app/services/sec_client.py

@@ -21,6 +21,7 @@ from __future__ import annotations
 import asyncio
 import logging
 import os
+import re
 from datetime import date, datetime
 from pathlib import Path
 from typing import Any
@@ -44,13 +45,31 @@ _FORMS_10 = frozenset({"10-K", "10-Q", "10-K/A", "10-Q/A"})
 
 
 class SecError(ProviderError):
-    """SEC request failed."""
+    """SEC request failed (403, exhausted 429/5xx, timeout, transport, parse)."""
 
 
 class SecForbiddenError(SecError):
     """SEC returned 403 — User-Agent/pattern rejected. Alert and stop."""
 
 
+class SecNotFoundError(SecError):
+    """SEC returned 404 — the resource does not exist (e.g. no index for a day).
+
+    The *only* error a caller may treat as 'missing' — every other SecError
+    (403, exhausted retries, 5xx, timeout) must propagate so a fetch failure is
+    never mistaken for an empty result."""
+
+
+def _looks_like_contact_email(ua: str) -> bool:
+    if "example.com" in ua.lower() or "set-a-real-email" in ua.lower():
+        return False
+    return re.search(r"[^@\s]+@[^@\s]+\.[^@\s]+", ua) is not None
+
+
+# SEC asks callers to stay well under 10 req/s; enforce a floor on real clients.
+_MIN_PROD_SPACING = 0.11
+
+
 def cik10(cik: int | str) -> str:
     """Zero-pad a CIK to the 10-digit form SEC URLs use (320193 -> 0000320193)."""
     return str(int(cik)).zfill(10)
@@ -81,7 +100,24 @@ class SecClient:
         self._lock = asyncio.Lock()
         self._last_request = 0.0
 
+    def _validate_fair_access(self) -> None:
+        """On a real (non-mocked) client, enforce SEC fair-access preconditions
+        so we can't accidentally hammer SEC or get 403'd: a genuine contact-email
+        User-Agent and a spacing floor. Mock transports skip this (tests use 0)."""
+        if not _looks_like_contact_email(self._ua):
+            raise SecError(
+                "sec_user_agent must contain a real contact email (got "
+                f"{self._ua!r}) — SEC fair-access requires it"
+            )
+        if self._spacing < _MIN_PROD_SPACING:
+            raise SecError(
+                f"sec_request_spacing_seconds {self._spacing} is below the "
+                f"{_MIN_PROD_SPACING}s fair-access floor"
+            )
+
     async def __aenter__(self) -> "SecClient":
+        if self._transport is None:
+            self._validate_fair_access()
         self._client = httpx.AsyncClient(
             headers={"User-Agent": self._ua, "Accept-Encoding": "gzip, deflate"},
             timeout=self._timeout,
@@ -108,22 +144,34 @@ class SecClient:
         attempt = 0
         while True:
             await self._throttle()
-            resp = await self._client.get(url)
+            try:
-            if resp.status_code == 403:
+                resp = await self._client.get(url)
+            except (httpx.TimeoutException, httpx.TransportError) as exc:
+                attempt += 1
+                if attempt > self._max_retries:
+                    raise SecError(f"SEC network error for {url}: {exc}") from exc
+                await asyncio.sleep(min(2.0**attempt, 30.0))
+                continue
+
+            code = resp.status_code
+            if code == 403:
                 raise SecForbiddenError(
                     f"SEC 403 for {url} — User-Agent/pattern rejected; set a real "
                     "sec_user_agent contact email"
                 )
-            if resp.status_code == 429:
+            if code == 404:
+                raise SecNotFoundError(f"SEC 404 for {url}")
+            # 429 and 5xx are transient — retry with backoff, honoring Retry-After.
+            if code == 429 or 500 <= code < 600:
                 attempt += 1
                 if attempt > self._max_retries:
-                    raise SecError(f"SEC 429 after {self._max_retries} retries: {url}")
+                    raise SecError(f"SEC {code} after {self._max_retries} retries: {url}")
-                backoff = min(2.0**attempt, 30.0)
+                delay = _retry_after_seconds(resp) or min(2.0**attempt, 30.0)
-                logger.warning("SEC 429 for %s — backoff %.1fs (attempt %d)", url, backoff, attempt)
+                logger.warning("SEC %d for %s — backoff %.1fs (attempt %d)", code, url, delay, attempt)
-                await asyncio.sleep(backoff)
+                await asyncio.sleep(delay)
                 continue
-            if resp.status_code >= 400:
+            if code >= 400:
-                raise SecError(f"SEC {resp.status_code} for {url}")
+                raise SecError(f"SEC {code} for {url}")
             return resp
 
     async def get_json(self, url: str) -> Any:
@@ -144,18 +192,20 @@ class SecClient:
                 out[sym] = int(row["cik_str"])
         return out
 
