Files
knox/internal/cmd/ingest.go
david 52c4d1f1e6 fix: derived-state determinism, error visibility, metrics naming, HTTP hardening
- rebuild: fold observations per fingerprint in a total order
  (hcl DESC, node_id DESC, id DESC) so two nodes with identical logs
  rebuild identical entries (was: arbitrary bare-column row, merge-order
  dependent)
- threads: CreateThreadCluster uses INSERT OR IGNORE + existing-id
  fallback — concurrent auto-threaders converge instead of hitting UNIQUE
- errors surfaced instead of swallowed: scanEntries returns rows.Err(),
  Stats() fails fast on query errors, AutoLinkThreadObservations /
  linkTemporalNeighbors / golden-thread linking propagate failures,
  AddThreadNote + LinkObservationToThread write under one tx,
  watch records session upsert failures
- gossip client: push checks HTTP status and reports errors (a broken
  push direction no longer looks like a silent success); gossip diff
  gets a 10s timeout so a dead peer cannot hang the CLI
- ingest: failed source sweeps (obsidian/browser/gitea) are logged,
  and -d's help text now states its file-only scope
- watch --quiet: fatal errors go to stderr instead of io.Discard
- main: cobra SilenceErrors/SilenceUsage (errors print once, usage is
  not dumped on runtime failures); knox mcp exits 0 on SIGINT/SIGTERM
- metrics: drop _total suffix from gauges (knox_observations,
  knox_entries, knox_projects, knox_sessions, knox_peers, knox_threads);
  _total stays on counters per Prometheus convention
- http: ReadHeaderTimeout + IdleTimeout on gossip, metrics, and web servers

tests: concurrent cluster-create idempotency, HCL-order rebuild fold
(both merge orders), push HTTP-error surfacing; full suite + -race pass,
gofmt clean
2026-09-17 02:28:08 -07:00

127 lines
3.4 KiB
Go

package cmd
import (
"fmt"
"log"
"path/filepath"
"github.com/david/knox/internal/db"
"github.com/david/knox/internal/ingest"
"github.com/david/knox/internal/watch"
"github.com/spf13/cobra"
)
func NewIngestCmd(kdb *db.KnoxDB) *cobra.Command {
var dirs []string
cmd := &cobra.Command{
Use: "ingest",
Short: "One-time full sweep of all sources into the knowledge index",
Run: func(cmd *cobra.Command, args []string) {
if len(dirs) == 0 {
dirs = defaultWatchDirs()
}
ingesters := []ingest.Ingester{
ingest.NewSessionDiffIngester(),
ingest.NewLogIngester(),
ingest.NewSkillsIngester(),
}
var totalNew, totalUpdated int
record := func(result *ingest.IngestResult) {
_, isNew, err := kdb.RecordObservation(db.ObservationRecord{
Fingerprint: result.Fingerprint,
SourceID: result.SourceID,
SourcePath: result.SourcePath,
Project: result.Project,
ContentType: result.ContentType,
Title: result.Title,
Summary: result.Summary,
CreatedAt: result.CreatedAt,
LineStart: result.LineStart,
LineEnd: result.LineEnd,
Confidence: result.Confidence,
IngesterVersion: result.IngesterVersion,
Trigger: "ingest",
Provenance: ingest.ProvenanceJSON(result.Provenance),
})
if err != nil {
log.Printf("[knox] db error: %v", err)
return
}
if isNew {
totalNew++
} else {
totalUpdated++
}
if result.SourceID == "opencode-session" {
sessionID, _ := result.Provenance["session_id"].(string)
if sessionID != "" {
kdb.UpsertSession(sessionID, result.Project, result.Title, "active")
}
}
}
for _, ing := range ingesters {
sid := ing.SourceID()
log.Printf("[knox] ingesting %s...", sid)
for _, dir := range dirs {
patterns := []string{
dir + "/*",
dir + "/*/SKILL.md",
}
for _, pattern := range patterns {
entries, _ := filepath.Glob(pattern)
for _, path := range entries {
if !watch.MatchesIngester(path, sid) {
continue
}
result, err := ing.Ingest(path)
if err != nil || result == nil {
continue
}
record(result)
}
}
}
}
// Non-file sources: obsidian vault, browser history, gitea
if vault, err := ingest.DetectObsidianVault(); err == nil {
log.Printf("[knox] ingesting obsidian...")
if results, err := ingest.NewObsidianIngester(vault).IngestAll(); err == nil {
for _, r := range results {
record(r)
}
} else {
log.Printf("[knox] obsidian ingest failed: %v", err)
}
}
log.Printf("[knox] ingesting browser-history...")
if results, err := ingest.NewBrowserHistoryIngester().IngestAll(); err == nil {
for _, r := range results {
record(r)
}
} else {
log.Printf("[knox] browser-history ingest failed: %v", err)
}
log.Printf("[knox] ingesting gitea...")
if results, err := ingest.NewGiteaIngester().IngestAll(); err == nil {
for _, r := range results {
record(r)
}
} else {
log.Printf("[knox] gitea ingest failed: %v", err)
}
fmt.Printf("\nIngest complete: %d new entries, %d updated\n", totalNew, totalUpdated)
},
}
cmd.Flags().StringSliceVarP(&dirs, "dir", "d", nil, "Directories to scan (default: opencode storage/log + skills)")
return cmd
}