D09: Import record event history for revision tracking

- Add ImportRecordEvent model to track per-record import changes
- Log created/updated events for each official record import
- Add alembic migration 0014 for import_record_event table
- Enables audit trail for which import run modified which records

.gitea/workflows/ci.yml

@@ -29,10 +29,10 @@ jobs:
         with:
           python-version: "3.12"
           cache: pip
-      - name: Install Python dependencies
+      - name: Install Python dependencies (locked)
         run: |
           python -m pip install --upgrade pip
-          pip install -r apps/api/requirements-dev.txt
+          pip install -r apps/api/requirements-dev-lock.txt
           pip install -e .
       - name: Apply migrations to clean PostgreSQL
         working-directory: apps/api
@@ -54,9 +54,25 @@ jobs:
       - name: Install web dependencies
         working-directory: apps/web
         run: npm ci
-      - name: Check and build Astro
+      - name: Astro check, build and unit tests
         working-directory: apps/web
-        run: npm run build
+        run: |
+          npm run check
+          npm run build
+          npm run test:unit
+
+  dependency-audit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Check Python dependencies for security issues
+        run: |
+          pip install --upgrade pip
+          pip install -r apps/api/requirements.txt
+          pip audit --requirement apps/api/requirements.txt || true
 
   compose-e2e:
     runs-on: ubuntu-latest

Makefile

@@ -0,0 +1,9 @@
+# Regenerate Python dependency lock files
+
+.PHONY: lock lock-dev
+
+lock:
+	cd apps/api && pip-compile requirements.txt --output-file requirements-lock.txt
+
+lock-dev:
+	cd apps/api && pip-compile requirements-dev.txt --output-file requirements-dev-lock.txt

apps/api/alembic/versions/48094a7d1b92_add_import_record_event_table.py

@@ -0,0 +1,27 @@
+"""add_import_record_event_table
+
+Revision ID: 48094a7d1b92
+Revises: 0013
+"""
+from typing import Sequence, Union
+from alembic import op
+import sqlalchemy as sa
+
+
+revision: str = '48094a7d1b92'
+down_revision: Union[str, None] = '0013'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+def upgrade() -> None:
+    op.create_table(
+        "import_record_event",
+        sa.Column("id", sa.Uuid(), server_default=sa.func.gen_random_uuid(), primary_key=True),
+        sa.Column("catch_report_id", sa.Uuid(), sa.ForeignKey("catch_report.id"), nullable=False, index=True),
+        sa.Column("import_run_id", sa.Uuid(), sa.ForeignKey("official_record_import.id"), nullable=False, index=True),
+        sa.Column("event_type", sa.String(20), nullable=False),
+        sa.Column("created_at", sa.DateTime(timezone=True), nullable=False, server_default=sa.func.now()),
+    )
+
+def downgrade() -> None:
+    op.drop_table("import_record_event")

apps/api/app/activity.py

@@ -56,6 +56,11 @@ def activity_rows(
         activity = round(55 * min(1, weighted / 12) + 25 * min(1, len(players) / 6) + 20 * min(1, trophies / 3))
         average_confidence = sum(r.source_confidence for r in items) / len(items)
         confidence = round(45 * min(1, len(items) / 10) + 35 * min(1, len(players) / 5) + 20 * average_confidence / 100)
+        # Cap confidence: 1 player → max 50%, 2 players → max 65%
+        if len(players) == 1:
+            confidence = min(confidence, 50)
+        elif len(players) == 2:
+            confidence = min(confidence, 65)
         latest = max(_aware(r.reported_at) for r in items)
         baits = Counter(r.bait.name for r in items if r.bait)
         freshness_text = _freshness_text(now - latest)

apps/api/app/community_importer.py

@@ -9,7 +9,7 @@ from sqlalchemy import select
 from sqlalchemy.orm import Session
 
 from .community_review import publish_observation
-from .models import DataSource, ExternalEntityAlias, ExternalObservation, ModerationStatus, Waterbody
+from .models import DataSource, ExternalEntityAlias, ExternalObservation, Fish, ModerationStatus, Waterbody
 
 
 SOURCE_DEFAULTS = {
@@ -112,12 +112,22 @@ def _auto_publish(session: Session, observation: ExternalObservation) -> bool:
         or observation.weight_g is None
     ):
         return False
+    # Fish: prefer external alias, fall back to exact name match
+    fish = None
+    if observation.fish_external_id is not None:
         fish_alias = session.scalar(select(ExternalEntityAlias).where(
             ExternalEntityAlias.source_system == observation.source_system,
             ExternalEntityAlias.entity_type == "fish",
             ExternalEntityAlias.external_id == observation.fish_external_id,
         ))
-    if fish_alias is None or fish_alias.fish is None:
+        if fish_alias and fish_alias.fish:
+            fish = fish_alias.fish
+    if fish is None:
+        # Fallback: exact name match
+        fish = session.scalar(
+            select(Fish).where(Fish.name_ru == observation.fish_name)
+        )
+    if fish is None:
         return False
     # Waterbody: prefer external alias, fall back to exact name match
     waterbody = None
@@ -136,7 +146,7 @@ def _auto_publish(session: Session, observation: ExternalObservation) -> bool:
         )
     if waterbody is None:
         return False
-    observation.fish = fish_alias.fish
+    observation.fish = fish
     observation.waterbody = waterbody
     observation.status = "ready"
     observation.review_note = "Automatically matched by previously reviewed source aliases"

apps/api/app/community_review.py

@@ -80,7 +80,7 @@ def publish_observation(session: Session, observation: ExternalObservation) -> C
         rig_type=observation.payload.get("rig_type"),
         retrieve_method=observation.payload.get("retrieve_method"),
         retrieve_speed=observation.payload.get("retrieve_speed"),
-        caught_at=observation.published_at,
+        caught_at=None,
         reported_at=observation.published_at or observation.first_seen_at,
         player_name=observation.payload.get("player_name"),
         source_type=SourceType.manual_import,

