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"}
+232
View File
@@ -0,0 +1,232 @@
from __future__ import annotations
from datetime import datetime, timedelta
import pytest
from fastapi import FastAPI
from httpx import ASGITransport, AsyncClient
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
from app.api.posts import router as posts_router
from app.database import get_db
from app.models import Base, Post
@pytest.mark.asyncio
async def test_posts_paged_filters_and_counts():
engine = create_async_engine("sqlite+aiosqlite:///:memory:", future=True)
session_factory = async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False)
async with engine.begin() as conn:
await conn.run_sync(Base.metadata.create_all)
now = datetime(2026, 5, 30, 12, 0, 0)
async with session_factory() as session:
session.add_all([
Post(
external_id="truth-buy",
text="Bullish signal",
source="truth",
published_at=now,
sentiment="bullish",
signal="buy",
ai_confidence=91,
ai_reasoning="AI saw upside",
relevant=True,
),
Post(
external_id="truth-short",
text="Bearish signal",
source="truth",
published_at=now - timedelta(minutes=1),
sentiment="bearish",
signal="short",
ai_confidence=88,
ai_reasoning="AI saw downside",
relevant=True,
),
Post(
external_id="truth-hold",
text="Neutral but scored",
source="truth",
published_at=now - timedelta(minutes=2),
sentiment="neutral",
signal="hold",
ai_confidence=45,
ai_reasoning="No trade edge",
relevant=True,
),
Post(
external_id="truth-noise",
text="Off-topic golf post",
source="truth",
published_at=now - timedelta(minutes=3),
sentiment="neutral",
signal=None,
ai_confidence=0,
ai_reasoning=None,
relevant=False,
),
Post(
external_id="macro-buy",
text="Macro buy",
source="btc_bottom_reversal",
published_at=now - timedelta(minutes=4),
sentiment="bullish",
signal="buy",
ai_confidence=97,
ai_reasoning="Macro setup",
relevant=True,
),
Post(
external_id="archive-breakout",
text="Legacy breakout signal",
source="breakout",
published_at=now - timedelta(minutes=5),
sentiment="bullish",
signal="buy",
ai_confidence=73,
ai_reasoning="Old scanner",
relevant=True,
),
Post(
external_id="archive-sma",
text="Legacy sma reclaim signal",
source="sma_reclaim",
published_at=now - timedelta(minutes=6),
sentiment="bullish",
signal="short",
ai_confidence=64,
ai_reasoning="Old scanner 2",
relevant=True,
),
])
await session.commit()
app = FastAPI()
app.include_router(posts_router, prefix="/api")
async def override_get_db():
async with session_factory() as session:
yield session
app.dependency_overrides[get_db] = override_get_db
transport = ASGITransport(app=app)
async with AsyncClient(transport=transport, base_url="http://testserver") as client:
res = await client.get("/api/posts-paged", params={"source": "truth", "limit": 10, "page": 1})
assert res.status_code == 200
data = res.json()
assert data["total"] == 4
assert len(data["items"]) == 4
assert data["counts"] == {
"all": 4,
"actionable": 2,
"buy": 1,
"short": 1,
"off_topic": 1,
}
assert data["source_counts"] == [{"source": "truth", "count": 4, "latest": "2026-05-30T12:00:00.000Z"}]
actionable = await client.get(
"/api/posts-paged",
params={"source": "truth", "signal": "actionable", "limit": 10, "page": 1},
)
assert actionable.status_code == 200
actionable_data = actionable.json()
assert actionable_data["total"] == 2
assert {item["signal"] for item in actionable_data["items"]} == {"buy", "short"}
assert actionable_data["counts"]["all"] == 4
scored_only = await client.get(
"/api/posts-paged",
params={"source": "truth", "ai_scored_only": "true", "limit": 10, "page": 1},
)
assert scored_only.status_code == 200
scored_data = scored_only.json()
assert scored_data["total"] == 3
assert all(item["ai_confidence"] > 0 or item["ai_reasoning"] for item in scored_data["items"])
assert scored_data["counts"] == {
"all": 3,
"actionable": 2,
"buy": 1,
"short": 1,
"off_topic": 1,
}
bearish_buy = await client.get(
"/api/posts-paged",
params={
"source": "truth",
"sentiment": "bearish",
"signal": "buy",
"limit": 10,
"page": 1,
},
)
assert bearish_buy.status_code == 200
bearish_buy_data = bearish_buy.json()
assert bearish_buy_data["total"] == 0
assert bearish_buy_data["counts"] == {
"all": 1,
"actionable": 1,
"buy": 0,
"short": 1,
"off_topic": 0,
}
archive = await client.get(
"/api/posts-paged",
params={
"archive_only": "true",
"limit": 10,
"page": 1,
},
)
assert archive.status_code == 200
archive_data = archive.json()
assert archive_data["total"] == 2
assert len(archive_data["items"]) == 2
assert {item["source"] for item in archive_data["items"]} == {"breakout", "sma_reclaim"}
assert archive_data["source_counts"] == [
{"source": "breakout", "count": 1, "latest": "2026-05-30T11:55:00.000Z"},
{"source": "sma_reclaim", "count": 1, "latest": "2026-05-30T11:54:00.000Z"},
]
