mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-07-26 09:52:11 +03:00
0594af6a6c
* feat(cursor): vision (image_url) input + tool-commit/output-constraint enhancements Add image/vision input to the Cursor provider's agent.v1 endpoint, plus the supporting prompt-engineering and resilience work developed alongside it. Vision input - Decode OpenAI `image_url` parts (base64 `data:` URIs and remote `http(s)` URLs) and inline them as `SelectedContext.selected_images[]` — field numbers pinned from the cursor-agent agent.v1 protobuf descriptor (SelectedImage.data oneof, uuid, optional Dimension, mime_type). Cross-checked against composer-api's shape. - New `resolveCursorImages` helper: SSRF-guarded remote fetches via the repo's canonical `parseAndValidatePublicUrl` (always public-only for client URLs), <=1 MiB per image (pre-decode + streaming cap), `image/*` enforced, max 12 images, sanitized `CursorImageError` (no stack/path leakage). - `openai-to-cursor` translator now preserves `image_url` parts instead of dropping them; executor `buildRequest` resolves images and attaches them to the user turn. The no-image path is byte-identical to before (test-asserted). Supporting cursor enhancements - Tool-commit directive (raises composer-2.5 tool-call rate ~53% -> ~88%), `tool_choice` none/required/specific handling, and output constraints (`response_format` / `max_tokens` / `stop` surfaced as prompt instructions). - `cursorSessionManager`: clear pending tool-call mappings on session close. - `cursorVersionDetector`: export `FALLBACK_VERSION` as a single source of truth. Tests & docs - New unit suite for the image encoder + resolver (field layout, byte-identical no-image path, SSRF / oversize / bad-base64 / too-many rejections, sanitized error body), translator image-preservation tests, and live e2e tests (base64 + remote URL, gated on `CURSOR_E2E_TOKEN`). - Documented `CURSOR_TOOL_DIRECTIVE` and `CURSOR_IMAGE_FETCH_TIMEOUT_MS` in `.env.example` and `docs/reference/ENVIRONMENT.md`. * fix(cursor): address review — redirect SSRF, large-payload guard, stream OOM, case/NaN nits Resolves the gemini-code-assist review on #3104: - SSRF via redirect (critical): fetchImageBytes now uses redirect:"manual" and re-validates every hop through parseAndValidatePublicUrl, so a public URL can't 30x-redirect to a private/link-local address. Bounded to 3 redirects. - Large data URL (high): reject on raw payload length before the whitespace-strip regex, so an oversized data URL can't burn CPU. - Stream read (high): readCapped consumes the body as an async iterable (Node Readable + Web Streams) or via getReader, capping mid-read; uncapped arrayBuffer() is only a last resort. - data: scheme (medium): match case-insensitively (RFC 2397) while preserving the original payload. - NaN timeouts (medium): CURSOR_IMAGE_FETCH_TIMEOUT_MS and CURSOR_STREAM_TIMEOUT_MS fall back to defaults when the env value isn't a positive integer. Adds tests: redirect-to-private blocked, redirect-to-public followed, too-many- redirects rejected, uppercase DATA: accepted. * fix(cursor): defend image fetch against DNS-rebinding SSRF Address the @codex review on #3104: parseAndValidatePublicUrl only checks the hostname string, so a public-looking host that (re)resolves to a private / link-local / metadata IP would still be fetched. Each hop now resolves the host via dns.lookup({all:true}) and rejects if ANY answer is private (isPrivateHost), before connecting. IP literals are skipped (already validated by the URL guard). This narrows but doesn't fully close the TOCTOU window vs fetch's own resolution; a connection-time IP filter on the shared outbound guard would close it for every caller. Adds unit tests for the IP gate and a mocked DNS-rebinding case (public host -> 127.0.0.1, fetch never reached).
title, version, lastUpdated
| title | version | lastUpdated |
|---|---|---|
| OmniRoute Documentation | 3.8.2 | 2026-05-13 |
OmniRoute Documentation
Navigable index of the OmniRoute documentation set. Topics are grouped by intent so you can find what you need quickly.
Looking for the project overview, install steps, or release notes? See the root README.md, CHANGELOG.md, and CONTRIBUTING.md.
architecture/
How the system is put together — read these to understand the runtime, code layout, and resilience model.
- ARCHITECTURE.md — high-level system architecture (request pipeline, layers, modules).
