mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-29 11:07:18 -04:00
* feat(usage): add Source, APIKeyID, APIKeyName columns to UsageRecord Adds three additive columns plus UsageSource* constants. The columns are auto-migrated by InitDB. APIKeyID is a nullable foreign reference to UserAPIKey.ID; APIKeyName is snapshotted on each row so revoked keys keep showing their name in history. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(usage): backfill Source on pre-feature usage rows InitDB now classifies any pre-existing usage_record with an empty source: 'legacy-api-key' user -> legacy, everything else -> web. The backfill is idempotent (only touches NULL/empty rows). Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(usage): add GetUserUsageBySource aggregator Groups by (bucket, source, api_key_id, api_key_name). Filters out legacy by default. Returns both per-bucket detail and roll-ups (by_source, by_key sorted desc and capped at 200, grand_total). The MAX(created_at) projection is iterated via Rows().Scan into a string column and parsed manually because the SQLite driver surfaces the aggregated timestamp as a string, which database/sql refuses to scan directly into time.Time. Postgres returns a real timestamp; the same string path handles its RFC3339 form too. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(usage): log Rows() errors and assert LastUsed in tests Adds rows.Err() and Rows() open-failure logging in computeSourceTotals so silent data drops surface in logs. Logs on parseLastUsedString format misses for the same reason. Strengthens the snapshot-survival test to assert LastUsed is a recent timestamp, locking the SQLite time-string parser behaviour. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(usage): add admin GetAllUsageBySource with filters and truncation Optional user_id and api_key_id filters (composed with AND). Legacy bucket is included for admin callers. truncated=true when more than 200 distinct keys would be in the by_key roll-up. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(auth): plumb auth_source and auth_apikey through Echo context tryAuthenticate now sets auth_source on every successful branch (web for session/Bearer-session, apikey for Bearer-key/x-api-key/ token-cookie, legacy for legacy env key match). For named-key branches it also stores the resolved *UserAPIKey under auth_apikey so downstream middlewares can snapshot id+name without re-validating. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(auth): expand tryAuthenticate godoc and cover Bearer-session branch Documents all three context-keys side effects (auth_source, auth_apikey, _auth_session) plus the split of responsibilities with the parent Middleware. Adds a test for the Bearer-as-session-token classification so future regressions there fail loudly. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(usage): UsageMiddleware records source + snapshots key name Reads auth_source and auth_apikey from the Echo context (set by auth.Middleware in the previous task). Snapshots UserAPIKey.ID and Name onto each row so revoked keys remain readable in history. Falls back to source=web when no auth_source is set (auth disabled or unrecognised path). Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(usage): add /api/auth/usage/sources and admin variant Self endpoint filters legacy server-side; admin endpoint includes legacy and accepts user_id + api_key_id filters. Response includes buckets, totals.{by_source, by_key, grand_total}, and a truncated flag set when the per-key roll-up was capped at 200. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(routes): mark test mirror handlers as keep-in-sync with production The newTestAuthApp helper duplicates production route handlers inline because it cannot use RegisterAuthRoutes (which requires a *application.Application). Naming the source path on each mirror makes the drift contract explicit for future maintainers. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ui): add usageApi.getMySources/getAdminSources + i18n strings Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ui): add Sources tab skeleton with data fetch Adds Usage page tab that fetches /api/auth/usage/sources (or the admin variant). Renders raw totals plus a placeholder key list; real visualisations land in subsequent commits. Restructures the existing tab button block so Models and Sources are visible to non-admins (Users remains admin-only). Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ui): source mix ribbon + searchable/sortable sources table Replaces the SourcesTab placeholder rendering with two reusable components: SourceMixRibbon (one segmented bar per source class) and SourcesTable (search + sort + revoked-key dim). Pulls the current API key list to detect revoked keys. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(ui): skip revoked-key detection until the key list is known existingKeyIds defaulted to an empty Set, which made every live api_key row render as (revoked) during the brief window before apiKeysApi.list() resolved, and permanently after a fetch failure. Use null as the unknown state and suppress the revoked badge until the parent provides a real Set. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(ui): top-N stacked time chart and drill-in chip for Sources tab Top 7 sources by total tokens get distinct colours; the rest roll up into 'Other'. Clicking a row in the SourcesTable dims everything except that series in the chart; the chip is the canonical clear. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * docs(usage): document per-API-key Sources tab and endpoints Extends features/authentication.md Usage Tracking section with: - A 'Sources' tab description and source-class taxonomy - Endpoint documentation for /api/auth/usage/sources and the admin variant - Response shape example with by_source / by_key / grand_total - Migration note about pre-feature row backfill Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * fix(usage): silence errcheck on deferred rows.Close CI errcheck flagged the bare 'defer rows.Close()' in computeSourceTotals. Wrap in a closure that discards the close error explicitly; an error here is non-actionable since we have already drained the rows and logged any iteration failure. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * refactor(usage): bound batcher intake and add Shutdown/FlushNow hooks The pre-existing usage batcher had no cap on its add() path; the usageMaxPending=5000 constant only guarded the re-queue path after a failed write, leaving memory growth unbounded if the DB fell behind. This commit: - Adds the cap to add() so saturation drops new records (rate-limited warn at 1/1024) instead of growing unbounded. - Raises usageMaxPending to 50000 to absorb realistic inference bursts. - Replaces the package-level batcher global with a mutex-guarded pair plus a currentBatcher() accessor so Init / Shutdown cycles are race-free. - Adds ShutdownUsageRecorder() for graceful drain on process exit (not yet wired into app shutdown, just published). - Adds FlushNow() for deterministic tests; the middleware suite no longer needs 6s sleeps per spec and now runs in ~50ms instead of 18s. - Re-queue on failed flush is now cap-aware: prepends as much of the failed batch as fits alongside concurrent arrivals, instead of dropping the whole batch when full. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(usage): drain usage batcher on graceful shutdown Registers ShutdownUsageRecorder with the existing signals.RegisterGracefulTerminationHandler so SIGINT/SIGTERM synchronously flushes any in-memory usage records before the process exits. Without this, up to one flush interval (5s) of recorded usage was lost when LocalAI restarted. Refs: #9862 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
141 lines
4.2 KiB
Go
141 lines
4.2 KiB
Go
//go:build auth
|
|
|
|
package middleware_test
|
|
|
|
import (
|
|
"bytes"
|
|
"encoding/json"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
|
|
"github.com/labstack/echo/v4"
|
|
"github.com/mudler/LocalAI/core/http/auth"
|
|
"github.com/mudler/LocalAI/core/http/middleware"
|
|
. "github.com/onsi/ginkgo/v2"
|
|
. "github.com/onsi/gomega"
|
|
"gorm.io/gorm"
|
|
)
|
|
|
|
// testAuthDB returns a fresh in-memory SQLite auth DB.
|
|
func testAuthDB() *gorm.DB {
|
|
db, err := auth.InitDB(":memory:")
|
|
if err != nil {
|
|
panic(err)
|
|
}
|
|
return db
|
|
}
|
|
|
|
var _ = Describe("UsageMiddleware", func() {
|
|
var (
|
|
e *echo.Echo
|
|
db *gorm.DB
|
|
)
|
|
|
|
BeforeEach(func() {
|
|
db = testAuthDB()
|
|
e = echo.New()
|
|
middleware.InitUsageRecorder(db)
|
|
})
|
|
|
|
AfterEach(func() {
|
|
middleware.ShutdownUsageRecorder()
|
|
})
|
|
|
|
okHandler := func(c echo.Context) error {
|
|
body, _ := json.Marshal(map[string]any{
|
|
"model": "gpt-4",
|
|
"usage": map[string]int{
|
|
"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15,
|
|
},
|
|
})
|
|
c.Response().Header().Set("Content-Type", "application/json")
|
|
c.Response().WriteHeader(http.StatusOK)
|
|
_, _ = c.Response().Write(body)
|
|
return nil
|
|
}
|
|
|
|
// FlushNow drains pending records synchronously, replacing the 6s sleep
|
|
// that was previously needed to wait for the batcher's ticker.