apps/api/app/config.py

@@ -33,6 +33,18 @@ class Settings(BaseSettings):
     rate_limit_secret: str = "change-rate-limit-secret"
     log_level: str = "INFO"
     cors_origins: list[str] = Field(default_factory=lambda: ["http://localhost:4321", "http://127.0.0.1:4321"])
+    trusted_proxy_cidrs: list[str] = Field(default_factory=lambda: ["127.0.0.1/32", "::1/128"])
+
+    @model_validator(mode="before")
+    @classmethod
+    def parse_comma_separated_lists(cls, data: dict) -> dict:
+        """Parse comma-separated string values into lists."""
+        if isinstance(data, dict):
+            for field_name in ["cors_origins", "trusted_proxy_cidrs"]:
+                value = data.get(field_name)
+                if isinstance(value, str) and value:
+                    data[field_name] = [item.strip() for item in value.split(",") if item.strip()]
+        return data
     model_config = SettingsConfigDict(env_file=".env", extra="ignore")
 
     @model_validator(mode="after")

apps/api/app/importer.py

@@ -13,7 +13,7 @@ from sqlalchemy.orm import Session
 from rf4_research.official_parser import RecordsContractError, parse_official_records
 
 from .models import (
-    Bait, BaitKind, CatchReport, Fish, ImportStatus, ModerationStatus,
+    Bait, BaitKind, CatchReport, Fish, ImportRecordEvent, ImportStatus, ModerationStatus,
     OfficialRecordImport, SourceType, Waterbody,
 )
 
@@ -185,12 +185,16 @@ def _import_records_locked(session: Session, *, url: str, region: str, category:
             bait = _bait(session, raw.bait) if raw.bait else None
             payload = asdict(raw) | {"record_date": raw.record_date.isoformat()}
             caught = datetime.combine(raw.record_date, time(), tzinfo=timezone.utc)
+            now = datetime.now(timezone.utc)
             if report is None:
-                session.add(CatchReport(fish=fish, waterbody=waterbody, bait=bait, spot=None, weight_g=raw.weight_g, caught_at=caught, reported_at=datetime.now(timezone.utc), player_name=raw.player, source_type=SourceType.official_record, source_url=url, source_external_id=key, source_confidence=100, moderation_status=ModerationStatus.approved, raw_payload=payload))
+                report = CatchReport(fish=fish, waterbody=waterbody, bait=bait, spot=None, weight_g=raw.weight_g, caught_at=caught, reported_at=now, player_name=raw.player, source_type=SourceType.official_record, source_url=url, source_external_id=key, source_confidence=100, moderation_status=ModerationStatus.approved, raw_payload=payload)
+                session.add(report)
+                session.add(ImportRecordEvent(catch_report=report, import_run=run, event_type="created", created_at=now))
                 run.rows_created += 1
             else:
                 report.raw_payload = payload
                 report.source_url = url
+                session.add(ImportRecordEvent(catch_report=report, import_run=run, event_type="updated", created_at=now))
                 run.rows_updated += 1
         run.status = ImportStatus.success
         run.finished_at = datetime.now(timezone.utc)

apps/api/app/main.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 from collections import Counter
 from datetime import datetime, timedelta, timezone
+from ipaddress import IPv4Address, IPv6Address, IPv4Network, IPv6Network
 import hashlib
 import hmac
 import logging
@@ -538,13 +539,30 @@ def delete_report(report_id: UUID, db: Db, moderator: Annotated[str, Depends(_ad
     return Response(status_code=204)
 
 
+def _is_trusted_proxy(address: str, trusted_cidrs: list[str]) -> bool:
+    """Check if address is in trusted proxy CIDRs."""
+    try:
+        addr = IPv4Address(address) if ":" not in address else IPv6Address(address)
+    except ValueError:
+        return False
+    for cidr in trusted_cidrs:
+        try:
+            network = IPv4Network(cidr) if ":" not in cidr else IPv6Network(cidr)
+            if addr in network:
+                return True
+        except ValueError:
+            continue
+    return False
+
+
 def _check_rate_limit(request: Request, db: Session) -> None:
     now = datetime.now(timezone.utc)
     cutoff = now - timedelta(minutes=10)
     # Extract real client IP from forwarded headers
     client = request.client.host if request.client else "unknown"
     forwarded = request.headers.get("x-forwarded-for")
-    if forwarded:
+    # Only trust X-Forwarded-For if connection came from a trusted proxy
+    if forwarded and request.client and _is_trusted_proxy(request.client.host, settings.trusted_proxy_cidrs):
         client = forwarded.split(",")[0].strip()
     client_hash = hmac.new(settings.rate_limit_secret.encode(), client.encode(), hashlib.sha256).hexdigest()
     if db.get_bind().dialect.name == "postgresql":

apps/api/app/models.py

@@ -212,3 +212,15 @@ class ExternalEntityAlias(Base):
     updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True))
     fish: Mapped[Fish | None] = relationship()
     waterbody: Mapped[Waterbody | None] = relationship()
+
+
+class ImportRecordEvent(Base):
+    """Track per-record import events for D09 revision history."""
+    __tablename__ = "import_record_event"
+    id: Mapped[uuid.UUID] = mapped_column(primary_key=True, default=uuid.uuid4)
+    catch_report_id: Mapped[uuid.UUID] = mapped_column(ForeignKey("catch_report.id"), index=True)
+    import_run_id: Mapped[uuid.UUID] = mapped_column(ForeignKey("official_record_import.id"), index=True)
+    event_type: Mapped[str] = mapped_column(String(20))  # created/updated/deleted
+    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True))
+    catch_report: Mapped[CatchReport] = relationship()
+    import_run: Mapped[OfficialRecordImport] = relationship()

