Initial commit: goodNews constructive-news ingestion prototype

Local-first RSS/Atom ingestion pipeline with metadata-only storage, heuristic + local-LLM scoring, and daily brief builder. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-05-30 00:48:26 +00:00
commit 068073423f
14 changed files with 1722 additions and 0 deletions
@@ -0,0 +1,169 @@
+from __future__ import annotations
+
+import re
+
+
+POSITIVE_TERMS = {
+    "breakthrough",
+    "progress",
+    "improve",
+    "improves",
+    "improved",
+    "solution",
+    "solutions",
+    "recovery",
+    "restore",
+    "restores",
+    "rescued",
+    "rescue",
+    "volunteer",
+    "community",
+    "donate",
+    "donation",
+    "cure",
+    "treatment",
+    "therapy",
+    "clean energy",
+    "renewable",
+    "conservation",
+    "protect",
+    "protects",
+    "restoration",
+    "kindness",
+    "hope",
+    "first",
+    "record",
+}
+
+AGENCY_TERMS = {
+    "how",
+    "helps",
+    "helping",
+    "protect",
+    "protects",
+    "builds",
+    "creates",
+    "launches",
+    "teaches",
+    "learn",
+    "guide",
+    "tool",
+    "program",
+    "initiative",
+    "effort",
+    "plan",
+    "rebuild",
+}
+
+CORTISOL_TERMS = {
+    "war",
+    "killed",
+    "dead",
+    "death",
+    "murder",
+    "shooting",
+    "attack",
+    "crisis",
+    "catastrophe",
+    "disaster",
+    "collapse",
+    "panic",
+    "warning",
+    "threat",
+    "fear",
+    "fears",
+    "lawsuit",
+    "scandal",
+}
+
+RAGEBAIT_TERMS = {
+    "slams",
+    "blasts",
+    "furious",
+    "outrage",
+    "rage",
+    "shocking",
+    "you won't believe",
+    "sparks backlash",
+    "destroyed",
+    "humiliates",
+}
+
+PR_TERMS = {
+    "announces",
+    "unveils",
+    "funding round",
+    "raises",
+    "partnership",
+    "brand",
+    "sponsored",
+    "press release",
+}
+
+WORD_RE = re.compile(r"[a-z0-9']+")
+
+
+def _count_terms(text: str, terms: set[str]) -> int:
+    lowered = text.lower()
+    words = set(WORD_RE.findall(lowered))
+    count = 0
+    for term in terms:
+        if " " in term:
+            count += 1 if term in lowered else 0
+        elif term in words:
+            count += 1
+    return count
+
+
+def score_article(title: str, description: str | None, source_pr_risk: int) -> dict:
+    text = f"{title}. {description or ''}"
+    positive = _count_terms(text, POSITIVE_TERMS)
+    agency = _count_terms(text, AGENCY_TERMS)
+    cortisol = _count_terms(text, CORTISOL_TERMS)
+    ragebait = _count_terms(text, RAGEBAIT_TERMS)
+    pr_terms = _count_terms(text, PR_TERMS)
+
+    constructive_score = min(10, 2 + positive * 2 + agency)
+    agency_score = min(10, 1 + agency * 2)
+    cortisol_score = min(10, cortisol * 3)
+    ragebait_score = min(10, ragebait * 4)
+    pr_risk_score = min(10, source_pr_risk + pr_terms * 2)
+    human_benefit_score = min(10, positive * 2 + agency)
+    novelty_score = 5
+
+    accepted = (
+        constructive_score >= 5
+        and cortisol_score <= 5
+        and ragebait_score <= 3
+        and pr_risk_score <= 7
+    )
+
+    if accepted:
+        reason_code = "heuristic_constructive_candidate"
+        reason_text = "Constructive or agency-oriented language with low obvious cortisol/ragebait signals."
+    elif ragebait_score > 3:
+        reason_code = "heuristic_reject_ragebait_language"
+        reason_text = "Headline or snippet contains outrage-oriented language."
+    elif cortisol_score > 5:
+        reason_code = "heuristic_reject_cortisol_heavy"
+        reason_text = "Headline or snippet appears tragedy, threat, conflict, or crisis centered."
+    elif pr_risk_score > 7:
+        reason_code = "heuristic_reject_pr_risk"
+        reason_text = "Headline or source has signs of corporate PR framing."
+    else:
+        reason_code = "heuristic_needs_review"
+        reason_text = "Not enough constructive signal for automatic acceptance."
+
+    return {
+        "constructive_score": constructive_score,
+        "cortisol_score": cortisol_score,
+        "ragebait_score": ragebait_score,
+        "agency_score": agency_score,
+        "human_benefit_score": human_benefit_score,
+        "novelty_score": novelty_score,
+        "pr_risk_score": pr_risk_score,
+        "accepted": 1 if accepted else 0,
+        "reason_code": reason_code,
+        "reason_text": reason_text,
+        "model_name": "heuristic-v0",
+    }