Compare commits

..

1 Commits

Author SHA1 Message Date
BigBodyCobain 4b4c154a07 Fix #279: add defusedxml to uv.lock so Docker image installs it
defusedxml is listed in backend/pyproject.toml line 18 but was missing
from uv.lock. The backend Dockerfile uses `uv sync --frozen --no-dev`,
which only installs packages pinned in the lockfile. As a result the
runtime image shipped without defusedxml even though pyproject declared
it, and any import path that touched it crashed at startup with:

    ModuleNotFoundError: No module named 'defusedxml'

Affected import sites:

- backend/services/psk_reporter_fetcher.py:10
- backend/services/fetchers/aircraft_database.py:21
- backend/services/cctv_pipeline.py:990
- backend/services/cctv_pipeline.py:1018

Fix: regenerate uv.lock so defusedxml v0.7.1 (matching the >=0.7.1
specifier in pyproject) is locked. No code changes -- only the lockfile.
Next image build picks it up via the existing `uv sync --frozen` step.

Reporter: external user. Thanks for catching the missing dep.
2026-05-21 10:15:01 -06:00
17 changed files with 248 additions and 2614 deletions
-4
View File
@@ -105,10 +105,6 @@ backend/data/*
# the self-updater as a second-line integrity check when the release's
# SHA256SUMS.txt asset can't be fetched.
!backend/data/release_digests.json
# Issue #244/#245/#246: one-shot carrier-position seed shipped with each
# release. Used ONLY on first-ever startup to bootstrap carrier_cache.json;
# after that the cache reflects this install's own GDELT observations.
!backend/data/carrier_seed.json
# OS generated files
.DS_Store
-120
View File
@@ -1,120 +0,0 @@
{
"_meta": {
"as_of": "2026-03-09",
"source": "USNI News Fleet & Marine Tracker",
"source_url": "https://news.usni.org/2026/03/09/usni-news-fleet-and-marine-tracker-march-9-2026",
"note": "One-shot bootstrap for first-run carrier positions. Once carrier_cache.json exists in the runtime data volume, this seed file is never read again. All subsequent updates come from GDELT (and any future sources) and are written to carrier_cache.json. A year from now, your runtime cache reflects whatever your install has observed since first launch — not these snapshot positions."
},
"carriers": {
"CVN-68": {
"lat": 47.5535,
"lng": -122.6400,
"heading": 90,
"desc": "Bremerton, WA (Maintenance)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed"
},
"CVN-76": {
"lat": 47.5580,
"lng": -122.6360,
"heading": 90,
"desc": "Bremerton, WA (Decommissioning)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed"
},
"CVN-69": {
"lat": 36.9465,
"lng": -76.3265,
"heading": 0,
"desc": "Norfolk, VA (Post-deployment maintenance)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed"
},
"CVN-78": {
"lat": 18.0,
"lng": 39.5,
"heading": 0,
"desc": "Red Sea — Operation Epic Fury (USNI Mar 9)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed"
},
"CVN-74": {
"lat": 36.98,
"lng": -76.43,
"heading": 0,
"desc": "Newport News, VA (RCOH refueling overhaul)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed"
},
"CVN-75": {
"lat": 36.0,
"lng": 15.0,
"heading": 0,
"desc": "Mediterranean Sea deployment (USNI Mar 9)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed"
},
"CVN-77": {
"lat": 36.5,
"lng": -74.0,
"heading": 0,
"desc": "Atlantic — Pre-deployment workups (USNI Mar 9)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed"
},
"CVN-70": {
"lat": 32.6840,
"lng": -117.1290,
"heading": 180,
"desc": "San Diego, CA (Homeport)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed"
},
"CVN-71": {
"lat": 32.6885,
"lng": -117.1280,
"heading": 180,
"desc": "San Diego, CA (Maintenance)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed"
},
"CVN-72": {
"lat": 20.0,
"lng": 64.0,
"heading": 0,
"desc": "Arabian Sea — Operation Epic Fury (USNI Mar 9)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed"
},
"CVN-73": {
"lat": 35.2830,
"lng": 139.6700,
"heading": 180,
"desc": "Yokosuka, Japan (Forward deployed)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed"
}
}
}
+3 -31
View File
@@ -1080,18 +1080,8 @@ def _public_mesh_log_size(entries: list[dict[str, Any]]) -> int:
return sum(1 for item in entries if _public_mesh_log_entry(item) is not None)
# Issue #243 (tg12): the public redaction now exposes only the bare
# "is Wormhole on?" boolean. Transport choice (tor/i2p/mixnet/direct),
# anonymous-mode state, and the named privacy profile are all
# operational posture and were leaking actionable recon to any
# unauthenticated caller. They are now gated behind authenticated reads
# (admin key or scoped-view token). Loopback Tauri shells and Docker
# bridge frontend containers continue to see full status because the
# Next.js catch-all proxy injects the configured ADMIN_KEY for
# same-origin/non-browser callers (see PR #263), so legitimate operator
# UX is unaffected.
_WORMHOLE_PUBLIC_SETTINGS_FIELDS = {"enabled"}
_WORMHOLE_PUBLIC_PROFILE_FIELDS = {"wormhole_enabled"}
_WORMHOLE_PUBLIC_SETTINGS_FIELDS = {"enabled", "transport", "anonymous_mode"}
_WORMHOLE_PUBLIC_PROFILE_FIELDS = {"profile", "wormhole_enabled"}
_PRIVATE_LANE_CONTROL_FIELDS = {"private_lane_tier", "private_lane_policy"}
_PUBLIC_RNS_STATUS_FIELDS = {"enabled", "ready", "configured_peers", "active_peers"}
_NODE_PUBLIC_EVENT_HOOK_REGISTERED = False
@@ -8820,14 +8810,9 @@ async def api_uw_flow(request: Request):
from services.news_feed_config import get_feeds, save_feeds, reset_feeds
@app.get(
"/api/settings/news-feeds",
dependencies=[Depends(require_local_operator)],
)
@app.get("/api/settings/news-feeds")
@limiter.limit("30/minute")
async def api_get_news_feeds(request: Request):
"""Issue #252 (tg12): gated on local-operator. See the canonical
handler in backend/routers/admin.py for the full rationale."""
return get_feeds()
@@ -9030,22 +9015,9 @@ class NodeSettingsUpdate(BaseModel):
@app.get("/api/settings/node")
@limiter.limit("30/minute")
async def api_get_node_settings(request: Request):
"""Issue #243 (tg12): node mode and participant state are
operational posture. Anonymous callers receive an empty stub
enough for the UI to know the endpoint exists but nothing
fingerprintable. Authenticated callers see the full state.
Authenticated == local-operator (loopback / Docker bridge) OR an
admin / scoped-view token. The Tauri shell and Docker frontend
container both qualify via their existing transport (PR #263 +
PR #278), so legitimate operator UX is unchanged.
"""
from services.node_settings import read_node_settings
data = await asyncio.to_thread(read_node_settings)
authenticated = _scoped_view_authenticated(request, "node")
if not authenticated:
return {}
return {
**data,
"node_mode": _current_node_mode(),
+2 -30
View File
@@ -82,18 +82,9 @@ async def api_get_keys_meta(request: Request):
return get_env_path_info()
@router.get(
"/api/settings/news-feeds",
dependencies=[Depends(require_local_operator)],
)
@router.get("/api/settings/news-feeds")
@limiter.limit("30/minute")
async def api_get_news_feeds(request: Request):
"""Issue #252 (tg12): the curated feed inventory is configuration
state, not a public data feed. Gated on local-operator so the
Tauri shell, the Docker bridge frontend, and any caller with an
admin key all see the full list; anonymous LAN/internet callers
can no longer enumerate operator source URLs.
"""
from services.news_feed_config import get_feeds
return get_feeds()
@@ -127,18 +118,9 @@ async def api_reset_news_feeds(request: Request):
@router.get("/api/settings/node")
@limiter.limit("30/minute")
async def api_get_node_settings(request: Request):
"""Issue #243 (tg12): node_mode and node_enabled are operational
posture. Anonymous callers receive an empty stub; authenticated
callers (local-operator or admin/scoped token) see the full
state. See the canonical handler in backend/main.py for the full
rationale.
"""
import asyncio
from auth import _scoped_view_authenticated
from services.node_settings import read_node_settings
data = await asyncio.to_thread(read_node_settings)
if not _scoped_view_authenticated(request, "node"):
return {}
return {
**data,
"node_mode": _current_node_mode(),
@@ -228,19 +210,9 @@ async def api_set_meshtastic_mqtt_settings(request: Request, body: MeshtasticMqt
return _meshtastic_runtime_snapshot()
@router.get(
"/api/settings/timemachine",
dependencies=[Depends(require_local_operator)],
)
@router.get("/api/settings/timemachine")
@limiter.limit("30/minute")
async def api_get_timemachine_settings(request: Request):
"""Issue #253 (tg12): archival-capture posture is operationally
sensitive — it tells a remote caller whether this deployment is
retaining replayable historical surveillance data. Gated on
local-operator so the Tauri shell and Docker bridge frontend
still see the toggle state, but anonymous LAN/internet callers
can no longer fingerprint Time Machine state.
"""
import asyncio
from services.node_settings import read_node_settings
data = await asyncio.to_thread(read_node_settings)
+2 -7
View File
@@ -160,13 +160,8 @@ router = APIRouter()
# --- Constants ---
# Issue #243 (tg12): the public redaction now exposes only the bare
# "is this on?" boolean. Transport choice, anonymous-mode state, and
# the named privacy profile were all leaking actionable recon to
# unauthenticated callers and are now gated behind authenticated reads.
# See the matching block in backend/main.py for the full rationale.
_WORMHOLE_PUBLIC_SETTINGS_FIELDS = {"enabled"}
_WORMHOLE_PUBLIC_PROFILE_FIELDS = {"wormhole_enabled"}
_WORMHOLE_PUBLIC_SETTINGS_FIELDS = {"enabled", "transport", "anonymous_mode"}
_WORMHOLE_PUBLIC_PROFILE_FIELDS = {"profile", "wormhole_enabled"}
_PRIVATE_LANE_CONTROL_FIELDS = {"private_lane_tier", "private_lane_policy"}
_PUBLIC_RNS_STATUS_FIELDS = {"enabled", "ready", "configured_peers", "active_peers"}
_NODE_PUBLIC_EVENT_HOOK_REGISTERED = False
+173 -371
View File
@@ -1,90 +1,46 @@
"""
Carrier Strike Group OSINT Tracker
===================================
Maintains estimated positions for US Navy Carrier Strike Groups with
honest provenance and freshness signals.
Scrapes multiple OSINT sources to maintain current estimated positions
for US Navy Carrier Strike Groups. Updates on startup + 00:00 & 12:00 UTC.
Issues #244 / #245 / #246 (tg12 external audit):
The previous implementation baked a snapshot of USNI News Fleet &
Marine Tracker positions (March 9, 2026) into the registry as
``fallback_lat``/``fallback_lng`` and stamped ``updated = now()``
every time the dossier was rendered. That presented stale editorial
data as live state. It also persisted GDELT-derived positions to the
on-disk cache with no freshness signal, so a single news mention from
months ago could keep overriding the (already-stale) registry default
indefinitely.
Architecture after this PR:
::
backend/data/carrier_seed.json read-only, shipped with image,
used ONCE on first-ever startup
to bootstrap carrier_cache.json.
backend/data/carrier_cache.json mutable, lives in the runtime data
volume, written by every GDELT
refresh + any future source.
Startup flow:
1. ``carrier_cache.json`` exists? → load it.
2. Otherwise, copy ``carrier_seed.json`` → ``carrier_cache.json``,
then load it. (This happens once, ever, per install.)
3. Background: GDELT fetch runs. Any carrier mentioned in fresh news
gets its entry replaced with the news-derived position.
``position_source_at`` is set to the news article timestamp.
Freshness is a *labelling* decision, not an eviction decision:
- ``position_source_at`` within the configurable freshness window
(default 14 days) → ``position_confidence = "recent"``.
- Older than that → ``position_confidence = "stale"``.
- Bootstrapped from the seed file (never updated) → ``"seed"``.
- No cache entry at all (e.g. a carrier added to the registry after
first install) → carrier renders at its homeport with
``"homeport_default"``.
Carriers are never hidden, never teleported, never disappeared. The
position the user sees is always the last position the system actually
observed, with an honest "as-of" timestamp the UI can render however
it likes. A year from now, the runtime cache reflects whatever this
install has observed via GDELT — not the seed snapshot.