# Regression: selecting one archive source via source_in must narrow the
# paged items/total, but source_counts (the chip bar) must STILL list
# every archived source so the UI can offer a way back to "all".
archive_one = await client.get(
"/api/posts-paged",
params={
"archive_only": "true",
"source_in": "breakout",
"limit": 10,
"page": 1,
},
)
assert archive_one.status_code == 200
archive_one_data = archive_one.json()
assert archive_one_data["total"] == 1
assert {item["source"] for item in archive_one_data["items"]} == {"breakout"}
# Chip bar is NOT collapsed to the selected source.
assert archive_one_data["source_counts"] == [
{"source": "breakout", "count": 1, "latest": "2026-05-30T11:55:00.000Z"},
{"source": "sma_reclaim", "count": 1, "latest": "2026-05-30T11:54:00.000Z"},
]
archive_compat = await client.get(
"/api/posts-paged",
params={
"archive_only": "true",
"source_not_in": "truth",
"limit": 10,
"page": 1,
},
)
assert archive_compat.status_code == 200
archive_compat_data = archive_compat.json()
assert archive_compat_data["total"] == 2
assert {item["source"] for item in archive_compat_data["items"]} == {"breakout", "sma_reclaim"}
await engine.dispose()
+10 -1
View File
@@ -41,6 +41,12 @@ class _Trade:
pnl_usd = 2.25
class _ClosedTrade(_Trade):
"""Same as _Trade but with closed_at set, simulating a committed close."""
from datetime import datetime, timezone
closed_at = datetime(2026, 1, 1, 0, 0, 0)
class _Sub:
leverage = 3
hl_api_key = None
@@ -65,7 +71,10 @@ async def test_manual_close_returns_close_result(monkeypatch):
monkeypatch.setattr(bot_engine, "close_and_finalize", fake_close_and_finalize)
db = _Db([_Trade(), _Sub(), _Trade()])
# Responses in order: load trade → load sub → populate_existing re-read
# (B45 fix: one query with populate_existing=True instead of old stale cache).
# _ClosedTrade has closed_at set so the B46 success guard passes.
db = _Db([_Trade(), _Sub(), _ClosedTrade()])
result = await positions.manual_close(7, _Request(), db)
+47
View File
@@ -10,6 +10,8 @@ change accidentally turns "BTC bottom triggers: 3/3 firing" into a less
clear phrasing, CI catches it.
"""
import pytest
from app.services.telegram_digest import (
GlobalDigest, MacroBlock, KolBlock, TrumpBlock, format_digest,
)
@@ -174,3 +176,48 @@ def test_total_length_well_under_telegram_cap():
"open_pnl_summary": "3 open (+125.3 USD)",
})
assert len(out) < 4096
# ── build_global_digest DB aggregation (twitter-noise exclusion) ───────────────
@pytest.mark.asyncio
async def test_build_global_digest_excludes_twitter_noise(monkeypatch):
"""KOL posts_24h must NOT count twitter noise (gm / RT / jokes). Substack
essays (tier=NULL) and twitter signal posts (tier!='noise') count; twitter
noise (tier='noise') is excluded. Regression guard for the digest count
being inflated by a KOL's gm/RT spam after X ingestion landed."""
