Compare commits

..

5 Commits

Author SHA1 Message Date
Diego Rodrigues de Sa e Souza
ba71a68441 chore(quality): shave the #5976 fix comment back under the auth.ts file-size freeze (2447) 2026-07-06 02:24:52 -03:00
Diego Rodrigues de Sa e Souza
7a14a96b83 fix(security): crypto-backed randomNumericId in doubao-web (CodeQL js/insecure-randomness)
The synthetic Dola device/web id was built from Math.random; CodeQL flags it
as insecure randomness in a security context. Not a secret, but
crypto.getRandomValues costs the same and closes alert #692 at the source.
Doubao executor tests 14/14 green. Alerts #693-695 (incomplete-url-substring
in unit-test asserts) dismissed as false positives per the v3.8.35 precedent
(Hard Rule #14).
2026-07-06 02:09:46 -03:00
Diego Rodrigues de Sa e Souza
adede73fe2 fix(resilience): 502/503/504 keep the connection-unavailability path — only the exact 500 skips lockout (#5976 contract)
The #6216 branch used 'status >= 500', so a 503 on a per-model-quota /
openai-compatible provider returned cooldownMs 0 — no model lockout AND no
connection cooldown — hot-looping the failing upstream and breaking the
resilience-http-e2e 'priority combo falls back on 503' guard on the release
PR (the request after a 503 hit the same primary again). #6216's OWN unit
contract pins the narrow behavior ('Gemini 503 should NOT skip cooldown',
combo-provider-cooldown-sibling.test.ts) but computes the condition inline
instead of exercising auth.ts. Code aligned to the tested contract:
status === 500 skips (intermittent, not model-specific); 502/503/504 keep
the pre-#6216 model-lockout path. Validated: the failing integration test
flips red -> green locally (19s, deterministic before).
2026-07-06 01:56:15 -03:00
Diego Rodrigues de Sa e Souza
cc2f19a965 chore(release): v3.8.45 — 2026-07-06 2026-07-06 01:28:52 -03:00
Diego Rodrigues de Sa e Souza
60a3e08a55 docs(changelog): v3.8.45 reconciliation — fold Unreleased into the version section, 30 missing bullets, contributors hall
Phase 0a reconciliation (/generate-release): every commit since v3.8.44 now
has a bullet or a Maintenance rollup (82 commits; the only ref-less residues
are the bump/recording commits); #6193 bullet gains its PR ref; #6298
diagnosis credited (@subhansh-dev, landed via #6234); [3.8.44] header dated;
'### 🙌 Contributors' table injected (27 external + maintainer) + 42 i18n
mirrors resynced.
2026-07-06 01:14:54 -03:00
4441 changed files with 113339 additions and 730022 deletions

View File

@@ -1,201 +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/
# NOTA: src/lib/env/, src/app/api/{cloud,sync/cloud,system/env,agent-skills/coverage}/
# foram removidos daqui (2026-08-05). Os nomes sugerem dados/segredos locais, mas os
# 8 arquivos sao route handlers e modulos rastreados no git — escondia-los do grafo
# criava pontos cegos em buscas e em analise de impacto.
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/
# Docs traduzidas: 1.215 arquivos / 94 MB (inclui 20+ copias do CHANGELOG).
# Sao traducoes do tree em ingles, ja indexado — no grafo so geram ruido em
# search_code e consomem o auto_index_limit.
docs/i18n/
# ─────────────────────────────────────────────────────────────────────────────
# 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
# NOTA: bin/omniroute.mjs foi removido daqui (2026-08-05). Estava marcado como
# "scratch", mas e o entrypoint real do CLI publicado (package.json -> bin.omniroute)
# e consta em PACK_ARTIFACT_REQUIRED_PATHS. Precisa estar no grafo.
# Deploy / docker backups
deploy.sh
docker-compose.yml.bak
docker-compose.minimal.yml

View File

@@ -7,13 +7,7 @@
**/.vscode
# Dependencies and build output
# `node_modules` alone matches the ROOT only — Docker's matcher does not cross
# `/` like .gitignore does. Without the `**/` form, nested installs ship in the
# build context (e.g. @omniroute/opencode-provider/node_modules, ~79 MB of
# devDependencies). Both forms are kept: the bare one is the documented root
# rule, the `**/` one covers every nested package.
node_modules
**/node_modules
.next
.build
out
@@ -43,17 +37,6 @@ tests
test-results
playwright-report
blob-report
output
.playwright-cli
.playwright-mcp
.stryker-tmp
reports/mutation
# Local caches and quality-gate artifacts (all gitignored). `_*` does not match
# dot-prefixed names, so these need explicit entries.
.artifacts
.eslintcache
.eslintcache-complexity
# Documentation
# Issue #2348: The Dashboard Docs viewer reads markdown from `/app/docs` at
@@ -66,10 +49,6 @@ reports/mutation
# (English) sources at runtime, so translations are not required in the
# container image.
docs/i18n/**
# Internal planning artifacts (gitignored). `*.md` above only matches the root,
# so without this rule these land in /app/docs and become readable through the
# dashboard's Docs viewer at runtime.
docs/superpowers/**
docs/diagrams/**/*.png
docs/diagrams/**/*.jpg
docs/diagrams/**/*.jpeg

View File

@@ -40,11 +40,6 @@ INITIAL_PASSWORD=CHANGEME
# also if you want to share the same database as "npm run dev" use "./data"
# DATA_DIR=/var/lib/omniroute
# Fallback alias for DATA_DIR, checked only when DATA_DIR is unset.
# Used by: open-sse/executors/promptql/threadSticky.ts — locates the PromptQL
# executor's on-disk thread-sticky session cache. Leave unset to rely on DATA_DIR.
# OMNIROUTE_DATA_DIR=/var/lib/omniroute
# Encryption key for SQLite database encryption at rest.
# Used by: src/lib/db/encryption.ts — encrypts the entire SQLite database.
# Generate: openssl rand -hex 32 | Leave empty to disable DB encryption.
@@ -80,26 +75,8 @@ PORT=20128
# Base path (URL subpath) when serving OmniRoute behind a reverse proxy under a subpath.
# Used by: next.config.mjs — sets Next.js `basePath`; auth redirects are basePath-aware.
# Also mirrored to NEXT_PUBLIC_OMNIROUTE_BASE_PATH at build time so the dashboard
# 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
# as OMNIROUTE_BASE_PATH; when unset the hook falls back to OMNIROUTE_BASE_PATH.
# Used by: src/shared/hooks/useDisplayBaseUrl.ts
# NEXT_PUBLIC_OMNIROUTE_BASE_PATH=
#
# Optional: set the public origin *with* the same path so OAuth and display URLs
# stay consistent without relying on window.location.origin alone:
# NEXT_PUBLIC_BASE_URL=https://host/omniroute
# Split-port mode: serve Dashboard and API on separate ports for network isolation.
# Used by: src/lib/runtime/ports.ts — overrides PORT for each service.
@@ -107,22 +84,10 @@ PORT=20128
# API_HOST=0.0.0.0
# DASHBOARD_PORT=20128
# Connection backpressure: cap concurrent in-flight chat connections (503 + Retry-After when full).
# Used by: src/sse/utils/backpressure.ts — disabled when unset/0.
# OMNI_MAX_CONCURRENT_CONNECTIONS=0
# Optional OmniRoute-to-OmniRoute peer chaining guard. Give every instance a
# unique ID and allowlist only the other OmniRoute base URLs it may call.
# Requests to allowlisted peers carry X-OmniRoute-Peer-Trace; repeated instances
# and exhausted hop budgets are rejected with HTTP 508 before provider routing.
# OMNIROUTE_INSTANCE_ID=gateway-a
# OMNIROUTE_PEER_URLS=http://gateway-b:20128/v1
# OMNIROUTE_PEER_MAX_HOPS=4
# Port for the real-time WebSocket live monitoring server.
# Used by: src/server/ws/liveServer.ts, src/app/api/v1/ws/route.ts
# Default: 20132
# LIVE_WS_PORT=20132
# Default: 20129
# LIVE_WS_PORT=20129
# Bind address for the live WebSocket server.
# Default: 127.0.0.1 (loopback only). Set to 0.0.0.0 to expose on LAN —
@@ -147,14 +112,16 @@ PORT=20128
# Public URL for the live dashboard WebSocket (client-side, browser only).
# Set this when fronting the WS server with a reverse proxy or Cloudflare Tunnel.
# The browser will connect to this URL instead of ws://hostname:20132.
# The path portion of this URL (e.g. ws://localhost:20132/live-ws -> /live-ws) is also used by the dev proxy
# (scripts/dev/standalone-server-ws.mjs) and the handshake response to route
# WebSocket upgrades. Default path: /live-ws.
# Used by: src/hooks/useLiveDashboard.ts, src/app/api/v1/ws/route.ts,
# scripts/dev/standalone-server-ws.mjs, and scripts/start-ws-server.mjs.
# The browser will connect to this URL instead of ws://hostname:20129.
# The /live-ws path is already proxied from the main app (port 20128) to the
# live WS server (port 20129) by scripts/dev/standalone-server-ws.mjs.
# Used by: src/hooks/useLiveDashboard.ts
# Example: NEXT_PUBLIC_LIVE_WS_PUBLIC_URL=wss://ws.my-ai.com/live-ws
# NEXT_PUBLIC_LIVE_WS_PUBLIC_URL=ws://localhost:20132/live-ws
# NEXT_PUBLIC_LIVE_WS_PUBLIC_URL=
# Disable the standalone live WebSocket helper used by scripts/start-ws-server.mjs.
# Used by: scripts/start-ws-server.mjs (CI/embedded harness toggle).
# OMNIROUTE_DISABLE_LIVE_WS=0
# Enable the real-time dashboard WebSocket server.
# Used by: src/server/ws/liveServer.ts, scripts/start-ws-server.mjs
@@ -207,12 +174,6 @@ OMNIROUTE_USE_TURBOPACK=1
# hints in production logs.
# OMNIROUTE_PROXY_FETCH_DEBUG=true
# Set to any non-empty value to emit `[omniroute completion]` diagnostics from
# the CLI shell-completion cache paths (read/refresh/write) in
# bin/cli/commands/completion.mjs. Off by default — these caches fail silently
# so a missing/corrupt cache never breaks tab-completion.
# OMNIROUTE_DEBUG_COMPLETION=1
# Docker production port mappings (docker-compose.prod.yml only).
# These set the HOST-side published ports. Container ports use PORT/API_PORT.
# PROD_DASHBOARD_PORT=20130
@@ -230,9 +191,9 @@ OMNIROUTE_USE_TURBOPACK=1
# the machine name by bash/zsh. The .env loader cannot override it (first-wins
# semantics). Use OMNIROUTE_SERVER_HOST instead for `omniroute serve`.
# See: https://github.com/diegosouzapw/OmniRoute/issues/6194
# HOST=0.0.0.0
# HOSTNAME=127.0.0.1
# OMNIROUTE_SERVER_HOST=0.0.0.0
#HOST=0.0.0.0
#HOSTNAME=127.0.0.1
#OMNIROUTE_SERVER_HOST=0.0.0.0
# Environment mode — affects Next.js behavior, logging verbosity, and caching.
# Values: production | development | Default: production
@@ -240,22 +201,10 @@ 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.
# Used by: src/lib/skills/sandbox.ts + src/lib/skills/containerProvider.ts
# Values: auto | docker | apple | wsl | orbstack | podman
# - auto: OS-aware auto-detect (apple/orbstack on macOS, wsl on Windows, podman on Linux)
# - apple: Apple Container (native OCI on macOS 26+)
# - wsl: WSL Container CLI (wslc.exe on Windows)
# - orbstack: OrbStack (high-perf Linux VM + docker shim on macOS)
# - podman: Podman (rootless, daemonless)
# - docker: Docker (default fallback)
# (defined under SKILLS & SANDBOXING section below)
# ═══════════════════════════════════════════════════════════════════════════════
# 4. SECURITY & AUTHENTICATION
# ═══════════════════════════════════════════════════════════════════════════════
@@ -320,25 +269,18 @@ ALLOW_API_KEY_REVEAL=false
# Default: 10485760 (10 MB)
# MAX_BODY_SIZE_BYTES=10485760
# Atomic admission for POST /v1/chat/completions (#7846). Large request bodies
# amplify into multiple transient representations during parsing, compression, and
# provider dispatch. Heavyweight capacity is reserved before parsing; excess work
# receives 503 + Retry-After instead of overlapping until the process OOMs.
# Heap-pressure-aware admission for POST /v1/chat/completions (#5152). A large
# coding-agent "compact" body amplifies into hundreds of MB of transient JS objects
# on the combo path; concurrent compacts can stack past the V8 heap ceiling and OOM
# the process. These shed a LARGE body with 503 (Retry-After) only while the heap is
# already under pressure — healthy heap admits every body untouched.
# Used by: src/shared/middleware/chatBodyAdmission.ts
# Actual bodies at or above this size require a heavyweight lease. Default 262144 (256 KB).
# Bodies below this size skip the guard entirely (heap not even sampled). Default 262144 (256 KB).
# OMNIROUTE_CHAT_LARGE_BODY_BYTES=262144
# Actual-byte hard cap enforced during bounded ingestion. Default 52428800 (50 MB).
# Hard cap — bodies above this are rejected with 413 before any clone/parse. Default 52428800 (50 MB).
# OMNIROUTE_CHAT_HARD_MAX_BODY_BYTES=52428800
# Maximum heavyweight requests simultaneously admitted in one process. Default 1.
# OMNIROUTE_CHAT_MAX_HEAVY_IN_FLIGHT=1
# Message count that classifies an otherwise small body as heavyweight. Default 200.
# OMNIROUTE_CHAT_HEAVY_MESSAGE_COUNT=200
# Tool count that classifies an otherwise small body as heavyweight. Default 64.
# OMNIROUTE_CHAT_HEAVY_TOOL_COUNT=64
# Conservative string-size token estimate that classifies a request as heavyweight. Default 32000.
# OMNIROUTE_CHAT_HEAVY_ESTIMATED_TOKENS=32000
# Hard message-count cap; excess receives compact-required 413. Default 800.
# OMNIROUTE_CHAT_HARD_MAX_MESSAGES=800
# Shed large bodies once heapUsed/heap_size_limit reaches this ratio (0<r<1). Default 0.75.
# OMNIROUTE_CHAT_HEAP_SHED_RATIO=0.75
# Hard cap (bytes) for a non-streaming upstream response buffered fully into memory
# (#5152). Past this the upstream reader is cancelled and the request fails fast
@@ -379,24 +321,16 @@ ALLOW_API_KEY_REVEAL=false
# ── Request-Side: Prompt Injection Guard ──
# Scans incoming messages for prompt injection patterns before routing.
# Used by: src/middleware/promptInjectionGuard.ts
# Default ON when unset. Set to false/0/no/off to disable. Truthy: true/1/yes/on.
# INPUT_SANITIZER_ENABLED=false
# INPUT_SANITIZER_MODE=warn # warn = log only | block = reject request | redact = legacy (does NOT strip injection; use PII_REDACTION_ENABLED for request PII)
# INPUT_SANITIZER_BLOCK_THRESHOLD=high # high (default) | medium | low — severities at/above this are blocked in block mode
# INPUT_SANITIZER_ENABLED=true
# INPUT_SANITIZER_MODE=warn # warn = log only | block = reject request | redact = strip patterns
# Legacy aliases for INPUT_SANITIZER_MODE / INPUT_SANITIZER_BLOCK_THRESHOLD (same effect).
# Legacy alias for INPUT_SANITIZER_MODE (same effect).
# INJECTION_GUARD_MODE=warn
# INJECTION_GUARD_BLOCK_THRESHOLD=high
# PII detection in incoming requests (emails, phone numbers, SSNs, etc.).
# Used by: src/middleware/promptInjectionGuard.ts — extends injection guard.
# PII_REDACTION_ENABLED=false
# Redacts well-known API-key / secret-token patterns (OpenAI, Anthropic, GitHub,
# Slack, etc.) from request/response payloads before they reach providers/clients.
# Opt-in; mirrors PII_REDACTION_ENABLED. Used by: src/lib/guardrails/credentialMasker.ts.
# CREDENTIAL_REDACTION_ENABLED=false
# Minimum streaming window size for PII detection (bytes). Default: 200.
# Used by: src/lib/streamingPiiTransform.ts.
# PII_WINDOW_SIZE=200
@@ -552,9 +486,7 @@ NEXT_PUBLIC_CLOUD_URL=
#OMNIROUTE_CROF_USAGE_URL=https://crof.ai/usage_api/
#OMNIROUTE_CODEWHISPERER_BASE_URL=https://codewhisperer.us-east-1.amazonaws.com
#OMNIROUTE_OPENCODE_QUOTA_URL=https://opencode.ai/zen/go/v1/quota
# OpenCode Go has no public quota API — this has no default and stays
# unset unless you explicitly opt in to a self-hosted/mirrored endpoint:
#OMNIROUTE_OPENCODE_GO_QUOTA_URL=
#OMNIROUTE_OPENCODE_GO_QUOTA_URL=https://api.z.ai/api/monitor/usage/quota/limit
#OMNIROUTE_OPENCODE_GO_DASHBOARD_URL=https://opencode.ai/workspace
#OMNIROUTE_OLLAMA_CLOUD_USAGE_URL=https://ollama.com/settings
@@ -696,15 +628,6 @@ NEXT_PUBLIC_ENABLE_SOCKS5_PROXY=true
# Legacy alias for OMNIROUTE_API_KEY.
# ROUTER_API_KEY=
# Enable the offline/local Issue Agent recorded-triage endpoint.
# Used by: src/app/api/issue-agent/runs/route.ts. Default: disabled.
# OMNIROUTE_ISSUE_AGENT_ENABLED=false
# Timeout (ms) for a single Issue Agent recorded-triage run. Clamped to an internal
# maximum; falls back to the built-in default when unset or invalid.
# Used by: src/lib/issueAgent/execution.ts.
# OMNIROUTE_ISSUE_AGENT_TIMEOUT_MS=
# CLI remote-mode context/profile for `omniroute` commands (overrides the active
# context in the local contexts store). Equivalent to the `--context <name>` flag.
# Used by: bin/cli/program.mjs, bin/cli/api.mjs (remote mode).
@@ -811,15 +734,6 @@ 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
@@ -882,11 +796,10 @@ PROVIDER_LIMITS_SYNC_SPACING_MS=1500
# Used by: open-sse/executors/antigravity.ts — escape hatch for multi-project setups.
# OMNIROUTE_ALLOW_BODY_PROJECT_OVERRIDE=0
# Control Antigravity Google One AI credit usage. Used by:
# open-sse/services/antigravityCredits.ts — accepts off, retry, or always.
# off (default): never use credits; retry: use credits once after eligible quota 429;
# always: use credits on the first request (higher account and spend risk).
#ANTIGRAVITY_CREDITS=off
# Adjust how Antigravity advertises remaining credits. Used by:
# open-sse/services/antigravityCredits.ts — accepts forced override strings.
# Default: empty (use upstream-reported credits).
#ANTIGRAVITY_CREDITS=
# Override the path to the Antigravity CLI (agy) token file read by the
# "auto-detect local login" import. Used by:
@@ -940,17 +853,15 @@ CODEX_OAUTH_CLIENT_ID=app_EMoamEEZ73f0CkXaXp7hrann
# ANTIGRAVITY_OAUTH_CLIENT_SECRET=
# WINDSURF_FIREBASE_API_KEY=
# ── Qwen (Alibaba) ──
QWEN_OAUTH_CLIENT_ID=f0304373b74a44d2b584a3fb70ca9e56
# ── Kimi Coding (Moonshot) ──
KIMI_CODING_OAUTH_CLIENT_ID=17e5f671-d194-4dfb-9706-5516cb48c098
# ── GitHub Copilot ──
GITHUB_OAUTH_CLIENT_ID=Iv1.b507a08c87ecfe98
# ── GitHub Enterprise (GHE) Copilot ──
# Optional override for GHE Copilot's OAuth client id. Falls back to the public
# GITHUB_OAUTH_CLIENT_ID default when unset. Used by: src/lib/oauth/constants/oauth.ts.
# GHE_COPILOT_OAUTH_CLIENT_ID=
# ── GitLab Duo ──
# Register an OAuth app at: https://gitlab.com/-/profile/applications
# Set redirect URI to: http://localhost:20128/callback (or your NEXT_PUBLIC_BASE_URL + /callback)
@@ -1055,7 +966,7 @@ GITHUB_OAUTH_CLIENT_ID=Iv1.b507a08c87ecfe98
# Used by: open-sse/executors/base.ts — buildHeaders() dynamic lookup.
# Update these when providers release new CLI versions to avoid blocks.
CLAUDE_USER_AGENT="claude-cli/2.1.219 (external, cli)"
CLAUDE_USER_AGENT="claude-cli/2.1.195 (external, cli)"
# Disable the deterministic tool-name cloak applied on both Anthropic-bound paths
# (executors/base.ts native OAuth + executors/cliproxyapi.ts CLIProxyAPI) —
@@ -1064,7 +975,7 @@ CLAUDE_USER_AGENT="claude-cli/2.1.219 (external, cli)"
# stream with a misleading 400 out-of-extra-usage placeholder. Set to true to
# forward the original names verbatim (debugging only).
# CLAUDE_DISABLE_TOOL_NAME_CLOAK=false
CODEX_USER_AGENT="codex-cli/0.144.1 (Windows 10.0.26200; x64)"
CODEX_USER_AGENT="codex-cli/0.142.0 (Windows 10.0.26200; x64)"
GITHUB_USER_AGENT="GitHubCopilotChat/0.54.0"
ANTIGRAVITY_USER_AGENT="antigravity/2.0.1 linux/arm64 google-api-nodejs-client/10.3.0"
KIRO_USER_AGENT="AWS-SDK-JS/3.0.0 kiro-ide/1.0.0"
@@ -1080,11 +991,12 @@ KIRO_USER_AGENT="AWS-SDK-JS/3.0.0 kiro-ide/1.0.0"
# Used by: open-sse/executors/kiro.ts
# KIRO_VERIFY_FULL_CRC=false
QODER_USER_AGENT="Qoder-Cli"
QWEN_USER_AGENT="QwenCode/0.19.3 (linux; x64)"
CURSOR_USER_AGENT="Cursor/3.4"
# Override Codex client version sent in headers independently of the
# CODEX_USER_AGENT string. Used by: open-sse/config/codexClient.ts.
# CODEX_CLIENT_VERSION=0.144.1
# CODEX_CLIENT_VERSION=0.142.0
# Kill-switch to strip non-standard `codex.*` SSE events (e.g. codex.rate_limits)
# from the Codex Responses stream. These frames break the OpenAI SDK's
@@ -1109,6 +1021,8 @@ CURSOR_USER_AGENT="Cursor/3.4"
# CLI_COMPAT_KIMI_CODING=1
# CLI_COMPAT_KILOCODE=1
# CLI_COMPAT_CLINE=1
# CLI_COMPAT_QWEN=1
# Or enable for all providers at once:
# CLI_COMPAT_ALL=1
@@ -1204,20 +1118,6 @@ CURSOR_USER_AGENT="Cursor/3.4"
# OMNIROUTE_GROK_TLS_TIMEOUT_MS=60000
# OMNIROUTE_GROK_TLS_GRACE_MS=10000
# ── Notion web TLS sidecar (Chrome-fingerprinted client) ──
# Used by: open-sse/services/notionTlsClient.ts — wire-level timeout for the
# bogdanfinn/tls-client koffi binding and the JS-side grace window layered on
# top of it when the native library is wedged. The notion-web executor raises
# the wire timeout per-request to 180000 for long generations.
# OMNIROUTE_NOTION_TLS_TIMEOUT_MS=30000
# OMNIROUTE_NOTION_TLS_GRACE_MS=10000
# ── Grok web quota fetcher (auth.json override) ──
# Used by: open-sse/services/grokQuotaFetcher.ts — path of the Grok CLI
# auth.json used to fetch the grok-web weekly quota. Defaults to
# ~/.grok/auth.json; override for tests or a non-standard CLI install.
# GROK_AUTH_PATH=
# ── Browser-backed web-cookie chat (Playwright shared pool) ──
# Used by: open-sse/services/browserPool.ts + browserBackedChat.ts. The shared
# browser pool warms a headless context for web-cookie providers (e.g. claude-web)
@@ -1248,13 +1148,6 @@ CURSOR_USER_AGENT="Cursor/3.4"
# PIN_DROP_BACKOFF_LEVEL=2
# PIN_DROP_GRACE_MS=20000
# Whether OmniRoute may emit SSE `:` comment lines (e.g. the `: keepalive` heartbeat).
# Some strict OpenAI-compatible clients parse every SSE line as JSON and crash on `:`
# comments. Set to `off` to suppress comment-shaped heartbeats (they become a no-op);
# `data:` heartbeats are unaffected. Default: enabled.
# Used by: open-sse/utils/sseHeartbeat.ts.
# OMNIROUTE_SSE_COMMENTS=off
# ── Stream idle detection ──
# STREAM_IDLE_TIMEOUT_MS=600000 # Max silence between SSE chunks (default: 600000)
# # Extended-thinking models rarely pause >90s.
@@ -1414,6 +1307,10 @@ 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)
@@ -1507,12 +1404,6 @@ APP_LOG_TO_FILE=true
# NANOBANANA_POLL_TIMEOUT_MS=120000 # Max wait for job completion (default: 120s)
# NANOBANANA_POLL_INTERVAL_MS=2500 # Poll frequency (default: 2.5s)
# ── Microsoft Designer Web (Image Generation) ──
# Polling config for the microsoft-designer-web submit-then-poll image job.
# Used by: open-sse/handlers/imageGeneration/providers/designerWeb.ts
# DESIGNER_WEB_POLL_TIMEOUT_MS=60000 # Max wait for job completion (default: 60s)
# DESIGNER_WEB_POLL_INTERVAL_MS=2000 # Poll frequency (default: 2s)
# ── AWS Bedrock (Kiro / Audio) ──
# Region used to construct AWS Bedrock endpoints. Used by:
# src/lib/providers/validation.ts and open-sse/handlers/audioSpeech.ts.
@@ -1621,11 +1512,6 @@ APP_LOG_TO_FILE=true
# Timeout for fast-fail health checks (ms). Default: 2000
# PROXY_FAST_FAIL_TIMEOUT_MS=2000
# Time window (hours) for calculating the average latency of candidate proxies
# in the latency-optimized pool strategy. Default: 3
# Used by: src/lib/db/proxies.ts
# PROXY_LATENCY_WINDOW_HOURS=3
# Health check result cache TTL (ms). Default: 30000 (30s)
# PROXY_HEALTH_CACHE_TTL_MS=30000
@@ -1658,13 +1544,9 @@ APP_LOG_TO_FILE=true
# Also configurable from Dashboard > Settings > Feature Flags.
# OMNIROUTE_CONTROL_PLANE_PROXY_DIRECT_FALLBACK=false
# Rate limit maximum wait time before failing a request (ms). Default: 15000 (15s)
# Rate limit maximum wait time before failing a request (ms). Default: 120000 (2 min)
# Used by: open-sse/services/rateLimitManager.ts
# RATE_LIMIT_MAX_WAIT_MS=15000
# Rate limit queue admission cap: reject with 429 queue_full once this many requests
# are already queued (0 = disabled/unbounded, the default). Used by: open-sse/services/rateLimitManager.ts
# RATE_LIMIT_MAX_QUEUE_DEPTH=0
# RATE_LIMIT_MAX_WAIT_MS=120000
# Force the auto-enable rate limit safety net on/off regardless of the persisted
# Dashboard setting. Used by: open-sse/services/rateLimitManager.ts.
@@ -1713,17 +1595,6 @@ APP_LOG_TO_FILE=true
# Used by: src/lib/tokenHealthCheck.ts. Default: 3000.
# HEALTHCHECK_STAGGER_MS=3000
# Randomized jitter range (ms) added on top of HEALTHCHECK_STAGGER_MS between
# provider token healthchecks, to prevent bursting (Issue #1220).
# Used by: src/lib/tokenHealthCheck.ts. Defaults: min=500, max=5000.
# HEALTHCHECK_JITTER_MIN_MS=500
# HEALTHCHECK_JITTER_MAX_MS=5000
# Concurrent-check batch size for the startup token-healthcheck sweep. Larger
# values check more connections in parallel; smaller values reduce burst load.
# Used by: src/lib/tokenHealthCheck.ts. Default: 20 (Issue #7875, regression of #7719).
# HEALTHCHECK_BATCH_SIZE=20
# ═══════════════════════════════════════════════════════════════════════════════
# 22. DEBUGGING
# ═══════════════════════════════════════════════════════════════════════════════
@@ -1759,19 +1630,10 @@ APP_LOG_TO_FILE=true
# Used by: open-sse/utils/cursorImages.ts.
# CURSOR_IMAGE_FETCH_TIMEOUT_MS=15000
# Cursor state DB path override (for IDE cursor version detection).
# Cursor state DB path override (for cursor version detection).
# Used by: open-sse/utils/cursorVersionDetector.ts. Default: probed automatically.
# CURSOR_STATE_DB_PATH=
# Cursor Agent CLI build id for AgentService/Run impersonation (YYYY.MM.DD-<hash>).
# Used by: open-sse/utils/cursorAgentCliVersion.ts. Default: detect local install, else pin.
# CURSOR_AGENT_CLI_VERSION=2026.07.08-0c04a8a
# Cursor Agent CLI data directory override (versions live under <dir>/versions/).
# Used by: open-sse/utils/cursorAgentCliVersion.ts. Default: ~/.local/share/cursor-agent (unix)
# or %LOCALAPPDATA%\cursor-agent (win32). Official agent CLI also honors this var.
# CURSOR_DATA_DIR=
# Direct Cursor bearer token used by scripts/ad-hoc/cursor-tap.cjs (developer tooling).
# CURSOR_TOKEN=
@@ -1826,10 +1688,6 @@ 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.
@@ -1866,22 +1724,6 @@ APP_LOG_TO_FILE=true
# for root-less / user-namespaced deployments (e.g. rootless Docker/Podman)
# where the operator trusts the CA manually (e.g. via Node's extra-CA-certs mechanism).
# OMNIROUTE_NO_SUDO=0
# Explicit opt-out: skip provisioning /etc/hosts DNS entries for the Antigravity
# proxy hostnames entirely (containers with no sudo/root available).
# Used by: src/mitm/dns/provision.ts.
# SKIP_ANTIGRAVITY_DNS=true
# Skip writing to the hosts file when adding/removing DNS entries (e.g. sandboxed
# or read-only test environments). Used by: src/mitm/dns/dnsConfig.ts.
# OMNIROUTE_SKIP_DNS_WRITE=1
# Opt in to the root-CA + per-host-leaf cert model for the MITM proxy (#6684).
# Fresh installs and installs with this set to "true" get a persisted root CA that
# signs per-host leaves; installs with a pre-existing trusted legacy leaf keep the
# legacy fixed-SAN cert unless opted in. Used by: src/mitm/manager.ts.
# MITM_ROOT_CA_ENABLED=true
# Set BY the MITM manager for the spawned proxy process ("root-ca" | "legacy") —
# reflects the migration decision above; not meant to be set manually.
# Read by: src/mitm/server.cjs.
# MITM_CERT_MODE=legacy
# ── Test/CI-only guards (never needed in production) ──
# Set automatically by tests/_setup/isolateDataDir.ts and the CI workflows: the
@@ -1901,14 +1743,6 @@ APP_LOG_TO_FILE=true
# ONEPROXY_MAX_PROXIES=500
# ONEPROXY_MIN_QUALITY_THRESHOLD=50
# ── Free Proxy Pool (auto-sync scheduler) ──
# Background refresh of the free-proxy pool. Opt-in, OFF by default (parallels
# Hard Rule #20's default-off posture for data-mutating background features).
# Used by: src/lib/freeProxyProviders/scheduler.ts
# FREE_PROXY_AUTO_SYNC_ENABLED=true
# Sync interval in ms (default: 1800000 = 30 min).
# FREE_PROXY_AUTO_SYNC_INTERVAL_MS=1800000
# ── Free Proxy Pool (1proxy source) ──
# Used by: src/lib/freeProxyProviders/oneproxy.ts
# Set FREE_PROXY_1PROXY_ENABLED=false to disable this source.
@@ -1965,11 +1799,6 @@ APP_LOG_TO_FILE=true
# Used by: src/lib/db/backup.ts.
# DB_BACKUP_MAX_FILES=20
# DB_BACKUP_RETENTION_DAYS=0
# Tick interval (ms) of the server-side job that executes backup-schedule.json.
# Must stay well under the 1-minute cron granularity; values below 5000 (or
# unparseable) fall back to the 30000 default.
# Used by: src/lib/jobs/backupScheduleJob.ts
# OMNIROUTE_BACKUP_SCHEDULE_JOB_INTERVAL_MS=30000
# ── TLS sidecar override ──
# Used by: open-sse/services/chatgptTlsClient.ts tests. Production deployments
@@ -1986,15 +1815,6 @@ APP_LOG_TO_FILE=true
# SKILLS_SANDBOX_NETWORK_ENABLED=0
# SKILLS_ALLOWED_SANDBOX_IMAGES=
# Container runtime used by the skill sandbox. Accepted values:
# auto — pick the best installed runtime per host OS (default)
# docker — Docker Engine / Docker Desktop
# apple — Apple Container (macOS native, micro-VM)
# wsl — WSL Container (Windows native via wslc.exe)
# orbstack — OrbStack (high-perf Linux VM + docker shim on macOS)
# podman — Podman (rootless, daemonless)
# SKILLS_SANDBOX_RUNTIME=auto
# ═══════════════════════════════════════════════════════════════════════════════
# 25. TEST & E2E
# ═══════════════════════════════════════════════════════════════════════════════
@@ -2040,7 +1860,7 @@ APP_LOG_TO_FILE=true
# OMNIROUTE_TRANSLATION_API_URL=
# Bearer token for the translation backend (NEVER commit a real key here).
# OMNIROUTE_TRANSLATION_API_KEY=
# Model id, e.g. gpt-4o-mini or cx/gpt-5.6-sol.
# Model id, e.g. gpt-4o-mini or cx/gpt-5.4-mini.
# OMNIROUTE_TRANSLATION_MODEL=gpt-4o-mini
# Per-request timeout in milliseconds (default 60000).
# OMNIROUTE_TRANSLATION_TIMEOUT_MS=60000
@@ -2132,15 +1952,6 @@ QUOTA_STORE_DRIVER=sqlite # sqlite | redis
# the full (unfiltered) pool with a warning. Source: open-sse/services/autoCombo/virtualFactory.ts
# OMNIROUTE_AUTO_FREE_FALLBACK_TO_FULL_POOL=false
# ─── Auto-Combo chaos panel (broadcast variant) ────────────────────────────
# Tuning for the `auto/*:chaos` variant, which fans a single request out to a
# panel of provider-diverse models. Panel size is clamped to 1..10 (default 5);
# min-panel and the panel hard-timeout fall back to the engine defaults when
# unset. Source: open-sse/services/autoCombo/virtualFactory.ts
# OMNIROUTE_CHAOS_MAX_PANEL=5
# OMNIROUTE_CHAOS_MIN_PANEL=
# OMNIROUTE_CHAOS_PANEL_TIMEOUT_MS=
# ─── OpenCode config regeneration (scripts/ad-hoc/regen-opencode-config.ts) ───
# Base URL of the OmniRoute instance to query for /v1/models when regenerating
# an opencode.json with accurate limit.context values. Used by:
@@ -2257,72 +2068,3 @@ QUOTA_STORE_DRIVER=sqlite # sqlite | redis
# BIFROST_API_KEY=
# BIFROST_STREAMING_ENABLED=true
# BIFROST_TIMEOUT_MS=30000
# ─────────────────────────────────────────────────────────────────────────────
# Account rotation config (operator-managed; consumed by open-sse/services/rotationConfig.ts)
# Lets a supervising front-end mirror its rotation rules onto the backend's account-fallback
# engine. All optional; defaults preserve the historical behavior.
# ─────────────────────────────────────────────────────────────────────────────
# OMNIROUTE_ROTATION_ENABLED=true
# OMNIROUTE_ROTATION_RATE_LIMIT_RESET_SECONDS=0
# OMNIROUTE_ROTATION_DISABLE_TAG_WITHOUT_RESET=true
# OMNIROUTE_ROTATE_ON_429=true
# OMNIROUTE_ROTATE_429_THRESHOLD=1
# OMNIROUTE_ROTATE_429_WINDOW_SECONDS=120
# OMNIROUTE_ROTATE_ON_500=true
# OMNIROUTE_ROTATE_500_THRESHOLD=1
# OMNIROUTE_ROTATE_500_WINDOW_SECONDS=120
# OMNIROUTE_ROTATE_ON_502=true
# OMNIROUTE_ROTATE_502_THRESHOLD=1
# OMNIROUTE_ROTATE_502_WINDOW_SECONDS=120
# OMNIROUTE_ROTATE_ON_400=false
# OMNIROUTE_ROTATE_400_THRESHOLD=1
# OMNIROUTE_ROTATE_400_WINDOW_SECONDS=120
# ─────────────────────────────────────────────────────────────────────────────
# PromptQL playground provider (Unofficial/Experimental — src/shared/constants/providers/web-cookie.ts)
# Reverse-engineered GraphQL session bridge for prompt.ql.app. All optional —
# defaults point at the public playground endpoints; override only for a
# self-hosted/alternate PromptQL deployment.
# Used by: open-sse/executors/promptql.ts, open-sse/services/usage/promptql.ts
# ─────────────────────────────────────────────────────────────────────────────
# PROMPTQL_GRAPHQL_ENDPOINT=https://data.prompt.ql.app/promptql/playground-v2-hge/v1/graphql
# PROMPTQL_CREDITS_ENDPOINT=https://data.pro.ql.app/v1/graphql
# PROMPTQL_TOKEN_REFRESH_URL=https://auth.pro.ql.app/ddn/project/token
# PROMPTQL_POLL_TIMEOUT_MS=180000
# ─────────────────────────────────────────────────────────────────────────────
# HyperAgent web provider (Unofficial/Experimental — src/shared/constants/providers/web-cookie.ts)
# Reverse-engineered session bridge for hyperagent.com. Optional — defaults
# point at the public billing/usage endpoint; override only for a
# self-hosted/alternate HyperAgent deployment.
# Used by: open-sse/services/usage/hyperagent.ts
# ─────────────────────────────────────────────────────────────────────────────
# HYPERAGENT_USAGE_URL=https://hyperagent.com/api/settings/billing/usage
# ─────────────────────────────────────────────────────────────────────────────
# Browser-login VNC sessions (optional — src/lib/vncSession/manifest.ts)
# Containerized Chromium+VNC used for interactive browser-login credential
# capture via /api/vnc-session. All optional — defaults target the bundled
# `omniroute-vnc-chromium:local` image; override only for a custom image, ports,
# or lifecycle tuning.
# ─────────────────────────────────────────────────────────────────────────────
# OMNIROUTE_VNC_IMAGE=omniroute-vnc-chromium:local
# OMNIROUTE_DOCKER_BIN=docker
# OMNIROUTE_VNC_CONTAINER_VNC_PORT=3000
# OMNIROUTE_VNC_CONTAINER_CDP_PORT=9223
# OMNIROUTE_VNC_CONTAINER_PROFILE_DIR=/config
# OMNIROUTE_VNC_PROFILE_DIR=
# OMNIROUTE_VNC_IDLE_MS=600000
# OMNIROUTE_VNC_MAX_MS=1800000
# OMNIROUTE_VNC_MAX_SESSIONS=4
# OMNIROUTE_VNC_READY_MS=45000
# OMNIROUTE_VNC_HARVEST_MS=20000
# OMNIROUTE_VNC_CHROMIUM_ARGS=--remote-debugging-port=9222 --no-first-run --no-default-browser-check
# ─────────────────────────────────────────────────────────────────────────────
# Data-dir alias (optional — open-sse/services/notionThreadSessions.ts)
# Legacy fallback for DATA_DIR, checked only after DATA_DIR and
# OMNIROUTE_DATA_DIR are both unset. Locates the Notion web-thread session cache.
# ─────────────────────────────────────────────────────────────────────────────
# VIBEPROXY_DATA_DIR=

View File

@@ -1,9 +0,0 @@
# Homologação E2E real — copie para .env.homolog (NUNCA commitar o real)
HOMOLOG_BASE_URL=http://192.168.0.15:20128
# Senha de management do dashboard da VPS (a mesma do /login)
HOMOLOG_ADMIN_PASSWORD=
# Deixe vazio: a suíte cria uma API key efêmera via admin e revoga no fim.
# Só preencha para depurar uma camada isolada com uma key fixa.
HOMOLOG_API_KEY=
# Tier crítico (chat real, max_tokens=5). Demais providers: só validação de catálogo.
HOMOLOG_CRITICAL_PROVIDERS=openai,anthropic,gemini,codex,grok,glm,deepseek,openrouter

