mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-01 04:42:10 +03:00
chore: merge release/v3.8.5 to resolve conflicts
This commit is contained in:
diegosouzapw
@@ -37,6 +37,8 @@ INITIAL_PASSWORD=CHANGEME
|
||||
# Base directory for all persistent data (SQLite DB, logs, backups).
|
||||
# Used by: src/lib/db/core.ts — resolves the SQLite database file path.
|
||||
# Default: ~/.omniroute/ | Override for Docker or custom installations.
|
||||
# Hint: When running in Docker, consider mounting a host directory here for data persistence across container restarts
|
||||
# also if you want to share the same database as "npm run dev" use "./data"
|
||||
# DATA_DIR=/var/lib/omniroute
|
||||
|
||||
# Encryption key for SQLite database encryption at rest.
|
||||
|
||||
12
CHANGELOG.md
12
CHANGELOG.md
@@ -15,15 +15,25 @@
|
||||
|
||||
- **docker:** rebuild `better-sqlite3` native bindings after hardened install to resolve container startup crash (#2772 — thanks @thanet-s)
|
||||
- **combos:** make combo target timeout configurable, inheriting resolved request timeout by default and clamping values so they only shorten fallback latency (#2775 — thanks @rdself)
|
||||
- **oauth:** use public callbacks for remote Google OAuth with custom creds (#2787 — thanks @akarray)
|
||||
- **combos:** allow rate-limited provider connections after transient 429s (#2786 — thanks @JxnLexn)
|
||||
- **logs:** keep database log settings in sync with the pipeline toggle (#2785 — thanks @JxnLexn)
|
||||
- **docker:** speedup docker creation by reducing steps and bunch up copy operations (#2784 — thanks @hartmark)
|
||||
- **codex:** apply global service tiers to combo request bodies (#2783 — thanks @JxnLexn)
|
||||
|
||||
### ⚡ Performance / CI
|
||||
|
||||
- **ci:** build Docker platforms on native runners (linux/amd64 on ubuntu-24.04 and linux/arm64 on ubuntu-24.04-arm) instead of emulated QEMU, reducing build times significantly (#2774 — thanks @thanet-s)
|
||||
|
||||
### 📝 Documentation
|
||||
|
||||
- **docs:** fix broken documentation links in README after Fumadocs migration (#2782 — thanks @kjhq)
|
||||
|
||||
### 🏆 Hall of Contributors
|
||||
|
||||
A special thanks to everyone who contributed code, reviews, and tests for this release:
|
||||
@hartmark, @hijak, @rdself, @thanet-s
|
||||
@akarray, @hartmark, @hijak, @JxnLexn, @kjhq, @rdself, @thanet-s
|
||||
|
||||
|
||||
---
|
||||
|
||||
|
||||
@@ -232,18 +232,25 @@ tests/
|
||||
├── translator/ # Translator-specific tests
|
||||
└── load/ # Load tests
|
||||
|
||||
docs/ # Documentation
|
||||
├── ARCHITECTURE.md # System architecture
|
||||
├── API_REFERENCE.md # All endpoints
|
||||
├── USER_GUIDE.md # Provider setup, CLI integration
|
||||
├── TROUBLESHOOTING.md # Common issues
|
||||
├── MCP-SERVER.md # MCP server (25 tools)
|
||||
├── A2A-SERVER.md # A2A agent protocol
|
||||
├── AUTO-COMBO.md # Auto-combo engine
|
||||
├── CLI-TOOLS.md # CLI tools integration
|
||||
├── COVERAGE_PLAN.md # Test coverage improvement plan
|
||||
├── openapi.yaml # OpenAPI specification
|
||||
└── adr/ # Architecture Decision Records
|
||||
docs/
|
||||
├── adr/ # Architecture Decision Records
|
||||
├── architecture/ # System architecture & resilience
|
||||
├── comparison/ # OmniRoute vs alternatives
|
||||
├── compression/ # Compression guides & rules
|
||||
├── dev/ # Development guides
|
||||
├── diagrams/ # Architecture diagrams
|
||||
├── frameworks/ # MCP, A2A, OpenCode, Memory, Skills
|
||||
├── guides/ # User guide, Docker, setup, troubleshooting
|
||||
├── i18n/ # Internationalized README translations
|
||||
├── marketing/ # Marketing materials
|
||||
├── ops/ # Deployment, proxy, coverage, releases
|
||||
├── providers/ # Provider-specific docs
|
||||
├── reference/ # API reference, env vars, CLI tools, free tiers
|
||||
├── releases/ # Release notes
|
||||
├── routing/ # Auto-combo engine, reasoning replay
|
||||
├── screenshots/ # Dashboard screenshots
|
||||
├── security/ # Guardrails, compliance, stealth, tokens
|
||||
└── specs/ # Design specs
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
51
Dockerfile
51
Dockerfile
@@ -1,10 +1,22 @@
|
||||
FROM node:24-trixie-slim AS builder
|
||||
# ── Common base with runtime deps ──────────────────────────────────────────
|
||||
FROM node:24-trixie-slim AS base
|
||||
WORKDIR /app
|
||||
|
||||
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
|
||||
--mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
|
||||
RUN --mount=type=cache,target=/var/cache/apt,sharing=shared \
|
||||
--mount=type=cache,target=/var/lib/apt/lists,sharing=shared \
|
||||
apt-get update \
|
||||
&& apt-get install -y --no-install-recommends libsecret-1-0 ca-certificates python3 make g++ \
|
||||
&& apt-get install -y --no-install-recommends libsecret-1-0 ca-certificates \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
|
||||
# ── Builder ────────────────────────────────────────────────────────────────
|
||||
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,target=/var/cache/apt,sharing=shared \
|
||||
--mount=type=cache,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/*
|
||||
|
||||
COPY package*.json ./
|
||||
@@ -26,12 +38,15 @@ RUN --mount=type=cache,target=/root/.npm \
|
||||
&& npm rebuild better-sqlite3 \
|
||||
&& node -e "require('better-sqlite3')(':memory:').close()"
|
||||
|
||||
# Use Turbopack for significant build speedup
|
||||
ENV OMNIROUTE_USE_TURBOPACK=1
|
||||
|
||||
COPY . ./
|
||||
RUN --mount=type=cache,target=/app/.next/cache \
|
||||
mkdir -p /app/data && npm run build -- --webpack
|
||||
mkdir -p /app/data && npm run build
|
||||
|
||||
FROM node:24-trixie-slim AS runner-base
|
||||
WORKDIR /app
|
||||
# ── Runner base ────────────────────────────────────────────────────────────
|
||||
FROM base AS runner-base
|
||||
|
||||
LABEL org.opencontainers.image.title="omniroute" \
|
||||
org.opencontainers.image.description="Unified AI proxy — route any LLM through one endpoint" \
|
||||
@@ -46,15 +61,11 @@ ENV NODE_OPTIONS="--max-old-space-size=256"
|
||||
|
||||
# Data directory inside Docker — must match the volume mount in docker-compose.yml
|
||||
ENV DATA_DIR=/app/data
|
||||
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
|
||||
--mount=type=cache,target=/var/lib/apt/lists,sharing=locked \
|
||||
apt-get update \
|
||||
&& apt-get install -y --no-install-recommends libsecret-1-0 ca-certificates \
|
||||
&& rm -rf /var/lib/apt/lists/*
|
||||
RUN mkdir -p /app/data
|
||||
|
||||
COPY --from=builder /app/public ./public
|
||||
COPY --from=builder /app/.next/static ./.next/static
|
||||
# The standalone build + syncStandaloneExtraModules bundles all runtime files
|
||||
# (.next, node_modules, migrations, scripts, docs, etc.) into .next/standalone/.
|
||||
# Explicit overrides below cover modules that NFT tracing may miss.
|
||||
COPY --from=builder /app/.next/standalone ./
|
||||
# Explicitly copy @swc/helpers — not always traced by standalone output but needed at runtime
|
||||
COPY --from=builder /app/node_modules/@swc/helpers ./node_modules/@swc/helpers
|
||||
@@ -70,18 +81,6 @@ COPY --from=builder /app/node_modules/split2 ./node_modules/split2
