254 lines
8.5 KiB
Go
254 lines
8.5 KiB
Go
// tmctl is the TextMachine CLI (Фаза 0: translate один чанк + report).
|
||
package main
|
||
|
||
import (
|
||
"bufio"
|
||
"context"
|
||
"errors"
|
||
"flag"
|
||
"fmt"
|
||
"os"
|
||
"os/signal"
|
||
"path/filepath"
|
||
"strings"
|
||
"syscall"
|
||
|
||
"textmachine/backend/internal/obs"
|
||
"textmachine/backend/internal/pipeline"
|
||
)
|
||
|
||
// Exit codes (Веха 2): 0 clean · 2 completed-with-flags (приёмка допускает N
|
||
// флагов) · 1 infra failure. The exit-2 case is carried up as a typed sentinel
|
||
// (*pipeline.CompletedWithFlags) so a "clean run, attention needed" never
|
||
// masquerades as an infra crash and vice-versa.
|
||
func main() {
|
||
err := run()
|
||
var flagged *pipeline.CompletedWithFlags
|
||
switch {
|
||
case err == nil:
|
||
return
|
||
case errors.As(err, &flagged):
|
||
fmt.Fprintln(os.Stderr, "tmctl:", err)
|
||
os.Exit(2)
|
||
default:
|
||
fmt.Fprintln(os.Stderr, "tmctl:", err)
|
||
os.Exit(1)
|
||
}
|
||
}
|
||
|
||
func run() error {
|
||
if len(os.Args) < 2 {
|
||
return fmt.Errorf("usage: tmctl <translate|report> --config book.yaml")
|
||
}
|
||
cmd, args := os.Args[1], os.Args[2:]
|
||
|
||
// ContinueOnError (not ExitOnError): the stdlib's ExitOnError calls os.Exit(2)
|
||
// on a parse failure, which would COLLIDE with exit code 2 (completed-with-
|
||
// flags). Returning the error routes a bad flag to main()'s default branch →
|
||
// exit 1, keeping 2 exclusive to the flagged-chunks case (self-review Веха 2).
|
||
fs := flag.NewFlagSet(cmd, flag.ContinueOnError)
|
||
cfgPath := fs.String("config", "", "path to book.yaml")
|
||
resnapshot := fs.Bool("resnapshot", false, "re-pin existing jobs to the current config snapshot (пере-перевод оплаченных чанков — явное согласие)")
|
||
if err := fs.Parse(args); err != nil {
|
||
return err
|
||
}
|
||
if *cfgPath == "" {
|
||
return fmt.Errorf("--config book.yaml is required")
|
||
}
|
||
|
||
loadDotEnv(filepath.Join(filepath.Dir(*cfgPath), ".env"))
|
||
loadDotEnv(".env")
|
||
|
||
ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM)
|
||
defer stop()
|
||
// LogBodies решается один раз на допуске (privacy by default): содержимое
|
||
// LLM-обменов попадает в логи только при LOG_LLM_BODIES=1 И LOG_LEVEL=debug.
