'write'
@@ -50,13 +43,11 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
fetch-depth: 0
- name: 'Checkout Release Code'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
path: 'release'
fetch-depth: 0
@@ -71,11 +62,6 @@ jobs:
working-directory: './release'
run: 'npm ci'
- name: 'Download macOS Binaries'
uses: './.github/actions/download-mac-binaries'
with:
path: 'release/dist'
- name: 'Print Inputs'
shell: 'bash'
env:
@@ -145,12 +131,12 @@ jobs:
skip-branch-cleanup: true
force-skip-tests: "${{ github.event_name != 'schedule' && github.event.inputs.force_skip_tests == 'true' }}"
gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
npm-registry-publish-url: "${{ vars.NPM_REGISTRY_PUBLISH_URL || 'https://wombat-dressing-room.appspot.com' }}"
npm-registry-url: "${{ vars.NPM_REGISTRY_URL || 'https://wombat-dressing-room.appspot.com' }}"
npm-registry-scope: "${{ vars.NPM_REGISTRY_SCOPE || '@google' }}"
cli-package-name: "${{ vars.CLI_PACKAGE_NAME || '@google/gemini-cli' }}"
core-package-name: "${{ vars.CORE_PACKAGE_NAME || '@google/gemini-cli-core' }}"
a2a-package-name: "${{ vars.A2A_PACKAGE_NAME || '@google/gemini-cli-a2a-server' }}"
npm-registry-publish-url: '${{ vars.NPM_REGISTRY_PUBLISH_URL }}'
npm-registry-url: '${{ vars.NPM_REGISTRY_URL }}'
npm-registry-scope: '${{ vars.NPM_REGISTRY_SCOPE }}'
cli-package-name: '${{ vars.CLI_PACKAGE_NAME }}'
core-package-name: '${{ vars.CORE_PACKAGE_NAME }}'
a2a-package-name: '${{ vars.A2A_PACKAGE_NAME }}'
- name: 'Create and Merge Pull Request'
if: "github.event.inputs.environment != 'dev'"
+3 -7
View File
@@ -29,15 +29,14 @@ jobs:
pull-requests: 'write'
steps:
- name: 'Checkout repository'
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
uses: 'actions/checkout@v4'
with:
persist-credentials: false
# 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
uses: 'actions/setup-node@v4'
with:
node-version: '20'
@@ -71,10 +70,7 @@ jobs:
- 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
env:
GEMINI_CLI_TRUST_WORKSPACE: true
with:
upload_artifacts: 'true'
gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
prompt: |
Activate the 'docs-changelog' skill.
@@ -90,7 +86,7 @@ jobs:
- name: 'Create Pull Request'
if: "steps.validate_version.outputs.CONTINUE == 'true'"
uses: 'peter-evans/create-pull-request@c5a7806660adbe173f04e3e038b0ccdcd758773c' # ratchet:peter-evans/create-pull-request@v6
uses: 'peter-evans/create-pull-request@v6'
with:
token: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
commit-message: 'docs(changelog): update for ${{ steps.release_info.outputs.VERSION }}'
@@ -17,7 +17,6 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
fetch-depth: 1
- name: 'Slash Command Dispatch'
@@ -54,7 +54,6 @@ jobs:
with:
ref: '${{ github.event.inputs.ref }}'
fetch-depth: 0
persist-credentials: false
- name: 'Setup Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
@@ -64,7 +64,6 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: "${{ github.event.inputs.workflow_ref || 'main' }}"
fetch-depth: 1
@@ -53,14 +53,12 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
fetch-depth: 0
fetch-tags: true
- name: 'Checkout Release Code'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.release_ref }}'
path: 'release'
fetch-depth: 0
+4 -31
View File
@@ -55,7 +55,6 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
fetch-depth: 0
fetch-tags: true
@@ -106,9 +105,7 @@ jobs:
echo "NIGHTLY_JSON: ${NIGHTLY_JSON}"
echo "STABLE_VERSION=${STABLE_VERSION}" >> "${GITHUB_OUTPUT}"
