feat(news): index news packages and research persistent events

Extract reusable literal keywords once per source revision, assign complete news packages to long-lived events, and research all event members with immutable evidence and references.

Add additive research storage, vocabulary snapshots, the two-stage workspace, isolated acceptance coverage, and a paused rollout with an initial fixed 50-news production trial.

backend/tests/test_news_vocabulary.py

@@ -0,0 +1,156 @@
+"""Vocabulary and fixed-version behavior, isolated from production I/O."""
+
+import asyncio
+from types import SimpleNamespace as N
+from unittest.mock import AsyncMock
+import pytest
+
+
+def test_equivalence_preserves_literal_aliases_and_quotes(trading):
+    from alphapulse.news_research.vocabulary import normalize, expand, VocabularyInput
+
+    data = VocabularyInput(
+        base_revision=0, entries=[{"canonical": "币安", "aliases": ["Binance"]}]
+    )
+    snapshot = {"revision": 1, "entries": [e.model_dump() for e in data.entries]}
+    original = [
+        {
+            "canonical": "Binance交易所",
+            "aliases": ["Binance"],
+            "quote": "Binance reported",
+        }
+    ]
+    assert normalize(original, snapshot) == [{**original[0], "canonical": "币安"}]
+    assert original[0]["canonical"] == "Binance交易所"
+    assert expand([" BINANCE "], snapshot) == ["币安", "binance"]
+    assert expand(["Bank of Canada"], snapshot) == ["bank of canada"]
+
+
+@pytest.mark.parametrize(
+    "entries",
+    [
+        [{"canonical": " ", "aliases": []}],
+        [{"canonical": "币安", "aliases": ["Binance", "BINANCE"]}],
+        [
+            {"canonical": "币安", "aliases": ["Binance"]},
+            {"canonical": "别家", "aliases": ["binance"]},
+        ],
+        [{"canonical": "币安", "aliases": []}, {"canonical": "币安", "aliases": []}],
+    ],
+)
+def test_reject_ambiguous_or_empty_vocabulary(trading, entries):
+    from alphapulse.news_research.vocabulary import VocabularyInput
+
+    with pytest.raises(ValueError):
+        VocabularyInput(base_revision=0, entries=entries)
+
+
+def test_merging_tags_never_invents_literal_alias(trading):
+    from alphapulse.news_research.vocabulary import normalize
+
+    snapshot = {"entries": [{"canonical": "币安", "aliases": ["Binance"]}]}
+    result = normalize(
+        [
+            {"canonical": c, "aliases": [a], "quote": a}
+            for c, a in [("币安", "币安"), ("Binance", "Binance")]
+        ],
+        snapshot,
+    )
+    assert len(result) == 1 and result[0]["aliases"] == ["币安", "Binance"]
+
+
+def test_stale_vocabulary_save_conflicts_without_writing(trading, monkeypatch):
+    from fastapi import HTTPException
+    from alphapulse.news_research import api
+
+    monkeypatch.setattr(
+        api.vocab, "snapshot", AsyncMock(return_value={"revision": 2, "entries": []})
+    )
+    session = N(execute=AsyncMock(), add=AsyncMock(), commit=AsyncMock())
+    with pytest.raises(HTTPException) as error:
+        asyncio.run(
+            api.save_vocabulary(
+                api.vocab.VocabularyInput(base_revision=1, entries=[]), session
+            )
+        )
+    assert error.value.status_code == 409
+    session.add.assert_not_called()
+    session.commit.assert_not_called()
+
+
+@pytest.mark.parametrize(
+    "event_id,state", [(2, "done"), (1, "failed"), (1, "superseded")]
+)
+def test_fixed_version_rejects_wrong_event_and_unsuccessful_versions(
+    trading, event_id, state
+):
+    from fastapi import HTTPException
+    from alphapulse.news_research.api import event_version
+
+    session = N(get=AsyncMock(return_value=N(event_id=event_id, state=state)))
+    with pytest.raises(HTTPException) as error:
+        asyncio.run(event_version(1, 9, session))
+    assert error.value.status_code == 404
+
+
+def test_acceptance_budget_is_shared_and_counts_failed_streams(trading, tmp_path):
+    import importlib.util
+    from pathlib import Path
+
+    spec = importlib.util.spec_from_file_location(
+        "acceptance_budget",
+        Path(__file__).resolve().parents[2] / "scripts/accept_news_research.py",
+    )
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    counter = tmp_path / "requests"
+    first = module.Budget(counter, limit=2)
+    second = module.Budget(counter, limit=2)
+    first.take()
+    second.take()
+    with pytest.raises(module.BudgetExceeded):
+        first.take()
+    assert counter.read_text() == "2"
+
+
+def test_budget_counts_transport_failures_before_retry(trading, tmp_path):
+    import importlib.util
+    from pathlib import Path
+
+    spec = importlib.util.spec_from_file_location(
+        "failed_stream_budget",
+        Path(__file__).resolve().parents[2] / "scripts/accept_news_research.py",
+    )
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    budget = module.Budget(tmp_path / "counter", limit=2)
+    sent = []
+
+    async def failing():
+        sent.append(True)
+        raise ConnectionError("isolated failure")
+        yield
+
+    async def attempt():
+        async for _ in budget.wrap(failing)():
+            pass
+
+    async def run():
+        return await asyncio.gather(
+            *(attempt() for _ in range(3)), return_exceptions=True
+        )
+
+    errors = asyncio.run(run())
+    assert len(sent) == 2
+    assert sum(isinstance(e, module.BudgetExceeded) for e in errors) == 1
+
+
+def test_supplemental_citation_must_use_returned_article_id(trading):
+    from alphapulse.news_risk.pipeline import validate_evidence, Evidence
+
+    sources = {-1: {"news_id": 1004, "content": "Original correction"}}
+    validate_evidence([Evidence(article_id=-1, quote="Original correction")], sources)
+    with pytest.raises(ValueError):
+        validate_evidence(
+            [Evidence(article_id=1004, quote="Original correction")], sources
+        )