feat(scada): require complete authorized investigation evidence

app/mcp/scada_readings.py

@@ -0,0 +1,121 @@
+"""Complete project SCADA reads with explicit frozen-scope and missing-data accounting."""
+
+import json
+from collections import Counter
+
+from fastapi import HTTPException
+from fastapi.encoders import jsonable_encoder
+
+from app.mcp.models import BoundContext, ScadaInput
+from app.mcp.scope import QueryScope
+from app.infra.db.postgresql import read_queries as reads
+from app.infra.db.postgresql.scada_replays import ScadaReplayRepository
+from app.services.scada_replay_queries import check_replay_window, check_snapshot_start
+
+
+MAX_COMPLETE_SCADA_BYTES = 8 * 1024 * 1024
+
+
+async def read_complete_scada(
+    scope: QueryScope, binding: BoundContext, args: ScadaInput,
+) -> tuple[dict, dict, list[str], str]:
+    """Exhaust source pages; never treat a first page or selected device subset as a full scan."""
+    devices = []
+    offset = 0
+    size = 0
+
+    def account(items):
+        nonlocal size
+        size += len(json.dumps(jsonable_encoder(items), ensure_ascii=False).encode())
+        if size > MAX_COMPLETE_SCADA_BYTES:
+            raise HTTPException(413, "Complete SCADA result exceeds 8 MiB; split the time window and retain every device")
+
+    while True:
+        page = await reads.scada_devices(scope.connection, limit=501, offset=offset)
+        batch = page[:500]
+        account(batch)
+        devices.extend(batch)
+        if len(page) <= 500:
+            break
+        offset += len(batch)
+
+    project_device_count = len(devices)
+    context = getattr(binding, "replay_context", None)
+    catalog = {str(device["device_id"]): device for device in devices}
+    outside_scope = []
+    if context:
+        check_replay_window(context, args.start, args.end)
+        repository = ScadaReplayRepository(scope.connection, scope.project.project_id)
+        run = await repository.get(context["replay_id"])
+        if not run:
+            raise HTTPException(404, "SCADA replay was not found in the current project")
+        check_snapshot_start(run, args.start)
+        frozen = {str(device["device_id"]): device for device in run.get("devices", [])}
+        selected = list(dict.fromkeys(run["config"]["device_ids"]))
+        outside_scope = sorted(set(catalog) - set(selected))
+        # Retain devices removed from the current catalogue but present in the frozen source.
+        for device in selected:
+            if device not in catalog:
+                catalog[device] = frozen.get(device, {"device_id": device})
+        devices = list(catalog.values())
+    else:
+        selected = list(catalog)
+
+    rows = []
+    offset = 0
+    # The public limit controls source page size, not completeness of this operation.
+    page_size = min(max(args.limit, 1000), 10000)
+
+    async def read_pages(connection=None):
+        nonlocal offset
+        while selected:
+            if context:
+                page = await repository.detected_outputs(
+                    context["replay_id"], selected, args.start, args.end, context["batch_sequence"],
+                    limit=page_size + 1, offset=offset,
+                )
+            else:
+                page = await reads.series_rows(
+                    connection, source="scada", element_type="junction", ids=selected,
+                    start=args.start, end=args.end, field=None,
+                    limit=page_size + 1, offset=offset,
+                )
+            batch = page[:page_size]
+            if context:
+                # Match the existing frozen-reading contract; internal source hashes are not observations.
+                fields = ("time", "device_id", "monitored_value", "cleaned_value", "quality", "reason")
+                batch = [{key: row[key] for key in fields if key in row} for row in batch]
+            account(batch)
+            rows.extend(batch)
+            if len(page) <= page_size:
+                break
+            offset += len(batch)
+
+    if context:
+        await read_pages()
+    elif selected:
+        async with scope.timescale() as connection:
+            await read_pages(connection)
+
+    counts = Counter(str(row["device_id"]) for row in rows)
+    missing = sorted(set(selected) - counts.keys())
+    coverage = {
+        "mode": "all_scada", "query_complete": True,
+        "project_device_count": project_device_count, "queried_device_count": len(selected),
+        "devices_with_readings": len(counts), "reading_count": len(rows),
+        "queried_device_ids": selected, "missing_device_ids": missing,
+        "outside_frozen_scope_device_ids": outside_scope,
+        "readings_per_device": {device: counts[device] for device in selected},
+        "replay_id": context["replay_id"] if context else None,
+        "batch_sequence": context["batch_sequence"] if context else None,
+    }
+    data = {"devices": devices, "readings": rows, "coverage": coverage}
+    account([coverage])
+    gaps = []
+    if missing:
+        gaps.append(f"{len(missing)} queried SCADA devices have no readings in this window; see coverage.missing_device_ids")
+    if outside_scope:
+        gaps.append(f"{len(outside_scope)} project devices are outside this frozen replay; see coverage.outside_frozen_scope_device_ids")
+    units = {device: catalog[device]["measurement_unit"] for device in selected
+             if catalog[device].get("measurement_unit")}
+    return data, units, gaps, "synthetic" if context else "system_data"