View File

@@ -24,32 +24,12 @@ updates:
update-types: ["version-update:semver-major"]
- dependency-name: "eslint-config-next"
update-types: ["version-update:semver-major"]
# typescript majors are peer-blocked by typescript-eslint, which pins a hard
# upper bound (8.64.0 → peerDependencies.typescript ">=4.8.4 <6.1.0"). A TS 7
# bump therefore violates the peer and takes down the whole toolchain at once —
# #7068 grouped it with 6 harmless bumps and turned Build + Lint + Quality Ratchet
# + Unit (6/8, 8/8) + Integration (1/2, 2/2) + dast-smoke red in one shot, blocking
# the innocuous updates riding along with it. Un-ignore once typescript-eslint
# widens the peer, and migrate TS majors intentionally (own PR, own CI run).
- dependency-name: "typescript"
update-types: ["version-update:semver-major"]
# jscpd v5 is a Rust rewrite (native binary, no Node.js programmatic API).
# scripts/check/check-duplication.mjs is deliberately pinned to jscpd@4 (it
# parses jscpd-report.json against a frozen baseline). A v5 major would break
# the duplication gate — migrate the gate intentionally, not via dependabot.
- dependency-name: "jscpd"
update-types: ["version-update:semver-major"]
# ioredis is a SOFT/optional dependency loaded through a dynamic import
# (src/lib/quota/redisQuotaStore.ts — "Redis driver requires ioredis package"),
# so a breaking major never fails at build or typecheck time: the only consumers
# are the distributed quota store (redisQuotaStore.ts, storeFactory.ts) and the
# `import type Redis` in src/shared/utils/rateLimiter.ts. Nothing in the unit or
# vitest suites exercises a live Redis connection, so a v5→v6 API break would ship
# green and only surface at runtime for operators running distributed quota — the
# exact users least able to absorb it. #9310 grouped that major with 9 harmless
# bumps; majors here need their own PR and a deliberate migration review.
- dependency-name: "ioredis"
update-types: ["version-update:semver-major"]
# @huggingface/transformers is HARD-PINNED at 3.5.2 (exact, no caret) — FROZEN.
# It is load-bearing for the LLMLingua ONNX compression engine (open-sse/services/
# compression/engines/llmlingua/ — worker.ts pins @huggingface/transformers@3.5.2)

View File

@@ -9,15 +9,10 @@
## 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):
- [ ] Change type: provider / routing / UI / i18n / CLI / DB / build-deploy / other
- [ ] Focused tests and category gates from the golden path
- [ ] `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
- [ ] `npm run test:unit`
- [ ] `npm run test:coverage`
- [ ] Coverage is still `>= 60%` for statements, lines, functions, and branches
- [ ] SonarQube PR analysis is green or any remaining issues are explicitly documented below
## Tests Added Or Updated
@@ -32,4 +27,4 @@ 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

@@ -33,35 +33,17 @@ jobs:
docs: ${{ steps.classify.outputs.docs }}
i18n: ${{ steps.classify.outputs.i18n }}
workflow: ${{ steps.classify.outputs.workflow }}
testsOnly: ${{ steps.classify.outputs.testsOnly }}
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v7
with:
node-version: ${{ env.CI_NODE_VERSION }}
# 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
- id: classify
env:
EVENT_NAME: ${{ github.event_name }}
BASE_SHA: ${{ github.event.pull_request.base.sha }}
HEAD_SHA: ${{ github.event.pull_request.head.sha }}
run: |
# Single source of truth: scripts/quality/classify-pr-changes.mjs
# (unit-tested). Push/dispatch always enable every lane.
if [ "$EVENT_NAME" != "pull_request" ]; then
{
echo "code=true"
@@ -72,18 +54,51 @@ jobs:
exit 0
fi
code=false
docs=false
i18n=false
workflow=false
git diff --name-only "$BASE_SHA" "$HEAD_SHA" > changed-files.txt
node scripts/quality/classify-pr-changes.mjs changed-files.txt >> "$GITHUB_OUTPUT"
while IFS= read -r file; do
case "$file" in
.github/workflows/*|.zizmor.yml)
workflow=true
code=true
;;
docs/*|*.md)
docs=true
;;
src/i18n/*|src/i18n/messages/*|scripts/i18n/*|config/i18n.json)
i18n=true
code=true
;;
src/*|open-sse/*|bin/*|electron/*|tests/*|scripts/*|package.json|package-lock.json|tsconfig*.json|next.config.*|vitest*.config.*|playwright.config.*)
code=true
;;
db/*|config/*)
code=true
;;
*)
code=true
;;
esac
done < changed-files.txt
{
echo "code=$code"
echo "docs=$docs"
echo "i18n=$i18n"
echo "workflow=$workflow"
} >> "$GITHUB_OUTPUT"
lint:
name: Lint
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).
# Path filter: pure docs / pure message-catalog PRs skip the code lint bag + typecheck.
# Existence reason of this job is code regression; docs/i18n have dedicated jobs.
if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false && needs.changes.outputs.code == 'true') }}
if: ${{ github.event_name != 'pull_request' || github.event.pull_request.draft == false }}
env:
# tsx gates below (known-symbols, route-guard-membership) import modules that
# open SQLite on load; provide DB env so a fresh CI DB initializes cleanly.
@@ -94,34 +109,14 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: npm run check:node-runtime
- run: npm run audit:deps
- name: Restore ESLint file cache
uses: actions/cache@v6
with:
path: |
.eslintcache
.eslintcache-complexity
key: eslint-${{ runner.os }}-${{ hashFiles('eslint.config.mjs', 'eslint.complexity-ratchets.config.mjs', 'config/quality/eslint-suppressions.json', 'package-lock.json') }}
restore-keys: |
eslint-${{ runner.os }}-
# Single ESLint inventory (JSON) — quality-gate reuses the artifact instead of
# a second cold full-tree pass for eslintWarnings ratchet counts.
- name: ESLint (JSON report)
run: npm run lint:json
- name: Upload ESLint results
if: always()
uses: actions/upload-artifact@v7
with:
name: eslint-results
path: .artifacts/eslint-results.json
if-no-files-found: warn
retention-days: 7
- run: npm run lint
- run: npm run check:cycles
- run: npm run check:route-validation:t06
- run: npm run check:any-budget:t11
@@ -137,44 +132,21 @@ 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.
- name: hadolint (Dockerfile)
run: docker run --rm -i hadolint/hadolint@sha256:27086352fd5e1907ea2b934eb1023f217c5ae087992eb59fde121dce9c9ff21e hadolint --failure-threshold error - < Dockerfile
- run: npm run check:lockfile
- run: npm run check:licenses
# check:docs-sync is run by the docs-sync-strict job (via check:docs-all) and the
# husky pre-commit hook; the standalone copy here was redundant (ROI dedup).
- run: npm run typecheck:core
# #7033: typecheck:core's curated file allowlist does not cover
# src/app/(dashboard) TSX (and next.config.mjs sets ignoreBuildErrors:
# true, so `next build` never type-checks it either) — orphaned
# identifiers there (see #6625/#6909) were invisible to CI. This gate
# runs tsc scoped to the dashboard tree against a frozen baseline of
# pre-existing errors; only NEW errors fail it.
- run: npm run check:dashboard-typecheck
# typecheck:noimplicit:core dropped from this job (2026-07 optimize):
# it was advisory (continue-on-error) and largely subsumed by the blocking
# check:type-coverage ratchet in quality-gate. Local: npm run typecheck:noimplicit:core.
# typecheck:noimplicit:core is a forward-looking gate (noImplicitAny).
# Run informationally for now — many pre-existing call sites still need
# explicit annotations; track in a dedicated follow-up.
- run: npm run typecheck:noimplicit:core
continue-on-error: true
quality-gate:
name: Quality Ratchet
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]
needs: test-coverage
# Run even when test-coverage was SKIPPED/FAILED (e.g. a single flaky Coverage
# Shard breaks the shard→coverage→ratchet chain). The DETERMINISTIC ratchets
# (eslint / complexity / cognitive-complexity / duplication / codeql) do NOT need
@@ -183,8 +155,7 @@ jobs:
# release PR #4854, where the drift cascade only surfaced post-merge in #5029).
# The coverage.* metrics degrade gracefully: the download is continue-on-error and
# the ratchet runs with --allow-missing, so absent coverage is skipped, not failed.
# Path filter: code-only — pure docs/i18n PRs have nothing for these ratchets to guard.
if: ${{ !cancelled() && !contains(github.event.pull_request.labels.*.name, 'hotfix') && (github.event_name != 'pull_request' || (github.event.pull_request.draft == false && needs.changes.outputs.code == 'true' && (needs.lint.result == 'success' || needs.lint.result == 'failure'))) }}
if: ${{ !cancelled() && (github.event_name != 'pull_request' || github.event.pull_request.draft == false) }}
# security-events: read lets the CodeQL ratchet read open code-scanning alerts
# via `gh api .../code-scanning/alerts`. contents: read keeps checkout working.
permissions:
@@ -194,20 +165,11 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- name: Restore ESLint file cache
uses: actions/cache@v6
with:
path: |
.eslintcache
.eslintcache-complexity
key: eslint-${{ runner.os }}-${{ hashFiles('eslint.config.mjs', 'eslint.complexity-ratchets.config.mjs', 'config/quality/eslint-suppressions.json', 'package-lock.json') }}
restore-keys: |
eslint-${{ runner.os }}-
# Coverage mergeada (coverage-summary.json) p/ o ratchet de cobertura.
# continue-on-error: o artifact pode não existir se a job test-coverage foi
# SKIPPED (shard flaky). Nesse caso collect-metrics pula coverage.* (ausente sem
@@ -218,13 +180,6 @@ jobs:
with:
name: coverage-report
path: coverage/
# Prefer lint job's ESLint JSON (one inventory, two consumers).
- name: Download ESLint results
continue-on-error: true
uses: actions/download-artifact@v8
with:
name: eslint-results
path: .artifacts/
- run: npm run quality:collect
# Catraca: falha se qualquer métrica regredir vs quality-baseline.json (commitado).
# Hoje: contagem de warnings do ESLint. Fase 4 estende com cobertura (lida do
@@ -246,13 +201,15 @@ jobs:
# para não pesar no caminho crítico do lint.
- name: Duplication ratchet
run: npm run check:duplication
# Complexity + cognitive: one ESLint walk, two independent baselines (by ruleId).
- name: Complexity + cognitive ratchets
run: npm run check:complexity-ratchets
# Fase 7 INT: dead-code, type-coverage promovidos de advisory (quality-extended)
# para BLOQUEANTES aqui. cognitive-complexity is folded into the step above.
- name: Complexity ratchet
run: npm run check:complexity
# Fase 7 INT: dead-code, cognitive-complexity, type-coverage promovidos de
# advisory (quality-extended) para BLOQUEANTES aqui. Os 3 leem seus baseline
# de quality-baseline.json e saem 1 em regressão.
- name: Dead-code ratchet (knip)
run: npm run check:dead-code
- name: Cognitive complexity ratchet (sonarjs)
run: npm run check:cognitive-complexity
- name: Type coverage ratchet
run: npm run check:type-coverage
- name: Compression budget ratchet (F2.4 / N4)
@@ -290,11 +247,9 @@ jobs:
quality-extended:
name: Quality Gates (Extended)
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).
# Path filter: code-only (scanners/ratchets target production surface).
if: ${{ !contains(github.event.pull_request.labels.*.name, 'hotfix') && (github.event_name != 'pull_request' || (github.event.pull_request.draft == false && needs.changes.outputs.code == 'true')) }}
if: ${{ github.event_name != 'pull_request' || github.event.pull_request.draft == false }}
steps:
# fetch-depth: 0 — the OpenAPI breaking-change gate (oasdiff) reads the base
# spec via `git show <base_ref>:docs/openapi.yaml`; a shallow clone
@@ -303,7 +258,7 @@ jobs:
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -353,16 +308,8 @@ jobs:
install -m 0755 /tmp/osv/*linux_amd64 "$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
@@ -410,16 +357,14 @@ jobs:
docs-sync-strict:
name: Docs Sync (Strict)
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')) }}
if: ${{ github.event_name != 'pull_request' || github.event.pull_request.draft == false }}
steps:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -434,20 +379,19 @@ jobs:
run: npm run check:openapi-coverage
- name: OpenAPI security-tier consistency (advisory)
run: npm run check:openapi-security-tiers
# One FS inventory of src/app/api for both anti-hallucination directions.
- name: API docs refs (openapi + prose → routes)
run: npm run check:api-docs-refs
- name: OpenAPI spec paths resolve to real routes (anti-hallucination)
run: npm run check:openapi-routes
- name: Doc /api refs resolve to real routes (anti-hallucination)
run: npm run check:docs-symbols
- name: i18n translation drift (warn)
run: node scripts/i18n/check-translation-drift.mjs --warn
docs-lint:
name: Docs Lint (prose — advisory)
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).
# Prose/markdown only — skip when the PR has no doc surface.
if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false && needs.changes.outputs.docs == 'true') }}
if: ${{ github.event_name != 'pull_request' || github.event.pull_request.draft == false }}
# Advisory (warning-first): prose/markdown style must not block merges while the
# existing doc corpus is brought up to style. Promote to blocking once it converges.
continue-on-error: true
@@ -455,7 +399,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -474,52 +418,19 @@ jobs:
i18n-ui-coverage:
name: i18n UI Coverage
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')) }}
if: ${{ github.event_name != 'pull_request' || github.event.pull_request.draft == false }}
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@v7
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
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-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@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
# D4 (plano mestre testes+CI): a matrix de ~40 jobs de <1min por idioma saturava sozinha
# a concorrência de jobs da conta (Free = 20 slots, compartilhados entre TODOS os repos)
@@ -529,17 +440,15 @@ jobs:
i18n:
name: i18n Validation (all languages)
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).
# Message-catalog / i18n-tooling only — pure code without i18n surface skips this lane.
if: ${{ github.event_name != 'pull_request' || (github.event.pull_request.draft == false && needs.changes.outputs.i18n == 'true') }}
if: ${{ github.event_name != 'pull_request' || github.event.pull_request.draft == false }}
continue-on-error: true
steps:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-python@v7
- uses: actions/setup-python@v6
with:
python-version: "3.12"
- name: Validate all languages
@@ -577,11 +486,11 @@ jobs:
with:
persist-credentials: false
fetch-depth: 0
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
- name: Fetch base branch
run: git fetch --no-tags origin "${GITHUB_BASE_REF}"
run: git fetch --no-tags origin "${GITHUB_BASE_REF}" --depth=1
- name: Validate source changes include tests
run: node scripts/check/check-pr-test-policy.mjs --summary-file .artifacts/pr-test-policy.md
# Anti test-masking: flag net assert removal / new assert.ok(true) in changed tests.
@@ -616,7 +525,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -664,7 +573,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -684,26 +593,12 @@ jobs:
- name: Assert dist/server.js exists
run: test -f dist/server.js || (echo "dist/server.js missing — build:cli did not assemble correctly" && exit 1)
- run: npm run check:pack-artifact
# WS1.2 (#7065 class): pack the real tarball, install it into a clean prefix and
# BOOT it to a healthy /api/monitoring/health — the gate that structure checks
# cannot provide (3 releases shipped boot-crashing tarballs with green lists).
- name: Boot-smoke the packed tarball
run: npm run check:pack-boot
electron-package-smoke:
name: Electron Package Smoke (${{ matrix.os }})
runs-on: ${{ matrix.os }}
timeout-minutes: 30
name: Electron Package Smoke
runs-on: ubuntu-latest
timeout-minutes: 25
needs: build
# WS1.5 (v3.8.49 plan): the Electron rebuild/spawn path previously executed for
# the FIRST time on the release tag — the v3.8.48 Windows bug (npx.cmd spawned
# without shell, CVE-2024-27980 behavior change) could only surface at release.
# windows-latest runs prepare:bundle (the ABI rebuild + spawn plan) per release
# PR; ubuntu keeps the full pack + headless smoke.
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, windows-latest]
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
CSC_IDENTITY_AUTO_DISCOVERY: "false"
@@ -711,7 +606,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -729,21 +624,9 @@ jobs:
working-directory: electron
run: npm install --no-audit --no-fund
- name: Pack Electron app
if: runner.os == 'Linux'
working-directory: electron
run: npm run pack
# ADVISORY while the new Windows leg matures (repo convention, dast-smoke
# precedent): its first-ever real run (2026-07-15, run 29457533565) died in
# 0.7s with the error swallowed by pwsh — bash shell captures stderr and
# continue-on-error keeps the heavy gate green while we harden it (#7336).
- name: Prepare Electron standalone (Windows ABI rebuild + spawn path)
if: runner.os == 'Windows'
working-directory: electron
continue-on-error: true
shell: bash
run: npm run prepare:bundle 2>&1
- name: Smoke packaged Electron app
if: runner.os == 'Linux'
env:
ELECTRON_SMOKE_TIMEOUT_MS: 60000
run: xvfb-run -a npm run electron:smoke:packaged
@@ -751,13 +634,7 @@ jobs:
test-unit:
name: Unit Tests (${{ matrix.shard }}/8)
# Same dynamic-runner rule as Build (own-origin only; fallback ubuntu-latest).
# 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-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
@@ -778,7 +655,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -809,33 +686,10 @@ jobs:
path: coverage-shard/*.json
if-no-files-found: error
test-bun-sqlite:
name: Bun SQLite Compatibility
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@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-latest).
# 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-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
@@ -848,30 +702,19 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
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).
# WS5.2/5.3 (v3.8.49 plan): JUnit output feeds Trunk Flaky Tests (advisory upload
# below). node:test stays OUT of the first wave (fd1-sensitive reporter stream).
- run: npm run test:vitest -- --reporter=default --reporter=junit --outputFile.junit=trunk-junit/vitest-mcp.xml
# vitest:ui went back to 870/870 green in the v3.8.49 quality plan (WS6.1,
# PR #7127 — 69 fails triaged: matchMedia polyfill, node:testvitest migration,
# CompareTab D22 cap). Promoted to BLOCKING per the plan's post-merge step.
- run: npm run test:vitest:ui -- --reporter=default --reporter=junit --outputFile.junit=trunk-junit/vitest-ui.xml
# Trunk Flaky Tests upload — advisory (never blocks), own-origin only (fork PRs
# have no TRUNK_TOKEN). Pinned by SHA (tag v2.1.2).
- name: Upload test results to Trunk (advisory)
if: ${{ always() && (github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository) }}
- run: npm run test:vitest
# vitest:ui is RED today (14 fails — UI component drift accumulated while the
# suite never ran in CI). Informational until the Fase 6A triage (2026-06-16+)
# fixes the components/tests; then drop continue-on-error to make it blocking.
- run: npm run test:vitest:ui
continue-on-error: true
uses: trunk-io/analytics-uploader@385f1ccdf345b4532dc4b6c665dd432b702b8e28 # v2.1.2
with:
junit-paths: trunk-junit/**/*.xml
org-slug: omniroute
token: ${{ secrets.TRUNK_TOKEN }}
# Node 24/26 compatibility matrices moved to .github/workflows/nightly-compat.yml
# (plano mestre testes+CI, Eixo D2 — they cost ~28% of every heavy run to catch a
@@ -880,12 +723,9 @@ jobs:
test-coverage:
name: Coverage
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).
timeout-minutes: 20
timeout-minutes: 10
needs: test-unit
if: ${{ !cancelled() && needs.test-unit.result == 'success' && !contains(github.event.pull_request.labels.*.name, 'hotfix') }}
if: ${{ !cancelled() && needs.test-unit.result == 'success' }}
env:
JWT_SECRET: ci-test-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-test-api-key-secret-long
@@ -893,7 +733,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -933,7 +773,6 @@ jobs:
--merge-async \
--reporter=text-summary \
--reporter=json-summary \
--reporter=lcov \
--exclude=tests/** \
--exclude=**/*.test.* \
--check-coverage \
@@ -955,18 +794,6 @@ jobs:
> coverage/coverage-report.md
fi
cat coverage/coverage-report.md >> "$GITHUB_STEP_SUMMARY"
# WS5.6 (D7, v3.8.49 plan): patch coverage on the PR diff via Codecov —
# informational during calibration (codecov.yml sets informational: true);
# promote to blocking only after ~2 weeks without false blocks. The lcov
# reporter above also fixes coverage/lcov.info being silently absent
# (if-no-files-found: warn) — Sonar consumes the same file.
- name: Upload coverage to Codecov (informational)
if: always()
uses: codecov/codecov-action@fb8b3582c8e4def4969c97caa2f19720cb33a72f # v7.0.0
with:
files: coverage/lcov.info
token: ${{ secrets.CODECOV_TOKEN }}
fail_ci_if_error: false
- name: Upload coverage artifacts
if: always()
uses: actions/upload-artifact@v7
@@ -991,14 +818,10 @@ jobs:
with:
persist-credentials: false
fetch-depth: 0
# The upload strips the common `coverage/` prefix, so the artifact root holds
# lcov.info directly — download into coverage/ so it lands at coverage/lcov.info,
# where sonar.javascript.lcov.reportPaths expects it (path: . left the Sonar
# new-code coverage at 0% every scan).
- uses: actions/download-artifact@v8
with:
name: coverage-report
path: coverage/
path: .
- name: Explain SonarQube skip
if: ${{ github.event_name != 'pull_request' || env.SONAR_TOKEN == '' || env.SONAR_HOST_URL == '' }}
run: |
@@ -1117,12 +940,7 @@ jobs:
# ~33%. Playwright browser is cached across runs (~1.5min saved per shard).
# Heavy shard target: ≤20min (was ~40min). Timeout 45min to cover slow runners.
timeout-minutes: 45
needs: [build, changes]
# WS3.1 hotfix fast-lane: the 9-shard E2E matrix is the CI critical path (~25min).
# It skips for (a) PRs labeled `hotfix` (entry policy in docs/ops/RELEASE_CHECKLIST.md:
# production-broken only, full-suite evidence from the previous green run linked in the
# PR) and (b) tests-only diffs outside tests/e2e/ (cannot change the served app).
if: ${{ needs.changes.outputs.testsOnly != 'true' && !contains(github.event.pull_request.labels.*.name, 'hotfix') }}
needs: build
strategy:
fail-fast: false
matrix:
@@ -1136,14 +954,14 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- uses: ./.github/actions/npm-ci-retry
- run: npm run check:node-runtime
- name: Cache Playwright browsers
uses: actions/cache@v6
uses: actions/cache@v6.1.0
with:
path: ~/.cache/ms-playwright
key: playwright-chromium-${{ runner.os }}-${{ hashFiles('package-lock.json') }}
@@ -1157,34 +975,7 @@ jobs:
- name: Extract Next.js build artifact
run: |
tar -xzf /tmp/e2e-build.tar.gz
# WS4.1: duration-balanced shards (LPT over config/quality/e2e-timings.json).
# Measured skew of plain --shard was 14× (24m47s vs 1m47s) — E2E was the CI
# critical path. The balancer self-verifies completeness and exits non-zero on
# any inconsistency, falling back to plain --shard (never fewer specs).
- name: Run E2E tests (duration-balanced shard)
env:
SHARD: ${{ matrix.shard }}
PLAYWRIGHT_JUNIT_OUTPUT_NAME: junit-e2e-results.xml
run: |
if FILES=$(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
npx playwright test $(echo "$FILES" | tr '\n' ' ') --reporter=line,junit
else
echo "[e2e-balance] balancer unavailable — plain --shard fallback"
npx playwright test tests/e2e/*.spec.ts --shard="$SHARD"/9 --reporter=line,junit
fi
# WS5.2/5.3: Trunk Flaky Tests upload — advisory, own-origin only, SHA-pinned.
- 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
with:
junit-paths: junit-e2e-results.xml
org-slug: omniroute
token: ${{ secrets.TRUNK_TOKEN }}
- run: npx playwright test tests/e2e/*.spec.ts --shard=${{ matrix.shard }}/9
test-integration:
name: Integration Tests (${{ matrix.shard }}/2)
@@ -1207,7 +998,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -1230,7 +1021,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -1247,7 +1038,6 @@ jobs:
- lint
- docs-sync-strict
- i18n-ui-coverage
- i18n-glossary-zhcn
- i18n
- pr-test-policy
- build
@@ -1272,8 +1062,6 @@ 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 "$1" in
@@ -1288,29 +1076,6 @@ jobs:
echo "# 🚀 CI Dashboard" >> "$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"
@@ -1318,7 +1083,6 @@ jobs:
echo "| Lint | $(status '${{ needs.lint.result }}') |" >> "$GITHUB_STEP_SUMMARY"
echo "| Docs Sync (Strict) | $(status '${{ needs.docs-sync-strict.result }}') |" >> "$GITHUB_STEP_SUMMARY"
echo "| i18n UI Coverage | $(status '${{ needs.i18n-ui-coverage.result }}') |" >> "$GITHUB_STEP_SUMMARY"
echo "| i18n Glossary (zh-CN) | $(status '${{ needs.i18n-glossary-zhcn.result }}') |" >> "$GITHUB_STEP_SUMMARY"
echo "| PR Test Policy | $(status '${{ needs.pr-test-policy.result }}') |" >> "$GITHUB_STEP_SUMMARY"
echo "| SonarQube | $(status '${{ needs.sonarqube.result }}') |" >> "$GITHUB_STEP_SUMMARY"

View File

@@ -19,13 +19,13 @@ jobs:
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
- uses: github/codeql-action/init@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
with:
languages: javascript-typescript
queries: security-extended
- uses: github/codeql-action/analyze@e4fba868fa4b1b91e1fdab776edc8cfbe6e9fb81 # v4.37.3
- uses: github/codeql-action/analyze@54f647b7e1bb85c95cddabcd46b0c578ec92bc1a # v4.36.3
with:
category: "/language:javascript-typescript"

View File

@@ -2,45 +2,28 @@ name: DAST smoke (PR)
on:
pull_request:
branches: ["main", "release/**"]
# Runner-cost guard (#8084): the CLI-bundle build alone is 6-11min; a docs-only PR
# cannot change DAST behavior, so skip the whole workflow for pure docs/markdown
# changes. Any code path in the diff still runs the full smoke.
paths-ignore:
- "docs/**"
- "**/*.md"
permissions:
contents: read
# Superseded runs on the same PR must not stack 25-minute advisory builds
# (force-push storms were holding 2-3 runners each). Same group rule as quality.yml.
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
dast-smoke:
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
# Build CLI bundle alone varies 6-11min on GitHub-hosted runners (3 consecutive
# timeouts observed on 2026-07-14 with the old 12min cap killing schemathesis
# mid-run) — 25min leaves real headroom for the actual DAST steps.
timeout-minutes: 25
timeout-minutes: 12
env:
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
- uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
with:
node-version: "24"
cache: npm
- run: npm ci
- name: Build CLI bundle
env:
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
run: npm run build:cli
- name: Start OmniRoute
env:
@@ -53,20 +36,14 @@ jobs:
if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo up; break; fi
sleep 2
done
- uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
- uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
with:
python-version: "3.12"
- 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

@@ -155,13 +155,13 @@ jobs:
uses: docker/setup-buildx-action@v4
- name: Login to Docker Hub
uses: docker/login-action@v4.5.2
uses: docker/login-action@v4
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Login to GitHub Container Registry
uses: docker/login-action@v4.5.2
uses: docker/login-action@v4
with:
registry: ghcr.io
username: ${{ github.actor }}
@@ -255,13 +255,13 @@ jobs:
uses: docker/setup-buildx-action@v4
- name: Login to Docker Hub
uses: docker/login-action@v4.5.2
uses: docker/login-action@v4
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Login to GitHub Container Registry
uses: docker/login-action@v4.5.2
uses: docker/login-action@v4
with:
registry: ghcr.io
username: ${{ github.actor }}
@@ -390,7 +390,7 @@ jobs:
- name: Upload Trivy SARIF to Security tab
if: needs.prepare.outputs.version != 'main'
continue-on-error: true
uses: github/codeql-action/upload-sarif@v4.37.3
uses: github/codeql-action/upload-sarif@v4
with:
sarif_file: trivy-results.sarif
category: trivy-image

View File

@@ -88,7 +88,7 @@ jobs:
with:
persist-credentials: false
- name: Setup Node
uses: actions/setup-node@v7
uses: actions/setup-node@v6
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: ${{ matrix.platform == 'linux' && '0' || '1' }}
run: npm run build
- name: Sync version in electron/package.json
@@ -213,12 +201,6 @@ jobs:
[ -f "$file" ] && cp "$file" "../../release-assets/OmniRoute.exe" && break
done
fi
# electron-updater manifests (latest.yml / latest-mac.yml / latest-linux.yml)
# must be published alongside the installers, or autoUpdater fails with
# "Cannot find latest.yml in the latest release artifacts" (#6766).
for file in latest*.yml; do
[ -f "$file" ] && cp "$file" ../../release-assets/
done
- name: Upload artifacts
uses: actions/upload-artifact@v7
@@ -229,16 +211,6 @@ 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-latest
permissions:
contents: write # softprops/action-gh-release creates the GitHub Release
@@ -249,33 +221,11 @@ jobs:
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:
@@ -313,53 +263,11 @@ jobs:
release-assets/*.AppImage
release-assets/*.deb
release-assets/*.blockmap
release-assets/*.yml
release-assets/*.source.tar.gz
release-assets/*.source.zip
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: ${{ !cancelled() && needs.release.result == 'success' }}
runs-on: ubuntu-latest
permissions:
contents: read
steps:
- name: Assert every platform is present on the release
env:
# Regex-validated (^v[0-9]+\.[0-9]+\.[0-9]+$) 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

@@ -44,7 +44,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm

View File

@@ -66,25 +66,12 @@ jobs:
with:
ref: ${{ needs.resolve-branch.outputs.target }}
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
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 ubuntu-latest 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)
@@ -106,7 +93,7 @@ jobs:
with:
ref: ${{ needs.resolve-branch.outputs.target }}
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ matrix.node }}
cache: npm

View File

@@ -15,13 +15,11 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with: { node-version: "24", cache: npm }
- run: npm ci
- name: Build CLI bundle
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
env: { JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation }
run: npm run build:cli
- name: Start OmniRoute (block mode)
env:
@@ -67,16 +65,14 @@ jobs:
with:
persist-credentials: false
if: steps.gate.outputs.run == 'true'
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
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
if: steps.gate.outputs.run == 'true'
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
env: { JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation }
run: npm run build:cli
- name: Start OmniRoute
if: steps.gate.outputs.run == 'true'
@@ -90,7 +86,7 @@ jobs:
if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo up; break; fi
sleep 2
done
- uses: actions/setup-python@v7
- uses: actions/setup-python@v6
if: steps.gate.outputs.run == 'true'
with: { python-version: "3.12" }
- run: pip install garak

View File

@@ -107,7 +107,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm
@@ -148,10 +148,10 @@ jobs:
runs-on: ubuntu-latest
timeout-minutes: 15
steps:
- uses: actions/checkout@v7
- uses: actions/checkout@v6
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
- name: Download all mutation reports

View File

@@ -13,7 +13,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm

View File

@@ -1,18 +1,11 @@
name: Release-Green (continuous)
name: Nightly Release-Green
# Solution D — continuous, NON-BLOCKING drift signal for the active release branch.
#
# WHY: the full gate (ci.yml) only runs on the release PR (PR → main), so reds
# accrue silently on release/** and explode — in layers — at release time. This
# workflow reproduces the release-equivalent validation on the release branch and,
# when there are HARD failures, opens/updates a single tracking issue.
#
# WS5.1 (v3.8.49 quality plan) — two modes:
# push to release/v* (code paths) → --quick (fast HARD gates, ~5-8min). Catches the
# captain's direct pushes (sync-back — the one ungated write path) AND the merged
# COMBINATION right after every PR merge, attributing the offending push range in
# the issue. Base-red MTTD drops from ≤24h to ≤~15min after the offending push.
# schedule (3×/day) → full --with-build --full-ci (the deep sweep incl. build+suites).
# nightly reproduces the release-equivalent validation on the active release branch
# HEAD and, when there are HARD failures, opens/updates a single tracking issue.
#
# It is NOT a required status check and never touches a contributor PR — it only
# reports. Ratchet drift (eslint warnings / cognitive-complexity / file-size) is
@@ -21,23 +14,8 @@ name: Release-Green (continuous)
# package-artifact) flip the issue open.
on:
push:
branches: ["release/v*", "main"]
paths:
- "src/**"
- "open-sse/**"
- "bin/**"
- "electron/**"
- "scripts/**"
- "tests/**"
- "config/**"
- "package.json"
- "package-lock.json"
- "tsconfig*.json"
schedule:
- cron: "23 5 * * *" # full sweep — off-peak, distinct from other nightlies
- cron: "23 12 * * *" # full sweep — midday (WS5.1: 3×/day instead of 1×)
- cron: "23 18 * * *" # full sweep — evening
- cron: "23 5 * * *" # 05:23 UTC daily — off-peak, distinct from other nightlies
workflow_dispatch:
inputs:
branch:
@@ -50,9 +28,7 @@ permissions:
issues: write
concurrency:
# push storms during merge campaigns collapse to the newest commit per branch;
# scheduled full sweeps keep their own single lane.
group: release-green-${{ github.event_name }}-${{ github.ref }}
group: nightly-release-green
cancel-in-progress: true
env:
@@ -61,9 +37,6 @@ env:
jobs:
release-green:
name: Validate active release branch
# On a push, only run for release/* pushes — a push to main is handled by the
# main-green job below. Schedule/dispatch always run (they validate the highest release).
if: ${{ github.event_name != 'push' || startsWith(github.ref_name, 'release/') }}
# Dynamic runner: with USE_VPS_RUNNER=true (release window / on-demand pre-flight)
# 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.
@@ -83,15 +56,10 @@ jobs:
id: branch
env:
INPUT_BRANCH: ${{ github.event.inputs.branch }}
EVENT_NAME: ${{ github.event_name }}
PUSHED_REF: ${{ github.ref_name }}
run: |
set -euo pipefail
if [ -n "${INPUT_BRANCH:-}" ]; then
TARGET="$INPUT_BRANCH"
elif [ "$EVENT_NAME" = "push" ]; then
# validate exactly what was pushed, not the highest branch
TARGET="$PUSHED_REF"
else
# highest release/vX.Y.Z by semver among remote branches
TARGET=$(git for-each-ref --format='%(refname:short)' 'refs/remotes/origin/release/v*' \
@@ -116,7 +84,7 @@ jobs:
git checkout "$TARGET"
git log -1 --oneline
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm
@@ -125,27 +93,11 @@ jobs:
- name: Release-green validation (full)
id: validate
env:
EVENT_NAME: ${{ github.event_name }}
run: |
set +e
# --hermetic: scrub live-test trigger vars (self-hosted runner may carry
# operator env; hosted ignores the unknown flag before #6300 lands).
# push → --quick: fast HARD gates only (~5-8min), per-merge signal.
# schedule/dispatch → --with-build --full-ci: ALSO run every static gate from
# ci.yml's gate jobs (lint, quality-gate, quality-extended, docs-sync-strict,
# pr-test-policy) + build + full suites. PRs into release/** only get the
# fast-gates, so these accrue silently and explode in layers on the release PR
# (v3.8.46: 11 static base-reds leaked).
if [ "$EVENT_NAME" = "push" ]; then
MODE="--quick"
else
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
node scripts/quality/validate-release-green.mjs --json --hermetic $MODE \
node scripts/quality/validate-release-green.mjs --json --with-build --hermetic \
1> release-green.json 2> release-green.log
echo "exit=$?" >> "$GITHUB_OUTPUT"
echo "------- report -------"
@@ -157,28 +109,15 @@ jobs:
GH_TOKEN: ${{ github.token }}
TARGET: ${{ steps.branch.outputs.target }}
RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
EVENT_NAME: ${{ github.event_name }}
BEFORE_SHA: ${{ github.event.before }}
AFTER_SHA: ${{ github.event.after }}
run: |
set -euo pipefail
TITLE="🔴 Release branch not green: ${TARGET}"
{
echo "The **release-green** validation found HARD failures on \`${TARGET}\`."
echo "The nightly **release-green** validation found HARD failures on \`${TARGET}\`."
echo "These are real defects that would block the release PR — fix them in the"
echo "originating PR branch (via co-authorship), not by demanding it from contributors."
echo ""
echo "**Run:** ${RUN_URL} (mode: ${EVENT_NAME})"
# WS5.1 attribution: on push events the offending change IS this push's range
# (one merge per push in the normal queue), so name it — no bisect needed.
if [ "$EVENT_NAME" = "push" ] && [ -n "${BEFORE_SHA:-}" ] && \
git cat-file -e "$BEFORE_SHA" 2>/dev/null; then
echo ""
echo "**Offending push range** (\`${BEFORE_SHA:0:9}..${AFTER_SHA:0:9}\`):"
echo '```'
git log --no-decorate --oneline "${BEFORE_SHA}..${AFTER_SHA}" | head -20
echo '```'
fi
echo "**Run:** ${RUN_URL}"
echo ""
echo '```'
sed -n '/──────── verdict ────────/,$p' release-green.log || tail -40 release-green.log
@@ -198,250 +137,10 @@ jobs:
- name: Upload report artifact
if: always()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v4
with:
name: release-green-report
path: |
release-green.json
release-green.log
if-no-files-found: ignore
# Companion arm for `main`. Under the parallel-cycle model, main only receives merged
# work at the release squash — so a gate/infra fix that lands only on release leaves
# main red the whole cycle, and repo-wide gates (CodeQL alert count, ratchet baselines)
# turn EVERY PR into main red on a check unrelated to its diff. This detects that and
# opens a "🔴 main not green" tracking issue. The PREVENTION is the companion-PR reflex
# (Hard Rule #21 area / _shared/merge-gates.md §8); this is the automated backstop.
main-green:
name: Validate main branch
# 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-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@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@v7
with:
node-version: "24"
cache: npm
- uses: ./.github/actions/npm-ci-retry
- name: Main-green validation
id: validate
env:
EVENT_NAME: ${{ github.event_name }}
run: |
set +e
# push (a merge into main) → --quick fast HARD gates; schedule/dispatch → full sweep.
if [ "$EVENT_NAME" = "push" ]; then
MODE="--quick"
else
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
node scripts/quality/validate-release-green.mjs --json --hermetic $MODE \
1> main-green.json 2> main-green.log
echo "exit=$?" >> "$GITHUB_OUTPUT"
echo "------- report -------"
cat main-green.log
- name: Open / update tracking issue on HARD failure
if: steps.validate.outputs.exit != '0'
env:
GH_TOKEN: ${{ github.token }}
RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
EVENT_NAME: ${{ github.event_name }}
run: |
set -euo pipefail
TITLE="🔴 main branch not green"
{
echo "The **main-green** validation found HARD failures on \`main\`."
echo ""
echo "Because \`main\` only receives merged work at the release squash, a gate/infra"
echo "fix that landed only on the release branch leaves \`main\` broken for the whole"
echo "cycle — and repo-wide gates (CodeQL alert count, ratchet baselines) then turn"
echo "**every open PR into main** red on a check unrelated to its diff. The fix is a"
echo "companion PR \`--base main\` carrying the release-side fix (see"
echo "\`_shared/merge-gates.md\` §8), NOT chasing each contributor PR."
echo ""
echo "**Run:** ${RUN_URL} (mode: ${EVENT_NAME})"
echo ""
echo '```'
sed -n '/──────── verdict ────────/,$p' main-green.log || tail -40 main-green.log
echo '```'
echo ""
echo "_Ratchet drift (eslint warnings / cognitive-complexity / file-size) is expected mid-cycle and did NOT, on its own, open this issue._"
} > issue-body.md
EXISTING=$(gh issue list --repo "$GITHUB_REPOSITORY" --state open \
--search "in:title $TITLE" --json number --jq '.[0].number' 2>/dev/null || echo "")
if [ -n "$EXISTING" ]; then
gh issue comment "$EXISTING" --repo "$GITHUB_REPOSITORY" --body-file issue-body.md
echo "Updated existing issue #$EXISTING"
else
gh issue create --repo "$GITHUB_REPOSITORY" --title "$TITLE" --body-file issue-body.md
fi
- name: Upload report artifact
if: always()
uses: actions/upload-artifact@v7
with:
name: main-green-report
path: |
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-latest
permissions:
contents: write
pull-requests: write
steps:
- uses: actions/checkout@v7
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: actions/setup-node@v7
with:
node-version: "24"
cache: npm
- 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

@@ -15,7 +15,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm
@@ -29,7 +29,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm
@@ -43,7 +43,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm
@@ -51,7 +51,6 @@ jobs:
- name: Build CLI bundle
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
run: npm run build:cli
- name: Start OmniRoute (background)
env:
@@ -95,7 +94,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "24"
cache: npm

View File

@@ -16,13 +16,11 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with: { node-version: "24", cache: npm }
- run: npm ci
- name: Build CLI bundle
env:
JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
OMNIROUTE_BUILD_BACKEND_ONLY: "1"
env: { JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation }
run: npm run build:cli
- name: Start OmniRoute (background)
env:
@@ -35,7 +33,7 @@ jobs:
if curl -sf http://localhost:20128/api/monitoring/health >/dev/null; then echo "server up"; break; fi
sleep 2
done
- uses: actions/setup-python@v7
- uses: actions/setup-python@v6
with: { python-version: "3.12" }
- name: Install schemathesis
run: pip install schemathesis

