mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-13 06:45:26 -04:00
The tunnel, the fence, the registry and the relay were all built and none of them carried a byte: every dial from the frontend still went to the address a worker registered. This is where that stops. One WorkerDialer resolves where a worker's tunnel is held, opens a stream on it locally or relays through the owning replica, and hands back a conn past both handshakes; gRPC, the file stager's HTTP client and the log-streaming WebSocket are all pointed at it. A worker's address stops being somewhere to connect to and becomes the name of which backend process a stream is for. It still appears in URLs, logs and errors, because that is what identifies the process; what it no longer decides is where the bytes go. Nothing falls back to dialling it. BackendClientFactory now has exactly one method, NewClientForNode, and returns an error where there is no way to reach the worker. The direct-dial constructor was removed rather than kept beside it, because leaving one on the interface keeps the bypass one word away from every call site that holds an address, which is all of them. The second construction path is closed too. DistributedModelStore built remote models with a nil client, and pkg/model.Model.GRPC then dialled the raw address lazily on first use - reached in production by ShutdownModel's Free and by the backend monitor's Status. Those models now carry the tunnel-backed client, and a model that cannot be given one is logged and not listed. Four conditions stay unmixable, and one path produces absence: the dialer answers ErrNoConnection only where Owner's liveness join did. A peer that will not answer, a stale ownership row, a worker's own refusal and a missing relay path are each reported as themselves. This matters because nodes ACTS on absence, and the collapse would have it reclaim the models of a worker that is connected and busy. That is not hypothetical. Writing the mutation for it exposed the bug in this change's own first draft: probeHealth returned bare false when it could not build a client, and tryWarmPath deletes the replica row on a false probe. A frontend whose dialer broke would have emptied node_models for the whole deployment while every model kept running. probeHealth now returns alive and probed separately, the reconciler gets a ProbeUnknown outcome that neither advances nor clears a failure streak, and the health monitor skips rather than counting a miss. Task 5 left the relay's open timeout at a fixed 15s and said so: no operator has the information to set it, because the number that matters is the original client's remaining budget, which is invisible on the relay side. The dialer has that budget, so it now states it in the relay request frame and the owner takes the smaller of the two. It can only shorten - a patient client must not be able to park a relay goroutine and a stream slot on a worker that stopped accepting. Zero is written as no budget at all, since on the far side the number zero is a caller with nothing left and would refuse healthy traffic. Seven mutations, each reddening a named spec: peer-unreachable as absence; the local-failure guard dropped; max instead of min on the budget; the nil-client model restored; ProbeUnknown falling through to the reaper; OwnerRow instead of Owner; probed collapsed into alive. The first budget spec passed for the wrong reason - a handshake deadline, not the relay - and was replaced by three that each assert one link, including one where the spec plays the owning replica and reads the budget out of the frame instead of inferring it from a clock. Assisted-by: Claude Opus 5 [claude-code] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
800 lines
32 KiB
Go
800 lines
32 KiB
Go
package http
|
|
|
|
import (
|
|
"context"
|
|
"embed"
|
|
"errors"
|
|
"fmt"
|
|
"io/fs"
|
|
"math"
|
|
"mime"
|
|
"net"
|
|
"net/http"
|
|
"os"
|
|
"path/filepath"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/labstack/echo/v4"
|
|
"github.com/labstack/echo/v4/middleware"
|
|
|
|
"github.com/mudler/LocalAI/pkg/model"
|
|
|
|
corebackend "github.com/mudler/LocalAI/core/backend"
|
|
"github.com/mudler/LocalAI/core/http/auth"
|
|
"github.com/mudler/LocalAI/core/http/endpoints/localai"
|
|
|
|
httpMiddleware "github.com/mudler/LocalAI/core/http/middleware"
|
|
"github.com/mudler/LocalAI/core/http/routes"
|
|
|
|
"github.com/mudler/LocalAI/core/application"
|
|
"github.com/mudler/LocalAI/core/schema"
|
|
clustersvc "github.com/mudler/LocalAI/core/services/cluster"
|
|
"github.com/mudler/LocalAI/core/services/distributed"
|
|
"github.com/mudler/LocalAI/core/services/finetune"
|
|
"github.com/mudler/LocalAI/core/services/galleryop"
|
|
"github.com/mudler/LocalAI/core/services/messaging"
|
|
"github.com/mudler/LocalAI/core/services/nodes"
|
|
"github.com/mudler/LocalAI/core/services/quantization"
|
|
|
|
"github.com/mudler/xlog"
|
|
)
|
|
|
|
// Embed a directory
|
|
//
|
|
//go:embed static/*
|
|
var embedDirStatic embed.FS
|
|
|
|
// Embed React UI build output
|
|
//
|
|
//go:embed react-ui/dist/*
|
|
var reactUI embed.FS
|
|
|
|
var quietPaths = []string{"/api/operations", "/api/resources", "/healthz", "/readyz"}
|
|
|
|
// immutableAssetCacheControl is the Cache-Control served for content-hashed
|
|
// build output. The filename changes whenever the content does, so a one-year
|
|
// TTL plus `immutable` is safe and removes both the re-download and the
|
|
// conditional revalidation round-trip.
|
|
const immutableAssetCacheControl = "public, max-age=31536000, immutable"
|
|
|
|
func defaultBodyLimitSkipper(c echo.Context) bool {
|
|
// Remeshing accepts generated GLBs that routinely exceed the default
|
|
// upload limit. The route has its own tighter, format-specific limit.