Sources:
1. GDELT News API — recent carrier movement headlines
2. WikiVoyage / public port-call databases
3. Fallback — last-known or static OSINT estimates
"""
import os
import re
import json
import time
import logging
import threading
import random
import shutil
from datetime import datetime, timedelta, timezone
from datetime import datetime, timezone
from pathlib import Path
from typing import Any, Dict, List, Optional, Tuple
from typing import Dict, List, Optional
from services.network_utils import fetch_with_curl
logger = logging.getLogger(__name__)
# -----------------------------------------------------------------
# Carrier registry: hull number → identity only.
#
# Issue #244 (tg12): the previous registry carried hard-coded
# ``fallback_lat``/``fallback_lng`` that were dated editorial
# snapshots from a 2026-03-09 article. Those fields are DELETED. The
# registry is now identity + homeport only; positions are sourced
# exclusively from carrier_cache.json (and via that, from the
# bootstrap seed or live OSINT).
# Carrier registry: hull number → metadata + fallback position
# -----------------------------------------------------------------
CARRIER_REGISTRY: Dict[str, dict] = {
# Fallback positions sourced from USNI News Fleet & Marine Tracker (Mar 9, 2026)
# https://news.usni.org/2026/03/09/usni-news-fleet-and-marine-tracker-march-9-2026
# --- Bremerton, WA (Naval Base Kitsap) ---
# Distinct pier positions along Sinclair Inlet so carriers don't stack
"CVN-68": {
"name": "USS Nimitz (CVN-68)",
"wiki": "https://en.wikipedia.org/wiki/USS_Nimitz",
"homeport": "Bremerton, WA",
"homeport_lat": 47.5535,
"homeport_lng": -122.6400,
"fallback_lat": 47.5535,
"fallback_lng": -122.6400,
"fallback_heading": 90,
"fallback_desc": "Bremerton, WA (Maintenance)",
},
"CVN-76": {
"name": "USS Ronald Reagan (CVN-76)",
@@ -92,14 +48,23 @@ CARRIER_REGISTRY: Dict[str, dict] = {
"homeport": "Bremerton, WA",
"homeport_lat": 47.5580,
"homeport_lng": -122.6360,
"fallback_lat": 47.5580,
"fallback_lng": -122.6360,
"fallback_heading": 90,
"fallback_desc": "Bremerton, WA (Decommissioning)",
},
# --- Norfolk, VA (Naval Station Norfolk) ---
# Piers run N-S along Willoughby Bay; each carrier gets a distinct berth
"CVN-69": {
"name": "USS Dwight D. Eisenhower (CVN-69)",
"wiki": "https://en.wikipedia.org/wiki/USS_Dwight_D._Eisenhower",
"homeport": "Norfolk, VA",
"homeport_lat": 36.9465,
"homeport_lng": -76.3265,
"fallback_lat": 36.9465,
"fallback_lng": -76.3265,
"fallback_heading": 0,
"fallback_desc": "Norfolk, VA (Post-deployment maintenance)",
},
"CVN-78": {
"name": "USS Gerald R. Ford (CVN-78)",
@@ -107,6 +72,10 @@ CARRIER_REGISTRY: Dict[str, dict] = {
"homeport": "Norfolk, VA",
"homeport_lat": 36.9505,
"homeport_lng": -76.3250,
"fallback_lat": 18.0,
"fallback_lng": 39.5,
"fallback_heading": 0,
"fallback_desc": "Red Sea — Operation Epic Fury (USNI Mar 9)",
},
"CVN-74": {
"name": "USS John C. Stennis (CVN-74)",
@@ -114,6 +83,10 @@ CARRIER_REGISTRY: Dict[str, dict] = {
"homeport": "Norfolk, VA",
"homeport_lat": 36.9540,
"homeport_lng": -76.3235,
"fallback_lat": 36.98,
"fallback_lng": -76.43,
"fallback_heading": 0,
"fallback_desc": "Newport News, VA (RCOH refueling overhaul)",
},
"CVN-75": {
"name": "USS Harry S. Truman (CVN-75)",
@@ -121,6 +94,10 @@ CARRIER_REGISTRY: Dict[str, dict] = {
"homeport": "Norfolk, VA",
"homeport_lat": 36.9580,
"homeport_lng": -76.3220,
"fallback_lat": 36.0,
"fallback_lng": 15.0,
"fallback_heading": 0,
"fallback_desc": "Mediterranean Sea deployment (USNI Mar 9)",
},
"CVN-77": {
"name": "USS George H.W. Bush (CVN-77)",
@@ -128,14 +105,23 @@ CARRIER_REGISTRY: Dict[str, dict] = {
"homeport": "Norfolk, VA",
"homeport_lat": 36.9620,
"homeport_lng": -76.3210,
"fallback_lat": 36.5,
"fallback_lng": -74.0,
"fallback_heading": 0,
"fallback_desc": "Atlantic — Pre-deployment workups (USNI Mar 9)",
},
# --- San Diego, CA (Naval Base San Diego) ---
# Carrier piers along the east shore of San Diego Bay, spread N-S
"CVN-70": {
"name": "USS Carl Vinson (CVN-70)",
"wiki": "https://en.wikipedia.org/wiki/USS_Carl_Vinson",
"homeport": "San Diego, CA",
"homeport_lat": 32.6840,
"homeport_lng": -117.1290,
"fallback_lat": 32.6840,
"fallback_lng": -117.1290,
"fallback_heading": 180,
"fallback_desc": "San Diego, CA (Homeport)",
},
"CVN-71": {
"name": "USS Theodore Roosevelt (CVN-71)",
@@ -143,6 +129,10 @@ CARRIER_REGISTRY: Dict[str, dict] = {
"homeport": "San Diego, CA",
"homeport_lat": 32.6885,
"homeport_lng": -117.1280,
"fallback_lat": 32.6885,
"fallback_lng": -117.1280,
"fallback_heading": 180,
"fallback_desc": "San Diego, CA (Maintenance)",
},
"CVN-72": {
"name": "USS Abraham Lincoln (CVN-72)",
@@ -150,6 +140,10 @@ CARRIER_REGISTRY: Dict[str, dict] = {
"homeport": "San Diego, CA",
"homeport_lat": 32.6925,
"homeport_lng": -117.1275,
"fallback_lat": 20.0,
"fallback_lng": 64.0,
"fallback_heading": 0,
"fallback_desc": "Arabian Sea — Operation Epic Fury (USNI Mar 9)",
},
# --- Yokosuka, Japan (CFAY) ---
"CVN-73": {
@@ -158,18 +152,16 @@ CARRIER_REGISTRY: Dict[str, dict] = {
"homeport": "Yokosuka, Japan",
"homeport_lat": 35.2830,
"homeport_lng": 139.6700,
"fallback_lat": 35.2830,
"fallback_lng": 139.6700,
"fallback_heading": 180,
"fallback_desc": "Yokosuka, Japan (Forward deployed)",
},
}
# -----------------------------------------------------------------
# Region → approximate center coordinates.
#
# Issue #245 (tg12): converting a region name straight into precise
# map coordinates is false precision. We still use this table to
# infer a coarse position from a headline mention, but the resulting
# carrier object is now stamped ``position_confidence = "approximate"``
# so the UI can render an uncertainty radius / dimmed icon. The
# centroid is a best-effort midpoint of the named body of water.
# Region → approximate center coordinates
# Used to map textual geographic descriptions to lat/lng
# -----------------------------------------------------------------
REGION_COORDS: Dict[str, tuple] = {
# Oceans & Seas
@@ -228,39 +220,9 @@ REGION_COORDS: Dict[str, tuple] = {
}
# -----------------------------------------------------------------
# Files
# Cache file for persisting positions between restarts
# -----------------------------------------------------------------
#
# The seed lives in the read-only image data dir (it ships with each
# release). The cache lives in the same data dir but is written at
# runtime; under Docker compose this dir is volume-mounted so the
# cache persists across container restarts, which is the whole point
# of the seed-then-observe model — the user's runtime observations
# survive image upgrades.
SEED_FILE = Path(__file__).parent.parent / "data" / "carrier_seed.json"
CACHE_FILE = Path(__file__).parent.parent / "data" / "carrier_cache.json"
# -----------------------------------------------------------------
# Freshness window for position_confidence labeling. Issue #246 (tg12):
# previously persisted cache entries had no freshness signal at all.
# After this change, the position itself is preserved (we never lose
# what was last observed) but the confidence label flips from
# "recent" to "stale" once the underlying source is older than this
# window. Operator-overridable via env var.
# -----------------------------------------------------------------
_DEFAULT_FRESHNESS_WINDOW_DAYS = 14
def _freshness_window_days() -> int:
raw = str(os.environ.get("SHADOWBROKER_CARRIER_FRESHNESS_DAYS", "") or "").strip()
if not raw:
return _DEFAULT_FRESHNESS_WINDOW_DAYS
try:
n = int(raw)
return n if n > 0 else _DEFAULT_FRESHNESS_WINDOW_DAYS
except (TypeError, ValueError):
return _DEFAULT_FRESHNESS_WINDOW_DAYS
CACHE_FILE = Path(__file__).parent.parent / "carrier_cache.json"
_carrier_positions: Dict[str, dict] = {}
_positions_lock = threading.Lock()
@@ -272,159 +234,25 @@ _GDELT_REQUEST_DELAY_SECONDS = 1.25
_GDELT_REQUEST_JITTER_SECONDS = 0.35
def _now_iso() -> str:
return datetime.now(timezone.utc).isoformat()
def _parse_iso(ts: str) -> Optional[datetime]:
if not ts:
return None
try:
# Python's fromisoformat accepts +00:00 but not 'Z' until 3.11.
normalized = ts.replace("Z", "+00:00")
dt = datetime.fromisoformat(normalized)
if dt.tzinfo is None:
dt = dt.replace(tzinfo=timezone.utc)
return dt
except (TypeError, ValueError):
return None
def _compute_position_confidence(entry: dict, *, now: Optional[datetime] = None) -> str:
"""Return the public confidence label for a carrier cache entry.
Order of precedence:
- explicit "homeport_default" / "seed" labels are preserved.
- dated entries (with position_source_at) are "recent" if within
the configured freshness window, else "stale".
- missing position_source_at falls through to "stale".
"""
raw_label = str(entry.get("position_confidence", "") or "").strip()
# Explicit "kind of provenance" labels are preserved as-is. They
# describe HOW we got the position, not WHEN — a fresh headline-to-
# centroid match (#245) is still imprecise no matter how recently
# it was observed, and the seed (#244) is always the seed.
if raw_label in {"seed", "homeport_default", "approximate"}:
# Approximate entries can still age into "stale_approximate" if
# they fall out of the freshness window — that distinction lets
# the UI render a different badge for old-and-imprecise vs
# recent-and-imprecise. seed/homeport_default never age (they
# were never timestamped against real observations).
if raw_label == "approximate":
source_at = _parse_iso(str(entry.get("position_source_at", "") or ""))
if source_at is not None:
reference = now or datetime.now(timezone.utc)
if reference - source_at > timedelta(days=_freshness_window_days()):
return "stale_approximate"
return raw_label
source_at = _parse_iso(str(entry.get("position_source_at", "") or ""))
if not source_at:
return "stale"
reference = now or datetime.now(timezone.utc)
window = timedelta(days=_freshness_window_days())
if reference - source_at <= window:
return "recent"
return "stale"
def _load_seed() -> Dict[str, dict]:
"""Load the read-only seed file shipped with the image.
Returns a hull→entry dict (no _meta wrapper). Missing or malformed
seed files yield an empty dict — the caller falls back to homeport
defaults.
"""
try:
if not SEED_FILE.exists():
logger.info("Carrier seed file not present at %s; first-run will fall back to homeport defaults", SEED_FILE)
return {}
raw = json.loads(SEED_FILE.read_text(encoding="utf-8"))
carriers = raw.get("carriers", {}) if isinstance(raw, dict) else {}
if not isinstance(carriers, dict):
return {}
logger.info("Carrier seed loaded: %d entries from %s", len(carriers), SEED_FILE)
return carriers
except (IOError, OSError, json.JSONDecodeError, ValueError) as e:
logger.warning("Failed to load carrier seed file %s: %s", SEED_FILE, e)
return {}
def _load_cache() -> Dict[str, dict]:
"""Load the mutable cache (last-known positions persisted between restarts)."""
"""Load cached carrier positions from disk."""
try:
if CACHE_FILE.exists():
data = json.loads(CACHE_FILE.read_text(encoding="utf-8"))
if isinstance(data, dict):
logger.info("Carrier cache loaded: %d carriers from %s", len(data), CACHE_FILE)
return data
data = json.loads(CACHE_FILE.read_text())
logger.info(f"Carrier cache loaded: {len(data)} carriers from {CACHE_FILE}")
return data
except (IOError, OSError, json.JSONDecodeError, ValueError) as e:
logger.warning("Failed to load carrier cache: %s", e)
logger.warning(f"Failed to load carrier cache: {e}")
return {}
def _save_cache(positions: Dict[str, dict]) -> None:
"""Persist the mutable cache. Atomic write (temp + rename) so a crash
mid-write can't leave the file truncated."""
def _save_cache(positions: Dict[str, dict]):
"""Persist carrier positions to disk."""
try:
CACHE_FILE.parent.mkdir(parents=True, exist_ok=True)
tmp = CACHE_FILE.with_suffix(CACHE_FILE.suffix + ".tmp")
tmp.write_text(json.dumps(positions, indent=2), encoding="utf-8")
# On Windows os.replace is atomic and overwrites existing files.
os.replace(tmp, CACHE_FILE)
logger.info("Carrier cache saved: %d carriers", len(positions))
CACHE_FILE.write_text(json.dumps(positions, indent=2))
logger.info(f"Carrier cache saved: {len(positions)} carriers")
except (IOError, OSError) as e:
logger.warning("Failed to save carrier cache: %s", e)
def _homeport_entry_for(hull: str) -> Optional[dict]:
"""Return a homeport-default cache entry for a hull, or None if the
hull is not in the registry."""
info = CARRIER_REGISTRY.get(hull)
if not info:
return None
return {
"lat": info["homeport_lat"],
"lng": info["homeport_lng"],
"heading": 0,
"desc": f"{info['homeport']} (no observations yet)",
"source": f"Homeport default ({info['homeport']})",
"source_url": info.get("wiki", ""),
"position_source_at": _now_iso(),
"position_confidence": "homeport_default",
}
def _bootstrap_cache_if_missing() -> Dict[str, dict]:
"""One-shot: if no cache exists, materialize one from the seed file.
