feat(deploy): schedule fundamentals shadow imports

.env.example

@@ -32,7 +32,8 @@ ALPHA_VANTAGE_API_KEY=
 #   e.g. Windows: C:\Program Files\Dolt\bin\dolt.exe). DOLT_DATA_DIR holds the
 #   clones; in PRODUCTION it MUST be outside the deploy tree (deploy is
 #   rsync --delete) — e.g. /var/lib/signal-platform/dolt. The earnings clone lives
-#   at <DOLT_DATA_DIR>/<DOLT_EARNINGS_SUBDIR>. Set up: dolt clone post-no-preference/earnings <dir>.
+#   at <DOLT_DATA_DIR>/<DOLT_EARNINGS_SUBDIR>. Production setup is automated by
+#   deploy/provision_fundamentals.sh; see docs/fundamentals-deployment.md.
 DOLT_BINARY=dolt
 DOLT_DATA_DIR=dolt-data
 DOLT_EARNINGS_SUBDIR=earnings

app/scheduler.py

@@ -41,6 +41,9 @@ from app.services import (
     settings_store,
     shadow_book_service,
 )
+from app.services.data_import import STATUS_FAILED, SourceImporter, run_import
+from app.services.dolt_earnings_importer import DoltEarningsImporter
+from app.services.sec_fundamentals_importer import SecFundamentalsImporter
 from app.services.alert_service import dispatch_alerts
 from app.services.backtest_service import (
     BACKTEST_TARGET_MODELS,
@@ -93,6 +96,8 @@ _JOB_NAMES = [
     "data_backfill",
     "sentiment_collector",
     "fundamental_collector",
+    "dolt_earnings_import",
+    "sec_fundamentals_import",
     "rr_scanner",
     "ticker_universe_sync",
     "alerts",
@@ -912,6 +917,70 @@ async def collect_fundamentals() -> None:
         _runtime_finish(job_name, "error", processed=processed, total=total, message=str(exc))
 