|
|
flush := middleware.FlushNow
|
|
|
|
It("records source=web when auth_source is web", func() {
|
|
e.POST("/v1/chat/completions", okHandler, func(next echo.HandlerFunc) echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
c.Set("auth_user", &auth.User{ID: "alice", Name: "Alice"})
|
|
c.Set("auth_source", auth.UsageSourceWeb)
|
|
return next(c)
|
|
}
|
|
}, middleware.UsageMiddleware(db))
|
|
|
|
req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewReader([]byte(`{}`)))
|
|
e.ServeHTTP(httptest.NewRecorder(), req)
|
|
flush()
|
|
|
|
var rec auth.UsageRecord
|
|
Expect(db.Where("user_id = ?", "alice").First(&rec).Error).To(Succeed())
|
|
Expect(rec.Source).To(Equal(auth.UsageSourceWeb))
|
|
Expect(rec.APIKeyID).To(BeNil())
|
|
Expect(rec.APIKeyName).To(BeEmpty())
|
|
})
|
|
|
|
It("records source=apikey with snapshotted name when auth_apikey is set", func() {
|
|
e.POST("/v1/chat/completions", okHandler, func(next echo.HandlerFunc) echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
c.Set("auth_user", &auth.User{ID: "alice", Name: "Alice"})
|
|
c.Set("auth_source", auth.UsageSourceAPIKey)
|
|
c.Set("auth_apikey", &auth.UserAPIKey{ID: "key-1", Name: "ci-runner"})
|
|
return next(c)
|
|
}
|
|
}, middleware.UsageMiddleware(db))
|
|
|
|
req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewReader([]byte(`{}`)))
|
|
e.ServeHTTP(httptest.NewRecorder(), req)
|
|
flush()
|
|
|
|
var rec auth.UsageRecord
|
|
Expect(db.Where("user_id = ?", "alice").First(&rec).Error).To(Succeed())
|
|
Expect(rec.Source).To(Equal(auth.UsageSourceAPIKey))
|
|
Expect(rec.APIKeyID).ToNot(BeNil())
|
|
Expect(*rec.APIKeyID).To(Equal("key-1"))
|
|
Expect(rec.APIKeyName).To(Equal("ci-runner"))
|
|
})
|
|
|
|
It("FlushNow drains pending records synchronously", func() {
|
|
e.POST("/v1/chat/completions", okHandler, func(next echo.HandlerFunc) echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
c.Set("auth_user", &auth.User{ID: "carol", Name: "Carol"})
|
|
c.Set("auth_source", auth.UsageSourceWeb)
|
|
return next(c)
|
|
}
|
|
}, middleware.UsageMiddleware(db))
|
|
|
|
req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewReader([]byte(`{}`)))
|
|
e.ServeHTTP(httptest.NewRecorder(), req)
|
|
|
|
// No sleep: FlushNow should drain immediately.
|
|
middleware.FlushNow()
|
|
|
|
var rec auth.UsageRecord
|
|
Expect(db.Where("user_id = ?", "carol").First(&rec).Error).To(Succeed())
|
|
Expect(rec.Source).To(Equal(auth.UsageSourceWeb))
|
|
})
|
|
|
|
It("falls back to source=web when auth_source is empty", func() {
|
|
e.POST("/v1/chat/completions", okHandler, func(next echo.HandlerFunc) echo.HandlerFunc {
|
|
return func(c echo.Context) error {
|
|
c.Set("auth_user", &auth.User{ID: "alice", Name: "Alice"})
|
|
// no auth_source set
|
|
return next(c)
|
|
}
|
|
}, middleware.UsageMiddleware(db))
|
|
|
|
req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewReader([]byte(`{}`)))
|
|
e.ServeHTTP(httptest.NewRecorder(), req)
|
|
flush()
|
|
|
|
var rec auth.UsageRecord
|
|
Expect(db.Where("user_id = ?", "alice").First(&rec).Error).To(Succeed())
|
|
Expect(rec.Source).To(Equal(auth.UsageSourceWeb))
|
|
})
|
|
})
|