Read RSS and Atom feeds, and speak about them only when asked (#258)

internal/rss parses RSS 2.0 and Atom, and polls each configured feed on its own
interval; internal/webfetch is the one door either of them uses to touch the
network. The poller writes items as notes with source "rss:<feed>" and nothing
else: the answer path reads them back when he asks "что нового в лентах?", and
nothing is announced on arrival. A feed that dispatched would be a nag, which is
why the plan's breaking-news rule was left out rather than built.

webfetch is where the limits live, as code rather than a paragraph: http(s)
only, an allowlist (the configured feeds' hosts) and a denylist, a 2 MiB body
cap, a 3-redirect cap, one request per host per second, and a refusal to connect
to any private address — checked in the dialer's Control hook so it holds for
every resolved address and every redirect hop, not just for a literal IP.

Off unless configured: no "feeds" block, no poller, no outbound request. How far
a feed was read is a config fact (rss:latest:<name>), so a restart does not
re-note yesterday's headlines.
This commit is contained in:
kami
2026-08-01 03:27:45 +04:00
parent ee7bec11e3
commit cb3641e7bb
17 changed files with 2069 additions and 0 deletions
+63
View File
@@ -12,6 +12,7 @@ import (
"github.com/kami/maven/internal/memory"
"github.com/kami/maven/internal/morning"
"github.com/kami/maven/internal/router"
"github.com/kami/maven/internal/rss"
"github.com/kami/maven/internal/weather"
)
@@ -67,6 +68,11 @@ var querySources = []querySource{
// answer it from whatever he once said about spending. Its matcher needs a
// money noun plus an actual ask, so "я потратил весь день" is untouched.
{"money", (*reactiveHandler).queryMoney},
// Before the recall sources and before general knowledge: "что нового?" is
// a question about the feeds she reads, and general knowledge would answer
// it by inventing news. Its matcher needs a feed noun plus an ask, so
// "у меня новая лента в инстаграме" is untouched.
{"feeds", (*reactiveHandler).queryFeeds},
{"calendar", (*reactiveHandler).queryCalendar},
{"weather", (*reactiveHandler).queryWeather},
{"embed", (*reactiveHandler).queryEmbed},
@@ -180,6 +186,63 @@ func (h *reactiveHandler) queryHabits(ctx context.Context, t *queryTurn) (string
return profile.FormatOverallRU(), true
}
// feedNoteWindow — how many recent notes are scanned for feed items, and
// feedReadOut — how many headlines she actually reads back. She summarises the
// top of the pile, she does not recite a river.
const (
feedNoteWindow = 200
feedReadOut = 3
)
// queryFeeds — "что нового в лентах?", "что нового по технологиям?"
// (Vikunja #258).
//
// This is the ONLY way a feed item reaches him. The poller writes notes and
// never speaks; asking is the trigger. If that ever changes, the thing that
// changed is "Maven is not a nag", not a detail of this file.
func (h *reactiveHandler) queryFeeds(ctx context.Context, t *queryTurn) (string, bool) {
q, ok := router.ParseFeedQuery(t.dec.Utterance)
if !ok {
return "", false
}
if !h.feedsOn {
// Claim the turn rather than fall through: "не читаю ленты" is true, and
// letting general knowledge answer "что нового?" would be an invented
// news bulletin.
return "я пока не читаю ленты — они не настроены.", true
}
notes, err := h.api.RecentNotes(ctx, feedNoteWindow)
if err != nil {
log.Printf("voice: feeds: recent notes: %v", err)
return "не получилось посмотреть ленты.", true
}
var picked []string
for _, n := range notes {
if !strings.HasPrefix(n.Source, rss.SourcePrefix) {
continue
}
if !router.CategoryMatches(n.Text, q.Category) {
continue
}
// The note carries title, summary and link; she reads the title.
title := n.Text
if i := strings.IndexByte(title, '\n'); i > 0 {
title = title[:i]
}
picked = append(picked, strings.TrimSpace(title))
if len(picked) == feedReadOut {
break
}
}
if len(picked) == 0 {
if q.Category != "" {
return "по этой теме в лентах пока ничего.", true
}
return "в лентах пока ничего нового.", true
}
return "вот что нового: " + strings.Join(picked, "; "), true
}
// queryCalendar — "что у меня сегодня?", "планы на завтра?"
// h.now(), not time.Now(): the handler's clock is the injected one, so this
// source can be tested at a fixed time like the rest.