 
+# ---------------------------------------------------------------------------
+# Jobs: shadow fundamentals sources
+# ---------------------------------------------------------------------------
+
+
+async def _run_shadow_import(job_name: str, importer: SourceImporter) -> None:
+    """Run one source importer and surface its audit result in Admin → Jobs."""
+    _log_event(logging.INFO, "job_start", job=job_name)
+    _runtime_start(job_name, total=1)
+
+    try:
+        async with async_session_factory() as db:
+            if not await _is_job_enabled(db, job_name):
+                _log_event(logging.INFO, "job_skipped", job=job_name, reason="disabled")
+                _runtime_finish(job_name, "skipped", processed=0, total=1, message="Disabled")
+                return
+
+        run = await run_import(importer)
+        if run is None:
+            message = "Another import for this source is already running"
+            _log_event(logging.INFO, "job_skipped", job=job_name, reason="source_locked")
+            _runtime_finish(job_name, "skipped", processed=0, total=1, message=message)
+            return
+
+        revision = f" · {run.revision[:12]}" if run.revision else ""
+        message = f"{run.status}{revision}"
+        if run.status == STATUS_FAILED:
+            message = run.error_details or message
+            _log_event(logging.ERROR, "job_error", job=job_name, message=message)
+            _runtime_finish(job_name, "error", processed=0, total=1, message=message)
+            return
+
+        _log_event(
+            logging.INFO,
+            "job_complete",
+            job=job_name,
+            import_status=run.status,
+            revision=run.revision,
+        )
+        _runtime_finish(job_name, "completed", processed=1, total=1, message=message)
+    except asyncio.CancelledError:
+        _runtime_finish(job_name, "error", processed=0, total=1, message="Cancelled")
+        raise
+    except Exception as exc:
+        _log_event(
+            logging.ERROR,
+            "job_error",
+            job=job_name,
+            error_type=type(exc).__name__,
+            message=str(exc),
+        )
+        _runtime_finish(job_name, "error", processed=0, total=1, message=str(exc))
+
+
+async def run_dolt_earnings_import() -> None:
+    """Pull and import the Dolt earnings calendar/results feed in shadow."""
+    await _run_shadow_import("dolt_earnings_import", DoltEarningsImporter())
+
+
+async def run_sec_fundamentals_import() -> None:
+    """Import tracked-universe SEC facts in shadow."""
+    await _run_shadow_import("sec_fundamentals_import", SecFundamentalsImporter())
+
+
 # ---------------------------------------------------------------------------
 # Job: R:R Scanner
 # ---------------------------------------------------------------------------
@@ -1452,6 +1521,9 @@ SCHEDULE_DEFAULTS: dict[str, str] = {
     "schedule_timezone": "America/New_York",
     # Morning data/display refresh (no qualifying R:R scan).
     "schedule_daily_pipeline_cron": "0 2 * * *",
+    # Shadow source imports. They never write legacy fundamental_data before A5.
+    "schedule_dolt_earnings_cron": "30 2 * * *",
+    "schedule_sec_fundamentals_cron": "0 4 * * *",
     # Fetch in-progress bars → scan → Telegram (manual MOC window).
     "schedule_near_close_pipeline_cron": "30 15 * * mon-fri",
     # Fetch final bars → outcome eval (must not run on the partial near-close bar).
@@ -1465,6 +1537,8 @@ SCHEDULE_DEFAULTS: dict[str, str] = {
 # job id -> schedule setting key
 _CRON_JOBS: dict[str, str] = {
     "daily_pipeline": "schedule_daily_pipeline_cron",
+    "dolt_earnings_import": "schedule_dolt_earnings_cron",
+    "sec_fundamentals_import": "schedule_sec_fundamentals_cron",
     "near_close_pipeline": "schedule_near_close_pipeline_cron",
     "after_close_pipeline": "schedule_after_close_pipeline_cron",
     "intraday_pipeline": "schedule_intraday_pipeline_cron",
@@ -1549,6 +1623,28 @@ def configure_scheduler(schedule_config: dict[str, str] | None = None) -> None:
         _cron_trigger(cfg["schedule_daily_pipeline_cron"], tz, "schedule_daily_pipeline_cron"),
         id="daily_pipeline", name="Morning Pipeline", replace_existing=True,
     )
+    scheduler.add_job(
+        run_dolt_earnings_import,
+        _cron_trigger(
+            cfg["schedule_dolt_earnings_cron"],
+            tz,
+            "schedule_dolt_earnings_cron",
+        ),
+        id="dolt_earnings_import",
+        name="Dolt Earnings Import (shadow)",
+        replace_existing=True,
+    )
+    scheduler.add_job(
+        run_sec_fundamentals_import,
+        _cron_trigger(
+            cfg["schedule_sec_fundamentals_cron"],
+            tz,
+            "schedule_sec_fundamentals_cron",
+        ),
+        id="sec_fundamentals_import",
+        name="SEC Fundamentals Import (shadow)",
+        replace_existing=True,
+    )
     scheduler.add_job(
         run_near_close_pipeline,
         _cron_trigger(
@@ -1622,6 +1718,8 @@ def configure_scheduler(schedule_config: dict[str, str] | None = None) -> None:
             "cron": cfg["schedule_daily_pipeline_cron"],
             "steps": [name for name, _ in _DAILY_PIPELINE_STEPS],
         },
+        dolt_earnings_import={"cron": cfg["schedule_dolt_earnings_cron"]},
+        sec_fundamentals_import={"cron": cfg["schedule_sec_fundamentals_cron"]},
         near_close_pipeline={
             "cron": cfg["schedule_near_close_pipeline_cron"],
             "steps": [name for name, _ in _NEAR_CLOSE_PIPELINE_STEPS],

