mirror of
https://github.com/supabase/supabase.git
synced 2026-10-09 11:25:06 +03:00
Pedro RodriguesandClaude Opus 4.8
c4c213ce3d
## I have read the [CONTRIBUTING.md](<https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md>) file. YES ## What kind of change does this PR introduce? Feature / refactor. ## What is the current behavior? The dashboard assistant runs `@supabase/mcp-server-supabase` in-process over an in-memory transport (`lib/ai/supabase-mcp.ts`). ## What is the new behavior? The assistant connects to the **remote MCP server** over HTTP (`@ai-sdk/mcp`), forwarding the dashboard session token as a bearer. URL comes from `NEXT_PUBLIC_MCP_URL` with a local-dev fallback; platform-only, and Nimbus works via the same env var. * **Tool model unchanged:** UI-controlled `execute_sql` (with `needsApproval`) and `deploy_edge_function` still come from Studio; the allowlist (`TOOL_CATEGORY_MAP`) remains the gate keeping the remote's write tools away from the assistant (`read_only` is defense-in-depth). * **Attribution:** sends `x-source-name: supabase-studio` (+ `x-source-version`) → logged as `source_name`/`client_name`. * **Connection lifecycle:** the HTTP client is closed via the request's `AbortSignal` (tools execute later during streaming); `signal` is required on `getTools`/`getMcpTools`. * **Resilience:** a remote-MCP failure degrades to the remaining tools instead of failing the assistant. * **Drift protection:** relied-upon tools are typed against `keyof typeof supabaseMcpToolSchemas`, so a package bump that renames/removes one fails `pnpm typecheck`; a runtime check also warns if the deployed server returns fewer tools. * Adds unit tests for the above. ## Additional context * Verified end-to-end against a local remote MCP server with a dashboard token: `initialize` 200, tools listed, a tool executed, client closed cleanly. * The remote MCP (mgmt-api) already accepts dashboard session tokens (GoTrue-JWT auth path) — no backend change needed. `NEXT_PUBLIC_MCP_URL` must point at each env's `/mcp`. * `@supabase/mcp-server-supabase` is kept — still used by the self-hosted `/api/mcp` routes. Closes [AI-137](https://linear.app/supabase/issue/AI-137/switch-dashboard-assistant-to-remote-mcp) ## Rollout * **Rollout:** merges with `USE_REMOTE_MCP` off (in-process); flip it to `true` per environment (staging → prod → Nimbus) once each one's prerequisites land. * **Rollback:** unset `USE_REMOTE_MCP` and redeploy to fall back to the in-process client — no revert needed. ## Summary by CodeRabbit * **Bug Fixes** * Improved AI request handling so tool loading and generation clean up properly when a request is cancelled or the browser connection closes. * Added safer fallback behavior when remote tool loading fails, so AI features can continue with available tools instead of stopping entirely. * Updated remote tool access to use the current project reference and preserve the correct access headers. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * AI tools now connect more reliably to remote services and stop cleanly when requests end or are canceled. * Tool loading is more resilient, continuing with available tools if remote access is unavailable. * **Bug Fixes** * Improved cleanup to prevent lingering connections during SQL generation and policy workflows. * Added safer handling for remote tool changes and invalid responses. * **Tests** * Expanded automated coverage for remote tool setup, cancellation, and fallback behavior. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
141 lines
4.7 KiB
JSON
141 lines
4.7 KiB
JSON
{
|
|
"$schema": "./../../node_modules/turbo/schema.json",
|
|
"extends": ["//"],
|
|
"tasks": {
|
|
"build": {
|
|
"dependsOn": ["^build"],
|
|
"env": [
|
|
"ANALYZE",
|
|
"CI",
|
|
"NEXT_PUBLIC_SUPPORT_API_URL",
|
|
"NEXT_PUBLIC_CONTENT_API_URL",
|
|
"NEXT_PUBLIC_BASE_PATH",
|
|
"NEXT_PUBLIC_STRIPE_PUBLIC_KEY",
|
|
"NEXT_PUBLIC_SUPPORT_ANON_KEY",
|
|
"NEXT_PUBLIC_ENVIRONMENT",
