226 lines
15 KiB
Go
226 lines
15 KiB
Go
package main
|
||
|
||
import (
|
||
"flag"
|
||
"fmt"
|
||
"io"
|
||
"math"
|
||
"strconv"
|
||
|
||
"textmachine/backend/internal/pipeline"
|
||
)
|
||
|
||
// invocation.go: CLI argument parsing, extracted into a pure function (package №4 —
|
||
// tmctl had 0 tests for the contract invariants: bad-flag→exit 1, not 2;
|
||
// the redrive selector; validation order). The flag/error-text contract is FROZEN
|
||
// (D12/D15.3) — this function merely relocates it to a testable place.
|
||
|
||
// invocation is one parsed tmctl command line.
|
||
type invocation struct {
|
||
cmd string
|
||
cfgPath string
|
||
seedPath string // seed-lint: the glossary seed YAML to validate (no --config)
|
||
// decisionsPath is the bank-apply decision document (the JSON the platform hands the engine).
|
||
decisionsPath string
|
||
// dryRun is bank-apply's projection mode. redrive keeps its own copy inside sel (a selector field),
|
||
// and the two are the same flag with the same meaning: report, touch nothing.
|
||
dryRun bool
|
||
resnapshot bool
|
||
acceptRebill pipeline.RebillConsent // --accept-rebill[=usd]: Р6 consent to a projected re-payment
|
||
asJSON bool
|
||
asPlaintext bool
|
||
asPairs bool // export: include the source column (--pairs) for the DC1/DC2 FP-measure
|
||
// verifyBank is the bank-verification FLAG (pack-20 / D39.42 п.5 · D39.144): stop at the bank-mining
|
||
// boundary and show the table when the delta holds never-presented terms, instead of carrying an
|
||
// unsigned bank into the edit wave. CLI-only and BINARY — «флаг бинарный» (owner) — and deliberately
|
||
// not a book.yaml key: whether a human is available to review right now is a property of the
|
||
// invocation, not of the book.
|
||
verifyBank bool
|
||
// keysFile is the DEPLOYMENT's provider-key file (backlog row 211), empty when the flag was absent.
|
||
// `translate` only: the $0 read commands must not merely tolerate keys, they must not demand them at
|
||
// all (D20.4), and a flag they accept is a flag a caller will eventually be required to pass.
|
||
keysFile string
|
||
// ceilingUSD is the BOOK ceiling for THIS RUN ONLY (row 145 / D39.110), 0 when the flag was absent.
|
||
// It is an invocation property for the same reason verifyBank is: the amount a caller is willing to
|
||
// spend on one run belongs to that run, not to the book's data — writing it into book.yaml would make
|
||
// a caller's number a permanent record in the engine's config and mix the zones (D39.81/D39.85).
|
||
ceilingUSD float64
|
||
sel pipeline.RedriveSelector
|
||
}
|
||
|
||
// rebillConsentValue parses `--accept-rebill[=usd]` (D20.2-Q2): the OPTIONAL-VALUE form of Р6, where a
|
||
// bare flag consents to the whole projected re-payment and `--accept-rebill=1.50` consents only while
|
||
// the projection stays at or below $1.50. It is a flag.Value with IsBoolFlag, which is the only way the
|
||
// stdlib grants a flag an optional value: bare, the package calls Set("true").
|
||
type rebillConsentValue struct{ c pipeline.RebillConsent }
|
||
|
||
func (v *rebillConsentValue) String() string {
|
||
switch {
|
||
case v == nil || !v.c.Given:
|
||
return "false"
|
||
case v.c.Capped:
|
||
return strconv.FormatFloat(v.c.CapUSD, 'g', -1, 64)
|
||
default:
|
||
return "true"
|
||
}
|
||
}
|
||
|
||
func (v *rebillConsentValue) Set(s string) error {
|
||
switch s {
|
||
case "true":
|
||
v.c = pipeline.RebillConsent{Given: true}
|
||
return nil
|
||
case "false":
|
||
v.c = pipeline.RebillConsent{}
|
||
return nil
|
||
}
|
||
usd, err := strconv.ParseFloat(s, 64)
|
||
if err != nil || math.IsNaN(usd) || math.IsInf(usd, 0) || usd < 0 {
|
||
return fmt.Errorf("--accept-rebill takes a non-negative USD ceiling (--accept-rebill=1.50) or no value at all; got %q", s)
|
||
}
|
||
v.c = pipeline.RebillConsent{Given: true, Capped: true, CapUSD: usd}
|
||
return nil
|
||
}
|
||
|
||
// IsBoolFlag lets `--accept-rebill` stand alone. The cost of that stdlib affordance is that
|
||
// `--accept-rebill 1.50` does NOT bind the amount — the flag reads as bare and 1.50 becomes a stray
|
||
// argument — which would silently turn a capped consent into an unlimited one. parseInvocation refuses
|
||
// that spelling explicitly rather than let it read as consent to everything.