app/services/admin_service.py

@@ -612,6 +612,8 @@ VALID_JOB_NAMES = {
     "benchmark_collector",
     "sentiment_collector",
     "fundamental_collector",
+    "dolt_earnings_import",
+    "sec_fundamentals_import",
     "rr_scanner",
     "ticker_universe_sync",
     "outcome_evaluator",
@@ -633,6 +635,8 @@ JOB_LABELS = {
     "benchmark_collector": "Benchmark Collector",
     "sentiment_collector": "Sentiment Collector",
     "fundamental_collector": "Fundamental Collector",
+    "dolt_earnings_import": "Dolt Earnings Import (shadow)",
+    "sec_fundamentals_import": "SEC Fundamentals Import (shadow)",
     "rr_scanner": "R:R Scanner",
     "ticker_universe_sync": "Ticker Universe Sync",
     "outcome_evaluator": "Outcome Evaluator",

deploy/provision_fundamentals.sh

@@ -0,0 +1,100 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# One-time production provisioning for the shadow fundamentals sources.
+# Run as root to install; run with --check as the deploy user for a read-only
+# preflight. Version upgrades are intentional code changes, never "latest".
+DOLT_VERSION="2.2.0"
+DOLT_BINARY="${DOLT_BINARY:-/usr/local/bin/dolt}"
+DOLT_DATA_DIR="${DOLT_DATA_DIR:-/var/lib/signal-platform/dolt}"
+DOLT_EARNINGS_SUBDIR="${DOLT_EARNINGS_SUBDIR:-earnings}"
+APP_USER="${APP_USER:-deploy}"
+APP_GROUP="${APP_GROUP:-deploy}"
+ENV_FILE="${ENV_FILE:-/opt/signalplatform/.env}"
+MIN_FREE_GB="${DOLT_MIN_FREE_DISK_GB:-5}"
+EARNINGS_DIR="${DOLT_DATA_DIR}/${DOLT_EARNINGS_SUBDIR}"
+
+fail() {
+  echo "ERROR: $*" >&2
+  exit 1
+}
+
+version_ok() {
+  local output
+  output="$("$DOLT_BINARY" version 2>/dev/null || true)"
+  grep -Eq "(^|[[:space:]])v?${DOLT_VERSION}([[:space:]]|$)" <<<"$output"
+}
+
+check_free_space() {
+  local available_kb
+  available_kb="$(df -Pk "$DOLT_DATA_DIR" | awk 'NR == 2 {print $4}')"
+  [[ "$available_kb" =~ ^[0-9]+$ ]] || fail "could not read free space for $DOLT_DATA_DIR"
+  if ! awk -v available="$available_kb" -v minimum_gb="$MIN_FREE_GB" \
+    'BEGIN { exit !(available >= minimum_gb * 1024 * 1024) }'; then
+    fail "$DOLT_DATA_DIR has less than ${MIN_FREE_GB} GB free"
+  fi
+}
+
+check_env() {
+  [[ -f "$ENV_FILE" ]] || fail "missing environment file: $ENV_FILE"
+  grep -Fqx "DOLT_BINARY=$DOLT_BINARY" "$ENV_FILE" \
+    || fail "set DOLT_BINARY=$DOLT_BINARY in $ENV_FILE"
+  grep -Fqx "DOLT_DATA_DIR=$DOLT_DATA_DIR" "$ENV_FILE" \
+    || fail "set DOLT_DATA_DIR=$DOLT_DATA_DIR in $ENV_FILE"
+  grep -Fqx "DOLT_EARNINGS_SUBDIR=$DOLT_EARNINGS_SUBDIR" "$ENV_FILE" \
+    || fail "set DOLT_EARNINGS_SUBDIR=$DOLT_EARNINGS_SUBDIR in $ENV_FILE"
+  grep -Eq '^SEC_USER_AGENT=.*@.*' "$ENV_FILE" \
+    || fail "SEC_USER_AGENT in $ENV_FILE must contain a real contact email"
+}
+
+check_all() {
+  id "$APP_USER" >/dev/null 2>&1 || fail "missing service user: $APP_USER"
+  [[ -x "$DOLT_BINARY" ]] || fail "missing Dolt binary: $DOLT_BINARY"
+  version_ok || fail "expected Dolt $DOLT_VERSION at $DOLT_BINARY"
+  [[ -d "$EARNINGS_DIR/.dolt" ]] \
+    || fail "missing earnings clone: $EARNINGS_DIR"
+  if [[ "$(id -un)" == "$APP_USER" ]]; then
+    [[ -r "$EARNINGS_DIR/.dolt" ]] \
+      || fail "earnings clone is not readable by $APP_USER"
+  elif command -v runuser >/dev/null 2>&1; then
+    runuser -u "$APP_USER" -- test -r "$EARNINGS_DIR/.dolt" \
+      || fail "earnings clone is not readable by $APP_USER"
+  else
+    fail "run --check as $APP_USER (or install runuser)"
+  fi
+  check_free_space
+  check_env
+  echo "OK: Dolt $DOLT_VERSION and earnings clone are provisioned"
+}
+
+if [[ "${1:-}" == "--check" ]]; then
+  check_all
+  exit 0
+fi
+
+[[ "$EUID" -eq 0 ]] || fail "run provisioning as root (or use --check)"
+command -v curl >/dev/null 2>&1 || fail "curl is required"
+command -v runuser >/dev/null 2>&1 || fail "runuser is required"
+id "$APP_USER" >/dev/null 2>&1 || fail "missing service user: $APP_USER"
+
+if ! version_ok; then
+  installer="$(mktemp)"
+  trap 'rm -f "$installer"' EXIT
+  curl -fsSL \
+    "https://github.com/dolthub/dolt/releases/download/v${DOLT_VERSION}/install.sh" \
+    -o "$installer"
+  bash "$installer"
+fi
+version_ok || fail "Dolt $DOLT_VERSION installation failed"
+
+install -d -o "$APP_USER" -g "$APP_GROUP" -m 0750 "$DOLT_DATA_DIR"
+check_free_space
+
+if [[ ! -d "$EARNINGS_DIR/.dolt" ]]; then
+  [[ ! -e "$EARNINGS_DIR" ]] \
+    || fail "$EARNINGS_DIR exists but is not a Dolt clone"
+  runuser -u "$APP_USER" -- \
+    "$DOLT_BINARY" clone post-no-preference/earnings "$EARNINGS_DIR"
+fi
+
+check_all