|
||||
# traced by Next.js standalone output — copy them explicitly.
|
||||
COPY --from=builder /app/src/lib/db/migrations ./migrations
|
||||
ENV OMNIROUTE_MIGRATIONS_DIR=/app/migrations
|
||||
# MITM server.cjs is spawned at runtime via child_process — not traced by nft
|
||||
COPY --from=builder /app/src/mitm/server.cjs ./src/mitm/server.cjs
|
||||
# Runtime docs are pruned by .dockerignore to English markdown + OpenAPI.
|
||||
# Next.js standalone tracing does not include docs read via fs.
|
||||
COPY --from=builder /app/.next/standalone/docs ./docs
|
||||
|
||||
COPY --from=builder /app/scripts/dev/run-standalone.mjs ./dev/run-standalone.mjs
|
||||
COPY --from=builder /app/scripts/build/runtime-env.mjs ./build/runtime-env.mjs
|
||||
COPY --from=builder /app/scripts/build/bootstrap-env.mjs ./build/bootstrap-env.mjs
|
||||
COPY --from=builder /app/scripts/dev/healthcheck.mjs ./healthcheck.mjs
|
||||
|
||||
RUN node -e "require('better-sqlite3')(':memory:').close()"
|
||||
|
||||
# Hand /app over to the baked-in `node` non-root user (UID/GID 1000) so the
|
||||
# runtime process never holds root privileges. The chown happens after all
|
||||
|
||||
76
README.md
76
README.md
@@ -275,7 +275,7 @@ Result: 4 layers of fallback = zero downtime
|
||||
<b>＋ also works with</b> · Cline · Antigravity · Windsurf · AMP · Hermes · Qwen CLI · Roo · Continue · <b>any OpenAI-compatible tool</b>
|
||||
</div>
|
||||
|
||||
<sub>📖 Per-tool setup for all 16+ tools → [`docs/CLI-TOOLS.md`](docs/CLI-TOOLS.md) · 🧩 OpenCode plugin → [`@omniroute/opencode-provider`](https://www.npmjs.com/package/@omniroute/opencode-provider)</sub>
|
||||
<sub>📖 Per-tool setup for all 16+ tools → [`docs/reference/CLI-TOOLS.md`](docs/reference/CLI-TOOLS.md) · 🧩 OpenCode plugin → [`@omniroute/opencode-provider`](https://www.npmjs.com/package/@omniroute/opencode-provider)</sub>
|
||||
|
||||
</div>
|
||||
|
||||
@@ -332,7 +332,7 @@ Result: 4 layers of fallback = zero downtime
|
||||
| 🧩 **OpenCode plugin** | `@omniroute/opencode-provider` | Native OpenCode integration |
|
||||
| 🛠️ **From source** | `npm install && npm run dev` | Hack on it, contribute |
|
||||
|
||||
<sub>📖 [Docker Guide](docs/DOCKER_GUIDE.md) · [Desktop](electron/README.md) · [Termux](docs/TERMUX_GUIDE.md) · [PWA](docs/PWA_GUIDE.md) · [OpenCode](docs/frameworks/OPENCODE.md)</sub>
|
||||
<sub>📖 [Docker Guide](docs/guides/DOCKER_GUIDE.md) · [Desktop](electron/README.md) · [Termux](docs/guides/TERMUX_GUIDE.md) · [PWA](docs/guides/PWA_GUIDE.md) · [OpenCode](docs/frameworks/OPENCODE.md)</sub>
|
||||
|
||||
<br/>
|
||||
|
||||
@@ -440,7 +440,7 @@ range = 78.4 – 94.6%
|
||||
|
||||
Code blocks, URLs, JSON and structured data are **always protected** by the preservation engine. Auto-trigger compression by token threshold, or assign a compression pipeline per routing combo.
|
||||
|
||||
📖 [`COMPRESSION_GUIDE.md`](docs/COMPRESSION_GUIDE.md) · [`RTK_COMPRESSION.md`](docs/RTK_COMPRESSION.md) · [`COMPRESSION_ENGINES.md`](docs/COMPRESSION_ENGINES.md)
|
||||
📖 [`COMPRESSION_GUIDE.md`](docs/compression/COMPRESSION_GUIDE.md) · [`RTK_COMPRESSION.md`](docs/compression/RTK_COMPRESSION.md) · [`COMPRESSION_ENGINES.md`](docs/compression/COMPRESSION_ENGINES.md)
|
||||
|
||||
<br/>
|
||||
|
||||
@@ -509,7 +509,7 @@ pnpm install -g omniroute && pnpm approve-builds -g && omniroute
|
||||
yay -S omniroute-bin && systemctl --user enable --now omniroute.service
|
||||
```
|
||||
|
||||
📖 [Docker Guide](docs/DOCKER_GUIDE.md) — Compose profiles, Caddy HTTPS, Cloudflare tunnels.
|
||||
📖 [Docker Guide](docs/guides/DOCKER_GUIDE.md) — Compose profiles, Caddy HTTPS, Cloudflare tunnels.
|
||||
|
||||
</details>
|
||||
|
||||
@@ -580,7 +580,7 @@ yay -S omniroute-bin && systemctl --user enable --now omniroute.service
|
||||
|
||||
> 💡 The dashboard "cost" is a **savings tracker**, not a bill — OmniRoute never charges you. A "$290 total cost" using free models means **$290 saved**.
|
||||
|
||||
📖 Complete free directory → [`docs/FREE_TIERS.md`](docs/FREE_TIERS.md) — 25+ providers, quotas, base URLs.
|
||||
📖 Complete free directory → [`docs/reference/FREE_TIERS.md`](docs/reference/FREE_TIERS.md) — 25+ providers, quotas, base URLs.
|
||||
|
||||
</details>
|
||||
|
||||
@@ -616,7 +616,7 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
|
||||
- **🆓 1proxy marketplace** — hundreds of free validated proxies, quality scores, auto-rotation
|
||||
- **Anti-detection** — TLS fingerprint spoofing (`wreq-js`), CLI fingerprint matching, proxy IP preservation
|
||||
|
||||
📖 [`docs/PROXY_GUIDE.md`](docs/PROXY_GUIDE.md)
|
||||
📖 [`docs/ops/PROXY_GUIDE.md`](docs/ops/PROXY_GUIDE.md)
|
||||
|
||||
</details>
|
||||
|
||||
@@ -631,7 +631,7 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
|
||||
**Quality & Ops:** built-in **Evals** (golden-set: exact/contains/regex/custom) · guardrails (PII, injection, vision) · health dashboard · p50/p95/p99 telemetry · webhooks · compliance audit.
|
||||
**AI Agent Skills:** drop-in markdown manifests — point any agent at `skills/omniroute/SKILL.md`. 10 skills available.
|
||||
|
||||
📖 [MCP Server](open-sse/mcp-server/README.md) · [A2A Server](src/lib/a2a/README.md) · [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md) · [Features Gallery](docs/FEATURES.md)
|
||||
📖 [MCP Server](open-sse/mcp-server/README.md) · [A2A Server](src/lib/a2a/README.md) · [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md) · [Features Gallery](docs/guides/FEATURES.md)