-    async def submissions(self, cik: int | str) -> dict[str, Any]:
+    async def submissions(self, cik: int | str, *, include_history: bool = False) -> dict[str, Any]:
-        """Issuer metadata + the FULL merged filing history.
+        """Issuer metadata + filing list.
 
         ``filings.recent`` caps at 1000; older accessions live in
-        ``filings.files[]`` shards. This merges them so backfill sees every
+        ``filings.files[]`` shards. Only ``include_history=True`` (the one-time
-        filing's reportDate / acceptanceDateTime / isXBRL.
+        full backfill) fetches those shards — SIC refresh and incremental runs
+        use the recent list alone and make no extra requests.
         """
         base = await self.get_json(f"{_DATA}/submissions/CIK{cik10(cik)}.json")
         filings = _rows_from_arrays(base["filings"]["recent"])
-        for shard in base["filings"].get("files") or []:
+        if include_history:
-            shard_data = await self.get_json(f"{_DATA}/submissions/{shard['name']}")
+            for shard in base["filings"].get("files") or []:
-            filings.extend(_rows_from_arrays(shard_data))
+                shard_data = await self.get_json(f"{_DATA}/submissions/{shard['name']}")
+                filings.extend(_rows_from_arrays(shard_data))
         return {
             "cik": int(base["cik"]),
             "name": base.get("name"),
@@ -178,8 +228,8 @@ class SecClient:
             url = f"{_WWW}/Archives/edgar/daily-index/{year}/QTR{qtr}/index.json"
             try:
                 idx = await self.get_json(url)
-            except SecError:
+            except SecNotFoundError:
-                continue
+                continue  # quarter dir absent — only 404 is "missing"
             dates = [
                 d
                 for item in idx.get("directory", {}).get("item", [])
@@ -201,9 +251,9 @@ class SecClient:
         url = f"{_WWW}/Archives/edgar/daily-index/{day.year}/QTR{qtr}/form.{day:%Y%m%d}.idx"
         try:
             text = await self.get_text(url)
-        except SecError as exc:
+        except SecNotFoundError:
-            logger.info("no daily index for %s (%s)", day, exc)
+            logger.info("no daily index for %s (404)", day)
-            return []
+            return []  # weekend/holiday/not-yet-published; other errors propagate
         return _parse_form_index(text)
 
 
@@ -252,6 +302,17 @@ def _parse_form_index(text: str) -> list[dict[str, Any]]:
     return rows
 
 
+def _retry_after_seconds(resp: httpx.Response) -> float | None:
+    """Parse a numeric-seconds Retry-After header (SEC uses seconds), capped."""
+    raw = resp.headers.get("Retry-After")
+    if not raw:
+        return None
+    try:
+        return min(float(raw), 60.0)
+    except (TypeError, ValueError):
+        return None
+
+
 def _index_file_date(name: str) -> date | None:
     if name.startswith("form.") and name.endswith(".idx"):
         try:

app/services/sec_universe.py

@@ -1,19 +1,26 @@
 """Tracked-universe CIK/SIC resolution and the SEC importer's composite revision.
 