docs/dolt-integration-plan.md

@@ -164,8 +164,11 @@ calls. Check free disk space before pulling; alert and skip if below threshold.
 **Deployment constraints:** deploy is `rsync --delete` of the repo tree
 (`.gitea/workflows/deploy.yml:127`), so clones and archives must live **outside the
 deployment path** — an env-configured persistent directory (e.g.
-`DOLT_DATA_DIR=/var/lib/signal-platform/dolt`), backed up. The dolt binary is a new
+`DOLT_DATA_DIR=/var/lib/signal-platform/dolt`). The dolt binary is a new prod
-prod runtime dependency: install with a pinned version in the deploy workflow.
+runtime dependency: install it once with the version-pinned provisioner in
+`deploy/provision_fundamentals.sh`; operational steps are in
+`docs/fundamentals-deployment.md`. The clone is reproducible from DoltHub; the
+normalized PostgreSQL rows remain part of the normal database backup.
 
 **Validation gates (block promotion, raise an alert via the existing system-events
 path):** source freshness as expected; tracked-universe coverage; no duplicate
@@ -193,13 +196,14 @@ Workstream A:
 
 - Dolt earnings import: daily ~02:30 ET (with the future-row replacement above).
 - **SEC fundamentals job: daily ~04:00 ET.** One job, three steps:
-  (a) freshness check **using conditional HTTP metadata (ETag/Last-Modified /
+  (a) detect a composite revision from the latest EDGAR daily-index date, the
-  If-None-Match) before downloading** — an unchanged archive is a `no_op` without
+  exact tracked index rows, and the tracked-universe fingerprint — an unchanged
-  pulling the multi-GB file; verify by SHA-256 after any actual download;
+  revision is a `no_op` before Company Facts are fetched;
-  (b) when changed, **parse and write only tracked-universe CIKs** through
+  (b) when changed, fetch and parse Company Facts only for tracked-universe CIKs
-  staging→promotion (the tracked universe is `ticker_universe_service`'s set;
+  that filed, plus full available history for the first run or a newly added
-  CIKs are resolved from `company_tickers.json` each run, so a newly added ticker
+  issuer, through validation→atomic promotion. Universe resolution and the exact
-  self-resolves on its next SEC run — until then its metrics are simply null);
+  index inputs are cached during revision detection and reused during staging;
+  CIKs are resolved from `company_tickers.json` without writes until promotion;
   (c) **always, locally, and only after production activation** (the phase-A5
   parity approval): refresh the legacy `fundamental_data` fields and mark affected
   cached fundamental scores stale. **Sources differ per field** — do not assume all
@@ -405,9 +409,9 @@ workstream B — Alpaca remains the price source throughout.
 **Workstream A:**
 
 - A0. License review **DONE** (earnings approved for private/internal use under
-  CC BY-SA 4.0, no redistribution — see Licensing above); still pending at deploy
+  CC BY-SA 4.0, no redistribution — see Licensing above). The Dolt version,
-  time: dolt binary pinned in deploy; `DOLT_DATA_DIR` outside the rsync tree
+  persistent `DOLT_DATA_DIR`, clone, and production checks are captured in
-  (earnings clone only — small), provisioned and backed up.
+  `deploy/provision_fundamentals.sh` and `docs/fundamentals-deployment.md`.
 - A1. Migration 026, import-run framework.
 - A2. Earnings ingestion in shadow (writes `earnings_events`, prod untouched);
   verify forward-calendar coverage and rescheduling behavior.