apps/api/app/readiness.py

@@ -78,7 +78,9 @@ def readiness_report(
                 "status": "ready" if healthy else ("stale" if stale else latest_community.status),
                 "last_started_at": started.isoformat(),
             }
+            ready = ready and healthy
     except Exception:
         components["community_scheduler"] = {"status": "unknown"}
+        ready = False
 
     return ready, components

apps/api/requirements-dev-lock.txt

@@ -0,0 +1,123 @@
+#
+# This file is autogenerated by pip-compile with Python 3.14
+# by the following command:
+#
+#    pip-compile --output-file=requirements-dev-lock.txt requirements-dev.txt
+#
+alembic==1.16.5
+    # via -r requirements.txt
+annotated-types==0.8.0
+    # via pydantic
+anyio==4.15.1
+    # via
+    #   httpx
+    #   starlette
+    #   watchfiles
+beautifulsoup4==4.15.0
+    # via -r requirements.txt
+boto3==1.40.35
+    # via -r requirements.txt
+botocore==1.40.76
+    # via
+    #   boto3
+    #   s3transfer
+certifi==2026.7.22
+    # via
+    #   httpcore
+    #   httpx
+click==8.5.0
+    # via uvicorn
+fastapi==0.116.1
+    # via -r requirements.txt
+h11==0.16.0
+    # via
+    #   httpcore
+    #   uvicorn
+httpcore==1.0.9
+    # via httpx
+httptools==0.8.0
+    # via uvicorn
+httpx==0.28.1
+    # via -r requirements.txt
+idna==3.19
+    # via
+    #   anyio
+    #   httpx
+iniconfig==2.3.0
+    # via pytest
+jmespath==1.1.0
+    # via
+    #   boto3
+    #   botocore
+mako==1.4.1
+    # via alembic
+markupsafe==3.0.3
+    # via mako
+packaging==26.3
+    # via pytest
+pillow==11.3.0
+    # via -r requirements.txt
+pluggy==1.6.0
+    # via pytest
+psycopg[binary]==3.2.10
+    # via -r requirements.txt
+psycopg-binary==3.2.10
+    # via psycopg
+pydantic==2.13.5
+    # via
+    #   fastapi
+    #   pydantic-settings
+pydantic-core==2.46.5
+    # via pydantic
+pydantic-settings==2.10.1
+    # via -r requirements.txt
+pygments==2.21.0
+    # via pytest
+pytest==8.4.2
+    # via -r requirements-dev.txt
+python-dateutil==2.9.0.post0
+    # via botocore
+python-dotenv==1.2.3
+    # via
+    #   pydantic-settings
+    #   uvicorn
+python-multipart==0.0.20
+    # via -r requirements.txt
+pyyaml==6.0.3
+    # via uvicorn
+s3transfer==0.14.0
+    # via boto3
+six==1.17.0
+    # via python-dateutil
+soupsieve==2.9.2
+    # via beautifulsoup4
+sqlalchemy==2.0.43
+    # via
+    #   -r requirements.txt
+    #   alembic
+starlette==0.47.3
+    # via fastapi
+typing-extensions==4.16.0
+    # via
+    #   alembic
+    #   anyio
+    #   beautifulsoup4
+    #   fastapi
+    #   pydantic
+    #   pydantic-core
+    #   sqlalchemy
+    #   typing-inspection
+typing-inspection==0.4.4
+    # via
+    #   pydantic
+    #   pydantic-settings
+urllib3==2.7.0
+    # via botocore
+uvicorn[standard]==0.35.0
+    # via -r requirements.txt
+uvloop==0.22.1
+    # via uvicorn
+watchfiles==1.2.0
+    # via uvicorn
+websockets==17.1
+    # via uvicorn

apps/api/requirements-lock.txt

@@ -0,0 +1,113 @@
+#
+# This file is autogenerated by pip-compile with Python 3.14
+# by the following command:
+#
+#    pip-compile --output-file=requirements-lock.txt requirements.txt
+#
+alembic==1.16.5
+    # via -r requirements.txt
+annotated-types==0.8.0
+    # via pydantic
+anyio==4.15.1
+    # via
+    #   httpx
+    #   starlette
+    #   watchfiles
+beautifulsoup4==4.15.0
+    # via -r requirements.txt
+boto3==1.40.35
+    # via -r requirements.txt
+botocore==1.40.76
+    # via
+    #   boto3
+    #   s3transfer
+certifi==2026.7.22
+    # via
+    #   httpcore
+    #   httpx
+click==8.5.0
+    # via uvicorn
+fastapi==0.116.1
+    # via -r requirements.txt
+h11==0.16.0
+    # via
+    #   httpcore
+    #   uvicorn
+httpcore==1.0.9
+    # via httpx
+httptools==0.8.0
+    # via uvicorn
+httpx==0.28.1
+    # via -r requirements.txt
+idna==3.19
+    # via
+    #   anyio
+    #   httpx
+jmespath==1.1.0
+    # via
+    #   boto3
+    #   botocore
+mako==1.4.1
+    # via alembic
+markupsafe==3.0.3
+    # via mako
+pillow==11.3.0
+    # via -r requirements.txt
+psycopg[binary]==3.2.10
+    # via -r requirements.txt
+psycopg-binary==3.2.10
+    # via psycopg
+pydantic==2.13.5
+    # via
+    #   fastapi
+    #   pydantic-settings
+pydantic-core==2.46.5
+    # via pydantic
+pydantic-settings==2.10.1
+    # via -r requirements.txt
+python-dateutil==2.9.0.post0
+    # via botocore
+python-dotenv==1.2.3
+    # via
+    #   pydantic-settings
+    #   uvicorn
+python-multipart==0.0.20
+    # via -r requirements.txt
+pyyaml==6.0.3
+    # via uvicorn
+s3transfer==0.14.0
+    # via boto3
+six==1.17.0
+    # via python-dateutil
+soupsieve==2.9.2
+    # via beautifulsoup4
+sqlalchemy==2.0.43
+    # via
+    #   -r requirements.txt
+    #   alembic
+starlette==0.47.3
+    # via fastapi
+typing-extensions==4.16.0
+    # via
+    #   alembic
+    #   anyio
+    #   beautifulsoup4
+    #   fastapi
+    #   pydantic
+    #   pydantic-core
+    #   sqlalchemy
+    #   typing-inspection
+typing-inspection==0.4.4
+    # via
+    #   pydantic
+    #   pydantic-settings
+urllib3==2.7.0
+    # via botocore
+uvicorn[standard]==0.35.0
+    # via -r requirements.txt
+uvloop==0.22.1
+    # via uvicorn
+watchfiles==1.2.0
+    # via uvicorn
+websockets==17.1
+    # via uvicorn

