Initial commit

internal/classifier/prompts.go

@@ -0,0 +1,110 @@
+package classifier
+
+import (
+	"fmt"
+	"strings"
+
+	"pete/internal/ingestion"
+	"pete/internal/storage"
+)
+
+// BuildTier1Prompt builds the routing-only prompt for Tier 1 stories.
+func BuildTier1Prompt(item *ingestion.FeedItem, recent []storage.RecentHeadline) string {
+	return fmt.Sprintf(`You are a news router for a community discussion platform with three channels: tech, politics, and gaming.
+
+This story comes from a curated Tier 1 source. It will be posted. Your only job is to decide which channel it belongs in.
+
+Choose exactly one channel:
+- tech: technology products, software, hardware, industry — where technology itself is the primary subject
+- gaming: games, gaming platforms, gaming industry, esports
+- politics: everything else — political, policy, current events, public interest, significant world events
+
+Politics is the default. When in doubt, choose politics.
+
+Routing guidance:
+- GPU launch, software release, hardware review → tech
+- Game release, platform announcement, studio news → gaming
+- Election, legislation, court ruling → politics
+- AI regulation, antitrust action, surveillance policy → politics (policy is the story, not the technology)
+- Death of a public figure → politics
+- Violent crime, assassination attempt, arrest of public figure → politics
+- Natural disaster, humanitarian crisis → politics
+- Celebrity gossip, lifestyle with no broader significance → politics (still gets posted, still needs a home)
+
+For gaming stories only: identify which platforms are relevant from this list:
+nintendo-switch, playstation, xbox, pc, retro, mobile, multi
+Return an empty array if no specific platform applies.
+
+Also check: does this story cover the same underlying event as any story in the recent window? Different outlets covering the same event counts as a duplicate. If yes, set duplicate_of to that story's GUID. If no match, set duplicate_of to null.
+
+Respond ONLY with valid JSON. No preamble, no explanation outside the JSON:
+{
+  "channel": "tech|politics|gaming",
+  "platforms": [string],
+  "duplicate_of": string | null,
+  "rationale": "one sentence max, for logging only"
+}
+
+INCOMING STORY:
+Source: %s
+Tier: %d
+Feed hint: %s
+Headline: %s
+Lede: %s
+
+RECENT STORIES (last 24hr):
+%s`, item.Source, item.Tier, item.FeedHint, item.Headline, item.Lede, formatRecentStories(recent))
+}
+
+// BuildTier2Prompt builds the gating + routing prompt for Tier 2 stories.
+func BuildTier2Prompt(item *ingestion.FeedItem, recent []storage.RecentHeadline) string {
+	return fmt.Sprintf(`You are a news classifier for a community discussion platform with three channels: tech, politics, and gaming.
+
+This story comes from a wire service. Unlike curated sources, wire feeds publish everything — not all stories warrant posting. First decide if this story is worth posting, then decide where.
+
+Step 1 — Should this be posted?
+Post if the story has clear public significance: major world events, policy decisions, significant deaths, natural disasters, major technology developments. Do not post: local news with no broader relevance, routine financial filings, minor sports results, entertainment fluff.
+
+Step 2 — If posting, choose exactly one channel:
+- tech: technology products, software, hardware, industry
+- gaming: games, gaming platforms, gaming industry
+- politics: everything else — the default
+
+Politics is the default when in doubt.
+
+For gaming stories only: identify relevant platforms from: nintendo-switch, playstation, xbox, pc, retro, mobile, multi
+
+Also check for duplicates against the recent window. If this story covers the same underlying event as a recent story, set duplicate_of to that story's GUID.
+
+Respond ONLY with valid JSON:
+{
+  "post": true|false,
+  "channel": "tech|politics|gaming",
+  "platforms": [string],
+  "duplicate_of": string | null,
+  "rationale": "one sentence max, for logging only"
+}
+
+If post is false, channel may be omitted.
+
+INCOMING STORY:
+Source: %s
+Tier: %d
+Feed hint: %s
+Headline: %s
+Lede: %s
+
+RECENT STORIES (last 24hr):
+%s`, item.Source, item.Tier, item.FeedHint, item.Headline, item.Lede, formatRecentStories(recent))
+}
+
+func formatRecentStories(recent []storage.RecentHeadline) string {
+	if len(recent) == 0 {
+		return "(none)"
+	}
+	var sb strings.Builder
+	for _, h := range recent {
+		fmt.Fprintf(&sb, "[%s] %s — %s\n", h.GUID, h.Headline, h.Source)
+	}
+	return sb.String()
+}