Compare commits

..

2 Commits

Author SHA1 Message Date
diegosouzapw
48f04073e9 feat(providers): add unit tests, ESLint suppressions, and fix hardcoded userid for TinyCMS Web
- Add unit tests for WASM init, UUID validation, challenge flow (15 tests)
- Add WASM source comment explaining binary origin
- Replace hardcoded userid with dynamic provider-specific data
- Add ESLint suppressions for no-explicit-any in WASM bridge code
- Add explanatory comments for DOM shim (runtime WASM-bindgen, not test mocks)

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>
2026-08-04 11:51:52 -03:00
jhordanjw123
d98737578e feat(providers): add support for TinyCMS Web including WASM-based cryptographic signing and Proof-of-Work emulation 2026-07-26 23:12:37 -03:00
1588 changed files with 14512 additions and 173466 deletions

View File

@@ -1,197 +0,0 @@
# codebase-memory-mcp ignore list
#
# Padrão gitignore-style. Linhas começando com `#` são comentários.
# Barra final (`/`) = só diretório. Sem barra = casa arquivo OU diretório.
#
# O CBM também lê `.gitignore` automaticamente — esta lista deixa explícito o que
# os hooks do CBM vão pular. Se uma regra entrar em conflito entre os dois arquivos,
# vale a união. Editar este arquivo é mais barato do que confiar na herança implícita.
#
# Última reconciliação: 2026-07-31, status `ready` (513k nodes / 689k edges),
# `auto_index_limit=50000`, total indexável medido ≈11.546 arquivos (folga 4,3×).
#
# Fontes cruzadas:
# - `codebase-memory-mcp cli index_status --project home-diegosouzapw-dev-proxys-OmniRoute`
# → `not_indexed.dirs` (27) + `not_indexed.files` (336), todos `BY DESIGN`.
# - `.gitignore` deste repo (5.691 B) — fonte canônica secundária.
#
# Como auditar mudanças: depois de editar este arquivo, rodar `index_repository`
# (ou esperar `auto_watch` re-indexar) e re-checar `cli index_status` → comparar
# contagens em `not_indexed.dirs_count` e `not_indexed.files_count`.
# ─────────────────────────────────────────────────────────────────────────────
# 1. Diretorios de runtime / pacote — nao sao codigo-fonte
# ─────────────────────────────────────────────────────────────────────────────
node_modules/
node_modules
# Builds e artefatos reproduziveis (Layer 1 Next.js / Electron)
.build/
dist/
.next/
out/
# Electron especifico
electron/dist-electron/
electron/node_modules/
icon.iconset/
# Workspaces internos que tem proprio node_modules
@omniroute/opencode-plugin/dist/
@omniroute/opencode-plugin/node_modules/
@omniroute/opencode-provider/dist/
@omniroute/opencode-provider/node_modules/
# Recursos nativos compilados (C/JNI/wasm)
src/mitm/tproxy/native/build/
# Artefatos locais do Stryker / Playwright / coverage
.stryker-tmp/
reports/mutation/
stryker-output-*.json
.playwright-mcp/
test-results/
playwright-report/
blob-report/
# Analise / linters / caches
.analysis/
.sisyphus/
.plans/
.gitnexus
.worktrees
.codegraph/
# Quality artifacts (gerados por npm run lint --cache etc)
.eslintcache
.eslintcache-complexity
# Claude Code local state
.claude/scheduled_tasks.lock
.claude/scheduled_tasks/
.claude/sessions/
.claude/state.json
.claude/settings.local.json
# Serena / Antigravity / outras tools locais
.serena/
.antigravitycli/
.gemini/
.config/
# ─────────────────────────────────────────────────────────────────────────────
# 2. Diretorios com prefixo `_` — locais / privados (regra global do .gitignore)
# ─────────────────────────────────────────────────────────────────────────────
_*/
_artifacts/
_cache/
_mono_repo/
_references/
_tasks/
# ─────────────────────────────────────────────────────────────────────────────
# 3. Diretorios de tooling IA (state local, nao codigo)
# ─────────────────────────────────────────────────────────────────────────────
.agents/
.claude/
.vscode/
.idea/
.junie/
.omc/
.data/
.data-dev/
.local-data/
.logs/
.artifacts/
.source/
.superpowers/
.claude-flow/
.omnivscodeagent/
omnirouteCloud/
omnirouteSite/
.omniroute/
.stent/
# Subpaths especificos do Claude Code que nao estao em .claude/ (criados sob repo)
.claude/worktrees/
# ─────────────────────────────────────────────────────────────────────────────
# 4. Diretorios de dados / runtime locais (storage, env, secrets, scratch)
# ─────────────────────────────────────────────────────────────────────────────
data/
src/lib/env/
src/app/api/agent-skills/coverage/
src/app/api/cloud/
src/app/api/sync/cloud/
src/app/api/system/env/
tests/golden-set/data/
# Logs e saida de teste
logs/*
test_output.log
home-diegosouzapw-dev-automacoes-*.txt
# ─────────────────────────────────────────────────────────────────────────────
# 5. Diretorios do monorepo por subprojeto (nao fazem parte do app principal)
# ─────────────────────────────────────────────────────────────────────────────
security-analysis/
vscode-extension/
obsidian-plugin/node_modules/
# ─────────────────────────────────────────────────────────────────────────────
# 6. Diretorios de documentacao interna / workflow
# ─────────────────────────────────────────────────────────────────────────────
docs/superpowers/
# ─────────────────────────────────────────────────────────────────────────────
# 7. Arquivos especificos (nao diretorios inteiros)
# ─────────────────────────────────────────────────────────────────────────────
# Segredos e env — NUNCA indexar
.env
.env.*
!.env.example
!.env.homolog.example
# TypeScript build info e next env declaration
*.tsbuildinfo
next-env.d.ts
typescript
# SQLite transient files (WAL/SHM/journal)
*.sqlite-shm
*.sqlite-wal
*.sqlite-journal
# Mapas e source maps
*.map
# Bun / npm lockfiles ruidosos
bun.lock
# `cheaper-inference-gateway.svg` e arquivos de midia na raiz/asset ja cobertos
# pelos `ignored-suffix` do indexador (svg/png/jpg/ico/etc >50kB ou >500linhas);
# manter a regra explicita aqui ajuda a auditar:
cheaper-inference-gateway.svg
cheaper-inference-gateway-*.svg
# Husky internals
.husky/_/
# CI / quality metric artifacts
config/quality/quality-metrics.json
config/quality/test-impact-map.json
audit-report.json
.gh-discussions.json
# i18n audit (gerado por npm run scripts)
scripts/i18n/_audit.json
scripts/i18n/_pending-keys.json
# Cli binario local (scratch)
bin/omniroute.mjs
# Deploy / docker backups
deploy.sh
docker-compose.yml.bak
docker-compose.minimal.yml

View File

@@ -18,7 +18,6 @@ coverage
# Runtime data and logs
data
logs
.sandbox
# Local env files (inject at runtime via --env-file or -e)
.env

View File

@@ -1,6 +0,0 @@
ENABLE_LIVE_DEVIN_TESTS=0
DEVIN_BRIDGE_MODEL=devin-cli-agentic/swe-1-7
DEVIN_BRIDGE_SONNET_MODEL=devin-cli-agentic/swe-1-7
DEVIN_BRIDGE_OPUS_MODEL=devin-cli-agentic/swe-1-7
DEVIN_BRIDGE_HAIKU_MODEL=devin-cli-agentic/swe-1-7
DEVIN_BRIDGE_SUBAGENT_MODEL=devin-cli-agentic/swe-1-7

View File

@@ -84,12 +84,7 @@ PORT=20128
# endpoint display (useDisplayBaseUrl) shows https://host/omniroute/v1 instead of
# https://host/v1. Rebuild after changing this value (Next basePath is build-time).
# Default: "" (served at the domain root). Example: /omniroute to serve under https://host/omniroute
# Docker: baked at image build time via build-arg; root-path images can also apply this at
# container start (see docs/guides/DOCKER_GUIDE.md).
# OMNIROUTE_BASE_PATH=
# Client fetch/EventSource under this path are rewritten via installBasePathFetch
# (src/shared/utils/basePathFetch.ts) so absolute `/api/*` and `/v1/*` hits work
# without a reverse-proxy rewrite. Rebuild after changing (Next basePath is build-time).
#
# Browser-visible mirror of OMNIROUTE_BASE_PATH, inlined at build time so the
# dashboard endpoint display can read it client-side. Set it to the same value
@@ -240,9 +235,8 @@ NODE_ENV=production
# Container runtime — controls startup script behavior (permissions, advice).
# Values: docker | podman | Default: docker
# Set to "podman" for any Podman topology. The entrypoint cannot determine
# whether the engine is local or reached through Podman Machine, so it prints
# topology-neutral guidance and links contrib/podman/README.md.
# Set to "podman" when running under rootless Podman so the entrypoint
# gives the correct fix instructions (podman unshare chown vs sudo chown).
CONTAINER_HOST=docker
# Container runtime override for skill sandboxing.
@@ -811,15 +805,6 @@ PROVIDER_LIMITS_SYNC_SPACING_MS=1500
# Default: <repo>/src/lib/db/migrations.
#OMNIROUTE_MIGRATIONS_DIR=
# Additional migration directories, as `namespace=dir` entries separated by the
# platform path delimiter (`:` on POSIX, `;` on Windows). Files found there are
# recorded as `<namespace>-<number>` (e.g. `ee-134`), a version space that cannot
# collide with the upstream numeric slots — so a distribution shipping its own
# migrations never silently loses one to a number the upstream set also claimed.
# A malformed entry, an invalid namespace or a missing directory aborts startup
# rather than skipping the schema. Unset = no extra directories (the default).
#OMNIROUTE_EXTRA_MIGRATIONS_DIRS=ee=/opt/app/enterprise/db/migrations
# Mass-pending-migrations safety threshold (#3416). If more than this many
# migrations are pending on an existing DB, startup aborts (a wiped tracking
# table could cause data loss). Raise it to restore an older backup; set to 0
@@ -1414,6 +1399,10 @@ APP_LOG_TO_FILE=true
# Default: ~/.omniroute/plugins/ Override in dev/CI to point at a local plugin tree.
# OMNIROUTE_PLUGIN_PATH=
# Allow plugins to request the 'exec' permission (spawn child processes from the
# plugin worker sandbox). Disabled by default; set to 1 to enable (local operator only).
# OMNIROUTE_PLUGINS_ALLOW_EXEC=0
# ── Prompt cache (system prompt deduplication) ──
# Used by: open-sse/services — caches identical system prompts across requests.
# PROMPT_CACHE_MAX_SIZE=50 # Max cached entries (default: 50)
@@ -1826,10 +1815,6 @@ APP_LOG_TO_FILE=true
# Tokens reserved for completion output when computing prompt budgets.
# Used by: open-sse/services/contextManager.ts. Default: 1024.
# CONTEXT_RESERVE_TOKENS=1024
# How many of the newest inline images to keep when pruning older ones to fit
# the context window (#8560). Used by: open-sse/services/contextManager.ts.
# Default: 2.
# CONTEXT_KEEP_LATEST_IMAGES=2
# ── Model alias rewriting (legacy compatibility) ──
# Toggle the legacy model-alias compatibility layer used by older clients.
@@ -1839,18 +1824,6 @@ APP_LOG_TO_FILE=true
# ── Devin CLI binary path ──
# Used by: open-sse/executors/devin-cli.ts. Default: looked up via PATH.
# CLI_DEVIN_BIN=devin
# Agentic bridge-only binary override. The bridge still executes ACP stdio only.
# CLI_DEVIN_AGENTIC_BIN=devin
# Required isolated HOME for the agentic Devin child process.
# DEVIN_AGENTIC_HOME=/home/bridge
# Bounded ACP turn timeout in milliseconds. Default: 120000.
# DEVIN_AGENTIC_ACP_TIMEOUT_MS=120000
# Agentic bridge model aliases. Values must keep the devin-cli-agentic/ prefix.
# DEVIN_BRIDGE_MODEL=devin-cli-agentic/swe-1-7
# DEVIN_BRIDGE_SONNET_MODEL=devin-cli-agentic/swe-1-7
# DEVIN_BRIDGE_OPUS_MODEL=devin-cli-agentic/swe-1-7
# DEVIN_BRIDGE_HAIKU_MODEL=devin-cli-agentic/swe-1-7
# DEVIN_BRIDGE_SUBAGENT_MODEL=devin-cli-agentic/swe-1-7
# ── Command Code (custom CLI) callback ──
# Local port used for OAuth-style callbacks from the Command Code CLI helper.
@@ -2312,18 +2285,6 @@ QUOTA_STORE_DRIVER=sqlite # sqlite | redis
# ─────────────────────────────────────────────────────────────────────────────
# HYPERAGENT_USAGE_URL=https://hyperagent.com/api/settings/billing/usage
# ─────────────────────────────────────────────────────────────────────────────
# ChatGPT Web (Codex) headless browser and outbound tool tunnel
# Used by: open-sse/executors/chatgpt-web-codex.ts
# Connection values entered in the dashboard override these global defaults.
# ─────────────────────────────────────────────────────────────────────────────
# CHATGPT_WEB_CODEX_CHROME_PATH=/usr/bin/chromium
# CHROME_PATH=/usr/bin/chromium
# CHATGPT_WEB_CODEX_CDP_URL=http://chatgpt-web-codex-browser:9223
# CHATGPT_WEB_CODEX_TUNNEL_ID=tunnel_0123456789abcdef0123456789abcdef
# CHATGPT_WEB_CODEX_RUNTIME_KEY=
# CHATGPT_WEB_CODEX_CONNECTOR_NAME=OmniRoute Codex
# ─────────────────────────────────────────────────────────────────────────────
# Browser-login VNC sessions (optional — src/lib/vncSession/manifest.ts)
# Containerized Chromium+VNC used for interactive browser-login credential

View File

@@ -9,14 +9,11 @@
## Validation
Choose the change type and focused loop from the
[Contribution Golden Path](../docs/dev/CONTRIBUTION_GOLDEN_PATH.md). The full unit suite,
Vitest, the 60% coverage gate, and the production build all run in CI on this PR (#8329):
Run only the focused loop for what you changed — the full unit suite, Vitest, the
60% coverage gate, and the production build all run in CI on this PR (#8329):
- [ ] Change type: provider / routing / UI / i18n / CLI / DB / build-deploy / other
- [ ] Focused tests and category gates from the golden path
- [ ] Focused tests for the change: `node --import tsx/esm --test tests/unit/<file>.test.ts`
- [ ] `npm run lint`
- [ ] Reconciled with the current active release base; focused checks rerun afterward
- [ ] Production-code changes include a new or updated automated test in this PR
- [ ] SonarQube PR analysis is green or any remaining issues are explicitly documented below
@@ -32,4 +29,4 @@ Vitest, the 60% coverage gate, and the production build all run in CI on this PR
## Reviewer Notes
- Call out any risky areas, migrations, feature flags, or manual validation that reviewers should know about.
- Call out any risky areas, migrations, feature flags, or manual validation that reviewers should know about.

71
.github/workflows/build-fork.yml vendored Normal file
View File

@@ -0,0 +1,71 @@
name: Publish Fork Image to GHCR
on:
push:
branches: [main]
tags:
- "v*"
workflow_dispatch:
# Least-privilege default: read-only at the top level; the build job that pushes to
# GHCR grants packages: write itself (Scorecard TokenPermissions).
permissions:
contents: read
env:
IMAGE_NAME: ghcr.io/kang-heewon/omniroute
jobs:
build:
name: Build and Push Fork Image
if: github.repository == 'kang-heewon/OmniRoute'
runs-on: ubuntu-latest
permissions:
contents: read
packages: write
steps:
- name: Checkout
uses: actions/checkout@v7
with:
persist-credentials: false
- name: Set up QEMU
uses: docker/setup-qemu-action@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
- name: Login to GitHub Container Registry
uses: docker/login-action@v4
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract Docker metadata
id: meta
uses: docker/metadata-action@v6
with:
images: ${{ env.IMAGE_NAME }}
tags: |
type=raw,value=latest,enable={{is_default_branch}}
type=sha,prefix=sha-
type=ref,event=tag
labels: |
org.opencontainers.image.title=omniroute
org.opencontainers.image.description=Unified AI proxy/router — fork image
org.opencontainers.image.url=https://github.com/kang-heewon/OmniRoute
org.opencontainers.image.source=https://github.com/kang-heewon/OmniRoute
org.opencontainers.image.licenses=MIT
- name: Build and push
uses: docker/build-push-action@v7
with:
context: .
target: runner-base
platforms: linux/amd64,linux/arm64
push: true
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
cache-from: type=gha
cache-to: type=gha,mode=max