|
||||
|
||||
</details>
|
||||
|
||||
@@ -651,7 +651,7 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
|
||||
**Will compression hurt quality?** No — it only compresses the **input**; code, URLs, JSON are always protected.
|
||||
**Does it work where AI is blocked?** Yes — 3-level proxy + 1proxy marketplace reach all 177 providers.
|
||||
|
||||
📖 [User Guide](docs/USER_GUIDE.md) · [API Reference](docs/API_REFERENCE.md) · [Environment Config](docs/ENVIRONMENT.md)
|
||||
📖 [User Guide](docs/guides/USER_GUIDE.md) · [API Reference](docs/reference/API_REFERENCE.md) · [Environment Config](docs/reference/ENVIRONMENT.md)
|
||||
|
||||
</details>
|
||||
|
||||
@@ -669,7 +669,7 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
|
||||
| Docker SQLite locks | Use `--stop-timeout 40` for clean WAL checkpoint |
|
||||
| Node runtime errors | Use Node `>=20.20.2 <21`, `>=22.22.2 <23`, or `>=24 <25` |
|
||||
|
||||
🐛 **Reporting a bug?** Run `npm run system-info` and attach `system-info.txt`. 📖 [`docs/TROUBLESHOOTING.md`](docs/TROUBLESHOOTING.md)
|
||||
🐛 **Reporting a bug?** Run `npm run system-info` and attach `system-info.txt`. 📖 [`docs/guides/TROUBLESHOOTING.md`](docs/guides/TROUBLESHOOTING.md)
|
||||
|
||||
</details>
|
||||
|
||||
@@ -740,50 +740,50 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
|
||||
|
||||
| Document | Description |
|
||||
| ------------------------------------- | ----------------------------------------------------------------------------- |
|
||||
| [User Guide](docs/USER_GUIDE.md) | Providers, combos, CLI integration, deployment |
|
||||
| [Setup Guide](docs/SETUP_GUIDE.md) | Full install methods, CLI tool configs, protocol setup, timeout tuning |
|
||||
| [CLI Tools Guide](docs/CLI-TOOLS.md) | Per-tool setup for Claude Code, Codex, Cursor, Cline, OpenClaw, Kilo, Copilot |
|
||||
| [User Guide](docs/guides/USER_GUIDE.md) | Providers, combos, CLI integration, deployment |
|
||||
| [Setup Guide](docs/guides/SETUP_GUIDE.md) | Full install methods, CLI tool configs, protocol setup, timeout tuning |
|
||||
| [CLI Tools Guide](docs/reference/CLI-TOOLS.md) | Per-tool setup for Claude Code, Codex, Cursor, Cline, OpenClaw, Kilo, Copilot |
|
||||
| [Quick Start](README.md#-quick-start) | 3-step install → connect → configure |
|
||||
|
||||
### 🔧 Operations & Deployment
|
||||
|
||||
| Document | Description |
|
||||
| ---------------------------------------------------- | -------------------------------------------------------------- |
|
||||
| [Docker Guide](docs/DOCKER_GUIDE.md) | Docker run, Compose profiles, Caddy HTTPS, tunnels, image tags |
|
||||
| [VM Deployment](docs/VM_DEPLOYMENT_GUIDE.md) | Complete guide: VM + nginx + Cloudflare setup |
|
||||
| [Fly.io Deployment](docs/FLY_IO_DEPLOYMENT_GUIDE.md) | Deploy to Fly.io with persistent storage |
|
||||
| [Termux Guide](docs/TERMUX_GUIDE.md) | Run OmniRoute on Android via Termux |
|
||||
| [PWA Guide](docs/PWA_GUIDE.md) | Progressive Web App install, caching, architecture |
|
||||
| [Uninstall Guide](docs/UNINSTALL.md) | Clean removal for all install methods |
|
||||
| [Environment Config](docs/ENVIRONMENT.md) | Complete `.env` variables and references |
|
||||
| [Docker Guide](docs/guides/DOCKER_GUIDE.md) | Docker run, Compose profiles, Caddy HTTPS, tunnels, image tags |
|
||||
| [VM Deployment](docs/ops/VM_DEPLOYMENT_GUIDE.md) | Complete guide: VM + nginx + Cloudflare setup |
|
||||
| [Fly.io Deployment](docs/ops/FLY_IO_DEPLOYMENT_GUIDE.md) | Deploy to Fly.io with persistent storage |
|
||||
| [Termux Guide](docs/guides/TERMUX_GUIDE.md) | Run OmniRoute on Android via Termux |
|
||||
| [PWA Guide](docs/guides/PWA_GUIDE.md) | Progressive Web App install, caching, architecture |
|
||||
| [Uninstall Guide](docs/guides/UNINSTALL.md) | Clean removal for all install methods |
|
||||
| [Environment Config](docs/reference/ENVIRONMENT.md) | Complete `.env` variables and references |
|
||||
|
||||
### 🧠 Features & Architecture
|
||||
|
||||
| Document | Description |
|
||||
| ---------------------------------------------------------------- | ----------------------------------------------------------------------------- |
|
||||
| [Architecture](docs/ARCHITECTURE.md) | System architecture, data flow, and internals |
|
||||
| [Compression Guide](docs/COMPRESSION_GUIDE.md) | 7-option pipeline: off / lite / standard / aggressive / ultra / RTK / stacked |
|
||||
| [RTK Compression](docs/RTK_COMPRESSION.md) | Command-output compression, filters, trust, verify, raw-output recovery |
|
||||
| [Compression Engines](docs/COMPRESSION_ENGINES.md) | Caveman, RTK, stacked pipelines, dashboard/API/MCP surfaces |
|
||||
| [Compression Rules Format](docs/COMPRESSION_RULES_FORMAT.md) | JSON rule-pack schemas for Caveman and RTK filters |
|
||||
| [Compression Language Packs](docs/COMPRESSION_LANGUAGE_PACKS.md) | Language detection and Caveman rule-pack authoring |
|
||||
| [Resilience Guide](docs/RESILIENCE_GUIDE.md) | Circuit breakers, cooldowns, queue, anti-thundering herd, TLS spoofing |
|
||||
| [Auto-Combo Engine](docs/AUTO-COMBO.md) | 6-factor scoring, mode packs, self-healing |
|
||||
| [Proxy Guide](docs/PROXY_GUIDE.md) | 3-level proxy system, 1proxy marketplace, registry CRUD |
|
||||
| [Free Tiers](docs/FREE_TIERS.md) | 25+ free API providers consolidated directory |
|
||||
| [Features Gallery](docs/FEATURES.md) | Visual dashboard tour with screenshots |
|
||||
| [Codebase Documentation](docs/CODEBASE_DOCUMENTATION.md) | Beginner-friendly codebase walkthrough |
|
||||
| [Architecture](docs/architecture/ARCHITECTURE.md) | System architecture, data flow, and internals |
|
||||
| [Compression Guide](docs/compression/COMPRESSION_GUIDE.md) | 7-option pipeline: off / lite / standard / aggressive / ultra / RTK / stacked |
|
||||
| [RTK Compression](docs/compression/RTK_COMPRESSION.md) | Command-output compression, filters, trust, verify, raw-output recovery |
|
||||
| [Compression Engines](docs/compression/COMPRESSION_ENGINES.md) | Caveman, RTK, stacked pipelines, dashboard/API/MCP surfaces |
|
||||
| [Compression Rules Format](docs/compression/COMPRESSION_RULES_FORMAT.md) | JSON rule-pack schemas for Caveman and RTK filters |
|
||||
| [Compression Language Packs](docs/compression/COMPRESSION_LANGUAGE_PACKS.md) | Language detection and Caveman rule-pack authoring |
|
||||
| [Resilience Guide](docs/architecture/RESILIENCE_GUIDE.md) | Circuit breakers, cooldowns, queue, anti-thundering herd, TLS spoofing |
|
||||
| [Auto-Combo Engine](docs/routing/AUTO-COMBO.md) | 6-factor scoring, mode packs, self-healing |
|
||||
| [Proxy Guide](docs/ops/PROXY_GUIDE.md) | 3-level proxy system, 1proxy marketplace, registry CRUD |
|
||||
| [Free Tiers](docs/reference/FREE_TIERS.md) | 25+ free API providers consolidated directory |
|
||||
| [Features Gallery](docs/guides/FEATURES.md) | Visual dashboard tour with screenshots |
|
||||
| [Codebase Documentation](docs/architecture/CODEBASE_DOCUMENTATION.md) | Beginner-friendly codebase walkthrough |
|
||||
|
||||
### 🤖 Protocols & APIs
|
||||
|
||||
| Document | Description |
|
||||
| ------------------------------------------- | --------------------------------------------------- |
|
||||
| [API Reference](docs/API_REFERENCE.md) | All endpoints with examples |
|
||||
| [OpenAPI Spec](docs/openapi.yaml) | OpenAPI 3.0 specification |
|
||||
| [API Reference](docs/reference/API_REFERENCE.md) | All endpoints with examples |
|
||||
| [OpenAPI Spec](docs/reference/openapi.yaml) | OpenAPI 3.0 specification |
|
||||
| [MCP Server](open-sse/mcp-server/README.md) | 29 MCP tools, IDE configs, Python/TS/Go clients |
|
||||
| [MCP Server Guide](docs/MCP-SERVER.md) | MCP installation, transports, and tool reference |
|
||||
| [MCP Server Guide](docs/frameworks/MCP-SERVER.md) | MCP installation, transports, and tool reference |
|
||||
| [A2A Server](src/lib/a2a/README.md) | JSON-RPC 2.0 protocol, skills, streaming, task mgmt |
|
||||
| [A2A Server Guide](docs/A2A-SERVER.md) | A2A agent card, tasks, skills, and streaming |
|
||||
| [A2A Server Guide](docs/frameworks/A2A-SERVER.md) | A2A agent card, tasks, skills, and streaming |
|
||||
|
||||
### 📋 Project & Quality
|
||||
|
||||
@@ -791,9 +791,9 @@ Compression: aggressive (~50%) → double your free quota · Cost: $0/mo
|
||||
| ---------------------------------------------- | ----------------------------------------------- |
|
||||
| [Contributing](CONTRIBUTING.md) | Development setup and guidelines |
|
||||
| [Security Policy](SECURITY.md) | Vulnerability reporting and security practices |
|
||||
| [i18n Guide](docs/I18N.md) | 40+ language support, translation workflow, RTL |
|
||||
| [Release Checklist](docs/RELEASE_CHECKLIST.md) | Pre-release validation steps |
|
||||
| [Coverage Plan](docs/COVERAGE_PLAN.md) | Test coverage strategy and 4,690+ test suite |
|
||||
| [i18n Guide](docs/guides/I18N.md) | 40+ language support, translation workflow, RTL |
|
||||
| [Release Checklist](docs/ops/RELEASE_CHECKLIST.md) | Pre-release validation steps |
|
||||
| [Coverage Plan](docs/ops/COVERAGE_PLAN.md) | Test coverage strategy and 4,690+ test suite |
|
||||
|
||||
<br/>
|
||||
|
||||
|
||||
@@ -1,134 +0,0 @@
|
||||
# OmniRoute Auto-Combo Engine
|
||||
|
||||
> Self-managing model chains with adaptive scoring + zero-config auto-routing
|
||||
|
||||
## Zero-Config Auto-Routing (`auto/` prefix)
|
||||
|
||||
> **NEW:** No combo creation required. Use `auto/` prefix directly in any client.