docs/fundamentals-deployment.md

@@ -0,0 +1,133 @@
+# Fundamentals production deployment
+
+This is the one-time production setup for the Dolt earnings and SEC fundamentals
+imports. Both imports remain shadow inputs until the separate A5 scoring-cutover
+approval. Do not add OS cron entries: the application scheduler owns both jobs.
+
+## What the deployment adds
+
+- `Dolt Earnings Import (shadow)` runs daily at 02:30 America/New_York.
+- `SEC Fundamentals Import (shadow)` runs daily at 04:00 America/New_York.
+- Both jobs are visible, toggleable, and manually triggerable in Admin → Jobs.
+- Cron expressions are editable in Admin → Schedule.
+- Every attempt is recorded in `data_import_runs`; failures also create a system
+  event. A failed validation does not promote partial data.
+
+The systemd service uses one application worker. The import framework also holds
+a PostgreSQL advisory lock per source, so an overlapping manual/scheduled run is
+skipped safely.
+
+## Prerequisites
+
+The production `.env` at `/opt/signalplatform/.env` must contain:
+
+```dotenv
+DOLT_BINARY=/usr/local/bin/dolt
+DOLT_DATA_DIR=/var/lib/signal-platform/dolt
+DOLT_EARNINGS_SUBDIR=earnings
+DOLT_MIN_FREE_DISK_GB=5.0
+SEC_USER_AGENT=signal-platform/1.0 (contact: real-address@example.com)
+SEC_REQUEST_SPACING_SECONDS=0.2
+```
+
+Use a real monitored contact address. Keep at least 5 GB free at the Dolt data
+path; 8–10 GB gives comfortable growth headroom. The data directory must stay
+outside `/opt/signalplatform`, because deployments use `rsync --delete` there.
+
+## One-time provisioning
+
+First deploy the commit containing this bundle to production. Then SSH to the
+server and run:
+
+```bash
+cd /opt/signalplatform
+sudo bash ./deploy/provision_fundamentals.sh
+sudo -u deploy bash ./deploy/provision_fundamentals.sh --check
+sudo systemctl restart signalplatform.service
+curl -fsS http://127.0.0.1:8998/api/v1/health
+```
+
+The provisioner is idempotent. It installs the pinned Dolt version, creates the
+persistent directory as `deploy:deploy`, clones
+`post-no-preference/earnings`, verifies free space and `.env`, and refuses an
+unexpected Dolt version. It does not modify PostgreSQL or start an import.
+
+Do not replace the pinned version with `latest`. A future Dolt upgrade should be
+a reviewed change to `DOLT_VERSION`, followed by the same provision/check flow.
+
+## First-run verification
+
+In Admin → Jobs, wait until no other job is running, then:
+
+1. Trigger **Dolt Earnings Import (shadow)**. Expect `completed` with import
+   status `promoted`; a repeat without an upstream change should report `no_op`.
+2. Trigger **SEC Fundamentals Import (shadow)**. The first run performs the
+   tracked-universe history backfill and can take materially longer than a daily
+   incremental run. Expect `completed` with import status `promoted`.
+3. Check Admin → System Events. There should be no new import error.
+4. Confirm the next-run times correspond to 02:30 and 04:00 New York time.
+5. Open several ticker pages and confirm the fundamentals panel has populated