# shellcheck disable=SC1083
PREVIOUS_PREVIEW_TAG=$(echo "${PREVIEW_JSON}" | jq -r .previousReleaseTag)
STABLE_SHA=$(git rev-parse "${PREVIOUS_PREVIEW_TAG}^{commit}")
echo "STABLE_SHA=${STABLE_SHA}" >> "${GITHUB_OUTPUT}"
echo "STABLE_SHA=$(git rev-parse "$(echo "${PREVIEW_JSON}" | jq -r .previousReleaseTag)"^{commit})" >> "${GITHUB_OUTPUT}"
echo "PREVIOUS_STABLE_TAG=$(echo "${STABLE_JSON}" | jq -r .previousReleaseTag)" >> "${GITHUB_OUTPUT}"
echo "PREVIEW_VERSION=$(echo "${PREVIEW_JSON}" | jq -r .releaseVersion)" >> "${GITHUB_OUTPUT}"
# shellcheck disable=SC1083
@@ -174,13 +171,11 @@ jobs:
- name: 'Checkout Ref'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
- name: 'Checkout correct SHA'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ matrix.sha }}'
path: 'release'
fetch-depth: 0
@@ -202,15 +197,9 @@ jobs:
gemini_api_key: '${{ secrets.GEMINI_API_KEY }}'
working-directory: './release'
build-mac:
if: "github.repository == 'google-gemini/gemini-cli'"
uses: './.github/workflows/build-unsigned-mac-binaries.yml'
with:
ref: '${{ github.event.inputs.ref }}'
publish-preview:
name: 'Publish preview'
needs: ['calculate-versions', 'test', 'build-mac']
needs: ['calculate-versions', 'test']
runs-on: 'ubuntu-latest'
environment: "${{ github.event.inputs.environment || 'prod' }}"
permissions:
@@ -221,13 +210,11 @@ jobs:
- name: 'Checkout Ref'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
- name: 'Checkout correct SHA'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ needs.calculate-versions.outputs.PREVIEW_SHA }}'
path: 'release'
fetch-depth: 0
@@ -242,11 +229,6 @@ jobs:
working-directory: './release'
run: 'npm ci'
- name: 'Download macOS Binaries'
uses: './.github/actions/download-mac-binaries'
with:
path: 'release/dist'
- name: 'Publish Release'
uses: './.github/actions/publish-release'
with:
@@ -284,7 +266,7 @@ jobs:
publish-stable:
name: 'Publish stable'
needs: ['calculate-versions', 'test', 'publish-preview', 'build-mac']
needs: ['calculate-versions', 'test', 'publish-preview']
runs-on: 'ubuntu-latest'
environment: "${{ github.event.inputs.environment || 'prod' }}"
permissions:
@@ -295,13 +277,11 @@ jobs:
- name: 'Checkout Ref'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
- name: 'Checkout correct SHA'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ needs.calculate-versions.outputs.STABLE_SHA }}'
path: 'release'
fetch-depth: 0
@@ -316,11 +296,6 @@ jobs:
working-directory: './release'
run: 'npm ci'
- name: 'Download macOS Binaries'
uses: './.github/actions/download-mac-binaries'
with:
path: 'release/dist'
- name: 'Publish Release'
uses: './.github/actions/publish-release'
with:
@@ -369,7 +344,6 @@ jobs:
- name: 'Checkout Ref'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
- name: 'Setup Node.js'
@@ -405,7 +379,6 @@ jobs:
BRANCH_NAME: '${{ steps.release_branch.outputs.BRANCH_NAME }}'
DRY_RUN: '${{ github.event.inputs.dry_run }}'
NEEDS_CALCULATE_VERSIONS_OUTPUTS_NEXT_NIGHTLY_VERSION: '${{ needs.calculate-versions.outputs.NEXT_NIGHTLY_VERSION }}'
GIT_PUSH_TOKEN: '${{ secrets.GEMINI_CLI_ROBOT_GITHUB_PAT }}'
run: |-
git add package.json packages/*/package.json
if [ -f package-lock.json ]; then
@@ -414,7 +387,7 @@ jobs:
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 "https://x-access-token:${GIT_PUSH_TOKEN}@github.com/${{ github.repository }}.git" "HEAD:${BRANCH_NAME}" --follow-tags
git push --set-upstream origin "${BRANCH_NAME}"
else
echo "Dry run enabled. Skipping push."
