textmachine/backend/cmd/tmctl/main.go

// tmctl is the TextMachine CLI: translate / report / status / redrive.
// main.go — thin wiring (package №4): argument parsing — invocation.go,
// output renderers — render.go, .env — dotenv.go; here just the
// «parse → env → ctx → fetch → render» wiring and exit-code mapping.
package main

import (
	"context"
	"errors"
	"fmt"
	"os"
	"os/signal"
	"path/filepath"
	"syscall"

	"textmachine/backend/internal/membank"
	"textmachine/backend/internal/obs"
	"textmachine/backend/internal/pipeline"
	"textmachine/backend/internal/store"
)

func main() {
	err := run()
	if err != nil {
		fmt.Fprintln(os.Stderr, "tmctl:", err)
	}
	os.Exit(exitCode(err))
}

// exitCode maps a run() error onto the ratified shell contract (Milestone 2 / R1-FL-A): 0 clean · 2
// completed-with-flags (acceptance allows N flags; a typed sentinel
// *pipeline.CompletedWithFlags, survives %w-wraps via errors.As) · 3 bank-mining
// signature stop (*pipeline.WaveSignatureStop — the run paused before the edit wave for owner
// sign; a DELIBERATE human-in-the-loop halt, not a crash) · 1 infra failure and everything else,
// including a flag-parse error. 3 is DISTINCT from both 2 (flagged chunks) and 1 (crash) so
// exit-code automation can tell a sign-boundary pause from a real failure — a human sees the
// stderr text either way, but a script that shipped "translate && export" must NOT treat the
// pause as success (exit 0) nor as an infra crash (exit 1).
func exitCode(err error) int {
	var flagged *pipeline.CompletedWithFlags
	var sigStop *pipeline.WaveSignatureStop
	switch {
	case err == nil:
		return 0
	case errors.As(err, &sigStop):
		return 3
	case errors.As(err, &flagged):
		return 2
	default:
		return 1
	}
}

func run() error {
	inv, err := parseInvocation(os.Args[1:], os.Stderr)
	if err != nil {
		return err
	}

	loadDotEnv(filepath.Join(filepath.Dir(inv.cfgPath), ".env"))
	loadDotEnv(".env")

	ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM)
	defer stop()
	// LogBodies is decided once at admission (privacy by default): the content
	// of LLM exchanges reaches the logs only when LOG_LLM_BODIES=1 AND LOG_LEVEL=debug.
	ctx = obs.WithReqInfo(ctx, obs.ReqInfo{
		TraceID:   obs.NewTraceID(),
		LogBodies: os.Getenv("LOG_LLM_BODIES") == "1",
	})

	switch inv.cmd {
	case "translate":
		return translate(ctx, inv.cfgPath, inv.resnapshot)
	case "report":
		return report(inv.cfgPath)
	case "status":
		return status(ctx, inv.cfgPath, inv.asJSON)
	case "export":
		return export(inv.cfgPath, inv.asPlaintext, inv.asPairs)
	case "redrive":
		return redrive(ctx, inv.cfgPath, inv.resnapshot, inv.sel)
	case "seed-lint":
		return seedLint(inv.seedPath)
	default:
		return fmt.Errorf("unknown command %q (want translate|report|status|export|redrive|seed-lint)", inv.cmd)
	}
}

func translate(ctx context.Context, cfgPath string, resnapshot bool) error {
	r, err := pipeline.NewRunner(cfgPath, obs.NewLogger())
	if err != nil {
		return err
	}
	defer r.Close()
	r.Resnapshot = resnapshot

	res, err := r.TranslateBook(ctx)
	if err != nil {
		// R1-FL-A: the bank-mining signature stop is a typed sentinel, not an infra failure — render the
		// operator's next steps to stdout (terms + signature-map path + resume guidance) and return it so
		// main() maps it to the distinct exit code 3 (the Error() text also prints to stderr).
		var sigStop *pipeline.WaveSignatureStop
		if errors.As(err, &sigStop) {
			renderSignatureStop(os.Stdout, sigStop)
		}
		return err
	}
	return renderTranslate(os.Stdout, res, func() (float64, float64, error) {
		return r.Store.SpentUSD(res.BookID)
	})
}

