bb852faa27
Implements the top findings from the codebase review, verified with tests and live CLI/MCP checks. **Gossip integrity** - Push validation: 4 MiB body cap, 1000-row batch cap; rows claiming the local node id (vector-poisoning), empty node ids, and negative HCLs rejected (internal/watch/gossip.go, internal/db/gossip.go) - Reconcile-on-pull: Run returns the pulled count, syncGossip rebuilds derived state when > 0 — entry-count comparison could never fire, so synced observations never materialized into searchable entries **Data-layer safety** - HLC resumed from MAX(hcl) at Open (hlc.SeekTo): a restart with a regressed wall clock cannot reissue values the (node_id, hcl) locator and pull cursors depend on - Writer serialization: _txlock=immediate DSN + SetMaxOpenConns(1) + per-KnoxDB mutex around RecordObservation's check-then-insert dedup (closes duplicate-row race) **Watch daemon** - Ticker guard flags now atomic.Bool (was a cross-goroutine data race) - Trailing-edge per-path debounce (timer-based, pruned on fire/delete) - Recursive watches (startup tree walk + watcher.Add on dir Create); Rename re-ingests, Remove cancels pending ingests **MCP + CLI** - Strict arg validation, no silent clamping: thread_id 0 errors instead of renaming thread #1; empty knox_thread_link {} errors instead of false success; thread existence checked before writes; golden-thread tool nil-safe - --page 0 errors instead of panicking; query/recent pagination actually pages (page x limit) **Tests** (new internal/hlc and internal/db packages): SeekTo monotonicity, concurrent dedup race, push validation, reopen HCL monotonicity, batch caps, self-spoof rejection, idempotency on observation counts. Verified: go build, go vet, full suite with -race, live MCP stdio transcripts against a scratch DB. Reviewed-on: #3 Co-authored-by: David Gwilliam <dhgwilliam@gmail.com> Co-committed-by: David Gwilliam <dhgwilliam@gmail.com>
175 lines
4.8 KiB
Go
175 lines
4.8 KiB
Go
package cmd
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"os"
|
|
"strings"
|
|
|
|
"github.com/david/knox/internal/db"
|
|
"github.com/david/knox/internal/index"
|
|
"github.com/spf13/cobra"
|
|
)
|
|
|
|
func paginate(entries []db.Entry, page, limit int) []db.Entry {
|
|
start := (page - 1) * limit
|
|
if start < 0 || start >= len(entries) {
|
|
return nil
|
|
}
|
|
end := start + limit
|
|
if end > len(entries) {
|
|
end = len(entries)
|
|
}
|
|
return entries[start:end]
|
|
}
|
|
|
|
func NewStatusCmd(kdb *db.KnoxDB) *cobra.Command {
|
|
var jsonOut bool
|
|
cmd := &cobra.Command{
|
|
Use: "status",
|
|
Short: "Show knowledge index statistics",
|
|
RunE: func(c *cobra.Command, args []string) error {
|
|
stats, err := kdb.Stats()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if jsonOut {
|
|
b, _ := json.MarshalIndent(stats, "", " ")
|
|
fmt.Println(string(b))
|
|
return nil
|
|
}
|
|
fmt.Println("Knox Knowledge Index")
|
|
fmt.Println("====================")
|
|
for k, v := range stats {
|
|
switch val := v.(type) {
|
|
case int:
|
|
fmt.Printf(" %-24s %d\n", k+":", val)
|
|
case string:
|
|
fmt.Printf(" %-24s %s\n", k+":", val)
|
|
default:
|
|
fmt.Printf(" %-24s %v\n", k+":", val)
|
|
}
|
|
}
|
|
return nil
|
|
},
|
|
}
|
|
cmd.Flags().BoolVar(&jsonOut, "json", false, "Output as JSON")
|
|
return cmd
|
|
}
|
|
|
|
func NewQueryCmd(kdb *db.KnoxDB) *cobra.Command {
|
|
var page, limit int
|
|
cmd := &cobra.Command{
|
|
Use: "query [search text]",
|
|
Short: "Search the knowledge index",
|
|
Long: "Search the knowledge index. Reads from stdin pipe if no positional arg given.",
|
|
RunE: func(c *cobra.Command, args []string) error {
|
|
query := ""
|
|
if len(args) > 0 {
|
|
query = args[0]
|
|
} else {
|
|
stdin, _ := os.ReadFile(os.Stdin.Name())
|
|
query = strings.TrimSpace(string(stdin))
|
|
}
|
|
if query == "" {
|
|
return fmt.Errorf("search query required (positional arg or stdin pipe)")
|
|
}
|
|
if page < 1 || limit < 1 {
|
|
return fmt.Errorf("page and limit must be >= 1 (got page=%d limit=%d)", page, limit)
|
|
}
|
|
// Fetch enough rows to cover the requested page: Search caps at its
|
|
// limit argument, so slicing a limit-sized result set could never
|
|
// reach page 2+.