|
|
return c.Request().Method == http.MethodPost && c.Path() == "/3d/remesh"
|
|
}
|
|
|
|
// applyModelLoadCooldown maps a ModelLoadCooldownError anywhere in err's chain
|
|
// to HTTP 503 with a Retry-After header (whole seconds, floor 1), so a client
|
|
// polling a model whose load recently failed backs off instead of triggering a
|
|
// fresh backend start. If err is not a cooldown error, code is returned as-is.
|
|
func applyModelLoadCooldown(err error, code int, c echo.Context) int {
|
|
var coolErr *model.ModelLoadCooldownError
|
|
if !errors.As(err, &coolErr) {
|
|
return code
|
|
}
|
|
secs := int(math.Ceil(coolErr.RetryAfter.Seconds()))
|
|
if secs < 1 {
|
|
secs = 1
|
|
}
|
|
c.Response().Header().Set("Retry-After", strconv.Itoa(secs))
|
|
return http.StatusServiceUnavailable
|
|
}
|
|
|
|
func applyBackendAdmission(err error, code int, c echo.Context) int {
|
|
var capacityErr *corebackend.BackendAdmissionError
|
|
if !errors.As(err, &capacityErr) {
|
|
return code
|
|
}
|
|
c.Response().Header().Set("Retry-After", strconv.Itoa(int(capacityErr.RetryAfter.Seconds())))
|
|
return http.StatusServiceUnavailable
|
|
}
|
|
|
|
// respondModelLoading answers a request whose model is still cold-loading with
|
|
// 503, a Retry-After header and the live `loading` object, reporting true when
|
|
// it handled the error.
|
|
//
|
|
// The distinction from applyModelLoadCooldown matters: a cooldown means "the
|
|
// last load FAILED, back off", this means "the load is progressing, here is how
|
|
// far it got". Both used to look like the same anonymous error, so an operator
|
|
// watching a 35 GB model stage normally onto a new worker saw only failures.
|
|
func respondModelLoading(err error, c echo.Context) bool {
|
|
var loadErr *nodes.ModelLoadingError
|
|
if !errors.As(err, &loadErr) {
|
|
return false
|
|
}
|
|
setModelLoadingRetryAfter(loadErr, c)
|
|
status := loadErr.Status
|
|
if jerr := c.JSON(http.StatusServiceUnavailable, schema.ModelLoadingResponse{
|
|
Error: &schema.APIError{
|
|
Message: loadErr.Error(),
|
|
Code: "model_loading",
|
|
Type: "model_loading",
|
|
},
|
|
Loading: &status,
|
|
}); jerr != nil {
|
|
xlog.Debug("Failed to write model-loading response", "error", jerr)
|
|
}
|
|
return true
|
|
}
|
|
|
|
// applyModelLoading is the body-less half of respondModelLoading, for the
|
|
// opaque-errors handler: status and Retry-After only.
|
|
func applyModelLoading(err error, code int, c echo.Context) int {
|
|
var loadErr *nodes.ModelLoadingError
|
|
if !errors.As(err, &loadErr) {
|
|
return code
|
|
}
|
|
setModelLoadingRetryAfter(loadErr, c)
|
|
return http.StatusServiceUnavailable
|
|
}
|
|
|
|
func setModelLoadingRetryAfter(loadErr *nodes.ModelLoadingError, c echo.Context) {
|
|
secs := int(math.Ceil(loadErr.RetryAfter.Seconds()))
|
|
if secs < 1 {
|
|
secs = 1
|
|
}
|
|
c.Response().Header().Set("Retry-After", strconv.Itoa(secs))
|
|
}
|
|
|
|
// @title LocalAI API
|
|
// @version 2.0.0
|
|
// @description The LocalAI Rest API.
|
|
// @termsOfService
|
|
// @contact.name LocalAI
|
|
// @contact.url https://localai.io
|
|
// @license.name MIT
|
|
// @license.url https://raw.githubusercontent.com/mudler/LocalAI/master/LICENSE
|
|
// @BasePath /
|
|
// @schemes http https
|
|
// @securityDefinitions.apikey BearerAuth
|
|
// @in header
|
|
// @name Authorization
|
|
// @tag.name inference
|
|
// @tag.description Chat completions, text completions, edits, and responses (OpenAI-compatible)
|
|
// @tag.name embeddings
|
|
// @tag.description Vector embeddings (OpenAI-compatible)
|
|
// @tag.name audio
|
|
// @tag.description Text-to-speech, transcription, voice activity detection, sound generation
|
|
// @tag.name images
|
|
// @tag.description Image generation and inpainting
|
|
// @tag.name video
|
|
// @tag.description Video generation from prompts
|
|
// @tag.name detection
|
|
// @tag.description Object detection in images
|
|
// @tag.name tokenize
|
|
// @tag.description Tokenization and token metrics
|
|
// @tag.name models
|
|
// @tag.description Model gallery browsing, installation, deletion, and listing
|
|
// @tag.name backends
|
|
// @tag.description Backend gallery browsing, installation, deletion, and listing
|
|
// @tag.name config
|
|
// @tag.description Model configuration metadata, autocomplete, PATCH updates, VRAM estimation
|
|
// @tag.name monitoring
|
|
// @tag.description Prometheus metrics, backend status, system information
|
|
// @tag.name mcp
|
|
// @tag.description Model Context Protocol — tool-augmented chat with MCP servers
|
|
// @tag.name agent-jobs
|
|
// @tag.description Agent task and job management
