KOL feeds: fix dead/blocked sources, drop stale feeds (29→25)

Feed-health pass over KOL_FEEDS:
- raoulpal: stale Substack (last 2024-05) → Real Vision podcast feed
- dampedspring: paywalled (0 entries) → free "Damped Spring 101" Substack
- unchained: Cloudflare 403 → canonical Megaphone podcast feed
- lynalden: Cloudflare 202 → FeedBurner mirror
- glassnode: recovered via httpx http2=True (was 403 on HTTP/1.1)
- browser User-Agent + Accept headers on feed fetch
- removed dead feeds with no active replacement: placeholder,
  dragonfly, niccarter, eugene
- pin h2==4.3.0 (required by http2=True)

All 25 remaining feeds verified fetching real body content; newest
post per feed ≤88d. Bundles in-flight KOL-module work already in the
working tree (kol_x ingest, migration 027, tests).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
k
2026-06-09 22:55:16 +08:00
parent 213bb911e3
commit 54884f3e24
38 changed files with 2340 additions and 322 deletions
+272
View File
@@ -0,0 +1,272 @@
"""Tests for the X (Twitter) KOL ingester (kol_x).
The twitterapi.io fetch and the AI scorer are mocked so we exercise the
storage / dedup / mapping logic deterministically — no network, no AI spend.
The contract these lock down:
- tweets land as KolPost(source="twitter")
- kol_handle is the CANONICAL handle (joins to KolWallet), not the X username
- bare retweets are skipped before scoring
- tickers_json keeps the {ticker, action, conviction} shape kol_divergence reads
- tier / post_type / talks_vs_trades_flag / sentiment are persisted (migration 027)
- re-running is idempotent (dedup by tweet id)
- page-level early-stop fires when a full page is all-dedup
- no twitterapi key → full no-op
"""
from __future__ import annotations
import json
from typing import AsyncGenerator
import pytest
from sqlalchemy import select
from sqlalchemy.ext.asyncio import (
AsyncSession, async_sessionmaker, create_async_engine,
)
from app.config import settings
from app.models import Base, KolPost
from app.services import kol_x
_FAKE_TWEETS = [
{ # actionable position statement → should be stored + scored
"id": "111",
"text": "I just dumped my entire $HYPE position",
"url": "https://x.com/CryptoHayes/status/111",
"createdAt": "Thu Jun 04 05:49:13 +0000 2026",
"author": {"followers": 797330},
},
{ # bare retweet → skipped before the AI call
"id": "222",
"text": "RT @someone: not my words",
"createdAt": "Thu Jun 04 06:00:00 +0000 2026",
"author": {"followers": 797330},
},
{ # low-signal but original → stored (AI decides noise/not)
"id": "333",
"text": "gm crypto fam",
"createdAt": "Thu Jun 04 07:00:00 +0000 2026",
"author": {"followers": 797330},
},
]
_FAKE_SCORE = {
"post_type": "original",
"tier": "trade_signal",
"summary": "Dumped HYPE",
"tickers": [{"ticker": "HYPE", "action": "sell", "conviction": 0.95}],
"talks_vs_trades_flag": True,
"sentiment": "bearish",
"model": "test-model",
"version": "x-test",
"error": None,
}
_KOL = {"handle": "cryptohayes", "x_username": "CryptoHayes", "display_name": "Hayes"}
async def _fresh_session_factory():
"""Each test gets its own isolated in-memory DB."""
engine = create_async_engine("sqlite+aiosqlite:///:memory:", future=True)
async with engine.begin() as conn:
await conn.run_sync(Base.metadata.create_all)
return async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False)
def _make_page_iter(pages: list[list[dict]]):
"""Return an async generator that yields one page at a time from `pages`."""