+   data and still handles partial/missing issuers cleanly.
+
+Optional database verification:
+
+```sql
+SELECT source, status, revision, source_max_date, started_at, completed_at,
+       validation_json
+FROM data_import_runs
+WHERE source IN ('dolt_earnings', 'sec_facts')
+ORDER BY id DESC
+LIMIT 10;
+
+SELECT count(*) FROM earnings_events WHERE source = 'dolt_earnings';
+SELECT count(*), count(DISTINCT cik) FROM fundamental_snapshots;
+```
+
+During the longer first SEC run, execute the following in a second SSH session.
+It opens an independent database connection and attempts the same source lock:
+
+```bash
+cd /opt/signalplatform
+sudo -u deploy .venv/bin/python - <<'PY'
+import asyncio
+
+from sqlalchemy import text
+
+from app.database import engine
+from app.services.data_import import _advisory_key
+
+
+async def main():
+    key = _advisory_key("sec_facts")
+    async with engine.connect() as connection:
+        acquired = await connection.scalar(
+            text("SELECT pg_try_advisory_lock(:key)"), {"key": key}
+        )
+        print("UNEXPECTED: lock acquired" if acquired else "OK: source lock is busy")
+        if acquired:
+            await connection.execute(
+                text("SELECT pg_advisory_unlock(:key)"), {"key": key}
+            )
+
+
+asyncio.run(main())
+PY
+```
+
+Expect `OK: source lock is busy`. This is the remaining live-PostgreSQL
+mutual-exclusion check; SQLite unit tests cannot exercise PostgreSQL advisory
+locks. A second Admin trigger should independently report the job as busy.
+
+## Failure and rollback
+
+- Disable the failing shadow job in Admin → Jobs. This stops scheduled imports
+  without changing existing data or the legacy scoring path.
+- Inspect the job runtime, latest `data_import_runs.validation_json`, service
+  logs, and Admin → System Events before retrying.
+- Re-run `sudo -u deploy bash ./deploy/provision_fundamentals.sh --check` for
+  binary, clone, permission, disk, or environment failures.
+- The Dolt clone is a reproducible cache and does not need a bespoke backup.
+  PostgreSQL (including `earnings_events`, `fundamental_snapshots`, and import
+  audit rows) must remain covered by the normal production database backup.
+- Do not proceed to A5 while either shadow feed is unhealthy or the parity gate
+  has not received explicit approval.

frontend/src/components/admin/ScheduleSettings.tsx

@@ -6,10 +6,12 @@ import { SkeletonTable } from '../ui/Skeleton';
 const DEFAULTS: ScheduleConfig = {
   schedule_timezone: 'America/New_York',
   schedule_daily_pipeline_cron: '0 2 * * *',
-  schedule_near_close_pipeline_cron: '30 15 * * 1-5',
+  schedule_dolt_earnings_cron: '30 2 * * *',
-  schedule_after_close_pipeline_cron: '45 16 * * 1-5',
+  schedule_sec_fundamentals_cron: '0 4 * * *',
-  schedule_intraday_pipeline_cron: '0 10-15 * * 1-5',
+  schedule_near_close_pipeline_cron: '30 15 * * mon-fri',
-  schedule_fundamentals_cron: '0 1 * * 1',
+  schedule_after_close_pipeline_cron: '45 16 * * mon-fri',
+  schedule_intraday_pipeline_cron: '0 10-15 * * mon-fri',
+  schedule_fundamentals_cron: '0 1 * * mon',
 };
 
