Add /tldr: a private overview of what you missed in a channel

/tldr [since] summarizes the messages in the channel it is run in that the
caller has not been summarized yet, using a small local model on Ollama, and
replies ephemerally. The answer streams into the reply as it is written.

- Per-user, per-channel cursor (tldr_cursors) so each run picks up where the
  last left off; `since:` (e.g. 6h, 2d, max 7d) peeks without moving it.
  First use covers the last 24h, and a stale cursor never reaches back more
  than 7 days.
- Only summarizes channels both the caller and the bot can read.
- The transcript drops bots, system messages, reactions and filler, turns
  links, GIFs, images and files into short tags ([link: site], [image],
  [file: name], preview titles), marks replies, and writes a date marker
  where the chat paused for 3h or more so the model can keep topics apart.
- The prompt asks for one bullet per conversation, oldest first, with a
  worked example; it was tuned against a synthetic chat and a real export
  with qwen3:4b-instruct-2507 (the default model).
- One model call at a time across the bot, one /tldr per user.
- docker-compose: Ollama service (CPU only, 8g memory cap: 6g killed the
  runner mid-request), model pull on startup.

Needs the tldr_cursors migration (velox-dashboard-api 000016).

Co-Authored-By: Claude Opus 5.5 <[email protected]>

internal/tldr/fetch.go

@@ -0,0 +1,46 @@
+package tldr
+
+import (
+	"sort"
+
+	"github.com/bwmarrin/discordgo"
+)
+
+type MessageFetcher interface {
+	ChannelMessages(channelID string, limit int, beforeID, afterID, aroundID string, options ...discordgo.RequestOption) ([]*discordgo.Message, error)
+}
+
+// FetchAfter pages forward from afterID and returns up to limit messages,
+// oldest first. Discord returns the messages immediately following the ID,
+// so paging with the newest ID of each batch walks toward the present.
+func FetchAfter(f MessageFetcher, channelID, afterID string, limit int) ([]*discordgo.Message, error) {
+	var all []*discordgo.Message
+	after := afterID
+
+	for len(all) < limit {
+		want := min(100, limit-len(all))
+		batch, err := f.ChannelMessages(channelID, want, "", after, "")
+		if err != nil {
+			return nil, err
+		}
+		if len(batch) == 0 {
+			break
+		}
+
+		newest := batch[0].ID
+		for _, m := range batch {
+			if CompareIDs(m.ID, newest) > 0 {
+				newest = m.ID
+			}
+		}
+		all = append(all, batch...)
+		after = newest
+
+		if len(batch) < want {
+			break
+		}
+	}
+
+	sort.Slice(all, func(i, j int) bool { return CompareIDs(all[i].ID, all[j].ID) < 0 })
+	return all, nil
+}