|
||
ctx = obs.WithReqInfo(ctx, obs.ReqInfo{
|
||
TraceID: obs.NewTraceID(),
|
||
LogBodies: os.Getenv("LOG_LLM_BODIES") == "1",
|
||
})
|
||
|
||
switch cmd {
|
||
case "translate":
|
||
return translate(ctx, *cfgPath, *resnapshot)
|
||
case "report":
|
||
return report(*cfgPath)
|
||
default:
|
||
return fmt.Errorf("unknown command %q (want translate|report)", 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 {
|
||
return err
|
||
}
|
||
|
||
for _, ch := range res.Chunks {
|
||
fmt.Printf("=== ГЛАВА %d ЧАНК %d — %s%s ===\n", ch.Chapter, ch.ChunkIdx, ch.Disposition, flagSuffix(ch.FlagReason))
|
||
if ch.Disposition == pipeline.DispOK {
|
||
fmt.Println(ch.FinalText)
|
||
} else {
|
||
fmt.Printf("[ФЛАГ %s] чанк не переведён — черновик/редактура непригодны, помечен для человека\n", ch.FlagReason)
|
||
}
|
||
for _, st := range ch.Stages {
|
||
how := "call"
|
||
switch {
|
||
case st.Disposition == pipeline.DispSkipped:
|
||
how = "skipped"
|
||
case st.FromResume:
|
||
how = "resume"
|
||
}
|
||
fmt.Printf(" %-8s %-22s %-8s %-8s%s $%.6f (cum $%.6f) in=%d (cached=%d) out=%d+%d att=%d %dms finish=%s\n",
|
||
st.Stage, st.Model, how, st.Disposition, flagSuffix(st.FlagReason),
|
||
st.CostUSD, st.CumCostUSD,
|
||
st.Usage.PromptTokens, st.Usage.CachedTokens,
|
||
st.Usage.CompletionTokens, st.Usage.ReasoningTokens, st.Attempts, st.LatencyMS, st.FinishReason)
|
||
}
|
||
fmt.Println()
|
||
}
|
||
|
||
fmt.Printf("ИТОГО (этот запуск): $%.6f — чанков %d, флагов %d\n", res.TotalUSD, len(res.Chunks), res.Flagged)
|
||
committed, reserved, err := r.Store.SpentUSD(res.BookID)
|
||
if err != nil {
|
||
return err
|
||
}
|
||
fmt.Printf("Ledger книги: committed=$%.6f reserved=$%.6f\n", committed, reserved)
|
||
|
||
// Exit code 2 is a typed sentinel, not an infra error: the report above is
|
||
// already on stdout; main() maps this to a non-zero exit for the operator.
|
||
if res.Flagged > 0 {
|
||
return &pipeline.CompletedWithFlags{Flagged: res.Flagged, Total: len(res.Chunks)}
|
||
}
|
||
return nil
|
||
}
|
||
|
||
// flagSuffix renders a non-empty flag reason as "(reason)".
|
||
func flagSuffix(r pipeline.FlagReason) string {
|
||
if r == "" {
|
||
return ""
|
||
}
|
||
return "(" + string(r) + ")"
|
||
}
|
||
|
||
func report(cfgPath string) error {
|
||
r, err := pipeline.NewRunner(cfgPath, obs.NewLogger())
|
||
if err != nil {
|
||
return err
|
||
}
|
||
defer r.Close()
|
||
|
||
rows, err := r.Store.RequestLogRows(r.Book.BookID)
|
||
if err != nil {
|
||
return err
|
||
}
|
||
|
||
fmt.Printf("%-20s %-8s %-12s %-22s %8s %8s %8s %8s %8s %10s %8s %-8s %-5s %-3s\n",
|
||
"ts", "stage", "role", "model", "prompt", "cached", "cwrite", "compl", "reason", "cost_usd", "ms", "finish", "tmhit", "ok")
|
||
for _, row := range rows {
|
||
fmt.Printf("%-20s %-8s %-12s %-22s %8d %8d %8d %8d %8d %10.6f %8d %-8s %-5d %-3d\n",
|
||
row.TS, row.Stage, row.Role, row.ModelActual, row.PromptTokens, row.CachedTokens,
|
||
row.CacheCreationTokens, row.CompletionTokens, row.ReasoningTokens, row.CostUSD,
|
||
row.LatencyMS, row.FinishReason, row.TMHit, row.OK)
|
||
}
|
||
|
||
// Flag section (Веха 2): every chunk×stage whose disposition ≠ ok — the
|
||
// "флаг редактору" the plan requires (02-mvp Фаза-1 приёмка допускает N).