|
||
func (v *rebillConsentValue) IsBoolFlag() bool { return true }
|
||
|
||
// parseInvocation parses os.Args[1:] into an invocation. flagOut receives the
|
||
// stdlib's flag diagnostics ("flag provided but not defined" + usage) — main
|
||
// passes os.Stderr, tests a buffer; the bytes and their destination are part of
|
||
// the frozen contract.
|
||
//
|
||
// Deliberately preserved quirks (changing them = changing the contract):
|
||
// - the command NAME is not validated here — `tmctl bogus --config x` reaches
|
||
// the dispatch switch (after dotenv/ctx setup) and errors there, while
|
||
// `tmctl bogus` without --config errors "--config book.yaml is required";
|
||
// - ContinueOnError, NOT ExitOnError: the stdlib's ExitOnError would call
|
||
// os.Exit(2) on a bad flag and would COLLAPSE onto exit code 2
|
||
// (completed-with-flags); returning an error routes the bad flag into
|
||
// main()'s default branch → exit 1, leaving 2 exclusive to flagged chunks.
|
||
func parseInvocation(args []string, flagOut io.Writer) (invocation, error) {
|
||
if len(args) < 1 {
|
||
// The command list is the dispatch switch's, in full (row 176): `backup` and `migrate` are
|
||
// deploy-step commands and `seed-lint` is the $0 seed validator, and a usage line that omits them
|
||
// tells the operator they do not exist. seed-lint and bank-apply are on their own clauses because
|
||
// their arguments differ — seed-lint takes --seed and no --config, bank-apply needs --decisions —
|
||
// and folding them into the first clause would be the same class of lie.
|
||
return invocation{}, fmt.Errorf("usage: tmctl <translate|report|status|export|redrive|manifest|backup|migrate> --config book.yaml | tmctl bank-apply --config book.yaml --decisions decisions.json | tmctl seed-lint --seed glossary.yaml")
|
||
}
|
||
cmd, rest := args[0], args[1:]
|
||
|
||
fs := flag.NewFlagSet(cmd, flag.ContinueOnError)
|
||
fs.SetOutput(flagOut)
|
||
cfgPath := fs.String("config", "", "path to book.yaml")
|
||
resnapshot := fs.Bool("resnapshot", false, "re-pin existing jobs to the current config snapshot (re-translates already-paid chunks — explicit consent)")
|
||
acceptRebill := &rebillConsentValue{}
|
||
fs.Var(acceptRebill, "accept-rebill", "translate/redrive: consent to the projected RE-PAYMENT of already-billed work (D20.2-Q2). Bare accepts the whole projected amount; --accept-rebill=1.50 accepts it only up to $1.50")
|
||
asJSON := fs.Bool("json", false, "status: emit the projection as JSON (stable disposition/flag_reason enums) for CI/IDE; manifest: emit the manifest document instead of a summary")
|
||
asPlaintext := fs.Bool("plaintext", false, "export: emit the concatenated human text instead of the default stable JSON")
|
||
asPairs := fs.Bool("pairs", false, "export: include the source text per chunk (src↔target column for the DC1/DC2 FP-measure, WS5)")
|
||
chapter := fs.Int("chapter", -1, "redrive: restrict to this chapter (default: any)")
|
||
chunk := fs.Int("chunk", -1, "redrive: restrict to this chunk index within the chapter (default: any)")
|
||
reason := fs.String("reason", "", "redrive: restrict to this flag_reason (default: any)")
|
||
dryRun := fs.Bool("dry-run", false, "redrive: report what would be re-attacked without touching anything; bank-apply: print the projection of the decisions and write NOTHING")
|
||
verifyBank := fs.Bool("verify-bank", false, "translate/redrive: STOP at the bank-mining boundary and print the bank table when the delta holds terms no earlier stop has shown (D39.144: the flag trips on novelty; a resumed run goes on and undecided terms ride to the editor marked). Default: never stop")
|
||
ceilingUSD := fs.Float64("ceiling-usd", 0, "translate/redrive: the book USD ceiling in force for THIS RUN ONLY — it OVERRIDES book.yaml `ceilings.book_usd` and is never written back. It caps the book's CUMULATIVE committed+reserved spend, not this run's increment, and must be > 0")
|
||
seed := fs.String("seed", "", "seed-lint: path to the glossary seed YAML to validate ($0, no --config)")
|
||
keysFile := fs.String("keys-file", "", "translate: path to the DEPLOYMENT's provider-key file (KEY=VALUE lines). Loaded FIRST, so it wins over the .env beside book.yaml; a named file that cannot be read is a refusal, never a silent skip")
|
||
decisions := fs.String("decisions", "", "bank-apply: path to the JSON decision document to apply to the book's memory bank ($0)")
|
||
if err := fs.Parse(rest); err != nil {
|
||
return invocation{}, err
|
||
}
|
||
// Which flags were actually PRESENT on the command line.