View File

@@ -22,14 +22,6 @@ on:
- latest
- next
- historic
publish_mode:
description: "staged = npm stage publish (owner approves with 2FA after the staged boot-verify); direct = legacy immediate publish (emergency fallback only)"
required: false
default: "staged"
type: choice
options:
- staged
- direct
workflow_call:
inputs:
version:
@@ -56,15 +48,8 @@ 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-latest' }}
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
@@ -78,7 +63,7 @@ jobs:
fetch-depth: 0
- name: Setup Node.js
uses: actions/setup-node@v7
uses: actions/setup-node@v6
with:
node-version: ${{ env.NPM_PUBLISH_NODE_VERSION }}
registry-url: https://registry.npmjs.org
@@ -152,74 +137,6 @@ jobs:
run: |
npm version "$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:
@@ -249,46 +166,8 @@ jobs:
TAG: ${{ github.ref_name }}
run: gh release upload "$TAG" sbom-npm.cdx.json --clobber
# WS1.2/WS1.3 (#7065 class): the artifact that is about to be published must
# BOOT. build:cli already assembled dist/ above; this packs+installs+boots the
# real tarball and fails the publish before anything reaches the registry.
- name: Boot-smoke the tarball before ANY publish
- name: Publish to npm
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
# human gate to AFTER the proof instead of before it. Requires npm >= 11.15
# (staged publishing GA 2026-05-22). publish_mode=direct is the emergency
# fallback (legacy immediate publish) via workflow_dispatch.
- name: Ensure npm supports staged publishing
if: steps.resolve.outputs.skip != 'true' && (github.event_name != 'workflow_dispatch' || inputs.publish_mode != 'direct')
run: |
set -euo pipefail
CUR=$(npm --version)
if ! node -e "const [a,b]='$(npm --version)'.split('.').map(Number); process.exit(a>11||(a===11&&b>=15)?0:1)"; then
# Pinned exact version (supply-chain: never float @latest in the publish
# job); bump deliberately when a newer npm is required.
echo "npm $CUR < 11.15 — installing pinned npm 11.15.0 for staged publishing"
npm install -g --ignore-scripts npm@11.15.0
fi
npm --version
- name: Publish to npm (staged — owner approves with 2FA)
if: steps.resolve.outputs.skip != 'true' && (github.event_name != 'workflow_dispatch' || inputs.publish_mode != 'direct')
env:
VERSION: ${{ steps.resolve.outputs.version }}
TAG: ${{ steps.resolve.outputs.tag }}
@@ -296,32 +175,10 @@ jobs:
run: |
set -euo pipefail
# Always pass --tag explicitly. Defense in depth: even if VERSION is
# accidentally an older release, the historic tag will NOT claim `@latest`.
npm stage publish --provenance --access public --tag "$TAG"
{
echo "## 📦 omniroute@$VERSION STAGED (not yet installable)"
echo ""
echo "The exact bytes are parked on the registry. To release them:"
echo '```'
echo "npm stage list omniroute # find the stage id"
echo "npm stage approve <id> # owner 2FA — THE publish"
echo '```'
echo "To verify the staged bytes first: npm stage download <id> → run"
echo "scripts/check/check-pack-boot.mjs against them (see RELEASE_CHECKLIST)."
echo "To discard: npm stage reject <id>."
} >> "$GITHUB_STEP_SUMMARY"
echo "✅ Staged omniroute@$VERSION (dist-tag=$TAG) — awaiting owner 'npm stage approve'"
- name: Publish to npm (DIRECT — emergency fallback)
if: steps.resolve.outputs.skip != 'true' && github.event_name == 'workflow_dispatch' && inputs.publish_mode == 'direct'
env:
VERSION: ${{ steps.resolve.outputs.version }}
TAG: ${{ steps.resolve.outputs.tag }}
NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
run: |
set -euo pipefail
# accidentally an older release, `npm publish --tag historic` will
# NOT promote it to `@latest`.
npm publish --provenance --access public --tag "$TAG"
echo "✅ Published omniroute@$VERSION (dist-tag=$TAG) [DIRECT mode]"
echo "✅ Published omniroute@$VERSION (dist-tag=$TAG)"
- name: Publish to GitHub Packages
if: steps.resolve.outputs.skip != 'true'
@@ -352,7 +209,7 @@ jobs:
# Full history needed for auto-bump: git diff against previous release tag
- name: Setup Node.js
uses: actions/setup-node@v7
uses: actions/setup-node@v6
with:
node-version: ${{ env.NPM_PUBLISH_NODE_VERSION }}
registry-url: https://registry.npmjs.org

View File

@@ -35,7 +35,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ matrix.node }}
cache: npm
@@ -52,7 +52,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "22"
cache: npm

View File

@@ -35,7 +35,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ matrix.node }}
cache: npm
@@ -51,7 +51,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: "20"
cache: npm

View File

@@ -21,110 +21,8 @@ env:
CI_NODE_VERSION: "24"
jobs:
# Same classifier as ci.yml (scripts/quality/classify-pr-changes.mjs) so PR→release
# path filters share existence reasons: code / docs / i18n / workflow.
changes:
name: Change Classification
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@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 }}
BASE_SHA: ${{ github.event.pull_request.base.sha }}
HEAD_SHA: ${{ github.event.pull_request.head.sha }}
run: |
if [ "$EVENT_NAME" != "pull_request" ]; then
{
echo "code=true"
echo "docs=true"
echo "i18n=true"
echo "workflow=true"
} >> "$GITHUB_OUTPUT"
exit 0
fi
git diff --name-only "$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') }}
# Dynamic runner — same fork-safe rule as ci.yml / fast-gates.
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' }}
# #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
with:
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # 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 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-latest
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
# One walk of src/app/api for openapi-routes + docs-symbols (both still fail independently).
- run: npm run check:api-docs-refs
- name: Docs accuracy (fabricated-docs + i18n mirrors, strict)
run: npm run check:docs-all
fast-gates:
name: Fast Quality Gates
needs: changes
# Code surface only — pure docs/i18n PRs skip this bag (docs-gates covers docs).
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 (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-latest, 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-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.
@@ -137,36 +35,19 @@ jobs:
with:
fetch-depth: 0
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
- name: Restore ESLint file cache
uses: actions/cache@v6
with:
path: |
.eslintcache
.eslintcache-complexity
key: eslint-${{ runner.os }}-${{ hashFiles('eslint.config.mjs', 'eslint.complexity-ratchets.config.mjs', 'config/quality/eslint-suppressions.json', 'package-lock.json') }}
restore-keys: |
eslint-${{ runner.os }}-
- run: npm run check:provider-consistency
- run: npm run check:fetch-targets
# docs-all / openapi-routes / docs-symbols live in docs-gates (path-filtered).
- run: npm run check:openapi-routes
- run: npm run check:docs-symbols
- name: Docs accuracy (fabricated-docs + i18n mirrors, strict)
run: npm run check:docs-all
- run: npm run check:deps
# #8522: --base-ref mode for PR events — compare against max(frozen, base) so
# inherited drift (base already over frozen cap) doesn't red an innocent PR.
# workflow_dispatch (no PR base) falls back to absolute comparison.
- name: File-size ratchet (base-relative on PR)
env:
PR_BASE_SHA: ${{ github.event.pull_request.base.sha }}
run: |
if [ -n "$PR_BASE_SHA" ]; then
npm run check:file-size -- --base-ref "$PR_BASE_SHA"
else
npm run check:file-size
fi
- run: npm run check:file-size
- run: npm run check:error-helper
- run: npm run check:migration-numbering
- run: npm run check:public-creds
@@ -187,184 +68,46 @@ jobs:
# leaking into the npm tarball (v3.8.36: 6 ops bin/*.sh) per-PR instead of only on
# the release PR's heavy Package Artifact job.
- run: npm run check:pack-policy
# 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: ${{ github.base_ref && format('origin/{0}', github.base_ref) || '' }}
run: npm run check:openapi-breaking -- --ratchet
# Complexity + cognitive-complexity ratchets on the fast-path (PR→release) so
# cycle drift is rebaselined PER-PR instead of cascading onto the release PR's
# Quality Ratchet (v3.8.36: +30 complexity / +15 cognitive surfaced only post-merge).
- run: npm run check:complexity
- run: npm run check:cognitive-complexity
- name: Typecheck (core)
run: npm run typecheck:core
# #7033: dashboard-scoped typecheck gate — src/app/(dashboard) TSX is not
# covered by typecheck:core's curated allowlist. See check-dashboard-typecheck.mjs.
- name: Typecheck (dashboard)
run: npm run check:dashboard-typecheck
# WS4.2 (v3.8.49 plan): TypeScript 7 native-compiler SHADOW — advisory only.
# TS7 went GA 2026-07-08 with 8-12x type-check speedups; its Compiler API only
# arrives in 7.1, so typescript-eslint / type-coverage / Stryker stay on 6.x
# (the hybrid is the officially documented pattern). Isolated npx on purpose:
# installing an alias package could collide node_modules/.bin/tsc with 6.x.
# Promote to the blocking gate after ~1 week of parity with the step above.
- name: Typecheck (core) — TS7 native shadow (advisory)
continue-on-error: true
run: |
RC=0
START=$(date +%s)
npx -y -p typescript@7 tsc --pretty false -p tsconfig.typecheck-core.json || RC=$?
echo "[ts7-shadow] exit=$RC elapsed=$(( $(date +%s) - START ))s — the 6.x step above stays authoritative"
exit $RC
# TIA: build the impact map at runtime (gitignored, ~21MB) and run only the
# unit tests impacted by this PR's changed files. On hub/unmapped changes the
# 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 ubuntu-latest) without extra coverage.
# unit tests impacted by this PR's changed files. Fail-safe runs the FULL
# unit suite on hub/unmapped changes — TIA accelerates, never replaces, the net.
#
# BLOCKING for the *impacted subset* (flipped 2026-06-17). Fail-safe full
# coverage remains required via `Unit Tests fast-path` (fast-unit).
- name: Impacted unit tests (TIA subset; blocking)
# BLOCKING (flipped 2026-06-17). The pre-existing release unit test-debt that kept
# this advisory was cleared: #4030 (16 Zod/registry reds, lossless restore) and
# #4063 (the last red — the LiveWS boot test — root-caused as a real event-loop
# stall in the WS sidecar, fixed + relocated to the integration suite). A full
# ci.yml run on release/v3.8.28 then showed all 8 unit shards green, so PR->release
# now blocks on unit-test regressions in the impacted set (typecheck:core already
# blocked above). Fail-safe still runs the FULL unit suite on hub/unmapped changes.
- name: Impacted unit tests (TIA, fail-safe full; blocking)
env:
GITHUB_BASE_REF: ${{ github.base_ref }}
run: |
git fetch --no-tags origin "$GITHUB_BASE_REF" || true
node scripts/quality/build-test-impact-map.mjs
SEL="$(node scripts/quality/select-impacted-tests.mjs)"
# Shadow evidence (#8084): persist every selection so TIA false negatives can
# be measured against fast-unit's full-suite verdict across releases BEFORE
# any gate authority moves off ordinary PRs. Artifact uploaded below.
printf '%s\n' "$SEL" > tia-selection.txt
if [ -z "$SEL" ]; then
echo "TIA selection: empty (no source/test changes)" >> "$GITHUB_STEP_SUMMARY"
echo "No source/test changes — skipping unit tests"; exit 0
fi
if [ -z "$SEL" ]; then echo "No source/test changes — skipping unit tests"; exit 0; fi
# CI runners are 4-vCPU; run at --test-concurrency=4 (matching the ci.yml unit
# job) rather than test:unit's local-tuned concurrency=20. Oversubscribing the
# runner makes timing-sensitive tests (db-backup, upstream-timeout, ...) flake,
# which must not happen on a blocking gate. DATA_DIR isolation keeps the parallel
# run race-free regardless of concurrency.
if echo "$SEL" | grep -q "__RUN_ALL__"; then
echo "TIA selection: __RUN_ALL__ (fail-safe) — full-suite authority stays with fast-unit" >> "$GITHUB_STEP_SUMMARY"
echo "Fail-safe: __RUN_ALL__ — deferring FULL unit suite to fast-unit (4-shard)."
echo "Not re-running unsharded test:unit:ci here (duplicate of fast-unit coverage)."
exit 0
echo "Fail-safe: running FULL unit suite (CI concurrency)"; npm run test:unit:ci; exit $?
fi
echo "TIA selection: $(grep -c . tia-selection.txt) impacted test file(s) — full suite still runs in fast-unit (shadow-evidence phase, #8084)" >> "$GITHUB_STEP_SUMMARY"
echo "Running impacted tests:"; echo "$SEL"
mapfile -t FILES <<< "$SEL"
# Loader parity with test:unit:ci:shard (#6787): tests/unit/dashboard/** runs
# under `--import tsx` (CJS transform — required for ESM-only deep imports like
# @lobehub/icons/es/* reached via lobeProviderIcons.ts); everything else under
# `--import tsx/esm`. A single tsx/esm invocation false-reds every dashboard
# module-shape test the impact map selects ("Unexpected token 'export'").
DASH=(); REST=()
for f in "${FILES[@]}"; do
case "$f" in
tests/unit/dashboard/*) DASH+=("$f") ;;
*) REST+=("$f") ;;
esac
done
RC=0
if [ ${#REST[@]} -gt 0 ]; then
node --import tsx/esm --import ./open-sse/utils/setupPolyfill.ts --import ./tests/_setup/isolateDataDir.ts --test --test-force-exit --test-concurrency=4 "${REST[@]}" || RC=$?
fi
if [ ${#DASH[@]} -gt 0 ]; then
node --import tsx --import ./open-sse/utils/setupPolyfill.ts --import ./tests/_setup/isolateDataDir.ts --test --test-force-exit --test-concurrency=4 "${DASH[@]}" || RC=$?
fi
exit $RC
# #8084 shadow evidence: keep the raw selection downloadable so TIA misses can be
# audited against fast-unit failures on the same run (gate moves need this data).
- name: Upload TIA selection (shadow evidence)
if: always()
uses: actions/upload-artifact@v7
with:
name: tia-selection
path: tia-selection.txt
if-no-files-found: ignore
retention-days: 30
node --import tsx/esm --import ./open-sse/utils/setupPolyfill.ts --import ./tests/_setup/isolateDataDir.ts --test --test-force-exit --test-concurrency=4 "${FILES[@]}"
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).
# 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-latest
env:
JWT_SECRET: ci-lint-secret-with-sufficient-length-for-validation
@@ -374,44 +117,20 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
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
with:
junit-paths: trunk-junit/**/*.xml
org-slug: omniroute
token: ${{ secrets.TRUNK_TOKEN }}
- run: npm run test:vitest
fast-unit:
name: Unit Tests fast-path (${{ matrix.shard }}/4)
needs: changes
if: ${{ github.event_name != 'pull_request' || ((github.event.pull_request.draft == false || startsWith(github.head_ref, 'mergify/merge-queue/')) && needs.changes.outputs.code == 'true') }}
# Dynamic runner — see fast-gates (own-origin + flag; fork/unset → ubuntu-latest).
# This is the heaviest fast-path job; 4-way sharding (was 2, #6781) halves the
# critical path again (~8.5min → ~4.5min on ubuntu-latest; ~2min on the 8-slot
# runner box). Node's native --test-shard=N/total takes any denominator — only
# this matrix and the TEST_SHARD env below encode the shard count.
# PINNED to hosted, deliberately not on the USE_VPS_RUNNER switch (gap 19). One variable
# governed the build and the test jobs, which want OPPOSITE machines: the build needs the
# .113's RAM, the tests need the hosted runner's link. Measured on 2026-07-29 —
# actions/setup-node took 20m06s on .113 with 4 concurrent runners versus 16s hosted (npm
# cache restore saturating the link), while the tests themselves tied, 2m54 vs 2m31. So
# self-hosted is strictly worse here and there is nothing to configure.
name: Unit Tests fast-path (${{ matrix.shard }}/2)
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
shard: [1, 2, 3, 4]
shard: [1, 2]
env:
JWT_SECRET: ci-lint-secret-with-sufficient-length-for-validation
API_KEY_SECRET: ci-lint-api-key-secret-long
@@ -420,7 +139,7 @@ jobs:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
@@ -430,7 +149,7 @@ jobs:
# silenciosamente não rodavam no fast path) e o setupPolyfill não era importado.
- run: npm run test:unit:ci:shard
env:
TEST_SHARD: ${{ matrix.shard }}/4
TEST_SHARD: ${{ matrix.shard }}/2
# ── Pacote 4 (plano mestre testes+CI, aprovado 2026-07-04) ─────────────────────────
# No-new-warnings por PR via ESLint bulk suppressions nativo (>=9.24). O baseline
@@ -446,60 +165,19 @@ jobs:
# contribuidor NUNCA é bloqueado nem cobrado).
lint-guard:
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-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@v7
with:
persist-credentials: false
- uses: actions/setup-node@v7
- uses: actions/setup-node@v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm
- run: npm ci
- name: Restore ESLint file cache
uses: actions/cache@v6
with:
path: |
.eslintcache
.eslintcache-complexity
key: eslint-${{ runner.os }}-${{ hashFiles('eslint.config.mjs', 'eslint.complexity-ratchets.config.mjs', 'config/quality/eslint-suppressions.json', 'package-lock.json') }}
restore-keys: |
eslint-${{ runner.os }}-
- 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
run: npx eslint . --suppressions-location config/quality/eslint-suppressions.json --max-warnings 0
# 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
@@ -514,8 +192,6 @@ jobs:
# nunca é bloqueado.
merge-integrity:
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-latest
continue-on-error: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.repo.fork == true }}
env:
@@ -523,11 +199,11 @@ jobs:
API_KEY_SECRET: ci-lint-api-key-secret-long
DISABLE_SQLITE_AUTO_BACKUP: "true"
steps:
- uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
with:
fetch-depth: 0
persist-credentials: false
- uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v6
- uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6
with:
node-version: ${{ env.CI_NODE_VERSION }}
cache: npm

View File

@@ -26,7 +26,7 @@ jobs:
persist-credentials: false
- name: Run analysis
uses: ossf/scorecard-action@v2.4.4
uses: ossf/scorecard-action@v2.4.3
with:
results_file: results.sarif
results_format: sarif

View File

@@ -6,19 +6,13 @@ on:
branches: ["main"]
permissions:
contents: read
# Cancel superseded PR runs (same rule as quality.yml). No paths filter on purpose:
# p/secrets must keep scanning docs-only diffs too — credentials leak in .md files.
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
semgrep:
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

@@ -40,7 +40,7 @@ jobs:
uses: actions/checkout@v7
- name: Setup Node
uses: actions/setup-node@v7
uses: actions/setup-node@v6
with:
node-version: "24"

31
.gitignore vendored
View File

@@ -72,7 +72,6 @@ yarn-error.log*
# env files (can opt-in for committing if needed)
.env*
!.env.example
!.env.homolog.example
# Provider API keys (never commit)
*.api-key
.nvidia-api-key
@@ -171,6 +170,7 @@ config/quality/test-impact-map.json
# GitNexus local index
.gitnexus
.worktrees
bin/omniroute.mjs
# Consistent with .dockerignore / .npmignore
.omc/
@@ -200,10 +200,7 @@ 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/
@@ -235,28 +232,4 @@ omniroute.md
# mise configuration
mise.toml
# release-green artifacts (.gitignore has no inline comments — a trailing
# `# ...` becomes part of the pattern, so it must sit on its own line).
# Already covered by /_*/ above; kept explicit for discoverability.
_artifacts/
.claude-flow/
# ESLint file cache (npm run lint --cache / complexity ratchets)
.eslintcache
.eslintcache-complexity
# CI/local quality artifacts (eslint-results.json, quality-ratchet.md, etc.)
.artifacts/
# Homologation E2E suite (npm run homolog) — real-environment credentials + report output
.env.homolog
tests/homolog/.auth/
tests/homolog/ui/.auth/
homolog-report/
docker-compose.yml.bak
.playwright-cli/
# Playwright screenshot/log output. Today every artifact happens to land inside
# output/**/.playwright-cli/ (covered above), but anything written directly to
# output/ would otherwise show up as untracked.
/output/

View File

@@ -74,22 +74,3 @@
# '''tests/unit/''',
# ]
#
[[rules]]
# Falsos-positivos comprovados do generic-api-key — zerados em 2026-07-13 (WS6/D3,
# plano v3.8.49). Revisar em v3.9.0. Nenhum é credencial: dois são NOMES DE CAMPO
# de métricas de latência; o terceiro é o valor PÚBLICO de um beta header da API
# da Anthropic (documentado publicamente, não é segredo).
id = "generic-api-key"
[rules.allowlist]
description = "Field names + public Anthropic beta-header value (não são segredos)"
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''',
]

View File

@@ -1,9 +1,7 @@
#!/usr/bin/env sh
# .husky/pre-push — intentionally light.
# any-budget + tracked-artifacts already run on pre-commit; re-running them on
# every push only doubles local wall time for the same existence reason (CI still
# enforces both). Keep this hook as a PATH/npm sanity check + reminder.
# Intentionally excludes test:unit / typecheck (slow; covered by CI).
# .husky/pre-push — fast deterministic gates (<10s total)
# Intentionally excludes test:unit (slow; covered by CI pre-push remote run).
# Activated: 2026-06-13 (6A.12 — replaced commented-out test:unit stub)
if ! command -v npm >/dev/null 2>&1; then
echo "⚠️ npm not found in PATH — skipping pre-push hooks"
@@ -11,5 +9,4 @@ if ! command -v npm >/dev/null 2>&1; then
exit 0
fi
# No-op success: real local gates live in pre-commit; CI owns the rest.
exit 0
npm run check:any-budget:t11 && npm run check:tracked-artifacts

View File

@@ -1,74 +0,0 @@
# Mergify merge queue — WS3.4/D5 of the v3.8.49 quality/velocity master plan.
#
# WHY: ~85-100 active PR authors/month and 300+ PRs/week peaks, all merged by ONE
# identity. The manual merge-train validated batches by hand; this queue automates
# it with batching + automatic batch bisection (a red batch of N costs ~log2(N)
# revalidations instead of N). Mergify Open Source plan: free, unlimited, public repo.
#
# GOVERNANCE (non-negotiable, mirrors CLAUDE.md Hard Rules #21/#22 + the owner's
# pre-merge ⭐ gate):
# • A PR enters the queue ONLY via the `queue` label — applied by the owner (or a
# session acting for the owner) AFTER the pre-merge ⭐ report/decision. The label
# IS the merge approval; Mergify only executes it.
# • During a release-freeze (open issue labeled `release-freeze`), do NOT label PRs
# targeting the frozen branch — the freeze is a human-honored coordination signal
# the queue cannot see. Retarget to the active release/vX+1 first (Hard Rule #21).
# • Never label a PR another session is actively working (Hard Rule #22b).
# • Fallback path if Mergify misbehaves or the OSS plan changes: the manual
# merge-train runbook (docs/ops/MERGE_TRAIN.md) — remove labels, proceed by hand.
# Auto-enqueue (current Mergify model, 2026): auto_merge_conditions in
# merge_protections_settings — the rules-based queue action / autoqueue path is
# deprecated (EOL 2026-07-16). The owner-applied `queue` label IS the approval.
merge_protections_settings:
auto_merge_conditions:
- label = queue
queue_rules:
- name: release
# Any current or future release branch — the reason GitHub's native queue was
# rejected (no wildcard support on personal-account repos).
queue_conditions:
- base~=^release/v\d+\.\d+\.\d+$
- label=queue
- -draft
- -conflict
# "Everything that ran is green, nothing still running, AND the always-on
# anchor check succeeded" — robust to the path-filtered fast-gates (docs-only
# PRs skip code jobs; matrix shard names vary) while never fail-open: a PR with
# zero checks cannot vacuously merge, because `Merge integrity` runs on EVERY
# non-draft PR (quality.yml) and must be an affirmative success. Review approval
# is intentionally NOT a condition here: the owner-applied `queue` label IS the
# approval in this repo's single-maintainer model (see governance header).
merge_conditions:
# "Zero failures" — EXCEPT the advisory "Build (advisory)" job (quality.yml):
# continue-on-error by design, and its GH-hosted Turbopack build hangs
# recurrently mid-"Creating an optimized production build" (100% failure rate
# across every sampled PR since the job was added 2026-07-27, always killed by
# a runner timeout/shutdown signal, never a real compile error). Any OTHER
# failure still blocks (anti-fail-open kept). The prior dast-smoke exception
# (#7225) was dropped here: dast-smoke's hang (#7226) has been dormant for
# weeks (0 failures in the last 30 runs; 2 all-time, none since 2026-07-13) —
# carrying its tolerance forward would mask problems it no longer causes.
- or:
- "#check-failure=0"
- and:
- "#check-failure=1"
- check-failure=Build (advisory)
- "#check-pending=0"
- "#check-success>=1"
- check-success=Merge integrity (changelog + generated skills)
# NO batching: 'Merge Queue Batch' requires a paid Mergify tier (live finding
# 2026-07-15 — the queue command fails with "Cannot use Merge Queue batch" on
# the free plan). Serial queue (1 PR at a time) still automates the train.
# Squash keeps the one-commit-per-PR history the CHANGELOG reconciliation expects.
merge_method: squash
pull_request_rules:
- name: clean up the queue label after merge
conditions:
- merged
actions:
label:
remove:
- queue

View File

@@ -4,14 +4,11 @@ data/
**/db.json
# VS Code extension test runtime (large binary, not needed in npm package)
app/vscode-extension/
**/data/
**/db.json
# Source code (pre-built dist/ is published instead)
#
# NOTA (2026-08-05): as entradas `app/*` foram removidas — o diretorio `app/`
# foi renomeado para `dist/` na Layer 1 e nao existe mais. Elas sugeriam um
# layout que ja nao e o do projeto.
# Source code (pre-built app/ is published instead)
#
# NOTE (#3578 / #3821-review): package.json "files" is the source of truth for what
# ships. It now allowlists the backend source closure the MCP server needs at runtime
@@ -52,6 +49,8 @@ scripts/
.vscode/
.agents/
.env*
app/.env
app/.env*
eslint.config.mjs
prettier.config.mjs
postcss.config.mjs
@@ -83,6 +82,8 @@ bun.lock
*.deb
*.rpm
electron/
app/electron/
app/vscode-extension/
# Subprojects
clipr/
@@ -92,6 +93,10 @@ vscode-extension/
# Root-level underscore-prefixed directories (private/draft — never publish)
/_*/
app/_*/
app/coverage/
app/logs/
app/tests/
# Consistent with .gitignore and .dockerignore
.DS_Store

View File

@@ -1,16 +1,2 @@
# Long reference tables are manually aligned; formatting the whole file causes noisy diffs.
docs/reference/ENVIRONMENT.md
# Generated by `npm run gen:provider-reference`; the generator aligns the tables and
# is their formatter of record. Without this, lint-staged reformats the file whenever
# it is staged and the next generator run reverts it — a diff ping-pong.
docs/reference/PROVIDER_REFERENCE.md
# Dense auto-generated free-tier budget rows (one object per line) — prettier multi-line expand blows past file-size cap 800.
open-sse/config/freeModelCatalog.data.ts
# Generated by scripts/skills/generate-agent-skills.mjs; the generator is their
# formatter of record and check:agent-skills-sync diffs its output byte-for-byte.
# Prettier reformats the frontmatter (blank line after ---), which makes the gate
# fail on any skill that happens to pass through lint-staged.
skills/*/SKILL.md

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
};

10
.vscode/settings.json vendored
View File

@@ -48,19 +48,11 @@
"**/.build",
"**/dist",
"**/coverage",
"**/.worktrees",
"**/.claude/worktrees",
"**/electron",
"**/_references",
"**/_mono_repo",
"**/_tasks"
"**/.worktrees"
]
},
// Para esconder os diretórios gerados da árvore do Explorer, descomente:
// (MANTIDO comentado — o dono precisa ver _references/_mono_repo/_tasks na árvore.
// A performance é resolvida por watcherExclude + search.exclude + tsserver, sem
// precisar escondê-los do Explorer.)
// "files.exclude": {
// "**/.worktrees": true,
// "**/coverage": true,

View File

@@ -10,8 +10,7 @@ This plugin solves that by:
- Fetching `/v1/models` and `/api/combos` **at OpenCode startup, in Node.js** — no CORS, no WebView restrictions
- Emitting the provider block **dynamically** in the plugin's `config`/`provider` hook — so `opencode.json` only needs the plugin entry, not a static `provider.omniroute`
- Re-fetching on a configurable TTL (default 5 min) **and** background auto-discovery while OpenCode is running (`autoSyncIntervalMs`, default 5 min), so new models / combo changes appear without restarting OpenCode
- Exposing a force-refresh path (`omniroute_sync_models` tool + `/omni-sync` command template) equivalent to Pi `/omni sync`
- Re-fetching on a configurable TTL (default 5 min), so new models / combo changes in the OmniRoute UI appear without restarting OpenCode
- Computing `limit.context` for combos as `min(member.context_length)` from the live catalog (no more `null` values that cause 4K-token truncation)
- **Auto-pickup of `interleaved` capability** for thinking models (merged via PR #3138)
@@ -74,9 +73,6 @@ Peer dep: `@opencode-ai/plugin` (managed by your OpenCode install).
{
"providerId": "omniroute",
"baseURL": "https://or.example.com",
// Background re-discovery while OpenCode is running (Pi parity).
// Default 300000 (5 min). Minimum 60000. Set 0 to disable.
"autoSyncIntervalMs": 300000,
},
],
],
@@ -92,27 +88,6 @@ opencode auth login --provider omniroute
Restart OpenCode. `/models` lists the full live catalog. Variants (`-low`, `-medium`, `-high`, `-thinking`) and combos appear as first-class IDs — OmniRoute is the source of truth, no client-side synthesis.
### Live catalog refresh (auto + force)
While OpenCode is running, the plugin keeps the model catalog fresh in two ways:
| Mechanism | Default | What it does |
| --- | --- | --- |
| `modelCacheTtl` | `300000` (5 min) | On-demand TTL: next provider/models hook after expiry re-fetches `/v1/models` |
| `autoSyncIntervalMs` | `300000` (5 min) | Background timer: proactively invalidates + re-fetches while the harness is running. Min `60000`. Set `0` to disable background polling (TTL still applies) |
**Force sync now** (Pi `/omni sync` equivalent) — OpenCode has no Pi-style slash-command registration API, so the plugin wires both a tool and command templates:
1. **Tool:** `omniroute_sync_models` — invalidates in-memory + disk caches, re-fetches `GET /v1/models` (and combos/enrichment when enabled), returns `{ ok, count, ... }`.
2. **Command templates** (type these in OpenCode):
- `/omni-sync` — asks the agent to call `omniroute_sync_models` and report the result
- `/omni-autosync` — asks the agent to report current `autoSyncIntervalMs` / `modelCacheTtl` status
```text
/omni-sync
/omni-autosync
```
## Multi-instance (prod + preprod side-by-side)
> ⚠ OC ≤1.15.5 dedupes plugin loads by absolute module path. Two `plugin:` entries pointing at the same `dist/index.js` collapse into one (last-listed options win). Workaround: install the plugin twice into separate directories so each entry resolves to a distinct module file. v0.2.x will introduce an `instances: [...]` shape that registers N providers from a single load.
@@ -190,7 +165,7 @@ npm install --prefix ~/.config/opencode/plugins/omniroute-opencode-plugin-prepro
| Dynamic `/v1/models` | Pulls live catalog (455+ entries on prod) on each refresh, TTL-cached | `provider.models` |
| Variants pass-through | `-low`/`-medium`/`-high`/`-thinking` ship as first-class IDs from OmniRoute (no client synthesis) | `provider.models` |
| Combo LCD aggregation | Combos appear with intersected capabilities + min context/output across members | `provider.models` + `config` |
| `combo/<slug>` namespace + `Combo:` prefix | Combos surface under `combo/claude-primary` (not the upstream UUID) and the picker shows `Combo: claude-primary` so they stand apart from raw provider/model pairs | both hooks |
| `combo/<slug>` namespace + `Combo: ` prefix | Combos surface under `combo/claude-primary` (not the upstream UUID) and the picker shows `Combo: claude-primary` so they stand apart from raw provider/model pairs | both hooks |
| Nice names + cost | `/api/pricing/models` display names AND `/api/pricing` per-million-token cost overlaid onto the live catalog | both hooks |
| Canonical-twin dedup + alias-fallback | `/v1/models` exposes the same upstream model under both short alias (`cc/claude-opus-4-7`) and canonical name (`claude/claude-opus-4-7`); the plugin drops the canonical twin when an alias twin exists (no duplicate rows in the picker) and reverse-maps canonical → alias to pick up enrichment for short aliases (`dg/nova-3 → Deepgram - Nova 3`) that `/api/pricing/models` only indexes by canonical | both hooks |
| Compression pipeline tags | Combo names get tagged with their compression pipeline (e.g. `Combo: claude-primary [rtk🟡 → caveman🟠]`) when `features.compressionMetadata: true`. Intensity tokens render as a traffic-light emoji: 🟢 lite/minimal · 🟡 standard · 🟠 aggressive/full · 🔴 ultra | both hooks |
@@ -204,33 +179,30 @@ npm install --prefix ~/.config/opencode/plugins/omniroute-opencode-plugin-prepro
## Plugin options
| Option | Type | Default | Description |
| --------------------- | -------- | ------------------------------------------ | ----------------------------------------------------------------------------------------------------- |
| `providerId` | `string` | `"omniroute"` | OpenCode provider id; must be unique across plugin entries |
| `displayName` | `string` | `"OmniRoute"` or `OmniRoute (<id>)` | Label in the OC UI |
| `modelCacheTtl` | `number` | `300000` (5 min) | `/v1/models` TTL in ms |
| `baseURL` | `string` | resolved from `auth.json` after `/connect` | Override OmniRoute base URL |
| `managementReadToken` | `string` | falls back to `apiKey` | Optional read-only token for management catalog GETs; `/v1` inference stays on the connected `apiKey` |
| `features` | `object` | see below | Feature toggles (all opt-in/out, defaults preserve v0.1.0) |
For least-privilege deployments, set top-level `managementReadToken` to a read-only management token. It is sent only to catalog reads (`/api/combos`, `/api/combos/auto`, `/api/pricing/models`, `/api/pricing`, `/api/context/combos`, and `/api/providers`). Inference requests under `/v1`, including chat, continue to use the `apiKey` stored by OpenCode. `features.mcpToken` remains independent. If `managementReadToken` is omitted, catalog reads retain the previous `apiKey` behavior.
| Option | Type | Default | Description |
| --------------- | -------- | ------------------------------------------ | ---------------------------------------------------------- |
| `providerId` | `string` | `"omniroute"` | OpenCode provider id; must be unique across plugin entries |
| `displayName` | `string` | `"OmniRoute"` or `OmniRoute (<id>)` | Label in the OC UI |
| `modelCacheTtl` | `number` | `300000` (5 min) | `/v1/models` TTL in ms |
| `baseURL` | `string` | resolved from `auth.json` after `/connect` | Override OmniRoute base URL |
| `features` | `object` | see below | Feature toggles (all opt-in/out, defaults preserve v0.1.0) |
### `features` block
Every field is optional. Defaults mirror v0.1.0 behaviour so existing `opencode.json` files do not need to change.
| Feature | Type | Default | What it does |
| --------------------- | --------- | ------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `combos` | `boolean` | `true` | Discover `/api/combos` and surface them as pseudo-models with LCD capabilities. Combos are keyed under the `combo/<slug>` namespace and labelled `Combo: <name>` in the model picker so they're distinguishable from raw provider/model pairs. |
| `enrichment` | `boolean` | `true` | Pull display names from `/api/pricing/models` AND per-million-token pricing (`input`, `output`, `cached``cacheRead`, `cache_creation``cacheWrite`) from `/api/pricing`, then overlay both onto the live catalog (so the UI shows `Claude 4.7 Opus` with `cost.input: 5`, `cost.output: 25` instead of raw IDs and zeroed cost). |
| `compressionMetadata` | `boolean` | `false` | Pull `/api/context/combos` so combo names get tagged with their compression pipeline, e.g. `Combo: claude-primary [rtk🟡 → caveman🟠]`. Intensity tokens render as traffic-light emoji (🟢 lite/minimal · 🟡 standard · 🟠 aggressive/full · 🔴 ultra) so the picker advertises "how compressed" each combo is at a glance. |
| `providerTag` | `boolean` | `true` | Prepend a short upstream-provider label to the enriched display name with `" - "` separator, so `cc/claude-opus-4-7 → Claude - Claude Opus 4.7` differs visibly from `kr/claude-opus-4-7 → Kiro - Claude Opus 4.7` in the OC TUI model picker. Label resolution: use `/api/pricing/models[<alias>].name` verbatim when ≤8 chars (e.g. `Claude`, `Kiro`, `Codex`, `Qwen`), otherwise fall back to `UPPER(alias)` (e.g. `GitHub Models``GHM`, `Gemini``GEMINI`). Idempotent. Combos intentionally skipped (the `Combo:` prefix already conveys multi-upstream). |
| `usableOnly` | `boolean` | `false` | Read `/api/providers` and filter the catalog to providers that have at least one connection with `isActive: true` AND `testStatus: 'active'`. Subtract-filter semantics: providers unknown to BOTH the pricing-models catalog AND the connection table pass through (so synthetic prefixes like `agentrouter/*` survive). On fetch failure the filter is disabled for the refresh — never hides the whole catalog. |
| `diskCache` | `boolean` | `true` | Persist the last successful `/v1/models` + `/api/combos` + enrichment + connections + compression snapshot to `${OPENCODE_DATA_DIR ?? ~/.local/share/opencode}/plugins/omniroute-<providerId>.json`. On a subsequent cold start where `/v1/models` throws (network down / IP whitelist drop / 5xx) the static block hydrates from the snapshot so OC's model picker survives offline. Soft-fail on read/write — never blocks publishing. |
| `geminiSanitization` | `boolean` | `true` | Strip `$schema`/`$ref`/`additionalProperties` from tool params when the model id matches `gemini` |
| `mcpAutoEmit` | `boolean` | `false` | Auto-write an `mcp.<providerId>` remote entry into the OC config pointing at `<baseURL>/api/mcp/stream` with the resolved Bearer token |
| `mcpToken` | `string` | _unset_ | Optional separate Bearer for the auto-emitted MCP entry. Falls back to the provider's `apiKey` (from `auth.json`) when unset |
| `fetchInterceptor` | `boolean` | `true` | Inject `Authorization: Bearer` + default `Content-Type` on every outbound request targeting `baseURL` (suffix-spoof guarded) |
| Feature | Type | Default | What it does |
| --------------------- | --------- | ------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `combos` | `boolean` | `true` | Discover `/api/combos` and surface them as pseudo-models with LCD capabilities. Combos are keyed under the `combo/<slug>` namespace and labelled `Combo: <name>` in the model picker so they're distinguishable from raw provider/model pairs. |
| `enrichment` | `boolean` | `true` | Pull display names from `/api/pricing/models` AND per-million-token pricing (`input`, `output`, `cached``cacheRead`, `cache_creation``cacheWrite`) from `/api/pricing`, then overlay both onto the live catalog (so the UI shows `Claude 4.7 Opus` with `cost.input: 5`, `cost.output: 25` instead of raw IDs and zeroed cost). |
| `compressionMetadata` | `boolean` | `false` | Pull `/api/context/combos` so combo names get tagged with their compression pipeline, e.g. `Combo: claude-primary [rtk🟡 → caveman🟠]`. Intensity tokens render as traffic-light emoji (🟢 lite/minimal · 🟡 standard · 🟠 aggressive/full · 🔴 ultra) so the picker advertises "how compressed" each combo is at a glance. |
| `providerTag` | `boolean` | `true` | Prepend a short upstream-provider label to the enriched display name with `" - "` separator, so `cc/claude-opus-4-7 → Claude - Claude Opus 4.7` differs visibly from `kr/claude-opus-4-7 → Kiro - Claude Opus 4.7` in the OC TUI model picker. Label resolution: use `/api/pricing/models[<alias>].name` verbatim when ≤8 chars (e.g. `Claude`, `Kiro`, `Codex`, `Qwen`), otherwise fall back to `UPPER(alias)` (e.g. `GitHub Models``GHM`, `Gemini``GEMINI`). Idempotent. Combos intentionally skipped (the `Combo: ` prefix already conveys multi-upstream). |
| `usableOnly` | `boolean` | `false` | Read `/api/providers` and filter the catalog to providers that have at least one connection with `isActive: true` AND `testStatus: 'active'`. Subtract-filter semantics: providers unknown to BOTH the pricing-models catalog AND the connection table pass through (so synthetic prefixes like `agentrouter/*` survive). On fetch failure the filter is disabled for the refresh — never hides the whole catalog. |
| `diskCache` | `boolean` | `true` | Persist the last successful `/v1/models` + `/api/combos` + enrichment + connections + compression snapshot to `${OPENCODE_DATA_DIR ?? ~/.local/share/opencode}/plugins/omniroute-<providerId>.json`. On a subsequent cold start where `/v1/models` throws (network down / IP whitelist drop / 5xx) the static block hydrates from the snapshot so OC's model picker survives offline. Soft-fail on read/write — never blocks publishing. |
| `geminiSanitization` | `boolean` | `true` | Strip `$schema`/`$ref`/`additionalProperties` from tool params when the model id matches `gemini` |
| `mcpAutoEmit` | `boolean` | `false` | Auto-write an `mcp.<providerId>` remote entry into the OC config pointing at `<baseURL>/api/mcp/stream` with the resolved Bearer token |
| `mcpToken` | `string` | _unset_ | Optional separate Bearer for the auto-emitted MCP entry. Falls back to the provider's `apiKey` (from `auth.json`) when unset |
| `fetchInterceptor` | `boolean` | `true` | Inject `Authorization: Bearer` + default `Content-Type` on every outbound request targeting `baseURL` (suffix-spoof guarded) |
#### Example — enrichment + compression tags + MCP auto-emit
@@ -242,7 +214,6 @@ Every field is optional. Defaults mirror v0.1.0 behaviour so existing `opencode.
{
"providerId": "omniroute",
"baseURL": "https://or.example.com",
"managementReadToken": "<read-only-management-token>",
"features": {
"combos": true,
"enrichment": true,