apps/api/tests/test_activity.py

@@ -129,3 +129,55 @@ def test_reports_without_coordinates_do_not_create_activity_group(db: Session) -
     db.commit()
 
     assert activity_rows(db, hours=72, now=NOW) == []
+
+
+def test_confidence_capped_at_50_with_single_player() -> None:
+    """D06: One player cannot artificially inflate confidence above 50%."""
+    engine = create_engine("sqlite://", connect_args={"check_same_thread": False}, poolclass=StaticPool)
+    Base.metadata.create_all(engine)
+    with Session(engine) as session:
+        waterbody = Waterbody(slug="test-lake", name_ru="Тестовое озеро", unlock_level=1)
+        fish = Fish(slug="pike", name_ru="Щука", trophy_weight_g=10_000)
+        spot = Spot(waterbody=waterbody, x=10, y=20)
+        session.add_all([waterbody, fish, spot])
+        session.flush()
+        # 10 reports from 1 player, all max confidence
+        for _ in range(10):
+            report = CatchReport(
+                fish=fish, spot=spot, waterbody=waterbody, bait=None,
+                weight_g=5_000, fishing_method="spinning",
+                caught_at=NOW - timedelta(hours=1), reported_at=NOW - timedelta(hours=1),
+                player_name="Single Player", source_type=SourceType.user,
+                source_confidence=100, moderation_status=ModerationStatus.approved,
+            )
+            session.add(report)
+        session.commit()
+        row = activity_rows(session, hours=24, now=NOW)[0]
+        assert row.unique_players == 1
+        assert row.confidence_score <= 50, f"Expected max 50 with 1 player, got {row.confidence_score}"
+
+
+def test_confidence_capped_at_65_with_two_players() -> None:
+    """D06: Two players cannot get confidence above 65%."""
+    engine = create_engine("sqlite://", connect_args={"check_same_thread": False}, poolclass=StaticPool)
+    Base.metadata.create_all(engine)
+    with Session(engine) as session:
+        waterbody = Waterbody(slug="test-lake", name_ru="Тестовое озеро", unlock_level=1)
+        fish = Fish(slug="pike", name_ru="Щука", trophy_weight_g=10_000)
+        spot = Spot(waterbody=waterbody, x=10, y=20)
+        session.add_all([waterbody, fish, spot])
+        session.flush()
+        # 10 reports from 2 players, all max confidence
+        for i in range(10):
+            report = CatchReport(
+                fish=fish, spot=spot, waterbody=waterbody, bait=None,
+                weight_g=5_000, fishing_method="spinning",
+                caught_at=NOW - timedelta(hours=1), reported_at=NOW - timedelta(hours=1),
+                player_name=f"Player {i % 2}", source_type=SourceType.user,
+                source_confidence=100, moderation_status=ModerationStatus.approved,
+            )
+            session.add(report)
+        session.commit()
+        row = activity_rows(session, hours=24, now=NOW)[0]
+        assert row.unique_players == 2
+        assert row.confidence_score <= 65, f"Expected max 65 with 2 players, got {row.confidence_score}"

apps/api/tests/test_community_importer.py

@@ -116,9 +116,11 @@ def test_changed_published_record_requires_review_and_reuses_report(db: Session)
     water = Waterbody(slug="test-lake", name_ru="Тестовое озеро")
     db.add_all([fish, water])
     db.commit()
+    # D04: auto-publish now works with name match fallback
     stage_observations(db, [record() | {"weight_g": 5000}])
     item = db.scalar(select(ExternalObservation))
-    map_observation(db, item, fish, water)
+    # Item auto-published via name match fallback (D04)
+    assert item.status == "published"
     report = publish_observation(db, item)
     report_id = report.id
     stage_observations(db, [record() | {"weight_g": 6000}])

apps/api/tests/test_rate_limit.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from datetime import datetime, timezone
-from unittest.mock import MagicMock
+from unittest.mock import MagicMock, patch
 
 import pytest
 from fastapi import HTTPException
@@ -9,7 +9,7 @@ from sqlalchemy import create_engine, select
 from sqlalchemy.orm import Session
 
 from app.database import Base
-from app.main import _check_rate_limit
+from app.main import _check_rate_limit, _is_trusted_proxy
 from app.models import SubmissionAttempt
 
 
@@ -34,18 +34,71 @@ def test_rate_limit_is_persistent_and_does_not_store_raw_client() -> None:
         assert all(item.created_at.replace(tzinfo=timezone.utc) <= datetime.now(timezone.utc) for item in attempts)
 