|
||
//
|
||
// fs.Lookup does not answer this — it returns the DECLARED flag whether or not anybody passed it —
|
||
// and fs.Visit is the only thing that does. The difference is the whole of the two guards below: they
|
||
// keyed on the VALUE being non-empty, so `--decisions=` with an empty value was invisible to them and
|
||
// `tmctl translate --decisions=` went down the PAID path exactly as if the flag were absent. The live
|
||
// trigger is not a typist: it is `--decisions=$DOC` in a unit file or a script with the variable
|
||
// unset. The precedent for the technique is `ceiling-usd` below, which has needed it since D39.110.
|
||
given := map[string]bool{}
|
||
fs.Visit(func(f *flag.Flag) { given[f.Name] = true })
|
||
// Keys belong to the ONE command that spends money. Refused rather than ignored for a read command:
|
||
// silently accepting it teaches a caller to pass it everywhere, and the next reader of that wiring
|
||
// concludes the $0 projections need keys — the exact belief D20.4 exists to prevent. Placed before the
|
||
// seed-lint branch so no command escapes the rule, and scoped to the flag being PRESENT so the frozen
|
||
// "--config first" validation order is untouched for every invocation that does not pass it.
|
||
if given["keys-file"] {
|
||
if cmd != "translate" {
|
||
// The reason has to describe EVERY command the branch turns away, or the operator who gets it
|
||
// is taught something false about the system. It names them all, and the test that guards it
|
||
// enumerates dispatchCommands rather than a hand-written list — the hand list is what left
|
||
// `bank-apply`, the very verb this pack added, undescribed by its own refusal.
|
||
return invocation{}, fmt.Errorf("--keys-file is accepted by `translate` only, not by %q: `translate` is the one command that spends. The $0 read commands (report/status/export/manifest/seed-lint/bank-apply) must not demand provider keys at all (D20.4); `redrive` does re-attack and re-bill, but takes its keys from its own conventional .env; `backup` and `migrate` are deploy steps that call no provider", cmd)
|
||
}
|
||
// A PRESENT flag with an empty value is refused rather than ignored, for the reason the flag
|
||
// exists: an unset variable in a deployment's unit file would otherwise fall back to the
|
||
// conventional .env, and the deployment would believe it had supplied its own keys.
|
||
if *keysFile == "" {
|
||
return invocation{}, fmt.Errorf("--keys-file was given with no path: a deployment that names its key file and passes nothing has an unset variable, and falling back to the conventional .env would hide it")
|
||
}
|
||
}
|
||
// The same rule for the decision document, and here the silent version costs MONEY: the flags of this
|
||
// CLI live in one FlagSet, so `tmctl translate --decisions d.json` parsed cleanly and ran a paid
|
||
// translation while its caller believed it was applying a user's bank corrections. A flag a command
|
||
// does not act on is refused, never ignored.
