Maven/cmd/mavend/mail.go

// mavend/mail.go — core's half of the email reader (Vikunja #246,
// docs/plans/01-email-reader.md).
//
// The split: cmd/mavmaild holds the IMAP credential, connects to the mailbox
// and converts messages to plaintext; it hands each message to core over
// ipc.MethodIngestMail. Core runs the extraction on the resident model —
// llama-server lives in this process, spawned by the phraser — and writes what
// comes back through the one task intake seam.
//
// What this file may produce is exactly one thing: rows in `tasks` with status
// "candidate". No fact, no reminder, no note, no nudge, no calendar event. A
// 1.7B misreading a mail can therefore put a wrong line on a review page and
// nothing else; it can never make Maven speak, and it can never make her
// recite something out of an advert as true.
//
// Off unless configured twice over: no `email` block in mavend.json ⇒ the IPC
// method does not exist; no llama-server phraser ⇒ same. A reader pointed at a
// core that is not set up for mail gets ErrUnknownMethod rather than silence.
package main

import (
	"context"
	"fmt"
	"log"
	"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/phraser"
	"github.com/kami/maven/internal/store"
)

// evidenceMaxChars — how much of the subject line is kept as a candidate's
// evidence. Enough to recognise the mail on /tasks, not enough to turn the task
// list into a copy of his mailbox.
const evidenceMaxChars = 160

// mailIntake — extraction + capture for one message at a time.
type mailIntake struct {
	st      *store.Store
	ex      *email.Extractor
	timeout time.Duration
	now     func() time.Time
}

// newMailIntake returns nil when mail ingestion must not be available, which is
// the default. Both preconditions are real:
//
//   - no cfg.Email ⇒ not configured, and a capability is off unless configured;
//   - no llama-server phraser ⇒ nothing to extract with. There is deliberately
//     no keyword fallback: "the subject line became a task" is not extraction,
//     it is a mailbox rendered as a to-do list, and it would fill the review
//     page faster than he could clear it.
func newMailIntake(st *store.Store, phr phraser.Phraser, cfg *config.Config) *mailIntake {
	if cfg.Email == nil {
		return nil
	}
	lp, ok := phr.(*phraser.LLMPhraser)
	if !ok {
		log.Printf("mail intake: configured but no llama-server phraser — mail ingestion disabled")
		return nil
	}
	timeout := time.Duration(cfg.Email.Timeout)
	if timeout <= 0 {
		timeout = config.DefaultEmailTimeout
	}
	ex := email.NewExtractor(llm.New(lp.BaseURL(), timeout), cfg.Email.MaxTasks, contextBlockFn(cfg, time.Now))
	log.Printf("mail intake: enabled (max %d candidates per message, timeout %s)", cfg.Email.MaxTasks, timeout)
	return &mailIntake{st: st, ex: ex, timeout: timeout, now: time.Now}
}

// ingest handles one ipc.MethodIngestMail call.
//
// Junk and empty messages are answered Skipped without touching the model — the
// reader's header filter is what keeps the resident model off newsletters.
//
// Every candidate is captured with Status "candidate", Source "email:<mailbox>"
// and the subject as Evidence. CaptureTask dedupes on normalised text among
// live rows, so a mailbox re-read after a restart produces Created=0 rather
// than a second copy of every task.
func (m *mailIntake) ingest(ctx context.Context, req ipc.IngestMailReq) (ipc.IngestMailResp, error) {
	msg := email.Message{
		UID:     req.UID,
		From:    req.From,
		Subject: req.Subject,
		Date:    req.Date,
		Body:    req.Body,
		Junk:    req.Junk,
	}
	if msg.Junk || (msg.Subject == "" && msg.Body == "") {
		return ipc.IngestMailResp{Skipped: true}, nil
	}

	ctx, cancel := context.WithTimeout(ctx, m.timeout)
	defer cancel()
	cands, err := m.ex.Extract(ctx, msg)
	if err != nil {
		// The error from internal/email never carries mail text; keep it that way
		// by not adding the subject here.
		return ipc.IngestMailResp{}, fmt.Errorf("mail intake: uid %d: %w", req.UID, err)
	}
	if len(cands) == 0 {
		return ipc.IngestMailResp{}, nil
	}

	source := email.SourcePrefix + req.Mailbox
	evidence := truncateRunes(req.Subject, evidenceMaxChars)
	now := m.now()
	var resp ipc.IngestMailResp
	for _, c := range cands {
		t := store.Task{
			CreatedTs: now,
			Text:      c.Text,
			Source:    source,
			Evidence:  evidence,
			// The one status this path may ever write. Anything Maven derived from
			// something she read is a suggestion until he confirms it on /tasks.
			Status: store.TaskCandidate,
		}
		if due, ok := email.ParseDue(c.Due); ok {
			t.Due = &due
		}
		id, created, err := m.st.CaptureTask(ctx, t)
		if err != nil {
			return resp, fmt.Errorf("mail intake: capture: %w", err)
		}
		resp.TaskIDs = append(resp.TaskIDs, id)
		if created {
			resp.Created++
		}
	}
	// Counts only: the log line names the mailbox and the UID, never the subject,
	// the sender or the task text. Reviewing a candidate is what /tasks is for.
	log.Printf("mail intake: %s uid %d → %d candidate(s), %d new", source, req.UID, len(cands), resp.Created)
	return resp, nil
}

// wireMailIntake installs the IPC hook, or leaves it nil so the method reports
// ErrUnknownMethod. Called on both startup paths (unlocked boot and passkey
// unlock) so mail behaves the same either way.
func wireMailIntake(srv *ipc.Server, st *store.Store, phr phraser.Phraser, cfg *config.Config) {
	mi := newMailIntake(st, phr, cfg)
	if mi == nil {
		return
	}
	srv.IngestMailFn = mi.ingest
}

// truncateRunes cuts a string to n runes, marking the cut.
func truncateRunes(s string, n int) string {
	r := []rune(s)
	if len(r) <= n {
		return s
	}
	return string(r[:n]) + "…"
}