View File

@@ -1,6 +1,6 @@
{
"name": "@omniroute/opencode-plugin",
"version": "0.2.1",
"version": "0.2.0",
"description": "OpenCode plugin for the OmniRoute AI Gateway. Drives dynamic model discovery, /connect auth flow, and multi-instance OmniRoute providers via the official @opencode-ai/plugin contract.",
"type": "module",
"main": "./dist/index.js",
@@ -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",
"prepublishOnly": "npm run clean && npm run build && npm test"
},
"keywords": [

File diff suppressed because it is too large Load Diff

View File

@@ -1,130 +0,0 @@
/**
* Auto-discovery + force-sync (OpenCode parity with Pi `/omni sync`).
*/
import test from "node:test";
import assert from "node:assert/strict";
import {
sanitizeAutoSyncIntervalMs,
DEFAULT_AUTO_SYNC_INTERVAL_MS,
MIN_AUTO_SYNC_INTERVAL_MS,
parseOmniRoutePluginOptions,
resolveOmniRoutePluginOptions,
invalidateOmniRouteFetchCache,
forceSyncOmniRouteModels,
type OmniRouteFetchCache,
} from "../src/index.js";
test("sanitizeAutoSyncIntervalMs: unset → default 300000", () => {
assert.equal(sanitizeAutoSyncIntervalMs(undefined), DEFAULT_AUTO_SYNC_INTERVAL_MS);
assert.equal(sanitizeAutoSyncIntervalMs(null), DEFAULT_AUTO_SYNC_INTERVAL_MS);
});
test("sanitizeAutoSyncIntervalMs: 0 disables", () => {
assert.equal(sanitizeAutoSyncIntervalMs(0), 0);
});
test("sanitizeAutoSyncIntervalMs: clamps below min to 60000", () => {
assert.equal(sanitizeAutoSyncIntervalMs(1), MIN_AUTO_SYNC_INTERVAL_MS);
assert.equal(sanitizeAutoSyncIntervalMs(59_999), MIN_AUTO_SYNC_INTERVAL_MS);
});
test("sanitizeAutoSyncIntervalMs: keeps valid values", () => {
assert.equal(sanitizeAutoSyncIntervalMs(60_000), 60_000);
assert.equal(sanitizeAutoSyncIntervalMs(300_000), 300_000);
});
test("parseOmniRoutePluginOptions accepts autoSyncIntervalMs including 0", () => {
assert.equal(parseOmniRoutePluginOptions({ autoSyncIntervalMs: 0 }).autoSyncIntervalMs, 0);
assert.equal(parseOmniRoutePluginOptions({ autoSyncIntervalMs: 120_000 }).autoSyncIntervalMs, 120_000);
});
test("resolveOmniRoutePluginOptions defaults autoSyncIntervalMs to 300000", () => {
const r = resolveOmniRoutePluginOptions({});
assert.equal(r.autoSyncIntervalMs, DEFAULT_AUTO_SYNC_INTERVAL_MS);
});
test("resolveOmniRoutePluginOptions clamps low positive autoSyncIntervalMs", () => {
const r = resolveOmniRoutePluginOptions({ autoSyncIntervalMs: 5000 });
assert.equal(r.autoSyncIntervalMs, MIN_AUTO_SYNC_INTERVAL_MS);
});
test("invalidateOmniRouteFetchCache clears by baseURL prefix", () => {
const cache: OmniRouteFetchCache = new Map();
cache.set("https://a.example/v1::abc", {
rawModels: [],
rawCombos: [],
rawAutoCombos: [],
rawEnrichment: new Map(),
rawCompressionCombos: [],
rawConnections: [],
expiresAt: Date.now() + 1000,
});
cache.set("https://b.example/v1::def", {
rawModels: [],
rawCombos: [],
rawAutoCombos: [],
rawEnrichment: new Map(),
rawCompressionCombos: [],
rawConnections: [],
expiresAt: Date.now() + 1000,
});
const removed = invalidateOmniRouteFetchCache(cache, "https://a.example/v1");
assert.equal(removed, 1);
assert.equal(cache.size, 1);
assert.equal(cache.has("https://b.example/v1::def"), true);
});
test("forceSyncOmniRouteModels: fetches, populates cache, returns count", async () => {
const cache: OmniRouteFetchCache = new Map();
const resolved = resolveOmniRoutePluginOptions({
providerId: "omniroute",
baseURL: "https://omniroute.example/v1",
autoSyncIntervalMs: 0,
features: {
combos: false,
autoCombos: false,
enrichment: false,
compressionMetadata: false,
usableOnly: false,
diskCache: false,
},
});
const result = await forceSyncOmniRouteModels({
resolved,
cache,
readAuthJson: async () => ({
omniroute: { type: "api", key: "test-key" },
}),
fetcher: async () => [
{ id: "model-a", object: "model" },
{ id: "model-b", object: "model" },
],
now: () => 1_000_000,
});
assert.equal(result.ok, true);
assert.equal(result.count, 2);
assert.equal(result.provider, "omniroute");
assert.equal(cache.size, 1);
const entry = [...cache.values()][0];
assert.equal(entry.rawModels.length, 2);
assert.equal(entry.expiresAt, 1_000_000 + resolved.modelCacheTtl);
});
test("forceSyncOmniRouteModels: missing auth returns error", async () => {
const cache: OmniRouteFetchCache = new Map();
const resolved = resolveOmniRoutePluginOptions({
providerId: "omniroute",
baseURL: "https://omniroute.example/v1",
autoSyncIntervalMs: 0,
features: { diskCache: false },
});
const result = await forceSyncOmniRouteModels({
resolved,
cache,
readAuthJson: async () => ({}),
});
assert.equal(result.ok, false);
assert.match(result.error ?? "", /credentials|baseURL|connect/i);
});

View File

@@ -447,14 +447,14 @@ test("models() returns combo entries merged into the map", async () => {
// 3 raw models + 1 combo = 4 entries
assert.equal(Object.keys(out).length, 4);
assert.ok(out["omniroute/claude-primary"]);
assert.ok(out["omniroute/claude-secondary"]);
assert.ok(out["omniroute/gemini-3-flash"]);
assert.ok(out["omniroute/claude-tier"]);
assert.ok(out["opencode-omniroute/claude-primary"]);
assert.ok(out["opencode-omniroute/claude-secondary"]);
assert.ok(out["opencode-omniroute/gemini-3-flash"]);
assert.ok(out["opencode-omniroute/claude-tier"]);
const combo = out["omniroute/claude-tier"];
const combo = out["opencode-omniroute/claude-tier"];
assert.equal(combo.name, "Claude Tier");
assert.equal(combo.providerID, "omniroute");
assert.equal(combo.providerID, "opencode-omniroute");
// LCD over claude-primary (200k, reasoning) + claude-secondary (100k, no reasoning)
assert.equal(combo.limit.context, 100_000);
assert.equal(combo.capabilities.reasoning, false);
@@ -478,11 +478,11 @@ test("models(): combo with unknown member ids degrades to all-false LCD posture"
{ fetcher: modelsFetcher, combosFetcher }
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
assert.ok(out["omniroute/phantom-combo"]);
assert.ok(out["opencode-omniroute/phantom-combo"]);
// With zero resolvable members, LCD = all-false (defensive posture).
assert.equal(out["omniroute/phantom-combo"].capabilities.toolcall, false);
assert.equal(out["omniroute/phantom-combo"].capabilities.reasoning, false);
assert.equal(out["omniroute/phantom-combo"].limit.context, 0);
assert.equal(out["opencode-omniroute/phantom-combo"].capabilities.toolcall, false);
assert.equal(out["opencode-omniroute/phantom-combo"].capabilities.reasoning, false);
assert.equal(out["opencode-omniroute/phantom-combo"].limit.context, 0);
});
test("models(): hidden combos are excluded from the map", async () => {
@@ -505,8 +505,8 @@ test("models(): hidden combos are excluded from the map", async () => {
{ fetcher: modelsFetcher, combosFetcher }
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
assert.ok(out["omniroute/visible"]);
assert.ok(!out["omniroute/hidden"], "hidden combo must be omitted");
assert.ok(out["opencode-omniroute/visible"]);
assert.ok(!out["opencode-omniroute/hidden"], "hidden combo must be omitted");
});
test("models(): combo name exactly matches raw model id → raw deleted, raw deleted, no warn", async () => {
@@ -530,8 +530,8 @@ test("models(): combo name exactly matches raw model id → raw deleted, raw del
});
// Raw model replaced by combo of the same key; combo now lives at the bare slug.
assert.ok(out["omniroute/claude-primary"], "combo surfaces under prefixed key");
assert.equal(out["omniroute/claude-primary"].name, "claude-primary");
assert.ok(out["opencode-omniroute/claude-primary"], "combo surfaces under prefixed key");
assert.equal(out["opencode-omniroute/claude-primary"].name, "claude-primary");
// No collision warning fires — dedup makes keys disjoint.
const collisionWarns = warnings.filter((w) => {
@@ -565,8 +565,8 @@ test("models(): two combos with same slug → second gets disambiguator suffix",
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
// First combo gets the bare slug; second gets disambiguated.
assert.ok(out["omniroute/claude"], "first combo at prefixed slug");
assert.ok(out["omniroute/claude-uuid"], "second combo disambiguated by id prefix");
assert.ok(out["opencode-omniroute/claude"], "first combo at prefixed slug");
assert.ok(out["opencode-omniroute/claude-uuid"], "second combo disambiguated by id prefix");
});
test("models(): combos fetch fails → falls back to models-only, warn emitted, no throw", async () => {
@@ -583,8 +583,8 @@ test("models(): combos fetch fails → falls back to models-only, warn emitted,
// Catalog includes the models but NOT any combo entries.
assert.equal(Object.keys(out).length, 2);
assert.ok(out["omniroute/claude-primary"]);
assert.ok(out["omniroute/claude-secondary"]);
assert.ok(out["opencode-omniroute/claude-primary"]);
assert.ok(out["opencode-omniroute/claude-secondary"]);
// Soft-fail warning surfaced.
const softFail = warnings.find((w) => {
@@ -609,7 +609,7 @@ test("models(): combos cached + reused within TTL (one combo fetch per TTL windo
const second = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
assert.equal(combosFetcher.callCount(), 1, "combos fetched only once within TTL");
assert.equal(modelsFetcher.callCount(), 1, "models fetched only once within TTL");
assert.ok(second["omniroute/claude-tier"]);
assert.ok(second["opencode-omniroute/claude-tier"]);
});
test("models(): combos refetched after TTL expiry (same key as models)", async () => {
@@ -701,7 +701,7 @@ test("models(): nested combo-ref context is the min of nested + raw members", as
{ fetcher: modelsFetcher, combosFetcher }
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-z") as never });
const masterLight = out["omniroute/master-light"];
const masterLight = out["opencode-omniroute/master-light"];
assert.ok(masterLight, "MASTER-LIGHT entry must exist");
assert.equal(
masterLight.limit.context,

View File

@@ -248,7 +248,7 @@ test("config: with valid auth.json + apiKey + baseURL → mutates input.provider
// Combo surfaces under bare key + LCD'd
// (gemini's reasoning=false → combo reasoning=false).
const combo = entry.models["omniroute/claude-tier"];
const combo = entry.models["opencode-omniroute/claude-tier"];
assert.ok(combo, "combo surfaced under bare key");
assert.equal(combo.name, "Claude Tier");
assert.equal(combo.reasoning, false, "LCD: any member reasoning=false → combo reasoning=false");
@@ -474,7 +474,7 @@ test("config: combos fetcher throws → emit models-only catalog (no combos in m
"opencode-omniroute/claude-sonnet-4-6",
"opencode-omniroute/gemini-3-flash",
]);
assert.equal(entry.models["omniroute/claude-tier"], undefined, "no combo entry");
assert.equal(entry.models["opencode-omniroute/claude-tier"], undefined, "no combo entry");
assert.ok(
logger.entries.some((e) => String(e[0]).includes("/api/combos fetch failed")),
"combos-fetch breadcrumb emitted"
@@ -748,7 +748,7 @@ test("buildStaticProviderEntry: hidden combos are excluded", () => {
"https://or.example/v1",
"sk-test"
);
assert.equal(block.models["omniroute/claude-tier"], undefined);
assert.equal(block.models["opencode-omniroute/claude-tier"], undefined);
assert.ok(block.models["opencode-omniroute/claude-sonnet-4-6"]);
});
@@ -858,7 +858,7 @@ test("buildStaticProviderEntry: combo modalities = intersection of members (LCD)
"https://or.example/v1",
"sk-test"
);
const combo = block.models["omniroute/mixed-tier"];
const combo = block.models["opencode-omniroute/mixed-tier"];
assert.ok(combo, "combo emitted under slug key");
// claude has text+image, text-only has text → intersection drops image.
assert.deepEqual(combo.modalities?.input, ["text"]);
@@ -970,7 +970,7 @@ test("config: enrichment fetched + name overlaid on raw-model entries", async ()
assert.equal(entry.models["opencode-omniroute/claude-sonnet-4-6"].name, "Claude Sonnet 4.6");
assert.equal(entry.models["opencode-omniroute/gemini-3-flash"].name, "Gemini 3 Flash");
// Combo names still come from /api/combos — enrichment overlay does NOT touch combos.
assert.equal(entry.models["omniroute/claude-tier"].name, "Claude Tier");
assert.equal(entry.models["opencode-omniroute/claude-tier"].name, "Claude Tier");
assert.equal(enrichmentFetcher.callCount(), 1);
});
@@ -1337,7 +1337,7 @@ test("config: providerTag (default-on) prepends '<provider> - ' to enriched raw-
);
assert.equal(entry.models["opencode-omniroute/gemini-3-flash"].name, "Gemini - Gemini 3 Flash");
// Combos stay untouched — `Combo: ` prefix already conveys multi-upstream.
assert.equal(entry.models["omniroute/claude-tier"].name, "Claude Tier");
assert.equal(entry.models["opencode-omniroute/claude-tier"].name, "Claude Tier");
});
test("config: providerTag=false suppresses the suffix", async () => {
@@ -1516,7 +1516,7 @@ test("buildStaticProviderEntry: nested combo-ref context is the bottleneck acros
);
// Pre-fix: Parent would advertise 200_000 (only raw-big counted).
// Post-fix: Parent should advertise 8_000 (TinyCombo bottleneck).
const parent = block.models["omniroute/parent"];
const parent = block.models["opencode-omniroute/parent"];
assert.ok(parent, "Parent combo must be in the static catalog");
assert.equal(parent.limit?.context, 8_000);
});

View File

@@ -40,7 +40,7 @@ test("defaultDiskSnapshotWriter writes an owner-only (no group/other) snapshot",
process.env.OPENCODE_DATA_DIR = tmp;
try {
await defaultDiskSnapshotWriter("perm-test", makeEntry(), "test-snapshot-identity");
await defaultDiskSnapshotWriter("perm-test", makeEntry());
const file = diskSnapshotPath("perm-test");
assert.ok(fs.existsSync(file), "snapshot file should be written");

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

@@ -376,8 +376,7 @@ test("provider hook: enrichment fetcher called when features.enrichment !== fals
);
const out = await hook.models!({} as never, { auth: apiAuth("sk") as never });
assert.equal(called, 1, "enrichment fetcher called once");
// #6859: dynamic-hook catalog keys use the unprefixed omnirouteProviderId.
const m = out["omniroute/claude-sonnet-4-6"];
const m = out["opencode-omniroute/claude-sonnet-4-6"];
assert.equal(m.name, "Claude Sonnet 4.6", "enrichment name overlay applied");
assert.equal(m.cost.input, 3, "enrichment pricing applied");
assert.equal(m.cost.output, 15);
@@ -403,7 +402,7 @@ test("provider hook: enrichment fetcher NOT called when features.enrichment:fals
const out = await hook.models!({} as never, { auth: apiAuth("sk") as never });
assert.equal(called, 0, "enrichment fetcher NOT called when gated off");
assert.equal(
out["omniroute/claude-sonnet-4-6"].name,
out["opencode-omniroute/claude-sonnet-4-6"].name,
"claude-sonnet-4-6",
"raw id preserved"
);
@@ -464,7 +463,7 @@ test("provider hook: compression metadata fetcher called when opted in", async (
);
const out = await hook.models!({} as never, { auth: apiAuth("sk") as never });
assert.equal(called, 1, "compression metadata fetcher called");
const combo = out["omniroute/claude-primary"];
const combo = out["opencode-omniroute/claude-primary"];
assert.ok(combo, "combo entry present");
assert.match(
combo.name,

View File

@@ -50,52 +50,6 @@ test("createOmniRouteFetchInterceptor: targets baseURL → Authorization header
}
});
test("createOmniRouteFetchInterceptor: path-prefixed baseURL scopes auth to its normalized inference paths", async () => {
const { calls, restore } = installFetchRecorder();
try {
const prefixedBase = "https://or.example.com/tenant-a/v1";
const f = createOmniRouteFetchInterceptor({
apiKey: KEY,
baseURL: `${prefixedBase}///`,
});
const streamingBody = '{"stream":true}';
await f(`${prefixedBase}/chat/completions?trace=1`, {
method: "POST",
body: streamingBody,
headers: { Accept: "text/event-stream" },
});
await f(`${prefixedBase}/models/?refresh=1`);
await f("https://or.example.com/v1/chat/completions", { method: "POST", body: "{}" });
await f("https://or.example.com/v1/models");
await f("https://or.example.com/tenant-b/v1/chat/completions", {
method: "POST",
body: "{}",
});
await f(`${prefixedBase}/chat/completions/batch`, { method: "POST", body: "{}" });
const headers = calls.map(({ init }) => new Headers(init?.headers));
assert.equal(headers[0]?.get("Authorization"), `Bearer ${KEY}`);
assert.equal(headers[1]?.get("Authorization"), `Bearer ${KEY}`);
for (const index of [2, 3, 4, 5]) {
assert.equal(headers[index]?.get("Authorization"), null);
}
assert.equal(calls[0]?.input, `${prefixedBase}/chat/completions?trace=1`);
assert.equal(calls[0]?.init?.body, streamingBody);
assert.equal(headers[0]?.get("Accept"), "text/event-stream");
const suffixingInterceptor = createOmniRouteFetchInterceptor({
apiKey: KEY,
baseURL: "https://or.example.com/tenant-a/",
});
await suffixingInterceptor(`${prefixedBase}/models`);
const suffixedHeaders = new Headers(calls[6]?.init?.headers);
assert.equal(suffixedHeaders.get("Authorization"), `Bearer ${KEY}`);
} finally {
restore();
}
});
test("createOmniRouteFetchInterceptor: targets baseURL → Authorization OVERRIDES caller-supplied Bearer", async () => {
const { calls, restore } = installFetchRecorder();
try {
@@ -305,7 +259,7 @@ test("loader integration: wired interceptor actually injects Bearer when invoked
{} as never
);
const wiredFetch = (result as { fetch: typeof fetch }).fetch;
await wiredFetch(`${BASE}/models`, {});
await wiredFetch(`${BASE}/v1/models`, {});
assert.equal(calls.length, 1);
const sentHeaders = new Headers((calls[0]!.init as RequestInit).headers);
assert.equal(sentHeaders.get("Authorization"), `Bearer ${KEY}`);

View File

@@ -1,271 +0,0 @@
import test from "node:test";
import assert from "node:assert/strict";
import fs from "node:fs";
import os from "node:os";
import path from "node:path";
import {
createOmniRouteAuthHook,
createOmniRouteConfigHook,
createOmniRouteProviderHook,
parseOmniRoutePluginOptions,
type OmniRouteCompressionMetaFetcher,
type OmniRouteEnrichmentFetcher,
type OmniRouteProvidersFetcher,
type OmniRouteRawModelEntry,
} from "../src/index.js";
const BASE_URL = "https://or.example.com/v1";
const API_KEY = "sk-inference-only";
const MANAGEMENT_READ_TOKEN = "sk-management-read-only";
const RAW_MODELS: OmniRouteRawModelEntry[] = [
{
id: "openai/gpt-test",
context_length: 16_000,
max_output_tokens: 4_000,
capabilities: {
tool_calling: true,
reasoning: false,
vision: false,
thinking: false,
temperature: true,
},
input_modalities: ["text"],
output_modalities: ["text"],
},
];
function apiAuth(key: string) {
return { type: "api" as const, key };
}
test("options: managementReadToken is accepted and preserved", () => {
const parsed = parseOmniRoutePluginOptions({ managementReadToken: MANAGEMENT_READ_TOKEN });
assert.equal(parsed.managementReadToken, MANAGEMENT_READ_TOKEN);
});
test("provider hook: management GET fetchers use managementReadToken while /v1 uses apiKey", async () => {
const calls: Array<[string, string]> = [];
const enrichmentFetcher: OmniRouteEnrichmentFetcher = async (_baseURL, token) => {
calls.push(["pricing", token]);
return new Map();
};
const compressionMetaFetcher: OmniRouteCompressionMetaFetcher = async (_baseURL, token) => {
calls.push(["context", token]);
return [];
};
const providersFetcher: OmniRouteProvidersFetcher = async (_baseURL, token) => {
calls.push(["providers", token]);
return [];
};
const hook = createOmniRouteProviderHook(
{
baseURL: BASE_URL,
managementReadToken: MANAGEMENT_READ_TOKEN,
features: { compressionMetadata: true, usableOnly: true },
},
{
fetcher: async (_baseURL, token) => {
calls.push(["models", token]);
return RAW_MODELS;
},
combosFetcher: async (_baseURL, token) => {
calls.push(["combos", token]);
return [];
},
autoCombosFetcher: async (_baseURL, token) => {
calls.push(["auto-combos", token]);
return [];
},
enrichmentFetcher,
compressionMetaFetcher,
providersFetcher,
}
);
await hook.models!({} as never, { auth: apiAuth(API_KEY) as never });
assert.deepEqual(calls, [
["models", API_KEY],
["combos", MANAGEMENT_READ_TOKEN],
["auto-combos", MANAGEMENT_READ_TOKEN],
["pricing", MANAGEMENT_READ_TOKEN],
["context", MANAGEMENT_READ_TOKEN],
["providers", MANAGEMENT_READ_TOKEN],
]);
});
test("provider hook: absent managementReadToken preserves apiKey fallback", async () => {
const calls: Array<[string, string]> = [];
const hook = createOmniRouteProviderHook(
{ baseURL: BASE_URL, features: { enrichment: false, autoCombos: false } },
{
fetcher: async (_baseURL, token) => {
calls.push(["models", token]);
return RAW_MODELS;
},
combosFetcher: async (_baseURL, token) => {
calls.push(["combos", token]);
return [];
},
}
);
await hook.models!({} as never, { auth: apiAuth(API_KEY) as never });
assert.deepEqual(calls, [
["models", API_KEY],
["combos", API_KEY],
]);
});
test("config hook: managementReadToken stays out of provider inference and MCP config", async () => {
const calls: Array<[string, string]> = [];
const hook = createOmniRouteConfigHook(
{
baseURL: BASE_URL,
managementReadToken: MANAGEMENT_READ_TOKEN,
features: { enrichment: false, autoCombos: false, diskCache: false, mcpAutoEmit: true },
},
{
readAuthJson: async () => ({
"opencode-omniroute": { type: "api" as const, key: API_KEY },
}),
fetcher: async (_baseURL, token) => {
calls.push(["models", token]);
return RAW_MODELS;
},
combosFetcher: async (_baseURL, token) => {
calls.push(["combos", token]);
return [];
},
logger: { warn: () => {} },
}
);
const input: { provider?: Record<string, any>; mcp?: Record<string, any> } = {};
await hook(input as never);
assert.deepEqual(calls, [
["models", API_KEY],
["combos", MANAGEMENT_READ_TOKEN],
]);
assert.equal(input.provider?.["opencode-omniroute"]?.options?.apiKey, API_KEY);
assert.equal(
input.mcp?.["opencode-omniroute"]?.headers?.Authorization,
`Bearer ${API_KEY}`,
"mcpAutoEmit remains independent of managementReadToken"
);
});
test("auth fetch: only intended same-origin inference paths receive apiKey", async () => {
const calls: Array<{ input: RequestInfo | URL; init?: RequestInit }> = [];
const originalFetch = globalThis.fetch;
globalThis.fetch = (async (input: RequestInfo | URL, init?: RequestInit) => {
calls.push({ input, init });
return new Response("ok");
}) as typeof fetch;
try {
const hook = createOmniRouteAuthHook({
baseURL: `${BASE_URL}/`,
managementReadToken: MANAGEMENT_READ_TOKEN,
});
const loaded = await hook.loader!(async () => apiAuth(API_KEY) as never, {} as never);
const interceptedFetch = (loaded as { fetch: typeof fetch }).fetch;
const streamingBody = '{"stream":true}';
await interceptedFetch(`${BASE_URL}/chat/completions?trace=1`, {
method: "POST",
body: streamingBody,
headers: { Accept: "text/event-stream" },
});
await interceptedFetch(`${BASE_URL}/models/?refresh=1`);
await interceptedFetch("https://or.example.com/api/combos");
await interceptedFetch("https://or.example.com/api/mcp/stream");
await interceptedFetch("https://or.example.com/v1/embeddings");
await interceptedFetch("https://third-party.example/v1/chat/completions", {
method: "POST",
body: "{}",
});
const headers = calls.map(({ init }) => new Headers(init?.headers));
assert.equal(headers[0]?.get("Authorization"), `Bearer ${API_KEY}`);
assert.equal(headers[1]?.get("Authorization"), `Bearer ${API_KEY}`);
for (const index of [2, 3, 4, 5]) {
assert.equal(headers[index]?.get("Authorization"), null);
}
assert.equal(calls[0]?.input, `${BASE_URL}/chat/completions?trace=1`);
assert.equal(calls[0]?.init?.body, streamingBody);
assert.equal(headers[0]?.get("Accept"), "text/event-stream");
assert.equal(
calls.some(({ init }) =>
[...new Headers(init?.headers).values()].some((value) =>
value.includes(MANAGEMENT_READ_TOKEN)
)
),
false,
"managementReadToken must never enter inference fetch headers"
);
} finally {
globalThis.fetch = originalFetch;
}
});
test("disk cache: snapshot written under management token A is rejected under token B", async () => {
const tmp = fs.mkdtempSync(path.join(os.tmpdir(), "omniroute-token-snapshot-"));
const previousDataDir = process.env.OPENCODE_DATA_DIR;
process.env.OPENCODE_DATA_DIR = tmp;
try {
const commonDeps = {
readAuthJson: async () => ({
"opencode-omniroute": {
type: "api" as const,
key: API_KEY,
baseURL: BASE_URL,
},
}),
combosFetcher: async () => [],
logger: { warn: () => {} },
};
const features = {
enrichment: false,
autoCombos: false,
diskCache: true,
} as const;
const tokenAHook = createOmniRouteConfigHook(
{ managementReadToken: "token-A", features },
{
...commonDeps,
fetcher: async () => RAW_MODELS,
}
);
await tokenAHook({} as never);
const tokenBHook = createOmniRouteConfigHook(
{ managementReadToken: "token-B", features },
{
...commonDeps,
fetcher: async () => {
throw new Error("offline");
},
}
);
const input: { provider?: Record<string, { models: Record<string, unknown> }> } = {};
await tokenBHook(input as never);
assert.deepEqual(
input.provider?.["opencode-omniroute"]?.models,
{},
"catalog from token A must not hydrate after switching to token B"
);
} finally {
if (previousDataDir === undefined) delete process.env.OPENCODE_DATA_DIR;
else process.env.OPENCODE_DATA_DIR = previousDataDir;
fs.rmSync(tmp, { recursive: true, force: true });
}
});

View File

@@ -1,141 +0,0 @@
/**
* Regression test for #6859.
*
* `resolveOmniRoutePluginOptions()` auto-prefixes `providerId` with
* `"opencode-"` (commit 75b52e286) so OpenCode 1.17.8+'s native-adapter gate
* accepts it as an OC-registered provider id. That prefixed value must stay
* OC-internal (AuthHook.provider / provider registration keys) — it must
* NEVER leak into the identifiers OmniRoute's own server parses to resolve
* credentials (`mapRawModelToModelV2`'s `id`/`providerID`,
* `mapComboToModelV2`'s `providerID`, and the dynamic-hook catalog keys).
*
* OmniRoute's server-side `parseModel()` (open-sse/services/model.ts) splits
* a dispatched model string on `/` to recover the provider name and look up
* credentials. If the plugin embeds the OC-gate-prefixed id in that string,
* the server looks up credentials for a provider named "opencode-omniroute"
* (which never exists in `src/shared/constants/providers.ts`) instead of
* "omniroute" — producing the exact "No credentials for opencode-omniroute" /
* "No active credentials for provider: opencode-omniroute" errors reported
* in #6859.
*/
import test from "node:test";
import assert from "node:assert/strict";
import {
buildStaticProviderEntry,
createOmniRouteProviderHook,
mapRawModelToModelV2,
resolveOmniRoutePluginOptions,
type OmniRouteRawCombo,
} from "../src/index.js";
/**
* Minimal stand-in for OmniRoute's own `parseModel()` (open-sse/services/
* model.ts), which splits a dispatched `<providerID>/<modelID>` string on the
* FIRST "/" to recover the provider name used for credential lookup. Kept
* local (rather than cross-importing the real module) so this package's
* self-contained test suite (`cd @omniroute/opencode-plugin && npm test`)
* doesn't depend on the root repo's `@/*` path-alias resolution.
*/
function splitProviderFromDispatchedModel(modelStr: string): string {
const idx = modelStr.indexOf("/");
return idx === -1 ? modelStr : modelStr.slice(0, idx);
}
const apiAuth = (key: string) => ({ type: "api" as const, key });
test("#6859: server-facing model id/providerID must resolve to the unprefixed provider name", () => {
const resolved = resolveOmniRoutePluginOptions();
// The OC-gate-compatible id stays prefixed — it is legitimate for
// AuthHook.provider / provider registration.
assert.equal(resolved.providerId, "opencode-omniroute");
// A second, unprefixed id must be exposed for anything that reaches
// OmniRoute's own server (model id prefix, ModelV2.providerID, combo keys).
assert.equal(
resolved.omnirouteProviderId,
"omniroute",
"resolveOmniRoutePluginOptions() must expose an unprefixed omnirouteProviderId"
);
// A bare raw /v1/models entry (no existing "/" in its id — the common
// case for OmniRoute's catalog) mapped with the server-facing id.
const model = mapRawModelToModelV2(
{ id: "claude-opus-4-7" },
{ providerId: resolved.omnirouteProviderId, baseURL: "http://localhost:20128" }
);
assert.equal(model.providerID, "omniroute");
assert.equal(model.id, "omniroute/claude-opus-4-7");
// OpenCode dispatches back to OmniRoute using `providerID/modelKey`
// (matches the issue's own repro: `-m opencode-omniroute/oc/big-pickle`).
const dispatchedModelString = `${model.providerID}/claude-opus-4-7`;
const parsedProvider = splitProviderFromDispatchedModel(dispatchedModelString);
assert.equal(
parsedProvider,
"omniroute",
`server-side provider split resolved '${parsedProvider}', expected 'omniroute' — ` +
`credentials lookup would fail for an OC-gate-prefixed provider id`
);
});
test("#6859: createOmniRouteProviderHook end-to-end — catalog keys/providerID never carry the OC-gate prefix", async () => {
const hook = createOmniRouteProviderHook(
{ baseURL: "https://or.example.com/v1" },
{
fetcher: async () => [{ id: "claude-opus-4-7" }],
combosFetcher: async () => [],
}
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-test") as never });
const model = out["omniroute/claude-opus-4-7"];
assert.ok(model, "catalog keyed under the unprefixed provider name");
assert.equal(model.providerID, "omniroute");
assert.ok(
!model.providerID.startsWith("opencode-"),
"the OC-gate prefix must never leak into ModelV2.providerID"
);
});
// #7976: buildStaticProviderEntry (the STATIC provider() config-hook path,
// exercised when the plugin writes `opencode.json` up front rather than
// registering the dynamic `provider.models()` hook) never received the
// #6859 fix. OC dispatches a static-catalog `models` map key verbatim as
// the `model` field of the outbound request — only the top-level
// `provider["<id>"]` segment is stripped for routing — so a bare-slug combo
// key built with the OC-gated `providerId` reaches OmniRoute's server
// doubled and fails credential lookup for the nonexistent provider
// `opencode-omniroute`. Confirmed against the issue's own curl repro
// (`model: "opencode-omniroute/hermes-smart-stack"` → "No active
// credentials for provider: opencode-omniroute").
test("#7976: buildStaticProviderEntry keys bare-slug combo ids with the unprefixed omnirouteProviderId (no double OC-gate prefix)", () => {
const resolved = resolveOmniRoutePluginOptions({ providerId: "omniroute" });
assert.equal(resolved.providerId, "opencode-omniroute");
assert.equal(resolved.omnirouteProviderId, "omniroute");
const combo = {
id: "combo-abc123",
name: "Hermes Smart Stack",
isHidden: false,
models: [],
} as unknown as OmniRouteRawCombo;
const block = buildStaticProviderEntry(
[],
[combo],
resolved,
"https://or.example/v1",
"sk-test"
);
assert.deepEqual(Object.keys(block.models), ["omniroute/hermes-smart-stack"]);
assert.equal(
block.models["opencode-omniroute/hermes-smart-stack"],
undefined,
"combo key must not carry the OC-gate-prefixed providerId — it doubles up once " +
"OC dispatches it verbatim as the `model` field"
);
});

View File

@@ -101,10 +101,7 @@ test("models: extracts apiKey from ctx.auth (type=api) and calls fetcher with it
assert.equal(fetcher.callCount(), 1);
assert.deepEqual(fetcher.callsBy()[0], ["https://or.example.com/v1", "sk-abc"]);
assert.equal(Object.keys(out).length, 3);
// #6859: dynamic-hook catalog keys use the unprefixed omnirouteProviderId
// ("omniroute"), not the OC-gate-prefixed hook.id ("opencode-omniroute") —
// that prefix must never leak into anything OmniRoute's server parses.
assert.ok(out["omniroute/claude-primary"]);
assert.ok(out["opencode-omniroute/claude-primary"]);
});
test("models: returns {} when ctx.auth is null/undefined/wrong-type/empty-key", async () => {
@@ -155,17 +152,13 @@ test("models: maps a sample /v1/models entry to ModelV2 (sanity)", async () => {
{ fetcher, combosFetcher: async () => [] }
);
const out = await hook.models!({} as never, { auth: apiAuth("sk-abc") as never });
// #6859: dynamic-hook catalog keys/ids/providerID use the unprefixed
// omnirouteProviderId ("omniroute") — the OC-gate prefix ("opencode-")
// must stay OC-internal (hook.id / AuthHook.provider) and never leak into
// anything OmniRoute's own server parses for credential lookup.
const claude = out["omniroute/claude-primary"];
const claude = out["opencode-omniroute/claude-primary"];
assert.ok(claude, "claude-primary present");
// `mapRawModelToModelV2` stamps the provider prefix on the id so OC's
// static-catalog reader resolves `(providerID, modelID)` from the key.
assert.equal(claude.id, "omniroute/claude-primary");
assert.equal(claude.id, "opencode-omniroute/claude-primary");
assert.equal(claude.name, "claude-primary");
assert.equal(claude.providerID, "omniroute");
assert.equal(claude.providerID, "opencode-omniroute");
assert.equal(claude.api.id, "openai-compatible");
assert.equal(claude.api.url, "https://or.example.com/v1");
assert.equal(claude.api.npm, "@ai-sdk/openai-compatible");