|
||||
|
||||
### Quick Examples
|
||||
|
||||
| Model ID | Variant | Behavior |
|
||||
| -------------- | ------- | ------------------------------------------------------------------------ |
|
||||
| `auto` | default | All connected providers, LKGP strategy, balanced weights |
|
||||
| `auto/coding` | coding | Quality-first weights, suitable for code generation |
|
||||
| `auto/fast` | fast | Low-latency weighted selection |
|
||||
| `auto/cheap` | cheap | Cost-optimized routing (lowest cost first) |
|
||||
| `auto/offline` | offline | Favors providers with highest quota availability |
|
||||
| `auto/smart` | smart | Quality-first + higher exploration rate (10%) for better model discovery |
|
||||
| `auto/lkgp` | lkgp | Explicit LKGP (same as default `auto`) |
|
||||
|
||||
**How to use:**
|
||||
|
||||
```bash
|
||||
# Any IDE or CLI tool that supports OpenAI format
|
||||
Base URL: http://localhost:20128/v1
|
||||
API Key: <your-endpoint-key>
|
||||
|
||||
# In your code/config, set model to:
|
||||
model: "auto" # balanced default
|
||||
model: "auto/coding" # best for coding tasks
|
||||
model: "auto/fast" # fastest available
|
||||
model: "auto/cheap" # cheapest per token
|
||||
```
|
||||
|
||||
**What happens:**
|
||||
|
||||
1. OmniRoute detects `auto/` prefix in `src/sse/handlers/chat.ts`
|
||||
2. Queries all **active provider connections** from the database
|
||||
3. Filters to those with valid credentials (API key or OAuth token)
|
||||
4. Determines the model per connection (`connection.defaultModel` or provider's first model)
|
||||
5. Builds a **virtual combo** in-memory (not stored in DB)
|
||||
6. Routes using the selected variant's weight profile + LKGP strategy
|
||||
|
||||
**Key properties:**
|
||||
|
||||
- ✅ **Always-on:** No toggle, no combo creation, no configuration needed
|
||||
- ✅ **Dynamic:** Reflects current connected providers automatically
|
||||
- ✅ **Session stickiness:** LKGP ensures last successful provider is prioritized
|
||||
- ✅ **Multi-account aware:** Each provider connection becomes a separate candidate
|
||||
- ✅ **No DB writes:** Virtual combo exists only for the request, zero persistence overhead
|
||||
|
||||
**Behind the scenes:**
|
||||
|
||||
```txt
|
||||
Request: { model: "auto/coding" }
|
||||
↓
|
||||
src/sse/handlers/chat.ts detects prefix
|
||||
↓
|
||||
createVirtualAutoCombo('coding') → candidatePool from active connections
|
||||
↓
|
||||
handleComboChat (same engine as persisted combos)
|
||||
↓
|
||||
Auto-scoring selects best provider/model per request
|
||||
```
|
||||
|
||||
**Implementation files:**
|
||||
|
||||
| File | Purpose |
|
||||
| --------------------------------------------------------- | ----------------------------------------- |
|
||||
| `open-sse/services/autoCombo/autoPrefix.ts` | Prefix parser (`parseAutoPrefix`) |
|
||||
| `open-sse/services/autoCombo/virtualFactory.ts` | Creates virtual `AutoComboConfig` objects |
|
||||
| `open-sse/services/autoCombo/providerRegistryAccessor.ts` | Test hook for mocking provider registry |
|
||||
| `src/sse/handlers/chat.ts` | Integration: auto prefix short-circuit |
|
||||
| `src/shared/constants/providers.ts` | `SYSTEM_PROVIDERS.auto` system entry |
|
||||
|
||||
## How It Works (Persisted Auto-Combos)
|
||||
|
||||
The Auto-Combo Engine dynamically selects the best provider/model for each request using a **6-factor scoring function**:
|
||||
|
||||
| Factor | Weight | Description |
|
||||
| :--------- | :----- | :---------------------------------------------- |
|
||||
| Quota | 0.20 | Remaining capacity [0..1] |
|
||||
| Health | 0.25 | Circuit breaker: CLOSED=1.0, HALF=0.5, OPEN=0.0 |
|
||||
| CostInv | 0.20 | Inverse cost (cheaper = higher score) |
|
||||
| LatencyInv | 0.15 | Inverse p95 latency (faster = higher) |
|
||||
| TaskFit | 0.10 | Model × task type fitness score |
|
||||
| Stability | 0.10 | Low variance in latency/errors |
|
||||
|
||||
## Mode Packs
|
||||
|
||||
| Pack | Focus | Key Weight |
|
||||
| :---------------------- | :----------- | :--------------- |
|
||||
| 🚀 **Ship Fast** | Speed | latencyInv: 0.35 |
|
||||
| 💰 **Cost Saver** | Economy | costInv: 0.40 |
|
||||
| 🎯 **Quality First** | Best model | taskFit: 0.40 |
|
||||
| 📡 **Offline Friendly** | Availability | quota: 0.40 |
|
||||
|
||||
## Self-Healing
|
||||
|
||||
- **Temporary exclusion**: Score < 0.2 → excluded for 5 min (progressive backoff, max 30 min)
|
||||
- **Circuit breaker awareness**: OPEN → auto-excluded; HALF_OPEN → probe requests
|
||||
- **Incident mode**: >50% OPEN → disable exploration, maximize stability
|
||||
- **Cooldown recovery**: After exclusion, first request is a "probe" with reduced timeout
|
||||
|
||||
## Bandit Exploration
|
||||
|
||||
5% of requests (configurable) are routed to random providers for exploration. Disabled in incident mode.