|
|
// @tag.name p2p
|
|
// @tag.description Peer-to-peer networking nodes and tokens
|
|
// @tag.name rerank
|
|
// @tag.description Document reranking
|
|
// @tag.name instructions
|
|
// @tag.description API instruction discovery — browse instruction areas and get endpoint guides
|
|
|
|
func API(application *application.Application) (*echo.Echo, error) {
|
|
e := echo.New()
|
|
|
|
// Set body limit
|
|
if application.ApplicationConfig().UploadLimitMB > 0 {
|
|
e.Use(middleware.BodyLimitWithConfig(middleware.BodyLimitConfig{
|
|
Limit: fmt.Sprintf("%dM", application.ApplicationConfig().UploadLimitMB),
|
|
Skipper: defaultBodyLimitSkipper,
|
|
}))
|
|
}
|
|
|
|
// SPA fallback handler, set later when React UI is available
|
|
var spaFallback func(echo.Context) error
|
|
|
|
// Set error handler
|
|
if !application.ApplicationConfig().OpaqueErrors {
|
|
e.HTTPErrorHandler = func(err error, c echo.Context) {
|
|
if respondModelLoading(err, c) {
|
|
return
|
|
}
|
|
code := http.StatusInternalServerError
|
|
var he *echo.HTTPError
|
|
if errors.As(err, &he) {
|
|
code = he.Code
|
|
}
|
|
code = applyModelLoadCooldown(err, code, c)
|
|
code = applyBackendAdmission(err, code, c)
|
|
|
|
// Handle 404 errors: serve React SPA for HTML requests, JSON otherwise
|
|
if code == http.StatusNotFound {
|
|
if spaFallback != nil {
|
|
accept := c.Request().Header.Get("Accept")
|
|
contentType := c.Request().Header.Get("Content-Type")
|
|
if strings.Contains(accept, "text/html") && !strings.Contains(contentType, "application/json") {
|
|
spaFallback(c)
|
|
return
|
|
}
|
|
}
|
|
notFoundHandler(c)
|
|
return
|
|
}
|
|
|
|
// Send custom error page
|
|
c.JSON(code, schema.ErrorResponse{
|
|
Error: &schema.APIError{Message: err.Error(), Code: code},
|
|
})
|
|
}
|
|
} else {
|
|
e.HTTPErrorHandler = func(err error, c echo.Context) {
|
|
code := http.StatusInternalServerError
|
|
var he *echo.HTTPError
|
|
if errors.As(err, &he) {
|
|
code = he.Code
|
|
}
|
|
code = applyModelLoadCooldown(err, code, c)
|
|
code = applyBackendAdmission(err, code, c)
|
|
// Opaque errors deliberately withhold the body, so a still-loading
|
|
// model gets the status and Retry-After but no progress detail.
|
|
code = applyModelLoading(err, code, c)
|
|
c.NoContent(code)
|
|
}
|
|
}
|
|
|
|
// Set renderer
|
|
e.Renderer = renderEngine()
|
|
|
|
// Hide banner
|
|
e.HideBanner = true
|
|
e.HidePort = true
|
|
|
|
// Middleware - StripPathPrefix must be registered early as it uses Rewrite which runs before routing
|
|
e.Pre(httpMiddleware.StripPathPrefix())
|
|
|
|
// Stamp the configured external base URL into each request context so
|
|
// middleware.BaseURL can treat it as authoritative for self-referential
|
|
// links. Registered as Pre so it runs before routing and handlers.
|
|
if extBaseURL := application.ApplicationConfig().ExternalBaseURL; extBaseURL != "" {
|
|
e.Pre(func(next echo.HandlerFunc) echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
c.Set("_external_base_url", extBaseURL)
|
|
return next(c)
|
|
}
|
|
})
|
|
}
|
|
|
|
e.Pre(middleware.RemoveTrailingSlash())
|
|
|
|
if application.ApplicationConfig().MachineTag != "" {
|
|
e.Use(func(next echo.HandlerFunc) echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
c.Response().Header().Set("Machine-Tag", application.ApplicationConfig().MachineTag)
|
|
return next(c)
|
|
}
|
|
})
|
|
}
|
|
|
|
// Security headers (CSP, X-Content-Type-Options, X-Frame-Options,
|
|
// Referrer-Policy). Set early so every response — including 404s and
|
|
// errors — picks them up.
|
|
e.Use(httpMiddleware.SecurityHeaders())
|
|
|
|
// Gzip responses. Registered before the tracing and handler middlewares so
|
|
// the response writer it installs sits underneath them: the trace buffer
|
|
// keeps capturing plaintext while the wire carries the compressed bytes.
|
|
if !application.ApplicationConfig().DisableHTTPCompression {
|
|
e.Use(httpMiddleware.Compression(application.ApplicationConfig().HTTPCompressionMinLength))
|
|
}
|
|
|
|
// Custom logger middleware using xlog
|
|
e.Use(func(next echo.HandlerFunc) echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
req := c.Request()
|
|
res := c.Response()
|
|
err := next(c)
|
|
|
|
// Echo's central HTTPErrorHandler runs *after* this middleware
|
|
// returns, so res.Status still reads the default 200 here when a
|
|
// handler returned an error without writing a response. Mirror
|
|
// echo.DefaultHTTPErrorHandler's status derivation so the access
|
|
// log reflects the status the client actually receives — without
|
|
// this, every silent handler error logs as 200.