from datetime import datetime, timedelta
from sqlalchemy.ext.asyncio import (
AsyncSession, async_sessionmaker, create_async_engine,
)
from app.models import Base, KolPost
from app.services import telegram_digest
engine = create_async_engine("sqlite+aiosqlite:///:memory:", future=True)
async with engine.begin() as conn:
await conn.run_sync(Base.metadata.create_all)
sf = async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False)
now = datetime(2026, 6, 4, 12, 0, 0)
recent = now - timedelta(hours=2)
def _post(ext, source, tier=None, handle="cryptohayes"):
return KolPost(
kol_handle=handle, source=source, external_id=ext,
url=f"https://x.com/x/status/{ext}", published_at=recent,
raw_text="body", content_hash=ext, tier=tier,
)
async with sf() as s:
s.add_all([
_post("sub1", "substack", tier=None, handle="raoulpal"), # essay → count
_post("tw1", "twitter", tier="directional"), # signal → count
_post("tw2", "twitter", tier="noise"), # gm noise → exclude
_post("tw3", "twitter", tier="noise"), # RT noise → exclude
])
await s.commit()
monkeypatch.setattr(telegram_digest, "async_session", sf)
g = await telegram_digest.build_global_digest(now=now)
# 2 real posts (substack essay + twitter signal); 2 noise excluded
assert g.kol.posts_24h == 2
+150
View File
@@ -0,0 +1,150 @@
"""Tests for trade-alert broadcasts and balance pre-check logic added 2026-06-01.
Coverage targets:
1. _broadcast_trade_alert — fire-and-forget, must not raise
2. Balance pre-check maths — required_margin = (notional / leverage) * 1.1
3. Startup drain in the Telegram bot loop — offset advances past pending updates
"""
from __future__ import annotations
import asyncio
import pytest
# ── 1. _broadcast_trade_alert ─────────────────────────────────────────────────
@pytest.mark.asyncio
async def test_broadcast_trade_alert_no_connections(monkeypatch):
"""broadcast_trade_alert must silently succeed when no WS clients are connected."""
from app.services.bot_engine import _broadcast_trade_alert
from app.ws import manager as mgr_mod
# Patch manager.broadcast to verify it's called with correct payload
calls: list[dict] = []
async def fake_broadcast(msg: dict):
calls.append(msg)
monkeypatch.setattr(mgr_mod.manager, "broadcast", fake_broadcast)
await _broadcast_trade_alert("0xabc", "execution_failed", asset="BTC", reason="test error")
assert len(calls) == 1
assert calls[0]["type"] == "trade_alert"
assert calls[0]["wallet"] == "0xabc"
assert calls[0]["event"] == "execution_failed"
assert calls[0]["asset"] == "BTC"
@pytest.mark.asyncio
async def test_broadcast_trade_alert_swallows_exceptions(monkeypatch):
"""broadcast_trade_alert must not propagate exceptions — trade flow must continue."""
from app.services.bot_engine import _broadcast_trade_alert
from app.ws import manager as mgr_mod
async def exploding_broadcast(msg: dict):
raise RuntimeError("WS layer crashed")
monkeypatch.setattr(mgr_mod.manager, "broadcast", exploding_broadcast)
# Must not raise
await _broadcast_trade_alert("0xabc", "budget_reached", asset="BTC")
# ── 2. Balance pre-check maths ────────────────────────────────────────────────
def test_required_margin_formula():
"""required_margin = (notional / leverage) * 1.1 — verify key scenarios."""
def required_margin(notional: float, leverage: int) -> float:
return round((notional / max(leverage, 1)) * 1.1, 2)
# 2× leverage, $100 position → $50 margin + 10% buffer = $55
assert required_margin(100, 2) == 55.0
# 5× leverage, $500 position → $100 margin + 10% = $110
assert required_margin(500, 5) == 110.0
# 1× leverage, $20 position → $20 + 10% = $22
assert required_margin(20, 1) == 22.0
# edge: leverage=0 treated as 1 (no divide-by-zero)
assert required_margin(100, 0) == 110.0
def test_balance_check_does_not_block_low_leverage():
"""With $100 balance and 10× leverage on a $200 notional, margin = $22 — should PASS."""
balance = 100.0
notional = 200.0
leverage = 10
required = (notional / max(leverage, 1)) * 1.1
assert balance >= required, (
f"Balance ${balance} should cover ${required:.2f} margin "
f"(${notional} notional at {leverage}×)"
)
def test_balance_check_fires_at_truly_insufficient_balance():
"""With $5 balance and 2× on $20 notional, margin = $11 — should BLOCK."""
balance = 5.0
notional = 20.0
leverage = 2
required = (notional / max(leverage, 1)) * 1.1
assert balance < required, (
f"Balance ${balance} should NOT cover ${required:.2f} margin"
)
# ── 3. Telegram startup drain ────────────────────────────────────────────────
@pytest.mark.asyncio
async def test_telegram_startup_drain_advances_offset(monkeypatch):
"""Verify the drain calls getUpdates with timeout=0 and ACKs the last update_id."""