|
||||
|
||||
## API
|
||||
|
||||
```bash
|
||||
# Create auto-combo
|
||||
curl -X POST http://localhost:20128/api/combos/auto \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"id":"my-auto","name":"Auto Coder","candidatePool":["anthropic","google","openai"],"modePack":"ship-fast"}'
|
||||
|
||||
# List auto-combos
|
||||
curl http://localhost:20128/api/combos/auto
|
||||
```
|
||||
|
||||
## Task Fitness
|
||||
|
||||
30+ models scored across 6 task types (`coding`, `review`, `planning`, `analysis`, `debugging`, `documentation`). Supports wildcard patterns (e.g., `*-coder` → high coding score).
|
||||
|
||||
## Files
|
||||
|
||||
| File | Purpose |
|
||||
| :------------------------------------------- | :------------------------------------ |
|
||||
| `open-sse/services/autoCombo/scoring.ts` | Scoring function & pool normalization |
|
||||
| `open-sse/services/autoCombo/taskFitness.ts` | Model × task fitness lookup |
|
||||
| `open-sse/services/autoCombo/engine.ts` | Selection logic, bandit, budget cap |
|
||||
| `open-sse/services/autoCombo/selfHealing.ts` | Exclusion, probes, incident mode |
|
||||
| `open-sse/services/autoCombo/modePacks.ts` | 4 weight profiles |
|
||||
| `src/app/api/combos/auto/route.ts` | REST API |
|
||||
@@ -147,6 +147,18 @@ export async function syncStandaloneNativeAssets(
|
||||
sourcePath: path.join(rootDir, "node_modules", "wreq-js", "rust"),
|
||||
destinationPath: path.join(rootDir, ".next", "standalone", "node_modules", "wreq-js", "rust"),
|
||||
},
|
||||
{
|
||||
label: "better-sqlite3 native binary",
|
||||
sourcePath: path.join(rootDir, "node_modules", "better-sqlite3", "build"),
|
||||
destinationPath: path.join(
|
||||
rootDir,
|
||||
".next",
|
||||
"standalone",
|
||||
"node_modules",
|
||||
"better-sqlite3",
|
||||
"build"
|
||||
),
|
||||
},
|
||||
];
|
||||
|
||||
let changed = false;
|
||||
@@ -171,6 +183,90 @@ export async function syncStandaloneNativeAssets(
|
||||
return changed;
|
||||
}
|
||||
|
||||
export async function syncStandaloneExtraModules(
|
||||
rootDir = projectRoot,
|
||||
fsImpl = fs,
|
||||
log = console
|
||||
) {
|
||||
const entries = [
|
||||
{
|
||||
label: "@swc/helpers",
|
||||
sourcePath: path.join(rootDir, "node_modules", "@swc", "helpers"),
|
||||
destRelative: path.join("node_modules", "@swc", "helpers"),
|
||||
},
|
||||
{
|
||||
label: "pino-abstract-transport",
|
||||
sourcePath: path.join(rootDir, "node_modules", "pino-abstract-transport"),
|
||||
destRelative: path.join("node_modules", "pino-abstract-transport"),
|
||||
},
|
||||
{
|
||||
label: "pino-pretty",
|
||||
sourcePath: path.join(rootDir, "node_modules", "pino-pretty"),
|
||||
destRelative: path.join("node_modules", "pino-pretty"),
|
||||
},
|
||||
{
|
||||
label: "split2",
|
||||
sourcePath: path.join(rootDir, "node_modules", "split2"),
|
||||
destRelative: path.join("node_modules", "split2"),
|
||||
},
|
||||
{
|
||||
label: "migrations",
|
||||
sourcePath: path.join(rootDir, "src", "lib", "db", "migrations"),
|
||||
destRelative: "migrations",
|
||||
},
|
||||
{
|
||||
label: "MITM server",
|
||||
sourcePath: path.join(rootDir, "src", "mitm", "server.cjs"),
|
||||
destRelative: path.join("src", "mitm", "server.cjs"),
|
||||
},
|
||||
{
|
||||
label: "run-standalone script",
|
||||
sourcePath: path.join(rootDir, "scripts", "dev", "run-standalone.mjs"),
|
||||
destRelative: path.join("dev", "run-standalone.mjs"),
|
||||
},
|
||||
{
|
||||
label: "runtime-env script",
|
||||
sourcePath: path.join(rootDir, "scripts", "build", "runtime-env.mjs"),
|
||||
destRelative: path.join("build", "runtime-env.mjs"),
|
||||
},
|
||||
{
|
||||
label: "bootstrap-env script",
|
||||
sourcePath: path.join(rootDir, "scripts", "build", "bootstrap-env.mjs"),
|
||||
destRelative: path.join("build", "bootstrap-env.mjs"),
|
||||
},
|
||||
{
|
||||
label: "healthcheck script",
|
||||
sourcePath: path.join(rootDir, "scripts", "dev", "healthcheck.mjs"),
|
||||
destRelative: "healthcheck.mjs",
|
||||
},
|
||||
{
|
||||
label: "public directory",
|
||||
sourcePath: path.join(rootDir, "public"),
|
||||
destRelative: "public",
|
||||
},
|
||||
{
|
||||
label: "playwright-core (dynamic import by gemini-web executor)",
|
||||
sourcePath: path.join(rootDir, "node_modules", "playwright-core"),
|
||||
destRelative: path.join("node_modules", "playwright-core"),
|
||||
},
|
||||
];
|
||||
|
||||
let changed = false;
|
||||
const standaloneRoot = path.join(rootDir, ".next", "standalone");
|
||||
|
||||
for (const entry of entries) {
|
||||
if (!(await exists(entry.sourcePath))) continue;
|
||||
|
||||
const destPath = path.join(standaloneRoot, entry.destRelative);
|
||||
await fsImpl.mkdir(path.dirname(destPath), { recursive: true });
|
||||
await fsImpl.cp(entry.sourcePath, destPath, { recursive: true, force: true });
|
||||
log.log(`[build-next-isolated] Synced standalone module: ${entry.label}`);
|
||||
changed = true;
|
||||
}
|
||||
|
||||
return changed;
|
||||
}
|
||||
|
||||
export async function main() {
|
||||
const movedPaths = [];
|
||||
const transientBuildPaths = getTransientBuildPaths();
|
||||
@@ -225,6 +321,15 @@ export async function main() {
|
||||
nativeAssetErr
|
||||
);
|
||||
}
|
||||
|
||||
try {
|
||||
await syncStandaloneExtraModules(projectRoot);
|
||||
} catch (extraModuleErr) {
|
||||
console.warn(
|
||||
"[build-next-isolated] Non-fatal error syncing extra modules:",
|
||||
extraModuleErr
|
||||
);
|
||||
}
|
||||
}
|
||||
process.exitCode = result.code;
|
||||
} catch (error) {
|
||||
|
||||
@@ -9,6 +9,7 @@ import {
|
||||
getRequestDetailLogCount,
|
||||
isDetailedLoggingEnabled,
|
||||
} from "@/lib/db/detailedLogs";
|
||||
import { getUserDatabaseSettings, updateDatabaseSettings } from "@/lib/db/databaseSettings";
|
||||
import { updateSettings } from "@/lib/db/settings";
|
||||
|
||||
export const dynamic = "force-dynamic";
|
||||
@@ -36,6 +37,14 @@ export async function POST(req: NextRequest) {
|
||||
const enabled = body.enabled === true || body.enabled === "1";
|
||||
|
||||
await updateSettings({ call_log_pipeline_enabled: enabled });
|
||||
const databaseSettings = getUserDatabaseSettings();
|
||||
updateDatabaseSettings({
|
||||
logs: {
|
||||
...databaseSettings.logs,
|
||||
detailedLogsEnabled: enabled,
|
||||
callLogPipelineEnabled: enabled,
|
||||
},
|
||||
});
|
||||
|
||||
return NextResponse.json({
|
||||
success: true,
|
||||
|
||||
@@ -6,6 +6,7 @@ import {
|
||||
exchangeTokens,
|
||||
requestDeviceCode,
|
||||
pollForToken,
|
||||
resolveBrowserOAuthRedirectUri,
|
||||
} from "@/lib/oauth/providers";
|
||||
import {
|
||||
createProviderConnection,
|
||||
@@ -80,7 +81,9 @@ export async function GET(
|
||||
const { searchParams } = new URL(request.url);
|
||||
|
||||
if (action === "authorize") {
|
||||