Returns the cache contents (hull→entry). On first-ever startup,
this writes ``carrier_cache.json`` so subsequent restarts skip the
seed entirely. Operator-deleted caches re-bootstrap the same way —
operators can use that to "reset" carrier positions, but it's an
explicit operator action.
"""
if CACHE_FILE.exists():
return _load_cache()
seed = _load_seed()
if not seed:
# No seed file either. Build a homeport-default cache so the
# first save_cache call still produces something honest.
homeports: Dict[str, dict] = {}
for hull in CARRIER_REGISTRY:
entry = _homeport_entry_for(hull)
if entry is not None:
homeports[hull] = entry
if homeports:
_save_cache(homeports)
return homeports
# Persist the seed as the first cache so subsequent runs skip this branch.
_save_cache(seed)
logger.info("Carrier cache bootstrapped from seed (first-ever startup)")
return dict(seed)
logger.warning(f"Failed to save carrier cache: {e}")
def _match_region(text: str) -> Optional[tuple]:
@@ -442,8 +270,10 @@ def _match_carrier(text: str) -> Optional[str]:
for hull, info in CARRIER_REGISTRY.items():
hull_check = hull.lower().replace("-", "")
name_parts = info["name"].lower()
# Match hull number (e.g., "CVN-78", "CVN78")
if hull.lower() in text_lower or hull_check in text_lower.replace("-", ""):
return hull
# Match ship name (e.g., "Ford", "Eisenhower", "Vinson")
ship_name = name_parts.split("(")[0].strip()
last_name = ship_name.split()[-1] if ship_name else ""
if last_name and len(last_name) > 3 and last_name in text_lower:
@@ -493,9 +323,8 @@ def _fetch_gdelt_carrier_news() -> List[dict]:
articles = data.get("articles", [])
for art in articles:
title = art.get("title", "")
article_url = art.get("url", "")
article_at = art.get("seendate") or art.get("date") or ""
results.append({"title": title, "url": article_url, "seendate": article_at})
url = art.get("url", "")
results.append({"title": title, "url": url})
except (ConnectionError, TimeoutError, ValueError, KeyError, OSError) as e:
logger.debug(f"GDELT search failed for '{term}': {e}")
continue
@@ -511,139 +340,108 @@ def _fetch_gdelt_carrier_news() -> List[dict]:
return results
def _gdelt_seendate_to_iso(seendate: str) -> Optional[str]:
"""GDELT returns YYYYMMDDhhmmss (UTC). Convert to ISO8601 for
position_source_at. Returns None if the input is unparseable."""
raw = (seendate or "").strip()
if len(raw) < 8 or not raw.isdigit():
return None
try:
dt = datetime.strptime(raw[:14] if len(raw) >= 14 else raw[:8] + "000000", "%Y%m%d%H%M%S")
return dt.replace(tzinfo=timezone.utc).isoformat()
except (TypeError, ValueError):
return None
def _parse_carrier_positions_from_news(articles: List[dict]) -> Dict[str, dict]:
"""Parse carrier positions from news article titles.
Issue #245 (tg12): the position is a region centroid, which is
coarse — we now stamp ``position_confidence = "approximate"`` so
the UI can render that uncertainty. Issue #244: the
``position_source_at`` field is the news article's actual seen
date, NOT now(), so the freshness check correctly flips entries
to "stale" once they age past the configured window.
"""
"""Parse carrier positions from news article titles and descriptions."""
updates: Dict[str, dict] = {}
for article in articles:
title = article.get("title", "")
# Try to match a carrier from the title
hull = _match_carrier(title)
if not hull:
continue
# Try to match a region from the title
coords = _match_region(title)
if not coords:
continue
# First match wins (most recent article, GDELT returns newest first
# per term).
# Only update if we haven't seen this carrier yet (first match wins — most recent)
if hull not in updates:
iso_at = _gdelt_seendate_to_iso(str(article.get("seendate", ""))) or _now_iso()
updates[hull] = {
"lat": coords[0],
"lng": coords[1],
"heading": 0,
"desc": title[:100],
"source": "GDELT News API (headline region match — approximate)",
"source": "GDELT News API",
"source_url": article.get("url", "https://api.gdeltproject.org"),
"position_source_at": iso_at,
# Headline-to-centroid match is explicitly approximate.
"position_confidence": "approximate",
"updated": datetime.now(timezone.utc).isoformat(),
}
logger.info(
"Carrier update: %s%s (from: %s)",
CARRIER_REGISTRY[hull]["name"],
coords,
title[:80],
f"Carrier update: {CARRIER_REGISTRY[hull]['name']}{coords} (from: {title[:80]})"
)
return updates
def _enrich_for_rendering(hull: str, entry: dict, *, now: Optional[datetime] = None) -> dict:
"""Add live computed fields (confidence label, last_osint_update)
on top of the persisted cache entry. The persisted entry is left
untouched; this function builds the public-facing object.
"""
info = CARRIER_REGISTRY.get(hull, {})
confidence = _compute_position_confidence(entry, now=now)
return {
"name": entry.get("name", info.get("name", hull)),
"lat": entry["lat"],
"lng": entry["lng"],
"heading": entry.get("heading", 0),
"desc": entry.get("desc", ""),
"wiki": entry.get("wiki", info.get("wiki", "")),
"source": entry.get("source", "OSINT estimated position"),
"source_url": entry.get("source_url", ""),
"position_source_at": entry.get("position_source_at", ""),
"position_confidence": confidence,
# Existing field preserved for backward compatibility with the
# current frontend ShipPopup; now reflects the SOURCE's observed
# time (not now()), so "last reported X days ago" is honest.
"last_osint_update": entry.get("position_source_at", ""),
# Convenience boolean for the UI: true when the position is
# NOT live OSINT (used to render dimmed icons / badges).
"is_fallback": confidence in {"seed", "stale", "stale_approximate", "homeport_default"},
}
def _load_carrier_fallbacks() -> Dict[str, dict]:
"""Build carrier positions from static fallbacks + disk cache (instant, no network)."""
positions: Dict[str, dict] = {}
for hull, info in CARRIER_REGISTRY.items():
positions[hull] = {
"name": info["name"],
"lat": info["fallback_lat"],
"lng": info["fallback_lng"],
"heading": info["fallback_heading"],
"desc": info["fallback_desc"],
"wiki": info["wiki"],
"source": "USNI News Fleet & Marine Tracker",
"source_url": "https://news.usni.org/category/fleet-tracker",
"updated": datetime.now(timezone.utc).isoformat(),
}
# Overlay cached positions from previous runs (may have GDELT data)
cached = _load_cache()
for hull, cached_pos in cached.items():
if hull in positions:
if cached_pos.get("source", "").startswith("GDELT") or cached_pos.get(
"source", ""
).startswith("News"):
positions[hull].update(
{
"lat": cached_pos["lat"],
"lng": cached_pos["lng"],
"desc": cached_pos.get("desc", positions[hull]["desc"]),
"source": cached_pos.get("source", "Cached OSINT"),
"updated": cached_pos.get("updated", ""),
}
)
return positions
def update_carrier_positions() -> None:
"""Refresh carrier positions.
def update_carrier_positions():
"""Main update function — called on startup and every 12h.
Phase 1 (instant): publish whatever's in carrier_cache.json (or
bootstrap from seed on first-ever run), so the map has carriers
immediately.
Phase 2 (slow): query GDELT and replace position entries for any
carrier mentioned in fresh news. Persist back to cache.
Phase 1 (instant): publish fallback + cached positions so the map has carriers immediately.
Phase 2 (slow): query GDELT for fresh OSINT positions and update in-place.
"""
global _last_update
# --- Phase 1: instant cache (bootstrap from seed on first-ever run) ---
positions = _bootstrap_cache_if_missing()
# Ensure every registered hull has SOMETHING in the cache. A hull
# the seed didn't cover (e.g. added after install) renders at its
# homeport with "homeport_default" confidence.
for hull in CARRIER_REGISTRY:
if hull not in positions:
entry = _homeport_entry_for(hull)
if entry is not None:
positions[hull] = entry
# --- Phase 1: instant fallback + cache ---
positions = _load_carrier_fallbacks()
with _positions_lock:
# Only overwrite if positions are currently empty (first startup).
# If we already have data from a previous cycle, keep it while GDELT runs.
if not _carrier_positions:
_carrier_positions.update(positions)
_last_update = datetime.now(timezone.utc)
logger.info(
"Carrier tracker: %d carriers loaded from cache (GDELT enrichment starting...)",
len(positions),
f"Carrier tracker: {len(positions)} carriers loaded from fallback/cache (GDELT enrichment starting...)"
)
# --- Phase 2: GDELT enrichment ---
# --- Phase 2: slow GDELT enrichment ---
try:
articles = _fetch_gdelt_carrier_news()
news_positions = _parse_carrier_positions_from_news(articles)
for hull, pos in news_positions.items():
# Always overwrite — newest GDELT mention wins. The previous
# entry's position is preserved in git history and the next
# cycle either confirms or replaces it.
positions[hull] = pos
logger.info("Carrier OSINT: updated %s from news", CARRIER_REGISTRY[hull]["name"])
if hull in positions:
positions[hull].update(pos)
logger.info(f"Carrier OSINT: updated {CARRIER_REGISTRY[hull]['name']} from news")
except (ValueError, KeyError, json.JSONDecodeError, OSError) as e:
logger.warning("GDELT carrier fetch failed: %s", e)
logger.warning(f"GDELT carrier fetch failed: {e}")
# Save and update the global state with enriched positions
with _positions_lock:
_carrier_positions.clear()
_carrier_positions.update(positions)
@@ -651,15 +449,21 @@ def update_carrier_positions() -> None:
_save_cache(positions)
confidences: Dict[str, int] = {}
for entry in positions.values():
label = _compute_position_confidence(entry)
confidences[label] = confidences.get(label, 0) + 1
logger.info("Carrier tracker: %d carriers updated. Confidence: %s", len(positions), confidences)
sources = {}
for p in positions.values():
src = p.get("source", "unknown")
sources[src] = sources.get(src, 0) + 1
logger.info(f"Carrier tracker: {len(positions)} carriers updated. Sources: {sources}")
def _deconflict_positions(result: List[dict]) -> List[dict]:
"""Offset carriers that share identical coordinates so they don't stack."""
"""Offset carriers that share identical coordinates so they don't stack.
At port: offset along the pier axis (~500m / 0.004° apart).
At sea: offset perpendicular to each other (~0.08° / ~9km apart)
so they're visibly separate but clearly operating together.
"""
# Group by rounded lat/lng (within ~0.01° ≈ 1km = same spot)
from collections import defaultdict
groups: dict[str, list[int]] = defaultdict(list)
@@ -671,6 +475,7 @@ def _deconflict_positions(result: List[dict]) -> List[dict]:
if len(indices) < 2:
continue
n = len(indices)
# Determine if this is a port (near a homeport) or at sea
sample = result[indices[0]]
at_port = any(
abs(sample["lat"] - info.get("homeport_lat", 0)) < 0.05
@@ -679,6 +484,7 @@ def _deconflict_positions(result: List[dict]) -> List[dict]:
)
if at_port:
# Use each carrier's distinct homeport pier coordinates
for idx in indices:
carrier = result[idx]
hull = None
@@ -691,7 +497,8 @@ def _deconflict_positions(result: List[dict]) -> List[dict]:
carrier["lat"] = info["homeport_lat"]
carrier["lng"] = info["homeport_lng"]
else:
spacing = 0.08
# At sea: spread in a line perpendicular to travel (~0.08° apart)
spacing = 0.08 # ~9km — close enough to see they're together
start_offset = -(n - 1) * spacing / 2
for j, idx in enumerate(indices):
result[idx]["lng"] += start_offset + j * spacing
@@ -700,44 +507,36 @@ def _deconflict_positions(result: List[dict]) -> List[dict]:
def get_carrier_positions() -> List[dict]:
"""Return current carrier positions for the data pipeline.
Each entry has the full provenance + freshness fields; the UI can
decide how to render them. Carriers are never hidden — only
labeled.
"""
now = datetime.now(timezone.utc)
"""Return current carrier positions for the data pipeline."""
with _positions_lock:
result: List[dict] = []
for hull, entry in _carrier_positions.items():
enriched = _enrich_for_rendering(hull, entry, now=now)
result = []
for hull, pos in _carrier_positions.items():
info = CARRIER_REGISTRY.get(hull, {})
result.append(
{
"name": enriched["name"],
"name": pos.get("name", info.get("name", hull)),
"type": "carrier",
"lat": enriched["lat"],
"lng": enriched["lng"],
"heading": None, # OSINT cannot determine true heading.
"lat": pos["lat"],
"lng": pos["lng"],
"heading": None, # Heading unknown for carriers — OSINT cannot determine true heading
"sog": 0,
"cog": 0,
"country": "United States",
"desc": enriched["desc"],
"wiki": enriched["wiki"],
"desc": pos.get("desc", ""),
"wiki": pos.get("wiki", info.get("wiki", "")),
"estimated": True,
"source": enriched["source"],
"source_url": enriched["source_url"],
"last_osint_update": enriched["last_osint_update"],
# New fields (additive — existing UI continues to work):
"position_source_at": enriched["position_source_at"],
"position_confidence": enriched["position_confidence"],
"is_fallback": enriched["is_fallback"],
"source": pos.get("source", "OSINT estimated position"),
"source_url": pos.get(
"source_url", "https://news.usni.org/category/fleet-tracker"
),
"last_osint_update": pos.get("updated", ""),
}
)
return _deconflict_positions(result)
# -----------------------------------------------------------------
# Scheduler: runs at startup, then at 00:00 and 12:00 UTC daily.
# Scheduler: runs at startup, then at 00:00 and 12:00 UTC daily
# -----------------------------------------------------------------
_scheduler_thread: Optional[threading.Thread] = None
_scheduler_stop = threading.Event()
@@ -745,6 +544,7 @@ _scheduler_stop = threading.Event()
def _scheduler_loop():
"""Background thread that triggers updates at 00:00 and 12:00 UTC."""
