mirror of
https://github.com/tiennm99/goclaw.git
synced 2026-10-20 02:17:24 +00:00
viettranx
dabb1eaa11
Add POST /v1/agents/{agentID}/vault/rescan to backfill vault_documents
from filesystem. Walks agent workspace, registers missing/changed files,
publishes enrichment events for async summarize + embed + link classify.
Backend:
- SafeWalkWorkspace: symlink-safe walker with exclusion patterns,
resource limits (5K files, 500MB, 50MB/file), context deadline
- RescanWorkspace: hash-based dedup, path-based scope detection
(teams/{id}/ → team scope), idempotent via UpsertDocument ON CONFLICT
- Per-agent mutex (409 Conflict for concurrent rescans)
- Tenant-scoped workspace resolution (config.TenantWorkspace)
- Enrichment worker: semaphore-based parallel summarize (max 3 concurrent)
- Media files without summary skip LLM summarize, embed title+path only
- DRY: export InferTitle/InferDocType from vault pkg, remove from interceptor
- Auto-register text uploads in vault via onTextUploaded callback
Frontend:
- Rescan button in vault page header (FolderSync icon)
- Toast with result counts, 409 warning, error handling
- i18n strings for en/vi/zh
Security: skip all symlinks, boundary checks, per-file size limit,
tenant isolation via server-side workspace resolution.
81 lines
2.1 KiB
Go
81 lines
2.1 KiB
Go
package vault
|
|
|
|
import "testing"
|
|
|
|
func TestInferScopeFromPath(t *testing.T) {
|
|
tests := []struct {
|
|
path string
|
|
scope string
|
|
hasTeam bool
|
|
teamID string
|
|
}{
|
|
{"notes/doc.md", "personal", false, ""},
|
|
{"web-fetch/page.txt", "personal", false, ""},
|
|
{"report.md", "personal", false, ""},
|
|
{"teams/abc-def-123/report.md", "team", true, "abc-def-123"},
|
|
{"teams/abc-def-123/deep/nested.md", "team", true, "abc-def-123"},
|
|
{"teams/", "personal", false, ""}, // malformed, no team ID
|
|
{"teams", "personal", false, ""}, // no slash
|
|
{"teamsfoo/bar.md", "personal", false, ""}, // not teams/ prefix
|
|
{"telegram/123/teams/x/y.md", "personal", false, ""}, // teams not at root
|
|
}
|
|
for _, tt := range tests {
|
|
t.Run(tt.path, func(t *testing.T) {
|
|
scope, teamID := inferScopeFromPath(tt.path)
|
|
if scope != tt.scope {
|
|
t.Errorf("scope = %q, want %q", scope, tt.scope)
|
|
}
|
|
if tt.hasTeam && (teamID == nil || *teamID != tt.teamID) {
|
|
t.Errorf("teamID = %v, want %q", teamID, tt.teamID)
|
|
}
|
|
if !tt.hasTeam && teamID != nil {
|
|
t.Errorf("teamID = %v, want nil", teamID)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestInferVaultDocType(t *testing.T) {
|
|
tests := []struct {
|
|
path string
|
|
docType string
|
|
}{
|
|
{"screenshot.png", "media"},
|
|
{"photo.jpg", "media"},
|
|
{"video.mp4", "media"},
|
|
{"audio.mp3", "media"},
|
|
{"notes/meeting.md", "note"},
|
|
{"report.txt", "note"},
|
|
{"web-fetch/page.html", "note"},
|
|
{"skills/my-skill/SKILL.md", "skill"},
|
|
{"deep/soul.md", "context"},
|
|
}
|
|
for _, tt := range tests {
|
|
t.Run(tt.path, func(t *testing.T) {
|
|
got := InferDocType(tt.path)
|
|
if got != tt.docType {
|
|
t.Errorf("InferDocType(%q) = %q, want %q", tt.path, got, tt.docType)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestInferTitle(t *testing.T) {
|
|
tests := []struct {
|
|
path string
|
|
title string
|
|
}{
|
|
{"report.md", "report"},
|
|
{"notes/meeting-notes.txt", "meeting-notes"},
|
|
{"deep/nested/file.png", "file"},
|
|
}
|
|
for _, tt := range tests {
|
|
t.Run(tt.path, func(t *testing.T) {
|
|
got := InferTitle(tt.path)
|
|
if got != tt.title {
|
|
t.Errorf("InferTitle(%q) = %q, want %q", tt.path, got, tt.title)
|
|
}
|
|
})
|
|
}
|
|
}
|