655
AGENTS.md
View File

@@ -1,117 +1,596 @@
# OmniRoute agent guide
# omniroute — Agent Guidelines
## Project
OmniRoute is a unified AI proxy/router. The repository contains the Next.js application
(`src/`), streaming engine workspace (`open-sse/`), Electron desktop app (`electron/`),
CLI (`bin/`), and tests (`tests/`).
Unified AI proxy/router — route any LLM through one endpoint. Multi-provider support
with **237 provider entries** (OpenAI, Anthropic, Gemini, DeepSeek, Groq, xAI, Mistral, Fireworks,
Cohere, NVIDIA, Cerebras, Pollinations, Puter, Cloudflare AI, HuggingFace, DeepInfra,
SambaNova, Meta Llama API, Moonshot AI, AI21 Labs, Databricks, Snowflake, and many more)
with **MCP Server** (94 tools), **A2A v0.3 Protocol**, and **Electron desktop app**.
## Setup and focused checks
> **Live counts (v3.8.43)**: providers 237 · MCP tools 94 · MCP scopes 30 · A2A skills 6 ·
> open-sse services 134 · routing strategies 17 · auto-combo scoring factors 12 ·
> DB modules 95 · DB migrations 110 · base tables 17 · search providers 11 ·
> i18n locales 42. **Refresh with `npm run check:docs-all`.**
- Runtime: Node.js `>=22.22.3 <23` or `>=24.0.0 <27`; npm 10+.
- Install dependencies: `npm install`.
- Start development: `npm run dev`.
- Build: `npm run build`; release build: `npm run build:release`.
- Lint: `npm run lint`.
- Core type check: `npm run typecheck:core`.
- Run the most focused test for changed code first:
`node --import tsx/esm --test tests/unit/<file>.test.ts`.
- Other suites: `npm run test:vitest`, `npm run test:e2e`,
`npm run test:protocols:e2e`, and `npm run test:ecosystem`.
- Run `npm run check:docs-all` after changing documentation.
## Doc Accuracy Discipline (read before writing any doc)
For the complete test matrix, coverage requirements, and pull-request gates, read
[`CONTRIBUTING.md`](CONTRIBUTING.md#running-tests).
> **If `grep -rn "name" src/ open-sse/ bin/` returns nothing, the name does not exist. Do not document it.**
## Documentation accuracy
The recurring failure mode in AI-generated docs is _plausible-but-unverified specifics_.
Every claim in a `.md` file under `docs/` should be verifiable against the source.
Documentation must describe verified behavior, not plausible behavior.
**Rules (enforced by `npm run check:fabricated-docs`):**
1. Before documenting an API name, endpoint, path, CLI command, or environment variable,
search for it: `rg -n "name" src/ open-sse/ bin/`. If it has no source match, do not
document it.
2. Measure mutable counts instead of writing them from memory: use `wc -l <file>` or a
directory-specific count command.
3. Copy code examples from working usage or run them. Prefer a source link such as
`path/to/file.ts:line` to an invented signature.
4. Run `npm run check:docs-all` for edits under `docs/`; it includes the fabricated-docs
validation.
1. **Never state an API name, endpoint, path, CLI command, or env var without grepping for it first.**
```bash
grep -rn "theName" src/ open-sse/ bin/
# 0 hits → do not document
```
2. **Never write a line count, file size, migration count, provider count, or strategy count from memory.**
```bash
wc -l <file> # exact line count
ls <dir>/*.ts | wc -l # file count
```
3. **Every code example should be copy-pasted from real usage or actually run** — not synthesized.
Link to a real call site (`path:line`) instead of inventing a signature.
4. **Prefer citing real source (`file.ts:line`) over paraphrasing behavior** — verifiable and self-correcting.
5. **A shorter doc that is 100% accurate beats a comprehensive one with fabrications.**
Wrong docs cost more than missing docs, because people trust and act on them.
## Code conventions
The script `scripts/check/check-fabricated-docs.mjs` extracts every route path, env var, hook
name, function name, and file reference from `docs/**/*.md` and verifies each one against the
codebase. Run it locally before pushing docs; it runs in CI via `npm run check:docs-all`.
- Format with Prettier: two spaces, semicolons, double quotes, 100-character line width,
and ES5 trailing commas. Run Prettier on changed files.
- TypeScript target is ES2022 with bundler module resolution. Prefer explicit types.
- Import order: external, internal (`@/` and `@omniroute/open-sse`), then relative.
- Do not add logic to `src/lib/localDb.ts`; import from the owning `src/lib/db/` module.
- Use specific errors and contextual logging. Do not silently swallow SSE-stream failures;
use abort signals for cleanup and return appropriate HTTP status codes.
## Stack
## Security requirements
- **Runtime**: Next.js 16 (App Router), Node.js `>=22.0.0 <23 || >=24.0.0 <27`, ES Modules (`"type": "module"`)
- **Language**: TypeScript 6.0 (`src/`) + JavaScript (`open-sse/`, `electron/`)
- **Database**: better-sqlite3 (SQLite) — `DATA_DIR` configurable, default `~/.omniroute/`
- **Streaming**: SSE via `open-sse` internal workspace package
- **Styling**: Tailwind CSS v4
- **i18n**: next-intl with 42 locales (`src/i18n/messages/`) — refresh with `ls src/i18n/messages/*.json | wc -l`
- **Desktop**: Electron (cross-platform: Windows, macOS, Linux)
- **Schemas**: Zod v4 for all API / MCP input validation
- Never commit credentials or log SQLite encryption keys.
- Validate API inputs with Zod and use the route's required authentication path.
- Sanitize user HTML with DOMPurify.
- Use `resolvePublicCred()` for public upstream OAuth identifiers; never add them as string
literals. See [`docs/security/PUBLIC_CREDS.md`](docs/security/PUBLIC_CREDS.md).
- Use `buildErrorBody()` or `sanitizeErrorMessage()` for HTTP, SSE, executor, and MCP errors;
do not return raw `err.stack` or `err.message`. See
[`docs/security/ERROR_SANITIZATION.md`](docs/security/ERROR_SANITIZATION.md).
- Pass runtime values to `exec()` or `spawn()` through `env`, not interpolation into a script.
---
## Repository map
## Build, Lint, and Test Commands
Read the nearest `AGENTS.md` and the linked deep-dive before making a non-trivial change.
| Command | Description |
| ----------------------------------- | ------------------------------------------------------------------ |
| `npm run dev` | Start Next.js dev server |
| `npm run build` | Production build: `next build` → `.build/next/` + assemble `dist/` |
| `npm run build:release` | Clean rebuild + HEAD sentinel (`dist/BUILD_SHA`) — use for deploy |
| `npm run start` | Run production build |
| `npm run build:cli` | Build CLI package |
| `npm run lint` | ESLint on all source files |
| `npm run typecheck:core` | TypeScript core type checking |
| `npm run typecheck:noimplicit:core` | Strict checking (no implicit any) |
| `npm run check` | Run lint + test |
| `npm run check:cycles` | Check for circular dependencies |
| `npm run electron:dev` | Run Electron app in dev mode |
| `npm run electron:build` | Build Electron app for current OS |
| Area | Location | Start here |
| ---------------------------------- | ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |
| API routes | `src/app/api/v1/` | [`docs/architecture/ARCHITECTURE.md`](docs/architecture/ARCHITECTURE.md) |
| Streaming request handling | `open-sse/handlers/` | [`docs/architecture/ARCHITECTURE.md`](docs/architecture/ARCHITECTURE.md) |
| Provider execution and translation | `open-sse/executors/`, `open-sse/translator/` | [`docs/architecture/CODEBASE_DOCUMENTATION.md`](docs/architecture/CODEBASE_DOCUMENTATION.md) |
| Routing and resilience | `open-sse/services/` | [`open-sse/services/AGENTS.md`](open-sse/services/AGENTS.md), [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md) |
| Database and migrations | `src/lib/db/`, `db/migrations/` | [`src/lib/db/AGENTS.md`](src/lib/db/AGENTS.md) |
| Domain policy | `src/domain/` | [`docs/architecture/ARCHITECTURE.md`](docs/architecture/ARCHITECTURE.md) |
| MCP and A2A | `open-sse/mcp-server/`, `src/lib/a2a/` | [`docs/frameworks/MCP-SERVER.md`](docs/frameworks/MCP-SERVER.md), [`docs/frameworks/A2A-SERVER.md`](docs/frameworks/A2A-SERVER.md) |
| Agent features | `src/lib/{acp,memory,skills,cloudAgent}/` | [`docs/frameworks/AGENT_PROTOCOLS_GUIDE.md`](docs/frameworks/AGENT_PROTOCOLS_GUIDE.md), [`docs/frameworks/SKILLS.md`](docs/frameworks/SKILLS.md) |
| Safety and governance | `src/lib/{guardrails,compliance}/`, `src/server/authz/` | [`docs/security/GUARDRAILS.md`](docs/security/GUARDRAILS.md), [`docs/architecture/AUTHZ_GUIDE.md`](docs/architecture/AUTHZ_GUIDE.md) |
| Operations | `src/mitm/`, tunnel modules, `electron/` | [`docs/ops/TUNNELS_GUIDE.md`](docs/ops/TUNNELS_GUIDE.md), [`docs/guides/ELECTRON_GUIDE.md`](docs/guides/ELECTRON_GUIDE.md) |
**Build output layout:**
## Review focus
| Directory | Purpose | Gitignored |
| --------- | -------------------------------------------------- | ---------- |
| `src/` | Application source (TypeScript / TSX) | No |
| `.build/` | Build intermediates (`distDir = .build/next`) | Yes |
| `dist/` | Shippable bundle assembled by `assembleStandalone` | Yes |
- Keep database operations in `src/lib/db/`; do not issue raw SQL from routes.
- Send provider requests through `open-sse/handlers/`.
- Keep MCP and A2A pages as tabs inside `/dashboard/endpoint`.
- Preserve SSE cleanup, rate-limit header parsing, Zod validation, and provider-schema
validation.
- Treat Memory and Skills as cross-cutting changes that can affect MCP tools, the request
pipeline, and A2A skills.
- Do not close a contributor pull request after using its code; merge it through GitHub so
the contributor receives credit.
The pipeline is a single `next build` pass — intermediates land in `.build/next/`, the
assembled bundle in `dist/`. VPS deploys rsync `dist/` into the remote
`/usr/lib/node_modules/omniroute/app/` directory (VPS image path is unchanged).
## Upstream contributions
### Running Tests
This checkout is a fork of `diegosouzapw/OmniRoute`. Keep fork-only deployment and personal
automation changes out of upstream PRs.
```bash
# All tests (unit + vitest + ecosystem + e2e)
npm run test:all
Start upstream work from the active upstream default branch, not `main`:
# Single test file (Node.js native test runner — most tests use this)
node --import tsx/esm --test tests/unit/your-file.test.ts
node --import tsx/esm --test tests/unit/plan3-p0.test.ts
node --import tsx/esm --test tests/unit/fixes-p1.test.ts
node --import tsx/esm --test tests/unit/security-fase01.test.ts
# Integration tests
node --import tsx/esm --test tests/integration/*.test.ts
# Vitest (MCP server, autoCombo)
npm run test:vitest
# E2E with Playwright
npm run test:e2e
# Protocol clients E2E (MCP transports, A2A)
npm run test:protocols:e2e
# Ecosystem compatibility tests
npm run test:ecosystem
# Coverage (see CONTRIBUTING.md)
npm run test:coverage
```
**For authoritative coverage requirements, test execution, and PR gates, see [`CONTRIBUTING.md`](CONTRIBUTING.md#running-tests).**
---
## Code Style Guidelines
### Formatting (Prettier — enforced via lint-staged)
2 spaces · semicolons required · double quotes (`"`) · 100 char width · es5 trailing commas.
Always run `prettier --write` on changed files.
### TypeScript
- **Target**: ES2022 · **Module**: `esnext` · **Resolution**: `bundler`
- `strict: false` — prefer explicit types, don't rely on inference
- Path aliases: `@/*` → `src/`, `@omniroute/open-sse` → `open-sse/`, `@omniroute/open-sse/*` → `open-sse/*`
### ESLint Rules
- **Security (error, everywhere)**: `no-eval`, `no-implied-eval`, `no-new-func`
- **Relaxed in `open-sse/` and `tests/`**: `@typescript-eslint/no-explicit-any` = warn
- React hooks rules and `@next/next/no-assign-module-variable` disabled in `open-sse/` and `tests/`
### Naming
| Element | Convention | Example |
| ------------------- | -------------------------------- | ------------------------------------ |
| Files | camelCase / kebab-case | `chatCore.ts`, `tokenHealthCheck.ts` |
| React components | PascalCase | `Dashboard.tsx`, `ProviderCard.tsx` |
| Functions/variables | camelCase | `getHealth()`, `switchCombo()` |
| Constants | UPPER_SNAKE | `MAX_RETRIES`, `DEFAULT_TIMEOUT` |
| Interfaces | PascalCase (`I` prefix optional) | `ProviderConfig` |
| Enums | PascalCase (members too) | `LogLevel.Error` |
### Imports
- **Order**: external → internal (`@/`, `@omniroute/open-sse`) → relative (`./`, `../`)
- **No barrel imports** from `localDb.ts` — import from the specific `db/` module instead
### Error Handling
- try/catch with specific error types; always log with context (pino logger)
- Never silently swallow errors in SSE streams — use abort signals for cleanup
- Return proper HTTP status codes (4xx client, 5xx server)
### Security
- **NEVER** commit API keys, secrets, or credentials
- Validate all user inputs with Zod schemas
- Auth middleware required on all API routes
- Never log SQLite encryption keys
- Sanitize user content (dompurify for HTML)
- **Public upstream OAuth identifiers** (Gemini / Antigravity / Windsurf-style client_id/secret + Firebase Web keys extracted from public CLIs): use `resolvePublicCred()` from `open-sse/utils/publicCreds.ts`, **never** as string literals. Full pattern in `docs/security/PUBLIC_CREDS.md`.
- **Error responses** (HTTP / SSE / executor / MCP): use `buildErrorBody()` or `sanitizeErrorMessage()` from `open-sse/utils/error.ts`, **never** put raw `err.stack` / `err.message` in a Response body. Full pattern in `docs/security/ERROR_SANITIZATION.md`.
- **`exec()` / `spawn()` with runtime values**: pass via the `env` option, **never** string-interpolate paths/values into the script body. Reference: `src/mitm/cert/install.ts::updateNssDatabases`.
- Prefer secure-by-default libraries when available — see [tldrsec/awesome-secure-defaults](https://github.com/tldrsec/awesome-secure-defaults) for the curated list (Helmet.js, DOMPurify, ssrf-req-filter, safe-regex, Google Tink, etc.).
---
## Architecture
### Data Layer (`src/lib/db/`)
All persistence uses SQLite through **95 domain-specific modules** in `src/lib/db/`. Top modules:
- Core: `core.ts`, `migrationRunner.ts`, `encryption.ts`, `stateReset.ts`
- Providers / catalog: `providers.ts`, `models.ts`, `providerLimits.ts`, `compressionAnalytics.ts`
- Routing: `combos.ts`, `modelComboMappings.ts`, `domainState.ts`, `commandCodeAuth.ts`
- Auth: `apiKeys.ts`, `secrets.ts`, `registeredKeys.ts`, `sessionAccountAffinity.ts`
- Usage / billing: `quotaSnapshots.ts`, `creditBalance.ts`, `usage*.ts`, `compressionCacheStats.ts`
- Storage: `backup.ts`, `cleanup.ts`, `jsonMigration.ts`, `healthCheck.ts`, `databaseSettings.ts`
- Extension modules: `evals.ts`, `webhooks.ts`, `reasoningCache.ts`, `readCache.ts`, `tierConfig.ts`, `compressionCombos.ts`, `compressionScheduler.ts`, `batches.ts`, `files.ts`, `syncTokens.ts`, `proxies.ts`, `oneproxy.ts`, `upstreamProxy.ts`, `versionManager.ts`, `cliToolState.ts`, `prompts.ts`, `detailedLogs.ts`, `contextHandoffs.ts`, `compression.ts`, `stats.ts`
Live count: `ls src/lib/db/*.ts | wc -l` (currently 95). Drift detection: `npm run check:docs-counts`.
Schema migrations live in `db/migrations/` (**110 files** as of v3.8.43) and run via `migrationRunner.ts`.
`src/lib/localDb.ts` is a **re-export layer only** — never add logic there.
#### DB Internals
- **`core.ts`**: `getDbInstance()` returns a singleton `better-sqlite3` instance with WAL
journaling. `SCHEMA_SQL` defines **17 base tables** (verify with `grep -c "CREATE TABLE" src/lib/db/core.ts` minus 1 for the bookkeeping `_omniroute_migrations` table). Helpers: `rowToCamel`, `encryptConnectionFields`.
- **`migrationRunner.ts`**: Applies versioned SQL files from `db/migrations/` inside transactions.
Tracks applied migrations in `_omniroute_migrations` table.
- **Migrations**: 110 files (`001_initial_schema.sql` → `110_*.sql`).
Each migration is idempotent and runs in a transaction. Live count: `ls src/lib/db/migrations/*.sql | wc -l`.
- **Domain modules** import `getDbInstance()` from `core.ts` for all CRUD operations.
Each module owns a specific table/set of tables (e.g., `providers.ts` → `provider_connections`,
`combos.ts` → `combos`). Encryption helpers protect sensitive fields at rest.
- **`localDb.ts`** re-exports all domain modules — consumers import from here for convenience.
### API Route Layer (`src/app/api/v1/`)
Next.js App Router routes — each follows a consistent pattern:
```
Route → CORS preflight → Body validation (Zod) → Optional auth (extractApiKey/isValidApiKey)
→ API key policy enforcement (enforceApiKeyPolicy) → Handler delegation (open-sse)
```
| Route | Handler | Notes |
| ------------------------------- | ------------------------- | ------------------------------------------------------------- |
| `chat/completions/route.ts` | `handleChat()` | + prompt injection guard (clones request) |
| `responses/route.ts` | `handleChat()` (unified) | Responses API format |
| `embeddings/route.ts` | `handleEmbedding()` | Model listing + creation |
| `images/generations/route.ts` | `handleImageGeneration()` | Model listing + creation |
| `audio/transcriptions/route.ts` | audio handler | Multipart form data |
| `audio/speech/route.ts` | TTS handler | Binary audio response |
| `videos/generations/route.ts` | video handler | ComfyUI/SD WebUI |
| `music/generations/route.ts` | music handler | ComfyUI workflows |
| `moderations/route.ts` | moderation handler | Content safety |
| `rerank/route.ts` | rerank handler | Document relevance |
| `search/route.ts` | search handler | Web search (12 providers per `open-sse/handlers/search.ts:6`) |
**No global Next.js middleware file** — interception is route-specific. Auth is optional
(controlled by `REQUIRE_API_KEY` env). Prompt injection guard is unique to chat completions.
### Request Pipeline (`open-sse/`)
The `open-sse/` workspace is the core streaming engine. Full request flow:
```
Client Request
→ src/app/api/v1/.../route.ts (Next.js route)
→ open-sse/handlers/chatCore.ts::handleChatCore()
→ Semantic/signature cache check
→ Rate limit check (rateLimitManager)
→ Combo routing? → open-sse/services/combo.ts::handleComboChat()
→ resolveComboTargets() → ordered ResolvedComboTarget[]
→ For each target: handleSingleModel() (wraps chatCore)
→ translateRequest() (open-sse/translator/)
→ Convert source format (e.g., OpenAI) → target format (e.g., Claude)
→ getExecutor() → provider-specific executor instance
→ executor.execute() (BaseExecutor → DefaultExecutor or provider-specific)
→ buildUrl() + buildHeaders() + transformRequest()
→ fetch() to upstream provider
→ Retry logic with exponential backoff
→ Response translation back to client format
→ If Responses API: responsesTransformer.ts TransformStream
→ SSE stream or JSON response to client
```
**Handlers** (`open-sse/handlers/`): `chatCore.ts`, `responsesHandler.ts`, `embeddings.ts`,
`imageGeneration.ts`, `videoGeneration.ts`, `musicGeneration.ts`, `audioSpeech.ts`,
`audioTranscription.ts`, `moderations.ts`, `rerank.ts`, `search.ts`.
**Upstream headers**: merged after default auth; same header name replaces executor value.
**T5 intra-family fallback** recomputes headers using only the fallback model id.
Forbidden header names: `src/shared/constants/upstreamHeaders.ts` — keep sanitize,
Zod schemas, and unit tests aligned when editing.
### Provider Categories
- **Free** (3): Qoder AI, Qwen Code, Kiro AI
- **OAuth** (14): Claude Code, Antigravity, Codex, GitHub Copilot, Cursor, Kimi Coding, Kilo Code, Cline, Qwen (⚠️ free tier discontinued 2026-04-15), Kiro, Qoder, Gemini, Windsurf (v3.8), GitLab Duo (v3.8)
- **API Key** (120+): OpenAI, Anthropic, Gemini, DeepSeek, Groq, xAI, Mistral, Perplexity,
Together, Fireworks, Cerebras, Cohere, NVIDIA, Nebius, SiliconFlow, Hyperbolic,
HuggingFace, OpenRouter, Vertex AI, Cloudflare AI, Scaleway, AI/ML API, Pollinations,
Puter, Longcat, Alibaba, Kimi, Minimax, Blackbox, Synthetic, Kilo Gateway,
Z.AI, GLM, Deepgram, AssemblyAI, ElevenLabs, Cartesia, PlayHT, Inworld,
NanoBanana, SD WebUI, ComfyUI, Ollama Cloud, Perplexity Search, Serper, Brave, Exa,
Tavily, OpenCode Zen/Go, Bailian Coding Plan, DeepInfra, Vercel AI Gateway,
Lambda AI, SambaNova, nScale, OVHcloud AI, Baseten, PublicAI, Moonshot AI,
Meta Llama API, v0 (Vercel), Morph, Featherless AI, FriendliAI, LlamaGate,
Galadriel, Weights & Biases Inference, Volcengine, AI21 Labs, Venice.ai,
Codestral, Upstage, Maritalk, Xiaomi MiMo, Inference.net, NanoGPT, Predibase,
Bytez, Heroku AI, Databricks, Snowflake Cortex, GigaChat (Sber), CrofAI,
AgentRouter, ChatGPT Web, Baidu Qianfan, AWS Polly, RunwayML, GitLab Duo,
Amazon Q, Empower, Poe, and many more.
- **Self-Hosted** (8+): LM Studio, vLLM, Lemonade, Llamafile, Triton, Docker Model Runner, Xinference, Oobabooga
- **Custom**: OpenAI-compatible (`openai-compatible-*`) and Anthropic-compatible (`anthropic-compatible-*`) prefixes
Providers are registered in `src/shared/constants/providers.ts` with Zod validation at module load.
### Executors (`open-sse/executors/`)
Provider-specific request executors: `base.ts`, `default.ts`, `cursor.ts`, `codex.ts`,
`antigravity.ts`, `github.ts`, `kiro.ts`, `qoder.ts`, `vertex.ts`,
`cloudflare-ai.ts`, `opencode.ts`, `pollinations.ts`, `puter.ts`.
#### Executor Internals
- **`base.ts`** (`BaseExecutor`): Abstract base with `buildUrl()`, `buildHeaders()`,
`transformRequest()`, retry logic (exponential backoff), and `execute()`. Subclasses
override URL/header/transform methods for provider-specific behavior.
- **`default.ts`** (`DefaultExecutor extends BaseExecutor`): Handles most OpenAI-compatible
providers. Reads provider config from `providerRegistry.ts` to resolve base URL, auth
header format, and request transformations.
- **`getExecutor()`** (`executors/index.ts`): Factory that returns the correct executor
instance based on provider ID. Provider-specific executors (Cursor, Codex, Vertex, etc.)
override only what differs from the default.
### Translator (`open-sse/translator/`)
Translates between API formats (OpenAI-format ↔ Anthropic, Gemini, etc.).
Includes request/response translators with helpers for image handling.
#### Translator Internals
- **`translator/index.ts`**: Exports `translateRequest()` and format constants. Called by
`chatCore.ts` before executor dispatch.
- **Flow**: `translateRequest(body, sourceFormat, targetFormat)` → detects source format
(OpenAI, Anthropic, Gemini) → applies the matching translator module → returns
transformed body ready for the target provider.
- **Response translation** runs in reverse after upstream response, converting back to
the client's expected format.
### Transformer (`open-sse/transformer/`)
`responsesTransformer.ts` — transforms Responses API format to/from Chat Completions format.
#### Transformer Internals
- **`createResponsesApiTransformStream()`**: Returns a `TransformStream` that converts
Chat Completions SSE chunks (`data: {"choices":[...]}`) into Responses API SSE events
(`response.output_item.added`, `response.output_text.delta`, etc.).
- Used when the client sends a Responses API request: the request is internally converted
to Chat Completions format, dispatched normally, and the response is piped through this
transform stream before reaching the client.
### Services (`open-sse/services/`)
134 service modules in `open-sse/services/` (top-level only; more including sub-dirs like `autoCombo/` and `compression/`). Refresh: `ls open-sse/services/*.ts | wc -l`. Key modules:
`combo.ts` (routing engine), `usage.ts`, `tokenRefresh.ts`,
`rateLimitManager.ts`, `accountFallback.ts`, `sessionManager.ts`, `wildcardRouter.ts`,
`autoCombo/`, `intentClassifier.ts`, `taskAwareRouter.ts`, `thinkingBudget.ts`,
`contextManager.ts`, `modelDeprecation.ts`, `modelFamilyFallback.ts`,
`emergencyFallback.ts`, `workflowFSM.ts`, `backgroundTaskDetector.ts`, `ipFilter.ts`,
`signatureCache.ts`, `volumeDetector.ts`, `contextHandoff.ts`, `compression/` (prompt
compression pipeline), and more.
#### Prompt Compression Pipeline (`compression/`)
Modular prompt compression that runs proactively before the existing reactive context manager.
- **`strategySelector.ts`**: Selects compression mode based on config, compression combo assignments,
combo overrides, auto-trigger thresholds, and defaults. Priority: assigned compression combo >
combo override > auto-trigger > default mode > off.
- **`lite.ts`**: 5 lite-mode techniques: `collapseWhitespace`, `dedupSystemPrompt`,
`compressToolResults`, `removeRedundantContent`, `replaceImageUrls`. Target: 10-15% savings at
<1ms latency.
- **`caveman.ts` / `cavemanRules.ts`**: Caveman-style semantic condensation backed by built-in
rules plus file-loaded language packs under `compression/rules/`.
- **`engines/rtk/`**: Rule-based terminal/tool-output compression inspired by RTK patterns. Detects
command output classes, applies JSON filter packs, deduplicates repeated lines, strips ANSI/code
noise, and preserves errors/actionable context. The RTK JSON DSL supports replace,
match-output short-circuit, strip/keep, per-line truncation, head/tail/max-line truncation,
inline tests, trust-gated project/global custom filters, and optional redacted raw-output
retention for authenticated recovery.
- **`engines/registry.ts`**: Registers engines (`caveman`, `rtk`) and powers stacked pipelines.
- **`stats.ts`**: Per-request compression stats tracking (original tokens, compressed tokens,
savings %, techniques used, engine breakdown, compression combo id).
- **`types.ts`**: `CompressionMode` (off/lite/standard/aggressive/ultra/rtk/stacked),
`CompressionConfig`, `CompressionStats`, `CompressionResult`.
- DB settings in `src/lib/db/compression.ts`, compression combos in
`src/lib/db/compressionCombos.ts`, API routes under `src/app/api/settings/compression/`,
`src/app/api/context/*`, and preview/language-pack routes under `src/app/api/compression/*`.
#### Combo Routing Engine (`combo.ts`)
- **`handleComboChat()`**: Entry point for combo-routed requests. Receives the combo config
and iterates through targets in order until one succeeds or all fail.
- **`resolveComboTargets()`**: Expands a combo configuration into an ordered array of
`ResolvedComboTarget[]`, each specifying provider + model + account + credentials.
- **Strategies** (17): priority, weighted, fill-first, round-robin, P2C, random, least-used, reset-aware (v3.8),
reset-window, cost-optimized, strict-random, auto, lkgp, context-optimized, context-relay, headroom, fusion. Source: `ROUTING_STRATEGY_VALUES` in `src/shared/constants/routingStrategies.ts`.
- Each target calls **`handleSingleModel()`** which wraps `handleChatCore()` with
per-target error handling and circuit breaker checks.
### Domain Layer (`src/domain/`)
Policy engine modules: `policyEngine.ts`, `comboResolver.ts`, `costRules.ts`,
`degradation.ts`, `fallbackPolicy.ts`, `lockoutPolicy.ts`, `modelAvailability.ts`,
`providerExpiration.ts`, `quotaCache.ts`, `responses.ts`, `configAudit.ts`.
### MCP Server (`open-sse/mcp-server/`)
**94 tools** total (`TOTAL_MCP_TOOL_COUNT`, `open-sse/mcp-server/server.ts`): a 34-entry base registry (`MCP_TOOLS` in `schemas/tools.ts`, bundling the core / cache / compression / 1proxy / advanced tools) **plus** standalone module sets — memory (3), skill (4), agentSkill (3), pool (6), gamification (8), plugin (8), notion (6), obsidian (22). 3 transports (stdio / SSE / Streamable HTTP). Scoped auth (30 scopes — see `OMNIROUTE_MCP_SCOPES`), Zod schemas. See [`docs/frameworks/MCP-SERVER.md`](docs/frameworks/MCP-SERVER.md).
**Core tools** (20): get_health, list_combos, get_combo_metrics, switch_combo, check_quota,
route_request, cost_report, list_models_catalog, web_search, simulate_route, set_budget_guard,
set_routing_strategy, set_resilience_profile, test_combo, get_provider_metrics,
best_combo_for_task, explain_route, get_session_snapshot, db_health_check, sync_pricing.
**Cache tools** (2): cache_stats, cache_flush.
**Compression tools** (5): compression_status, compression_configure, set_compression_engine,
list_compression_combos, compression_combo_stats.
**1proxy tools** (3): oneproxy_fetch, oneproxy_rotate, oneproxy_stats.
**Memory tools** (3): memory_search, memory_add, memory_clear.
**Skill tools** (4): skills_list, skills_enable, skills_execute, skills_executions.
**Agent-skill tools** (3): A2A skill discovery / invocation bridges.
**Gamification tools** (8): levels, badges, leaderboard, and community-federation queries.
**Plugin tools** (8): plugin marketplace listing, install/enable/disable, and runtime inspection.
**Notion tools** (6) + **Obsidian tools** (22): knowledge-base read/write integrations (the largest tool family — vault search, note CRUD, WebDAV-backed file ops).
#### MCP Internals
- **Tool registration**: Each tool is an object with `{ name, description, inputSchema: ZodSchema,
handler: async (args) => {...} }`. Zod validates inputs before the handler fires.
- **`createMcpServer()`** and **`startMcpStdio()`** exported from `mcp-server/index.ts`.
`createMcpServer()` wires all tool sets; `startMcpStdio()` launches the stdio transport.
- **Transports**: stdio (CLI `omniroute --mcp`), SSE (`/api/mcp/sse`), Streamable HTTP
(`/api/mcp/stream`). All share the same tool/scope engine.
- **Scopes** (30): Control which tool categories an API key can access. Enforcement happens
before handler dispatch.
- **Audit**: Every tool invocation is logged to SQLite (`mcp_audit` table) with tool name,
args, success/failure, API key attribution, and timestamp.
### A2A Server (`src/lib/a2a/`)
JSON-RPC 2.0, SSE streaming, Task Manager with TTL cleanup.
Agent Card at `/.well-known/agent.json`.
Skills (6): `smartRouting.ts`, `quotaManagement.ts`, `providerDiscovery.ts`, `costAnalysis.ts`, `healthReport.ts`, `listCapabilities.ts`.
#### A2A Internals
- **`taskManager.ts`**: State machine lifecycle for tasks: `submitted → working →
completed | failed | canceled`. Tasks have TTL and are cleaned up automatically.
- **JSON-RPC methods**: `message/send` (sync), `message/stream` (SSE), `tasks/get`,
`tasks/cancel`. Dispatched via `POST /a2a`.
- **Skills**: Registered in a DB-backed registry. Each skill receives task context
(messages, metadata) and returns structured results. `quotaManagement.ts` summarizes
quota; `smartRouting.ts` recommends routing decisions.
- **Agent Card**: `/.well-known/agent.json` exposes capabilities, skills, and metadata
for client auto-discovery.
### ACP Module (`src/lib/acp/`)
Agent Communication Protocol registry and manager.
### Memory System (`src/lib/memory/`)
Extraction, injection, retrieval, summarization, and store modules for persistent
conversational memory across sessions.
### Skills System (`src/lib/skills/`)
Extensible skill framework: registry, executor, sandbox, built-in skills,
custom skill support, interception, and injection.
#### Skills Internals
- **`registry.ts`**: DB-backed skill registration and discovery. Skills have metadata
(name, description, version, enabled status) stored in SQLite.
- **`executor.ts`**: Execution engine with configurable timeout and retry logic.
Receives skill name + input, looks up the skill, runs it in the sandbox.
- **`sandbox.ts`**: Isolation layer for custom (user-provided) skills. Limits resource
access and execution time.
- **Built-in skills**: Ship with OmniRoute (e.g., quota management, routing). Located
alongside the registry.
- **Interception/Injection**: Skills can intercept requests in the pipeline (pre/post
processing) or inject context into prompts.
### Compliance (`src/lib/compliance/`)
Policy index for compliance enforcement.
### MITM Proxy (`src/mitm/`)
MITM proxy capability with certificate management, DNS handling, and target routing.
### Middleware (`src/middleware/`)
Request middleware including `promptInjectionGuard.ts`.
### Guardrails (`src/lib/guardrails/`)
Hot-reloadable guardrails framework (3 built-in: pii-masker, prompt-injection, vision-bridge). Fail-open. The `pii-masker` guardrail is registered and runs on every request, but its data-mutating logic is **opt-in** and OFF by default — it only redacts when `PII_REDACTION_ENABLED` (request) / `PII_RESPONSE_SANITIZATION` (response + streaming) are enabled (both `defaultValue: "false"`); with them off, payloads pass through untouched. A request can additionally opt OUT of any guardrail via header (`x-omniroute-disabled-guardrails`). Never make PII default-on (Hard Rule #20). See [`docs/security/GUARDRAILS.md`](docs/security/GUARDRAILS.md).
### Cloud Agents (`src/lib/cloudAgent/`)
`CloudAgentBase` abstract class + 3 agents (codex-cloud, devin, jules). Tasks persisted in `cloud_agent_tasks`; management auth required. See [`docs/frameworks/CLOUD_AGENT.md`](docs/frameworks/CLOUD_AGENT.md).
### Evals (`src/lib/evals/`)
Generic eval framework: `evalRunner.ts`, `runtime.ts`. Targets: combo / model / suite-default. See [`docs/frameworks/EVALS.md`](docs/frameworks/EVALS.md).
### Webhooks (`src/lib/webhookDispatcher.ts`)
HMAC-signed delivery, exponential backoff, auto-disable after 10 failures. 7 event types. See [`docs/frameworks/WEBHOOKS.md`](docs/frameworks/WEBHOOKS.md).
### Authorization Pipeline (`src/server/authz/`)
`classify → policies → enforce`. 3 route classes (PUBLIC / CLIENT_API / MANAGEMENT). See [`docs/architecture/AUTHZ_GUIDE.md`](docs/architecture/AUTHZ_GUIDE.md).
### Reasoning Replay (`src/lib/db/reasoningCache.ts` + `open-sse/services/reasoningCache.ts`)
Hybrid in-memory + SQLite cache for `reasoning_content`. Re-injects on multi-turn for strict providers (DeepSeek V4, Kimi K2, Qwen-Thinking, GLM, xiaomi-mimo). See [`docs/routing/REASONING_REPLAY.md`](docs/routing/REASONING_REPLAY.md).
### Tunnels (`src/lib/{cloudflaredTunnel,ngrokTunnel}.ts` + `src/app/api/tunnels/`)
Cloudflare Quick/Named, ngrok, Tailscale Funnel. See [`docs/ops/TUNNELS_GUIDE.md`](docs/ops/TUNNELS_GUIDE.md).
### Adding a New Provider
1. Register in `src/shared/constants/providers.ts`
2. Add executor in `open-sse/executors/` (if custom logic needed)
3. Add translator in `open-sse/translator/` (if non-OpenAI format)
4. Add OAuth config in `src/lib/oauth/constants/oauth.ts` (if OAuth-based)
5. Add models in `open-sse/config/providerRegistry.ts`
---
## Subdirectory AGENTS.md Files
- **[`src/lib/db/AGENTS.md`](src/lib/db/AGENTS.md)** — SQLite persistence, domain modules, migrations
- **[`open-sse/services/AGENTS.md`](open-sse/services/AGENTS.md)** — Routing engine, combo resolution, strategy selection
## Reference Documentation (docs/)
For any non-trivial change, read the matching deep-dive first:
| Area | Doc |
| ------------------------------------------ | --------------------------------------------------------------------------------------------------------------- |
| Repo navigation | [`docs/architecture/REPOSITORY_MAP.md`](docs/architecture/REPOSITORY_MAP.md) |
| Architecture | [`docs/architecture/ARCHITECTURE.md`](docs/architecture/ARCHITECTURE.md) |
| Engineering reference | [`docs/architecture/CODEBASE_DOCUMENTATION.md`](docs/architecture/CODEBASE_DOCUMENTATION.md) |
| Auto-Combo (12-factor, 17 strategies) | [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md) |
| Resilience (3 layers) | [`docs/architecture/RESILIENCE_GUIDE.md`](docs/architecture/RESILIENCE_GUIDE.md) |
| Skills | [`docs/frameworks/SKILLS.md`](docs/frameworks/SKILLS.md) |
| Memory | [`docs/frameworks/MEMORY.md`](docs/frameworks/MEMORY.md) |
| Cloud agents | [`docs/frameworks/CLOUD_AGENT.md`](docs/frameworks/CLOUD_AGENT.md) |
| Guardrails | [`docs/security/GUARDRAILS.md`](docs/security/GUARDRAILS.md) |
| Evals | [`docs/frameworks/EVALS.md`](docs/frameworks/EVALS.md) |
| Compliance | [`docs/security/COMPLIANCE.md`](docs/security/COMPLIANCE.md) |
| Webhooks | [`docs/frameworks/WEBHOOKS.md`](docs/frameworks/WEBHOOKS.md) |
| Authz | [`docs/architecture/AUTHZ_GUIDE.md`](docs/architecture/AUTHZ_GUIDE.md) |
| Stealth | [`docs/security/STEALTH_GUIDE.md`](docs/security/STEALTH_GUIDE.md) |
| Reasoning replay | [`docs/routing/REASONING_REPLAY.md`](docs/routing/REASONING_REPLAY.md) |
| Agent protocols (A2A / ACP / Cloud) | [`docs/frameworks/AGENT_PROTOCOLS_GUIDE.md`](docs/frameworks/AGENT_PROTOCOLS_GUIDE.md) |
| MCP server | [`docs/frameworks/MCP-SERVER.md`](docs/frameworks/MCP-SERVER.md) |
| A2A server | [`docs/frameworks/A2A-SERVER.md`](docs/frameworks/A2A-SERVER.md) |
| API reference | [`docs/reference/API_REFERENCE.md`](docs/reference/API_REFERENCE.md) + [`docs/openapi.yaml`](docs/openapi.yaml) |
| Provider catalog (auto-generated) | [`docs/reference/PROVIDER_REFERENCE.md`](docs/reference/PROVIDER_REFERENCE.md) |
| Tunnels | [`docs/ops/TUNNELS_GUIDE.md`](docs/ops/TUNNELS_GUIDE.md) |
| Electron desktop | [`docs/guides/ELECTRON_GUIDE.md`](docs/guides/ELECTRON_GUIDE.md) |
| Release flow | [`docs/ops/RELEASE_CHECKLIST.md`](docs/ops/RELEASE_CHECKLIST.md) |
| Quality gates (35 gates, allowlist policy) | [`docs/architecture/QUALITY_GATES.md`](docs/architecture/QUALITY_GATES.md) |
| Cluster opt-in profiles (memory, bifrost) | [`docs/architecture/cluster-decisions.md`](docs/architecture/cluster-decisions.md) |
---
## Fork / Upstream Workflow
This repository is a fork of `diegosouzapw/OmniRoute`. Keep fork-only operational
changes (for example GHCR image publishing, personal deployment workflows, or local
automation) out of upstream contribution PRs.
When preparing a PR for upstream, always start the work branch from `upstream/main`,
not from this fork's `main`:
```bash
git fetch upstream
git switch -c <branch-name> upstream/<default-branch>
git switch -c <branch-name> upstream/main
```
Target that same release branch in the pull request. Stage only the intended files, run the
focused checks, and use a Conventional Commit message (for example, `docs: slim AGENTS.md`).
Only cherry-pick or reapply the changes intended for the upstream PR.
## Reference documentation
---
Use the source of truth for the area you are changing:
## Review Focus
| Area | Reference |
| -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Repository navigation and architecture | [`docs/architecture/REPOSITORY_MAP.md`](docs/architecture/REPOSITORY_MAP.md), [`docs/architecture/ARCHITECTURE.md`](docs/architecture/ARCHITECTURE.md) |
| API and providers | [`docs/reference/API_REFERENCE.md`](docs/reference/API_REFERENCE.md), [`docs/reference/PROVIDER_REFERENCE.md`](docs/reference/PROVIDER_REFERENCE.md), [`docs/openapi.yaml`](docs/openapi.yaml) |
| Routing, resilience, and reasoning | [`docs/routing/AUTO-COMBO.md`](docs/routing/AUTO-COMBO.md), [`docs/architecture/RESILIENCE_GUIDE.md`](docs/architecture/RESILIENCE_GUIDE.md), [`docs/routing/REASONING_REPLAY.md`](docs/routing/REASONING_REPLAY.md) |
| Security | [`docs/security/GUARDRAILS.md`](docs/security/GUARDRAILS.md), [`docs/security/COMPLIANCE.md`](docs/security/COMPLIANCE.md), [`docs/security/STEALTH_GUIDE.md`](docs/security/STEALTH_GUIDE.md) |
| Platform features | [`docs/frameworks/MCP-SERVER.md`](docs/frameworks/MCP-SERVER.md), [`docs/frameworks/A2A-SERVER.md`](docs/frameworks/A2A-SERVER.md), [`docs/frameworks/SKILLS.md`](docs/frameworks/SKILLS.md), [`docs/frameworks/MEMORY.md`](docs/frameworks/MEMORY.md) |
| Releases and quality | [`docs/ops/RELEASE_CHECKLIST.md`](docs/ops/RELEASE_CHECKLIST.md), [`docs/architecture/QUALITY_GATES.md`](docs/architecture/QUALITY_GATES.md) |
- **DB ops** go through `src/lib/db/` modules, never raw SQL in routes
- **Provider requests** flow through `open-sse/handlers/`
- **MCP/A2A pages** are tabs inside `/dashboard/endpoint`, not standalone routes
- **No memory leaks** in SSE streams (abort signals, cleanup)
- **Rate limit headers** must be parsed correctly
- All API inputs validated with **Zod schemas**
- **Provider constants** validated at module load via Zod (`src/shared/validation/providerSchema.ts`)
- **Pricing data** syncs from LiteLLM via `src/lib/pricingSync.ts`
- **Memory/Skills** are cross-cutting: affect MCP tools, request pipeline, and A2A skills
- **⛔ NEVER close a contributor's PR** after using their code — always merge via GitHub so they get credit. See `.agents/workflows/review-prs.md` for full policy.