|
||
flags, err := r.Store.ChunkStatusesForBook(r.Book.BookID)
|
||
if err != nil {
|
||
return err
|
||
}
|
||
headerPrinted := false
|
||
for _, f := range flags {
|
||
if f.Disposition == "ok" {
|
||
continue
|
||
}
|
||
if !headerPrinted {
|
||
fmt.Printf("\n=== ФЛАГИ (disposition ≠ ok) ===\n")
|
||
fmt.Printf("%-4s %-6s %-8s %-9s %-16s %5s %10s %s\n",
|
||
"ch", "chunk", "stage", "disp", "reason", "att", "cost_usd", "detail")
|
||
headerPrinted = true
|
||
}
|
||
fmt.Printf("%-4d %-6d %-8s %-9s %-16s %5d %10.6f %s\n",
|
||
f.Chapter, f.ChunkIdx, f.Stage, f.Disposition, f.FlagReason, f.Attempts, f.CostUSD, f.Detail)
|
||
}
|
||
|
||
// Memory section (шаг 4): the per-chunk retrieval-state, surfaced so silent glossary
|
||
// degradation is LOUD. The aggregate line always prints when a glossary is in use;
|
||
// each chunk with a post-check miss is listed (the flagger-mode signal — the model
|
||
// ignored an approved term, or we injected the wrong dst) with the offending src→dst.
|
||
states, err := r.Store.RetrievalStatesForBook(r.Book.BookID)
|
||
if err != nil {
|
||
return err
|
||
}
|
||
if len(states) > 0 {
|
||
var injected, sticky, ambiguous, spoiler, evicted, misses int
|
||
for _, rs := range states {
|
||
injected += rs.NExactHits
|
||
sticky += rs.NSticky
|
||
ambiguous += rs.NAmbiguousFlagged
|
||
spoiler += rs.NSpoilerBlocked
|
||
evicted += rs.NEvicted
|
||
misses += rs.NPostcheckMiss
|
||
}
|
||
fmt.Printf("\n=== ПАМЯТЬ (retrieval-state) ===\n")
|
||
fmt.Printf("инъекций(точных)=%d sticky=%d ambiguous=%d спойлер-блок=%d вытеснено=%d post-check-промахов=%d\n",
|
||
injected, sticky, ambiguous, spoiler, evicted, misses)
|
||
printed := false
|
||
for _, rs := range states {
|
||
if rs.NPostcheckMiss == 0 {
|
||
continue
|
||
}
|
||
if !printed {
|
||
fmt.Printf("%-4s %-6s %6s %s\n", "ch", "chunk", "misses", "detail (src→dst не найден в выводе)")
|
||
printed = true
|
||
}
|
||
fmt.Printf("%-4d %-6d %6d %s\n", rs.Chapter, rs.ChunkIdx, rs.NPostcheckMiss, rs.PostcheckDetail)
|
||
}
|
||
}
|
||
|
||
committed, reserved, err := r.Store.SpentUSD(r.Book.BookID)
|
||
if err != nil {
|
||
return err
|
||
}
|
||
fmt.Printf("\nLedger книги: committed=$%.6f reserved=$%.6f\n", committed, reserved)
|
||
return nil
|
||
}
|
||
|
||
// loadDotEnv reads KEY=VALUE lines into the environment without overriding
|
||
// already-set variables. Ключи — из backend/.env (gitignored); секреты никогда
|
||
// не попадают в конфиги/репо.
|
||
func loadDotEnv(path string) {
|
||
f, err := os.Open(path)
|
||
if err != nil {
|
||
return
|
||
}
|
||
defer f.Close()
|
||
sc := bufio.NewScanner(f)
|
||
for sc.Scan() {
|
||
line := strings.TrimSpace(sc.Text())
|
||
if line == "" || strings.HasPrefix(line, "#") {
|
||
continue
|
||
}
|
||
k, v, ok := strings.Cut(line, "=")
|
||
if !ok {
|
||
continue
|
||
}
|
||
k, v = strings.TrimSpace(k), strings.TrimSpace(v)
|
||
// Снимаем только ПАРНЫЕ обрамляющие кавычки: Trim по набору символов
|
||
// откусил бы легитимную кавычку в конце ключа (находка ревью).
|
||
if n := len(v); n >= 2 && (v[0] == '"' || v[0] == '\'') && v[n-1] == v[0] {
|
||
v = v[1 : n-1]
|
||
}
|
||
if os.Getenv(k) == "" {
|
||
os.Setenv(k, v)
|
||
}
|
||
}
|
||
}
|