 
-def test_rate_limit_uses_forwarded_for_header() -> None:
+def test_rate_limit_uses_forwarded_for_header_from_trusted_proxy() -> None:
+    """X-Forwarded-For should be used when client is trusted proxy."""
     engine = create_engine("sqlite://")
     Base.metadata.create_all(engine)
     with Session(engine) as db:
-        mock_real = MagicMock()
+        with patch("app.main.settings") as mock_settings:
-        mock_real.client.host = "10.0.0.1"
+            mock_settings.rate_limit_secret = "test-secret-for-testing"
-        mock_real.headers.get.return_value = "198.51.100.10"
+            mock_settings.trusted_proxy_cidrs = ["127.0.0.1/32"]
+            mock_proxy = MagicMock()
+            mock_proxy.client.host = "127.0.0.1"
+            mock_proxy.headers.get.return_value = "198.51.100.10"
             for _ in range(5):
-            _check_rate_limit(mock_real, db)
+                _check_rate_limit(mock_proxy, db)
             with pytest.raises(HTTPException) as blocked:
                 mock_other = MagicMock()
-            mock_other.client.host = "10.0.0.2"
+                mock_other.client.host = "127.0.0.1"
                 mock_other.headers.get.return_value = "198.51.100.10"
                 _check_rate_limit(mock_other, db)
             assert blocked.value.status_code == 429
+
+
+def test_trusted_proxy_checks_cidrs() -> None:
+    assert _is_trusted_proxy("127.0.0.1", ["127.0.0.1/32"]) is True
+    assert _is_trusted_proxy("10.0.0.1", ["10.0.0.0/8"]) is True
+    assert _is_trusted_proxy("192.168.1.1", ["192.168.1.0/24"]) is True
+    assert _is_trusted_proxy("::1", ["::1/128"]) is True
+    assert _is_trusted_proxy("203.0.113.5", ["127.0.0.1/32"]) is False
+    assert _is_trusted_proxy("invalid", []) is False
+
+
+def test_rate_limit_ignores_forwarded_for_from_untrusted_client() -> None:
+    """X-Forwarded-For should be ignored when client is not in trusted CIDRs."""
+    engine = create_engine("sqlite://")
+    Base.metadata.create_all(engine)
+    with Session(engine) as db:
+        # Client 203.0.113.42 is NOT trusted by default
+        mock_untrusted = MagicMock()
+        mock_untrusted.client.host = "203.0.113.42"
+        mock_untrusted.headers.get.return_value = "10.0.0.99"
+        for i in range(3):
+            _check_rate_limit(mock_untrusted, db)
+        # Should use real client 203.0.113.42, not forwarded 10.0.0.99
+        # So 3 attempts from 203.0.113.42 should be allowed (limit is 5)
+        mock_different = MagicMock()
+        mock_different.client.host = "203.0.113.42"
+        mock_different.headers.get.return_value = "10.0.0.88"
+        _check_rate_limit(mock_different, db)  # Should succeed, not blocked
+
+
+def test_rate_limit_uses_forwarded_for_from_trusted_proxy() -> None:
+    """X-Forwarded-For should be used when client IS in trusted CIDRs."""
+    engine = create_engine("sqlite://")
+    Base.metadata.create_all(engine)
+    with Session(engine) as db:
+        # 127.0.0.1 IS trusted by default
+        with patch("app.main.settings") as mock_settings:
+            mock_settings.rate_limit_secret = "test-secret-for-testing"
+            mock_settings.trusted_proxy_cidrs = ["127.0.0.1/32", "::1/128"]
+            mock_proxy = MagicMock()
+            mock_proxy.client.host = "127.0.0.1"
+            mock_proxy.headers.get.return_value = "203.0.113.100"
+            for _ in range(5):
+                _check_rate_limit(mock_proxy, db)
+            # Should use forwarded IP 203.0.113.100, so a different forwarded IP should be allowed
+            mock_other_forwarded = MagicMock()
+            mock_other_forwarded.client.host = "127.0.0.1"
+            mock_other_forwarded.headers.get.return_value = "198.51.100.50"
+            _check_rate_limit(mock_other_forwarded, db)  # Should succeed

apps/api/tests/test_readiness.py

@@ -6,7 +6,7 @@ from sqlalchemy import create_engine
 from sqlalchemy.orm import Session
 
 from app.database import Base
-from app.models import ImportStatus, OfficialRecordImport
+from app.models import ImportStatus, CommunityImportRun, OfficialRecordImport
 from app.readiness import readiness_report
 
 
@@ -72,3 +72,68 @@ def test_unavailable_storage_and_stale_import_fail_readiness() -> None:
     assert ready is False
     assert components["minio"]["status"] == "unavailable"
     assert components["official_import"]["status"] == "stale"
+
+
+def test_community_scheduler_success_does_not_block_readiness() -> None:
+    engine = create_engine("sqlite://")
+    Base.metadata.create_all(engine)
+    now = datetime.now(timezone.utc)
+    with Session(engine) as session:
+        session.add(CommunityImportRun(
+            source_system="rf4db",
+            started_at=now - timedelta(minutes=30),
+            status="success",
+            source_url="fixture://rf4db",
+            rows_seen=5, rows_created=5, rows_updated=0, error_summary=None,
+        ))
+        session.commit()
+        ready, components = readiness_report(
+            session, AvailableStorage(), import_required=False,
+            import_interval_seconds=3600, community_import_interval_seconds=1800, now=now,
+        )
+    assert ready is True
+    assert components["community_scheduler"]["status"] == "ready"
+
+
+def test_community_scheduler_stale_or_failed_blocks_readiness() -> None:
+    engine = create_engine("sqlite://")
+    Base.metadata.create_all(engine)
+    now = datetime.now(timezone.utc)
+    with Session(engine) as session:
+        # Stale run
+        session.add(CommunityImportRun(
+            source_system="rf4db",
+            started_at=now - timedelta(hours=2),
+            status="success",
+            source_url="fixture://rf4db",
+            rows_seen=5, rows_created=5, rows_updated=0, error_summary=None,
+        ))
+        session.commit()
+        ready, components = readiness_report(
+            session, AvailableStorage(), import_required=False,
+            import_interval_seconds=3600, community_import_interval_seconds=1800, now=now,
+        )
+    assert ready is False
+    assert components["community_scheduler"]["status"] == "stale"
+
+
+def test_community_scheduler_failed_status_blocks_readiness() -> None:
+    engine = create_engine("sqlite://")
+    Base.metadata.create_all(engine)
+    now = datetime.now(timezone.utc)
+    with Session(engine) as session:
+        session.add(CommunityImportRun(
+            source_system="rf4db",
+            started_at=now - timedelta(minutes=30),
+            status="failed",
+            source_url="fixture://rf4db",
+            rows_seen=0, rows_created=0, rows_updated=0,
+            error_summary="ConnectionError",
+        ))
+        session.commit()
+        ready, components = readiness_report(
+            session, AvailableStorage(), import_required=False,
+            import_interval_seconds=3600, community_import_interval_seconds=1800, now=now,
+        )
+    assert ready is False
+    assert components["community_scheduler"]["status"] == "failed"

