rohit/probo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add proboctl catalog and banner reset commands

Browse Source 
Add operator commands to proboctl for iterating on the cookie-banner
agents.

The global catalog groups (common-tracker-pattern, common-third-party)
list/filter/sort/show the catalogs using the shared coredata cursor
layer, and common-tracker-pattern reenrich re-describes selected rows by
running the enricher in-process (so it completes synchronously rather
than racing the async queue); a --cfg-file flag reuses probod's config
to wire the agent. --linked-banner/--linked-org target exactly the
catalog rows a banner or org depends on.

The cookie-banner reset-trackers command is tenant-scoped (it derives a
coredata.Scope from the banner/org GID) and rebuilds a banner's
uncategorised, non-excluded patterns from detected_trackers, decomposing
derived globs back into exacts, then re-arms the analysis and mapping
workers. --mapping-only skips the rebuild. A DB-backed test covers the
rebuild, link clearing, and preservation of categorised/excluded
patterns.

Signed-off-by: Émile Ré <emile@probo.com>
This commit is contained in:
Émile Ré
2026-06-03 13:37:48 +02:00
parent 662c0ae428
commit c763f83b13
16 changed files with 2142 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
pkg/proboctl/cmdutil/cmdutil.go
View File

@@ -16,16 +16,25 @@ package cmdutil
import (
"fmt"
"os"
"github.com/prometheus/client_golang/prometheus"
"go.gearno.de/kit/log"
"go.gearno.de/kit/pg"
"go.opentelemetry.io/otel/trace/noop"
"go.probo.inc/probo/pkg/agentsbuild"
"go.probo.inc/probo/pkg/cmd/iostreams"
"go.probo.inc/probo/pkg/cookiebanner"
"go.probo.inc/probo/pkg/proboctl/pgconn"
"go.probo.inc/probo/pkg/probodconfig"
"sigs.k8s.io/yaml"
)
type Factory struct {
IOStreams *iostreams.IOStreams
Version string
PgDSN string
CfgFile string
}
func (f *Factory) PgClient() (*pg.Client, error) {
@@ -35,3 +44,56 @@ func (f *Factory) PgClient() (*pg.Client, error) {
return pgconn.NewPgClientFromDSN(f.PgDSN)
}
// ProbodConfig loads the shared probod configuration file (--cfg-file).
// It reuses the exact file, struct, and json-tagged (un)marshaling probod
// uses, so proboctl and probod stay consistent.
func (f *Factory) ProbodConfig() (probodconfig.Config, error) {
if f.CfgFile == "" {
return probodconfig.Config{}, fmt.Errorf("set --cfg-file to the probod config file")
}
data, err := os.ReadFile(f.CfgFile)
if err != nil {
return probodconfig.Config{}, fmt.Errorf("cannot read config file %q: %w", f.CfgFile, err)
}
var full probodconfig.FullConfig
if err := yaml.Unmarshal(data, &full); err != nil {
return probodconfig.Config{}, fmt.Errorf("cannot parse config file %q: %w", f.CfgFile, err)
}
return full.Probod, nil
}
// TrackerAgentsConfig builds the tracker-agents config (LLM client +
// Firecrawl key) from the shared probod config for in-process agent
// execution, e.g. synchronous common-pattern re-enrichment. It errors
// when no LLM provider is configured.
func (f *Factory) TrackerAgentsConfig() (cookiebanner.TrackerAgentsConfig, error) {
cfg, err := f.ProbodConfig()
if err != nil {
return cookiebanner.TrackerAgentsConfig{}, err
}
logger := log.NewLogger(
log.WithName("proboctl"),
log.WithOutput(f.IOStreams.ErrOut),
)
trackerCfg, _, err := agentsbuild.BuildTrackerAgentsConfig(
cfg,
logger,
noop.NewTracerProvider(),
prometheus.NewRegistry(),
)
if err != nil {
return cookiebanner.TrackerAgentsConfig{}, fmt.Errorf("cannot build tracker agents config: %w", err)
}
if trackerCfg.LLMClient == nil {
return cookiebanner.TrackerAgentsConfig{}, fmt.Errorf("no LLM provider configured; set llm.tracker-mapping.provider in %q", f.CfgFile)
}
return trackerCfg, nil
}