View File

@@ -27,7 +27,7 @@ env:
jobs:
changes:
name: Change Classification
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
outputs:
code: ${{ steps.classify.outputs.code }}
docs: ${{ steps.classify.outputs.docs }}
@@ -35,22 +35,13 @@ jobs:
workflow: ${{ steps.classify.outputs.workflow }}
testsOnly: ${{ steps.classify.outputs.testsOnly }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0
with:
persist-credentials: false
fetch-depth: 0
# Refuse a PR that targets its own head branch before spending anything on it. #8912 has
# head == base == release/v3.8.50: no diff, can never merge, and it sits in the queue with
# a full check board attached on every push to that branch. One field comparison.
- name: Reject a PR that targets its own branch
if: github.event_name == 'pull_request'
env:
HEAD_REF: ${{ github.head_ref }}
BASE_REF: ${{ github.base_ref }}
HEAD_SHA: ${{ github.event.pull_request.head.sha }}
BASE_SHA: ${{ github.event.pull_request.base.sha }}
run: node scripts/check/check-pr-self-target.mjs
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
- id: classify
env:
EVENT_NAME: ${{ github.event_name }}
@@ -74,7 +65,7 @@ jobs:
lint:
name: Lint
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
needs: changes
# P3 (plano mestre): a release-PR viva fica DRAFT o ciclo inteiro — jobs pesados pulam
# drafts (ciclo v3.8.44: 123 runs pesados re-disparados por merges na release, 88 cancelados).
@@ -88,9 +79,13 @@ jobs:
API_KEY_SECRET: ci-lint-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: npm run check:node-runtime
- run: npm run audit:deps
@@ -130,17 +125,6 @@ jobs:
- run: npm run check:route-guard-membership
- run: npm run check:test-discovery
- run: npm run check:tracked-artifacts
# (gap 30) Also lives in quality.yml's PR-only "Merge integrity" job — because the
# CHANGELOG half of that job needs a base to diff against. This half does NOT: the
# generator either reproduces the committed SKILL.md files or it does not.
#
# Keeping it PR-only left a real hole. This cycle's merge trains landed in batches with
# `--admin`, which bypasses required checks, so three SKILL.md files drifted from the route
# catalog, rode the release squash into `main`, and the next cycle's sync-back turned them
# into a base-red that blocked EVERY PR into release/v3.8.50 until #8954. Running it here
# means a push to `main` catches the drift at the source instead of the next cycle
# inheriting it.
- run: npm run check:agent-skills-sync
# WS1.7 (v3.8.49 plan): Dockerfile lint (hadolint, pinned by digest).
# failure-threshold=error keeps the 5 pre-existing warnings (DL3008/DL3003/
# DL3016 version pinning / WORKDIR) visible without blocking; any ERROR fails.
@@ -164,7 +148,7 @@ jobs:
quality-gate:
name: Quality Ratchet
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
# needs lint so eslint-results artifact is available (same inventory as the
# blocking lint step). Allow lint failure so other ratchets still run.
needs: [changes, test-coverage, lint]
@@ -184,9 +168,13 @@ jobs:
contents: read
security-events: read
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- name: Restore ESLint file cache
uses: actions/cache@v6
@@ -278,7 +266,7 @@ jobs:
# SonarQube needs SONAR_TOKEN/SONAR_HOST_URL secrets.
quality-extended:
name: Quality Gates (Extended)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
needs: changes
# P3 (plano mestre): a release-PR viva fica DRAFT o ciclo inteiro — jobs pesados pulam
# drafts (ciclo v3.8.44: 123 runs pesados re-disparados por merges na release, 88 cancelados).
@@ -288,10 +276,14 @@ jobs:
# fetch-depth: 0 — the OpenAPI breaking-change gate (oasdiff) reads the base
# spec via `git show <base_ref>:docs/openapi.yaml`; a shallow clone
# would lack the base ref and the gate would self-skip (base-unresolved).
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
# Dead-code, cognitive-complexity, type-coverage foram promovidos ao job
# quality-gate (bloqueante) na Fase 7 INT — não rodam aqui para evitar duplo custo.
@@ -338,16 +330,8 @@ jobs:
install -m 0755 /tmp/osv/*linux_amd64 "$HOME/.local/bin/osv-scanner"
# actionlint — official download script
bash <(curl -fsSL https://raw.githubusercontent.com/rhysd/actionlint/main/scripts/download-actionlint.bash) latest "$HOME/.local/bin"
# zizmor — PyPI (pipx preferred, pip --user fallback); lands in ~/.local/bin.
# PINNED on purpose. Unpinned, the runner installed whatever PyPI served that day and
# measured 1 finding MORE than the devbox on the identical commit (190 vs 189) during
# the v3.8.49 cycle — which cost a second rebaseline push per release, chasing a
# number that was never the code's. The ratchet compares counts across machines, so
# the auditor version has to be the same on both. Bump this deliberately, and
# rebaseline in the same commit: check-workflows.mjs now prints `zizmorVersion=` next
# to the count so the new number is traceable to the tool that produced it.
ZIZMOR_VERSION=1.25.2
pipx install "zizmor==$ZIZMOR_VERSION" || pip install --user "zizmor==$ZIZMOR_VERSION"
# zizmor — PyPI (pipx preferred, pip --user fallback); lands in ~/.local/bin
pipx install zizmor || pip install --user zizmor
# oasdiff — download latest linux amd64 tarball via gh (authed), extract binary
rm -rf /tmp/oasd && mkdir -p /tmp/oasd
gh release download --repo oasdiff/oasdiff --pattern '*linux_amd64.tar.gz' --dir /tmp/oasd
@@ -394,16 +378,20 @@ jobs:
docs-sync-strict:
name: Docs Sync (Strict)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
needs: changes
# P3 (plano mestre): a release-PR viva fica DRAFT o ciclo inteiro — jobs pesados pulam
# drafts (ciclo v3.8.44: 123 runs pesados re-disparados por merges na release, 88 cancelados).
# Run when docs OR code change: API/route code can break doc/OpenAPI contract gates.
if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false && (needs.changes.outputs.docs == 'true' || needs.changes.outputs.code == 'true')) }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: npm run check:docs-all
# Previously-orphaned contract gates (existed as files, never wired anywhere).
@@ -423,7 +411,7 @@ jobs:
docs-lint:
name: Docs Lint (prose — advisory)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
needs: changes
# P3 (plano mestre): a release-PR viva fica DRAFT o ciclo inteiro — jobs pesados pulam
# drafts (ciclo v3.8.44: 123 runs pesados re-disparados por merges na release, 88 cancelados).
@@ -433,9 +421,13 @@ jobs:
# existing doc corpus is brought up to style. Promote to blocking once it converges.
continue-on-error: true
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- name: markdownlint (docs + root, advisory)
run: npx --yes markdownlint-cli2 "docs/**/*.md" "*.md" "!docs/i18n" "!docs/research" || true
- name: Vale prose lint (Microsoft style, advisory)
@@ -450,42 +442,39 @@ jobs:
i18n-ui-coverage:
name: i18n UI Coverage
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
needs: changes
# P3 (plano mestre): a release-PR viva fica DRAFT o ciclo inteiro — jobs pesados pulam
# drafts (ciclo v3.8.44: 123 runs pesados re-disparados por merges na release, 88 cancelados).
# UI keys move with dashboard code OR message catalogs.
if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false && (needs.changes.outputs.i18n == 'true' || needs.changes.outputs.code == 'true')) }}
steps:
# fetch-depth: 0 — the value-drift gate diffs en.json against the merge base to
# find rewritten English strings. On a shallow clone the base ref is missing and
# the gate self-skips (base-unresolved), so it would never actually run.
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: node scripts/i18n/check-ui-keys-coverage.mjs --threshold=65
# #8463: a rewritten English value used to leave its 39 translations behind
# silently (googleOAuthWarning shipped wrong copy in 39 locales for months).
# Key parity above cannot see it — a stale translation counts as covered.
- name: i18n UI value drift (stale translations)
env:
BASE_REF: ${{ github.base_ref && format('origin/{0}', github.base_ref) || '' }}
run: node scripts/i18n/check-ui-value-drift.mjs
# #8038: cheap single-locale glossary/protected-terms consistency gate —
# complements i18n-ui-coverage (key parity) and the ICU `i18n` job below
# without needing app-boot/Playwright infra. Same gating as i18n-ui-coverage.
i18n-glossary-zhcn:
name: i18n Glossary (zh-CN)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
needs: changes
if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false && (needs.changes.outputs.i18n == 'true' || needs.changes.outputs.code == 'true')) }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: node scripts/i18n/check-glossary-consistency.mjs --locale=zh-CN
- run: node scripts/i18n/check-glossary-consistency.mjs --locale=zh-TW
@@ -497,7 +486,7 @@ jobs:
# idioma (a matrix antiga subia 40 artifacts cujo result.txt colidia no merge-multiple).
i18n:
name: i18n Validation (all languages)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
needs: changes
# P3 (plano mestre): a release-PR viva fica DRAFT o ciclo inteiro — jobs pesados pulam
# drafts (ciclo v3.8.44: 123 runs pesados re-disparados por merges na release, 88 cancelados).
@@ -505,7 +494,7 @@ jobs:
if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false && needs.changes.outputs.i18n == 'true') }}
continue-on-error: true
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-python@v7
@@ -540,12 +529,15 @@ jobs:
pr-test-policy:
name: PR Test Policy
if: ${{ github.event_name == 'pull_request' && github.event.pull_request.draft == false }}
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
- name: Fetch base branch
run: git fetch --no-tags origin "${GITHUB_BASE_REF}"
- name: Validate source changes include tests
@@ -572,17 +564,17 @@ jobs:
# online), the heavy jobs run on the dedicated 32-core VPS runners (label
# omni-release) instead of queueing on the 20-concurrent-job hosted pool.
# Safety: fork PRs NEVER reach the self-hosted runner — the expression falls
# back to ubuntu-26.04 unless the PR head repo is this repository (push /
# back to ubuntu-latest unless the PR head repo is this repository (push /
# dispatch events are own-origin by definition). Any failure path (VM down,
# var unset/false) also falls back to ubuntu-26.04.
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-26.04' }}
# var unset/false) also falls back to ubuntu-latest.
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-latest' }}
needs: changes
if: ${{ github.event_name != 'pull_request' || (needs.changes.outputs.code == 'true' && github.event.pull_request.draft == false) }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -622,14 +614,18 @@ jobs:
package-artifact:
name: Package Artifact
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
needs: build
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: npm run check:node-runtime
- name: Download Next.js build artifact
@@ -665,15 +661,15 @@ jobs:
strategy:
fail-fast: false
matrix:
os: [ubuntu-26.04, windows-latest]
os: [ubuntu-latest, windows-latest]
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
CSC_IDENTITY_AUTO_DISCOVERY: "false"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -712,14 +708,8 @@ jobs:
test-unit:
name: Unit Tests (${{ matrix.shard }}/8)
# Same dynamic-runner rule as Build (own-origin only; fallback ubuntu-26.04).
# PINNED to hosted, deliberately not on the USE_VPS_RUNNER switch (gap 19). One variable
# governed the build and the test jobs, which want OPPOSITE machines: the build needs the
# .113's RAM, the tests need the hosted runner's link. Measured on 2026-07-29 —
# actions/setup-node took 20m06s on .113 with 4 concurrent runners versus 16s hosted (npm
# cache restore saturating the link), while the tests themselves tied, 2m54 vs 2m31. So
# self-hosted is strictly worse here and there is nothing to configure.
runs-on: ubuntu-26.04
# Same dynamic-runner rule as Build (own-origin only; fallback ubuntu-latest).
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-latest' }}
timeout-minutes: 25
# needs: changes (not build) — this job never downloads the next-build artifact;
# gating it on Build only serialized ~20min of wall-clock for nothing. Jobs that
@@ -737,9 +727,13 @@ jobs:
API_KEY_SECRET: ci-test-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: npm run check:node-runtime
# QW-d (plano mestre): fonte única — o MESMO npm script dos runs locais (adiciona o
@@ -769,27 +763,25 @@ jobs:
test-bun-sqlite:
name: Bun SQLite Compatibility
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
timeout-minutes: 10
needs: changes
if: ${{ github.event_name != 'pull_request' || (needs.changes.outputs.code == 'true' && github.event.pull_request.draft == false) }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: npm run test:bun:db
test-vitest:
name: Vitest (MCP / autoCombo / UI components)
# Same dynamic-runner rule as Build (own-origin only; fallback ubuntu-26.04).
# PINNED to hosted, deliberately not on the USE_VPS_RUNNER switch (gap 19). One variable
# governed the build and the test jobs, which want OPPOSITE machines: the build needs the
# .113's RAM, the tests need the hosted runner's link. Measured on 2026-07-29 —
# actions/setup-node took 20m06s on .113 with 4 concurrent runners versus 16s hosted (npm
# cache restore saturating the link), while the tests themselves tied, 2m54 vs 2m31. So
# self-hosted is strictly worse here and there is nothing to configure.
runs-on: ubuntu-26.04
# Same dynamic-runner rule as Build (own-origin only; fallback ubuntu-latest).
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-latest' }}
timeout-minutes: 15
# needs: changes (not build) — no artifact consumed; see test-unit note.
needs: changes
@@ -799,9 +791,13 @@ jobs:
API_KEY_SECRET: ci-test-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
# The second test runner (CLAUDE.md: "Both test runners must pass") — was never
# wired into CI until the 2026-06-09 quality audit (Fase 6A.2).
@@ -829,7 +825,7 @@ jobs:
# the release gate can still exercise them via workflow_dispatch when needed).
test-coverage:
name: Coverage
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
# 10min was sized before #7114 added the lcov reporter (Codecov/Sonar need it);
# merging 8 shard JSONs + text+json+lcov now takes ~10-12min — three consecutive
# release-tip runs died at exactly 10m as job-timeout "cancelled" (2026-07-15/16).
@@ -840,9 +836,13 @@ jobs:
JWT_SECRET: ci-test-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-test-api-key-secret-long
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- name: Download all shard coverage
uses: actions/download-artifact@v8
@@ -926,14 +926,14 @@ jobs:
sonarqube:
name: SonarQube
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
needs: test-coverage
if: ${{ !cancelled() && needs.test-coverage.result == 'success' }}
env:
SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }}
SONAR_HOST_URL: ${{ secrets.SONAR_HOST_URL }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
fetch-depth: 0
@@ -978,7 +978,7 @@ jobs:
coverage-pr-comment:
name: PR Coverage Comment
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
if: ${{ !cancelled() && github.event_name == 'pull_request' && github.event.pull_request.draft == false && github.event.pull_request.head.repo.fork == false && needs.changes.outputs.code == 'true' }}
needs:
- changes
@@ -1057,7 +1057,7 @@ jobs:
test-e2e:
name: E2E Tests (${{ matrix.shard }}/9)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
# Build artifact from the `build` job is downloaded instead of rebuilding
# (~5min saved per shard). 9 shards (up from 6) reduces tests per shard by
# ~33%. Playwright browser is cached across runs (~1.5min saved per shard).
@@ -1079,9 +1079,13 @@ jobs:
DISABLE_SQLITE_AUTO_BACKUP: "true"
OMNIROUTE_PLAYWRIGHT_SKIP_BUILD: "1"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: npm run check:node-runtime
- name: Cache Playwright browsers
@@ -1111,8 +1115,7 @@ jobs:
if FILES=$(node scripts/quality/balance-e2e-shards.mjs "$SHARD" 9); then
if [ -z "$FILES" ]; then echo "[e2e-balance] shard $SHARD has no files"; exit 0; fi
echo "[e2e-balance] shard $SHARD runs:"; echo "$FILES"
# FILES is our own newline-separated path list, so word-splitting is intended
# shellcheck disable=SC2086,SC2046
# shellcheck disable=SC2086 — FILES is our own newline-separated path list
npx playwright test $(echo "$FILES" | tr '\n' ' ') --reporter=line,junit
else
echo "[e2e-balance] balancer unavailable — plain --shard fallback"
@@ -1130,7 +1133,7 @@ jobs:
test-integration:
name: Integration Tests (${{ matrix.shard }}/2)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
timeout-minutes: 15
# needs: changes (not build) — no artifact consumed; see test-unit note.
needs: changes
@@ -1146,9 +1149,13 @@ jobs:
DATA_DIR: /tmp/omniroute-ci-${{ matrix.shard }}
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: npm run check:node-runtime
# (tsx/esm = QW-b; o alinhamento de ESCOPO do integration com o npm script fica p/ follow-up)
@@ -1156,7 +1163,7 @@ jobs:
test-security:
name: Security Tests
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
# needs: changes (not build) — no artifact consumed; see test-unit note.
needs: changes
if: ${{ github.event_name != 'pull_request' || (needs.changes.outputs.code == 'true' && github.event.pull_request.draft == false) }}
@@ -1165,16 +1172,20 @@ jobs:
API_KEY_SECRET: ci-test-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: npm run check:node-runtime
- run: npm run test:security
ci-summary:
name: CI Dashboard
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
if: ${{ !cancelled() }}
needs:
- changes
@@ -1206,8 +1217,6 @@ jobs:
- name: Generate dashboard
env:
EVENT_NAME: ${{ github.event_name }}
# Workflow-controlled data (job results), not user input — safe to read here.
NEEDS_JSON: ${{ toJSON(needs) }}
run: |
status() {
case "$1" in
@@ -1222,29 +1231,6 @@ jobs:
echo "# 🚀 CI Dashboard" >> "$GITHUB_STEP_SUMMARY"
echo "" >> "$GITHUB_STEP_SUMMARY"
# (gap 12) A cancelled job never reported a verdict, and in a long table that reads the
# same as a green one. `cancel-in-progress` plus incremental fixing cancels jobs on every
# push, and this cycle the Vitest job was cancelled in rounds 1, 2 and 3 — it only ran to
# completion in round 4, where it revealed a suite that had been broken the whole cycle
# plus two production bugs. A gate that never finishes is indistinguishable from one that
# passes, so name them at the TOP instead of leaving them to be spotted mid-table.
CANCELLED_JOBS=$(printf '%s' "$NEEDS_JSON" \
| jq -r 'to_entries | map(select(.value.result == "cancelled")) | .[].key' 2>/dev/null \
| sort | paste -sd", " -) || CANCELLED_JOBS=""
if [ -n "$CANCELLED_JOBS" ]; then
{
echo "> ### ⚫ Cancelled — no verdict was reported"
echo ">"
echo "> \`$CANCELLED_JOBS\`"
echo ">"
echo "> These did not fail; they never finished, so nothing was checked. Treat this"
echo "> run as INCOMPLETE for those gates. If the cancellation came from"
echo "> \`cancel-in-progress\` on a newer push, the newer run covers it — otherwise"
echo "> re-run them before reading this dashboard as green."
echo ""
} >> "$GITHUB_STEP_SUMMARY"
fi
echo "## 🧱 Core Checks" >> "$GITHUB_STEP_SUMMARY"
echo "| Job | Status |" >> "$GITHUB_STEP_SUMMARY"
echo "|-----|--------|" >> "$GITHUB_STEP_SUMMARY"

View File

@@ -21,7 +21,7 @@ jobs:
(github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
(github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
(github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
permissions:
contents: read
pull-requests: read
@@ -30,7 +30,7 @@ jobs:
actions: read # Required for Claude to read CI results on PRs
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@v7
with:
persist-credentials: false
fetch-depth: 1

View File

@@ -13,13 +13,13 @@ permissions:
jobs:
analyze:
name: Analyze (javascript-typescript)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
permissions:
security-events: write
actions: read
contents: read
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- uses: github/codeql-action/init@e4fba868fa4b1b91e1fdab776edc8cfbe6e9fb81 # v4.37.3

View File

@@ -18,7 +18,7 @@ concurrency:
cancel-in-progress: true
jobs:
dast-smoke:
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
# ADVISORY while this new gate matures (repo convention: advisory -> blocking).
# Flip to blocking (remove continue-on-error) once it's proven stable across a few PRs.
continue-on-error: true
@@ -30,9 +30,13 @@ jobs:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-api-key-secret-with-sufficient-length-aaaa
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
with:
node-version: "24"
cache: npm
- run: npm ci
- name: Build CLI bundle
env:
@@ -55,14 +59,8 @@ jobs:
- run: pip install schemathesis
- name: Schemathesis smoke (high-risk endpoints, blocking)
run: |
# /api/auth/oidc/* is a BROWSER redirect flow (302 to the IdP, 302 back to
# /login?oidc_error=... on every failure), not a REST endpoint: Schemathesis reads
# those 302s as "the API accepted a schema-violating request" and the configured-off
# 400 as "rejected a schema-compliant request". Documenting the flow in the spec is
# still right (operators need it); fuzzing it is not what this smoke is for.
schemathesis run docs/openapi.yaml --url http://localhost:20128 \
--include-path-regex '^/v1/(chat/completions|models)$|^/api/(auth|keys)' \
--exclude-path-regex '^/api/auth/oidc/' \
--max-examples 8 --workers 4 --checks all --max-response-time 30 \
--request-timeout 20 --suppress-health-check all --no-color
- name: promptfoo injection-guard (blocking)

View File

@@ -15,7 +15,7 @@ jobs:
(github.event_name == 'workflow_dispatch' || github.event.workflow_run.conclusion == 'success')
&& vars.DEPLOY_ENABLED == 'true'
name: Deploy OmniRoute to VPS
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- name: Check VPS SSH reachability from runner
id: reach

View File

@@ -33,7 +33,7 @@ permissions:
jobs:
prepare:
name: Resolve Docker release metadata
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
outputs:
version: ${{ steps.version.outputs.version }}
promote_latest: ${{ steps.version.outputs.promote_latest }}
@@ -42,7 +42,7 @@ jobs:
IMAGE_NAME: diegosouzapw/omniroute
steps:
- name: Checkout
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@v7
with:
persist-credentials: false
ref: ${{ github.event_name == 'workflow_dispatch' && format('refs/tags/v{0}', inputs.version) || '' }}
@@ -145,7 +145,7 @@ jobs:
GHCR_IMAGE_NAME: ghcr.io/diegosouzapw/omniroute
steps:
- name: Checkout
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@v7
with:
persist-credentials: false
ref: ${{ github.event_name == 'workflow_dispatch' && format('refs/tags/v{0}', inputs.version) || '' }}
@@ -233,7 +233,7 @@ jobs:
- prepare
- build
if: needs.prepare.outputs.skip != 'true'
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
permissions:
contents: read
packages: write
@@ -245,7 +245,7 @@ jobs:
PROMOTE_LATEST: ${{ needs.prepare.outputs.promote_latest }}
steps:
- name: Checkout
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@v7
with:
persist-credentials: false
ref: ${{ github.event_name == 'workflow_dispatch' && format('refs/tags/v{0}', inputs.version) || '' }}

View File

@@ -20,14 +20,14 @@ permissions:
jobs:
validate:
name: Validate version
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
permissions:
contents: read
outputs:
version: ${{ steps.validate.outputs.version }}
steps:
- name: Checkout code
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@v7
with:
persist-credentials: false
fetch-depth: 0
@@ -78,17 +78,17 @@ jobs:
target: mac-arm64
ext: -arm64.dmg
- platform: linux
runner: ubuntu-26.04
runner: ubuntu-latest
target: linux
ext: .AppImage
deb_ext: .deb
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- name: Setup Node
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
uses: actions/setup-node@v7
with:
node-version: 24
cache: npm
@@ -120,18 +120,6 @@ jobs:
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
NODE_OPTIONS: "--max_old_space_size=6144"
# Linux builds with webpack, not Turbopack. Turbopack's production build
# allocates natively (Rust, off the V8 heap), so --max_old_space_size does
# not bound it, and on this module graph it peaks above what the hosted
# runner can give — the VM is reclaimed mid-compile with "The runner has
# received a shutdown signal", no exit code. That is what silently took the
# whole desktop channel out of v3.8.49: the linux leg died, `release` was
# skipped, and the release shipped with ZERO assets. Measured on a 32 GB
# box the same build passes and peaks past 14 GB. The webpack fallback is
# the project's documented escape hatch for RAM-constrained machines
# (docs/reference/ENVIRONMENT.md, #6409) and is the same remedy already
# applied to nightly-compat's Node 26 build (#8090).
OMNIROUTE_USE_TURBOPACK: ${{ matrix.platform == 'linux' && '0' || '1' }}
run: npm run build
- name: Sync version in electron/package.json
@@ -229,53 +217,21 @@ jobs:
release:
name: Create Release
needs: [validate, build]
# Fail-partial, not fail-closed. `build` is a 4-leg matrix with `fail-fast: false`,
# so the legs that succeed still upload their artifacts — but a default `needs:`
# gate skips this job the moment ANY leg fails, discarding all of them. That is
# exactly what happened to v3.8.49: the linux leg died and the release shipped with
# ZERO assets, throwing away 1.7 GB of good Windows/macOS installers **and** the
# source archives + SBOM, which do not depend on a build at all. The result was
# indistinguishable from "this version has no desktop channel".
# Now: attach everything that did build, then fail the job loudly (see the last
# step) so an incomplete channel is visible instead of silent.
if: ${{ !cancelled() && needs.validate.result == 'success' }}
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
permissions:
contents: write # softprops/action-gh-release creates the GitHub Release
steps:
- name: Checkout
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@v7
with:
persist-credentials: false
fetch-depth: 0
# `merge-multiple` is deliberately OFF. It resolves same-name collisions by ARRIVAL
# ORDER, and the two macOS jobs each emit their own `latest-mac.yml` listing only their
# own dmg (measured: 338 and 350 bytes, different content, identical name). One silently
# overwrote the other — arm64 won in the published v3.8.48, and since the Intel dmg
# carries no arch suffix in its name, electron-updater's
# `files.find(url includes process.arch) ?? files.shift()` sends every Intel Mac to the
# ARM dmg. Downloading into per-artifact subdirectories keeps both, so they can be
# merged on purpose instead of by luck.
- name: Download all artifacts
uses: actions/download-artifact@v8
with:
path: artifacts
# Writes release-assets/latest-mac.yml with BOTH dmgs, un-suffixed entry first (that is
# the one electron-updater can only reach through its fallback). Refuses to write when the
# inputs disagree on version — a manifest stitched from two builds is worse than none.
- name: Merge the per-arch macOS updater manifests
run: node scripts/release/merge-mac-update-manifest.mjs artifacts release-assets
# Everything else moves across as-is. The partial latest-mac.yml files are excluded so
# they cannot clobber the merged one; -n is a second belt on the same braces.
- name: Collect the remaining artifacts
run: |
mkdir -p release-assets
find artifacts -type f ! -name latest-mac.yml -exec cp -n {} release-assets/ \;
echo "release-assets:"
ls -la release-assets/
path: release-assets
merge-multiple: true
- name: Create source archives
env:
@@ -319,47 +275,6 @@ jobs:
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
verify-desktop-assets:
name: Verify desktop assets landed
needs: [validate, release]
# Deliberately a SEPARATE job, not a final step of `release`: failing inside
# `release` would cascade into `publish-npm` (which gates on `needs: release`) and
# block the npm channel over a desktop-only gap. Here the assets are attached, npm
# still publishes, and an incomplete desktop channel shows up as a red job instead
# of passing unnoticed — the v3.8.49 release had ZERO assets and every gate was
# green, because nothing ever asserted the release HAS binaries.
if: ${{ !cancelled() && needs.release.result == 'success' }}
runs-on: ubuntu-26.04
permissions:
contents: read
steps:
- name: Assert every platform is present on the release
env:
# Regex-validated (^v[0-9]+\.[0-9]+\.[0-9]+$) in the `validate` job, and
# passed via env rather than interpolated into the script body.
VERSION: ${{ needs.validate.outputs.version }}
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
names=$(gh release view "$VERSION" --repo "$GITHUB_REPOSITORY" \
--json assets --jq '.assets[].name')
echo "Assets on $VERSION:"
echo "$names" | sed 's/^/ /'
missing=""
# `[ ... ] && missing=...` as the last command in a branch returns 1 and
# would abort the whole script under Actions' default `set -e`. Use if/fi.
for want in '\.exe$' '\.dmg$' '\.AppImage$' '\.deb$' '^latest.*\.yml$' '\.source\.tar\.gz$'; do
if ! echo "$names" | grep -qE "$want"; then
missing="$missing $want"
fi
done
if [ -n "$missing" ]; then
echo "::error::Desktop channel incomplete on $VERSION — no asset matching:$missing"
exit 1
fi
echo "✓ every platform present on $VERSION"
publish-npm:
name: Publish to npm
needs: [validate, release]

View File

@@ -40,7 +40,7 @@ jobs:
# ─────────────────────────────────────────────────────────────────────────
lock-branch:
if: github.event_name == 'release' || github.event_name == 'workflow_dispatch'
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- name: Lock release/<tag> branch
env:
@@ -97,7 +97,7 @@ jobs:
# ─────────────────────────────────────────────────────────────────────────
guard-no-push-after-release:
if: github.event_name == 'push'
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- name: Reject push if matching release tag exists
env:

View File

@@ -22,7 +22,7 @@ permissions:
jobs:
stryker-nobail:
name: Stryker disableBail (batch ${{ matrix.batch.name }})
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
@@ -41,9 +41,13 @@ jobs:
mutate: "open-sse/handlers/chatCore/telemetryHelpers.ts,open-sse/handlers/chatCore/memorySkillsInjection.ts,open-sse/handlers/chatCore/semanticCache.ts"
timeout-minutes: 300
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
- run: npm ci
- name: Run Stryker (disableBail)
env:

View File

@@ -28,11 +28,11 @@ concurrency:
jobs:
resolve-branch:
name: Resolve active release branch
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
outputs:
target: ${{ steps.branch.outputs.target }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
fetch-depth: 0
persist-credentials: false
@@ -58,37 +58,24 @@ jobs:
compat-build-26:
name: Node 26 Compatibility Build
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
timeout-minutes: 25
needs: resolve-branch
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
ref: ${{ needs.resolve-branch.outputs.target }}
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
- uses: actions/setup-node@v7
with:
node-version: "26"
cache: npm
- uses: ./.github/actions/npm-ci-retry
# #8090 — this is the ONLY Node 26 build in the whole CI matrix (ci.yml pins
# CI_NODE_VERSION=24). It failed every nightly with the runner-reclaimed
# signature ("The runner has received a shutdown signal" / "The operation was
# canceled", no exit code) always at the same Turbopack compile phase — a
# classic OOM kill on the memory-constrained 16 GB hosted runner. Turbopack's
# native (Rust, off-V8-heap) allocation is NOT bounded by --max-old-space-size
# and peaks far higher than webpack on this large module graph (#6409), and is
# heavier still under Node 26. Use the documented webpack fallback here: it still
# validates that the app *builds* on Node 26 (the point of this compat job) at a
# much lower memory peak. Turbopack-on-Node-24 stays covered by ci.yml's build
# job. See docs/reference/ENVIRONMENT.md (OMNIROUTE_USE_TURBOPACK) and #6409.
- run: npm run build
env:
OMNIROUTE_USE_TURBOPACK: "0"
compat-tests:
name: Node ${{ matrix.node }} Compat Tests (${{ matrix.shard }}/4)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
timeout-minutes: 25
needs: resolve-branch
strategy:
@@ -102,11 +89,11 @@ jobs:
DISABLE_SQLITE_AUTO_BACKUP: "true"
TEST_SHARD: ${{ matrix.shard }}/4
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
ref: ${{ needs.resolve-branch.outputs.target }}
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
- uses: actions/setup-node@v7
with:
node-version: ${{ matrix.node }}
cache: npm
@@ -116,7 +103,7 @@ jobs:
report:
name: Open / update tracking issue on failure
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
if: ${{ !cancelled() && (needs.compat-tests.result == 'failure' || needs.compat-build-26.result == 'failure') }}
needs: [resolve-branch, compat-build-26, compat-tests]
permissions:

View File

@@ -10,11 +10,13 @@ permissions:
jobs:
promptfoo-guard:
name: promptfoo — injection guard (block mode, no secret)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with: { node-version: "24", cache: npm }
- run: npm ci
- name: Build CLI bundle
env:
@@ -44,7 +46,7 @@ jobs:
garak:
name: garak probes (skip without provider secret)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
# NOTE: the `secrets` context is NOT available in a job-level `if:` — referencing
# it there makes GitHub reject the file on push (startup_failure on every push).
# Map the secret into a job-level env and gate each step on a presence check, so
@@ -61,10 +63,13 @@ jobs:
echo "run=false" >> "$GITHUB_OUTPUT"
echo "::notice::PROMPTFOO_PROVIDER_KEY not set — skipping garak probes (advisory)."
fi
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
if: steps.gate.outputs.run == 'true'
- uses: actions/setup-node@v7
if: steps.gate.outputs.run == 'true'
with: { node-version: "24", cache: npm }
- run: npm ci
if: steps.gate.outputs.run == 'true'
- name: Build CLI bundle

View File

@@ -10,7 +10,7 @@ permissions:
jobs:
stryker:
name: Stryker mutation (batch ${{ matrix.batch.name }} — advisory)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
# Mutation testing is expensive. History of the budget:
# - Full 8-module set TIMED OUT at the 180min cap (run 27705123780 = exactly 180min).
# The two god-files chatCore.ts/combo.ts dominated ~2/3 of the mutants and were
@@ -104,9 +104,13 @@ jobs:
# scripts/quality/mutation-radiography.mjs both merge per file).
timeout-minutes: ${{ matrix.batch.timeout || 180 }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
- run: npm ci
- name: Restore Stryker incremental cache
uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v6.1.0
@@ -141,12 +145,15 @@ jobs:
name: Mutation score ratchet (blocking)
needs: stryker
if: always()
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
timeout-minutes: 15
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v6
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: "24"
- name: Download all mutation reports
uses: actions/download-artifact@v8
with:

View File

@@ -8,11 +8,15 @@ permissions:
issues: write
jobs:
property-random-seed:
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
- run: npm ci
- name: fast-check random seed (high runs)
id: prop

View File

@@ -68,13 +68,13 @@ jobs:
# this runs on the dedicated VPS runner — clean env (no operator OMNIROUTE_API_KEY,
# no local noauth CLIs => zero machine-specific false positives) and no contention.
# Nightly cron normally finds the var false (VM off) and falls back to hosted.
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && fromJSON('["self-hosted","omni-release"]')) || 'ubuntu-26.04' }}
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && fromJSON('["self-hosted","omni-release"]')) || 'ubuntu-latest' }}
env:
JWT_SECRET: ci-nightly-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-nightly-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
fetch-depth: 0
persist-credentials: false
@@ -116,7 +116,7 @@ jobs:
git checkout "$TARGET"
git log -1 --oneline
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
@@ -143,8 +143,7 @@ jobs:
MODE="--with-build --full-ci"
fi
echo "[release-green] mode: $MODE (event: $EVENT_NAME)"
# MODE is an intentional flag list, so word-splitting is wanted here
# shellcheck disable=SC2086
# shellcheck disable=SC2086 — MODE is an intentional flag list
node scripts/quality/validate-release-green.mjs --json --hermetic $MODE \
1> release-green.json 2> release-green.log
echo "exit=$?" >> "$GITHUB_OUTPUT"
@@ -217,19 +216,19 @@ jobs:
# On a push, only run for a push to main — a push to release/* is handled by
# release-green above. Schedule/dispatch always run (they also sweep main).
if: ${{ github.event_name != 'push' || github.ref_name == 'main' }}
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && fromJSON('["self-hosted","omni-release"]')) || 'ubuntu-26.04' }}
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && fromJSON('["self-hosted","omni-release"]')) || 'ubuntu-latest' }}
env:
JWT_SECRET: ci-nightly-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-nightly-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
ref: main # literal — no injection surface; scheduled runs default to the repo default branch (a release/v*), so pin main explicitly
fetch-depth: 0
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
@@ -249,8 +248,7 @@ jobs:
MODE="--with-build --full-ci"
fi
echo "[main-green] mode: $MODE (event: $EVENT_NAME)"
# MODE is an intentional flag list, so word-splitting is wanted here
# shellcheck disable=SC2086
# shellcheck disable=SC2086 — MODE is an intentional flag list
node scripts/quality/validate-release-green.mjs --json --hermetic $MODE \
1> main-green.json 2> main-green.log
echo "exit=$?" >> "$GITHUB_OUTPUT"
@@ -303,140 +301,3 @@ jobs:
main-green.json
main-green.log
if-no-files-found: ignore
# ── Banking lane (#8584) ──────────────────────────────────────────────────
# The ratchet is asymmetric: RAISING a cap is a ten-second manual JSON edit made
# under merge pressure, LOWERING one requires someone to run `--update` and commit
# — which no workflow does. Grep `.github/workflows/` for `--update`: only
# wiki-sync.yml (unrelated) and ci.yml's check-quality-ratchet.mjs --require-tighten
# (a different script, a different metric). So a cap outlives the code that earned
# it and every completed decomposition silently becomes a growth allowance for
# whoever touches the file next. Measured on 2026-07-25: 18 frozen files already at
# or under the 800-line new-file cap, up to 132x (schemas.ts, 19 lines / 2523 cap),
# and 31 unfulfilled "tighten via --update next cycle" notes honoured exactly once
# (-1 unit) in six weeks.
#
# This job closes that loop by making the DOWNWARD direction as automatic as the
# upward one is easy. It measures the active release branch, runs the shrink-only
# `--update` paths, and opens ONE always-current PR with the result. It never
# pushes to release/* — a human still merges, so a bad measurement cannot land
# unreviewed. verify-ratchet-bank.mjs is the hard guarantee that the automation can
# only ever write in the shrink direction; if anything was raised, added, or a
# rebaseline note was touched, the job aborts and opens nothing.
#
# Schedule/dispatch only, deliberately NOT on push: banking has no latency
# requirement (a shrink banked within 8h is fine) and a per-merge run would rebuild
# the PR branch repeatedly during merge campaigns while paying for a full ESLint
# walk each time. Detection stays on push (release-green above); banking is batched.
bank-ratchet-shrinks:
name: Bank ratchet shrinks
if: ${{ github.event_name != 'push' }}
runs-on: ubuntu-26.04
permissions:
contents: write
pull-requests: write
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
with:
fetch-depth: 0
- name: Resolve active release branch
id: branch
env:
INPUT_BRANCH: ${{ github.event.inputs.branch }}
run: |
set -euo pipefail
if [ -n "${INPUT_BRANCH:-}" ]; then
TARGET="$INPUT_BRANCH"
else
TARGET=$(git for-each-ref --format='%(refname:short)' 'refs/remotes/origin/release/v*' \
| sed 's#origin/##' \
| sort -t/ -k2 -V \
| tail -1)
fi
if [ -z "$TARGET" ]; then echo "No release/v* branch found"; exit 1; fi
# Same strict guard as the validation job — blocks ref/command injection
# through the workflow_dispatch input.
if ! printf '%s' "$TARGET" | grep -qE '^release/v[0-9]+\.[0-9]+\.[0-9]+$'; then
echo "Refusing non-canonical branch name: $TARGET"; exit 1
fi
echo "target=$TARGET" >> "$GITHUB_OUTPUT"
echo "bank_branch=chore/bank-ratchet-${TARGET#release/}" >> "$GITHUB_OUTPUT"
- name: Checkout the release branch
env:
TARGET: ${{ steps.branch.outputs.target }}
run: |
set -euo pipefail
git checkout "$TARGET"
git log -1 --oneline
- uses: ./.github/actions/npm-ci-retry
- name: Ratchet the baselines down
run: |
# Both --update paths are shrink-only by construction (file-size writes only
# on `improvements`, complexity-ratchets only when `.improved`), and both exit
# non-zero while the branch is over baseline — which is exactly when there is
# nothing to bank. Their exit code is not the signal; the verifier below is.
set +e
node scripts/check/check-file-size.mjs --update
node scripts/check/check-complexity-ratchets.mjs --update
exit 0
- name: Verify the write only went downward
id: verify
run: |
set -euo pipefail
# Exits 1 if ANYTHING was raised/added or a rebaseline note was touched.
# `set -e` then aborts the job before a commit exists — no PR is opened.
node scripts/quality/verify-ratchet-bank.mjs > bank-summary.md
if [ -n "$(git status --porcelain config/quality/)" ]; then
echo "changed=true" >> "$GITHUB_OUTPUT"
else
echo "changed=false" >> "$GITHUB_OUTPUT"
echo "Nothing to bank — baselines already match the code."
fi
- name: Open / update the banking PR
if: steps.verify.outputs.changed == 'true'
env:
GH_TOKEN: ${{ github.token }}
TARGET: ${{ steps.branch.outputs.target }}
BANK_BRANCH: ${{ steps.branch.outputs.bank_branch }}
RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
run: |
set -euo pipefail
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
git checkout -B "$BANK_BRANCH"
git add config/quality/
git commit -m "chore(quality): bank ratchet shrinks measured on ${TARGET}"
git push --force origin "$BANK_BRANCH"
{
echo "Automated banking of quality-ratchet **shrinks** already present in"
echo "\`${TARGET}\` — the downward half of the ratchet, which nothing else runs (#8584)."
echo ""
echo "Produced by \`check:file-size --update\` + \`check:complexity-ratchets --update\`,"
echo "then verified by \`scripts/quality/verify-ratchet-bank.mjs\`: **nothing was raised,"
echo "nothing was added, no rebaseline note was touched** — the job aborts without"
echo "opening a PR if any of those is violated."
echo ""
echo "No product code changes. Merging retires growth allowances that the code no"
echo "longer needs; not merging leaves them available to whoever edits those files next."
echo ""
cat bank-summary.md
echo ""
echo "**Run:** ${RUN_URL}"
} > pr-body.md
EXISTING=$(gh pr list --repo "$GITHUB_REPOSITORY" --head "$BANK_BRANCH" \
--state open --json number --jq '.[0].number' 2>/dev/null || echo "")
if [ -n "$EXISTING" ]; then
gh pr edit "$EXISTING" --repo "$GITHUB_REPOSITORY" --body-file pr-body.md
echo "Updated existing PR #$EXISTING"
else
gh pr create --repo "$GITHUB_REPOSITORY" --base "$TARGET" --head "$BANK_BRANCH" \
--title "chore(quality): bank ratchet shrinks (${TARGET})" --body-file pr-body.md
fi

View File

@@ -10,31 +10,43 @@ permissions:
jobs:
heap:
name: Heap-growth gate
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
- run: npm ci
- run: npm run test:heap
chaos:
name: Resilience chaos (fault injection)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
- run: npm ci
- run: npm run test:chaos
k6-soak:
name: k6 load/soak
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
- run: npm ci
- name: Build CLI bundle
env:
@@ -66,7 +78,7 @@ jobs:
a11y:
name: A11y axe (nightly, freeze-and-alert)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
# The Playwright webServer (`start` mode) builds Next via build-next-isolated.mjs and
# boots the standalone server itself (waits on /api/monitoring/health, 15min webServer
# timeout). Unlike the per-PR test-e2e job, this nightly job has no pre-built artifact,
@@ -80,9 +92,13 @@ jobs:
DISABLE_SQLITE_AUTO_BACKUP: "true"
REQUIRE_AXE: "1"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: "24"
cache: npm
- run: npm ci
- name: Cache Playwright browsers
uses: actions/cache@v6.1.0

View File

@@ -10,12 +10,14 @@ permissions:
jobs:
schemathesis:
name: Schemathesis — OpenAPI contract fuzz (advisory)
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
timeout-minutes: 30
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with: { node-version: "24", cache: npm }
- run: npm ci
- name: Build CLI bundle
env:

View File

@@ -56,21 +56,14 @@ env:
jobs:
publish:
# Same dynamic-runner rule as ci.yml's `build`/`test-unit`: `build:cli` falls back to a
# full `next build`, whose working set outgrew the 16 GB hosted runner during the
# v3.8.49 cycle — the publish died with "The runner has received a shutdown signal"
# mid-"Creating an optimized production build" while v3.8.48 had still fit in 16min.
# This job never runs on `pull_request`, so the fork-safety clause is always true here;
# it is kept verbatim so the expression stays greppable against ci.yml.
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-26.04' }}
runs-on: ubuntu-latest
permissions:
actions: read # find + download the CI run's next-build artifact for this SHA
contents: write # gh release upload (attach SBOM to the GitHub Release)
id-token: write # npm provenance
packages: write # publish to npm.pkg.github.com
steps:
- name: Checkout
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@v7
with:
persist-credentials: false
# Need full tag history to compare against highest semver when
@@ -78,7 +71,7 @@ jobs:
fetch-depth: 0
- name: Setup Node.js
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
uses: actions/setup-node@v7
with:
node-version: ${{ env.NPM_PUBLISH_NODE_VERSION }}
registry-url: https://registry.npmjs.org
@@ -152,74 +145,6 @@ jobs:
run: |
npm version "$VERSION" --no-git-tag-version --allow-same-version
# Fast path: CI already built the standalone tree for THIS commit and uploaded it as
# `next-build`. `build:cli` (scripts/build/prepublish.ts) only shells out to a full
# `next build` when `.build/next/standalone/server.js` is missing — restoring the
# artifact turns the heaviest step of the publish into a download. Matching on
# `head_sha` is the tree-equality guarantee: same commit, same tree.
# Best-effort by design (retention is 1 day): every miss falls through to the build
# step below, which is why the dynamic runner above matters as the backstop.
#
# The `head_repository.full_name == env.REPO` clause is a supply-chain guard, not a
# filter refinement. This artifact becomes the published npm tarball. `pull_request`
# runs from forks execute in THIS repository's context and upload their own
# `next-build` built from fork-controlled source, and the runs API returns them for a
# matching `head_sha` — 57 such runs exist in this repo today. Without the clause,
# anything that made a fork's head commit coincide with the publish commit could put
# attacker-built bytes on npm. Requiring the run to originate from this repository
# excludes every fork run while keeping the fast path intact (verified: the same
# single run is selected either way for the current tip).
# CodeQL: actions/artifact-poisoning/critical.
- name: Reuse CI's next-build artifact (skips the heavy rebuild)
if: steps.resolve.outputs.skip != 'true'
continue-on-error: true
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
HEAD_SHA: ${{ github.sha }}
REPO: ${{ github.repository }}
run: |
set -uo pipefail
# The question is "which run HAS the artifact", not "which run passed" (gap 16).
# Requiring `conclusion == "success"` on the whole run discarded a perfectly good tree
# whenever any unrelated shard went red — one flaky test then pushed the publish into
# the 40-minute build this step exists to avoid. The artifact is only uploaded if the
# Build job itself succeeded, so its PRESENCE is the accurate signal; the run's overall
# conclusion is noise from jobs that have nothing to do with the tree.
#
# `head_repository.full_name == env.REPO` stays, and it is not a filter refinement:
# this tree becomes the published npm tarball, and fork `pull_request` runs execute in
# THIS repository's context uploading their own next-build. That clause is the
# supply-chain guard (CodeQL actions/artifact-poisoning).
CANDIDATES=$(gh api "repos/$REPO/actions/runs?head_sha=$HEAD_SHA&per_page=100" \
--jq '[.workflow_runs[]
| select(.name == "CI"
and .head_repository.full_name == env.REPO)]
| sort_by(.run_started_at) | reverse | .[0:5] | .[].id') || CANDIDATES=""
if [ -z "$CANDIDATES" ]; then
echo "::notice::no CI run from this repository for $HEAD_SHA — falling back to a full build"
exit 0
fi
RUN=""
for candidate in $CANDIDATES; do
if gh run download "$candidate" --repo "$REPO" --name next-build --dir /tmp/next-build 2>/dev/null; then
RUN="$candidate"
break
fi
echo " run $candidate carries no usable next-build — trying the next"
done
if [ -z "$RUN" ]; then
echo "::notice::none of the candidate runs still carries next-build (1-day retention) — falling back to a full build"
exit 0
fi
tar -xzf /tmp/next-build/e2e-build.tar.gz -C .
rm -rf /tmp/next-build
if [ -f .build/next/standalone/server.js ]; then
echo "✅ standalone tree restored from CI run $RUN — build:cli will skip next build"
else
echo "::notice::extract did not yield .build/next/standalone — falling back to a full build"
rm -rf .build
fi
- name: Build CLI bundle (standalone app)
if: steps.resolve.outputs.skip != 'true'
env:
@@ -256,18 +181,6 @@ jobs:
if: steps.resolve.outputs.skip != 'true'
run: npm run check:pack-boot
# The boot-smoke above proves a CLEAN install boots. It does not prove the path that
# actually broke us: installing over an existing version, where ~110 SQLite migrations
# run against a populated database. v3.8.48 shipped as a hotfix because the published
# 3.8.47 crashed on boot, and the v3.8.49 upgrade path was first exercised end-to-end
# by hand on a real 3.8.48 box (VPS .16) — after publishing, which is exactly backwards.
# Runs BEFORE `npm stage publish` so a broken upgrade never reaches the registry at all;
# a staged package that is never approved simply expires, with no `npm deprecate` needed.
- name: Prove clean-install AND upgrade-over-previous both boot
if: steps.resolve.outputs.skip != 'true'
timeout-minutes: 30
run: npm run check:install-upgrade
# WS1.3 (D2, v3.8.49 plan): STAGED publishing by default — `npm stage publish`
# parks the exact bytes on the registry WITHOUT making them installable; the
# owner then verifies and approves with 2FA (`npm stage approve`), moving the
@@ -339,20 +252,20 @@ jobs:
echo "✅ Action finished for GitHub Packages"
publish-opencode-plugin:
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
permissions:
contents: read
id-token: write # npm provenance
steps:
- name: Checkout
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@v7
with:
persist-credentials: false
fetch-depth: 0
# Full history needed for auto-bump: git diff against previous release tag
- name: Setup Node.js
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
uses: actions/setup-node@v7
with:
node-version: ${{ env.NPM_PUBLISH_NODE_VERSION }}
registry-url: https://registry.npmjs.org

View File

@@ -26,16 +26,16 @@ defaults:
jobs:
test:
name: Test (Node ${{ matrix.node }})
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
node: ["22", "24"]
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
- uses: actions/setup-node@v7
with:
node-version: ${{ matrix.node }}
cache: npm
@@ -46,13 +46,13 @@ jobs:
build:
name: Build
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
needs: test
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
- uses: actions/setup-node@v7
with:
node-version: "22"
cache: npm

View File

@@ -26,16 +26,16 @@ defaults:
jobs:
test:
name: Test (Node ${{ matrix.node }})
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
node: ["20", "22", "24"]
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
- uses: actions/setup-node@v7
with:
node-version: ${{ matrix.node }}
cache: npm
@@ -45,13 +45,13 @@ jobs:
build:
name: Build
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
needs: test
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
- uses: actions/setup-node@v7
with:
node-version: "20"
cache: npm