# Initial update on startup
try:
update_carrier_positions()
except Exception as e:
@@ -752,6 +552,7 @@ def _scheduler_loop():
while not _scheduler_stop.is_set():
now = datetime.now(timezone.utc)
# Next target: 00:00 or 12:00 UTC, whichever is sooner
hour = now.hour
if hour < 12:
next_hour = 12
@@ -760,17 +561,18 @@ def _scheduler_loop():
next_run = now.replace(hour=next_hour % 24, minute=0, second=0, microsecond=0)
if next_hour == 24:
from datetime import timedelta
next_run = (now + timedelta(days=1)).replace(hour=0, minute=0, second=0, microsecond=0)
wait_seconds = (next_run - now).total_seconds()
logger.info(
"Carrier tracker: next update at %s (%.1fh)",
next_run.isoformat(),
wait_seconds / 3600,
f"Carrier tracker: next update at {next_run.isoformat()} ({wait_seconds/3600:.1f}h)"
)
# Wait until next scheduled time, or until stop event
if _scheduler_stop.wait(timeout=wait_seconds):
break
break # Stop event was set
try:
update_carrier_positions()
+3 -30
View File
@@ -4,7 +4,7 @@ import concurrent.futures
from urllib.parse import quote
import requests as _requests
from cachetools import TTLCache
from services.network_utils import fetch_with_curl, DEFAULT_USER_AGENT
from services.network_utils import fetch_with_curl
logger = logging.getLogger(__name__)
@@ -15,25 +15,6 @@ dossier_cache = TTLCache(maxsize=500, ttl=86400)
# Nominatim requires max 1 req/sec — track last call time
_nominatim_last_call = 0.0
# Issue #218 / #219 (tg12): Wikimedia's User-Agent policy requires API
# clients to identify themselves with a stable User-Agent that includes
# a contact path. Bare "python-requests/x.y" or generic strings violate
# the policy and risk getting blocked. We send the project default UA
# (operator-overridable via SHADOWBROKER_USER_AGENT) on EVERY outbound
# Wikimedia request, plus the policy-recommended Api-User-Agent which
# Wikimedia explicitly accepts on top of the regular UA.
#
# This is documented and stable so a Wikimedia operator who wants to
# rate-limit or contact us has a fixed identifier to grep for.
_WIKIMEDIA_REQUEST_HEADERS = {
"User-Agent": DEFAULT_USER_AGENT,
"Api-User-Agent": (
f"{DEFAULT_USER_AGENT} "
"(+https://github.com/BigBodyCobain/Shadowbroker; "
"report issues at /issues)"
),
}
def _reverse_geocode_offline(lat: float, lng: float) -> dict:
"""Offline fallback via reverse_geocoder when external reverse geocoding is blocked."""
@@ -140,13 +121,7 @@ def _fetch_wikidata_leader(country_name: str) -> dict:
"""
url = f"https://query.wikidata.org/sparql?query={quote(sparql)}&format=json"
try:
# Issue #218 (tg12): Wikimedia's User-Agent policy requires
# outbound API traffic to be identifiable. fetch_with_curl()
# sends the project default, and we also add the Wikimedia-
# specific Api-User-Agent that the policy specifically asks
# for, since this request originates from a backend service
# that proxies on behalf of (potentially many) browser users.
res = fetch_with_curl(url, timeout=6, headers=_WIKIMEDIA_REQUEST_HEADERS)
res = fetch_with_curl(url, timeout=6)
if res.status_code == 200:
results = res.json().get("results", {}).get("bindings", [])
if results:
@@ -172,9 +147,7 @@ def _fetch_local_wiki_summary(place_name: str, country_name: str = "") -> dict:
slug = quote(name.replace(" ", "_"))
url = f"https://en.wikipedia.org/api/rest_v1/page/summary/{slug}"
try:
# Issue #219 (tg12): identify ourselves to Wikimedia per
# their UA policy; see _fetch_wikidata_leader above.
res = fetch_with_curl(url, timeout=5, headers=_WIKIMEDIA_REQUEST_HEADERS)
res = fetch_with_curl(url, timeout=5)
if res.status_code == 200:
data = res.json()
if data.get("type") != "disambiguation":
@@ -1,677 +0,0 @@
{
"_meta": {
"issue": "#239",
"note": "Snapshot of currently-tolerated duplicate route registrations. The test in test_no_new_duplicate_routes.py fails if any NEW (method, path) duplicate appears outside this list. Removing entries (by actually deduping) is fine and the test stays green. New entries here require explicit, reviewed updates.",
"generated_with": "python -c 'see tests/test_no_new_duplicate_routes.py'"
},
"duplicates": {
"DELETE /api/mesh/peers": [
"main",
"routers.mesh_operator",
"routers.mesh_public"
],
"DELETE /api/wormhole/dm/contact/{peer_id}": [
"main",
"routers.wormhole"
],
"DELETE /api/wormhole/dm/invite/handles/{handle}": [
"main",
"routers.wormhole"
],
"GET /api/cctv/media": [
"main",
"routers.cctv"
],
"GET /api/debug-latest": [
"main",
"routers.health"
],
"GET /api/geocode/reverse": [
"main",
"routers.tools"
],
"GET /api/geocode/search": [
"main",
"routers.tools"
],
"GET /api/health": [
"main",
"routers.health"
],
"GET /api/live-data": [
"main",
"routers.data"
],
"GET /api/live-data/fast": [
"main",
"routers.data"
],
"GET /api/live-data/slow": [
"main",
"routers.data"
],
"GET /api/mesh/channels": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/dm/count": [
"main",
"routers.mesh_dm"
],
"GET /api/mesh/dm/poll": [
"main",
"routers.mesh_dm"
],
"GET /api/mesh/dm/prekey-bundle": [
"main",
"routers.mesh_dm"
],
"GET /api/mesh/dm/pubkey": [
"main",
"routers.mesh_dm"
],
"GET /api/mesh/dm/witness": [
"main",
"routers.mesh_dm"
],
"GET /api/mesh/gate/list": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/gate/{gate_id}": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/gate/{gate_id}/messages": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/infonet/event/{event_id}": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/infonet/events": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/infonet/locator": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/infonet/merkle": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/infonet/messages": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/infonet/messages/wait": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/infonet/node/{node_id}": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/infonet/status": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/infonet/sync": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/log": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/messages": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/metrics": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/oracle/consensus": [
"main",
"routers.mesh_oracle"
],
"GET /api/mesh/oracle/markets": [
"main",
"routers.mesh_oracle"
],
"GET /api/mesh/oracle/markets/more": [
"main",
"routers.mesh_oracle"
],
"GET /api/mesh/oracle/predictions": [
"main",
"routers.mesh_oracle"
],
"GET /api/mesh/oracle/profile": [
"main",
"routers.mesh_oracle"
],
"GET /api/mesh/oracle/search": [
"main",
"routers.mesh_oracle"
],
"GET /api/mesh/oracle/stakes/{message_id}": [
"main",
"routers.mesh_oracle"
],
"GET /api/mesh/peers": [
"main",
"routers.mesh_operator",
"routers.mesh_public"
],
"GET /api/mesh/reputation": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/reputation/all": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/reputation/batch": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/rns/status": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/signals": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/status": [
"main",
"routers.mesh_public"
],
"GET /api/mesh/trust/vouches": [
"main",
"routers.mesh_dm"
],
"GET /api/oracle/region-intel": [
"main",
"routers.sigint"
],
"GET /api/radio/nearest": [
"main",
"routers.radio"
],
"GET /api/radio/nearest-list": [
"main",
"routers.radio"
],
"GET /api/radio/openmhz/audio": [
"main",
"routers.radio"
],
"GET /api/radio/openmhz/calls/{sys_name}": [
"main",
"routers.radio"
],
"GET /api/radio/openmhz/systems": [
"main",
"routers.radio"
],
"GET /api/radio/top": [
"main",
"routers.radio"
],
"GET /api/refresh": [
"main",
"routers.data"
],
"GET /api/region-dossier": [
"main",
"routers.tools"
],
"GET /api/route/{callsign}": [
"main",
"routers.radio"
],
"GET /api/sentinel2/search": [
"main",
"routers.tools"
],
"GET /api/settings/api-keys": [
"main",
"routers.admin"
],
"GET /api/settings/api-keys/meta": [
"main",
"routers.admin"
],
"GET /api/settings/news-feeds": [
"main",
"routers.admin"
],
"GET /api/settings/node": [
"main",
"routers.admin"
],
"GET /api/settings/privacy-profile": [
"main",
"routers.wormhole"
],
"GET /api/settings/wormhole": [
"main",
"routers.wormhole"
],
"GET /api/settings/wormhole-status": [
"main",
"routers.wormhole"
],
"GET /api/sigint/nearest-sdr": [
"main",
"routers.sigint"
],
"GET /api/thermal/verify": [
"main",
"routers.sigint"
],
"GET /api/tools/shodan/status": [
"main",
"routers.tools"
],
"GET /api/tools/uw/status": [
"main",
"routers.tools"
],
"GET /api/wormhole/dm/contacts": [
"main",
"routers.wormhole"
],
"GET /api/wormhole/dm/identity": [
"main",
"routers.wormhole"
],
"GET /api/wormhole/dm/invite": [
"main",
"routers.wormhole"
],
"GET /api/wormhole/dm/invite/handles": [
"main",
"routers.wormhole"
],
"GET /api/wormhole/gate/{gate_id}/identity": [
"main",
"routers.wormhole"
],
"GET /api/wormhole/gate/{gate_id}/key": [
"main",
"routers.wormhole"
],
"GET /api/wormhole/gate/{gate_id}/personas": [
"main",
"routers.wormhole"
],
"GET /api/wormhole/health": [
"main",
"routers.wormhole"
],
"GET /api/wormhole/identity": [
"main",
"routers.wormhole"
],
"GET /api/wormhole/status": [
"main",
"routers.wormhole"
],
"PATCH /api/mesh/peers": [
"main",
"routers.mesh_operator",
"routers.mesh_public"
],
"POST /api/ais/feed": [
"main",
"routers.data"
],
"POST /api/layers": [
"main",
"routers.data"
],
"POST /api/mesh/dm/block": [
"main",
"routers.mesh_dm"
],
"POST /api/mesh/dm/count": [
"main",
"routers.mesh_dm"
],
"POST /api/mesh/dm/poll": [
"main",
"routers.mesh_dm"
],
"POST /api/mesh/dm/register": [
"main",
"routers.mesh_dm"
],
"POST /api/mesh/dm/send": [
"main",
"routers.mesh_dm"
],
"POST /api/mesh/dm/witness": [
"main",
"routers.mesh_dm"
],
"POST /api/mesh/gate/create": [
"main",
"routers.mesh_public"
],
"POST /api/mesh/gate/peer-pull": [
"main",
"routers.mesh_peer_sync"
],
"POST /api/mesh/gate/peer-push": [
"main",
"routers.mesh_peer_sync"
],
"POST /api/mesh/gate/{gate_id}/message": [
"main",
"routers.mesh_public"
],
"POST /api/mesh/identity/revoke": [
"main",
"routers.mesh_public"
],
"POST /api/mesh/identity/rotate": [
"main",
"routers.mesh_public"
],
"POST /api/mesh/infonet/ingest": [
"main",
"routers.mesh_public"
],
"POST /api/mesh/infonet/peer-push": [
"main",
"routers.mesh_peer_sync"
],
"POST /api/mesh/infonet/sync": [
"main",
"routers.mesh_public"
],
"POST /api/mesh/oracle/predict": [
"main",
"routers.mesh_oracle"
],
"POST /api/mesh/oracle/resolve": [
"main",
"routers.mesh_oracle"
],
"POST /api/mesh/oracle/resolve-stakes": [
"main",
"routers.mesh_oracle"
],
"POST /api/mesh/oracle/stake": [
"main",
"routers.mesh_oracle"
],
"POST /api/mesh/peers": [
"main",
"routers.mesh_operator",
"routers.mesh_public"
],
"POST /api/mesh/report": [
"main",
"routers.mesh_public"
],
"POST /api/mesh/send": [
"main",
"routers.mesh_public"
],
"POST /api/mesh/trust/vouch": [
"main",
"routers.mesh_dm"
],
"POST /api/mesh/vote": [
"main",
"routers.mesh_public"
],
"POST /api/sentinel/tile": [
"main",
"routers.tools"
],
"POST /api/sentinel/token": [
"main",
"routers.tools"
],
"POST /api/settings/news-feeds/reset": [
"main",
"routers.admin"
],
"POST /api/sigint/transmit": [
"main",
"routers.sigint"
],
"POST /api/system/update": [
"main",
"routers.admin"
],
"POST /api/tools/shodan/count": [
"main",
"routers.tools"
],
"POST /api/tools/shodan/host": [
"main",
"routers.tools"
],
"POST /api/tools/shodan/search": [
"main",
"routers.tools"
],
"POST /api/tools/uw/congress": [
"main",
"routers.tools"
],
"POST /api/tools/uw/darkpool": [
"main",
"routers.tools"
],
"POST /api/tools/uw/flow": [
"main",
"routers.tools"
],
"POST /api/viewport": [
"main",
"routers.data"
],
"POST /api/wormhole/connect": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/disconnect": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/bootstrap-decrypt": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/bootstrap-encrypt": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/build-seal": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/compose": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/dead-drop-token": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/dead-drop-tokens": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/decrypt": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/encrypt": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/invite/import": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/open-seal": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/pairwise-alias": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/pairwise-alias/rotate": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/prekey/register": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/register-key": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/reset": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/sas": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/dm/sender-token": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/enter": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/key/grant": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/key/rotate": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/leave": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/message/compose": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/message/decrypt": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/message/post": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/message/post-encrypted": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/message/sign-encrypted": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/messages/decrypt": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/persona/activate": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/persona/clear": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/persona/create": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/persona/retire": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/proof": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/gate/state/export": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/identity/bootstrap": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/join": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/leave": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/restart": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/sign": [
"main",
"routers.wormhole"
],
"POST /api/wormhole/sign-raw": [
"main",
"routers.wormhole"
],
"PUT /api/mesh/gate/{gate_id}/envelope_policy": [
"main",
"routers.mesh_public"
],
"PUT /api/mesh/gate/{gate_id}/legacy_envelope_fallback": [
"main",
"routers.mesh_public"
],
"PUT /api/settings/news-feeds": [
"main",
"routers.admin"
],
"PUT /api/settings/node": [
"main",
"routers.admin"
],
"PUT /api/settings/privacy-profile": [
"main",
"routers.wormhole"
],
"PUT /api/settings/wormhole": [
"main",
"routers.wormhole"
],
"PUT /api/wormhole/dm/contact": [
"main",
"routers.wormhole"
]
}
}
@@ -1,389 +0,0 @@
"""Issues #244, #245, #246 (tg12 external audit): carrier tracker
quality + provenance + freshness.