-Resolves the app's tracked tickers to SEC issuers (CIK) and back-fills
+Resolves the app's tracked tickers to SEC issuers (CIK) and prepares
-``tickers.cik/sic/sic_description``. Also builds the **universe fingerprint** that
+``tickers.cik/sic/sic_description`` back-fills. Also builds the **universe
-goes into the importer's composite revision, so that adding a ticker changes the
+fingerprint** in the importer's composite revision, so adding a ticker changes
-revision and forces a run instead of being ``no_op``'d away or starved waiting for
+the revision and forces a run instead of being ``no_op``'d away or starved
-its issuer to file (A3 design, Decision 1 review fix).
+waiting for its issuer to file (A3 design, Decision 1 review fix).
+
+**Transaction contract:** resolution is read-only — `resolve_ciks` and
+`fetch_sic_updates` compute *proposed* updates and mutate nothing. They run in
+the importer's `stage` (which must not write, or a failed validation would leak
+changes on the framework's failure commit). The proposals are applied only in
+`promote`, via `apply_ticker_updates`, atomically with the snapshot inserts.
 """
 
 from __future__ import annotations
 
 import hashlib
 import logging
+from dataclasses import dataclass, field
 from typing import Iterable
 
-from sqlalchemy import select
+from sqlalchemy import select, update
 
 from app.models.ticker import Ticker
 from app.services.earnings_alignment import normalise_symbol
@@ -22,47 +29,72 @@ from app.services.sec_client import SecClient
 logger = logging.getLogger(__name__)
 
 
-async def resolve_ciks(db, client: SecClient) -> dict[str, int]:
+@dataclass
-    """Resolve tracked tickers to CIKs via company_tickers.json and persist
+class ResolvedUniverse:
-    ``tickers.cik`` where it changed. Returns {normalised symbol: cik} for the
+    """Read-only result of CIK resolution. `cik_updates` are proposed writes
-    tracked tickers that resolved (multi-class tickers share a CIK)."""
+    (ticker_id → new cik string) applied later in promote."""
-    ticker_to_cik = await client.company_tickers()
-    rows = (await db.execute(select(Ticker))).scalars().all()
 
-    resolved: dict[str, int] = {}
+    symbol_to_cik: dict[str, int] = field(default_factory=dict)
-    changed = 0
+    cik_to_ticker_ids: dict[int, list[int]] = field(default_factory=dict)
-    for t in rows:
+    cik_updates: list[tuple[int, str]] = field(default_factory=list)
-        if not t.symbol:
+
+
+async def resolve_ciks(db, client: SecClient) -> ResolvedUniverse:
+    """Resolve tracked tickers to CIKs via company_tickers.json. **Read-only** —
+    returns the mapping + proposed `tickers.cik` writes; mutates nothing."""
+    ticker_to_cik = await client.company_tickers()
+    rows = (await db.execute(select(Ticker.id, Ticker.symbol, Ticker.cik))).all()
+
+    result = ResolvedUniverse()
+    for tid, symbol, current_cik in rows:
+        if not symbol:
             continue
-        sym = normalise_symbol(t.symbol)
+        sym = normalise_symbol(symbol)
         cik = ticker_to_cik.get(sym)
         if cik is None:
-            continue  # e.g. ADRs / non-SEC issuers — snapshots simply absent
+            continue  # ADRs / non-SEC issuers — snapshots simply absent
-        resolved[sym] = cik
+        result.symbol_to_cik[sym] = cik
-        cik_str = f"{cik:010d}"
+        result.cik_to_ticker_ids.setdefault(cik, []).append(tid)
-        if t.cik != cik_str:
+        if current_cik != f"{cik:010d}":
-            t.cik = cik_str
+            result.cik_updates.append((tid, f"{cik:010d}"))
-            changed += 1
+    logger.info(
-    logger.info("resolve_ciks: %d tracked resolved, %d cik updates", len(resolved), changed)
+        "resolve_ciks: %d resolved, %d proposed cik updates",
-    return resolved
+        len(result.symbol_to_cik),
+        len(result.cik_updates),
+    )
+    return result
 