View File

@@ -25,17 +25,20 @@ jobs:
# path filters share existence reasons: code / docs / i18n / workflow.
changes:
name: Change Classification
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
outputs:
code: ${{ steps.classify.outputs.code }}
docs: ${{ steps.classify.outputs.docs }}
i18n: ${{ steps.classify.outputs.i18n }}
workflow: ${{ steps.classify.outputs.workflow }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
- id: classify
env:
EVENT_NAME: ${{ github.event_name }}
@@ -54,39 +57,21 @@ jobs:
git diff --name-only "$BASE_SHA" "$HEAD_SHA" > changed-files.txt
node scripts/quality/classify-pr-changes.mjs changed-files.txt >> "$GITHUB_OUTPUT"
build:
name: Build (advisory)
needs: changes
if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
# Fork-safe fallback uses Ubuntu 26.04's bundled Node 24 without setup-node.
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-26.04' }}
# #7307: advisory for the first week of release-PR runs; remove
# continue-on-error after the production-build signal is stable.
continue-on-error: true
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
with:
persist-credentials: false
- run: node -e 'if (process.versions.node.split(".")[0] !== process.env.CI_NODE_VERSION) throw new Error("Expected Node " + process.env.CI_NODE_VERSION)'
- uses: ./.github/actions/npm-ci-retry
- run: npm run check:node-runtime
- run: npm run build
env:
OMNIROUTE_USE_TURBOPACK: "1"
# No artifact upload here: the PR-to-release quality workflow has no
# downstream package/e2e jobs that consume the Next.js build output.
# Docs/OpenAPI contract gates only — existence reason is doc accuracy + route refs.
# Split out of fast-gates so pure-docs PRs skip typecheck/unit while still validating docs.
docs-gates:
name: Docs Gates (fast-path)
needs: changes
if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && (needs.changes.outputs.docs == 'true' || needs.changes.outputs.code == 'true')) }}
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
# One walk of src/app/api for openapi-routes + docs-symbols (both still fail independently).
- run: npm run check:api-docs-refs
@@ -101,21 +86,8 @@ jobs:
# Dynamic runner (same rule as ci.yml): use the self-hosted VPS pool only when the
# release captain has USE_VPS_RUNNER=true AND this is not a fork PR (own-origin
# branches only — a fork PR must never execute on the LAN runner). Var unset/false
# or a fork PR falls back to ubuntu-26.04, so this is inert until the flag flips.
# PINNED to hosted (gap 19). This job carried the USE_VPS_RUNNER expression, and that
# expression was DEAD CONFIGURATION: across 160 quality.yml runs the job never once landed on
# a self-hosted runner — every non-skipped sample is `GitHub Actions NNNN`. The classifier is
# not at fault: in the same window ci.yml's Build demonstrably ran on omniroute-113-7 and
# omniroute-113-6, so self-hosted runs are visible when they happen.
#
# And if it ever HAD fired it would have inherited the measured penalty, because this job's
# first two steps are exactly the bottleneck: actions/setup-node + npm ci took 20m06s on .113
# with 4 concurrent runners versus 16s hosted (npm cache restore saturating the link). Median
# here is 5.6 min hosted across 72 successful runs.
#
# With this pinned, USE_VPS_RUNNER governs ONLY build-like jobs — one variable, one coherent
# purpose. That is what gap 19 asked for; a second variable turned out to be unnecessary.
runs-on: ubuntu-26.04
# or a fork PR falls back to ubuntu-latest, so this is inert until the flag flips.
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-latest' }}
# tsx gates (known-symbols, route-guard-membership) import modules that open
# SQLite on load; provide DB env so a fresh CI DB initializes cleanly.
env:
@@ -123,10 +95,14 @@ jobs:
API_KEY_SECRET: ci-lint-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
fetch-depth: 0
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
- name: Restore ESLint file cache
uses: actions/cache@v6
@@ -165,81 +141,6 @@ jobs:
# Complexity + cognitive-complexity: ONE ESLint walk (both baselines still
# enforced separately by ruleId). Avoids two cold tree walks on fast-path.
- run: npm run check:complexity-ratchets
# ── G0 (trilho .50): gates do trilho A que faltavam no trilho B ──────────────
# The god-file refactor happens in PRs→release/**; without these, the release
# rail never sees a new import cycle, dead code, duplication or a security
# regression until the release PR to main. Deliberately NOT brought here:
# bundle-size (self-skips without a build — this rail's build job is advisory
# and uploads nothing, so it would be dead configuration) and the coverage
# run (fast-unit already runs the full suite; the coverage ratchet stays on
# the main rail via --allow-missing in lint-guard).
- run: npm run check:cycles
- run: npm run check:lockfile
- name: Duplication ratchet
run: npm run check:duplication
- name: Dead-code ratchet (knip)
run: npm run check:dead-code
- name: Type coverage ratchet
run: npm run check:type-coverage
- name: Compression budget ratchet
run: npm run check:compression-budget
# Security scanners — same hardened install as ci.yml quality-extended
# (gh release download = authenticated, 5000 req/hr; curl to api.github.com
# is rate-limited to 60/hr and silently no-ops when throttled). The blocking
# gates below SKIP (exit 0) when their binary is absent — only a measured
# regression vs config/quality/quality-baseline.json blocks.
- name: Install security scanners (gitleaks/osv/actionlint/zizmor/oasdiff)
continue-on-error: true
env:
GH_TOKEN: ${{ github.token }}
run: |
set +e
mkdir -p "$HOME/.local/bin"
# Ratchets compare scanner COUNTS across runs. Pin every auditor: a rule-set
# update must be an explicit PR that re-measures/rebaselines, never a random
# red (or green) caused by whatever "latest" served that morning.
GITLEAKS_VERSION=v8.30.1
OSV_SCANNER_VERSION=v2.3.8
ACTIONLINT_VERSION=v1.7.12
ZIZMOR_VERSION=1.25.2
OASDIFF_VERSION=v1.19.1
# gitleaks — pinned linux x64 tarball via gh (authed), extract binary
rm -rf /tmp/gl && mkdir -p /tmp/gl
gh release download "$GITLEAKS_VERSION" --repo gitleaks/gitleaks --pattern '*linux_x64.tar.gz' --dir /tmp/gl
tar -xzf /tmp/gl/*linux_x64.tar.gz -C "$HOME/.local/bin" gitleaks
# osv-scanner — pinned linux amd64 bare binary via gh (authed)
rm -rf /tmp/osv && mkdir -p /tmp/osv
gh release download "$OSV_SCANNER_VERSION" --repo google/osv-scanner --pattern '*linux_amd64' --dir /tmp/osv
install -m 0755 /tmp/osv/*linux_amd64 "$HOME/.local/bin/osv-scanner"
# actionlint — official installer from a pinned release tag (never main)
bash <(curl -fsSL "https://raw.githubusercontent.com/rhysd/actionlint/${ACTIONLINT_VERSION}/scripts/download-actionlint.bash") "$ACTIONLINT_VERSION" "$HOME/.local/bin"
# zizmor — pinned PyPI package (same version as ci.yml quality-extended)
pipx install "zizmor==$ZIZMOR_VERSION" || pip install --user "zizmor==$ZIZMOR_VERSION"
# oasdiff — pinned linux amd64 tarball via gh (authed), extract binary
rm -rf /tmp/oasd && mkdir -p /tmp/oasd
gh release download "$OASDIFF_VERSION" --repo Tufin/oasdiff --pattern '*linux_amd64.tar.gz' --dir /tmp/oasd
tar -xzf /tmp/oasd/*linux_amd64.tar.gz -C "$HOME/.local/bin" oasdiff
# ALWAYS export the bin dir (even if any step above failed)
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
"$HOME/.local/bin/gitleaks" version || true
"$HOME/.local/bin/actionlint" -version || true
"$HOME/.local/bin/osv-scanner" --version || true
"$HOME/.local/bin/oasdiff" --version || true
zizmor --version || true
- name: Secret scan (gitleaks, ratchet, blocking)
run: npm run check:secrets -- --ratchet
- name: Vulnerability ratchet (osv-scanner, ratchet, blocking)
run: npm run check:vuln-ratchet -- --ratchet
- name: Workflow lint (actionlint+zizmor, ratchet, blocking)
run: npm run check:workflows -- --ratchet
# BASE_REF is read by the script from the env (never interpolated into a
# shell body) — workflow-injection-safe. actions/checkout fetches remote
# refs, not a local branch named github.base_ref, so prefix origin/ or this
# gate self-skips every PR with reason=base-unresolved.
- name: OpenAPI breaking-change (oasdiff, ratchet, blocking)
env:
BASE_REF: ${{ github.base_ref && format('origin/{0}', github.base_ref) || '' }}
run: npm run check:openapi-breaking -- --ratchet
- name: Typecheck (core)
run: npm run typecheck:core
# #7033: dashboard-scoped typecheck gate — src/app/(dashboard) TSX is not
@@ -265,7 +166,7 @@ jobs:
# selector returns __RUN_ALL__ — full-suite authority is the parallel
# `fast-unit` 4-shard job (test:unit:ci:shard; was 2-shard, #6781), NOT an
# unsharded re-run here. Stacking unsharded test:unit:ci on top of fast-unit
# doubled wall time (~16 min extra on the hosted runner) without extra coverage.
# doubled wall time (~16 min extra on ubuntu-latest) without extra coverage.
#
# BLOCKING for the *impacted subset* (flipped 2026-06-17). Fail-safe full
# coverage remains required via `Unit Tests fast-path` (fast-unit).
@@ -329,15 +230,30 @@ jobs:
if-no-files-found: ignore
retention-days: 30
# Share fast-gates' checkout + npm ci instead of spending ~80s preparing a
# separate runner for a ~13s Vitest invocation. !cancelled() preserves the
# independent test signal when an earlier fast gate fails.
- name: Vitest
if: ${{ !cancelled() }}
run: npm run test:vitest -- --reporter=default --reporter=junit --outputFile.junit=trunk-junit/vitest-fastpath.xml
# WS5.2/5.3: JUnit feeds Trunk Flaky Tests — the fast path runs on every PR.
# Advisory upload, own-origin only.
- name: Upload Vitest results to Trunk (advisory)
fast-vitest:
name: Vitest (fast-path)
needs: changes
if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
# Dynamic runner — see fast-gates (own-origin + flag; fork/unset → ubuntu-latest).
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-latest' }}
env:
JWT_SECRET: ci-lint-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-lint-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
# WS5.2/5.3: JUnit feeds Trunk Flaky Tests — the fast-path runs on EVERY PR,
# which is where flaky-detection volume actually comes from (ci.yml's heavy
# jobs only run on the release PR). Advisory upload, own-origin only.
- run: npm run test:vitest -- --reporter=default --reporter=junit --outputFile.junit=trunk-junit/vitest-fastpath.xml
- name: Upload test results to Trunk (advisory)
if: ${{ always() && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository) }}
continue-on-error: true
uses: trunk-io/analytics-uploader@385f1ccdf345b4532dc4b6c665dd432b702b8e28 # v2.1.2
@@ -350,18 +266,12 @@ jobs:
name: Unit Tests fast-path (${{ matrix.shard }}/4)
needs: changes
if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
# Dynamic runner — see fast-gates (own-origin + flag; fork/unset → ubuntu-26.04).
# Dynamic runner — see fast-gates (own-origin + flag; fork/unset → ubuntu-latest).
# This is the heaviest fast-path job; 4-way sharding (was 2, #6781) halves the
# critical path again (~8.5min → ~4.5min hosted; ~2min on the 8-slot
# critical path again (~8.5min → ~4.5min on ubuntu-latest; ~2min on the 8-slot
# runner box). Node's native --test-shard=N/total takes any denominator — only
# this matrix and the TEST_SHARD env below encode the shard count.
# PINNED to hosted, deliberately not on the USE_VPS_RUNNER switch (gap 19). One variable
# governed the build and the test jobs, which want OPPOSITE machines: the build needs the
# .113's RAM, the tests need the hosted runner's link. Measured on 2026-07-29 —
# actions/setup-node took 20m06s on .113 with 4 concurrent runners versus 16s hosted (npm
# cache restore saturating the link), while the tests themselves tied, 2m54 vs 2m31. So
# self-hosted is strictly worse here and there is nothing to configure.
runs-on: ubuntu-26.04
runs-on: ${{ (vars.USE_VPS_RUNNER == 'true' && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository)) && fromJSON('["self-hosted","omni-release"]') || 'ubuntu-latest' }}
strategy:
fail-fast: false
matrix:
@@ -371,9 +281,13 @@ jobs:
API_KEY_SECRET: ci-lint-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
# QW-d: fonte única — o mesmo npm script do CI pesado/local. Fecha dois drifts do
# comando inline antigo: os dirs `memory` e `usage` estavam FORA do glob (testes
@@ -398,18 +312,16 @@ jobs:
name: No new ESLint warnings
needs: changes
if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
continue-on-error: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.repo.fork == true }}
# G0 (trilho .50): security-events:read lets the CodeQL ratchet below read open
# code-scanning alerts via `gh api .../code-scanning/alerts` (same as ci.yml's
# quality-gate job). contents: read keeps checkout working.
permissions:
contents: read
security-events: read
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
- name: Restore ESLint file cache
uses: actions/cache@v6
@@ -423,29 +335,6 @@ jobs:
- name: ESLint (baseline congelado — warning novo = vermelho)
# lint:json writes the report; --max-warnings 0 keeps no-new-warnings policy.
run: npm run lint:json -- --max-warnings 0
# ── G0 (trilho .50): motor de ratchet também no trilho B ─────────────────────
# This job just wrote .artifacts/eslint-results.json — collect-metrics prefers
# that file, so the ratchet engine lands here at ZERO extra ESLint cost (one
# inventory, two consumers; same reason ci.yml chains lint → quality-gate).
# The coverage-report artifact does not exist on this rail, so both ratchet
# invocations run --allow-missing: coverage.* metrics skip gracefully while
# the deterministic ones (eslint / openapi-coverage / i18n-ui) stay BLOCKING.
# Coverage authority remains on the main rail (ci.yml test-coverage → quality-gate).
- run: npm run quality:collect
- name: Ratchet check (blocking)
run: node scripts/quality/check-quality-ratchet.mjs --allow-missing --summary .artifacts/quality-ratchet.md
- name: Require-tighten (blocking)
run: node scripts/quality/check-quality-ratchet.mjs --allow-missing --require-tighten
# CodeQL alerts ratchet — same semantics as ci.yml quality-gate: exits 1 ONLY
# on a real regression (open alerts > baseline in quality-baseline.json);
# a measurement failure (gh/auth/api) self-skips with exit 0.
- name: CodeQL alerts ratchet (blocking)
run: npm run check:codeql-ratchet
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Append ratchet summary
if: always()
run: cat .artifacts/quality-ratchet.md >> "$GITHUB_STEP_SUMMARY" || true
# Merge-integrity: pega no PR os dois vazamentos crônicos de merge que hoje só
# explodem na release-PR. (1) CHANGELOG-eat — o auto-resolve do merge come
@@ -462,17 +351,21 @@ jobs:
name: Merge integrity (changelog + generated skills)
# Always on non-draft PRs — CHANGELOG/skills can break on docs-only merges too.
if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) }}
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
continue-on-error: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.repo.fork == true }}
env:
JWT_SECRET: ci-lint-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-lint-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
with:
fetch-depth: 0
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
- name: CHANGELOG integrity (nenhum bullet da base pode sumir no merge-result)
run: npm run check:changelog-integrity

View File

@@ -11,7 +11,7 @@ permissions: read-all
jobs:
analysis:
name: Scorecard analysis
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
permissions:
# security-events: write removed — Scorecard findings are advisory and no longer
# uploaded to the code-scanning Security tab (they are supply-chain/posture scores,
@@ -21,7 +21,7 @@ jobs:
contents: read
steps:
- name: Checkout
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@v7
with:
persist-credentials: false

View File

@@ -14,11 +14,11 @@ concurrency:
cancel-in-progress: true
jobs:
semgrep:
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
container:
image: semgrep/semgrep
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
with:
persist-credentials: false
- name: Run semgrep (advisory)

View File

@@ -34,10 +34,15 @@ concurrency:
jobs:
sync-wiki:
name: Sync wiki with docs
runs-on: ubuntu-26.04
runs-on: ubuntu-latest
steps:
- name: Checkout repo
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
uses: actions/checkout@v7
- name: Setup Node
uses: actions/setup-node@v7
with:
node-version: "24"
- name: Clone wiki
env:

12
.gitignore vendored
View File

@@ -72,7 +72,6 @@ yarn-error.log*
# env files (can opt-in for committing if needed)
.env*
!.env.example
!.env.devin-bridge.example
!.env.homolog.example
# Provider API keys (never commit)
*.api-key
@@ -172,6 +171,7 @@ config/quality/test-impact-map.json
# GitNexus local index
.gitnexus
.worktrees
bin/omniroute.mjs
# Consistent with .dockerignore / .npmignore
.omc/
@@ -201,17 +201,12 @@ scripts/i18n/_pending-keys.json
.codegraph/
# Fumadocs generated source
/.source/
# Temporary local worktrees used to build unpublished npm tarballs
/.deploy-build-*/
.source/
# AI agent local settings and configs
.agents/
.antigravitycli/
.claude/
!tests/fixtures/devin-bridge/e2e-workspace/.claude/
!tests/fixtures/devin-bridge/e2e-workspace/.claude/**
# PR Reviews and local feedback files
pr_reviews*.json
@@ -248,8 +243,6 @@ _artifacts/ # release-green artifacts
# CI/local quality artifacts (eslint-results.json, quality-ratchet.md, etc.)
.artifacts/
# Isolated Devin bridge workspaces, evidence, and test databases
.sandbox/
# Homologation E2E suite (npm run homolog) — real-environment credentials + report output
.env.homolog
@@ -257,4 +250,3 @@ tests/homolog/.auth/
tests/homolog/ui/.auth/
homolog-report/
docker-compose.yml.bak
.playwright-cli/

View File

@@ -86,10 +86,4 @@
regexes = [
'''latencyP\d{2}Ms''',
'''interleaved-thinking-2025-05-14''',
# v3.8.49 pre-flight (2026-07-28). Nenhum dos dois e credencial:
# - chave de localStorage do banner de patrocinio (#8723), so um identificador de UI;
# - x-api-key PUBLICO do Firefly web (documentado em open-sse/utils/publicCreds.ts:207);
# as duas ocorrencias sinalizadas estao em COMENTARIOS JSDoc, o runtime le de resolvePublicCred().
'''omniroute-kimi-sponsor-banner-dismissed-v1''',
'''SunbreakWebUI1''',
]

8
.source/dynamic.ts Normal file
View File

@@ -0,0 +1,8 @@
// @ts-nocheck
import { dynamic } from 'fumadocs-mdx/runtime/dynamic';
import * as Config from '../source.config';
const create = await dynamic<typeof Config, import("fumadocs-mdx/runtime/types").InternalTypeConfig & {
DocData: {
}
}>(Config, {"configPath":"source.config.ts","environment":"next","outDir":".source"}, {"doc":{"passthroughs":["extractedReferences"]}});

22
.source/source.config.mjs Normal file
View File

@@ -0,0 +1,22 @@
// source.config.ts
import { defineDocs, defineConfig } from "fumadocs-mdx/config";
var docs = defineDocs({
dir: "docs",
docs: {
files: [
"./architecture/**/*.md",
"./guides/**/*.md",
"./reference/**/*.md",
"./frameworks/**/*.md",
"./routing/**/*.md",
"./security/**/*.md",
"./compression/**/*.md",
"./ops/**/*.md"
]
}
});
var source_config_default = defineConfig();
export {
source_config_default as default,
docs
};

View File

@@ -1,12 +1,12 @@
{
"name": "@omniroute/opencode-plugin",
"version": "0.2.1",
"version": "0.2.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "@omniroute/opencode-plugin",
"version": "0.2.1",
"version": "0.2.0",
"license": "MIT",
"dependencies": {
"zod": "^4.4.3"

View File

@@ -23,7 +23,7 @@
"scripts": {
"build": "tsup",
"clean": "rm -rf dist",
"test": "node --import tsx/esm --test tests/scaffold.test.ts tests/auth.test.ts tests/options-schema.test.ts tests/multi-instance.test.ts tests/fetch-interceptor.test.ts tests/provider.test.ts tests/gemini-sanitize.test.ts tests/combos.test.ts tests/config-shim.test.ts tests/features.test.ts tests/feature-defaults.test.ts tests/usable-combo.test.ts tests/disk-snapshot-perms.test.ts tests/fork-features.test.ts tests/auto-combo-context.test.ts tests/provider-id-routing.test.ts tests/management-read-token.test.ts tests/auto-sync.test.ts",
"test": "node --import tsx/esm --test tests/scaffold.test.ts tests/auth.test.ts tests/options-schema.test.ts tests/multi-instance.test.ts tests/fetch-interceptor.test.ts tests/provider.test.ts tests/gemini-sanitize.test.ts tests/combos.test.ts tests/config-shim.test.ts tests/features.test.ts tests/usable-combo.test.ts tests/disk-snapshot-perms.test.ts tests/fork-features.test.ts tests/auto-combo-context.test.ts tests/provider-id-routing.test.ts tests/management-read-token.test.ts tests/auto-sync.test.ts",
"prepublishOnly": "npm run clean && npm run build && npm test"
},
"keywords": [

View File

@@ -216,59 +216,6 @@ const optionsSchema = z
*/
export type OmniRoutePluginOptions = z.infer<typeof optionsSchema>;
/**
* Explicit default state for every boolean `features.*` toggle.
*
* #7624: `featuresSchema` marks every flag `.optional()` with no default, and
* the effective value is applied implicitly at each read site (default-ON flags
* use the `features.X !== false` convention, default-OFF flags use
* `features.X === true`). That implicit convention is scattered across the file,
* so an operator who omits the `features` block cannot tell whether
* combos / autoCombos / enrichment are enabled — they think features are
* disabled when they are actually on. Centralising the declared defaults here
* (mirroring the read-site conventions exactly, so runtime behaviour is
* unchanged) makes the effective flags introspectable and self-documenting.
*/
export const OMNIROUTE_FEATURE_DEFAULTS = {
// default-ON (read sites use `features.X !== false`)
combos: true,
autoCombos: true,
enrichment: true,
diskCache: true,
providerTag: true,
fetchInterceptor: true,
geminiSanitization: true,
// default-OFF (read sites use `features.X === true`)
compressionMetadata: false,
usableOnly: false,
mcpAutoEmit: false,
debugLog: false,
startupDebug: false,
} as const;
/** Union of the boolean feature-flag keys declared in `OMNIROUTE_FEATURE_DEFAULTS`. */
export type OmniRouteFeatureFlag = keyof typeof OMNIROUTE_FEATURE_DEFAULTS;
/**
* Resolve the EFFECTIVE boolean state of every feature toggle, applying the
* declared default for any flag the operator omitted. A missing `features`
* block (or an empty one) yields the full default set — so callers and the
* startup diagnostics can surface exactly which features are active instead of
* relying on the implicit `!== false` / `=== true` conventions. Purely
* derived: it does not mutate options nor change any read-site behaviour.
*/
export function resolveEffectiveFeatureFlags(
features?: OmniRoutePluginOptions["features"]
): Record<OmniRouteFeatureFlag, boolean> {
const f: Partial<Record<OmniRouteFeatureFlag, boolean>> = features ?? {};
const out = {} as Record<OmniRouteFeatureFlag, boolean>;
for (const key of Object.keys(OMNIROUTE_FEATURE_DEFAULTS) as OmniRouteFeatureFlag[]) {
const val = f[key];
out[key] = typeof val === "boolean" ? val : OMNIROUTE_FEATURE_DEFAULTS[key];
}
return out;
}
export const OMNIROUTE_PROVIDER_KEY = "omniroute" as const;
/** Deployed plugin version (injected at build time by tsup define). */
@@ -2053,7 +2000,6 @@ async function writeStartupDiagnostics(params: {
autoComboCount: number;
enrichment: OmniRouteEnrichmentMap;
autoCombos: OmniRouteRawAutoCombo[];
features?: OmniRoutePluginOptions["features"];
}): Promise<void> {
const {
providerId,
@@ -2064,7 +2010,6 @@ async function writeStartupDiagnostics(params: {
autoComboCount,
enrichment,
autoCombos,
features,
} = params;
const enriched = [...enrichment.entries()];
const withName = enriched.filter(([, e]) => e.name);
@@ -2077,16 +2022,6 @@ async function writeStartupDiagnostics(params: {
lines.push(
`models=${modelCount} combos=${comboCount} enrichment=${enrichmentSize} autoCombos=${autoComboCount}`
);
// #7624: surface the EFFECTIVE feature flags so an operator who omitted the
// `features` block can see combos/autoCombos/enrichment are on (the counts
// above can read 0 for reasons unrelated to the flags — e.g. missing auth).
const effectiveFlags = resolveEffectiveFeatureFlags(features);
lines.push(
`features(effective): ` +
(Object.keys(effectiveFlags) as OmniRouteFeatureFlag[])
.map((k) => `${k}=${effectiveFlags[k] ? "on" : "off"}`)
.join(" ")
);
lines.push(
`enrichment: ${withName.length} with name, ${withPricing.length} with pricing, ${withFree.length} free`
);
@@ -3195,7 +3130,6 @@ export function createOmniRouteProviderHook(
autoComboCount: rawAutoCombos.length,
enrichment: rawEnrichment,
autoCombos: rawAutoCombos,
features: resolved.features,
});
}
}
@@ -5274,7 +5208,6 @@ export function createOmniRouteConfigHook(
autoComboCount: rawAutoCombos.length,
enrichment: rawEnrichment,
autoCombos: rawAutoCombos,
features: resolved.features,
});
}