These tests pin the post-fix contract:
- **#244**: dated editorial snapshot positions no longer live in the
registry. They live in a one-shot seed file that is consumed once
on first-ever startup. After that, the runtime cache reflects only
what THIS install has actually observed.
- **#245**: headline-derived positions (centroid of a region keyword)
are stamped ``position_confidence = "approximate"`` so the UI can
render them with appropriate uncertainty.
- **#246**: freshness is a *labelling* decision, not an eviction
decision. Positions older than the configurable freshness window
flip from ``"recent"`` to ``"stale"`` but are NEVER replaced with
the registry default — that would teleport the carrier. The user
always sees the last position the system actually observed.
"""
from __future__ import annotations
import json
import os
from datetime import datetime, timedelta, timezone
from pathlib import Path
from unittest.mock import patch
import pytest
@pytest.fixture
def fresh_tracker(tmp_path, monkeypatch):
"""Isolated carrier_tracker with seed/cache paths redirected to tmp.
Yields the module so tests can call its functions; resets globals
between tests so position caches don't leak across cases.
"""
from services import carrier_tracker
seed_path = tmp_path / "data" / "carrier_seed.json"
cache_path = tmp_path / "carrier_cache.json"
seed_path.parent.mkdir(parents=True, exist_ok=True)
monkeypatch.setattr(carrier_tracker, "SEED_FILE", seed_path)
monkeypatch.setattr(carrier_tracker, "CACHE_FILE", cache_path)
monkeypatch.delenv("SHADOWBROKER_CARRIER_FRESHNESS_DAYS", raising=False)
# Reset module-level mutable state.
carrier_tracker._carrier_positions.clear()
carrier_tracker._cached_gdelt_articles.clear()
carrier_tracker._last_gdelt_fetch_at = 0.0
yield carrier_tracker
# Clean up so subsequent tests start fresh.
carrier_tracker._carrier_positions.clear()
carrier_tracker._cached_gdelt_articles.clear()
def _write_seed(path: Path, hull: str = "CVN-78", **overrides) -> None:
payload = {
"_meta": {
"as_of": "2026-03-09",
"source": "USNI News Fleet & Marine Tracker",
"source_url": "https://news.usni.org/...",
"note": "test",
},
"carriers": {
hull: {
"lat": 18.0,
"lng": 39.5,
"heading": 0,
"desc": "Red Sea — Operation Epic Fury (USNI Mar 9)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed",
**overrides,
}
},
}
path.write_text(json.dumps(payload), encoding="utf-8")
# ---------------------------------------------------------------------------
# #244 — first-run seed bootstrap, never re-seeds after that
# ---------------------------------------------------------------------------
class TestSeedBootstrap:
def test_first_ever_startup_bootstraps_from_seed(self, fresh_tracker, tmp_path):
_write_seed(fresh_tracker.SEED_FILE)
# No cache exists yet.
assert not fresh_tracker.CACHE_FILE.exists()
positions = fresh_tracker._bootstrap_cache_if_missing()
# The seed entry made it into the cache.
assert "CVN-78" in positions
assert positions["CVN-78"]["lat"] == 18.0
assert positions["CVN-78"]["position_confidence"] == "seed"
# And the cache file is now on disk so subsequent runs skip the seed.
assert fresh_tracker.CACHE_FILE.exists()
def test_subsequent_startup_ignores_seed(self, fresh_tracker, tmp_path):
# Pre-seed a different position into the cache; the seed file says Red Sea.
cache_data = {
"CVN-78": {
"lat": 25.0,
"lng": 55.0,
"heading": 0,
"desc": "Persian Gulf — operator-observed",
"source": "Operator log",
"source_url": "",
"position_source_at": "2026-04-15T12:00:00Z",
"position_confidence": "recent",
}
}
fresh_tracker.CACHE_FILE.write_text(json.dumps(cache_data))
_write_seed(fresh_tracker.SEED_FILE) # seed is present but should NOT be used
positions = fresh_tracker._bootstrap_cache_if_missing()
assert positions["CVN-78"]["lat"] == 25.0
assert positions["CVN-78"]["desc"] == "Persian Gulf — operator-observed"
def test_no_seed_no_cache_falls_back_to_homeport(self, fresh_tracker):
# Neither seed nor cache. Must fall back to homeport defaults
# (carrier never disappears).
assert not fresh_tracker.SEED_FILE.exists()
assert not fresh_tracker.CACHE_FILE.exists()
positions = fresh_tracker._bootstrap_cache_if_missing()
# Every registered carrier has SOMETHING.
assert set(positions.keys()) == set(fresh_tracker.CARRIER_REGISTRY.keys())
# All entries are labelled as homeport defaults.
for hull, entry in positions.items():
assert entry["position_confidence"] == "homeport_default"
registry = fresh_tracker.CARRIER_REGISTRY[hull]
assert entry["lat"] == registry["homeport_lat"]
assert entry["lng"] == registry["homeport_lng"]
# ---------------------------------------------------------------------------
# #244 — no editorial fallbacks live in the registry
# ---------------------------------------------------------------------------
class TestRegistryShape:
def test_registry_has_no_dated_fallback_fields(self, fresh_tracker):
"""The Mar 9 editorial coordinates are gone from the registry.
They live only in the seed file."""
forbidden = {"fallback_lat", "fallback_lng", "fallback_heading", "fallback_desc"}
for hull, entry in fresh_tracker.CARRIER_REGISTRY.items():
offending = forbidden & set(entry.keys())
assert not offending, f"{hull} still has dated registry fields: {offending}"
def test_registry_keeps_homeport_for_every_hull(self, fresh_tracker):
for hull, entry in fresh_tracker.CARRIER_REGISTRY.items():
assert "homeport_lat" in entry, f"{hull} missing homeport_lat"
assert "homeport_lng" in entry, f"{hull} missing homeport_lng"
assert "name" in entry
assert "wiki" in entry
# ---------------------------------------------------------------------------
# #246 — freshness labelling, NOT eviction
# ---------------------------------------------------------------------------
class TestFreshnessLabelling:
def test_recent_observation_labels_recent(self, fresh_tracker):
now = datetime(2026, 6, 1, tzinfo=timezone.utc)
entry = {
"lat": 25.0,
"lng": 55.0,
"position_source_at": (now - timedelta(days=3)).isoformat(),
}
assert fresh_tracker._compute_position_confidence(entry, now=now) == "recent"
def test_aged_observation_flips_to_stale(self, fresh_tracker):
now = datetime(2026, 6, 1, tzinfo=timezone.utc)
entry = {
"lat": 25.0,
"lng": 55.0,
"position_source_at": (now - timedelta(days=30)).isoformat(),
}
assert fresh_tracker._compute_position_confidence(entry, now=now) == "stale"
def test_seed_label_is_preserved_explicitly(self, fresh_tracker):
now = datetime(2026, 6, 1, tzinfo=timezone.utc)
entry = {
"lat": 18.0,
"lng": 39.5,
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed",
}
# Even though the source is months old, the explicit "seed" label wins
# so the UI can render the seed-specific badge instead of generic "stale".
assert fresh_tracker._compute_position_confidence(entry, now=now) == "seed"
def test_homeport_default_label_is_preserved(self, fresh_tracker):
now = datetime(2026, 6, 1, tzinfo=timezone.utc)
entry = {
"lat": 36.95,
"lng": -76.32,
"position_source_at": now.isoformat(),
"position_confidence": "homeport_default",
}
assert fresh_tracker._compute_position_confidence(entry, now=now) == "homeport_default"
def test_freshness_window_is_env_configurable(self, fresh_tracker, monkeypatch):
now = datetime(2026, 6, 1, tzinfo=timezone.utc)
entry = {
"lat": 25.0,
"lng": 55.0,
"position_source_at": (now - timedelta(days=20)).isoformat(),
}
# Default window = 14 days → 20-day-old entry is stale.
assert fresh_tracker._compute_position_confidence(entry, now=now) == "stale"
# Stretch to 30 days → same entry is now "recent".
monkeypatch.setenv("SHADOWBROKER_CARRIER_FRESHNESS_DAYS", "30")
assert fresh_tracker._compute_position_confidence(entry, now=now) == "recent"
def test_aged_cache_entry_keeps_its_position_never_reverts(self, fresh_tracker):
"""The core regression test for the user's intent: a year-old
cache entry must NOT be replaced with the seed or homeport.
The PHYSICAL position the user sees is the last one observed;
only the freshness LABEL changes."""
a_year_ago = (datetime.now(timezone.utc) - timedelta(days=365)).isoformat()
cache_data = {
"CVN-78": {
"lat": 25.0,
"lng": 55.0,
"heading": 0,
"desc": "Persian Gulf",
"source": "GDELT News API",
"source_url": "https://news.example/...",
"position_source_at": a_year_ago,
"position_confidence": "recent", # was recent when written
}
}
fresh_tracker.CACHE_FILE.write_text(json.dumps(cache_data))
positions = fresh_tracker._bootstrap_cache_if_missing()
enriched = fresh_tracker._enrich_for_rendering("CVN-78", positions["CVN-78"])
# The position is preserved exactly.
assert enriched["lat"] == 25.0
assert enriched["lng"] == 55.0
# But the live label has flipped to stale.
assert enriched["position_confidence"] == "stale"
assert enriched["is_fallback"] is True
# ---------------------------------------------------------------------------
# #245 — approximate confidence for region-centroid positions
# ---------------------------------------------------------------------------
class TestApproximateConfidenceForNewsDerivedPositions:
def test_news_parsing_stamps_approximate_confidence(self, fresh_tracker):
articles = [
{
"title": "USS Ford carrier deployed in Mediterranean for joint exercise",
"url": "https://news.example/ford-mediterranean",
"seendate": "20260415120000",
}
]
updates = fresh_tracker._parse_carrier_positions_from_news(articles)
assert "CVN-78" in updates
entry = updates["CVN-78"]
assert entry["position_confidence"] == "approximate"
# And the source_at is the article's seen date, not now().
assert entry["position_source_at"].startswith("2026-04-15")
def test_gdelt_seendate_parser_handles_well_formed_input(self, fresh_tracker):
iso = fresh_tracker._gdelt_seendate_to_iso("20260415120000")
assert iso is not None
assert iso.startswith("2026-04-15T12:00:00")
def test_gdelt_seendate_parser_returns_none_on_garbage(self, fresh_tracker):
assert fresh_tracker._gdelt_seendate_to_iso("") is None
assert fresh_tracker._gdelt_seendate_to_iso("not-a-date") is None
assert fresh_tracker._gdelt_seendate_to_iso("2026") is None
# ---------------------------------------------------------------------------
# Full enrichment → public API shape
# ---------------------------------------------------------------------------
class TestEnrichForRendering:
def test_seed_entry_produces_expected_public_fields(self, fresh_tracker):
seed_entry = {
"lat": 18.0,
"lng": 39.5,
"heading": 0,
"desc": "Red Sea (USNI Mar 9)",
"source": "USNI News Fleet & Marine Tracker (seed, as of 2026-03-09)",
"source_url": "https://news.usni.org/category/fleet-tracker",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed",
}
enriched = fresh_tracker._enrich_for_rendering("CVN-78", seed_entry)
# Existing UI fields preserved.
assert enriched["lat"] == 18.0
assert enriched["lng"] == 39.5
assert enriched["source"].startswith("USNI")
assert enriched["last_osint_update"] == "2026-03-09T00:00:00Z"
# New audit-required fields.
assert enriched["position_confidence"] == "seed"
assert enriched["position_source_at"] == "2026-03-09T00:00:00Z"
assert enriched["is_fallback"] is True
def test_recent_observation_is_not_fallback(self, fresh_tracker):
now = datetime.now(timezone.utc)
recent_entry = {
"lat": 25.0,
"lng": 55.0,
"heading": 0,
"desc": "Persian Gulf",
"source": "GDELT News API",
"source_url": "https://news.example/...",
"position_source_at": (now - timedelta(days=2)).isoformat(),
"position_confidence": "approximate",
}
enriched = fresh_tracker._enrich_for_rendering("CVN-78", recent_entry, now=now)
assert enriched["position_confidence"] == "approximate"
# Approximate (from a recent headline) is honest precision, but the UI
# treats it as live data — is_fallback only flips True for explicit
# fallback categories (seed / stale / homeport_default).
assert enriched["is_fallback"] is False
# ---------------------------------------------------------------------------
# Regression: existing frontend fields are preserved
# ---------------------------------------------------------------------------
class TestPublicResponseShapeBackwardCompat:
"""The frontend ShipPopup expects `estimated`, `source`, `source_url`,
`last_osint_update`. The new fields are additive and existing fields
keep their meaning so the UI does not need updating to keep working."""
def test_get_carrier_positions_preserves_existing_keys(self, fresh_tracker):
_write_seed(fresh_tracker.SEED_FILE)
fresh_tracker._bootstrap_cache_if_missing()
with fresh_tracker._positions_lock:
fresh_tracker._carrier_positions.update(
{
"CVN-78": {
"lat": 18.0,
"lng": 39.5,
"heading": 0,
"desc": "Red Sea (seed)",
"source": "Seed",
"source_url": "",
"position_source_at": "2026-03-09T00:00:00Z",
"position_confidence": "seed",
}
}
)
out = fresh_tracker.get_carrier_positions()
assert len(out) == 1
c = out[0]
# Old fields the frontend uses.
for key in (
"name",
"type",
"lat",
"lng",
"country",
"desc",
"wiki",
"estimated",
"source",
"source_url",
"last_osint_update",
):
assert key in c, f"missing legacy field {key!r}"
# New fields.
for key in ("position_confidence", "position_source_at", "is_fallback"):
assert key in c, f"missing audit-required field {key!r}"
assert c["type"] == "carrier"
assert c["estimated"] is True
@@ -1,208 +0,0 @@
"""Issue #239 (tg12): backend registers duplicate API routes in both
``main.py`` and router modules, so request behavior depends on the
order ``FastAPI`` happened to register them.