async def fake_iter(_username, max_pages=3) -> AsyncGenerator[list[dict], None]:
for page in pages:
yield page
return fake_iter
def _patch_io(monkeypatch, pages: list[list[dict]] | None = None):
if pages is None:
pages = [list(_FAKE_TWEETS)] # one page containing all fake tweets
async def fake_score(**_kw):
return dict(_FAKE_SCORE)
monkeypatch.setattr(settings, "twitterapi_io_key", "test-key")
monkeypatch.setattr(kol_x, "_iter_tweet_pages", _make_page_iter(pages))
monkeypatch.setattr(kol_x.x_analysis, "analyze_x_post", fake_score)
# ── Core contract ─────────────────────────────────────────────────────────────
@pytest.mark.asyncio
async def test_run_x_poll_noop_without_key(monkeypatch):
monkeypatch.setattr(settings, "twitterapi_io_key", "")
assert await kol_x.run_x_poll() == []
@pytest.mark.asyncio
async def test_ingest_writes_divergence_ready_kolposts(monkeypatch):
_patch_io(monkeypatch)
sf = await _fresh_session_factory()
async with sf() as s:
stats = await kol_x._ingest_kol_x(s, _KOL)
# 111 + 333 stored; 222 (bare RT) skipped before scoring
assert stats["new"] == 2
assert stats["skipped"] == 1
assert stats["analyzed"] == 2
assert stats["errors"] == 0
rows = (await s.execute(
select(KolPost).where(KolPost.source == "twitter")
)).scalars().all()
assert {r.external_id for r in rows} == {"111", "333"}
# canonical handle (joins to KolWallet), NOT the X screen name
assert all(r.kol_handle == "cryptohayes" for r in rows)
signal = next(r for r in rows if r.external_id == "111")
tk = json.loads(signal.tickers_json)
assert tk[0]["ticker"] == "HYPE"
assert tk[0]["action"] == "sell" # in kol_divergence._POST_SHORT
assert tk[0]["conviction"] == 0.95
assert signal.analysis_model == "test-model"
assert signal.analysis_version == "x-test"
# published_at parsed from the X date string into a naive datetime
assert signal.published_at.year == 2026 and signal.published_at.month == 6
@pytest.mark.asyncio
async def test_ingest_stores_extended_analysis_fields(monkeypatch):
"""migration 027 fields — tier / post_type / talks_vs_trades_flag / sentiment."""
_patch_io(monkeypatch)
sf = await _fresh_session_factory()
async with sf() as s:
await kol_x._ingest_kol_x(s, _KOL)
signal = (await s.execute(
select(KolPost).where(KolPost.external_id == "111")
)).scalar_one()
assert signal.tier == "trade_signal"
assert signal.post_type == "original"
assert signal.talks_vs_trades_flag is True
assert signal.sentiment == "bearish"
@pytest.mark.asyncio
async def test_ingest_is_idempotent_on_rerun(monkeypatch):
_patch_io(monkeypatch)
sf = await _fresh_session_factory()
async with sf() as s:
first = await kol_x._ingest_kol_x(s, _KOL)
second = await kol_x._ingest_kol_x(s, _KOL)
assert first["new"] == 2
assert second["new"] == 0 # everything already stored
assert second["skipped"] == 3 # 2 existing + 1 bare RT
@pytest.mark.asyncio
async def test_fetch_failure_does_not_raise(monkeypatch):
"""A dead/blocked KOL must not abort the run — empty pages → empty stats."""
monkeypatch.setattr(settings, "twitterapi_io_key", "test-key")
_patch_io(monkeypatch, pages=[]) # generator yields nothing
sf = await _fresh_session_factory()
async with sf() as s:
stats = await kol_x._ingest_kol_x(s, _KOL)
assert stats["new"] == 0 and stats["errors"] == 0
# ── Multi-page & early-stop ───────────────────────────────────────────────────
@pytest.mark.asyncio
async def test_multipage_fetches_all_new_tweets(monkeypatch):
"""Two pages of distinct tweets → both pages are stored."""