 const FIELDS: { key: keyof ScheduleConfig; label: string; hint: string; mono?: boolean }[] = [
@@ -24,6 +26,18 @@ const FIELDS: { key: keyof ScheduleConfig; label: string; hint: string; mono?: b
     hint: 'OHLCV → benchmark → sentiment → regime → alerts (no R:R scan). Default 02:00 ET so regime-quadrant changes hit Telegram in the morning.',
     mono: true,
   },
+  {
+    key: 'schedule_dolt_earnings_cron',
+    label: 'Dolt earnings (shadow)',
+    hint: 'Pull and import earnings dates/results daily at 02:30 ET. Live scoring remains untouched before A5.',
+    mono: true,
+  },
+  {
+    key: 'schedule_sec_fundamentals_cron',
+    label: 'SEC fundamentals (shadow)',
+    hint: 'Import tracked-universe SEC facts daily at 04:00 ET. Unchanged revisions become no-op runs.',
+    mono: true,
+  },
   {
     key: 'schedule_near_close_pipeline_cron',
     label: 'Near-close pipeline (scan + alert)',
@@ -44,8 +58,8 @@ const FIELDS: { key: keyof ScheduleConfig; label: string; hint: string; mono?: b
   },
   {
     key: 'schedule_fundamentals_cron',
-    label: 'Fundamentals (weekly)',
+    label: 'Legacy fundamentals (weekly)',
-    hint: 'Slow, rate-limited. Default early Monday ET.',
+    hint: 'Existing provider chain retained until the A5 parity approval and A6 removal.',
     mono: true,
   },
 ];

frontend/src/lib/types.ts

@@ -191,6 +191,8 @@ export interface ActivationConfig {
 export interface ScheduleConfig {
   schedule_timezone: string;
   schedule_daily_pipeline_cron: string;
+  schedule_dolt_earnings_cron: string;
+  schedule_sec_fundamentals_cron: string;
   schedule_near_close_pipeline_cron: string;
   schedule_after_close_pipeline_cron: string;
   schedule_intraday_pipeline_cron: string;

tests/unit/test_schedule_config.py

@@ -80,6 +80,28 @@ class TestTradingDayCrons:
         )
         assert fire.strftime("%a") == "Mon"
 
+    @pytest.mark.parametrize(
+        ("key", "hour", "minute"),
+        (
+            ("schedule_dolt_earnings_cron", 2, 30),
+            ("schedule_sec_fundamentals_cron", 4, 0),
+        ),
+    )
+    def test_shadow_imports_run_daily_at_expected_et_time(
+        self, key: str, hour: int, minute: int
+    ):
+        from datetime import datetime
+
+        from apscheduler.triggers.cron import CronTrigger
+
+        trigger = CronTrigger.from_crontab(
+            SCHEDULE_DEFAULTS[key], timezone=SCHEDULE_DEFAULTS["schedule_timezone"]
+        )
+        fire = trigger.get_next_fire_time(
+            None, datetime(2026, 7, 19, tzinfo=trigger.timezone)
+        )
+        assert (fire.hour, fire.minute) == (hour, minute)
+
 
 class TestScheduleConfig:
     async def test_defaults_when_unset(self, session: AsyncSession):

tests/unit/test_scheduler.py

@@ -1,5 +1,7 @@
 """Unit tests for app.scheduler module."""
 