|
|
status := res.Status
|
|
if err != nil && !res.Committed {
|
|
status = http.StatusInternalServerError
|
|
var he *echo.HTTPError
|
|
if errors.As(err, &he) {
|
|
status = he.Code
|
|
}
|
|
}
|
|
|
|
// Fix for #7989: Reduce log verbosity of Web UI polling, resources API, and health checks
|
|
// These paths are logged at DEBUG level (hidden by default) instead of INFO.
|
|
isQuietPath := false
|
|
for _, path := range quietPaths {
|
|
if req.URL.Path == path {
|
|
isQuietPath = true
|
|
break
|
|
}
|
|
}
|
|
|
|
if isQuietPath && status == 200 {
|
|
xlog.Debug("HTTP request", "method", req.Method, "path", req.URL.Path, "status", status)
|
|
} else {
|
|
xlog.Info("HTTP request", "method", req.Method, "path", req.URL.Path, "status", status)
|
|
}
|
|
return err
|
|
}
|
|
})
|
|
|
|
// Recover middleware
|
|
if !application.ApplicationConfig().Debug {
|
|
e.Use(middleware.Recover())
|
|
}
|
|
|
|
// Metrics middleware. The metric service was created in
|
|
// application.start() so the OTel global provider is set before any
|
|
// counter is registered (the routing-module billing recorder relies
|
|
// on this). We reuse that instance here rather than calling
|
|
// monitoring.NewLocalAIMetricsService a second time, which would
|
|
// create a second provider, second prometheus exporter, and orphan
|
|
// whichever instance lost the SetMeterProvider race.
|
|
if metricsService := application.MetricsService(); metricsService != nil {
|
|
e.Use(localai.LocalAIMetricsAPIMiddleware(metricsService))
|
|
e.Server.RegisterOnShutdown(func() {
|
|
_ = metricsService.Shutdown()
|
|
})
|
|
}
|
|
|
|
// Health Checks should always be exempt from auth, so register these first
|
|
routes.HealthRoutes(e, application.Ready)
|
|
|
|
// Build auth middleware: use the new auth.Middleware when auth is enabled or
|
|
// as a unified replacement for the legacy key-auth middleware.
|
|
authMiddleware := auth.Middleware(application.AuthDB(), application.ApplicationConfig())
|
|
|
|
// Favicon handler
|
|
e.GET("/favicon.svg", func(c echo.Context) error {
|
|
data, err := embedDirStatic.ReadFile("static/favicon.svg")
|
|
if err != nil {
|
|
return c.NoContent(http.StatusNotFound)
|
|
}
|
|
c.Response().Header().Set("Content-Type", "image/svg+xml")
|
|
return c.Blob(http.StatusOK, "image/svg+xml", data)
|
|
})
|
|
|
|
// Static files - use fs.Sub to create a filesystem rooted at "static"
|
|
staticFS, err := fs.Sub(embedDirStatic, "static")
|
|
if err != nil {
|
|
return nil, fmt.Errorf("failed to create static filesystem: %w", err)
|
|
}
|
|
e.StaticFS("/static", staticFS)
|
|
|
|
// Generated content directories
|
|
if application.ApplicationConfig().GeneratedContentDir != "" {
|
|
os.MkdirAll(application.ApplicationConfig().GeneratedContentDir, 0750)
|
|
audioPath := filepath.Join(application.ApplicationConfig().GeneratedContentDir, "audio")
|
|
imagePath := filepath.Join(application.ApplicationConfig().GeneratedContentDir, "images")
|
|
videoPath := filepath.Join(application.ApplicationConfig().GeneratedContentDir, "videos")
|
|
threeDPath := filepath.Join(application.ApplicationConfig().GeneratedContentDir, "3d")
|
|
|
|
os.MkdirAll(audioPath, 0750)
|
|
os.MkdirAll(imagePath, 0750)
|
|
os.MkdirAll(videoPath, 0750)
|
|
_ = os.MkdirAll(threeDPath, 0750)
|
|
|
|
// Go's built-in MIME table has no .glb entry and minimal containers
|
|
// ship no /etc/mime.types, so generated GLBs would otherwise be
|
|
// served as application/octet-stream.
|
|
_ = mime.AddExtensionType(".glb", "model/gltf-binary")
|
|
|
|
e.Static("/generated-audio", audioPath)
|
|
e.Static("/generated-images", imagePath)
|
|
e.Static("/generated-videos", videoPath)
|
|
e.Static("/generated-3d", threeDPath)
|
|
}
|
|
|
|
// Usage recording is initialised in application/startup.go and
|
|
// surfaced via application.StatsRecorder(); routes wire UsageMiddleware
|
|
// against that recorder regardless of auth state.
|
|
|
|
// Auth is applied to _all_ endpoints. Filtering out endpoints to bypass is
|
|
// the role of the exempt-path logic inside the middleware.
|
|
e.Use(authMiddleware)
|
|
|
|
// Feature and model access control (after auth middleware, before routes)
|
|
if application.AuthDB() != nil {
|
|
e.Use(auth.RequireRouteFeature(application.AuthDB()))
|
|
e.Use(auth.RequireModelAccess(application.AuthDB()))
|
|
e.Use(auth.RequireQuota(application.AuthDB()))
|
|
}
|
|
|
|
// CORS middleware. When CORS=true the operator must also specify the
|
|
// allowed origins; an empty allowlist would otherwise let Echo fall back
|
|
// to AllowOrigins=["*"], which is almost never what someone enabling
|
|
// "strict CORS" intended.