View File

@@ -1,95 +0,0 @@
/**
* #7624 — explicit feature-flag defaults.
*
* The `features` block in opencode.json marks every toggle `.optional()` with
* no default. The effective value was previously only knowable by tracing the
* implicit `features.X !== false` (default-ON) / `features.X === true`
* (default-OFF) convention scattered across each read site, which left
* operators unsure whether combos / autoCombos / enrichment were enabled when
* they omitted the block.
*
* `OMNIROUTE_FEATURE_DEFAULTS` declares those defaults explicitly and
* `resolveEffectiveFeatureFlags(features)` derives the effective state for any
* (possibly-undefined) features object, mirroring the read-site conventions
* exactly. These are purely derived — runtime routing behaviour is unchanged.
*/
import test from "node:test";
import assert from "node:assert/strict";
import {
OMNIROUTE_FEATURE_DEFAULTS,
resolveEffectiveFeatureFlags,
} from "../src/index.js";
const DEFAULT_ON = [
"combos",
"autoCombos",
"enrichment",
"diskCache",
"providerTag",
"fetchInterceptor",
"geminiSanitization",
] as const;
const DEFAULT_OFF = [
"compressionMetadata",
"usableOnly",
"mcpAutoEmit",
"debugLog",
"startupDebug",
] as const;
test("OMNIROUTE_FEATURE_DEFAULTS: declares each flag with its documented default", () => {
for (const key of DEFAULT_ON) {
assert.equal(OMNIROUTE_FEATURE_DEFAULTS[key], true, `${key} defaults ON`);
}
for (const key of DEFAULT_OFF) {
assert.equal(OMNIROUTE_FEATURE_DEFAULTS[key], false, `${key} defaults OFF`);
}
});
test("resolveEffectiveFeatureFlags: undefined features → full declared default set", () => {
const flags = resolveEffectiveFeatureFlags(undefined);
for (const key of DEFAULT_ON) {
assert.equal(flags[key], true, `${key} effective ON when features omitted`);
}
for (const key of DEFAULT_OFF) {
assert.equal(flags[key], false, `${key} effective OFF when features omitted`);
}
});
test("resolveEffectiveFeatureFlags: empty features object → same as omitted", () => {
assert.deepEqual(
resolveEffectiveFeatureFlags({}),
resolveEffectiveFeatureFlags(undefined)
);
});
test("resolveEffectiveFeatureFlags: explicit false disables a default-ON flag", () => {
const flags = resolveEffectiveFeatureFlags({ autoCombos: false });
assert.equal(flags.autoCombos, false, "explicit autoCombos:false honoured");
// Untouched flags keep their declared defaults.
assert.equal(flags.combos, true);
assert.equal(flags.enrichment, true);
});
test("resolveEffectiveFeatureFlags: explicit true enables a default-OFF flag", () => {
const flags = resolveEffectiveFeatureFlags({ compressionMetadata: true });
assert.equal(flags.compressionMetadata, true, "explicit compressionMetadata:true honoured");
assert.equal(flags.usableOnly, false, "other opt-in flags stay OFF");
});
test("resolveEffectiveFeatureFlags: non-boolean sibling keys do not leak into flags", () => {
// features may also carry mcpToken/logLevel/apiFormat — the resolver must
// only ever return the boolean toggle keys.
const flags = resolveEffectiveFeatureFlags({
mcpAutoEmit: true,
mcpToken: "sk-mcp-token-abc",
logLevel: "debug",
});
assert.equal(flags.mcpAutoEmit, true);
assert.equal(Object.keys(flags).length, Object.keys(OMNIROUTE_FEATURE_DEFAULTS).length);
assert.equal("mcpToken" in flags, false);
assert.equal("logLevel" in flags, false);
});

View File

@@ -1,5 +0,0 @@
node_modules
dist
*.log
.DS_Store
.env

View File

@@ -1,21 +0,0 @@
MIT License
Copyright (c) 2026 OmniRoute contributors
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

View File

@@ -1,118 +0,0 @@
# @omniroute/openhands-plugin
OpenHands integration for the **OmniRoute AI Gateway**. Generates the OpenHands
environment and Docker config that wires an OpenHands agent-server to a running
OmniRoute instance — with the integration gotchas already handled.
## Why
Running OpenHands against OmniRoute directly hits several wall:
1. **Model name mismatch** — OpenHands sends `model: "deepseek-chat"`, OmniRoute
uses provider-prefixed IDs (`ds/deepseek-v4-flash`) or combos.
2. **Python 3.13 sandbox**`socket.socketpair()` fails under Docker's default
seccomp profile; the agent-server needs `privileged: true`.
3. **Host reachability** — the sandbox can't resolve `localhost` to the OmniRoute
host; needs `host.docker.internal:host-gateway`.
4. **Lost state** — conversations die with the container unless
`OH_PERSISTENCE_DIR` is a host volume.
5. **CORS** — the dashboard origin can't reach agent-server unless
`PERMITTED_CORS_ORIGINS` allows it.
This plugin encodes all of that into one command.
## Install
```bash
npm install -g @omniroute/openhands-plugin
# or: npx @omniroute/openhands-plugin ...
```
## Quick start
Generate the OpenHands `.env`:
```bash
omniroute-openhands env \
--api-key sk-... \
--model deepseek-chat \
--url http://192.168.3.106:20128
```
Generate a `docker-compose.yml` service:
```bash
omniroute-openhands compose \
--api-key sk-... \
--model glm-5.2 \
--persistence-dir /Users/me/.openhands-state \
--cors-origins http://100.73.44.17:3000
```
Or a plain `docker run`:
```bash
omniroute-openhands docker-run \
--api-key sk-... \
--model vivanta-core \
--persistence-dir /Users/me/.openhands-state
```
## Commands
| Command | Description |
|---------|-------------|
| `env` | Print OpenHands `.env` contents |
| `compose` | Print a Docker Compose service block |
| `docker-run` | Print a full `docker run` command |
| `models` | Print the default OpenHands → OmniRoute model map |
### Common options
| Flag | Description | Default |
|------|-------------|---------|
| `--api-key` | OmniRoute API key (`sk-...`) | — |
| `--model` | OpenHands model name or OmniRoute combo | — |
| `--url` | OmniRoute base URL | `http://localhost:20128` |
| `--persistence-dir` | Host dir for conversation state | `.openhands-state` |
| `--cors-origins` | Comma-separated allowed origins | `localhost:3000,3001` |
| `--sandbox-image` | OpenHands sandbox base image | — |
## Model mapping
OpenHands-friendly names are mapped to OmniRoute IDs/combo names:
| OpenHands sends | OmniRoute resolves to |
|-----------------|----------------------|
| `deepseek-chat` | `ds/deepseek-v4-flash` |
| `deepseek-reasoner` | `ds/deepseek-v4-pro` |
| `glm-5.2` | `nvidia/z-ai/glm-5.2` |
| `gpt-4o` | `openai/gpt-4o` |
| `claude-sonnet-4.5` | `anthropic/claude-sonnet-4.5` |
| ... | ... |
Or just pass an OmniRoute combo name (e.g. `--model vivanta-core`) — the Model
Alias Resolver and combo router accept it directly.
## Library usage
```ts
import {
buildOpenHandsEnv,
serializeOpenHandsEnv,
buildOpenHandsCompose,
resolveOpenHandsModel,
} from "@omniroute/openhands-plugin";
const env = buildOpenHandsEnv({
apiKey: "sk-...",
model: resolveOpenHandsModel("deepseek-chat"),
omnirouteUrl: "http://localhost:20128",
persistenceDir: "/Users/me/.openhands-state",
});
console.log(serializeOpenHandsEnv(env));
```
## License
MIT — same as OmniRoute.

File diff suppressed because it is too large Load Diff

View File

@@ -1,79 +0,0 @@
{
"name": "@omniroute/openhands-plugin",
"version": "0.1.0",
"description": "OpenHands integration for the OmniRoute AI Gateway. Generates OpenHands env + Docker Compose config (model mapping, sandbox, CORS, persistence) so OpenHands agents talk to OmniRoute out of the box.",
"type": "module",
"main": "./dist/index.js",
"types": "./dist/index.d.ts",
"bin": {
"omniroute-openhands": "./dist/cli.js"
},
"exports": {
".": {
"types": "./dist/index.d.ts",
"import": "./dist/index.js"
},
"./env": {
"types": "./dist/env.d.ts",
"import": "./dist/env.js"
},
"./docker": {
"types": "./dist/docker.d.ts",
"import": "./dist/docker.js"
},
"./model-map": {
"types": "./dist/model-map.d.ts",
"import": "./dist/model-map.js"
}
},
"files": [
"dist",
"README.md",
"LICENSE"
],
"scripts": {
"build": "tsup",
"clean": "rm -rf dist",
"test": "node --import tsx/esm --test tests/env.test.ts tests/model-map.test.ts tests/docker.test.ts",
"prepublishOnly": "npm run clean && npm run build && npm test"
},
"keywords": [
"omniroute",
"openhands",
"open-hands",
"openhands-plugin",
"openai-compatible",
"docker",
"agent"
],
"author": "OmniRoute contributors",
"license": "MIT",
"repository": {
"type": "git",
"url": "https://github.com/diegosouzapw/OmniRoute.git",
"directory": "@omniroute/openhands-plugin"
},
"bugs": {
"url": "https://github.com/diegosouzapw/OmniRoute/issues"
},
"homepage": "https://github.com/diegosouzapw/OmniRoute/tree/main/%40omniroute/openhands-plugin#readme",
"engines": {
"node": ">=18.0.0"
},
"peerDependencies": {
"@omniroute/open-sse": "*"
},
"peerDependenciesMeta": {
"@omniroute/open-sse": {
"optional": true
}
},
"publishConfig": {
"access": "public"
},
"devDependencies": {
"@types/node": "^22.19.19",
"tsup": "^8.5.1",
"tsx": "^4.22.3"
}
}

View File

@@ -1,104 +0,0 @@
#!/usr/bin/env node
/**
* @omniroute/openhands-plugin CLI — generate OpenHands .env / Docker config
* for a running OmniRoute instance.
*
* Usage:
* omniroute-openhands env --api-key sk-... --model deepseek-chat [--url http://localhost:20128]
* omniroute-openhands compose --api-key sk-... --model deepseek-chat [--persistence-dir /path]
* omniroute-openhands docker-run --api-key sk-... --model deepseek-chat
* omniroute-openhands models (print the default model map)
*/
import { buildOpenHandsEnv, serializeOpenHandsEnv } from "./env.ts";
import { buildOpenHandsCompose, buildOpenHandsDockerRun } from "./docker.ts";
import { DEFAULT_OPENHANDS_MODEL_MAP } from "./model-map.ts";
function parseArgs(argv: string[]): Record<string, string> {
const out: Record<string, string> = {};
for (let i = 0; i < argv.length; i++) {
const arg = argv[i];
if (!arg.startsWith("--")) continue;
const key = arg.slice(2);
const next = argv[i + 1];
if (next !== undefined && !next.startsWith("--")) {
out[key] = next;
i++;
} else {
out[key] = "true";
}
}
return out;
}
function requireArgs(args: Record<string, string>, names: string[]): void {
for (const name of names) {
if (!args[name]) {
console.error(`Missing required --${name}`);
process.exit(2);
}
}
}
const [cmd, ...rest] = process.argv.slice(2);
const args = parseArgs(rest);
switch (cmd) {
case "env": {
requireArgs(args, ["api-key", "model"]);
const env = buildOpenHandsEnv({
apiKey: args["api-key"],
model: args.model,
omnirouteUrl: args.url,
persistenceDir: args["persistence-dir"],
corsOrigins: args["cors-origins"]?.split(","),
});
process.stdout.write(serializeOpenHandsEnv(env));
break;
}
case "compose": {
requireArgs(args, ["api-key", "model"]);
process.stdout.write(
buildOpenHandsCompose({
apiKey: args["api-key"],
model: args.model,
omnirouteUrl: args.url,
persistenceDir: args["persistence-dir"] ?? ".openhands-state",
corsOrigins: args["cors-origins"]?.split(","),
sandboxBaseImage: args["sandbox-image"],
})
);
break;
}
case "docker-run": {
requireArgs(args, ["api-key", "model"]);
process.stdout.write(
buildOpenHandsDockerRun({
apiKey: args["api-key"],
model: args.model,
omnirouteUrl: args.url,
persistenceDir: args["persistence-dir"] ?? ".openhands-state",
corsOrigins: args["cors-origins"]?.split(","),
sandboxBaseImage: args["sandbox-image"],
})
);
break;
}
case "models": {
for (const [name, target] of Object.entries(DEFAULT_OPENHANDS_MODEL_MAP)) {
process.stdout.write(`${name}\t->\t${target}\n`);
}
break;
}
default:
console.error(
"Usage: omniroute-openhands <env|compose|docker-run|models> [options]\n" +
"Options:\n" +
" --api-key <sk-...> OmniRoute API key (required for env/compose/docker-run)\n" +
" --model <name> OpenHands model name or OmniRoute combo\n" +
" --url <base> OmniRoute URL (default http://localhost:20128)\n" +
" --persistence-dir <path> Host dir for conversation state\n" +
" --cors-origins <a,b,...> Allowed CORS origins\n" +
" --sandbox-image <image> OpenHands sandbox base image"
);
process.exit(1);
}

View File

@@ -1,92 +0,0 @@
/**
* OpenHands agent-server Docker Compose generator for OmniRoute.
*
* Bakes in the integration fixes that were needed to run OpenHands against
* OmniRoute reliably:
* - `privileged: true` — Python 3.13 socket.socketpair() needs it under
* Docker's default seccomp profile
* - `extra_hosts` — host.docker.internal → host-gateway so the
* sandbox can reach OmniRoute on the host
* - host volume for OH_PERSISTENCE_DIR so conversations survive `docker rm`
* - PERMITTED_CORS_ORIGINS — allow the dashboard origin to hit agent-server
*/
export interface OpenHandsDockerOptions {
/** Agent-server image (default: the official OpenHands runtime image). */
image?: string;
/** Container name (default: openhands-agent). */
containerName?: string;
/** Model name to pass via LLM_MODEL. */
model: string;
/** OmniRoute API key. */
apiKey: string;
/** OmniRoute base URL reachable from the sandbox (default http://localhost:20128). */
omnirouteUrl?: string;
/** Host directory for OH_PERSISTENCE_DIR (must match env.ts persistenceDir). */
persistenceDir: string;
/** CORS origins to permit. */
corsOrigins?: string[];
/** Sandbox base image (defaults to OpenHands default). */
sandboxBaseImage?: string;
/** Set true to use host networking instead of extra_hosts. */
hostNetwork?: boolean;
}
export function buildOpenHandsCompose(opts: OpenHandsDockerOptions): string {
const image = opts.image ?? "docker.all-hands.dev/all-hands-ai/openhands:latest";
const containerName = opts.containerName ?? "openhands-agent";
const omnirouteHost = (opts.omnirouteUrl ?? "http://localhost:20128").replace(/\/+$/, "");
const cors =
opts.corsOrigins && opts.corsOrigins.length > 0
? opts.corsOrigins
: ["http://localhost:3000", "http://localhost:3001"];
const lines: string[] = [];
lines.push(`services:`);
lines.push(` openhands:`);
lines.push(` image: ${image}`);
lines.push(` container_name: ${containerName}`);
lines.push(` privileged: true`);
lines.push(` environment:`);
lines.push(` LLM_MODEL: "${opts.model}"`);
lines.push(` LLM_BASE_URL: "${omnirouteHost}/v1"`);
lines.push(` LLM_API_KEY: "${opts.apiKey}"`);
lines.push(` OH_PERSISTENCE_DIR: "/opt/.openhands-state"`);
lines.push(` PERMITTED_CORS_ORIGINS: "${cors.join(",")}"`);
if (opts.sandboxBaseImage) {
lines.push(` SANDBOX_BASE_IMAGE: "${opts.sandboxBaseImage}"`);
}
lines.push(` volumes:`);
lines.push(` - ${opts.persistenceDir}:/opt/.openhands-state`);
lines.push(` extra_hosts:`);
lines.push(` - "host.docker.internal:host-gateway"`);
return lines.join("\n") + "\n";
}
/**
* docker run equivalent of {@link buildOpenHandsCompose} — returns the full
* `docker run` command line.
*/
export function buildOpenHandsDockerRun(opts: OpenHandsDockerOptions): string {
const image = opts.image ?? "docker.all-hands.dev/all-hands-ai/openhands:latest";
const omnirouteHost = (opts.omnirouteUrl ?? "http://localhost:20128").replace(/\/+$/, "");
const cors =
opts.corsOrigins && opts.corsOrigins.length > 0
? opts.corsOrigins
: ["http://localhost:3000", "http://localhost:3001"];
const parts = [
"docker run",
"--privileged",
"--add-host host.docker.internal:host-gateway",
`-e LLM_MODEL="${opts.model}"`,
`-e LLM_BASE_URL="${omnirouteHost}/v1"`,
`-e LLM_API_KEY="${opts.apiKey}"`,
`-e OH_PERSISTENCE_DIR=/opt/.openhands-state`,
`-e PERMITTED_CORS_ORIGINS="${cors.join(",")}"`,
`-v "${opts.persistenceDir}:/opt/.openhands-state"`,
image,
];
return parts.join(" ") + "\n";
}

View File

@@ -1,63 +0,0 @@
/**
* OpenHands `.env` generator for the OmniRoute AI Gateway.
*
* Produces the OpenHands environment that points an OpenHands agent-server at
* a running OmniRoute instance and fixes the integration gotchas found in the
* field:
* - LLM_MODEL — OpenHands-friendly model name → OmniRoute model/combo
* - LLM_BASE_URL — OmniRoute OpenAI-compatible endpoint
* - LLM_API_KEY — OmniRoute key (sk-...)
* - OH_PERSISTENCE_DIR — host-mounted SQLite/conversation persistence
* - PERMITTED_CORS_ORIGINS — allow the dashboard origin to reach agent-server
*/
export interface OpenHandsEnvOptions {
/** OmniRoute base URL as seen from the agent-server (default localhost:20128). */
omnirouteUrl?: string;
/** OmniRoute API key (sk-...). */
apiKey: string;
/** OpenHands model name (e.g. "deepseek-chat") or OmniRoute combo/model. */
model: string;
/** Host directory for OH_PERSISTENCE_DIR (default: current dir + .openhands-state). */
persistenceDir?: string;
/** CORS origins that must reach the agent-server (default dashboard origin + localhost). */
corsOrigins?: string[];
/** Optional OpenHands sandbox base image. */
sandboxBaseImage?: string;
}
export function buildOpenHandsEnv(opts: OpenHandsEnvOptions): Record<string, string> {
const omnirouteHost = (opts.omnirouteUrl ?? "http://localhost:20128").replace(/\/+$/, "");
const persistence = opts.persistenceDir ?? `${process.cwd()}/.openhands-state`;
const cors =
opts.corsOrigins && opts.corsOrigins.length > 0
? opts.corsOrigins
: ["http://localhost:3000", "http://localhost:3001"];
const env: Record<string, string> = {
LLM_MODEL: opts.model,
LLM_BASE_URL: `${omnirouteHost}/v1`,
LLM_API_KEY: opts.apiKey,
OH_PERSISTENCE_DIR: persistence,
PERMITTED_CORS_ORIGINS: cors.join(","),
};
if (opts.sandboxBaseImage) {
env.SANDBOX_BASE_IMAGE = opts.sandboxBaseImage;
}
return env;
}
/**
* Serialize the env record to `.env` file content (KEY=VALUE lines).
* Values are not quoted unless they contain whitespace or `#`.
*/
export function serializeOpenHandsEnv(env: Record<string, string>): string {
const lines: string[] = [];
for (const [key, value] of Object.entries(env)) {
const needsQuotes = /[\s#]/.test(value);
lines.push(needsQuotes ? `${key}="${value}"` : `${key}=${value}`);
}
return lines.join("\n") + "\n";
}

View File

@@ -1,18 +0,0 @@
/**
* @omniroute/openhands-plugin — OpenHands integration for the OmniRoute AI Gateway.
*
* Generates the OpenHands environment and Docker Compose / docker run config
* that wires an OpenHands agent-server to a running OmniRoute instance:
* model mapping, sandbox privileges, host-gateway networking, persistent
* conversation state and CORS.
*/
export { buildOpenHandsEnv, serializeOpenHandsEnv } from "./env.ts";
export type { OpenHandsEnvOptions } from "./env.ts";
export { buildOpenHandsCompose, buildOpenHandsDockerRun } from "./docker.ts";
export type { OpenHandsDockerOptions } from "./docker.ts";
export {
DEFAULT_OPENHANDS_MODEL_MAP,
resolveOpenHandsModel,
buildOpenHandsModel,
} from "./model-map.ts";
export type { OpenHandsModelMap } from "./model-map.ts";

View File

@@ -1,64 +0,0 @@
/**
* OpenHands → OmniRoute model mapping.
*
* OpenHands sends `model: "<LLM_MODEL>"` and expects the OpenAI-compatible
* endpoint to accept that exact string. OmniRoute uses provider-prefixed
* model IDs (`ds/deepseek-v4-flash`) and combo names. This module maps
* common OpenHands-friendly names to the OmniRoute model/combo they should
* resolve to, and back-fills the `LLM_MODEL` value for OpenHands.
*/
export interface OpenHandsModelMap {
/** OpenHands-friendly model name (e.g. "deepseek-chat") */
[openHandsName: string]: string;
}
/**
* Default mapping for the model names OpenHands and the broader ecosystem
* commonly send. Values are OmniRoute model IDs or combo names. Extend or
* override via {@link resolveOpenHandsModel}.
*/
export const DEFAULT_OPENHANDS_MODEL_MAP: OpenHandsModelMap = Object.freeze({
// DeepSeek
"deepseek-chat": "ds/deepseek-v4-flash",
"deepseek-reasoner": "ds/deepseek-v4-pro",
// Claude / Anthropic
"claude-sonnet-4.5": "anthropic/claude-sonnet-4.5",
"claude-opus-4.1": "anthropic/claude-opus-4.1",
"claude-haiku-4.5": "anthropic/claude-haiku-4.5",
// GPT / OpenAI
"gpt-4o": "openai/gpt-4o",
"gpt-4o-mini": "openai/gpt-4o-mini",
"gpt-5": "openai/gpt-5",
// Gemini
"gemini-2.5-flash": "gemini/gemini-2.5-flash",
"gemini-2.5-pro": "gemini/gemini-2.5-pro",
// GLM / Z.AI (NVIDIA NIM free endpoint)
"glm-5.2": "nvidia/z-ai/glm-5.2",
});
/**
* Resolve the OmniRoute model ID for an OpenHands-friendly model name.
* Returns the input unchanged when no mapping exists (OmniRoute will try to
* resolve it as a literal model/combo).
*/
export function resolveOpenHandsModel(
openHandsModel: string,
map: OpenHandsModelMap = DEFAULT_OPENHANDS_MODEL_MAP
): string {
if (!openHandsModel) return openHandsModel;
const mapped = map[openHandsModel];
return mapped ?? openHandsModel;
}
/**
* Build the `LLM_MODEL` value for OpenHands from an OmniRoute model ID/combo.
*
* OpenHands only surfaces the literal `LLM_MODEL` string in its UI, so for
* OmniRoute combos (e.g. "vivanta-core") that's already the right value.
* For provider-prefixed IDs, we return them as-is — the OmniRoute Model
* Alias Resolver accepts both the raw ID and aliases on the `/v1` endpoint.
*/
export function buildOpenHandsModel(omnirouteModelOrCombo: string): string {
return omnirouteModelOrCombo;
}

