Files
Maven/cmd/mavend/mail_test.go
T
kami f42d1594ef Turn a mail into task candidates, and into nothing else (#246)
The extraction half. internal/email.Extractor asks the resident Qwen3-1.7B,
under a GBNF grammar, what one message requires of him, and returns at most
three short candidates with an optional date.

Everything it can produce is a row in `tasks` with status "candidate",
written through the intake seam #130 built for exactly this (Source
"email:<mailbox>", Evidence = the subject line). No reminder, no fact, no
note, no calendar event. That bound is the design: a reminder FIRES, so a
1.7B misreading "встреча была в четверг" as a future appointment would wake
him up about it, whereas a wrong candidate is a line he dismisses in one
click. A due date the model read out of the mail is stored on the candidate,
where no scheduler reads it — the review page sorts by it. Relative wording
("до пятницы") is deliberately left in the text rather than resolved to a
date the model would get wrong.

The prompt is written against the two things a small model does here: it
summarises when asked to extract, and it invents an obligation out of a
polite closing line. Hence the demand for a verb phrase, and an explicit
empty array — most mail contains no task, and a model with no way to say
"nothing" says something.

Wiring: core owns extraction because llama-server lives in core's process,
so the reader hands messages over a new ipc.MethodIngestMail. It is a Server
hook (like StepUp/UnlockFn), not a CoreAPI method — not a store operation,
and no CoreAPI implementation should have to carry it. The hook stays nil
without an `email` config block or without a llama-server phraser, so the
method answers ErrUnknownMethod: off unless configured, twice over. There is
no keyword fallback on purpose — "the subject became a task" is a mailbox
rendered as a to-do list, not extraction.

Privacy: junk is refused before the model is called, mail text is never
search input, extraction errors carry byte counts rather than the reply, the
stored evidence is a truncated subject, and the log line names the mailbox
and the UID only.
2026-08-01 03:06:55 +04:00