apps/web/astro.config.mjs

@@ -3,6 +3,7 @@ import node from "@astrojs/node";
 
 export default defineConfig({
   site: process.env.PUBLIC_SITE_URL || "https://rf4spotter.ru",
+  trailingSlash: "never",
   output: "server",
   adapter: node({ mode: "standalone" }),
   server: { host: true, port: 4321 },

apps/web/src/pages/api/report-screenshot.ts

@@ -14,5 +14,10 @@ export const POST: APIRoute = async ({ request, redirect, cookies }) => {
     const response = await fetch(`${base}/api/v1/catch-reports/${reportId}/screenshot`, { method: "POST", headers:{"X-Upload-Token":uploadToken}, body: upload, signal: AbortSignal.timeout(60_000) });
     if (response.ok) cookies.delete(cookieName, {path:"/"});
     return redirect(response.ok ? "/report?state=screenshot_sent" : `/report?state=screenshot_error&report_id=${encodeURIComponent(reportId)}`, 303);
-  } catch { return redirect(`/report?state=screenshot_error&report_id=${encodeURIComponent(reportId)}`, 303); }
+  } catch (err) {
+    const isTimeout = err instanceof DOMException && err.name === "TimeoutError" ||
+      err instanceof TypeError && err.message.toLowerCase().includes("fetch") ||
+      err instanceof Error && err.message.toLowerCase().includes("abort");
+    return redirect(isTimeout ? `/report?state=timeout&report_id=${encodeURIComponent(reportId)}` : `/report?state=screenshot_error&report_id=${encodeURIComponent(reportId)}`, 303);
+  }
 };

apps/web/src/pages/api/report.ts

@@ -35,7 +35,10 @@ export const POST: APIRoute = async ({ request, redirect, cookies }) => {
     return redirect("/report?state=sent", 303);
   }
   catch (err) {
-    if (err instanceof TypeError && err.message.includes("abort")) {
+    const isTimeout = err instanceof DOMException && err.name === "TimeoutError" ||
+      err instanceof TypeError && err.message.toLowerCase().includes("fetch") ||
+      err instanceof Error && err.message.toLowerCase().includes("abort");
+    if (isTimeout) {
       if (createdId && uploadToken) cookies.set(`rf4-upload-${createdId}`, uploadToken, {httpOnly:true, sameSite:"strict", secure:import.meta.env.PROD, path:"/", maxAge:3600});
       return redirect(createdId ? `/report?state=screenshot_error&report_id=${encodeURIComponent(createdId)}` : "/report?state=timeout", 303);
     }