+from types import SimpleNamespace
+
 import pytest
 
 from app.scheduler import (
@@ -8,7 +10,9 @@ from app.scheduler import (
     _parse_frequency,
     _resume_tickers,
     _last_successful,
+    _run_shadow_import,
     configure_scheduler,
+    get_job_runtime_snapshot,
     queue_backtest_options,
     queue_backtest_target_model,
     scheduler,
@@ -106,6 +110,8 @@ class TestConfigureScheduler:
             "benchmark_collector",
             "sentiment_collector",
             "fundamental_collector",
+            "dolt_earnings_import",
+            "sec_fundamentals_import",
             "rr_scanner",
             "shadow_book",
             "ticker_universe_sync",
@@ -137,6 +143,8 @@ class TestConfigureScheduler:
             "data_collector",
             "data_backfill",
             "fundamental_collector",
+            "dolt_earnings_import",
+            "sec_fundamentals_import",
             "market_regime",
             "near_close_pipeline",
             "regime_monitor",
@@ -147,3 +155,91 @@ class TestConfigureScheduler:
             "shadow_book",
             "ticker_universe_sync",
         ])
+
+
+class _SessionContext:
+    async def __aenter__(self):
+        return object()
+
+    async def __aexit__(self, *exc):
+        return None
+
+
+class TestShadowImportJobs:
+    @staticmethod
+    def _session_factory():
+        return _SessionContext()
+
+    async def test_promoted_run_surfaces_completion(self, monkeypatch):
+        async def enabled(db, job_name):
+            return True
+
+        async def imported(importer):
+            return SimpleNamespace(
+                status="promoted", revision="abcdef1234567890", error_details=None
+            )
+
+        monkeypatch.setattr("app.scheduler.async_session_factory", self._session_factory)
+        monkeypatch.setattr("app.scheduler._is_job_enabled", enabled)
+        monkeypatch.setattr("app.scheduler.run_import", imported)
+
+        await _run_shadow_import("dolt_earnings_import", object())
+
+        runtime = get_job_runtime_snapshot("dolt_earnings_import")
+        assert runtime["status"] == "completed"
+        assert runtime["processed"] == 1
+        assert runtime["message"] == "promoted · abcdef123456"
+
+    async def test_failed_run_surfaces_error(self, monkeypatch):
+        async def enabled(db, job_name):
+            return True
+
+        async def imported(importer):
+            return SimpleNamespace(
+                status="failed", revision=None, error_details="validation failed"
+            )
+
+        monkeypatch.setattr("app.scheduler.async_session_factory", self._session_factory)
+        monkeypatch.setattr("app.scheduler._is_job_enabled", enabled)
+        monkeypatch.setattr("app.scheduler.run_import", imported)
+
+        await _run_shadow_import("sec_fundamentals_import", object())
+
+        runtime = get_job_runtime_snapshot("sec_fundamentals_import")
+        assert runtime["status"] == "error"
+        assert runtime["processed"] == 0
+        assert runtime["message"] == "validation failed"
+
+    async def test_source_lock_surfaces_skipped(self, monkeypatch):
+        async def enabled(db, job_name):
+            return True
+
+        async def imported(importer):
+            return None
+
+        monkeypatch.setattr("app.scheduler.async_session_factory", self._session_factory)
+        monkeypatch.setattr("app.scheduler._is_job_enabled", enabled)
+        monkeypatch.setattr("app.scheduler.run_import", imported)
+
+        await _run_shadow_import("dolt_earnings_import", object())
+
+        runtime = get_job_runtime_snapshot("dolt_earnings_import")
+        assert runtime["status"] == "skipped"
+        assert "already running" in runtime["message"]
+
+    async def test_disabled_job_never_runs_importer(self, monkeypatch):
+        async def disabled(db, job_name):
+            return False
+
+        async def should_not_run(importer):
+            raise AssertionError("disabled job ran importer")
+
+        monkeypatch.setattr("app.scheduler.async_session_factory", self._session_factory)
+        monkeypatch.setattr("app.scheduler._is_job_enabled", disabled)
+        monkeypatch.setattr("app.scheduler.run_import", should_not_run)
+
+        await _run_shadow_import("sec_fundamentals_import", object())
+
+        runtime = get_job_runtime_snapshot("sec_fundamentals_import")
+        assert runtime["status"] == "skipped"
+        assert runtime["message"] == "Disabled"