fi
+2 -4
View File
@@ -52,7 +52,6 @@ jobs:
- name: 'Checkout repository'
uses: 'actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955' # ratchet:actions/checkout@v4
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref }}'
fetch-depth: 0
@@ -82,8 +81,7 @@ jobs:
ORIGIN_TAG: '${{ steps.origin_tag.outputs.ORIGIN_TAG }}'
shell: 'bash'
run: |
ORIGIN_HASH=$(git rev-parse "${ORIGIN_TAG}")
echo "ORIGIN_HASH=${ORIGIN_HASH}" >> "$GITHUB_OUTPUT"
echo "ORIGIN_HASH=$(git rev-parse "${ORIGIN_TAG}")" >> "$GITHUB_OUTPUT"
- name: 'Change tag'
if: "${{ github.event.inputs.rollback_destination != '' }}"
@@ -194,7 +192,7 @@ jobs:
run: |
echo "ROLLBACK_TAG=$ROLLBACK_TAG_NAME" >> "$GITHUB_OUTPUT"
git tag "$ROLLBACK_TAG_NAME" "${ORIGIN_HASH}"
git push "https://x-access-token:${GITHUB_TOKEN}@github.com/${{ github.repository }}.git" --tags
git push origin --tags
- name: 'Verify Rollback Tag Added'
if: "${{ github.event.inputs.dry-run == 'false' }}"
-1
View File
@@ -26,7 +26,6 @@ jobs:
- name: 'Checkout'
uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
ref: '${{ github.event.inputs.ref || github.sha }}'
fetch-depth: 0
- name: 'Push'
-1
View File
@@ -32,7 +32,6 @@ jobs:
with:
ref: '${{ github.event.inputs.ref || github.sha }}'
fetch-depth: 0
persist-credentials: false
- name: 'Install Dependencies'
run: 'npm ci'
- name: 'Build bundle'
+44
View File
@@ -0,0 +1,44 @@
name: 'Mark stale issues and pull requests'
# Run as a daily cron at 1:30 AM
on:
schedule:
- cron: '30 1 * * *'
workflow_dispatch:
jobs:
stale:
strategy:
fail-fast: false
matrix:
runner:
- 'ubuntu-latest' # GitHub-hosted
runs-on: '${{ matrix.runner }}'
if: |-
${{ github.repository == 'google-gemini/gemini-cli' }}
permissions:
issues: 'write'
pull-requests: 'write'
concurrency:
group: '${{ github.workflow }}-stale'
cancel-in-progress: true
steps:
- uses: 'actions/stale@5bef64f19d7facfb25b37b414482c7164d639639' # ratchet:actions/stale@v9
with:
repo-token: '${{ secrets.GITHUB_TOKEN }}'
stale-issue-message: >-
This issue has been automatically marked as stale due to 60 days of inactivity.
It will be closed in 14 days if no further activity occurs.
stale-pr-message: >-
This pull request has been automatically marked as stale due to 60 days of inactivity.
It will be closed in 14 days if no further activity occurs.
close-issue-message: >-
This issue has been closed due to 14 additional days of inactivity after being marked as stale.
If you believe this is still relevant, feel free to comment or reopen the issue. Thank you!
close-pr-message: >-
This pull request has been closed due to 14 additional days of inactivity after being marked as stale.
If this is still relevant, you are welcome to reopen or leave a comment. Thanks for contributing!
days-before-stale: 60
days-before-close: 14
exempt-issue-labels: 'pinned,security,🔒 maintainer only,help wanted,🗓️ Public Roadmap'
exempt-pr-labels: 'pinned,security,🔒 maintainer only,help wanted,🗓️ Public Roadmap'
+4 -7
View File
@@ -33,9 +33,7 @@ jobs:
steps:
- name: 'Checkout'
uses: 'actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5' # ratchet:actions/checkout@v4
with:
persist-credentials: false
uses: 'actions/checkout@v4'
- name: 'Optimize Windows Performance'
if: "matrix.os == 'windows-latest'"
@@ -48,7 +46,7 @@ jobs:
shell: 'powershell'
- name: 'Set up Node.js'
uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions/setup-node@v4
uses: 'actions/setup-node@v4'
with:
node-version-file: '.nvmrc'
architecture: '${{ matrix.arch }}'
@@ -65,7 +63,7 @@ jobs:
- name: 'Setup Windows SDK (Windows)'
if: "matrix.os == 'windows-latest'"
uses: 'microsoft/setup-msbuild@6fb02220983dee41ce7ae257b6f4d8f9bf5ed4ce' # ratchet:microsoft/setup-msbuild@v2
uses: 'microsoft/setup-msbuild@v2'
- name: 'Add Signtool to Path (Windows)'
if: "matrix.os == 'windows-latest'"
@@ -143,7 +141,6 @@ jobs:
if: "github.event_name != 'pull_request'"
env:
GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
GEMINI_CLI_TRUST_WORKSPACE: true
run: |
echo "Running integration tests with binary..."