File diff suppressed because it is too large Load Diff

View File

@@ -35,22 +35,22 @@ For full test matrix, see `CONTRIBUTING.md` → "Running Tests". For deep archit
## Project at a Glance
**OmniRoute** — unified AI proxy/router. One endpoint, 290 LLM providers, auto-fallback.
**OmniRoute** — unified AI proxy/router. One endpoint, 237 LLM providers, auto-fallback.
| Layer | Location | Purpose |
| ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
| API Routes | `src/app/api/v1/` | Next.js App Router — entry points |
| Handlers | `open-sse/handlers/` | Request processing (chat, embeddings, etc) |
| Executors | `open-sse/executors/` | Provider-specific HTTP dispatch |
| 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) |
| 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 |
| Skills | `src/lib/skills/` | Extensible skill framework |
| Memory | `src/lib/memory/` | Persistent conversational memory |
| Layer | Location | Purpose |
| ------------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
| API Routes | `src/app/api/v1/` | Next.js App Router — entry points |
| Handlers | `open-sse/handlers/` | Request processing (chat, embeddings, etc) |
| Executors | `open-sse/executors/` | Provider-specific HTTP dispatch |
| 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 (95 files, 110 migrations) |
| Domain/Policy | `src/domain/` | Policy engine, cost rules, fallback logic |
| MCP Server | `open-sse/mcp-server/` | 94 tools (34 base + memory/skill/agentSkill/pool/notion/obsidian/gamification/plugin modules), 3 transports (stdio / SSE / Streamable HTTP), 30 scopes |
| A2A Server | `src/lib/a2a/` | JSON-RPC 2.0 agent protocol |
| Skills | `src/lib/skills/` | Extensible skill framework |
| Memory | `src/lib/memory/` | Persistent conversational memory |
Monorepo: `src/` (Next.js 16 app), `open-sse/` (streaming engine workspace), `electron/` (desktop app), `tests/`, `bin/` (CLI entry point).
@@ -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`): 17 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). 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.
---
@@ -221,7 +221,7 @@ connection continue serving other models.
- **2 spaces**, semicolons, double quotes, 100 char width, es5 trailing commas (enforced by lint-staged via Prettier)
- **Imports**: external → internal (`@/`, `@omniroute/open-sse`) → relative
- **Naming**: files=camelCase/kebab, components=PascalCase, constants=UPPER_SNAKE
- **ESLint**: `no-eval`, `no-implied-eval`, `no-new-func` = error everywhere; `no-explicit-any` = **error** in `open-sse/` and `tests/` (since #6218 — pre-existing violations are frozen in `config/quality/eslint-suppressions.json`, new ones must be fixed; `npm run lint` applies the suppressions and is what CI runs)
- **ESLint**: `no-eval`, `no-implied-eval`, `no-new-func` = error everywhere; `no-explicit-any` = warn in `open-sse/` and `tests/`
- **TypeScript**: `strict: false`, target ES2022, module esnext, resolution bundler. Prefer explicit types.
### Database
@@ -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, 17 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` |
@@ -428,10 +428,8 @@ git push -u origin feat/your-feature
**Husky hooks**:
- **pre-commit**: lint-staged + `check-docs-sync` + `check:any-budget:t11` + `check:tracked-artifacts`
- **pre-push**: intentionally light (PATH/npm sanity only). `any-budget` + `tracked-artifacts`
already run on pre-commit; re-running them on every push was pure double-pay. CI still
enforces both. (Was Fase 6A.12 full pre-push gate; folded into pre-commit in #6716.)
- **pre-commit**: lint-staged + `check-docs-sync` + `check:any-budget:t11`
- **pre-push**: fast deterministic gates (`check:any-budget:t11` + `check:tracked-artifacts`); intentionally excludes `test:unit` (slow — covered by the CI `test-unit` job). Activated 2026-06-13 (Quality Gates Fase 6A.12).
### Worktree isolation (MANDATORY for every development task)
@@ -461,18 +459,10 @@ 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`.
@@ -490,8 +480,8 @@ list` shows worktrees you didn't create, leave them alone. End every session wit
## Environment
- **Runtime**: Node.js ≥22.0.0 <23 || ≥24.0.0 <27, ES Modules. This is the **only supported** runtime for the published `omniroute` CLI, the server, and the test suites (`node:test` + vitest) — `engines.node` is authoritative and end users never need Bun. A **best-effort `bun:sqlite` compatibility path** exists so a global Bun install (`bun install -g omniroute`) can start without `better-sqlite3` (driver adapter + Bun-aware process spawning); it is **not** a supported runtime — no support guarantees — and every Bun-specific runtime change MUST preserve the Node driver/fallback chain and ship a Bun test (`test:bun:db`) or an explicit reason why the path is Node-only.
- **Bun (build/dev script runner + compatibility smoke only)**: Bun `1.3.14` is pinned as an **exact devDependency** (provisioned through the existing `npm ci` via the lockfile's `@oven/bun-*` platform binaries — no `setup-bun`/ad-hoc install). It is used **only** to execute a small, allow-listed set of TypeScript **gate/generator scripts** (replacing `node --import tsx` for startup speed): the CI checks `check:provider-consistency`, `check:compression-budget`, `check:known-symbols`, and the non-CI `gen:provider-reference`, `bench:compression` — plus the focused `test:bun:db` compatibility smoke suite for the best-effort `bun:sqlite` path. **Do NOT** widen Bun to `npm install`, the build (`build:cli*`), `check:pack-artifact`, the supported published runtime, or the main test runners — those stay on Node. Any new Bun-invoking gate/generator script must be validated byte-identical against its `node --import tsx` output first. After pulling the lockfile change, run `npm install` so `bun` resolves locally (a stale `node_modules` will fail those scripts with `bun: not found`).
- **Runtime**: Node.js ≥22.0.0 <23 || ≥24.0.0 <27, ES Modules. This is the **only** runtime for the published `omniroute` CLI, the server, and the test suites (`node:test` + vitest) — `engines.node` is authoritative and end users never need Bun.
- **Bun (build/dev script runner only)**: Bun `1.3.10` is pinned as an **exact devDependency** (provisioned through the existing `npm ci` via the lockfile's `@oven/bun-*` platform binaries — no `setup-bun`/ad-hoc install). It is used **only** to execute a small, allow-listed set of TypeScript **gate/generator scripts** (replacing `node --import tsx` for startup speed): the CI checks `check:provider-consistency`, `check:compression-budget`, `check:known-symbols`, and the non-CI `gen:provider-reference`, `bench:compression`. **Do NOT** widen Bun to `npm install`, the build (`build:cli*`), `check:pack-artifact`, the published runtime, or the test runners — those stay on Node. Any new Bun-invoking script must be validated byte-identical against its `node --import tsx` output first. After pulling the lockfile change, run `npm install` so `bun` resolves locally (a stale `node_modules` will fail those 5 scripts with `bun: not found`).
- **TypeScript**: 6.0+, target ES2022, module esnext, resolution bundler
- **Path aliases**: `@/*` → `src/`, `@omniroute/open-sse` → `open-sse/`, `@omniroute/open-sse/*` → `open-sse/*`
- **Default port**: 20128 (API + dashboard on same port)
@@ -550,10 +540,10 @@ the stale-enforcement added in Fase 6A.3.
18. Every bug fix must be validated before shipping: a failing-then-passing unit/integration test (TDD) OR a documented live test on the production VPS (192.168.0.15). A fix without either is not merged. See Testing → "Bug fix / issue triage protocol" for the full decision tree.
19. Never develop on the shared main checkout. Every development task runs in its own git worktree on its own dedicated branch, and you MUST confirm the base branch with the operator (e.g. via `AskUserQuestion`) before creating the worktree/branch — never assume `main` or the currently checked-out branch. A `git checkout` in the shared checkout silently destroys other sessions' uncommitted work. Tear down only the worktrees/branches you created (by name, never `fix/*`/`feat/*` wildcards), leave other sessions' worktrees untouched, and end on the branch you started on (the active `release/vX.Y.Z`, never `main`). See Git Workflow → "Worktree isolation".
20. PII redaction/sanitization is **opt-in — never on by default**. OmniRoute proxies for self-hosted/local LLMs where the operator owns the data, so mutating request/response payloads by default would silently corrupt legitimate traffic. The two data-mutating PII feature flags **MUST** keep `defaultValue: "false"` in `src/shared/constants/featureFlagDefinitions.ts`: `PII_REDACTION_ENABLED` (request-side) and `PII_RESPONSE_SANITIZATION` (response + streaming). All three application points — `src/lib/guardrails/piiMasker.ts` (request guardrail), `src/lib/piiSanitizer.ts` (response), `src/lib/streamingPiiTransform.ts` (SSE) — are gated on these flags; with both off the `pii-masker` guardrail still runs but never mutates payloads (data passes through untouched). Flipping either default to `"true"` requires explicit operator approval. The regression guard is `tests/unit/pii-opt-in-default.test.ts` (asserts both definition defaults + behavioral pass-through). Opt-in is per-operator via env or the settings/DB override (`src/lib/db/featureFlags.ts`), never a silent default. See `docs/security/GUARDRAILS.md`.
21. **Release-freeze — the FROZEN release branch belongs to the release captain; development does NOT stop (parallel-cycle model, 2026-07-04).** `/generate-release` opens a marker issue labeled `release-freeze` at the start of reconciliation (Phase 0a), **immediately cuts the next cycle's branch `release/vX+1` from the frozen tip (Phase 0a.0b — bump + living release PR + re-home of open PRs)**, and closes the freeze once the release PR squash-merges to `main`. Before merging **any** PR, every campaign workflow (`/review-prs`, `/review-group-prs`, `/merge-prs`, `/triage-fix-bugs`, `/implement-fix-bugs`, `/triage-features`, `/implement-features`, `/green-prs`, `/port-upstream-*`) **MUST** check `gh issue list --repo diegosouzapw/OmniRoute --label release-freeze --state open` — if a freeze is active: **NEVER merge into the frozen `release/vX.Y.Z` named in the freeze title**; instead resolve the ACTIVE development branch (the **highest** `release/v*` by semver — normally `release/vX+1`, announced in a freeze-issue comment) and **retarget the PR there** (`gh pr edit <N> --base release/vX+1`, then VERIFY with `gh pr view <N> --json baseRefName` — the edit fails silently) and merge normally. **HOLD only when the highest release/v\* branch IS the frozen one** (the short window before 0a.0b completes, or a pre-parallel-cycle release) — in that case leave the PR ready and open, tell the operator, and resume when the next branch appears or the freeze lifts. The just-shipped fixes reach `release/vX+1` via the Phase 5 sync-back (`scripts/release/sync-next-cycle.mjs`); do not try to sync mid-release. This is a **coordination signal, not a permission lock**: the release captain and the campaign sessions share the `diegosouzapw` identity, so a GitHub branch-protection lock cannot distinguish them — only this honored marker prevents the mid-release commit races that forced full CHANGELOG re-reconciliation in v3.8.40/v3.8.41 (a parallel campaign advanced `release/vX.Y.Z` by 34 commits mid-run). The release captain's own reconciliation/cycle-open pushes are exempt — they _are_ the release. Fixes that must land during a freeze (a homologation finding) follow the post-merge read-only rule: land on `main` first via `fix/release-vX.Y.Z-*`. **⛔ ONLY `/generate-release` may raise a release-freeze, and ONLY at its Phase 0a (start of generating a new version) — lifted at Phase 12c after the squash-merge to `main`.** No campaign, session, or agent may open a `release-freeze` marker at any other time — a freeze is **never** a mid-development coordination tool. If a session ever believes a freeze is genuinely, unavoidably necessary outside the `/generate-release` flow, it **MUST first ask the operator (`diegosouzapw`) in chat, explicitly alert "estou criando um freeze" and get an explicit yes** — never open, extend, or re-open a `release-freeze` autonomously. Conversely, do **not** close/lift an active `/generate-release` freeze to unblock campaign merges: it protects the captain's single clean CI run and auto-lifts at Phase 12c — closing it early re-triggers the exact commit race it prevents. Verify a freeze is legitimate before acting on it: an open `release-freeze` whose title/body references an **OPEN** release PR (`gh pr view <N> --json state`) is the authorized captain freeze — hold, don't touch.
21. **Release-freeze — the FROZEN release branch belongs to the release captain; development does NOT stop (parallel-cycle model, 2026-07-04).** `/generate-release` opens a marker issue labeled `release-freeze` at the start of reconciliation (Phase 0a), **immediately cuts the next cycle's branch `release/vX+1` from the frozen tip (Phase 0a.0b — bump + living release PR + re-home of open PRs)**, and closes the freeze once the release PR squash-merges to `main`. Before merging **any** PR, every campaign workflow (`/review-issues`, `/review-prs`, `/implement-features`, `/green-prs`, `/port-upstream-*`) **MUST** check `gh issue list --repo diegosouzapw/OmniRoute --label release-freeze --state open` — if a freeze is active: **NEVER merge into the frozen `release/vX.Y.Z` named in the freeze title**; instead resolve the ACTIVE development branch (the **highest** `release/v*` by semver — normally `release/vX+1`, announced in a freeze-issue comment) and **retarget the PR there** (`gh pr edit <N> --base release/vX+1`, then VERIFY with `gh pr view <N> --json baseRefName` — the edit fails silently) and merge normally. **HOLD only when the highest release/v\* branch IS the frozen one** (the short window before 0a.0b completes, or a pre-parallel-cycle release) — in that case leave the PR ready and open, tell the operator, and resume when the next branch appears or the freeze lifts. The just-shipped fixes reach `release/vX+1` via the Phase 5 sync-back (`scripts/release/sync-next-cycle.mjs`); do not try to sync mid-release. This is a **coordination signal, not a permission lock**: the release captain and the campaign sessions share the `diegosouzapw` identity, so a GitHub branch-protection lock cannot distinguish them — only this honored marker prevents the mid-release commit races that forced full CHANGELOG re-reconciliation in v3.8.40/v3.8.41 (a parallel campaign advanced `release/vX.Y.Z` by 34 commits mid-run). The release captain's own reconciliation/cycle-open pushes are exempt — they _are_ the release. Fixes that must land during a freeze (a homologation finding) follow the post-merge read-only rule: land on `main` first via `fix/release-vX.Y.Z-*`. **⛔ ONLY `/generate-release` may raise a release-freeze, and ONLY at its Phase 0a (start of generating a new version) — lifted at Phase 12c after the squash-merge to `main`.** No campaign, session, or agent may open a `release-freeze` marker at any other time — a freeze is **never** a mid-development coordination tool. If a session ever believes a freeze is genuinely, unavoidably necessary outside the `/generate-release` flow, it **MUST first ask the operator (`diegosouzapw`) in chat, explicitly alert "estou criando um freeze" and get an explicit yes** — never open, extend, or re-open a `release-freeze` autonomously. Conversely, do **not** close/lift an active `/generate-release` freeze to unblock campaign merges: it protects the captain's single clean CI run and auto-lifts at Phase 12c — closing it early re-triggers the exact commit race it prevents. Verify a freeze is legitimate before acting on it: an open `release-freeze` whose title/body references an **OPEN** release PR (`gh pr view <N> --json state`) is the authorized captain freeze — hold, don't touch.
22. **Cross-session safety — this repo is worked by MANY parallel sessions/agents at once; never step on another's in-flight work.** Two absolute bans, both recurring incidents (this rule exists because they keep happening):
- **(a) Never `git stash` / `git stash pop` — ANYWHERE in this repo, including inside an isolated worktree, and including inside any subagent you dispatch.** `git stash` operates on the **shared repository object store**, not the per-worktree working tree — so a stash pushed or popped in one session can silently clobber or resurrect another parallel session's uncommitted changes. This is not hypothetical: 2026-07-02 a `#5923` quotaCache change leaked into the unrelated `#2296` worktree via a global `stash pop`, and the same class reincided through a **subagent**. To compare working changes against a base ref **without** stashing, use `git show <ref>:<path>` or `git diff <ref> -- <path>`; to confirm a typecheck/lint error is pre-existing on the base, inspect the base ref directly (`git show origin/release/vX.Y.Z:<path>`) — never stash your tree away to "get it clean". **Put this ban verbatim in the prompt of every subagent that touches git** (agents don't inherit this file's context — the recurrence was a subagent).
- **(b) Never merge, push, rebase, or force-push a PR / branch / worktree that another session is actively working.** An open PR whose head is a live fix worktree in `.claude/worktrees/` you did **not** create (e.g. `fix-5852`/`fix-5923` carrying fresh commits, even when they share your `diegosouzapw` identity), or any branch another session owns, is **off-limits — HOLD**, and let the owning session merge it. **Before** merging or pushing to any PR you did not create _this_ session, run `git worktree list` to check for a matching in-flight worktree and re-check `gh pr view <N> --json state,headRefOid`. Only the owning session merges its own in-flight PR; mid-flight merges race the owner and re-trigger the exact commit/CHANGELOG races Rule #19 and Rule #21 guard against. (Reinforces Rule #19.)
- **(b) Never merge, push, rebase, or force-push a PR / branch / worktree that another session is actively working.** An open PR whose head is a live fix worktree in `.claude/worktrees/` you did **not** create (e.g. `fix-5852`/`fix-5923` carrying fresh commits, even when they share your `diegosouzapw` identity), or any branch another session owns, is **off-limits — HOLD**, and let the owning session merge it. **Before** merging or pushing to any PR you did not create *this* session, run `git worktree list` to check for a matching in-flight worktree and re-check `gh pr view <N> --json state,headRefOid`. Only the owning session merges its own in-flight PR; mid-flight merges race the owner and re-trigger the exact commit/CHANGELOG races Rule #19 and Rule #21 guard against. (Reinforces Rule #19.)
---

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
@@ -108,19 +103,13 @@ Default URLs:
## Git Workflow
> ⚠️ **NEVER commit directly to `main`.** Always use feature branches.
>
> **PR base:** target the active `release/vX.Y.Z` branch (not `main`). See
> [`docs/ops/BRANCHING_MODEL.md`](docs/ops/BRANCHING_MODEL.md) for the
> release-per-branch + tag-at-ship model.
```bash
# Branch from the active release tip (example: release/v3.8.49)
git fetch origin
git checkout -b feat/your-feature-name origin/release/v3.8.49
git checkout -b feat/your-feature-name
# ... make changes ...
git commit -m "feat: describe your change"
git push -u origin feat/your-feature-name
# Open a Pull Request with base = release/v3.8.49
# Open a Pull Request on GitHub
```
### Branch Naming
@@ -203,15 +192,11 @@ 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 or merging a PR:
- Run the test files that cover your change: `node --import tsx/esm --test tests/unit/<file>.test.ts`
- Run `npm run lint`
- Include or update automated tests in the same PR whenever production code changes
- Run `npm run test:unit`
- Run `npm run test:coverage`
- Ensure the coverage gate stays at **60%+** statements/lines/functions/branches
- Include the changed or added test files in the PR description when production code changed
- Check the SonarQube result on the PR when the project secrets are configured in CI
@@ -237,31 +222,6 @@ Current test status: **122 unit test files** covering:
- **Zod validation** — Use Zod v4 schemas for all API input validation
- **Naming**: Files = camelCase/kebab-case, components = PascalCase, constants = UPPER_SNAKE
### Error handling / empty catch blocks
Never leave a `catch` unexplained. Classify it into one of two buckets (operationalizes
the hard rule "never silently swallow errors in SSE streams"):
- **Intentional (our own best-effort cleanup/telemetry)** — a failure here is expected and
harmless; add a one-line rationale comment, no logging (logging on every request is the
noise this convention avoids).
```ts
} catch {} // closing an already-closed controller after client disconnect is expected
```
- **Should log (external/caller-supplied code, or the swallow changes control flow)** — keep
the catch (never let it break the stream) but emit a contextual `console.debug`/`warn` so the
failure is discoverable.
```ts
} catch (e) {
console.debug("[STREAM] onFailure callback error:", e);
}
```
See `open-sse/utils/stream.ts` and `open-sse/utils/streamHandler.ts` for applied examples.
---
## Project Structure
@@ -277,7 +237,7 @@ 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 +247,7 @@ 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 +255,7 @@ 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
@@ -381,7 +341,7 @@ Write unit tests in `tests/unit/` covering at minimum:
- [ ] Error responses route through `buildErrorBody()` / `sanitizeErrorMessage()` — no raw stack traces in response bodies (see [`docs/security/ERROR_SANITIZATION.md`](./docs/security/ERROR_SANITIZATION.md))
- [ ] Shell commands (`exec` / `spawn`) pass runtime values via `env`, not via string interpolation
- [ ] All inputs validated with Zod schemas
- [ ] Changelog **fragment** added under `changelog.d/{features|fixes|maintenance}/<PR>-<slug>.md` for user-facing changes (see [`changelog.d/README.md`](./changelog.d/README.md)) — do **not** edit `CHANGELOG.md` directly; fragments are aggregated at release time and never conflict between PRs
- [ ] CHANGELOG updated (if user-facing change)
- [ ] Documentation updated (if applicable)
- [ ] No new CodeQL / Secret-Scanning alerts opened, or each one dismissed with technical justification referencing the relevant `docs/security/` doc
- [ ] Routes that spawn child processes (`/api/mcp/`, `/api/cli-tools/runtime/`) classified as `isLocalOnlyPath()` in `src/server/authz/routeGuard.ts` — see [Hard Rule #15](docs/security/ROUTE_GUARD_TIERS.md)

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/*
@@ -55,35 +55,10 @@ ENV NPM_CONFIG_LEGACY_PEER_DEPS=true
# are reproducible.
RUN test -f package-lock.json \
|| (echo "package-lock.json is required for reproducible Docker builds" >&2 && exit 1)
# `npm rebuild <pkg>` re-runs the package's own install script, so under npm 11 +
# `--ignore-scripts` on the parent `npm ci` it depends on npm's script-allowlist
# machinery correctly re-enabling that one package's script. Some self-hosted build
# environments (e.g. Dokploy) hit a broken/incomplete better-sqlite3 native binding
# from that indirection. Invoking `node-gyp rebuild` directly inside the package
# directory bypasses npm's script-running layer entirely and is deterministic
# regardless of npm version or ignore-scripts allowlist behavior.
# node-gyp comes from npm's own bundled copy (deterministic, already in the image)
# instead of `npx --yes`, which would install an arbitrary registry version
# on-demand and run its lifecycle scripts (Sonar docker:S6505).
#
# tls-client-node (chatgpt-web/claude-web/grok-web/lmarena/perplexity-web TLS
# impersonation) hits the same --ignore-scripts wall: its own postinstall.js
# fetches a platform .so/.dylib/.dll from the bogdanfinn/tls-client GitHub
# Releases API and is never invoked when npm ci skips lifecycle scripts. Unlike
# better-sqlite3 above, that script never throws on failure — it only
# `console.warn`s and exits 0 — so a rate-limited or offline build would
# otherwise succeed silently with an empty bin/ and only fail at first request
# in production (TlsClientUnavailableError, #7802). Run it explicitly here so
# a broken/rate-limited fetch fails the BUILD loudly instead of shipping a
# broken image.
RUN --mount=type=cache,id=npm-cache,target=/root/.npm \
npm ci --no-audit --no-fund --legacy-peer-deps --ignore-scripts \
&& (cd node_modules/better-sqlite3 \
&& node /usr/local/lib/node_modules/npm/node_modules/node-gyp/bin/node-gyp.js rebuild) \
&& node -e "require('better-sqlite3')(':memory:').close()" \
&& node node_modules/tls-client-node/scripts/postinstall.js \
&& (test -n "$(find node_modules/tls-client-node/bin -mindepth 1 -print -quit 2>/dev/null)" \
|| (echo "tls-client-node native binary missing after postinstall — GitHub API fetch likely rate-limited or failed (#7802)" >&2 && exit 1))
&& npm rebuild better-sqlite3 \
&& node -e "require('better-sqlite3')(':memory:').close()"
# Build with Turbopack (stable in Next 16, the repo default). The v3.8.27-era
# TurbopackInternalError panic ("entered unreachable code: there must be a path to a
@@ -95,16 +70,6 @@ RUN --mount=type=cache,id=npm-cache,target=/root/.npm \
# See docs/ops/QUALITY_GATE_PLAYBOOK.md Parte 6.
ENV OMNIROUTE_USE_TURBOPACK=1
# Next.js basePath is fixed at build time; pass OMNIROUTE_BASE_PATH here when the
# image should serve under a reverse-proxy subpath without a runtime patch.
ARG OMNIROUTE_BASE_PATH=""
ENV OMNIROUTE_BASE_PATH=$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).
ENV OMNIROUTE_MITM_STUB=1
# Raise the V8 heap ceiling for the build. The webpack production optimization
# pass needs more than V8's default ceiling (~2 GB) for a codebase this size; a
# memory-constrained Docker build otherwise dies with "FATAL ERROR: ... JavaScript
@@ -133,12 +98,6 @@ LABEL org.opencontainers.image.title="omniroute" \
ENV NODE_ENV=production
ENV PORT=20128
ENV HOSTNAME=0.0.0.0
# Runtime heap ceiling. 1024MB is enough for normal traffic but can be tight
# for large fusion-combo panels (many models fanned out in parallel, each
# response buffered in full — see open-sse/services/fusion.ts::FUSION_DEFAULTS
# .maxPanel, issue #1905). Override at `docker run` time with
# `-e OMNIROUTE_MEMORY_MB=2048` (or higher) if you raise fusionTuning.maxPanel
# above the default cap.
ENV OMNIROUTE_MEMORY_MB=1024
ENV NODE_OPTIONS="--max-old-space-size=${OMNIROUTE_MEMORY_MB}"

View File

@@ -27,7 +27,7 @@ When creating _any_ validation tests or one-off logic scripts, default to using
7. **Never bypass Husky hooks** (`--no-verify`, `--no-gpg-sign`) without explicit operator approval.
8. **Always validate inputs with Zod schemas** from `src/shared/validation/schemas.ts`.
9. **Always include tests when changing production code** (`src/`, `open-sse/`, `electron/`, `bin/`).
10. **Coverage must stay**60 % statements / lines / functions / branches — the official CI gate (`npm run test:coverage`). The ratchet baseline in `quality-baseline.json` may freeze a higher floor; never regress it.
10. **Coverage must stay**75 % statements / 75 % lines / 75 % functions / 70 % branches (real measured: ~82 %).
## 3. Codebase navigation

1446
README.md

File diff suppressed because it is too large Load Diff

View File

@@ -42,7 +42,7 @@ Request → CORS → Authz pipeline (classify → policies → enforce)
| --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| **Dashboard Login** | Password-based auth with JWT tokens (HttpOnly cookies) |
| **API Key Auth** | HMAC-signed keys with CRC validation |
| **OAuth 2.0 + PKCE** | 13 providers (Claude, Codex, GitHub, Cursor, Antigravity, Gemini, Kimi Coding, Kilo Code, Cline, Kiro, Qoder, Windsurf, GitLab Duo) |
| **OAuth 2.0 + PKCE** | 14 providers (Claude, Codex, GitHub, Cursor, Antigravity, Gemini, Kimi Coding, Kilo Code, Cline, Qwen, Kiro, Qoder, Windsurf, GitLab Duo) |
| **Token Refresh** | Automatic OAuth token refresh before expiry |
| **Secure Cookies** | `AUTH_COOKIE_SECURE=true` for HTTPS environments |
| **Authz Pipeline** | Route classification (PUBLIC / CLIENT_API / MANAGEMENT) — see `docs/architecture/AUTHZ_GUIDE.md` |
@@ -77,28 +77,21 @@ Custom guardrails register via `registerGuardrail(new MyGuardrail())`. The model
### 🧠 Prompt Injection Guard
Best-effort heuristic middleware that detects prompt injection patterns in LLM requests.
**Not a complete prompt-injection firewall** — can produce false positives (benign
persona/RPG prompts) and false negatives (leetspeak, spacing, non-English patterns).
Middleware that detects and blocks prompt injection attacks in LLM requests:
| Pattern Type | Severity | Example |
| ------------------- | -------- | ---------------------------------------------- |
| System Override | High | "ignore all previous instructions" |
| Role Hijack | Medium | "you are now DAN, you can do anything" |
| Delimiter Injection | High | Encoded separators to break context boundaries |
| DAN/Jailbreak | Medium | Known jailbreak prompt patterns |
| Instruction Leak | High | "show me your system prompt" |
| Encoding Evasion | Medium | base64/rot13/hex decode + instruction keywords |
Only **High** severity detections are blocked in `block` mode. Medium-severity
families are logged but never blocked by `sanitizeRequest`.
| Role Hijack | High | "you are now DAN, you can do anything" |
| Delimiter Injection | Medium | Encoded separators to break context boundaries |
| DAN/Jailbreak | High | Known jailbreak prompt patterns |
| Instruction Leak | Medium | "show me your system prompt" |
Configure via dashboard (Settings → Security) or `.env`:
```env
INPUT_SANITIZER_ENABLED=true
INPUT_SANITIZER_MODE=block # warn | block (injection policy; legacy "redact" does not strip injection text)
INPUT_SANITIZER_BLOCK_THRESHOLD=high # high (default) | medium | low — severities at/above this are blocked in block mode
INPUT_SANITIZER_MODE=block # warn | block | redact
```
### 🔒 PII Redaction
@@ -115,8 +108,7 @@ Automatic detection and optional redaction of personally identifiable informatio
| SSN (US) | `123-45-6789` | `[SSN_REDACTED]` |
```env
PII_REDACTION_ENABLED=true # request PII rewrite; independent of INPUT_SANITIZER_MODE
PII_RESPONSE_SANITIZATION=true # optional: redact PII in provider responses returned to clients
PII_REDACTION_ENABLED=true
```
### 🌐 Network Security

View File

@@ -1,230 +0,0 @@
/**
* ESM path-alias resolver for global installs.
*
* Problem (#7791): when OmniRoute is installed via `npm i -g omniroute`, the
* package files live under `node_modules/omniroute/`. tsx's tsconfig-path
* resolution does not apply there, so specifiers like `@/shared/utils/featureFlags`
* (declared in tsconfig.json `paths` as `@/* → ./src/*`) or
* `@omniroute/open-sse/services/usage` fail with `ERR_MODULE_NOT_FOUND`.
* The CLI crashes before any command can run.
*
* Fix: register a Node ESM `resolve` hook that rewrites alias specifiers to
* absolute file URLs. Covers all tsconfig.json `paths` entries:
* - `@/*` → `./src/*`
* - `@omniroute/open-sse` → `./open-sse/index.ts`
* - `@omniroute/open-sse/*` → `./open-sse/*`
* The hook runs after tsx so `.ts` extensions are already handled, and only
* intercepts matched prefixes — everything else falls through to Node's
* default resolver.
*
* Exposed as pure functions so the mapping logic is unit-testable without a
* running module loader.
*/
import { existsSync, statSync } from "node:fs";
import { dirname, join, relative, isAbsolute } from "node:path";
import { fileURLToPath, pathToFileURL } from "node:url";
/**
* Alias mapping table — mirrors tsconfig.json `paths`.
* Processed top-to-bottom; first matching prefix wins.
*
* Each entry:
* prefix — specifier prefix to match (e.g. `"@/"`, `"@omniroute/open-sse/"`)
* target — directory name under the package root (e.g. `"src"`, `"open-sse"`)
* exact — if true, the prefix also matches when the specifier equals the
* prefix *without* a trailing slash (e.g. `@omniroute/open-sse` →
* `<root>/open-sse/index.ts`).
*
* Exported for tests/consumers.
*/
export const ALIAS_MAP = [
{ prefix: "@/", target: "src", exact: false },
{ prefix: "@omniroute/open-sse/", target: "open-sse", exact: false },
{ prefix: "@omniroute/open-sse", target: "open-sse", exact: true },
];
/** @deprecated Use ALIAS_MAP instead. Kept for backward compat. */
export const ALIAS_PREFIX = "@/";
// This file is ESM (no CJS __dirname global) — derive it from import.meta.url
// so the pathToFileURL(join(__dirname, ...)) call below resolves correctly
// regardless of the caller's cwd.
const __dirname = dirname(fileURLToPath(import.meta.url));
/**
* Resolve an alias specifier to an absolute file URL.
*
* Rules mirror tsconfig.json `paths` via `ALIAS_MAP`:
* "@/..." → <root>/src/...
* "@omniroute/open-sse/..." → <root>/open-sse/...
* "@omniroute/open-sse" → <root>/open-sse/index.*
*
* - Strips the matched alias prefix and joins the remainder against the
* corresponding target directory.
* - Probes the underlying filesystem for the actual source file: the specifier
* itself, then with common source extensions (`.ts`, `.tsx`, `.js`, `.mjs`,
* `.cjs`, `.json`), then `<dir>/index.*`. Returns the first existing match
* as a `file://` URL.
* - Returns `null` for specifiers that do not match any alias, for malformed
* escapes, for path-traversal attempts, or when no corresponding source
* file exists on disk. The caller treats `null` as "defer to the default
* resolver".
*
* @param {string} specifier Module specifier from an `import` statement.
* @param {string} root Absolute path to the package root.
* @returns {string|null} Absolute `file://` URL, or `null` when unresolved.
*/
const SOURCE_EXTENSIONS = [".ts", ".tsx", ".js", ".mjs", ".cjs", ".json"];
export function resolveAlias(specifier, root) {
if (typeof specifier !== "string" || !root || typeof root !== "string") {
return null;
}
// Find the first matching alias entry (top-to-bottom order).
let matchedEntry = null;
let rest = null;
for (const entry of ALIAS_MAP) {
if (specifier.startsWith(entry.prefix)) {
// For non-exact entries, require at least one char after the prefix
// to avoid matching bare "@/" as "nothing".
const after = specifier.slice(entry.prefix.length);
if (after.length === 0 && !entry.exact) continue;
matchedEntry = entry;
rest = after;
break;
}
}
if (!matchedEntry) return null;
const targetDir = join(root, matchedEntry.target);
// Exact match (e.g. `@omniroute/open-sse` with no trailing path) →
// resolve to `<target>/index.*`.
if (rest === "" || rest === undefined) {
return probeIndex(targetDir);
}
// Guard against absolute-ish escapes (`@//etc/passwd`, `@/\x00`).
if (rest.startsWith("/") || rest.startsWith("\\")) {
return null;
}
// Guard against path-traversal escapes (`@/../../../etc/hostname`).
const segments = rest.split(/[\\\/]+/);
if (segments.includes("..")) {
return null;
}
const base = join(targetDir, rest);
if (!isWithinRoot(targetDir, base)) {
return null;
}
return probeFile(base) ?? probeIndex(base) ?? null;
}
/**
* Probe a bare path and its extension variants. Returns the first existing
* match as a `file://` URL, or `null`.
*/
function probeFile(base) {
// Try extension variants first — a bare `base` that happens to be a directory
// would match existsSync() but should NOT be returned as a file URL (the
// caller expects a file, not a directory). Extension-probing avoids this
// false positive (e.g. `usage` vs `usage.ts` vs `usage/`).
for (const ext of SOURCE_EXTENSIONS) {
const candidate = base + ext;
if (existsSync(candidate)) return pathToFileURL(candidate).href;
}
// Only accept the bare path if it is NOT a directory.
if (existsSync(base)) {
try {
const st = statSync(base);
if (!st.isDirectory()) return pathToFileURL(base).href;
} catch {}
}
return null;
}
/**
* Probe a directory for an `index.*` entry. Returns the first existing
* match as a `file://` URL, or `null`.
*/
function probeIndex(dir) {
const indexBase = join(dir, "index");
for (const ext of SOURCE_EXTENSIONS) {
const candidate = indexBase + ext;
if (existsSync(candidate)) return pathToFileURL(candidate).href;
}
return null;
}
/**
* True when `candidate` resolves to a location inside `ancestor` (or is
* `ancestor` itself). Used as a second, path-normalization-aware layer of
* defense against traversal beyond the literal `..` segment check above.
*
* @param {string} ancestor
* @param {string} candidate
* @returns {boolean}
*/
function isWithinRoot(ancestor, candidate) {
const rel = relative(ancestor, candidate);
return rel === "" || (!rel.startsWith("..") && !isAbsolute(rel));
}
/**
* Register the ESM resolve hook for the current process. Safe to call multiple
* times — subsequent calls are no-ops once the hook is installed.
*
* Uses Node's stable `module.register()` API (available since Node 20.6,
* required Node 22+ here). The hook runs in a worker thread but only reads the
* captured `root`, so no shared-state hazards.
*
* @param {string} root Absolute path to the package root.
* @returns {Promise<boolean>} Resolves `true` once registered (or if already
* registered), `false` on environments where `module.register` is unavailable.
*/
let _registered = false;
export async function registerAliasResolver(root) {
// Validate input FIRST, before the _registered short-circuit. Otherwise the
// second call in the same process (e.g. a test suite that already registered
// once) would silently return `true` for invalid input instead of rejecting,
// masking programmer errors. Input validation must be unconditional.
if (!root || typeof root !== "string") {
throw new TypeError("registerAliasResolver: root must be a non-empty string");
}
if (_registered) return true;
// if the directory does not exist we would only mask a real misconfiguration
// by installing a hook that rewrites to nowhere.
if (!existsSync(join(root, "src"))) {
return false;
}
try {
const { register } = await import("node:module");
// #7808: load the hook from a real file on disk via pathToFileURL() instead
// of building a `data:text/javascript,...` URL dynamically. CodeQL's
// `js/incomplete-url-substring-sanitization` flagged the interpolated
// `new URL(...)` call; a file URL produced by pathToFileURL() is a trusted,
// fully-parsed URL — no sanitization ambiguity. The hook source lives in
// `bin/aliasResolverHook.mjs` (sibling of this file), shipped via
// package.json "files": ["bin/"].
const hookPath = join(__dirname, "aliasResolverHook.mjs");
const hookUrl = pathToFileURL(hookPath);
register(hookUrl, { data: { root } });
_registered = true;
return true;
} catch {
// Older Node or sandboxed env without module.register — fall back to the
// default resolver. The bug will resurface only in the exact global-install
// scenario, which is what we explicitly patched; other entry points still
// work because they import via relative paths.
return false;
}
}
// #7808: the ESM loader hook source now lives in `bin/aliasResolverHook.mjs`,
// loaded via `pathToFileURL()` above. The previous inline `HOOK_SOURCE` template
// literal was removed because its `new URL(\`data:text/javascript,...\`)` wrapper
// triggered CodeQL `js/incomplete-url-substring-sanitization`. The hook logic
// itself is unchanged — see aliasResolverHook.mjs for the resolver behaviour.

View File

@@ -1,126 +0,0 @@
/**
* ESM loader hook for path-alias resolution (#7791 + #7808).
*
* This file runs in Node's loader worker thread after being registered via
* `module.register(url, data)` from `bin/aliasResolver.mjs`. It MUST NOT import
* anything from the parent module — all inputs arrive through `initialize(data)`.
*
* Behaviour:
* - Rewrites alias specifiers to absolute filesystem paths, mirroring
* tsconfig.json `paths`:
* - `@/*` → <root>/src/*
* - `@omniroute/open-sse` → <root>/open-sse/index.*
* - `@omniroute/open-sse/*` → <root>/open-sse/*
* - Probes the usual source extensions (`.ts`, `.tsx`, `.js`, `.mjs`, `.cjs`,
* `.json`) plus `index.*` for directory imports.
* - Returns `shortCircuit: true` only when a candidate file exists on disk;
* otherwise delegates to the next resolver (tsx/Node) so unrelated imports
* and legitimate "module not found" errors pass through unchanged.
*
* Why a separate file instead of an inline `data:` URL?
* CodeQL's `js/incomplete-url-substring-sanitization` flags dynamic `new URL(...)`
* construction with interpolated strings. A real file URL produced by
* `pathToFileURL()` is a trusted, fully-parsed URL — no sanitization ambiguity.
*/
import { pathToFileURL } from "node:url";
import { join, relative, isAbsolute } from "node:path";
import { existsSync, statSync } from "node:fs";
let ROOT = "";
export function initialize(data) {
ROOT = (data && data.root) || "";
}
const EXTENSIONS = [".ts", ".tsx", ".js", ".mjs", ".cjs", ".json"];
/**
* Alias prefix table — mirrors ALIAS_MAP in aliasResolver.mjs and
* tsconfig.json `paths`. Processed top-to-bottom; first match wins.
*
* @type {Array<{prefix: string, target: string, exact: boolean}>}
*/
const ALIAS_TABLE = [
{ prefix: "@/", target: "src", exact: false },
{ prefix: "@omniroute/open-sse/", target: "open-sse", exact: false },
{ prefix: "@omniroute/open-sse", target: "open-sse", exact: true },
];
function tryResolveAliasFsPath(specifier) {
if (!ROOT || typeof specifier !== "string") return null;
// Find the first matching alias entry.
let matchedEntry = null;
let rest = null;
for (const entry of ALIAS_TABLE) {
if (specifier.startsWith(entry.prefix)) {
const after = specifier.slice(entry.prefix.length);
if (after.length === 0 && !entry.exact) continue;
matchedEntry = entry;
rest = after;
break;
}
}
if (!matchedEntry) return null;
const targetDir = join(ROOT, matchedEntry.target);
// Exact match (e.g. `@omniroute/open-sse`) → resolve to `<target>/index.*`.
if (rest === "" || rest === undefined) {
return probeIndex(targetDir);
}
// Guard against absolute-ish escapes.
if (rest.startsWith("/") || rest.startsWith("\\")) return null;
// Guard against path-traversal escapes.
const segments = rest.split(/[\\\/]+/);
if (segments.includes("..")) return null;
const base = join(targetDir, rest);
if (!isWithinRoot(targetDir, base)) return null;
return probeFile(base) ?? probeIndex(base) ?? null;
}
function probeFile(base) {
// Extension variants first — avoids matching a bare directory name.
for (const ext of EXTENSIONS) {
const candidate = base + ext;
if (existsSync(candidate)) return candidate;
}
if (existsSync(base)) {
try {
const st = statSync(base);
if (!st.isDirectory()) return base;
} catch {}
}
return null;
}
function probeIndex(dir) {
const indexBase = join(dir, "index");
for (const ext of EXTENSIONS) {
const candidate = indexBase + ext;
if (existsSync(candidate)) return candidate;
}
return null;
}
/**
* True when `candidate` resolves to a location inside `ancestor` (or is
* `ancestor` itself). Path-normalization-aware defense against traversal.
*/
function isWithinRoot(ancestor, candidate) {
const rel = relative(ancestor, candidate);
return rel === "" || (!rel.startsWith("..") && !isAbsolute(rel));
}
export function resolve(specifier, context, nextResolve) {
const fsPath = tryResolveAliasFsPath(specifier);
if (fsPath) {
return {
url: pathToFileURL(fsPath).href,
shortCircuit: true,
};
}
return nextResolve(specifier, context);
}

View File

@@ -1,163 +0,0 @@
import { chmodSync, existsSync, writeFileSync } from "node:fs";
import { decryptCredential } from "../encryption.mjs";
import { findProviderConnection, listProviderConnections } from "../provider-store.mjs";
import { openOmniRouteDb } from "../sqlite.mjs";
import { t } from "../i18n.mjs";
/**
* Local-only, operator-invoked command that dumps DECRYPTED provider credentials
* (apiKey/accessToken/refreshToken/idToken). This never runs inside the HTTP server
* process and must never be reachable over the network — no src/app/api/ route wraps
* this. See docs/security/ for the threat-model writeup referenced in issue #6683.
*/
const CREDENTIAL_FIELDS = [
{ key: "apiKey", envSuffix: "API_KEY" },
{ key: "accessToken", envSuffix: "ACCESS_TOKEN" },
{ key: "refreshToken", envSuffix: "REFRESH_TOKEN" },
{ key: "idToken", envSuffix: "ID_TOKEN" },
];
const VALID_FORMATS = new Set(["json", "env"]);
const SECURE_FILE_MODE = 0o600;
export function registerAuthExport(program) {
program
.command("auth export")
.description(t("authExport.description"))
.option("--id <id>", t("authExport.idOpt"))
.option("--format <format>", t("authExport.formatOpt"), "json")
.option("--out <file>", t("authExport.outOpt"))
.option("--force", t("authExport.forceOpt"))
.action(async (opts, cmd) => {
const globalOpts = cmd.optsWithGlobals();
const exitCode = await runAuthExportCommand({ ...opts, ...globalOpts });
if (exitCode !== 0) process.exit(exitCode);
});
}
export async function runAuthExportCommand(opts = {}) {
// Security control (a): confirmation gate BEFORE any DB access — a dry invocation
// never opens the database and never decrypts anything.
if (!opts.force) {
printConfirmationGate();
return 0;
}
const format = opts.format || "json";
if (!VALID_FORMATS.has(format)) {
console.error(t("authExport.invalidFormat", { format }));
return 1;
}
if (!process.env.STORAGE_ENCRYPTION_KEY) {
console.error(t("authExport.missingKey"));
return 1;
}
// Security control (b): stderr warning banner BEFORE any plaintext is emitted.
process.stderr.write(t("authExport.warning") + "\n");
const rows = await loadTargetConnections(opts.id);
if (rows === null) {
console.error(t("authExport.notFound", { id: opts.id }));
return 1;
}
const exported = rows.map(exportConnection);
const content = format === "env" ? formatAsEnv(exported) : formatAsJson(exported);
if (opts.out) {
writeSecureFile(opts.out, content);
} else {
console.log(content);
}
return 0;
}
function printConfirmationGate() {
console.log(
`\n${t("authExport.confirmHeading")}\n\n${t("authExport.confirmBody")}\n\n${t("authExport.confirmFooter")}\n`
);
}
async function loadTargetConnections(id) {
const { db } = await openOmniRouteDb();
try {
if (!id) return listProviderConnections(db);
const connection = findProviderConnection(db, id);
return connection ? [connection] : null;
} finally {
db.close();
}
}
function decryptField(rawValue) {
// Security control (d): a per-field decrypt failure surfaces as a boolean flag,
// never the caught error text. Security control (e): the caught error is never
// interpolated into any message.
try {
return { value: decryptCredential(rawValue), failed: false };
} catch {
return { value: null, failed: true };
}
}
function exportConnection(connection) {
const result = {
id: connection.id,
provider: connection.provider,
name: connection.name,
authType: connection.authType,
};
for (const { key } of CREDENTIAL_FIELDS) {
const rawValue = connection[key];
if (!rawValue) {
result[key] = null;
result[`${key}DecryptFailed`] = false;
continue;
}
const { value, failed } = decryptField(rawValue);
result[key] = value;
result[`${key}DecryptFailed`] = failed;
}
return result;
}
function formatAsJson(rows) {
return JSON.stringify(rows, null, 2);
}
function envSafeSegment(value) {
return String(value || "")
.toUpperCase()
.replace(/[^A-Z0-9]+/g, "_")
.replace(/^_+|_+$/g, "");
}
function formatAsEnv(rows) {
const lines = [];
for (const row of rows) {
lines.push(`# ${row.provider} (${row.id})`);
const providerSegment = envSafeSegment(row.provider);
for (const { key, envSuffix } of CREDENTIAL_FIELDS) {
const value = row[key];
if (!value) continue;
lines.push(`OMNIROUTE_${providerSegment}_${envSuffix}=${value}`);
}
}
return lines.join("\n");
}
function writeSecureFile(filePath, content) {
// Security control (c): file output written with mode 0o600 (plus chmodSync if the
// file pre-existed, belt-and-suspenders against an already world-readable file).
const preExisted = existsSync(filePath);
writeFileSync(filePath, content, { mode: SECURE_FILE_MODE });
if (preExisted) {
chmodSync(filePath, SECURE_FILE_MODE);
}
}