View File

@@ -1,76 +0,0 @@
import test from "node:test";
import assert from "node:assert/strict";
import { buildOpenHandsEnv, serializeOpenHandsEnv } from "../src/env.ts";
import { resolveOpenHandsModel, buildOpenHandsModel } from "../src/model-map.ts";
import { buildOpenHandsCompose, buildOpenHandsDockerRun } from "../src/docker.ts";
test("buildOpenHandsEnv produces LLM vars pointing at OmniRoute", () => {
const env = buildOpenHandsEnv({
apiKey: "sk-test-123",
model: "deepseek-chat",
omnirouteUrl: "http://192.168.3.106:20128",
persistenceDir: "/opt/state",
corsOrigins: ["http://100.73.44.17:3000"],
});
assert.equal(env.LLM_MODEL, "deepseek-chat");
assert.equal(env.LLM_BASE_URL, "http://192.168.3.106:20128/v1");
assert.equal(env.LLM_API_KEY, "sk-test-123");
assert.equal(env.OH_PERSISTENCE_DIR, "/opt/state");
assert.equal(env.PERMITTED_CORS_ORIGINS, "http://100.73.44.17:3000");
});
test("serializeOpenHandsEnv quotes values with whitespace/#", () => {
const out = serializeOpenHandsEnv({ LLM_MODEL: "deepseek-chat", LLM_BASE_URL: "http://localhost:20128/v1" });
const lines = out.trim().split("\n");
assert.ok(lines.some((l) => l.startsWith("LLM_MODEL=deepseek-chat")));
assert.ok(lines.some((l) => l.startsWith("LLM_BASE_URL=http://localhost:20128/v1")));
});
test("resolveOpenHandsModel maps known names to OmniRoute IDs", () => {
assert.equal(resolveOpenHandsModel("deepseek-chat"), "ds/deepseek-v4-flash");
assert.equal(resolveOpenHandsModel("glm-5.2"), "nvidia/z-ai/glm-5.2");
assert.equal(resolveOpenHandsModel("gpt-4o"), "openai/gpt-4o");
});
test("resolveOpenHandsModel passes unknown names through unchanged", () => {
assert.equal(resolveOpenHandsModel("vivanta-core"), "vivanta-core");
assert.equal(resolveOpenHandsModel(""), "");
});
test("resolveOpenHandsModel accepts custom map overrides", () => {
const custom = { "my-alias": "nvidia/z-ai/glm-5.2" };
assert.equal(resolveOpenHandsModel("my-alias", custom), "nvidia/z-ai/glm-5.2");
assert.equal(resolveOpenHandsModel("deepseek-chat", custom), "deepseek-chat");
});
test("buildOpenHandsModel passes combo names through", () => {
assert.equal(buildOpenHandsModel("vivanta-core"), "vivanta-core");
assert.equal(buildOpenHandsModel("ds/deepseek-v4-flash"), "ds/deepseek-v4-flash");
});
test("buildOpenHandsCompose includes privileged, extra_hosts, volume, CORS", () => {
const compose = buildOpenHandsCompose({
apiKey: "sk-x",
model: "deepseek-chat",
persistenceDir: "/Users/me/.openhands-state",
corsOrigins: ["http://localhost:3000"],
});
assert.ok(compose.includes("privileged: true"), "privileged present");
assert.ok(compose.includes("host.docker.internal:host-gateway"), "host-gateway present");
assert.ok(compose.includes("/Users/me/.openhands-state"), "persistence volume present");
assert.ok(compose.includes("LLM_BASE_URL: \"http://localhost:20128/v1\""), "base url present");
assert.ok(compose.includes("PERMITTED_CORS_ORIGINS: \"http://localhost:3000\""), "cors present");
});
test("buildOpenHandsDockerRun produces a runnable docker command", () => {
const run = buildOpenHandsDockerRun({
apiKey: "sk-x",
model: "glm-5.2",
persistenceDir: "/opt/state",
});
assert.ok(run.startsWith("docker run"));
assert.ok(run.includes("--privileged"));
assert.ok(run.includes("--add-host host.docker.internal:host-gateway"));
assert.ok(run.includes("LLM_MODEL=\"glm-5.2\""));
assert.ok(run.includes("LLM_BASE_URL=\"http://localhost:20128/v1\""));
});

View File

@@ -1,22 +0,0 @@
{
"compilerOptions": {
"target": "ES2022",
"module": "ESNext",
"moduleResolution": "Bundler",
"lib": ["ES2022"],
"types": ["node"],
"ignoreDeprecations": "6.0",
"strict": true,
"esModuleInterop": true,
"skipLibCheck": true,
"allowImportingTsExtensions": true,
"declaration": true,
"isolatedModules": true,
"forceConsistentCasingInFileNames": true,
"noUncheckedIndexedAccess": false,
"outDir": "dist",
"rootDir": "src"
},
"include": ["src/**/*.ts"],
"exclude": ["dist", "node_modules", "tests"]
}

View File

@@ -1,15 +0,0 @@
import { defineConfig } from "tsup";
export default defineConfig({
entry: ["src/index.ts", "src/cli.ts"],
format: ["esm"],
dts: true,
clean: true,
sourcemap: false,
splitting: false,
treeshake: false,
target: "node18",
outDir: "dist",
minify: false,
cjsInterop: false,
});