if [[ "${{ matrix.os }}" == 'windows-latest' ]]; then
@@ -156,7 +153,7 @@ jobs:
npm run test:integration:sandbox:none -- --testTimeout=600000
- name: 'Upload Artifact'
uses: 'actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02' # ratchet:actions/upload-artifact@v4
uses: 'actions/upload-artifact@v4'
with:
name: 'gemini-cli-${{ matrix.platform_name }}'
path: 'dist/${{ matrix.platform_name }}/'
-45
View File
@@ -1,45 +0,0 @@
name: 'Testing: Tools (Python)'
on:
push:
branches:
- 'main'
- 'release/**'
paths:
- 'tools/**'
pull_request:
branches:
- 'main'
- 'release/**'
paths:
- 'tools/**'
defaults:
run:
shell: 'bash'
jobs:
python-tests:
name: 'Python Tests'
runs-on: 'ubuntu-latest'
steps:
- name: 'Checkout'
uses: 'actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683' # ratchet:actions/checkout@v4
- name: 'Set up Python'
uses: 'actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55' # ratchet:actions/setup-python@v5
with:
python-version: '3.13'
cache: 'pip'
cache-dependency-path: 'tools/caretaker-agent/cloudrun/triage-worker/requirements.txt'
- name: 'Install dependencies'
run: |
python -m pip install --upgrade pip
if [ -f tools/caretaker-agent/cloudrun/triage-worker/requirements.txt ]; then
python -m pip install -r tools/caretaker-agent/cloudrun/triage-worker/requirements.txt
fi
- name: 'Run unittest suite'
run: |
PYTHONPATH=tools/caretaker-agent/cloudrun/triage-worker python -m unittest discover -s tools/caretaker-agent/cloudrun/triage-worker/tests -t tools/caretaker-agent/cloudrun/triage-worker
@@ -40,13 +40,13 @@ jobs:
steps:
- name: 'Generate GitHub App Token'
id: 'generate_token'
uses: 'actions/create-github-app-token@fee1f7d63c2ff003460e3d139729b119787bc349' # ratchet:actions/create-github-app-token@v2
uses: 'actions/create-github-app-token@v2'
with:
app-id: '${{ secrets.APP_ID }}'
private-key: '${{ secrets.PRIVATE_KEY }}'
- name: 'Unassign inactive assignees'
uses: 'actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b' # ratchet:actions/github-script@v7
uses: 'actions/github-script@v7'
env:
DRY_RUN: '${{ inputs.dry_run }}'
with:
-2
View File
@@ -44,8 +44,6 @@ jobs:
shell: 'bash'
run: 'echo "${{ toJSON(vars) }}"'
- uses: 'actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8'
with:
persist-credentials: false
- name: 'Verify release'
uses: './.github/actions/verify-release'
with:
-4
View File
@@ -48,7 +48,6 @@ packages/cli/src/generated/
packages/core/src/generated/
packages/devtools/src/_client-assets.ts
.integration-tests/
.perf-tests/
packages/vscode-ide-companion/*.vsix
packages/cli/download-ripgrep*/
@@ -65,6 +64,3 @@ gemini-debug.log
evals/logs/
temp_agents/
# conductor extension and planning directories
conductor/
-2
View File
@@ -22,5 +22,3 @@ Thumbs.db
.pytest_cache
**/SKILL.md
packages/sdk/test-data/*.json
*.mdx
packages/vscode-ide-companion/NOTICES.txt
+1 -5
View File
@@ -43,13 +43,9 @@
{
"type": "node",
"request": "launch",
"name": "CLI: Run Current File",
"runtimeExecutable": "node",
"runtimeArgs": ["--import", "tsx"],
"name": "Launch Program",
"skipFiles": ["<node_internals>/**"],
"program": "${file}",
"cwd": "${workspaceFolder}",
"console": "integratedTerminal",
"outFiles": ["${workspaceFolder}/**/*.js"]
},
{

Some files were not shown because too many files have changed in this diff Show More