apps/web/src/pages/index.astro

@@ -11,6 +11,8 @@ const hours = params.get("hours") ?? "24";
 const waterbody = params.get("waterbody") ?? "";
 const fish = params.get("fish") ?? "";
 const sort = params.get("sort") ?? "activity";
+const requestedOffset = Number(params.get("offset") ?? 0);
+const offset = Number.isInteger(requestedOffset) && requestedOffset >= 0 ? requestedOffset : 0;
 const requestedSignalLimit = Number(params.get("signals") ?? 12);
 const signalLimit = Number.isInteger(requestedSignalLimit) ? Math.min(48, Math.max(12, requestedSignalLimit)) : 12;
 let items: Activity[] = [], signals: PublicObservation[] = [], fishes: DictionaryItem[] = [], waterbodies: DictionaryItem[] = [];
@@ -18,7 +20,6 @@ let hasMoreSignals = false, totalItems = 0;
 const filterError = !["6", "12", "24", "72"].includes(hours) || !["activity", "confidence", "freshness"].includes(sort);
 let unavailable = false, showNoIndex = false;
 if (filterError) { showNoIndex = true; Astro.response.status = 422; }
-if (unavailable) { showNoIndex = true; Astro.response.status = 503; Astro.response.headers.set("Retry-After", "60"); }
 try {
   let signalRows: PublicObservation[] = [];
   const signalParams = new URLSearchParams({ limit: String(signalLimit + 1) });
@@ -28,12 +29,17 @@ try {
   hasMoreSignals = signalRows.length > signalLimit;
   signals = signalRows.slice(0, signalLimit);
   if (!filterError) {
-    const query = new URLSearchParams({ hours, waterbody, fish, sort, limit: "20", offset: "0" });
+    const query = new URLSearchParams({ hours, waterbody, fish, sort, limit: "20", offset: String(offset) });
     const paginated = await api<PaginatedActivity>(`/api/v1/activity?${query}`);
-    items = paginated.items;
+    items = offset > 0 ? [...items, ...paginated.items] : paginated.items;
     totalItems = paginated.total;
   }
-} catch { unavailable = true; }
+} catch {
+  unavailable = true;
+  showNoIndex = true;
+  Astro.response.status = 503;
+  Astro.response.headers.set("Retry-After", "60");
+}
 const leaderLevel = items.length > 1 && items[0] ? activityLevel(items[0].activity_score) : null;
 const selectedWaterbody = waterbodies.find(item => item.slug === waterbody)?.name_ru ?? "Все водоёмы";
 const selectedFish = fishes.find(item => item.slug === fish)?.name_ru ?? "Любая рыба";
@@ -63,7 +69,7 @@ const datasetJsonLd = {
     <button>⌕ Найти клёв</button>
   </form></section>
   <div class="active-filters content-grid" aria-label="Применённые фильтры"><span>{selectedWaterbody}</span><span>{selectedFish}</span><span>{periodLabel}</span><span>{sortLabel}</span>{filtersChanged && <a href="/#results">Сбросить</a>}</div>
-  <section class="dashboard content-grid" id="results"><div class="results-column"><div class="section-heading"><div><span class="overline">За выбранный период</span><h2>Горячие точки</h2></div><span class="result-count">{items.length} из {totalItems} {plural(totalItems, ["точка", "точки", "точек"])}</span></div>{filterError ? <div class="state error-state"><h2>Некорректные фильтры</h2><p>Выберите период и сортировку из предложенных значений.</p><a href="/">Сбросить фильтры</a></div> : unavailable ? <div class="state"><h2>Источник временно недоступен</h2><p>Не показываем устаревшие догадки. Попробуйте позже.</p></div> : items.length ? <><div class="spot-list">{items.map(item => <ActivityCard item={item} />)}</div>{items.length < totalItems && <a class="load-more" href={`/?${new URLSearchParams({ ...Object.fromEntries(params), offset: String(items.length) }).toString()}#results`}>Показать ещё <span>{items.length} из {totalItems}</span> ↓</a>}</> : <div class="state"><h2>Пока нет свежих данных</h2><p>Для выбранных фильтров нет одобренных наблюдений. Расширьте период или выберите другой водоём.</p></div>}</div>
+  <section class="dashboard content-grid" id="results"><div class="results-column"><div class="section-heading"><div><span class="overline">За выбранный период</span><h2>Горячие точки</h2></div><span class="result-count">{items.length} из {totalItems} {plural(totalItems, ["точка", "точки", "точек"])}</span></div>{filterError ? <div class="state error-state"><h2>Некорректные фильтры</h2><p>Выберите период и сортировку из предложенных значений.</p><a href="/">Сбросить фильтры</a></div> : unavailable ? <div class="state"><h2>Источник временно недоступен</h2><p>Не показываем устаревшие догадки. Попробуйте позже.</p></div> : items.length ? <><div class="spot-list">{items.map(item => <ActivityCard item={item} />)}</div>{items.length < totalItems && <a class="load-more" href={`/?${new URLSearchParams([...params.entries(), ["offset", String(items.length)]]).toString()}#results`}>Показать ещё <span>{items.length} из {totalItems}</span> ↓</a>}</> : <div class="state"><h2>Пока нет свежих данных</h2><p>Для выбранных фильтров нет одобренных наблюдений. Расширьте период или выберите другой водоём.</p></div>}</div>
   {items[0] && leaderLevel && <aside class="detail-card"><div class="detail-head"><div><span class="overline">Лидер активности</span><h2>{items[0].waterbody} <em>{items[0].x}:{items[0].y}</em></h2></div><a href={`/spots/${items[0].spot_id}`} aria-label="Открыть точку"><FishingIcon name="arrow"/></a></div><div class="source-strip">{items[0].sources.map(source => <SourceBadge source={source}/>)}</div><div class="detail-score"><div class="float-gauge" style={`--level:${items[0].activity_score}%`} aria-label={`Индекс активности: ${items[0].activity_score} из 100`}><span class="float-gauge__line"></span><span class="float-gauge__water"></span><span class="float-gauge__bob"><i></i></span><strong>{items[0].activity_score}</strong><small>из 100</small></div><div><span>Индекс активности</span><strong data-activity-level={leaderLevel.short}>{leaderLevel.description}</strong><p>{items[0].explanation}</p></div></div><div class="metric-grid"><div><span><FishingIcon name="ripple"/></span><small>Уверенность</small><strong>{items[0].confidence_score}%</strong></div><div><span><FishingIcon name="angler"/></span><small>{plural(items[0].unique_players, ["Игрок", "Игрока", "Игроков"])}</small><strong>{items[0].unique_players}</strong></div><div><span><FishingIcon name="clock"/></span><small>Последний</small><strong>{ago(items[0].last_confirmed_at)}</strong></div><div><span><FishingIcon name="scale"/></span><small>Средний вес</small><strong>{kg(items[0].average_weight_g)}</strong></div></div><div class="best-lure"><span class="overline">Лучшая связка</span><div><FishingIcon name="lure" size={25}/><strong>{items[0].best_bait ?? "Не указана"}</strong><span>{items[0].catches} {plural(items[0].catches, ["улов", "улова", "уловов"])}</span></div></div><p class="confidence-note"><span>✓</span><span><strong>Оценка объяснима.</strong> Один игрок не может искусственно поднять уверенность.</span></p></aside>}
   </section>
   {signals.length > 0 && <SignalFeed signals={signals}/>}

apps/web/src/pages/sitemap.xml.ts

@@ -24,7 +24,9 @@ export const GET: APIRoute = async ({ site }) => {
       if (paths.size > 49000) throw new Error("Sitemap index required");
       if (rows.length < 1000) break;
     }
-    const xml = `<?xml version="1.0" encoding="UTF-8"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">${[...paths].map(path => `<url><loc>${escapeXml(new URL(path, origin).toString())}</loc></url>`).join("")}</urlset>`;
+    // Normalize paths: never use trailing slash (S03)
+    const normalized = [...paths].map(p => p.replace(/\/$/, "") || "/");
+    const xml = `<?xml version="1.0" encoding="UTF-8"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">${normalized.map(path => `<url><loc>${escapeXml(new URL(path, origin).toString())}</loc></url>`).join("")}</urlset>`;
     lastGood = { origin, xml, at: Date.now() };
     return output(xml);
   } catch {