View File

@@ -78,15 +78,18 @@ export function registerBackup(program) {
if (exitCode !== 0) process.exit(exitCode);
});
// Legacy: `omniroute backup` without a subcommand still creates a backup
// (documented as the canonical usage in USER_GUIDE.md / CLI-TOOLS.md /
// AGENT-SKILLS.md). No flags are declared here — declaring the same
// option names as `create`/`auto enable` here previously shadowed them
// (#8512), and no doc shows `omniroute backup` invoked with flags.
// Legacy: `omniroute backup` without subcommand still creates a backup
backup.action(async (opts) => {
const exitCode = await runBackupCommand(opts);
if (exitCode !== 0) process.exit(exitCode);
});
backup
.option("--name <name>", t("backup.nameOpt"))
.option("--cloud", t("backup.cloudOpt"))
.option("--encrypt", t("backup.encryptOpt"))
.option("--key-file <path>", t("backup.keyFileOpt"))
.option("--exclude <pattern>", t("backup.excludeOpt"), (v, prev = []) => [...prev, v], [])
.option("--retention <n>", t("backup.retentionOpt"), parseInt);
}
export function registerRestore(program) {

View File

@@ -15,11 +15,7 @@ function readCache() {
try {
const raw = JSON.parse(readFileSync(cachePath(), "utf8"));
if (raw && typeof raw.ts === "number" && Date.now() - raw.ts < CACHE_TTL_MS) return raw;
} catch (err) {
if (process.env.OMNIROUTE_DEBUG_COMPLETION) {
console.error("[omniroute completion] readCache failed:", err?.message ?? err);
}
}
} catch {}
return null;
}
@@ -45,20 +41,12 @@ async function refreshCache(opts = {}) {
const j = await mr.value.json();
models = (Array.isArray(j) ? j : j.data || []).map((m) => m.id).filter(Boolean);
}
} catch (err) {
if (process.env.OMNIROUTE_DEBUG_COMPLETION) {
console.error("[omniroute completion] refreshCache failed:", err?.message ?? err);
}
}
} catch {}
const data = { combos, providers, models, ts: Date.now() };
try {
mkdirSync(dirname(cachePath()), { recursive: true });
writeFileSync(cachePath(), JSON.stringify(data));
} catch (err) {
if (process.env.OMNIROUTE_DEBUG_COMPLETION) {
console.error("[omniroute completion] writeCache failed:", err?.message ?? err);
}
}
} catch {}
return data;
}

View File

@@ -24,7 +24,7 @@ async function restCompressionStatus() {
const combosBody = combosRes.ok ? await combosRes.json() : { combos: [] };
const analytics = analyticsRes && analyticsRes.ok ? await analyticsRes.json() : null;
return {
strategy: settings.defaultMode || "standard",
engine: settings.engine ?? null,
settings,
combos: combosBody.combos ?? combosBody,
analytics,
@@ -33,10 +33,7 @@ async function restCompressionStatus() {
async function restCompressionConfigure(config) {
const body = { ...config };
if (body.strategy) {
body.defaultMode = body.strategy === "caveman" ? "standard" : normalizeEngine(body.strategy);
delete body.strategy;
}
if (body.engine) body.engine = normalizeEngine(body.engine);
const res = await apiFetch("/api/settings/compression", { method: "PUT", body });
if (!res.ok) {
process.stderr.write(`Error: ${res.status}\n`);
@@ -46,10 +43,9 @@ async function restCompressionConfigure(config) {
}
async function restSetEngine(name) {
const normalized = normalizeEngine(name);
const res = await apiFetch("/api/settings/compression", {
method: "PUT",
body: { defaultMode: normalized === "caveman" ? "standard" : normalized },
body: { engine: normalizeEngine(name) },
});
if (!res.ok) {
process.stderr.write(`Error: ${res.status}\n`);
@@ -107,11 +103,7 @@ export async function runCompressionStatus(opts, cmd) {
export async function runCompressionConfigure(opts, cmd) {
const config = {};
// #6571 — both the MCP tool schema (compressionConfigureInput) and
// handleCompressionConfigure expect `strategy`, not `engine`; a non-strict
// MCP schema silently strips an unrecognized `engine` key on the primary
// (MCP-mounted) path, so this must be `strategy` on both paths.
if (opts.engine) config.strategy = normalizeEngine(opts.engine);
if (opts.engine) config.engine = opts.engine;
if (opts.cavemanAggressiveness !== undefined)
config.caveman = { aggressiveness: opts.cavemanAggressiveness };
if (opts.rtkBudget !== undefined) config.rtk = { tokenBudget: opts.rtkBudget };
@@ -171,7 +163,7 @@ export function registerCompression(program) {
engine.command("set <name>").action(runCompressionEngineSet);
engine.command("get").action(async (opts, cmd) => {
const data = await mcpCall("omniroute_compression_status", {}, restCompressionStatus);
process.stdout.write(`${data.strategy ?? "(default)"}\n`);
process.stdout.write(`${data.engine ?? "(default)"}\n`);
});
const combos = cmp.command("combos").description(t("compression.combos.description"));

View File

@@ -1,22 +1,17 @@
import { execFile } from "node:child_process";
import { t } from "../i18n.mjs";
function parsePort(value, fallback) {
const parsed = parseInt(String(value), 10);
return Number.isFinite(parsed) && parsed > 0 && parsed <= 65535 ? parsed : fallback;
}
export function registerDashboard(program) {
program
.command("dashboard")
.description(t("dashboard.description"))
.option("--url", t("dashboard.urlOnly"))
.option("--port <port>", "Port the server is running on")
.option("--port <port>", "Port the server is running on", "20128")
.option("--tui", t("dashboard.tui") || "Open interactive TUI dashboard (terminal UI)")
.action(async (opts, cmd) => {
if (opts.tui) {
const globalOpts = cmd.optsWithGlobals();
const port = parsePort(opts.port ?? process.env.PORT ?? "20128", 20128);
const port = opts.port ? parseInt(String(opts.port), 10) : 20128;
const baseUrl = globalOpts.baseUrl ?? `http://localhost:${port}`;
const apiKey = globalOpts.apiKey ?? null;
const { startInteractiveTui } = await import("../tui/Dashboard.jsx");
@@ -29,7 +24,7 @@ export function registerDashboard(program) {
}
export async function runDashboardCommand(opts = {}) {
const port = parsePort(opts.port ?? process.env.PORT ?? "20128", 20128);
const port = opts.port ? parseInt(String(opts.port), 10) : 20128;
const dashboardUrl = `http://localhost:${port}`;
if (opts.url) {
@@ -49,22 +44,22 @@ export async function runDashboardCommand(opts = {}) {
return 0;
}
/**
* Resolve the command and args to open a URL in the default browser
* for a given platform. Exported for testing — callers should use openFallback().
* @param {"darwin"|"win32"|string} platform
* @param {string} url
* @returns {{ cmd: string, args: string[] }}
*/
export function resolveOpenCommand(platform, url) {
if (platform === "darwin") return { cmd: "open", args: [url] };
if (platform === "win32") return { cmd: "rundll32", args: ["url.dll,FileProtocolHandler", url] };
return { cmd: "xdg-open", args: [url] };
}
function openFallback(url) {
return new Promise((resolve) => {
const { cmd, args } = resolveOpenCommand(process.platform, url);
const { platform } = process;
let cmd, args;
if (platform === "darwin") {
cmd = "open";
args = [url];
} else if (platform === "win32") {
cmd = "cmd";
args = ["/c", "start", "", url];
} else {
cmd = "xdg-open";
args = [url];
}
execFile(cmd, args, { stdio: "ignore" }, () => resolve());
});
}

View File

@@ -48,11 +48,7 @@ export async function runHealthCommand(opts = {}) {
}
try {
const res = await apiFetch("/api/monitoring/health", {
retry: false,
timeout: 5000,
acceptNotOk: true,
});
const res = await apiFetch("/api/health", { retry: false, timeout: 5000, acceptNotOk: true });
if (!res.ok) {
console.error(t("common.error", { message: `HTTP ${res.status}` }));
return 1;
@@ -70,22 +66,29 @@ export async function runHealthCommand(opts = {}) {
if (health.uptime) console.log(t("health.uptime", { uptime: health.uptime }));
if (health.version) console.log(` Version: ${health.version}`);
if (health.activeConnections !== undefined) {
console.log(t("health.requests", { count: health.activeConnections }));
if (health.requests !== undefined) {
console.log(t("health.requests", { count: health.requests }));
}
if (health.circuitBreakers && opts.verbose) {
if (health.breakers && opts.verbose) {
console.log("\n \x1b[1mCircuit Breakers\x1b[0m");
const { open = 0, halfOpen = 0, closed = 0 } = health.circuitBreakers;
console.log(` \x1b[32m● closed\x1b[0m ${closed}`);
console.log(` \x1b[33m○ half-open\x1b[0m ${halfOpen}`);
console.log(` \x1b[31m○ open\x1b[0m ${open}`);
for (const [name, status] of Object.entries(health.breakers)) {
const state =
status.state === "closed" ? "\x1b[32m● closed\x1b[0m" : "\x1b[33m○ open\x1b[0m";
console.log(` ${name.padEnd(20)} ${state}`);
}
}
if (opts.verbose && health.memoryUsage) {
if (health.cache && opts.verbose) {
console.log("\n \x1b[1mCache\x1b[0m");
console.log(` Semantic hits: ${health.cache.semanticHits || 0}`);
console.log(` Signature hits: ${health.cache.signatureHits || 0}`);
}
if (opts.verbose && health.memory) {
console.log("\n \x1b[1mMemory\x1b[0m");
console.log(` RSS: ${health.memoryUsage.rss || "N/A"}`);
console.log(` Heap used: ${health.memoryUsage.heapUsed || "N/A"}`);
console.log(` RSS: ${health.memory.rss || "N/A"}`);
console.log(` Heap used: ${health.memory.heapUsed || "N/A"}`);
}
return 0;
@@ -97,17 +100,13 @@ export async function runHealthCommand(opts = {}) {
export async function runHealthComponentsCommand(opts = {}) {
try {
const res = await apiFetch("/api/monitoring/health", {
retry: false,
timeout: 5000,
acceptNotOk: true,
});
const res = await apiFetch("/api/health", { retry: false, timeout: 5000, acceptNotOk: true });
if (!res.ok) {
console.error(`HTTP ${res.status}`);
return 1;
}
const health = await res.json();
const components = health.components || health.circuitBreakers || {};
const components = health.components || health.breakers || {};
for (const [name, info] of Object.entries(components)) {
const status =
typeof info === "object" ? info.state || info.status || "unknown" : String(info);

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
@@ -20,33 +19,6 @@ const STRIPPED_CODEX_ENV_KEYS = [
/** Placeholder so codex's `env_key` is always satisfied when the backend is open. */
const NO_AUTH_SENTINEL = "omniroute-no-auth";
// On Windows the `codex` binary is an npm `.cmd` shim that `spawn` cannot resolve
// without a shell (bare "codex" → ENOENT). Mirror the qodercli Windows fix (#6263):
// spawn `codex.cmd` through a shell on win32, and the bare binary elsewhere.
export function resolveCodexSpawn(platform) {
if (platform === "win32") {
return { command: "codex.cmd", shell: true };
}
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;
@@ -154,10 +126,10 @@ export async function runLaunchCodexCommand(opts = {}, codexArgs = []) {
if (!(await healthCheck(baseUrl))) {
console.error(
(
t("launch.notRunning") ||
"OmniRoute is not reachable at {port}. Start it with 'omniroute serve'."
).replace("{port}", baseUrl)
(t("launch.notRunning") || "OmniRoute is not reachable at {port}. Start it with 'omniroute serve'.").replace(
"{port}",
baseUrl
)
);
return 1;
}
@@ -170,12 +142,7 @@ export async function runLaunchCodexCommand(opts = {}, codexArgs = []) {
const env = buildCodexEnv(process.env, authToken);
return await new Promise((resolve) => {
const { command: codexLaunch, shell: shellValue } = resolveCodexSpawn(process.platform);
const child = spawn(codexLaunch, quoteCodexArgs(extraArgs, process.platform), {
env,
stdio: "inherit",
shell: shellValue,
});
const child = spawn("codex", extraArgs, { env, stdio: "inherit" });
child.on("error", (err) => {
if (err?.code === "ENOENT") {
console.error(
@@ -198,25 +165,16 @@ export function registerLaunchCodex(program) {
t("launchCodex.description") || "Launch Codex CLI pointed at OmniRoute (local or remote VPS)"
)
.option("--port <port>", "Local OmniRoute port (ignored when --remote is set)", "20128")
.option(
"--remote <url>",
"Remote OmniRoute base URL, e.g. http://192.168.0.15:20128 (overrides --port + context)"
)
.option("--remote <url>", "Remote OmniRoute base URL, e.g. http://192.168.0.15:20128 (overrides --port + context)")
.option("--profile <name>", "Codex profile to activate (passed as --profile <name>)")
.option("-p, --p <name>", "Alias for --profile")
.option(
"--api-key <key>",
"OmniRoute API key (overrides OMNIROUTE_API_KEY env var for this invocation)"
)
.option("--api-key <key>", "OmniRoute API key (overrides OMNIROUTE_API_KEY env var for this invocation)")
.allowUnknownOption(true)
.allowExcessArguments(true)
.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
@@ -135,10 +106,10 @@ export async function runLaunchCommand(opts = {}, claudeArgs = []) {
if (!res.ok) throw new Error(`status ${res.status}`);
} catch {
console.error(
(
t("launch.notRunning") ||
"OmniRoute is not reachable at {port}. Start it with 'omniroute serve'."
).replace("{port}", baseUrl)
(t("launch.notRunning") || "OmniRoute is not reachable at {port}. Start it with 'omniroute serve'.").replace(
"{port}",
baseUrl
)
);
return 1;
}
@@ -149,13 +120,7 @@ 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), {
env,
stdio: "inherit",
shell,
...(process.platform === "win32" ? { windowsHide: true } : {}),
});
const child = spawn("claude", claudeArgs, { env, stdio: "inherit" });
child.on("error", (err) => {
if (err && err.code === "ENOENT") {
console.error(t("launch.notFound") || "The 'claude' CLI was not found in PATH.");
@@ -177,20 +142,14 @@ export function registerLaunch(program) {
)
.option("--port <port>", t("serve.port") || "Proxy port", "20128")
.option("--remote <url>", "Remote OmniRoute base URL (overrides --port and the active context)")
.option(
"--profile <name>",
"Claude Code profile to use (CLAUDE_CONFIG_DIR ~/.claude/profiles/<name>)"
)
.option("--profile <name>", "Claude Code profile to use (CLAUDE_CONFIG_DIR ~/.claude/profiles/<name>)")
.option("--token <token>", t("launch.token") || "Token Claude sends (ANTHROPIC_AUTH_TOKEN)")
.option("--api-key <key>", "Alias for --token (OmniRoute access token / API key)")
.allowUnknownOption(true)
.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

@@ -7,6 +7,7 @@ const PROVIDERS_WITH_OAUTH = [
{ id: "gemini", name: "Google Gemini", flow: "browser" },
{ id: "antigravity", name: "Antigravity", flow: "browser" },
{ id: "windsurf", name: "Windsurf", flow: "browser" },
{ id: "qwen", name: "Qwen Code", flow: "browser" },
{ id: "cursor", name: "Cursor", flow: "import" },
{ id: "zed", name: "Zed", flow: "import" },
{ id: "kiro", name: "Amazon Kiro", flow: "social" },

View File

@@ -37,7 +37,6 @@ import { registerProviders } from "./providers.mjs";
import { registerProvider } from "./provider-cmd.mjs";
import { registerConfig } from "./config.mjs";
import { registerKeys } from "./keys.mjs";
import { registerAuthExport } from "./auth-export.mjs";
import { registerModels } from "./models.mjs";
import { registerCombo } from "./combo.mjs";
import { registerStatus } from "./status.mjs";
@@ -70,8 +69,8 @@ import { registerSetupCursor } from "./setup-cursor.mjs";
import { registerSetupRoo } from "./setup-roo.mjs";
import { registerSetupCrush } from "./setup-crush.mjs";
import { registerSetupGoose } from "./setup-goose.mjs";
import { registerSetupAider } from "./setup-aider.mjs";
import { registerSetupQwen } from "./setup-qwen.mjs";
import { registerSetupAider } from "./setup-aider.mjs";
import { registerConnect } from "./connect.mjs";
import { registerContexts } from "./contexts.mjs";
import { registerTokens } from "./tokens.mjs";
@@ -119,7 +118,6 @@ export function registerCommands(program) {
registerProvider(program);
registerConfig(program);
registerKeys(program);
registerAuthExport(program);
registerModels(program);
registerCombo(program);
registerStatus(program);
@@ -153,8 +151,8 @@ export function registerCommands(program) {
registerSetupRoo(program);
registerSetupCrush(program);
registerSetupGoose(program);
registerSetupAider(program);
registerSetupQwen(program);
registerSetupAider(program);
registerConnect(program);
registerContexts(program);
registerTokens(program);

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 (existsSync(sqliteBinary) && !isNativeBinaryCompatible(sqliteBinary)) {
console.error(
"\x1b[31m✖ better-sqlite3 native module is incompatible with this platform.\x1b[0m"
);
@@ -267,16 +230,12 @@ 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("node", [...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 +246,11 @@ 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("node", [...buildNodeHeapArgs(process.env, memoryLimit), serverJs], {
cwd: APP_DIR,
env,
stdio: "pipe",
});
writePidFile("server", server.pid);
@@ -304,7 +259,6 @@ 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 +268,7 @@ 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);
@@ -401,38 +351,11 @@ async function runWithSupervisor(
if (up) {
if (useTray) await maybeStartTray(dashboardPort, apiPort, supervisor);
onReady(dashboardPort, apiPort, noOpen, startedAt);
} else {
reportReadinessTimeout(dashboardPort, supervisor);
}
});
}
}
// #6321: waitForServer resolving `false` used to fall through silently — the CLI
// printed the banner + "⏳ Starting server..." and then produced ZERO further
// output forever, even though the child process may well have crashed or be
// stuck (issue reports show the server sometimes actually comes up later, or is
// reachable directly while the CLI still looks hung). Surface a clear diagnostic
// plus whatever stdout/stderr the child buffered instead of going silent.
export function reportReadinessTimeout(dashboardPort, supervisor) {
console.error(
`\n\x1b[33m⚠ Server did not respond within 60s.\x1b[0m It may still be starting, or may` +
` have failed silently.`
);
console.error(` Try: curl -I http://localhost:${dashboardPort}/api/monitoring/health`);
console.error(` Or: rerun with \x1b[36m--log\x1b[0m to see live server output.\n`);
const recentLog = supervisor?.getRecentLog?.() ?? [];
if (recentLog.length) {
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"));
}
}
let _killTray = null;
function killTrayIfActive() {
if (_killTray) {

View File

@@ -218,29 +218,13 @@ function registerPluginInOpenCodeConfig({
* a clear "could not run opencode" message instead of a hard import
* failure.
*/
/**
* Pure resolver for the `opencode auth login` spawn descriptor. Extracted so the
* platform-branching logic is unit-testable without mocking child_process or
* mutating process.platform.
*
* On Windows the `opencode` binary is an npm `.cmd` shim that Node's hardened
* spawnSync (post CVE-2024-27980) refuses to run without a shell — spawning it
* with shell:false throws EINVAL (#7913). Mirror the same fix already applied to
* codex (resolveCodexSpawn in launch-codex.mjs, crediting #6263) and
* qodercli/Auggie (#6263/#6304): shell:true on win32, shell:false everywhere else.
*/
export function resolveOpenCodeAuthSpawn(providerId, platform = process.platform) {
const isWin = platform === "win32";
return {
command: isWin ? "opencode.cmd" : "opencode",
args: ["auth", "login", "--provider", providerId],
options: { stdio: "inherit", shell: isWin },
};
}
export function runOpenCodeAuth(providerId) {
const { command, args, options } = resolveOpenCodeAuthSpawn(providerId);
const res = spawnSync(command, args, options);
function runOpenCodeAuth(providerId) {
const isWin = process.platform === "win32";
const opencodeBin = isWin ? "opencode.cmd" : "opencode";
const res = spawnSync(opencodeBin, ["auth", "login", "--provider", providerId], {
stdio: "inherit",
shell: false,
});
if (res.error) {
// ENOENT = opencode is not on PATH
if (res.error.code === "ENOENT") {

View File

@@ -1,166 +1,156 @@
/** Configure Qwen Code's OpenAI-compatible provider for OmniRoute. */
/**
* omniroute setup-qwen — configure Qwen Code (QwenLM/qwen-code) for OmniRoute.
*
* Qwen Code is a terminal AI agent with a file-based config at
* ~/.qwen/settings.json. For a custom OpenAI-compatible endpoint it uses a
* `modelProviders` entry with authType "openai", baseUrl WITH /v1, and an
* `envKey` naming the env var holding the key (secret stays in the env, never the
* file). Remote-aware; headless test via `qwen -p "..."`.
*/
import {
chmodSync,
existsSync,
mkdirSync,
readFileSync,
renameSync,
unlinkSync,
writeFileSync,
} from "node:fs";
import { existsSync, mkdirSync, readFileSync, writeFileSync } from "node:fs";
import { join } from "node:path";
import os from "node:os";
import path from "node:path";
import {
mergeQwenCodeEnv,
mergeQwenCodeSettings,
normalizeQwenCodeBaseUrl,
} from "../../../src/shared/services/qwenCodeConfig.ts";
import { printHeading, printInfo, printSuccess, printError, createPrompt } from "../io.mjs";
import { resolveActiveContext } from "../contexts.mjs";
import { createPrompt, printError, printHeading, printInfo, printSuccess } from "../io.mjs";
/** Resolve base URL and key from flags, active context, then local defaults. */
export function resolveQwenTarget(opts = {}) {
let root = opts.remote ? String(opts.remote) : "";
let context;
if (!root || !(opts.apiKey ?? opts["api-key"])) {
try {
context = resolveActiveContext(opts.context ?? process.env.OMNIROUTE_CONTEXT);
} catch {
// An active context is optional for local setup.
}
}
if (!root) root = context?.baseUrl || "";
if (!root) {
const port = Number(opts.port ?? process.env.PORT ?? 20128) || 20128;
root = `http://localhost:${port}`;
}
const apiKey =
opts.apiKey ??
opts["api-key"] ??
context?.accessToken ??
context?.apiKey ??
process.env.OMNIROUTE_API_KEY ??
"sk_omniroute";
return { baseUrl: normalizeQwenCodeBaseUrl(root), apiKey };
function ensureV1(url) {
const s = String(url || "").replace(/\/+$/, "");
return s.endsWith("/v1") ? s : `${s}/v1`;
}
const readSettings = (filePath) => {
if (!existsSync(filePath)) return {};
const parsed = JSON.parse(readFileSync(filePath, "utf8"));
if (!parsed || typeof parsed !== "object" || Array.isArray(parsed)) {
throw new Error("Qwen Code settings.json must contain a JSON object");
}
return parsed;
};
const readText = (filePath) => (existsSync(filePath) ? readFileSync(filePath, "utf8") : "");
const writeAtomic = (filePath, content, mode) => {
const tempPath = `${filePath}.${process.pid}.${Date.now()}.tmp`;
try {
writeFileSync(tempPath, content, { encoding: "utf8", mode });
if (mode !== undefined) chmodSync(tempPath, mode);
renameSync(tempPath, filePath);
} catch (error) {
/** Resolve baseUrl (WITH /v1) + apiKey from flags → active context → localhost. */
export function resolveQwenTarget(opts = {}) {
let root;
if (opts.remote) root = String(opts.remote).replace(/\/+$/, "");
else {
try {
unlinkSync(tempPath);
root = resolveActiveContext(opts.context ?? process.env.OMNIROUTE_CONTEXT)?.baseUrl;
} catch {
// The temporary file may not have been created.
/* none */
}
throw error;
if (!root) root = `http://localhost:${Number(opts.port ?? process.env.PORT ?? 20128) || 20128}`;
}
};
let apiKey = opts.apiKey ?? opts["api-key"];
if (!apiKey) {
try {
const c = resolveActiveContext(opts.context ?? process.env.OMNIROUTE_CONTEXT);
apiKey = c?.accessToken || c?.apiKey;
} catch {
/* none */
}
}
if (!apiKey) apiKey = process.env.OMNIROUTE_API_KEY || "";
return { baseUrl: ensureV1(root), apiKey };
}
const fetchModelIds = async (baseUrl, apiKey) => {
/** Merge the OmniRoute modelProvider into Qwen's settings.json (preserve rest). */
export function buildQwenSettings(existing, { baseUrl, model }) {
const s = existing && typeof existing === "object" ? { ...existing } : {};
const providers = Array.isArray(s.modelProviders)
? s.modelProviders.filter((p) => p?.id !== "omniroute")
: [];
providers.push({
id: "omniroute",
name: "OmniRoute",
authType: "openai",
baseUrl,
envKey: "OMNIROUTE_API_KEY",
});
s.modelProviders = providers;
if (model) {
s.selectedProvider = "omniroute";
s.model = model;
}
return s;
}
function readJson(path) {
try {
const response = await fetch(`${baseUrl}/models`, {
headers: { Authorization: `Bearer ${apiKey}` },
if (existsSync(path)) return JSON.parse(readFileSync(path, "utf8"));
} catch {
/* corrupt/missing */
}
return {};
}
async function fetchModelIds(baseUrl, apiKey) {
try {
const headers = { "Content-Type": "application/json" };
if (apiKey) headers["Authorization"] = `Bearer ${apiKey}`;
const res = await fetch(`${baseUrl.replace(/\/v1$/, "")}/v1/models`, {
headers,
signal: AbortSignal.timeout(8000),
});
if (!response.ok) return [];
const body = await response.json();
const models = Array.isArray(body) ? body : (body.data ?? body.models ?? []);
return models.map((entry) => (typeof entry === "string" ? entry : entry?.id)).filter(Boolean);
if (!res.ok) return [];
const body = await res.json();
const list = Array.isArray(body) ? body : (body.data ?? body.models ?? []);
return list.map((m) => (typeof m === "string" ? m : m?.id)).filter(Boolean);
} catch {
return [];
}
};
}
export async function runSetupQwenCommand(opts = {}) {
const { baseUrl, apiKey } = resolveQwenTarget(opts);
const dryRun = Boolean(opts.dryRun ?? opts["dry-run"]);
const settingsPath =
opts.configPath ?? opts["config-path"] ?? path.join(os.homedir(), ".qwen", "settings.json");
const envPath = opts.envPath ?? opts["env-path"] ?? path.join(path.dirname(settingsPath), ".env");
const configPath =
opts.configPath ?? opts["config-path"] ?? join(os.homedir(), ".qwen", "settings.json");
printHeading("OmniRoute → Qwen Code (OpenAI-compatible)");
printHeading("OmniRoute → Qwen Code (openai-compatible)");
printInfo(`baseUrl: ${baseUrl}`);
let model = String(opts.model || "").trim();
if (!model && !opts.yes) {
const modelIds = await fetchModelIds(baseUrl, apiKey);
if (modelIds.length > 0) {
printInfo(`Examples: ${modelIds.slice(0, 20).join(", ")}${modelIds.length > 20 ? " …" : ""}`);
}
const prompt = createPrompt();
try {
model = String(await prompt.ask("Model id for Qwen Code")).trim();
} finally {
prompt.close();
let model = opts.model;
if (!model) {
const ids = await fetchModelIds(baseUrl, apiKey);
if (ids.length && !opts.yes) {
printInfo(`Examples: ${ids.slice(0, 20).join(", ")}${ids.length > 20 ? " …" : ""}`);
const prompt = createPrompt();
try {
model = await prompt.ask("Model id for Qwen");
} finally {
prompt.close();
}
}
}
if (!model) {
printError("A model is required. Pass --model <id>.");
return 2;
}
try {
const settings = mergeQwenCodeSettings(readSettings(settingsPath), { baseUrl, model });
const envText = mergeQwenCodeEnv(readText(envPath), apiKey);
const settingsText = `${JSON.stringify(settings, null, 2)}\n`;
const merged = buildQwenSettings(readJson(configPath), { baseUrl, model });
const out = JSON.stringify(merged, null, 2) + "\n";
if (dryRun) {
console.log(`\n${settingsText}`);
printInfo(`[dry-run] settings → ${settingsPath}`);
printInfo(`[dry-run] credential → ${envPath} (OMNIROUTE_API_KEY)`);
return 0;
}
mkdirSync(path.dirname(settingsPath), { recursive: true, mode: 0o700 });
mkdirSync(path.dirname(envPath), { recursive: true, mode: 0o700 });
writeAtomic(settingsPath, settingsText);
writeAtomic(envPath, envText, 0o600);
printSuccess(`Wrote ${settingsPath}`);
printSuccess(`Updated ${envPath} (OMNIROUTE_API_KEY only)`);
printInfo('Run: qwen (or headless: qwen -p "reply OK")');
return 0;
} catch (error) {
printError(`Failed to configure Qwen Code: ${error?.message || error}`);
return 1;
if (dryRun) {
console.log("\n" + out);
printInfo(`[dry-run] ${configPath}`);
} else {
mkdirSync(join(configPath, ".."), { recursive: true });
writeFileSync(configPath, out, "utf8");
printSuccess(`Wrote ${configPath}`);
}
printInfo(
"\nProvide the key (settings reference OMNIROUTE_API_KEY): export OMNIROUTE_API_KEY=..."
);
printInfo('Then run: qwen (or headless: qwen -p "reply OK")');
return 0;
}
export function registerSetupQwen(program) {
program
.command("setup-qwen")
.description("Configure Qwen Code's upstream V4 modelProviders format for OmniRoute")
.description(
"Configure Qwen Code for OmniRoute: write ~/.qwen/settings.json (openai modelProvider)"
)
.option("--port <port>", "Local OmniRoute port (ignored when --remote is set)", "20128")
.option("--remote <url>", "Remote OmniRoute URL")
.option("--api-key <key>", "OmniRoute API key")
.option("--model <id>", "Model id for Qwen Code")
.option("--config-path <path>", "Qwen Code settings.json path")
.option("--env-path <path>", "Qwen Code .env path")
.option("--yes", "Non-interactive; requires --model")
.option("--dry-run", "Print settings without writing files or secrets")
.option("--remote <url>", "Remote OmniRoute URL, e.g. http://192.168.0.15:20128")
.option("--api-key <key>", "OmniRoute API key (defaults to OMNIROUTE_API_KEY env var)")
.option("--model <id>", "Model id for Qwen (required unless picked interactively)")
.option("--config-path <path>", "settings.json path (default: ~/.qwen/settings.json)")
.option("--yes", "Non-interactive: do not prompt (requires --model)")
.option("--dry-run", "Print what would be written without touching the filesystem")
.action(async (opts) => {
const code = await runSetupQwenCommand(opts);
if (code !== 0) process.exitCode = code;
if (code !== 0) process.exit(code);
});
}

View File

@@ -26,7 +26,6 @@ function wantsProviderSetup(opts) {
async function resolvePassword(opts, prompt, nonInteractive) {
if (opts.password) return opts.password;
if (process.env.INITIAL_PASSWORD) return process.env.INITIAL_PASSWORD;
if (nonInteractive) return "";
const answer = await prompt.ask("Set an admin password now? [y/N]", "N");

View File

@@ -8,7 +8,6 @@ import {
sleep,
} from "../utils/pid.mjs";
import { t } from "../i18n.mjs";
import { stopProcessGracefully } from "../../../src/shared/platform/windowsProcess.ts";
const execFileAsync = promisify(execFile);
@@ -28,11 +27,18 @@ export async function runStopCommand(opts = {}) {
if (pid && isPidRunning(pid)) {
console.log(t("stop.stopping", { pid }));
try {
// #8045: on win32, process.kill(pid, "SIGTERM") unconditionally force-terminates
// the target instead of delivering an interceptable signal, racing (and beating)
// the server's own async graceful shutdown / WAL checkpoint. stopProcessGracefully
// skips the immediate SIGTERM on win32 and just polls before escalating to SIGKILL.
await stopProcessGracefully({ pid, timeoutMs: 5000, isPidRunning, sleep });
process.kill(pid, "SIGTERM");
let waited = 0;
while (waited < 5000 && isPidRunning(pid)) {
await sleep(100);
waited += 100;
}
if (isPidRunning(pid)) {
process.kill(pid, "SIGKILL");
await sleep(500);
}
killAllSubprocesses();
cleanupPidFile("server");

View File

@@ -133,20 +133,6 @@
"listTitle": "Keys expiring within {days} days:"
}
},
"authExport": {
"description": "Export DECRYPTED provider credentials (local-only, plaintext output)",
"idOpt": "Export only the connection matching this id/name/provider",
"formatOpt": "Output format: json or env",
"outOpt": "Write output to a file instead of stdout (written with 0600 permissions)",
"forceOpt": "Confirm you understand this prints/writes plaintext secrets",
"warning": "⚠ This prints/writes DECRYPTED plaintext API keys and OAuth tokens. Make sure your screen, shell history, and any output file stay private.",
"confirmHeading": "⚠ WARNING: this exports DECRYPTED provider credentials in plaintext",
"confirmBody": "This command decrypts and prints/writes apiKey, accessToken, refreshToken, and\nidToken for the selected connection(s). Treat the output as a secret.",
"confirmFooter": "To confirm, run:\n omniroute auth export --force",
"missingKey": "STORAGE_ENCRYPTION_KEY is required to export credentials.",
"notFound": "Connection not found: {id}",
"invalidFormat": "Invalid format: {format}. Use json or env."
},
"stream": {
"description": "Stream a chat response with SSE inspection modes",
"file": "Read prompt from file",

View File

@@ -132,20 +132,6 @@
"listTitle": "Chaves que expiram nos próximos {days} dias:"
}
},
"authExport": {
"description": "Exportar credenciais DESCRIPTOGRAFADAS de provedores (somente local, saída em texto puro)",
"idOpt": "Exportar apenas a conexão correspondente a este id/nome/provedor",
"formatOpt": "Formato de saída: json ou env",
"outOpt": "Gravar a saída em um arquivo em vez do stdout (gravado com permissão 0600)",
"forceOpt": "Confirma que você entende que isso imprime/grava segredos em texto puro",
"warning": "⚠ Isso imprime/grava chaves de API e tokens OAuth DESCRIPTOGRAFADOS em texto puro. Garanta que sua tela, o histórico do shell e qualquer arquivo de saída permaneçam privados.",
"confirmHeading": "⚠ AVISO: isso exporta credenciais de provedores DESCRIPTOGRAFADAS em texto puro",
"confirmBody": "Este comando descriptografa e imprime/grava apiKey, accessToken, refreshToken e\nidToken da(s) conexão(ões) selecionada(s). Trate a saída como um segredo.",
"confirmFooter": "Para confirmar, execute:\n omniroute auth export --force",
"missingKey": "STORAGE_ENCRYPTION_KEY é obrigatório para exportar credenciais.",
"notFound": "Conexão não encontrada: {id}",
"invalidFormat": "Formato inválido: {format}. Use json ou env."
},
"stream": {
"description": "Transmitir resposta de chat com modos de inspeção SSE",
"file": "Ler prompt de arquivo",

