c5bc97de19
Ports all remaining LEM pipeline commands from pkg/lem into core ml, eliminating the standalone LEM CLI dependency. Each command is split into reusable business logic (pkg/ml/) and a thin cobra wrapper (internal/cmd/ml/). New commands: query, inventory, metrics, ingest, normalize, seed-influx, consolidate, import-all, approve, publish, coverage. Adds Path(), Exec(), QueryRowScan() convenience methods to DB type. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
44 lines
934 B
Go
44 lines
934 B
Go
package ml
|
|
|
|
import (
|
|
"fmt"
|
|
"os"
|
|
|
|
"forge.lthn.ai/core/cli/pkg/cli"
|
|
"forge.lthn.ai/core/cli/pkg/ml"
|
|
)
|
|
|
|
var normalizeMinLen int
|
|
|
|
var normalizeCmd = &cli.Command{
|
|
Use: "normalize",
|
|
Short: "Normalize seeds into expansion prompts",
|
|
Long: "Deduplicates seeds against golden_set and prompts, creating the expansion_prompts table with priority-based ordering.",
|
|
RunE: runNormalize,
|
|
}
|
|
|
|
func init() {
|
|
normalizeCmd.Flags().IntVar(&normalizeMinLen, "min-length", 50, "Minimum prompt length in characters")
|
|
}
|
|
|
|
func runNormalize(cmd *cli.Command, args []string) error {
|
|
path := dbPath
|
|
if path == "" {
|
|
path = os.Getenv("LEM_DB")
|
|
}
|
|
if path == "" {
|
|
return fmt.Errorf("--db or LEM_DB env is required")
|
|
}
|
|
|
|
db, err := ml.OpenDBReadWrite(path)
|
|
if err != nil {
|
|
return fmt.Errorf("open db: %w", err)
|
|
}
|
|
defer db.Close()
|
|
|
|
cfg := ml.NormalizeConfig{
|
|
MinLength: normalizeMinLen,
|
|
}
|
|
|
|
return ml.NormalizeSeeds(db, cfg, os.Stdout)
|
|
}
|