File diff suppressed because it is too large Load Diff

View File

@@ -45,7 +45,7 @@ For full test matrix, see `CONTRIBUTING.md` → "Running Tests". For deep archit
| Translators | `open-sse/translator/` | Format conversion (OpenAI↔Claude↔Gemini) |
| Transformer | `open-sse/transformer/` | Responses API ↔ Chat Completions |
| Services | `open-sse/services/` | Combo routing, rate limits, caching, etc |
| Database | `src/lib/db/` | SQLite domain modules (130 migrations) |
| Database | `src/lib/db/` | SQLite domain modules (95 files, 110 migrations) |
| Domain/Policy | `src/domain/` | Policy engine, cost rules, fallback logic |
| MCP Server | `open-sse/mcp-server/` | 104 tools (42 base + memory/skill/agentSkill/pool/notion/obsidian/gamification/plugin modules), 3 transports (stdio / SSE / Streamable HTTP), 31 scopes |
| A2A Server | `src/lib/a2a/` | JSON-RPC 2.0 agent protocol |
@@ -72,7 +72,7 @@ Client → /v1/chat/completions (Next.js route)
API routes follow a consistent pattern: `Route → CORS preflight → Zod body validation → Optional auth (extractApiKey/isValidApiKey) → API key policy enforcement → Handler delegation (open-sse)`. No global Next.js middleware — interception is route-specific.
**Combo routing** (`open-sse/services/combo.ts`): 19 public strategies (priority, weighted, fill-first, round-robin, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, cache-optimized, context-relay, fusion, pipeline). Each target calls `handleSingleModel()` which wraps `handleChatCore()` with per-target error handling and circuit breaker checks. The `fusion` strategy is the exception: it fans out to a panel of models in parallel, then a judge model synthesizes one final answer (`open-sse/services/fusion.ts`). See `docs/routing/AUTO-COMBO.md` for the 13-factor Auto-Combo scoring + the full strategy table and `docs/architecture/RESILIENCE_GUIDE.md` for the 3 resilience layers.
**Combo routing** (`open-sse/services/combo.ts`): 18 strategies (priority, weighted, fill-first, round-robin, p2c, random, least-used, cost-optimized, reset-aware, reset-window, headroom, strict-random, auto, lkgp, context-optimized, context-relay, fusion, pipeline). Each target calls `handleSingleModel()` which wraps `handleChatCore()` with per-target error handling and circuit breaker checks. The `fusion` strategy is the exception: it fans out to a panel of models in parallel, then a judge model synthesizes one final answer (`open-sse/services/fusion.ts`). See `docs/routing/AUTO-COMBO.md` for the 12-factor Auto-Combo scoring + the full strategy table and `docs/architecture/RESILIENCE_GUIDE.md` for the 3 resilience layers.
---
@@ -332,7 +332,7 @@ For any non-trivial change, read the matching deep-dive first:
| Repo navigation | `docs/architecture/REPOSITORY_MAP.md` |
| Architecture | `docs/architecture/ARCHITECTURE.md` |
| Engineering reference | `docs/architecture/CODEBASE_DOCUMENTATION.md` |
| Auto-Combo (13-factor scoring, 19 strategies) | `docs/routing/AUTO-COMBO.md` |
| Auto-Combo (12-factor scoring, 18 strategies) | `docs/routing/AUTO-COMBO.md` |
| Resilience (3 mechanisms) | `docs/architecture/RESILIENCE_GUIDE.md` |
| Reasoning replay | `docs/routing/REASONING_REPLAY.md` |
| Skills framework | `docs/frameworks/SKILLS.md` |
@@ -461,18 +461,10 @@ own dedicated branch, and you MUST confirm the base branch with the operator bef
git fetch origin "$BASE_BRANCH"
git worktree add ".claude/worktrees/${TASK##*/}" -b "$TASK" "origin/$BASE_BRANCH"
cd ".claude/worktrees/${TASK##*/}"
# Reuse the main checkout's node_modules to skip a per-worktree npm install.
# HARD LINKS (`cp -al`), never a symlink: ~5s for the whole tree and near-zero extra
# disk (the inodes are shared), and unlike a symlink it does not break the dev server.
cp -al "$(git -C <main_checkout> rev-parse --show-toplevel)/node_modules" node_modules
# symlink node_modules from the main checkout to skip a per-worktree npm install:
ln -s "$(git -C <main_checkout> rev-parse --show-toplevel)/node_modules" node_modules
```
**Never `ln -s` node_modules.** Turbopack rejects a symlink that resolves outside the
project root, so `npm run dev` dies with a FATAL panic (`Symlink [project]/node_modules
is invalid, it points out of the filesystem root`) while typecheck, lint and the test
runners all keep passing — the error names "filesystem root", not the worktree, so it
reads like a Next/build bug and costs real time to trace (incident 2026-07-31, #9043).
In Claude Code prefer the native `EnterWorktree` tool (it already creates worktrees under
`.claude/worktrees/`): create the worktree with the command above, then call `EnterWorktree`
with its `path`.

View File

@@ -2,11 +2,6 @@
Thank you for your interest in contributing! This guide covers everything you need to get started.
For the official per-change workflow, start with the
[Contribution Golden Path](docs/dev/CONTRIBUTION_GOLDEN_PATH.md). It maps provider, routing,
UI/UX, i18n, CLI, database, and build/deploy changes to their contracts, focused tests, CI
coverage, and reconciliation steps.
---
## Development Setup
@@ -203,11 +198,10 @@ Coverage notes:
### Pull Request Requirements
Before opening a PR, use the
[Contribution Golden Path](docs/dev/CONTRIBUTION_GOLDEN_PATH.md) to run the focused loop for
what you changed. The full unit suite (4 CI shards), Vitest, the **60%+** coverage gate, and
the production build are CI's responsibility — running them locally adds no signal the PR
checks will not already give you, and on smaller machines it can saturate the host (#8084):
Before opening a PR, run the focused loop for what you changed. The full unit suite
(4 CI shards), Vitest, the **60%+** coverage gate, and the production build are CI's
responsibility — running them locally adds no signal the PR checks will not already
give you, and on smaller machines it can saturate the host (#8084):
- Run the test files that cover your change: `node --import tsx/esm --test tests/unit/<file>.test.ts`
- Run `npm run lint`
@@ -277,7 +271,7 @@ src/ # TypeScript (.ts / .tsx)
│ ├── a2a/ # Agent-to-Agent v0.3 protocol server
│ ├── acp/ # Agent Communication Protocol registry
│ ├── compliance/ # Compliance policy engine
│ ├── db/ # SQLite domain modules + 130 migrations
│ ├── db/ # SQLite database layer (21 modules + 16 migrations)
│ ├── memory/ # Persistent conversational memory
│ ├── oauth/ # OAuth providers, services, and utilities
│ ├── skills/ # Extensible skill framework
@@ -287,7 +281,7 @@ src/ # TypeScript (.ts / .tsx)
├── mitm/ # MITM proxy (cert, DNS, target routing)
├── shared/
│ ├── components/ # React components (.tsx)
│ ├── constants/ # Provider definitions (290), MCP scopes, 19 routing strategies
│ ├── constants/ # Provider definitions (177), MCP scopes, 14 routing strategies
│ ├── utils/ # Circuit breaker, sanitizer, auth helpers
│ └── validation/ # Zod v4 schemas
└── sse/ # SSE proxy pipeline
@@ -295,7 +289,7 @@ src/ # TypeScript (.ts / .tsx)
open-sse/ # @omniroute/open-sse workspace
├── executors/ # 14 provider-specific request executors
├── handlers/ # 11 request handlers (chat, responses, embeddings, images, etc.)
├── mcp-server/ # MCP server (104 tools, 3 transports, 31 scopes)
├── mcp-server/ # MCP server (25 tools, 3 transports, 10 scopes)
├── services/ # 36+ services (combo, autoCombo, rateLimitManager, etc.)
├── translator/ # Format translators (OpenAI ↔ Claude ↔ Gemini ↔ Responses ↔ Ollama)
├── transformer/ # Responses API transformer

View File

@@ -1,5 +1,5 @@
# ── Common base with runtime deps ──────────────────────────────────────────
FROM node:26-trixie-slim AS base
FROM node:24-trixie-slim AS base
WORKDIR /app
# `apt-get upgrade` pulls the security-patched versions of the Debian (trixie)
@@ -8,8 +8,8 @@ WORKDIR /app
# that already have a fix published in trixie. CVEs without an upstream fix yet
# (local-only TOCTOU, etc.) remain until the distro patches them and the image
# is rebuilt; none are reachable from the proxy's request surface at runtime.
RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=locked \
RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=shared \
--mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=shared \
apt-get update \
&& apt-get upgrade -y \
&& apt-get install -y --no-install-recommends libsecret-1-0 ca-certificates \
@@ -29,8 +29,8 @@ FROM base AS builder
# Build tools for native module compilation
# apt-get update needed here because base's rm -rf clears the shared cache
RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=locked \
RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=shared \
--mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=shared \
apt-get update \
&& apt-get install -y --no-install-recommends python3 make g++ \
&& rm -rf /var/lib/apt/lists/*
@@ -95,11 +95,6 @@ RUN --mount=type=cache,id=npm-cache,target=/root/.npm \
# See docs/ops/QUALITY_GATE_PLAYBOOK.md Parte 6.
ENV OMNIROUTE_USE_TURBOPACK=1
# Next.js basePath is fixed at build time; pass OMNIROUTE_BASE_PATH here when the
# image should serve under a reverse-proxy subpath without a runtime patch.
ARG OMNIROUTE_BASE_PATH=""
ENV OMNIROUTE_BASE_PATH=$OMNIROUTE_BASE_PATH
# Docker containers cannot run the MITM/Agent-Bridge stack (no host DNS/cert
# access), so keep @/mitm/manager on the graceful stub (#3390). This flag is
# Docker-only: npm/Electron/VPS builds must bundle the REAL manager (#6344).
@@ -236,11 +231,6 @@ FROM runner-base AS runner-cli
# runner-base runs.
USER root
# The CLI image can use the internal ChatGPT Web (Codex) Chromium sidecar over
# CDP without installing a second browser in this container.
COPY --from=builder /app/node_modules/playwright-core ./node_modules/playwright-core
COPY --from=builder /app/node_modules/playwright ./node_modules/playwright
# Install system dependencies required by openclaw (git+ssh references).
RUN --mount=type=cache,id=apt-cache,target=/var/cache/apt,sharing=locked \
--mount=type=cache,id=apt-lists,target=/var/lib/apt/lists,sharing=locked \

159
README.md
View File

@@ -67,46 +67,32 @@
<table>
<tr>
<td align="right"><b>🚀 Start</b></td>
<td align="center"><a href="#-quick-start">🚀 Quick Start</a></td>
<td align="center"><a href="#-more-install-methods--docker-source-pnpm-arch">📦 Install</a></td>
<td align="center"><a href="#-works-the-second-you-install-it--no-keys-no-config">🆓 Zero-config</a></td>
<td align="center"><a href="#-quick-start"><b>🚀 Quick Start</b></a></td>
<td align="center"><a href="#-combos--the-flagship"><b>🎯 Combos</b></a></td>
<td align="center"><a href="#-290-ai-providers--90-free"><b>🌐 Providers</b></a></td>
</tr>
<tr>
<td align="right"><b>💡 Learn</b></td>
<td align="center"><a href="#-full-cli--a2a--mcp"><b>🔌 CLI &amp; MCP</b></a></td>
<td align="center"><a href="#%EF%B8%8F-save-1595-tokens--automatically"><b>🗜️ Compression</b></a></td>
<td align="center"><a href="https://omniroute.online"><b>🌍 Website</b></a></td>
</tr>
</table>
<table>
<tr>
<td align="center"><a href="#-the-promise">💥 The Promise</a></td>
<td align="center"><a href="#-why-omniroute">🤔 Why OmniRoute</a></td>
<td align="center"><a href="#-why-omniroute">🤔 Why</a></td>
<td align="center"><a href="#-what-sets-omniroute-apart">🏆 What Sets Apart</a></td>
</tr>
<tr>
<td align="right"><b>⚙️ Features</b></td>
<td align="center"><a href="#-combos--the-flagship">🎯 Combos</a></td>
<td align="center"><a href="#-290-ai-providers--90-free">🌐 Providers</a></td>
<td align="center"><a href="#-full-cli--a2a--mcp">🔌 CLI &amp; MCP</a></td>
</tr>
<tr>
<td align="right"></td>
<td align="center"><a href="#%EF%B8%8F-save-1595-tokens--automatically">🗜️ Compression</a></td>
<td align="center"><a href="#-compatible-clis--coding-agents">🤖 Compatible CLIs</a></td>
<td align="center"><a href="#%EF%B8%8F-where-omniroute-runs--anywhere">🖥️ Where It Runs</a></td>
<td align="center"><a href="#-private--local-first">🔒 Private</a></td>
</tr>
<tr>
<td align="right"><b>👀 See it</b></td>
<td align="center"><a href="#-omniroute-in-action">🎬 In Action</a></td>
<td align="center"><a href="#-whats-new">✨ What's New</a></td>
<td align="center"><a href="#-compatible-clis--coding-agents">🤖 Compatible CLIs</a></td>
</tr>
<tr>
<td align="right"><b>💚 Support</b></td>
<td align="center"><a href="#-support-omniroute">💚 Support / Donate</a></td>
<td align="center"><a href="#-community--help">💬 Community</a></td>
<td align="center"><a href="#-sponsors">💖 Sponsors</a></td>
</tr>
<tr>
<td align="right"><b>📦 Project</b></td>
<td align="center"><a href="#%EF%B8%8F-tech-stack">🛠️ Tech Stack</a></td>
<td align="center"><a href="#-documentation">📖 Docs</a></td>
<td align="center"><a href="#-500-contributors">👥 Contributors</a></td>
<td align="center"><a href="#-dashboard-screenshots">📸 Screenshots</a></td>
<td align="center"><a href="#-support--community">📧 Support</a></td>
</tr>
</table>
@@ -241,53 +227,12 @@ curl http://localhost:20128/v1/chat/completions \
<b>What Kimi's support powers:</b> Kimi's API credits power OmniRoute's AI-validated release pipeline — the <i>merge validation powered by Kimi K3</i> stage that reviews every pull request before it ships — plus day-to-day feature development. First-class Kimi support ships on both rails: the direct <a href="https://platform.kimi.ai?aff=omniroute">Kimi API</a> (<code>kimi-k3</code>) and the <a href="https://www.kimi.com/code?aff=omniroute">Kimi Code coding plan</a> (OAuth and API key). OmniRoute is also the first Brazilian open-source project in Kimi's support program. <a href="https://platform.kimi.ai?aff=omniroute"><b>Get a Kimi API key →</b></a>
</td>
</tr>
<tr>
<td align="center" width="150">
<a href="https://cheaperinference.com/?utm_source=omniroute">
<img src="public/providers/cheaperinference.svg" width="64" alt="Cheaper Inference"/>
</a>
<br/><b>Cheaper Inference</b><br/><sub>cheaperinference.com</sub><br/><br/>
<img src="https://img.shields.io/badge/Open_Source_Friend-31f889?style=flat-square&labelColor=04170d" alt="Open Source Friend"/>
</td>
<td>
Thanks to <b>Cheaper Inference</b>, an OmniRoute Open Source Friend, for backing this project! Cheaper Inference is a cost-ranked gateway that resells 42 frontier models — Claude, GPT-5.x, Gemini, Kimi K3, GLM, DeepSeek, Grok and MiniMax — behind one OpenAI-compatible endpoint, routing each request to the cheapest eligible provider without ever charging above the model maker's list price.
<br/><br/>
<b>First-class support in OmniRoute:</b> Chat Completions, the native <code>/v1/responses</code> endpoint, vision, tool calling and 3 image models (<code>grok-imagine</code>, <code>nano-banana-pro</code>, <code>nano-banana-2</code>, reachable as <code>cheaperinference/&lt;model&gt;</code>). <a href="https://cheaperinference.com/?utm_source=omniroute"><b>Get an API key →</b></a>
</td>
</tr>
</table>
<sub>Links tagged <code>aff=omniroute</code> are partner links. They fund the project at no extra cost to you.</sub>
<br/>
<details open>
<summary><sub><b>🎟️ Affiliates Promo</b> — free signup coupons from providers we don't sponsor (click to expand)</sub></summary>
<sub><i>This section is for referral/coupon codes only. Sponsored partnerships live in <b>🤝 Supported by our Open Source Friends</b> above. OmniRoute has no sponsorship or partnership with the providers listed here — these are public coupons anyone can use.</i></sub>
<table>
<tr>
<td align="center" width="120">
<a href="https://agentrouter.org/register?aff=70LM">
<img src="public/providers/agentrouter.png" width="32" alt="AgentRouter"/>
</a>
<br/><sub><b>AgentRouter</b></sub><br/><sub>agentrouter.org</sub>
</td>
<td>
<sub><b><a href="https://agentrouter.org/register?aff=70LM">AgentRouter</a></b> — affiliate signup · <b>$100 free credits</b> on signup (free server, expect higher latency — best for testing, not production). First-class support in OmniRoute since <b>v3.8.50</b>: Chat Completions, the Anthropic-compatible wire format and the OpenAI-compatible path. Available models include <code>claude-opus-4-8</code>, <code>claude-opus-5</code>, <code>gpt-5.6-sol</code> and more. <b><a href="https://agentrouter.org/register?aff=70LM">Grab your $100 →</a></b></sub>
<br/><br/>
<sub>⚠️ <i>Affiliate link — OmniRoute has no sponsorship or partnership with this provider.</i></sub>
</td>
</tr>
</table>
<sub>Know another provider with a generous free signup coupon that benefits OmniRoute users? Open an issue and we'll add it here.</sub>
</details>
<br/>
<div align="center">
## 🎯 Combos — The Flagship
@@ -445,50 +390,13 @@ All **19** strategies — mix & match per combo step:
<br/>
## 💚 Support OmniRoute
## ❤️ Support
OmniRoute is MIT-licensed and maintained in the open. If it saves you time or money, here's how to keep it independent — pick whatever fits you. Sponsorship never affects routing priority; it buys visibility, not ranking.
OmniRoute is free and open source, built and maintained in the open. If it saves you time or money, consider supporting development:
<table>
<tr><td nowrap>⭐ <b>Star the repo</b></td><td>Free — genuinely helps visibility</td><td><a href="https://github.com/diegosouzapw/OmniRoute">Star OmniRoute</a></td></tr>
<tr><td nowrap>🐙 <b>GitHub Sponsors</b></td><td>One-off or monthly · zero platform fee</td><td><a href="https://github.com/sponsors/diegosouzapw">github.com/sponsors/diegosouzapw</a></td></tr>
<tr><td nowrap>🏢 <b>Open Collective</b></td><td><b>Companies</b> — issues an invoice/receipt · transparent books</td><td><a href="https://opencollective.com/omniroute">opencollective.com/omniroute</a></td></tr>
<tr><td nowrap>☕ <b>Ko-fi</b></td><td>Quick one-off tip, no signup for the donor</td><td><a href="https://ko-fi.com/diegosouzapw">ko-fi.com/diegosouzapw</a></td></tr>
<tr><td nowrap>🧋 <b>Buy Me a Coffee</b></td><td>Small, informal gesture</td><td><a href="https://www.buymeacoffee.com/diegosouzapw">buymeacoffee.com/diegosouzapw</a></td></tr>
<tr><td nowrap>🖐 <b>Liberapay</b></td><td>Recurring · non-profit · open source</td><td><a href="https://liberapay.com/diegosouzapw">liberapay.com/diegosouzapw</a></td></tr>
<tr><td nowrap>🇧🇷 <b>PIX</b> (Brazil)</td><td>Instant, no fees</td><td>key &amp; QR below</td></tr>
<tr><td nowrap>₿ <b>Crypto</b></td><td>BTC · ETH · USDT-TRC20 · USDC-Solana</td><td>addresses below</td></tr>
</table>
**🇧🇷 PIX** — instant, no fees (Brazil)
<img src="docs/assets/pix-qr.png" width="140" align="right" alt="OmniRoute PIX QR code"/>
Key (random): `5d865059-bc44-483a-962d-43ceb80126eb`
Pix copia-e-cola:
```
00020101021126580014br.gov.bcb.pix01365d865059-bc44-483a-962d-43ceb80126eb5204000053039865802BR5922OMNIROUTE CONTRIBUICAO6006BRASIL62070503***630475DD
```
<br clear="right"/>
<details>
<summary><b>₿ Crypto</b> — BTC · ETH · USDT-TRC20 · USDC-Solana (click to expand)</summary>
<table>
<tr><td nowrap><b>₿ BTC</b></td><td nowrap>Bitcoin (SegWit)</td><td><code>bc1qh00smz004sy85wyl28v77tenkt3ckl6eaep7fd</code></td></tr>
<tr><td nowrap><b>Ξ ETH</b></td><td nowrap>Ethereum (ERC20)</td><td><code>0x64Cf6B68A6Ff34288e89172950a2d00102337a84</code></td></tr>
<tr><td nowrap><b>₮ USDT</b></td><td nowrap>Tron (TRC20)</td><td><code>TKAF41JpuQrHbKTnsQa9svJE2T192Hvsc2</code></td></tr>
<tr><td nowrap><b>$ USDC</b></td><td nowrap>Solana</td><td><code>2emNNZzVVWQc3FQ2wk9M6qXUQmW8AKdjjL174fXR28Tu</code></td></tr>
</table>
<sub>⚠️ Send each coin only on the network shown — sending on the wrong network can lose the funds.</sub>
</details>
🐛 Found a bug or have feedback? Open a [Discussion](https://github.com/diegosouzapw/OmniRoute/discussions).
-**Star the repo** — it genuinely helps visibility
- 💖 **[GitHub Sponsors](https://github.com/sponsors/diegosouzapw)** — fund ongoing maintenance and new providers
- 🐛 **Report bugs and share feedback** in [Discussions](https://github.com/diegosouzapw/OmniRoute/discussions)
<br/>
@@ -510,12 +418,11 @@ Pix copia-e-cola:
- **🕵️ Transparent MITM decrypt (TPROXY)** — capture CLIs that ignore proxy env vars, with a per-SNI CA + trust-store installer. → [MITM/TPROXY](docs/security/MITM-TPROXY-DECRYPT.md)
- **💸 Cost telemetry everywhere** — `X-OmniRoute-*` cost/usage headers on every endpoint, cache-HIT savings header, per-key USD spend quotas. → [API Reference](docs/reference/API_REFERENCE.md)
- **🧠 Memory you control** — off by default, opt-in int8 vector quantization + typed decay, per-request `x-omniroute-no-memory`. → [Memory](docs/frameworks/MEMORY.md)
- **🛡️ Security** — prompt-injection guard on every LLM route (red-team suite), opt-in credential-masking guardrail (redacts leaked API keys/secrets in both directions), free DuckDuckGo last-resort web search, and an optional OIDC login gate for the dashboard (password login always stays available). → [Guardrails](docs/security/GUARDRAILS.md)
- **🛡️ Security** — prompt-injection guard on every LLM route (red-team suite) + free DuckDuckGo last-resort web search. → [Guardrails](docs/security/GUARDRAILS.md)
- **🖼️ New endpoints** — `/v1/ocr` (Mistral OCR) and `/v1/audio/translations` (Whisper-style) round out the media surface. → [API Reference](docs/reference/API_REFERENCE.md)
- **🎨 Image / video / audio generation** — one API for media: xAI Grok Imagine & Novita AI video, ComfyUI, Freepik, Adobe Firefly, Microsoft Designer, Google Imagen, Segmind, EdgeTTS. → [API Reference](docs/reference/API_REFERENCE.md)
- **🌍 Deployment & ops** — reverse-proxy `basePath`, browser-language auto-detect, per-key device tracking, root-less MITM trust, zh-TW localization. → [Environment](docs/reference/ENVIRONMENT.md)
- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI) with browser + OAuth login, Ollama first-class card, Claude Opus 5 & Sonnet 5, Kimi official partnership (Code/Web/Moonshot), Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **290-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
- **📡 Routing transparency** — every response carries an `X-OmniRoute-Decision` header naming the strategy/provider/latency that served it, a new `cache-optimized` combo strategy + Auto-Combo `cacheAffinity` factor route repeat requests back to the connection holding the cached prefix, and a read-only `/v1/auto-combo/{channel}/candidates` endpoint exposes an `auto/*` channel's live candidate pool. → [Auto-Combo](docs/routing/AUTO-COMBO.md)
- **🤝 More providers & agents** — Cursor Cloud Agent, Grok Build (xAI), Ollama first-class card, Claude Sonnet 5, Zed, Requesty, SenseNova, Yuanbao, Agnes AI… and a refreshed **290-provider catalog**. → [Providers](docs/reference/PROVIDER_REFERENCE.md)
- **⚡ Local performance & infra** — one-click local Redis, Cloudflare Workers / Deno Deploy relay deployers, Bifrost & Mux as supervised embedded services. → [Embedded Services](docs/frameworks/EMBEDDED-SERVICES.md)
<br/>
@@ -926,22 +833,18 @@ devbox run npm run dev
**🦭 Podman**
```bash
# 1. Prepare the bind-mounted data directory
mkdir -p data
# 1. Build the image
podman build --target runner-base -t omniroute:base .
# 2. Linux + local rootless Podman only (never a remote Podman Machine client):
podman unshare chown 1000:1000 ./data
# 2. Fix data directory permissions for rootless Podman
mkdir -p data && podman unshare chown 1000:1000 ./data
# 3. Set the runtime hint, build the local Compose image, and start
# 3. Set runtime in .env, then run (see contrib/podman/ for Quadlet)
echo "CONTAINER_HOST=podman" >> .env
podman compose --profile base up -d --build
podman compose --profile base up -d
```
On macOS or Windows, Podman uses a remote Podman Machine: skip `podman unshare` and
follow the [topology-specific data directory guidance](contrib/podman/README.md#data-directory-permissions-by-topology).
📖 [Podman Guide](contrib/podman/README.md) — Compose builds, Podman Machine, and
Linux/systemd Quadlet setup.
📖 [Podman Guide](contrib/podman/README.md) — Quadlet setup, podman-compose, Quadlet.
**⚡ Faster / leaner install (skip the native build)**
@@ -997,7 +900,7 @@ same process on one port, so there is no separate CLI-only package today.
<div align="center">
# 📧 Community & Help
# 📧 Support & Community
> Everything in one place — follow the maintainer, chat with the community, or open an issue.
@@ -1013,7 +916,7 @@ same process on one port, so there is no separate CLI-only package today.
| 📦 **Source code** | [github.com/diegosouzapw/OmniRoute](https://github.com/diegosouzapw/OmniRoute) |
| 🐛 **Report a bug** | [open an issue](https://github.com/diegosouzapw/OmniRoute/issues) — attach `npm run system-info` output |
| 🤝 **Contribute** | [CONTRIBUTING.md](CONTRIBUTING.md) · [Branching & Release Model](docs/ops/BRANCHING_MODEL.md) · pick a `good first issue` |
| 💚 **Support the project** | [Ways to support ↑](#-support-omniroute) · [GitHub Sponsors](https://github.com/sponsors/diegosouzapw) |
| **Support the project** | [Star the repo](https://github.com/diegosouzapw/OmniRoute) · [GitHub Sponsors](https://github.com/sponsors/diegosouzapw) |
</div>

View File

@@ -1,26 +0,0 @@
# Third-Party Notices
## codex-chatgpt-web
Parts of `open-sse/vendor/codex-chatgpt-web/` are adapted from
[`miuuyy/codex-chatgpt-web`](https://github.com/miuuyy/codex-chatgpt-web), commit
`55592fca0ba19a27f1b769cec8fff61ff340a785`.
MIT License
Copyright (c) 2026 codex-chatgpt-web contributors
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and
associated documentation files (the "Software"), to deal in the Software without restriction,
including without limitation the rights to use, copy, modify, merge, publish, distribute,
sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or substantial
portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT
NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT
OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

View File

@@ -1,56 +0,0 @@
#!/usr/bin/env node
import { existsSync } from "node:fs";
import { dirname, join } from "node:path";
import { fileURLToPath, pathToFileURL } from "node:url";
const here = dirname(fileURLToPath(import.meta.url));
const root = join(here, "..");
export function resolveChatGptWebCodexMcpEntry(rootDir = root, exists = existsSync) {
const candidates = [
join(
rootDir,
"dist",
"open-sse",
"vendor",
"codex-chatgpt-web",
"adapters",
"chatgpt-web",
"mcp-server.js"
),
join(
rootDir,
"open-sse",
"vendor",
"codex-chatgpt-web",
"adapters",
"chatgpt-web",
"mcp-server.ts"
),
];
return candidates.find((candidate) => exists(candidate)) ?? null;
}
export async function startChatGptWebCodexMcp(args = process.argv.slice(2), rootDir = root) {
const socketIndex = args.indexOf("--broker-socket");
const brokerSocketPath = socketIndex >= 0 ? args[socketIndex + 1] : undefined;
if (!brokerSocketPath) throw new Error("--broker-socket is required");
const entry = resolveChatGptWebCodexMcpEntry(rootDir);
if (!entry) throw new Error("ChatGPT Web (Codex) MCP entrypoint was not found");
if (entry.endsWith(".ts")) {
const { register } = await import("node:module");
register("tsx/esm", pathToFileURL(`${rootDir}/`));
}
const module = await import(pathToFileURL(entry).href);
await module.runChatGptMcpServer({ brokerSocketPath });
}
if (process.argv[1] && fileURLToPath(import.meta.url) === process.argv[1]) {
startChatGptWebCodexMcp().catch((error) => {
console.error(
`ChatGPT Web (Codex) MCP konnte nicht gestartet werden: ${error?.message || error}`
);
process.exit(1);
});
}

View File

@@ -1,7 +1,6 @@
import { spawn } from "node:child_process";
import { t } from "../i18n.mjs";
import { resolveActiveContext } from "../contexts.mjs";
import { quoteShellArgs } from "../utils/winShellArgs.mjs";
/** OpenAI/Codex env keys stripped from the child so a stale OpenAI key/base-url
* in the shell can't shadow the omniroute provider (defense-in-depth). Mirrors
@@ -30,23 +29,6 @@ export function resolveCodexSpawn(platform) {
return { command: "codex", shell: undefined };
}
/**
* `shell: true` makes Node join argv with plain spaces and no escaping (the
* DEP0190 warning). That mangles every launch-codex invocation on Windows, not
* just the ones with a multi-word user argument: the injected `-c` provider
* flags carry TOML values whose quotes cmd.exe strips
* (`model_providers.omniroute.name="OmniRoute"` arrives unquoted and no longer
* parses as TOML). Quote the args ourselves on that path; off Windows there is
* no shell, so argv is passed through untouched. Same fix as `launch` (#8837).
*
* @param {string[]} args
* @param {NodeJS.Platform|string} platform
* @returns {string[]}
*/
export function quoteCodexArgs(args, platform) {
return quoteShellArgs(args, platform);
}
function stripTrailingSlash(value) {
let s = String(value);
let end = s.length;
@@ -171,7 +153,7 @@ export async function runLaunchCodexCommand(opts = {}, codexArgs = []) {
return await new Promise((resolve) => {
const { command: codexLaunch, shell: shellValue } = resolveCodexSpawn(process.platform);
const child = spawn(codexLaunch, quoteCodexArgs(extraArgs, process.platform), {
const child = spawn(codexLaunch, extraArgs, {
env,
stdio: "inherit",
shell: shellValue,
@@ -213,10 +195,7 @@ export function registerLaunchCodex(program) {
.argument("[codexArgs...]", "arguments passed through to the codex binary")