View File

@@ -29,16 +29,16 @@
"setup": {
"title": "OmniRoute 设置",
"passwordPrompt": "管理员密码",
"providerPrompt": "默认提供(留空跳过)",
"providerPrompt": "默认提供(留空跳过)",
"done": "设置完成",
"passwordSet": "管理员密码已配置",
"providerSet": "提供已配置:{name}",
"testingProvider": "正在测试提供连接:{name}",
"testPassed": "提供测试通过",
"testFailed": "提供测试失败:{error}",
"providerSet": "提供已配置:{name}",
"testingProvider": "正在测试提供连接:{name}",
"testPassed": "提供测试通过",
"testFailed": "提供测试失败:{error}",
"loginEnabled": "登录:已启用(密码已更新)",
"loginDisabled": "登录:已禁用",
"providerInfo": "提供{info}"
"providerInfo": "提供{info}"
},
"doctor": {
"title": "OmniRoute 诊断",
@@ -52,29 +52,29 @@
"warnings": "{count} 个警告 — 见上文。"
},
"providers": {
"title": "提供",
"noProviders": "未配置提供。运行omniroute setup",
"title": "提供",
"noProviders": "未配置提供。运行omniroute setup",
"testing": "正在测试 {name}...",
"available": "{count} 个提供可用",
"available": "{count} 个提供可用",
"connected": "已连接",
"disconnected": "未连接",
"validationFailed": "验证失败:{error}",
"metrics": {
"description": "显示提供性能指标(延迟、成功率、成本)",
"provider": "按提供 ID 筛选",
"description": "显示提供性能指标(延迟、成功率、成本)",
"provider": "按提供 ID 筛选",
"connection_id": "按连接 ID 筛选",
"period": "时间范围1h|6h|24h|7d|30d默认24h",
"metric": "关注特定指标字段",
"sort": "按字段排序(降序)",
"limit": "最大行数默认50",
"watch": "每 5 秒刷新(实时模式)",
"compare": "逗号分隔的提供 ID并排比较"
"compare": "逗号分隔的提供 ID并排比较"
},
"metric_single": {
"description": "获取特定连接的单个指标值"
},
"rotate": {
"description": "轮换提供连接的上游 API 密钥",
"description": "轮换提供连接的上游 API 密钥",
"newKeyOpt": "新 API 密钥值(避免使用:优先使用 --from-env",
"fromEnvOpt": "从环境变量 VAR 读取新密钥",
"oauthOpt": "改为触发 OAuth 重新认证流程",
@@ -89,18 +89,18 @@
"testFailed": "轮换后测试失败:{error}"
},
"status": {
"description": "显示所有提供连接的密钥健康状态(期限、过期、冷却)",
"providerOpt": "按提供名称筛选",
"header": "ID 提供 名称 过期状态 测试状态 冷却至",
"noData": "没有可用的提供连接数据。",
"description": "显示所有提供连接的密钥健康状态(期限、过期、冷却)",
"providerOpt": "按提供名称筛选",
"header": "ID 提供 名称 过期状态 测试状态 冷却至",
"noData": "没有可用的提供连接数据。",
"requiresServer": "providers status 需要 OmniRoute 服务器正在运行。"
}
},
"keys": {
"title": "API 密钥",
"addDescription": "为提供添加或更新 API 密钥",
"addDescription": "为提供添加或更新 API 密钥",
"listDescription": "列出所有已配置的 API 密钥",
"removeDescription": "移除提供的 API 密钥",
"removeDescription": "移除提供的 API 密钥",
"regenerateDescription": "重新生成 OmniRoute API 密钥",
"revokeDescription": "撤销 OmniRoute API 密钥",
"revealDescription": "显示未掩码的 API 密钥值",
@@ -122,10 +122,10 @@
"revoked": "密钥 {id} 已撤销。",
"rotated": "密钥 {id} 已轮换。新密钥 ID{newId}",
"revealWarning": "⚠ 这将显示完整的未掩码密钥。请确保您的屏幕不被人看到。",
"providerRequired": "需要提供。",
"providerRequired": "需要提供。",
"keyRequired": "需要 API 密钥。",
"stdinEmpty": "未通过标准输入提供 API 密钥。",
"unknownProvider": "未知提供{provider}",
"unknownProvider": "未知提供{provider}",
"policy": {
"title": "密钥策略",
"showDescription": "显示密钥的速率/成本策略",
@@ -165,7 +165,7 @@
"analytics": {
"description": "显示汇总使用分析",
"period": "时间范围1d|7d|30d|90d|ytd|all默认30d",
"provider": "按提供 ID 筛选"
"provider": "按提供 ID 筛选"
},
"budget": {
"description": "管理成本预算",
@@ -175,8 +175,8 @@
}
},
"quota": {
"description": "显示提供配额使用情况",
"provider": "按提供 ID 筛选",
"description": "显示提供配额使用情况",
"provider": "按提供 ID 筛选",
"check": "显示新请求是否有可用配额"
},
"logs": {
@@ -201,7 +201,7 @@
}
},
"cost": {
"description": "按提供、模型、组合或 API 密钥显示成本报告",
"description": "按提供、模型、组合或 API 密钥显示成本报告",
"period": "时间范围1d|7d|30d|90d|ytd|all默认30d",
"since": "开始日期ISO 格式,例如 2026-01-01— 覆盖 --period",
"until": "结束日期ISO 格式)",
@@ -210,7 +210,7 @@
"limit": "显示的最大行数默认100"
},
"simulate": {
"description": "模拟路由(空运行)— 显示将选择哪些提供而不调用上游",
"description": "模拟路由(空运行)— 显示将选择哪些提供而不调用上游",
"file": "从 JSON 文件加载完整请求体",
"model": "模型 ID默认auto",
"combo": "强制指定组合名称",
@@ -301,7 +301,7 @@
"cost": "成本24h"
},
"quota": {
"description": "显示提供配额使用情况",
"description": "显示提供配额使用情况",
"noServer": "服务器未运行。启动omniroute serve",
"noData": "没有可用的配额信息。"
},
@@ -315,12 +315,12 @@
"description": "一键启动本地 Redis 容器Podman 或 Docker用于 OmniRoute 缓存和配额跟踪"
},
"test": {
"description": "测试提供连接",
"description": "测试提供连接",
"noServer": "服务器未运行。启动omniroute serve",
"testing": "正在测试 {provider} / {model}...",
"passed": "连接成功!",
"failed": "连接失败:{error}",
"allProvidersOpt": "测试所有已配置的提供",
"allProvidersOpt": "测试所有已配置的提供",
"latencyOpt": "显示延迟测量值(平均/最小/最大 毫秒)",
"repeatOpt": "重复测试 N 次并汇总结果",
"compareOpt": "逗号分隔的要比较的模型(例如 gpt-4o,claude-3-5-sonnet",
@@ -328,7 +328,7 @@
"saved": "结果已保存至 {path}",
"compareTitle": "模型比较",
"compareMinTwo": "--compare 需要至少两个模型(逗号分隔)",
"noProviders": "未配置提供。添加omniroute keys add"
"noProviders": "未配置提供。添加omniroute keys add"
},
"update": {
"checking": "正在检查更新...",
@@ -509,7 +509,7 @@
},
"models": {
"description": "列出可用模型(需要服务器)",
"search": "按 ID、名称、提供或描述筛选模型",
"search": "按 ID、名称、提供或描述筛选模型",
"noServer": "服务器未运行。启动omniroute serve",
"noModels": "未找到模型。"
},
@@ -656,25 +656,25 @@
}
},
"oauth": {
"description": "管理 OAuth 提供连接",
"description": "管理 OAuth 提供连接",
"providers": {
"description": "列出支持 OAuth 的提供及其流程类型"
"description": "列出支持 OAuth 的提供及其流程类型"
},
"start": {
"description": "为提供启动 OAuth 授权流程",
"provider": "提供 IDgemini, copilot, cursor, ...",
"description": "为提供启动 OAuth 授权流程",
"provider": "提供 IDgemini, copilot, cursor, ...",
"no_browser": "仅打印 URL — 不打开浏览器",
"import_system": "从本地系统配置自动导入凭据",
"social": "社交登录提供google|github— kiro 需要",
"social": "社交登录提供google|github— kiro 需要",
"timeout": "等待授权超时时间毫秒默认300000"
},
"status": {
"description": "列出活动的 OAuth 连接",
"provider": "按提供 ID 筛选"
"provider": "按提供 ID 筛选"
},
"revoke": {
"description": "撤销 OAuth 连接",
"provider": "要撤销的提供 ID",
"provider": "要撤销的提供 ID",
"connection_id": "按 ID 撤销特定连接",
"yes": "跳过确认提示"
}
@@ -884,11 +884,11 @@
"description": "管理模型定价数据",
"sync": {
"description": "从上游同步价格",
"provider": "按提供筛选",
"provider": "按提供筛选",
"force": "强制重新同步"
},
"list": {
"provider": "按提供筛选",
"provider": "按提供筛选",
"model": "按模型筛选",
"limit": "最大结果数"
},
@@ -907,25 +907,25 @@
"resilience": {
"description": "检查和管理弹性机制",
"status": {
"provider": "按提供筛选"
"provider": "按提供筛选"
},
"breakers": {
"provider": "按提供筛选"
"provider": "按提供筛选"
},
"cooldowns": {
"provider": "按提供筛选",
"provider": "按提供筛选",
"connectionId": "按连接 ID 筛选"
},
"lockouts": {
"provider": "按提供筛选",
"provider": "按提供筛选",
"model": "按模型筛选"
},
"reset": {
"description": "重置断路器/冷却状态",
"provider": "要重置的提供",
"provider": "要重置的提供",
"connectionId": "要重置的连接 ID",
"model": "要重置锁定状态的模型",
"allCooldowns": "重置提供的所有冷却",
"allCooldowns": "重置提供的所有冷却",
"yes": "跳过确认"
},
"profile": {
@@ -940,13 +940,13 @@
}
},
"nodes": {
"description": "管理提供节点(端点)",
"description": "管理提供节点(端点)",
"list": {
"provider": "按提供筛选",
"provider": "按提供筛选",
"enabled": "仅显示已启用的节点"
},
"add": {
"provider": "提供名称",
"provider": "提供名称",
"baseUrl": "节点的基础 URL",
"name": "节点名称",
"weight": "负载均衡权重",
@@ -965,7 +965,7 @@
},
"validate": {
"baseUrl": "要验证的 URL",
"provider": "要验证的提供"
"provider": "要验证的提供"
},
"test": {
"description": "向节点发送测试请求"
@@ -1091,7 +1091,7 @@
"oneproxy": {
"description": "管理 OneProxy 上游代理池",
"stats": {
"provider": "按提供筛选",
"provider": "按提供筛选",
"period": "时间范围默认24h"
},
"fetch": {
@@ -1101,14 +1101,14 @@
},
"rotate": {
"description": "强制轮换代理",
"provider": "要轮换的提供",
"provider": "要轮换的提供",
"connectionId": "要轮换的特定连接 ID"
},
"config": {
"description": "显示或更新 OneProxy 配置",
"enabled": "启用代理池true|false",
"poolSize": "池大小",
"providerSource": "代理提供的 URL",
"providerSource": "代理提供的 URL",
"rotationPolicy": "轮换策略sticky|per-request|periodic"
},
"pool": {
@@ -1201,7 +1201,7 @@
"bash": "打印 bash 补全脚本",
"fish": "打印 fish 补全脚本",
"install": "为检测到的 Shell 全局安装补全脚本",
"refresh": "刷新组合/提供/模型缓存"
"refresh": "刷新组合/提供/模型缓存"
},
"logs": {
"description": "流式传输或导出请求日志",

File diff suppressed because it is too large Load Diff

View File

@@ -37,7 +37,6 @@ function inferSchema(sample) {
function formatCell(v, col) {
if (v == null) return "";
if (col.formatter) return col.formatter(v);
if (typeof v === "object") return JSON.stringify(v);
return String(v);
}

View File

@@ -52,31 +52,6 @@ export function hasModule(name) {
return existsSync(join(runtimeModules(), name, "package.json"));
}
/**
* Probe whether a native addon (.node) file can actually be dlopen'd by the Node runtime that
* is going to load it. Runs in a throwaway subprocess so a real ABI mismatch (which can segfault
* the process instead of throwing) never takes down the caller — only the probe subprocess.
*/
function probeNativeBinaryLoadable(binary) {
try {
const res = spawnSync(
process.execPath,
[
"-e",
"try { require(process.argv[1]); process.exit(0); } catch (e) { process.exit(1); }",
binary,
],
{ timeout: 10_000, stdio: "ignore" }
);
// status === 0 means require() (and therefore dlopen) succeeded. Anything else — a thrown
// ERR_DLOPEN_FAILED/NODE_MODULE_VERSION mismatch (status 1) or a crash (status null with a
// signal, e.g. SIGSEGV) — means the binary is not safe to load.
return res.status === 0;
} catch {
return false;
}
}
export function isBetterSqliteBinaryValid() {
const binary = join(
runtimeModules(),
@@ -93,18 +68,10 @@ export function isBetterSqliteBinaryValid() {
closeSync(fd);
const magic = buf.toString("hex");
const os = platform();
let formatOk;
if (os === "linux") formatOk = magic.startsWith("7f454c46"); // ELF
else if (os === "darwin")
formatOk = magic.startsWith("cffaedfe") || magic.startsWith("cefaedfe"); // Mach-O
else if (os === "win32") formatOk = magic.startsWith("4d5a"); // PE/MZ
else formatOk = true;
if (!formatOk) return false;
// File-format magic bytes alone do not guarantee the binary was built for the Node ABI
// (NODE_MODULE_VERSION) that will load it — a stale/foreign-ABI binary passes the header
// check and then crashes (segfault) on load instead of triggering a rebuild. Actually
// attempt to load it, isolated in a subprocess.
return probeNativeBinaryLoadable(binary);
if (os === "linux") return magic.startsWith("7f454c46"); // ELF
if (os === "darwin") return magic.startsWith("cffaedfe") || magic.startsWith("cefaedfe"); // Mach-O
if (os === "win32") return magic.startsWith("4d5a"); // PE/MZ
return true;
} catch {
return false;
}

View File

@@ -1,6 +1,6 @@
import { spawn } from "node:child_process";
import { dirname } from "node:path";
import { writePidFile, cleanupPidFile, killAllSubprocesses, isPidRunning } from "../utils/pid.mjs";
import { writePidFile, cleanupPidFile, killAllSubprocesses } from "../utils/pid.mjs";
import {
RESTART_RESET_MS,
DEFAULT_MAX_RESTARTS,
@@ -9,22 +9,11 @@ import {
waitUntilPortFree,
} 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;
@@ -35,60 +24,33 @@ 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
// heap via NODE_OPTIONS (a CLI arg would shadow/override their value). The
// calibrated heap is already carried by env.NODE_OPTIONS either way.
const heapArgs = buildNodeHeapArgs(process.env, this.memoryLimit);
// #6321: stdout used to be discarded (`"ignore"`) whenever `--log`/OMNIROUTE_SHOW_LOG
// wasn't set (the default) — any debug/pino output written to stdout vanished
// 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("node", [...heapArgs, this.serverPath], {
cwd: dirname(this.serverPath),
env: this.env,
stdio: showLog ? "inherit" : ["ignore", "ignore", "pipe"],
});
writePidFile("server", this.child.pid);
const bufferOutput = (data) => {
const text = data.toString();
const lines = text.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) {
this.child.stdout.on("data", bufferOutput);
}
if (this.child.stderr) {
this.child.stderr.on("data", bufferOutput);
this.child.stderr.on("data", (data) => {
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);
}
});
}
this.child.on("error", (err) => this.handleExit(-1, err));
@@ -97,32 +59,12 @@ export class ServerSupervisor {
return this.child;
}
handleExit(code, err) {
handleExit(code) {
// Node.js v24+ requires process.exit() to receive a number. Spawn-error events
// deliver err.code (a string like 'ENOENT') via the 'error' listener; normalise here.
const exitCode = typeof code === "number" ? code : null;
cleanupPidFile("server");
// #8091: the child's spawn 'error' listener passes `err` through as a second
// argument, but it used to be silently dropped — the user only ever saw the
// hardcoded "code=-1" with a permanently empty crash log, with no way to
// diagnose why the child never started (ENOENT/EACCES/bad path/etc.). Surface
// the real reason immediately, both on the console and in the crash-log buffer
// so `dumpCrashLog()` shows it too.
if (err) {
const detail = [
err.code && `code=${err.code}`,
err.syscall && `syscall=${err.syscall}`,
err.path && `path=${err.path}`,
err.message,
]
.filter(Boolean)
.join(" ");
const line = `⚠ Spawn error: ${detail || String(err)}`;
console.error(line);
this.crashLog.push(line);
}
// #4425: only exit on an intentional shutdown. A spontaneous code-0 exit (e.g. a
// systemd MemoryMax cgroup kill, which reports the process exited cleanly) is anomalous
// and must be restarted, not treated as a graceful stop that leaves the gateway dead.
@@ -165,12 +107,6 @@ export class ServerSupervisor {
}, delay);
}
// #6321: exposes the buffered stdout+stderr lines so a caller (e.g. a readiness
// timeout) can print what the child actually said instead of silence.
getRecentLog() {
return [...this.crashLog];
}
dumpCrashLog() {
console.error("\n--- Server crash log ---");
this.crashLog.forEach((l) => console.error(l));
@@ -180,13 +116,14 @@ export class ServerSupervisor {
stop() {
this.isShuttingDown = true;
if (this.child?.pid) {
// #8045: on win32, process.kill(pid, "SIGTERM") unconditionally force-terminates
// the target — it is never a real, interceptable signal there. The child already
// receives the real CTRL_C_EVENT/CTRL_CLOSE_EVENT independently (it shares the
// console) and runs its own async graceful shutdown (WAL checkpoint). Sending
// SIGTERM immediately on win32 races and beats that cleanup. Fire-and-forget:
// stop() itself stays sync so callers keep their existing control flow.
void stopProcessGracefully({ pid: this.child.pid, timeoutMs: 5000, isPidRunning });
try {
process.kill(this.child.pid, "SIGTERM");
} catch {}
setTimeout(() => {
try {
process.kill(this.child.pid, "SIGKILL");
} catch {}
}, 5000);
}
killAllSubprocesses();
}

View File

@@ -3,85 +3,12 @@ import { resolveDataDir, resolveStoragePath } from "./data-dir.mjs";
import { ensureProviderSchema } from "./provider-store.mjs";
import { ensureSettingsSchema, hashManagementPassword, updateSettings } from "./settings-store.mjs";
async function loadSqlite() {
if (process.versions.bun) {
return { Database: (await import("bun:sqlite")).Database };
}
async function loadBetterSqlite() {
try {
return { Database: (await import("better-sqlite3")).default };
} catch (error) {
return { error };
}
}
// #7586: unlike the real server (src/lib/db/adapters/driverFactory.ts::tryOpenSync),
// this CLI helper historically had NO fallback beyond better-sqlite3 — so on any
// machine where better-sqlite3's native binary is unavailable (Windows without a
// prebuilt addon, etc.), every `omniroute doctor` DB check reported a false FAIL
// even when the actual server was healthy via its own (correct) driver cascade.
// Reuse that same cascade here instead of re-deriving it.
async function openWithSyncDriverFallback(dbPath, options, importError) {
try {
const { tryOpenSync } = await import("../../src/lib/db/adapters/driverFactory.ts");
const adapter = tryOpenSync(dbPath, options);
if (adapter) {
return adapter;
}
return (await import("better-sqlite3")).default;
} catch {
// fall through to the original better-sqlite3 error below
throw new Error("better-sqlite3 is not installed. Run npm install before using setup.");
}
throw createSqliteNativeError(importError);
}
function openBunSqlite(Database, dbPath, options) {
const raw = new Database(dbPath, options);
const prepare = (sql) => {
const statement = raw.query(sql);
return {
run: (...params) => statement.run(...normalizeBunSqliteParams(params)),
get: (...params) => statement.get(...normalizeBunSqliteParams(params)),
all: (...params) => statement.all(...normalizeBunSqliteParams(params)),
};
};
return {
prepare,
query: (sql) => raw.query(sql),
exec: (sql) => raw.exec(sql),
transaction: (fn) => raw.transaction(fn),
close: () => raw.close(),
serialize: () => raw.serialize(),
pragma: (pragmaStr, pragmaOptions) => {
const statement = raw.query(`PRAGMA ${pragmaStr}`);
if (pragmaOptions?.simple) {
const row = statement.get();
return row ? (Object.values(row)[0] ?? null) : null;
}
return statement.all();
},
};
}
export function normalizeBunSqliteParams(params) {
if (
params.length !== 1 ||
params[0] === null ||
typeof params[0] !== "object" ||
Array.isArray(params[0]) ||
params[0] instanceof Uint8Array ||
(typeof Buffer !== "undefined" && Buffer.isBuffer(params[0]))
) {
return params;
}
const expanded = {};
for (const [key, value] of Object.entries(params[0])) {
if (/^[:@$]/.test(key)) expanded[key] = value;
else {
expanded[`@${key}`] = value;
expanded[`:${key}`] = value;
expanded[`$${key}`] = value;
}
}
return [expanded];
}
export function createSqliteNativeError(error) {
@@ -94,41 +21,13 @@ export function createSqliteNativeError(error) {
"(rebuilds into a user-writable runtime; works without a C++ toolchain)."
);
}
if (
message.includes("Could not locate the bindings file") ||
message.includes("MODULE_NOT_FOUND") ||
message.includes("Cannot find module 'better-sqlite3'")
) {
return new Error(
"better-sqlite3 native binding could not be found (no prebuilt addon for this platform). " +
"This is common under `npx`, which runs a fresh, ephemeral install that never built the addon. " +
"Run: omniroute runtime repair " +
"(rebuilds into a user-writable runtime; works without a C++ toolchain)."
);
}
return error;
}
async function openSqliteDatabase(dbPath, options = {}) {
const loaded = await loadSqlite();
if (process.versions.bun) {
if (options.fileMustExist && !fs.existsSync(dbPath)) {
throw new Error(`SQLite file does not exist: ${dbPath}`);
}
const bunOptions = options.readonly
? { readonly: true }
: { readwrite: true, create: options.fileMustExist !== true };
try {
return openBunSqlite(loaded.Database, dbPath, bunOptions);
} catch (error) {
throw createSqliteNativeError(error);
}
}
if (loaded.error) {
return openWithSyncDriverFallback(dbPath, options, loaded.error);
}
const Database = await loadBetterSqlite();
try {
return new loaded.Database(dbPath, options);
return new Database(dbPath, options);
} catch (error) {
throw createSqliteNativeError(error);
}
@@ -160,16 +59,7 @@ export async function withReadonlySqlite(dbPath, callback) {
export async function backupSqliteFile(sourcePath, destPath) {
const db = await openSqliteDatabase(sourcePath, { readonly: true });
try {
if (typeof db.backup === "function") {
await db.backup(destPath);
} else if (sourcePath === ":memory:" && typeof db.serialize === "function") {
fs.writeFileSync(destPath, Buffer.from(db.serialize()));
} else {
try {
db.exec("PRAGMA wal_checkpoint(TRUNCATE)");
} catch {}
fs.copyFileSync(sourcePath, destPath);
}
await db.backup(destPath);
} finally {
db.close();
}

View File

@@ -6,7 +6,6 @@ import { fileURLToPath } from "node:url";
const APP_LABEL = "com.omniroute.autostart";
const WIN_REG_VALUE = "OmniRoute";
const WIN_STARTUP_FILE = "OmniRoute.vbs";
const LINUX_SERVICE_NAME = "omniroute.service";
const LINUX_DESKTOP_NAME = "omniroute.desktop";
@@ -324,101 +323,38 @@ function isEnabledMac() {
);
}
/**
* Returns the absolute path to the Windows Startup folder
* (%APPDATA%\Microsoft\Windows\Start Menu\Programs\Startup\),
* or null when APPDATA is not set.
*/
function winStartupDir() {
if (!process.env.APPDATA) return null;
return join(process.env.APPDATA, "Microsoft", "Windows", "Start Menu", "Programs", "Startup");
}
/**
* Returns the full path to the VBS autostart script in the Startup folder,
* or null when the Startup folder cannot be resolved.
*/
function winStartupPath() {
const dir = winStartupDir();
return dir ? join(dir, WIN_STARTUP_FILE) : null;
}
/**
* Builds the VBScript source that launches OmniRoute with WSH's Run method
* using SW_HIDE (0) so no console window appears.
*
* 9Router uses the same pattern: a .vbs file in the Startup folder that calls
* WScript.Shell.Run with window style 0 (hidden). This avoids the console
* window flash that HKCU\Run causes for console-mode node.exe.
*/
function buildWinVbsContent(cliPath) {
const execLine = buildServeExecLine(cliPath, { tray: true });
// VBScript doubles `"` inside a string to escape them. The execLine already
// contains quoted paths; escape each `"` to `""` so the VBS parser reads
// them as literal quote characters in the command string passed to Run().
const vbsSafe = execLine.replace(/"/g, '""');
return [
'Set WshShell = CreateObject("WScript.Shell")',
`WshShell.Run "${vbsSafe}", 0, False`,
"",
].join("\n");
}
/**
* Removes the legacy HKCU\Run registry value if present. Callers use this
* during migration so stale Run entries don't linger after switching to the
* VBS-based autostart.
*/
function cleanLegacyWinReg() {
try {
execSync(
`reg delete HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Run /v ${WIN_REG_VALUE} /f 2>nul`,
{ stdio: "ignore", windowsHide: true }
);
} catch {
// entry did not exist or already removed — noop
}
}
function enableWin() {
const cliPath = resolveCliPath();
if (!cliPath) return false;
const vbsPath = winStartupPath();
if (!vbsPath) return false;
const dir = dirname(vbsPath);
mkdirSync(dir, { recursive: true });
writeFileSync(vbsPath, buildWinVbsContent(cliPath), { mode: 0o644 });
// Migrate away from the legacy HKCU\Run entry — it launches node.exe with
// a visible console window. The VBS approach is the replacement.
cleanLegacyWinReg();
return existsSync(vbsPath);
const value = `"${process.execPath}" "${cliPath}" serve --tray --no-open`;
try {
execSync(
`reg add HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Run /v ${WIN_REG_VALUE} /t REG_SZ /d "${value}" /f`,
{ stdio: "ignore", windowsHide: true }
);
return true;
} catch {
return false;
}
}
function disableWin() {
const vbsPath = winStartupPath();
if (!vbsPath) return false;
try {
unlinkSync(vbsPath);
execSync(
`reg delete HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Run /v ${WIN_REG_VALUE} /f`,
{ stdio: "ignore", windowsHide: true }
);
return true;
} catch {
// already removed
return false;
}
// Also clean up any lingering legacy registry entry as a safety net.
cleanLegacyWinReg();
return !existsSync(vbsPath);
}
function isEnabledWin() {
const vbsPath = winStartupPath();
if (!vbsPath) return false;
// Primary check: VBS file exists in the Startup folder.
if (existsSync(vbsPath)) return true;
// Fallback check: legacy HKCU\Run entry (for users who enabled autostart
// before the VBS migration). Treat it as enabled so the tray menu shows
// the correct toggle state, and calling disable() will clean it up.
try {
const out = execSync(
`reg query HKCU\\Software\\Microsoft\\Windows\\CurrentVersion\\Run /v ${WIN_REG_VALUE}`,
{ stdio: "pipe", windowsHide: true, encoding: "utf8", timeout: 3000 }
{ stdio: "pipe", windowsHide: true, encoding: "utf8" }
);
return out.includes(WIN_REG_VALUE);
} catch {

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

@@ -65,52 +65,34 @@ export function sleep(ms) {
// cold start due to filesystem watchers, antivirus, etc.) get a working
// "server ready" signal instead of a phantom timeout while the server is
// still booting. TCP fallback marks the server as ready when the port
// has been listening for >= 3s consecutively AND the health route is
// actively rejecting/resetting connections fast (route not mounted yet,
// but the HTTP server is clearly alive and responsive) — never for a
// socket that merely accepts TCP and then hangs without ever completing
// a single request (#6800: that's a still-booting/CPU-bound process, not
// a "route not mounted" gap, and must NOT be reported as ready).
// has been listening for >= 3s consecutively but /api/monitoring/health
// has not yet been mounted — common during dev cold start.
export async function waitForServer(port, timeout = 60000) {
const start = Date.now();
let tcpListeningSince = null;
while (Date.now() - start < timeout) {
const outcome = await pollHealthOnce(port);
if (outcome === "ready") return true;
if (outcome === "fast-reject") {
try {
const res = await fetch(`http://localhost:${port}/api/monitoring/health`, {
signal: AbortSignal.timeout(2000),
});
if (res.ok) return true;
// Server responded but health endpoint is not ready yet — keep
// polling, but the fact that we got a response means TCP is open.
if (tcpListeningSince === null) tcpListeningSince = Date.now();
if (Date.now() - tcpListeningSince >= 3000) return true;
} else {
// "hanging" (request timed out with no response at all) or
// "not-listening" — neither counts toward the grace window.
tcpListeningSince = null;
} catch {
const listening = await isPortListening(port).catch(() => false);
if (listening) {
if (tcpListeningSince === null) tcpListeningSince = Date.now();
if (Date.now() - tcpListeningSince >= 3000) return true;
} else {
tcpListeningSince = null;
}
}
await sleep(500);
}
return false;
}
// Polls /api/monitoring/health once and classifies the outcome:
// - "ready": got a 2xx HTTP response.
// - "fast-reject": got a non-2xx HTTP response, or the connection was
// actively refused/reset (not a timeout) — the HTTP server is alive and
// answering quickly, just not routing this endpoint yet (#2460).
// - "hanging": the request timed out waiting for any response — the
// process accepted the TCP connection but never answered (#6800).
// - "not-listening": nothing is accepting connections on the port at all.
async function pollHealthOnce(port) {
try {
const res = await fetch(`http://localhost:${port}/api/monitoring/health`, {
signal: AbortSignal.timeout(2000),
});
return res.ok ? "ready" : "fast-reject";
} catch (err) {
if (err?.name === "TimeoutError") return "hanging";
const listening = await isPortListening(port).catch(() => false);
return listening ? "fast-reject" : "not-listening";
}
}
async function isPortListening(port) {
const net = await import("node:net");
return new Promise((resolve) => {

View File

@@ -1,25 +0,0 @@
/**
* Decide whether a CLI invocation is a bare `--version`/`-V` query that should
* short-circuit BEFORE the runtime polyfill import, env-file loading, and
* Commander's command registration (~70 command modules) are loaded.
*
* Scope is intentionally narrow — only a single, unambiguous `--version`/`-V`
* argument fast-paths. Anything else (extra args, a subcommand, `--help`,
* global options like `--lang`/`--output` alongside it) falls through to the
* normal Commander flow. Unlike `--version`, OmniRoute's `--help` output is
* generated dynamically from every registered subcommand, so skipping
* registration would change (truncate) the help text — that flag is
* deliberately NOT fast-pathed here.
*
* Mirrors the intent of upstream 9router PR #2414 (fast-path help/version
* before expensive self-heal hooks), adapted to OmniRoute's Commander-based
* CLI where the equivalent expensive work is eager command registration
* rather than npm-install-based runtime self-healing.
*
* @param {string[]} argv - process.argv (node + script + args).
* @returns {boolean}
*/
export function isVersionFastPath(argv) {
const args = Array.isArray(argv) ? argv.slice(2) : [];
return args.length === 1 && (args[0] === "--version" || args[0] === "-V");
}

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

@@ -4,17 +4,13 @@
* OmniRoute CLI entry point.
*
* Special bypasses (handled before Commander):
* --version / -V (alone) Fast-path: print the version and exit, skipping the
* tsx/esm + polyfill imports, env-file loading, and
* Commander's ~70-command registration entirely.
* --mcp Start MCP server over stdio
* reset-encrypted-columns Recovery tool for broken encrypted credentials
* reset-password Reset the admin/management password
*
* All other commands are routed through Commander (bin/cli/program.mjs).
*/
import { existsSync, readFileSync, writeFileSync } from "node:fs";
import { existsSync, readFileSync } from "node:fs";
import { join, dirname } from "node:path";
import { fileURLToPath, pathToFileURL } from "node:url";
import updateNotifier from "update-notifier";
@@ -22,26 +18,6 @@ import { isNativeBinaryCompatible } from "../scripts/build/native-binary-compat.
import { getNodeRuntimeSupport, getNodeRuntimeWarning } from "./nodeRuntimeSupport.mjs";
import { getDefaultDataDir } from "./cli/data-dir.mjs";
import { shouldProvisionStorageKey } from "./cli/utils/storageKeyProvision.mjs";
import { isVersionFastPath } from "./cli/utils/versionFastPath.mjs";
const __filename = fileURLToPath(import.meta.url);
const __dirname = dirname(__filename);
const ROOT = join(__dirname, "..");
// Fast-path a bare `--version`/`-V` query BEFORE the tsx/esm registration, the
// polyfill import, env-file loading, or Commander's command registration (~70
// modules — DB, providers, OAuth, etc.) run. None of that work is needed to answer
// "what version is this" — mirrors upstream 9router PR #2414 (fast-path help/version
// ahead of expensive self-heal hooks), adapted to OmniRoute's Commander CLI where the
// equivalent expensive work is eager command registration rather than npm-install-based
// runtime self-healing. `--help` is intentionally NOT fast-pathed here: its output is
// generated dynamically from every registered subcommand, so skipping registration
// would truncate the help text instead of just speeding it up.
if (isVersionFastPath(process.argv)) {
const pkg = JSON.parse(readFileSync(join(ROOT, "package.json"), "utf8"));
console.log(pkg.version);
process.exit(0);
}
// Register tsx so dynamic imports of .ts source files (referenced as .js per
// TypeScript conventions) resolve correctly. The build never emits .js for
@@ -49,14 +25,9 @@ if (isVersionFastPath(process.argv)) {
await import("tsx/esm");
await import("../open-sse/utils/setupPolyfill.ts");
// #7791: tsx's tsconfig-path resolution does not apply when OmniRoute is
// installed globally (files live under node_modules/omniroute/), so bare
// `@/...` specifiers (declared in tsconfig.json paths as `@/* → ./src/*`)
// fail with ERR_MODULE_NOT_FOUND. Register an ESM resolve hook that maps
// `@/...` to absolute file URLs under <ROOT>/src/. Safe no-op in dev checkout
// (paths already resolve via tsconfig) and when ROOT has no `src/` dir.
const { registerAliasResolver } = await import("./aliasResolver.mjs");
await registerAliasResolver(ROOT);
const __filename = fileURLToPath(import.meta.url);
const __dirname = dirname(__filename);
const ROOT = join(__dirname, "..");
// MCP stdio transport uses stdout exclusively for JSON-RPC messages.
// Redirect console.log/warn to stderr early (before loadEnvFile and DB init)
@@ -68,28 +39,6 @@ if (process.argv.includes("--mcp")) {
console.warn = stderrConsole.warn.bind(stderrConsole);
}
// Electron persists secrets (JWT_SECRET, API_KEY_SECRET, STORAGE_ENCRYPTION_KEY) to
// `<DATA_DIR>/server.env` (electron/main.js), never `.env`. Migrating an existing
// install (storage.sqlite + server.env) to the CLI left those secrets undiscoverable —
// the CLI only ever looked for `.env`, so the STORAGE_ENCRYPTION_KEY needed to decrypt
// the migrated database was silently dropped (#7302). One-time, one-directory migration:
// if `<dataDir>/.env` is absent but `<dataDir>/server.env` is present, copy it to `.env`
// so it flows through the normal env-loading path below. Never overwrites an existing
// `.env` — an explicit `.env` always wins over a legacy `server.env`.
function migrateElectronServerEnv(dataDir) {
try {
const envPath = join(dataDir, ".env");
const serverEnvPath = join(dataDir, "server.env");
if (existsSync(envPath) || !existsSync(serverEnvPath)) return;
writeFileSync(envPath, readFileSync(serverEnvPath, "utf-8"), "utf-8");
console.log(
` \x1b[2m♻ Migrated Electron secrets from ${serverEnvPath} to ${envPath}\x1b[0m`
);
} catch {
// Ignore errors migrating server.env — fall back to normal env loading below.
}
}
function loadEnvFile() {
const envPaths = [];
const loadedEnvPaths = [];
@@ -100,8 +49,6 @@ function loadEnvFile() {
envPaths.push(envPath);
};
migrateElectronServerEnv(process.env.DATA_DIR || getDefaultDataDir());
if (process.env.DATA_DIR) {
addEnvPath(join(process.env.DATA_DIR, ".env"));
}
@@ -145,15 +92,6 @@ 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
@@ -272,15 +210,6 @@ if (process.argv.includes("reset-encrypted-columns")) {
process.exit(exitCode ?? 0);
}
if (process.argv.includes("reset-password")) {
// bin/reset-password.mjs self-executes its `main()` on import and calls
// process.exit() on completion/error. Await a never-resolving promise so
// control never falls through to Commander (which would then reject
// `reset-password` as an unknown command). See #6261.
await import(pathToFileURL(join(ROOT, "bin", "reset-password.mjs")).href);
await new Promise(() => {});
}
try {
const { createProgram } = await import(
pathToFileURL(join(ROOT, "bin", "cli", "program.mjs")).href

View File

@@ -5,15 +5,10 @@
*
* Usage:
* node bin/reset-password.mjs
* omniroute reset-password
*
* Non-interactive / scripted usage (piped stdin, e.g. CI or Docker):
* printf 'NewPass123\nNewPass123\n' | omniroute reset-password
* printf 'NewPass123' | omniroute reset-password --password-stdin
* npx omniroute reset-password
*
* Resets the admin password for OmniRoute.
* Prompts for a new password (interactive TTY) or reads it from stdin
* (non-TTY) and updates the database directly.
* Prompts for a new password and updates the database directly.
*
* @module bin/reset-password
*/
@@ -26,61 +21,19 @@ import { readManagementPasswordState, resetManagementPassword } from "./cli/sqli
const DATA_DIR = resolveDataDir();
const DB_PATH = resolveStoragePath(DATA_DIR);
const MIN_PASSWORD_LENGTH = 8;
const rl = createInterface({
input: process.stdin,
output: process.stdout,
});
/** Read the entire stdin stream as a UTF-8 string (used for non-TTY input). */
function readAllStdin() {
return new Promise((resolve) => {
let data = "";
process.stdin.setEncoding("utf8");
process.stdin.on("data", (chunk) => {
data += chunk;
});
process.stdin.on("end", () => resolve(data));
process.stdin.on("error", () => resolve(data));
// Resuming is implied by attaching a 'data' listener, but be explicit so a
// paused stream (some spawn setups) still flows to EOF.
process.stdin.resume();
});
function ask(question) {
return new Promise((resolve) => rl.question(question, resolve));
}
/**
* Obtain the new password (and its confirmation).
*
* - `--password-stdin`: the ENTIRE stdin is the password, no confirmation.
* - non-TTY stdin (piped): read all of stdin once; first line is the password,
* second line — when present — is the confirmation, else the first line is
* reused (a single-line pipe means "no separate confirmation").
* - interactive TTY: two sequential prompts (unchanged behavior).
*
* The non-TTY path exists because two sequential `rl.question` promises never
* settle under a piped EOF — the second read blocks forever, so the reset was
* silently never applied (#6258).
*/
async function collectPassword() {
if (process.argv.includes("--password-stdin")) {
const raw = await readAllStdin();
const password = raw.replace(/[\r\n]+$/, "");
return { password, confirm: password };
}
if (!process.stdin.isTTY) {
const raw = await readAllStdin();
const lines = raw.split(/\r?\n/);
const password = lines[0] ?? "";
const confirm = lines[1] ? lines[1] : password;
return { password, confirm };
}
const rl = createInterface({ input: process.stdin, output: process.stdout });
try {
const ask = (question) => new Promise((resolve) => rl.question(question, resolve));
const password = await ask("Enter new password (min 8 chars): ");
const confirm = await ask("Confirm new password: ");
return { password, confirm };
} finally {
rl.close();
}
function exitWithError(message) {
console.error(message);
rl.close();
process.exit(1);
}
console.log("\n🔑 OmniRoute — Password Reset\n");
@@ -101,34 +54,27 @@ async function main() {
console.log(" No password is currently set.");
}
const { password, confirm } = await collectPassword();
const password = await ask("Enter new password (min 8 chars): ");
if (!password || password.length < MIN_PASSWORD_LENGTH) {
console.error(`\n❌ Password must be at least ${MIN_PASSWORD_LENGTH} characters.\n`);
process.exit(1);
if (!password || password.length < 8) {
exitWithError("\n❌ Password must be at least 8 characters.\n");
}
const confirm = await ask("Confirm new password: ");
if (password !== confirm) {
console.error("\n❌ Passwords do not match.\n");
process.exit(1);
exitWithError("\n❌ Passwords do not match.\n");
}
await resetManagementPassword(password, DB_PATH);
rl.close();
console.log("\n✅ Password reset successfully!");
console.log(" Restart OmniRoute for changes to take effect.\n");
}
main()
.then(() => {
// Explicit exit(0) so a caller that imports this module (bin/omniroute.mjs
// routes `omniroute reset-password` here) terminates cleanly instead of
// hanging / exiting with code 13 on an unsettled wrapper await. On POSIX,
// console.log to a pipe is synchronous, so the success line is already
// flushed by the time we exit.
process.exit(0);
})
.catch((err) => {
console.error(`\n❌ Error: ${err.message}\n`);
process.exit(1);
});
main().catch((err) => {
console.error(`\n❌ Error: ${err.message}\n`);
rl.close();
process.exit(1);
});

View File

@@ -1,42 +0,0 @@
# changelog.d/ — changelog fragments
**A PR never edits `CHANGELOG.md` directly during the cycle.** Instead it adds ONE new
file here — its changelog entry as a *fragment*. Two PRs never touch the same file, so
changelog merge conflicts (the "CHANGELOG-eat" cascade that forced a re-sync push + full
CI re-run after every sibling merge) are structurally impossible.
## Convention
| Directory | Aggregates under |
| -------------- | ----------------------- |
| `features/` | `### ✨ New Features` |
| `fixes/` | `### 🐛 Bug Fixes` |
| `maintenance/` | `### 📝 Maintenance` |
- **Filename**: `<PR-number>-<short-slug>.md` (e.g. `fixes/6700-dockerfile-better-sqlite3.md`).
The PR number prefix keeps aggregation order deterministic.
- **Content**: the exact bullet line(s) that should land in `CHANGELOG.md`, starting with
`- `. Multi-line (continuation) bullets are fine. Keep the repo's credit format:
`(#PR — thanks @user)`.
- One fragment per PR (rarely more, e.g. a PR that both fixes and adds).
## Example
`changelog.d/fixes/6496-cloudflare-relay-worker-syntax.md`:
```markdown
- **fix(providers):** Cloudflare relay Worker deploys use Service Worker syntax with `body_part` metadata ([#6496](https://github.com/diegosouzapw/OmniRoute/pull/6496)) — thanks @SeaXen
```
## Aggregation
The release captain (or `/generate-release`) folds all fragments into `CHANGELOG.md` and
deletes them:
```bash
node scripts/release/aggregate-changelog.mjs # write + delete fragments
node scripts/release/aggregate-changelog.mjs --dry-run # preview only
```
Fragment well-formedness is enforced by `npm run check:changelog-integrity` (the same
gate that guards against CHANGELOG-eat for legacy direct edits).

View File

@@ -1 +0,0 @@
- **feat(core):** add Layer A capability filter at router (#5696)

View File

@@ -1 +0,0 @@
- **docs:** add management authentication terminology guide ([#7786](https://github.com/diegosouzapw/OmniRoute/issues/7786))

View File

@@ -1 +0,0 @@
- **feat(sse):** deprecated the legacy `gemini-cli` **upstream provider**. It was not routable (no registry entry, no executor), yet the scheduler kept refreshing its token against Google — maintaining a credential that could never serve a request. A stored connection now becomes terminal with a legible reason and a working migration path: re-add the account under `gemini`, which uses the same Google OAuth client. The `gemini-cli` **client identity** (requests arriving *from* the Gemini CLI, issue #7034) is untouched ([#8980](https://github.com/diegosouzapw/OmniRoute/pull/8980))

View File

@@ -1 +0,0 @@
- **feat(providers):** filter provider detail connections server-side while preserving full-page search and pagination. (thanks @RobertsXML)

View File

@@ -1,3 +0,0 @@
- fix(vision-bridge): describe-model no longer returns unreachable "openai/gpt-4o-mini" when every vision-capable provider is unreachable on the instance — returns null instead and surfaces a clear error (#8430)
- fix(vision-bridge): validate fixedModel against usable credentials before short-circuiting in getBestVisionModel, so the default "openai/gpt-4o-mini" is not unconditionally selected when no OpenAI connection exists (#8430)
- fix(vision-bridge): in the combo describe path, replace raw images with an error text stub when all describe attempts fail, instead of forwarding images to a confirmed non-vision backend that would reject them with an opaque serde error (#8430)

View File

@@ -1 +0,0 @@
- fix(quality): add base-relative file-size check so inherited drift does not red innocent PRs (#8522)

View File

@@ -1 +0,0 @@
- fix(executor): guard claude/anthropic buildHeaders against empty credentials and extend dual-Bearer parity for third-party baseUrls (#8653)

View File

@@ -1 +0,0 @@
- **fix(api):** Let image and video providers enforce their own request-size limits instead of rejecting media payloads at OmniRoute's 10 MB global default ([#8843](https://github.com/diegosouzapw/OmniRoute/pull/8843)) — thanks @artickc

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