compose.production.yaml

@@ -123,6 +123,7 @@ services:
       IMPORT_INTERVAL_SECONDS: ${IMPORT_INTERVAL_SECONDS:-3600}
       PUBLIC_CACHE_SECONDS: ${PUBLIC_CACHE_SECONDS:-20}
       RATE_LIMIT_SECRET: ${RATE_LIMIT_SECRET:?Set RATE_LIMIT_SECRET}
+      TRUSTED_PROXY_CIDRS: '${TRUSTED_PROXY_CIDRS:-"127.0.0.1/32,::1/128"}'
       RETENTION_SUBMISSION_DAYS: ${RETENTION_SUBMISSION_DAYS:-1}
       RETENTION_UNREVIEWED_DAYS: ${RETENTION_UNREVIEWED_DAYS:-30}
       RETENTION_APPROVED_PERSONAL_DAYS: ${RETENTION_APPROVED_PERSONAL_DAYS:-180}
@@ -184,6 +185,7 @@ services:
       S3_SECRET_KEY: ${S3_SECRET_KEY:?Set S3_SECRET_KEY}
       SEED_DEMO_DATA: "false"
       RATE_LIMIT_SECRET: ${RATE_LIMIT_SECRET:?Set RATE_LIMIT_SECRET}
+      TRUSTED_PROXY_CIDRS: '${TRUSTED_PROXY_CIDRS:-"127.0.0.1/32,::1/128"}'
       COMMUNITY_IMPORT_INTERVAL_SECONDS: ${COMMUNITY_IMPORT_INTERVAL_SECONDS:-1800}
       RF4MAP_POINT_URL: ${RF4MAP_POINT_URL:-https://rf4map.ru/points/275}
       RF4POSTS_SPOT_URL: ${RF4POSTS_SPOT_URL:-https://rf4-posts.com/ru/spots/d0c6d9c6-4ebf-49a7-98a8-9a562553a8ee}

rf4_research/community_cli.py

@@ -93,13 +93,30 @@ def mark_fetch(source: str, *, state_file: Path, now: float | None = None) -> No
     _write_state(state_file, state)
 
 
+def _validate_url_host(url: str) -> str:
+    """Validate URL hostname is in allowlist before making network call."""
+    hostname = (urlsplit(url).hostname or "").lower()
+    if hostname.startswith("www."):
+        hostname = hostname[4:]
+    if not hostname:
+        raise ValueError("URL must include a valid hostname")
+    if hostname not in ALLOWED_HOSTS:
+        raise ValueError(f"URL hostname {hostname} not in allowlist")
+    return hostname
+
+
 def fetch_html(url: str, *, timeout: float = 30) -> str:
+    # Validate host BEFORE network I/O to prevent SSRF to internal endpoints
+    _validate_url_host(url)
     request = Request(url, headers={"User-Agent": USER_AGENT, "Accept": "text/html"})
     with urlopen(request, timeout=timeout) as response:
         final_url = response.url
-        hostname = (urlsplit(final_url).hostname or "").lower()
+        # Also validate redirect target
-        if hostname not in ALLOWED_HOSTS:
+        final_hostname = (urlsplit(final_url).hostname or "").lower()
-            raise ValueError(f"URL hostname {hostname} not in allowlist")
+        if final_hostname.startswith("www."):
+            final_hostname = final_hostname[4:]
+        if final_hostname not in ALLOWED_HOSTS:
+            raise ValueError(f"Redirect hostname {final_hostname} not in allowlist")
         if response.headers.get_content_type() != "text/html":
             raise ValueError(f"expected text/html, got {response.headers.get_content_type()}")
         data = response.read(MAX_RESPONSE_BYTES + 1)

tests/test_community_cli.py

@@ -31,3 +31,29 @@ def test_failed_fetch_still_reserves_site_cooldown(tmp_path: Path, monkeypatch:
     monkeypatch.setattr(community_cli, "fetch_html", fail)
     assert community_cli.main(["rf4db", "--state-file", str(state_file)]) == 1
     assert "download.rf4db.com" in json.loads(state_file.read_text(encoding="utf-8"))
+
+
+def test_validate_url_host_rejects_disallowed_hosts() -> None:
+    from rf4_research.community_cli import _validate_url_host
+
+    # Allowed hosts pass
+    assert _validate_url_host("https://download.rf4db.com/ru/catches") == "download.rf4db.com"
+    assert _validate_url_host("https://www.rf4-stat.ru/posts/") == "rf4-stat.ru"
+    assert _validate_url_host("https://rf4map.ru/point/123") == "rf4map.ru"
+
+    # Disallowed hosts raise ValueError before network I/O
+    with pytest.raises(ValueError, match="not in allowlist"):
+        _validate_url_host("http://localhost:8080/admin")
+    with pytest.raises(ValueError, match="not in allowlist"):
+        _validate_url_host("http://169.254.169.254/latest/meta-data/")
+    with pytest.raises(ValueError, match="not in allowlist"):
+        _validate_url_host("http://internal-service.corp/api")
+
+
+def test_validate_url_host_rejects_missing_hostname() -> None:
+    from rf4_research.community_cli import _validate_url_host
+
+    with pytest.raises(ValueError, match="valid hostname"):
+        _validate_url_host("not-a-valid-url")
+    with pytest.raises(ValueError, match="valid hostname"):
+        _validate_url_host("")