|
|
if application.ApplicationConfig().CORS {
|
|
if application.ApplicationConfig().CORSAllowOrigins == "" {
|
|
xlog.Warn("LOCALAI_CORS=true but LOCALAI_CORS_ALLOW_ORIGINS is empty; refusing to register a wildcard CORS policy. Set the allowlist or unset LOCALAI_CORS.")
|
|
} else {
|
|
corsConfig := middleware.CORSConfig{
|
|
AllowOrigins: strings.Split(application.ApplicationConfig().CORSAllowOrigins, ","),
|
|
}
|
|
e.Use(middleware.CORSWithConfig(corsConfig))
|
|
}
|
|
} else {
|
|
e.Use(middleware.CORS())
|
|
}
|
|
|
|
// CSRF middleware (enabled by default, disable with LOCALAI_DISABLE_CSRF=true)
|
|
//
|
|
// Protection relies on Echo's Sec-Fetch-Site header check (supported by all
|
|
// modern browsers). The legacy cookie+token approach is removed because
|
|
// Echo's Sec-Fetch-Site short-circuit never sets the cookie, so the frontend
|
|
// could never read a token to send back.
|
|
if !application.ApplicationConfig().DisableCSRF {
|
|
xlog.Debug("Enabling CSRF middleware (Sec-Fetch-Site mode)")
|
|
e.Use(middleware.CSRFWithConfig(middleware.CSRFConfig{
|
|
Skipper: func(c echo.Context) bool {
|
|
// Skip CSRF for API clients using auth headers (may be cross-origin)
|
|
if c.Request().Header.Get("Authorization") != "" {
|
|
return true
|
|
}
|
|
if c.Request().Header.Get("x-api-key") != "" || c.Request().Header.Get("xi-api-key") != "" {
|
|
return true
|
|
}
|
|
// Skip when Sec-Fetch-Site header is absent (older browsers, reverse
|
|
// proxies that strip the header). The SameSite=Lax cookie attribute
|
|
// provides baseline CSRF protection for these clients.
|
|
if c.Request().Header.Get("Sec-Fetch-Site") == "" {
|
|
return true
|
|
}
|
|
return false
|
|
},
|
|
// Allow same-site requests (subdomains / different ports) in addition
|
|
// to same-origin which Echo already permits by default.
|
|
AllowSecFetchSiteFunc: func(c echo.Context) (bool, error) {
|
|
secFetchSite := c.Request().Header.Get("Sec-Fetch-Site")
|
|
if secFetchSite == "same-site" {
|
|
return true, nil
|
|
}
|
|
// cross-site: block
|
|
return false, nil
|
|
},
|
|
}))
|
|
}
|
|
|
|
// Admin middleware: enforces admin role when auth is enabled, no-op otherwise
|
|
var adminMiddleware echo.MiddlewareFunc
|
|
if application.AuthDB() != nil {
|
|
adminMiddleware = auth.RequireAdmin()
|
|
} else {
|
|
adminMiddleware = auth.NoopMiddleware()
|
|
}
|
|
|
|
// Feature middlewares: per-feature access control
|
|
agentsMw := auth.RequireFeature(application.AuthDB(), auth.FeatureAgents)
|
|
skillsMw := auth.RequireFeature(application.AuthDB(), auth.FeatureSkills)
|
|
collectionsMw := auth.RequireFeature(application.AuthDB(), auth.FeatureCollections)
|
|
mcpJobsMw := auth.RequireFeature(application.AuthDB(), auth.FeatureMCPJobs)
|
|
|
|
requestExtractor := httpMiddleware.NewRequestExtractor(application.ModelConfigLoader(), application.ModelLoader(), application.ApplicationConfig())
|
|
|
|
// Register auth routes (login, callback, API keys, user management)
|
|
routes.RegisterAuthRoutes(e, application)
|
|
|
|
// Register routing-module usage endpoints. Unlike /api/auth/usage
|
|
// these go through the StatsRecorder and work in no-auth single-user
|
|
// mode by attributing requests to the synthetic "local" user.
|
|
routes.RegisterUsageRoutes(e, application)
|
|
routes.RegisterPIIRoutes(e, application)
|
|
routes.RegisterMiddlewareRoutes(e, application)
|
|
|
|
routes.RegisterElevenLabsRoutes(e, requestExtractor, application.ModelConfigLoader(), application.ModelLoader(), application.ApplicationConfig())
|
|
|
|
// Create opcache for tracking UI operations (used by both UI and LocalAI routes)
|
|
var opcache *galleryop.OpCache
|
|
if !application.ApplicationConfig().DisableWebUI {
|
|
opcache = galleryop.NewOpCache(application.GalleryService())
|
|
// In distributed mode, wire the NATS client + gallery store so this
|
|
// replica's OpCache stays in sync with peers — without this the
|
|
// /api/operations endpoint returns whatever this single replica
|
|
// happened to admit, and a load-balanced UI poll alternates between
|
|
// "operation visible" and "operation gone" between replicas.