const redirectUri = searchParams.get("redirect_uri") || "http://localhost:8080/callback";
|
||||
const requestedRedirectUri =
|
||||
searchParams.get("redirect_uri") || "http://localhost:8080/callback";
|
||||
const redirectUri = resolveBrowserOAuthRedirectUri(provider, requestedRedirectUri);
|
||||
const authData = generateAuthData(provider, redirectUri);
|
||||
if (provider === "qoder" && !authData.authUrl) {
|
||||
return NextResponse.json({
|
||||
|
||||
@@ -83,6 +83,17 @@ function parseStoredValue(rawValue: unknown): unknown {
|
||||
}
|
||||
}
|
||||
|
||||
function toBooleanSetting(value: unknown): boolean | null {
|
||||
if (typeof value === "boolean") return value;
|
||||
if (typeof value === "number") return !Number.isNaN(value) && value !== 0;
|
||||
if (typeof value !== "string") return null;
|
||||
|
||||
const normalized = value.trim().toLowerCase();
|
||||
if (["1", "true", "yes", "on"].includes(normalized)) return true;
|
||||
if (["0", "false", "no", "off"].includes(normalized)) return false;
|
||||
return null;
|
||||
}
|
||||
|
||||
function readNamespace(namespace: string): Record<string, unknown> {
|
||||
const db = getDbInstance();
|
||||
const rows = db
|
||||
@@ -119,6 +130,18 @@ function mergeTopLevelSections(target: UserDatabaseSettings, values: Record<stri
|
||||
}
|
||||
}
|
||||
|
||||
function mergeRuntimeLogSettings(target: UserDatabaseSettings, values: Record<string, unknown>) {
|
||||
const pipelineEnabled = toBooleanSetting(values.call_log_pipeline_enabled);
|
||||
if (pipelineEnabled !== null) {
|
||||
target.logs.callLogPipelineEnabled = pipelineEnabled;
|
||||
}
|
||||
|
||||
const legacyDetailedEnabled = toBooleanSetting(values.detailed_logs_enabled);
|
||||
if (legacyDetailedEnabled !== null) {
|
||||
target.logs.detailedLogsEnabled = legacyDetailedEnabled;
|
||||
}
|
||||
}
|
||||
|
||||
function mergeDatabaseSettingsNamespace(
|
||||
target: UserDatabaseSettings,
|
||||
values: Record<string, unknown>
|
||||
@@ -195,6 +218,7 @@ export function getUserDatabaseSettings(): UserDatabaseSettings {
|
||||
|
||||
mergeTopLevelSections(settings, mainSettings);
|
||||
mergeDatabaseSettingsNamespace(settings, readNamespace(DATABASE_SETTINGS_NAMESPACE));
|
||||
mergeRuntimeLogSettings(settings, mainSettings);
|
||||
|
||||
return settings;
|
||||
}
|
||||
@@ -236,6 +260,14 @@ export function updateDatabaseSettings(
|
||||
const insert = db.prepare(
|
||||
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES (?, ?, ?)"
|
||||
);
|
||||
const settingsInsert = db.prepare(
|
||||
"INSERT OR REPLACE INTO key_value (namespace, key, value) VALUES ('settings', ?, ?)"
|
||||
);
|
||||
|
||||
const requestedLogs = updates.logs as Partial<UserDatabaseSettings["logs"]> | undefined;
|
||||
const pipelineEnabled = requestedLogs?.callLogPipelineEnabled;
|
||||
const detailedEnabled = requestedLogs?.detailedLogsEnabled;
|
||||
|
||||
const tx = db.transaction(() => {
|
||||
for (const section of DATABASE_SETTINGS_SECTIONS) {
|
||||
const sectionValues = nextSettings[section] as Record<string, unknown>;
|
||||
@@ -244,6 +276,10 @@ export function updateDatabaseSettings(
|
||||
insert.run(DATABASE_SETTINGS_NAMESPACE, `${section}.${key}`, JSON.stringify(value));
|
||||
}
|
||||
}
|
||||
|
||||
if (pipelineEnabled !== undefined) {
|
||||
settingsInsert.run("call_log_pipeline_enabled", JSON.stringify(Boolean(pipelineEnabled)));
|
||||
}
|
||||
});
|
||||
tx();
|
||||
|
||||
|
||||
@@ -10,6 +10,66 @@
|
||||
import { generatePKCE, generateState } from "./utils/pkce";
|
||||
import { PROVIDERS } from "./providers/index";
|
||||
|
||||
const GOOGLE_BROWSER_PROVIDERS = new Set(["antigravity", "gemini-cli"]);
|
||||
|
||||
function normalizeBaseUrl(value) {
|
||||
const trimmed = typeof value === "string" ? value.trim() : "";
|
||||
if (!trimmed) return "";
|
||||
return trimmed.replace(/\/+$/, "");
|
||||
}
|
||||
|
||||
function hasCustomGoogleOAuthCredentials(providerName, env = process.env) {
|
||||
if (providerName === "antigravity") {
|
||||
return !!env.ANTIGRAVITY_OAUTH_CLIENT_ID?.trim();
|
||||
}
|
||||
|
||||
if (providerName === "gemini-cli") {
|
||||
return !!env.GEMINI_CLI_OAUTH_CLIENT_ID?.trim() || !!env.GEMINI_OAUTH_CLIENT_ID?.trim();
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* Google providers default to localhost redirects so the embedded public
|
||||
* credentials keep working on out-of-the-box local installs. When operators
|
||||
* provide their own Google OAuth client IDs for a remote deployment, prefer the
|
||||
* public callback URL documented in .env.example / docs/README so the popup can
|
||||
* navigate back to OmniRoute instead of stalling on localhost.
|
||||
*/
|
||||
export function resolveBrowserOAuthRedirectUri(
|
||||
providerName,
|
||||
redirectUri,
|
||||
env = process.env
|
||||
) {
|
||||
if (!GOOGLE_BROWSER_PROVIDERS.has(providerName)) {
|
||||
return redirectUri;
|
||||
}
|
||||
|
||||
if (!hasCustomGoogleOAuthCredentials(providerName, env)) {
|
||||
return redirectUri;
|
||||
}
|
||||
|
||||
const publicBaseUrl =
|
||||
normalizeBaseUrl(env.NEXT_PUBLIC_BASE_URL) || normalizeBaseUrl(env.OMNIROUTE_PUBLIC_BASE_URL);
|
||||
|
||||
if (!publicBaseUrl) {
|
||||
return redirectUri;
|
||||
}
|
||||
|
||||
try {
|
||||
const requested = new URL(redirectUri);
|
||||
const isLocalhostRedirect = /^(localhost|127\.0\.0\.1)$/i.test(requested.hostname);
|
||||
if (!isLocalhostRedirect) {
|
||||
return redirectUri;
|
||||
}
|
||||
} catch {
|
||||
return redirectUri;
|
||||
}
|
||||
|
||||
return `${publicBaseUrl}/callback`;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get provider handler
|
||||
*/
|
||||
|
||||
@@ -130,8 +130,8 @@ export interface ApplyCodexGlobalFastServiceTierOptions {
|
||||
*/
|
||||
model?: string | null;
|
||||
/**
|
||||
* Outbound request body. Per-request body.service_tier is left untouched if
|
||||
* already set.
|
||||
* Outbound request body. A valid per-request body.service_tier is left untouched
|
||||
* when already set.
|
||||
*/
|
||||
body?: Record<string, unknown> | null;
|
||||
}
|
||||
@@ -188,12 +188,11 @@ export function applyCodexGlobalFastServiceTier<T extends JsonRecord | null | un
|
||||
} as T;
|
||||
}
|
||||
|
||||
if (resolved.tier === "flex") {
|
||||
// Write the wire value directly to the outbound body when possible. The executor
|
||||
// also accepts requestDefaults.serviceTier = "flex" for downstream accounting.
|
||||
if (body && typeof body === "object" && !Array.isArray(body)) {
|
||||
(body as JsonRecord).service_tier = "flex";
|
||||
}
|
||||
if (body && typeof body === "object" && !Array.isArray(body)) {
|
||||
// Write the wire value directly to the outbound body when possible, so combo
|
||||
// request previews and logs show the same effective tier that the executor sends.