This test is the **CI guard** that locks in the invariant going forward.
It does NOT delete any existing duplicates — those are tolerated via an
explicit baseline file. What it DOES block is *new* duplicates appearing
later, which is what the audit was actually asking for: a way to stop
the drift before it gets worse.
Findings (empirically verified, see PR #286 description):
- ``main.app`` calls ``include_router(...)`` for every router at module
import time around line 3316.
- Every ``@app.get/post/put/...`` decorator inside ``main.py`` runs
*after* those include_router calls, so the router handler is the one
that actually serves requests. The duplicates in ``main.py`` are
dead code at the route-resolution layer.
- Behavior today is deterministic (router wins), but if someone later
adds a NEW route only in ``main.py``, or edits one copy of an
existing pair without the other, drift starts.
How this test works:
- Walks ``main.app.routes`` and records every ``(method, path)`` that
appears more than once, along with which modules registered each
copy.
- Compares that set against the baseline in
``backend/tests/data/duplicate_routes_baseline.json``.
- **Fails** if any duplicate appears that is NOT in the baseline
(or if the registering modules for an existing duplicate change).
- **Stays green** when duplicates are *removed* by genuinely deduping
the code. (The baseline is a ceiling, not a floor.)
To extend in the future:
- If you actually dedupe a route, leave the baseline alone — the test
still passes. Subsequent regenerations of the baseline (``python -m
scripts.regen_duplicate_routes_baseline`` or the snippet in this
test's docstring) will shrink it.
- If you legitimately need a new duplicate (you probably do not), add
it to the baseline AND explain why in the PR description so reviewers
can push back.
"""
from __future__ import annotations
import json
from collections import defaultdict
from pathlib import Path
import pytest
BASELINE_PATH = (
Path(__file__).parent / "data" / "duplicate_routes_baseline.json"
)
def _current_duplicates() -> dict[str, list[str]]:
"""Walk ``main.app.routes`` and return ``{'METHOD /path': [module, ...]}``
for every (method, path) registered more than once."""
import main
by_key: dict[str, list[str]] = defaultdict(list)
for route in main.app.routes:
path = getattr(route, "path", None)
methods = getattr(route, "methods", None)
endpoint = getattr(route, "endpoint", None)
if not path or not methods or endpoint is None:
continue
for method in methods:
if method in ("HEAD", "OPTIONS"):
continue
by_key[f"{method} {path}"].append(endpoint.__module__)
return {
key: sorted(modules) for key, modules in by_key.items() if len(modules) > 1
}
def _load_baseline() -> dict[str, list[str]]:
if not BASELINE_PATH.exists():
return {}
raw = json.loads(BASELINE_PATH.read_text(encoding="utf-8"))
dups = raw.get("duplicates", {})
if not isinstance(dups, dict):
return {}
return {k: sorted(v) for k, v in dups.items()}
def test_no_new_duplicate_route_registrations():
"""Block any (method, path) duplicate not already in the baseline.
This is the primary CI guard: PRs that add a NEW shadowed
``@app.get`` while a router module already serves the same route
fail here with an actionable message.
"""
current = _current_duplicates()
baseline = _load_baseline()
new_or_changed = []
for key, modules in sorted(current.items()):
if key not in baseline:
new_or_changed.append(
f" + {key} (NEW duplicate; registered in: {modules})"
)
continue
if modules != baseline[key]:
new_or_changed.append(
f" ~ {key} "
f"(modules changed: was {baseline[key]}, now {modules})"
)
if new_or_changed:
pytest.fail(
"Issue #239 CI guard: detected duplicate route registrations "
"that are NOT in the tolerated baseline.\n"
"\n"
"If you added a new @app.get/post/... in main.py for a path "
"that a router module already serves, please move the handler "
"into the router and delete the main.py copy — the router "
"version wins on request routing anyway, so the main.py copy "
"is dead code that just creates drift risk.\n"
"\n"
"Offending entries:\n"
+ "\n".join(new_or_changed)
+ "\n\n"
"Baseline lives at "
f"{BASELINE_PATH.relative_to(BASELINE_PATH.parent.parent.parent)}."
)
def test_baseline_only_lists_real_duplicates():
"""Catch baseline drift in the other direction: if an entry in the
baseline is no longer actually a duplicate (because someone deduped
it manually), the baseline is stale and should be shrunk so future
re-introductions of that duplicate get caught.
This test is informational — it does NOT fail the build today (the
audit's main concern is *new* duplicates, not stale baseline
entries). It prints a warning so the next baseline regeneration
can clean things up.
"""
current = _current_duplicates()
baseline = _load_baseline()
stale = sorted(k for k in baseline if k not in current)
if stale:
# Use warnings instead of fail so this is friendly housekeeping,
# not a CI blocker. The other test catches the actual safety
# concern.
import warnings
warnings.warn(
f"duplicate_routes_baseline.json contains {len(stale)} entry/entries "
"no longer present in app.routes — consider regenerating the baseline. "
f"Stale: {stale[:5]}{'...' if len(stale) > 5 else ''}",
stacklevel=2,
)
def test_router_handler_is_the_one_that_serves():
"""Pin the empirical claim from PR #286: for every duplicated
(method, path), the FIRST-registered handler is in a router
module, not in main.py. If this ever flips — e.g. someone moves
include_router calls to the bottom of main.py — duplicate routes
start silently changing which handler runs. This catches that
rearrangement immediately.
"""
import main
first_seen: dict[str, str] = {}
for route in main.app.routes:
path = getattr(route, "path", None)
methods = getattr(route, "methods", None)
endpoint = getattr(route, "endpoint", None)
if not path or not methods or endpoint is None:
continue
for method in methods:
if method in ("HEAD", "OPTIONS"):
continue
key = f"{method} {path}"
if key not in first_seen:
first_seen[key] = endpoint.__module__
main_winning = sorted(
k for k, mod in first_seen.items() if mod == "main"
)
# The duplicates we tolerate are router-first. If main is the first
# registered for any duplicated path, the router copy gets shadowed
# instead, which would invalidate every assumption made in audit
# rounds 5 and 6 about "the router version is canonical."
baseline = _load_baseline()
main_first_in_baseline = [k for k in main_winning if k in baseline]
if main_first_in_baseline:
pytest.fail(
"Issue #239 invariant broken: for at least one duplicated "
"(method, path), main.py is now registered FIRST and is "
"serving requests instead of the router copy. Audit rounds "
"5 and 6 assumed the router handler wins.\n"
"\n"
"Affected entries:\n"
+ "\n".join(f" {k}" for k in main_first_in_baseline)
+ "\n\n"
"Most likely cause: someone moved app.include_router(...) "
"calls in main.py to after the @app.get decorators. Move "
"them back to before the @app routes (currently around "
"line 3316)."
)
@@ -1,91 +0,0 @@
"""Issues #218 / #219 (tg12): outbound Wikipedia + Wikidata calls must
identify ShadowBroker via the Wikimedia-recommended User-Agent /
Api-User-Agent headers.
Before this fix, ``backend/services/region_dossier.py`` called
``fetch_with_curl(url)`` with no explicit headers, falling back to the
generic project default UA. That sent a too-anonymous identifier to
Wikimedia. Per Wikimedia's policy
(https://foundation.wikimedia.org/wiki/Policy:Wikimedia_Foundation_User-Agent_Policy)
the API caller should send a stable, contactable identifier so Wikimedia
operators can rate-limit or reach the project.
This test does NOT make network calls. It patches ``fetch_with_curl``
and asserts the headers that get passed through.
"""
from __future__ import annotations
from unittest.mock import MagicMock, patch
import pytest
def _fake_resp(payload: dict, status: int = 200) -> MagicMock:
r = MagicMock()
r.status_code = status
r.json.return_value = payload
return r
def test_wikidata_call_passes_wikimedia_request_headers():
from services import region_dossier
calls = []
def fake_fetch(url, **kwargs):
calls.append(kwargs.get("headers"))
return _fake_resp({"results": {"bindings": []}})
with patch.object(region_dossier, "fetch_with_curl", side_effect=fake_fetch):
region_dossier._fetch_wikidata_leader("Testlandia")
assert calls, "fetch_with_curl was not called"
headers = calls[0] or {}
assert "User-Agent" in headers
assert "Api-User-Agent" in headers
# Stable identifier should mention the project + a contact path.
assert "Shadowbroker" in headers["Api-User-Agent"] or "ShadowBroker" in headers["Api-User-Agent"]
assert "github.com" in headers["Api-User-Agent"].lower()
def test_wikipedia_summary_call_passes_wikimedia_request_headers():
from services import region_dossier
calls = []
def fake_fetch(url, **kwargs):
calls.append((url, kwargs.get("headers")))
return _fake_resp(
{
"type": "standard",
"description": "test desc",
"extract": "test extract",
"thumbnail": {"source": ""},
}
)
with patch.object(region_dossier, "fetch_with_curl", side_effect=fake_fetch):
region_dossier._fetch_local_wiki_summary("Paris", "France")
# At least one Wikipedia REST call was issued.
wikipedia_calls = [c for c in calls if "wikipedia.org" in c[0]]
assert wikipedia_calls, "no Wikipedia call was issued"
for url, headers in wikipedia_calls:
headers = headers or {}
assert "User-Agent" in headers, f"missing User-Agent on {url}"
assert "Api-User-Agent" in headers, f"missing Api-User-Agent on {url}"
assert "github.com" in headers["Api-User-Agent"].lower()
def test_wikimedia_headers_constant_is_stable():
"""Regression guard: if someone removes the contact path from the
Api-User-Agent we want a loud test failure, not a silent ToS drift.
"""
from services.region_dossier import _WIKIMEDIA_REQUEST_HEADERS
aua = _WIKIMEDIA_REQUEST_HEADERS.get("Api-User-Agent", "")
assert "Shadowbroker" in aua or "ShadowBroker" in aua
assert "github.com" in aua.lower()
# Must include a path Wikimedia operators can use to contact us
# (we use /issues against the public repo).
assert "issues" in aua.lower()
@@ -1,263 +0,0 @@
"""Issues #243, #252, #253 (tg12): settings endpoints must not leak
operational posture to unauthenticated callers.
- **#243**: ``GET /api/settings/wormhole``, ``/api/settings/privacy-profile``,
and ``/api/settings/node`` were leaking transport choice, anonymous-mode
state, the named privacy profile, and node-participant state to any
unauthenticated caller. The fix tightens the redaction allowlists to
expose ONLY a bare "is this feature on?" boolean and gates node mode
behind authenticated reads.
- **#252**: ``GET /api/settings/news-feeds`` returned the operator's full
curated feed inventory (names + URLs) to anyone. Now gated on
local-operator.
- **#253**: ``GET /api/settings/timemachine`` returned whether archival
capture is enabled to anyone. Now gated on local-operator.
Auth model: ``require_local_operator`` allows loopback (Tauri shell),
the Docker bridge frontend container (via the hostname-bound trust from
PR #278), and any caller that presents the configured admin key.
Anonymous LAN or internet callers do NOT pass and either receive 403
(news-feeds, timemachine) or a redacted minimum (wormhole / node).
"""
from __future__ import annotations
from unittest.mock import patch, MagicMock
import pytest
from fastapi.testclient import TestClient
_ADMIN_KEY = "test-admin-key-for-round5-fixture-32+chars"
@pytest.fixture
def client():
"""TestClient with the private-lane transport middleware disabled.
Same shape as the oracle resolve fixture — the mesh privacy
middleware returns 202 for ``/api/settings/*`` under TestClient
because Wormhole is not actually running. Patching out the tier
requirement lets requests reach the route's auth gate.