|
|
if d := application.Distributed(); d != nil {
|
|
opcache.SetMessagingClient(d.Nats)
|
|
if d.DistStores != nil && d.DistStores.Gallery != nil {
|
|
opcache.SetGalleryStore(d.DistStores.Gallery)
|
|
}
|
|
if err := opcache.Start(application.ApplicationConfig().Context); err != nil {
|
|
xlog.Warn("OpCache distributed subscribe failed; running standalone", "error", err)
|
|
}
|
|
}
|
|
}
|
|
|
|
mcpMw := auth.RequireFeature(application.AuthDB(), auth.FeatureMCP)
|
|
routes.RegisterLocalAIRoutes(e, requestExtractor, application.ModelConfigLoader(), application.ModelLoader(), application.ApplicationConfig(), application.GalleryService(), opcache, application.TemplatesEvaluator(), application, adminMiddleware, mcpJobsMw, mcpMw)
|
|
routes.RegisterAgentPoolRoutes(e, application, agentsMw, skillsMw, collectionsMw)
|
|
// Fine-tuning routes
|
|
fineTuningMw := auth.RequireFeature(application.AuthDB(), auth.FeatureFineTuning)
|
|
// In distributed mode pass the shared NATS client + PostgreSQL store so
|
|
// fine-tune jobs stay consistent across replicas (the SyncedMap broadcasts
|
|
// mutations and hydrates from the DB); standalone passes nil for both.
|
|
var ftNats messaging.MessagingClient
|
|
var ftStore *distributed.FineTuneStore
|
|
if d := application.Distributed(); d != nil {
|
|
ftNats = d.Nats
|
|
if d.DistStores != nil && d.DistStores.FineTune != nil {
|
|
ftStore = d.DistStores.FineTune
|
|
}
|
|
}
|
|
ftService := finetune.NewFineTuneService(
|
|
application.ApplicationConfig(),
|
|
application.ModelLoader(),
|
|
application.ModelConfigLoader(),
|
|
ftNats,
|
|
ftStore,
|
|
)
|
|
routes.RegisterFineTuningRoutes(e, ftService, application.ApplicationConfig(), application, fineTuningMw)
|
|
|
|
// Quantization routes
|
|
quantizationMw := auth.RequireFeature(application.AuthDB(), auth.FeatureQuantization)
|
|
// In distributed mode pass the shared NATS client + PostgreSQL store so
|
|
// quantization jobs stay consistent across replicas (the SyncedMap broadcasts
|
|
// mutations and hydrates from the DB); standalone passes nil for both.
|
|
var quantNats messaging.MessagingClient
|
|
var quantStore *distributed.QuantStore
|
|
if d := application.Distributed(); d != nil {
|
|
quantNats = d.Nats
|
|
if d.DistStores != nil && d.DistStores.Quant != nil {
|
|
quantStore = d.DistStores.Quant
|
|
}
|
|
}
|
|
qService := quantization.NewQuantizationService(
|
|
application.ApplicationConfig(),
|
|
application.ModelLoader(),
|
|
application.ModelConfigLoader(),
|
|
quantNats,
|
|
quantStore,
|
|
)
|
|
routes.RegisterQuantizationRoutes(e, qService, application.ApplicationConfig(), application, quantizationMw)
|
|
|
|
// Node management routes (distributed mode)
|
|
distCfg := application.ApplicationConfig().Distributed
|
|
var registry *nodes.NodeRegistry
|
|
var remoteUnloader nodes.NodeCommandSender
|
|
// How the admin log-proxy routes reach a worker's own HTTP server. Left nil
|
|
// outside distributed mode, where there are no workers and no tunnels; the
|
|
// routes then refuse rather than dialling an address directly.
|
|
var workerHTTPDialFor nodes.WorkerNetDialerFor
|
|
if d := application.Distributed(); d != nil {
|
|
registry = d.Registry
|
|
if d.Router != nil {
|
|
remoteUnloader = d.Router.Unloader()
|
|
}
|
|
if d.WorkerDialer != nil {
|
|
workerHTTPDialFor = func(nodeID string) func(ctx context.Context, network, addr string) (net.Conn, error) {
|
|
return d.WorkerDialer.DialerFor(nodeID, clustersvc.StreamTagHTTP)
|
|
}
|
|
}
|
|
}
|
|
natsCfg := distCfg.NatsAuthConfig()
|
|
routes.RegisterNodeSelfServiceRoutes(e, registry, distCfg.RegistrationToken, distCfg.AutoApproveNodes, application.AuthDB(), application.ApplicationConfig().Auth.APIKeyHMACSecret, natsCfg)
|
|
routes.RegisterNodeAdminRoutes(e, registry, remoteUnloader, application.GalleryService(), opcache, application.ApplicationConfig(), adminMiddleware, application.AuthDB(), application.ApplicationConfig().Auth.APIKeyHMACSecret, application.ApplicationConfig().Distributed.RegistrationToken, natsCfg, workerHTTPDialFor)
|
|
|
|
// Replica-to-replica peer link. Registered only in distributed mode: in
|
|
// single-node mode there are no peers, and the route authenticates with the
|
|
// registration token, so publishing it unconditionally would put a
|
|
// multiplexer on every single-binary install.
|
|
if d := application.Distributed(); d != nil && d.PeerSessions != nil {
|
|
if distCfg.RegistrationToken == "" {
|
|
// The handler fails closed on an empty token, which is right and
|
|
// invisible: without this line an operator sees only 401s on a
|
|
// route they never configured, and nothing connecting them to the
|
|
// token they did not set.