|
|
"NEXT_PUBLIC_IS_PLATFORM",
|
|
"NEXT_PUBLIC_SITE_URL",
|
|
"NEXT_PUBLIC_API_URL",
|
|
"NEXT_PUBLIC_DOCS_URL",
|
|
"NEXT_PUBLIC_CONFIGCAT_SDK_KEY",
|
|
"NEXT_PUBLIC_CONFIGCAT_PROXY_URL",
|
|
"NEXT_PUBLIC_HCAPTCHA_SITE_KEY",
|
|
"NEXT_PUBLIC_SUPABASE_URL",
|
|
"NEXT_PUBLIC_SUPABASE_ANON_KEY",
|
|
"NEXT_PUBLIC_NODE_ENV",
|
|
"NEXT_PUBLIC_GOTRUE_URL",
|
|
"NEXT_PUBLIC_VERCEL_BRANCH_URL",
|
|
"NEXT_PUBLIC_GOOGLE_MAPS_KEY",
|
|
"NEXT_RUNTIME",
|
|
"NIMBUS_PROD_PROJECTS_URL",
|
|
"NIMBUS_PROD_PROJECTS_URL_WS",
|
|
"NODE_ENV",
|
|
"SUPABASE_URL",
|
|
"VERCEL",
|
|
"VERCEL_ENV",
|
|
"MAINTENANCE_MODE",
|
|
// These envs are used in the packages
|
|
"NEXT_PUBLIC_STORAGE_KEY",
|
|
"NEXT_PUBLIC_AUTH_DEBUG_KEY",
|
|
"NEXT_PUBLIC_AUTH_PERSISTED_KEY",
|
|
"NEXT_PUBLIC_AUTH_NAVIGATOR_LOCK_KEY",
|
|
"NEXT_PUBLIC_AUTH_DETECT_SESSION_IN_URL",
|
|
"NEXT_PUBLIC_GOOGLE_TAG_MANAGER_ID",
|
|
"NEXT_PUBLIC_VERCEL_ENV",
|
|
"NEXT_PUBLIC_USERCENTRICS_RULESET_ID",
|
|
"NEXT_PUBLIC_MCP_URL",
|
|
"NEXT_PUBLIC_IS_NIMBUS",
|
|
"NEXT_PUBLIC_ONGOING_INCIDENT",
|
|
// These envs are technically passthrough env vars because they're only used on the server side of Nextjs
|
|
"PLATFORM_PG_META_URL",
|
|
"STUDIO_PG_META_URL",
|
|
"PG_META_CRYPTO_KEY",
|
|
"PGRST_DB_SCHEMAS",
|
|
"PGRST_DB_MAX_ROWS",
|
|
"PGRST_DB_EXTRA_SEARCH_PATH",
|
|
"POSTGRES_PASSWORD",
|
|
"POSTGRES_HOST",
|
|
"POSTGRES_USER_READ_WRITE",
|
|
"POSTGRES_USER_READ_ONLY",
|
|
"POSTGRES_DB",
|
|
"POSTGRES_PORT",
|
|
"READ_ONLY_URL",
|
|
"READ_ONLY_API_KEY",
|
|
"SUPABASE_SERVICE_KEY",
|
|
"SUPABASE_ANON_KEY",
|
|
"SUPABASE_PUBLISHABLE_KEY",
|
|
"SUPABASE_SECRET_KEY",
|
|
"SUPABASE_PUBLIC_URL",
|
|
"DEFAULT_PROJECT_NAME",
|
|
"DEFAULT_ORGANIZATION_NAME",
|
|
"OPENAI_API_KEY",
|
|
"BRAINTRUST_API_KEY",
|
|
"BRAINTRUST_PROJECT_ID",
|
|
// Gates the dashboard assistant between the remote MCP server and the
|
|
// legacy in-process one (see lib/ai/tools/mcp-tools.ts).
|
|
"USE_REMOTE_MCP",
|
|
"AUTH_JWT_SECRET",
|
|
"LOGFLARE_API_KEY",
|
|
"LOGFLARE_PUBLIC_ACCESS_TOKEN",
|
|
"LOGFLARE_PRIVATE_ACCESS_TOKEN",
|
|
"LOGFLARE_URL",
|
|
"SENTRY_ORG",
|
|
"SENTRY_PROJECT",
|
|
"SENTRY_AUTH_TOKEN",
|
|
"NEXT_PUBLIC_SENTRY_DSN",
|
|
"AWS_BEDROCK_PROFILE",
|
|
"AWS_BEDROCK_ROLE_ARN",
|
|
"AWS_ACCESS_KEY_ID",
|
|
"AWS_SECRET_ACCESS_KEY",
|
|
"FORCE_ASSET_CDN",
|
|
"ASSET_CDN_S3_ENDPOINT",
|
|
"SITE_NAME",
|
|
"VERCEL_URL",
|
|
"IS_BRAINTRUST_PUSH",
|
|
"GITHUB_HEAD_REF",
|
|
"GITHUB_REF_NAME",
|
|
"GITHUB_PR_NUMBER",
|
|
"IS_THROTTLED",
|
|
"AI_PRO_MODEL",
|
|
"AI_NORMAL_MODEL",
|
|
"SUPPORT_SUPABASE_SECRET_KEY",
|
|
"STATUSPAGE_API_KEY",
|
|
"STATUSPAGE_PAGE_ID",
|
|
"INCIDENT_IO_API_KEY",
|
|
"LIVE_SUPABASE_SECRET_KEY",
|
|
// Selects the build mode for the studio's `build`/`start` scripts
|
|
// (e.g. e2e sets `MODE=test`). Listed so turbo invalidates the
|
|
// cache when it changes — without this, switching between test and
|
|
// production builds reuses a stale cached output.
|
|
"MODE",
|
|
// Read by scripts/serve.js (the Node host for `pnpm start`).
|
|
// Declared here so the studio-package turbo env lint rule passes
|
|
// even though turbo doesn't directly drive `start`.
|
|
"PORT",
|
|
// Gates the TanStack vs Next path in api/server.js, vercel.ts,
|
|
// and scripts/dispatch.js (the dev/build/start dispatcher).
|
|
"STUDIO_FRAMEWORK",
|
|
// Vite's built-in `import.meta.env.SSR` flag (used in ConnectStepsSection
|
|
// to gate Vite-only `import.meta.glob`). Not a real process env var
|
|
// but turbo's `no-undeclared-env-vars` lint flags any `env.SSR` access.
|
|
"SSR",
|
|
],
|
|
"passThroughEnv": [
|
|
"CURRENT_CLI_VERSION",
|
|
"VERCEL_GIT_COMMIT_REF",
|
|
"VERCEL_GIT_COMMIT_SHA",
|
|
"SNIPPETS_MANAGEMENT_FOLDER",
|
|
"EDGE_FUNCTIONS_MANAGEMENT_FOLDER",
|
|
"S3_PROTOCOL_ACCESS_KEY_ID",
|
|
"S3_PROTOCOL_ACCESS_KEY_SECRET",
|
|
],
|
|
"outputs": [
|
|
".next/**",
|
|
"!.next/cache/**",
|
|
"!.next/dev/**/*",
|
|
"dist/**",
|
|
],
|
|
},
|
|
},
|
|
}
|