|
||||
// The executor also accepts requestDefaults.serviceTier for downstream accounting.
|
||||
(body as JsonRecord).service_tier = resolved.tier;
|
||||
}
|
||||
|
||||
// Intentional precedence: body service_tier > global mode > connection defaults.
|
||||
|
||||
@@ -381,9 +381,9 @@ export default function OAuthModal({
|
||||
// - Codex/OpenAI: always port 1455 (registered in OAuth app)
|
||||
// - Windsurf/Devin CLI (remote fallback): use localhost with OmniRoute port + /auth/callback
|
||||
// (on true localhost the callback server handles it; this is only reached on remote)
|
||||
// - Google OAuth providers (antigravity, gemini-cli): always localhost, regardless of
|
||||
// where OmniRoute is hosted — Google only accepts pre-registered localhost URIs with
|
||||
// the built-in credentials. Remote users must configure their own credentials.
|
||||
// - Google OAuth providers (antigravity, gemini-cli): default to localhost so the
|
||||
// bundled credentials keep working. The authorize route upgrades this to the public
|
||||
// callback when custom Google credentials + NEXT_PUBLIC_BASE_URL are configured.
|
||||
// - Other providers on remote: use actual origin (supports PUBLIC_URL env var)
|
||||
// - Localhost: use localhost:port
|
||||
let redirectUri: string;
|
||||
@@ -433,7 +433,7 @@ export default function OAuthModal({
|
||||
);
|
||||
}
|
||||
|
||||
setAuthData({ ...data, redirectUri });
|
||||
setAuthData({ ...data, redirectUri: data.redirectUri || redirectUri });
|
||||
|
||||
// For non-true-localhost (LAN IPs, remote) or manual fallback: use manual input mode (user pastes callback URL)
|
||||
if (!isTrueLocalhost || forceManual) {
|
||||
|
||||
@@ -606,6 +606,47 @@ test("chat pipeline persists Codex responses cache and reasoning tokens to call
|
||||
assert.equal(callLog.tokens.reasoning, 13);
|
||||
});
|
||||
|
||||
test("chat pipeline applies global Codex priority service tier inside combos", async () => {
|
||||
await seedConnection("codex", { apiKey: "sk-codex-combo-priority" });
|
||||
await settingsDb.updateSettings({
|
||||
codexServiceTier: { enabled: true, tier: "priority" },
|
||||
});
|
||||
await combosDb.createCombo({
|
||||
name: "codex-priority-combo",
|
||||
strategy: "priority",
|
||||
config: { maxRetries: 0, retryDelayMs: 0 },
|
||||
models: ["codex/gpt-5.5"],
|
||||
});
|
||||
const fetchCalls = [];
|
||||
|
||||
globalThis.fetch = async (url, init: RequestInit = {}) => {
|
||||
fetchCalls.push({
|
||||
url: String(url),
|
||||
headers: toPlainHeaders(init.headers),
|
||||
body: init.body ? JSON.parse(String(init.body)) : null,
|
||||
});
|
||||
return buildOpenAIResponsesSSE({ text: "combo priority ok", model: "gpt-5.5" });
|
||||
};
|
||||
|
||||
const response = await handleChat(
|
||||
buildRequest({
|
||||
body: {
|
||||
model: "codex-priority-combo",
|
||||
stream: false,
|
||||
messages: [{ role: "user", content: "Use Codex combo priority" }],
|
||||
},
|
||||
})
|
||||
);
|
||||
|
||||
const json = (await response.json()) as any;
|
||||
assert.equal(response.status, 200);
|
||||
assert.equal(fetchCalls.length, 1);
|
||||
assert.match(fetchCalls[0].url, /\/responses$/);
|
||||
assert.equal(fetchCalls[0].headers.Authorization, "Bearer sk-codex-combo-priority");
|
||||
assert.equal(fetchCalls[0].body.service_tier, "priority");
|
||||
assert.equal(json.choices[0].message.content, "combo priority ok");
|
||||
});
|
||||
|
||||
test("chat pipeline applies Codex CLI fingerprint to OAuth responses requests", async () => {
|
||||
setCliCompatProviders(["codex"]);
|
||||
await seedConnection("codex", {
|
||||
@@ -950,12 +991,7 @@ test("chat pipeline sends Gemini CLI OAuth requests with native Cloud Code trans
|
||||
assert.equal(generateCall.body.requestId, undefined);
|
||||
assert.equal(generateCall.body.user_prompt_id, generateCall.body.request.session_id);
|
||||
const keys = Object.keys(generateCall.body).slice(0, 4);
|
||||
assert.deepEqual(keys.sort(), [
|
||||
"model",
|
||||
"project",
|
||||
"request",
|
||||
"user_prompt_id",
|
||||
]);
|
||||
assert.deepEqual(keys.sort(), ["model", "project", "request", "user_prompt_id"]);
|
||||
assert.equal(generateCall.body.request.sessionId, undefined);
|
||||
assert.match(generateCall.body.request.session_id, /^[0-9a-f-]{36}$/i);
|
||||
assert.equal(generateCall.body.request.contents.at(-1).parts[0].text, "Hello Gemini CLI");
|
||||
|
||||
@@ -495,3 +495,79 @@ test.skip("round-robin path fast-skip: round-robin combo also skips exhausted pr
|
||||
assert.equal(openaiCalls, 1, "round-robin should skip second openai target");
|
||||
assert.equal(anthropicCalls, 1);
|
||||
});
|
||||
|
||||
test("allow rate-limited connections after transient 429 on subsequent targets in same combo", async () => {
|
||||
const now = Date.now();
|
||||
await seedConnection("openai", {
|
||||
name: "openai-rate-limited-reused",
|
||||
apiKey: "sk-openai-rate-limited-reused",
|
||||
rateLimitedUntil: new Date(now + 60000).toISOString(),
|
||||
});
|
||||
|
||||
await seedConnection("openai", {
|
||||
name: "openai-fresh-429",
|
||||
apiKey: "sk-openai-fresh-429",
|
||||
});
|
||||
|
||||
await settingsDb.updateSettings({
|
||||
requestRetry: 0,
|
||||
maxRetryIntervalSec: 0,
|
||||
});
|
||||
|
||||
await combosDb.createCombo({
|
||||
name: "rate-limit-reuse-combo",
|
||||
strategy: "priority",
|
||||
config: { maxRetries: 0, retryDelayMs: 0, fallbackDelayMs: 0 },
|
||||
models: [
|
||||
"openai/gpt-4o-mini",
|
||||
"openai/gpt-3.5-turbo",
|
||||
],
|
||||
});
|
||||
|
||||
let openaiCalls = 0;
|
||||
let usedApiKeys: string[] = [];
|
||||
|
||||
globalThis.fetch = async (_url: string, init: any = {}) => {
|
||||
const headers = toPlainHeaders(init.headers);
|
||||
const authHeader = headers.authorization ?? headers.Authorization;
|
||||
|
||||
openaiCalls += 1;
|
||||
if (authHeader === "Bearer sk-openai-fresh-429") {
|
||||
usedApiKeys.push("fresh");
|
||||
return new Response(JSON.stringify({ error: { message: "Too many requests" } }), {
|
||||
status: 429,
|
||||
headers: { "Content-Type": "application/json" },
|
||||
});
|
||||
}
|
||||
|
||||
if (authHeader === "Bearer sk-openai-rate-limited-reused") {
|
||||
usedApiKeys.push("rate-limited");
|
||||
return new Response(
|
||||
JSON.stringify({ choices: [{ message: { content: "rate limited reuse success" } }] }),
|
||||
{
|
||||
status: 200,
|
||||
headers: { "Content-Type": "application/json" },
|
||||
}
|
||||
);
|
||||
}
|
||||
|
||||
throw new Error(`unexpected upstream headers: ${JSON.stringify(headers)}`);
|
||||
};
|
||||
|
||||
const response = await handleChat(
|
||||
buildRequest({
|
||||
body: {
|
||||
model: "rate-limit-reuse-combo",
|
||||
stream: false,
|
||||
messages: [{ role: "user", content: "test rate limit reuse" }],
|
||||
},
|
||||
})
|
||||
);
|
||||
|
||||