|
|
xlog.Warn("Replica peer link will refuse every dial: no registration token is configured",
|
|
"route", clustersvc.PeerPath, "knob", "LOCALAI_REGISTRATION_TOKEN")
|
|
}
|
|
routes.RegisterClusterRoutes(e, distCfg.RegistrationToken, d.PeerSessions.Accept)
|
|
}
|
|
|
|
// The worker tunnel, registered unconditionally. Both arguments are nil
|
|
// outside distributed mode and the handler refuses every dial then, which
|
|
// is what makes registering it always safe; what it buys is the
|
|
// route-coverage test walking the route in a plain single-binary
|
|
// application, and that test is what holds the rule that an unauthenticated
|
|
// dial is refused BEFORE the WebSocket upgrade.
|
|
var tunnels *clustersvc.TunnelRegistry
|
|
if d := application.Distributed(); d != nil {
|
|
tunnels = d.Tunnels
|
|
if distCfg.RegistrationToken == "" {
|
|
// A different warning from the peer link's, for the same missing
|
|
// knob, because what breaks is different. Tunnels themselves work
|
|
// without a registration token: each node is minted its own tunnel
|
|
// credential at registration whether or not one is configured. What
|
|
// is missing is the gate in FRONT of that. With no registration
|
|
// token, RegisterNodeEndpoint validates nothing, so anyone who can
|
|
// reach this frontend can register a node and be issued a tunnel
|
|
// credential for it.
|
|
//
|
|
// How far that gets them depends on the OTHER knob. With
|
|
// auto-approve on, the node is healthy at once and the credential
|
|
// works immediately. With it off, the node is pending, and the
|
|
// tunnel route refuses a pending node on every dial, so the
|
|
// credential is inert until an admin approves it and approval is
|
|
// the real gate. Worth stating precisely, because the same commit
|
|
// argues exactly this distinction three files away to justify
|
|
// minting for pending nodes at all.
|
|
//
|
|
// This warning replaced one that said the opposite, that tunnels
|
|
// would refuse every dial without this token. That was true while
|
|
// the tunnel authenticated against the registration token's own
|
|
// hash, and stopped being true when nodes got credentials of their
|
|
// own.
|
|
xlog.Warn("Node registration is unauthenticated, so any caller that can reach this frontend can register a worker and be issued a tunnel credential",
|
|
"route", clustersvc.ConnectPath, "knob", "LOCALAI_REGISTRATION_TOKEN")
|
|
}
|
|
}
|
|
routes.RegisterWorkerTunnelRoute(e, registry, tunnels)
|
|
|
|
// Distributed SSE routes (job progress + agent events via NATS)
|
|
if d := application.Distributed(); d != nil {
|
|
if d.Dispatcher != nil {
|
|
e.GET("/api/agent/jobs/:id/progress", d.Dispatcher.SSEHandler(), mcpJobsMw)
|
|
}
|
|
if d.AgentBridge != nil {
|
|
e.GET("/api/agents/:name/sse/distributed", d.AgentBridge.SSEHandler(), agentsMw)
|
|
}
|
|
}
|
|
|
|
routes.RegisterOpenAIRoutes(e, requestExtractor, application)
|
|
routes.RegisterAnthropicRoutes(e, requestExtractor, application)
|
|
routes.RegisterOpenResponsesRoutes(e, requestExtractor, application)
|
|
routes.RegisterOllamaRoutes(e, requestExtractor, application)
|
|
if application.ApplicationConfig().OllamaAPIRootEndpoint {
|
|
routes.RegisterOllamaRootEndpoint(e)
|
|
}
|
|
if !application.ApplicationConfig().DisableWebUI {
|
|
routes.RegisterUIAPIRoutes(e, application.ModelConfigLoader(), application.ModelLoader(), application.ApplicationConfig(), application.GalleryService(), opcache, application, adminMiddleware)
|
|
routes.RegisterUIRoutes(e, application.ModelConfigLoader(), application.ApplicationConfig(), application.GalleryService(), adminMiddleware)
|
|
|
|
// Serve React SPA from / with SPA fallback via 404 handler
|
|
reactFS, fsErr := fs.Sub(reactUI, "react-ui/dist")
|
|
if fsErr != nil {
|
|
xlog.Warn("React UI not available (build with 'make core/http/react-ui/dist')", "error", fsErr)
|
|
} else {
|
|
serveIndex := func(c echo.Context) error {
|
|
indexHTML, err := reactUI.ReadFile("react-ui/dist/index.html")
|
|
if err != nil {
|
|
return c.String(http.StatusNotFound, "React UI not built")
|
|
}
|
|
// index.html names the content-hashed bundles, so it must never
|
|
// be cached: a stale copy pins the browser to the previous
|
|
// deploy's assets.
|
|
c.Response().Header().Set("Cache-Control", "no-cache")
|
|
// Inject <base href> for reverse-proxy support; baseURL comes
|
|
// from attacker-controllable Host / X-Forwarded-Host headers.
|
|
baseURL := httpMiddleware.BaseURL(c)
|
|
if baseURL != "" {
|
|
baseTag := `<base href="` + httpMiddleware.SecureBaseHref(baseURL) + `" />`
|
|
indexHTML = []byte(strings.Replace(string(indexHTML), "<head>", "<head>\n "+baseTag, 1))
|
|
}
|
|
// <base href> only changes how relative URLs resolve; path-absolute
|
|
// URLs (those starting with `/`) still resolve against the origin
|
|
// and would bypass the reverse-proxy prefix. Rewrite the internal
|
|
// path-absolute references emitted by the build so the browser
|
|
// requests them through the proxy under the prefix.