.action(async (codexArgs, opts) => {
const merged = { ...opts, profile: opts.profile ?? opts.p };
// process.exit() here aborted the process with a libuv assertion on
// Windows (`!(handle->flags & UV_HANDLE_CLOSING)`, async.c:94): it tears
// the loop down while the inherited stdio handles of the just-exited
// child are still closing. Setting exitCode lets the loop drain first.
process.exitCode = await runLaunchCodexCommand(merged, codexArgs ?? []);
const exitCode = await runLaunchCodexCommand(merged, codexArgs ?? []);
if (exitCode !== 0) process.exit(exitCode);
});
}

View File

@@ -3,7 +3,6 @@ import { join } from "node:path";
import os from "node:os";
import { t } from "../i18n.mjs";
import { resolveActiveContext } from "../contexts.mjs";
import { quoteShellArgs } from "../utils/winShellArgs.mjs";
function stripTrailingSlash(value) {
let s = String(value);
@@ -91,34 +90,6 @@ export function resolveLaunchTarget(opts = {}) {
return { baseUrl, authToken };
}
/**
* #8246: on Windows, npm installs claude as a `.cmd` shim — spawn() without a
* shell cannot resolve PATHEXT shims (and Node refuses to exec `.cmd` directly
* since CVE-2024-27980), so the Windows path must go through cmd.exe.
*
* @param {NodeJS.Platform|string} platform
* @returns {{ command: string, shell: true|undefined }}
*/
export function resolveClaudeSpawn(platform) {
return platform === "win32"
? { command: "claude.cmd", shell: true }
: { command: "claude", shell: undefined };
}
/**
* `shell: true` makes Node join argv with plain spaces and no escaping (the
* DEP0190 warning), so `-p "two words"` used to reach claude as `-p two` plus
* three stray positional arguments. Quote the args ourselves on that path.
* Off Windows there is no shell, so argv is passed through untouched.
*
* @param {string[]} args
* @param {NodeJS.Platform|string} platform
* @returns {string[]}
*/
export function quoteClaudeArgs(args, platform) {
return quoteShellArgs(args, platform);
}
/**
* @param {{port?:string, remote?:string, token?:string, apiKey?:string, profile?:string, claudeHome?:string}} opts
* @param {string[]} claudeArgs pass-through args for the claude binary
@@ -149,12 +120,13 @@ export async function runLaunchCommand(opts = {}, claudeArgs = []) {
const env = buildClaudeEnv(process.env, baseUrl, authToken, { configDir });
return await new Promise((resolve) => {
const { command, shell } = resolveClaudeSpawn(process.platform);
const child = spawn(command, quoteClaudeArgs(claudeArgs, process.platform), {
// #8246: on Windows, npm installs claude as a .cmd shim — spawn() without
// shell:true cannot resolve PATHEXT shims and fails with ENOENT.
const claudeCommand = process.platform === "win32" ? "claude.cmd" : "claude";
const child = spawn(claudeCommand, claudeArgs, {
env,
stdio: "inherit",
shell,
...(process.platform === "win32" ? { windowsHide: true } : {}),
...(process.platform === "win32" ? { shell: true, windowsHide: true } : {}),
});
child.on("error", (err) => {
if (err && err.code === "ENOENT") {
@@ -187,10 +159,7 @@ export function registerLaunch(program) {
.allowExcessArguments(true)
.argument("[claudeArgs...]", "arguments passed through to the claude binary")
.action(async (claudeArgs, opts) => {
// process.exit() here aborted the process with a libuv assertion on
// Windows (`!(handle->flags & UV_HANDLE_CLOSING)`, async.c:94): it tears
// the loop down while the inherited stdio handles of the just-exited
// child are still closing. Setting exitCode lets the loop drain first.
process.exitCode = await runLaunchCommand(opts, claudeArgs ?? []);
const exitCode = await runLaunchCommand(opts, claudeArgs ?? []);
if (exitCode !== 0) process.exit(exitCode);
});
}

View File

@@ -7,11 +7,6 @@ import { t } from "../i18n.mjs";
import { writePidFile, cleanupPidFile, waitForServer } from "../utils/pid.mjs";
import { ServerSupervisor, detectMitmCrash } from "../runtime/processSupervisor.mjs";
import { isTermux } from "../../../scripts/build/postinstallSupport.mjs";
import {
ensureAndroidCacheDir,
isFatalInstrumentationHookFailure,
formatAndroidInstrumentationFailureHint,
} from "../utils/ensureAndroidCacheDir.mjs";
import {
resolveMaxOldSpaceMb,
calibrateHeapFallbackMb,
@@ -67,37 +62,9 @@ export function registerServe(program) {
});
}
/** Once-per-process guard so the Android/Termux cache hint is not spammed. */
let instrumentationFailureHintPrinted = false;
/**
* If child output looks like Next.js failed to load its instrumentation hook
* on Android/Termux, print a clear operator-facing fix hint.
* Exported for unit tests.
*
* @param {string} text
* @returns {boolean} true when a hint was printed
*/
export function maybeReportInstrumentationHookFailure(text) {
if (instrumentationFailureHintPrinted) return false;
if (!isFatalInstrumentationHookFailure(text)) return false;
instrumentationFailureHintPrinted = true;
process.stderr.write(formatAndroidInstrumentationFailureHint(process.env.XDG_CACHE_HOME));
return true;
}
/** Test-only reset for the once-per-process hint guard. */
export function resetInstrumentationFailureHintForTests() {
instrumentationFailureHintPrinted = false;
}
export async function runServe(opts = {}) {
const startedAt = performance.now();
// Same prep as bin/omniroute.mjs — keep it here so a direct `runServe()` call
// (tests / programmatic) still gets a writable Next.js cache dir before spawn.
ensureAndroidCacheDir({ env: process.env });
const { isNativeBinaryCompatible } =
await import("../../../scripts/build/native-binary-compat.mjs");
const { getNodeRuntimeSupport, getNodeRuntimeWarning } =
@@ -167,11 +134,7 @@ export async function runServe(opts = {}) {
"Release",
"better_sqlite3.node"
);
if (
!process.versions.bun &&
existsSync(sqliteBinary) &&
!isNativeBinaryCompatible(sqliteBinary)
) {
if (!process.versions.bun && existsSync(sqliteBinary) && !isNativeBinaryCompatible(sqliteBinary)) {
console.error(
"\x1b[31m✖ better-sqlite3 native module is incompatible with this platform.\x1b[0m"
);
@@ -267,16 +230,15 @@ export async function runServe(opts = {}) {
function runDaemon(serverJs, env, memoryLimit, dashboardPort, apiPort) {
// #5238: skip the explicit CLI --max-old-space-size when the user pinned the
// heap via NODE_OPTIONS (a CLI arg would shadow/override their value).
const server = spawn(
process.versions.bun ? process.execPath : "node",
[...(process.versions.bun ? [] : buildNodeHeapArgs(process.env, memoryLimit)), serverJs],
{
cwd: APP_DIR,
env,
stdio: "ignore",
detached: true,
}
);
const server = spawn(process.versions.bun ? process.execPath : "node", [
...(process.versions.bun ? [] : buildNodeHeapArgs(process.env, memoryLimit)),
serverJs,
], {
cwd: APP_DIR,
env,
stdio: "ignore",
detached: true,
});
writePidFile("server", server.pid);
server.unref();
console.log(`\x1b[32m✔ OmniRoute started in background (PID: ${server.pid})\x1b[0m`);
@@ -287,15 +249,14 @@ function runDaemon(serverJs, env, memoryLimit, dashboardPort, apiPort) {
function runWithoutRecovery(serverJs, env, memoryLimit, dashboardPort, apiPort, noOpen, startedAt) {
// #5238: skip the explicit CLI --max-old-space-size when the user pinned the
// heap via NODE_OPTIONS (a CLI arg would shadow/override their value).
const server = spawn(
process.versions.bun ? process.execPath : "node",
[...(process.versions.bun ? [] : buildNodeHeapArgs(process.env, memoryLimit)), serverJs],
{
cwd: APP_DIR,
env,
stdio: "pipe",
}
);
const server = spawn(process.versions.bun ? process.execPath : "node", [
...(process.versions.bun ? [] : buildNodeHeapArgs(process.env, memoryLimit)),
serverJs,
], {
cwd: APP_DIR,
env,
stdio: "pipe",
});
writePidFile("server", server.pid);
@@ -304,7 +265,6 @@ function runWithoutRecovery(serverJs, env, memoryLimit, dashboardPort, apiPort,
server.stdout.on("data", (data) => {
const text = data.toString();
process.stdout.write(text);
maybeReportInstrumentationHookFailure(text);
if (
!started &&
(text.includes("Ready") || text.includes("started") || text.includes("listening"))
@@ -314,11 +274,7 @@ function runWithoutRecovery(serverJs, env, memoryLimit, dashboardPort, apiPort,
}
});
server.stderr.on("data", (data) => {
const text = data.toString();
process.stderr.write(text);
maybeReportInstrumentationHookFailure(text);
});
server.stderr.on("data", (data) => process.stderr.write(data));
server.on("error", (err) => {
console.error("\x1b[31m✖ Failed to start server:\x1b[0m", err.message);
@@ -427,9 +383,6 @@ export function reportReadinessTimeout(dashboardPort, supervisor) {
console.error("--- Recent server output ---");
recentLog.forEach((l) => console.error(l));
console.error("--- End recent output ---\n");
// If the buffered log already shows the Android instrumentation failure,
// print the actionable hint even when --log was off (default).
maybeReportInstrumentationHookFailure(recentLog.join("\n"));
}
}

View File

@@ -10,21 +10,11 @@ import {
} from "./supervisorPolicy.mjs";
import { buildNodeHeapArgs } from "../../../scripts/build/runtime-env.mjs";
import { stopProcessGracefully } from "../../../src/shared/platform/windowsProcess.ts";
import {
isFatalInstrumentationHookFailure,
formatAndroidInstrumentationFailureHint,
} from "../utils/ensureAndroidCacheDir.mjs";
const CRASH_LOG_LINES = 50;
export class ServerSupervisor {
constructor({
serverPath,
env,
maxRestarts = DEFAULT_MAX_RESTARTS,
memoryLimit = 512,
onCrashCallback,
}) {
constructor({ serverPath, env, maxRestarts = DEFAULT_MAX_RESTARTS, memoryLimit = 512, onCrashCallback }) {
this.serverPath = serverPath;
this.env = env;
this.maxRestarts = maxRestarts;
@@ -35,13 +25,11 @@ export class ServerSupervisor {
this.crashLog = [];
this.child = null;
this.isShuttingDown = false;
this.instrumentationFailureHintPrinted = false;
}
start() {
this.startedAt = Date.now();
this.crashLog = [];
this.instrumentationFailureHintPrinted = false;
const showLog = process.env.OMNIROUTE_SHOW_LOG === "1";
// #5238: skip the explicit CLI --max-old-space-size when the user pinned the
@@ -53,35 +41,23 @@ export class ServerSupervisor {
// silently, so a boot that never becomes ready looked like a dead hang with zero
// output even at APP_LOG_LEVEL=debug. Pipe stdout too and buffer it alongside
// stderr so a readiness timeout can surface what the child actually printed.
this.child = spawn(
process.versions.bun ? process.execPath : "node",
[...(process.versions.bun ? [] : heapArgs), this.serverPath],
{
cwd: dirname(this.serverPath),
env: this.env,
stdio: showLog ? "inherit" : ["ignore", "pipe", "pipe"],
}
);
this.child = spawn(process.versions.bun ? process.execPath : "node", [
...(process.versions.bun ? [] : heapArgs),
this.serverPath,
], {
cwd: dirname(this.serverPath),
env: this.env,
stdio: showLog ? "inherit" : ["ignore", "pipe", "pipe"],
});
writePidFile("server", this.child.pid);
const bufferOutput = (data) => {
const text = data.toString();
const lines = text.split("\n").filter(Boolean);
const lines = data.toString().split("\n").filter(Boolean);
this.crashLog.push(...lines);
if (this.crashLog.length > CRASH_LOG_LINES) {
this.crashLog = this.crashLog.slice(-CRASH_LOG_LINES);
}
// Surface Android/Termux instrumentation-hook failures even when --log is
// off (output is only buffered otherwise).
if (!this.instrumentationFailureHintPrinted && isFatalInstrumentationHookFailure(text)) {
this.instrumentationFailureHintPrinted = true;
process.stderr.write(
formatAndroidInstrumentationFailureHint(
this.env?.XDG_CACHE_HOME || process.env.XDG_CACHE_HOME
)
);
}
};
if (this.child.stdout) {

View File

@@ -1,122 +0,0 @@
/**
* Next.js cache-dir prep for Android / Termux.
*
* Next.js `getCacheDirectory()` has no dedicated branch for
* `process.platform === "android"`. On that path it only accepts a cache root
* that *already* exists (`fs.existsSync` on `~/.cache` or a generic tmp dir).
* If neither exists it prints `Unsupported platform: android` and exits — the
* CLI can still look "running" while every request returns a bare HTTP 500
* because the instrumentation hook never loads (and so neither does logging).
*
* Termux Node sometimes reports `platform === "android"` and sometimes
* `"linux"` with Termux env signals (`TERMUX_VERSION` / `PREFIX`). Creating
* `~/.cache` (and pointing `XDG_CACHE_HOME` at it when unset) makes the probe
* succeed on both shapes.
*
* Call this *before* spawning or loading Next.js. Safe no-op on desktop
* platforms that are not Termux.
*/
import { existsSync, mkdirSync } from "node:fs";
import { homedir } from "node:os";
import { join } from "node:path";
import { isTermux } from "../../../scripts/build/postinstallSupport.mjs";
/**
* @param {string} [platform]
* @param {NodeJS.ProcessEnv} [env]
* @returns {boolean}
*/
export function needsAndroidCacheDirPrep(platform = process.platform, env = process.env) {
return platform === "android" || isTermux(env);
}
/**
* @param {() => string} [homedirFn]
* @param {NodeJS.ProcessEnv} [env]
* @returns {string}
*/
export function resolveAndroidCacheDir(homedirFn = homedir, env = process.env) {
if (typeof env.XDG_CACHE_HOME === "string" && env.XDG_CACHE_HOME.trim()) {
return env.XDG_CACHE_HOME;
}
return join(homedirFn(), ".cache");
}
/**
* Ensure a writable cache directory exists for Next.js on Android/Termux.
*
* @param {object} [options]
* @param {string} [options.platform]
* @param {NodeJS.ProcessEnv} [options.env]
* @param {() => string} [options.homedirFn]
* @param {typeof mkdirSync} [options.mkdirSyncFn]
* @param {typeof existsSync} [options.existsSyncFn]
* @param {boolean} [options.setEnv] When true (default), set `XDG_CACHE_HOME` on `env`
* if unset so child processes inherit a known-writable cache root.
* @returns {{ prepared: boolean, cacheDir: string | null, created: boolean }}
*/
export function ensureAndroidCacheDir(options = {}) {
const {
platform = process.platform,
env = process.env,
homedirFn = homedir,
mkdirSyncFn = mkdirSync,
existsSyncFn = existsSync,
setEnv = true,
} = options;
if (!needsAndroidCacheDirPrep(platform, env)) {
return { prepared: false, cacheDir: null, created: false };
}
const cacheDir = resolveAndroidCacheDir(homedirFn, env);
let created = false;
if (!existsSyncFn(cacheDir)) {
mkdirSyncFn(cacheDir, { recursive: true });
created = true;
}
if (setEnv && !(typeof env.XDG_CACHE_HOME === "string" && env.XDG_CACHE_HOME.trim())) {
env.XDG_CACHE_HOME = cacheDir;
}
return { prepared: true, cacheDir, created };
}
/**
* Detect Next.js instrumentation-hook failures that leave the server looking
* "up" while requests get silent HTTP 500s (typical when the Android cache
* probe failed before logging started).
*
* @param {string} text
* @returns {boolean}
*/
export function isFatalInstrumentationHookFailure(text) {
if (!text) return false;
return (
/Unsupported platform:\s*android/i.test(text) ||
/error occurred while loading instrumentation hook/i.test(text)
);
}
/**
* Operator-facing hint when that instrumentation failure shows up in child
* output — defense in depth if prep was skipped or a future Next.js probe
* regresses.
*
* @param {string} [cacheDir]
* @returns {string}
*/
export function formatAndroidInstrumentationFailureHint(cacheDir) {
const dir = cacheDir || join(homedir(), ".cache");
return (
`\n\x1b[31m✖ Next.js instrumentation failed on Android/Termux (likely missing cache dir).\x1b[0m\n` +
` OmniRoute tried to create a writable cache at:\n` +
` \x1b[36m${dir}\x1b[0m\n` +
` Manual workaround (survives reinstalls — do NOT patch dist/server.js):\n` +
` \x1b[36mmkdir -p ~/.cache\x1b[0m\n` +
` then restart: \x1b[36momniroute serve\x1b[0m\n` +
` See: docs/guides/TERMUX_GUIDE.md → Troubleshooting → Unsupported platform: android\n`
);
}

View File

@@ -1,47 +0,0 @@
/**
* Argument escaping for child processes spawned with `shell: true` on Windows.
*
* The launchers (`omniroute launch`, `omniroute launch-codex`) must go through
* cmd.exe on win32 because the target binaries are npm `.cmd` shims that Node
* cannot exec directly (CVE-2024-27980). With `shell: true` Node joins argv with
* plain spaces and no escaping at all (the DEP0190 warning), so anything with a
* space, a quote or a cmd metacharacter reaches the child mangled.
*/
/** cmd.exe metacharacters that stay live inside a quoted argument. */
const WIN_META_CHARS = /([()\][%!^"`<>&|;, *?])/g;
/**
* Escape one argument for a cmd.exe command line built by `shell: true`.
*
* Two layers, in order:
* 1. the CRT argv rules the target binary parses (double the backslashes that
* precede a quote, escape embedded quotes, wrap in quotes);
* 2. cmd.exe's metacharacters, caret-escaped — applied TWICE because the
* target is an npm `.cmd` shim that forwards `%*` to node, so the line is
* parsed by cmd a second time. Single-escaping truncated any argument at
* the first `&` or `|`. (Same rule as cross-spawn's doubleEscapeMetaChars.)
*
* @param {unknown} arg
* @returns {string}
*/
export function escapeWindowsShellArg(arg) {
const s = String(arg);
if (s === "") return '""';
let out = s.replace(/(\\*)"/g, '$1$1\\"').replace(/(\\*)$/, "$1$1");
out = `"${out}"`;
return out.replace(WIN_META_CHARS, "^$1").replace(WIN_META_CHARS, "^$1");
}
/**
* Escape a whole argv for the `shell: true` path. Off Windows there is no shell,
* so argv is passed through untouched.
*
* @param {string[]} args
* @param {NodeJS.Platform|string} platform
* @returns {string[]}
*/
export function quoteShellArgs(args, platform) {
const list = [...(args ?? [])];
return platform === "win32" ? list.map(escapeWindowsShellArg) : list;
}

View File

@@ -145,15 +145,6 @@ function loadEnvFile() {
loadEnvFile();
// Next.js has no android branch in getCacheDirectory(): if ~/.cache (and tmp)
// do not already exist it aborts the instrumentation hook, and every request
// then returns a silent HTTP 500 even though the CLI still looks "running".
// Create the cache dir (and set XDG_CACHE_HOME when unset) before serve/Next.
{
const { ensureAndroidCacheDir } = await import("./cli/utils/ensureAndroidCacheDir.mjs");
ensureAndroidCacheDir();
}
// Generate STORAGE_ENCRYPTION_KEY if not set (persisted to ~/.omniroute/.env)
// This ensures the key survives across upgrades and is not regenerated on each install.
// See: https://github.com/diegosouzapw/OmniRoute/issues/1622

View File

@@ -0,0 +1 @@
- **feat(sse):** every completion response now carries an `X-OmniRoute-Decision: strategy=<name>; provider=<alias>; latency_ms=<n>` header exposing the routing decision — `<name>` is the combo strategy (`priority`, `weighted`, `fusion`, etc.) or `single` for a non-combo request — for client-side debugging/analytics without server log access (#6022 — thanks @chirag127).

View File

@@ -0,0 +1 @@
- **feat(ws):** the live-dashboard WebSocket server now auto-starts in-process (via `instrumentation-node.ts`) across every deployment mode — dev, production, Docker, Electron — with no separate sidecar script; the default WS port moved from 20129 to **20132** to avoid colliding with `API_PORT` in split-port setups, the deprecated `OMNIROUTE_DISABLE_LIVE_WS` env was consolidated into `OMNIROUTE_ENABLE_LIVE_WS` (default enabled), and the WS path is now derived from `NEXT_PUBLIC_LIVE_WS_PUBLIC_URL`'s pathname (`/live-ws` fallback) (#6072 — thanks @ianriizky).

View File

@@ -0,0 +1 @@
- feat(sse): configurable per-model upstream header-response timeout override, precedence model > provider > global; applied to codex reasoning-heavy tiers (gpt-5.5-high/xhigh, gpt-5.6-\*-high/xhigh) (#6354)

View File

@@ -0,0 +1 @@
- **feat(dashboard):** Replace free-text model inputs in the Routing (web search route), Combo Defaults (handoff model), and Background Degradation tabs with a `hidePaidModels`-aware `ModelSelectField`, add a fail-open "paid-only pattern" warning to the per-model routing rule pattern field, and reject paid-only model targets at save time on `PATCH /api/settings`, `PATCH /api/settings/combo-defaults`, and `PUT /api/settings/background-degradation` when `hidePaidModels` is on ([#6540](https://github.com/diegosouzapw/OmniRoute/issues/6540))

View File

@@ -0,0 +1 @@
- **feat(compression):** new **omniglyph** engine (context-as-image) — renders system prompt, tool docs, and dense history as compact PNG pages the model reads instead of text (~10× fewer tokens on the converted block; 5970% end-to-end measured). Works stacked with RTK/Caveman (`stackPriority: 90`) or standalone (`mode: omniglyph`); restricted to Claude Fable 5 over the direct Anthropic route, fail-closed gates with `skip:<reason>` techniques, preview (`stable: false`, off by default) (#6556). Dependency bumped to `omniglyph@^1.0.2` for upstream ReDoS fixes (#6661).

View File

@@ -0,0 +1 @@
- **feat(sse):** rate-limit request queue admission control — `resilienceSettings.requestQueue.maxQueueDepth` (default `0` = disabled, opt-in 0100000) fast-rejects a request with a typed `RATE_LIMIT_QUEUE_FULL` error once the local per-provider+connection queue already holds `maxQueueDepth` requests, instead of growing the queue unboundedly; the factory default for `requestQueue.maxWaitMs` (how long a request may wait before being dropped) also fell from 120s to 15s so a saturated queue fails fast (#6593 — thanks @chirag127).

View File

@@ -0,0 +1 @@
- **feat(sandbox):** the skill sandbox gained a container-provider abstraction that auto-detects and uses the best native runtime per host — Apple Container (macOS 26+), WSL container (`wslc.exe`), OrbStack, Podman — instead of hardcoding `docker run`, removing the Docker Desktop requirement on macOS/Windows (#6611 — thanks @KooshaPari).

View File

@@ -0,0 +1 @@
- feat(oauth): accept the full ChatGPT session JSON (not just a bare access token) when pasting Codex credentials manually or via `POST /api/oauth/codex/import-token` (#6636)

View File

@@ -0,0 +1 @@
- feat(sse): add 5 no-key g4f.space gateway providers — `g4f-groq`, `g4f-gemini`, `g4f-pollinations`, `g4f-ollama`, `g4f-nvidia` — a free, no-signup reverse proxy (gpt4free project) fronting Groq, Gemini, Pollinations, Ollama, and NVIDIA NIM, rate-limited to 5 req/min per IP (#6650 — thanks @chirag127).

View File

@@ -0,0 +1 @@
- feat(sse): add DeepInfra as a video-generation provider via its native synchronous inference endpoint (#6653)

View File

@@ -0,0 +1 @@
- feat(providers): add Freepik (Magnific Mystic) API-key image generation provider — async submit/poll flow with realism/fluid/zen/flexible/super_real/editorial_portraits models (#6654)

View File

@@ -0,0 +1 @@
- feat(providers): add Rev AI speech-to-text provider with async job upload/poll/transcript flow (#6655)

View File

@@ -0,0 +1 @@
- **feat(providers):** add **Segmind** as an image + video generation provider — `x-api-key` auth against `POST https://api.segmind.com/v1/{model}`, with a curated starter model list (Flux, Stable Diffusion XL/3.5, Kandinsky for image; Wan, Hunyuan, LTX, Kling for video) (#6656).

View File

@@ -0,0 +1 @@
- feat(providers): add Gladia as an async speech-to-text provider (#6657)

View File

@@ -0,0 +1 @@
- feat(video): add Novita AI as a video-generation provider (Wan/Kling async submit-poll) (#6658)

View File

@@ -0,0 +1 @@
- **feat(providers):** add Speechmatics as an STT provider — async batch transcription (Enhanced operating point), 8 hours/month free tier, no credit card required. Streaming (real-time) mode is out of scope for v1. (#6659)

View File

@@ -0,0 +1 @@
- feat(providers): add Mixedbread AI as an embeddings provider (`mxbai-embed-large-v1`, `mxbai-embed-2d-large-v1`, free tier) (#6660)

View File

@@ -0,0 +1 @@
- **feat(providers):** add Felo (felo.ai) as a free, no-signup, no-API-key chat/search-agent aggregator provider (`felo-web`) — joins the existing `-web` family (DuckDuckGo AI Chat, Blackbox, etc). Five models (`felo-chat`, `felo-search`, `felo-scholar`, `felo-social`, `felo-document`) map to Felo's search categories; the executor opens a search thread then translates Felo's bespoke SSE stream into OpenAI-compatible chunks (#6666).

View File

@@ -0,0 +1 @@
- **feat(providers):** add gTTS (Google Translate TTS) as a free, no-signup audio-speech provider — routes through Google's current `batchexecute` RPC endpoint (the previously proposed `translate_tts` endpoint is deprecated), splitting input at the 100-char-per-request limit. (#6667)

View File

@@ -0,0 +1 @@
- **feat(sse):** add EdgeTTS (Microsoft Edge "Read Aloud") as a free, no-API-key `audio-tts` provider — the first WebSocket-transport speech provider, with per-client-IP rate limiting. (#6668)

View File

@@ -0,0 +1 @@
- feat(providers): add FreeTheAi as an OpenAI-compatible gateway provider with a free Discord-signup tier (#6670)

View File

@@ -0,0 +1 @@
- feat(sse): add Microsoft Designer as an unofficial web-session image provider, reverse-engineered submit-then-poll DallE.ashx flow (#6672)

View File

@@ -0,0 +1 @@
- **feat(providers):** add Hailuo Web (`hailuo-web`) — a free, `_token`-based web-cookie chat provider for the MiniMax consumer chat product at hailuo.ai, ported from the g4f reference implementation (MD5-chain request signing, custom `event:`/`data:` SSE parsing). Distinct from the existing paid API-key `minimax`/`minimax-cn` providers. (#6673)

View File

@@ -0,0 +1 @@
- **feat(cli):** new `omniroute auth export` command dumps DECRYPTED provider credentials (`apiKey`/`accessToken`/`refreshToken`/`idToken`) for one connection (`--id <id>`) or all connections, as `json` or `env` (`--format`), local-only and gated behind `--force` — no DB access happens without it, a stderr warning banner prints before any plaintext, `--out <file>` writes with `0600` permissions, and per-field decrypt failures surface as a `<field>DecryptFailed` boolean instead of aborting the export or leaking the caught error text (#6683)

View File

@@ -0,0 +1 @@
- **feat(mitm):** the AgentBridge static MITM server (`server.cjs`) can now issue a per-host TLS leaf from a persisted local root CA (`src/mitm/cert/rootCa.ts`, reusing the CA/leaf crypto already proven for TPROXY in `tproxy/dynamicCert.ts`) instead of a single static self-signed leaf scoped only to the 4 antigravity hosts — a fresh install covers the full `MITM_TOOL_HOSTS` set automatically; an install that already trusted the old leaf keeps using it until the operator opts in via `MITM_ROOT_CA_ENABLED=true` (`src/mitm/cert/migration.ts`), so no existing install is silently upgraded to the more powerful any-host-signing CA trust model (#6684).

View File

@@ -0,0 +1 @@
- **fix(sse):** skip `thinkingConfig` for Gemma models on the OpenAI→Gemini path so OpenAI-shape clients no longer get a 400 from Vertex. (thanks @chy1211)

View File

@@ -0,0 +1 @@
- **feat(xai):** route xAI clients to Grok's native `/v1/responses` endpoint instead of the chat-completions bridge. (thanks @ryanngit)

View File

@@ -0,0 +1 @@
- **feat(models):** add a Settings → AI "Model Overrides" UI plus `/api/model-capability-overrides` CRUD and a `model_capability_overrides` table, letting operators set a manual max-output-token override per provider/model (#6727 — thanks @xz-dev).

View File

@@ -0,0 +1 @@
- **feat(api):** add `Vary: Accept-Encoding` to token-authenticated `/v1*`/`/v1beta*` responses so downstream caches distinguish compressed vs uncompressed variants (RFC 9110 §12.5.5). (thanks @chirag127)

View File

@@ -0,0 +1 @@
- feat(sse): add Notion AI Web (Unofficial/Experimental) cookie-session provider (#6758)

View File

@@ -0,0 +1 @@
- **feat(dashboard):** add per-routing-combo compression-mode override to the Compression Combos page under Context & Cache, alongside the existing combo-card quick override. (#6760)

View File

@@ -0,0 +1 @@
- **feat(resilience):** operator-configurable account rotation policy — a new `rotationConfig` layer lets operators tune how connections rotate on failure, wired into `accountFallback` (#6763 — thanks @artickc).

View File

@@ -0,0 +1 @@
- **feat(sse):** preserve `tools`/`tool_choice` for tool-bearing requests through fusion combos — bypass panel synthesis and route straight to the judge with tools intact (#6771 — thanks @chirag127).

View File

@@ -0,0 +1 @@
- **chore(cursor): add Grok 4.5 effort/fast model IDs** (#6774 — thanks @andrewmunsell).

View File

@@ -0,0 +1 @@
- **feat(codex):** Codex provider model discovery now fetches the live catalog from `chatgpt.com/backend-api/codex/models` using Codex-shaped headers, falling back to a GitHub-hosted model manifest and then to the local static catalog when the live/GitHub sources are unavailable or return an unexpected shape — new `src/app/api/providers/[id]/models/discovery/codex.ts` (normalization, version-gating, merge/enrich against the local catalog) covered by `tests/unit/provider-models-discovery-split.test.ts` and `tests/unit/provider-models-route-codex.test.ts` (#6776 — thanks @JxnLexn).

View File

@@ -0,0 +1 @@
- **feat(cursor):** register the Opus 4.8, Fable 5, and Sonnet 5 model families for the Cursor Agent provider so the latest Claude/Fable model ids route correctly (#6779 — thanks @andrewmunsell).

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