 
-async def refresh_sic(db, client: SecClient, ciks: Iterable[int]) -> int:
+async def fetch_sic_updates(
-    """Fetch submissions for the given CIKs and set sic/sic_description on every
+    client: SecClient, cik_to_ticker_ids: dict[int, Iterable[int]]
-    tracked ticker sharing each CIK. Returns the number of CIKs refreshed. Callers
+) -> list[tuple[int, str | None, str | None]]:
-    pass only the CIKs that need it (e.g. those still missing a SIC) to stay light."""
+    """Fetch SIC for each CIK (recent-only submissions, no history shards) and
-    refreshed = 0
+    return proposed `(ticker_id, sic, sic_description)` writes. **Read-only** — no
-    for cik in sorted(set(int(c) for c in ciks)):
+    DB mutation. Callers pass only the CIKs that need it (e.g. missing a SIC)."""
-        sub = await client.submissions(cik)
+    updates: list[tuple[int, str | None, str | None]] = []
-        cik_str = f"{cik:010d}"
+    for cik, ticker_ids in cik_to_ticker_ids.items():
-        rows = (
+        sub = await client.submissions(cik, include_history=False)
-            await db.execute(select(Ticker).where(Ticker.cik == cik_str))
+        sic = str(sub["sic"]) if sub.get("sic") else None
-        ).scalars().all()
+        desc = sub.get("sic_description")
-        for t in rows:
+        for tid in ticker_ids:
-            t.sic = str(sub["sic"]) if sub.get("sic") else None
+            updates.append((tid, sic, desc))
-            t.sic_description = sub.get("sic_description")
+    return updates
-        refreshed += 1
+
-    return refreshed
+
+async def apply_ticker_updates(
+    db,
+    resolved: ResolvedUniverse,
+    sic_updates: list[tuple[int, str | None, str | None]] | None = None,
+) -> dict[str, int]:
+    """Apply the proposed cik / sic writes. **The only writer** — call inside
+    promote so it commits atomically with the snapshot inserts."""
+    for tid, cik in resolved.cik_updates:
+        await db.execute(update(Ticker).where(Ticker.id == tid).values(cik=cik))
+    for tid, sic, desc in sic_updates or []:
+        await db.execute(
+            update(Ticker).where(Ticker.id == tid).values(sic=sic, sic_description=desc)
+        )
+    return {"cik_updates": len(resolved.cik_updates), "sic_updates": len(sic_updates or [])}
 
 
 def universe_fingerprint(symbol_to_cik: dict[str, int]) -> str:
@@ -72,16 +104,16 @@ def universe_fingerprint(symbol_to_cik: dict[str, int]) -> str:
     return hashlib.blake2b(canonical.encode("utf-8"), digest_size=12).hexdigest()
 
 
-def compose_revision(
-    index_date, index_content_hash: str, symbol_to_cik: dict[str, int]
-) -> str:
-    """The importer's composite revision: latest processed index date + a hash of
-    the index content consumed this run + the universe fingerprint. Equal revision
-    across runs ⇒ nothing new to import ⇒ no_op."""
-    return f"{index_date}:{index_content_hash}:{universe_fingerprint(symbol_to_cik)}"
-
-
 def index_content_hash(index_rows: Iterable[dict]) -> str:
     """Order-independent hash of the tracked index accessions consumed this run."""
     keys = sorted(f"{r['cik']}/{r['accession']}" for r in index_rows)
     return hashlib.blake2b("|".join(keys).encode("utf-8"), digest_size=12).hexdigest()
+
+
+def compose_revision(index_date, content_hash: str, symbol_to_cik: dict[str, int]) -> str:
+    """Composite revision = processed index date + index-content hash + universe
+    fingerprint. Equal across runs ⇒ nothing new ⇒ no_op. Rejects a missing index
+    date rather than emitting a `None:...` revision that could false-match."""
+    if index_date is None:
+        raise ValueError("compose_revision requires a non-null index date")
+    return f"{index_date}:{content_hash}:{universe_fingerprint(symbol_to_cik)}"

tests/unit/test_sec_client.py

@@ -88,9 +88,9 @@ async def test_company_tickers_normalised_and_multiclass():
     assert m["BRK-B"] == 1067983  # dash form
 
 
-async def test_submissions_merges_shards_and_filters_forms():
+async def test_submissions_history_merges_shards_and_filters_forms():
     async with _client() as c:
-        sub = await c.submissions(320193)
+        sub = await c.submissions(320193, include_history=True)
     assert sub["sic"] == "3571" and sub["fiscal_year_end"] == "0926"
     accns = {f["accession"] for f in sub["filings"]}
     # 10-Q + 10-K from recent, 10-Q from the shard; the 8-K is filtered out
@@ -99,6 +99,20 @@ async def test_submissions_merges_shards_and_filters_forms():
     assert older["report_date"] == "1993-12-31" and older["is_xbrl"] is False
 