|
||
if given["decisions"] {
|
||
if cmd != "bank-apply" {
|
||
return invocation{}, fmt.Errorf("--decisions is accepted by `bank-apply` only, not by %q: %q does not apply decisions, and running it with this flag would do something other than what the flag says", cmd, cmd)
|
||
}
|
||
if *decisions == "" {
|
||
return invocation{}, fmt.Errorf("--decisions was given with no path: an unset variable must not read as «apply nothing», and for bank-apply the document IS the command")
|
||
}
|
||
}
|
||
// And the same rule for --dry-run, whose silent version is the most expensive of the three:
|
||
// `tmctl translate --dry-run` parsed cleanly and ran a PAID translation while its caller believed
|
||
// it was asking for a $0 projection — the exact inversion of what the flag promises everywhere else.
|
||
if given["dry-run"] && cmd != "bank-apply" && cmd != "redrive" {
|
||
return invocation{}, fmt.Errorf("--dry-run is accepted by `bank-apply` and `redrive` only, not by %q: %q has no projection mode, and running it with this flag would spend real money on a call its caller believes is free", cmd, cmd)
|
||
}
|
||
// seed-lint validates a standalone seed YAML — it takes --seed, not --config (no book/store/keys).
|
||
if cmd == "seed-lint" {
|
||
if *seed == "" {
|
||
return invocation{}, fmt.Errorf("--seed <glossary.yaml> is required for seed-lint")
|
||
}
|
||
return invocation{cmd: cmd, seedPath: *seed}, nil
|
||
}
|
||
if *cfgPath == "" {
|
||
return invocation{}, fmt.Errorf("--config book.yaml is required")
|
||
}
|
||
// The run ceiling is refused rather than defaulted when it is present but not a spendable amount, so
|
||
// the flag can only ever ADD a bound, never remove one (D39.110: «выключено» is not a state).
|
||
//
|
||
// Р7's own validator (config.LoadBook) is untouched and is NOT the same rule: it demands at least ONE
|
||
// of book_usd/day_usd, so a book may legitimately declare a daily ceiling only — and then the book
|
||
// ceiling this flag overrides is zero, i.e. absent, and passing the flag introduces one for this run.
|
||
// fs.Visit reports only flags actually PRESENT on the command line, which is what separates
|
||
// "--ceiling-usd 0" (a refusal) from an absent flag (the book's own ceiling stands). Placed AFTER the
|
||
// --config check so the frozen validation order is untouched: a missing --config is still the first
|
||
// thing a caller is told about.
|
||
if given["ceiling-usd"] && (math.IsNaN(*ceilingUSD) || math.IsInf(*ceilingUSD, 0) || *ceilingUSD <= 0) {
|
||
return invocation{}, fmt.Errorf("--ceiling-usd must be a finite amount greater than zero (it is the ceiling for THIS run and overrides book.yaml ceilings.book_usd); got %v — omit the flag to run under the book's own ceiling", *ceilingUSD)
|
||
}
|
||
// The optional-value trap (see IsBoolFlag): `--accept-rebill 1.50` leaves 1.50 as a stray argument
|
||
// and the consent unlimited. Refuse loud rather than bill the difference. Scoped to exactly that
|
||
// spelling, so the historically-tolerated stray argument stays tolerated everywhere else.
|
||
if acceptRebill.c.Given && !acceptRebill.c.Capped && fs.NArg() > 0 {
|
||
return invocation{}, fmt.Errorf("--accept-rebill takes its ceiling with an «=» (--accept-rebill=%s), not a space: as written %q is a stray argument and the flag consents to the FULL projected re-payment", fs.Arg(0), fs.Arg(0))
|
||
}
|
||
// bank-apply is meaningless without the document it applies, and defaulting that path to some
|
||
// convention would let an argument-less invocation mutate the book's decisions.
|
||
if cmd == "bank-apply" && *decisions == "" {
|
||
return invocation{}, fmt.Errorf("--decisions <decisions.json> is required for bank-apply")
|
||
}
|
||
return invocation{
|
||
cmd: cmd, cfgPath: *cfgPath, resnapshot: *resnapshot, acceptRebill: acceptRebill.c,
|
||
asJSON: *asJSON, asPlaintext: *asPlaintext, asPairs: *asPairs, verifyBank: *verifyBank,
|
||
ceilingUSD: *ceilingUSD, keysFile: *keysFile, decisionsPath: *decisions, dryRun: *dryRun,
|
||
sel: pipeline.RedriveSelector{
|
||
Chapter: *chapter, ChunkIdx: *chunk, Reason: *reason, DryRun: *dryRun,
|
||
},
|
||
}, nil
|
||
}
|