import httpx
drain_calls: list[dict] = []
class FakeResponse:
status_code = 200
def json(self):
if len(drain_calls) == 1: # first call: return pending updates
return {"result": [{"update_id": 100}, {"update_id": 101}]}
return {"result": []} # second call (ACK): no pending
class FakeClient:
async def __aenter__(self): return self
async def __aexit__(self, *a): pass
async def get(self, url, params=None):
drain_calls.append(params or {})
return FakeResponse()
monkeypatch.setattr(httpx, "AsyncClient", lambda **kw: FakeClient())
# Simulate only the drain portion (extract the logic)
from app.config import settings
monkeypatch.setattr(settings, "telegram_bot_token", "test-token")
import httpx as _httpx
# Re-run the drain logic inline (mirrors telegram_bot.py startup drain)
token = "test-token"
TG_API = "https://api.telegram.org/bot{token}/{method}"
async with _httpx.AsyncClient(timeout=10) as client:
r = await client.get(
TG_API.format(token=token, method="getUpdates"),
params={"timeout": 0, "limit": 100},
)
if r.status_code == 200:
pending = r.json().get("result", [])
if pending:
drain_offset = pending[-1]["update_id"] + 1
async with _httpx.AsyncClient(timeout=10) as client:
await client.get(
TG_API.format(token=token, method="getUpdates"),
params={"timeout": 0, "offset": drain_offset},
)
# First call: drain request (timeout=0, limit=100)
assert drain_calls[0].get("timeout") == 0
assert drain_calls[0].get("limit") == 100
# Second call: ACK with offset = last_update_id + 1
assert drain_calls[1].get("offset") == 102 # 101 + 1
+217
View File
@@ -0,0 +1,217 @@
"""Tests for x_analysis — the DETERMINISTIC normalization layer.
The LLM call is mocked so each test feeds a controlled raw model response and
asserts how analyze_x_post normalizes it. This locks down the enforcement rules
that protect downstream consumers (kol_x → kol_divergence), independent of
whatever the model actually returns:
- retweet post_type → forced noise
- trade_signal requires a buy/sell/reduce ticker with conviction ≥ 0.7,
else it downgrades to directional (never silently dropped)
- noise → tickers cleared + talks_vs_trades_flag forced false
- ticker hygiene: conviction clamped 0..1, bad action → mention,
overlong symbol dropped
- invalid tier/post_type → safe defaults
- bad JSON / empty text → graceful fallback, never raises
These are pure logic (no network, no AI spend) so they're fast and stable.
"""
from __future__ import annotations
import json
import pytest
from app.config import settings
from app.services import x_analysis
# ── helpers ────────────────────────────────────────────────────────────────
def _patch_llm(monkeypatch, raw: dict):
"""Force analyze_x_post's LLM call to return `raw` (serialized). We patch
the OpenAI path (anthropic key blanked) since that's the default in CI."""
payload = json.dumps(raw)
class _Msg:
content = payload
class _Choice:
message = _Msg()
class _Resp:
choices = [_Choice()]
class _Completions:
async def create(self, **_kw):
return _Resp()
class _Chat:
completions = _Completions()
class _Client:
chat = _Chat()
monkeypatch.setattr(settings, "anthropic_api_key", "") # → OpenAI path
monkeypatch.setattr(x_analysis, "_oai", lambda: _Client())
def _raw(**over):
"""Minimal well-formed raw model response; override per test."""