 
+async def test_submissions_recent_only_skips_shard_requests():
+    seen = []
+
+    def handler(request):
+        seen.append(str(request.url))
+        return _handler(request)
+
+    async with SecClient(transport=httpx.MockTransport(handler), spacing_seconds=0) as c:
+        sub = await c.submissions(320193)  # include_history defaults False
+    assert not any("submissions-001" in u for u in seen)  # no shard fetch
+    accns = {f["accession"] for f in sub["filings"]}
+    assert accns == {"0000320193-26-000013", "0000320193-26-000006"}  # recent only
+
+
 async def test_daily_index_parses_10kq_rows():
     async with _client() as c:
         rows = await c.daily_index(date(2026, 7, 21))
@@ -157,3 +171,53 @@ async def test_429_gives_up_after_max_retries(monkeypatch):
     async with SecClient(transport=httpx.MockTransport(handler), spacing_seconds=0, max_retries=2) as c:
         with pytest.raises(SecError):
             await c.get_json("https://data.sec.gov/z")
+
+
+def _status_client(status):
+    def handler(request):
+        return httpx.Response(status)
+    # max_retries=0 so 5xx/429 raise immediately (no retry sleeps)
+    return SecClient(transport=httpx.MockTransport(handler), spacing_seconds=0, max_retries=0)
+
+
+async def test_index_methods_propagate_403():
+    # A 403 must NOT be mistaken for "no index".
+    async with _status_client(403) as c:
+        with pytest.raises(sc.SecForbiddenError):
+            await c.daily_index(date(2026, 7, 21))
+    async with _status_client(403) as c:
+        with pytest.raises(sc.SecForbiddenError):
+            await c.latest_index_date(today=date(2026, 7, 22))
+
+
+async def test_index_methods_propagate_500():
+    async with _status_client(500) as c:
+        with pytest.raises(SecError):
+            await c.daily_index(date(2026, 7, 21))
+    async with _status_client(500) as c:
+        with pytest.raises(SecError):
+            await c.latest_index_date(today=date(2026, 7, 22))
+
+
+async def test_only_404_is_treated_as_missing():
+    async with _status_client(404) as c:
+        assert await c.daily_index(date(2026, 7, 21)) == []
+        assert await c.latest_index_date(today=date(2026, 7, 22)) is None
+
+
+async def test_fair_access_validation_on_real_client():
+    # Placeholder email rejected.
+    with pytest.raises(SecError):
+        async with SecClient(user_agent="signal-platform (contact: you@example.com)"):
+            pass
+    # Non-email UA rejected.
+    with pytest.raises(SecError):
+        async with SecClient(user_agent="signal-platform"):
+            pass
+    # Valid UA but unsafe production spacing rejected.
+    with pytest.raises(SecError):
+        async with SecClient(user_agent="signal-platform real@person.io", spacing_seconds=0.0):
+            pass
+    # Valid UA + safe spacing opens fine.
+    async with SecClient(user_agent="signal-platform real@person.io", spacing_seconds=0.2):
+        pass

tests/unit/test_sec_universe.py

@@ -1,4 +1,5 @@
-"""Tests for CIK/SIC resolution and the composite-revision fingerprint."""
+"""Tests for CIK/SIC resolution (read-only), apply-in-promote, and the
+composite-revision fingerprint."""
 
 from __future__ import annotations
 
@@ -40,11 +41,11 @@ class FakeSecClient:
     async def company_tickers(self):
         return dict(self._tickers)
 
-    async def submissions(self, cik):
+    async def submissions(self, cik, *, include_history=False):
         return self._submissions[int(cik)]
 
 
-async def test_resolve_ciks_sets_cik_and_returns_mapping(factory):
+async def test_resolve_ciks_is_read_only_and_proposes_updates(factory):
     async with factory() as s:
         for sym in ["AAPL", "GOOGL", "GOOG", "ZZZZ"]:  # ZZZZ not in SEC
             s.add(Ticker(symbol=sym))
@@ -52,35 +53,47 @@ async def test_resolve_ciks_sets_cik_and_returns_mapping(factory):
 
     client = FakeSecClient({"AAPL": 320193, "GOOGL": 1652044, "GOOG": 1652044})
     async with factory() as s:
-        mapping = await su.resolve_ciks(s, client)
+        resolved = await su.resolve_ciks(s, client)
-        await s.commit()
+        assert not s.dirty and not s.new  # NOTHING mutated during resolution
+        await s.rollback()
 