|
|
all, err := kdb.Search(query, page*limit)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
results := paginate(all, page, limit)
|
|
if len(results) == 0 {
|
|
fmt.Println("No results found.")
|
|
return nil
|
|
}
|
|
fmt.Printf("Found %d results for %q — showing %d (page %d, %d per page):\n\n", len(all), query, len(results), page, limit)
|
|
for _, r := range results {
|
|
fmt.Printf(" %-8s %-30s [%s] %s\n", shortFP(r.Fingerprint), truncateStr(r.Title, 30), r.Project, r.SourceID)
|
|
if r.Summary != "" {
|
|
fmt.Printf(" %-8s %s\n", "", truncateStr(r.Summary, 80))
|
|
}
|
|
fmt.Println()
|
|
}
|
|
return nil
|
|
},
|
|
}
|
|
cmd.Flags().IntVarP(&page, "page", "p", 1, "Page number (1-based)")
|
|
cmd.Flags().IntVarP(&limit, "limit", "l", 20, "Results per page")
|
|
return cmd
|
|
}
|
|
|
|
func NewRecentCmd(kdb *db.KnoxDB) *cobra.Command {
|
|
var page, limit int
|
|
cmd := &cobra.Command{
|
|
Use: "recent",
|
|
Short: "Show recent knowledge entries",
|
|
RunE: func(c *cobra.Command, args []string) error {
|
|
if page < 1 || limit < 1 {
|
|
return fmt.Errorf("page and limit must be >= 1 (got page=%d limit=%d)", page, limit)
|
|
}
|
|
all, err := kdb.RecentEntries(page * limit)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
entries := paginate(all, page, limit)
|
|
if len(entries) == 0 {
|
|
if page > 1 {
|
|
fmt.Printf("No more entries on page %d (page %d of %d).\n", page, page, (len(all)+limit-1)/limit)
|
|
} else {
|
|
fmt.Println("No entries yet. Run `knox watch` to start ingesting.")
|
|
}
|
|
return nil
|
|
}
|
|
fmt.Printf("Recent %d entries (page %d, %d per page):\n\n", len(entries), page, limit)
|
|
for _, e := range entries {
|
|
fmt.Printf(" %-8s %-30s [%s] %s\n", shortFP(e.Fingerprint), truncateStr(e.Title, 30), e.Project, e.SourceID)
|
|
}
|
|
return nil
|
|
},
|
|
}
|
|
cmd.Flags().IntVarP(&page, "page", "p", 1, "Page number (1-based)")
|
|
cmd.Flags().IntVarP(&limit, "limit", "l", 20, "Results per page")
|
|
return cmd
|
|
}
|
|
|
|
func NewReflectCmd(kdb *db.KnoxDB) *cobra.Command {
|
|
return &cobra.Command{
|
|
Use: "reflect",
|
|
Short: "Process pending sessions for reflection",
|
|
Long: "Scans for sessions not yet indexed, runs reflection, and reports findings.",
|
|
RunE: func(c *cobra.Command, args []string) error {
|
|
reflector := index.NewReflector(kdb)
|
|
results, err := reflector.Reflect()
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if len(results) == 0 {
|
|
fmt.Println("All caught up — no pending sessions to reflect on.")
|
|
return nil
|
|
}
|
|
fmt.Printf("Reflected %d sessions:\n\n", len(results))
|
|
fmt.Print(reflector.FormatResult(results))
|
|
|
|
gaps, _ := reflector.Gaps()
|
|
if len(gaps) > 0 {
|
|
fmt.Printf("\nProjects with indexed knowledge:\n")
|
|
for _, g := range gaps {
|
|
fmt.Printf(" %-20s %d entries\n", g.Project, g.TotalEntries)
|
|
}
|
|
}
|
|
return nil
|
|
},
|
|
}
|
|
}
|
|
|
|
func getHomeDir() (string, error) {
|
|
return os.UserHomeDir()
|
|
}
|