"""
import main
with patch("main._minimum_transport_tier", return_value=None):
yield TestClient(main.app, raise_server_exceptions=False)
# ---------------------------------------------------------------------------
# #243: Wormhole posture redaction
# ---------------------------------------------------------------------------
class TestWormholeSettingsRedaction:
"""``GET /api/settings/wormhole`` must NOT leak transport choice or
anonymous-mode state to unauthenticated callers."""
def _read_settings_payload(self):
return {
"enabled": True,
"transport": "tor_arti",
"anonymous_mode": True,
"privacy_profile": "high",
"socks_proxy": "socks5h://127.0.0.1:9050",
}
def test_anonymous_caller_sees_only_enabled_bool(self, client):
with (
patch("main.read_wormhole_settings", return_value=self._read_settings_payload()),
patch("routers.wormhole.read_wormhole_settings", return_value=self._read_settings_payload()),
patch("services.wormhole_settings.read_wormhole_settings", return_value=self._read_settings_payload()),
patch("auth._current_admin_key", return_value=_ADMIN_KEY),
):
r = client.get("/api/settings/wormhole")
assert r.status_code == 200
body = r.json()
# Only the bare "is Wormhole on?" boolean is exposed publicly.
assert "enabled" in body
assert body["enabled"] is True
# Posture fields the audit flagged must be absent.
assert "transport" not in body
assert "anonymous_mode" not in body
assert "privacy_profile" not in body
assert "socks_proxy" not in body
def test_authenticated_caller_sees_full_state(self, client):
with (
patch("main.read_wormhole_settings", return_value=self._read_settings_payload()),
patch("routers.wormhole.read_wormhole_settings", return_value=self._read_settings_payload()),
patch("services.wormhole_settings.read_wormhole_settings", return_value=self._read_settings_payload()),
patch("auth._current_admin_key", return_value=_ADMIN_KEY),
):
r = client.get(
"/api/settings/wormhole",
headers={"X-Admin-Key": _ADMIN_KEY},
)
assert r.status_code == 200
body = r.json()
# All fields visible when authenticated.
assert body["enabled"] is True
assert body["transport"] == "tor_arti"
assert body["anonymous_mode"] is True
assert body["privacy_profile"] == "high"
class TestPrivacyProfileRedaction:
"""``GET /api/settings/privacy-profile`` must NOT leak the named
profile to unauthenticated callers (the profile name itself
discloses operator intent)."""
def _payload(self):
return {
"enabled": True,
"transport": "tor_arti",
"anonymous_mode": True,
"privacy_profile": "high",
}
def test_anonymous_caller_sees_only_wormhole_enabled_bool(self, client):
with (
patch("main.read_wormhole_settings", return_value=self._payload()),
patch("routers.wormhole.read_wormhole_settings", return_value=self._payload()),
patch("services.wormhole_settings.read_wormhole_settings", return_value=self._payload()),
patch("auth._current_admin_key", return_value=_ADMIN_KEY),
):
r = client.get("/api/settings/privacy-profile")
assert r.status_code == 200
body = r.json()
assert "wormhole_enabled" in body
assert body["wormhole_enabled"] is True
# The named profile, transport, and anonymous mode must NOT
# leak to anonymous callers.
assert "profile" not in body or body.get("profile") is None
assert "transport" not in body
assert "anonymous_mode" not in body
def test_authenticated_caller_sees_named_profile_and_transport(self, client):
with (
patch("main.read_wormhole_settings", return_value=self._payload()),
patch("routers.wormhole.read_wormhole_settings", return_value=self._payload()),
patch("services.wormhole_settings.read_wormhole_settings", return_value=self._payload()),
patch("auth._current_admin_key", return_value=_ADMIN_KEY),
):
r = client.get(
"/api/settings/privacy-profile",
headers={"X-Admin-Key": _ADMIN_KEY},
)
assert r.status_code == 200
body = r.json()
assert body["profile"] == "high"
assert body["wormhole_enabled"] is True
assert body["transport"] == "tor_arti"
assert body["anonymous_mode"] is True
class TestNodeSettingsRedaction:
"""``GET /api/settings/node`` must NOT disclose node_mode or
node_enabled to anonymous callers."""
def _node_data(self):
return {"some_node_field": "value"}
def test_anonymous_caller_sees_empty_stub(self, client):
with (
patch("services.node_settings.read_node_settings", return_value=self._node_data()),
patch("routers.admin._current_node_mode", return_value="participant"),
patch("routers.admin._participant_node_enabled", return_value=True),
patch("auth._current_admin_key", return_value=_ADMIN_KEY),
):
r = client.get("/api/settings/node")
assert r.status_code == 200
body = r.json()
# No posture fields.
assert "node_mode" not in body
assert "node_enabled" not in body
assert "some_node_field" not in body
def test_authenticated_caller_sees_full_node_state(self, client):
with (
patch("services.node_settings.read_node_settings", return_value=self._node_data()),
patch("routers.admin._current_node_mode", return_value="participant"),
patch("routers.admin._participant_node_enabled", return_value=True),
patch("auth._current_admin_key", return_value=_ADMIN_KEY),
):
r = client.get(
"/api/settings/node",
headers={"X-Admin-Key": _ADMIN_KEY},
)
assert r.status_code == 200
body = r.json()
assert body["node_mode"] == "participant"
assert body["node_enabled"] is True
assert body["some_node_field"] == "value"
# ---------------------------------------------------------------------------
# #252: news-feeds auth gate
# ---------------------------------------------------------------------------
class TestNewsFeedsAuthGate:
def _fake_feeds(self):
return [
{"name": "Custom Internal", "url": "https://internal.example/rss", "weight": 5},
{"name": "Default News", "url": "https://news.example/rss", "weight": 3},
]
def test_anonymous_caller_rejected(self, client):
with (
patch("services.news_feed_config.get_feeds", return_value=self._fake_feeds()) as get_feeds,
patch("auth._current_admin_key", return_value=_ADMIN_KEY),
):
r = client.get("/api/settings/news-feeds")
assert r.status_code == 403
# Critically: the underlying config read must NOT have been performed
# (else the response body could leak the count via response timing).
assert get_feeds.call_count == 0
def test_authenticated_caller_sees_full_feed_inventory(self, client):
with (
patch("services.news_feed_config.get_feeds", return_value=self._fake_feeds()),
patch("auth._current_admin_key", return_value=_ADMIN_KEY),
):
r = client.get(
"/api/settings/news-feeds",
headers={"X-Admin-Key": _ADMIN_KEY},
)
assert r.status_code == 200
body = r.json()
assert len(body) == 2
assert body[0]["name"] == "Custom Internal"
assert body[0]["url"] == "https://internal.example/rss"
# ---------------------------------------------------------------------------
# #253: timemachine auth gate
# ---------------------------------------------------------------------------
class TestTimemachineAuthGate:
def test_anonymous_caller_rejected(self, client):
node_data = {"timemachine_enabled": True}
with (
patch("services.node_settings.read_node_settings", return_value=node_data),
patch("auth._current_admin_key", return_value=_ADMIN_KEY),
):
r = client.get("/api/settings/timemachine")
assert r.status_code == 403
def test_authenticated_caller_sees_enabled_state(self, client):
node_data = {"timemachine_enabled": True}
with (
patch("services.node_settings.read_node_settings", return_value=node_data),
patch("auth._current_admin_key", return_value=_ADMIN_KEY),
):
r = client.get(
"/api/settings/timemachine",
headers={"X-Admin-Key": _ADMIN_KEY},
)
assert r.status_code == 200
body = r.json()
assert body["enabled"] is True
assert "storage_warning" in body
@@ -1,164 +0,0 @@
/**
* Issues #218 / #219 / #220 (tg12 external audit):
*
* Every browser-direct call to Wikipedia or Wikidata must send the
* `Api-User-Agent` header that Wikimedia's UA policy asks for. These
* tests pin that requirement on the shared `lib/wikimediaClient`
* helper that WikiImage, NewsFeed, and useRegionDossier all route
* through, so a future refactor that drops the header gets a loud
* test failure rather than a silent ToS regression.
*/
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import {
WIKIMEDIA_API_USER_AGENT,
fetchWikipediaSummary,
fetchWikidataSparql,
_resetWikimediaClientCacheForTests,
} from '@/lib/wikimediaClient';
const originalFetch = globalThis.fetch;
describe('lib/wikimediaClient', () => {
beforeEach(() => {
_resetWikimediaClientCacheForTests();
});
afterEach(() => {
globalThis.fetch = originalFetch;
vi.restoreAllMocks();
});
it('exposes a stable Api-User-Agent identifier with a contact path', () => {
expect(WIKIMEDIA_API_USER_AGENT).toContain('Shadowbroker');
expect(WIKIMEDIA_API_USER_AGENT.toLowerCase()).toContain('github.com');
expect(WIKIMEDIA_API_USER_AGENT.toLowerCase()).toContain('issues');
});
it('sends Api-User-Agent on Wikipedia summary fetch', async () => {
const calls: Array<{ url: string; init?: RequestInit }> = [];
globalThis.fetch = vi.fn(async (url: any, init?: RequestInit) => {
calls.push({ url: String(url), init });
return new Response(
JSON.stringify({
type: 'standard',
title: 'Boeing 747',
description: 'aircraft',
extract: 'long extract',
thumbnail: { source: 'https://example.org/thumb.jpg' },
}),
{ status: 200 },
);
}) as any;
const summary = await fetchWikipediaSummary('Boeing 747');
expect(summary?.thumbnail).toBe('https://example.org/thumb.jpg');
expect(calls).toHaveLength(1);
const headers = (calls[0].init?.headers || {}) as Record<string, string>;
expect(headers['Api-User-Agent']).toBe(WIKIMEDIA_API_USER_AGENT);
});
it('sends Api-User-Agent on Wikidata SPARQL fetch', async () => {
const calls: Array<{ url: string; init?: RequestInit }> = [];
globalThis.fetch = vi.fn(async (url: any, init?: RequestInit) => {
calls.push({ url: String(url), init });
return new Response(
JSON.stringify({
results: {
bindings: [
{
leaderLabel: { value: 'Test Leader' },
govTypeLabel: { value: 'Test Government' },
},
],
},
}),
{ status: 200 },
);
}) as any;
const bindings = await fetchWikidataSparql('SELECT * WHERE { ?s ?p ?o }');
expect(bindings).toHaveLength(1);
const headers = (calls[0].init?.headers || {}) as Record<string, string>;
expect(headers['Api-User-Agent']).toBe(WIKIMEDIA_API_USER_AGENT);
expect(headers['Accept']).toBe('application/sparql-results+json');
});
it('shares cache across consecutive callers for the same Wikipedia title', async () => {
let fetchCount = 0;
globalThis.fetch = vi.fn(async () => {
fetchCount++;
return new Response(
JSON.stringify({
type: 'standard',
title: 'Eiffel Tower',
description: 'iron lattice tower',
extract: '...',
thumbnail: { source: 'https://example.org/eiffel.jpg' },
}),
{ status: 200 },
);
}) as any;
const a = await fetchWikipediaSummary('Eiffel Tower');
const b = await fetchWikipediaSummary('Eiffel Tower');
expect(fetchCount).toBe(1);
expect(a?.thumbnail).toBe(b?.thumbnail);
});
it('deduplicates concurrent in-flight requests for the same title', async () => {
let fetchCount = 0;
globalThis.fetch = vi.fn(async () => {
fetchCount++;
await new Promise((r) => setTimeout(r, 5));
return new Response(
JSON.stringify({
type: 'standard',
title: 'Mount Fuji',
description: 'stratovolcano',
extract: '...',
thumbnail: { source: 'https://example.org/fuji.jpg' },
}),
{ status: 200 },
);
}) as any;
const [a, b, c] = await Promise.all([
fetchWikipediaSummary('Mount Fuji'),
fetchWikipediaSummary('Mount Fuji'),
fetchWikipediaSummary('Mount Fuji'),
]);
expect(fetchCount).toBe(1);
expect(a?.thumbnail).toBe('https://example.org/fuji.jpg');
expect(b).toEqual(a);
expect(c).toEqual(a);
});
it('returns null on disambiguation pages without throwing', async () => {
globalThis.fetch = vi.fn(async () =>
new Response(JSON.stringify({ type: 'disambiguation' }), { status: 200 }),
) as any;
const summary = await fetchWikipediaSummary('Mercury');
expect(summary).toBeNull();
});
it('returns null on HTTP error without throwing', async () => {
globalThis.fetch = vi.fn(async () => new Response('not found', { status: 404 })) as any;
const summary = await fetchWikipediaSummary('Nonexistent Article 12345');
expect(summary).toBeNull();
});
it('returns null on network error without throwing', async () => {
globalThis.fetch = vi.fn(async () => {
throw new Error('network down');
}) as any;
const summary = await fetchWikipediaSummary('Anything');
expect(summary).toBeNull();
});
it('returns null on empty input', async () => {
globalThis.fetch = vi.fn(async () => new Response('{}', { status: 200 })) as any;
expect(await fetchWikipediaSummary('')).toBeNull();
expect(await fetchWikipediaSummary(' ')).toBeNull();
expect(globalThis.fetch).not.toHaveBeenCalled();
});
});
+20 -24
View File
@@ -5,7 +5,6 @@ import { motion, AnimatePresence } from 'framer-motion';
import { AlertTriangle, Clock, Minus, Plus, ExternalLink, Brain, Loader2 } from 'lucide-react';
import React, { useEffect, useRef, useCallback } from 'react';
import WikiImage from '@/components/WikiImage';
import { fetchWikipediaSummary } from '@/lib/wikimediaClient';
import type { SelectedEntity, RegionDossier, FimiData } from "@/types/dashboard";
import { useDataKeys } from '@/hooks/useDataStore';
import { API_BASE } from '@/lib/api';
@@ -204,37 +203,34 @@ function resolveAircraftWikiTitle(model: string | undefined): string | null {
return AIRCRAFT_WIKI[model] || resolveAcTypeWiki(model);
}
// Issue #220 (tg12): the previous implementation kept its own
// module-local Wikipedia thumbnail cache and issued anonymous fetches
// without `Api-User-Agent`. We now delegate to lib/wikimediaClient,
// which sends the policy-compliant header and shares one cache with
// WikiImage and useRegionDossier.