base = {
"post_type": "original",
"tier": "directional",
"summary": "x",
"tickers": [],
"talks_vs_trades_flag": False,
"has_price_target": False,
"price_targets": [],
"sentiment": "neutral",
"reasoning": "y",
}
base.update(over)
return base
# ── tier enforcement ───────────────────────────────────────────────────────
@pytest.mark.asyncio
async def test_retweet_post_type_forced_to_noise(monkeypatch):
_patch_llm(monkeypatch, _raw(
post_type="retweet", tier="trade_signal",
tickers=[{"ticker": "BTC", "action": "buy", "conviction": 0.9}],
))
r = await x_analysis.analyze_x_post(handle="k", text="some original-looking text body")
assert r["tier"] == "noise"
assert r["tickers"] == []
@pytest.mark.asyncio
async def test_trade_signal_downgrades_without_strong_action(monkeypatch):
# tier=trade_signal but only a 'bullish' ticker (not buy/sell/reduce)
_patch_llm(monkeypatch, _raw(
tier="trade_signal",
tickers=[{"ticker": "SOL", "action": "bullish", "conviction": 0.9}],
))
r = await x_analysis.analyze_x_post(handle="k", text="SOL looking strong")
assert r["tier"] == "directional"
assert r["tickers"][0]["ticker"] == "SOL"
@pytest.mark.asyncio
async def test_trade_signal_downgrades_on_low_conviction(monkeypatch):
_patch_llm(monkeypatch, _raw(
tier="trade_signal",
tickers=[{"ticker": "SOL", "action": "buy", "conviction": 0.5}],
))
r = await x_analysis.analyze_x_post(handle="k", text="bought a little SOL maybe")
assert r["tier"] == "directional" # 0.5 < 0.7 floor
@pytest.mark.asyncio
async def test_trade_signal_kept_when_strong(monkeypatch):
_patch_llm(monkeypatch, _raw(
tier="trade_signal",
tickers=[{"ticker": "SOL", "action": "buy", "conviction": 0.9}],
))
r = await x_analysis.analyze_x_post(handle="k", text="aped SOL full size lfg")
assert r["tier"] == "trade_signal"
@pytest.mark.asyncio
async def test_invalid_tier_falls_back_to_noise(monkeypatch):
_patch_llm(monkeypatch, _raw(tier="超级买入"))
r = await x_analysis.analyze_x_post(handle="k", text="ambiguous content here")
assert r["tier"] == "noise"
# ── noise enforcement ──────────────────────────────────────────────────────
@pytest.mark.asyncio
async def test_noise_clears_tickers_and_flag(monkeypatch):
_patch_llm(monkeypatch, _raw(
tier="noise", talks_vs_trades_flag=True,
tickers=[{"ticker": "BTC", "action": "buy", "conviction": 0.9}],
))
r = await x_analysis.analyze_x_post(handle="k", text="gm frens beautiful day")
assert r["tickers"] == []
assert r["talks_vs_trades_flag"] is False
# ── ticker hygiene ─────────────────────────────────────────────────────────
@pytest.mark.asyncio
async def test_conviction_clamped_to_unit_interval(monkeypatch):
_patch_llm(monkeypatch, _raw(
tier="directional",
tickers=[{"ticker": "BTC", "action": "bullish", "conviction": 1.8}],
))
r = await x_analysis.analyze_x_post(handle="k", text="BTC going parabolic")
assert r["tickers"][0]["conviction"] == 1.0
@pytest.mark.asyncio
async def test_invalid_action_becomes_mention(monkeypatch):
_patch_llm(monkeypatch, _raw(
tier="directional",
tickers=[{"ticker": "BTC", "action": "yolo", "conviction": 0.5}],
))
r = await x_analysis.analyze_x_post(handle="k", text="BTC yolo time")
assert r["tickers"][0]["action"] == "mention"
@pytest.mark.asyncio
async def test_overlong_ticker_dropped(monkeypatch):
_patch_llm(monkeypatch, _raw(
tier="directional",
tickers=[{"ticker": "THISISWAYTOOLONG", "action": "bullish", "conviction": 0.5}],
))
r = await x_analysis.analyze_x_post(handle="k", text="some long token mention")
assert r["tickers"] == []
# ── graceful failure ───────────────────────────────────────────────────────
@pytest.mark.asyncio
async def test_empty_text_short_circuits_without_llm(monkeypatch):
# no _patch_llm → if it called the LLM it would error; it must not.
r = await x_analysis.analyze_x_post(handle="k", text=" ")
assert r["tier"] == "noise"
assert r["error"] == "empty post"
@pytest.mark.asyncio
async def test_bare_retweet_prefiltered_without_llm(monkeypatch):
r = await x_analysis.analyze_x_post(handle="k", text="RT @someone: gm")
assert r["tier"] == "noise"
assert r["post_type"] == "retweet"
@pytest.mark.asyncio
async def test_bad_json_returns_fallback(monkeypatch):
class _Msg:
content = "not json at all {{{ "
class _Choice:
message = _Msg()
class _Resp:
choices = [_Choice()]
class _Completions:
async def create(self, **_kw):
return _Resp()
class _Chat:
completions = _Completions()
class _Client:
chat = _Chat()
monkeypatch.setattr(settings, "anthropic_api_key", "")
monkeypatch.setattr(x_analysis, "_oai", lambda: _Client())
r = await x_analysis.analyze_x_post(handle="k", text="real content that triggers llm")
assert r["tier"] == "noise"
assert r["error"] and "parse_error" in r["error"]