|
|
//
|
|
// HTML-escape the prefix before interpolating it into attributes:
|
|
// BasePathPrefix already gates X-Forwarded-Prefix via
|
|
// SafeForwardedPrefix, but the validator only blocks open-redirect
|
|
// shapes (// prefix, backslashes, control chars), not attribute
|
|
// breakout characters like `"`. Escaping makes this resilient
|
|
// even if the validator ever loosens.
|
|
if prefix := httpMiddleware.BasePathPrefix(c); prefix != "/" {
|
|
safePrefix := httpMiddleware.SecureBaseHref(prefix)
|
|
html := string(indexHTML)
|
|
html = strings.ReplaceAll(html, `="/assets/`, `="`+safePrefix+`assets/`)
|
|
html = strings.ReplaceAll(html, `="/favicon.svg"`, `="`+safePrefix+`favicon.svg"`)
|
|
indexHTML = []byte(html)
|
|
}
|
|
return c.HTMLBlob(http.StatusOK, indexHTML)
|
|
}
|
|
|
|
// Enable SPA fallback in the 404 handler for client-side routing
|
|
spaFallback = serveIndex
|
|
|
|
// Serve React SPA at /app
|
|
e.GET("/app", serveIndex)
|
|
e.GET("/app/*", serveIndex)
|
|
|
|
// prefixRedirect performs a redirect that preserves X-Forwarded-Prefix
|
|
// for reverse-proxy support. The prefix is forgeable on misconfigured
|
|
// proxy chains, so reject anything that isn't a same-origin path.
|
|
prefixRedirect := func(c echo.Context, target string) error {
|
|
if prefix, ok := httpMiddleware.SafeForwardedPrefix(c.Request().Header.Get("X-Forwarded-Prefix")); ok {
|
|
target = strings.TrimSuffix(prefix, "/") + target
|
|
}
|
|
return c.Redirect(http.StatusMovedPermanently, target)
|
|
}
|
|
|
|
// Redirect / to /app
|
|
e.GET("/", func(c echo.Context) error {
|
|
return prefixRedirect(c, "/app")
|
|
})
|
|
|
|
// Backward compatibility: redirect /browse/* to /app/*
|
|
e.GET("/browse", func(c echo.Context) error {
|
|
return prefixRedirect(c, "/app")
|
|
})
|
|
e.GET("/browse/*", func(c echo.Context) error {
|
|
p := c.Param("*")
|
|
return prefixRedirect(c, "/app/"+p)
|
|
})
|
|
|
|
// Serve React static assets (JS, CSS, etc.) and i18n locale JSONs
|
|
// from the embedded React build. cacheControl is stamped on every
|
|
// hit so the browser can reuse the bytes instead of re-fetching
|
|
// ~1.8 MB of bundle on each navigation.
|
|
serveReactSubdir := func(subdir, cacheControl string) echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
p := subdir + "/" + c.Param("*")
|
|
f, err := reactFS.Open(p)
|
|
if err == nil {
|
|
defer f.Close()
|
|
stat, statErr := f.Stat()
|
|
if statErr == nil && !stat.IsDir() {
|
|
contentType := mime.TypeByExtension(filepath.Ext(p))
|
|
if contentType == "" {
|
|
contentType = echo.MIMEOctetStream
|
|
}
|
|
if cacheControl != "" {
|
|
c.Response().Header().Set("Cache-Control", cacheControl)
|
|
}
|
|
return c.Stream(http.StatusOK, contentType, f)
|
|
}
|
|
}
|
|
return echo.NewHTTPError(http.StatusNotFound)
|
|
}
|
|
}
|
|
// Vite content-hashes everything under /assets (Manage-DrwQK63f.js),
|
|
// so a given URL can never change content: cache it for a year and
|
|
// skip revalidation entirely. Locale JSONs keep stable names, so
|
|
// they only get a short TTL.
|
|
e.GET("/assets/*", serveReactSubdir("assets", immutableAssetCacheControl))
|
|
e.GET("/locales/*", serveReactSubdir("locales", "public, max-age=300"))
|
|
}
|
|
}
|
|
routes.RegisterJINARoutes(e, requestExtractor, application.ModelConfigLoader(), application.ModelLoader(), application.ApplicationConfig())
|
|
|
|
// Note: 404 handling is done via HTTPErrorHandler above, no need for catch-all route
|
|
|
|
// HTTP server timeouts.
|
|
//
|
|
// - ReadHeaderTimeout: bounds the slow-headers Slowloris case. 30s is
|
|
// enough for a real client on a poor connection but cuts off a
|
|
// drip-feeding attacker.
|
|
// - IdleTimeout: bounds idle keep-alive connections.
|
|
//
|
|
// We deliberately leave ReadTimeout and WriteTimeout at 0:
|
|
// - Request bodies can be multi-GB model/dataset uploads.
|
|
// - Chat-completion and SSE responses can stream for many minutes.
|
|
// Operators who need stricter limits should front the server with a
|
|
// reverse proxy that terminates slow clients per-request.
|
|
e.Server.ReadHeaderTimeout = 30 * time.Second
|
|
e.Server.IdleTimeout = 120 * time.Second
|
|
|
|
// Log startup message
|
|
e.Server.RegisterOnShutdown(func() {
|
|
xlog.Info("LocalAI API server shutting down")
|
|
})
|
|
|
|
return e, nil
|
|
}
|