const body = (await response.json()) as any;
|
||||
assert.equal(response.status, 200);
|
||||
assert.equal(body.choices[0].message.content, "rate limited reuse success");
|
||||
assert.equal(openaiCalls, 2);
|
||||
assert.deepEqual(usedApiKeys, ["fresh", "rate-limited"]);
|
||||
});
|
||||
|
||||
|
||||
@@ -106,15 +106,17 @@ test("Codex global service tier injects selected mode and can override connectio
|
||||
});
|
||||
|
||||
test("Codex global service tier matches provider-prefixed combo model ids", () => {
|
||||
const body: Record<string, unknown> = {};
|
||||
assert.deepEqual(
|
||||
applyCodexGlobalFastServiceTier(
|
||||
"codex",
|
||||
{ providerSpecificData: {} },
|
||||
{ codexServiceTier: { enabled: true, tier: "priority" } },
|
||||
{ model: "codex/gpt-5.5" }
|
||||
{ model: "codex/gpt-5.5", body }
|
||||
),
|
||||
{ providerSpecificData: { requestDefaults: { serviceTier: "priority" } } }
|
||||
);
|
||||
assert.equal(body.service_tier, "priority");
|
||||
|
||||
const unsupported = { providerSpecificData: {} };
|
||||
assert.equal(
|
||||
@@ -155,7 +157,7 @@ test("Codex global service tier only short-circuits on valid body service_tier",
|
||||
assert.deepEqual(injected, {
|
||||
providerSpecificData: { requestDefaults: { serviceTier: "priority" } },
|
||||
});
|
||||
assert.equal(invalidBody.service_tier, "invalid");
|
||||
assert.equal(invalidBody.service_tier, "priority");
|
||||
|
||||
const validBody: Record<string, unknown> = { service_tier: " Flex " };
|
||||
const unchanged = { providerSpecificData: {} };
|
||||
|
||||
@@ -11,6 +11,7 @@ process.env.DISABLE_SQLITE_AUTO_BACKUP = "true";
|
||||
const core = await import("../../src/lib/db/core.ts");
|
||||
const databaseSettings = await import("../../src/lib/db/databaseSettings.ts");
|
||||
const databaseSettingsRoute = await import("../../src/app/api/settings/database/route.ts");
|
||||
const settingsDb = await import("../../src/lib/db/settings.ts");
|
||||
const cleanup = await import("../../src/lib/db/cleanup.ts");
|
||||
const aggregateHistory = await import("../../src/lib/usage/aggregateHistory.ts");
|
||||
|
||||
@@ -101,6 +102,23 @@ test("database settings reader supports legacy flat keys and lets nested saves w
|
||||
assert.equal(databaseSettings.getUserDatabaseSettings().retention.callLogs, 7);
|
||||
});
|
||||
|
||||
test("database log settings mirror the runtime pipeline toggle", async () => {
|
||||
await settingsDb.updateSettings({ call_log_pipeline_enabled: false });
|
||||
|
||||
assert.equal(databaseSettings.getUserDatabaseSettings().logs.callLogPipelineEnabled, false);
|
||||
|
||||
databaseSettings.updateDatabaseSettings({
|
||||
logs: {
|
||||
...databaseSettings.getUserDatabaseSettings().logs,
|
||||
callLogPipelineEnabled: true,
|
||||
},
|
||||
});
|
||||
|
||||
const settings = await settingsDb.getSettings();
|
||||
assert.equal(settings.call_log_pipeline_enabled, true);
|
||||
assert.equal(databaseSettings.getUserDatabaseSettings().logs.callLogPipelineEnabled, true);
|
||||
});
|
||||
|
||||
test("purgeDetailedLogs deletes request_detail_logs", async () => {
|
||||
const db = core.getDbInstance();
|
||||
db.prepare("INSERT INTO request_detail_logs (id, timestamp, duration_ms) VALUES (?, ?, ?)").run(
|
||||
|
||||
@@ -18,8 +18,10 @@ const providersModule = await import("../../src/lib/oauth/providers/index.ts");
|
||||
const oauthModule = await import("../../src/lib/oauth/constants/oauth.ts");
|
||||
const registryModule = await import("../../open-sse/config/providerRegistry.ts");
|
||||
const antigravityHeadersModule = await import("../../open-sse/services/antigravityHeaders.ts");
|
||||
const oauthHelpersModule = await import("../../src/lib/oauth/providers.ts");
|
||||
|
||||
const PROVIDERS = providersModule.default;
|
||||
const { resolveBrowserOAuthRedirectUri } = oauthHelpersModule;
|
||||
const {
|
||||
ANTIGRAVITY_CONFIG,
|
||||
CLAUDE_CONFIG,
|
||||
@@ -316,6 +318,44 @@ test("browser-based providers expose buildAuthUrl and return provider-specific a
|
||||
assert.equal(clineUrl.origin, "https://api.cline.bot");
|
||||
});
|
||||
|
||||
test("custom Google OAuth credentials switch Antigravity remote callbacks to NEXT_PUBLIC_BASE_URL", () => {
|
||||
const redirectUri = resolveBrowserOAuthRedirectUri(
|
||||
"antigravity",
|
||||
"http://localhost:20128/callback",
|
||||
{
|
||||
NEXT_PUBLIC_BASE_URL: "https://omniroute.example.com/",
|
||||
ANTIGRAVITY_OAUTH_CLIENT_ID: "custom-antigravity.apps.googleusercontent.com",
|
||||
}
|
||||
);
|
||||
|
||||
assert.equal(redirectUri, "https://omniroute.example.com/callback");
|
||||
});
|
||||
|
||||
test("custom Google OAuth credentials switch Gemini remote callbacks to OMNIROUTE_PUBLIC_BASE_URL", () => {
|
||||
const redirectUri = resolveBrowserOAuthRedirectUri(
|
||||
"gemini-cli",
|
||||
"http://127.0.0.1:20128/callback",
|
||||
{
|
||||
OMNIROUTE_PUBLIC_BASE_URL: "https://omniroute.example.com",
|
||||
GEMINI_CLI_OAUTH_CLIENT_ID: "custom-gemini.apps.googleusercontent.com",
|
||||
}
|
||||
);
|
||||
|
||||
assert.equal(redirectUri, "https://omniroute.example.com/callback");
|
||||
});
|
||||
|
||||
test("Google OAuth callbacks stay on localhost when no custom credentials are configured", () => {
|
||||
const redirectUri = resolveBrowserOAuthRedirectUri(
|
||||
"antigravity",
|
||||
"http://localhost:20128/callback",
|
||||
{
|
||||
NEXT_PUBLIC_BASE_URL: "https://omniroute.example.com",
|
||||
}
|
||||
);
|
||||
|
||||
assert.equal(redirectUri, "http://localhost:20128/callback");
|
||||
});
|
||||
|
||||
test("device and import-token providers expose the flow-specific fields expected by their configs", () => {
|
||||
const deviceProviders = ["qwen", "kimi-coding", "github", "kiro", "amazon-q", "kilocode"];
|
||||
|
||||
|
||||
@@ -608,6 +608,22 @@ test("getProviderCredentials retains rate-limited accounts when allowSuppressedC
|
||||
assert.equal(bypassed.connectionId, connection.id);
|
||||
});
|
||||
|
||||
test("getProviderCredentials retains rate-limited accounts when allowRateLimitedConnections is enabled", async () => {
|
||||
const connection = await seedConnection("openai", {
|
||||
name: "allow-rate-limit-option",
|
||||
rateLimitedUntil: futureIso(),
|
||||
});
|
||||
|
||||
const blocked = await auth.getProviderCredentials("openai");
|
||||
const bypassed = await auth.getProviderCredentials("openai", null, null, null, {
|
||||
allowRateLimitedConnections: true,
|
||||
});
|
||||
|
||||
assert.equal(blocked.allRateLimited, true);
|
||||
assert.equal(bypassed.connectionId, connection.id);
|
||||
});
|
||||
|
||||
|
||||
test("getProviderCredentials retains terminal accounts for combo live tests", async () => {
|
||||
const connection = await seedConnection("openai", {
|
||||
name: "suppressed-terminal",
|
||||
|
||||
Reference in New Issue
Block a user