- CODEBASE_DOCUMENTATION.md — engineering reference for the codebase.
- REPOSITORY_MAP.md — directory-by-directory navigation guide.
- AUTHZ_GUIDE.md — authorization pipeline (route classifier + policy engine).
- RESILIENCE_GUIDE.md — provider circuit breaker, connection cooldown, and model lockout.
guides/
Task-focused walkthroughs for operators and end users.
- SETUP_GUIDE.md — first-time setup of OmniRoute.
- USER_GUIDE.md — daily usage of the dashboard and API.
- DOCKER_GUIDE.md — running OmniRoute under Docker.
- ELECTRON_GUIDE.md — desktop (Electron) builds.
- TERMUX_GUIDE.md — running on Android via Termux.
- PWA_GUIDE.md — installing the dashboard as a PWA.
- TROUBLESHOOTING.md — common issues and fixes.
- UNINSTALL.md — clean removal steps.
- I18N.md — translation and locale workflow.
- FEATURES.md — dashboard feature gallery.
reference/
Lookup material — API surface, environment variables, CLI flags, provider catalog.
- API_REFERENCE.md — REST API endpoints and shapes.
- PROVIDER_REFERENCE.md — auto-generated provider catalog.
- openapi.yaml — OpenAPI 3.1 spec for the public API.
- ENVIRONMENT.md — environment variables reference.
- CLI-TOOLS.md — bundled CLI commands.
- FREE_TIERS.md — free-tier LLM provider directory.
frameworks/
Pluggable subsystems exposed to clients, agents, and operators.
- MCP-SERVER.md — Model Context Protocol server.
- A2A-SERVER.md — Agent-to-Agent (A2A) JSON-RPC server.
- AGENT_PROTOCOLS_GUIDE.md — A2A / ACP / Cloud agent overview.
- CLOUD_AGENT.md — cloud agent runtime and providers.
- SKILLS.md — Skills framework (sandboxed extension).
- MEMORY.md — persistent memory (FTS5 + Qdrant).
- WEBHOOKS.md — webhook events and dispatch.
- EVALS.md — eval suites.
routing/
Combo routing, scoring, and replay.
- AUTO-COMBO.md — Auto-Combo (9-factor scoring, 14 strategies).
- REASONING_REPLAY.md — reasoning replay flow.
security/
Guardrails, compliance, stealth, and the mandatory patterns for handling public credentials and error messages.
- GUARDRAILS.md — PII, prompt injection, vision guardrails.
- COMPLIANCE.md — audit trails and compliance.
- STEALTH_GUIDE.md — TLS / fingerprint stealth.
- PUBLIC_CREDS.md — mandatory pattern for embedding public upstream OAuth client_id/secret + Firebase Web keys without tripping secret scanners.
- ERROR_SANITIZATION.md — mandatory pattern for routing every error response through
sanitizeErrorMessageto prevent stack-trace exposure.
compression/
Prompt compression engines, rules, and language packs.
- COMPRESSION_GUIDE.md — top-level compression overview.
- COMPRESSION_ENGINES.md — available compression engines.
- COMPRESSION_RULES_FORMAT.md — rule file format.
- COMPRESSION_LANGUAGE_PACKS.md — language packs.
- RTK_COMPRESSION.md — RTK engine deep dive.
ops/
Release, deployment, proxies, tunnels, coverage.
- RELEASE_CHECKLIST.md — release flow checklist.
- COVERAGE_PLAN.md — test coverage plan.
- FLY_IO_DEPLOYMENT_GUIDE.md — Fly.io deployment.
- VM_DEPLOYMENT_GUIDE.md — generic VM deployment.
- PROXY_GUIDE.md — upstream proxy configuration.
- TUNNELS_GUIDE.md — Cloudflare tunnel and friends.
diagrams/
Mermaid sources and exported SVG/PNG diagrams referenced from the docs above. Populated incrementally — see diagrams/README.md.
i18n/
Translated mirrors of the documentation in 40 locales. See i18n/README.md for the supported language list.
screenshots/
Static screenshots used by the dashboard and the README. Not part of the doc body.
Auto-generated artifacts
- reference/PROVIDER_REFERENCE.md is generated by
scripts/docs/gen-provider-reference.tsfromsrc/shared/constants/providers.ts. Do not edit by hand. - The
/docsUI is backed by Fumadocs MDX source generation from the subfolders above.