-    assert mapping == {"AAPL": 320193, "GOOGL": 1652044, "GOOG": 1652044}
+    assert resolved.symbol_to_cik == {"AAPL": 320193, "GOOGL": 1652044, "GOOG": 1652044}
+    assert len(resolved.cik_updates) == 3  # AAPL, GOOGL, GOOG (ZZZZ unresolved)
+    assert set(resolved.cik_to_ticker_ids) == {320193, 1652044}
+
+    # Read-only really means the DB is untouched until apply.
     async with factory() as s:
         ciks = {t.symbol: t.cik for t in (await s.execute(select(Ticker))).scalars()}
-    assert ciks["AAPL"] == "0000320193"
+    assert all(v is None for v in ciks.values())
-    assert ciks["GOOGL"] == ciks["GOOG"] == "0001652044"  # multi-class share CIK
-    assert ciks["ZZZZ"] is None  # unresolved stays null
 
 
-async def test_refresh_sic_updates_all_tickers_of_a_cik(factory):
+async def test_apply_ticker_updates_writes_cik_and_sic(factory):
     async with factory() as s:
         for sym in ["GOOGL", "GOOG"]:
-            s.add(Ticker(symbol=sym, cik="0001652044"))
+            s.add(Ticker(symbol=sym))
         await s.commit()
 
     client = FakeSecClient(
-        {}, submissions={1652044: {"sic": "7370", "sic_description": "Services-Computer"}}
+        {"GOOGL": 1652044, "GOOG": 1652044},
+        submissions={1652044: {"sic": "7370", "sic_description": "Services-Computer"}},
     )
     async with factory() as s:
-        n = await su.refresh_sic(s, client, [1652044])
+        resolved = await su.resolve_ciks(s, client)
+        sic_updates = await su.fetch_sic_updates(client, resolved.cik_to_ticker_ids)
+        counts = await su.apply_ticker_updates(s, resolved, sic_updates)
         await s.commit()
 
-    assert n == 1
+    assert counts == {"cik_updates": 2, "sic_updates": 2}
     async with factory() as s:
-        rows = {t.symbol: (t.sic, t.sic_description) for t in (await s.execute(select(Ticker))).scalars()}
+        rows = {t.symbol: (t.cik, t.sic, t.sic_description) for t in (await s.execute(select(Ticker))).scalars()}
-    assert rows["GOOGL"] == ("7370", "Services-Computer")
+    assert rows["GOOGL"] == ("0001652044", "7370", "Services-Computer")
-    assert rows["GOOG"] == ("7370", "Services-Computer")
+    assert rows["GOOG"] == ("0001652044", "7370", "Services-Computer")
+
+
+async def test_fetch_sic_updates_is_read_only(factory):
+    client = FakeSecClient({}, submissions={1: {"sic": "1", "sic_description": "x"}})
+    updates = await su.fetch_sic_updates(client, {1: [10, 11]})
+    assert updates == [(10, "1", "x"), (11, "1", "x")]  # proposals only, no DB touched
 
 
 def test_universe_fingerprint_changes_on_membership():
@@ -93,11 +106,13 @@ def test_universe_fingerprint_changes_on_membership():
     assert a != remapped  # changed CIK mapping forces a new revision
 
 
+def test_compose_revision_rejects_missing_index_date():
+    with pytest.raises(ValueError):
+        su.compose_revision(None, "abc", {"AAPL": 320193})
+
+
 def test_compose_revision_and_index_hash():
-    rows = [
+    rows = [{"cik": 320193, "accession": "a-1"}, {"cik": 66740, "accession": "b-2"}]
-        {"cik": 320193, "accession": "a-1"},
-        {"cik": 66740, "accession": "b-2"},
-    ]
     h1 = su.index_content_hash(rows)
     h2 = su.index_content_hash(list(reversed(rows)))
     assert h1 == h2  # order-independent