183 lines
5.8 KiB
Go

package main
import (
"context"
"strings"
"testing"
"time"
"github.com/kami/maven/internal/config"
"github.com/kami/maven/internal/email"
"github.com/kami/maven/internal/ipc"
"github.com/kami/maven/internal/llm"
"github.com/kami/maven/internal/store"
)
// mailLLM — a canned extraction reply.
type mailLLM struct {
reply string
calls int
}
func (m *mailLLM) Complete(_ context.Context, _ llm.Req) (string, error) {
m.calls++
return m.reply, nil
}
func newTestIntake(t *testing.T, reply string) (*mailIntake, *store.Store, *mailLLM) {
t.Helper()
st := newTestStore(t)
fake := &mailLLM{reply: reply}
return &mailIntake{
st: st,
ex: email.NewExtractor(fake, 0, nil),
timeout: 5 * time.Second,
now: func() time.Time { return time.Date(2026, 8, 1, 10, 0, 0, 0, time.UTC) },
}, st, fake
}
func ingestReq() ipc.IngestMailReq {
return ipc.IngestMailReq{
Mailbox: "INBOX", UID: 42,
From: "billing@isp.example",
Subject: "Счёт за интернет",
Body: "Оплатите счёт до 5 августа.",
}
}
// The one property that matters: a mail-derived task is a candidate, attributed
// to the mailbox, with the subject as reviewable evidence — and nothing else is
// written.
func TestIngestCapturesCandidates(t *testing.T) {
mi, st, _ := newTestIntake(t, `[{"text":"оплатить счёт за интернет","due":"2026-08-05"}]`)
resp, err := mi.ingest(context.Background(), ingestReq())
if err != nil {
t.Fatalf("ingest: %v", err)
}
if resp.Created != 1 || len(resp.TaskIDs) != 1 {
t.Fatalf("resp = %+v, want one created task", resp)
}
tasks, err := st.ListTasks(context.Background(), "")
if err != nil {
t.Fatalf("list: %v", err)
}
if len(tasks) != 1 {
t.Fatalf("got %d tasks, want 1", len(tasks))
}
got := tasks[0]
if got.Status != store.TaskCandidate {
t.Errorf("status = %q, want %q — mail may only produce candidates", got.Status, store.TaskCandidate)
}
if got.Source != "email:INBOX" {
t.Errorf("source = %q, want email:INBOX", got.Source)
}
if got.Evidence != "Счёт за интернет" {
t.Errorf("evidence = %q, want the subject line", got.Evidence)
}
if got.Due == nil || got.Due.Format("2006-01-02") != "2026-08-05" {
t.Errorf("due = %v, want 2026-08-05", got.Due)
}
// Nothing else may have been written: no reminder, no fact.
rem, err := st.ListReminders(context.Background(), 10)
if err != nil {
t.Fatalf("list reminders: %v", err)
}
if len(rem) != 0 {
t.Errorf("mail created %d reminders; a misread mail must never be able to fire", len(rem))
}
}
// Re-reading a mailbox must not grow the list — CaptureTask dedupes among live
// rows, and the intake relies on exactly that.
func TestIngestSameMailTwiceIsIdempotent(t *testing.T) {
mi, st, _ := newTestIntake(t, `[{"text":"оплатить счёт","due":""}]`)
if _, err := mi.ingest(context.Background(), ingestReq()); err != nil {
t.Fatalf("first ingest: %v", err)
}
resp, err := mi.ingest(context.Background(), ingestReq())
if err != nil {
t.Fatalf("second ingest: %v", err)
}
if resp.Created != 0 || len(resp.TaskIDs) != 1 {
t.Errorf("resp = %+v, want the existing row and Created=0", resp)
}
tasks, _ := st.ListTasks(context.Background(), "")
if len(tasks) != 1 {
t.Errorf("got %d tasks after two reads, want 1", len(tasks))
}
}
func TestIngestJunkSkipsTheModel(t *testing.T) {
mi, st, fake := newTestIntake(t, `[{"text":"купить со скидкой","due":""}]`)
req := ingestReq()
req.Junk = true
resp, err := mi.ingest(context.Background(), req)
if err != nil {
t.Fatalf("ingest: %v", err)
}
if !resp.Skipped || resp.Created != 0 {
t.Errorf("resp = %+v, want skipped", resp)
}
if fake.calls != 0 {
t.Errorf("model called %d times for junk, want 0", fake.calls)
}
if tasks, _ := st.ListTasks(context.Background(), ""); len(tasks) != 0 {
t.Errorf("junk produced %d tasks, want 0", len(tasks))
}
}
func TestIngestEmptyMessageSkipped(t *testing.T) {
mi, _, fake := newTestIntake(t, "[]")
resp, err := mi.ingest(context.Background(), ipc.IngestMailReq{Mailbox: "INBOX", UID: 1})
if err != nil || !resp.Skipped {
t.Fatalf("resp = %+v, err = %v; want skipped", resp, err)
}
if fake.calls != 0 {
t.Errorf("model called %d times for an empty message, want 0", fake.calls)
}
}
func TestIngestNoTasksWritesNothing(t *testing.T) {
mi, st, _ := newTestIntake(t, "[]")
resp, err := mi.ingest(context.Background(), ingestReq())
if err != nil {
t.Fatalf("ingest: %v", err)
}
if resp.Created != 0 || len(resp.TaskIDs) != 0 || resp.Skipped {
t.Errorf("resp = %+v, want nothing captured and not skipped", resp)
}
if tasks, _ := st.ListTasks(context.Background(), ""); len(tasks) != 0 {
t.Errorf("got %d tasks, want 0", len(tasks))
}
}
func TestIngestTruncatesEvidence(t *testing.T) {
mi, st, _ := newTestIntake(t, `[{"text":"дело","due":""}]`)
req := ingestReq()
req.Subject = strings.Repeat("щ", 400)
if _, err := mi.ingest(context.Background(), req); err != nil {
t.Fatalf("ingest: %v", err)
}
tasks, _ := st.ListTasks(context.Background(), "")
if len(tasks) != 1 {
t.Fatalf("got %d tasks, want 1", len(tasks))
}
if n := len([]rune(tasks[0].Evidence)); n > evidenceMaxChars+1 {
t.Errorf("evidence kept %d runes, want ≤ %d", n, evidenceMaxChars)
}
}
// Off unless configured: no email block ⇒ no intake, so the IPC method does not
// exist at all.
func TestNewMailIntakeOffWithoutConfig(t *testing.T) {
st := newTestStore(t)
if mi := newMailIntake(st, nil, &config.Config{}); mi != nil {
t.Error("no email block must mean no mail intake")
}
// Configured but with a non-LLM phraser: still off — there is no fallback
// extraction, by design.
if mi := newMailIntake(st, nil, &config.Config{Email: &config.EmailConfig{}}); mi != nil {
t.Error("without a llama-server phraser there is nothing to extract with")
}
}