// seedLint validates a glossary seed YAML (a manual seed or the emitted mined delta) through the REAL
// loadGlossarySeed fail-louds + the shared-key collision check (WS3). $0, no store, no provider keys — a
// pre-flight the operator runs on the mined delta before the W1.5 reseed. Prints "OK" on a clean seed.
func seedLint(seedPath string) error {
	if err := membank.SeedLint(seedPath); err != nil {
		return err
	}
	fmt.Fprintf(os.Stdout, "seed-lint OK: %s is loadable (0 fail-louds, 0 shared-key collisions)\n", seedPath)
	return nil
}

func report(cfgPath string) error {
	// Read-only ($0): no API keys required (D20.4 — a store audit must not demand provider keys).
	r, err := pipeline.NewReadOnlyRunner(cfgPath, obs.NewLogger())
	if err != nil {
		return err
	}
	defer r.Close()

	// Reads via callbacks (interleaved with printing, as historically): a read failure
	// mid-audit leaves the already-printed part on stdout (see renderReport).
	if err := renderReport(os.Stdout,
		func() ([]store.RequestLogView, error) { return r.Store.RequestLogRows(r.Book.BookID) },
		func() ([]store.ChunkStatus, error) { return r.Store.ChunkStatusesForBook(r.Book.BookID) },
		func() ([]store.RetrievalState, error) { return r.Store.RetrievalStatesForBook(r.Book.BookID) },
		func() (float64, float64, error) { return r.Store.SpentUSD(r.Book.BookID) }); err != nil {
		return err
	}
	// Per-run quality-report (D39 layer 5): aggregate the deterministic quality signals into a readable
	// summary — the "telemetry from day one" the owner asked for (H5). Read-only ($0), never a gate.
	q, err := r.QualityReport()
	if err != nil {
		return err
	}
	return renderQuality(os.Stdout, q)
}

// export prints the READ-ONLY export projection (D39 layer 6 / D39.2-open №1): every chunk's FINAL
// export text EXACTLY by prod semantics (final_hash → checkpoint → exportNormalize), so the polygon
// extractor / reader-samples read the SAME bytes the backend ships instead of the raw checkpoint. Like
// report/status it is $0 and needs no provider keys (D20.4 — an audit surface must not demand keys).
// Default output is stable JSON (the machine surface); --plaintext emits the human concatenation.
func export(cfgPath string, asPlaintext, asPairs bool) error {
	r, err := pipeline.NewReadOnlyRunner(cfgPath, obs.NewLogger())
	if err != nil {
		return err
	}
	defer r.Close()

	exp, err := r.Export(asPairs)
	if err != nil {
		return err
	}
	return renderExport(os.Stdout, exp, asPlaintext)
}

// status prints the READ-ONLY progress projection (D15.3): 0 LLM, 0 replay. --json emits the
// StatusReport with stable disposition/flag_reason enums for CI/IDE; the default is a human
// dashboard (unit counts, per-chapter quality passports, money, secondary ETA). BOTH modes exit 2
// (completed-with-flags) when flagged>0 (minor 1d — --json used to always exit 0), so a consumer
// never reads a clean 0 over a book that still needs attention.
func status(ctx context.Context, cfgPath string, asJSON bool) error {
	// Read-only ($0): no API keys required (D20.4 — a progress projection must not demand keys).
	r, err := pipeline.NewReadOnlyRunner(cfgPath, obs.NewLogger())
	if err != nil {
		return err
	}
	defer r.Close()

	rep, err := r.Status(ctx)
	if err != nil {
		return err
	}
	if asJSON {
		return renderStatusJSON(os.Stdout, rep)
	}
	return renderStatusHuman(os.Stdout, rep, cfgPath)
}

// redrive re-attacks the FLAGGED chunks matching the selector (D15.3): it resets their terminal
// flag (chunk_status + checkpoints of the flagged/skipped stages) and re-runs the durable loop
// with a FRESH retry/escalation budget, never touching DispOK work. On --dry-run it only reports
// the plan. Redrive-calls bill normally; money already spent on the discarded attempts stays
// committed (honest). By default it requires the current config to render the SAME snapshot the
// flagged rows carry (else it fails loud); passing --resnapshot wires r.Resnapshot so Redrive skips
// that drift guard and accepts the re-pin/re-pay explicitly (D20.4: the flag used to be parsed but
// silently ignored — Redrive already honoured r.Resnapshot, only the CLI never set it).
func redrive(ctx context.Context, cfgPath string, resnapshot bool, sel pipeline.RedriveSelector) error {
	r, err := pipeline.NewRunner(cfgPath, obs.NewLogger())
	if err != nil {
		return err
	}
	defer r.Close()
	r.Resnapshot = resnapshot

	summary, res, err := r.Redrive(ctx, sel)
	if err != nil {
		return err
	}
	return renderRedrive(os.Stdout, r.Book.BookID, summary, res, func() (float64, float64, error) {
		return r.Store.SpentUSD(r.Book.BookID)
	})
}