// Module-level cache for Wikipedia thumbnails (persists across re-renders)
const _wikiThumbCache: Record<string, { url: string | null; loading: boolean }> = {};
function useAircraftImage(model: string | undefined): { imgUrl: string | null; wikiUrl: string | null; loading: boolean } {
const [imgUrl, setImgUrl] = useState<string | null>(null);
const [loading, setLoading] = useState(false);
const [, forceUpdate] = useState(0);
const wikiTitle = resolveAircraftWikiTitle(model) || undefined;
const wikiUrl = wikiTitle ? `https://en.wikipedia.org/wiki/${wikiTitle.replace(/ /g, '_')}` : null;
useEffect(() => {
let cancelled = false;
if (!wikiTitle) {
setImgUrl(null);
setLoading(false);
return;
}
setLoading(true);
fetchWikipediaSummary(wikiTitle).then((summary) => {
if (cancelled) return;
setImgUrl(summary?.thumbnail || null);
setLoading(false);
});
return () => {
cancelled = true;
};
if (!wikiTitle) return;
const key = wikiTitle;
if (_wikiThumbCache[key]) return; // Already fetched or in-flight
_wikiThumbCache[key] = { url: null, loading: true };
fetch(`https://en.wikipedia.org/api/rest_v1/page/summary/${encodeURIComponent(wikiTitle)}`)
.then(r => r.json())
.then(d => {
_wikiThumbCache[key] = { url: d.thumbnail?.source || null, loading: false };
forceUpdate(n => n + 1);
})
.catch(() => {
_wikiThumbCache[key] = { url: null, loading: false };
forceUpdate(n => n + 1);
});
}, [wikiTitle]);
if (!wikiTitle) return { imgUrl: null, wikiUrl: null, loading: false };
return { imgUrl, wikiUrl, loading };
const cached = _wikiThumbCache[wikiTitle];
return { imgUrl: cached?.url || null, wikiUrl, loading: cached?.loading || false };
}
+23 -25
View File
@@ -1,17 +1,13 @@
'use client';
import React, { useState, useEffect } from 'react';
import ExternalImage from '@/components/ExternalImage';
import { fetchWikipediaSummary } from '@/lib/wikimediaClient';
// Module-level cache: Wikipedia article title → thumbnail URL
const _cache: Record<string, { url: string | null; done: boolean }> = {};
/**
* WikiImage — displays a Wikipedia thumbnail for a given article URL.
*
* Issue #220 (tg12): this component previously had its own
* module-local Wikipedia fetch + cache. It now delegates to
* `lib/wikimediaClient`, which sends the policy-compliant
* `Api-User-Agent` header and shares one cache across every UI
* component that asks Wikipedia for an article summary (WikiImage,
* NewsFeed, useRegionDossier).
* Uses the Wikipedia REST API with a module-level cache (only fetches once per article).
*
* Props:
* wikiUrl: Full Wikipedia URL, e.g. "https://en.wikipedia.org/wiki/Boeing_787_Dreamliner"
@@ -30,30 +26,32 @@ export default function WikiImage({
maxH?: string;
accent?: string;
}) {
const [imgUrl, setImgUrl] = useState<string | null>(null);
const [loading, setLoading] = useState(true);
const [, forceUpdate] = useState(0);
// Extract article title from URL
const title = wikiUrl.replace(/^https?:\/\/[^/]+\/wiki\//, '');
useEffect(() => {
let cancelled = false;
if (!title) {
setImgUrl(null);
setLoading(false);
return;
}
setLoading(true);
fetchWikipediaSummary(title).then((summary) => {
if (cancelled) return;
setImgUrl(summary?.thumbnail || null);
setLoading(false);
});
return () => {
cancelled = true;
};
if (!title || _cache[title]?.done) return;
if (_cache[title]) return; // In-flight
_cache[title] = { url: null, done: false };
fetch(`https://en.wikipedia.org/api/rest_v1/page/summary/${encodeURIComponent(title)}`)
.then((r) => r.json())
.then((d) => {
_cache[title] = { url: d.thumbnail?.source || d.originalimage?.source || null, done: true };
forceUpdate((n) => n + 1);
})
.catch(() => {
_cache[title] = { url: null, done: true };
forceUpdate((n) => n + 1);
});
}, [title]);
const cached = _cache[title];
const imgUrl = cached?.url;
const loading = cached && !cached.done;
return (
<div className="pb-2">
{loading && (
+22 -23
View File
@@ -1,6 +1,5 @@
import { useCallback, useState, useEffect } from 'react';
import type { RegionDossier, SelectedEntity } from '@/types/dashboard';
import { fetchWikipediaSummary, fetchWikidataSparql } from '@/lib/wikimediaClient';
// ─── CACHE ─────────────────────────────────────────────────────────────────
// Simple in-memory cache keyed by rounded lat/lng (0.1° ≈ 11km grid), 24h TTL.
@@ -115,11 +114,7 @@ async function fetchCountryData(countryCode: string) {
return Array.isArray(data) ? data[0] || {} : data || {};
}
/** Fetch head of state + government type from Wikidata SPARQL.
*
* Issue #218 (tg12): routes through lib/wikimediaClient so the
* Api-User-Agent header is set per Wikimedia's UA policy.
*/
/** Fetch head of state + government type from Wikidata SPARQL (direct browser call). */
async function fetchLeader(countryName: string) {
if (!countryName) return { leader: 'Unknown', government_type: 'Unknown' };
const safeName = countryName.replace(/"/g, '\\"').replace(/'/g, "\\'");
@@ -132,11 +127,13 @@ async function fetchLeader(countryName: string) {
SERVICE wikibase:label { bd:serviceParam wikibase:language "en". }
} LIMIT 1
`;
const results = await fetchWikidataSparql<{
leaderLabel?: { value: string };
govTypeLabel?: { value: string };
}>(sparql);
if (results && results.length > 0) {
const url = `https://query.wikidata.org/sparql?query=${encodeURIComponent(sparql)}&format=json`;
const res = await fetch(url, {
headers: { Accept: 'application/sparql-results+json' },
});
if (!res.ok) throw new Error(`Wikidata HTTP ${res.status}`);
const results = (await res.json()).results?.bindings || [];
if (results.length > 0) {
return {
leader: results[0].leaderLabel?.value || 'Unknown',
government_type: results[0].govTypeLabel?.value || 'Unknown',
@@ -145,25 +142,27 @@ async function fetchLeader(countryName: string) {
return { leader: 'Unknown', government_type: 'Unknown' };
}
/** Fetch Wikipedia summary for a place.
*
* Issue #219 (tg12): routes through lib/wikimediaClient so the
* Api-User-Agent header is set per Wikimedia's UA policy, AND the
* shared cache means consecutive useRegionDossier + WikiImage +
* NewsFeed lookups for the same article all hit the same slot.
*/
/** Fetch Wikipedia summary for a place (direct browser call). */
async function fetchLocalWikiSummary(placeName: string, countryName = '') {
if (!placeName) return {};
const candidates = [placeName];
if (countryName) candidates.push(`${placeName}, ${countryName}`);
for (const name of candidates) {
const summary = await fetchWikipediaSummary(name);
if (summary) {
try {
const slug = encodeURIComponent(name.replace(/ /g, '_'));
const url = `https://en.wikipedia.org/api/rest_v1/page/summary/${slug}`;
const res = await fetch(url);
if (!res.ok) continue;
const data = await res.json();
if (data.type === 'disambiguation') continue;
return {
description: summary.description,
extract: summary.extract,
thumbnail: summary.thumbnail,
description: data.description || '',
extract: data.extract || '',
thumbnail: data.thumbnail?.source || '',
};
} catch {
continue;
}
}
return {};
-157
View File
@@ -1,157 +0,0 @@
/**
* wikimediaClient — single fetch surface for Wikipedia / Wikidata.
*
* Issues #218, #219, #220 (tg12 external audit):
*
* Wikimedia's User-Agent policy asks API clients to identify themselves
* via `Api-User-Agent` when calling from browser JavaScript (because the
* browser does not let JS set `User-Agent` directly). Before this
* module existed, three independent components issued anonymous browser
* fetches against Wikipedia / Wikidata:
*
* - useRegionDossier (Wikidata SPARQL + Wikipedia REST summary)
* - WikiImage (Wikipedia REST summary)
* - NewsFeed (Wikipedia REST summary)
*
* Each component shipped its own copy-pasted fetch + module-local cache.
* Provider-policy compliance was missing in all three places.
*
* This module centralizes:
*
* 1. The `Api-User-Agent` header on every request.
* 2. A single LRU cache for Wikipedia summary lookups (keyed by article
* title). Multiple components asking for the same article share
* one in-flight request and one cache slot.
* 3. One predictable kill switch — if Wikimedia ever asks us to back
* off, we change `WIKIMEDIA_API_USER_AGENT` here and the whole
* frontend updates.
*
* This does NOT change end-user UX:
*
* - WikiImage still shows the same thumbnails.
* - NewsFeed still shows aircraft thumbnails.
* - useRegionDossier still returns the same place summary + leader.
*
* What changes:
*
* - Wikimedia can identify our traffic from any other anonymous
* browser visitor pool.
* - Provider-policy fixes happen here once, not in three places.
*/
// Stable identifier per Wikimedia UA policy. Includes a contact path so
// Wikimedia's operators can reach the project if they need to rate-limit
// or coordinate. Bump the version when the contact path changes.
export const WIKIMEDIA_API_USER_AGENT =
'Shadowbroker/1.0 (+https://github.com/BigBodyCobain/Shadowbroker; ' +
'report issues at /issues)';
// Module-level cache shared by WikiImage, NewsFeed, and useRegionDossier.
// Keyed by Wikipedia article title (NOT slug — we keep the human-readable
// form so debugging the cache is easier). Values track in-flight state
// so concurrent callers for the same title share one network request.
export interface WikipediaSummary {
title: string;
description: string;
extract: string;
thumbnail: string;
type: string; // 'standard' | 'disambiguation' | etc.
}
interface CacheEntry {
summary: WikipediaSummary | null;
inflight: Promise<WikipediaSummary | null> | null;
loaded: boolean;
}
const _summaryCache: Map<string, CacheEntry> = new Map();
const SUMMARY_CACHE_MAX = 512;
function evictIfOverCap() {
if (_summaryCache.size <= SUMMARY_CACHE_MAX) return;
const oldest = _summaryCache.keys().next().value;
if (oldest) _summaryCache.delete(oldest);
}
/** Fetch a Wikipedia article summary (titles, NOT URLs).
*
* Empty / invalid input resolves to `null`. Network errors and disambig
* pages also resolve to `null` so callers can render a fallback without
* a try/catch. Per the audit's "fail forward, not loud" rule.
*/
export async function fetchWikipediaSummary(
title: string,
): Promise<WikipediaSummary | null> {
const trimmed = (title || '').trim();
if (!trimmed) return null;
const cached = _summaryCache.get(trimmed);
if (cached?.loaded) return cached.summary;
if (cached?.inflight) return cached.inflight;
const slug = encodeURIComponent(trimmed.replace(/ /g, '_'));
const url = `https://en.wikipedia.org/api/rest_v1/page/summary/${slug}`;
const promise = fetch(url, {
headers: { 'Api-User-Agent': WIKIMEDIA_API_USER_AGENT },
})
.then(async (r) => {
if (!r.ok) return null;
const d = await r.json();
if (d?.type === 'disambiguation') return null;
const summary: WikipediaSummary = {
title: trimmed,
description: d?.description || '',
extract: d?.extract || '',
thumbnail: d?.thumbnail?.source || d?.originalimage?.source || '',
type: d?.type || 'standard',
};
return summary;
})
.catch(() => null)
.then((summary) => {
_summaryCache.set(trimmed, { summary, inflight: null, loaded: true });
evictIfOverCap();
return summary;
});
_summaryCache.set(trimmed, { summary: null, inflight: promise, loaded: false });
evictIfOverCap();
return promise;
}
/** Fetch a Wikidata SPARQL query result.
*
* Returns the parsed JSON `results.bindings` array on success; `null`
* (not throwing) on any failure so callers can render fallbacks
* silently. Kept as a thin wrapper so the audit-required UA header is
* applied in exactly one place.
*/
export async function fetchWikidataSparql<T = Record<string, { value: string }>>(
sparql: string,
): Promise<T[] | null> {
const trimmed = (sparql || '').trim();
if (!trimmed) return null;
const url = `https://query.wikidata.org/sparql?query=${encodeURIComponent(
trimmed,
)}&format=json`;
try {
const res = await fetch(url, {
headers: {
'Api-User-Agent': WIKIMEDIA_API_USER_AGENT,
Accept: 'application/sparql-results+json',
},
});
if (!res.ok) return null;
const json = await res.json();
const bindings = json?.results?.bindings;
return Array.isArray(bindings) ? (bindings as T[]) : null;
} catch {
return null;
}
}
/** Internal: clear the shared cache. Exposed for tests only. */
export function _resetWikimediaClientCacheForTests() {
_summaryCache.clear();
}