page1 = [{"id": "p1_1", "text": "SOL is the play", "createdAt": "Thu Jun 04 05:00:00 +0000 2026", "author": {"followers": 100000}}]
page2 = [{"id": "p2_1", "text": "ETH too slow ngmi", "createdAt": "Wed Jun 03 10:00:00 +0000 2026", "author": {"followers": 100000}}]
_patch_io(monkeypatch, pages=[page1, page2])
sf = await _fresh_session_factory()
async with sf() as s:
stats = await kol_x._ingest_kol_x(s, _KOL)
assert stats["new"] == 2
@pytest.mark.asyncio
async def test_early_stop_when_page_fully_deduped(monkeypatch):
"""After page1 is stored, a second run should detect all-dedup on page1
and break before page2 is consumed — verified by keeping a 'new' tweet
on page2 that must NOT appear in the DB if early-stop fired correctly."""
page1 = [{"id": "old1", "text": "BTC to the moon",
"createdAt": "Thu Jun 04 05:00:00 +0000 2026", "author": {}}]
page2 = [{"id": "brand_new", "text": "Sold everything",
"createdAt": "Wed Jun 03 09:00:00 +0000 2026", "author": {}}]
run = 0
pages_yielded: list[list] = []
async def counting_iter(_username, max_pages=3):
nonlocal run
run += 1
if run == 1:
# First run: only page1 (simulates single-page normal daily run)
pages_yielded.append(page1)
yield page1
else:
# Second run: both pages available, but early-stop should fire at page1
for page in [page1, page2]:
pages_yielded.append(page)
yield page
async def fake_score(**_kw):
return dict(_FAKE_SCORE)
monkeypatch.setattr(settings, "twitterapi_io_key", "test-key")
monkeypatch.setattr(kol_x, "_iter_tweet_pages", counting_iter)
monkeypatch.setattr(kol_x.x_analysis, "analyze_x_post", fake_score)
sf = await _fresh_session_factory()
async with sf() as s:
first = await kol_x._ingest_kol_x(s, _KOL)
assert first["new"] == 1 # page1 stored (1 tweet)
pages_yielded.clear()
second = await kol_x._ingest_kol_x(s, _KOL)
assert second["new"] == 0 # page1 all deduped → early stop
# Only page1 should have been yielded — early-stop broke before page2
assert pages_yielded == [page1]
# page2's tweet must NOT be in the DB (generator closed before it was yielded)
rows = (await s.execute(
select(KolPost).where(KolPost.source == "twitter")
)).scalars().all()
assert {r.external_id for r in rows} == {"old1"}
@pytest.mark.asyncio
async def test_all_retweet_page_does_not_early_stop(monkeypatch):
"""A page that is ALL bare retweets (page_new=0, page_deduped=0) must NOT
trigger early-stop — the next page can still hold original posts. Regression
guard: previously 'page_new == 0' alone stopped paging on RT-heavy pages,
silently dropping originals on older pages."""
page1 = [
{"id": "rt1", "text": "RT @a: gm", "createdAt": "Thu Jun 04 05:00:00 +0000 2026", "author": {}},
{"id": "rt2", "text": "RT @b: wagmi", "createdAt": "Thu Jun 04 04:00:00 +0000 2026", "author": {}},
]
page2 = [
{"id": "orig1", "text": "Just sold all my $SOL", "createdAt": "Wed Jun 03 09:00:00 +0000 2026", "author": {}},
]
_patch_io(monkeypatch, pages=[page1, page2])
sf = await _fresh_session_factory()
async with sf() as s:
stats = await kol_x._ingest_kol_x(s, _KOL)
# page1 all-RT → skipped 2, NO early-stop → page2 consumed → orig1 stored
assert stats["new"] == 1
assert stats["skipped"] == 2
rows = (await s.execute(
select(KolPost).where(KolPost.source == "twitter")
)).scalars().all()
assert {r.external_id for r in rows} == {"orig1"}